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
2023-01-24 05:00:25.080764: step: 4/527, loss: 0.04923645034432411
2023-01-24 05:00:26.120499: step: 8/527, loss: 0.043383460491895676
2023-01-24 05:00:27.167078: step: 12/527, loss: 0.06345069408416748
2023-01-24 05:00:28.217042: step: 16/527, loss: 0.037945427000522614
2023-01-24 05:00:29.244093: step: 20/527, loss: 0.026889178901910782
2023-01-24 05:00:30.326444: step: 24/527, loss: 0.014282737858593464
2023-01-24 05:00:31.360838: step: 28/527, loss: 0.07314743101596832
2023-01-24 05:00:32.405635: step: 32/527, loss: 0.013953915797173977
2023-01-24 05:00:33.457813: step: 36/527, loss: 0.02508673444390297
2023-01-24 05:00:34.492612: step: 40/527, loss: 0.014697683043777943
2023-01-24 05:00:35.537680: step: 44/527, loss: 0.01800478808581829
2023-01-24 05:00:36.583534: step: 48/527, loss: 0.011815366335213184
2023-01-24 05:00:37.642613: step: 52/527, loss: 0.05149368941783905
2023-01-24 05:00:38.683806: step: 56/527, loss: 0.027764907106757164
2023-01-24 05:00:39.746036: step: 60/527, loss: 0.02928166277706623
2023-01-24 05:00:40.802698: step: 64/527, loss: 0.06118535250425339
2023-01-24 05:00:41.846933: step: 68/527, loss: 0.0191913191229105
2023-01-24 05:00:42.886147: step: 72/527, loss: 0.014914190396666527
2023-01-24 05:00:43.932380: step: 76/527, loss: 0.020977135747671127
2023-01-24 05:00:44.997698: step: 80/527, loss: 0.06389444321393967
2023-01-24 05:00:46.053828: step: 84/527, loss: 0.03556324541568756
2023-01-24 05:00:47.108226: step: 88/527, loss: 0.03598419576883316
2023-01-24 05:00:48.160069: step: 92/527, loss: 0.017860865220427513
2023-01-24 05:00:49.222952: step: 96/527, loss: 0.017174694687128067
2023-01-24 05:00:50.268415: step: 100/527, loss: 0.03404431417584419
2023-01-24 05:00:51.309894: step: 104/527, loss: 0.05877925455570221
2023-01-24 05:00:52.384237: step: 108/527, loss: 0.056674402207136154
2023-01-24 05:00:53.428003: step: 112/527, loss: 0.022927330806851387
2023-01-24 05:00:54.488028: step: 116/527, loss: 0.014627698808908463
2023-01-24 05:00:55.540597: step: 120/527, loss: 0.03617612272500992
2023-01-24 05:00:56.591810: step: 124/527, loss: 0.021311931312084198
2023-01-24 05:00:57.656238: step: 128/527, loss: 0.02233605645596981
2023-01-24 05:00:58.709469: step: 132/527, loss: 0.052028801292181015
2023-01-24 05:00:59.758025: step: 136/527, loss: 0.019956503063440323
2023-01-24 05:01:00.828522: step: 140/527, loss: 0.017463866621255875
2023-01-24 05:01:01.881968: step: 144/527, loss: 0.01615358144044876
2023-01-24 05:01:02.920568: step: 148/527, loss: 0.02121655084192753
2023-01-24 05:01:03.968950: step: 152/527, loss: 0.018111443147063255
2023-01-24 05:01:05.010464: step: 156/527, loss: 0.05822242796421051
2023-01-24 05:01:06.051430: step: 160/527, loss: 0.0
2023-01-24 05:01:07.103284: step: 164/527, loss: 0.014703494496643543
2023-01-24 05:01:08.159071: step: 168/527, loss: 0.012373027391731739
2023-01-24 05:01:09.200115: step: 172/527, loss: 0.021156037226319313
2023-01-24 05:01:10.258024: step: 176/527, loss: 0.017676973715424538
2023-01-24 05:01:11.307293: step: 180/527, loss: 0.01889359951019287
2023-01-24 05:01:12.355845: step: 184/527, loss: 0.016506966203451157
2023-01-24 05:01:13.420231: step: 188/527, loss: 0.020693611353635788
2023-01-24 05:01:14.472643: step: 192/527, loss: 0.03187645971775055
2023-01-24 05:01:15.517087: step: 196/527, loss: 0.009794244542717934
2023-01-24 05:01:16.571417: step: 200/527, loss: 0.01717703975737095
2023-01-24 05:01:17.620607: step: 204/527, loss: 0.018400736153125763
2023-01-24 05:01:18.670832: step: 208/527, loss: 0.010766998864710331
2023-01-24 05:01:19.728484: step: 212/527, loss: 0.029402419924736023
2023-01-24 05:01:20.770348: step: 216/527, loss: 0.016083508729934692
2023-01-24 05:01:21.814652: step: 220/527, loss: 0.048895031213760376
2023-01-24 05:01:22.865103: step: 224/527, loss: 0.01457796711474657
2023-01-24 05:01:23.925226: step: 228/527, loss: 0.014130916446447372
2023-01-24 05:01:24.971987: step: 232/527, loss: 0.03943173959851265
2023-01-24 05:01:26.036131: step: 236/527, loss: 0.024307668209075928
2023-01-24 05:01:27.091677: step: 240/527, loss: 0.04134993255138397
2023-01-24 05:01:28.146099: step: 244/527, loss: 0.0866246372461319
2023-01-24 05:01:29.206895: step: 248/527, loss: 0.04274255782365799
2023-01-24 05:01:30.258043: step: 252/527, loss: 0.02999594435095787
2023-01-24 05:01:31.326752: step: 256/527, loss: 0.014202937483787537
2023-01-24 05:01:32.387964: step: 260/527, loss: 0.019418755546212196
2023-01-24 05:01:33.433408: step: 264/527, loss: 0.01926596648991108
2023-01-24 05:01:34.486319: step: 268/527, loss: 0.0678904801607132
2023-01-24 05:01:35.534085: step: 272/527, loss: 0.0191855039447546
2023-01-24 05:01:36.569092: step: 276/527, loss: 0.00817350298166275
2023-01-24 05:01:37.615679: step: 280/527, loss: 0.025740692391991615
2023-01-24 05:01:38.674462: step: 284/527, loss: 0.02880026213824749
2023-01-24 05:01:39.740893: step: 288/527, loss: 0.009712154977023602
2023-01-24 05:01:40.817074: step: 292/527, loss: 0.05614226311445236
2023-01-24 05:01:41.876455: step: 296/527, loss: 0.007925443351268768
2023-01-24 05:01:42.930161: step: 300/527, loss: 0.011007772758603096
2023-01-24 05:01:43.977267: step: 304/527, loss: 0.02407767064869404
2023-01-24 05:01:45.032675: step: 308/527, loss: 0.04419030249118805
2023-01-24 05:01:46.088863: step: 312/527, loss: 0.03359941393136978
2023-01-24 05:01:47.150011: step: 316/527, loss: 0.07747422903776169
2023-01-24 05:01:48.202896: step: 320/527, loss: 0.01955069601535797
2023-01-24 05:01:49.261918: step: 324/527, loss: 0.051893677562475204
2023-01-24 05:01:50.307360: step: 328/527, loss: 0.013612684793770313
2023-01-24 05:01:51.366764: step: 332/527, loss: 0.012552589178085327
2023-01-24 05:01:52.413371: step: 336/527, loss: 0.03841537982225418
2023-01-24 05:01:53.477082: step: 340/527, loss: 0.010561777278780937
2023-01-24 05:01:54.524072: step: 344/527, loss: 0.04348571598529816
2023-01-24 05:01:55.583065: step: 348/527, loss: 0.04455193132162094
2023-01-24 05:01:56.639955: step: 352/527, loss: 0.010561950504779816
2023-01-24 05:01:57.697054: step: 356/527, loss: 0.014725720509886742
2023-01-24 05:01:58.739928: step: 360/527, loss: 0.01387280784547329
2023-01-24 05:01:59.790953: step: 364/527, loss: 0.0053038764744997025
2023-01-24 05:02:00.846841: step: 368/527, loss: 0.05532926321029663
2023-01-24 05:02:01.898756: step: 372/527, loss: 0.0818491280078888
2023-01-24 05:02:02.959557: step: 376/527, loss: 0.018701819702982903
2023-01-24 05:02:03.995700: step: 380/527, loss: 0.05909799784421921
2023-01-24 05:02:05.035707: step: 384/527, loss: 0.010057435370981693
2023-01-24 05:02:06.102526: step: 388/527, loss: 0.08583433926105499
2023-01-24 05:02:07.151902: step: 392/527, loss: 0.01276600081473589
2023-01-24 05:02:08.199783: step: 396/527, loss: 0.02201969176530838
2023-01-24 05:02:09.244541: step: 400/527, loss: 0.009124068543314934
2023-01-24 05:02:10.284820: step: 404/527, loss: 0.008228073827922344
2023-01-24 05:02:11.344204: step: 408/527, loss: 0.013764871284365654
2023-01-24 05:02:12.388176: step: 412/527, loss: 0.009872580878436565
2023-01-24 05:02:13.444063: step: 416/527, loss: 0.006959422491490841
2023-01-24 05:02:14.497533: step: 420/527, loss: 0.008295686915516853
2023-01-24 05:02:15.552852: step: 424/527, loss: 0.04326401278376579
2023-01-24 05:02:16.597017: step: 428/527, loss: 0.05508603900671005
2023-01-24 05:02:17.674742: step: 432/527, loss: 0.04993807524442673
2023-01-24 05:02:18.731321: step: 436/527, loss: 0.01477036438882351
2023-01-24 05:02:19.775593: step: 440/527, loss: 0.019256919622421265
2023-01-24 05:02:20.817450: step: 444/527, loss: 0.02263311669230461
2023-01-24 05:02:21.853142: step: 448/527, loss: 0.024339186027646065
2023-01-24 05:02:22.905889: step: 452/527, loss: 0.01530923880636692
2023-01-24 05:02:23.946694: step: 456/527, loss: 0.0
2023-01-24 05:02:24.997564: step: 460/527, loss: 0.01358681172132492
2023-01-24 05:02:26.045787: step: 464/527, loss: 0.05225981026887894
2023-01-24 05:02:27.104660: step: 468/527, loss: 0.012450088746845722
2023-01-24 05:02:28.143054: step: 472/527, loss: 0.00823119468986988
2023-01-24 05:02:29.185629: step: 476/527, loss: 0.04928778484463692
2023-01-24 05:02:30.245922: step: 480/527, loss: 0.014564726501703262
2023-01-24 05:02:31.293542: step: 484/527, loss: 0.011767190881073475
2023-01-24 05:02:32.336798: step: 488/527, loss: 0.052691712975502014
2023-01-24 05:02:33.376703: step: 492/527, loss: 0.014807982370257378
2023-01-24 05:02:34.412492: step: 496/527, loss: 0.0032415720634162426
2023-01-24 05:02:35.458976: step: 500/527, loss: 0.012801028788089752
2023-01-24 05:02:36.516539: step: 504/527, loss: 0.010832608677446842
2023-01-24 05:02:37.564326: step: 508/527, loss: 0.02535327523946762
2023-01-24 05:02:38.611264: step: 512/527, loss: 0.030488912016153336
2023-01-24 05:02:39.675931: step: 516/527, loss: 0.019557097926735878
2023-01-24 05:02:40.754253: step: 520/527, loss: 0.042833928018808365
2023-01-24 05:02:41.808536: step: 524/527, loss: 0.0021354856435209513
2023-01-24 05:02:42.857015: step: 528/527, loss: 0.012811513617634773
2023-01-24 05:02:43.898560: step: 532/527, loss: 0.009690161794424057
2023-01-24 05:02:44.942226: step: 536/527, loss: 0.061977434903383255
2023-01-24 05:02:45.983421: step: 540/527, loss: 0.01449664682149887
2023-01-24 05:02:47.042915: step: 544/527, loss: 0.019814014434814453
2023-01-24 05:02:48.122889: step: 548/527, loss: 0.05334167182445526
2023-01-24 05:02:49.172620: step: 552/527, loss: 0.015172426588833332
2023-01-24 05:02:50.240908: step: 556/527, loss: 0.01659049466252327
2023-01-24 05:02:51.292163: step: 560/527, loss: 0.010038601234555244
2023-01-24 05:02:52.345683: step: 564/527, loss: 0.012357079423964024
2023-01-24 05:02:53.397210: step: 568/527, loss: 0.010617715306580067
2023-01-24 05:02:54.459517: step: 572/527, loss: 0.06289331614971161
2023-01-24 05:02:55.511909: step: 576/527, loss: 0.007434506434947252
2023-01-24 05:02:56.564020: step: 580/527, loss: 0.007518386468291283
2023-01-24 05:02:57.626901: step: 584/527, loss: 0.013077018782496452
2023-01-24 05:02:58.670419: step: 588/527, loss: 0.07850120216608047
2023-01-24 05:02:59.718230: step: 592/527, loss: 0.03388079255819321
2023-01-24 05:03:00.776127: step: 596/527, loss: 0.035493068397045135
2023-01-24 05:03:01.841028: step: 600/527, loss: 0.03494912013411522
2023-01-24 05:03:02.896802: step: 604/527, loss: 0.019684508442878723
2023-01-24 05:03:03.952226: step: 608/527, loss: 0.009311813861131668
2023-01-24 05:03:05.017614: step: 612/527, loss: 0.057334091514348984
2023-01-24 05:03:06.064285: step: 616/527, loss: 0.006807522848248482
2023-01-24 05:03:07.116365: step: 620/527, loss: 0.013769448734819889
2023-01-24 05:03:08.165036: step: 624/527, loss: 0.014124431647360325
2023-01-24 05:03:09.221172: step: 628/527, loss: 0.007340814918279648
2023-01-24 05:03:10.264469: step: 632/527, loss: 0.013471441343426704
2023-01-24 05:03:11.339455: step: 636/527, loss: 0.04327579587697983
2023-01-24 05:03:12.405388: step: 640/527, loss: 0.010253100655972958
2023-01-24 05:03:13.471943: step: 644/527, loss: 0.014752187766134739
2023-01-24 05:03:14.528632: step: 648/527, loss: 0.06564674526453018
2023-01-24 05:03:15.581640: step: 652/527, loss: 0.011777317151427269
2023-01-24 05:03:16.646194: step: 656/527, loss: 0.008777322247624397
2023-01-24 05:03:17.704990: step: 660/527, loss: 0.023550763726234436
2023-01-24 05:03:18.753306: step: 664/527, loss: 0.029071390628814697
2023-01-24 05:03:19.812460: step: 668/527, loss: 0.011349665001034737
2023-01-24 05:03:20.878135: step: 672/527, loss: 0.022541021928191185
2023-01-24 05:03:21.935564: step: 676/527, loss: 0.03227221593260765
2023-01-24 05:03:22.980670: step: 680/527, loss: 0.045231226831674576
2023-01-24 05:03:24.044285: step: 684/527, loss: 0.02103865146636963
2023-01-24 05:03:25.110521: step: 688/527, loss: 0.018973032012581825
2023-01-24 05:03:26.153969: step: 692/527, loss: 0.026441611349582672
2023-01-24 05:03:27.203356: step: 696/527, loss: 0.05431555211544037
2023-01-24 05:03:28.254128: step: 700/527, loss: 0.0534958653151989
2023-01-24 05:03:29.297123: step: 704/527, loss: 0.003933245316147804
2023-01-24 05:03:30.345910: step: 708/527, loss: 0.011422310955822468
2023-01-24 05:03:31.399414: step: 712/527, loss: 0.032320261001586914
2023-01-24 05:03:32.454711: step: 716/527, loss: 0.008242209441959858
2023-01-24 05:03:33.496096: step: 720/527, loss: 0.011768379248678684
2023-01-24 05:03:34.569825: step: 724/527, loss: 0.0736803412437439
2023-01-24 05:03:35.613841: step: 728/527, loss: 0.028010506182909012
2023-01-24 05:03:36.670271: step: 732/527, loss: 0.041286222636699677
2023-01-24 05:03:37.729872: step: 736/527, loss: 0.026666691526770592
2023-01-24 05:03:38.775028: step: 740/527, loss: 0.01516043022274971
2023-01-24 05:03:39.834888: step: 744/527, loss: 0.07718952745199203
2023-01-24 05:03:40.887337: step: 748/527, loss: 0.010381504893302917
2023-01-24 05:03:41.939581: step: 752/527, loss: 0.007148078642785549
2023-01-24 05:03:43.005663: step: 756/527, loss: 0.010911373421549797
2023-01-24 05:03:44.060894: step: 760/527, loss: 0.022200558334589005
2023-01-24 05:03:45.113624: step: 764/527, loss: 0.014294442720711231
2023-01-24 05:03:46.140853: step: 768/527, loss: 0.030063582584261894
2023-01-24 05:03:47.182952: step: 772/527, loss: 0.00841920729726553
2023-01-24 05:03:48.223119: step: 776/527, loss: 0.03538789227604866
2023-01-24 05:03:49.282456: step: 780/527, loss: 0.021538633853197098
2023-01-24 05:03:50.343702: step: 784/527, loss: 0.010347490198910236
2023-01-24 05:03:51.385826: step: 788/527, loss: 0.01486788410693407
2023-01-24 05:03:52.437303: step: 792/527, loss: 0.040787018835544586
2023-01-24 05:03:53.490187: step: 796/527, loss: 0.00893323589116335
2023-01-24 05:03:54.545061: step: 800/527, loss: 0.013890317641198635
2023-01-24 05:03:55.577903: step: 804/527, loss: 0.010352769866585732
2023-01-24 05:03:56.623201: step: 808/527, loss: 0.040759921073913574
2023-01-24 05:03:57.671257: step: 812/527, loss: 0.018781933933496475
2023-01-24 05:03:58.713030: step: 816/527, loss: 0.014692301861941814
2023-01-24 05:03:59.764776: step: 820/527, loss: 0.00933702290058136
2023-01-24 05:04:00.826340: step: 824/527, loss: 0.023195777088403702
2023-01-24 05:04:01.881414: step: 828/527, loss: 0.006671345327049494
2023-01-24 05:04:02.915165: step: 832/527, loss: 0.017655614763498306
2023-01-24 05:04:03.987345: step: 836/527, loss: 0.03672616556286812
2023-01-24 05:04:05.034630: step: 840/527, loss: 0.008209939114749432
2023-01-24 05:04:06.097822: step: 844/527, loss: 0.009100494906306267
2023-01-24 05:04:07.141837: step: 848/527, loss: 0.033512990921735764
2023-01-24 05:04:08.189150: step: 852/527, loss: 0.007788464426994324
2023-01-24 05:04:09.234292: step: 856/527, loss: 0.016441211104393005
2023-01-24 05:04:10.290488: step: 860/527, loss: 0.0071509359404444695
2023-01-24 05:04:11.330756: step: 864/527, loss: 0.023158783093094826
2023-01-24 05:04:12.378026: step: 868/527, loss: 0.007005530409514904
2023-01-24 05:04:13.445261: step: 872/527, loss: 0.018883144482970238
2023-01-24 05:04:14.508914: step: 876/527, loss: 0.013088423758745193
2023-01-24 05:04:15.569634: step: 880/527, loss: 0.013050662353634834
2023-01-24 05:04:16.623515: step: 884/527, loss: 0.011257769539952278
2023-01-24 05:04:17.684062: step: 888/527, loss: 0.011637862771749496
2023-01-24 05:04:18.735997: step: 892/527, loss: 0.010010679252445698
2023-01-24 05:04:19.798637: step: 896/527, loss: 0.04781891033053398
2023-01-24 05:04:20.841677: step: 900/527, loss: 0.05245564505457878
2023-01-24 05:04:21.884961: step: 904/527, loss: 0.03748883679509163
2023-01-24 05:04:22.935175: step: 908/527, loss: 0.04363131523132324
2023-01-24 05:04:23.997128: step: 912/527, loss: 0.00877950806170702
2023-01-24 05:04:25.064558: step: 916/527, loss: 0.0525088869035244
2023-01-24 05:04:26.113473: step: 920/527, loss: 0.006738531868904829
2023-01-24 05:04:27.170196: step: 924/527, loss: 0.010972203686833382
2023-01-24 05:04:28.228396: step: 928/527, loss: 0.013852679170668125
2023-01-24 05:04:29.278104: step: 932/527, loss: 0.025796569883823395
2023-01-24 05:04:30.334483: step: 936/527, loss: 0.013459406793117523
2023-01-24 05:04:31.379288: step: 940/527, loss: 0.012326393276453018
2023-01-24 05:04:32.419035: step: 944/527, loss: 0.014031559228897095
2023-01-24 05:04:33.469651: step: 948/527, loss: 0.02120394818484783
2023-01-24 05:04:34.514203: step: 952/527, loss: 0.0197740625590086
2023-01-24 05:04:35.565958: step: 956/527, loss: 0.03490378335118294
2023-01-24 05:04:36.628595: step: 960/527, loss: 0.0196097269654274
2023-01-24 05:04:37.692405: step: 964/527, loss: 0.009637261740863323
2023-01-24 05:04:38.747142: step: 968/527, loss: 0.0049220542423427105
2023-01-24 05:04:39.793984: step: 972/527, loss: 0.013535046949982643
2023-01-24 05:04:40.827142: step: 976/527, loss: 0.010385559871792793
2023-01-24 05:04:41.874415: step: 980/527, loss: 0.013344008475542068
2023-01-24 05:04:42.922262: step: 984/527, loss: 0.0060921115800738335
2023-01-24 05:04:43.973359: step: 988/527, loss: 0.013868375681340694
2023-01-24 05:04:45.040051: step: 992/527, loss: 0.013543576002120972
2023-01-24 05:04:46.085423: step: 996/527, loss: 0.016153769567608833
2023-01-24 05:04:47.133665: step: 1000/527, loss: 0.005323866847902536
2023-01-24 05:04:48.185724: step: 1004/527, loss: 0.01036792155355215
2023-01-24 05:04:49.260007: step: 1008/527, loss: 0.041970763355493546
2023-01-24 05:04:50.293560: step: 1012/527, loss: 0.024016601964831352
2023-01-24 05:04:51.333603: step: 1016/527, loss: 0.040281787514686584
2023-01-24 05:04:52.402945: step: 1020/527, loss: 0.026675747707486153
2023-01-24 05:04:53.436810: step: 1024/527, loss: 0.013697942718863487
2023-01-24 05:04:54.498599: step: 1028/527, loss: 0.039383962750434875
2023-01-24 05:04:55.543479: step: 1032/527, loss: 0.014411290176212788
2023-01-24 05:04:56.604135: step: 1036/527, loss: 0.033551596105098724
2023-01-24 05:04:57.672638: step: 1040/527, loss: 0.010896379128098488
2023-01-24 05:04:58.734094: step: 1044/527, loss: 0.046110495924949646
2023-01-24 05:04:59.763551: step: 1048/527, loss: 0.05814679339528084
2023-01-24 05:05:00.833039: step: 1052/527, loss: 0.009706827811896801
2023-01-24 05:05:01.885494: step: 1056/527, loss: 0.016290973871946335
2023-01-24 05:05:02.926769: step: 1060/527, loss: 0.003077411325648427
2023-01-24 05:05:03.981162: step: 1064/527, loss: 0.008014618419110775
2023-01-24 05:05:05.038802: step: 1068/527, loss: 0.016418689861893654
2023-01-24 05:05:06.089994: step: 1072/527, loss: 0.009384910576045513
2023-01-24 05:05:07.159137: step: 1076/527, loss: 0.006921080872416496
2023-01-24 05:05:08.197504: step: 1080/527, loss: 0.020065046846866608
2023-01-24 05:05:09.256615: step: 1084/527, loss: 0.013070640154182911
2023-01-24 05:05:10.325495: step: 1088/527, loss: 0.02336178347468376
2023-01-24 05:05:11.392206: step: 1092/527, loss: 0.00855566468089819
2023-01-24 05:05:12.470197: step: 1096/527, loss: 0.006551303435117006
2023-01-24 05:05:13.517016: step: 1100/527, loss: 0.012348373420536518
2023-01-24 05:05:14.605409: step: 1104/527, loss: 0.017696712166070938
2023-01-24 05:05:15.652271: step: 1108/527, loss: 0.009105103090405464
2023-01-24 05:05:16.720092: step: 1112/527, loss: 0.046973537653684616
2023-01-24 05:05:17.789173: step: 1116/527, loss: 0.047595299780368805
2023-01-24 05:05:18.850860: step: 1120/527, loss: 0.012884553521871567
2023-01-24 05:05:19.917819: step: 1124/527, loss: 0.0391993410885334
2023-01-24 05:05:20.979868: step: 1128/527, loss: 0.0156722255051136
2023-01-24 05:05:22.038418: step: 1132/527, loss: 0.014547361060976982
2023-01-24 05:05:23.088877: step: 1136/527, loss: 0.07776817679405212
2023-01-24 05:05:24.168025: step: 1140/527, loss: 0.013856232166290283
2023-01-24 05:05:25.218798: step: 1144/527, loss: 0.020356912165880203
2023-01-24 05:05:26.283351: step: 1148/527, loss: 0.00910620205104351
2023-01-24 05:05:27.348797: step: 1152/527, loss: 0.005105924792587757
2023-01-24 05:05:28.393463: step: 1156/527, loss: 0.010484758764505386
2023-01-24 05:05:29.476818: step: 1160/527, loss: 0.03854474797844887
2023-01-24 05:05:30.539338: step: 1164/527, loss: 0.03841403126716614
2023-01-24 05:05:31.591581: step: 1168/527, loss: 0.009553241543471813
2023-01-24 05:05:32.637536: step: 1172/527, loss: 0.016660507768392563
2023-01-24 05:05:33.686899: step: 1176/527, loss: 0.00820698868483305
2023-01-24 05:05:34.737248: step: 1180/527, loss: 0.02934238128364086
2023-01-24 05:05:35.788992: step: 1184/527, loss: 0.007767180446535349
2023-01-24 05:05:36.845634: step: 1188/527, loss: 0.0075871325097978115
2023-01-24 05:05:37.886970: step: 1192/527, loss: 0.0077916705049574375
2023-01-24 05:05:38.966921: step: 1196/527, loss: 0.030841263011097908
2023-01-24 05:05:40.028887: step: 1200/527, loss: 0.03321535885334015
2023-01-24 05:05:41.071700: step: 1204/527, loss: 0.02610904909670353
2023-01-24 05:05:42.133805: step: 1208/527, loss: 0.020991189405322075
2023-01-24 05:05:43.187597: step: 1212/527, loss: 0.009386571124196053
2023-01-24 05:05:44.230603: step: 1216/527, loss: 0.023512419313192368
2023-01-24 05:05:45.267605: step: 1220/527, loss: 0.008178832940757275
2023-01-24 05:05:46.327922: step: 1224/527, loss: 0.005385445896536112
2023-01-24 05:05:47.394718: step: 1228/527, loss: 0.012898849323391914
2023-01-24 05:05:48.439381: step: 1232/527, loss: 0.012308849021792412
2023-01-24 05:05:49.499834: step: 1236/527, loss: 0.014423832297325134
2023-01-24 05:05:50.582638: step: 1240/527, loss: 0.01827123761177063
2023-01-24 05:05:51.619062: step: 1244/527, loss: 0.006917300634086132
2023-01-24 05:05:52.673423: step: 1248/527, loss: 0.009379149414598942
2023-01-24 05:05:53.735949: step: 1252/527, loss: 0.01035989262163639
2023-01-24 05:05:54.799648: step: 1256/527, loss: 0.008993702940642834
2023-01-24 05:05:55.873244: step: 1260/527, loss: 0.014762411825358868
2023-01-24 05:05:56.925985: step: 1264/527, loss: 0.03903532028198242
2023-01-24 05:05:57.975452: step: 1268/527, loss: 0.012304996140301228
2023-01-24 05:05:59.030184: step: 1272/527, loss: 0.020094679668545723
2023-01-24 05:06:00.080462: step: 1276/527, loss: 0.0125426622107625
2023-01-24 05:06:01.140374: step: 1280/527, loss: 0.01801511086523533
2023-01-24 05:06:02.200548: step: 1284/527, loss: 0.015352058224380016
2023-01-24 05:06:03.261713: step: 1288/527, loss: 0.0018933522514998913
2023-01-24 05:06:04.319334: step: 1292/527, loss: 0.010640609078109264
2023-01-24 05:06:05.370262: step: 1296/527, loss: 0.06180921569466591
2023-01-24 05:06:06.440408: step: 1300/527, loss: 0.04762286692857742
2023-01-24 05:06:07.490557: step: 1304/527, loss: 0.007108218967914581
2023-01-24 05:06:08.559785: step: 1308/527, loss: 0.005272018723189831
2023-01-24 05:06:09.620154: step: 1312/527, loss: 0.014031399972736835
2023-01-24 05:06:10.667879: step: 1316/527, loss: 0.03510887175798416
2023-01-24 05:06:11.727233: step: 1320/527, loss: 0.023932509124279022
2023-01-24 05:06:12.792039: step: 1324/527, loss: 0.014666752889752388
2023-01-24 05:06:13.847613: step: 1328/527, loss: 0.011219554580748081
2023-01-24 05:06:14.892422: step: 1332/527, loss: 0.009440240450203419
2023-01-24 05:06:15.962493: step: 1336/527, loss: 0.00312281702645123
2023-01-24 05:06:17.009904: step: 1340/527, loss: 0.0017904100241139531
2023-01-24 05:06:18.067192: step: 1344/527, loss: 0.029135361313819885
2023-01-24 05:06:19.133761: step: 1348/527, loss: 0.04780901223421097
2023-01-24 05:06:20.213240: step: 1352/527, loss: 0.013022257015109062
2023-01-24 05:06:21.288570: step: 1356/527, loss: 0.010202418081462383
2023-01-24 05:06:22.337545: step: 1360/527, loss: 0.013486332260072231
2023-01-24 05:06:23.428635: step: 1364/527, loss: 0.06929058581590652
2023-01-24 05:06:24.484155: step: 1368/527, loss: 0.004456627648323774
2023-01-24 05:06:25.537342: step: 1372/527, loss: 0.03167043626308441
2023-01-24 05:06:26.589489: step: 1376/527, loss: 0.014031722210347652
2023-01-24 05:06:27.655910: step: 1380/527, loss: 0.01597975194454193
2023-01-24 05:06:28.698114: step: 1384/527, loss: 0.012782503850758076
2023-01-24 05:06:29.764318: step: 1388/527, loss: 0.007612484972923994
2023-01-24 05:06:30.830366: step: 1392/527, loss: 0.008005892857909203
2023-01-24 05:06:31.887999: step: 1396/527, loss: 0.003933346830308437
2023-01-24 05:06:32.947745: step: 1400/527, loss: 0.00893066544085741
2023-01-24 05:06:33.990599: step: 1404/527, loss: 0.015828493982553482
2023-01-24 05:06:35.067547: step: 1408/527, loss: 0.010186729021370411
2023-01-24 05:06:36.125470: step: 1412/527, loss: 0.004033392760902643
2023-01-24 05:06:37.198840: step: 1416/527, loss: 0.007016969379037619
2023-01-24 05:06:38.271432: step: 1420/527, loss: 0.0452611967921257
2023-01-24 05:06:39.400575: step: 1424/527, loss: 0.011878282763063908
2023-01-24 05:06:40.454417: step: 1428/527, loss: 0.010270990431308746
2023-01-24 05:06:41.511997: step: 1432/527, loss: 0.011314825154840946
2023-01-24 05:06:42.559422: step: 1436/527, loss: 0.04765573889017105
2023-01-24 05:06:43.609815: step: 1440/527, loss: 0.013969712890684605
2023-01-24 05:06:44.659439: step: 1444/527, loss: 0.030887247994542122
2023-01-24 05:06:45.711584: step: 1448/527, loss: 0.013999665156006813
2023-01-24 05:06:46.768889: step: 1452/527, loss: 0.022451085969805717
2023-01-24 05:06:47.824912: step: 1456/527, loss: 0.037313204258680344
2023-01-24 05:06:48.899184: step: 1460/527, loss: 0.02577519230544567
2023-01-24 05:06:49.964824: step: 1464/527, loss: 0.011492750607430935
2023-01-24 05:06:51.015032: step: 1468/527, loss: 0.006659230217337608
2023-01-24 05:06:52.069153: step: 1472/527, loss: 0.014374570921063423
2023-01-24 05:06:53.139085: step: 1476/527, loss: 0.027423938736319542
2023-01-24 05:06:54.204126: step: 1480/527, loss: 0.0052278959192335606
2023-01-24 05:06:55.264044: step: 1484/527, loss: 0.00777996564283967
2023-01-24 05:06:56.340834: step: 1488/527, loss: 0.009974290616810322
2023-01-24 05:06:57.409607: step: 1492/527, loss: 0.030738811939954758
2023-01-24 05:06:58.449538: step: 1496/527, loss: 0.010464017279446125
2023-01-24 05:06:59.512417: step: 1500/527, loss: 0.007696117740124464
2023-01-24 05:07:00.574993: step: 1504/527, loss: 0.005756647791713476
2023-01-24 05:07:01.612567: step: 1508/527, loss: 0.006192333530634642
2023-01-24 05:07:02.671882: step: 1512/527, loss: 0.005386924371123314
2023-01-24 05:07:03.737301: step: 1516/527, loss: 0.004054374527186155
2023-01-24 05:07:04.800931: step: 1520/527, loss: 0.07301867008209229
2023-01-24 05:07:05.886211: step: 1524/527, loss: 0.04305405169725418
2023-01-24 05:07:06.950488: step: 1528/527, loss: 0.012200158089399338
2023-01-24 05:07:08.004954: step: 1532/527, loss: 0.015273768454790115
2023-01-24 05:07:09.070260: step: 1536/527, loss: 0.030957499518990517
2023-01-24 05:07:10.138162: step: 1540/527, loss: 0.01303430087864399
2023-01-24 05:07:11.174759: step: 1544/527, loss: 0.024624032899737358
2023-01-24 05:07:12.253450: step: 1548/527, loss: 0.007791030686348677
2023-01-24 05:07:13.338507: step: 1552/527, loss: 0.010313978418707848
2023-01-24 05:07:14.405230: step: 1556/527, loss: 0.009440312162041664
2023-01-24 05:07:15.451103: step: 1560/527, loss: 0.008625865913927555
2023-01-24 05:07:16.524576: step: 1564/527, loss: 0.007325490936636925
2023-01-24 05:07:17.597640: step: 1568/527, loss: 0.010690315626561642
2023-01-24 05:07:18.662121: step: 1572/527, loss: 0.018749846145510674
2023-01-24 05:07:19.715933: step: 1576/527, loss: 0.005152354948222637
2023-01-24 05:07:20.786728: step: 1580/527, loss: 0.04477600008249283
2023-01-24 05:07:21.844330: step: 1584/527, loss: 0.011427847668528557
2023-01-24 05:07:22.901101: step: 1588/527, loss: 0.007948131300508976
2023-01-24 05:07:23.962545: step: 1592/527, loss: 0.041392892599105835
2023-01-24 05:07:25.026285: step: 1596/527, loss: 0.009622021578252316
2023-01-24 05:07:26.084895: step: 1600/527, loss: 0.0037746590096503496
2023-01-24 05:07:27.124264: step: 1604/527, loss: 0.01732400804758072
2023-01-24 05:07:28.177737: step: 1608/527, loss: 0.03905663266777992
2023-01-24 05:07:29.241883: step: 1612/527, loss: 0.02227986603975296
2023-01-24 05:07:30.297517: step: 1616/527, loss: 0.014169770292937756
2023-01-24 05:07:31.353932: step: 1620/527, loss: 0.014529128558933735
2023-01-24 05:07:32.398683: step: 1624/527, loss: 0.004460591822862625
2023-01-24 05:07:33.462378: step: 1628/527, loss: 0.02952991984784603
2023-01-24 05:07:34.531422: step: 1632/527, loss: 0.0642104521393776
2023-01-24 05:07:35.588671: step: 1636/527, loss: 0.03177327662706375
2023-01-24 05:07:36.673661: step: 1640/527, loss: 0.00895645096898079
2023-01-24 05:07:37.722532: step: 1644/527, loss: 0.011493697762489319
2023-01-24 05:07:38.780305: step: 1648/527, loss: 0.002630829345434904
2023-01-24 05:07:39.846305: step: 1652/527, loss: 0.05805065110325813
2023-01-24 05:07:40.895884: step: 1656/527, loss: 0.008323252201080322
2023-01-24 05:07:41.968623: step: 1660/527, loss: 0.00827107671648264
2023-01-24 05:07:43.020763: step: 1664/527, loss: 0.02883150614798069
2023-01-24 05:07:44.100374: step: 1668/527, loss: 0.009317230433225632
2023-01-24 05:07:45.148400: step: 1672/527, loss: 0.031653061509132385
2023-01-24 05:07:46.205125: step: 1676/527, loss: 0.013449599035084248
2023-01-24 05:07:47.248432: step: 1680/527, loss: 0.00865088403224945
2023-01-24 05:07:48.311494: step: 1684/527, loss: 0.009988667443394661
2023-01-24 05:07:49.363005: step: 1688/527, loss: 0.034307632595300674
2023-01-24 05:07:50.414304: step: 1692/527, loss: 0.008244461379945278
2023-01-24 05:07:51.462492: step: 1696/527, loss: 0.015821607783436775
2023-01-24 05:07:52.516876: step: 1700/527, loss: 0.014487474225461483
2023-01-24 05:07:53.578199: step: 1704/527, loss: 0.006990600842982531
2023-01-24 05:07:54.655904: step: 1708/527, loss: 0.0161539688706398
2023-01-24 05:07:55.704692: step: 1712/527, loss: 0.025770502164959908
2023-01-24 05:07:56.767293: step: 1716/527, loss: 0.01005584467202425
2023-01-24 05:07:57.826151: step: 1720/527, loss: 0.0176510289311409
2023-01-24 05:07:58.899733: step: 1724/527, loss: 0.030513670295476913
2023-01-24 05:07:59.949963: step: 1728/527, loss: 0.013273200020194054
2023-01-24 05:08:01.012827: step: 1732/527, loss: 0.010769909247756004
2023-01-24 05:08:02.075889: step: 1736/527, loss: 0.053587283939123154
2023-01-24 05:08:03.123959: step: 1740/527, loss: 0.013260331936180592
2023-01-24 05:08:04.203392: step: 1744/527, loss: 0.041208021342754364
2023-01-24 05:08:05.279431: step: 1748/527, loss: 0.006117898039519787
2023-01-24 05:08:06.329453: step: 1752/527, loss: 0.04246333986520767
2023-01-24 05:08:07.398270: step: 1756/527, loss: 0.007902263663709164
2023-01-24 05:08:08.462219: step: 1760/527, loss: 0.037524960935115814
2023-01-24 05:08:09.520250: step: 1764/527, loss: 0.00913565419614315
2023-01-24 05:08:10.568591: step: 1768/527, loss: 0.021684909239411354
2023-01-24 05:08:11.626914: step: 1772/527, loss: 0.03140508010983467
2023-01-24 05:08:12.676817: step: 1776/527, loss: 0.008953028358519077
2023-01-24 05:08:13.719782: step: 1780/527, loss: 0.04349980130791664
2023-01-24 05:08:14.781437: step: 1784/527, loss: 0.008197353221476078
2023-01-24 05:08:15.829427: step: 1788/527, loss: 0.006808818783611059
2023-01-24 05:08:16.859287: step: 1792/527, loss: 0.005978906527161598
2023-01-24 05:08:17.919938: step: 1796/527, loss: 0.01945285126566887
2023-01-24 05:08:18.980187: step: 1800/527, loss: 0.007546133361756802
2023-01-24 05:08:20.056364: step: 1804/527, loss: 0.01640220545232296
2023-01-24 05:08:21.135681: step: 1808/527, loss: 0.041898034512996674
2023-01-24 05:08:22.209285: step: 1812/527, loss: 0.008640028536319733
2023-01-24 05:08:23.250172: step: 1816/527, loss: 0.017172126099467278
2023-01-24 05:08:24.302108: step: 1820/527, loss: 0.009918355382978916
2023-01-24 05:08:25.374372: step: 1824/527, loss: 0.02356589213013649
2023-01-24 05:08:26.440227: step: 1828/527, loss: 0.021140605211257935
2023-01-24 05:08:27.510853: step: 1832/527, loss: 0.0565682053565979
2023-01-24 05:08:28.559486: step: 1836/527, loss: 0.010100433602929115
2023-01-24 05:08:29.617947: step: 1840/527, loss: 0.006153437774628401
2023-01-24 05:08:30.672135: step: 1844/527, loss: 0.03274431452155113
2023-01-24 05:08:31.732478: step: 1848/527, loss: 0.01192291546612978
2023-01-24 05:08:32.794962: step: 1852/527, loss: 0.009296722710132599
2023-01-24 05:08:33.840910: step: 1856/527, loss: 0.009591406211256981
2023-01-24 05:08:34.891898: step: 1860/527, loss: 0.026896940544247627
2023-01-24 05:08:35.940702: step: 1864/527, loss: 0.03655450791120529
2023-01-24 05:08:36.995048: step: 1868/527, loss: 0.0128747234120965
2023-01-24 05:08:38.052604: step: 1872/527, loss: 0.012429596856236458
2023-01-24 05:08:39.104286: step: 1876/527, loss: 0.009383030235767365
2023-01-24 05:08:40.156508: step: 1880/527, loss: 0.02010120078921318
2023-01-24 05:08:41.214791: step: 1884/527, loss: 0.009326232597231865
2023-01-24 05:08:42.260056: step: 1888/527, loss: 0.012102792039513588
2023-01-24 05:08:43.310072: step: 1892/527, loss: 0.006842283997684717
2023-01-24 05:08:44.394991: step: 1896/527, loss: 0.03691709414124489
2023-01-24 05:08:45.451780: step: 1900/527, loss: 0.023316722363233566
2023-01-24 05:08:46.498768: step: 1904/527, loss: 0.009631594642996788
2023-01-24 05:08:47.562620: step: 1908/527, loss: 0.015783611685037613
2023-01-24 05:08:48.618337: step: 1912/527, loss: 0.01289606187492609
2023-01-24 05:08:49.709816: step: 1916/527, loss: 0.02982412464916706
2023-01-24 05:08:50.767086: step: 1920/527, loss: 0.018698425963521004
2023-01-24 05:08:51.829854: step: 1924/527, loss: 0.0043085478246212006
2023-01-24 05:08:52.894480: step: 1928/527, loss: 0.012623300775885582
2023-01-24 05:08:53.973384: step: 1932/527, loss: 0.034485820680856705
2023-01-24 05:08:55.048799: step: 1936/527, loss: 0.0386204868555069
2023-01-24 05:08:56.095323: step: 1940/527, loss: 0.012891515158116817
2023-01-24 05:08:57.144464: step: 1944/527, loss: 0.038250040262937546
2023-01-24 05:08:58.197049: step: 1948/527, loss: 0.011790971271693707
2023-01-24 05:08:59.254143: step: 1952/527, loss: 0.01894655078649521
2023-01-24 05:09:00.310664: step: 1956/527, loss: 0.012213597074151039
2023-01-24 05:09:01.379258: step: 1960/527, loss: 0.0093131298199296
2023-01-24 05:09:02.428438: step: 1964/527, loss: 0.007838459685444832
2023-01-24 05:09:03.495738: step: 1968/527, loss: 0.014537162147462368
2023-01-24 05:09:04.570783: step: 1972/527, loss: 0.01118561252951622
2023-01-24 05:09:05.647122: step: 1976/527, loss: 0.0030727682169526815
2023-01-24 05:09:06.714238: step: 1980/527, loss: 0.008721991442143917
2023-01-24 05:09:07.784116: step: 1984/527, loss: 0.020510070025920868
2023-01-24 05:09:08.841156: step: 1988/527, loss: 0.01436369027942419
2023-01-24 05:09:09.885881: step: 1992/527, loss: 0.03267817199230194
2023-01-24 05:09:10.955895: step: 1996/527, loss: 0.01706632599234581
2023-01-24 05:09:12.024142: step: 2000/527, loss: 0.007094400003552437
2023-01-24 05:09:13.083861: step: 2004/527, loss: 0.011377047747373581
2023-01-24 05:09:14.141803: step: 2008/527, loss: 0.026451947167515755
2023-01-24 05:09:15.197581: step: 2012/527, loss: 0.03436955064535141
2023-01-24 05:09:16.258355: step: 2016/527, loss: 0.00371461920440197
2023-01-24 05:09:17.311664: step: 2020/527, loss: 0.019599679857492447
2023-01-24 05:09:18.367657: step: 2024/527, loss: 0.01290049683302641
2023-01-24 05:09:19.452906: step: 2028/527, loss: 0.003558845492079854
2023-01-24 05:09:20.493224: step: 2032/527, loss: 0.005182476714253426
2023-01-24 05:09:21.536192: step: 2036/527, loss: 0.002554287202656269
2023-01-24 05:09:22.603454: step: 2040/527, loss: 0.011803234927356243
2023-01-24 05:09:23.669473: step: 2044/527, loss: 0.0056258318945765495
2023-01-24 05:09:24.715780: step: 2048/527, loss: 0.02907024510204792
2023-01-24 05:09:25.773105: step: 2052/527, loss: 0.034525007009506226
2023-01-24 05:09:26.816539: step: 2056/527, loss: 0.006202684249728918
2023-01-24 05:09:27.874667: step: 2060/527, loss: 0.01596401445567608
2023-01-24 05:09:28.949580: step: 2064/527, loss: 0.052929650992155075
2023-01-24 05:09:30.021507: step: 2068/527, loss: 0.03775949031114578
2023-01-24 05:09:31.063885: step: 2072/527, loss: 0.008293618448078632
2023-01-24 05:09:32.143447: step: 2076/527, loss: 0.057668909430503845
2023-01-24 05:09:33.208070: step: 2080/527, loss: 0.0658436194062233
2023-01-24 05:09:34.253312: step: 2084/527, loss: 0.011614012531936169
2023-01-24 05:09:35.288307: step: 2088/527, loss: 0.011249169707298279
2023-01-24 05:09:36.341890: step: 2092/527, loss: 0.005233381409198046
2023-01-24 05:09:37.406169: step: 2096/527, loss: 0.031973328441381454
2023-01-24 05:09:38.473205: step: 2100/527, loss: 0.004628822207450867
2023-01-24 05:09:39.546054: step: 2104/527, loss: 0.0032797774765640497
2023-01-24 05:09:40.598318: step: 2108/527, loss: 0.01285646203905344
==================================================
Loss: 0.022
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33470188079670793, 'r': 0.32517526179869916, 'f1': 0.32986980359560053}, 'combined': 0.24306196054412668, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3640699453333525, 'r': 0.28960109287880315, 'f1': 0.32259362244727435}, 'combined': 0.20645991836625555, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3536624256995926, 'r': 0.3241346330415621, 'f1': 0.3382553497285212}, 'combined': 0.24924078401048932, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3748069338473277, 'r': 0.3078405172255627, 'f1': 0.33803908648292524}, 'combined': 0.24236764691228604, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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': 0.33470188079670793, 'r': 0.32517526179869916, 'f1': 0.32986980359560053}, 'combined': 0.24306196054412668, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3640699453333525, 'r': 0.28960109287880315, 'f1': 0.32259362244727435}, 'combined': 0.20645991836625555, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3536624256995926, 'r': 0.3241346330415621, 'f1': 0.3382553497285212}, 'combined': 0.24924078401048932, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3748069338473277, 'r': 0.3078405172255627, 'f1': 0.33803908648292524}, 'combined': 0.24236764691228604, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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
2023-01-24 05:12:32.145831: step: 4/527, loss: 0.018123280256986618
2023-01-24 05:12:33.176404: step: 8/527, loss: 0.01113036647439003
2023-01-24 05:12:34.206989: step: 12/527, loss: 0.011442981660366058
2023-01-24 05:12:35.257870: step: 16/527, loss: 0.01591738872230053
2023-01-24 05:12:36.304285: step: 20/527, loss: 0.011292441748082638
2023-01-24 05:12:37.328574: step: 24/527, loss: 0.010824518278241158
2023-01-24 05:12:38.389722: step: 28/527, loss: 0.007420710287988186
2023-01-24 05:12:39.432992: step: 32/527, loss: 0.013100599870085716
2023-01-24 05:12:40.477997: step: 36/527, loss: 0.02413242682814598
2023-01-24 05:12:41.536775: step: 40/527, loss: 0.02858263999223709
2023-01-24 05:12:42.579223: step: 44/527, loss: 0.004235970322042704
2023-01-24 05:12:43.621687: step: 48/527, loss: 0.00850728154182434
2023-01-24 05:12:44.678241: step: 52/527, loss: 0.01044514961540699
2023-01-24 05:12:45.720554: step: 56/527, loss: 0.008220076560974121
2023-01-24 05:12:46.777910: step: 60/527, loss: 0.014187716878950596
2023-01-24 05:12:47.817964: step: 64/527, loss: 0.005522199906408787
2023-01-24 05:12:48.880851: step: 68/527, loss: 0.010371244512498379
2023-01-24 05:12:49.945948: step: 72/527, loss: 0.00860979501157999
2023-01-24 05:12:51.000078: step: 76/527, loss: 0.010606663301587105
2023-01-24 05:12:52.042420: step: 80/527, loss: 0.011769460514187813
2023-01-24 05:12:53.096691: step: 84/527, loss: 0.04180312901735306
2023-01-24 05:12:54.147775: step: 88/527, loss: 0.004522264935076237
2023-01-24 05:12:55.204523: step: 92/527, loss: 0.04639697074890137
2023-01-24 05:12:56.270425: step: 96/527, loss: 0.016354702413082123
2023-01-24 05:12:57.308648: step: 100/527, loss: 0.01197791751474142
2023-01-24 05:12:58.346170: step: 104/527, loss: 0.008995951153337955
2023-01-24 05:12:59.386529: step: 108/527, loss: 0.01863301731646061
2023-01-24 05:13:00.495455: step: 112/527, loss: 0.04583723843097687
2023-01-24 05:13:01.550658: step: 116/527, loss: 0.036483559757471085
2023-01-24 05:13:02.585370: step: 120/527, loss: 0.02192608267068863
2023-01-24 05:13:03.635931: step: 124/527, loss: 0.05907829478383064
2023-01-24 05:13:04.684238: step: 128/527, loss: 0.010600809939205647
2023-01-24 05:13:05.734997: step: 132/527, loss: 0.007352891843765974
2023-01-24 05:13:06.781862: step: 136/527, loss: 0.00801857840269804
2023-01-24 05:13:07.833760: step: 140/527, loss: 0.004974058363586664
2023-01-24 05:13:08.891186: step: 144/527, loss: 0.024974599480628967
2023-01-24 05:13:09.951114: step: 148/527, loss: 0.014170176349580288
2023-01-24 05:13:11.003146: step: 152/527, loss: 0.014072049409151077
2023-01-24 05:13:12.044743: step: 156/527, loss: 0.0
2023-01-24 05:13:13.103325: step: 160/527, loss: 0.005382283125072718
2023-01-24 05:13:14.151523: step: 164/527, loss: 0.015689590945839882
2023-01-24 05:13:15.208987: step: 168/527, loss: 0.03355139121413231
2023-01-24 05:13:16.276878: step: 172/527, loss: 0.01109452173113823
2023-01-24 05:13:17.333411: step: 176/527, loss: 0.010349083691835403
2023-01-24 05:13:18.372560: step: 180/527, loss: 0.008498347364366055
2023-01-24 05:13:19.437809: step: 184/527, loss: 0.013933093287050724
2023-01-24 05:13:20.501451: step: 188/527, loss: 0.008587097749114037
2023-01-24 05:13:21.549416: step: 192/527, loss: 0.017063884064555168
2023-01-24 05:13:22.604511: step: 196/527, loss: 0.0087741669267416
2023-01-24 05:13:23.655293: step: 200/527, loss: 0.012951512821018696
2023-01-24 05:13:24.703221: step: 204/527, loss: 0.009218239225447178
2023-01-24 05:13:25.774677: step: 208/527, loss: 0.007676574867218733
2023-01-24 05:13:26.823302: step: 212/527, loss: 0.003308728104457259
2023-01-24 05:13:27.865683: step: 216/527, loss: 0.00992603600025177
2023-01-24 05:13:28.914278: step: 220/527, loss: 0.06028809770941734
2023-01-24 05:13:29.958829: step: 224/527, loss: 0.02564755082130432
2023-01-24 05:13:31.019589: step: 228/527, loss: 0.010617483407258987
2023-01-24 05:13:32.072013: step: 232/527, loss: 0.01835789903998375
2023-01-24 05:13:33.122800: step: 236/527, loss: 0.015816032886505127
2023-01-24 05:13:34.178224: step: 240/527, loss: 0.008347642607986927
2023-01-24 05:13:35.260202: step: 244/527, loss: 0.03272389993071556
2023-01-24 05:13:36.314819: step: 248/527, loss: 0.010540221817791462
2023-01-24 05:13:37.361177: step: 252/527, loss: 0.06438185274600983
2023-01-24 05:13:38.440793: step: 256/527, loss: 0.002308423165231943
2023-01-24 05:13:39.505707: step: 260/527, loss: 0.0038301192689687014
2023-01-24 05:13:40.554505: step: 264/527, loss: 0.012879110872745514
2023-01-24 05:13:41.605501: step: 268/527, loss: 0.047585975378751755
2023-01-24 05:13:42.658139: step: 272/527, loss: 0.007781265303492546
2023-01-24 05:13:43.725536: step: 276/527, loss: 0.014498968608677387
2023-01-24 05:13:44.772030: step: 280/527, loss: 0.027096187695860863
2023-01-24 05:13:45.811177: step: 284/527, loss: 0.011391350999474525
2023-01-24 05:13:46.877833: step: 288/527, loss: 0.0075580524280667305
2023-01-24 05:13:47.941780: step: 292/527, loss: 0.02844475395977497
2023-01-24 05:13:49.007697: step: 296/527, loss: 0.029594112187623978
2023-01-24 05:13:50.065196: step: 300/527, loss: 0.004208073019981384
2023-01-24 05:13:51.125711: step: 304/527, loss: 0.01020155567675829
2023-01-24 05:13:52.183468: step: 308/527, loss: 0.009681605733931065
2023-01-24 05:13:53.239121: step: 312/527, loss: 0.017227400094270706
2023-01-24 05:13:54.287016: step: 316/527, loss: 0.008385112509131432
2023-01-24 05:13:55.339395: step: 320/527, loss: 0.0276352446526289
2023-01-24 05:13:56.375548: step: 324/527, loss: 0.014857093803584576
2023-01-24 05:13:57.442381: step: 328/527, loss: 0.014654400758445263
2023-01-24 05:13:58.484843: step: 332/527, loss: 0.003937077708542347
2023-01-24 05:13:59.539630: step: 336/527, loss: 0.006456168368458748
2023-01-24 05:14:00.607666: step: 340/527, loss: 0.009996989741921425
2023-01-24 05:14:01.662823: step: 344/527, loss: 0.047514837235212326
2023-01-24 05:14:02.746394: step: 348/527, loss: 0.006446389947086573
2023-01-24 05:14:03.789765: step: 352/527, loss: 0.03986106067895889
2023-01-24 05:14:04.836248: step: 356/527, loss: 0.013090807944536209
2023-01-24 05:14:05.884489: step: 360/527, loss: 0.007790746167302132
2023-01-24 05:14:06.934724: step: 364/527, loss: 0.004554046783596277
2023-01-24 05:14:08.012209: step: 368/527, loss: 0.014674236066639423
2023-01-24 05:14:09.069953: step: 372/527, loss: 0.026796650141477585
2023-01-24 05:14:10.130732: step: 376/527, loss: 0.02358562871813774
2023-01-24 05:14:11.172679: step: 380/527, loss: 0.044411905109882355
2023-01-24 05:14:12.223298: step: 384/527, loss: 0.012452136725187302
2023-01-24 05:14:13.273942: step: 388/527, loss: 0.028408855199813843
2023-01-24 05:14:14.334317: step: 392/527, loss: 0.04561150446534157
2023-01-24 05:14:15.377210: step: 396/527, loss: 0.008928496390581131
2023-01-24 05:14:16.435128: step: 400/527, loss: 0.014053450897336006
2023-01-24 05:14:17.501838: step: 404/527, loss: 0.010381078347563744
2023-01-24 05:14:18.541903: step: 408/527, loss: 0.005319703370332718
2023-01-24 05:14:19.595452: step: 412/527, loss: 0.008386380970478058
2023-01-24 05:14:20.651020: step: 416/527, loss: 0.04453711956739426
2023-01-24 05:14:21.700640: step: 420/527, loss: 0.011459262110292912
2023-01-24 05:14:22.781441: step: 424/527, loss: 0.04532322660088539
2023-01-24 05:14:23.838331: step: 428/527, loss: 0.032943982630968094
2023-01-24 05:14:24.899174: step: 432/527, loss: 0.020364120602607727
2023-01-24 05:14:25.962493: step: 436/527, loss: 0.02971181832253933
2023-01-24 05:14:27.024800: step: 440/527, loss: 0.011676590889692307
2023-01-24 05:14:28.082783: step: 444/527, loss: 0.012562346644699574
2023-01-24 05:14:29.152017: step: 448/527, loss: 0.018417175859212875
2023-01-24 05:14:30.216399: step: 452/527, loss: 0.02813078835606575
2023-01-24 05:14:31.283000: step: 456/527, loss: 0.019882671535015106
2023-01-24 05:14:32.336607: step: 460/527, loss: 0.017151357606053352
2023-01-24 05:14:33.382861: step: 464/527, loss: 0.009238461032509804
2023-01-24 05:14:34.460187: step: 468/527, loss: 0.01628982648253441
2023-01-24 05:14:35.516042: step: 472/527, loss: 0.009066357277333736
2023-01-24 05:14:36.570969: step: 476/527, loss: 0.01865309663116932
2023-01-24 05:14:37.618525: step: 480/527, loss: 0.003974127117544413
2023-01-24 05:14:38.667558: step: 484/527, loss: 0.004207334015518427
2023-01-24 05:14:39.717270: step: 488/527, loss: 0.024722395464777946
2023-01-24 05:14:40.766435: step: 492/527, loss: 0.002124141901731491
2023-01-24 05:14:41.835160: step: 496/527, loss: 0.01544024795293808
2023-01-24 05:14:42.881833: step: 500/527, loss: 0.019356610253453255
2023-01-24 05:14:43.934303: step: 504/527, loss: 0.014582685194909573
2023-01-24 05:14:44.985428: step: 508/527, loss: 0.0061416951939463615
2023-01-24 05:14:46.050621: step: 512/527, loss: 0.021815327927470207
2023-01-24 05:14:47.121460: step: 516/527, loss: 0.006505594588816166
2023-01-24 05:14:48.180378: step: 520/527, loss: 0.01506065670400858
2023-01-24 05:14:49.251715: step: 524/527, loss: 0.028149817138910294
2023-01-24 05:14:50.295679: step: 528/527, loss: 0.01869608648121357
2023-01-24 05:14:51.357577: step: 532/527, loss: 0.006509323138743639
2023-01-24 05:14:52.400180: step: 536/527, loss: 0.002958935219794512
2023-01-24 05:14:53.444138: step: 540/527, loss: 0.005710993893444538
2023-01-24 05:14:54.497535: step: 544/527, loss: 0.012775847688317299
2023-01-24 05:14:55.558779: step: 548/527, loss: 0.01182165089994669
2023-01-24 05:14:56.622854: step: 552/527, loss: 0.0019352142699062824
2023-01-24 05:14:57.674983: step: 556/527, loss: 0.010771512985229492
2023-01-24 05:14:58.760765: step: 560/527, loss: 0.021161146461963654
2023-01-24 05:14:59.803846: step: 564/527, loss: 0.004150019027292728
2023-01-24 05:15:00.860957: step: 568/527, loss: 0.011796188540756702
2023-01-24 05:15:01.937513: step: 572/527, loss: 0.013756037689745426
2023-01-24 05:15:03.006033: step: 576/527, loss: 0.006406253203749657
2023-01-24 05:15:04.061676: step: 580/527, loss: 0.05517202988266945
2023-01-24 05:15:05.142117: step: 584/527, loss: 0.0384361632168293
2023-01-24 05:15:06.203467: step: 588/527, loss: 0.030206233263015747
2023-01-24 05:15:07.252317: step: 592/527, loss: 0.016878217458724976
2023-01-24 05:15:08.303144: step: 596/527, loss: 0.03763467073440552
2023-01-24 05:15:09.362417: step: 600/527, loss: 0.013674174435436726
2023-01-24 05:15:10.426465: step: 604/527, loss: 0.026607193052768707
2023-01-24 05:15:11.477670: step: 608/527, loss: 0.021218687295913696
2023-01-24 05:15:12.529316: step: 612/527, loss: 0.0059247203171253204
2023-01-24 05:15:13.584658: step: 616/527, loss: 0.011762079782783985
2023-01-24 05:15:14.625321: step: 620/527, loss: 0.0027541397139430046
2023-01-24 05:15:15.678765: step: 624/527, loss: 0.013390828855335712
2023-01-24 05:15:16.742936: step: 628/527, loss: 0.011553638614714146
2023-01-24 05:15:17.782809: step: 632/527, loss: 0.0
2023-01-24 05:15:18.846296: step: 636/527, loss: 0.007285550236701965
2023-01-24 05:15:19.889219: step: 640/527, loss: 0.0054983580484986305
2023-01-24 05:15:20.937936: step: 644/527, loss: 0.010017899796366692
2023-01-24 05:15:21.975044: step: 648/527, loss: 0.047052692621946335
2023-01-24 05:15:23.046251: step: 652/527, loss: 0.006029477808624506
2023-01-24 05:15:24.092705: step: 656/527, loss: 0.003855266375467181
2023-01-24 05:15:25.144211: step: 660/527, loss: 0.0611177533864975
2023-01-24 05:15:26.207919: step: 664/527, loss: 0.00275116297416389
2023-01-24 05:15:27.249823: step: 668/527, loss: 0.0023651104420423508
2023-01-24 05:15:28.310415: step: 672/527, loss: 0.007305797655135393
2023-01-24 05:15:29.359705: step: 676/527, loss: 0.00989602506160736
2023-01-24 05:15:30.422638: step: 680/527, loss: 0.03270602971315384
2023-01-24 05:15:31.484114: step: 684/527, loss: 0.006119735073298216
2023-01-24 05:15:32.545952: step: 688/527, loss: 0.017699265852570534
2023-01-24 05:15:33.612402: step: 692/527, loss: 0.0
2023-01-24 05:15:34.672818: step: 696/527, loss: 0.008197142742574215
2023-01-24 05:15:35.744950: step: 700/527, loss: 0.008787122555077076
2023-01-24 05:15:36.812227: step: 704/527, loss: 0.009869945235550404
2023-01-24 05:15:37.862876: step: 708/527, loss: 0.007514165714383125
2023-01-24 05:15:38.909724: step: 712/527, loss: 0.018841061741113663
2023-01-24 05:15:39.950106: step: 716/527, loss: 0.007815783843398094
2023-01-24 05:15:41.017737: step: 720/527, loss: 0.023072386160492897
2023-01-24 05:15:42.093923: step: 724/527, loss: 0.021277835592627525
2023-01-24 05:15:43.164466: step: 728/527, loss: 0.008390788920223713
2023-01-24 05:15:44.214883: step: 732/527, loss: 0.013654526323080063
2023-01-24 05:15:45.282477: step: 736/527, loss: 0.006143168080598116
2023-01-24 05:15:46.329763: step: 740/527, loss: 0.004079313948750496
2023-01-24 05:15:47.387869: step: 744/527, loss: 0.006833904888480902
2023-01-24 05:15:48.451697: step: 748/527, loss: 0.036992333829402924
2023-01-24 05:15:49.498185: step: 752/527, loss: 0.019806277006864548
2023-01-24 05:15:50.572088: step: 756/527, loss: 0.03341313824057579
2023-01-24 05:15:51.629348: step: 760/527, loss: 0.0044708638451993465
2023-01-24 05:15:52.696080: step: 764/527, loss: 0.013582027517259121
2023-01-24 05:15:53.753339: step: 768/527, loss: 0.023160278797149658
2023-01-24 05:15:54.796472: step: 772/527, loss: 0.008496263064444065
2023-01-24 05:15:55.840113: step: 776/527, loss: 0.009298603050410748
2023-01-24 05:15:56.882299: step: 780/527, loss: 0.01866867020726204
2023-01-24 05:15:57.946991: step: 784/527, loss: 0.00896376371383667
2023-01-24 05:15:59.019424: step: 788/527, loss: 0.005661291535943747
2023-01-24 05:16:00.069256: step: 792/527, loss: 0.0055063762702047825
2023-01-24 05:16:01.134575: step: 796/527, loss: 0.007555162068456411
2023-01-24 05:16:02.194227: step: 800/527, loss: 0.013754550367593765
2023-01-24 05:16:03.272217: step: 804/527, loss: 0.01965765841305256
2023-01-24 05:16:04.321649: step: 808/527, loss: 0.002758193761110306
2023-01-24 05:16:05.380250: step: 812/527, loss: 0.013669691048562527
2023-01-24 05:16:06.430413: step: 816/527, loss: 0.045681025832891464
2023-01-24 05:16:07.480107: step: 820/527, loss: 0.06644242256879807
2023-01-24 05:16:08.539278: step: 824/527, loss: 0.013010891154408455
2023-01-24 05:16:09.597532: step: 828/527, loss: 0.048347603529691696
2023-01-24 05:16:10.665655: step: 832/527, loss: 0.010545626282691956
2023-01-24 05:16:11.722620: step: 836/527, loss: 0.0030454867519438267
2023-01-24 05:16:12.767808: step: 840/527, loss: 0.00696616992354393
2023-01-24 05:16:13.815963: step: 844/527, loss: 0.0010580855887383223
2023-01-24 05:16:14.879054: step: 848/527, loss: 0.007512359414249659
2023-01-24 05:16:15.930701: step: 852/527, loss: 0.015254289843142033
2023-01-24 05:16:16.992053: step: 856/527, loss: 0.024053217843174934
2023-01-24 05:16:18.063130: step: 860/527, loss: 0.011806032620370388
2023-01-24 05:16:19.145868: step: 864/527, loss: 0.0076525830663740635
2023-01-24 05:16:20.221232: step: 868/527, loss: 0.028572598472237587
2023-01-24 05:16:21.272271: step: 872/527, loss: 0.005810061935335398
2023-01-24 05:16:22.319190: step: 876/527, loss: 0.005152808502316475
2023-01-24 05:16:23.365056: step: 880/527, loss: 0.01600806601345539
2023-01-24 05:16:24.435998: step: 884/527, loss: 0.0075842938385903835
2023-01-24 05:16:25.482818: step: 888/527, loss: 0.00941468682140112
2023-01-24 05:16:26.547981: step: 892/527, loss: 0.026428719982504845
2023-01-24 05:16:27.610352: step: 896/527, loss: 0.0038772111292928457
2023-01-24 05:16:28.655309: step: 900/527, loss: 0.011145041324198246
2023-01-24 05:16:29.692301: step: 904/527, loss: 0.028039876371622086
2023-01-24 05:16:30.753207: step: 908/527, loss: 0.007937535643577576
2023-01-24 05:16:31.793106: step: 912/527, loss: 0.006360695231705904
2023-01-24 05:16:32.862987: step: 916/527, loss: 0.03871196135878563
2023-01-24 05:16:33.913634: step: 920/527, loss: 0.026212390512228012
2023-01-24 05:16:34.983751: step: 924/527, loss: 0.007839180529117584
2023-01-24 05:16:36.037165: step: 928/527, loss: 0.017373070120811462
2023-01-24 05:16:37.077368: step: 932/527, loss: 0.011837446130812168
2023-01-24 05:16:38.110688: step: 936/527, loss: 0.005958031862974167
2023-01-24 05:16:39.164449: step: 940/527, loss: 0.01136813685297966
2023-01-24 05:16:40.236978: step: 944/527, loss: 0.010612448677420616
2023-01-24 05:16:41.300136: step: 948/527, loss: 0.010316536761820316
2023-01-24 05:16:42.356887: step: 952/527, loss: 0.0356927253305912
2023-01-24 05:16:43.399551: step: 956/527, loss: 0.048618774861097336
2023-01-24 05:16:44.458775: step: 960/527, loss: 0.008397760801017284
2023-01-24 05:16:45.524047: step: 964/527, loss: 0.027125095948576927
2023-01-24 05:16:46.573220: step: 968/527, loss: 0.003724482608959079
2023-01-24 05:16:47.625798: step: 972/527, loss: 0.005296440329402685
2023-01-24 05:16:48.666225: step: 976/527, loss: 0.009009646251797676
2023-01-24 05:16:49.716529: step: 980/527, loss: 0.00929985474795103
2023-01-24 05:16:50.767818: step: 984/527, loss: 0.007095534820109606
2023-01-24 05:16:51.846743: step: 988/527, loss: 0.007457053754478693
2023-01-24 05:16:52.892972: step: 992/527, loss: 0.0038232351653277874
2023-01-24 05:16:53.949908: step: 996/527, loss: 0.009703759104013443
2023-01-24 05:16:55.000353: step: 1000/527, loss: 0.008962608873844147
2023-01-24 05:16:56.064813: step: 1004/527, loss: 0.004763863980770111
2023-01-24 05:16:57.119747: step: 1008/527, loss: 0.008955919183790684
2023-01-24 05:16:58.179188: step: 1012/527, loss: 0.03379448503255844
2023-01-24 05:16:59.213140: step: 1016/527, loss: 0.009278319776058197
2023-01-24 05:17:00.259871: step: 1020/527, loss: 0.003386962693184614
2023-01-24 05:17:01.317968: step: 1024/527, loss: 0.008770664222538471
2023-01-24 05:17:02.370469: step: 1028/527, loss: 0.008762028999626637
2023-01-24 05:17:03.424567: step: 1032/527, loss: 0.013162856921553612
2023-01-24 05:17:04.487310: step: 1036/527, loss: 0.040115103125572205
2023-01-24 05:17:05.530055: step: 1040/527, loss: 0.013916801661252975
2023-01-24 05:17:06.583799: step: 1044/527, loss: 0.005811354145407677
2023-01-24 05:17:07.662416: step: 1048/527, loss: 0.0283705722540617
2023-01-24 05:17:08.731514: step: 1052/527, loss: 0.008610613644123077
2023-01-24 05:17:09.789256: step: 1056/527, loss: 0.012159034609794617
2023-01-24 05:17:10.842529: step: 1060/527, loss: 0.007214654702693224
2023-01-24 05:17:11.891368: step: 1064/527, loss: 0.009670075960457325
2023-01-24 05:17:12.934419: step: 1068/527, loss: 0.020627478137612343
2023-01-24 05:17:13.997940: step: 1072/527, loss: 0.008537794463336468
2023-01-24 05:17:15.061762: step: 1076/527, loss: 0.004947997163981199
2023-01-24 05:17:16.119465: step: 1080/527, loss: 0.012593166902661324
2023-01-24 05:17:17.183000: step: 1084/527, loss: 0.03236313536763191
2023-01-24 05:17:18.228263: step: 1088/527, loss: 0.01142879854887724
2023-01-24 05:17:19.300503: step: 1092/527, loss: 0.009611567482352257
2023-01-24 05:17:20.354061: step: 1096/527, loss: 0.006485611200332642
2023-01-24 05:17:21.397365: step: 1100/527, loss: 0.0049271974712610245
2023-01-24 05:17:22.437072: step: 1104/527, loss: 0.054322656244039536
2023-01-24 05:17:23.498053: step: 1108/527, loss: 0.015809351578354836
2023-01-24 05:17:24.551198: step: 1112/527, loss: 0.008611029013991356
2023-01-24 05:17:25.597027: step: 1116/527, loss: 0.012601575814187527
2023-01-24 05:17:26.650572: step: 1120/527, loss: 0.006335206795483828
2023-01-24 05:17:27.717383: step: 1124/527, loss: 0.01283422764390707
2023-01-24 05:17:28.778402: step: 1128/527, loss: 0.025943251326680183
2023-01-24 05:17:29.843629: step: 1132/527, loss: 0.05394890159368515
2023-01-24 05:17:30.892811: step: 1136/527, loss: 0.0010803146287798882
2023-01-24 05:17:31.960714: step: 1140/527, loss: 0.021296994760632515
2023-01-24 05:17:33.027239: step: 1144/527, loss: 0.008542295545339584
2023-01-24 05:17:34.088564: step: 1148/527, loss: 0.008017108775675297
2023-01-24 05:17:35.161203: step: 1152/527, loss: 0.004137382842600346
2023-01-24 05:17:36.219067: step: 1156/527, loss: 0.010905577801167965
2023-01-24 05:17:37.266521: step: 1160/527, loss: 0.002994515234604478
2023-01-24 05:17:38.313246: step: 1164/527, loss: 0.010548352263867855
2023-01-24 05:17:39.361329: step: 1168/527, loss: 0.011764622293412685
2023-01-24 05:17:40.435096: step: 1172/527, loss: 0.008668174967169762
2023-01-24 05:17:41.477322: step: 1176/527, loss: 0.008785519748926163
2023-01-24 05:17:42.537971: step: 1180/527, loss: 0.007309382315725088
2023-01-24 05:17:43.580078: step: 1184/527, loss: 0.009179351851344109
2023-01-24 05:17:44.630314: step: 1188/527, loss: 0.024498607963323593
2023-01-24 05:17:45.676170: step: 1192/527, loss: 0.010385243222117424
2023-01-24 05:17:46.723479: step: 1196/527, loss: 0.007233790121972561
2023-01-24 05:17:47.779639: step: 1200/527, loss: 0.012378869578242302
2023-01-24 05:17:48.844747: step: 1204/527, loss: 0.006361040752381086
2023-01-24 05:17:49.902653: step: 1208/527, loss: 0.053797416388988495
2023-01-24 05:17:50.956052: step: 1212/527, loss: 0.007483770605176687
2023-01-24 05:17:52.020651: step: 1216/527, loss: 0.023426569998264313
2023-01-24 05:17:53.078863: step: 1220/527, loss: 0.06588196754455566
2023-01-24 05:17:54.125846: step: 1224/527, loss: 0.03428163751959801
2023-01-24 05:17:55.183536: step: 1228/527, loss: 0.007833165116608143
2023-01-24 05:17:56.251188: step: 1232/527, loss: 0.03375722095370293
2023-01-24 05:17:57.289507: step: 1236/527, loss: 0.007485273759812117
2023-01-24 05:17:58.326872: step: 1240/527, loss: 0.030452409759163857
2023-01-24 05:17:59.362130: step: 1244/527, loss: 0.022304274141788483
2023-01-24 05:18:00.401538: step: 1248/527, loss: 0.011296301148831844
2023-01-24 05:18:01.434505: step: 1252/527, loss: 0.031903501600027084
2023-01-24 05:18:02.495041: step: 1256/527, loss: 0.004422258585691452
2023-01-24 05:18:03.550959: step: 1260/527, loss: 0.04615252465009689
2023-01-24 05:18:04.593099: step: 1264/527, loss: 0.017315508797764778
2023-01-24 05:18:05.647349: step: 1268/527, loss: 0.01905614510178566
2023-01-24 05:18:06.697177: step: 1272/527, loss: 0.03857870772480965
2023-01-24 05:18:07.751316: step: 1276/527, loss: 0.0055539365857839584
2023-01-24 05:18:08.793933: step: 1280/527, loss: 0.010360308922827244
2023-01-24 05:18:09.841594: step: 1284/527, loss: 0.011691239662468433
2023-01-24 05:18:10.888345: step: 1288/527, loss: 0.004534219857305288
2023-01-24 05:18:11.931840: step: 1292/527, loss: 0.011701731011271477
2023-01-24 05:18:12.989095: step: 1296/527, loss: 0.016721613705158234
2023-01-24 05:18:14.036639: step: 1300/527, loss: 0.004042757209390402
2023-01-24 05:18:15.107476: step: 1304/527, loss: 0.010980832390487194
2023-01-24 05:18:16.152372: step: 1308/527, loss: 0.004228595644235611
2023-01-24 05:18:17.196266: step: 1312/527, loss: 0.022516494616866112
2023-01-24 05:18:18.248211: step: 1316/527, loss: 0.02876768447458744
2023-01-24 05:18:19.305329: step: 1320/527, loss: 0.01709855906665325
2023-01-24 05:18:20.365741: step: 1324/527, loss: 0.011386437341570854
2023-01-24 05:18:21.408037: step: 1328/527, loss: 0.007310559507459402
2023-01-24 05:18:22.428344: step: 1332/527, loss: 0.01878192462027073
2023-01-24 05:18:23.497607: step: 1336/527, loss: 0.020790914073586464
2023-01-24 05:18:24.556107: step: 1340/527, loss: 0.006903341971337795
2023-01-24 05:18:25.608328: step: 1344/527, loss: 0.002603257307782769
2023-01-24 05:18:26.665072: step: 1348/527, loss: 0.004824474919587374
2023-01-24 05:18:27.716312: step: 1352/527, loss: 0.009527553804218769
2023-01-24 05:18:28.767216: step: 1356/527, loss: 0.0046661836095154285
2023-01-24 05:18:29.817551: step: 1360/527, loss: 0.0019602004904299974
2023-01-24 05:18:30.874549: step: 1364/527, loss: 0.005691582802683115
2023-01-24 05:18:31.922287: step: 1368/527, loss: 0.08224951475858688
2023-01-24 05:18:32.979906: step: 1372/527, loss: 0.007733750622719526
2023-01-24 05:18:34.031140: step: 1376/527, loss: 0.0047766296193003654
2023-01-24 05:18:35.096160: step: 1380/527, loss: 0.006940816529095173
2023-01-24 05:18:36.149407: step: 1384/527, loss: 0.012327251955866814
2023-01-24 05:18:37.213148: step: 1388/527, loss: 0.0059159486554563046
2023-01-24 05:18:38.265137: step: 1392/527, loss: 0.005582594778388739
2023-01-24 05:18:39.317851: step: 1396/527, loss: 0.010335014201700687
2023-01-24 05:18:40.369055: step: 1400/527, loss: 0.01100069098174572
2023-01-24 05:18:41.419888: step: 1404/527, loss: 0.014025130309164524
2023-01-24 05:18:42.484621: step: 1408/527, loss: 0.024998778477311134
2023-01-24 05:18:43.534361: step: 1412/527, loss: 0.005577197764068842
2023-01-24 05:18:44.578076: step: 1416/527, loss: 0.014429930597543716
2023-01-24 05:18:45.642148: step: 1420/527, loss: 0.017160825431346893
2023-01-24 05:18:46.689987: step: 1424/527, loss: 0.016941893845796585
2023-01-24 05:18:47.746466: step: 1428/527, loss: 0.012483743950724602
2023-01-24 05:18:48.798271: step: 1432/527, loss: 0.003954943735152483
2023-01-24 05:18:49.840169: step: 1436/527, loss: 0.009415700100362301
2023-01-24 05:18:50.894375: step: 1440/527, loss: 0.009498503059148788
2023-01-24 05:18:51.939278: step: 1444/527, loss: 0.010833312757313251
2023-01-24 05:18:53.007682: step: 1448/527, loss: 0.0066607436165213585
2023-01-24 05:18:54.059429: step: 1452/527, loss: 0.006890186574310064
2023-01-24 05:18:55.117925: step: 1456/527, loss: 0.0044693974778056145
2023-01-24 05:18:56.160078: step: 1460/527, loss: 0.0029753760900348425
2023-01-24 05:18:57.206533: step: 1464/527, loss: 0.034443605691194534
2023-01-24 05:18:58.253934: step: 1468/527, loss: 0.00898395199328661
2023-01-24 05:18:59.295702: step: 1472/527, loss: 0.008948897942900658
2023-01-24 05:19:00.363644: step: 1476/527, loss: 0.012350128963589668
2023-01-24 05:19:01.439131: step: 1480/527, loss: 0.03569713234901428
2023-01-24 05:19:02.487597: step: 1484/527, loss: 0.005233981646597385
2023-01-24 05:19:03.535596: step: 1488/527, loss: 0.015533572062849998
2023-01-24 05:19:04.603159: step: 1492/527, loss: 0.008105774410068989
2023-01-24 05:19:05.649037: step: 1496/527, loss: 0.0019224288407713175
2023-01-24 05:19:06.699475: step: 1500/527, loss: 0.012415507808327675
2023-01-24 05:19:07.750578: step: 1504/527, loss: 0.0042087240144610405
2023-01-24 05:19:08.803609: step: 1508/527, loss: 0.012882072478532791
2023-01-24 05:19:09.854949: step: 1512/527, loss: 0.012384502217173576
2023-01-24 05:19:10.907829: step: 1516/527, loss: 0.005620758514851332
2023-01-24 05:19:11.953480: step: 1520/527, loss: 0.008363313972949982
2023-01-24 05:19:13.000296: step: 1524/527, loss: 0.008510236628353596
2023-01-24 05:19:14.043104: step: 1528/527, loss: 0.009194700978696346
2023-01-24 05:19:15.107198: step: 1532/527, loss: 0.005406866781413555
2023-01-24 05:19:16.164068: step: 1536/527, loss: 0.005108795594424009
2023-01-24 05:19:17.215118: step: 1540/527, loss: 0.02588803693652153
2023-01-24 05:19:18.247633: step: 1544/527, loss: 0.0032069990411400795
2023-01-24 05:19:19.319409: step: 1548/527, loss: 0.018077164888381958
2023-01-24 05:19:20.368424: step: 1552/527, loss: 0.007549144793301821
2023-01-24 05:19:21.414278: step: 1556/527, loss: 0.006199760362505913
2023-01-24 05:19:22.467936: step: 1560/527, loss: 0.030280020087957382
2023-01-24 05:19:23.514415: step: 1564/527, loss: 0.021325180307030678
2023-01-24 05:19:24.557701: step: 1568/527, loss: 0.008346924558281898
2023-01-24 05:19:25.607454: step: 1572/527, loss: 0.004945177119225264
2023-01-24 05:19:26.660934: step: 1576/527, loss: 0.004650773946195841
2023-01-24 05:19:27.705282: step: 1580/527, loss: 0.03521714359521866
2023-01-24 05:19:28.764926: step: 1584/527, loss: 0.004980199970304966
2023-01-24 05:19:29.820426: step: 1588/527, loss: 0.011413614265620708
2023-01-24 05:19:30.862988: step: 1592/527, loss: 0.01686055399477482
2023-01-24 05:19:31.918237: step: 1596/527, loss: 0.03376294672489166
2023-01-24 05:19:32.962717: step: 1600/527, loss: 0.008297530002892017
2023-01-24 05:19:34.013584: step: 1604/527, loss: 0.023515764623880386
2023-01-24 05:19:35.057807: step: 1608/527, loss: 0.007583301048725843
2023-01-24 05:19:36.097185: step: 1612/527, loss: 0.0026325020007789135
2023-01-24 05:19:37.141073: step: 1616/527, loss: 0.0022506117820739746
2023-01-24 05:19:38.197579: step: 1620/527, loss: 0.008329613134264946
2023-01-24 05:19:39.267495: step: 1624/527, loss: 0.00849849358201027
2023-01-24 05:19:40.338137: step: 1628/527, loss: 0.008249761536717415
2023-01-24 05:19:41.381874: step: 1632/527, loss: 0.060595810413360596
2023-01-24 05:19:42.441946: step: 1636/527, loss: 0.006368107162415981
2023-01-24 05:19:43.508061: step: 1640/527, loss: 0.010098547674715519
2023-01-24 05:19:44.566431: step: 1644/527, loss: 0.012657450512051582
2023-01-24 05:19:45.618502: step: 1648/527, loss: 0.027670621871948242
2023-01-24 05:19:46.675785: step: 1652/527, loss: 0.015922911465168
2023-01-24 05:19:47.723635: step: 1656/527, loss: 0.010136590339243412
2023-01-24 05:19:48.766111: step: 1660/527, loss: 0.029393425211310387
2023-01-24 05:19:49.822160: step: 1664/527, loss: 0.025644952431321144
2023-01-24 05:19:50.874145: step: 1668/527, loss: 0.009974253363907337
2023-01-24 05:19:51.925020: step: 1672/527, loss: 0.05640428513288498
2023-01-24 05:19:52.969552: step: 1676/527, loss: 0.004832874517887831
2023-01-24 05:19:54.013579: step: 1680/527, loss: 0.007441962603479624
2023-01-24 05:19:55.062171: step: 1684/527, loss: 0.018733033910393715
2023-01-24 05:19:56.107277: step: 1688/527, loss: 0.0010351308155804873
2023-01-24 05:19:57.153196: step: 1692/527, loss: 0.00944183487445116
2023-01-24 05:19:58.224143: step: 1696/527, loss: 0.006964751984924078
2023-01-24 05:19:59.275994: step: 1700/527, loss: 0.005171839613467455
2023-01-24 05:20:00.330947: step: 1704/527, loss: 0.01986236497759819
2023-01-24 05:20:01.394214: step: 1708/527, loss: 0.009714815765619278
2023-01-24 05:20:02.448039: step: 1712/527, loss: 0.010378447361290455
2023-01-24 05:20:03.488965: step: 1716/527, loss: 0.00603974936529994
2023-01-24 05:20:04.534250: step: 1720/527, loss: 0.02692074328660965
2023-01-24 05:20:05.579084: step: 1724/527, loss: 0.012999355792999268
2023-01-24 05:20:06.629081: step: 1728/527, loss: 0.009751521982252598
2023-01-24 05:20:07.671474: step: 1732/527, loss: 0.0057746293023228645
2023-01-24 05:20:08.713130: step: 1736/527, loss: 0.011407960206270218
2023-01-24 05:20:09.763987: step: 1740/527, loss: 0.02211788110435009
2023-01-24 05:20:10.821401: step: 1744/527, loss: 0.009267452172935009
2023-01-24 05:20:11.878151: step: 1748/527, loss: 0.0103457598015666
2023-01-24 05:20:12.947984: step: 1752/527, loss: 0.004588868468999863
2023-01-24 05:20:13.996797: step: 1756/527, loss: 0.00400989456102252
2023-01-24 05:20:15.036656: step: 1760/527, loss: 0.015373006463050842
2023-01-24 05:20:16.085500: step: 1764/527, loss: 0.004751627333462238
2023-01-24 05:20:17.144893: step: 1768/527, loss: 0.009738551452755928
2023-01-24 05:20:18.195265: step: 1772/527, loss: 0.005140881985425949
2023-01-24 05:20:19.259993: step: 1776/527, loss: 0.002203483134508133
2023-01-24 05:20:20.318079: step: 1780/527, loss: 0.006194181274622679
2023-01-24 05:20:21.380563: step: 1784/527, loss: 0.006157819181680679
2023-01-24 05:20:22.428367: step: 1788/527, loss: 0.003330419072881341
2023-01-24 05:20:23.521807: step: 1792/527, loss: 0.011604590341448784
2023-01-24 05:20:24.567912: step: 1796/527, loss: 0.03503284603357315
2023-01-24 05:20:25.624851: step: 1800/527, loss: 0.00614347355440259
2023-01-24 05:20:26.680504: step: 1804/527, loss: 0.01627521961927414
2023-01-24 05:20:27.715227: step: 1808/527, loss: 0.015544203110039234
2023-01-24 05:20:28.782044: step: 1812/527, loss: 0.029974795877933502
2023-01-24 05:20:29.835605: step: 1816/527, loss: 0.015867266803979874
2023-01-24 05:20:30.886509: step: 1820/527, loss: 0.013727860525250435
2023-01-24 05:20:31.942673: step: 1824/527, loss: 0.0074148159474134445
2023-01-24 05:20:32.991995: step: 1828/527, loss: 0.031863220036029816
2023-01-24 05:20:34.041303: step: 1832/527, loss: 0.007135330233722925
2023-01-24 05:20:35.094972: step: 1836/527, loss: 0.0053549036383628845
2023-01-24 05:20:36.156748: step: 1840/527, loss: 0.0060627879574894905
2023-01-24 05:20:37.197429: step: 1844/527, loss: 0.01659911684691906
2023-01-24 05:20:38.239697: step: 1848/527, loss: 0.006961342878639698
2023-01-24 05:20:39.292962: step: 1852/527, loss: 0.00940422248095274
2023-01-24 05:20:40.343321: step: 1856/527, loss: 0.02290002815425396
2023-01-24 05:20:41.398241: step: 1860/527, loss: 0.014562358148396015
2023-01-24 05:20:42.435850: step: 1864/527, loss: 0.0039009125903248787
2023-01-24 05:20:43.510694: step: 1868/527, loss: 0.010911677032709122
2023-01-24 05:20:44.550555: step: 1872/527, loss: 0.0071758064441382885
2023-01-24 05:20:45.609034: step: 1876/527, loss: 0.020267516374588013
2023-01-24 05:20:46.665456: step: 1880/527, loss: 0.0289051104336977
2023-01-24 05:20:47.728951: step: 1884/527, loss: 0.0031412984244525433
2023-01-24 05:20:48.784147: step: 1888/527, loss: 0.003647695994004607
2023-01-24 05:20:49.835623: step: 1892/527, loss: 0.00880490243434906
2023-01-24 05:20:50.878179: step: 1896/527, loss: 0.002776987385004759
2023-01-24 05:20:51.927534: step: 1900/527, loss: 0.008150040172040462
2023-01-24 05:20:52.977068: step: 1904/527, loss: 0.005806076806038618
2023-01-24 05:20:54.068842: step: 1908/527, loss: 0.005653920117765665
2023-01-24 05:20:55.106912: step: 1912/527, loss: 0.013935298658907413
2023-01-24 05:20:56.152274: step: 1916/527, loss: 0.010857168585062027
2023-01-24 05:20:57.213123: step: 1920/527, loss: 0.009352513588964939
2023-01-24 05:20:58.260808: step: 1924/527, loss: 0.03028571791946888
2023-01-24 05:20:59.314173: step: 1928/527, loss: 0.006492685992270708
2023-01-24 05:21:00.364643: step: 1932/527, loss: 0.07627073675394058
2023-01-24 05:21:01.412235: step: 1936/527, loss: 0.0060774837620556355
2023-01-24 05:21:02.477139: step: 1940/527, loss: 0.02620861679315567
2023-01-24 05:21:03.539192: step: 1944/527, loss: 0.017924658954143524
2023-01-24 05:21:04.596604: step: 1948/527, loss: 0.027919495478272438
2023-01-24 05:21:05.638035: step: 1952/527, loss: 0.004058958496898413
2023-01-24 05:21:06.695658: step: 1956/527, loss: 0.008040946908295155
2023-01-24 05:21:07.745617: step: 1960/527, loss: 0.012648562900722027
2023-01-24 05:21:08.790913: step: 1964/527, loss: 0.017326952889561653
2023-01-24 05:21:09.852519: step: 1968/527, loss: 0.031215587630867958
2023-01-24 05:21:10.914795: step: 1972/527, loss: 0.02237948402762413
2023-01-24 05:21:11.972057: step: 1976/527, loss: 0.006214444525539875
2023-01-24 05:21:13.022252: step: 1980/527, loss: 0.02078646421432495
2023-01-24 05:21:14.084192: step: 1984/527, loss: 0.012756140902638435
2023-01-24 05:21:15.144696: step: 1988/527, loss: 0.005657571833580732
2023-01-24 05:21:16.197036: step: 1992/527, loss: 0.013083589263260365
2023-01-24 05:21:17.243539: step: 1996/527, loss: 0.011768629774451256
2023-01-24 05:21:18.299346: step: 2000/527, loss: 0.007825766690075397
2023-01-24 05:21:19.351400: step: 2004/527, loss: 0.03417177125811577
2023-01-24 05:21:20.409269: step: 2008/527, loss: 0.027935318648815155
2023-01-24 05:21:21.448259: step: 2012/527, loss: 0.02431550808250904
2023-01-24 05:21:22.515874: step: 2016/527, loss: 0.03146444633603096
2023-01-24 05:21:23.576036: step: 2020/527, loss: 0.0378304049372673
2023-01-24 05:21:24.640598: step: 2024/527, loss: 0.005935895722359419
2023-01-24 05:21:25.693497: step: 2028/527, loss: 0.0038613921497017145
2023-01-24 05:21:26.759745: step: 2032/527, loss: 0.008751094341278076
2023-01-24 05:21:27.821395: step: 2036/527, loss: 0.030986562371253967
2023-01-24 05:21:28.874414: step: 2040/527, loss: 0.010361522436141968
2023-01-24 05:21:29.934618: step: 2044/527, loss: 0.004071739036589861
2023-01-24 05:21:31.003524: step: 2048/527, loss: 0.011194843798875809
2023-01-24 05:21:32.068265: step: 2052/527, loss: 0.017472080886363983
2023-01-24 05:21:33.116208: step: 2056/527, loss: 0.003715306054800749
2023-01-24 05:21:34.175086: step: 2060/527, loss: 0.006260259076952934
2023-01-24 05:21:35.221106: step: 2064/527, loss: 0.0017354401061311364
2023-01-24 05:21:36.299724: step: 2068/527, loss: 0.0698724240064621
2023-01-24 05:21:37.364726: step: 2072/527, loss: 0.004602520726621151
2023-01-24 05:21:38.420349: step: 2076/527, loss: 0.009425695054233074
2023-01-24 05:21:39.476985: step: 2080/527, loss: 0.03477642685174942
2023-01-24 05:21:40.526947: step: 2084/527, loss: 0.01011382881551981
2023-01-24 05:21:41.564243: step: 2088/527, loss: 0.018314184620976448
2023-01-24 05:21:42.612429: step: 2092/527, loss: 0.010672174394130707
2023-01-24 05:21:43.675323: step: 2096/527, loss: 0.012546362355351448
2023-01-24 05:21:44.748378: step: 2100/527, loss: 0.0014359191991388798
2023-01-24 05:21:45.811166: step: 2104/527, loss: 0.02782692387700081
2023-01-24 05:21:46.874368: step: 2108/527, loss: 0.019237518310546875
==================================================
Loss: 0.015
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3451288636635917, 'r': 0.3215526984038397, 'f1': 0.332923913671559}, 'combined': 0.24531235744220134, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3699546224171736, 'r': 0.2875556383333486, 'f1': 0.323592022676914}, 'combined': 0.20709889451322494, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3577601410934744, 'r': 0.32992680943345076, 'f1': 0.3432802143562262}, 'combined': 0.2529433158414298, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37058925398176007, 'r': 0.30125102844112195, 'f1': 0.33234206644656844}, 'combined': 0.21269892252580377, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3451288636635917, 'r': 0.3215526984038397, 'f1': 0.332923913671559}, 'combined': 0.24531235744220134, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3699546224171736, 'r': 0.2875556383333486, 'f1': 0.323592022676914}, 'combined': 0.20709889451322494, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:24:38.282471: step: 4/527, loss: 0.0019472651183605194
2023-01-24 05:24:39.333483: step: 8/527, loss: 0.00045936647802591324
2023-01-24 05:24:40.380428: step: 12/527, loss: 0.05795268714427948
2023-01-24 05:24:41.417761: step: 16/527, loss: 0.01626136526465416
2023-01-24 05:24:42.460120: step: 20/527, loss: 0.003307248931378126
2023-01-24 05:24:43.514986: step: 24/527, loss: 0.012959376908838749
2023-01-24 05:24:44.548734: step: 28/527, loss: 0.04898662492632866
2023-01-24 05:24:45.585171: step: 32/527, loss: 0.0029615783132612705
2023-01-24 05:24:46.637145: step: 36/527, loss: 0.006359742023050785
2023-01-24 05:24:47.677674: step: 40/527, loss: 0.006178473122417927
2023-01-24 05:24:48.719503: step: 44/527, loss: 0.008812231943011284
2023-01-24 05:24:49.795475: step: 48/527, loss: 0.005887409206479788
2023-01-24 05:24:50.856602: step: 52/527, loss: 0.016075002029538155
2023-01-24 05:24:51.903346: step: 56/527, loss: 0.005801203195005655
2023-01-24 05:24:52.950938: step: 60/527, loss: 0.03931571543216705
2023-01-24 05:24:53.996428: step: 64/527, loss: 0.035839393734931946
2023-01-24 05:24:55.058396: step: 68/527, loss: 0.007224041037261486
2023-01-24 05:24:56.098385: step: 72/527, loss: 0.003933871164917946
2023-01-24 05:24:57.144292: step: 76/527, loss: 0.00912049226462841
2023-01-24 05:24:58.211422: step: 80/527, loss: 0.017245899885892868
2023-01-24 05:24:59.250988: step: 84/527, loss: 0.01848674565553665
2023-01-24 05:25:00.292802: step: 88/527, loss: 0.001915311673656106
2023-01-24 05:25:01.349978: step: 92/527, loss: 0.06305068731307983
2023-01-24 05:25:02.403591: step: 96/527, loss: 0.009344151243567467
2023-01-24 05:25:03.450021: step: 100/527, loss: 0.019177034497261047
2023-01-24 05:25:04.500754: step: 104/527, loss: 0.00846317782998085
2023-01-24 05:25:05.546484: step: 108/527, loss: 0.0064727808348834515
2023-01-24 05:25:06.608341: step: 112/527, loss: 0.010484704747796059
2023-01-24 05:25:07.662332: step: 116/527, loss: 0.01720639131963253
2023-01-24 05:25:08.715374: step: 120/527, loss: 0.00674505066126585
2023-01-24 05:25:09.766666: step: 124/527, loss: 0.008513525128364563
2023-01-24 05:25:10.814317: step: 128/527, loss: 0.011099004186689854
2023-01-24 05:25:11.860182: step: 132/527, loss: 0.0030008687172085047
2023-01-24 05:25:12.906411: step: 136/527, loss: 0.01110610831528902
2023-01-24 05:25:13.963404: step: 140/527, loss: 0.006258530542254448
2023-01-24 05:25:15.009796: step: 144/527, loss: 0.005188685841858387
2023-01-24 05:25:16.065537: step: 148/527, loss: 0.00519842654466629
2023-01-24 05:25:17.115812: step: 152/527, loss: 0.011154260486364365
2023-01-24 05:25:18.169517: step: 156/527, loss: 0.021539486944675446
2023-01-24 05:25:19.255280: step: 160/527, loss: 0.010539108887314796
2023-01-24 05:25:20.301977: step: 164/527, loss: 0.017954345792531967
2023-01-24 05:25:21.367704: step: 168/527, loss: 0.040802549570798874
2023-01-24 05:25:22.414171: step: 172/527, loss: 0.00432178657501936
2023-01-24 05:25:23.452079: step: 176/527, loss: 0.0024467159528285265
2023-01-24 05:25:24.492368: step: 180/527, loss: 0.004625953733921051
2023-01-24 05:25:25.543978: step: 184/527, loss: 0.03450179845094681
2023-01-24 05:25:26.596080: step: 188/527, loss: 0.019679058343172073
2023-01-24 05:25:27.646500: step: 192/527, loss: 0.003656997112557292
2023-01-24 05:25:28.682045: step: 196/527, loss: 0.01148401852697134
2023-01-24 05:25:29.752082: step: 200/527, loss: 0.03636989742517471
2023-01-24 05:25:30.787522: step: 204/527, loss: 0.007308941334486008
2023-01-24 05:25:31.830132: step: 208/527, loss: 0.0032253314275294542
2023-01-24 05:25:32.881507: step: 212/527, loss: 0.02569805644452572
2023-01-24 05:25:33.927570: step: 216/527, loss: 0.04698735848069191
2023-01-24 05:25:35.005095: step: 220/527, loss: 0.011449437588453293
2023-01-24 05:25:36.051956: step: 224/527, loss: 0.0006532570696435869
2023-01-24 05:25:37.105238: step: 228/527, loss: 0.010402513667941093
2023-01-24 05:25:38.164723: step: 232/527, loss: 0.010985426604747772
2023-01-24 05:25:39.203417: step: 236/527, loss: 0.0016882745549082756
2023-01-24 05:25:40.256646: step: 240/527, loss: 0.011718044988811016
2023-01-24 05:25:41.283876: step: 244/527, loss: 0.013160007074475288
2023-01-24 05:25:42.333722: step: 248/527, loss: 0.00553869316354394
2023-01-24 05:25:43.385421: step: 252/527, loss: 0.010326913557946682
2023-01-24 05:25:44.446136: step: 256/527, loss: 0.006913777906447649
2023-01-24 05:25:45.502910: step: 260/527, loss: 0.0071021574549376965
2023-01-24 05:25:46.544369: step: 264/527, loss: 0.007434515282511711
2023-01-24 05:25:47.598083: step: 268/527, loss: 0.03991125524044037
2023-01-24 05:25:48.652021: step: 272/527, loss: 0.013365563936531544
2023-01-24 05:25:49.699394: step: 276/527, loss: 0.023147787898778915
2023-01-24 05:25:50.747613: step: 280/527, loss: 0.011969683691859245
2023-01-24 05:25:51.793703: step: 284/527, loss: 0.0029195528477430344
2023-01-24 05:25:52.833940: step: 288/527, loss: 0.007126101292669773
2023-01-24 05:25:53.875986: step: 292/527, loss: 0.009884514845907688
2023-01-24 05:25:54.932102: step: 296/527, loss: 0.006057575345039368
2023-01-24 05:25:55.988205: step: 300/527, loss: 0.005265767220407724
2023-01-24 05:25:57.044486: step: 304/527, loss: 0.010103418491780758
2023-01-24 05:25:58.092633: step: 308/527, loss: 0.006355458404868841
2023-01-24 05:25:59.137958: step: 312/527, loss: 0.007941097021102905
2023-01-24 05:26:00.195229: step: 316/527, loss: 0.005205498076975346
2023-01-24 05:26:01.246680: step: 320/527, loss: 0.003815067233517766
2023-01-24 05:26:02.324282: step: 324/527, loss: 0.03367021679878235
2023-01-24 05:26:03.368014: step: 328/527, loss: 0.012014445848762989
2023-01-24 05:26:04.439718: step: 332/527, loss: 0.015222628600895405
2023-01-24 05:26:05.490867: step: 336/527, loss: 0.03171848878264427
2023-01-24 05:26:06.557681: step: 340/527, loss: 0.010363505221903324
2023-01-24 05:26:07.615934: step: 344/527, loss: 0.007276894990354776
2023-01-24 05:26:08.669355: step: 348/527, loss: 0.0567045696079731
2023-01-24 05:26:09.722684: step: 352/527, loss: 0.026962192729115486
2023-01-24 05:26:10.761571: step: 356/527, loss: 0.02342049777507782
2023-01-24 05:26:11.819677: step: 360/527, loss: 0.005566221196204424
2023-01-24 05:26:12.879648: step: 364/527, loss: 0.02161421813070774
2023-01-24 05:26:13.952333: step: 368/527, loss: 0.007915153168141842
2023-01-24 05:26:15.004581: step: 372/527, loss: 0.004455730319023132
2023-01-24 05:26:16.069063: step: 376/527, loss: 0.009517781436443329
2023-01-24 05:26:17.124837: step: 380/527, loss: 0.006966050714254379
2023-01-24 05:26:18.170697: step: 384/527, loss: 0.004054506774991751
2023-01-24 05:26:19.255117: step: 388/527, loss: 0.007609184365719557
2023-01-24 05:26:20.307282: step: 392/527, loss: 0.012637414038181305
2023-01-24 05:26:21.377547: step: 396/527, loss: 0.021564841270446777
2023-01-24 05:26:22.416332: step: 400/527, loss: 0.00016283965669572353
2023-01-24 05:26:23.471568: step: 404/527, loss: 0.006162731908261776
2023-01-24 05:26:24.543273: step: 408/527, loss: 0.06655421108007431
2023-01-24 05:26:25.606767: step: 412/527, loss: 0.0010615808423608541
2023-01-24 05:26:26.649358: step: 416/527, loss: 0.0028288750909268856
2023-01-24 05:26:27.711676: step: 420/527, loss: 0.004220309667289257
2023-01-24 05:26:28.759649: step: 424/527, loss: 0.021024566143751144
2023-01-24 05:26:29.811087: step: 428/527, loss: 0.01765807531774044
2023-01-24 05:26:30.867917: step: 432/527, loss: 0.014151964336633682
2023-01-24 05:26:31.926184: step: 436/527, loss: 0.006327706854790449
2023-01-24 05:26:32.988754: step: 440/527, loss: 0.00396690284833312
2023-01-24 05:26:34.051957: step: 444/527, loss: 0.026631010696291924
2023-01-24 05:26:35.108424: step: 448/527, loss: 0.011762662790715694
2023-01-24 05:26:36.163100: step: 452/527, loss: 0.01275633554905653
2023-01-24 05:26:37.231558: step: 456/527, loss: 0.005071002058684826
2023-01-24 05:26:38.280154: step: 460/527, loss: 0.016328396275639534
2023-01-24 05:26:39.312778: step: 464/527, loss: 0.012322410941123962
2023-01-24 05:26:40.369810: step: 468/527, loss: 0.006799472030252218
2023-01-24 05:26:41.433973: step: 472/527, loss: 0.0020863860845565796
2023-01-24 05:26:42.499136: step: 476/527, loss: 0.009194653481245041
2023-01-24 05:26:43.535340: step: 480/527, loss: 0.011204421520233154
2023-01-24 05:26:44.579630: step: 484/527, loss: 0.031243499368429184
2023-01-24 05:26:45.647195: step: 488/527, loss: 0.028876738622784615
2023-01-24 05:26:46.708302: step: 492/527, loss: 0.020245103165507317
2023-01-24 05:26:47.767093: step: 496/527, loss: 0.009308438748121262
2023-01-24 05:26:48.828079: step: 500/527, loss: 0.004317193757742643
2023-01-24 05:26:49.881115: step: 504/527, loss: 0.007558333687484264
2023-01-24 05:26:50.910562: step: 508/527, loss: 0.006202024407684803
2023-01-24 05:26:51.963842: step: 512/527, loss: 0.00624776491895318
2023-01-24 05:26:53.025702: step: 516/527, loss: 0.003422696143388748
2023-01-24 05:26:54.088708: step: 520/527, loss: 0.008958730846643448
2023-01-24 05:26:55.129505: step: 524/527, loss: 0.008507025428116322
2023-01-24 05:26:56.190569: step: 528/527, loss: 0.007898330688476562
2023-01-24 05:26:57.239383: step: 532/527, loss: 0.006204289849847555
2023-01-24 05:26:58.278389: step: 536/527, loss: 9.811071504373103e-05
2023-01-24 05:26:59.323435: step: 540/527, loss: 0.001846045721322298
2023-01-24 05:27:00.368306: step: 544/527, loss: 0.005641768220812082
2023-01-24 05:27:01.412649: step: 548/527, loss: 0.0037336130626499653
2023-01-24 05:27:02.458370: step: 552/527, loss: 0.00901532731950283
2023-01-24 05:27:03.519144: step: 556/527, loss: 0.005902671720832586
2023-01-24 05:27:04.579053: step: 560/527, loss: 0.06052519008517265
2023-01-24 05:27:05.626117: step: 564/527, loss: 0.027774371206760406
2023-01-24 05:27:06.687127: step: 568/527, loss: 0.005201473832130432
2023-01-24 05:27:07.731117: step: 572/527, loss: 0.02104785107076168
2023-01-24 05:27:08.779242: step: 576/527, loss: 0.00717878108844161
2023-01-24 05:27:09.829515: step: 580/527, loss: 0.04445670545101166
2023-01-24 05:27:10.888527: step: 584/527, loss: 0.008279498666524887
2023-01-24 05:27:11.942491: step: 588/527, loss: 0.004925409331917763
2023-01-24 05:27:13.015887: step: 592/527, loss: 0.009139998815953732
2023-01-24 05:27:14.067510: step: 596/527, loss: 0.037103522568941116
2023-01-24 05:27:15.122977: step: 600/527, loss: 0.012650898657739162
2023-01-24 05:27:16.174966: step: 604/527, loss: 0.023029830306768417
2023-01-24 05:27:17.220900: step: 608/527, loss: 0.06605393439531326
2023-01-24 05:27:18.275481: step: 612/527, loss: 0.004582384135574102
2023-01-24 05:27:19.354063: step: 616/527, loss: 0.014879208989441395
2023-01-24 05:27:20.390263: step: 620/527, loss: 0.004906008951365948
2023-01-24 05:27:21.450912: step: 624/527, loss: 0.028087178245186806
2023-01-24 05:27:22.506343: step: 628/527, loss: 0.01640423573553562
2023-01-24 05:27:23.560444: step: 632/527, loss: 0.009729445911943913
2023-01-24 05:27:24.595123: step: 636/527, loss: 0.009771459735929966
2023-01-24 05:27:25.638441: step: 640/527, loss: 0.017573563382029533
2023-01-24 05:27:26.694538: step: 644/527, loss: 0.005665437784045935
2023-01-24 05:27:27.745802: step: 648/527, loss: 0.04363008588552475
2023-01-24 05:27:28.797195: step: 652/527, loss: 0.0037811200600117445
2023-01-24 05:27:29.822219: step: 656/527, loss: 0.003920457325875759
2023-01-24 05:27:30.886180: step: 660/527, loss: 0.024555912241339684
2023-01-24 05:27:31.950785: step: 664/527, loss: 0.01844160072505474
2023-01-24 05:27:32.998225: step: 668/527, loss: 0.04845099523663521
2023-01-24 05:27:34.038229: step: 672/527, loss: 0.016640199348330498
2023-01-24 05:27:35.088911: step: 676/527, loss: 0.0036800731904804707
2023-01-24 05:27:36.153311: step: 680/527, loss: 0.04842953011393547
2023-01-24 05:27:37.216283: step: 684/527, loss: 0.009288104251027107
2023-01-24 05:27:38.266319: step: 688/527, loss: 0.007285847328603268
2023-01-24 05:27:39.320900: step: 692/527, loss: 0.006700329482555389
2023-01-24 05:27:40.377176: step: 696/527, loss: 0.00467517739161849
2023-01-24 05:27:41.426375: step: 700/527, loss: 0.0001013468427117914
2023-01-24 05:27:42.471065: step: 704/527, loss: 0.015326598659157753
2023-01-24 05:27:43.524486: step: 708/527, loss: 0.00843038596212864
2023-01-24 05:27:44.573885: step: 712/527, loss: 0.003256844822317362
2023-01-24 05:27:45.624756: step: 716/527, loss: 0.013553074561059475
2023-01-24 05:27:46.658289: step: 720/527, loss: 0.008905477821826935
2023-01-24 05:27:47.712328: step: 724/527, loss: 0.012882758863270283
2023-01-24 05:27:48.769679: step: 728/527, loss: 0.01840660721063614
2023-01-24 05:27:49.824543: step: 732/527, loss: 0.005589759908616543
2023-01-24 05:27:50.868984: step: 736/527, loss: 0.00702686095610261
2023-01-24 05:27:51.920688: step: 740/527, loss: 0.1297561228275299
2023-01-24 05:27:52.977735: step: 744/527, loss: 0.01522014383226633
2023-01-24 05:27:54.022380: step: 748/527, loss: 0.024061452597379684
2023-01-24 05:27:55.078019: step: 752/527, loss: 0.006916760932654142
2023-01-24 05:27:56.132721: step: 756/527, loss: 0.03815501183271408
2023-01-24 05:27:57.180651: step: 760/527, loss: 0.045862630009651184
2023-01-24 05:27:58.219747: step: 764/527, loss: 0.016699789091944695
2023-01-24 05:27:59.271480: step: 768/527, loss: 0.012677228078246117
2023-01-24 05:28:00.333558: step: 772/527, loss: 0.001255549374036491
2023-01-24 05:28:01.377863: step: 776/527, loss: 0.026327967643737793
2023-01-24 05:28:02.431291: step: 780/527, loss: 0.003769800765439868
2023-01-24 05:28:03.473805: step: 784/527, loss: 0.06169474869966507
2023-01-24 05:28:04.515125: step: 788/527, loss: 0.0110657112672925
2023-01-24 05:28:05.562315: step: 792/527, loss: 0.019507996737957
2023-01-24 05:28:06.613189: step: 796/527, loss: 0.04768926650285721
2023-01-24 05:28:07.669916: step: 800/527, loss: 0.004048857372254133
2023-01-24 05:28:08.711078: step: 804/527, loss: 0.01741715706884861
2023-01-24 05:28:09.769747: step: 808/527, loss: 0.009874519892036915
2023-01-24 05:28:10.834660: step: 812/527, loss: 0.022808825597167015
2023-01-24 05:28:11.902237: step: 816/527, loss: 0.004506480414420366
2023-01-24 05:28:12.974143: step: 820/527, loss: 0.023001598194241524
2023-01-24 05:28:14.027857: step: 824/527, loss: 0.0019482597708702087
2023-01-24 05:28:15.101851: step: 828/527, loss: 0.06149015575647354
2023-01-24 05:28:16.138583: step: 832/527, loss: 0.0024485127069056034
2023-01-24 05:28:17.191659: step: 836/527, loss: 0.009832807816565037
2023-01-24 05:28:18.246495: step: 840/527, loss: 0.00894632376730442
2023-01-24 05:28:19.304571: step: 844/527, loss: 0.005954229738563299
2023-01-24 05:28:20.371633: step: 848/527, loss: 0.002683592028915882
2023-01-24 05:28:21.427466: step: 852/527, loss: 0.0031669861637055874
2023-01-24 05:28:22.487524: step: 856/527, loss: 0.00842226855456829
2023-01-24 05:28:23.547842: step: 860/527, loss: 0.01319480873644352
2023-01-24 05:28:24.631336: step: 864/527, loss: 0.013089342042803764
2023-01-24 05:28:25.698540: step: 868/527, loss: 0.016493460163474083
2023-01-24 05:28:26.750272: step: 872/527, loss: 0.010519245639443398
2023-01-24 05:28:27.781304: step: 876/527, loss: 0.00758923776447773
2023-01-24 05:28:28.845470: step: 880/527, loss: 0.007590882480144501
2023-01-24 05:28:29.878530: step: 884/527, loss: 0.018082482740283012
2023-01-24 05:28:30.932200: step: 888/527, loss: 0.005745083559304476
2023-01-24 05:28:31.985507: step: 892/527, loss: 0.004090290050953627
2023-01-24 05:28:33.039024: step: 896/527, loss: 0.005211257375776768
2023-01-24 05:28:34.095617: step: 900/527, loss: 0.009369587525725365
2023-01-24 05:28:35.143069: step: 904/527, loss: 0.004668599460273981
2023-01-24 05:28:36.192295: step: 908/527, loss: 0.00914757139980793
2023-01-24 05:28:37.231548: step: 912/527, loss: 0.007890195585787296
2023-01-24 05:28:38.282430: step: 916/527, loss: 0.003551984904333949
2023-01-24 05:28:39.343131: step: 920/527, loss: 0.005148402415215969
2023-01-24 05:28:40.384138: step: 924/527, loss: 0.015609413385391235
2023-01-24 05:28:41.434875: step: 928/527, loss: 0.005506484303623438
2023-01-24 05:28:42.489536: step: 932/527, loss: 0.012508809566497803
2023-01-24 05:28:43.534754: step: 936/527, loss: 0.002940128790214658
2023-01-24 05:28:44.596392: step: 940/527, loss: 0.006656321696937084
2023-01-24 05:28:45.661622: step: 944/527, loss: 0.003383379429578781
2023-01-24 05:28:46.715334: step: 948/527, loss: 0.019145991653203964
2023-01-24 05:28:47.762077: step: 952/527, loss: 0.008929871954023838
2023-01-24 05:28:48.817821: step: 956/527, loss: 0.016706202179193497
2023-01-24 05:28:49.876894: step: 960/527, loss: 0.03805391117930412
2023-01-24 05:28:50.951491: step: 964/527, loss: 0.002713154535740614
2023-01-24 05:28:52.006347: step: 968/527, loss: 0.012656132690608501
2023-01-24 05:28:53.059417: step: 972/527, loss: 0.03401487320661545
2023-01-24 05:28:54.106719: step: 976/527, loss: 0.013186130672693253
2023-01-24 05:28:55.165863: step: 980/527, loss: 0.0037962726783007383
2023-01-24 05:28:56.203588: step: 984/527, loss: 0.012958310544490814
2023-01-24 05:28:57.263450: step: 988/527, loss: 0.0232698954641819
2023-01-24 05:28:58.313938: step: 992/527, loss: 0.0036712519358843565
2023-01-24 05:28:59.361527: step: 996/527, loss: 0.01900840364396572
2023-01-24 05:29:00.432928: step: 1000/527, loss: 0.00459720753133297
2023-01-24 05:29:01.478370: step: 1004/527, loss: 0.002389513188973069
2023-01-24 05:29:02.531238: step: 1008/527, loss: 0.0050201681442558765
2023-01-24 05:29:03.579094: step: 1012/527, loss: 0.016077689826488495
2023-01-24 05:29:04.634327: step: 1016/527, loss: 0.02259223908185959
2023-01-24 05:29:05.689501: step: 1020/527, loss: 0.023427749052643776
2023-01-24 05:29:06.747307: step: 1024/527, loss: 0.014956757426261902
2023-01-24 05:29:07.819405: step: 1028/527, loss: 0.02330690436065197
2023-01-24 05:29:08.879835: step: 1032/527, loss: 0.00952431745827198
2023-01-24 05:29:09.926817: step: 1036/527, loss: 0.009679542854428291
2023-01-24 05:29:10.967312: step: 1040/527, loss: 0.0
2023-01-24 05:29:12.032494: step: 1044/527, loss: 0.0035289146471768618
2023-01-24 05:29:13.078066: step: 1048/527, loss: 0.013830331154167652
2023-01-24 05:29:14.116510: step: 1052/527, loss: 0.0029604050796478987
2023-01-24 05:29:15.163078: step: 1056/527, loss: 0.009815986268222332
2023-01-24 05:29:16.212930: step: 1060/527, loss: 0.001073924358934164
2023-01-24 05:29:17.256560: step: 1064/527, loss: 0.004243234638124704
2023-01-24 05:29:18.282126: step: 1068/527, loss: 0.007456034421920776
2023-01-24 05:29:19.347418: step: 1072/527, loss: 0.006499788723886013
2023-01-24 05:29:20.397777: step: 1076/527, loss: 0.002173013985157013
2023-01-24 05:29:21.442384: step: 1080/527, loss: 0.004147028550505638
2023-01-24 05:29:22.495220: step: 1084/527, loss: 0.0065850671380758286
2023-01-24 05:29:23.540991: step: 1088/527, loss: 0.0026100939139723778
2023-01-24 05:29:24.601232: step: 1092/527, loss: 0.011555547825992107
2023-01-24 05:29:25.659929: step: 1096/527, loss: 0.003990706522017717
2023-01-24 05:29:26.716258: step: 1100/527, loss: 0.004512408282607794
2023-01-24 05:29:27.756447: step: 1104/527, loss: 0.0035088045988231897
2023-01-24 05:29:28.809571: step: 1108/527, loss: 0.002885064808651805
2023-01-24 05:29:29.851618: step: 1112/527, loss: 0.019411331042647362
2023-01-24 05:29:30.898604: step: 1116/527, loss: 0.00392560288310051
2023-01-24 05:29:31.980086: step: 1120/527, loss: 0.046864207834005356
2023-01-24 05:29:33.013697: step: 1124/527, loss: 0.0027047258336097
2023-01-24 05:29:34.057197: step: 1128/527, loss: 0.0007161131361499429
2023-01-24 05:29:35.099821: step: 1132/527, loss: 0.008406261913478374
2023-01-24 05:29:36.154063: step: 1136/527, loss: 0.01717405579984188
2023-01-24 05:29:37.218895: step: 1140/527, loss: 0.011404656805098057
2023-01-24 05:29:38.267011: step: 1144/527, loss: 0.004440920427441597
2023-01-24 05:29:39.323211: step: 1148/527, loss: 0.05285952240228653
2023-01-24 05:29:40.362809: step: 1152/527, loss: 0.008084303699433804
2023-01-24 05:29:41.418051: step: 1156/527, loss: 0.008709576912224293
2023-01-24 05:29:42.475713: step: 1160/527, loss: 0.006324164569377899
2023-01-24 05:29:43.520677: step: 1164/527, loss: 0.011261779814958572
2023-01-24 05:29:44.595355: step: 1168/527, loss: 0.03855516016483307
2023-01-24 05:29:45.650010: step: 1172/527, loss: 0.003255103714764118
2023-01-24 05:29:46.680789: step: 1176/527, loss: 0.003080525901168585
2023-01-24 05:29:47.747479: step: 1180/527, loss: 0.0041559552773833275
2023-01-24 05:29:48.786828: step: 1184/527, loss: 0.00935401488095522
2023-01-24 05:29:49.847941: step: 1188/527, loss: 0.003595223417505622
2023-01-24 05:29:50.904416: step: 1192/527, loss: 0.007169822230935097
2023-01-24 05:29:51.953448: step: 1196/527, loss: 0.031760334968566895
2023-01-24 05:29:53.014451: step: 1200/527, loss: 0.003564560553058982
2023-01-24 05:29:54.075638: step: 1204/527, loss: 0.011569914408028126
2023-01-24 05:29:55.129676: step: 1208/527, loss: 0.0045539080165326595
2023-01-24 05:29:56.168367: step: 1212/527, loss: 0.0023483119439333677
2023-01-24 05:29:57.213991: step: 1216/527, loss: 0.03838162496685982
2023-01-24 05:29:58.264082: step: 1220/527, loss: 0.009832527488470078
2023-01-24 05:29:59.300581: step: 1224/527, loss: 0.0030852321069687605
2023-01-24 05:30:00.371979: step: 1228/527, loss: 0.004961112514138222
2023-01-24 05:30:01.420900: step: 1232/527, loss: 0.0038893776945769787
2023-01-24 05:30:02.465255: step: 1236/527, loss: 0.061964794993400574
2023-01-24 05:30:03.511325: step: 1240/527, loss: 0.0016118728090077639
2023-01-24 05:30:04.551600: step: 1244/527, loss: 0.008791719563305378
2023-01-24 05:30:05.599367: step: 1248/527, loss: 0.00736392242833972
2023-01-24 05:30:06.632291: step: 1252/527, loss: 0.0373251847922802
2023-01-24 05:30:07.678270: step: 1256/527, loss: 0.013917316682636738
2023-01-24 05:30:08.742341: step: 1260/527, loss: 0.003297120798379183
2023-01-24 05:30:09.798304: step: 1264/527, loss: 0.01039439719170332
2023-01-24 05:30:10.857138: step: 1268/527, loss: 0.02753548137843609
2023-01-24 05:30:11.905342: step: 1272/527, loss: 0.007985890842974186
2023-01-24 05:30:12.949737: step: 1276/527, loss: 0.0016036515589803457
2023-01-24 05:30:13.999864: step: 1280/527, loss: 0.010330391116440296
2023-01-24 05:30:15.069924: step: 1284/527, loss: 0.003874722635373473
2023-01-24 05:30:16.122460: step: 1288/527, loss: 0.015858067199587822
2023-01-24 05:30:17.174366: step: 1292/527, loss: 0.004830340389162302
2023-01-24 05:30:18.229560: step: 1296/527, loss: 0.06678352504968643
2023-01-24 05:30:19.300577: step: 1300/527, loss: 0.07401052862405777
2023-01-24 05:30:20.346246: step: 1304/527, loss: 0.005815865937620401
2023-01-24 05:30:21.406353: step: 1308/527, loss: 0.074469655752182
2023-01-24 05:30:22.448038: step: 1312/527, loss: 0.007657233159989119
2023-01-24 05:30:23.479332: step: 1316/527, loss: 0.010126876644790173
2023-01-24 05:30:24.529450: step: 1320/527, loss: 0.026489200070500374
2023-01-24 05:30:25.610965: step: 1324/527, loss: 0.012346141040325165
2023-01-24 05:30:26.684998: step: 1328/527, loss: 0.06684651970863342
2023-01-24 05:30:27.756975: step: 1332/527, loss: 0.023989371955394745
2023-01-24 05:30:28.811591: step: 1336/527, loss: 0.005770236719399691
2023-01-24 05:30:29.854094: step: 1340/527, loss: 0.0052342722192406654
2023-01-24 05:30:30.903103: step: 1344/527, loss: 0.008701438084244728
2023-01-24 05:30:31.943312: step: 1348/527, loss: 0.014546336606144905
2023-01-24 05:30:32.997887: step: 1352/527, loss: 0.0050030602142214775
2023-01-24 05:30:34.044554: step: 1356/527, loss: 0.004134844057261944
2023-01-24 05:30:35.099249: step: 1360/527, loss: 0.01821618527173996
2023-01-24 05:30:36.148233: step: 1364/527, loss: 0.029602590948343277
2023-01-24 05:30:37.192195: step: 1368/527, loss: 0.006892577279359102
2023-01-24 05:30:38.238455: step: 1372/527, loss: 0.0030683078803122044
2023-01-24 05:30:39.283908: step: 1376/527, loss: 0.05501647666096687
2023-01-24 05:30:40.321293: step: 1380/527, loss: 0.0
2023-01-24 05:30:41.373883: step: 1384/527, loss: 0.014835318550467491
2023-01-24 05:30:42.425151: step: 1388/527, loss: 0.005086015444248915
2023-01-24 05:30:43.477177: step: 1392/527, loss: 0.035345274955034256
2023-01-24 05:30:44.521459: step: 1396/527, loss: 0.00954096857458353
2023-01-24 05:30:45.572360: step: 1400/527, loss: 0.0013969441642984748
2023-01-24 05:30:46.623869: step: 1404/527, loss: 0.008144868537783623
2023-01-24 05:30:47.681033: step: 1408/527, loss: 0.0046132588759064674
2023-01-24 05:30:48.733493: step: 1412/527, loss: 0.0046321372501552105
2023-01-24 05:30:49.801335: step: 1416/527, loss: 0.0024720369838178158
2023-01-24 05:30:50.839395: step: 1420/527, loss: 0.00758796650916338
2023-01-24 05:30:51.890226: step: 1424/527, loss: 0.019266853109002113
2023-01-24 05:30:52.933454: step: 1428/527, loss: 0.014469382353127003
2023-01-24 05:30:53.993227: step: 1432/527, loss: 0.027585215866565704
2023-01-24 05:30:55.034264: step: 1436/527, loss: 0.022586941719055176
2023-01-24 05:30:56.081965: step: 1440/527, loss: 0.007138972170650959
2023-01-24 05:30:57.136594: step: 1444/527, loss: 0.0023658229038119316
2023-01-24 05:30:58.193615: step: 1448/527, loss: 0.018535802140831947
2023-01-24 05:30:59.256851: step: 1452/527, loss: 0.030143490061163902
2023-01-24 05:31:00.298872: step: 1456/527, loss: 0.002750793006271124
2023-01-24 05:31:01.353593: step: 1460/527, loss: 0.0014810208231210709
2023-01-24 05:31:02.443368: step: 1464/527, loss: 0.09174622595310211
2023-01-24 05:31:03.489838: step: 1468/527, loss: 0.0077330670319497585
2023-01-24 05:31:04.534199: step: 1472/527, loss: 0.003374515101313591
2023-01-24 05:31:05.584046: step: 1476/527, loss: 0.014382085762917995
2023-01-24 05:31:06.628876: step: 1480/527, loss: 0.006805216893553734
2023-01-24 05:31:07.687323: step: 1484/527, loss: 0.013255644589662552
2023-01-24 05:31:08.735264: step: 1488/527, loss: 0.007177384570240974
2023-01-24 05:31:09.798138: step: 1492/527, loss: 0.006798482034355402
2023-01-24 05:31:10.842343: step: 1496/527, loss: 0.013003462925553322
2023-01-24 05:31:11.882790: step: 1500/527, loss: 0.001318597118370235
2023-01-24 05:31:12.954962: step: 1504/527, loss: 0.011287938803434372
2023-01-24 05:31:14.003434: step: 1508/527, loss: 0.008135458454489708
2023-01-24 05:31:15.058114: step: 1512/527, loss: 0.016993878409266472
2023-01-24 05:31:16.109863: step: 1516/527, loss: 0.07533727586269379
2023-01-24 05:31:17.151578: step: 1520/527, loss: 0.006875397637486458
2023-01-24 05:31:18.194837: step: 1524/527, loss: 0.005762930028140545
2023-01-24 05:31:19.255701: step: 1528/527, loss: 0.01687450520694256
2023-01-24 05:31:20.296964: step: 1532/527, loss: 0.00984887219965458
2023-01-24 05:31:21.338848: step: 1536/527, loss: 0.0028607877902686596
2023-01-24 05:31:22.400326: step: 1540/527, loss: 0.03572121635079384
2023-01-24 05:31:23.458071: step: 1544/527, loss: 0.00899457186460495
2023-01-24 05:31:24.496988: step: 1548/527, loss: 0.039776477962732315
2023-01-24 05:31:25.543713: step: 1552/527, loss: 0.034703560173511505
2023-01-24 05:31:26.582367: step: 1556/527, loss: 0.00732477568089962
2023-01-24 05:31:27.617814: step: 1560/527, loss: 0.00390958646312356
2023-01-24 05:31:28.666026: step: 1564/527, loss: 0.009502626024186611
2023-01-24 05:31:29.717971: step: 1568/527, loss: 0.009714369662106037
2023-01-24 05:31:30.780373: step: 1572/527, loss: 0.021448219195008278
2023-01-24 05:31:31.831976: step: 1576/527, loss: 0.011181551963090897
2023-01-24 05:31:32.884410: step: 1580/527, loss: 0.009241553954780102
2023-01-24 05:31:33.920491: step: 1584/527, loss: 0.01548182312399149
2023-01-24 05:31:34.964699: step: 1588/527, loss: 0.01882026344537735
2023-01-24 05:31:36.014642: step: 1592/527, loss: 0.005637936294078827
2023-01-24 05:31:37.068064: step: 1596/527, loss: 0.02417459525167942
2023-01-24 05:31:38.115885: step: 1600/527, loss: 0.003551296191290021
2023-01-24 05:31:39.181571: step: 1604/527, loss: 0.02125997096300125
2023-01-24 05:31:40.255749: step: 1608/527, loss: 0.012055809609591961
2023-01-24 05:31:41.330338: step: 1612/527, loss: 0.01648874022066593
2023-01-24 05:31:42.385307: step: 1616/527, loss: 0.004450049716979265
2023-01-24 05:31:43.431274: step: 1620/527, loss: 0.001215534983202815
2023-01-24 05:31:44.474203: step: 1624/527, loss: 0.005571991670876741
2023-01-24 05:31:45.526570: step: 1628/527, loss: 0.005596946459263563
2023-01-24 05:31:46.569959: step: 1632/527, loss: 0.008297860622406006
2023-01-24 05:31:47.641099: step: 1636/527, loss: 0.007273584604263306
2023-01-24 05:31:48.688687: step: 1640/527, loss: 0.013721923343837261
2023-01-24 05:31:49.740055: step: 1644/527, loss: 0.008100690320134163
2023-01-24 05:31:50.788672: step: 1648/527, loss: 0.013942421413958073
2023-01-24 05:31:51.863707: step: 1652/527, loss: 0.0038877883926033974
2023-01-24 05:31:52.905117: step: 1656/527, loss: 0.058846235275268555
2023-01-24 05:31:53.936155: step: 1660/527, loss: 0.013884962536394596
2023-01-24 05:31:54.976531: step: 1664/527, loss: 0.05978230759501457
2023-01-24 05:31:56.052785: step: 1668/527, loss: 0.02195640467107296
2023-01-24 05:31:57.104529: step: 1672/527, loss: 0.012425919063389301
2023-01-24 05:31:58.148017: step: 1676/527, loss: 0.002420072676613927
2023-01-24 05:31:59.195322: step: 1680/527, loss: 0.02230508252978325
2023-01-24 05:32:00.238513: step: 1684/527, loss: 0.010975967161357403
2023-01-24 05:32:01.301581: step: 1688/527, loss: 0.009344184771180153
2023-01-24 05:32:02.348095: step: 1692/527, loss: 0.007283311802893877
2023-01-24 05:32:03.427139: step: 1696/527, loss: 0.02210157737135887
2023-01-24 05:32:04.476776: step: 1700/527, loss: 0.004351050592958927
2023-01-24 05:32:05.514991: step: 1704/527, loss: 0.003865842241793871
2023-01-24 05:32:06.586418: step: 1708/527, loss: 0.018277203664183617
2023-01-24 05:32:07.628024: step: 1712/527, loss: 0.0022287829779088497
2023-01-24 05:32:08.713566: step: 1716/527, loss: 0.0048011732287704945
2023-01-24 05:32:09.755118: step: 1720/527, loss: 0.007409593090415001
2023-01-24 05:32:10.800692: step: 1724/527, loss: 0.005694955121725798
2023-01-24 05:32:11.837871: step: 1728/527, loss: 0.011186397634446621
2023-01-24 05:32:12.869308: step: 1732/527, loss: 0.033404815942049026
2023-01-24 05:32:13.933802: step: 1736/527, loss: 0.007245366461575031
2023-01-24 05:32:14.989172: step: 1740/527, loss: 0.01462315022945404
2023-01-24 05:32:16.042326: step: 1744/527, loss: 0.007646861020475626
2023-01-24 05:32:17.100257: step: 1748/527, loss: 0.0016970261931419373
2023-01-24 05:32:18.157271: step: 1752/527, loss: 0.00301720155403018
2023-01-24 05:32:19.240277: step: 1756/527, loss: 0.023948779329657555
2023-01-24 05:32:20.300214: step: 1760/527, loss: 0.011112038046121597
2023-01-24 05:32:21.333564: step: 1764/527, loss: 0.011977504938840866
2023-01-24 05:32:22.389015: step: 1768/527, loss: 0.017544664442539215
2023-01-24 05:32:23.424123: step: 1772/527, loss: 0.00577186606824398
2023-01-24 05:32:24.464457: step: 1776/527, loss: 0.008312851190567017
2023-01-24 05:32:25.522037: step: 1780/527, loss: 0.005504704546183348
2023-01-24 05:32:26.578905: step: 1784/527, loss: 0.0010715055977925658
2023-01-24 05:32:27.623402: step: 1788/527, loss: 0.01258862018585205
2023-01-24 05:32:28.683907: step: 1792/527, loss: 0.021817810833454132
2023-01-24 05:32:29.733347: step: 1796/527, loss: 0.007140064146369696
2023-01-24 05:32:30.788926: step: 1800/527, loss: 0.0007058614864945412
2023-01-24 05:32:31.843672: step: 1804/527, loss: 0.013723025098443031
2023-01-24 05:32:32.908316: step: 1808/527, loss: 0.015082364901900291
2023-01-24 05:32:33.963886: step: 1812/527, loss: 0.00910787470638752
2023-01-24 05:32:35.008866: step: 1816/527, loss: 0.011241174302995205
2023-01-24 05:32:36.058223: step: 1820/527, loss: 0.01689973846077919
2023-01-24 05:32:37.143710: step: 1824/527, loss: 0.0022004563361406326
2023-01-24 05:32:38.199657: step: 1828/527, loss: 0.03286900371313095
2023-01-24 05:32:39.257249: step: 1832/527, loss: 0.014647014439105988
2023-01-24 05:32:40.319535: step: 1836/527, loss: 0.004199439659714699
2023-01-24 05:32:41.354334: step: 1840/527, loss: 0.0033072875812649727
2023-01-24 05:32:42.418239: step: 1844/527, loss: 0.13581690192222595
2023-01-24 05:32:43.473393: step: 1848/527, loss: 0.004670616239309311
2023-01-24 05:32:44.530710: step: 1852/527, loss: 0.010398413054645061
2023-01-24 05:32:45.583589: step: 1856/527, loss: 0.05213936045765877
2023-01-24 05:32:46.643923: step: 1860/527, loss: 0.009890140034258366
2023-01-24 05:32:47.685281: step: 1864/527, loss: 0.007445559371262789
2023-01-24 05:32:48.744352: step: 1868/527, loss: 0.0048018814995884895
2023-01-24 05:32:49.790617: step: 1872/527, loss: 0.003319947514683008
2023-01-24 05:32:50.823222: step: 1876/527, loss: 0.030779991298913956
2023-01-24 05:32:51.863589: step: 1880/527, loss: 0.0026039485819637775
2023-01-24 05:32:52.930245: step: 1884/527, loss: 0.010190390981733799
2023-01-24 05:32:53.986099: step: 1888/527, loss: 0.013070452958345413
2023-01-24 05:32:55.067891: step: 1892/527, loss: 0.007194320671260357
2023-01-24 05:32:56.115190: step: 1896/527, loss: 0.0035049982834607363
2023-01-24 05:32:57.160257: step: 1900/527, loss: 0.07489101588726044
2023-01-24 05:32:58.213999: step: 1904/527, loss: 0.014729148708283901
2023-01-24 05:32:59.254967: step: 1908/527, loss: 0.0036900367122143507
2023-01-24 05:33:00.295116: step: 1912/527, loss: 0.0036355936899781227
2023-01-24 05:33:01.347676: step: 1916/527, loss: 0.0054442123509943485
2023-01-24 05:33:02.388477: step: 1920/527, loss: 0.00244968943297863
2023-01-24 05:33:03.435266: step: 1924/527, loss: 0.015027009882032871
2023-01-24 05:33:04.485118: step: 1928/527, loss: 0.003041490912437439
2023-01-24 05:33:05.538109: step: 1932/527, loss: 0.004020232707262039
2023-01-24 05:33:06.572430: step: 1936/527, loss: 0.07933308184146881
2023-01-24 05:33:07.620408: step: 1940/527, loss: 0.013274340890347958
2023-01-24 05:33:08.665152: step: 1944/527, loss: 0.01796991191804409
2023-01-24 05:33:09.726712: step: 1948/527, loss: 0.024167299270629883
2023-01-24 05:33:10.786009: step: 1952/527, loss: 0.009892450645565987
2023-01-24 05:33:11.843067: step: 1956/527, loss: 0.007570433896034956
2023-01-24 05:33:12.896277: step: 1960/527, loss: 0.07348640263080597
2023-01-24 05:33:13.968596: step: 1964/527, loss: 0.006582705304026604
2023-01-24 05:33:15.029146: step: 1968/527, loss: 0.030393436551094055
2023-01-24 05:33:16.085928: step: 1972/527, loss: 0.0058537875302135944
2023-01-24 05:33:17.137123: step: 1976/527, loss: 0.0026069083251059055
2023-01-24 05:33:18.176957: step: 1980/527, loss: 0.009423689916729927
2023-01-24 05:33:19.254174: step: 1984/527, loss: 0.022480305284261703
2023-01-24 05:33:20.288381: step: 1988/527, loss: 0.030856041237711906
2023-01-24 05:33:21.349303: step: 1992/527, loss: 0.004838964436203241
2023-01-24 05:33:22.395536: step: 1996/527, loss: 0.005152531433850527
2023-01-24 05:33:23.438304: step: 2000/527, loss: 0.005777544807642698
2023-01-24 05:33:24.495127: step: 2004/527, loss: 0.014499610289931297
2023-01-24 05:33:25.539575: step: 2008/527, loss: 0.0042851450853049755
2023-01-24 05:33:26.597502: step: 2012/527, loss: 0.012328427284955978
2023-01-24 05:33:27.635554: step: 2016/527, loss: 0.016944842413067818
2023-01-24 05:33:28.668553: step: 2020/527, loss: 0.007113997358828783
2023-01-24 05:33:29.712070: step: 2024/527, loss: 0.05141862481832504
2023-01-24 05:33:30.758344: step: 2028/527, loss: 0.012867379933595657
2023-01-24 05:33:31.796311: step: 2032/527, loss: 0.004897923208773136
2023-01-24 05:33:32.850578: step: 2036/527, loss: 0.00516819953918457
2023-01-24 05:33:33.882199: step: 2040/527, loss: 0.016002006828784943
2023-01-24 05:33:34.925401: step: 2044/527, loss: 0.005539006553590298
2023-01-24 05:33:35.974181: step: 2048/527, loss: 0.007042177952826023
2023-01-24 05:33:37.035336: step: 2052/527, loss: 0.02467612735927105
2023-01-24 05:33:38.088737: step: 2056/527, loss: 0.009669848717749119
2023-01-24 05:33:39.128034: step: 2060/527, loss: 0.002288132905960083
2023-01-24 05:33:40.162486: step: 2064/527, loss: 0.014058349654078484
2023-01-24 05:33:41.207442: step: 2068/527, loss: 0.006001413334161043
2023-01-24 05:33:42.278913: step: 2072/527, loss: 0.026808515191078186
2023-01-24 05:33:43.327312: step: 2076/527, loss: 0.005903674755245447
2023-01-24 05:33:44.375122: step: 2080/527, loss: 0.00975488405674696
2023-01-24 05:33:45.438148: step: 2084/527, loss: 0.00612968485802412
2023-01-24 05:33:46.492632: step: 2088/527, loss: 0.012655384838581085
2023-01-24 05:33:47.528603: step: 2092/527, loss: 0.017377832904458046
2023-01-24 05:33:48.562067: step: 2096/527, loss: 0.00624031713232398
2023-01-24 05:33:49.611938: step: 2100/527, loss: 0.005781632848083973
2023-01-24 05:33:50.645549: step: 2104/527, loss: 3.921493771485984e-06
2023-01-24 05:33:51.684868: step: 2108/527, loss: 0.012473038397729397
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3674404761904762, 'r': 0.3346706424505286, 'f1': 0.35029082139310547}, 'combined': 0.25810902628965665, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.375917008358486, 'r': 0.29875329910415555, 'f1': 0.3329224517344891}, 'combined': 0.213070369110073, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36245993868877585, 'r': 0.31844203342106875, 'f1': 0.3390281850765722}, 'combined': 0.24981024163536897, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3833152972245292, 'r': 0.3025989493130741, 'f1': 0.33820789342480106}, 'combined': 0.24248867830457438, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:36:24.571426: step: 4/527, loss: 0.09630347788333893
2023-01-24 05:36:25.624003: step: 8/527, loss: 0.004018387757241726
2023-01-24 05:36:26.686476: step: 12/527, loss: 0.006106141023337841
2023-01-24 05:36:27.739329: step: 16/527, loss: 0.019484447315335274
2023-01-24 05:36:28.801046: step: 20/527, loss: 0.025568706914782524
2023-01-24 05:36:29.861895: step: 24/527, loss: 0.005435064435005188
2023-01-24 05:36:30.923345: step: 28/527, loss: 0.002151063410565257
2023-01-24 05:36:31.970644: step: 32/527, loss: 0.009927656501531601
2023-01-24 05:36:33.003482: step: 36/527, loss: 0.005331465974450111
2023-01-24 05:36:34.052825: step: 40/527, loss: 0.013922012411057949
2023-01-24 05:36:35.089248: step: 44/527, loss: 0.006039150059223175
2023-01-24 05:36:36.146538: step: 48/527, loss: 0.001960847992449999
2023-01-24 05:36:37.190055: step: 52/527, loss: 0.011658263392746449
2023-01-24 05:36:38.233810: step: 56/527, loss: 0.047435592859983444
2023-01-24 05:36:39.267795: step: 60/527, loss: 0.007725862320512533
2023-01-24 05:36:40.320837: step: 64/527, loss: 0.004883904475718737
2023-01-24 05:36:41.369930: step: 68/527, loss: 0.010088262148201466
2023-01-24 05:36:42.412530: step: 72/527, loss: 0.001696677994914353
2023-01-24 05:36:43.440786: step: 76/527, loss: 0.0034419659059494734
2023-01-24 05:36:44.490257: step: 80/527, loss: 0.0023205492179840803
2023-01-24 05:36:45.546729: step: 84/527, loss: 0.0010177545482292771
2023-01-24 05:36:46.586711: step: 88/527, loss: 0.0009474693215452135
2023-01-24 05:36:47.650015: step: 92/527, loss: 0.005022803321480751
2023-01-24 05:36:48.712380: step: 96/527, loss: 0.005060776136815548
2023-01-24 05:36:49.800664: step: 100/527, loss: 0.01681423746049404
2023-01-24 05:36:50.863944: step: 104/527, loss: 0.01177146378904581
2023-01-24 05:36:51.926589: step: 108/527, loss: 0.007815971039235592
2023-01-24 05:36:52.959991: step: 112/527, loss: 0.007773871533572674
2023-01-24 05:36:54.038190: step: 116/527, loss: 0.0027232191059738398
2023-01-24 05:36:55.107810: step: 120/527, loss: 0.005991565063595772
2023-01-24 05:36:56.152042: step: 124/527, loss: 0.00684939231723547
2023-01-24 05:36:57.185844: step: 128/527, loss: 0.0034862826578319073
2023-01-24 05:36:58.231328: step: 132/527, loss: 0.006345641799271107
2023-01-24 05:36:59.287763: step: 136/527, loss: 0.026764852926135063
2023-01-24 05:37:00.352178: step: 140/527, loss: 0.006506483536213636
2023-01-24 05:37:01.398892: step: 144/527, loss: 0.0008612524252384901
2023-01-24 05:37:02.444168: step: 148/527, loss: 0.005222842562943697
2023-01-24 05:37:03.494593: step: 152/527, loss: 0.00484373839572072
2023-01-24 05:37:04.540644: step: 156/527, loss: 0.006098178215324879
2023-01-24 05:37:05.588269: step: 160/527, loss: 0.004398141521960497
2023-01-24 05:37:06.627517: step: 164/527, loss: 0.010773123241961002
2023-01-24 05:37:07.679876: step: 168/527, loss: 0.036310240626335144
2023-01-24 05:37:08.740288: step: 172/527, loss: 0.007324503269046545
2023-01-24 05:37:09.795510: step: 176/527, loss: 0.005582513753324747
2023-01-24 05:37:10.831355: step: 180/527, loss: 0.011807762086391449
2023-01-24 05:37:11.908117: step: 184/527, loss: 0.0037986496463418007
2023-01-24 05:37:12.950895: step: 188/527, loss: 0.0023038529325276613
2023-01-24 05:37:14.000641: step: 192/527, loss: 0.0028449594974517822
2023-01-24 05:37:15.050329: step: 196/527, loss: 0.006153217051178217
2023-01-24 05:37:16.112657: step: 200/527, loss: 0.01319731306284666
2023-01-24 05:37:17.167347: step: 204/527, loss: 0.006297122221440077
2023-01-24 05:37:18.225067: step: 208/527, loss: 0.010150426998734474
2023-01-24 05:37:19.300264: step: 212/527, loss: 0.013856690376996994
2023-01-24 05:37:20.339127: step: 216/527, loss: 0.0013324968749657273
2023-01-24 05:37:21.379108: step: 220/527, loss: 0.010310085490345955
2023-01-24 05:37:22.427387: step: 224/527, loss: 0.007142497692257166
2023-01-24 05:37:23.487992: step: 228/527, loss: 0.002759611699730158
2023-01-24 05:37:24.531528: step: 232/527, loss: 0.005071406718343496
2023-01-24 05:37:25.572125: step: 236/527, loss: 0.013709788210690022
2023-01-24 05:37:26.631326: step: 240/527, loss: 0.00850035808980465
2023-01-24 05:37:27.670727: step: 244/527, loss: 0.009937750175595284
2023-01-24 05:37:28.729304: step: 248/527, loss: 0.008300106041133404
2023-01-24 05:37:29.783450: step: 252/527, loss: 0.023348016664385796
2023-01-24 05:37:30.852293: step: 256/527, loss: 0.01973486691713333
2023-01-24 05:37:31.906728: step: 260/527, loss: 0.00919699389487505
2023-01-24 05:37:32.945684: step: 264/527, loss: 0.00831583235412836
2023-01-24 05:37:33.995883: step: 268/527, loss: 0.002271933713927865
2023-01-24 05:37:35.041969: step: 272/527, loss: 0.009893148206174374
2023-01-24 05:37:36.082870: step: 276/527, loss: 0.005620964802801609
2023-01-24 05:37:37.146797: step: 280/527, loss: 0.025527391582727432
2023-01-24 05:37:38.220292: step: 284/527, loss: 0.00900374073535204
2023-01-24 05:37:39.287386: step: 288/527, loss: 0.005033768247812986
2023-01-24 05:37:40.327851: step: 292/527, loss: 0.022912397980690002
2023-01-24 05:37:41.390754: step: 296/527, loss: 0.005532699637115002
2023-01-24 05:37:42.456674: step: 300/527, loss: 0.004621663596481085
2023-01-24 05:37:43.513789: step: 304/527, loss: 0.0020022594835609198
2023-01-24 05:37:44.563530: step: 308/527, loss: 0.015827590599656105
2023-01-24 05:37:45.613607: step: 312/527, loss: 0.0014097942039370537
2023-01-24 05:37:46.678478: step: 316/527, loss: 0.012368621304631233
2023-01-24 05:37:47.739145: step: 320/527, loss: 0.004982339218258858
2023-01-24 05:37:48.779299: step: 324/527, loss: 0.03387031704187393
2023-01-24 05:37:49.832702: step: 328/527, loss: 0.01007978618144989
2023-01-24 05:37:50.870313: step: 332/527, loss: 0.02267213724553585
2023-01-24 05:37:51.941850: step: 336/527, loss: 0.005016049835830927
2023-01-24 05:37:53.001111: step: 340/527, loss: 0.02270680107176304
2023-01-24 05:37:54.051476: step: 344/527, loss: 0.02230987511575222
2023-01-24 05:37:55.103893: step: 348/527, loss: 0.024212274700403214
2023-01-24 05:37:56.156632: step: 352/527, loss: 0.006584585178643465
2023-01-24 05:37:57.187747: step: 356/527, loss: 0.004892353899776936
2023-01-24 05:37:58.243451: step: 360/527, loss: 0.0075839790515601635
2023-01-24 05:37:59.287453: step: 364/527, loss: 0.006894493941217661
2023-01-24 05:38:00.349018: step: 368/527, loss: 0.019412977620959282
2023-01-24 05:38:01.388558: step: 372/527, loss: 0.0022092692088335752
2023-01-24 05:38:02.444507: step: 376/527, loss: 0.0050852615386247635
2023-01-24 05:38:03.498689: step: 380/527, loss: 0.002591255586594343
2023-01-24 05:38:04.569579: step: 384/527, loss: 0.06252925843000412
2023-01-24 05:38:05.616910: step: 388/527, loss: 0.008522537536919117
2023-01-24 05:38:06.689253: step: 392/527, loss: 0.008968872018158436
2023-01-24 05:38:07.726575: step: 396/527, loss: 0.00962995458394289
2023-01-24 05:38:08.777402: step: 400/527, loss: 0.008363430388271809
2023-01-24 05:38:09.833304: step: 404/527, loss: 0.01252360362559557
2023-01-24 05:38:10.875335: step: 408/527, loss: 0.007110966369509697
2023-01-24 05:38:11.925741: step: 412/527, loss: 0.006380102597177029
2023-01-24 05:38:12.979139: step: 416/527, loss: 0.006093526259064674
2023-01-24 05:38:14.030512: step: 420/527, loss: 0.011622357182204723
2023-01-24 05:38:15.081183: step: 424/527, loss: 0.0031945989467203617
2023-01-24 05:38:16.114986: step: 428/527, loss: 0.01747400499880314
2023-01-24 05:38:17.171277: step: 432/527, loss: 0.045519184321165085
2023-01-24 05:38:18.227893: step: 436/527, loss: 0.006821592804044485
2023-01-24 05:38:19.297476: step: 440/527, loss: 0.004795973189175129
2023-01-24 05:38:20.332702: step: 444/527, loss: 0.005497786216437817
2023-01-24 05:38:21.388317: step: 448/527, loss: 0.006155397742986679
2023-01-24 05:38:22.433890: step: 452/527, loss: 0.005620886571705341
2023-01-24 05:38:23.499173: step: 456/527, loss: 0.009695395827293396
2023-01-24 05:38:24.572774: step: 460/527, loss: 0.02128414995968342
2023-01-24 05:38:25.631610: step: 464/527, loss: 0.004674040712416172
2023-01-24 05:38:26.664731: step: 468/527, loss: 0.015705401077866554
2023-01-24 05:38:27.694399: step: 472/527, loss: 0.0018358565866947174
2023-01-24 05:38:28.739728: step: 476/527, loss: 0.0009739425731822848
2023-01-24 05:38:29.781581: step: 480/527, loss: 0.035310838371515274
2023-01-24 05:38:30.838685: step: 484/527, loss: 0.006547639146447182
2023-01-24 05:38:31.887661: step: 488/527, loss: 0.0026764969807118177
2023-01-24 05:38:32.948120: step: 492/527, loss: 0.002714770380407572
2023-01-24 05:38:34.008604: step: 496/527, loss: 0.02095515839755535
2023-01-24 05:38:35.057586: step: 500/527, loss: 0.006102669518440962
2023-01-24 05:38:36.111837: step: 504/527, loss: 0.02948002889752388
2023-01-24 05:38:37.169748: step: 508/527, loss: 0.005745660979300737
2023-01-24 05:38:38.237424: step: 512/527, loss: 0.013627566397190094
2023-01-24 05:38:39.291356: step: 516/527, loss: 0.009460663422942162
2023-01-24 05:38:40.338626: step: 520/527, loss: 0.008031336590647697
2023-01-24 05:38:41.400685: step: 524/527, loss: 0.0041961390525102615
2023-01-24 05:38:42.443012: step: 528/527, loss: 0.00910942256450653
2023-01-24 05:38:43.504548: step: 532/527, loss: 0.004254691768437624
2023-01-24 05:38:44.574181: step: 536/527, loss: 0.0016187336295843124
2023-01-24 05:38:45.624041: step: 540/527, loss: 0.0005065691657364368
2023-01-24 05:38:46.669540: step: 544/527, loss: 0.02607870101928711
2023-01-24 05:38:47.726721: step: 548/527, loss: 0.0027424455620348454
2023-01-24 05:38:48.763910: step: 552/527, loss: 0.005031141918152571
2023-01-24 05:38:49.817639: step: 556/527, loss: 0.006300052627921104
2023-01-24 05:38:50.863529: step: 560/527, loss: 0.022951407358050346
2023-01-24 05:38:51.933308: step: 564/527, loss: 0.028079045936465263
2023-01-24 05:38:52.988346: step: 568/527, loss: 0.0240947138518095
2023-01-24 05:38:54.044951: step: 572/527, loss: 0.013987342827022076
2023-01-24 05:38:55.095938: step: 576/527, loss: 0.014969791285693645
2023-01-24 05:38:56.141904: step: 580/527, loss: 0.013831953518092632
2023-01-24 05:38:57.206106: step: 584/527, loss: 0.013960978016257286
2023-01-24 05:38:58.246521: step: 588/527, loss: 0.005384617485105991
2023-01-24 05:38:59.299845: step: 592/527, loss: 0.049049802124500275
2023-01-24 05:39:00.357942: step: 596/527, loss: 0.004875629674643278
2023-01-24 05:39:01.404634: step: 600/527, loss: 0.01216600276529789
2023-01-24 05:39:02.453438: step: 604/527, loss: 0.03795206546783447
2023-01-24 05:39:03.495276: step: 608/527, loss: 0.009664355777204037
2023-01-24 05:39:04.548093: step: 612/527, loss: 0.012557614594697952
2023-01-24 05:39:05.600568: step: 616/527, loss: 0.0034800933208316565
2023-01-24 05:39:06.654161: step: 620/527, loss: 0.005707267206162214
2023-01-24 05:39:07.694318: step: 624/527, loss: 0.01435763668268919
2023-01-24 05:39:08.734031: step: 628/527, loss: 0.009481802582740784
2023-01-24 05:39:09.784402: step: 632/527, loss: 0.012051774188876152
2023-01-24 05:39:10.838715: step: 636/527, loss: 0.002101621124893427
2023-01-24 05:39:11.898537: step: 640/527, loss: 0.007650560233741999
2023-01-24 05:39:12.952021: step: 644/527, loss: 0.024623781442642212
2023-01-24 05:39:14.001428: step: 648/527, loss: 0.00864055659621954
2023-01-24 05:39:15.055020: step: 652/527, loss: 0.013074246235191822
2023-01-24 05:39:16.127313: step: 656/527, loss: 0.004558406304568052
2023-01-24 05:39:17.187620: step: 660/527, loss: 0.002944357693195343
2023-01-24 05:39:18.244124: step: 664/527, loss: 0.008235105313360691
2023-01-24 05:39:19.303538: step: 668/527, loss: 0.008779531344771385
2023-01-24 05:39:20.349701: step: 672/527, loss: 0.008774541318416595
2023-01-24 05:39:21.406712: step: 676/527, loss: 0.00882588978856802
2023-01-24 05:39:22.457715: step: 680/527, loss: 0.006947447080165148
2023-01-24 05:39:23.517607: step: 684/527, loss: 0.002728177234530449
2023-01-24 05:39:24.575010: step: 688/527, loss: 0.005696764215826988
2023-01-24 05:39:25.618401: step: 692/527, loss: 0.0032642583828419447
2023-01-24 05:39:26.657702: step: 696/527, loss: 0.006180267781019211
2023-01-24 05:39:27.686650: step: 700/527, loss: 0.013511242344975471
2023-01-24 05:39:28.748235: step: 704/527, loss: 0.01107818353921175
2023-01-24 05:39:29.791046: step: 708/527, loss: 0.0003384547890163958
2023-01-24 05:39:30.840055: step: 712/527, loss: 0.006935957819223404
2023-01-24 05:39:31.878925: step: 716/527, loss: 0.0007469377596862614
2023-01-24 05:39:32.938417: step: 720/527, loss: 0.007006959989666939
2023-01-24 05:39:33.982871: step: 724/527, loss: 0.015508010052144527
2023-01-24 05:39:35.032316: step: 728/527, loss: 0.00976771954447031
2023-01-24 05:39:36.090915: step: 732/527, loss: 0.005833568051457405
2023-01-24 05:39:37.140260: step: 736/527, loss: 0.016178976744413376
2023-01-24 05:39:38.192579: step: 740/527, loss: 0.005664953030645847
2023-01-24 05:39:39.238251: step: 744/527, loss: 0.009345514699816704
2023-01-24 05:39:40.289694: step: 748/527, loss: 0.029329312965273857
2023-01-24 05:39:41.337960: step: 752/527, loss: 0.013494308106601238
2023-01-24 05:39:42.371591: step: 756/527, loss: 0.008023953065276146
2023-01-24 05:39:43.413268: step: 760/527, loss: 0.004013955593109131
2023-01-24 05:39:44.461779: step: 764/527, loss: 0.0053697009570896626
2023-01-24 05:39:45.521784: step: 768/527, loss: 0.01831982284784317
2023-01-24 05:39:46.567656: step: 772/527, loss: 0.006706717889755964
2023-01-24 05:39:47.609493: step: 776/527, loss: 0.006412239279597998
2023-01-24 05:39:48.669853: step: 780/527, loss: 0.010564597323536873
2023-01-24 05:39:49.727792: step: 784/527, loss: 0.023201294243335724
2023-01-24 05:39:50.778986: step: 788/527, loss: 0.008991423062980175
2023-01-24 05:39:51.839340: step: 792/527, loss: 0.004017589148133993
2023-01-24 05:39:52.878597: step: 796/527, loss: 7.491168798878789e-05
2023-01-24 05:39:53.947485: step: 800/527, loss: 0.01232368964701891
2023-01-24 05:39:55.012727: step: 804/527, loss: 0.0076598916202783585
2023-01-24 05:39:56.079146: step: 808/527, loss: 0.019467106088995934
2023-01-24 05:39:57.126348: step: 812/527, loss: 0.005291010718792677
2023-01-24 05:39:58.196024: step: 816/527, loss: 0.054278384894132614
2023-01-24 05:39:59.234529: step: 820/527, loss: 0.010627686977386475
2023-01-24 05:40:00.282155: step: 824/527, loss: 0.029858341440558434
2023-01-24 05:40:01.336289: step: 828/527, loss: 0.002811152022331953
2023-01-24 05:40:02.395135: step: 832/527, loss: 0.018511833623051643
2023-01-24 05:40:03.450453: step: 836/527, loss: 0.02764853835105896
2023-01-24 05:40:04.498204: step: 840/527, loss: 0.022996187210083008
2023-01-24 05:40:05.551778: step: 844/527, loss: 0.006607236806303263
2023-01-24 05:40:06.612144: step: 848/527, loss: 0.0020034622866660357
2023-01-24 05:40:07.670483: step: 852/527, loss: 0.005831459537148476
2023-01-24 05:40:08.747658: step: 856/527, loss: 0.0005701023619621992
2023-01-24 05:40:09.790705: step: 860/527, loss: 0.0021332784090191126
2023-01-24 05:40:10.836223: step: 864/527, loss: 0.004820593632757664
2023-01-24 05:40:11.906567: step: 868/527, loss: 0.00851569976657629
2023-01-24 05:40:12.960681: step: 872/527, loss: 0.0057282340712845325
2023-01-24 05:40:14.032011: step: 876/527, loss: 0.03575843200087547
2023-01-24 05:40:15.079455: step: 880/527, loss: 0.007071408908814192
2023-01-24 05:40:16.130180: step: 884/527, loss: 0.010876198299229145
2023-01-24 05:40:17.180673: step: 888/527, loss: 0.0015082152094691992
2023-01-24 05:40:18.240238: step: 892/527, loss: 0.04648592323064804
2023-01-24 05:40:19.300407: step: 896/527, loss: 0.003673673141747713
2023-01-24 05:40:20.344454: step: 900/527, loss: 0.011082727462053299
2023-01-24 05:40:21.407880: step: 904/527, loss: 0.009784271940588951
2023-01-24 05:40:22.480379: step: 908/527, loss: 0.0042418260127305984
2023-01-24 05:40:23.539695: step: 912/527, loss: 0.005253738723695278
2023-01-24 05:40:24.602688: step: 916/527, loss: 0.002525955904275179
2023-01-24 05:40:25.667672: step: 920/527, loss: 0.005559364799410105
2023-01-24 05:40:26.730506: step: 924/527, loss: 0.001615817192941904
2023-01-24 05:40:27.776541: step: 928/527, loss: 0.011296793818473816
2023-01-24 05:40:28.848868: step: 932/527, loss: 0.007280383259057999
2023-01-24 05:40:29.888248: step: 936/527, loss: 0.007404201664030552
2023-01-24 05:40:30.942730: step: 940/527, loss: 0.00373828480951488
2023-01-24 05:40:31.995828: step: 944/527, loss: 0.014845043420791626
2023-01-24 05:40:33.050307: step: 948/527, loss: 0.003047631587833166
2023-01-24 05:40:34.110514: step: 952/527, loss: 0.07062729448080063
2023-01-24 05:40:35.151146: step: 956/527, loss: 0.005586340092122555
2023-01-24 05:40:36.205661: step: 960/527, loss: 0.007183740381151438
2023-01-24 05:40:37.240520: step: 964/527, loss: 0.00403355248272419
2023-01-24 05:40:38.280545: step: 968/527, loss: 0.005623816046863794
2023-01-24 05:40:39.331733: step: 972/527, loss: 0.011466557160019875
2023-01-24 05:40:40.386840: step: 976/527, loss: 0.02611096389591694
2023-01-24 05:40:41.428569: step: 980/527, loss: 0.004564451519399881
2023-01-24 05:40:42.481143: step: 984/527, loss: 0.0065962281078100204
2023-01-24 05:40:43.537652: step: 988/527, loss: 0.031127341091632843
2023-01-24 05:40:44.581857: step: 992/527, loss: 0.029385266825556755
2023-01-24 05:40:45.623134: step: 996/527, loss: 0.004823361989110708
2023-01-24 05:40:46.682143: step: 1000/527, loss: 0.009636526927351952
2023-01-24 05:40:47.741024: step: 1004/527, loss: 0.009387986734509468
2023-01-24 05:40:48.785711: step: 1008/527, loss: 0.002747615799307823
2023-01-24 05:40:49.837854: step: 1012/527, loss: 0.005756690166890621
2023-01-24 05:40:50.904130: step: 1016/527, loss: 0.010362193919718266
2023-01-24 05:40:51.968063: step: 1020/527, loss: 0.0043361494317650795
2023-01-24 05:40:53.027641: step: 1024/527, loss: 0.014931879006326199
2023-01-24 05:40:54.084567: step: 1028/527, loss: 0.03934931010007858
2023-01-24 05:40:55.135822: step: 1032/527, loss: 0.007010089699178934
2023-01-24 05:40:56.198941: step: 1036/527, loss: 0.02363082766532898
2023-01-24 05:40:57.254733: step: 1040/527, loss: 0.003583756275475025
2023-01-24 05:40:58.297698: step: 1044/527, loss: 0.02431095950305462
2023-01-24 05:40:59.344719: step: 1048/527, loss: 0.005139993038028479
2023-01-24 05:41:00.403364: step: 1052/527, loss: 0.01207831222563982
2023-01-24 05:41:01.453430: step: 1056/527, loss: 0.025138530880212784
2023-01-24 05:41:02.526384: step: 1060/527, loss: 0.011888965964317322
2023-01-24 05:41:03.590940: step: 1064/527, loss: 0.019171904772520065
2023-01-24 05:41:04.649687: step: 1068/527, loss: 0.013876696117222309
2023-01-24 05:41:05.689447: step: 1072/527, loss: 0.015924135223031044
2023-01-24 05:41:06.749675: step: 1076/527, loss: 0.04972352832555771
2023-01-24 05:41:07.784508: step: 1080/527, loss: 0.00970274768769741
2023-01-24 05:41:08.853427: step: 1084/527, loss: 0.005475292447954416
2023-01-24 05:41:09.907341: step: 1088/527, loss: 0.004668317269533873
2023-01-24 05:41:10.958745: step: 1092/527, loss: 0.011428778059780598
2023-01-24 05:41:12.004930: step: 1096/527, loss: 0.01907227374613285
2023-01-24 05:41:13.065798: step: 1100/527, loss: 0.0066899326629936695
2023-01-24 05:41:14.134554: step: 1104/527, loss: 0.008204030804336071
2023-01-24 05:41:15.189527: step: 1108/527, loss: 0.003582809353247285
2023-01-24 05:41:16.241914: step: 1112/527, loss: 0.009270605631172657
2023-01-24 05:41:17.298628: step: 1116/527, loss: 0.004008301068097353
2023-01-24 05:41:18.342440: step: 1120/527, loss: 0.034290336072444916
2023-01-24 05:41:19.390350: step: 1124/527, loss: 0.02331523410975933
2023-01-24 05:41:20.436237: step: 1128/527, loss: 0.0029394710436463356
2023-01-24 05:41:21.503078: step: 1132/527, loss: 0.021229039877653122
2023-01-24 05:41:22.553825: step: 1136/527, loss: 0.013098455965518951
2023-01-24 05:41:23.603804: step: 1140/527, loss: 0.004252019338309765
2023-01-24 05:41:24.655539: step: 1144/527, loss: 0.004101179540157318
2023-01-24 05:41:25.715344: step: 1148/527, loss: 0.01199449971318245
2023-01-24 05:41:26.760303: step: 1152/527, loss: 0.009503703564405441
2023-01-24 05:41:27.813311: step: 1156/527, loss: 0.00757455313578248
2023-01-24 05:41:28.865163: step: 1160/527, loss: 0.034820638597011566
2023-01-24 05:41:29.926801: step: 1164/527, loss: 0.027094146236777306
2023-01-24 05:41:30.970461: step: 1168/527, loss: 0.0037842022720724344
2023-01-24 05:41:32.021706: step: 1172/527, loss: 0.014584150165319443
2023-01-24 05:41:33.079155: step: 1176/527, loss: 0.011031536385416985
2023-01-24 05:41:34.138449: step: 1180/527, loss: 0.0002956017560791224
2023-01-24 05:41:35.197131: step: 1184/527, loss: 0.005388931836932898
2023-01-24 05:41:36.279489: step: 1188/527, loss: 0.004438537638634443
2023-01-24 05:41:37.342900: step: 1192/527, loss: 0.0017783530056476593
2023-01-24 05:41:38.391213: step: 1196/527, loss: 0.0026618139818310738
2023-01-24 05:41:39.442840: step: 1200/527, loss: 0.0013757027918472886
2023-01-24 05:41:40.498562: step: 1204/527, loss: 0.0038849753327667713
2023-01-24 05:41:41.539046: step: 1208/527, loss: 0.003766994457691908
2023-01-24 05:41:42.594927: step: 1212/527, loss: 0.0011678735027089715
2023-01-24 05:41:43.643264: step: 1216/527, loss: 0.0021237481851130724
2023-01-24 05:41:44.677467: step: 1220/527, loss: 0.009384707547724247
2023-01-24 05:41:45.716517: step: 1224/527, loss: 0.005486843641847372
2023-01-24 05:41:46.763341: step: 1228/527, loss: 0.004588239826261997
2023-01-24 05:41:47.812046: step: 1232/527, loss: 0.007448290474712849
2023-01-24 05:41:48.855405: step: 1236/527, loss: 0.017806917428970337
2023-01-24 05:41:49.936102: step: 1240/527, loss: 0.03841574490070343
2023-01-24 05:41:50.982750: step: 1244/527, loss: 0.02057504653930664
2023-01-24 05:41:52.027604: step: 1248/527, loss: 0.004881734028458595
2023-01-24 05:41:53.072864: step: 1252/527, loss: 0.03089827299118042
2023-01-24 05:41:54.128483: step: 1256/527, loss: 0.0021302737295627594
2023-01-24 05:41:55.179519: step: 1260/527, loss: 0.0062431758269667625
2023-01-24 05:41:56.214235: step: 1264/527, loss: 0.0011526638409122825
2023-01-24 05:41:57.260902: step: 1268/527, loss: 0.008987120352685452
2023-01-24 05:41:58.316337: step: 1272/527, loss: 0.0035955901257693768
2023-01-24 05:41:59.370880: step: 1276/527, loss: 0.02776988409459591
2023-01-24 05:42:00.423004: step: 1280/527, loss: 0.011404940858483315
2023-01-24 05:42:01.469004: step: 1284/527, loss: 0.00906613189727068
2023-01-24 05:42:02.520151: step: 1288/527, loss: 0.013027424924075603
2023-01-24 05:42:03.563078: step: 1292/527, loss: 0.009509925730526447
2023-01-24 05:42:04.609538: step: 1296/527, loss: 0.024461472406983376
2023-01-24 05:42:05.655675: step: 1300/527, loss: 0.0008931338088586926
2023-01-24 05:42:06.724281: step: 1304/527, loss: 0.00578805897384882
2023-01-24 05:42:07.775748: step: 1308/527, loss: 0.011017491109669209
2023-01-24 05:42:08.815993: step: 1312/527, loss: 0.0020963025745004416
2023-01-24 05:42:09.872870: step: 1316/527, loss: 0.007990492507815361
2023-01-24 05:42:10.914935: step: 1320/527, loss: 0.03873471915721893
2023-01-24 05:42:11.976327: step: 1324/527, loss: 0.0013404254568740726
2023-01-24 05:42:13.018366: step: 1328/527, loss: 0.007413769606500864
2023-01-24 05:42:14.077695: step: 1332/527, loss: 0.018406588584184647
2023-01-24 05:42:15.112949: step: 1336/527, loss: 0.0036480906419456005
2023-01-24 05:42:16.166892: step: 1340/527, loss: 0.0018968930235132575
2023-01-24 05:42:17.223482: step: 1344/527, loss: 0.004612892400473356
2023-01-24 05:42:18.266215: step: 1348/527, loss: 0.003450157353654504
2023-01-24 05:42:19.331254: step: 1352/527, loss: 0.018316416069865227
2023-01-24 05:42:20.395360: step: 1356/527, loss: 0.003896051086485386
2023-01-24 05:42:21.426505: step: 1360/527, loss: 0.006394432857632637
2023-01-24 05:42:22.466495: step: 1364/527, loss: 0.010783486999571323
2023-01-24 05:42:23.504295: step: 1368/527, loss: 0.007230890914797783
2023-01-24 05:42:24.549063: step: 1372/527, loss: 0.008847628720104694
2023-01-24 05:42:25.590605: step: 1376/527, loss: 9.944938938133419e-05
2023-01-24 05:42:26.656735: step: 1380/527, loss: 0.01847342774271965
2023-01-24 05:42:27.721485: step: 1384/527, loss: 0.006782527081668377
2023-01-24 05:42:28.774604: step: 1388/527, loss: 0.009193900972604752
2023-01-24 05:42:29.809639: step: 1392/527, loss: 0.0022746522445231676
2023-01-24 05:42:30.860002: step: 1396/527, loss: 0.0030602654442191124
2023-01-24 05:42:31.920922: step: 1400/527, loss: 0.006369085982441902
2023-01-24 05:42:32.978389: step: 1404/527, loss: 0.02380537986755371
2023-01-24 05:42:34.033075: step: 1408/527, loss: 0.0026016035117208958
2023-01-24 05:42:35.077385: step: 1412/527, loss: 0.0034504702780395746
2023-01-24 05:42:36.148612: step: 1416/527, loss: 0.00810646079480648
2023-01-24 05:42:37.211629: step: 1420/527, loss: 0.027019396424293518
2023-01-24 05:42:38.271452: step: 1424/527, loss: 0.01575886830687523
2023-01-24 05:42:39.321692: step: 1428/527, loss: 0.007510844152420759
2023-01-24 05:42:40.386174: step: 1432/527, loss: 0.011695628985762596
2023-01-24 05:42:41.452046: step: 1436/527, loss: 0.0044456482864916325
2023-01-24 05:42:42.515685: step: 1440/527, loss: 0.01765453815460205
2023-01-24 05:42:43.554771: step: 1444/527, loss: 0.005490010604262352
2023-01-24 05:42:44.604567: step: 1448/527, loss: 0.001851929584518075
2023-01-24 05:42:45.641642: step: 1452/527, loss: 0.015075921081006527
2023-01-24 05:42:46.699872: step: 1456/527, loss: 0.0053201522678136826
2023-01-24 05:42:47.740817: step: 1460/527, loss: 0.005342629738152027
2023-01-24 05:42:48.788037: step: 1464/527, loss: 0.01672927848994732
2023-01-24 05:42:49.828118: step: 1468/527, loss: 0.006210397928953171
2023-01-24 05:42:50.900736: step: 1472/527, loss: 0.050433091819286346
2023-01-24 05:42:51.949700: step: 1476/527, loss: 0.015234251506626606
2023-01-24 05:42:52.992761: step: 1480/527, loss: 0.0038743913173675537
2023-01-24 05:42:54.013576: step: 1484/527, loss: 0.01153487153351307
2023-01-24 05:42:55.076869: step: 1488/527, loss: 0.012831402011215687
2023-01-24 05:42:56.124775: step: 1492/527, loss: 0.0058450717478990555
2023-01-24 05:42:57.199126: step: 1496/527, loss: 0.0267823226749897
2023-01-24 05:42:58.243779: step: 1500/527, loss: 0.0058557698503136635
2023-01-24 05:42:59.300132: step: 1504/527, loss: 0.005743971094489098
2023-01-24 05:43:00.344099: step: 1508/527, loss: 0.0
2023-01-24 05:43:01.406091: step: 1512/527, loss: 0.016628021374344826
2023-01-24 05:43:02.441400: step: 1516/527, loss: 0.005140840541571379
2023-01-24 05:43:03.476435: step: 1520/527, loss: 0.004369328264147043
2023-01-24 05:43:04.540836: step: 1524/527, loss: 0.003731008153408766
2023-01-24 05:43:05.604214: step: 1528/527, loss: 0.03829382359981537
2023-01-24 05:43:06.652922: step: 1532/527, loss: 0.008014494553208351
2023-01-24 05:43:07.709507: step: 1536/527, loss: 0.011885719373822212
2023-01-24 05:43:08.768988: step: 1540/527, loss: 0.01657886803150177
2023-01-24 05:43:09.815402: step: 1544/527, loss: 0.01222853735089302
2023-01-24 05:43:10.866166: step: 1548/527, loss: 0.0029392321594059467
2023-01-24 05:43:11.908670: step: 1552/527, loss: 0.004848426673561335
2023-01-24 05:43:12.948467: step: 1556/527, loss: 0.02532697655260563
2023-01-24 05:43:14.014339: step: 1560/527, loss: 0.01223083771765232
2023-01-24 05:43:15.070475: step: 1564/527, loss: 0.0010586688295006752
2023-01-24 05:43:16.099767: step: 1568/527, loss: 0.0027050855569541454
2023-01-24 05:43:17.147558: step: 1572/527, loss: 0.002986507024616003
2023-01-24 05:43:18.208264: step: 1576/527, loss: 0.005963047035038471
2023-01-24 05:43:19.293531: step: 1580/527, loss: 0.011919020675122738
2023-01-24 05:43:20.348156: step: 1584/527, loss: 0.010144336149096489
2023-01-24 05:43:21.408402: step: 1588/527, loss: 0.11049667745828629
2023-01-24 05:43:22.457314: step: 1592/527, loss: 0.0020202547311782837
2023-01-24 05:43:23.510305: step: 1596/527, loss: 0.003238413482904434
2023-01-24 05:43:24.547184: step: 1600/527, loss: 0.013794923201203346
2023-01-24 05:43:25.612546: step: 1604/527, loss: 0.007212123367935419
2023-01-24 05:43:26.676137: step: 1608/527, loss: 0.01122779306024313
2023-01-24 05:43:27.731955: step: 1612/527, loss: 0.035339292138814926
2023-01-24 05:43:28.773509: step: 1616/527, loss: 0.0023843515664339066
2023-01-24 05:43:29.822899: step: 1620/527, loss: 0.009645218960940838
2023-01-24 05:43:30.881750: step: 1624/527, loss: 0.011995306238532066
2023-01-24 05:43:31.936586: step: 1628/527, loss: 0.013134126551449299
2023-01-24 05:43:32.994145: step: 1632/527, loss: 0.02185082621872425
2023-01-24 05:43:34.030410: step: 1636/527, loss: 0.03338497877120972
2023-01-24 05:43:35.103227: step: 1640/527, loss: 0.0027892731595784426
2023-01-24 05:43:36.142607: step: 1644/527, loss: 0.004808598663657904
2023-01-24 05:43:37.201452: step: 1648/527, loss: 0.003547914791852236
2023-01-24 05:43:38.238183: step: 1652/527, loss: 0.0038693707901984453
2023-01-24 05:43:39.298658: step: 1656/527, loss: 0.015623710118234158
2023-01-24 05:43:40.348846: step: 1660/527, loss: 0.014417893253266811
2023-01-24 05:43:41.395654: step: 1664/527, loss: 8.103435538941994e-05
2023-01-24 05:43:42.451176: step: 1668/527, loss: 0.0063257645815610886
2023-01-24 05:43:43.497240: step: 1672/527, loss: 0.00885890331119299
2023-01-24 05:43:44.532390: step: 1676/527, loss: 0.005163947585970163
2023-01-24 05:43:45.590312: step: 1680/527, loss: 0.003962541464716196
2023-01-24 05:43:46.622438: step: 1684/527, loss: 0.0019523502560332417
2023-01-24 05:43:47.670138: step: 1688/527, loss: 0.00751158781349659
2023-01-24 05:43:48.707609: step: 1692/527, loss: 0.00586579879745841
2023-01-24 05:43:49.783667: step: 1696/527, loss: 0.03698648512363434
2023-01-24 05:43:50.812632: step: 1700/527, loss: 0.005073432344943285
2023-01-24 05:43:51.861748: step: 1704/527, loss: 0.04573269188404083
2023-01-24 05:43:52.907529: step: 1708/527, loss: 0.03874180093407631
2023-01-24 05:43:53.950566: step: 1712/527, loss: 0.009860971011221409
2023-01-24 05:43:55.013501: step: 1716/527, loss: 0.018232179805636406
2023-01-24 05:43:56.061783: step: 1720/527, loss: 0.008927026763558388
2023-01-24 05:43:57.122226: step: 1724/527, loss: 0.010142615996301174
2023-01-24 05:43:58.176741: step: 1728/527, loss: 0.008999330922961235
2023-01-24 05:43:59.224004: step: 1732/527, loss: 0.004921245388686657
2023-01-24 05:44:00.300706: step: 1736/527, loss: 0.00727794598788023
2023-01-24 05:44:01.350460: step: 1740/527, loss: 0.05593428388237953
2023-01-24 05:44:02.412111: step: 1744/527, loss: 0.007851863279938698
2023-01-24 05:44:03.464000: step: 1748/527, loss: 0.008311571553349495
2023-01-24 05:44:04.506806: step: 1752/527, loss: 0.03206690773367882
2023-01-24 05:44:05.567510: step: 1756/527, loss: 0.013040123507380486
2023-01-24 05:44:06.604521: step: 1760/527, loss: 0.02845063805580139
2023-01-24 05:44:07.650067: step: 1764/527, loss: 0.006320222280919552
2023-01-24 05:44:08.708190: step: 1768/527, loss: 0.009972857311367989
2023-01-24 05:44:09.747134: step: 1772/527, loss: 0.003992057871073484
2023-01-24 05:44:10.801482: step: 1776/527, loss: 0.0038140942342579365
2023-01-24 05:44:11.860699: step: 1780/527, loss: 0.004188275430351496
2023-01-24 05:44:12.897981: step: 1784/527, loss: 0.008014023303985596
2023-01-24 05:44:13.949710: step: 1788/527, loss: 0.009456348605453968
2023-01-24 05:44:15.005536: step: 1792/527, loss: 0.007598466239869595
2023-01-24 05:44:16.077102: step: 1796/527, loss: 0.006078129168599844
2023-01-24 05:44:17.119169: step: 1800/527, loss: 0.026917781680822372
2023-01-24 05:44:18.170709: step: 1804/527, loss: 0.010735039599239826
2023-01-24 05:44:19.249223: step: 1808/527, loss: 0.004990758839994669
2023-01-24 05:44:20.287900: step: 1812/527, loss: 0.002181178657338023
2023-01-24 05:44:21.341479: step: 1816/527, loss: 0.0036130601074546576
2023-01-24 05:44:22.400371: step: 1820/527, loss: 0.004037720616906881
2023-01-24 05:44:23.445970: step: 1824/527, loss: 0.0014690338866785169
2023-01-24 05:44:24.496848: step: 1828/527, loss: 0.005429030396044254
2023-01-24 05:44:25.549764: step: 1832/527, loss: 0.0015013277297839522
2023-01-24 05:44:26.601466: step: 1836/527, loss: 0.010830406099557877
2023-01-24 05:44:27.642607: step: 1840/527, loss: 0.0026708939112722874
2023-01-24 05:44:28.695943: step: 1844/527, loss: 0.008172836154699326
2023-01-24 05:44:29.751691: step: 1848/527, loss: 0.03005950339138508
2023-01-24 05:44:30.812003: step: 1852/527, loss: 0.00440314831212163
2023-01-24 05:44:31.853794: step: 1856/527, loss: 1.2473748938646168e-05
2023-01-24 05:44:32.899683: step: 1860/527, loss: 0.025359120219945908
2023-01-24 05:44:33.934403: step: 1864/527, loss: 0.02318563126027584
2023-01-24 05:44:34.994534: step: 1868/527, loss: 0.0008550297934561968
2023-01-24 05:44:36.053379: step: 1872/527, loss: 0.0002936632663477212
2023-01-24 05:44:37.093996: step: 1876/527, loss: 0.017690308392047882
2023-01-24 05:44:38.156661: step: 1880/527, loss: 0.007762353401631117
2023-01-24 05:44:39.203521: step: 1884/527, loss: 0.005471579264849424
2023-01-24 05:44:40.249599: step: 1888/527, loss: 0.0071036312729120255
2023-01-24 05:44:41.303756: step: 1892/527, loss: 0.01841791905462742
2023-01-24 05:44:42.354889: step: 1896/527, loss: 0.04170481488108635
2023-01-24 05:44:43.409216: step: 1900/527, loss: 0.03876521438360214
2023-01-24 05:44:44.465646: step: 1904/527, loss: 0.0042602806352078915
2023-01-24 05:44:45.525742: step: 1908/527, loss: 0.0024893295485526323
2023-01-24 05:44:46.580216: step: 1912/527, loss: 0.01631828211247921
2023-01-24 05:44:47.610938: step: 1916/527, loss: 0.018093852326273918
2023-01-24 05:44:48.660002: step: 1920/527, loss: 0.014130670577287674
2023-01-24 05:44:49.724498: step: 1924/527, loss: 0.0051779416389763355
2023-01-24 05:44:50.756449: step: 1928/527, loss: 0.007823098450899124
2023-01-24 05:44:51.804108: step: 1932/527, loss: 0.0035974006168544292
2023-01-24 05:44:52.864518: step: 1936/527, loss: 0.011179525405168533
2023-01-24 05:44:53.915121: step: 1940/527, loss: 0.0007153789047151804
2023-01-24 05:44:54.973559: step: 1944/527, loss: 0.006225020624697208
2023-01-24 05:44:56.004131: step: 1948/527, loss: 0.01100581232458353
2023-01-24 05:44:57.056757: step: 1952/527, loss: 0.0048622265458106995
2023-01-24 05:44:58.114854: step: 1956/527, loss: 0.00982161145657301
2023-01-24 05:44:59.167676: step: 1960/527, loss: 0.010374289005994797
2023-01-24 05:45:00.205713: step: 1964/527, loss: 0.006359482649713755
2023-01-24 05:45:01.245165: step: 1968/527, loss: 0.03307987377047539
2023-01-24 05:45:02.291410: step: 1972/527, loss: 0.00792419258505106
2023-01-24 05:45:03.328823: step: 1976/527, loss: 0.013120067305862904
2023-01-24 05:45:04.377021: step: 1980/527, loss: 0.0016312769148498774
2023-01-24 05:45:05.435623: step: 1984/527, loss: 0.0024427808821201324
2023-01-24 05:45:06.520365: step: 1988/527, loss: 0.01781153678894043
2023-01-24 05:45:07.560253: step: 1992/527, loss: 0.004233812913298607
2023-01-24 05:45:08.609889: step: 1996/527, loss: 0.005162104032933712
2023-01-24 05:45:09.656315: step: 2000/527, loss: 0.004399866797029972
2023-01-24 05:45:10.711809: step: 2004/527, loss: 0.0024165452923625708
2023-01-24 05:45:11.743935: step: 2008/527, loss: 0.01303536631166935
2023-01-24 05:45:12.786813: step: 2012/527, loss: 0.00421428307890892
2023-01-24 05:45:13.832461: step: 2016/527, loss: 0.005972134880721569
2023-01-24 05:45:14.900865: step: 2020/527, loss: 0.002349003218114376
2023-01-24 05:45:15.956359: step: 2024/527, loss: 0.012383715249598026
2023-01-24 05:45:16.994162: step: 2028/527, loss: 0.004792159888893366
2023-01-24 05:45:18.047951: step: 2032/527, loss: 0.041699036955833435
2023-01-24 05:45:19.094659: step: 2036/527, loss: 0.006186272948980331
2023-01-24 05:45:20.150766: step: 2040/527, loss: 0.0013455228181555867
2023-01-24 05:45:21.198739: step: 2044/527, loss: 0.003466531168669462
2023-01-24 05:45:22.256993: step: 2048/527, loss: 0.008250934071838856
2023-01-24 05:45:23.315025: step: 2052/527, loss: 0.029534438624978065
2023-01-24 05:45:24.362330: step: 2056/527, loss: 0.008110631257295609
2023-01-24 05:45:25.407861: step: 2060/527, loss: 0.002982160309329629
2023-01-24 05:45:26.441729: step: 2064/527, loss: 0.006174801383167505
2023-01-24 05:45:27.511981: step: 2068/527, loss: 0.0038659879937767982
2023-01-24 05:45:28.555679: step: 2072/527, loss: 0.005116707645356655
2023-01-24 05:45:29.587389: step: 2076/527, loss: 0.006999629084020853
2023-01-24 05:45:30.639550: step: 2080/527, loss: 0.011560342274606228
2023-01-24 05:45:31.700221: step: 2084/527, loss: 0.023093916475772858
2023-01-24 05:45:32.751513: step: 2088/527, loss: 0.0035630809143185616
2023-01-24 05:45:33.808539: step: 2092/527, loss: 0.0036325466353446245
2023-01-24 05:45:34.854505: step: 2096/527, loss: 0.0018851844361051917
2023-01-24 05:45:35.902167: step: 2100/527, loss: 0.010529978200793266
2023-01-24 05:45:36.947277: step: 2104/527, loss: 0.0022613334003835917
2023-01-24 05:45:37.993735: step: 2108/527, loss: 0.05637083202600479
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33755960672238416, 'r': 0.32090581208332913, 'f1': 0.32902210694146783}, 'combined': 0.24243734195687103, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.372580541813228, 'r': 0.288919274696985, 'f1': 0.3254595004267112}, 'combined': 0.20829408027309512, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.355508964719491, 'r': 0.33324749254540526, 'f1': 0.344018469287813}, 'combined': 0.25348729315944113, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3738002039302855, 'r': 0.30352169147472774, 'f1': 0.335014919612707}, 'combined': 0.21440954855213246, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.358285003431709, 'r': 0.31953311501499665, 'f1': 0.3378013071472482}, 'combined': 0.24890622631902498, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3842772029371519, 'r': 0.30966367128208044, 'f1': 0.3429591594108453}, 'combined': 0.24589524637004007, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 3}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 4
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:48:07.179819: step: 4/527, loss: 0.004798795562237501
2023-01-24 05:48:08.245801: step: 8/527, loss: 0.0029309168457984924
2023-01-24 05:48:09.274180: step: 12/527, loss: 0.0011004777625203133
2023-01-24 05:48:10.325471: step: 16/527, loss: 0.014637584798038006
2023-01-24 05:48:11.368208: step: 20/527, loss: 0.01262011006474495
2023-01-24 05:48:12.450951: step: 24/527, loss: 0.01471824012696743
2023-01-24 05:48:13.521837: step: 28/527, loss: 0.01483780425041914
2023-01-24 05:48:14.580885: step: 32/527, loss: 0.005570894572883844
2023-01-24 05:48:15.650357: step: 36/527, loss: 0.0041198041290044785
2023-01-24 05:48:16.701799: step: 40/527, loss: 0.001607234706170857
2023-01-24 05:48:17.763630: step: 44/527, loss: 0.005927626509219408
2023-01-24 05:48:18.833712: step: 48/527, loss: 0.01730796881020069
2023-01-24 05:48:19.880704: step: 52/527, loss: 0.00280939182266593
2023-01-24 05:48:20.953227: step: 56/527, loss: 0.008762883022427559
2023-01-24 05:48:22.005394: step: 60/527, loss: 0.03321302309632301
2023-01-24 05:48:23.037791: step: 64/527, loss: 0.0030898000113666058
2023-01-24 05:48:24.082206: step: 68/527, loss: 0.005210083909332752
2023-01-24 05:48:25.123196: step: 72/527, loss: 0.015607021749019623
2023-01-24 05:48:26.182674: step: 76/527, loss: 0.03765184059739113
2023-01-24 05:48:27.256247: step: 80/527, loss: 0.006425447762012482
2023-01-24 05:48:28.303544: step: 84/527, loss: 0.007916656322777271
2023-01-24 05:48:29.350596: step: 88/527, loss: 0.003766612382605672
2023-01-24 05:48:30.411222: step: 92/527, loss: 0.010192527435719967
2023-01-24 05:48:31.469095: step: 96/527, loss: 0.0017012403113767505
2023-01-24 05:48:32.520562: step: 100/527, loss: 0.007971801795065403
2023-01-24 05:48:33.567997: step: 104/527, loss: 0.0047422912903130054
2023-01-24 05:48:34.630776: step: 108/527, loss: 0.006395967677235603
2023-01-24 05:48:35.670479: step: 112/527, loss: 0.011883337050676346
2023-01-24 05:48:36.717304: step: 116/527, loss: 0.005027411971241236
2023-01-24 05:48:37.784398: step: 120/527, loss: 0.0009183065267279744
2023-01-24 05:48:38.834275: step: 124/527, loss: 0.020124750211834908
2023-01-24 05:48:39.883938: step: 128/527, loss: 0.004020323511213064
2023-01-24 05:48:40.945554: step: 132/527, loss: 0.006376670673489571
2023-01-24 05:48:42.003864: step: 136/527, loss: 0.003969069104641676
2023-01-24 05:48:43.059346: step: 140/527, loss: 0.004379172809422016
2023-01-24 05:48:44.108051: step: 144/527, loss: 0.034320998936891556
2023-01-24 05:48:45.160482: step: 148/527, loss: 0.004560271743685007
2023-01-24 05:48:46.224128: step: 152/527, loss: 0.011144979856908321
2023-01-24 05:48:47.298987: step: 156/527, loss: 0.02316906489431858
2023-01-24 05:48:48.342821: step: 160/527, loss: 0.00314704654738307
2023-01-24 05:48:49.393291: step: 164/527, loss: 0.05408405140042305
2023-01-24 05:48:50.438631: step: 168/527, loss: 0.0041894447058439255
2023-01-24 05:48:51.492937: step: 172/527, loss: 0.02124343253672123
2023-01-24 05:48:52.557182: step: 176/527, loss: 0.007926053367555141
2023-01-24 05:48:53.601096: step: 180/527, loss: 0.025341147556900978
2023-01-24 05:48:54.664881: step: 184/527, loss: 0.01771632768213749
2023-01-24 05:48:55.719515: step: 188/527, loss: 0.003960701171308756
2023-01-24 05:48:56.767242: step: 192/527, loss: 0.013658388517796993
2023-01-24 05:48:57.833080: step: 196/527, loss: 0.012370912358164787
2023-01-24 05:48:58.888462: step: 200/527, loss: 0.01231129840016365
2023-01-24 05:48:59.945907: step: 204/527, loss: 0.000923582527320832
2023-01-24 05:49:00.992926: step: 208/527, loss: 0.015850689262151718
2023-01-24 05:49:02.052240: step: 212/527, loss: 0.050579167902469635
2023-01-24 05:49:03.101378: step: 216/527, loss: 0.0015516100684180856
2023-01-24 05:49:04.163306: step: 220/527, loss: 0.003035517642274499
2023-01-24 05:49:05.209989: step: 224/527, loss: 0.004313284531235695
2023-01-24 05:49:06.268730: step: 228/527, loss: 0.009695312939584255
2023-01-24 05:49:07.322344: step: 232/527, loss: 0.022842252627015114
2023-01-24 05:49:08.367937: step: 236/527, loss: 0.0045544798485934734
2023-01-24 05:49:09.432639: step: 240/527, loss: 0.027661394327878952
2023-01-24 05:49:10.490991: step: 244/527, loss: 0.01109894085675478
2023-01-24 05:49:11.548221: step: 248/527, loss: 0.03341621533036232
2023-01-24 05:49:12.602780: step: 252/527, loss: 0.012176484800875187
2023-01-24 05:49:13.665865: step: 256/527, loss: 0.004430671222507954
2023-01-24 05:49:14.750244: step: 260/527, loss: 0.003769872710108757
2023-01-24 05:49:15.803513: step: 264/527, loss: 0.0009316790965385735
2023-01-24 05:49:16.837962: step: 268/527, loss: 0.017801864072680473
2023-01-24 05:49:17.882333: step: 272/527, loss: 0.009023908525705338
2023-01-24 05:49:18.942904: step: 276/527, loss: 0.004498614463955164
2023-01-24 05:49:19.981765: step: 280/527, loss: 0.0053957137279212475
2023-01-24 05:49:21.034197: step: 284/527, loss: 0.012265692465007305
2023-01-24 05:49:22.090466: step: 288/527, loss: 0.04098077490925789
2023-01-24 05:49:23.149444: step: 292/527, loss: 0.0038089097943156958
2023-01-24 05:49:24.212358: step: 296/527, loss: 0.00184653012547642
2023-01-24 05:49:25.265958: step: 300/527, loss: 0.013015697710216045
2023-01-24 05:49:26.322274: step: 304/527, loss: 0.013965689577162266
2023-01-24 05:49:27.363662: step: 308/527, loss: 0.020143380388617516
2023-01-24 05:49:28.424966: step: 312/527, loss: 0.0039999233558773994
2023-01-24 05:49:29.464652: step: 316/527, loss: 0.0055448804050683975
2023-01-24 05:49:30.529898: step: 320/527, loss: 0.006654916796833277
2023-01-24 05:49:31.587976: step: 324/527, loss: 0.004255559295415878
2023-01-24 05:49:32.643953: step: 328/527, loss: 0.005554490722715855
2023-01-24 05:49:33.688401: step: 332/527, loss: 0.004568501841276884
2023-01-24 05:49:34.729315: step: 336/527, loss: 0.005421648267656565
2023-01-24 05:49:35.785940: step: 340/527, loss: 0.0110981035977602
2023-01-24 05:49:36.828252: step: 344/527, loss: 0.008874951861798763
2023-01-24 05:49:37.866069: step: 348/527, loss: 0.0033424256835132837
2023-01-24 05:49:38.918360: step: 352/527, loss: 0.01518099382519722
2023-01-24 05:49:39.975051: step: 356/527, loss: 0.007731577381491661
2023-01-24 05:49:41.023227: step: 360/527, loss: 0.013318195939064026
2023-01-24 05:49:42.070982: step: 364/527, loss: 0.0269757229834795
2023-01-24 05:49:43.139824: step: 368/527, loss: 0.0055317347869277
2023-01-24 05:49:44.198796: step: 372/527, loss: 0.01124410331249237
2023-01-24 05:49:45.253597: step: 376/527, loss: 0.0033939657732844353
2023-01-24 05:49:46.296173: step: 380/527, loss: 0.004648104310035706
2023-01-24 05:49:47.346106: step: 384/527, loss: 0.012351693585515022
2023-01-24 05:49:48.412531: step: 388/527, loss: 0.034307222813367844
2023-01-24 05:49:49.472469: step: 392/527, loss: 0.02188608981668949
2023-01-24 05:49:50.542924: step: 396/527, loss: 0.00450518075376749
2023-01-24 05:49:51.583811: step: 400/527, loss: 0.002653697971254587
2023-01-24 05:49:52.624067: step: 404/527, loss: 3.119441316812299e-05
2023-01-24 05:49:53.677202: step: 408/527, loss: 0.0036495416425168514
2023-01-24 05:49:54.734737: step: 412/527, loss: 0.0007335481350310147
2023-01-24 05:49:55.797892: step: 416/527, loss: 0.03987220674753189
2023-01-24 05:49:56.852127: step: 420/527, loss: 0.009604169055819511
2023-01-24 05:49:57.906437: step: 424/527, loss: 0.008431042544543743
2023-01-24 05:49:58.967702: step: 428/527, loss: 0.033479176461696625
2023-01-24 05:50:00.018080: step: 432/527, loss: 0.027300521731376648
2023-01-24 05:50:01.069497: step: 436/527, loss: 0.007673206273466349
2023-01-24 05:50:02.123768: step: 440/527, loss: 0.004509297665208578
2023-01-24 05:50:03.172897: step: 444/527, loss: 0.009341058321297169
2023-01-24 05:50:04.220889: step: 448/527, loss: 0.002177347196266055
2023-01-24 05:50:05.271869: step: 452/527, loss: 0.02137337252497673
2023-01-24 05:50:06.311157: step: 456/527, loss: 0.0025187835562974215
2023-01-24 05:50:07.361517: step: 460/527, loss: 0.01424535270780325
2023-01-24 05:50:08.414002: step: 464/527, loss: 0.02961236983537674
2023-01-24 05:50:09.464369: step: 468/527, loss: 0.014148181304335594
2023-01-24 05:50:10.526412: step: 472/527, loss: 0.003883884521201253
2023-01-24 05:50:11.585795: step: 476/527, loss: 0.013511565513908863
2023-01-24 05:50:12.635759: step: 480/527, loss: 0.010334148071706295
2023-01-24 05:50:13.686744: step: 484/527, loss: 0.0026350081898272038
2023-01-24 05:50:14.730507: step: 488/527, loss: 0.016213631257414818
2023-01-24 05:50:15.784450: step: 492/527, loss: 0.006265159696340561
2023-01-24 05:50:16.818590: step: 496/527, loss: 0.003069190541282296
2023-01-24 05:50:17.880386: step: 500/527, loss: 0.006416722200810909
2023-01-24 05:50:18.924228: step: 504/527, loss: 0.0011410184670239687
2023-01-24 05:50:19.956127: step: 508/527, loss: 0.02092679776251316
2023-01-24 05:50:21.011626: step: 512/527, loss: 0.00888666883111
2023-01-24 05:50:22.063810: step: 516/527, loss: 0.008873362094163895
2023-01-24 05:50:23.116087: step: 520/527, loss: 0.008417917415499687
2023-01-24 05:50:24.162401: step: 524/527, loss: 0.005173789337277412
2023-01-24 05:50:25.214328: step: 528/527, loss: 0.009263423271477222
2023-01-24 05:50:26.260733: step: 532/527, loss: 0.011409972794353962
2023-01-24 05:50:27.316579: step: 536/527, loss: 0.030294368043541908
2023-01-24 05:50:28.356124: step: 540/527, loss: 0.004879303276538849
2023-01-24 05:50:29.400269: step: 544/527, loss: 0.04425245523452759
2023-01-24 05:50:30.443269: step: 548/527, loss: 0.0044807796366512775
2023-01-24 05:50:31.498245: step: 552/527, loss: 0.02414599061012268
2023-01-24 05:50:32.546431: step: 556/527, loss: 0.005646579433232546
2023-01-24 05:50:33.587284: step: 560/527, loss: 0.02515777014195919
2023-01-24 05:50:34.638763: step: 564/527, loss: 0.018965693190693855
2023-01-24 05:50:35.695287: step: 568/527, loss: 0.0115940161049366
2023-01-24 05:50:36.762133: step: 572/527, loss: 0.021791767328977585
2023-01-24 05:50:37.801821: step: 576/527, loss: 0.007542330306023359
2023-01-24 05:50:38.857332: step: 580/527, loss: 0.010915880091488361
2023-01-24 05:50:39.907735: step: 584/527, loss: 0.0016205202555283904
2023-01-24 05:50:40.972602: step: 588/527, loss: 0.004844542592763901
2023-01-24 05:50:42.030522: step: 592/527, loss: 0.004172665532678366
2023-01-24 05:50:43.087407: step: 596/527, loss: 0.005101096350699663
2023-01-24 05:50:44.140463: step: 600/527, loss: 0.0026512285694479942
2023-01-24 05:50:45.178934: step: 604/527, loss: 0.0021779858507215977
2023-01-24 05:50:46.226562: step: 608/527, loss: 0.005923046264797449
2023-01-24 05:50:47.281744: step: 612/527, loss: 0.0003572655259631574
2023-01-24 05:50:48.338825: step: 616/527, loss: 0.005643285345286131
2023-01-24 05:50:49.390495: step: 620/527, loss: 0.003275799797847867
2023-01-24 05:50:50.447646: step: 624/527, loss: 0.017841234803199768
2023-01-24 05:50:51.496843: step: 628/527, loss: 0.008541619405150414
2023-01-24 05:50:52.533720: step: 632/527, loss: 0.0028953668661415577
2023-01-24 05:50:53.575805: step: 636/527, loss: 0.0056040650233626366
2023-01-24 05:50:54.639374: step: 640/527, loss: 0.003257660660892725
2023-01-24 05:50:55.711959: step: 644/527, loss: 0.011811007745563984
2023-01-24 05:50:56.770589: step: 648/527, loss: 0.002472582971677184
2023-01-24 05:50:57.807118: step: 652/527, loss: 0.035941798239946365
2023-01-24 05:50:58.860897: step: 656/527, loss: 0.0047346120700240135
2023-01-24 05:50:59.910422: step: 660/527, loss: 0.02992715686559677
2023-01-24 05:51:00.954878: step: 664/527, loss: 0.002437981776893139
2023-01-24 05:51:01.991336: step: 668/527, loss: 0.0063609168864786625
2023-01-24 05:51:03.050851: step: 672/527, loss: 0.004914470948278904
2023-01-24 05:51:04.103063: step: 676/527, loss: 0.0037450063973665237
2023-01-24 05:51:05.156415: step: 680/527, loss: 0.007549316622316837
2023-01-24 05:51:06.215703: step: 684/527, loss: 0.0010297569679096341
2023-01-24 05:51:07.260919: step: 688/527, loss: 0.003464050590991974
2023-01-24 05:51:08.313092: step: 692/527, loss: 0.014582104049623013
2023-01-24 05:51:09.382126: step: 696/527, loss: 0.004058813210576773
2023-01-24 05:51:10.432450: step: 700/527, loss: 0.016312744468450546
2023-01-24 05:51:11.480980: step: 704/527, loss: 0.015867892652750015
2023-01-24 05:51:12.545889: step: 708/527, loss: 0.00382168497890234
2023-01-24 05:51:13.591221: step: 712/527, loss: 0.004260249435901642
2023-01-24 05:51:14.638322: step: 716/527, loss: 0.006121458951383829
2023-01-24 05:51:15.687826: step: 720/527, loss: 0.004989981651306152
2023-01-24 05:51:16.737114: step: 724/527, loss: 0.011474031955003738
2023-01-24 05:51:17.771471: step: 728/527, loss: 0.001981210894882679
2023-01-24 05:51:18.830785: step: 732/527, loss: 0.016398560255765915
2023-01-24 05:51:19.909406: step: 736/527, loss: 0.033520765602588654
2023-01-24 05:51:20.949143: step: 740/527, loss: 0.010036283172667027
2023-01-24 05:51:21.992746: step: 744/527, loss: 0.006581769324839115
2023-01-24 05:51:23.047722: step: 748/527, loss: 0.0044938949868083
2023-01-24 05:51:24.089476: step: 752/527, loss: 0.00012804719153791666
2023-01-24 05:51:25.151427: step: 756/527, loss: 0.0044247424229979515
2023-01-24 05:51:26.196740: step: 760/527, loss: 0.0003996891318820417
2023-01-24 05:51:27.272274: step: 764/527, loss: 0.016622699797153473
2023-01-24 05:51:28.323673: step: 768/527, loss: 0.02555469051003456
2023-01-24 05:51:29.377841: step: 772/527, loss: 0.008782824501395226
2023-01-24 05:51:30.426298: step: 776/527, loss: 0.019817352294921875
2023-01-24 05:51:31.467104: step: 780/527, loss: 0.012991409748792648
2023-01-24 05:51:32.537380: step: 784/527, loss: 0.007173345889896154
2023-01-24 05:51:33.590375: step: 788/527, loss: 0.006991872098296881
2023-01-24 05:51:34.634396: step: 792/527, loss: 0.025888260453939438
2023-01-24 05:51:35.678359: step: 796/527, loss: 0.01478448137640953
2023-01-24 05:51:36.745501: step: 800/527, loss: 0.007971160113811493
2023-01-24 05:51:37.801566: step: 804/527, loss: 0.01862054504454136
2023-01-24 05:51:38.859452: step: 808/527, loss: 0.007140390574932098
2023-01-24 05:51:39.932021: step: 812/527, loss: 0.013608364388346672
2023-01-24 05:51:40.980565: step: 816/527, loss: 0.0107984384521842
2023-01-24 05:51:42.036104: step: 820/527, loss: 0.028694182634353638
2023-01-24 05:51:43.095566: step: 824/527, loss: 0.007930814288556576
2023-01-24 05:51:44.161162: step: 828/527, loss: 0.022879892960190773
2023-01-24 05:51:45.197669: step: 832/527, loss: 0.014855567365884781
2023-01-24 05:51:46.247138: step: 836/527, loss: 0.024786897003650665
2023-01-24 05:51:47.311352: step: 840/527, loss: 0.006193472072482109
2023-01-24 05:51:48.356946: step: 844/527, loss: 0.029054781422019005
2023-01-24 05:51:49.380050: step: 848/527, loss: 0.016979951411485672
2023-01-24 05:51:50.429067: step: 852/527, loss: 0.011195342987775803
2023-01-24 05:51:51.474848: step: 856/527, loss: 0.0110057033598423
2023-01-24 05:51:52.527774: step: 860/527, loss: 0.005805686116218567
2023-01-24 05:51:53.576488: step: 864/527, loss: 0.0028822796884924173
2023-01-24 05:51:54.633169: step: 868/527, loss: 0.017254924401640892
2023-01-24 05:51:55.676781: step: 872/527, loss: 0.06004353240132332
2023-01-24 05:51:56.720420: step: 876/527, loss: 0.014923245646059513
2023-01-24 05:51:57.762904: step: 880/527, loss: 0.008303902111947536
2023-01-24 05:51:58.808378: step: 884/527, loss: 0.007086020428687334
2023-01-24 05:51:59.850712: step: 888/527, loss: 0.007097942288964987
2023-01-24 05:52:00.892960: step: 892/527, loss: 0.002108887070789933
2023-01-24 05:52:01.921088: step: 896/527, loss: 0.007246498018503189
2023-01-24 05:52:02.968156: step: 900/527, loss: 0.03540923818945885
2023-01-24 05:52:04.022333: step: 904/527, loss: 0.014381722547113895
2023-01-24 05:52:05.061630: step: 908/527, loss: 0.00739369448274374
2023-01-24 05:52:06.101264: step: 912/527, loss: 0.012750803492963314
2023-01-24 05:52:07.170819: step: 916/527, loss: 0.007424303330481052
2023-01-24 05:52:08.213490: step: 920/527, loss: 0.02110300585627556
2023-01-24 05:52:09.243390: step: 924/527, loss: 0.013303983956575394
2023-01-24 05:52:10.300699: step: 928/527, loss: 0.006884288974106312
2023-01-24 05:52:11.366601: step: 932/527, loss: 0.011327382177114487
2023-01-24 05:52:12.413835: step: 936/527, loss: 0.002374954055994749
2023-01-24 05:52:13.471338: step: 940/527, loss: 0.00717934500426054
2023-01-24 05:52:14.520806: step: 944/527, loss: 0.02322743646800518
2023-01-24 05:52:15.565806: step: 948/527, loss: 0.006958703976124525
2023-01-24 05:52:16.608908: step: 952/527, loss: 0.0018137339502573013
2023-01-24 05:52:17.653647: step: 956/527, loss: 0.006922414526343346
2023-01-24 05:52:18.710621: step: 960/527, loss: 0.008034479804337025
2023-01-24 05:52:19.777661: step: 964/527, loss: 0.005844409111887217
2023-01-24 05:52:20.830677: step: 968/527, loss: 0.03279508650302887
2023-01-24 05:52:21.868657: step: 972/527, loss: 0.022560451179742813
2023-01-24 05:52:22.924819: step: 976/527, loss: 0.002702136058360338
2023-01-24 05:52:23.999762: step: 980/527, loss: 0.032179586589336395
2023-01-24 05:52:25.050859: step: 984/527, loss: 0.0238084327429533
2023-01-24 05:52:26.098507: step: 988/527, loss: 0.016198376193642616
2023-01-24 05:52:27.143793: step: 992/527, loss: 0.00468091294169426
2023-01-24 05:52:28.194296: step: 996/527, loss: 0.005705349612981081
2023-01-24 05:52:29.250301: step: 1000/527, loss: 0.012686754576861858
2023-01-24 05:52:30.288888: step: 1004/527, loss: 0.0036708025727421045
2023-01-24 05:52:31.349676: step: 1008/527, loss: 0.011974627152085304
2023-01-24 05:52:32.392720: step: 1012/527, loss: 0.0050416444428265095
2023-01-24 05:52:33.446061: step: 1016/527, loss: 0.005563591606914997
2023-01-24 05:52:34.486883: step: 1020/527, loss: 0.00893318559974432
2023-01-24 05:52:35.544680: step: 1024/527, loss: 0.004403574857860804
2023-01-24 05:52:36.579562: step: 1028/527, loss: 0.006151125766336918
2023-01-24 05:52:37.609848: step: 1032/527, loss: 0.00041893532034009695
2023-01-24 05:52:38.667401: step: 1036/527, loss: 0.004295796155929565
2023-01-24 05:52:39.716058: step: 1040/527, loss: 0.008454680442810059
2023-01-24 05:52:40.767668: step: 1044/527, loss: 0.02144450508058071
2023-01-24 05:52:41.812154: step: 1048/527, loss: 0.013071775436401367
2023-01-24 05:52:42.860976: step: 1052/527, loss: 0.007843488827347755
2023-01-24 05:52:43.902500: step: 1056/527, loss: 0.02198074199259281
2023-01-24 05:52:44.958798: step: 1060/527, loss: 0.006096964236348867
2023-01-24 05:52:46.023932: step: 1064/527, loss: 0.011427431367337704
2023-01-24 05:52:47.055691: step: 1068/527, loss: 0.01927776262164116
2023-01-24 05:52:48.100943: step: 1072/527, loss: 0.005857015494257212
2023-01-24 05:52:49.165746: step: 1076/527, loss: 0.002251280937343836
2023-01-24 05:52:50.202598: step: 1080/527, loss: 0.0239707138389349
2023-01-24 05:52:51.268010: step: 1084/527, loss: 0.022794032469391823
2023-01-24 05:52:52.307107: step: 1088/527, loss: 0.0021768512669950724
2023-01-24 05:52:53.343788: step: 1092/527, loss: 0.0073958998546004295
2023-01-24 05:52:54.399997: step: 1096/527, loss: 0.09977622330188751
2023-01-24 05:52:55.441071: step: 1100/527, loss: 0.00838471483439207
2023-01-24 05:52:56.488838: step: 1104/527, loss: 0.037144169211387634
2023-01-24 05:52:57.551421: step: 1108/527, loss: 0.0156878512352705
2023-01-24 05:52:58.629993: step: 1112/527, loss: 0.001348948571830988
2023-01-24 05:52:59.695953: step: 1116/527, loss: 0.02171880006790161
2023-01-24 05:53:00.733081: step: 1120/527, loss: 0.007988469675183296
2023-01-24 05:53:01.786395: step: 1124/527, loss: 0.007513338699936867
2023-01-24 05:53:02.853834: step: 1128/527, loss: 0.005066821817308664
2023-01-24 05:53:03.915494: step: 1132/527, loss: 0.006134570576250553
2023-01-24 05:53:04.963827: step: 1136/527, loss: 0.024731654673814774
2023-01-24 05:53:06.000323: step: 1140/527, loss: 0.0020646771881729364
2023-01-24 05:53:07.065853: step: 1144/527, loss: 0.012673301622271538
2023-01-24 05:53:08.099044: step: 1148/527, loss: 0.010123465210199356
2023-01-24 05:53:09.158570: step: 1152/527, loss: 0.006663178559392691
2023-01-24 05:53:10.199685: step: 1156/527, loss: 0.008794235065579414
2023-01-24 05:53:11.253826: step: 1160/527, loss: 0.0056288582272827625
2023-01-24 05:53:12.315751: step: 1164/527, loss: 0.007989570498466492
2023-01-24 05:53:13.359890: step: 1168/527, loss: 0.009098177775740623
2023-01-24 05:53:14.398768: step: 1172/527, loss: 0.008912991732358932
2023-01-24 05:53:15.449504: step: 1176/527, loss: 0.004241116810590029
2023-01-24 05:53:16.498716: step: 1180/527, loss: 0.004711063113063574
2023-01-24 05:53:17.574423: step: 1184/527, loss: 0.0161958746612072
2023-01-24 05:53:18.627385: step: 1188/527, loss: 0.03359711915254593
2023-01-24 05:53:19.707183: step: 1192/527, loss: 0.0030436310917139053
2023-01-24 05:53:20.772496: step: 1196/527, loss: 0.014609329402446747
2023-01-24 05:53:21.818955: step: 1200/527, loss: 0.0043011498637497425
2023-01-24 05:53:22.872435: step: 1204/527, loss: 0.012104524299502373
2023-01-24 05:53:23.940918: step: 1208/527, loss: 0.002537710592150688
2023-01-24 05:53:24.976355: step: 1212/527, loss: 0.006075495854020119
2023-01-24 05:53:26.025555: step: 1216/527, loss: 0.03430553898215294
2023-01-24 05:53:27.077656: step: 1220/527, loss: 0.009878157638013363
2023-01-24 05:53:28.128017: step: 1224/527, loss: 0.0021241381764411926
2023-01-24 05:53:29.177662: step: 1228/527, loss: 0.016044380143284798
2023-01-24 05:53:30.223103: step: 1232/527, loss: 0.03437155857682228
2023-01-24 05:53:31.266244: step: 1236/527, loss: 0.009187907911837101
2023-01-24 05:53:32.318040: step: 1240/527, loss: 0.026836981996893883
2023-01-24 05:53:33.364668: step: 1244/527, loss: 0.02395525947213173
2023-01-24 05:53:34.411957: step: 1248/527, loss: 0.037901222705841064
2023-01-24 05:53:35.481520: step: 1252/527, loss: 0.0072151361964643
2023-01-24 05:53:36.527667: step: 1256/527, loss: 0.011878948658704758
2023-01-24 05:53:37.564950: step: 1260/527, loss: 0.03061460517346859
2023-01-24 05:53:38.624803: step: 1264/527, loss: 0.03187352418899536
2023-01-24 05:53:39.691780: step: 1268/527, loss: 0.014175578020513058
2023-01-24 05:53:40.758055: step: 1272/527, loss: 0.016100579872727394
2023-01-24 05:53:41.814801: step: 1276/527, loss: 0.004758130759000778
2023-01-24 05:53:42.881113: step: 1280/527, loss: 0.009700021706521511
2023-01-24 05:53:43.940797: step: 1284/527, loss: 0.013814649544656277
2023-01-24 05:53:45.008730: step: 1288/527, loss: 0.008729923516511917
2023-01-24 05:53:46.072355: step: 1292/527, loss: 0.0033721658401191235
2023-01-24 05:53:47.146651: step: 1296/527, loss: 0.03465705364942551
2023-01-24 05:53:48.191796: step: 1300/527, loss: 0.0037103756330907345
2023-01-24 05:53:49.256137: step: 1304/527, loss: 0.009560495615005493
2023-01-24 05:53:50.293443: step: 1308/527, loss: 0.00837091263383627
2023-01-24 05:53:51.338171: step: 1312/527, loss: 0.00782929826527834
2023-01-24 05:53:52.400234: step: 1316/527, loss: 0.00788565631955862
2023-01-24 05:53:53.450448: step: 1320/527, loss: 0.03325852006673813
2023-01-24 05:53:54.510437: step: 1324/527, loss: 0.013403902761638165
2023-01-24 05:53:55.555315: step: 1328/527, loss: 0.001752275973558426
2023-01-24 05:53:56.621612: step: 1332/527, loss: 0.015953881666064262
2023-01-24 05:53:57.670299: step: 1336/527, loss: 0.03616141527891159
2023-01-24 05:53:58.721193: step: 1340/527, loss: 0.04026893898844719
2023-01-24 05:53:59.778459: step: 1344/527, loss: 0.01275169663131237
2023-01-24 05:54:00.846312: step: 1348/527, loss: 0.008130903355777264
2023-01-24 05:54:01.907228: step: 1352/527, loss: 0.0037108901888132095
2023-01-24 05:54:02.965099: step: 1356/527, loss: 0.026075756177306175
2023-01-24 05:54:04.020231: step: 1360/527, loss: 0.0015174155123531818
2023-01-24 05:54:05.068747: step: 1364/527, loss: 0.007370895706117153
2023-01-24 05:54:06.128194: step: 1368/527, loss: 0.014556348323822021
2023-01-24 05:54:07.176492: step: 1372/527, loss: 0.009829215705394745
2023-01-24 05:54:08.256339: step: 1376/527, loss: 0.006865905597805977
2023-01-24 05:54:09.332703: step: 1380/527, loss: 0.007092609070241451
2023-01-24 05:54:10.397108: step: 1384/527, loss: 0.037890467792749405
2023-01-24 05:54:11.443066: step: 1388/527, loss: 0.016621911898255348
2023-01-24 05:54:12.487657: step: 1392/527, loss: 0.0073476312682032585
2023-01-24 05:54:13.550692: step: 1396/527, loss: 0.017868949100375175
2023-01-24 05:54:14.598576: step: 1400/527, loss: 0.01745520532131195
2023-01-24 05:54:15.649975: step: 1404/527, loss: 0.01043170876801014
2023-01-24 05:54:16.723941: step: 1408/527, loss: 0.033055443316698074
2023-01-24 05:54:17.790618: step: 1412/527, loss: 0.06796393543481827
2023-01-24 05:54:18.843744: step: 1416/527, loss: 0.005566603038460016
2023-01-24 05:54:19.904799: step: 1420/527, loss: 0.0189081858843565
2023-01-24 05:54:20.959149: step: 1424/527, loss: 0.013220678083598614
2023-01-24 05:54:22.017962: step: 1428/527, loss: 0.010770805180072784
2023-01-24 05:54:23.056305: step: 1432/527, loss: 0.0138105982914567
2023-01-24 05:54:24.110153: step: 1436/527, loss: 0.010265029966831207
2023-01-24 05:54:25.171787: step: 1440/527, loss: 0.08747374266386032
2023-01-24 05:54:26.240487: step: 1444/527, loss: 0.004809635691344738
2023-01-24 05:54:27.290937: step: 1448/527, loss: 0.0032816233579069376
2023-01-24 05:54:28.363235: step: 1452/527, loss: 0.0036028623580932617
2023-01-24 05:54:29.428585: step: 1456/527, loss: 0.009788953699171543
2023-01-24 05:54:30.478195: step: 1460/527, loss: 0.009355951100587845
2023-01-24 05:54:31.546204: step: 1464/527, loss: 0.005973074119538069
2023-01-24 05:54:32.593893: step: 1468/527, loss: 0.04549450799822807
2023-01-24 05:54:33.657462: step: 1472/527, loss: 0.024780411273241043
2023-01-24 05:54:34.711941: step: 1476/527, loss: 0.028518397361040115
2023-01-24 05:54:35.790511: step: 1480/527, loss: 0.002183921867981553
2023-01-24 05:54:36.841707: step: 1484/527, loss: 0.010395008139312267
2023-01-24 05:54:37.900976: step: 1488/527, loss: 0.0060562510043382645
2023-01-24 05:54:38.960343: step: 1492/527, loss: 0.007435582112520933
2023-01-24 05:54:40.014259: step: 1496/527, loss: 0.0027978983707726
2023-01-24 05:54:41.064635: step: 1500/527, loss: 0.006862413138151169
2023-01-24 05:54:42.111128: step: 1504/527, loss: 0.011185969226062298
2023-01-24 05:54:43.149265: step: 1508/527, loss: 0.02064533531665802
2023-01-24 05:54:44.201960: step: 1512/527, loss: 0.021287381649017334
2023-01-24 05:54:45.254355: step: 1516/527, loss: 0.008476035669445992
2023-01-24 05:54:46.311642: step: 1520/527, loss: 0.004403266590088606
2023-01-24 05:54:47.359378: step: 1524/527, loss: 0.003930867649614811
2023-01-24 05:54:48.412641: step: 1528/527, loss: 0.005387548822909594
2023-01-24 05:54:49.463652: step: 1532/527, loss: 0.004389140289276838
2023-01-24 05:54:50.530164: step: 1536/527, loss: 0.010187477804720402
2023-01-24 05:54:51.573506: step: 1540/527, loss: 0.02456819824874401
2023-01-24 05:54:52.622447: step: 1544/527, loss: 0.004405968822538853
2023-01-24 05:54:53.667001: step: 1548/527, loss: 0.03128984570503235
2023-01-24 05:54:54.724843: step: 1552/527, loss: 0.005347860511392355
2023-01-24 05:54:55.791312: step: 1556/527, loss: 0.02187165431678295
2023-01-24 05:54:56.849170: step: 1560/527, loss: 0.0018834836082533002
2023-01-24 05:54:57.895374: step: 1564/527, loss: 0.0028059252072125673
2023-01-24 05:54:58.965021: step: 1568/527, loss: 0.036271851509809494
2023-01-24 05:55:00.011421: step: 1572/527, loss: 9.282708924729377e-05
2023-01-24 05:55:01.079472: step: 1576/527, loss: 0.006122369319200516
2023-01-24 05:55:02.128594: step: 1580/527, loss: 0.0030074601527303457
2023-01-24 05:55:03.183688: step: 1584/527, loss: 0.01225368957966566
2023-01-24 05:55:04.225744: step: 1588/527, loss: 0.009725715965032578
2023-01-24 05:55:05.267844: step: 1592/527, loss: 0.03296318277716637
2023-01-24 05:55:06.318397: step: 1596/527, loss: 0.0022004502825438976
2023-01-24 05:55:07.372483: step: 1600/527, loss: 0.012196688912808895
2023-01-24 05:55:08.403961: step: 1604/527, loss: 0.0054717231541872025
2023-01-24 05:55:09.467411: step: 1608/527, loss: 0.020669111981987953
2023-01-24 05:55:10.513251: step: 1612/527, loss: 0.014488261193037033
2023-01-24 05:55:11.567719: step: 1616/527, loss: 0.012031824328005314
2023-01-24 05:55:12.620074: step: 1620/527, loss: 0.003091371851041913
2023-01-24 05:55:13.671335: step: 1624/527, loss: 0.013397125527262688
2023-01-24 05:55:14.735365: step: 1628/527, loss: 0.009961170144379139
2023-01-24 05:55:15.792498: step: 1632/527, loss: 0.0032252143137156963
2023-01-24 05:55:16.850397: step: 1636/527, loss: 0.083075612783432
2023-01-24 05:55:17.896206: step: 1640/527, loss: 0.0017018612707033753
2023-01-24 05:55:18.935700: step: 1644/527, loss: 0.002244790317490697
2023-01-24 05:55:19.999746: step: 1648/527, loss: 0.019958626478910446
2023-01-24 05:55:21.049331: step: 1652/527, loss: 0.0018631464336067438
2023-01-24 05:55:22.092103: step: 1656/527, loss: 0.004147750791162252
2023-01-24 05:55:23.146316: step: 1660/527, loss: 0.005792287643998861
2023-01-24 05:55:24.199306: step: 1664/527, loss: 0.004970904439687729
2023-01-24 05:55:25.249687: step: 1668/527, loss: 0.03062223643064499
2023-01-24 05:55:26.291798: step: 1672/527, loss: 0.005043509881943464
2023-01-24 05:55:27.338443: step: 1676/527, loss: 0.0039184922352433205
2023-01-24 05:55:28.393651: step: 1680/527, loss: 0.023870836943387985
2023-01-24 05:55:29.445752: step: 1684/527, loss: 0.0137215880677104
2023-01-24 05:55:30.491462: step: 1688/527, loss: 0.016430791467428207
2023-01-24 05:55:31.552161: step: 1692/527, loss: 0.07737080752849579
2023-01-24 05:55:32.602020: step: 1696/527, loss: 0.01367567852139473
2023-01-24 05:55:33.666806: step: 1700/527, loss: 0.03803643211722374
2023-01-24 05:55:34.707051: step: 1704/527, loss: 0.0014364771777763963
2023-01-24 05:55:35.741267: step: 1708/527, loss: 0.022895200178027153
2023-01-24 05:55:36.795871: step: 1712/527, loss: 0.009638975374400616
2023-01-24 05:55:37.852176: step: 1716/527, loss: 0.007268958725035191
2023-01-24 05:55:38.898058: step: 1720/527, loss: 0.008098487742245197
2023-01-24 05:55:39.946159: step: 1724/527, loss: 0.009427439421415329
2023-01-24 05:55:40.991124: step: 1728/527, loss: 0.00845731794834137
2023-01-24 05:55:42.042450: step: 1732/527, loss: 0.003358046058565378
2023-01-24 05:55:43.095349: step: 1736/527, loss: 0.00312783638946712
2023-01-24 05:55:44.149686: step: 1740/527, loss: 0.0025260988622903824
2023-01-24 05:55:45.195263: step: 1744/527, loss: 0.006439708638936281
2023-01-24 05:55:46.250306: step: 1748/527, loss: 0.008595471270382404
2023-01-24 05:55:47.304495: step: 1752/527, loss: 0.02937445417046547
2023-01-24 05:55:48.359939: step: 1756/527, loss: 0.07778147608041763
2023-01-24 05:55:49.459572: step: 1760/527, loss: 0.007810445036739111
2023-01-24 05:55:50.510314: step: 1764/527, loss: 0.016113916411995888
2023-01-24 05:55:51.547343: step: 1768/527, loss: 0.015464873984456062
2023-01-24 05:55:52.594154: step: 1772/527, loss: 0.05303625389933586
2023-01-24 05:55:53.631388: step: 1776/527, loss: 0.0011791265569627285
2023-01-24 05:55:54.676261: step: 1780/527, loss: 0.019628018140792847
2023-01-24 05:55:55.715114: step: 1784/527, loss: 0.002410472836345434
2023-01-24 05:55:56.759216: step: 1788/527, loss: 0.019561175256967545
2023-01-24 05:55:57.814966: step: 1792/527, loss: 0.007290417794138193
2023-01-24 05:55:58.867042: step: 1796/527, loss: 0.013378962874412537
2023-01-24 05:55:59.912672: step: 1800/527, loss: 0.003619763534516096
2023-01-24 05:56:00.962048: step: 1804/527, loss: 0.005326869431883097
2023-01-24 05:56:02.003766: step: 1808/527, loss: 0.007123375777155161
2023-01-24 05:56:03.052783: step: 1812/527, loss: 0.001479431870393455
2023-01-24 05:56:04.090456: step: 1816/527, loss: 0.0002616850833874196
2023-01-24 05:56:05.148764: step: 1820/527, loss: 0.004525614436715841
2023-01-24 05:56:06.206408: step: 1824/527, loss: 0.0013356241397559643
2023-01-24 05:56:07.241347: step: 1828/527, loss: 0.00701129250228405
2023-01-24 05:56:08.288819: step: 1832/527, loss: 0.006185004487633705
2023-01-24 05:56:09.333870: step: 1836/527, loss: 0.005583008285611868
2023-01-24 05:56:10.393788: step: 1840/527, loss: 0.00713853957131505
2023-01-24 05:56:11.471167: step: 1844/527, loss: 0.005338139832019806
2023-01-24 05:56:12.514586: step: 1848/527, loss: 0.004853971302509308
2023-01-24 05:56:13.558326: step: 1852/527, loss: 0.01282561756670475
2023-01-24 05:56:14.618236: step: 1856/527, loss: 0.009962816722691059
2023-01-24 05:56:15.663420: step: 1860/527, loss: 0.0063874083571136
2023-01-24 05:56:16.729320: step: 1864/527, loss: 0.012606088072061539
2023-01-24 05:56:17.792547: step: 1868/527, loss: 0.003858232870697975
2023-01-24 05:56:18.839386: step: 1872/527, loss: 0.027438918128609657
2023-01-24 05:56:19.889903: step: 1876/527, loss: 0.001566319027915597
2023-01-24 05:56:20.977426: step: 1880/527, loss: 0.004437906201928854
2023-01-24 05:56:22.039723: step: 1884/527, loss: 0.011134578846395016
2023-01-24 05:56:23.083427: step: 1888/527, loss: 0.013183685950934887
2023-01-24 05:56:24.138922: step: 1892/527, loss: 0.011707274243235588
2023-01-24 05:56:25.203006: step: 1896/527, loss: 0.005555757321417332
2023-01-24 05:56:26.252369: step: 1900/527, loss: 0.016193009912967682
2023-01-24 05:56:27.282712: step: 1904/527, loss: 0.0006685860571451485
2023-01-24 05:56:28.332442: step: 1908/527, loss: 0.006723953410983086
2023-01-24 05:56:29.383157: step: 1912/527, loss: 0.0076876431703567505
2023-01-24 05:56:30.444899: step: 1916/527, loss: 0.006427178159356117
2023-01-24 05:56:31.510319: step: 1920/527, loss: 0.005880905780941248
2023-01-24 05:56:32.556827: step: 1924/527, loss: 0.0012676960323005915
2023-01-24 05:56:33.608836: step: 1928/527, loss: 0.008009851910173893
2023-01-24 05:56:34.660338: step: 1932/527, loss: 0.0434921570122242
2023-01-24 05:56:35.708708: step: 1936/527, loss: 0.0025629119481891394
2023-01-24 05:56:36.752812: step: 1940/527, loss: 0.006032139994204044
2023-01-24 05:56:37.788787: step: 1944/527, loss: 0.008024443872272968
2023-01-24 05:56:38.855869: step: 1948/527, loss: 0.006688220892101526
2023-01-24 05:56:39.897841: step: 1952/527, loss: 0.007636374793946743
2023-01-24 05:56:40.926969: step: 1956/527, loss: 0.018973510712385178
2023-01-24 05:56:41.980435: step: 1960/527, loss: 0.00806934479624033
2023-01-24 05:56:43.044380: step: 1964/527, loss: 0.003991689067333937
2023-01-24 05:56:44.071696: step: 1968/527, loss: 0.005725575610995293
2023-01-24 05:56:45.122755: step: 1972/527, loss: 0.006628451868891716
2023-01-24 05:56:46.182497: step: 1976/527, loss: 0.004891253542155027
2023-01-24 05:56:47.241970: step: 1980/527, loss: 0.03173601254820824
2023-01-24 05:56:48.294462: step: 1984/527, loss: 0.0022919070906937122
2023-01-24 05:56:49.338319: step: 1988/527, loss: 0.002828119555488229
2023-01-24 05:56:50.388738: step: 1992/527, loss: 0.04499104246497154
2023-01-24 05:56:51.439581: step: 1996/527, loss: 0.0010336079867556691
2023-01-24 05:56:52.514200: step: 2000/527, loss: 0.009758410975337029
2023-01-24 05:56:53.551855: step: 2004/527, loss: 0.008675065822899342
2023-01-24 05:56:54.587531: step: 2008/527, loss: 0.012204213067889214
2023-01-24 05:56:55.643101: step: 2012/527, loss: 0.005348739214241505
2023-01-24 05:56:56.701360: step: 2016/527, loss: 0.006154006812721491
2023-01-24 05:56:57.759615: step: 2020/527, loss: 0.008105491288006306
2023-01-24 05:56:58.803559: step: 2024/527, loss: 0.0480058379471302
2023-01-24 05:56:59.878992: step: 2028/527, loss: 0.0035810123663395643
2023-01-24 05:57:00.929009: step: 2032/527, loss: 0.009700424037873745
2023-01-24 05:57:01.980007: step: 2036/527, loss: 0.010781696066260338
2023-01-24 05:57:03.020588: step: 2040/527, loss: 0.01747804507613182
2023-01-24 05:57:04.068641: step: 2044/527, loss: 0.03458770364522934
2023-01-24 05:57:05.128869: step: 2048/527, loss: 0.0025242650881409645
2023-01-24 05:57:06.178961: step: 2052/527, loss: 0.021751495078206062
2023-01-24 05:57:07.230094: step: 2056/527, loss: 0.009766235947608948
2023-01-24 05:57:08.285783: step: 2060/527, loss: 0.013502796180546284
2023-01-24 05:57:09.325119: step: 2064/527, loss: 0.0034496246371418238
2023-01-24 05:57:10.371689: step: 2068/527, loss: 0.033799927681684494
2023-01-24 05:57:11.413718: step: 2072/527, loss: 0.0007875370210967958
2023-01-24 05:57:12.464887: step: 2076/527, loss: 0.013467349112033844
2023-01-24 05:57:13.534719: step: 2080/527, loss: 0.020308133214712143
2023-01-24 05:57:14.578676: step: 2084/527, loss: 0.0029298237059265375
2023-01-24 05:57:15.617073: step: 2088/527, loss: 0.0046996851451694965
2023-01-24 05:57:16.653525: step: 2092/527, loss: 0.017699599266052246
2023-01-24 05:57:17.694861: step: 2096/527, loss: 0.011798987165093422
2023-01-24 05:57:18.727034: step: 2100/527, loss: 0.016439277678728104
2023-01-24 05:57:19.786926: step: 2104/527, loss: 0.0310671404004097
2023-01-24 05:57:20.830958: step: 2108/527, loss: 0.010649049654603004
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3458853501374787, 'r': 0.3242264951952836, 'f1': 0.33470590199395583}, 'combined': 0.2466254014692306, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3766876641206621, 'r': 0.291419274696985, 'f1': 0.3286122010934736}, 'combined': 0.21031180869982308, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36159057437407954, 'r': 0.33277310924369746, 'f1': 0.34658385093167704}, 'combined': 0.2553775743707094, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3710002578640197, 'r': 0.29855243275887505, 'f1': 0.3308567976522611}, 'combined': 0.21174835049744709, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36286100771987867, 'r': 0.322237099834731, 'f1': 0.34134462635759444}, 'combined': 0.2515170931055959, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3880125538595935, 'r': 0.3112589310815335, 'f1': 0.3454234166883584}, 'combined': 0.24766207234259663, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6, 'r': 0.20689655172413793, 'f1': 0.3076923076923077}, 'combined': 0.20512820512820512, 'stategy': 1, 'epoch': 4}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
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
2023-01-24 05:59:48.193575: step: 4/527, loss: 0.002969354623928666
2023-01-24 05:59:49.255529: step: 8/527, loss: 0.0014827997656539083
2023-01-24 05:59:50.292038: step: 12/527, loss: 0.011391973122954369
2023-01-24 05:59:51.335963: step: 16/527, loss: 0.004701155703514814
2023-01-24 05:59:52.383320: step: 20/527, loss: 0.002939260099083185
2023-01-24 05:59:53.433518: step: 24/527, loss: 0.007404353469610214
2023-01-24 05:59:54.468571: step: 28/527, loss: 0.008736512623727322
2023-01-24 05:59:55.520750: step: 32/527, loss: 0.002266091527417302
2023-01-24 05:59:56.566440: step: 36/527, loss: 0.008729124441742897
2023-01-24 05:59:57.630688: step: 40/527, loss: 0.005469411611557007
2023-01-24 05:59:58.695573: step: 44/527, loss: 0.007562476675957441
2023-01-24 05:59:59.754205: step: 48/527, loss: 0.003686920739710331
2023-01-24 06:00:00.800151: step: 52/527, loss: 0.0032590485643595457
2023-01-24 06:00:01.844403: step: 56/527, loss: 0.013321204110980034
2023-01-24 06:00:02.888870: step: 60/527, loss: 0.020682601258158684
2023-01-24 06:00:03.943519: step: 64/527, loss: 0.05404923856258392
2023-01-24 06:00:05.000134: step: 68/527, loss: 0.0010306095937266946
2023-01-24 06:00:06.041708: step: 72/527, loss: 0.024613196030259132
2023-01-24 06:00:07.092072: step: 76/527, loss: 0.005776167381554842
2023-01-24 06:00:08.160841: step: 80/527, loss: 0.015013959258794785
2023-01-24 06:00:09.223419: step: 84/527, loss: 0.019363850355148315
2023-01-24 06:00:10.261278: step: 88/527, loss: 0.004050699528306723
2023-01-24 06:00:11.300706: step: 92/527, loss: 0.03389830142259598
2023-01-24 06:00:12.348885: step: 96/527, loss: 0.0010759391589090228
2023-01-24 06:00:13.398404: step: 100/527, loss: 0.0017122612334787846
2023-01-24 06:00:14.454673: step: 104/527, loss: 0.0018421270651742816
2023-01-24 06:00:15.510867: step: 108/527, loss: 0.0018057593842968345
2023-01-24 06:00:16.586889: step: 112/527, loss: 0.03548183664679527
2023-01-24 06:00:17.640838: step: 116/527, loss: 0.0017532685305923223
2023-01-24 06:00:18.693183: step: 120/527, loss: 0.011274599470198154
2023-01-24 06:00:19.796957: step: 124/527, loss: 0.017829814925789833
2023-01-24 06:00:20.854240: step: 128/527, loss: 0.0006709989975206554
2023-01-24 06:00:21.914106: step: 132/527, loss: 0.014907999895513058
2023-01-24 06:00:22.956675: step: 136/527, loss: 0.01871870458126068
2023-01-24 06:00:24.024488: step: 140/527, loss: 0.005816675256937742
2023-01-24 06:00:25.082991: step: 144/527, loss: 0.008847100660204887
2023-01-24 06:00:26.150380: step: 148/527, loss: 0.0017618443816900253
2023-01-24 06:00:27.189642: step: 152/527, loss: 0.010032327845692635
2023-01-24 06:00:28.235928: step: 156/527, loss: 0.021026909351348877
2023-01-24 06:00:29.279958: step: 160/527, loss: 0.010059729218482971
2023-01-24 06:00:30.327432: step: 164/527, loss: 0.013219148851931095
2023-01-24 06:00:31.379657: step: 168/527, loss: 0.0032328632660210133
2023-01-24 06:00:32.435181: step: 172/527, loss: 0.0002496513770893216
2023-01-24 06:00:33.493756: step: 176/527, loss: 0.0064623611979186535
2023-01-24 06:00:34.545256: step: 180/527, loss: 0.029678309336304665
2023-01-24 06:00:35.599767: step: 184/527, loss: 0.01414361409842968
2023-01-24 06:00:36.654538: step: 188/527, loss: 0.011568525806069374
2023-01-24 06:00:37.712093: step: 192/527, loss: 0.006473075598478317
2023-01-24 06:00:38.766350: step: 196/527, loss: 0.015940334647893906
2023-01-24 06:00:39.802108: step: 200/527, loss: 0.009600615128874779
2023-01-24 06:00:40.861672: step: 204/527, loss: 0.007409001234918833
2023-01-24 06:00:41.908657: step: 208/527, loss: 0.004151436500251293
2023-01-24 06:00:42.958197: step: 212/527, loss: 0.005052375141531229
2023-01-24 06:00:44.017380: step: 216/527, loss: 0.007848276756703854
2023-01-24 06:00:45.054926: step: 220/527, loss: 0.007075367961078882
2023-01-24 06:00:46.103999: step: 224/527, loss: 0.03806260600686073
2023-01-24 06:00:47.149291: step: 228/527, loss: 0.002090335823595524
2023-01-24 06:00:48.197803: step: 232/527, loss: 0.004145875573158264
2023-01-24 06:00:49.263241: step: 236/527, loss: 0.0048092626966536045
2023-01-24 06:00:50.316703: step: 240/527, loss: 0.006860788911581039
2023-01-24 06:00:51.352772: step: 244/527, loss: 0.011368861421942711
2023-01-24 06:00:52.387278: step: 248/527, loss: 0.02221207693219185
2023-01-24 06:00:53.426970: step: 252/527, loss: 0.005869068671017885
2023-01-24 06:00:54.468288: step: 256/527, loss: 0.0024019372649490833
2023-01-24 06:00:55.527101: step: 260/527, loss: 0.009915287606418133
2023-01-24 06:00:56.558560: step: 264/527, loss: 0.0054763746447861195
2023-01-24 06:00:57.622132: step: 268/527, loss: 0.008758329786360264
2023-01-24 06:00:58.655281: step: 272/527, loss: 0.007811664137989283
2023-01-24 06:00:59.704002: step: 276/527, loss: 0.03288523852825165
2023-01-24 06:01:00.747915: step: 280/527, loss: 0.01274183765053749
2023-01-24 06:01:01.799748: step: 284/527, loss: 0.011776238679885864
2023-01-24 06:01:02.846613: step: 288/527, loss: 0.0012714744079858065
2023-01-24 06:01:03.911300: step: 292/527, loss: 0.005683154799044132
2023-01-24 06:01:04.969245: step: 296/527, loss: 0.0038965095300227404
2023-01-24 06:01:06.028135: step: 300/527, loss: 0.009876362048089504
2023-01-24 06:01:07.070030: step: 304/527, loss: 0.0007933435845188797
2023-01-24 06:01:08.122894: step: 308/527, loss: 0.009363846853375435
2023-01-24 06:01:09.177543: step: 312/527, loss: 0.03849930316209793
2023-01-24 06:01:10.226847: step: 316/527, loss: 0.02594965510070324
2023-01-24 06:01:11.266121: step: 320/527, loss: 0.0011536639649420977
2023-01-24 06:01:12.313026: step: 324/527, loss: 0.01028281357139349
2023-01-24 06:01:13.373125: step: 328/527, loss: 0.011264101602137089
2023-01-24 06:01:14.400670: step: 332/527, loss: 0.0010639885440468788
2023-01-24 06:01:15.461225: step: 336/527, loss: 0.03970203548669815
2023-01-24 06:01:16.526038: step: 340/527, loss: 0.006717577110975981
2023-01-24 06:01:17.586650: step: 344/527, loss: 0.002548638731241226
2023-01-24 06:01:18.629796: step: 348/527, loss: 0.020918942987918854
2023-01-24 06:01:19.721077: step: 352/527, loss: 0.03664001449942589
2023-01-24 06:01:20.773254: step: 356/527, loss: 0.0031418537255376577
2023-01-24 06:01:21.817745: step: 360/527, loss: 0.013708369806408882
2023-01-24 06:01:22.872359: step: 364/527, loss: 0.007406481541693211
2023-01-24 06:01:23.918860: step: 368/527, loss: 0.02865022048354149
2023-01-24 06:01:24.978158: step: 372/527, loss: 0.008868347853422165
2023-01-24 06:01:26.022795: step: 376/527, loss: 0.006646595895290375
2023-01-24 06:01:27.070597: step: 380/527, loss: 0.004173017106950283
2023-01-24 06:01:28.119814: step: 384/527, loss: 0.0068471902050077915
2023-01-24 06:01:29.162847: step: 388/527, loss: 0.007518232800066471
2023-01-24 06:01:30.227334: step: 392/527, loss: 0.003517703851684928
2023-01-24 06:01:31.279111: step: 396/527, loss: 0.0074419742450118065
2023-01-24 06:01:32.341926: step: 400/527, loss: 0.03165902569890022
2023-01-24 06:01:33.389990: step: 404/527, loss: 0.003697504522278905
2023-01-24 06:01:34.443805: step: 408/527, loss: 0.0033218746539205313
2023-01-24 06:01:35.502070: step: 412/527, loss: 0.010349982418119907
2023-01-24 06:01:36.555702: step: 416/527, loss: 0.0014420952647924423
2023-01-24 06:01:37.622078: step: 420/527, loss: 0.040701959282159805
2023-01-24 06:01:38.680364: step: 424/527, loss: 0.009987237863242626
2023-01-24 06:01:39.716867: step: 428/527, loss: 0.006658504717051983
2023-01-24 06:01:40.763550: step: 432/527, loss: 0.006679753307253122
2023-01-24 06:01:41.805793: step: 436/527, loss: 0.03932838886976242
2023-01-24 06:01:42.848190: step: 440/527, loss: 0.0023192455992102623
2023-01-24 06:01:43.920210: step: 444/527, loss: 0.03153736889362335
2023-01-24 06:01:44.960355: step: 448/527, loss: 0.0013293507508933544
2023-01-24 06:01:45.998597: step: 452/527, loss: 0.052417173981666565
2023-01-24 06:01:47.045111: step: 456/527, loss: 0.005422278307378292
2023-01-24 06:01:48.092862: step: 460/527, loss: 0.006223623640835285
2023-01-24 06:01:49.149310: step: 464/527, loss: 0.014947882853448391
2023-01-24 06:01:50.205929: step: 468/527, loss: 0.008250672370195389
2023-01-24 06:01:51.265291: step: 472/527, loss: 0.018661482259631157
2023-01-24 06:01:52.327296: step: 476/527, loss: 0.00026580668054521084
2023-01-24 06:01:53.385665: step: 480/527, loss: 0.02620423398911953
2023-01-24 06:01:54.447418: step: 484/527, loss: 0.012208274565637112
2023-01-24 06:01:55.491961: step: 488/527, loss: 0.013318589888513088
2023-01-24 06:01:56.542050: step: 492/527, loss: 0.000285789486952126
2023-01-24 06:01:57.599283: step: 496/527, loss: 0.009143110364675522
2023-01-24 06:01:58.643987: step: 500/527, loss: 0.0045474739745259285
2023-01-24 06:01:59.680604: step: 504/527, loss: 0.0029171151109039783
2023-01-24 06:02:00.740684: step: 508/527, loss: 0.01945706084370613
2023-01-24 06:02:01.790192: step: 512/527, loss: 0.0071182711981236935
2023-01-24 06:02:02.832710: step: 516/527, loss: 0.006222281139343977
2023-01-24 06:02:03.885516: step: 520/527, loss: 0.01364617794752121
2023-01-24 06:02:04.929588: step: 524/527, loss: 0.009088690392673016
2023-01-24 06:02:05.988639: step: 528/527, loss: 0.015786701813340187
2023-01-24 06:02:07.044477: step: 532/527, loss: 0.0033564644400030375
2023-01-24 06:02:08.095723: step: 536/527, loss: 0.008154332637786865
2023-01-24 06:02:09.136639: step: 540/527, loss: 0.0022767100017517805
2023-01-24 06:02:10.195303: step: 544/527, loss: 0.016711972653865814
2023-01-24 06:02:11.261246: step: 548/527, loss: 0.007074535824358463
2023-01-24 06:02:12.328736: step: 552/527, loss: 0.0381755530834198
2023-01-24 06:02:13.372651: step: 556/527, loss: 0.005773419979959726
2023-01-24 06:02:14.419581: step: 560/527, loss: 0.001738192979246378
2023-01-24 06:02:15.485859: step: 564/527, loss: 0.0025373923126608133
2023-01-24 06:02:16.536512: step: 568/527, loss: 0.023184970021247864
2023-01-24 06:02:17.585394: step: 572/527, loss: 0.0022909336257725954
2023-01-24 06:02:18.631878: step: 576/527, loss: 0.04253803566098213
2023-01-24 06:02:19.705226: step: 580/527, loss: 0.021489733830094337
2023-01-24 06:02:20.751411: step: 584/527, loss: 0.0005806525005027652
2023-01-24 06:02:21.793085: step: 588/527, loss: 0.007432470563799143
2023-01-24 06:02:22.843570: step: 592/527, loss: 0.012636465951800346
2023-01-24 06:02:23.890976: step: 596/527, loss: 0.010633801110088825
2023-01-24 06:02:24.949141: step: 600/527, loss: 0.0061531951650977135
2023-01-24 06:02:26.000310: step: 604/527, loss: 0.017504367977380753
2023-01-24 06:02:27.034834: step: 608/527, loss: 0.026440482586622238
2023-01-24 06:02:28.076650: step: 612/527, loss: 0.009087401442229748
2023-01-24 06:02:29.125552: step: 616/527, loss: 0.0044678207486867905
2023-01-24 06:02:30.173774: step: 620/527, loss: 0.011231588199734688
2023-01-24 06:02:31.205889: step: 624/527, loss: 0.0037329308688640594
2023-01-24 06:02:32.248370: step: 628/527, loss: 0.005498392041772604
2023-01-24 06:02:33.308407: step: 632/527, loss: 0.012921069748699665
2023-01-24 06:02:34.365117: step: 636/527, loss: 0.029064837843179703
2023-01-24 06:02:35.423192: step: 640/527, loss: 0.004471190273761749
2023-01-24 06:02:36.469245: step: 644/527, loss: 0.007544382940977812
2023-01-24 06:02:37.517485: step: 648/527, loss: 0.007371215149760246
2023-01-24 06:02:38.563027: step: 652/527, loss: 0.0022037853486835957
2023-01-24 06:02:39.609460: step: 656/527, loss: 0.007532479707151651
2023-01-24 06:02:40.651770: step: 660/527, loss: 0.0028670087922364473
2023-01-24 06:02:41.695533: step: 664/527, loss: 0.00627627968788147
2023-01-24 06:02:42.742067: step: 668/527, loss: 0.006216144654899836
2023-01-24 06:02:43.798295: step: 672/527, loss: 0.01613222062587738
2023-01-24 06:02:44.861195: step: 676/527, loss: 0.0036915522068738937
2023-01-24 06:02:45.913978: step: 680/527, loss: 0.013016798533499241
2023-01-24 06:02:46.963484: step: 684/527, loss: 0.005806453060358763
2023-01-24 06:02:47.995887: step: 688/527, loss: 0.0005305635277181864
2023-01-24 06:02:49.060529: step: 692/527, loss: 0.00021035685495007783
2023-01-24 06:02:50.115761: step: 696/527, loss: 0.004059563856571913
2023-01-24 06:02:51.153255: step: 700/527, loss: 0.014852388761937618
2023-01-24 06:02:52.210627: step: 704/527, loss: 0.009128103032708168
2023-01-24 06:02:53.257109: step: 708/527, loss: 0.01652321219444275
2023-01-24 06:02:54.311731: step: 712/527, loss: 0.02944299951195717
2023-01-24 06:02:55.359989: step: 716/527, loss: 0.003906652331352234
2023-01-24 06:02:56.410558: step: 720/527, loss: 0.007499282713979483
2023-01-24 06:02:57.475367: step: 724/527, loss: 0.009264912456274033
2023-01-24 06:02:58.522924: step: 728/527, loss: 0.01113964430987835
2023-01-24 06:02:59.568987: step: 732/527, loss: 0.008038428612053394
2023-01-24 06:03:00.611512: step: 736/527, loss: 0.03619419038295746
2023-01-24 06:03:01.660796: step: 740/527, loss: 0.002730597974732518
2023-01-24 06:03:02.720897: step: 744/527, loss: 0.003389413934201002
2023-01-24 06:03:03.778516: step: 748/527, loss: 0.011952356435358524
2023-01-24 06:03:04.851747: step: 752/527, loss: 0.012719747610390186
2023-01-24 06:03:05.898330: step: 756/527, loss: 0.0021842161659151316
2023-01-24 06:03:06.942046: step: 760/527, loss: 0.007026479579508305
2023-01-24 06:03:07.998054: step: 764/527, loss: 0.0064879958517849445
2023-01-24 06:03:09.040967: step: 768/527, loss: 0.0022806536871939898
2023-01-24 06:03:10.071938: step: 772/527, loss: 0.006598201580345631
2023-01-24 06:03:11.151573: step: 776/527, loss: 0.005487419664859772
2023-01-24 06:03:12.212379: step: 780/527, loss: 0.0011780932545661926
2023-01-24 06:03:13.267114: step: 784/527, loss: 0.002447796519845724
2023-01-24 06:03:14.309853: step: 788/527, loss: 0.011724085547029972
2023-01-24 06:03:15.362239: step: 792/527, loss: 0.010715875774621964
2023-01-24 06:03:16.406126: step: 796/527, loss: 0.004847763571888208
2023-01-24 06:03:17.450137: step: 800/527, loss: 0.0019091146532446146
2023-01-24 06:03:18.495410: step: 804/527, loss: 0.00435184221714735
2023-01-24 06:03:19.544523: step: 808/527, loss: 0.006244426593184471
2023-01-24 06:03:20.601026: step: 812/527, loss: 0.0171041302382946
2023-01-24 06:03:21.672695: step: 816/527, loss: 0.03753026947379112
2023-01-24 06:03:22.720865: step: 820/527, loss: 0.0028294953517615795
2023-01-24 06:03:23.785702: step: 824/527, loss: 0.006130837369710207
2023-01-24 06:03:24.839703: step: 828/527, loss: 0.0036286322865635157
2023-01-24 06:03:25.905677: step: 832/527, loss: 0.010490822605788708
2023-01-24 06:03:26.941076: step: 836/527, loss: 0.017498401924967766
2023-01-24 06:03:28.010691: step: 840/527, loss: 0.002916432451456785
2023-01-24 06:03:29.052024: step: 844/527, loss: 0.013589801266789436
2023-01-24 06:03:30.107523: step: 848/527, loss: 0.005216329358518124
2023-01-24 06:03:31.146602: step: 852/527, loss: 0.002796849934384227
2023-01-24 06:03:32.211805: step: 856/527, loss: 0.019581666216254234
2023-01-24 06:03:33.256059: step: 860/527, loss: 0.011264914646744728
2023-01-24 06:03:34.302108: step: 864/527, loss: 0.008222275413572788
2023-01-24 06:03:35.364591: step: 868/527, loss: 0.018901150673627853
2023-01-24 06:03:36.404252: step: 872/527, loss: 0.018296141177415848
2023-01-24 06:03:37.463920: step: 876/527, loss: 0.0031639791559427977
2023-01-24 06:03:38.516946: step: 880/527, loss: 0.025872010737657547
2023-01-24 06:03:39.566540: step: 884/527, loss: 0.002451978623867035
2023-01-24 06:03:40.612774: step: 888/527, loss: 0.005923663266003132
2023-01-24 06:03:41.656629: step: 892/527, loss: 0.016273170709609985
2023-01-24 06:03:42.730861: step: 896/527, loss: 0.00237936619669199
2023-01-24 06:03:43.796586: step: 900/527, loss: 0.02248707227408886
2023-01-24 06:03:44.853387: step: 904/527, loss: 0.004151094704866409
2023-01-24 06:03:45.911422: step: 908/527, loss: 0.0021933824755251408
2023-01-24 06:03:46.951947: step: 912/527, loss: 0.002742059761658311
2023-01-24 06:03:47.983642: step: 916/527, loss: 0.002953851129859686
2023-01-24 06:03:49.050932: step: 920/527, loss: 0.0033365164417773485
2023-01-24 06:03:50.105399: step: 924/527, loss: 0.004420835059136152
2023-01-24 06:03:51.180015: step: 928/527, loss: 0.013445116579532623
2023-01-24 06:03:52.234667: step: 932/527, loss: 7.957030175020918e-05
2023-01-24 06:03:53.286345: step: 936/527, loss: 0.003749594558030367
2023-01-24 06:03:54.350075: step: 940/527, loss: 0.017982684075832367
2023-01-24 06:03:55.406580: step: 944/527, loss: 0.01481990609318018
2023-01-24 06:03:56.450004: step: 948/527, loss: 0.0020884007681161165
2023-01-24 06:03:57.507189: step: 952/527, loss: 0.004878515377640724
2023-01-24 06:03:58.550951: step: 956/527, loss: 0.00833574403077364
2023-01-24 06:03:59.593377: step: 960/527, loss: 0.004025594796985388
2023-01-24 06:04:00.632484: step: 964/527, loss: 0.036562662571668625
2023-01-24 06:04:01.721071: step: 968/527, loss: 0.0011795436730608344
2023-01-24 06:04:02.763596: step: 972/527, loss: 0.026035521179437637
2023-01-24 06:04:03.838029: step: 976/527, loss: 0.0139453811571002
2023-01-24 06:04:04.885790: step: 980/527, loss: 0.0044447993859648705
2023-01-24 06:04:05.929816: step: 984/527, loss: 0.008876659907400608
2023-01-24 06:04:06.969554: step: 988/527, loss: 0.00867005530744791
2023-01-24 06:04:08.005872: step: 992/527, loss: 0.004711296409368515
2023-01-24 06:04:09.060207: step: 996/527, loss: 0.004192500840872526
2023-01-24 06:04:10.103104: step: 1000/527, loss: 0.0024711224250495434
2023-01-24 06:04:11.170005: step: 1004/527, loss: 0.0039834328927099705
2023-01-24 06:04:12.199813: step: 1008/527, loss: 0.0023470204323530197
2023-01-24 06:04:13.253995: step: 1012/527, loss: 0.006675094366073608
2023-01-24 06:04:14.315072: step: 1016/527, loss: 0.031667426228523254
2023-01-24 06:04:15.355603: step: 1020/527, loss: 0.003976329229772091
2023-01-24 06:04:16.410434: step: 1024/527, loss: 0.005665579345077276
2023-01-24 06:04:17.447775: step: 1028/527, loss: 0.026949133723974228
2023-01-24 06:04:18.495820: step: 1032/527, loss: 0.00815789494663477
2023-01-24 06:04:19.554485: step: 1036/527, loss: 0.004347816109657288
2023-01-24 06:04:20.596553: step: 1040/527, loss: 0.022784659639000893
2023-01-24 06:04:21.659860: step: 1044/527, loss: 0.010411013849079609
2023-01-24 06:04:22.729324: step: 1048/527, loss: 0.0279465951025486
2023-01-24 06:04:23.781614: step: 1052/527, loss: 0.0038170020561665297
2023-01-24 06:04:24.834028: step: 1056/527, loss: 0.004797334782779217
2023-01-24 06:04:25.888219: step: 1060/527, loss: 0.013142174109816551
2023-01-24 06:04:26.933913: step: 1064/527, loss: 0.011441509239375591
2023-01-24 06:04:27.995013: step: 1068/527, loss: 0.010451341979205608
2023-01-24 06:04:29.036624: step: 1072/527, loss: 0.0277873482555151
2023-01-24 06:04:30.080971: step: 1076/527, loss: 0.018156759440898895
2023-01-24 06:04:31.144467: step: 1080/527, loss: 0.014458867721259594
2023-01-24 06:04:32.197403: step: 1084/527, loss: 0.01924041286110878
2023-01-24 06:04:33.251553: step: 1088/527, loss: 0.005845629144459963
2023-01-24 06:04:34.326942: step: 1092/527, loss: 0.011642617173492908
2023-01-24 06:04:35.388594: step: 1096/527, loss: 0.02554919384419918
2023-01-24 06:04:36.430532: step: 1100/527, loss: 0.0011409070575609803
2023-01-24 06:04:37.476777: step: 1104/527, loss: 0.0065157730132341385
2023-01-24 06:04:38.524563: step: 1108/527, loss: 0.020355820655822754
2023-01-24 06:04:39.599337: step: 1112/527, loss: 0.011787410825490952
2023-01-24 06:04:40.660634: step: 1116/527, loss: 0.027298949658870697
2023-01-24 06:04:41.708894: step: 1120/527, loss: 0.021569516509771347
2023-01-24 06:04:42.770849: step: 1124/527, loss: 0.007379552815109491
2023-01-24 06:04:43.827111: step: 1128/527, loss: 0.008127819746732712
2023-01-24 06:04:44.896363: step: 1132/527, loss: 0.01808037795126438
2023-01-24 06:04:45.952812: step: 1136/527, loss: 0.008086105808615685
2023-01-24 06:04:47.015266: step: 1140/527, loss: 0.004028093535453081
2023-01-24 06:04:48.055998: step: 1144/527, loss: 0.009277253411710262
2023-01-24 06:04:49.120759: step: 1148/527, loss: 0.005190738011151552
2023-01-24 06:04:50.198466: step: 1152/527, loss: 0.005365185905247927
2023-01-24 06:04:51.272574: step: 1156/527, loss: 0.009627090767025948
2023-01-24 06:04:52.330208: step: 1160/527, loss: 0.022511985152959824
2023-01-24 06:04:53.385816: step: 1164/527, loss: 0.00419845525175333
2023-01-24 06:04:54.452275: step: 1168/527, loss: 0.002840465633198619
2023-01-24 06:04:55.500548: step: 1172/527, loss: 0.0045182122848927975
2023-01-24 06:04:56.546929: step: 1176/527, loss: 0.022903745993971825
2023-01-24 06:04:57.606687: step: 1180/527, loss: 0.003719200612977147
2023-01-24 06:04:58.653479: step: 1184/527, loss: 0.01360474992543459
2023-01-24 06:04:59.700162: step: 1188/527, loss: 0.0035302340984344482
2023-01-24 06:05:00.765449: step: 1192/527, loss: 0.023574169725179672
2023-01-24 06:05:01.829992: step: 1196/527, loss: 0.038673803210258484
2023-01-24 06:05:02.873184: step: 1200/527, loss: 0.0092678964138031
2023-01-24 06:05:03.904126: step: 1204/527, loss: 0.0035165001172572374
2023-01-24 06:05:04.946493: step: 1208/527, loss: 5.5617874750168994e-05
2023-01-24 06:05:06.012084: step: 1212/527, loss: 0.010505360551178455
2023-01-24 06:05:07.061973: step: 1216/527, loss: 0.04568411037325859
2023-01-24 06:05:08.110248: step: 1220/527, loss: 0.019272875040769577
2023-01-24 06:05:09.138347: step: 1224/527, loss: 0.011340446770191193
2023-01-24 06:05:10.185734: step: 1228/527, loss: 0.01919662021100521
2023-01-24 06:05:11.254991: step: 1232/527, loss: 0.05767522752285004
2023-01-24 06:05:12.295487: step: 1236/527, loss: 0.029466670006513596
2023-01-24 06:05:13.358138: step: 1240/527, loss: 0.007538609206676483
2023-01-24 06:05:14.407068: step: 1244/527, loss: 0.006212037988007069
2023-01-24 06:05:15.451867: step: 1248/527, loss: 0.009144243784248829
2023-01-24 06:05:16.510136: step: 1252/527, loss: 0.0007239718688651919
2023-01-24 06:05:17.569834: step: 1256/527, loss: 0.021091515198349953
2023-01-24 06:05:18.621185: step: 1260/527, loss: 0.006575802341103554
2023-01-24 06:05:19.670993: step: 1264/527, loss: 0.010765178129076958
2023-01-24 06:05:20.716297: step: 1268/527, loss: 0.008394895121455193
2023-01-24 06:05:21.758917: step: 1272/527, loss: 3.491679672151804e-05
2023-01-24 06:05:22.831369: step: 1276/527, loss: 0.019259685650467873
2023-01-24 06:05:23.884692: step: 1280/527, loss: 0.01469599362462759
2023-01-24 06:05:24.930977: step: 1284/527, loss: 0.01065925695002079
2023-01-24 06:05:25.981608: step: 1288/527, loss: 0.012464450672268867
2023-01-24 06:05:27.044865: step: 1292/527, loss: 0.026256101205945015
2023-01-24 06:05:28.078190: step: 1296/527, loss: 0.002674462739378214
2023-01-24 06:05:29.139033: step: 1300/527, loss: 0.0031843220349401236
2023-01-24 06:05:30.192652: step: 1304/527, loss: 0.005963290110230446
2023-01-24 06:05:31.246701: step: 1308/527, loss: 0.002744704717770219
2023-01-24 06:05:32.288753: step: 1312/527, loss: 0.037120621651411057
2023-01-24 06:05:33.348548: step: 1316/527, loss: 0.00917765125632286
2023-01-24 06:05:34.404222: step: 1320/527, loss: 0.012225555256009102
2023-01-24 06:05:35.450447: step: 1324/527, loss: 0.004405536223202944
2023-01-24 06:05:36.482473: step: 1328/527, loss: 0.003313221503049135
2023-01-24 06:05:37.519532: step: 1332/527, loss: 0.000770586309954524
2023-01-24 06:05:38.567439: step: 1336/527, loss: 0.004324547480791807
2023-01-24 06:05:39.599806: step: 1340/527, loss: 0.002289133844897151
2023-01-24 06:05:40.644446: step: 1344/527, loss: 0.002626942005008459
2023-01-24 06:05:41.691414: step: 1348/527, loss: 0.0017340255435556173
2023-01-24 06:05:42.749281: step: 1352/527, loss: 0.0002952470094896853
2023-01-24 06:05:43.790120: step: 1356/527, loss: 0.0034138751216232777
2023-01-24 06:05:44.855991: step: 1360/527, loss: 0.007477168459445238
2023-01-24 06:05:45.920466: step: 1364/527, loss: 0.003875673282891512
2023-01-24 06:05:46.976499: step: 1368/527, loss: 0.013424725271761417
2023-01-24 06:05:48.044300: step: 1372/527, loss: 0.003630690276622772
2023-01-24 06:05:49.085825: step: 1376/527, loss: 0.0028609067667275667
2023-01-24 06:05:50.126385: step: 1380/527, loss: 0.011709722690284252
2023-01-24 06:05:51.189530: step: 1384/527, loss: 0.005834583193063736
2023-01-24 06:05:52.235038: step: 1388/527, loss: 0.04574430361390114
2023-01-24 06:05:53.278896: step: 1392/527, loss: 0.02212393283843994
2023-01-24 06:05:54.334707: step: 1396/527, loss: 0.0039162845350801945
2023-01-24 06:05:55.366543: step: 1400/527, loss: 0.0017135880189016461
2023-01-24 06:05:56.439197: step: 1404/527, loss: 0.02152174711227417
2023-01-24 06:05:57.480594: step: 1408/527, loss: 0.004200255032628775
2023-01-24 06:05:58.536009: step: 1412/527, loss: 0.007566146086901426
2023-01-24 06:05:59.616814: step: 1416/527, loss: 0.03885927423834801
2023-01-24 06:06:00.673813: step: 1420/527, loss: 0.006391413044184446
2023-01-24 06:06:01.731879: step: 1424/527, loss: 0.00448015658184886
2023-01-24 06:06:02.770688: step: 1428/527, loss: 0.026661232113838196
2023-01-24 06:06:03.820881: step: 1432/527, loss: 0.01487383246421814
2023-01-24 06:06:04.864832: step: 1436/527, loss: 0.004046610556542873
2023-01-24 06:06:05.914514: step: 1440/527, loss: 0.005410411395132542
2023-01-24 06:06:06.959125: step: 1444/527, loss: 0.004408024251461029
2023-01-24 06:06:08.010970: step: 1448/527, loss: 0.016233105212450027
2023-01-24 06:06:09.069471: step: 1452/527, loss: 0.01613014005124569
2023-01-24 06:06:10.128186: step: 1456/527, loss: 0.008741861209273338
2023-01-24 06:06:11.183112: step: 1460/527, loss: 0.010356834158301353
2023-01-24 06:06:12.242377: step: 1464/527, loss: 0.002057206118479371
2023-01-24 06:06:13.293585: step: 1468/527, loss: 0.0026880325749516487
2023-01-24 06:06:14.337505: step: 1472/527, loss: 0.002831254852935672
2023-01-24 06:06:15.410700: step: 1476/527, loss: 0.002983893733471632
2023-01-24 06:06:16.486719: step: 1480/527, loss: 0.0180650781840086
2023-01-24 06:06:17.528594: step: 1484/527, loss: 0.04800155386328697
2023-01-24 06:06:18.572101: step: 1488/527, loss: 0.004443780984729528
2023-01-24 06:06:19.627871: step: 1492/527, loss: 0.005661570001393557
2023-01-24 06:06:20.723105: step: 1496/527, loss: 0.007349614053964615
2023-01-24 06:06:21.767384: step: 1500/527, loss: 0.011952241882681847
2023-01-24 06:06:22.807375: step: 1504/527, loss: 0.00030225442606024444
2023-01-24 06:06:23.865957: step: 1508/527, loss: 0.01005775947123766
2023-01-24 06:06:24.913433: step: 1512/527, loss: 0.008232921361923218
2023-01-24 06:06:25.966471: step: 1516/527, loss: 0.006454213988035917
2023-01-24 06:06:27.019627: step: 1520/527, loss: 0.0024536894634366035
2023-01-24 06:06:28.049350: step: 1524/527, loss: 8.150745270540938e-05
2023-01-24 06:06:29.116404: step: 1528/527, loss: 0.0038888035342097282
2023-01-24 06:06:30.153326: step: 1532/527, loss: 0.00791660975664854
2023-01-24 06:06:31.214516: step: 1536/527, loss: 0.0034462171606719494
2023-01-24 06:06:32.268656: step: 1540/527, loss: 0.004976110532879829
2023-01-24 06:06:33.328821: step: 1544/527, loss: 0.013882022351026535
2023-01-24 06:06:34.385433: step: 1548/527, loss: 0.01641835644841194
2023-01-24 06:06:35.430990: step: 1552/527, loss: 0.006974536459892988
2023-01-24 06:06:36.470257: step: 1556/527, loss: 0.008180052973330021
2023-01-24 06:06:37.533338: step: 1560/527, loss: 0.030093254521489143
2023-01-24 06:06:38.578967: step: 1564/527, loss: 0.030447788536548615
2023-01-24 06:06:39.633493: step: 1568/527, loss: 0.007571370340883732
2023-01-24 06:06:40.686102: step: 1572/527, loss: 0.005400706082582474
2023-01-24 06:06:41.750530: step: 1576/527, loss: 0.005711423698812723
2023-01-24 06:06:42.790137: step: 1580/527, loss: 0.018246019259095192
2023-01-24 06:06:43.856207: step: 1584/527, loss: 0.031007826328277588
2023-01-24 06:06:44.917255: step: 1588/527, loss: 0.003460594918578863
2023-01-24 06:06:45.978513: step: 1592/527, loss: 0.05547678843140602
2023-01-24 06:06:47.048193: step: 1596/527, loss: 0.006731846369802952
2023-01-24 06:06:48.096651: step: 1600/527, loss: 0.028741005808115005
2023-01-24 06:06:49.148059: step: 1604/527, loss: 0.010584404692053795
2023-01-24 06:06:50.207277: step: 1608/527, loss: 0.0035399007610976696
2023-01-24 06:06:51.251731: step: 1612/527, loss: 0.003735631238669157
2023-01-24 06:06:52.307625: step: 1616/527, loss: 0.005376417655497789
2023-01-24 06:06:53.354269: step: 1620/527, loss: 0.023900914937257767
2023-01-24 06:06:54.395305: step: 1624/527, loss: 0.009086580947041512
2023-01-24 06:06:55.441371: step: 1628/527, loss: 0.00670094508677721
2023-01-24 06:06:56.488235: step: 1632/527, loss: 0.0018897296395152807
2023-01-24 06:06:57.549480: step: 1636/527, loss: 0.0021955417469143867
2023-01-24 06:06:58.598763: step: 1640/527, loss: 0.0009489068761467934
2023-01-24 06:06:59.631991: step: 1644/527, loss: 0.008215104229748249
2023-01-24 06:07:00.680164: step: 1648/527, loss: 0.007600032724440098
2023-01-24 06:07:01.729102: step: 1652/527, loss: 0.011808929964900017
2023-01-24 06:07:02.770651: step: 1656/527, loss: 0.003579444717615843
2023-01-24 06:07:03.814814: step: 1660/527, loss: 0.004173597786575556
2023-01-24 06:07:04.874070: step: 1664/527, loss: 0.014817196875810623
2023-01-24 06:07:05.918628: step: 1668/527, loss: 0.006623163819313049
2023-01-24 06:07:06.974925: step: 1672/527, loss: 0.00447028037160635
2023-01-24 06:07:08.016584: step: 1676/527, loss: 0.011469677090644836
2023-01-24 06:07:09.045924: step: 1680/527, loss: 0.004856418818235397
2023-01-24 06:07:10.083807: step: 1684/527, loss: 0.0012031658552587032
2023-01-24 06:07:11.131510: step: 1688/527, loss: 0.019825154915452003
2023-01-24 06:07:12.178340: step: 1692/527, loss: 0.0031039812602102757
2023-01-24 06:07:13.237150: step: 1696/527, loss: 0.013692040927708149
2023-01-24 06:07:14.291229: step: 1700/527, loss: 0.0028177835047245026
2023-01-24 06:07:15.345431: step: 1704/527, loss: 0.006275123916566372
2023-01-24 06:07:16.379679: step: 1708/527, loss: 0.03189357370138168
2023-01-24 06:07:17.415541: step: 1712/527, loss: 0.004919901955872774
2023-01-24 06:07:18.481574: step: 1716/527, loss: 0.004597228951752186
2023-01-24 06:07:19.546445: step: 1720/527, loss: 0.005968692246824503
2023-01-24 06:07:20.616030: step: 1724/527, loss: 0.04046793654561043
2023-01-24 06:07:21.670603: step: 1728/527, loss: 0.008305750787258148
2023-01-24 06:07:22.709884: step: 1732/527, loss: 0.0064603895880281925
2023-01-24 06:07:23.760219: step: 1736/527, loss: 0.007813424803316593
2023-01-24 06:07:24.818564: step: 1740/527, loss: 0.0038077947683632374
2023-01-24 06:07:25.884456: step: 1744/527, loss: 0.005299651529639959
2023-01-24 06:07:26.935319: step: 1748/527, loss: 0.009291463531553745
2023-01-24 06:07:27.977183: step: 1752/527, loss: 0.0017409819411113858
2023-01-24 06:07:29.021724: step: 1756/527, loss: 0.007004793733358383
2023-01-24 06:07:30.087524: step: 1760/527, loss: 0.009343842044472694
2023-01-24 06:07:31.135486: step: 1764/527, loss: 0.009979411959648132
2023-01-24 06:07:32.174046: step: 1768/527, loss: 0.0006102912011556327
2023-01-24 06:07:33.236795: step: 1772/527, loss: 0.016799774020910263
2023-01-24 06:07:34.283026: step: 1776/527, loss: 0.0033510886132717133
2023-01-24 06:07:35.323877: step: 1780/527, loss: 0.012840097770094872
2023-01-24 06:07:36.385587: step: 1784/527, loss: 0.0252709798514843
2023-01-24 06:07:37.439236: step: 1788/527, loss: 0.0019171589519828558
2023-01-24 06:07:38.494732: step: 1792/527, loss: 0.007466321811079979
2023-01-24 06:07:39.541127: step: 1796/527, loss: 0.028352845460176468
2023-01-24 06:07:40.591471: step: 1800/527, loss: 0.020462721586227417
2023-01-24 06:07:41.642688: step: 1804/527, loss: 0.001348096877336502
2023-01-24 06:07:42.694559: step: 1808/527, loss: 0.004780034068971872
2023-01-24 06:07:43.750564: step: 1812/527, loss: 0.008875470608472824
2023-01-24 06:07:44.806329: step: 1816/527, loss: 0.0059275031089782715
2023-01-24 06:07:45.840648: step: 1820/527, loss: 0.027109917253255844
2023-01-24 06:07:46.878088: step: 1824/527, loss: 0.005415304563939571
2023-01-24 06:07:47.932008: step: 1828/527, loss: 0.05976094678044319
2023-01-24 06:07:48.974421: step: 1832/527, loss: 0.00021260854555293918
2023-01-24 06:07:50.037375: step: 1836/527, loss: 0.010727842338383198
2023-01-24 06:07:51.097717: step: 1840/527, loss: 0.018707668408751488
2023-01-24 06:07:52.130269: step: 1844/527, loss: 0.0036897333338856697
2023-01-24 06:07:53.195486: step: 1848/527, loss: 0.001390081481076777
2023-01-24 06:07:54.237155: step: 1852/527, loss: 0.005566315725445747
2023-01-24 06:07:55.286357: step: 1856/527, loss: 0.0016809921944513917
2023-01-24 06:07:56.332558: step: 1860/527, loss: 0.008079471997916698
2023-01-24 06:07:57.394224: step: 1864/527, loss: 0.004517318680882454
2023-01-24 06:07:58.442493: step: 1868/527, loss: 0.03713999316096306
2023-01-24 06:07:59.497746: step: 1872/527, loss: 0.005344726145267487
2023-01-24 06:08:00.558682: step: 1876/527, loss: 0.013714388012886047
2023-01-24 06:08:01.604585: step: 1880/527, loss: 0.01340159960091114
2023-01-24 06:08:02.660098: step: 1884/527, loss: 0.004132885951548815
2023-01-24 06:08:03.707555: step: 1888/527, loss: 0.02024313248693943
2023-01-24 06:08:04.785847: step: 1892/527, loss: 0.005223647691309452
2023-01-24 06:08:05.829445: step: 1896/527, loss: 0.028457213193178177
2023-01-24 06:08:06.874764: step: 1900/527, loss: 0.012500789947807789
2023-01-24 06:08:07.914449: step: 1904/527, loss: 0.002309531206265092
2023-01-24 06:08:08.951798: step: 1908/527, loss: 0.003618075279518962
2023-01-24 06:08:09.989648: step: 1912/527, loss: 0.004269478842616081
2023-01-24 06:08:11.051314: step: 1916/527, loss: 0.0013688202016055584
2023-01-24 06:08:12.095180: step: 1920/527, loss: 0.009433871135115623
2023-01-24 06:08:13.143284: step: 1924/527, loss: 0.007213959936052561
2023-01-24 06:08:14.192234: step: 1928/527, loss: 0.002427024533972144
2023-01-24 06:08:15.224241: step: 1932/527, loss: 0.0053839352913200855
2023-01-24 06:08:16.279725: step: 1936/527, loss: 0.01548903901129961
2023-01-24 06:08:17.358050: step: 1940/527, loss: 0.018061330541968346
2023-01-24 06:08:18.418150: step: 1944/527, loss: 0.000532692123670131
2023-01-24 06:08:19.488457: step: 1948/527, loss: 0.0012011309154331684
2023-01-24 06:08:20.536635: step: 1952/527, loss: 0.02080696076154709
2023-01-24 06:08:21.585154: step: 1956/527, loss: 0.003533650655299425
2023-01-24 06:08:22.647274: step: 1960/527, loss: 0.010113691911101341
2023-01-24 06:08:23.712184: step: 1964/527, loss: 0.004794816952198744
2023-01-24 06:08:24.755683: step: 1968/527, loss: 0.0
2023-01-24 06:08:25.812865: step: 1972/527, loss: 0.02904944308102131
2023-01-24 06:08:26.857156: step: 1976/527, loss: 0.003015698166564107
2023-01-24 06:08:27.892999: step: 1980/527, loss: 0.0051984768360853195
2023-01-24 06:08:28.953823: step: 1984/527, loss: 0.0041220299899578094
2023-01-24 06:08:29.989438: step: 1988/527, loss: 0.01986858807504177
2023-01-24 06:08:31.035620: step: 1992/527, loss: 0.010533158667385578
2023-01-24 06:08:32.101976: step: 1996/527, loss: 0.004473670851439238
2023-01-24 06:08:33.165097: step: 2000/527, loss: 0.0014370603021234274
2023-01-24 06:08:34.244279: step: 2004/527, loss: 0.0035524177365005016
2023-01-24 06:08:35.302706: step: 2008/527, loss: 0.0029565240256488323
2023-01-24 06:08:36.350070: step: 2012/527, loss: 0.0009394868393428624
2023-01-24 06:08:37.391466: step: 2016/527, loss: 0.006197627633810043
2023-01-24 06:08:38.429634: step: 2020/527, loss: 0.008275207132101059
2023-01-24 06:08:39.467963: step: 2024/527, loss: 0.0004387865774333477
2023-01-24 06:08:40.524235: step: 2028/527, loss: 0.008020678535103798
2023-01-24 06:08:41.579220: step: 2032/527, loss: 0.012076794169843197
2023-01-24 06:08:42.622007: step: 2036/527, loss: 0.0034120480995625257
2023-01-24 06:08:43.662860: step: 2040/527, loss: 0.0007011427660472691
2023-01-24 06:08:44.720504: step: 2044/527, loss: 0.0012681630905717611
2023-01-24 06:08:45.751959: step: 2048/527, loss: 0.0023309236858040094
2023-01-24 06:08:46.808628: step: 2052/527, loss: 0.000602313200943172
2023-01-24 06:08:47.868300: step: 2056/527, loss: 0.025826985016465187
2023-01-24 06:08:48.916007: step: 2060/527, loss: 0.0006361486157402396
2023-01-24 06:08:49.971499: step: 2064/527, loss: 0.004090974107384682
2023-01-24 06:08:51.023720: step: 2068/527, loss: 0.0165651086717844
2023-01-24 06:08:52.084918: step: 2072/527, loss: 0.012894713319838047
2023-01-24 06:08:53.136519: step: 2076/527, loss: 0.003250683192163706
2023-01-24 06:08:54.183827: step: 2080/527, loss: 0.0031449878588318825
2023-01-24 06:08:55.237676: step: 2084/527, loss: 0.033035244792699814
2023-01-24 06:08:56.289694: step: 2088/527, loss: 0.00939682312309742
2023-01-24 06:08:57.347497: step: 2092/527, loss: 0.0061929416842758656
2023-01-24 06:08:58.399752: step: 2096/527, loss: 0.004464729223400354
2023-01-24 06:08:59.450967: step: 2100/527, loss: 0.016868475824594498
2023-01-24 06:09:00.495669: step: 2104/527, loss: 0.013949783518910408
2023-01-24 06:09:01.541410: step: 2108/527, loss: 0.0008946279413066804
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3432263474957611, 'r': 0.32043142878162134, 'f1': 0.33143741504988117}, 'combined': 0.24421704266833347, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3802499433925248, 'r': 0.29210109287880315, 'f1': 0.3303971230505743}, 'combined': 0.2114541587523675, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36228512151748665, 'r': 0.33134995933857414, 'f1': 0.3461277077729011}, 'combined': 0.2550414688852955, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3798946328938285, 'r': 0.3032946251713672, 'f1': 0.33730038617542957}, 'combined': 0.21587224715227488, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3626751647589317, 'r': 0.32000749831670444, 'f1': 0.34000796696149843}, 'combined': 0.2505321861821567, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.387142419513711, 'r': 0.30738472871143324, 'f1': 0.342683991256547}, 'combined': 0.24569795599526015, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
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
2023-01-24 06:11:30.408616: step: 4/527, loss: 0.013858789578080177
2023-01-24 06:11:31.454576: step: 8/527, loss: 0.0068472097627818584
2023-01-24 06:11:32.492515: step: 12/527, loss: 0.008142342790961266
2023-01-24 06:11:33.531586: step: 16/527, loss: 0.001789297442883253
2023-01-24 06:11:34.618046: step: 20/527, loss: 0.006914615631103516
2023-01-24 06:11:35.671922: step: 24/527, loss: 0.005576504860073328
2023-01-24 06:11:36.744653: step: 28/527, loss: 0.019201723858714104
2023-01-24 06:11:37.805305: step: 32/527, loss: 0.0037800746504217386
2023-01-24 06:11:38.856347: step: 36/527, loss: 0.013856600970029831
2023-01-24 06:11:39.899141: step: 40/527, loss: 0.004672815091907978
2023-01-24 06:11:40.944461: step: 44/527, loss: 0.005283959675580263
2023-01-24 06:11:42.012263: step: 48/527, loss: 0.0046623265370726585
2023-01-24 06:11:43.077875: step: 52/527, loss: 0.027216605842113495
2023-01-24 06:11:44.129055: step: 56/527, loss: 0.008942375890910625
2023-01-24 06:11:45.165470: step: 60/527, loss: 0.005253983661532402
2023-01-24 06:11:46.221277: step: 64/527, loss: 0.0028702174313366413
2023-01-24 06:11:47.258284: step: 68/527, loss: 0.012408256530761719
2023-01-24 06:11:48.301298: step: 72/527, loss: 0.00613422179594636
2023-01-24 06:11:49.335484: step: 76/527, loss: 0.0018351746257394552
2023-01-24 06:11:50.387899: step: 80/527, loss: 0.0019695486407727003
2023-01-24 06:11:51.452567: step: 84/527, loss: 0.0032592942006886005
2023-01-24 06:11:52.506917: step: 88/527, loss: 0.00019935319141950458
2023-01-24 06:11:53.566339: step: 92/527, loss: 0.007793416269123554
2023-01-24 06:11:54.627404: step: 96/527, loss: 0.0067306384444236755
2023-01-24 06:11:55.679142: step: 100/527, loss: 0.009403027594089508
2023-01-24 06:11:56.749978: step: 104/527, loss: 0.0064580426551401615
2023-01-24 06:11:57.801226: step: 108/527, loss: 0.0035173215437680483
2023-01-24 06:11:58.854971: step: 112/527, loss: 0.00279689091257751
2023-01-24 06:11:59.909002: step: 116/527, loss: 0.004287382122129202
2023-01-24 06:12:00.951578: step: 120/527, loss: 0.001108821015805006
2023-01-24 06:12:01.992425: step: 124/527, loss: 0.010869753547012806
2023-01-24 06:12:03.030024: step: 128/527, loss: 0.003302973695099354
2023-01-24 06:12:04.070483: step: 132/527, loss: 0.0060366056859493256
2023-01-24 06:12:05.112593: step: 136/527, loss: 0.003964675590395927
2023-01-24 06:12:06.173709: step: 140/527, loss: 0.01599006913602352
2023-01-24 06:12:07.242293: step: 144/527, loss: 0.009253821335732937
2023-01-24 06:12:08.279339: step: 148/527, loss: 0.0041815536096692085
2023-01-24 06:12:09.340916: step: 152/527, loss: 0.00996509101241827
2023-01-24 06:12:10.395366: step: 156/527, loss: 0.026652518659830093
2023-01-24 06:12:11.454922: step: 160/527, loss: 0.002544883405789733
2023-01-24 06:12:12.513621: step: 164/527, loss: 0.0016231551999226213
2023-01-24 06:12:13.599320: step: 168/527, loss: 0.0036847686860710382
2023-01-24 06:12:14.667805: step: 172/527, loss: 0.01465566549450159
2023-01-24 06:12:15.715399: step: 176/527, loss: 0.006843749899417162
2023-01-24 06:12:16.778701: step: 180/527, loss: 0.00491265719756484
2023-01-24 06:12:17.849360: step: 184/527, loss: 0.009041664190590382
2023-01-24 06:12:18.909670: step: 188/527, loss: 0.030131850391626358
2023-01-24 06:12:19.954806: step: 192/527, loss: 0.0046157860197126865
2023-01-24 06:12:20.999302: step: 196/527, loss: 0.008553413674235344
2023-01-24 06:12:22.057265: step: 200/527, loss: 0.0022844148334115744
2023-01-24 06:12:23.094500: step: 204/527, loss: 0.0013727594632655382
2023-01-24 06:12:24.147771: step: 208/527, loss: 0.012246148660779
2023-01-24 06:12:25.187818: step: 212/527, loss: 0.005377107299864292
2023-01-24 06:12:26.238420: step: 216/527, loss: 0.0049127694219350815
2023-01-24 06:12:27.304086: step: 220/527, loss: 0.007973438128829002
2023-01-24 06:12:28.359830: step: 224/527, loss: 0.0065606338903307915
2023-01-24 06:12:29.398311: step: 228/527, loss: 0.01133472379297018
2023-01-24 06:12:30.448827: step: 232/527, loss: 0.007218982558697462
2023-01-24 06:12:31.493186: step: 236/527, loss: 0.004554699175059795
2023-01-24 06:12:32.546549: step: 240/527, loss: 0.008885643444955349
2023-01-24 06:12:33.580891: step: 244/527, loss: 0.006284310016781092
2023-01-24 06:12:34.613434: step: 248/527, loss: 0.007876320742070675
2023-01-24 06:12:35.668978: step: 252/527, loss: 0.005983966402709484
2023-01-24 06:12:36.726294: step: 256/527, loss: 0.009778381325304508
2023-01-24 06:12:37.769610: step: 260/527, loss: 0.009121174924075603
2023-01-24 06:12:38.819590: step: 264/527, loss: 0.0055168066173791885
2023-01-24 06:12:39.889585: step: 268/527, loss: 0.014901691116392612
2023-01-24 06:12:40.946502: step: 272/527, loss: 0.0025227766018360853
2023-01-24 06:12:41.992187: step: 276/527, loss: 0.003489930648356676
2023-01-24 06:12:43.034165: step: 280/527, loss: 0.00649976497516036
2023-01-24 06:12:44.090467: step: 284/527, loss: 0.01988983154296875
2023-01-24 06:12:45.144940: step: 288/527, loss: 0.005568318068981171
2023-01-24 06:12:46.191937: step: 292/527, loss: 0.006438949145376682
2023-01-24 06:12:47.269640: step: 296/527, loss: 0.006255479995161295
2023-01-24 06:12:48.333154: step: 300/527, loss: 0.006532568950206041
2023-01-24 06:12:49.403932: step: 304/527, loss: 0.004828070290386677
2023-01-24 06:12:50.451858: step: 308/527, loss: 0.0060275159776210785
2023-01-24 06:12:51.520924: step: 312/527, loss: 0.00839760061353445
2023-01-24 06:12:52.579464: step: 316/527, loss: 0.0012062633177265525
2023-01-24 06:12:53.643289: step: 320/527, loss: 0.006844904739409685
2023-01-24 06:12:54.698473: step: 324/527, loss: 0.0021191516425460577
2023-01-24 06:12:55.752519: step: 328/527, loss: 0.007696196436882019
2023-01-24 06:12:56.798106: step: 332/527, loss: 0.03252635896205902
2023-01-24 06:12:57.859720: step: 336/527, loss: 0.0032477176282554865
2023-01-24 06:12:58.908423: step: 340/527, loss: 0.034856900572776794
2023-01-24 06:12:59.957020: step: 344/527, loss: 0.01766323670744896
2023-01-24 06:13:01.026671: step: 348/527, loss: 0.007777311839163303
2023-01-24 06:13:02.067745: step: 352/527, loss: 0.004600877873599529
2023-01-24 06:13:03.121283: step: 356/527, loss: 0.004632095340639353
2023-01-24 06:13:04.178840: step: 360/527, loss: 0.014119184575974941
2023-01-24 06:13:05.277183: step: 364/527, loss: 0.003761056810617447
2023-01-24 06:13:06.322910: step: 368/527, loss: 0.0042406306602060795
2023-01-24 06:13:07.365075: step: 372/527, loss: 0.026668522506952286
2023-01-24 06:13:08.416962: step: 376/527, loss: 0.004697869531810284
2023-01-24 06:13:09.485699: step: 380/527, loss: 0.006828742101788521
2023-01-24 06:13:10.546343: step: 384/527, loss: 0.01649160124361515
2023-01-24 06:13:11.597510: step: 388/527, loss: 0.013972537592053413
2023-01-24 06:13:12.673438: step: 392/527, loss: 0.007497820537537336
2023-01-24 06:13:13.726992: step: 396/527, loss: 0.005453927908092737
2023-01-24 06:13:14.774673: step: 400/527, loss: 0.010237008333206177
2023-01-24 06:13:15.840894: step: 404/527, loss: 0.01906120590865612
2023-01-24 06:13:16.903511: step: 408/527, loss: 9.83189747785218e-05
2023-01-24 06:13:17.953650: step: 412/527, loss: 0.008188781328499317
2023-01-24 06:13:19.007286: step: 416/527, loss: 0.002651694929227233
2023-01-24 06:13:20.049719: step: 420/527, loss: 0.0013871266273781657
2023-01-24 06:13:21.110313: step: 424/527, loss: 0.0038687598425894976
2023-01-24 06:13:22.164104: step: 428/527, loss: 0.005508510395884514
2023-01-24 06:13:23.251576: step: 432/527, loss: 0.012011495418846607
2023-01-24 06:13:24.285477: step: 436/527, loss: 0.0023733838461339474
2023-01-24 06:13:25.338489: step: 440/527, loss: 0.0031815289985388517
2023-01-24 06:13:26.387752: step: 444/527, loss: 0.002654285402968526
2023-01-24 06:13:27.443484: step: 448/527, loss: 0.006022052373737097
2023-01-24 06:13:28.516150: step: 452/527, loss: 0.01670355349779129
2023-01-24 06:13:29.566214: step: 456/527, loss: 0.006755279377102852
2023-01-24 06:13:30.613323: step: 460/527, loss: 0.0013523250818252563
2023-01-24 06:13:31.660326: step: 464/527, loss: 0.015229029580950737
2023-01-24 06:13:32.715565: step: 468/527, loss: 0.007500459440052509
2023-01-24 06:13:33.765576: step: 472/527, loss: 0.004672660026699305
2023-01-24 06:13:34.829798: step: 476/527, loss: 0.02393902651965618
2023-01-24 06:13:35.874812: step: 480/527, loss: 0.002292448654770851
2023-01-24 06:13:36.931148: step: 484/527, loss: 0.002667705761268735
2023-01-24 06:13:37.970582: step: 488/527, loss: 0.005085463635623455
2023-01-24 06:13:39.030747: step: 492/527, loss: 0.010912981815636158
2023-01-24 06:13:40.084471: step: 496/527, loss: 0.0022410873789340258
2023-01-24 06:13:41.126186: step: 500/527, loss: 0.04836438223719597
2023-01-24 06:13:42.178828: step: 504/527, loss: 0.0013247053138911724
2023-01-24 06:13:43.232537: step: 508/527, loss: 0.006348397117108107
2023-01-24 06:13:44.278340: step: 512/527, loss: 0.0023427847772836685
2023-01-24 06:13:45.320889: step: 516/527, loss: 0.004499959293752909
2023-01-24 06:13:46.381377: step: 520/527, loss: 0.006391513627022505
2023-01-24 06:13:47.438775: step: 524/527, loss: 0.00026770145632326603
2023-01-24 06:13:48.484553: step: 528/527, loss: 0.023344792425632477
2023-01-24 06:13:49.545385: step: 532/527, loss: 0.004374243319034576
2023-01-24 06:13:50.608243: step: 536/527, loss: 0.017439447343349457
2023-01-24 06:13:51.662447: step: 540/527, loss: 0.013942568562924862
2023-01-24 06:13:52.713414: step: 544/527, loss: 0.00022667463053949177
2023-01-24 06:13:53.756299: step: 548/527, loss: 0.00016721135762054473
2023-01-24 06:13:54.813513: step: 552/527, loss: 0.003708152798935771
2023-01-24 06:13:55.874778: step: 556/527, loss: 0.004756446927785873
2023-01-24 06:13:56.917735: step: 560/527, loss: 0.003914811182767153
2023-01-24 06:13:57.971199: step: 564/527, loss: 0.005228899419307709
2023-01-24 06:13:59.025246: step: 568/527, loss: 0.014796995557844639
2023-01-24 06:14:00.087711: step: 572/527, loss: 0.0010173649061471224
2023-01-24 06:14:01.132578: step: 576/527, loss: 0.0005553365917876363
2023-01-24 06:14:02.174545: step: 580/527, loss: 0.017911789938807487
2023-01-24 06:14:03.223039: step: 584/527, loss: 0.006082690320909023
2023-01-24 06:14:04.288626: step: 588/527, loss: 0.11595837026834488
2023-01-24 06:14:05.364497: step: 592/527, loss: 0.0053380210883915424
2023-01-24 06:14:06.429354: step: 596/527, loss: 0.00829209852963686
2023-01-24 06:14:07.472239: step: 600/527, loss: 2.9707933208555914e-05
2023-01-24 06:14:08.529835: step: 604/527, loss: 0.004472649190574884
2023-01-24 06:14:09.581316: step: 608/527, loss: 0.0002699148317333311
2023-01-24 06:14:10.648483: step: 612/527, loss: 0.0035728083457797766
2023-01-24 06:14:11.703385: step: 616/527, loss: 0.006894966587424278
2023-01-24 06:14:12.749542: step: 620/527, loss: 0.0008049603784456849
2023-01-24 06:14:13.805644: step: 624/527, loss: 0.04674700275063515
2023-01-24 06:14:14.863100: step: 628/527, loss: 0.014055876061320305
2023-01-24 06:14:15.924769: step: 632/527, loss: 0.006032452918589115
2023-01-24 06:14:16.968778: step: 636/527, loss: 0.0017511112382635474
2023-01-24 06:14:18.015223: step: 640/527, loss: 0.005384983029216528
2023-01-24 06:14:19.059697: step: 644/527, loss: 0.012973129749298096
2023-01-24 06:14:20.118218: step: 648/527, loss: 0.004904575180262327
2023-01-24 06:14:21.178385: step: 652/527, loss: 0.032769348472356796
2023-01-24 06:14:22.235263: step: 656/527, loss: 0.019441980868577957
2023-01-24 06:14:23.311129: step: 660/527, loss: 0.0044271028600633144
2023-01-24 06:14:24.350588: step: 664/527, loss: 0.0037613767199218273
2023-01-24 06:14:25.396768: step: 668/527, loss: 0.0008808940183371305
2023-01-24 06:14:26.469006: step: 672/527, loss: 0.011488381773233414
2023-01-24 06:14:27.525254: step: 676/527, loss: 0.009461192414164543
2023-01-24 06:14:28.589114: step: 680/527, loss: 0.005549016874283552
2023-01-24 06:14:29.652847: step: 684/527, loss: 0.0047487132251262665
2023-01-24 06:14:30.704189: step: 688/527, loss: 0.07491440325975418
2023-01-24 06:14:31.773324: step: 692/527, loss: 0.010135111398994923
2023-01-24 06:14:32.819494: step: 696/527, loss: 0.0026387826073914766
2023-01-24 06:14:33.882384: step: 700/527, loss: 0.003873219480738044
2023-01-24 06:14:34.928379: step: 704/527, loss: 0.0010550337610766292
2023-01-24 06:14:35.977358: step: 708/527, loss: 0.010220732539892197
2023-01-24 06:14:37.023274: step: 712/527, loss: 0.0015176909510046244
2023-01-24 06:14:38.068700: step: 716/527, loss: 0.008627385832369328
2023-01-24 06:14:39.115437: step: 720/527, loss: 0.003731341799721122
2023-01-24 06:14:40.186710: step: 724/527, loss: 0.01755712553858757
2023-01-24 06:14:41.236988: step: 728/527, loss: 0.004385507199913263
2023-01-24 06:14:42.307223: step: 732/527, loss: 0.007302356883883476
2023-01-24 06:14:43.366958: step: 736/527, loss: 0.006042297929525375
2023-01-24 06:14:44.409496: step: 740/527, loss: 0.012654879130423069
2023-01-24 06:14:45.464732: step: 744/527, loss: 0.007096535060554743
2023-01-24 06:14:46.510796: step: 748/527, loss: 0.008909719996154308
2023-01-24 06:14:47.556024: step: 752/527, loss: 0.008092156611382961
2023-01-24 06:14:48.597199: step: 756/527, loss: 0.00423313956707716
2023-01-24 06:14:49.634682: step: 760/527, loss: 0.002946165855973959
2023-01-24 06:14:50.684432: step: 764/527, loss: 0.010203739628195763
2023-01-24 06:14:51.754255: step: 768/527, loss: 0.006518718786537647
2023-01-24 06:14:52.801653: step: 772/527, loss: 0.011371956206858158
2023-01-24 06:14:53.866511: step: 776/527, loss: 0.007888561114668846
2023-01-24 06:14:54.908515: step: 780/527, loss: 0.012847617268562317
2023-01-24 06:14:55.955921: step: 784/527, loss: 0.00215515517629683
2023-01-24 06:14:57.010825: step: 788/527, loss: 0.013022433035075665
2023-01-24 06:14:58.067093: step: 792/527, loss: 0.008794841356575489
2023-01-24 06:14:59.135980: step: 796/527, loss: 0.20729830861091614
2023-01-24 06:15:00.192526: step: 800/527, loss: 0.013999639078974724
2023-01-24 06:15:01.246206: step: 804/527, loss: 0.007690807338804007
2023-01-24 06:15:02.312203: step: 808/527, loss: 0.05223587527871132
2023-01-24 06:15:03.373966: step: 812/527, loss: 0.0006392710492946208
2023-01-24 06:15:04.441114: step: 816/527, loss: 0.011065471917390823
2023-01-24 06:15:05.496210: step: 820/527, loss: 0.00035611592466011643
2023-01-24 06:15:06.538226: step: 824/527, loss: 0.03008735366165638
2023-01-24 06:15:07.596154: step: 828/527, loss: 0.03518468886613846
2023-01-24 06:15:08.634621: step: 832/527, loss: 0.010908438824117184
2023-01-24 06:15:09.678110: step: 836/527, loss: 0.001667057629674673
2023-01-24 06:15:10.734104: step: 840/527, loss: 0.00141559645999223
2023-01-24 06:15:11.789042: step: 844/527, loss: 0.0023408320266753435
2023-01-24 06:15:12.838195: step: 848/527, loss: 0.006133314687758684
2023-01-24 06:15:13.890169: step: 852/527, loss: 0.038530729711055756
2023-01-24 06:15:14.940992: step: 856/527, loss: 0.0035190805792808533
2023-01-24 06:15:15.990614: step: 860/527, loss: 0.011946484446525574
2023-01-24 06:15:17.034036: step: 864/527, loss: 0.010769824497401714
2023-01-24 06:15:18.081263: step: 868/527, loss: 0.004497906658798456
2023-01-24 06:15:19.147954: step: 872/527, loss: 0.0001892131840577349
2023-01-24 06:15:20.202016: step: 876/527, loss: 0.019124925136566162
2023-01-24 06:15:21.258230: step: 880/527, loss: 0.0088470708578825
2023-01-24 06:15:22.313911: step: 884/527, loss: 0.0115622254088521
2023-01-24 06:15:23.358620: step: 888/527, loss: 0.0007585367420688272
2023-01-24 06:15:24.409968: step: 892/527, loss: 0.004425411578267813
2023-01-24 06:15:25.453764: step: 896/527, loss: 0.008273812010884285
2023-01-24 06:15:26.523621: step: 900/527, loss: 0.0007577762007713318
2023-01-24 06:15:27.575766: step: 904/527, loss: 0.0016283057630062103
2023-01-24 06:15:28.632562: step: 908/527, loss: 0.007221805397421122
2023-01-24 06:15:29.673389: step: 912/527, loss: 0.00942810345441103
2023-01-24 06:15:30.712613: step: 916/527, loss: 0.009683789685368538
2023-01-24 06:15:31.762999: step: 920/527, loss: 0.0033346693962812424
2023-01-24 06:15:32.804981: step: 924/527, loss: 0.011278386227786541
2023-01-24 06:15:33.846024: step: 928/527, loss: 0.008082011714577675
2023-01-24 06:15:34.917914: step: 932/527, loss: 0.008215578272938728
2023-01-24 06:15:35.976795: step: 936/527, loss: 0.004424274433404207
2023-01-24 06:15:37.013919: step: 940/527, loss: 0.009950798936188221
2023-01-24 06:15:38.064577: step: 944/527, loss: 0.00863655749708414
2023-01-24 06:15:39.123542: step: 948/527, loss: 0.003876417176797986
2023-01-24 06:15:40.161844: step: 952/527, loss: 0.008662656880915165
2023-01-24 06:15:41.202183: step: 956/527, loss: 0.004613472148776054
2023-01-24 06:15:42.250619: step: 960/527, loss: 0.005549674388021231
2023-01-24 06:15:43.323674: step: 964/527, loss: 0.03802313655614853
2023-01-24 06:15:44.375672: step: 968/527, loss: 0.0015504133189097047
2023-01-24 06:15:45.419662: step: 972/527, loss: 0.01773657463490963
2023-01-24 06:15:46.457510: step: 976/527, loss: 0.00028582499362528324
2023-01-24 06:15:47.510663: step: 980/527, loss: 0.004120856523513794
2023-01-24 06:15:48.570805: step: 984/527, loss: 0.003703651251271367
2023-01-24 06:15:49.627659: step: 988/527, loss: 0.0038197690155357122
2023-01-24 06:15:50.678277: step: 992/527, loss: 0.0008174747345037758
2023-01-24 06:15:51.722929: step: 996/527, loss: 0.013780878856778145
2023-01-24 06:15:52.780172: step: 1000/527, loss: 0.009317596442997456
2023-01-24 06:15:53.831085: step: 1004/527, loss: 0.010493717156350613
2023-01-24 06:15:54.885240: step: 1008/527, loss: 0.019394738599658012
2023-01-24 06:15:55.921206: step: 1012/527, loss: 0.02577967382967472
2023-01-24 06:15:56.978112: step: 1016/527, loss: 0.005452234763652086
2023-01-24 06:15:58.035899: step: 1020/527, loss: 0.010642754845321178
2023-01-24 06:15:59.079347: step: 1024/527, loss: 0.0095218475908041
2023-01-24 06:16:00.151247: step: 1028/527, loss: 0.04922255128622055
2023-01-24 06:16:01.201019: step: 1032/527, loss: 0.00043056276626884937
2023-01-24 06:16:02.230804: step: 1036/527, loss: 0.003438494633883238
2023-01-24 06:16:03.276449: step: 1040/527, loss: 0.004783006850630045
2023-01-24 06:16:04.330716: step: 1044/527, loss: 0.01521259918808937
2023-01-24 06:16:05.371902: step: 1048/527, loss: 0.006692052818834782
2023-01-24 06:16:06.441249: step: 1052/527, loss: 0.0197843499481678
2023-01-24 06:16:07.480218: step: 1056/527, loss: 0.004113410599529743
2023-01-24 06:16:08.530490: step: 1060/527, loss: 0.018774723634123802
2023-01-24 06:16:09.583338: step: 1064/527, loss: 0.01182416919618845
2023-01-24 06:16:10.643247: step: 1068/527, loss: 0.006834171712398529
2023-01-24 06:16:11.699718: step: 1072/527, loss: 0.005259782075881958
2023-01-24 06:16:12.748984: step: 1076/527, loss: 0.0082195233553648
2023-01-24 06:16:13.796225: step: 1080/527, loss: 0.010673260316252708
2023-01-24 06:16:14.837942: step: 1084/527, loss: 0.010740244761109352
2023-01-24 06:16:15.898467: step: 1088/527, loss: 0.03633970767259598
2023-01-24 06:16:16.949864: step: 1092/527, loss: 0.004128754138946533
2023-01-24 06:16:17.987669: step: 1096/527, loss: 0.009518708102405071
2023-01-24 06:16:19.037861: step: 1100/527, loss: 0.012892210856080055
2023-01-24 06:16:20.083199: step: 1104/527, loss: 0.003520045895129442
2023-01-24 06:16:21.140119: step: 1108/527, loss: 0.01902119815349579
2023-01-24 06:16:22.187195: step: 1112/527, loss: 0.008588296361267567
2023-01-24 06:16:23.247976: step: 1116/527, loss: 0.0016149862203747034
2023-01-24 06:16:24.281439: step: 1120/527, loss: 0.009680958464741707
2023-01-24 06:16:25.330519: step: 1124/527, loss: 0.004695790354162455
2023-01-24 06:16:26.384868: step: 1128/527, loss: 0.017347292974591255
2023-01-24 06:16:27.453650: step: 1132/527, loss: 0.004620944615453482
2023-01-24 06:16:28.499130: step: 1136/527, loss: 0.02449961006641388
2023-01-24 06:16:29.556908: step: 1140/527, loss: 0.012774487026035786
2023-01-24 06:16:30.608959: step: 1144/527, loss: 0.05937916412949562
2023-01-24 06:16:31.653288: step: 1148/527, loss: 0.011631275527179241
2023-01-24 06:16:32.727856: step: 1152/527, loss: 0.012058062478899956
2023-01-24 06:16:33.765645: step: 1156/527, loss: 0.008152112364768982
2023-01-24 06:16:34.817353: step: 1160/527, loss: 0.008222196251153946
2023-01-24 06:16:35.862132: step: 1164/527, loss: 0.0014271700056269765
2023-01-24 06:16:36.932237: step: 1168/527, loss: 0.01853320747613907
2023-01-24 06:16:37.975727: step: 1172/527, loss: 0.003556971438229084
2023-01-24 06:16:39.016995: step: 1176/527, loss: 0.008396762423217297
2023-01-24 06:16:40.080818: step: 1180/527, loss: 0.011722382158041
2023-01-24 06:16:41.131397: step: 1184/527, loss: 0.007182334549725056
2023-01-24 06:16:42.177025: step: 1188/527, loss: 0.006055328529328108
2023-01-24 06:16:43.221944: step: 1192/527, loss: 0.036495935171842575
2023-01-24 06:16:44.260779: step: 1196/527, loss: 0.02186264470219612
2023-01-24 06:16:45.309831: step: 1200/527, loss: 0.01584651879966259
2023-01-24 06:16:46.366203: step: 1204/527, loss: 0.010809837840497494
2023-01-24 06:16:47.416556: step: 1208/527, loss: 0.02692943997681141
2023-01-24 06:16:48.479391: step: 1212/527, loss: 0.009454113431274891
2023-01-24 06:16:49.544560: step: 1216/527, loss: 0.027783891186118126
2023-01-24 06:16:50.585685: step: 1220/527, loss: 0.004693866707384586
2023-01-24 06:16:51.658125: step: 1224/527, loss: 0.00023963444982655346
2023-01-24 06:16:52.690868: step: 1228/527, loss: 0.0038243255112320185
2023-01-24 06:16:53.732539: step: 1232/527, loss: 0.02387555129826069
2023-01-24 06:16:54.781000: step: 1236/527, loss: 0.014292039908468723
2023-01-24 06:16:55.843058: step: 1240/527, loss: 0.004833715967833996
2023-01-24 06:16:56.886122: step: 1244/527, loss: 0.002711265115067363
2023-01-24 06:16:57.960727: step: 1248/527, loss: 0.007548751775175333
2023-01-24 06:16:59.022386: step: 1252/527, loss: 0.00460277684032917
2023-01-24 06:17:00.084633: step: 1256/527, loss: 0.004603673703968525
2023-01-24 06:17:01.134416: step: 1260/527, loss: 0.007028146181255579
2023-01-24 06:17:02.173629: step: 1264/527, loss: 0.010227174498140812
2023-01-24 06:17:03.243062: step: 1268/527, loss: 0.004150801338255405
2023-01-24 06:17:04.288810: step: 1272/527, loss: 0.007186429109424353
2023-01-24 06:17:05.350295: step: 1276/527, loss: 0.02736535668373108
2023-01-24 06:17:06.417630: step: 1280/527, loss: 0.005742392502725124
2023-01-24 06:17:07.465878: step: 1284/527, loss: 0.005569592118263245
2023-01-24 06:17:08.527031: step: 1288/527, loss: 0.0033510392531752586
2023-01-24 06:17:09.572891: step: 1292/527, loss: 0.005017543211579323
2023-01-24 06:17:10.613427: step: 1296/527, loss: 0.01486192923039198
2023-01-24 06:17:11.685121: step: 1300/527, loss: 0.00042533804662525654
2023-01-24 06:17:12.733985: step: 1304/527, loss: 0.0162766445428133
2023-01-24 06:17:13.800049: step: 1308/527, loss: 0.008644442074000835
2023-01-24 06:17:14.848446: step: 1312/527, loss: 0.004043469671159983
2023-01-24 06:17:15.898831: step: 1316/527, loss: 0.016971854493021965
2023-01-24 06:17:16.950785: step: 1320/527, loss: 0.02391149289906025
2023-01-24 06:17:18.004579: step: 1324/527, loss: 0.0059237172827124596
2023-01-24 06:17:19.044170: step: 1328/527, loss: 0.040738124400377274
2023-01-24 06:17:20.113571: step: 1332/527, loss: 0.005882258526980877
2023-01-24 06:17:21.158882: step: 1336/527, loss: 0.006508353166282177
2023-01-24 06:17:22.221108: step: 1340/527, loss: 0.004140972625464201
2023-01-24 06:17:23.278096: step: 1344/527, loss: 0.0037541233468800783
2023-01-24 06:17:24.334889: step: 1348/527, loss: 0.006124555133283138
2023-01-24 06:17:25.371725: step: 1352/527, loss: 0.0029107732698321342
2023-01-24 06:17:26.418132: step: 1356/527, loss: 0.06534484028816223
2023-01-24 06:17:27.466644: step: 1360/527, loss: 0.00041893587331287563
2023-01-24 06:17:28.495648: step: 1364/527, loss: 0.0002086635649902746
2023-01-24 06:17:29.559019: step: 1368/527, loss: 0.010120702907443047
2023-01-24 06:17:30.608947: step: 1372/527, loss: 0.011724220588803291
2023-01-24 06:17:31.653350: step: 1376/527, loss: 0.0452674962580204
2023-01-24 06:17:32.718149: step: 1380/527, loss: 0.004746389575302601
2023-01-24 06:17:33.759738: step: 1384/527, loss: 0.00955195352435112
2023-01-24 06:17:34.808019: step: 1388/527, loss: 0.0017424571560695767
2023-01-24 06:17:35.851704: step: 1392/527, loss: 0.004315395839512348
2023-01-24 06:17:36.914979: step: 1396/527, loss: 0.007179904729127884
2023-01-24 06:17:37.982029: step: 1400/527, loss: 0.006254470907151699
2023-01-24 06:17:39.044898: step: 1404/527, loss: 0.011929718777537346
2023-01-24 06:17:40.102131: step: 1408/527, loss: 0.02120901457965374
2023-01-24 06:17:41.164676: step: 1412/527, loss: 0.01178006362169981
2023-01-24 06:17:42.217300: step: 1416/527, loss: 0.013863730244338512
2023-01-24 06:17:43.269744: step: 1420/527, loss: 0.029085958376526833
2023-01-24 06:17:44.326234: step: 1424/527, loss: 0.014001265168190002
2023-01-24 06:17:45.392534: step: 1428/527, loss: 0.010790448635816574
2023-01-24 06:17:46.451718: step: 1432/527, loss: 0.008747573010623455
2023-01-24 06:17:47.503953: step: 1436/527, loss: 0.03057769685983658
2023-01-24 06:17:48.541186: step: 1440/527, loss: 0.002285042544826865
2023-01-24 06:17:49.593627: step: 1444/527, loss: 0.017266442999243736
2023-01-24 06:17:50.627538: step: 1448/527, loss: 0.0036021436098963022
2023-01-24 06:17:51.667611: step: 1452/527, loss: 0.009646909311413765
2023-01-24 06:17:52.700261: step: 1456/527, loss: 0.0003939413873013109
2023-01-24 06:17:53.726114: step: 1460/527, loss: 0.016654180362820625
2023-01-24 06:17:54.782878: step: 1464/527, loss: 0.038487453013658524
2023-01-24 06:17:55.837220: step: 1468/527, loss: 0.017812369391322136
2023-01-24 06:17:56.891505: step: 1472/527, loss: 0.020881012082099915
2023-01-24 06:17:57.933532: step: 1476/527, loss: 0.01195050310343504
2023-01-24 06:17:58.981643: step: 1480/527, loss: 0.008777450770139694
2023-01-24 06:18:00.033031: step: 1484/527, loss: 0.011199723929166794
2023-01-24 06:18:01.115481: step: 1488/527, loss: 0.0025973960291594267
2023-01-24 06:18:02.170701: step: 1492/527, loss: 0.0035221234429627657
2023-01-24 06:18:03.222567: step: 1496/527, loss: 0.02600690722465515
2023-01-24 06:18:04.269901: step: 1500/527, loss: 0.010533664375543594
2023-01-24 06:18:05.329047: step: 1504/527, loss: 0.0397987961769104
2023-01-24 06:18:06.368440: step: 1508/527, loss: 0.018840234726667404
2023-01-24 06:18:07.409890: step: 1512/527, loss: 0.0033310847356915474
2023-01-24 06:18:08.459221: step: 1516/527, loss: 0.0038425689563155174
2023-01-24 06:18:09.512643: step: 1520/527, loss: 0.003512369003146887
2023-01-24 06:18:10.566552: step: 1524/527, loss: 0.005522511899471283
2023-01-24 06:18:11.626920: step: 1528/527, loss: 0.002252943115308881
2023-01-24 06:18:12.655169: step: 1532/527, loss: 0.018201924860477448
2023-01-24 06:18:13.729791: step: 1536/527, loss: 0.0021684232633560896
2023-01-24 06:18:14.775653: step: 1540/527, loss: 0.006839650683104992
2023-01-24 06:18:15.823159: step: 1544/527, loss: 0.006699761375784874
2023-01-24 06:18:16.880799: step: 1548/527, loss: 0.002429414540529251
2023-01-24 06:18:17.950323: step: 1552/527, loss: 0.00799989141523838
2023-01-24 06:18:19.002931: step: 1556/527, loss: 0.007017431780695915
2023-01-24 06:18:20.046299: step: 1560/527, loss: 0.008746856823563576
2023-01-24 06:18:21.091797: step: 1564/527, loss: 0.009376038797199726
2023-01-24 06:18:22.148247: step: 1568/527, loss: 0.01515976246446371
2023-01-24 06:18:23.196080: step: 1572/527, loss: 0.008484846912324429
2023-01-24 06:18:24.255380: step: 1576/527, loss: 0.0073716407641768456
2023-01-24 06:18:25.299984: step: 1580/527, loss: 0.002795808482915163
2023-01-24 06:18:26.370531: step: 1584/527, loss: 0.05331748351454735
2023-01-24 06:18:27.427211: step: 1588/527, loss: 0.004696378484368324
2023-01-24 06:18:28.484693: step: 1592/527, loss: 0.028546925634145737
2023-01-24 06:18:29.526336: step: 1596/527, loss: 0.023770490661263466
2023-01-24 06:18:30.591713: step: 1600/527, loss: 0.016821762546896935
2023-01-24 06:18:31.627236: step: 1604/527, loss: 0.005958883091807365
2023-01-24 06:18:32.679632: step: 1608/527, loss: 0.011343484744429588
2023-01-24 06:18:33.737474: step: 1612/527, loss: 0.04513514041900635
2023-01-24 06:18:34.799755: step: 1616/527, loss: 0.002865853952243924
2023-01-24 06:18:35.843481: step: 1620/527, loss: 0.020046016201376915
2023-01-24 06:18:36.889732: step: 1624/527, loss: 0.005779031198471785
2023-01-24 06:18:37.935367: step: 1628/527, loss: 0.024139486253261566
2023-01-24 06:18:39.004558: step: 1632/527, loss: 0.009461689740419388
2023-01-24 06:18:40.077374: step: 1636/527, loss: 0.018036510795354843
2023-01-24 06:18:41.111543: step: 1640/527, loss: 0.0014199659926816821
2023-01-24 06:18:42.154027: step: 1644/527, loss: 0.002625318244099617
2023-01-24 06:18:43.208647: step: 1648/527, loss: 0.011786160059273243
2023-01-24 06:18:44.256218: step: 1652/527, loss: 0.0008031951729208231
2023-01-24 06:18:45.303660: step: 1656/527, loss: 0.0030371220782399178
2023-01-24 06:18:46.353665: step: 1660/527, loss: 0.03089003451168537
2023-01-24 06:18:47.403579: step: 1664/527, loss: 0.002912268042564392
2023-01-24 06:18:48.479902: step: 1668/527, loss: 0.016414275392889977
2023-01-24 06:18:49.540916: step: 1672/527, loss: 0.0059144445694983006
2023-01-24 06:18:50.577931: step: 1676/527, loss: 0.005163245834410191
2023-01-24 06:18:51.632750: step: 1680/527, loss: 0.017710890620946884
2023-01-24 06:18:52.675236: step: 1684/527, loss: 0.001954286592081189
2023-01-24 06:18:53.707507: step: 1688/527, loss: 0.00947886798530817
2023-01-24 06:18:54.743338: step: 1692/527, loss: 0.0005294825532473624
2023-01-24 06:18:55.784722: step: 1696/527, loss: 0.010331869125366211
2023-01-24 06:18:56.822490: step: 1700/527, loss: 0.016443584114313126
2023-01-24 06:18:57.861977: step: 1704/527, loss: 0.003135921899229288
2023-01-24 06:18:58.924719: step: 1708/527, loss: 0.0030218912288546562
2023-01-24 06:18:59.964162: step: 1712/527, loss: 0.005403540097177029
2023-01-24 06:19:01.013893: step: 1716/527, loss: 0.003915396519005299
2023-01-24 06:19:02.064101: step: 1720/527, loss: 0.00950311403721571
2023-01-24 06:19:03.109142: step: 1724/527, loss: 0.00293614505790174
2023-01-24 06:19:04.165670: step: 1728/527, loss: 0.0018410051707178354
2023-01-24 06:19:05.206459: step: 1732/527, loss: 0.0005031333421356976
2023-01-24 06:19:06.258778: step: 1736/527, loss: 0.01653796061873436
2023-01-24 06:19:07.303130: step: 1740/527, loss: 0.012764845974743366
2023-01-24 06:19:08.348794: step: 1744/527, loss: 0.006373863201588392
2023-01-24 06:19:09.406592: step: 1748/527, loss: 0.006958916783332825
2023-01-24 06:19:10.464712: step: 1752/527, loss: 0.007993902079761028
2023-01-24 06:19:11.502237: step: 1756/527, loss: 0.0008073113858699799
2023-01-24 06:19:12.555073: step: 1760/527, loss: 0.0011528790928423405
2023-01-24 06:19:13.598565: step: 1764/527, loss: 0.002510812832042575
2023-01-24 06:19:14.651860: step: 1768/527, loss: 0.010897216387093067
2023-01-24 06:19:15.728610: step: 1772/527, loss: 0.02104314975440502
2023-01-24 06:19:16.756765: step: 1776/527, loss: 0.0071724653244018555
2023-01-24 06:19:17.814306: step: 1780/527, loss: 0.006791979540139437
2023-01-24 06:19:18.851751: step: 1784/527, loss: 0.004590075463056564
2023-01-24 06:19:19.906352: step: 1788/527, loss: 0.0061460682190954685
2023-01-24 06:19:20.969546: step: 1792/527, loss: 0.009351025335490704
2023-01-24 06:19:22.026086: step: 1796/527, loss: 0.00035061786184087396
2023-01-24 06:19:23.091696: step: 1800/527, loss: 0.004905285779386759
2023-01-24 06:19:24.155198: step: 1804/527, loss: 0.005148687399923801
2023-01-24 06:19:25.209439: step: 1808/527, loss: 0.009701180271804333
2023-01-24 06:19:26.249380: step: 1812/527, loss: 0.0033806965220719576
2023-01-24 06:19:27.319422: step: 1816/527, loss: 0.006968039553612471
2023-01-24 06:19:28.360856: step: 1820/527, loss: 0.015023082494735718
2023-01-24 06:19:29.400916: step: 1824/527, loss: 0.006000255234539509
2023-01-24 06:19:30.465580: step: 1828/527, loss: 0.008121452294290066
2023-01-24 06:19:31.516730: step: 1832/527, loss: 0.05960588529706001
2023-01-24 06:19:32.550336: step: 1836/527, loss: 0.0023274431005120277
2023-01-24 06:19:33.599563: step: 1840/527, loss: 0.039414361119270325
2023-01-24 06:19:34.665571: step: 1844/527, loss: 0.00644992059096694
2023-01-24 06:19:35.710734: step: 1848/527, loss: 0.006524163763970137
2023-01-24 06:19:36.779117: step: 1852/527, loss: 0.01013212651014328
2023-01-24 06:19:37.835134: step: 1856/527, loss: 0.004018633626401424
2023-01-24 06:19:38.879888: step: 1860/527, loss: 0.014596362598240376
2023-01-24 06:19:39.921204: step: 1864/527, loss: 0.025225821882486343
2023-01-24 06:19:40.973971: step: 1868/527, loss: 0.005242825020104647
2023-01-24 06:19:42.021108: step: 1872/527, loss: 0.01516877394169569
2023-01-24 06:19:43.079982: step: 1876/527, loss: 0.014488687738776207
2023-01-24 06:19:44.114361: step: 1880/527, loss: 0.005859555676579475
2023-01-24 06:19:45.162851: step: 1884/527, loss: 0.007024526596069336
2023-01-24 06:19:46.219533: step: 1888/527, loss: 0.015668893232941628
2023-01-24 06:19:47.265324: step: 1892/527, loss: 0.000999676762148738
2023-01-24 06:19:48.328026: step: 1896/527, loss: 0.0033800743985921144
2023-01-24 06:19:49.363823: step: 1900/527, loss: 0.013505561277270317
2023-01-24 06:19:50.418453: step: 1904/527, loss: 0.005636982619762421
2023-01-24 06:19:51.471516: step: 1908/527, loss: 0.012868654914200306
2023-01-24 06:19:52.550497: step: 1912/527, loss: 0.0019239624962210655
2023-01-24 06:19:53.594371: step: 1916/527, loss: 0.012410313822329044
2023-01-24 06:19:54.643825: step: 1920/527, loss: 0.0013808478834107518
2023-01-24 06:19:55.693637: step: 1924/527, loss: 0.0061982120387256145
2023-01-24 06:19:56.727621: step: 1928/527, loss: 0.004160887096077204
2023-01-24 06:19:57.807559: step: 1932/527, loss: 0.007977792993187904
2023-01-24 06:19:58.854106: step: 1936/527, loss: 0.006800683680921793
2023-01-24 06:19:59.887205: step: 1940/527, loss: 0.0003702831454575062
2023-01-24 06:20:00.945674: step: 1944/527, loss: 0.008752088062465191
2023-01-24 06:20:02.005069: step: 1948/527, loss: 0.006395608186721802
2023-01-24 06:20:03.068042: step: 1952/527, loss: 0.007251636125147343
2023-01-24 06:20:04.113805: step: 1956/527, loss: 0.0034479154273867607
2023-01-24 06:20:05.168437: step: 1960/527, loss: 0.005253272131085396
2023-01-24 06:20:06.219208: step: 1964/527, loss: 0.0028642623219639063
2023-01-24 06:20:07.275868: step: 1968/527, loss: 0.0029721830505877733
2023-01-24 06:20:08.332285: step: 1972/527, loss: 0.003342901123687625
2023-01-24 06:20:09.406846: step: 1976/527, loss: 0.08128899335861206
2023-01-24 06:20:10.469720: step: 1980/527, loss: 0.00876810122281313
2023-01-24 06:20:11.529167: step: 1984/527, loss: 0.0020359300542622805
2023-01-24 06:20:12.575312: step: 1988/527, loss: 0.0035185536835342646
2023-01-24 06:20:13.627232: step: 1992/527, loss: 0.006642031483352184
2023-01-24 06:20:14.683280: step: 1996/527, loss: 0.0020395193714648485
2023-01-24 06:20:15.768258: step: 2000/527, loss: 0.006527036428451538
2023-01-24 06:20:16.810266: step: 2004/527, loss: 0.00270862621255219
2023-01-24 06:20:17.873461: step: 2008/527, loss: 0.022922977805137634
2023-01-24 06:20:18.923386: step: 2012/527, loss: 0.002328132512047887
2023-01-24 06:20:19.982491: step: 2016/527, loss: 0.000278402934782207
2023-01-24 06:20:21.028354: step: 2020/527, loss: 0.0019245247822254896
2023-01-24 06:20:22.088972: step: 2024/527, loss: 0.0017612857045605779
2023-01-24 06:20:23.143536: step: 2028/527, loss: 0.00990452989935875
2023-01-24 06:20:24.195701: step: 2032/527, loss: 0.005405002739280462
2023-01-24 06:20:25.247782: step: 2036/527, loss: 0.016722535714507103
2023-01-24 06:20:26.305132: step: 2040/527, loss: 0.02127009630203247
2023-01-24 06:20:27.354509: step: 2044/527, loss: 0.00259059458039701
2023-01-24 06:20:28.400476: step: 2048/527, loss: 0.012533239088952541
2023-01-24 06:20:29.446697: step: 2052/527, loss: 0.012309527024626732
2023-01-24 06:20:30.501788: step: 2056/527, loss: 0.0042281183414161205
2023-01-24 06:20:31.548750: step: 2060/527, loss: 0.0022847955115139484
2023-01-24 06:20:32.609432: step: 2064/527, loss: 0.00895863026380539
2023-01-24 06:20:33.665412: step: 2068/527, loss: 0.012750847265124321
2023-01-24 06:20:34.719285: step: 2072/527, loss: 0.007263650186359882
2023-01-24 06:20:35.775798: step: 2076/527, loss: 0.006345091387629509
2023-01-24 06:20:36.815275: step: 2080/527, loss: 0.004227068740874529
2023-01-24 06:20:37.865765: step: 2084/527, loss: 0.0013252180069684982
2023-01-24 06:20:38.920756: step: 2088/527, loss: 0.014781714417040348
2023-01-24 06:20:39.955736: step: 2092/527, loss: 0.002819240093231201
2023-01-24 06:20:41.000328: step: 2096/527, loss: 0.00046975380973890424
2023-01-24 06:20:42.041278: step: 2100/527, loss: 0.015434990637004375
2023-01-24 06:20:43.093166: step: 2104/527, loss: 0.0014861068921163678
2023-01-24 06:20:44.145906: step: 2108/527, loss: 0.005742221605032682
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34468154134932216, 'r': 0.32375211189357583, 'f1': 0.3338891643207719}, 'combined': 0.24602359476267405, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37653896967920597, 'r': 0.2916465474242577, 'f1': 0.3287000022199626}, 'combined': 0.21036800142077602, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3578307962529274, 'r': 0.33134995933857414, 'f1': 0.34408163265306124}, 'combined': 0.25353383458646617, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37579173595013615, 'r': 0.3044561566462502, 'f1': 0.3363835709659021}, 'combined': 0.21528548541817732, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.362513874436351, 'r': 0.31986518332619207, 'f1': 0.3398567572840791}, 'combined': 0.2504207685251109, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.384690449035528, 'r': 0.3103473540532746, 'f1': 0.3435429338006481}, 'combined': 0.24631380159291752, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
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
2023-01-24 06:23:12.865198: step: 4/527, loss: 0.0011762861395254731
2023-01-24 06:23:13.916876: step: 8/527, loss: 0.005770666524767876
2023-01-24 06:23:14.968937: step: 12/527, loss: 0.0058799730613827705
2023-01-24 06:23:16.005029: step: 16/527, loss: 0.011273756623268127
2023-01-24 06:23:17.063518: step: 20/527, loss: 0.0026257140561938286
2023-01-24 06:23:18.101532: step: 24/527, loss: 0.00032926027779467404
2023-01-24 06:23:19.145929: step: 28/527, loss: 0.0006809047190472484
2023-01-24 06:23:20.208321: step: 32/527, loss: 0.004259904380887747
2023-01-24 06:23:21.267864: step: 36/527, loss: 0.0050410921685397625
2023-01-24 06:23:22.304782: step: 40/527, loss: 0.018239814788103104
2023-01-24 06:23:23.351468: step: 44/527, loss: 0.004635321907699108
2023-01-24 06:23:24.401599: step: 48/527, loss: 0.023965172469615936
2023-01-24 06:23:25.442098: step: 52/527, loss: 0.0016597952926531434
2023-01-24 06:23:26.486440: step: 56/527, loss: 0.00301774637773633
2023-01-24 06:23:27.544879: step: 60/527, loss: 0.008930178359150887
2023-01-24 06:23:28.595360: step: 64/527, loss: 0.0018494927790015936
2023-01-24 06:23:29.656489: step: 68/527, loss: 0.004239272326231003
2023-01-24 06:23:30.720223: step: 72/527, loss: 0.006199757102876902
2023-01-24 06:23:31.763555: step: 76/527, loss: 0.009897388517856598
2023-01-24 06:23:32.799405: step: 80/527, loss: 0.0020823294762521982
2023-01-24 06:23:33.854488: step: 84/527, loss: 0.005397001747041941
2023-01-24 06:23:34.903523: step: 88/527, loss: 0.0019322435837239027
2023-01-24 06:23:35.948610: step: 92/527, loss: 0.00641339085996151
2023-01-24 06:23:36.989980: step: 96/527, loss: 0.002924043918028474
2023-01-24 06:23:38.060912: step: 100/527, loss: 0.0010368796065449715
2023-01-24 06:23:39.112396: step: 104/527, loss: 0.0012904191389679909
2023-01-24 06:23:40.164526: step: 108/527, loss: 0.011828163638710976
2023-01-24 06:23:41.222387: step: 112/527, loss: 0.007874327711760998
2023-01-24 06:23:42.279770: step: 116/527, loss: 0.03741808608174324
2023-01-24 06:23:43.329333: step: 120/527, loss: 0.0041434974409639835
2023-01-24 06:23:44.380167: step: 124/527, loss: 0.015231378376483917
2023-01-24 06:23:45.424833: step: 128/527, loss: 0.0068403431214392185
2023-01-24 06:23:46.467638: step: 132/527, loss: 0.01907469518482685
2023-01-24 06:23:47.542402: step: 136/527, loss: 0.0038294813130050898
2023-01-24 06:23:48.600627: step: 140/527, loss: 0.0294569730758667
2023-01-24 06:23:49.663566: step: 144/527, loss: 0.016039030626416206
2023-01-24 06:23:50.717242: step: 148/527, loss: 0.004499699920415878
2023-01-24 06:23:51.794779: step: 152/527, loss: 0.004218806512653828
2023-01-24 06:23:52.847939: step: 156/527, loss: 0.003108569886535406
2023-01-24 06:23:53.888018: step: 160/527, loss: 0.0011567205656319857
2023-01-24 06:23:54.929981: step: 164/527, loss: 0.012250793166458607
2023-01-24 06:23:55.984218: step: 168/527, loss: 0.001836702460423112
2023-01-24 06:23:57.052879: step: 172/527, loss: 0.015831436961889267
2023-01-24 06:23:58.105746: step: 176/527, loss: 0.058130908757448196
2023-01-24 06:23:59.149613: step: 180/527, loss: 0.012560397386550903
2023-01-24 06:24:00.190866: step: 184/527, loss: 0.011316278018057346
2023-01-24 06:24:01.242699: step: 188/527, loss: 0.006172460038214922
2023-01-24 06:24:02.292916: step: 192/527, loss: 0.004307650029659271
2023-01-24 06:24:03.336063: step: 196/527, loss: 0.017391672357916832
2023-01-24 06:24:04.407416: step: 200/527, loss: 0.029506081715226173
2023-01-24 06:24:05.477168: step: 204/527, loss: 0.010138626210391521
2023-01-24 06:24:06.546857: step: 208/527, loss: 0.005423405673354864
2023-01-24 06:24:07.619328: step: 212/527, loss: 0.012503663077950478
2023-01-24 06:24:08.696360: step: 216/527, loss: 0.0118255615234375
2023-01-24 06:24:09.752386: step: 220/527, loss: 0.0021275379694998264
2023-01-24 06:24:10.808272: step: 224/527, loss: 0.005360076203942299
2023-01-24 06:24:11.868330: step: 228/527, loss: 0.004129832144826651
2023-01-24 06:24:12.913986: step: 232/527, loss: 0.003537638345733285
2023-01-24 06:24:13.971320: step: 236/527, loss: 0.016127267852425575
2023-01-24 06:24:15.020553: step: 240/527, loss: 0.008914195001125336
2023-01-24 06:24:16.064706: step: 244/527, loss: 0.006991427391767502
2023-01-24 06:24:17.120582: step: 248/527, loss: 0.014179665595293045
2023-01-24 06:24:18.163535: step: 252/527, loss: 0.0028274371288716793
2023-01-24 06:24:19.236898: step: 256/527, loss: 0.02464323490858078
2023-01-24 06:24:20.296326: step: 260/527, loss: 0.004434527363628149
2023-01-24 06:24:21.340340: step: 264/527, loss: 0.004369425121694803
2023-01-24 06:24:22.370440: step: 268/527, loss: 0.001455672667361796
2023-01-24 06:24:23.413653: step: 272/527, loss: 0.0025727252941578627
2023-01-24 06:24:24.476768: step: 276/527, loss: 0.015328909270465374
2023-01-24 06:24:25.527392: step: 280/527, loss: 0.0028654129710048437
2023-01-24 06:24:26.575683: step: 284/527, loss: 0.0019427868537604809
2023-01-24 06:24:27.667067: step: 288/527, loss: 0.004314064979553223
2023-01-24 06:24:28.724456: step: 292/527, loss: 0.004622200969606638
2023-01-24 06:24:29.783189: step: 296/527, loss: 0.001130652497522533
2023-01-24 06:24:30.841145: step: 300/527, loss: 0.004627163987606764
2023-01-24 06:24:31.891816: step: 304/527, loss: 0.006596438121050596
2023-01-24 06:24:32.934489: step: 308/527, loss: 0.0031702998094260693
2023-01-24 06:24:33.978417: step: 312/527, loss: 0.05189930647611618
2023-01-24 06:24:35.039754: step: 316/527, loss: 0.014070438221096992
2023-01-24 06:24:36.098824: step: 320/527, loss: 0.033695101737976074
2023-01-24 06:24:37.165154: step: 324/527, loss: 0.0010572454193606973
2023-01-24 06:24:38.219386: step: 328/527, loss: 0.0032614138908684254
2023-01-24 06:24:39.273497: step: 332/527, loss: 0.002125186612829566
2023-01-24 06:24:40.332342: step: 336/527, loss: 0.013929967768490314
2023-01-24 06:24:41.385387: step: 340/527, loss: 0.007350783795118332
2023-01-24 06:24:42.439078: step: 344/527, loss: 0.0029599317349493504
2023-01-24 06:24:43.483956: step: 348/527, loss: 0.0033247913233935833
2023-01-24 06:24:44.526451: step: 352/527, loss: 0.022639818489551544
2023-01-24 06:24:45.581099: step: 356/527, loss: 0.03472037985920906
2023-01-24 06:24:46.621361: step: 360/527, loss: 0.009670925326645374
2023-01-24 06:24:47.682819: step: 364/527, loss: 0.007359437178820372
2023-01-24 06:24:48.721895: step: 368/527, loss: 0.0007571582100354135
2023-01-24 06:24:49.783939: step: 372/527, loss: 0.01009386032819748
2023-01-24 06:24:50.842479: step: 376/527, loss: 0.011879819445312023
2023-01-24 06:24:51.890627: step: 380/527, loss: 0.002377040684223175
2023-01-24 06:24:52.940682: step: 384/527, loss: 0.004287994932383299
2023-01-24 06:24:54.000319: step: 388/527, loss: 0.014191503636538982
2023-01-24 06:24:55.047159: step: 392/527, loss: 0.005081395152956247
2023-01-24 06:24:56.089510: step: 396/527, loss: 0.005458964500576258
2023-01-24 06:24:57.137832: step: 400/527, loss: 0.011647974140942097
2023-01-24 06:24:58.213724: step: 404/527, loss: 0.04495551809668541
2023-01-24 06:24:59.262821: step: 408/527, loss: 0.001693369005806744
2023-01-24 06:25:00.302326: step: 412/527, loss: 0.0005285778315737844
2023-01-24 06:25:01.376197: step: 416/527, loss: 0.011131852865219116
2023-01-24 06:25:02.454762: step: 420/527, loss: 0.015228178352117538
2023-01-24 06:25:03.509493: step: 424/527, loss: 0.004915312398225069
2023-01-24 06:25:04.558938: step: 428/527, loss: 0.0009033419191837311
2023-01-24 06:25:05.610852: step: 432/527, loss: 0.005241208244115114
2023-01-24 06:25:06.674764: step: 436/527, loss: 0.004751232452690601
2023-01-24 06:25:07.730816: step: 440/527, loss: 0.002280104672536254
2023-01-24 06:25:08.761756: step: 444/527, loss: 0.00037919796886853874
2023-01-24 06:25:09.829414: step: 448/527, loss: 0.008740345016121864
2023-01-24 06:25:10.878074: step: 452/527, loss: 0.005086951889097691
2023-01-24 06:25:11.935199: step: 456/527, loss: 0.001967105781659484
2023-01-24 06:25:12.958196: step: 460/527, loss: 0.018408872187137604
2023-01-24 06:25:14.009938: step: 464/527, loss: 0.016983093693852425
2023-01-24 06:25:15.073626: step: 468/527, loss: 0.004702928941696882
2023-01-24 06:25:16.108597: step: 472/527, loss: 0.0006862246082164347
2023-01-24 06:25:17.163393: step: 476/527, loss: 0.015025509521365166
2023-01-24 06:25:18.224751: step: 480/527, loss: 0.0058099376037716866
2023-01-24 06:25:19.300163: step: 484/527, loss: 3.218735218979418e-05
2023-01-24 06:25:20.349588: step: 488/527, loss: 0.017115792259573936
2023-01-24 06:25:21.398499: step: 492/527, loss: 0.021023690700531006
2023-01-24 06:25:22.457813: step: 496/527, loss: 0.0056746965274214745
2023-01-24 06:25:23.523165: step: 500/527, loss: 0.0018623566720634699
2023-01-24 06:25:24.594437: step: 504/527, loss: 0.020436029881238937
2023-01-24 06:25:25.634897: step: 508/527, loss: 0.0036087525077164173
2023-01-24 06:25:26.679051: step: 512/527, loss: 0.0015722350217401981
2023-01-24 06:25:27.714487: step: 516/527, loss: 0.0060618286952376366
2023-01-24 06:25:28.763763: step: 520/527, loss: 0.014606723561882973
2023-01-24 06:25:29.813587: step: 524/527, loss: 0.03179058060050011
2023-01-24 06:25:30.861029: step: 528/527, loss: 0.007102565374225378
2023-01-24 06:25:31.911140: step: 532/527, loss: 0.002537408145144582
2023-01-24 06:25:32.946669: step: 536/527, loss: 0.0037960298359394073
2023-01-24 06:25:34.009283: step: 540/527, loss: 0.0036290937568992376
2023-01-24 06:25:35.080725: step: 544/527, loss: 0.006896753795444965
2023-01-24 06:25:36.121705: step: 548/527, loss: 0.01382986456155777
2023-01-24 06:25:37.193360: step: 552/527, loss: 0.020476488396525383
2023-01-24 06:25:38.245464: step: 556/527, loss: 0.007108153309673071
2023-01-24 06:25:39.294733: step: 560/527, loss: 0.0004783706972375512
2023-01-24 06:25:40.340410: step: 564/527, loss: 0.002413227455690503
2023-01-24 06:25:41.392822: step: 568/527, loss: 0.005749106407165527
2023-01-24 06:25:42.454464: step: 572/527, loss: 0.0029543943237513304
2023-01-24 06:25:43.515519: step: 576/527, loss: 0.0054740700870752335
2023-01-24 06:25:44.564340: step: 580/527, loss: 0.004652662668377161
2023-01-24 06:25:45.634245: step: 584/527, loss: 0.009162668138742447
2023-01-24 06:25:46.682819: step: 588/527, loss: 0.01541721448302269
2023-01-24 06:25:47.720620: step: 592/527, loss: 0.004740078002214432
2023-01-24 06:25:48.797204: step: 596/527, loss: 0.014616711065173149
2023-01-24 06:25:49.838726: step: 600/527, loss: 0.0007777657592669129
2023-01-24 06:25:50.885418: step: 604/527, loss: 0.0008933142526075244
2023-01-24 06:25:51.945570: step: 608/527, loss: 0.015309763140976429
2023-01-24 06:25:53.020528: step: 612/527, loss: 0.020909041166305542
2023-01-24 06:25:54.060908: step: 616/527, loss: 0.00640073511749506
2023-01-24 06:25:55.120875: step: 620/527, loss: 0.005111007019877434
2023-01-24 06:25:56.166958: step: 624/527, loss: 0.019747916609048843
2023-01-24 06:25:57.221839: step: 628/527, loss: 0.008677047677338123
2023-01-24 06:25:58.260242: step: 632/527, loss: 0.001905033364892006
2023-01-24 06:25:59.328264: step: 636/527, loss: 0.011477400548756123
2023-01-24 06:26:00.382281: step: 640/527, loss: 0.013894579373300076
2023-01-24 06:26:01.446425: step: 644/527, loss: 0.001782936160452664
2023-01-24 06:26:02.488267: step: 648/527, loss: 0.008497907780110836
2023-01-24 06:26:03.536385: step: 652/527, loss: 0.005031628534197807
2023-01-24 06:26:04.590769: step: 656/527, loss: 0.00017212475358974189
2023-01-24 06:26:05.657094: step: 660/527, loss: 0.007511868141591549
2023-01-24 06:26:06.714142: step: 664/527, loss: 0.006619738414883614
2023-01-24 06:26:07.769859: step: 668/527, loss: 0.006116640754044056
2023-01-24 06:26:08.854002: step: 672/527, loss: 0.004539389628916979
2023-01-24 06:26:09.912591: step: 676/527, loss: 0.010941772721707821
2023-01-24 06:26:10.966593: step: 680/527, loss: 0.012777542695403099
2023-01-24 06:26:12.015461: step: 684/527, loss: 0.028100110590457916
2023-01-24 06:26:13.068111: step: 688/527, loss: 0.0022654919885098934
2023-01-24 06:26:14.120721: step: 692/527, loss: 0.0014765422092750669
2023-01-24 06:26:15.157350: step: 696/527, loss: 0.0004512390587478876
2023-01-24 06:26:16.213048: step: 700/527, loss: 0.026108723133802414
2023-01-24 06:26:17.273466: step: 704/527, loss: 0.0021571919787675142
2023-01-24 06:26:18.312340: step: 708/527, loss: 0.034226201474666595
2023-01-24 06:26:19.374018: step: 712/527, loss: 0.015098475851118565
2023-01-24 06:26:20.426214: step: 716/527, loss: 0.03442610800266266
2023-01-24 06:26:21.468067: step: 720/527, loss: 0.004797043744474649
2023-01-24 06:26:22.524215: step: 724/527, loss: 2.5107931378443027e-07
2023-01-24 06:26:23.556592: step: 728/527, loss: 0.0004034257435705513
2023-01-24 06:26:24.618274: step: 732/527, loss: 0.0008951377240009606
2023-01-24 06:26:25.680639: step: 736/527, loss: 0.007962681353092194
2023-01-24 06:26:26.722344: step: 740/527, loss: 0.007262140978127718
2023-01-24 06:26:27.769897: step: 744/527, loss: 0.020501291379332542
2023-01-24 06:26:28.837190: step: 748/527, loss: 0.00503790145739913
2023-01-24 06:26:29.902142: step: 752/527, loss: 0.011922625824809074
2023-01-24 06:26:30.952548: step: 756/527, loss: 0.015006141737103462
2023-01-24 06:26:32.008896: step: 760/527, loss: 0.004677725490182638
2023-01-24 06:26:33.065811: step: 764/527, loss: 0.0007494300953112543
2023-01-24 06:26:34.111452: step: 768/527, loss: 0.0038482944946736097
2023-01-24 06:26:35.158916: step: 772/527, loss: 0.0001417314779246226
2023-01-24 06:26:36.217886: step: 776/527, loss: 0.029271438717842102
2023-01-24 06:26:37.271948: step: 780/527, loss: 0.007724877446889877
2023-01-24 06:26:38.318313: step: 784/527, loss: 0.00010587528231553733
2023-01-24 06:26:39.365468: step: 788/527, loss: 0.0071006715297698975
2023-01-24 06:26:40.421336: step: 792/527, loss: 0.007228069007396698
2023-01-24 06:26:41.480720: step: 796/527, loss: 0.007850813679397106
2023-01-24 06:26:42.535057: step: 800/527, loss: 0.010215306654572487
2023-01-24 06:26:43.592058: step: 804/527, loss: 0.005301190540194511
2023-01-24 06:26:44.639318: step: 808/527, loss: 0.0041169882752001286
2023-01-24 06:26:45.687267: step: 812/527, loss: 0.006976403295993805
2023-01-24 06:26:46.746387: step: 816/527, loss: 0.0020775748416781425
2023-01-24 06:26:47.783598: step: 820/527, loss: 0.01090807281434536
2023-01-24 06:26:48.838668: step: 824/527, loss: 0.007368314079940319
2023-01-24 06:26:49.883112: step: 828/527, loss: 0.0047179278917610645
2023-01-24 06:26:50.954567: step: 832/527, loss: 0.0035620173439383507
2023-01-24 06:26:52.005206: step: 836/527, loss: 0.0265518631786108
2023-01-24 06:26:53.050489: step: 840/527, loss: 0.03120836615562439
2023-01-24 06:26:54.107486: step: 844/527, loss: 0.04151497036218643
2023-01-24 06:26:55.158110: step: 848/527, loss: 0.009576591663062572
2023-01-24 06:26:56.201723: step: 852/527, loss: 0.006244817283004522
2023-01-24 06:26:57.238978: step: 856/527, loss: 0.0016189676243811846
2023-01-24 06:26:58.311201: step: 860/527, loss: 0.026952020823955536
2023-01-24 06:26:59.356232: step: 864/527, loss: 0.0037856451235711575
2023-01-24 06:27:00.401856: step: 868/527, loss: 0.007088650017976761
2023-01-24 06:27:01.461388: step: 872/527, loss: 0.0004930454306304455
2023-01-24 06:27:02.526727: step: 876/527, loss: 0.013458835892379284
2023-01-24 06:27:03.564376: step: 880/527, loss: 0.006491994950920343
2023-01-24 06:27:04.640646: step: 884/527, loss: 0.00951909739524126
2023-01-24 06:27:05.699037: step: 888/527, loss: 0.006218143738806248
2023-01-24 06:27:06.761168: step: 892/527, loss: 0.010673061944544315
2023-01-24 06:27:07.833476: step: 896/527, loss: 0.0011394878383725882
2023-01-24 06:27:08.889245: step: 900/527, loss: 0.004675300791859627
2023-01-24 06:27:09.948286: step: 904/527, loss: 0.011332347057759762
2023-01-24 06:27:11.004327: step: 908/527, loss: 0.08071253448724747
2023-01-24 06:27:12.041745: step: 912/527, loss: 0.002875578124076128
2023-01-24 06:27:13.099263: step: 916/527, loss: 0.0056468416005373
2023-01-24 06:27:14.157844: step: 920/527, loss: 0.017186572775244713
2023-01-24 06:27:15.221761: step: 924/527, loss: 0.018323130905628204
2023-01-24 06:27:16.273946: step: 928/527, loss: 0.0195182953029871
2023-01-24 06:27:17.314720: step: 932/527, loss: 0.022910984233021736
2023-01-24 06:27:18.378144: step: 936/527, loss: 0.014719245955348015
2023-01-24 06:27:19.457862: step: 940/527, loss: 0.004016861319541931
2023-01-24 06:27:20.514883: step: 944/527, loss: 0.004240079782903194
2023-01-24 06:27:21.553802: step: 948/527, loss: 0.011007502675056458
2023-01-24 06:27:22.619305: step: 952/527, loss: 0.004683236591517925
2023-01-24 06:27:23.653686: step: 956/527, loss: 0.022693928331136703
2023-01-24 06:27:24.721440: step: 960/527, loss: 0.0053064958192408085
2023-01-24 06:27:25.770885: step: 964/527, loss: 0.012264814227819443
2023-01-24 06:27:26.824051: step: 968/527, loss: 0.006496482063084841
2023-01-24 06:27:27.893689: step: 972/527, loss: 0.007213902194052935
2023-01-24 06:27:28.940507: step: 976/527, loss: 0.003221244551241398
2023-01-24 06:27:29.983928: step: 980/527, loss: 0.018335863947868347
2023-01-24 06:27:31.040419: step: 984/527, loss: 0.0014510139590129256
2023-01-24 06:27:32.100298: step: 988/527, loss: 0.00018173780699726194
2023-01-24 06:27:33.135908: step: 992/527, loss: 0.0005547582404688001
2023-01-24 06:27:34.187176: step: 996/527, loss: 0.007558836601674557
2023-01-24 06:27:35.251772: step: 1000/527, loss: 0.005875860340893269
2023-01-24 06:27:36.301833: step: 1004/527, loss: 0.003022552467882633
2023-01-24 06:27:37.356533: step: 1008/527, loss: 0.0037222157698124647
2023-01-24 06:27:38.413492: step: 1012/527, loss: 0.007213362492620945
2023-01-24 06:27:39.448316: step: 1016/527, loss: 0.005431391764432192
2023-01-24 06:27:40.482289: step: 1020/527, loss: 0.006150540895760059
2023-01-24 06:27:41.538755: step: 1024/527, loss: 0.026522129774093628
2023-01-24 06:27:42.585584: step: 1028/527, loss: 0.010076455771923065
2023-01-24 06:27:43.637144: step: 1032/527, loss: 0.007794274017214775
2023-01-24 06:27:44.677619: step: 1036/527, loss: 0.004307042341679335
2023-01-24 06:27:45.724447: step: 1040/527, loss: 0.004661035258322954
2023-01-24 06:27:46.792787: step: 1044/527, loss: 0.009102068841457367
2023-01-24 06:27:47.862738: step: 1048/527, loss: 0.009107415564358234
2023-01-24 06:27:48.922204: step: 1052/527, loss: 0.007682840805500746
2023-01-24 06:27:49.973923: step: 1056/527, loss: 0.007839532569050789
2023-01-24 06:27:51.033111: step: 1060/527, loss: 0.00691550737246871
2023-01-24 06:27:52.092684: step: 1064/527, loss: 0.01588447019457817
2023-01-24 06:27:53.128017: step: 1068/527, loss: 0.016561010852456093
2023-01-24 06:27:54.177436: step: 1072/527, loss: 0.0023054606281220913
2023-01-24 06:27:55.236724: step: 1076/527, loss: 0.005138486158102751
2023-01-24 06:27:56.285761: step: 1080/527, loss: 0.006244129966944456
2023-01-24 06:27:57.325941: step: 1084/527, loss: 0.004642792046070099
2023-01-24 06:27:58.394834: step: 1088/527, loss: 0.010316764935851097
2023-01-24 06:27:59.446934: step: 1092/527, loss: 0.006066053174436092
2023-01-24 06:28:00.494214: step: 1096/527, loss: 0.0024034250527620316
2023-01-24 06:28:01.536040: step: 1100/527, loss: 0.004848657175898552
2023-01-24 06:28:02.590160: step: 1104/527, loss: 0.000994514673948288
2023-01-24 06:28:03.626914: step: 1108/527, loss: 0.006069227121770382
2023-01-24 06:28:04.699557: step: 1112/527, loss: 0.0020929903257638216
2023-01-24 06:28:05.741909: step: 1116/527, loss: 0.000433559063822031
2023-01-24 06:28:06.803516: step: 1120/527, loss: 0.00041445757960900664
2023-01-24 06:28:07.858792: step: 1124/527, loss: 0.026016153395175934
2023-01-24 06:28:08.896651: step: 1128/527, loss: 0.0061644334346055984
2023-01-24 06:28:09.948245: step: 1132/527, loss: 0.004554815124720335
2023-01-24 06:28:11.027096: step: 1136/527, loss: 0.0036312779411673546
2023-01-24 06:28:12.089219: step: 1140/527, loss: 0.004106924869120121
2023-01-24 06:28:13.139505: step: 1144/527, loss: 0.0017886483110487461
2023-01-24 06:28:14.192621: step: 1148/527, loss: 0.0015938644064590335
2023-01-24 06:28:15.240634: step: 1152/527, loss: 0.0014809290878474712
2023-01-24 06:28:16.286518: step: 1156/527, loss: 0.016352303326129913
2023-01-24 06:28:17.329106: step: 1160/527, loss: 0.002711722394451499
2023-01-24 06:28:18.384803: step: 1164/527, loss: 0.01169298030436039
2023-01-24 06:28:19.468490: step: 1168/527, loss: 0.0002884409623220563
2023-01-24 06:28:20.511587: step: 1172/527, loss: 0.0029927738942205906
2023-01-24 06:28:21.570811: step: 1176/527, loss: 0.011302296072244644
2023-01-24 06:28:22.618120: step: 1180/527, loss: 0.00686067808419466
2023-01-24 06:28:23.664794: step: 1184/527, loss: 0.006412389222532511
2023-01-24 06:28:24.688265: step: 1188/527, loss: 0.0036091282963752747
2023-01-24 06:28:25.740623: step: 1192/527, loss: 0.009405727498233318
2023-01-24 06:28:26.778367: step: 1196/527, loss: 0.0026019210927188396
2023-01-24 06:28:27.833772: step: 1200/527, loss: 0.003222639672458172
2023-01-24 06:28:28.915906: step: 1204/527, loss: 0.006527747493237257
2023-01-24 06:28:29.964752: step: 1208/527, loss: 0.002040441380813718
2023-01-24 06:28:31.018595: step: 1212/527, loss: 0.005301251076161861
2023-01-24 06:28:32.059369: step: 1216/527, loss: 0.016271648928523064
2023-01-24 06:28:33.110874: step: 1220/527, loss: 0.006276706699281931
2023-01-24 06:28:34.154485: step: 1224/527, loss: 0.0022712545469403267
2023-01-24 06:28:35.197905: step: 1228/527, loss: 0.002332814736291766
2023-01-24 06:28:36.259198: step: 1232/527, loss: 0.011018120683729649
2023-01-24 06:28:37.321349: step: 1236/527, loss: 0.003257921664044261
2023-01-24 06:28:38.372367: step: 1240/527, loss: 0.010572624392807484
2023-01-24 06:28:39.423289: step: 1244/527, loss: 0.004362326581031084
2023-01-24 06:28:40.470095: step: 1248/527, loss: 0.0012781393015757203
2023-01-24 06:28:41.524272: step: 1252/527, loss: 0.0020749021787196398
2023-01-24 06:28:42.575917: step: 1256/527, loss: 0.009615735150873661
2023-01-24 06:28:43.667696: step: 1260/527, loss: 0.0025882520712912083
2023-01-24 06:28:44.712387: step: 1264/527, loss: 0.010402072221040726
2023-01-24 06:28:45.760592: step: 1268/527, loss: 0.003054817672818899
2023-01-24 06:28:46.799537: step: 1272/527, loss: 0.0019948140252381563
2023-01-24 06:28:47.850939: step: 1276/527, loss: 0.005946854595094919
2023-01-24 06:28:48.903662: step: 1280/527, loss: 0.006230685394257307
2023-01-24 06:28:49.965637: step: 1284/527, loss: 0.017413675785064697
2023-01-24 06:28:51.038523: step: 1288/527, loss: 0.05065235123038292
2023-01-24 06:28:52.087413: step: 1292/527, loss: 0.009509514085948467
2023-01-24 06:28:53.137097: step: 1296/527, loss: 0.0018403837457299232
2023-01-24 06:28:54.196422: step: 1300/527, loss: 0.002236853586509824
2023-01-24 06:28:55.233053: step: 1304/527, loss: 0.002076870994642377
2023-01-24 06:28:56.284849: step: 1308/527, loss: 0.017090918496251106
2023-01-24 06:28:57.353365: step: 1312/527, loss: 2.083394065266475e-05
2023-01-24 06:28:58.384744: step: 1316/527, loss: 0.003389152232557535
2023-01-24 06:28:59.456948: step: 1320/527, loss: 0.016382068395614624
2023-01-24 06:29:00.532951: step: 1324/527, loss: 0.007264185231178999
2023-01-24 06:29:01.582763: step: 1328/527, loss: 0.0006205785903148353
2023-01-24 06:29:02.608616: step: 1332/527, loss: 0.000725000980310142
2023-01-24 06:29:03.663150: step: 1336/527, loss: 0.0017693579429760575
2023-01-24 06:29:04.716887: step: 1340/527, loss: 0.0035823797807097435
2023-01-24 06:29:05.767317: step: 1344/527, loss: 0.012691323645412922
2023-01-24 06:29:06.812620: step: 1348/527, loss: 0.0054375301115214825
2023-01-24 06:29:07.855984: step: 1352/527, loss: 0.03330446034669876
2023-01-24 06:29:08.906444: step: 1356/527, loss: 0.012865869328379631
2023-01-24 06:29:09.967319: step: 1360/527, loss: 0.012280241586267948
2023-01-24 06:29:11.025355: step: 1364/527, loss: 0.023513102903962135
2023-01-24 06:29:12.069950: step: 1368/527, loss: 0.013600676320493221
2023-01-24 06:29:13.125019: step: 1372/527, loss: 0.005515237804502249
2023-01-24 06:29:14.165919: step: 1376/527, loss: 0.006135640665888786
2023-01-24 06:29:15.218314: step: 1380/527, loss: 0.0054725236259400845
2023-01-24 06:29:16.276471: step: 1384/527, loss: 0.010193255729973316
2023-01-24 06:29:17.327761: step: 1388/527, loss: 0.00300167896784842
2023-01-24 06:29:18.386248: step: 1392/527, loss: 0.0035158854443579912
2023-01-24 06:29:19.465182: step: 1396/527, loss: 0.011393156833946705
2023-01-24 06:29:20.509647: step: 1400/527, loss: 0.007708531338721514
2023-01-24 06:29:21.555160: step: 1404/527, loss: 0.029896896332502365
2023-01-24 06:29:22.619794: step: 1408/527, loss: 0.0033632079139351845
2023-01-24 06:29:23.665859: step: 1412/527, loss: 0.0020611356012523174
2023-01-24 06:29:24.712460: step: 1416/527, loss: 0.004310361109673977
2023-01-24 06:29:25.763847: step: 1420/527, loss: 0.010673295706510544
2023-01-24 06:29:26.804359: step: 1424/527, loss: 0.006751564797013998
2023-01-24 06:29:27.865669: step: 1428/527, loss: 0.0068667116574943066
2023-01-24 06:29:28.905069: step: 1432/527, loss: 0.007486337795853615
2023-01-24 06:29:29.959509: step: 1436/527, loss: 0.006137306336313486
2023-01-24 06:29:31.019048: step: 1440/527, loss: 0.0018077391432598233
2023-01-24 06:29:32.088434: step: 1444/527, loss: 0.009121482260525227
2023-01-24 06:29:33.144513: step: 1448/527, loss: 0.0013772554229944944
2023-01-24 06:29:34.210589: step: 1452/527, loss: 0.0028811676893383265
2023-01-24 06:29:35.269972: step: 1456/527, loss: 0.007387702353298664
2023-01-24 06:29:36.313758: step: 1460/527, loss: 0.0002977935073431581
2023-01-24 06:29:37.369433: step: 1464/527, loss: 0.00801931880414486
2023-01-24 06:29:38.436679: step: 1468/527, loss: 0.007619825657457113
2023-01-24 06:29:39.499857: step: 1472/527, loss: 0.009034757502377033
2023-01-24 06:29:40.559061: step: 1476/527, loss: 0.020904745906591415
2023-01-24 06:29:41.597504: step: 1480/527, loss: 0.008191004395484924
2023-01-24 06:29:42.645224: step: 1484/527, loss: 0.003263077698647976
2023-01-24 06:29:43.709346: step: 1488/527, loss: 0.003987972624599934
2023-01-24 06:29:44.767297: step: 1492/527, loss: 0.017899535596370697
2023-01-24 06:29:45.821957: step: 1496/527, loss: 0.002941242652013898
2023-01-24 06:29:46.873505: step: 1500/527, loss: 0.003999364096671343
2023-01-24 06:29:47.947086: step: 1504/527, loss: 0.0040275040082633495
2023-01-24 06:29:49.004845: step: 1508/527, loss: 0.009376759640872478
2023-01-24 06:29:50.057254: step: 1512/527, loss: 0.0031801059376448393
2023-01-24 06:29:51.114868: step: 1516/527, loss: 0.00037648380384780467
2023-01-24 06:29:52.213260: step: 1520/527, loss: 0.005084240809082985
2023-01-24 06:29:53.264600: step: 1524/527, loss: 0.002808620920404792
2023-01-24 06:29:54.294430: step: 1528/527, loss: 0.002762235002592206
2023-01-24 06:29:55.368728: step: 1532/527, loss: 0.00031852329266257584
2023-01-24 06:29:56.413437: step: 1536/527, loss: 0.0029655955731868744
2023-01-24 06:29:57.473628: step: 1540/527, loss: 0.009475357830524445
2023-01-24 06:29:58.529849: step: 1544/527, loss: 0.004274454433470964
2023-01-24 06:29:59.583203: step: 1548/527, loss: 0.00024244235828518867
2023-01-24 06:30:00.644349: step: 1552/527, loss: 0.00658113369718194
2023-01-24 06:30:01.696599: step: 1556/527, loss: 0.0017427315469831228
2023-01-24 06:30:02.736992: step: 1560/527, loss: 0.010992297902703285
2023-01-24 06:30:03.786611: step: 1564/527, loss: 0.004258877597749233
2023-01-24 06:30:04.837039: step: 1568/527, loss: 0.00022623898985330015
2023-01-24 06:30:05.896010: step: 1572/527, loss: 0.0011873444309458137
2023-01-24 06:30:06.943483: step: 1576/527, loss: 0.0016188404988497496
2023-01-24 06:30:07.991821: step: 1580/527, loss: 0.004137265495955944
2023-01-24 06:30:09.037611: step: 1584/527, loss: 0.005658352747559547
2023-01-24 06:30:10.077385: step: 1588/527, loss: 0.0010449644178152084
2023-01-24 06:30:11.124735: step: 1592/527, loss: 0.01422981545329094
2023-01-24 06:30:12.175837: step: 1596/527, loss: 0.007538523990660906
2023-01-24 06:30:13.234816: step: 1600/527, loss: 0.007514684461057186
2023-01-24 06:30:14.306270: step: 1604/527, loss: 4.9162977120431606e-06
2023-01-24 06:30:15.373302: step: 1608/527, loss: 0.001795978401787579
2023-01-24 06:30:16.437685: step: 1612/527, loss: 0.005608080420643091
2023-01-24 06:30:17.477281: step: 1616/527, loss: 0.0015663618687540293
2023-01-24 06:30:18.525848: step: 1620/527, loss: 0.0012878417037427425
2023-01-24 06:30:19.565774: step: 1624/527, loss: 0.007327280007302761
2023-01-24 06:30:20.619100: step: 1628/527, loss: 0.0031818028073757887
2023-01-24 06:30:21.668900: step: 1632/527, loss: 0.006334662437438965
2023-01-24 06:30:22.708665: step: 1636/527, loss: 0.0005831404705531895
2023-01-24 06:30:23.758943: step: 1640/527, loss: 0.004275789484381676
2023-01-24 06:30:24.811850: step: 1644/527, loss: 0.01633210852742195
2023-01-24 06:30:25.866405: step: 1648/527, loss: 0.005840673111379147
2023-01-24 06:30:26.930885: step: 1652/527, loss: 0.006150856614112854
2023-01-24 06:30:27.969009: step: 1656/527, loss: 0.004936764948070049
2023-01-24 06:30:29.012820: step: 1660/527, loss: 0.0006148935062810779
2023-01-24 06:30:30.055759: step: 1664/527, loss: 0.0020212149247527122
2023-01-24 06:30:31.107397: step: 1668/527, loss: 0.003940522205084562
2023-01-24 06:30:32.149499: step: 1672/527, loss: 0.006931124720722437
2023-01-24 06:30:33.198621: step: 1676/527, loss: 0.0016041100025177002
2023-01-24 06:30:34.239355: step: 1680/527, loss: 0.007625493686646223
2023-01-24 06:30:35.291532: step: 1684/527, loss: 0.003768304595723748
2023-01-24 06:30:36.337445: step: 1688/527, loss: 0.008148561231791973
2023-01-24 06:30:37.386639: step: 1692/527, loss: 0.003449991811066866
2023-01-24 06:30:38.436898: step: 1696/527, loss: 0.0007971778977662325
2023-01-24 06:30:39.483720: step: 1700/527, loss: 0.028176097199320793
2023-01-24 06:30:40.516296: step: 1704/527, loss: 0.014186665415763855
2023-01-24 06:30:41.559411: step: 1708/527, loss: 0.0055346558801829815
2023-01-24 06:30:42.609111: step: 1712/527, loss: 0.005703628994524479
2023-01-24 06:30:43.667592: step: 1716/527, loss: 0.004380775149911642
2023-01-24 06:30:44.704640: step: 1720/527, loss: 0.0010369113879278302
2023-01-24 06:30:45.751224: step: 1724/527, loss: 0.000326198321999982
2023-01-24 06:30:46.796002: step: 1728/527, loss: 0.01635780744254589
2023-01-24 06:30:47.834623: step: 1732/527, loss: 0.021077606827020645
2023-01-24 06:30:48.875669: step: 1736/527, loss: 0.022376619279384613
2023-01-24 06:30:49.949584: step: 1740/527, loss: 0.001262744190171361
2023-01-24 06:30:50.999135: step: 1744/527, loss: 0.011908268555998802
2023-01-24 06:30:52.045230: step: 1748/527, loss: 0.004396419040858746
2023-01-24 06:30:53.104387: step: 1752/527, loss: 0.026702603325247765
2023-01-24 06:30:54.149952: step: 1756/527, loss: 0.0011463734554126859
2023-01-24 06:30:55.185744: step: 1760/527, loss: 0.010404621250927448
2023-01-24 06:30:56.234923: step: 1764/527, loss: 0.010583776980638504
2023-01-24 06:30:57.281207: step: 1768/527, loss: 0.0028614166658371687
2023-01-24 06:30:58.323152: step: 1772/527, loss: 0.004903014283627272
2023-01-24 06:30:59.392362: step: 1776/527, loss: 0.003185364417731762
2023-01-24 06:31:00.444448: step: 1780/527, loss: 0.008488611318171024
2023-01-24 06:31:01.488996: step: 1784/527, loss: 0.006479854229837656
2023-01-24 06:31:02.536837: step: 1788/527, loss: 0.0031652546022087336
2023-01-24 06:31:03.586856: step: 1792/527, loss: 0.003490198403596878
2023-01-24 06:31:04.637341: step: 1796/527, loss: 0.020055042579770088
2023-01-24 06:31:05.689421: step: 1800/527, loss: 0.0017858686624094844
2023-01-24 06:31:06.759154: step: 1804/527, loss: 0.0051439846865832806
2023-01-24 06:31:07.814488: step: 1808/527, loss: 0.008592815138399601
2023-01-24 06:31:08.849929: step: 1812/527, loss: 0.007867495529353619
2023-01-24 06:31:09.908038: step: 1816/527, loss: 0.0036260022316128016
2023-01-24 06:31:10.962347: step: 1820/527, loss: 0.002685365965589881
2023-01-24 06:31:12.031746: step: 1824/527, loss: 0.004280132241547108
2023-01-24 06:31:13.084021: step: 1828/527, loss: 0.005354311782866716
2023-01-24 06:31:14.113581: step: 1832/527, loss: 0.0
2023-01-24 06:31:15.165667: step: 1836/527, loss: 0.00031337421387434006
2023-01-24 06:31:16.215904: step: 1840/527, loss: 0.0018453020602464676
2023-01-24 06:31:17.292998: step: 1844/527, loss: 0.0030670773703604937
2023-01-24 06:31:18.345610: step: 1848/527, loss: 0.011090303771197796
2023-01-24 06:31:19.400212: step: 1852/527, loss: 0.00362679036334157
2023-01-24 06:31:20.437450: step: 1856/527, loss: 0.014624183066189289
2023-01-24 06:31:21.483709: step: 1860/527, loss: 0.0017266328213736415
2023-01-24 06:31:22.537305: step: 1864/527, loss: 0.02116183564066887
2023-01-24 06:31:23.604689: step: 1868/527, loss: 0.009328898973762989
2023-01-24 06:31:24.668128: step: 1872/527, loss: 0.054570522159338
2023-01-24 06:31:25.720074: step: 1876/527, loss: 0.02399817295372486
2023-01-24 06:31:26.755983: step: 1880/527, loss: 0.0032696735579520464
2023-01-24 06:31:27.807773: step: 1884/527, loss: 0.007266837637871504
2023-01-24 06:31:28.855764: step: 1888/527, loss: 0.0030580516904592514
2023-01-24 06:31:29.922496: step: 1892/527, loss: 0.00226209731772542
2023-01-24 06:31:30.982868: step: 1896/527, loss: 0.009014708921313286
2023-01-24 06:31:32.035385: step: 1900/527, loss: 0.00284867687150836
2023-01-24 06:31:33.076061: step: 1904/527, loss: 0.011430088430643082
2023-01-24 06:31:34.126077: step: 1908/527, loss: 0.008479653857648373
2023-01-24 06:31:35.159377: step: 1912/527, loss: 0.002097503514960408
2023-01-24 06:31:36.222017: step: 1916/527, loss: 0.0004132471513003111
2023-01-24 06:31:37.264607: step: 1920/527, loss: 0.00039731647120788693
2023-01-24 06:31:38.322471: step: 1924/527, loss: 0.00582444341853261
2023-01-24 06:31:39.365392: step: 1928/527, loss: 0.004440548829734325
2023-01-24 06:31:40.411866: step: 1932/527, loss: 0.013903653249144554
2023-01-24 06:31:41.473711: step: 1936/527, loss: 0.02670356258749962
2023-01-24 06:31:42.533122: step: 1940/527, loss: 0.0012797055533155799
2023-01-24 06:31:43.587128: step: 1944/527, loss: 0.005963573232293129
2023-01-24 06:31:44.638267: step: 1948/527, loss: 0.0010697349207475781
2023-01-24 06:31:45.694097: step: 1952/527, loss: 0.009538499638438225
2023-01-24 06:31:46.738128: step: 1956/527, loss: 0.009736491367220879
2023-01-24 06:31:47.786117: step: 1960/527, loss: 0.023740118369460106
2023-01-24 06:31:48.824249: step: 1964/527, loss: 0.00720672681927681
2023-01-24 06:31:49.880410: step: 1968/527, loss: 0.018328851088881493
2023-01-24 06:31:50.938175: step: 1972/527, loss: 0.015286648645997047
2023-01-24 06:31:51.997893: step: 1976/527, loss: 0.00725268991664052
2023-01-24 06:31:53.041861: step: 1980/527, loss: 0.007340042851865292
2023-01-24 06:31:54.094643: step: 1984/527, loss: 0.005392418708652258
2023-01-24 06:31:55.137840: step: 1988/527, loss: 0.003717937506735325
2023-01-24 06:31:56.185229: step: 1992/527, loss: 0.008614039048552513
2023-01-24 06:31:57.231047: step: 1996/527, loss: 0.014852678403258324
2023-01-24 06:31:58.274467: step: 2000/527, loss: 0.0013763955794274807
2023-01-24 06:31:59.315744: step: 2004/527, loss: 0.0002763493394013494
2023-01-24 06:32:00.359186: step: 2008/527, loss: 0.0011422018287703395
2023-01-24 06:32:01.389972: step: 2012/527, loss: 0.0031692483462393284
2023-01-24 06:32:02.443050: step: 2016/527, loss: 0.007393590174615383
2023-01-24 06:32:03.504558: step: 2020/527, loss: 0.006015173625200987
2023-01-24 06:32:04.549597: step: 2024/527, loss: 0.003322953823953867
2023-01-24 06:32:05.610521: step: 2028/527, loss: 0.005143163725733757
2023-01-24 06:32:06.674084: step: 2032/527, loss: 0.0035218680277466774
2023-01-24 06:32:07.721913: step: 2036/527, loss: 0.00514903012663126
2023-01-24 06:32:08.771787: step: 2040/527, loss: 0.0094820661470294
2023-01-24 06:32:09.798939: step: 2044/527, loss: 0.009241255931556225
2023-01-24 06:32:10.844661: step: 2048/527, loss: 0.0016327640041708946
2023-01-24 06:32:11.890698: step: 2052/527, loss: 0.005420347210019827
2023-01-24 06:32:12.940640: step: 2056/527, loss: 0.002747166668996215
2023-01-24 06:32:13.980420: step: 2060/527, loss: 0.02144642546772957
2023-01-24 06:32:15.022420: step: 2064/527, loss: 0.004442389588803053
2023-01-24 06:32:16.060898: step: 2068/527, loss: 0.008240175433456898
2023-01-24 06:32:17.110591: step: 2072/527, loss: 0.0016872554551810026
2023-01-24 06:32:18.137562: step: 2076/527, loss: 0.004576928913593292
2023-01-24 06:32:19.183840: step: 2080/527, loss: 0.0008002108079381287
2023-01-24 06:32:20.226799: step: 2084/527, loss: 0.0009320533135905862
2023-01-24 06:32:21.282951: step: 2088/527, loss: 0.006594611331820488
2023-01-24 06:32:22.343216: step: 2092/527, loss: 0.0017086324514821172
2023-01-24 06:32:23.381577: step: 2096/527, loss: 0.000981308170594275
2023-01-24 06:32:24.435688: step: 2100/527, loss: 0.003248268272727728
2023-01-24 06:32:25.470533: step: 2104/527, loss: 0.0008998570265248418
2023-01-24 06:32:26.518320: step: 2108/527, loss: 0.002022647997364402
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3429785543707953, 'r': 0.32280334529016025, 'f1': 0.33258526484440754}, 'combined': 0.24506282672745816, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37109682234002767, 'r': 0.28641927469698497, 'f1': 0.32330549221824884}, 'combined': 0.20691551501967922, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36365243004418263, 'r': 0.3346706424505286, 'f1': 0.34856013551665727}, 'combined': 0.2568337840649053, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3754823728145319, 'r': 0.3021592936545643, 'f1': 0.33485393287737825}, 'combined': 0.21430651704152204, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36149668439593835, 'r': 0.32033956662789986, 'f1': 0.3396759589796845}, 'combined': 0.25028754872187275, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3874161535107055, 'r': 0.3114868253385982, 'f1': 0.3453269806937264}, 'combined': 0.24759292955399254, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3660277931607365, 'r': 0.3236602497398543, 'f1': 0.34354270214079197}, 'combined': 0.2531367278932151, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827752208013896, 'r': 0.3119426138527277, 'f1': 0.34374791300496466}, 'combined': 0.24646076781488033, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 1}
******************************
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
2023-01-24 06:34:54.596017: step: 4/527, loss: 0.0002330032002646476
2023-01-24 06:34:55.667382: step: 8/527, loss: 0.02729787304997444
2023-01-24 06:34:56.716547: step: 12/527, loss: 0.007976001128554344
2023-01-24 06:34:57.746186: step: 16/527, loss: 0.0023132420610636473
2023-01-24 06:34:58.782088: step: 20/527, loss: 0.004748682025820017
2023-01-24 06:34:59.824533: step: 24/527, loss: 0.004335749428719282
2023-01-24 06:35:00.867176: step: 28/527, loss: 0.0025923559442162514
2023-01-24 06:35:01.895009: step: 32/527, loss: 0.0049667623825371265
2023-01-24 06:35:02.955882: step: 36/527, loss: 0.012910578399896622
2023-01-24 06:35:03.991749: step: 40/527, loss: 0.0002899013343267143
2023-01-24 06:35:05.045835: step: 44/527, loss: 0.01253580953925848
2023-01-24 06:35:06.125936: step: 48/527, loss: 0.024305060505867004
2023-01-24 06:35:07.163932: step: 52/527, loss: 0.002811727812513709
2023-01-24 06:35:08.207617: step: 56/527, loss: 0.00012486337800510228
2023-01-24 06:35:09.245485: step: 60/527, loss: 0.0034543753135949373
2023-01-24 06:35:10.296501: step: 64/527, loss: 0.011078727431595325
2023-01-24 06:35:11.339630: step: 68/527, loss: 0.013558818027377129
2023-01-24 06:35:12.379937: step: 72/527, loss: 0.10520170629024506
2023-01-24 06:35:13.436003: step: 76/527, loss: 0.021485585719347
2023-01-24 06:35:14.482617: step: 80/527, loss: 0.002736761001870036
2023-01-24 06:35:15.527602: step: 84/527, loss: 0.005472817458212376
2023-01-24 06:35:16.580080: step: 88/527, loss: 0.01194784976541996
2023-01-24 06:35:17.633197: step: 92/527, loss: 0.0010049795964732766
2023-01-24 06:35:18.678867: step: 96/527, loss: 0.0065386053174734116
2023-01-24 06:35:19.737374: step: 100/527, loss: 0.003975197207182646
2023-01-24 06:35:20.784511: step: 104/527, loss: 0.0062440973706543446
2023-01-24 06:35:21.820305: step: 108/527, loss: 0.0007234518998302519
2023-01-24 06:35:22.870709: step: 112/527, loss: 0.004400024190545082
2023-01-24 06:35:23.920331: step: 116/527, loss: 0.0057484060525894165
2023-01-24 06:35:24.969932: step: 120/527, loss: 0.004360474180430174
2023-01-24 06:35:26.013571: step: 124/527, loss: 0.012358917854726315
2023-01-24 06:35:27.069724: step: 128/527, loss: 0.00728977657854557
2023-01-24 06:35:28.108738: step: 132/527, loss: 0.03357089310884476
2023-01-24 06:35:29.162797: step: 136/527, loss: 0.0019295202801004052
2023-01-24 06:35:30.206791: step: 140/527, loss: 0.021667294204235077
2023-01-24 06:35:31.280086: step: 144/527, loss: 0.0050947656854987144
2023-01-24 06:35:32.338976: step: 148/527, loss: 0.006025749258697033
2023-01-24 06:35:33.388347: step: 152/527, loss: 0.020102210342884064
2023-01-24 06:35:34.448778: step: 156/527, loss: 0.014660214073956013
2023-01-24 06:35:35.494597: step: 160/527, loss: 0.011936459690332413
2023-01-24 06:35:36.552377: step: 164/527, loss: 0.005218774080276489
2023-01-24 06:35:37.597310: step: 168/527, loss: 0.001708473777398467
2023-01-24 06:35:38.649434: step: 172/527, loss: 0.0016623052069917321
2023-01-24 06:35:39.692976: step: 176/527, loss: 0.00282743270508945
2023-01-24 06:35:40.752669: step: 180/527, loss: 0.02042945846915245
2023-01-24 06:35:41.792184: step: 184/527, loss: 0.0031801247969269753
2023-01-24 06:35:42.825870: step: 188/527, loss: 0.0024131627287715673
2023-01-24 06:35:43.871367: step: 192/527, loss: 0.01198330894112587
2023-01-24 06:35:44.919907: step: 196/527, loss: 0.008296951651573181
2023-01-24 06:35:45.968949: step: 200/527, loss: 0.0021316383499652147
2023-01-24 06:35:47.005192: step: 204/527, loss: 0.001449936768040061
2023-01-24 06:35:48.060830: step: 208/527, loss: 0.008732173591852188
2023-01-24 06:35:49.115347: step: 212/527, loss: 0.0013532432494685054
2023-01-24 06:35:50.194924: step: 216/527, loss: 0.0106819411739707
2023-01-24 06:35:51.232559: step: 220/527, loss: 0.0022255731746554375
2023-01-24 06:35:52.260741: step: 224/527, loss: 0.005370576400309801
2023-01-24 06:35:53.307114: step: 228/527, loss: 0.004589673597365618
2023-01-24 06:35:54.355730: step: 232/527, loss: 0.0036165020428597927
2023-01-24 06:35:55.399826: step: 236/527, loss: 0.0008657953003421426
2023-01-24 06:35:56.444721: step: 240/527, loss: 0.0029934286139905453
2023-01-24 06:35:57.498994: step: 244/527, loss: 0.006988136097788811
2023-01-24 06:35:58.548328: step: 248/527, loss: 0.002905474277213216
2023-01-24 06:35:59.608199: step: 252/527, loss: 0.0031236233189702034
2023-01-24 06:36:00.663510: step: 256/527, loss: 0.002505676122382283
2023-01-24 06:36:01.721337: step: 260/527, loss: 0.004616268910467625
2023-01-24 06:36:02.760915: step: 264/527, loss: 0.0005057173548266292
2023-01-24 06:36:03.837320: step: 268/527, loss: 0.00617041764780879
2023-01-24 06:36:04.877537: step: 272/527, loss: 0.00039459115942008793
2023-01-24 06:36:05.918640: step: 276/527, loss: 0.0009348386665806174
2023-01-24 06:36:06.959462: step: 280/527, loss: 0.0071175373159348965
2023-01-24 06:36:08.032902: step: 284/527, loss: 0.00035052213934250176
2023-01-24 06:36:09.073620: step: 288/527, loss: 0.005999334622174501
2023-01-24 06:36:10.119515: step: 292/527, loss: 0.006068206857889891
2023-01-24 06:36:11.173970: step: 296/527, loss: 0.022090910002589226
2023-01-24 06:36:12.219108: step: 300/527, loss: 0.0031325744930654764
2023-01-24 06:36:13.277501: step: 304/527, loss: 0.0035281346645206213
2023-01-24 06:36:14.343596: step: 308/527, loss: 0.0017932542832568288
2023-01-24 06:36:15.394651: step: 312/527, loss: 0.0
2023-01-24 06:36:16.443179: step: 316/527, loss: 0.005270319525152445
2023-01-24 06:36:17.511571: step: 320/527, loss: 0.004883794113993645
2023-01-24 06:36:18.565827: step: 324/527, loss: 0.0069733248092234135
2023-01-24 06:36:19.616730: step: 328/527, loss: 0.01385743822902441
2023-01-24 06:36:20.677801: step: 332/527, loss: 0.0051896171644330025
2023-01-24 06:36:21.730480: step: 336/527, loss: 0.002243006369099021
2023-01-24 06:36:22.775741: step: 340/527, loss: 0.007538812234997749
2023-01-24 06:36:23.834371: step: 344/527, loss: 7.229208858916536e-05
2023-01-24 06:36:24.885167: step: 348/527, loss: 0.01012858934700489
2023-01-24 06:36:25.938078: step: 352/527, loss: 0.018005182966589928
2023-01-24 06:36:26.998460: step: 356/527, loss: 8.664518099976704e-05
2023-01-24 06:36:28.062340: step: 360/527, loss: 0.0052614095620810986
2023-01-24 06:36:29.101568: step: 364/527, loss: 0.012073944322764874
2023-01-24 06:36:30.150226: step: 368/527, loss: 4.259724300936796e-05
2023-01-24 06:36:31.202057: step: 372/527, loss: 0.006876377854496241
2023-01-24 06:36:32.258358: step: 376/527, loss: 0.006834926083683968
2023-01-24 06:36:33.305642: step: 380/527, loss: 0.029001053422689438
2023-01-24 06:36:34.349208: step: 384/527, loss: 0.00043874207767657936
2023-01-24 06:36:35.404242: step: 388/527, loss: 0.001796349766664207
2023-01-24 06:36:36.478931: step: 392/527, loss: 0.011168502271175385
2023-01-24 06:36:37.527361: step: 396/527, loss: 0.0008980839047580957
2023-01-24 06:36:38.577337: step: 400/527, loss: 0.002164802746847272
2023-01-24 06:36:39.620694: step: 404/527, loss: 0.0066799866035580635
2023-01-24 06:36:40.703163: step: 408/527, loss: 0.008634811267256737
2023-01-24 06:36:41.776893: step: 412/527, loss: 0.0018915216205641627
2023-01-24 06:36:42.833020: step: 416/527, loss: 0.0006427945918403566
2023-01-24 06:36:43.878449: step: 420/527, loss: 0.00903363898396492
2023-01-24 06:36:44.923959: step: 424/527, loss: 0.007423573173582554
2023-01-24 06:36:45.959589: step: 428/527, loss: 0.0012286821147426963
2023-01-24 06:36:47.015445: step: 432/527, loss: 0.0008254091953858733
2023-01-24 06:36:48.066304: step: 436/527, loss: 0.0021102188620716333
2023-01-24 06:36:49.101529: step: 440/527, loss: 0.0007236019591800869
2023-01-24 06:36:50.190331: step: 444/527, loss: 0.011712201870977879
2023-01-24 06:36:51.238017: step: 448/527, loss: 0.021262140944600105
2023-01-24 06:36:52.299229: step: 452/527, loss: 0.012126308865845203
2023-01-24 06:36:53.342645: step: 456/527, loss: 0.00015690227155573666
2023-01-24 06:36:54.385093: step: 460/527, loss: 0.008970070630311966
2023-01-24 06:36:55.442324: step: 464/527, loss: 0.0036351275630295277
2023-01-24 06:36:56.482706: step: 468/527, loss: 7.463943620678037e-05
2023-01-24 06:36:57.539806: step: 472/527, loss: 0.0003010346554219723
2023-01-24 06:36:58.574960: step: 476/527, loss: 0.002852163976058364
2023-01-24 06:36:59.621319: step: 480/527, loss: 0.006341664586216211
2023-01-24 06:37:00.680441: step: 484/527, loss: 0.016170799732208252
2023-01-24 06:37:01.752209: step: 488/527, loss: 0.002987401094287634
2023-01-24 06:37:02.800478: step: 492/527, loss: 0.0036651454865932465
2023-01-24 06:37:03.842255: step: 496/527, loss: 0.005586111918091774
2023-01-24 06:37:04.906347: step: 500/527, loss: 0.019877005368471146
2023-01-24 06:37:05.950765: step: 504/527, loss: 0.004212568514049053
2023-01-24 06:37:06.994979: step: 508/527, loss: 0.011822903528809547
2023-01-24 06:37:08.049523: step: 512/527, loss: 0.0007722167647443712
2023-01-24 06:37:09.105247: step: 516/527, loss: 0.012896863743662834
2023-01-24 06:37:10.171894: step: 520/527, loss: 0.01329719740897417
2023-01-24 06:37:11.223571: step: 524/527, loss: 0.00451135216280818
2023-01-24 06:37:12.263961: step: 528/527, loss: 0.00040527002420276403
2023-01-24 06:37:13.301134: step: 532/527, loss: 0.004665345884859562
2023-01-24 06:37:14.370278: step: 536/527, loss: 0.008312974125146866
2023-01-24 06:37:15.395875: step: 540/527, loss: 0.010481510311365128
2023-01-24 06:37:16.460807: step: 544/527, loss: 0.006175869144499302
2023-01-24 06:37:17.520980: step: 548/527, loss: 0.002698532771319151
2023-01-24 06:37:18.569712: step: 552/527, loss: 0.008815715089440346
2023-01-24 06:37:19.611304: step: 556/527, loss: 0.0076772840693593025
2023-01-24 06:37:20.670344: step: 560/527, loss: 0.00502409553155303
2023-01-24 06:37:21.733438: step: 564/527, loss: 0.007560611702501774
2023-01-24 06:37:22.773123: step: 568/527, loss: 0.02690347097814083
2023-01-24 06:37:23.810587: step: 572/527, loss: 0.007281936705112457
2023-01-24 06:37:24.864106: step: 576/527, loss: 0.007622469682246447
2023-01-24 06:37:25.919236: step: 580/527, loss: 0.003367589320987463
2023-01-24 06:37:26.983855: step: 584/527, loss: 0.0024943158496171236
2023-01-24 06:37:28.026796: step: 588/527, loss: 0.00034372886875644326
2023-01-24 06:37:29.078909: step: 592/527, loss: 0.0071462118066847324
2023-01-24 06:37:30.128363: step: 596/527, loss: 0.0013170083984732628
2023-01-24 06:37:31.172405: step: 600/527, loss: 0.009740952402353287
2023-01-24 06:37:32.225905: step: 604/527, loss: 0.0035525483544915915
2023-01-24 06:37:33.284428: step: 608/527, loss: 0.030997183173894882
2023-01-24 06:37:34.322103: step: 612/527, loss: 1.1262402040301822e-05
2023-01-24 06:37:35.396517: step: 616/527, loss: 0.015109583735466003
2023-01-24 06:37:36.453489: step: 620/527, loss: 0.030643979087471962
2023-01-24 06:37:37.514738: step: 624/527, loss: 0.005113973747938871
2023-01-24 06:37:38.557988: step: 628/527, loss: 3.4255677746841684e-05
2023-01-24 06:37:39.607739: step: 632/527, loss: 0.02006569318473339
2023-01-24 06:37:40.649855: step: 636/527, loss: 0.0061117433942854404
2023-01-24 06:37:41.691049: step: 640/527, loss: 0.02205202728509903
2023-01-24 06:37:42.723194: step: 644/527, loss: 0.010564395226538181
2023-01-24 06:37:43.764297: step: 648/527, loss: 0.0041475845500826836
2023-01-24 06:37:44.835910: step: 652/527, loss: 0.00854248832911253
2023-01-24 06:37:45.890119: step: 656/527, loss: 0.004570312332361937
2023-01-24 06:37:46.942900: step: 660/527, loss: 0.021101294085383415
2023-01-24 06:37:47.985924: step: 664/527, loss: 0.004836041480302811
2023-01-24 06:37:49.040455: step: 668/527, loss: 0.0071386490017175674
2023-01-24 06:37:50.095278: step: 672/527, loss: 0.008905834518373013
2023-01-24 06:37:51.137871: step: 676/527, loss: 0.0029244543984532356
2023-01-24 06:37:52.177250: step: 680/527, loss: 0.05654022842645645
2023-01-24 06:37:53.225459: step: 684/527, loss: 0.003175996942445636
2023-01-24 06:37:54.281128: step: 688/527, loss: 0.010086827911436558
2023-01-24 06:37:55.336493: step: 692/527, loss: 0.007584595121443272
2023-01-24 06:37:56.378468: step: 696/527, loss: 0.001266351668164134
2023-01-24 06:37:57.428385: step: 700/527, loss: 0.00592766422778368
2023-01-24 06:37:58.466358: step: 704/527, loss: 0.0015044219326227903
2023-01-24 06:37:59.521464: step: 708/527, loss: 0.0006652773590758443
2023-01-24 06:38:00.568458: step: 712/527, loss: 0.0027493576053529978
2023-01-24 06:38:01.612951: step: 716/527, loss: 0.003988585900515318
2023-01-24 06:38:02.677951: step: 720/527, loss: 0.0007629691390320659
2023-01-24 06:38:03.740186: step: 724/527, loss: 0.002542082918807864
2023-01-24 06:38:04.789887: step: 728/527, loss: 0.0038389023393392563
2023-01-24 06:38:05.819331: step: 732/527, loss: 0.0005127739277668297
2023-01-24 06:38:06.888365: step: 736/527, loss: 0.00039715145248919725
2023-01-24 06:38:07.956041: step: 740/527, loss: 0.004576391074806452
2023-01-24 06:38:08.999430: step: 744/527, loss: 3.2848427508724853e-05
2023-01-24 06:38:10.041011: step: 748/527, loss: 0.0052435859106481075
2023-01-24 06:38:11.088283: step: 752/527, loss: 0.005188755225390196
2023-01-24 06:38:12.138979: step: 756/527, loss: 0.02018502727150917
2023-01-24 06:38:13.193534: step: 760/527, loss: 0.008143670856952667
2023-01-24 06:38:14.246096: step: 764/527, loss: 0.010538049042224884
2023-01-24 06:38:15.299586: step: 768/527, loss: 0.03353271260857582
2023-01-24 06:38:16.353248: step: 772/527, loss: 0.0014808360720053315
2023-01-24 06:38:17.408508: step: 776/527, loss: 0.012612264603376389
2023-01-24 06:38:18.461285: step: 780/527, loss: 0.017173869535326958
2023-01-24 06:38:19.522800: step: 784/527, loss: 0.003489251248538494
2023-01-24 06:38:20.554192: step: 788/527, loss: 0.0020209914073348045
2023-01-24 06:38:21.609551: step: 792/527, loss: 0.0037294598296284676
2023-01-24 06:38:22.661756: step: 796/527, loss: 0.004305354785174131
2023-01-24 06:38:23.719938: step: 800/527, loss: 0.00795734953135252
2023-01-24 06:38:24.775733: step: 804/527, loss: 0.002077963203191757
2023-01-24 06:38:25.849619: step: 808/527, loss: 0.0212895218282938
2023-01-24 06:38:26.907590: step: 812/527, loss: 0.006212583743035793
2023-01-24 06:38:27.970894: step: 816/527, loss: 0.05978365242481232
2023-01-24 06:38:29.025240: step: 820/527, loss: 0.0009756953804753721
2023-01-24 06:38:30.087175: step: 824/527, loss: 0.010629642754793167
2023-01-24 06:38:31.143131: step: 828/527, loss: 0.0069140540435910225
2023-01-24 06:38:32.189403: step: 832/527, loss: 0.003601226955652237
2023-01-24 06:38:33.266855: step: 836/527, loss: 0.0057035028003156185
2023-01-24 06:38:34.322827: step: 840/527, loss: 0.003114989958703518
2023-01-24 06:38:35.375280: step: 844/527, loss: 0.00820672232657671
2023-01-24 06:38:36.445871: step: 848/527, loss: 0.0012793459463864565
2023-01-24 06:38:37.514911: step: 852/527, loss: 0.004029910080134869
2023-01-24 06:38:38.587183: step: 856/527, loss: 0.0008026692667044699
2023-01-24 06:38:39.647590: step: 860/527, loss: 0.004268052522093058
2023-01-24 06:38:40.703346: step: 864/527, loss: 0.0040172613225877285
2023-01-24 06:38:41.758433: step: 868/527, loss: 0.007618907373398542
2023-01-24 06:38:42.817499: step: 872/527, loss: 0.005499640479683876
2023-01-24 06:38:43.881060: step: 876/527, loss: 0.0024879355914890766
2023-01-24 06:38:44.921025: step: 880/527, loss: 0.006155849434435368
2023-01-24 06:38:45.982382: step: 884/527, loss: 0.001059104222804308
2023-01-24 06:38:47.038244: step: 888/527, loss: 0.0014829837018623948
2023-01-24 06:38:48.081038: step: 892/527, loss: 0.049139536917209625
2023-01-24 06:38:49.133160: step: 896/527, loss: 0.001243019476532936
2023-01-24 06:38:50.210842: step: 900/527, loss: 0.007693006657063961
2023-01-24 06:38:51.250856: step: 904/527, loss: 0.0015366185689345002
2023-01-24 06:38:52.311887: step: 908/527, loss: 0.006956764031201601
2023-01-24 06:38:53.360854: step: 912/527, loss: 0.006277000997215509
2023-01-24 06:38:54.394491: step: 916/527, loss: 0.00041099803638644516
2023-01-24 06:38:55.440428: step: 920/527, loss: 0.006701781414449215
2023-01-24 06:38:56.493775: step: 924/527, loss: 0.0040606423281133175
2023-01-24 06:38:57.535120: step: 928/527, loss: 0.006661850959062576
2023-01-24 06:38:58.572570: step: 932/527, loss: 0.0011129322228953242
2023-01-24 06:38:59.620935: step: 936/527, loss: 0.006584456190466881
2023-01-24 06:39:00.658716: step: 940/527, loss: 0.003968577831983566
2023-01-24 06:39:01.714271: step: 944/527, loss: 0.0001048057310981676
2023-01-24 06:39:02.751467: step: 948/527, loss: 0.0034072063863277435
2023-01-24 06:39:03.827738: step: 952/527, loss: 0.018250852823257446
2023-01-24 06:39:04.875423: step: 956/527, loss: 0.0015229685232043266
2023-01-24 06:39:05.922774: step: 960/527, loss: 0.002207589102908969
2023-01-24 06:39:06.976729: step: 964/527, loss: 0.0075803580693900585
2023-01-24 06:39:08.038249: step: 968/527, loss: 0.005760957952588797
2023-01-24 06:39:09.085861: step: 972/527, loss: 3.1093827601580415e-06
2023-01-24 06:39:10.148012: step: 976/527, loss: 0.0047851852141320705
2023-01-24 06:39:11.207501: step: 980/527, loss: 0.041994061321020126
2023-01-24 06:39:12.261438: step: 984/527, loss: 0.002797425724565983
2023-01-24 06:39:13.308064: step: 988/527, loss: 0.0030285988468676805
2023-01-24 06:39:14.349589: step: 992/527, loss: 0.0021650884300470352
2023-01-24 06:39:15.398482: step: 996/527, loss: 0.005847195629030466
2023-01-24 06:39:16.449817: step: 1000/527, loss: 0.0027541974559426308
2023-01-24 06:39:17.505048: step: 1004/527, loss: 0.005877191666513681
2023-01-24 06:39:18.551467: step: 1008/527, loss: 0.018481340259313583
2023-01-24 06:39:19.592395: step: 1012/527, loss: 0.004654380958527327
2023-01-24 06:39:20.640415: step: 1016/527, loss: 0.004897973965853453
2023-01-24 06:39:21.683890: step: 1020/527, loss: 0.01480427011847496
2023-01-24 06:39:22.726388: step: 1024/527, loss: 0.0007993084145709872
2023-01-24 06:39:23.775941: step: 1028/527, loss: 0.001427156268619001
2023-01-24 06:39:24.835997: step: 1032/527, loss: 0.0023678552825003862
2023-01-24 06:39:25.907103: step: 1036/527, loss: 0.004320325795561075
2023-01-24 06:39:26.960182: step: 1040/527, loss: 0.008059259504079819
2023-01-24 06:39:28.013587: step: 1044/527, loss: 0.014456305652856827
2023-01-24 06:39:29.068655: step: 1048/527, loss: 0.012549159117043018
2023-01-24 06:39:30.128994: step: 1052/527, loss: 0.005220066290348768
2023-01-24 06:39:31.165366: step: 1056/527, loss: 0.02834226004779339
2023-01-24 06:39:32.221857: step: 1060/527, loss: 0.0029862169176340103
2023-01-24 06:39:33.271184: step: 1064/527, loss: 0.0010300502181053162
2023-01-24 06:39:34.312896: step: 1068/527, loss: 0.010499897412955761
2023-01-24 06:39:35.356342: step: 1072/527, loss: 0.000737980124540627
2023-01-24 06:39:36.404226: step: 1076/527, loss: 0.004008077550679445
2023-01-24 06:39:37.449538: step: 1080/527, loss: 0.002080274512991309
2023-01-24 06:39:38.501743: step: 1084/527, loss: 0.01271986123174429
2023-01-24 06:39:39.549654: step: 1088/527, loss: 0.0023002137895673513
2023-01-24 06:39:40.606037: step: 1092/527, loss: 0.0036973075475543737
2023-01-24 06:39:41.648388: step: 1096/527, loss: 0.00861350167542696
2023-01-24 06:39:42.698047: step: 1100/527, loss: 0.007053459994494915
2023-01-24 06:39:43.734673: step: 1104/527, loss: 0.002832916099578142
2023-01-24 06:39:44.797962: step: 1108/527, loss: 0.013927474617958069
2023-01-24 06:39:45.842941: step: 1112/527, loss: 0.014119810424745083
2023-01-24 06:39:46.879108: step: 1116/527, loss: 0.0002748257538769394
2023-01-24 06:39:47.923035: step: 1120/527, loss: 0.00318628060631454
2023-01-24 06:39:48.968477: step: 1124/527, loss: 0.005412677302956581
2023-01-24 06:39:50.052631: step: 1128/527, loss: 0.005162232555449009
2023-01-24 06:39:51.102163: step: 1132/527, loss: 0.02338983491063118
2023-01-24 06:39:52.170566: step: 1136/527, loss: 0.03006056323647499
2023-01-24 06:39:53.232518: step: 1140/527, loss: 0.03350941464304924
2023-01-24 06:39:54.281999: step: 1144/527, loss: 0.0013721227878704667
2023-01-24 06:39:55.349126: step: 1148/527, loss: 0.01300261914730072
2023-01-24 06:39:56.397068: step: 1152/527, loss: 0.007490198593586683
2023-01-24 06:39:57.471746: step: 1156/527, loss: 0.004557053092867136
2023-01-24 06:39:58.525430: step: 1160/527, loss: 0.002955510513857007
2023-01-24 06:39:59.583676: step: 1164/527, loss: 0.0034884281922131777
2023-01-24 06:40:00.638539: step: 1168/527, loss: 0.012828486040234566
2023-01-24 06:40:01.676064: step: 1172/527, loss: 0.004694011993706226
2023-01-24 06:40:02.721338: step: 1176/527, loss: 0.005613983608782291
2023-01-24 06:40:03.769006: step: 1180/527, loss: 0.001298802555538714
2023-01-24 06:40:04.816822: step: 1184/527, loss: 0.005122896749526262
2023-01-24 06:40:05.877997: step: 1188/527, loss: 0.0038382215425372124
2023-01-24 06:40:06.915241: step: 1192/527, loss: 0.006829976104199886
2023-01-24 06:40:07.961439: step: 1196/527, loss: 0.007122765760868788
2023-01-24 06:40:09.008388: step: 1200/527, loss: 0.013456560671329498
2023-01-24 06:40:10.062103: step: 1204/527, loss: 0.0008182553574442863
2023-01-24 06:40:11.110691: step: 1208/527, loss: 0.004961424972862005
2023-01-24 06:40:12.159228: step: 1212/527, loss: 0.006390864495187998
2023-01-24 06:40:13.206854: step: 1216/527, loss: 0.0012007488403469324
2023-01-24 06:40:14.256879: step: 1220/527, loss: 0.004697028547525406
2023-01-24 06:40:15.299954: step: 1224/527, loss: 0.005180972628295422
2023-01-24 06:40:16.362210: step: 1228/527, loss: 0.00177439721301198
2023-01-24 06:40:17.415386: step: 1232/527, loss: 0.00016822277393657714
2023-01-24 06:40:18.474645: step: 1236/527, loss: 0.00426302757114172
2023-01-24 06:40:19.545231: step: 1240/527, loss: 0.0056867473758757114
2023-01-24 06:40:20.588025: step: 1244/527, loss: 0.007592365611344576
2023-01-24 06:40:21.632074: step: 1248/527, loss: 0.02699047513306141
2023-01-24 06:40:22.660167: step: 1252/527, loss: 0.0001514601317467168
2023-01-24 06:40:23.701672: step: 1256/527, loss: 0.005626342259347439
2023-01-24 06:40:24.745986: step: 1260/527, loss: 0.007088867481797934
2023-01-24 06:40:25.794739: step: 1264/527, loss: 0.10504268109798431
2023-01-24 06:40:26.839659: step: 1268/527, loss: 0.011039432138204575
2023-01-24 06:40:27.890042: step: 1272/527, loss: 0.0011690608225762844
2023-01-24 06:40:28.962836: step: 1276/527, loss: 0.005887324456125498
2023-01-24 06:40:29.997958: step: 1280/527, loss: 0.013546577654778957
2023-01-24 06:40:31.042304: step: 1284/527, loss: 0.0008591560181230307
2023-01-24 06:40:32.105888: step: 1288/527, loss: 0.008857784792780876
2023-01-24 06:40:33.158996: step: 1292/527, loss: 0.0036294113378971815
2023-01-24 06:40:34.212462: step: 1296/527, loss: 0.007951263338327408
2023-01-24 06:40:35.256948: step: 1300/527, loss: 0.004809096455574036
2023-01-24 06:40:36.300348: step: 1304/527, loss: 0.0024872305803000927
2023-01-24 06:40:37.348770: step: 1308/527, loss: 0.012335199862718582
2023-01-24 06:40:38.425480: step: 1312/527, loss: 0.0016196668148040771
2023-01-24 06:40:39.486307: step: 1316/527, loss: 0.016291413456201553
2023-01-24 06:40:40.536227: step: 1320/527, loss: 0.0013489486882463098
2023-01-24 06:40:41.588856: step: 1324/527, loss: 0.020952150225639343
2023-01-24 06:40:42.646834: step: 1328/527, loss: 0.004605205729603767
2023-01-24 06:40:43.700888: step: 1332/527, loss: 0.008913586847484112
2023-01-24 06:40:44.746952: step: 1336/527, loss: 0.007838152348995209
2023-01-24 06:40:45.802544: step: 1340/527, loss: 0.027775771915912628
2023-01-24 06:40:46.865803: step: 1344/527, loss: 0.003997542429715395
2023-01-24 06:40:47.901744: step: 1348/527, loss: 0.007928516715765
2023-01-24 06:40:48.954059: step: 1352/527, loss: 0.0024348124861717224
2023-01-24 06:40:50.031657: step: 1356/527, loss: 0.008911040611565113
2023-01-24 06:40:51.080655: step: 1360/527, loss: 0.004522170405834913
2023-01-24 06:40:52.135946: step: 1364/527, loss: 0.016758102923631668
2023-01-24 06:40:53.179003: step: 1368/527, loss: 0.02025187388062477
2023-01-24 06:40:54.218298: step: 1372/527, loss: 0.004952143877744675
2023-01-24 06:40:55.273788: step: 1376/527, loss: 0.0029432408045977354
2023-01-24 06:40:56.327495: step: 1380/527, loss: 0.017527470365166664
2023-01-24 06:40:57.378552: step: 1384/527, loss: 0.002615528181195259
2023-01-24 06:40:58.431355: step: 1388/527, loss: 0.004539438523352146
2023-01-24 06:40:59.481827: step: 1392/527, loss: 0.0361332893371582
2023-01-24 06:41:00.542563: step: 1396/527, loss: 0.004856666550040245
2023-01-24 06:41:01.603846: step: 1400/527, loss: 0.06768810003995895
2023-01-24 06:41:02.663845: step: 1404/527, loss: 0.0186097864061594
2023-01-24 06:41:03.732426: step: 1408/527, loss: 0.012118324637413025
2023-01-24 06:41:04.783869: step: 1412/527, loss: 0.00044537955545820296
2023-01-24 06:41:05.841941: step: 1416/527, loss: 0.00634266110137105
2023-01-24 06:41:06.899220: step: 1420/527, loss: 0.004623272456228733
2023-01-24 06:41:07.926915: step: 1424/527, loss: 0.0037482138723134995
2023-01-24 06:41:08.975725: step: 1428/527, loss: 0.012909426353871822
2023-01-24 06:41:10.031233: step: 1432/527, loss: 0.012598827481269836
2023-01-24 06:41:11.086837: step: 1436/527, loss: 0.0020017647184431553
2023-01-24 06:41:12.134969: step: 1440/527, loss: 0.006603737827390432
2023-01-24 06:41:13.187419: step: 1444/527, loss: 0.016444412991404533
2023-01-24 06:41:14.259565: step: 1448/527, loss: 0.009363116696476936
2023-01-24 06:41:15.300080: step: 1452/527, loss: 0.001328960177488625
2023-01-24 06:41:16.347750: step: 1456/527, loss: 0.02919343113899231
2023-01-24 06:41:17.407198: step: 1460/527, loss: 0.010756390169262886
2023-01-24 06:41:18.473002: step: 1464/527, loss: 0.004611361771821976
2023-01-24 06:41:19.554886: step: 1468/527, loss: 0.006537396926432848
2023-01-24 06:41:20.622388: step: 1472/527, loss: 0.023674989119172096
2023-01-24 06:41:21.659246: step: 1476/527, loss: 0.001452240627259016
2023-01-24 06:41:22.720774: step: 1480/527, loss: 0.0025078426115214825
2023-01-24 06:41:23.768482: step: 1484/527, loss: 0.0019193928455933928
2023-01-24 06:41:24.822700: step: 1488/527, loss: 0.007772236131131649
2023-01-24 06:41:25.875794: step: 1492/527, loss: 0.005323073826730251
2023-01-24 06:41:26.946341: step: 1496/527, loss: 0.010731426998972893
2023-01-24 06:41:27.999147: step: 1500/527, loss: 0.0007174506899900734
2023-01-24 06:41:29.046455: step: 1504/527, loss: 0.0017662025056779385
2023-01-24 06:41:30.105770: step: 1508/527, loss: 0.0021301519591361284
2023-01-24 06:41:31.156736: step: 1512/527, loss: 0.019619354978203773
2023-01-24 06:41:32.212033: step: 1516/527, loss: 0.014806658960878849
2023-01-24 06:41:33.258700: step: 1520/527, loss: 0.0057207257486879826
2023-01-24 06:41:34.313531: step: 1524/527, loss: 0.004767339210957289
2023-01-24 06:41:35.364803: step: 1528/527, loss: 0.007127249613404274
2023-01-24 06:41:36.392940: step: 1532/527, loss: 0.00903788860887289
2023-01-24 06:41:37.445832: step: 1536/527, loss: 0.0018995794234797359
2023-01-24 06:41:38.496021: step: 1540/527, loss: 0.009936696849763393
2023-01-24 06:41:39.554567: step: 1544/527, loss: 0.002004675567150116
2023-01-24 06:41:40.614957: step: 1548/527, loss: 0.01250398624688387
2023-01-24 06:41:41.651265: step: 1552/527, loss: 0.014228587038815022
2023-01-24 06:41:42.717309: step: 1556/527, loss: 0.0029483947437256575
2023-01-24 06:41:43.761031: step: 1560/527, loss: 0.00852295383810997
2023-01-24 06:41:44.800947: step: 1564/527, loss: 0.006583585869520903
2023-01-24 06:41:45.855094: step: 1568/527, loss: 0.007297124247997999
2023-01-24 06:41:46.896259: step: 1572/527, loss: 0.0007486153044737875
2023-01-24 06:41:47.954256: step: 1576/527, loss: 0.0025018302258104086
2023-01-24 06:41:49.029696: step: 1580/527, loss: 0.002946759108453989
2023-01-24 06:41:50.087651: step: 1584/527, loss: 0.006021034903824329
2023-01-24 06:41:51.142430: step: 1588/527, loss: 0.001694349106401205
2023-01-24 06:41:52.195190: step: 1592/527, loss: 0.008421924896538258
2023-01-24 06:41:53.245447: step: 1596/527, loss: 0.003631877712905407
2023-01-24 06:41:54.308319: step: 1600/527, loss: 0.005108369514346123
2023-01-24 06:41:55.349510: step: 1604/527, loss: 0.003427752060815692
2023-01-24 06:41:56.407796: step: 1608/527, loss: 0.00750616192817688
2023-01-24 06:41:57.446032: step: 1612/527, loss: 0.017545530572533607
2023-01-24 06:41:58.487451: step: 1616/527, loss: 0.004852135665714741
2023-01-24 06:41:59.535468: step: 1620/527, loss: 0.011480141431093216
2023-01-24 06:42:00.587967: step: 1624/527, loss: 0.00036228299723006785
2023-01-24 06:42:01.623173: step: 1628/527, loss: 0.0027326145209372044
2023-01-24 06:42:02.672839: step: 1632/527, loss: 0.006708966102451086
2023-01-24 06:42:03.726938: step: 1636/527, loss: 0.004288940690457821
2023-01-24 06:42:04.793482: step: 1640/527, loss: 0.004090540111064911
2023-01-24 06:42:05.849440: step: 1644/527, loss: 0.01779811829328537
2023-01-24 06:42:06.920411: step: 1648/527, loss: 0.0066120317205786705
2023-01-24 06:42:07.975140: step: 1652/527, loss: 0.05339784547686577
2023-01-24 06:42:09.019988: step: 1656/527, loss: 0.012658665888011456
2023-01-24 06:42:10.062292: step: 1660/527, loss: 0.003409152152016759
2023-01-24 06:42:11.115734: step: 1664/527, loss: 0.004463388584554195
2023-01-24 06:42:12.155369: step: 1668/527, loss: 0.007682070601731539
2023-01-24 06:42:13.199291: step: 1672/527, loss: 0.0011302304919809103
2023-01-24 06:42:14.233097: step: 1676/527, loss: 0.0012633507139980793
2023-01-24 06:42:15.294201: step: 1680/527, loss: 0.0004005008959211409
2023-01-24 06:42:16.349760: step: 1684/527, loss: 0.004677613731473684
2023-01-24 06:42:17.405815: step: 1688/527, loss: 0.008651215583086014
2023-01-24 06:42:18.457695: step: 1692/527, loss: 0.005553642753511667
2023-01-24 06:42:19.518707: step: 1696/527, loss: 0.007715283893048763
2023-01-24 06:42:20.570120: step: 1700/527, loss: 0.003041085321456194
2023-01-24 06:42:21.621068: step: 1704/527, loss: 0.009844905696809292
2023-01-24 06:42:22.681662: step: 1708/527, loss: 0.003409659257158637
2023-01-24 06:42:23.709399: step: 1712/527, loss: 0.0015394684160128236
2023-01-24 06:42:24.777040: step: 1716/527, loss: 0.0003158093895763159
2023-01-24 06:42:25.831458: step: 1720/527, loss: 0.009782586246728897
2023-01-24 06:42:26.871477: step: 1724/527, loss: 0.0077540758065879345
2023-01-24 06:42:27.915488: step: 1728/527, loss: 0.010061799548566341
2023-01-24 06:42:28.971580: step: 1732/527, loss: 0.0055779218673706055
2023-01-24 06:42:30.011371: step: 1736/527, loss: 0.003011499298736453
2023-01-24 06:42:31.072363: step: 1740/527, loss: 0.004066950641572475
2023-01-24 06:42:32.120718: step: 1744/527, loss: 0.005180165637284517
2023-01-24 06:42:33.173114: step: 1748/527, loss: 0.019502606242895126
2023-01-24 06:42:34.211379: step: 1752/527, loss: 0.006202231626957655
2023-01-24 06:42:35.264986: step: 1756/527, loss: 0.0028805765323340893
2023-01-24 06:42:36.314902: step: 1760/527, loss: 0.006118957884609699
2023-01-24 06:42:37.363061: step: 1764/527, loss: 0.008253831416368484
2023-01-24 06:42:38.404616: step: 1768/527, loss: 0.007253426592797041
2023-01-24 06:42:39.461932: step: 1772/527, loss: 0.010060278698801994
2023-01-24 06:42:40.526707: step: 1776/527, loss: 0.014416994526982307
2023-01-24 06:42:41.563308: step: 1780/527, loss: 0.003989460878074169
2023-01-24 06:42:42.610479: step: 1784/527, loss: 0.0040052211843431
2023-01-24 06:42:43.652476: step: 1788/527, loss: 0.006135378964245319
2023-01-24 06:42:44.716417: step: 1792/527, loss: 0.007094192318618298
2023-01-24 06:42:45.758706: step: 1796/527, loss: 0.009925086051225662
2023-01-24 06:42:46.801197: step: 1800/527, loss: 0.00942633580416441
2023-01-24 06:42:47.850133: step: 1804/527, loss: 0.002414081012830138
2023-01-24 06:42:48.907191: step: 1808/527, loss: 0.0015909569337964058
2023-01-24 06:42:49.970561: step: 1812/527, loss: 0.006630251184105873
2023-01-24 06:42:51.010068: step: 1816/527, loss: 0.012628388591110706
2023-01-24 06:42:52.060059: step: 1820/527, loss: 0.0032436393667012453
2023-01-24 06:42:53.098394: step: 1824/527, loss: 0.006815536879003048
2023-01-24 06:42:54.158770: step: 1828/527, loss: 0.005601773504167795
2023-01-24 06:42:55.205884: step: 1832/527, loss: 0.0029775493312627077
2023-01-24 06:42:56.279020: step: 1836/527, loss: 0.0008988206391222775
2023-01-24 06:42:57.319421: step: 1840/527, loss: 0.005202633794397116
2023-01-24 06:42:58.365332: step: 1844/527, loss: 0.004864899441599846
2023-01-24 06:42:59.416438: step: 1848/527, loss: 0.015622783452272415
2023-01-24 06:43:00.463598: step: 1852/527, loss: 0.007590119261294603
2023-01-24 06:43:01.511737: step: 1856/527, loss: 0.0016814471455290914
2023-01-24 06:43:02.561879: step: 1860/527, loss: 0.01379324309527874
2023-01-24 06:43:03.610691: step: 1864/527, loss: 0.0002621396561153233
2023-01-24 06:43:04.663613: step: 1868/527, loss: 0.03247030824422836
2023-01-24 06:43:05.727370: step: 1872/527, loss: 0.0045582083985209465
2023-01-24 06:43:06.786649: step: 1876/527, loss: 0.013034965842962265
2023-01-24 06:43:07.848873: step: 1880/527, loss: 0.004103172104805708
2023-01-24 06:43:08.888988: step: 1884/527, loss: 0.002278828527778387
2023-01-24 06:43:09.949042: step: 1888/527, loss: 0.0071377526037395
2023-01-24 06:43:10.994405: step: 1892/527, loss: 0.00052174850134179
2023-01-24 06:43:12.058203: step: 1896/527, loss: 0.017427073791623116
2023-01-24 06:43:13.105312: step: 1900/527, loss: 0.002051716670393944
2023-01-24 06:43:14.155973: step: 1904/527, loss: 0.03487671539187431
2023-01-24 06:43:15.203995: step: 1908/527, loss: 0.0019895327277481556
2023-01-24 06:43:16.262834: step: 1912/527, loss: 0.0014655434060841799
2023-01-24 06:43:17.318072: step: 1916/527, loss: 0.005020969547331333
2023-01-24 06:43:18.357617: step: 1920/527, loss: 0.007100861053913832
2023-01-24 06:43:19.436443: step: 1924/527, loss: 0.00624576210975647
2023-01-24 06:43:20.495875: step: 1928/527, loss: 0.0026606405153870583
2023-01-24 06:43:21.544273: step: 1932/527, loss: 0.0025374190881848335
2023-01-24 06:43:22.578957: step: 1936/527, loss: 0.013194175437092781
2023-01-24 06:43:23.622852: step: 1940/527, loss: 0.043300073593854904
2023-01-24 06:43:24.665225: step: 1944/527, loss: 0.003854151349514723
2023-01-24 06:43:25.719619: step: 1948/527, loss: 0.006117967888712883
2023-01-24 06:43:26.753382: step: 1952/527, loss: 0.0012772480258718133
2023-01-24 06:43:27.800438: step: 1956/527, loss: 0.006637756712734699
2023-01-24 06:43:28.845451: step: 1960/527, loss: 0.013307631947100163
2023-01-24 06:43:29.908802: step: 1964/527, loss: 0.007159658707678318
2023-01-24 06:43:30.964737: step: 1968/527, loss: 0.0021677978802472353
2023-01-24 06:43:32.024731: step: 1972/527, loss: 0.0038607243914157152
2023-01-24 06:43:33.063001: step: 1976/527, loss: 0.004574859514832497
2023-01-24 06:43:34.115182: step: 1980/527, loss: 0.008794196881353855
2023-01-24 06:43:35.147611: step: 1984/527, loss: 6.689530709991232e-05
2023-01-24 06:43:36.195381: step: 1988/527, loss: 0.0054607815109193325
2023-01-24 06:43:37.244728: step: 1992/527, loss: 0.004425434861332178
2023-01-24 06:43:38.281310: step: 1996/527, loss: 0.0022823847830295563
2023-01-24 06:43:39.324136: step: 2000/527, loss: 0.0010275078238919377
2023-01-24 06:43:40.359323: step: 2004/527, loss: 0.007139250636100769
2023-01-24 06:43:41.407202: step: 2008/527, loss: 0.0002385387779213488
2023-01-24 06:43:42.466882: step: 2012/527, loss: 0.003703586058691144
2023-01-24 06:43:43.523797: step: 2016/527, loss: 0.0005519840051420033
2023-01-24 06:43:44.584484: step: 2020/527, loss: 0.0845273956656456
2023-01-24 06:43:45.624920: step: 2024/527, loss: 0.0003239141951780766
2023-01-24 06:43:46.675887: step: 2028/527, loss: 0.004487867932766676
2023-01-24 06:43:47.725649: step: 2032/527, loss: 0.006838872097432613
2023-01-24 06:43:48.771394: step: 2036/527, loss: 0.006086735520511866
2023-01-24 06:43:49.819050: step: 2040/527, loss: 0.00017563503934070468
2023-01-24 06:43:50.860295: step: 2044/527, loss: 0.016819581389427185
2023-01-24 06:43:51.904156: step: 2048/527, loss: 0.0034136290196329355
2023-01-24 06:43:52.953023: step: 2052/527, loss: 0.001498789875768125
2023-01-24 06:43:53.995990: step: 2056/527, loss: 0.004052781034260988
2023-01-24 06:43:55.050773: step: 2060/527, loss: 0.02138926461338997
2023-01-24 06:43:56.106201: step: 2064/527, loss: 0.0009345430880784988
2023-01-24 06:43:57.150992: step: 2068/527, loss: 0.01055892277508974
2023-01-24 06:43:58.186891: step: 2072/527, loss: 0.007733316160738468
2023-01-24 06:43:59.234531: step: 2076/527, loss: 0.01906740292906761
2023-01-24 06:44:00.270754: step: 2080/527, loss: 0.009845261462032795
2023-01-24 06:44:01.321053: step: 2084/527, loss: 0.0012843109434470534
2023-01-24 06:44:02.356021: step: 2088/527, loss: 0.0008479171083308756
2023-01-24 06:44:03.404575: step: 2092/527, loss: 0.004049117676913738
2023-01-24 06:44:04.454354: step: 2096/527, loss: 0.03851398080587387
2023-01-24 06:44:05.522120: step: 2100/527, loss: 0.004781814757734537
2023-01-24 06:44:06.574347: step: 2104/527, loss: 0.009083278477191925
2023-01-24 06:44:07.652102: step: 2108/527, loss: 0.012636136263608932
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33803048207919534, 'r': 0.32327772859186804, 'f1': 0.3304895498892618}, 'combined': 0.2435186157078771, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3640449051164759, 'r': 0.288919274696985, 'f1': 0.3221603671228418}, 'combined': 0.20618263495861872, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3511474469305795, 'r': 0.33182434264028193, 'f1': 0.341212543554007}, 'combined': 0.25141976893453144, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37422227682683973, 'r': 0.30488408929489125, 'f1': 0.33601339570938465}, 'combined': 0.21504857325400614, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36325359749028163, 'r': 0.3260321662483932, 'f1': 0.3436379032258064}, 'combined': 0.25320687606112047, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827405873011607, 'r': 0.313309979395116, 'f1': 0.344562453530268}, 'combined': 0.24704477800283367, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36325359749028163, 'r': 0.3260321662483932, 'f1': 0.3436379032258064}, 'combined': 0.25320687606112047, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827405873011607, 'r': 0.313309979395116, 'f1': 0.344562453530268}, 'combined': 0.24704477800283367, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
******************************
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
2023-01-24 06:46:48.077545: step: 4/527, loss: 0.0033048205077648163
2023-01-24 06:46:49.122639: step: 8/527, loss: 0.00628558499738574
2023-01-24 06:46:50.181147: step: 12/527, loss: 0.007464157417416573
2023-01-24 06:46:51.238300: step: 16/527, loss: 0.010390263982117176
2023-01-24 06:46:52.292230: step: 20/527, loss: 0.03318922221660614
2023-01-24 06:46:53.329036: step: 24/527, loss: 0.005193404853343964
2023-01-24 06:46:54.398146: step: 28/527, loss: 0.0054178559221327305
2023-01-24 06:46:55.446944: step: 32/527, loss: 0.0016802771715447307
2023-01-24 06:46:56.476200: step: 36/527, loss: 0.008208749815821648
2023-01-24 06:46:57.530425: step: 40/527, loss: 0.004966137930750847
2023-01-24 06:46:58.586413: step: 44/527, loss: 0.00980713777244091
2023-01-24 06:46:59.625027: step: 48/527, loss: 0.001211044960655272
2023-01-24 06:47:00.671310: step: 52/527, loss: 0.001335397595539689
2023-01-24 06:47:01.715966: step: 56/527, loss: 0.005293728783726692
2023-01-24 06:47:02.769136: step: 60/527, loss: 0.014024567790329456
2023-01-24 06:47:03.837345: step: 64/527, loss: 0.0037151824217289686
2023-01-24 06:47:04.886422: step: 68/527, loss: 0.004241329617798328
2023-01-24 06:47:05.944102: step: 72/527, loss: 0.010848058387637138
2023-01-24 06:47:06.979108: step: 76/527, loss: 0.0004890532582066953
2023-01-24 06:47:08.033330: step: 80/527, loss: 0.0344138965010643
2023-01-24 06:47:09.089879: step: 84/527, loss: 0.008191194385290146
2023-01-24 06:47:10.123269: step: 88/527, loss: 0.0031900103203952312
2023-01-24 06:47:11.175402: step: 92/527, loss: 0.003622998483479023
2023-01-24 06:47:12.220828: step: 96/527, loss: 0.002374161034822464
2023-01-24 06:47:13.277422: step: 100/527, loss: 7.176781946327537e-05
2023-01-24 06:47:14.310827: step: 104/527, loss: 6.124939682194963e-05
2023-01-24 06:47:15.357702: step: 108/527, loss: 0.0010666617890819907
2023-01-24 06:47:16.401728: step: 112/527, loss: 0.0009427742334082723
2023-01-24 06:47:17.454719: step: 116/527, loss: 0.015784695744514465
2023-01-24 06:47:18.495782: step: 120/527, loss: 0.0035453890450298786
2023-01-24 06:47:19.555353: step: 124/527, loss: 0.00014572578947991133
2023-01-24 06:47:20.608013: step: 128/527, loss: 0.0005226345383562148
2023-01-24 06:47:21.660256: step: 132/527, loss: 0.020005855709314346
2023-01-24 06:47:22.710459: step: 136/527, loss: 0.0069860536605119705
2023-01-24 06:47:23.755577: step: 140/527, loss: 0.0015370113542303443
2023-01-24 06:47:24.812900: step: 144/527, loss: 0.005408475641161203
2023-01-24 06:47:25.859070: step: 148/527, loss: 0.010170998051762581
2023-01-24 06:47:26.914656: step: 152/527, loss: 0.007378180045634508
2023-01-24 06:47:27.962430: step: 156/527, loss: 0.007173619233071804
2023-01-24 06:47:29.040138: step: 160/527, loss: 0.010527165606617928
2023-01-24 06:47:30.096723: step: 164/527, loss: 0.00205438956618309
2023-01-24 06:47:31.151534: step: 168/527, loss: 0.009719911031425
2023-01-24 06:47:32.195241: step: 172/527, loss: 0.0027593474369496107
2023-01-24 06:47:33.258972: step: 176/527, loss: 0.0027350790333002806
2023-01-24 06:47:34.302414: step: 180/527, loss: 0.0025922656059265137
2023-01-24 06:47:35.359039: step: 184/527, loss: 0.015137199312448502
2023-01-24 06:47:36.423925: step: 188/527, loss: 0.004287356976419687
2023-01-24 06:47:37.472521: step: 192/527, loss: 0.004597049672156572
2023-01-24 06:47:38.526680: step: 196/527, loss: 0.0009718707296997309
2023-01-24 06:47:39.594609: step: 200/527, loss: 0.0006976012955419719
2023-01-24 06:47:40.648520: step: 204/527, loss: 0.008843767456710339
2023-01-24 06:47:41.707038: step: 208/527, loss: 0.0010709972120821476
2023-01-24 06:47:42.753763: step: 212/527, loss: 0.0030473654624074697
2023-01-24 06:47:43.812195: step: 216/527, loss: 0.0059176222421228886
2023-01-24 06:47:44.862486: step: 220/527, loss: 0.001009593834169209
2023-01-24 06:47:45.914580: step: 224/527, loss: 0.0021999201271682978
2023-01-24 06:47:46.979295: step: 228/527, loss: 0.0015889824135228992
2023-01-24 06:47:48.032174: step: 232/527, loss: 0.011037415824830532
2023-01-24 06:47:49.088178: step: 236/527, loss: 0.008738135918974876
2023-01-24 06:47:50.137948: step: 240/527, loss: 0.00613620737567544
2023-01-24 06:47:51.225888: step: 244/527, loss: 0.07120721787214279
2023-01-24 06:47:52.267863: step: 248/527, loss: 0.004037360195070505
2023-01-24 06:47:53.308024: step: 252/527, loss: 0.0010949140414595604
2023-01-24 06:47:54.347673: step: 256/527, loss: 0.009065071120858192
2023-01-24 06:47:55.400593: step: 260/527, loss: 0.005262174177914858
2023-01-24 06:47:56.453340: step: 264/527, loss: 0.0025205330457538366
2023-01-24 06:47:57.517484: step: 268/527, loss: 0.004450581502169371
2023-01-24 06:47:58.561806: step: 272/527, loss: 0.013686439022421837
2023-01-24 06:47:59.609130: step: 276/527, loss: 0.0041384524665772915
2023-01-24 06:48:00.658063: step: 280/527, loss: 0.006845667026937008
2023-01-24 06:48:01.703357: step: 284/527, loss: 0.0023614733945578337
2023-01-24 06:48:02.751952: step: 288/527, loss: 0.007462221663445234
2023-01-24 06:48:03.821840: step: 292/527, loss: 0.0022659345995634794
2023-01-24 06:48:04.871692: step: 296/527, loss: 0.0024779837112873793
2023-01-24 06:48:05.935545: step: 300/527, loss: 0.0007155893836170435
2023-01-24 06:48:06.978141: step: 304/527, loss: 0.02356657385826111
2023-01-24 06:48:08.031516: step: 308/527, loss: 0.0005279480828903615
2023-01-24 06:48:09.083893: step: 312/527, loss: 0.006099306978285313
2023-01-24 06:48:10.151140: step: 316/527, loss: 0.007159698288887739
2023-01-24 06:48:11.197040: step: 320/527, loss: 0.0013627164298668504
2023-01-24 06:48:12.249940: step: 324/527, loss: 0.03577382490038872
2023-01-24 06:48:13.310957: step: 328/527, loss: 0.03740757703781128
2023-01-24 06:48:14.373971: step: 332/527, loss: 0.012488479726016521
2023-01-24 06:48:15.439428: step: 336/527, loss: 0.0020703908521682024
2023-01-24 06:48:16.505631: step: 340/527, loss: 0.00265825679525733
2023-01-24 06:48:17.558815: step: 344/527, loss: 0.0023790725972503424
2023-01-24 06:48:18.624282: step: 348/527, loss: 0.007340741343796253
2023-01-24 06:48:19.715315: step: 352/527, loss: 0.005207661539316177
2023-01-24 06:48:20.764559: step: 356/527, loss: 0.009817021898925304
2023-01-24 06:48:21.815242: step: 360/527, loss: 0.006574298720806837
2023-01-24 06:48:22.869859: step: 364/527, loss: 0.023271994665265083
2023-01-24 06:48:23.925798: step: 368/527, loss: 0.007112201768904924
2023-01-24 06:48:24.986860: step: 372/527, loss: 0.0051622046157717705
2023-01-24 06:48:26.047503: step: 376/527, loss: 0.0008659258019179106
2023-01-24 06:48:27.088408: step: 380/527, loss: 0.0018084509065374732
2023-01-24 06:48:28.127974: step: 384/527, loss: 0.0023707428481429815
2023-01-24 06:48:29.185924: step: 388/527, loss: 0.0011350124841555953
2023-01-24 06:48:30.238989: step: 392/527, loss: 0.011461051180958748
2023-01-24 06:48:31.275814: step: 396/527, loss: 0.0008804863318800926
2023-01-24 06:48:32.310937: step: 400/527, loss: 0.001423258800059557
2023-01-24 06:48:33.361643: step: 404/527, loss: 0.005903357174247503
2023-01-24 06:48:34.422042: step: 408/527, loss: 0.008300085552036762
2023-01-24 06:48:35.482617: step: 412/527, loss: 0.0011669457890093327
2023-01-24 06:48:36.557034: step: 416/527, loss: 0.006710781715810299
2023-01-24 06:48:37.617507: step: 420/527, loss: 0.004249363671988249
2023-01-24 06:48:38.676138: step: 424/527, loss: 0.002789535094052553
2023-01-24 06:48:39.721163: step: 428/527, loss: 0.005826150998473167
2023-01-24 06:48:40.769295: step: 432/527, loss: 0.001404089154675603
2023-01-24 06:48:41.818503: step: 436/527, loss: 0.00032881333027035
2023-01-24 06:48:42.868388: step: 440/527, loss: 0.0017484960844740272
2023-01-24 06:48:43.909623: step: 444/527, loss: 0.002080990467220545
2023-01-24 06:48:44.968105: step: 448/527, loss: 0.00020153906370978802
2023-01-24 06:48:46.024620: step: 452/527, loss: 0.0009347113082185388
2023-01-24 06:48:47.072480: step: 456/527, loss: 0.01221492700278759
2023-01-24 06:48:48.115489: step: 460/527, loss: 0.001383670256473124
2023-01-24 06:48:49.160120: step: 464/527, loss: 0.00013337848940864205
2023-01-24 06:48:50.218866: step: 468/527, loss: 0.0018460775027051568
2023-01-24 06:48:51.279910: step: 472/527, loss: 0.0016555074835196137
2023-01-24 06:48:52.342582: step: 476/527, loss: 8.989281195681542e-05
2023-01-24 06:48:53.380542: step: 480/527, loss: 0.00475011533126235
2023-01-24 06:48:54.472738: step: 484/527, loss: 0.005712158977985382
2023-01-24 06:48:55.540425: step: 488/527, loss: 0.003547893837094307
2023-01-24 06:48:56.602762: step: 492/527, loss: 0.0014360366621986032
2023-01-24 06:48:57.654353: step: 496/527, loss: 8.79975559655577e-05
2023-01-24 06:48:58.728177: step: 500/527, loss: 0.0028699792455881834
2023-01-24 06:48:59.777336: step: 504/527, loss: 0.007351300213485956
2023-01-24 06:49:00.829708: step: 508/527, loss: 0.01670556142926216
2023-01-24 06:49:01.910333: step: 512/527, loss: 0.003492743708193302
2023-01-24 06:49:02.959593: step: 516/527, loss: 0.0033423209097236395
2023-01-24 06:49:03.999897: step: 520/527, loss: 0.0024150048848241568
2023-01-24 06:49:05.069130: step: 524/527, loss: 0.004328024107962847
2023-01-24 06:49:06.136757: step: 528/527, loss: 0.006088695488870144
2023-01-24 06:49:07.185306: step: 532/527, loss: 0.009847326204180717
2023-01-24 06:49:08.233014: step: 536/527, loss: 0.0009617412579245865
2023-01-24 06:49:09.290276: step: 540/527, loss: 0.006474452558904886
2023-01-24 06:49:10.335221: step: 544/527, loss: 0.0002648832742124796
2023-01-24 06:49:11.388586: step: 548/527, loss: 0.0005481508560478687
2023-01-24 06:49:12.432214: step: 552/527, loss: 0.028697669506072998
2023-01-24 06:49:13.486302: step: 556/527, loss: 0.000871647906024009
2023-01-24 06:49:14.542048: step: 560/527, loss: 0.007545448839664459
2023-01-24 06:49:15.589362: step: 564/527, loss: 0.02357676438987255
2023-01-24 06:49:16.658436: step: 568/527, loss: 0.0023842155933380127
2023-01-24 06:49:17.720989: step: 572/527, loss: 0.0032975059002637863
2023-01-24 06:49:18.788910: step: 576/527, loss: 0.005622240714728832
2023-01-24 06:49:19.831744: step: 580/527, loss: 0.007460377179086208
2023-01-24 06:49:20.891520: step: 584/527, loss: 0.0036258345935493708
2023-01-24 06:49:21.945194: step: 588/527, loss: 0.004793180152773857
2023-01-24 06:49:22.990658: step: 592/527, loss: 0.005957207642495632
2023-01-24 06:49:24.026860: step: 596/527, loss: 0.016912993043661118
2023-01-24 06:49:25.091368: step: 600/527, loss: 0.005824789870530367
2023-01-24 06:49:26.151049: step: 604/527, loss: 0.022178053855895996
2023-01-24 06:49:27.208179: step: 608/527, loss: 0.000452561245765537
2023-01-24 06:49:28.265338: step: 612/527, loss: 0.0013217199593782425
2023-01-24 06:49:29.314047: step: 616/527, loss: 0.0008828747668303549
2023-01-24 06:49:30.367662: step: 620/527, loss: 0.0014094137586653233
2023-01-24 06:49:31.402832: step: 624/527, loss: 0.004334430210292339
2023-01-24 06:49:32.457401: step: 628/527, loss: 0.0017066608415916562
2023-01-24 06:49:33.525397: step: 632/527, loss: 0.002489479025825858
2023-01-24 06:49:34.572042: step: 636/527, loss: 0.0006815826054662466
2023-01-24 06:49:35.619511: step: 640/527, loss: 0.0053624981082975864
2023-01-24 06:49:36.690279: step: 644/527, loss: 0.009374787099659443
2023-01-24 06:49:37.750640: step: 648/527, loss: 0.005790805909782648
2023-01-24 06:49:38.815625: step: 652/527, loss: 0.006711133755743504
2023-01-24 06:49:39.882702: step: 656/527, loss: 0.009350858628749847
2023-01-24 06:49:40.936082: step: 660/527, loss: 0.0009404016309417784
2023-01-24 06:49:41.983181: step: 664/527, loss: 0.008918608538806438
2023-01-24 06:49:43.028440: step: 668/527, loss: 0.004295982886105776
2023-01-24 06:49:44.082179: step: 672/527, loss: 2.8885775464004837e-05
2023-01-24 06:49:45.113095: step: 676/527, loss: 0.0020936280488967896
2023-01-24 06:49:46.171717: step: 680/527, loss: 0.005032512824982405
2023-01-24 06:49:47.222366: step: 684/527, loss: 0.004130632616579533
2023-01-24 06:49:48.281958: step: 688/527, loss: 0.006223151460289955
2023-01-24 06:49:49.337405: step: 692/527, loss: 0.016337711364030838
2023-01-24 06:49:50.402813: step: 696/527, loss: 0.0030684652738273144
2023-01-24 06:49:51.453918: step: 700/527, loss: 0.006968655623495579
2023-01-24 06:49:52.486134: step: 704/527, loss: 0.0009030302753672004
2023-01-24 06:49:53.546629: step: 708/527, loss: 0.0012635773746296763
2023-01-24 06:49:54.589163: step: 712/527, loss: 0.0052895741537213326
2023-01-24 06:49:55.643385: step: 716/527, loss: 0.0007400992326438427
2023-01-24 06:49:56.707037: step: 720/527, loss: 0.0027009667828679085
2023-01-24 06:49:57.758771: step: 724/527, loss: 0.0011684899218380451
2023-01-24 06:49:58.810063: step: 728/527, loss: 0.044344719499349594
2023-01-24 06:49:59.855645: step: 732/527, loss: 0.0008587951306253672
2023-01-24 06:50:00.905562: step: 736/527, loss: 0.010753421112895012
2023-01-24 06:50:01.960797: step: 740/527, loss: 0.005611707456409931
2023-01-24 06:50:03.003164: step: 744/527, loss: 0.003588673658668995
2023-01-24 06:50:04.047200: step: 748/527, loss: 0.0005281084449961782
2023-01-24 06:50:05.110773: step: 752/527, loss: 0.00015799708489794284
2023-01-24 06:50:06.169178: step: 756/527, loss: 0.013051873072981834
2023-01-24 06:50:07.234642: step: 760/527, loss: 0.0017645241459831595
2023-01-24 06:50:08.288338: step: 764/527, loss: 0.0030068105552345514
2023-01-24 06:50:09.337044: step: 768/527, loss: 0.0032245442271232605
2023-01-24 06:50:10.403532: step: 772/527, loss: 0.001608636579476297
2023-01-24 06:50:11.457301: step: 776/527, loss: 0.0009087428916245699
2023-01-24 06:50:12.512542: step: 780/527, loss: 0.005056384485214949
2023-01-24 06:50:13.557552: step: 784/527, loss: 0.0043554785661399364
2023-01-24 06:50:14.603634: step: 788/527, loss: 0.0022038696333765984
2023-01-24 06:50:15.653421: step: 792/527, loss: 0.007971453480422497
2023-01-24 06:50:16.707684: step: 796/527, loss: 0.0022209854796528816
2023-01-24 06:50:17.754319: step: 800/527, loss: 0.0019030345138162374
2023-01-24 06:50:18.803498: step: 804/527, loss: 0.007975144311785698
2023-01-24 06:50:19.853464: step: 808/527, loss: 0.003980494569987059
2023-01-24 06:50:20.909080: step: 812/527, loss: 0.0034533338621258736
2023-01-24 06:50:21.950190: step: 816/527, loss: 0.00048152636736631393
2023-01-24 06:50:23.012531: step: 820/527, loss: 0.00901760533452034
2023-01-24 06:50:24.067371: step: 824/527, loss: 0.0010012831771746278
2023-01-24 06:50:25.122305: step: 828/527, loss: 0.014228510670363903
2023-01-24 06:50:26.189270: step: 832/527, loss: 0.0024030162021517754
2023-01-24 06:50:27.251765: step: 836/527, loss: 0.004572403151541948
2023-01-24 06:50:28.307892: step: 840/527, loss: 0.0006582144997082651
2023-01-24 06:50:29.351559: step: 844/527, loss: 0.01826358400285244
2023-01-24 06:50:30.405537: step: 848/527, loss: 0.004884585738182068
2023-01-24 06:50:31.453529: step: 852/527, loss: 0.005931575316935778
2023-01-24 06:50:32.502619: step: 856/527, loss: 0.0034075970761477947
2023-01-24 06:50:33.542706: step: 860/527, loss: 0.000262924178969115
2023-01-24 06:50:34.592033: step: 864/527, loss: 0.00541821401566267
2023-01-24 06:50:35.624720: step: 868/527, loss: 0.0029333201237022877
2023-01-24 06:50:36.688050: step: 872/527, loss: 0.01131183747202158
2023-01-24 06:50:37.746543: step: 876/527, loss: 0.002358927857130766
2023-01-24 06:50:38.799306: step: 880/527, loss: 0.011612359434366226
2023-01-24 06:50:39.858298: step: 884/527, loss: 0.00248313439078629
2023-01-24 06:50:40.910567: step: 888/527, loss: 0.001263869577087462
2023-01-24 06:50:41.970828: step: 892/527, loss: 0.0037806208711117506
2023-01-24 06:50:43.011154: step: 896/527, loss: 0.0002942613500636071
2023-01-24 06:50:44.077242: step: 900/527, loss: 0.03475181758403778
2023-01-24 06:50:45.138238: step: 904/527, loss: 0.0011011157184839249
2023-01-24 06:50:46.195525: step: 908/527, loss: 0.0038861355278640985
2023-01-24 06:50:47.253188: step: 912/527, loss: 0.0029995073564350605
2023-01-24 06:50:48.309792: step: 916/527, loss: 0.003938739653676748
2023-01-24 06:50:49.370494: step: 920/527, loss: 0.0034913131967186928
2023-01-24 06:50:50.416045: step: 924/527, loss: 0.022138547152280807
2023-01-24 06:50:51.473030: step: 928/527, loss: 0.01640618033707142
2023-01-24 06:50:52.521205: step: 932/527, loss: 0.0062112645246088505
2023-01-24 06:50:53.572962: step: 936/527, loss: 0.0028167078271508217
2023-01-24 06:50:54.628327: step: 940/527, loss: 0.016081981360912323
2023-01-24 06:50:55.670963: step: 944/527, loss: 0.00893818773329258
2023-01-24 06:50:56.724543: step: 948/527, loss: 0.0034072105772793293
2023-01-24 06:50:57.786162: step: 952/527, loss: 0.004192746710032225
2023-01-24 06:50:58.842670: step: 956/527, loss: 0.001134840422309935
2023-01-24 06:50:59.883626: step: 960/527, loss: 0.019354024901986122
2023-01-24 06:51:00.935324: step: 964/527, loss: 0.010273844003677368
2023-01-24 06:51:01.993627: step: 968/527, loss: 0.0009943839395418763
2023-01-24 06:51:03.040963: step: 972/527, loss: 0.004493022337555885
2023-01-24 06:51:04.080218: step: 976/527, loss: 0.0005187156493775547
2023-01-24 06:51:05.134570: step: 980/527, loss: 0.0060578277334570885
2023-01-24 06:51:06.180226: step: 984/527, loss: 0.006456491071730852
2023-01-24 06:51:07.227323: step: 988/527, loss: 0.0006316354847513139
2023-01-24 06:51:08.292167: step: 992/527, loss: 0.007543027400970459
2023-01-24 06:51:09.345646: step: 996/527, loss: 0.0046927956864237785
2023-01-24 06:51:10.396632: step: 1000/527, loss: 0.001250214409083128
2023-01-24 06:51:11.474497: step: 1004/527, loss: 0.0040900446474552155
2023-01-24 06:51:12.527739: step: 1008/527, loss: 0.011389343068003654
2023-01-24 06:51:13.581069: step: 1012/527, loss: 0.004603247623890638
2023-01-24 06:51:14.628763: step: 1016/527, loss: 0.002595828380435705
2023-01-24 06:51:15.671630: step: 1020/527, loss: 0.001541301142424345
2023-01-24 06:51:16.711959: step: 1024/527, loss: 6.932113319635391e-05
2023-01-24 06:51:17.787571: step: 1028/527, loss: 0.0052374848164618015
2023-01-24 06:51:18.827680: step: 1032/527, loss: 0.0
2023-01-24 06:51:19.868773: step: 1036/527, loss: 0.00318225403316319
2023-01-24 06:51:20.930693: step: 1040/527, loss: 0.007270502857863903
2023-01-24 06:51:21.983760: step: 1044/527, loss: 0.007681084331125021
2023-01-24 06:51:23.034226: step: 1048/527, loss: 0.007212923374027014
2023-01-24 06:51:24.080719: step: 1052/527, loss: 4.61352028651163e-05
2023-01-24 06:51:25.134734: step: 1056/527, loss: 0.003815811825916171
2023-01-24 06:51:26.172518: step: 1060/527, loss: 0.0013724776217713952
2023-01-24 06:51:27.232857: step: 1064/527, loss: 0.009887893684208393
2023-01-24 06:51:28.269488: step: 1068/527, loss: 0.00273287040181458
2023-01-24 06:51:29.328448: step: 1072/527, loss: 0.0027575402054935694
2023-01-24 06:51:30.380409: step: 1076/527, loss: 0.005254405550658703
2023-01-24 06:51:31.420483: step: 1080/527, loss: 0.012286016717553139
2023-01-24 06:51:32.476681: step: 1084/527, loss: 0.003363200929015875
2023-01-24 06:51:33.528537: step: 1088/527, loss: 0.0010884279618039727
2023-01-24 06:51:34.587666: step: 1092/527, loss: 0.001632597646676004
2023-01-24 06:51:35.621379: step: 1096/527, loss: 0.00014103917055763304
2023-01-24 06:51:36.669736: step: 1100/527, loss: 0.00603564502671361
2023-01-24 06:51:37.715302: step: 1104/527, loss: 0.0013685551239177585
2023-01-24 06:51:38.765586: step: 1108/527, loss: 0.020622577518224716
2023-01-24 06:51:39.806699: step: 1112/527, loss: 0.006159561220556498
2023-01-24 06:51:40.844810: step: 1116/527, loss: 0.004934003110975027
2023-01-24 06:51:41.885163: step: 1120/527, loss: 0.014519993215799332
2023-01-24 06:51:42.926046: step: 1124/527, loss: 0.00016985707043204457
2023-01-24 06:51:43.994986: step: 1128/527, loss: 0.00581841915845871
2023-01-24 06:51:45.058372: step: 1132/527, loss: 0.0029912195168435574
2023-01-24 06:51:46.102507: step: 1136/527, loss: 0.0021725844126194715
2023-01-24 06:51:47.151144: step: 1140/527, loss: 0.005850040819495916
2023-01-24 06:51:48.200043: step: 1144/527, loss: 0.007465075701475143
2023-01-24 06:51:49.255303: step: 1148/527, loss: 0.010512011125683784
2023-01-24 06:51:50.282532: step: 1152/527, loss: 0.003384977113455534
2023-01-24 06:51:51.326643: step: 1156/527, loss: 3.9365568227367476e-05
2023-01-24 06:51:52.369872: step: 1160/527, loss: 0.0033887599129229784
2023-01-24 06:51:53.404395: step: 1164/527, loss: 0.011170794256031513
2023-01-24 06:51:54.452083: step: 1168/527, loss: 0.0012819372350350022
2023-01-24 06:51:55.503014: step: 1172/527, loss: 0.002545284805819392
2023-01-24 06:51:56.562678: step: 1176/527, loss: 0.006260955706238747
2023-01-24 06:51:57.605506: step: 1180/527, loss: 0.003953002858906984
2023-01-24 06:51:58.667508: step: 1184/527, loss: 0.0008687982917763293
2023-01-24 06:51:59.727207: step: 1188/527, loss: 0.001278851181268692
2023-01-24 06:52:00.786823: step: 1192/527, loss: 0.003125661052763462
2023-01-24 06:52:01.828647: step: 1196/527, loss: 0.010133283212780952
2023-01-24 06:52:02.877675: step: 1200/527, loss: 0.011354834772646427
2023-01-24 06:52:03.912881: step: 1204/527, loss: 0.008050438947975636
2023-01-24 06:52:04.976511: step: 1208/527, loss: 0.015564941801130772
2023-01-24 06:52:06.036294: step: 1212/527, loss: 0.006989758461713791
2023-01-24 06:52:07.095448: step: 1216/527, loss: 0.006502440664917231
2023-01-24 06:52:08.148944: step: 1220/527, loss: 0.004202271346002817
2023-01-24 06:52:09.188282: step: 1224/527, loss: 0.00974033959209919
2023-01-24 06:52:10.237959: step: 1228/527, loss: 0.001350743230432272
2023-01-24 06:52:11.300496: step: 1232/527, loss: 0.006581700872629881
2023-01-24 06:52:12.349650: step: 1236/527, loss: 0.015475451946258545
2023-01-24 06:52:13.399681: step: 1240/527, loss: 0.022281644865870476
2023-01-24 06:52:14.442715: step: 1244/527, loss: 0.006544162053614855
2023-01-24 06:52:15.499314: step: 1248/527, loss: 0.001436798251233995
2023-01-24 06:52:16.543625: step: 1252/527, loss: 0.021127983927726746
2023-01-24 06:52:17.589789: step: 1256/527, loss: 0.011949064210057259
2023-01-24 06:52:18.636268: step: 1260/527, loss: 0.0021717033814638853
2023-01-24 06:52:19.722428: step: 1264/527, loss: 0.01362568698823452
2023-01-24 06:52:20.788181: step: 1268/527, loss: 0.009508670307695866
2023-01-24 06:52:21.833591: step: 1272/527, loss: 0.0018951075617223978
2023-01-24 06:52:22.876408: step: 1276/527, loss: 0.0011392015730962157
2023-01-24 06:52:23.913233: step: 1280/527, loss: 0.0015228339470922947
2023-01-24 06:52:24.949584: step: 1284/527, loss: 0.008156024850904942
2023-01-24 06:52:26.002085: step: 1288/527, loss: 0.004517382942140102
2023-01-24 06:52:27.064424: step: 1292/527, loss: 0.004823583178222179
2023-01-24 06:52:28.109178: step: 1296/527, loss: 0.0001608405145816505
2023-01-24 06:52:29.163412: step: 1300/527, loss: 0.008443241007626057
2023-01-24 06:52:30.231625: step: 1304/527, loss: 0.006816533859819174
2023-01-24 06:52:31.283237: step: 1308/527, loss: 0.0001046990291797556
2023-01-24 06:52:32.369359: step: 1312/527, loss: 0.008965989574790001
2023-01-24 06:52:33.423181: step: 1316/527, loss: 0.005940592382103205
2023-01-24 06:52:34.476079: step: 1320/527, loss: 0.0053385584615170956
2023-01-24 06:52:35.531088: step: 1324/527, loss: 0.0005323129007592797
2023-01-24 06:52:36.566855: step: 1328/527, loss: 0.0018906351178884506
2023-01-24 06:52:37.632200: step: 1332/527, loss: 0.006390294060111046
2023-01-24 06:52:38.677799: step: 1336/527, loss: 0.016296381130814552
2023-01-24 06:52:39.707101: step: 1340/527, loss: 0.0012550114188343287
2023-01-24 06:52:40.754498: step: 1344/527, loss: 0.002112034475430846
2023-01-24 06:52:41.796638: step: 1348/527, loss: 0.0056297811679542065
2023-01-24 06:52:42.846786: step: 1352/527, loss: 0.007862898521125317
2023-01-24 06:52:43.884957: step: 1356/527, loss: 0.015588123351335526
2023-01-24 06:52:44.930627: step: 1360/527, loss: 0.0
2023-01-24 06:52:45.965171: step: 1364/527, loss: 0.003212908050045371
2023-01-24 06:52:47.005816: step: 1368/527, loss: 0.009797049686312675
2023-01-24 06:52:48.066104: step: 1372/527, loss: 0.016829384490847588
2023-01-24 06:52:49.117247: step: 1376/527, loss: 0.005274294409900904
2023-01-24 06:52:50.208587: step: 1380/527, loss: 0.00189267098903656
2023-01-24 06:52:51.250080: step: 1384/527, loss: 0.015568006783723831
2023-01-24 06:52:52.312940: step: 1388/527, loss: 0.0030747901182621717
2023-01-24 06:52:53.369154: step: 1392/527, loss: 0.003674580017104745
2023-01-24 06:52:54.409959: step: 1396/527, loss: 0.002436636947095394
2023-01-24 06:52:55.468721: step: 1400/527, loss: 0.0010753895621746778
2023-01-24 06:52:56.527018: step: 1404/527, loss: 0.005425342358648777
2023-01-24 06:52:57.567924: step: 1408/527, loss: 0.0031529467087239027
2023-01-24 06:52:58.632588: step: 1412/527, loss: 0.0017186481272801757
2023-01-24 06:52:59.694232: step: 1416/527, loss: 0.008601337671279907
2023-01-24 06:53:00.736297: step: 1420/527, loss: 0.0001440748164895922
2023-01-24 06:53:01.793841: step: 1424/527, loss: 0.004143062513321638
2023-01-24 06:53:02.835734: step: 1428/527, loss: 0.004578811582177877
2023-01-24 06:53:03.866042: step: 1432/527, loss: 0.010508562438189983
2023-01-24 06:53:04.915134: step: 1436/527, loss: 0.005084532778710127
2023-01-24 06:53:05.944552: step: 1440/527, loss: 0.003376667620614171
2023-01-24 06:53:06.992810: step: 1444/527, loss: 0.007349275052547455
2023-01-24 06:53:08.053620: step: 1448/527, loss: 0.007827515713870525
2023-01-24 06:53:09.103714: step: 1452/527, loss: 0.001971168676391244
2023-01-24 06:53:10.146140: step: 1456/527, loss: 0.0033010949846357107
2023-01-24 06:53:11.206228: step: 1460/527, loss: 0.004628949332982302
2023-01-24 06:53:12.244336: step: 1464/527, loss: 0.005636187270283699
2023-01-24 06:53:13.318381: step: 1468/527, loss: 0.016175074502825737
2023-01-24 06:53:14.383353: step: 1472/527, loss: 0.006416806019842625
2023-01-24 06:53:15.435825: step: 1476/527, loss: 0.00404331972822547
2023-01-24 06:53:16.483233: step: 1480/527, loss: 0.01362985372543335
2023-01-24 06:53:17.530873: step: 1484/527, loss: 0.005481289699673653
2023-01-24 06:53:18.587960: step: 1488/527, loss: 0.007824812084436417
2023-01-24 06:53:19.649455: step: 1492/527, loss: 0.006577885709702969
2023-01-24 06:53:20.683847: step: 1496/527, loss: 0.00042355613550171256
2023-01-24 06:53:21.730482: step: 1500/527, loss: 0.03957362845540047
2023-01-24 06:53:22.783724: step: 1504/527, loss: 0.006651520729064941
2023-01-24 06:53:23.834726: step: 1508/527, loss: 0.003347818274050951
2023-01-24 06:53:24.909872: step: 1512/527, loss: 0.00016294789384119213
2023-01-24 06:53:25.963064: step: 1516/527, loss: 0.003195906290784478
2023-01-24 06:53:27.008292: step: 1520/527, loss: 0.00042527110781520605
2023-01-24 06:53:28.064356: step: 1524/527, loss: 0.004982766229659319
2023-01-24 06:53:29.118093: step: 1528/527, loss: 0.012321083806455135
2023-01-24 06:53:30.176575: step: 1532/527, loss: 0.009371409192681313
2023-01-24 06:53:31.219985: step: 1536/527, loss: 0.009588467888534069
2023-01-24 06:53:32.259127: step: 1540/527, loss: 0.0042380825616419315
2023-01-24 06:53:33.302822: step: 1544/527, loss: 1.6275606640192564e-06
2023-01-24 06:53:34.356911: step: 1548/527, loss: 0.01996329426765442
2023-01-24 06:53:35.400352: step: 1552/527, loss: 0.0034044182393699884
2023-01-24 06:53:36.452454: step: 1556/527, loss: 0.0027883679140359163
2023-01-24 06:53:37.504603: step: 1560/527, loss: 0.007521283347159624
2023-01-24 06:53:38.567247: step: 1564/527, loss: 0.010301162488758564
2023-01-24 06:53:39.631428: step: 1568/527, loss: 0.007357570342719555
2023-01-24 06:53:40.672914: step: 1572/527, loss: 0.0035316043067723513
2023-01-24 06:53:41.722224: step: 1576/527, loss: 0.00499480776488781
2023-01-24 06:53:42.780361: step: 1580/527, loss: 0.0066254339180886745
2023-01-24 06:53:43.830613: step: 1584/527, loss: 0.005504979752004147
2023-01-24 06:53:44.865328: step: 1588/527, loss: 0.002800211776047945
2023-01-24 06:53:45.897753: step: 1592/527, loss: 0.009911361150443554
2023-01-24 06:53:46.960405: step: 1596/527, loss: 0.0003656733315438032
2023-01-24 06:53:48.001576: step: 1600/527, loss: 0.009688540361821651
2023-01-24 06:53:49.036445: step: 1604/527, loss: 0.014820481650531292
2023-01-24 06:53:50.073697: step: 1608/527, loss: 0.0014237827854231
2023-01-24 06:53:51.133964: step: 1612/527, loss: 0.007423287723213434
2023-01-24 06:53:52.185308: step: 1616/527, loss: 0.002564249327406287
2023-01-24 06:53:53.243416: step: 1620/527, loss: 0.005924270488321781
2023-01-24 06:53:54.280782: step: 1624/527, loss: 0.0025675161741673946
2023-01-24 06:53:55.349600: step: 1628/527, loss: 0.008801406249403954
2023-01-24 06:53:56.385594: step: 1632/527, loss: 0.0040179709903895855
2023-01-24 06:53:57.444103: step: 1636/527, loss: 0.003670003730803728
2023-01-24 06:53:58.493773: step: 1640/527, loss: 0.002694187220185995
2023-01-24 06:53:59.547984: step: 1644/527, loss: 0.0025451581459492445
2023-01-24 06:54:00.613128: step: 1648/527, loss: 0.007700404152274132
2023-01-24 06:54:01.662320: step: 1652/527, loss: 0.0026077507063746452
2023-01-24 06:54:02.705003: step: 1656/527, loss: 0.001982457237318158
2023-01-24 06:54:03.744658: step: 1660/527, loss: 0.005754484795033932
2023-01-24 06:54:04.798700: step: 1664/527, loss: 0.011494054459035397
2023-01-24 06:54:05.840319: step: 1668/527, loss: 0.0015631213318556547
2023-01-24 06:54:06.896697: step: 1672/527, loss: 0.0017745968652889132
2023-01-24 06:54:07.941917: step: 1676/527, loss: 0.008026758208870888
2023-01-24 06:54:08.999595: step: 1680/527, loss: 0.000972359033767134
2023-01-24 06:54:10.058726: step: 1684/527, loss: 0.005759639199823141
2023-01-24 06:54:11.109456: step: 1688/527, loss: 0.0030640270560979843
2023-01-24 06:54:12.152704: step: 1692/527, loss: 0.004121731501072645
2023-01-24 06:54:13.219488: step: 1696/527, loss: 0.00786714255809784
2023-01-24 06:54:14.267347: step: 1700/527, loss: 0.0027322557289153337
2023-01-24 06:54:15.329127: step: 1704/527, loss: 0.00435422221198678
2023-01-24 06:54:16.366929: step: 1708/527, loss: 0.004531675949692726
2023-01-24 06:54:17.418304: step: 1712/527, loss: 0.003216907847672701
2023-01-24 06:54:18.455414: step: 1716/527, loss: 0.0037044119089841843
2023-01-24 06:54:19.546598: step: 1720/527, loss: 0.00047670950880274177
2023-01-24 06:54:20.593705: step: 1724/527, loss: 0.0023558507673442364
2023-01-24 06:54:21.629447: step: 1728/527, loss: 0.0002946642925962806
2023-01-24 06:54:22.658217: step: 1732/527, loss: 0.0003873909590765834
2023-01-24 06:54:23.713515: step: 1736/527, loss: 0.0026340989861637354
2023-01-24 06:54:24.766430: step: 1740/527, loss: 0.00020999550179112703
2023-01-24 06:54:25.798763: step: 1744/527, loss: 0.0033446657471358776
2023-01-24 06:54:26.869768: step: 1748/527, loss: 0.003600065829232335
2023-01-24 06:54:27.931984: step: 1752/527, loss: 0.019987093284726143
2023-01-24 06:54:28.976950: step: 1756/527, loss: 0.0019899429753422737
2023-01-24 06:54:30.032157: step: 1760/527, loss: 0.01258633378893137
2023-01-24 06:54:31.093131: step: 1764/527, loss: 0.005223503801971674
2023-01-24 06:54:32.151104: step: 1768/527, loss: 0.005940215662121773
2023-01-24 06:54:33.192776: step: 1772/527, loss: 0.0013130708830431104
2023-01-24 06:54:34.234615: step: 1776/527, loss: 0.0008674848359078169
2023-01-24 06:54:35.302239: step: 1780/527, loss: 0.0004331193631514907
2023-01-24 06:54:36.360183: step: 1784/527, loss: 0.010653001256287098
2023-01-24 06:54:37.417653: step: 1788/527, loss: 0.005102533381432295
2023-01-24 06:54:38.467609: step: 1792/527, loss: 0.005774473771452904
2023-01-24 06:54:39.510279: step: 1796/527, loss: 0.000965410319622606
2023-01-24 06:54:40.557676: step: 1800/527, loss: 0.010976944118738174
2023-01-24 06:54:41.615941: step: 1804/527, loss: 0.011997640132904053
2023-01-24 06:54:42.663024: step: 1808/527, loss: 0.004539198242127895
2023-01-24 06:54:43.718125: step: 1812/527, loss: 0.002840488450601697
2023-01-24 06:54:44.772926: step: 1816/527, loss: 0.0035524554550647736
2023-01-24 06:54:45.822843: step: 1820/527, loss: 0.0060480451211333275
2023-01-24 06:54:46.882684: step: 1824/527, loss: 0.0031858596485108137
2023-01-24 06:54:47.928319: step: 1828/527, loss: 0.005063018295913935
2023-01-24 06:54:48.964198: step: 1832/527, loss: 0.0026580675039440393
2023-01-24 06:54:50.018788: step: 1836/527, loss: 0.0028464419301599264
2023-01-24 06:54:51.057463: step: 1840/527, loss: 0.021969856694340706
2023-01-24 06:54:52.098011: step: 1844/527, loss: 0.016569070518016815
2023-01-24 06:54:53.130535: step: 1848/527, loss: 0.00024191215925384313
2023-01-24 06:54:54.189763: step: 1852/527, loss: 0.0017284497153013945
2023-01-24 06:54:55.236323: step: 1856/527, loss: 0.00017486634897068143
2023-01-24 06:54:56.288411: step: 1860/527, loss: 0.0003898689174093306
2023-01-24 06:54:57.346411: step: 1864/527, loss: 0.003978152759373188
2023-01-24 06:54:58.394643: step: 1868/527, loss: 0.006101039703935385
2023-01-24 06:54:59.447051: step: 1872/527, loss: 0.00025843296316452324
2023-01-24 06:55:00.484468: step: 1876/527, loss: 0.001974471379071474
2023-01-24 06:55:01.524705: step: 1880/527, loss: 0.003903137519955635
2023-01-24 06:55:02.572714: step: 1884/527, loss: 0.003618246875703335
2023-01-24 06:55:03.620512: step: 1888/527, loss: 0.001595757552422583
2023-01-24 06:55:04.677424: step: 1892/527, loss: 0.005377558991312981
2023-01-24 06:55:05.727152: step: 1896/527, loss: 0.007170847151428461
2023-01-24 06:55:06.784548: step: 1900/527, loss: 0.008971121162176132
2023-01-24 06:55:07.827546: step: 1904/527, loss: 0.003187012393027544
2023-01-24 06:55:08.863845: step: 1908/527, loss: 0.018539823591709137
2023-01-24 06:55:09.899000: step: 1912/527, loss: 0.004290503915399313
2023-01-24 06:55:10.952076: step: 1916/527, loss: 0.0031834153924137354
2023-01-24 06:55:12.000271: step: 1920/527, loss: 0.004645330831408501
2023-01-24 06:55:13.064471: step: 1924/527, loss: 0.005643555428832769
2023-01-24 06:55:14.118162: step: 1928/527, loss: 0.003038665046915412
2023-01-24 06:55:15.179451: step: 1932/527, loss: 0.0023239408619701862
2023-01-24 06:55:16.223870: step: 1936/527, loss: 0.00981674063950777
2023-01-24 06:55:17.278852: step: 1940/527, loss: 0.004298528656363487
2023-01-24 06:55:18.325619: step: 1944/527, loss: 0.002680855803191662
2023-01-24 06:55:19.366313: step: 1948/527, loss: 0.005807960871607065
2023-01-24 06:55:20.419997: step: 1952/527, loss: 0.0013155624037608504
2023-01-24 06:55:21.456739: step: 1956/527, loss: 0.005734990816563368
2023-01-24 06:55:22.494545: step: 1960/527, loss: 0.00031206291168928146
2023-01-24 06:55:23.573335: step: 1964/527, loss: 0.0018663842929527164
2023-01-24 06:55:24.627892: step: 1968/527, loss: 0.0022151663433760405
2023-01-24 06:55:25.660230: step: 1972/527, loss: 0.00681777810677886
2023-01-24 06:55:26.712018: step: 1976/527, loss: 0.0012103980407118797
2023-01-24 06:55:27.761356: step: 1980/527, loss: 0.009966288693249226
2023-01-24 06:55:28.802236: step: 1984/527, loss: 0.0021340358071029186
2023-01-24 06:55:29.869424: step: 1988/527, loss: 0.0022295245435088873
2023-01-24 06:55:30.908279: step: 1992/527, loss: 0.002826056443154812
2023-01-24 06:55:31.950690: step: 1996/527, loss: 0.0019474141299724579
2023-01-24 06:55:32.996478: step: 2000/527, loss: 0.008456511422991753
2023-01-24 06:55:34.074858: step: 2004/527, loss: 0.0041686114855110645
2023-01-24 06:55:35.104242: step: 2008/527, loss: 0.0017365453531965613
2023-01-24 06:55:36.147460: step: 2012/527, loss: 9.989827231038362e-05
2023-01-24 06:55:37.203129: step: 2016/527, loss: 0.003863633843138814
2023-01-24 06:55:38.261410: step: 2020/527, loss: 0.001388088334351778
2023-01-24 06:55:39.300913: step: 2024/527, loss: 9.909391519613564e-05
2023-01-24 06:55:40.361036: step: 2028/527, loss: 0.015627026557922363
2023-01-24 06:55:41.435865: step: 2032/527, loss: 0.0035361130721867085
2023-01-24 06:55:42.463162: step: 2036/527, loss: 0.001129011856392026
2023-01-24 06:55:43.515549: step: 2040/527, loss: 0.0007500606006942689
2023-01-24 06:55:44.557440: step: 2044/527, loss: 0.007517545484006405
2023-01-24 06:55:45.592429: step: 2048/527, loss: 0.0008999849087558687
2023-01-24 06:55:46.628130: step: 2052/527, loss: 0.0019135841866955161
2023-01-24 06:55:47.673493: step: 2056/527, loss: 0.00427060155197978
2023-01-24 06:55:48.724031: step: 2060/527, loss: 0.00032574342912994325
2023-01-24 06:55:49.792953: step: 2064/527, loss: 0.008994975127279758
2023-01-24 06:55:50.846657: step: 2068/527, loss: 0.0009440046269446611
2023-01-24 06:55:51.889808: step: 2072/527, loss: 0.0038226398173719645
2023-01-24 06:55:52.942661: step: 2076/527, loss: 0.01862499676644802
2023-01-24 06:55:53.997891: step: 2080/527, loss: 0.015223889611661434
2023-01-24 06:55:55.044844: step: 2084/527, loss: 0.00031723108259029686
2023-01-24 06:55:56.088938: step: 2088/527, loss: 0.00397729454562068
2023-01-24 06:55:57.149133: step: 2092/527, loss: 0.003177271457388997
2023-01-24 06:55:58.200891: step: 2096/527, loss: 0.00018040844588540494
2023-01-24 06:55:59.243805: step: 2100/527, loss: 0.004522176459431648
2023-01-24 06:56:00.291267: step: 2104/527, loss: 0.0021267361007630825
2023-01-24 06:56:01.358379: step: 2108/527, loss: 0.004273226950317621
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3383812011313037, 'r': 0.3223289619884525, 'f1': 0.3301600835139251}, 'combined': 0.2432758510102606, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3721707681748068, 'r': 0.2916465474242577, 'f1': 0.32702467091405046}, 'combined': 0.20929578938499227, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34833285426846794, 'r': 0.32850365952832744, 'f1': 0.3381277901785715}, 'combined': 0.2491467927631579, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3706506420283257, 'r': 0.30332082512944725, 'f1': 0.33362260586165976}, 'combined': 0.21351846775146222, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.362725056264066, 'r': 0.3255577829466854, 'f1': 0.3431379032258064}, 'combined': 0.2528384550084889, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3864361517897335, 'r': 0.3142215564233749, 'f1': 0.3466073880306106}, 'combined': 0.2485109574559095, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6, 'r': 0.20689655172413793, 'f1': 0.3076923076923077}, 'combined': 0.20512820512820512, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36325359749028163, 'r': 0.3260321662483932, 'f1': 0.3436379032258064}, 'combined': 0.25320687606112047, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827405873011607, 'r': 0.313309979395116, 'f1': 0.344562453530268}, 'combined': 0.24704477800283367, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
******************************
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
2023-01-24 06:58:32.240998: step: 4/527, loss: 0.004833657760173082
2023-01-24 06:58:33.280677: step: 8/527, loss: 0.0011364136589691043
2023-01-24 06:58:34.335994: step: 12/527, loss: 0.013693591579794884
2023-01-24 06:58:35.385518: step: 16/527, loss: 0.0008982678409665823
2023-01-24 06:58:36.429160: step: 20/527, loss: 0.00028102987562306225
2023-01-24 06:58:37.469288: step: 24/527, loss: 0.0021157904993742704
2023-01-24 06:58:38.517594: step: 28/527, loss: 0.0020598529372364283
2023-01-24 06:58:39.547718: step: 32/527, loss: 0.005269910208880901
2023-01-24 06:58:40.605328: step: 36/527, loss: 0.03047555685043335
2023-01-24 06:58:41.633072: step: 40/527, loss: 0.008462157100439072
2023-01-24 06:58:42.659017: step: 44/527, loss: 0.0009237699559889734
2023-01-24 06:58:43.693714: step: 48/527, loss: 0.014638824388384819
2023-01-24 06:58:44.746158: step: 52/527, loss: 0.0074201286770403385
2023-01-24 06:58:45.792456: step: 56/527, loss: 0.007807761896401644
2023-01-24 06:58:46.849334: step: 60/527, loss: 0.009378915652632713
2023-01-24 06:58:47.902578: step: 64/527, loss: 0.0028345270548015833
2023-01-24 06:58:48.954186: step: 68/527, loss: 0.004703216720372438
2023-01-24 06:58:50.013431: step: 72/527, loss: 0.010960305109620094
2023-01-24 06:58:51.066542: step: 76/527, loss: 0.007687015924602747
2023-01-24 06:58:52.116869: step: 80/527, loss: 0.001322070718742907
2023-01-24 06:58:53.164316: step: 84/527, loss: 0.0022883673664182425
2023-01-24 06:58:54.220818: step: 88/527, loss: 0.004564776550978422
2023-01-24 06:58:55.267308: step: 92/527, loss: 0.0018911577062681317
2023-01-24 06:58:56.301168: step: 96/527, loss: 0.019945869222283363
2023-01-24 06:58:57.349319: step: 100/527, loss: 0.0005262373015284538
2023-01-24 06:58:58.390537: step: 104/527, loss: 0.002583642490208149
2023-01-24 06:58:59.443150: step: 108/527, loss: 0.0010474671144038439
2023-01-24 06:59:00.493657: step: 112/527, loss: 1.6051326383603737e-05
2023-01-24 06:59:01.539881: step: 116/527, loss: 0.0030734159518033266
2023-01-24 06:59:02.571919: step: 120/527, loss: 0.00039913030923344195
2023-01-24 06:59:03.611282: step: 124/527, loss: 0.00012458326818887144
2023-01-24 06:59:04.653788: step: 128/527, loss: 0.007980993948876858
2023-01-24 06:59:05.703015: step: 132/527, loss: 0.0007757146959193051
2023-01-24 06:59:06.750970: step: 136/527, loss: 0.0032367203384637833
2023-01-24 06:59:07.807204: step: 140/527, loss: 0.008006197400391102
2023-01-24 06:59:08.866027: step: 144/527, loss: 0.0037750983610749245
2023-01-24 06:59:09.921737: step: 148/527, loss: 0.004418736323714256
2023-01-24 06:59:10.961604: step: 152/527, loss: 0.0016289552440866828
2023-01-24 06:59:12.003829: step: 156/527, loss: 0.019678598269820213
2023-01-24 06:59:13.045816: step: 160/527, loss: 0.0011051876936107874
2023-01-24 06:59:14.089849: step: 164/527, loss: 0.0004329594084993005
2023-01-24 06:59:15.146589: step: 168/527, loss: 0.00012706460256595165
2023-01-24 06:59:16.198030: step: 172/527, loss: 0.01562930829823017
2023-01-24 06:59:17.243886: step: 176/527, loss: 0.004352135583758354
2023-01-24 06:59:18.297051: step: 180/527, loss: 0.003814413445070386
2023-01-24 06:59:19.354674: step: 184/527, loss: 0.00027251176652498543
2023-01-24 06:59:20.417969: step: 188/527, loss: 0.0033607804216444492
2023-01-24 06:59:21.468790: step: 192/527, loss: 0.007782275322824717
2023-01-24 06:59:22.525685: step: 196/527, loss: 0.003576585790142417
2023-01-24 06:59:23.584047: step: 200/527, loss: 2.0078901741271693e-07
2023-01-24 06:59:24.640077: step: 204/527, loss: 0.002374565228819847
2023-01-24 06:59:25.694837: step: 208/527, loss: 0.0038562549743801355
2023-01-24 06:59:26.732643: step: 212/527, loss: 0.0022288477048277855
2023-01-24 06:59:27.776998: step: 216/527, loss: 0.009281554259359837
2023-01-24 06:59:28.831932: step: 220/527, loss: 0.00013035137089900672
2023-01-24 06:59:29.892807: step: 224/527, loss: 3.689919685712084e-05
2023-01-24 06:59:30.933251: step: 228/527, loss: 0.0007885729428380728
2023-01-24 06:59:31.978866: step: 232/527, loss: 0.0016048562247306108
2023-01-24 06:59:33.019951: step: 236/527, loss: 0.02389618195593357
2023-01-24 06:59:34.082344: step: 240/527, loss: 0.007483481429517269
2023-01-24 06:59:35.122395: step: 244/527, loss: 0.010217053815722466
2023-01-24 06:59:36.170423: step: 248/527, loss: 0.00013255391968414187
2023-01-24 06:59:37.231166: step: 252/527, loss: 0.005191694479435682
2023-01-24 06:59:38.276265: step: 256/527, loss: 1.3778627362626139e-05
2023-01-24 06:59:39.322711: step: 260/527, loss: 0.00015251721197273582
2023-01-24 06:59:40.379220: step: 264/527, loss: 0.027187911793589592
2023-01-24 06:59:41.413902: step: 268/527, loss: 0.007595769129693508
2023-01-24 06:59:42.473099: step: 272/527, loss: 0.002322762506082654
2023-01-24 06:59:43.537723: step: 276/527, loss: 0.002794540487229824
2023-01-24 06:59:44.594655: step: 280/527, loss: 0.007562355138361454
2023-01-24 06:59:45.633908: step: 284/527, loss: 0.00033715058816596866
2023-01-24 06:59:46.677585: step: 288/527, loss: 0.0005360583891160786
2023-01-24 06:59:47.712720: step: 292/527, loss: 0.008844222873449326
2023-01-24 06:59:48.766668: step: 296/527, loss: 0.0033350863959640265
2023-01-24 06:59:49.816753: step: 300/527, loss: 0.003205646062269807
2023-01-24 06:59:50.868152: step: 304/527, loss: 0.022825386375188828
2023-01-24 06:59:51.916696: step: 308/527, loss: 0.0027564482297748327
2023-01-24 06:59:52.980885: step: 312/527, loss: 0.011012528091669083
2023-01-24 06:59:54.026257: step: 316/527, loss: 0.000799546658527106
2023-01-24 06:59:55.073984: step: 320/527, loss: 0.0071962978690862656
2023-01-24 06:59:56.124563: step: 324/527, loss: 0.0036637221928685904
2023-01-24 06:59:57.169231: step: 328/527, loss: 0.003913890570402145
2023-01-24 06:59:58.205447: step: 332/527, loss: 0.004625939764082432
2023-01-24 06:59:59.252117: step: 336/527, loss: 0.001403993577696383
2023-01-24 07:00:00.304889: step: 340/527, loss: 0.0035943130496889353
2023-01-24 07:00:01.374448: step: 344/527, loss: 0.002903914311900735
2023-01-24 07:00:02.422159: step: 348/527, loss: 0.018021633848547935
2023-01-24 07:00:03.479537: step: 352/527, loss: 0.002456091344356537
2023-01-24 07:00:04.543903: step: 356/527, loss: 0.017133845016360283
2023-01-24 07:00:05.586671: step: 360/527, loss: 0.0025656798388808966
2023-01-24 07:00:06.645787: step: 364/527, loss: 0.005487536080181599
2023-01-24 07:00:07.696825: step: 368/527, loss: 0.0010569763835519552
2023-01-24 07:00:08.737482: step: 372/527, loss: 0.01532845851033926
2023-01-24 07:00:09.776077: step: 376/527, loss: 0.004308891948312521
2023-01-24 07:00:10.812915: step: 380/527, loss: 0.002837874460965395
2023-01-24 07:00:11.873691: step: 384/527, loss: 0.00013713547377847135
2023-01-24 07:00:12.920135: step: 388/527, loss: 0.012571699917316437
2023-01-24 07:00:13.997467: step: 392/527, loss: 0.002484510187059641
2023-01-24 07:00:15.043163: step: 396/527, loss: 0.0013878004392609
2023-01-24 07:00:16.092219: step: 400/527, loss: 0.0014320421032607555
2023-01-24 07:00:17.130630: step: 404/527, loss: 0.002912610536441207
2023-01-24 07:00:18.184222: step: 408/527, loss: 0.0035548831801861525
2023-01-24 07:00:19.250703: step: 412/527, loss: 0.0009113316191360354
2023-01-24 07:00:20.296453: step: 416/527, loss: 0.004987087566405535
2023-01-24 07:00:21.338846: step: 420/527, loss: 0.004824623465538025
2023-01-24 07:00:22.400350: step: 424/527, loss: 0.0003809690533671528
2023-01-24 07:00:23.438587: step: 428/527, loss: 5.815789336338639e-05
2023-01-24 07:00:24.487002: step: 432/527, loss: 0.002271481789648533
2023-01-24 07:00:25.547111: step: 436/527, loss: 0.003358307993039489
2023-01-24 07:00:26.595423: step: 440/527, loss: 0.015740172937512398
2023-01-24 07:00:27.648763: step: 444/527, loss: 0.0017715157009661198
2023-01-24 07:00:28.708725: step: 448/527, loss: 0.0017089046305045485
2023-01-24 07:00:29.765812: step: 452/527, loss: 0.0003556696465238929
2023-01-24 07:00:30.832094: step: 456/527, loss: 0.003091268241405487
2023-01-24 07:00:31.867226: step: 460/527, loss: 0.0024387831799685955
2023-01-24 07:00:32.910102: step: 464/527, loss: 0.004320340696722269
2023-01-24 07:00:33.964975: step: 468/527, loss: 0.004508669953793287
2023-01-24 07:00:35.010748: step: 472/527, loss: 0.0001858569448813796
2023-01-24 07:00:36.056362: step: 476/527, loss: 0.00457730982452631
2023-01-24 07:00:37.096445: step: 480/527, loss: 0.001630950951948762
2023-01-24 07:00:38.145977: step: 484/527, loss: 0.0008800184587016702
2023-01-24 07:00:39.191260: step: 488/527, loss: 0.0023561110720038414
2023-01-24 07:00:40.232924: step: 492/527, loss: 0.00024463661247864366
2023-01-24 07:00:41.283115: step: 496/527, loss: 0.0067946636117994785
2023-01-24 07:00:42.317466: step: 500/527, loss: 0.004996356088668108
2023-01-24 07:00:43.362511: step: 504/527, loss: 0.0007243560976348817
2023-01-24 07:00:44.404992: step: 508/527, loss: 0.00022676971275359392
2023-01-24 07:00:45.451392: step: 512/527, loss: 0.00014773133443668485
2023-01-24 07:00:46.507676: step: 516/527, loss: 0.005032065324485302
2023-01-24 07:00:47.543610: step: 520/527, loss: 0.00022982760856393725
2023-01-24 07:00:48.589823: step: 524/527, loss: 0.0025566464755684137
2023-01-24 07:00:49.646001: step: 528/527, loss: 0.00025172450114041567
2023-01-24 07:00:50.706153: step: 532/527, loss: 0.0019041320774704218
2023-01-24 07:00:51.752451: step: 536/527, loss: 0.017800897359848022
2023-01-24 07:00:52.823215: step: 540/527, loss: 0.004606978967785835
2023-01-24 07:00:53.880978: step: 544/527, loss: 0.0055726878345012665
2023-01-24 07:00:54.916511: step: 548/527, loss: 0.0058105806820094585
2023-01-24 07:00:55.966278: step: 552/527, loss: 0.003775089280679822
2023-01-24 07:00:57.007927: step: 556/527, loss: 0.0029681515879929066
2023-01-24 07:00:58.057765: step: 560/527, loss: 0.00196833279915154
2023-01-24 07:00:59.113367: step: 564/527, loss: 0.00226177042350173
2023-01-24 07:01:00.182866: step: 568/527, loss: 0.0015703982207924128
2023-01-24 07:01:01.225374: step: 572/527, loss: 0.006242364179342985
2023-01-24 07:01:02.278584: step: 576/527, loss: 0.002695418195798993
2023-01-24 07:01:03.321924: step: 580/527, loss: 0.0025354200042784214
2023-01-24 07:01:04.366945: step: 584/527, loss: 0.0
2023-01-24 07:01:05.415518: step: 588/527, loss: 0.005481021478772163
2023-01-24 07:01:06.461168: step: 592/527, loss: 0.0020466595888137817
2023-01-24 07:01:07.521928: step: 596/527, loss: 9.231808689946774e-06
2023-01-24 07:01:08.578815: step: 600/527, loss: 0.005630808882415295
2023-01-24 07:01:09.632016: step: 604/527, loss: 0.012374069541692734
2023-01-24 07:01:10.676446: step: 608/527, loss: 0.002124031074345112
2023-01-24 07:01:11.731723: step: 612/527, loss: 0.003565231105312705
2023-01-24 07:01:12.797039: step: 616/527, loss: 0.0006387982866726816
2023-01-24 07:01:13.849911: step: 620/527, loss: 0.001555423135869205
2023-01-24 07:01:14.899630: step: 624/527, loss: 0.01116778701543808
2023-01-24 07:01:15.964408: step: 628/527, loss: 0.0018999361200258136
2023-01-24 07:01:16.994116: step: 632/527, loss: 0.0003884321195073426
2023-01-24 07:01:18.043886: step: 636/527, loss: 0.005087822675704956
2023-01-24 07:01:19.089663: step: 640/527, loss: 0.003662888426333666
2023-01-24 07:01:20.131034: step: 644/527, loss: 0.00792395044118166
2023-01-24 07:01:21.170523: step: 648/527, loss: 0.00112702208571136
2023-01-24 07:01:22.234811: step: 652/527, loss: 0.002395574701949954
2023-01-24 07:01:23.283817: step: 656/527, loss: 0.01734435185790062
2023-01-24 07:01:24.339348: step: 660/527, loss: 0.006966793909668922
2023-01-24 07:01:25.380689: step: 664/527, loss: 0.0061254785396158695
2023-01-24 07:01:26.435266: step: 668/527, loss: 0.0013585977721959352
2023-01-24 07:01:27.491280: step: 672/527, loss: 0.012014559470117092
2023-01-24 07:01:28.525341: step: 676/527, loss: 0.0003197441983502358
2023-01-24 07:01:29.579974: step: 680/527, loss: 0.004277748055756092
2023-01-24 07:01:30.629549: step: 684/527, loss: 0.0005192296812310815
2023-01-24 07:01:31.682221: step: 688/527, loss: 0.0035792121198028326
2023-01-24 07:01:32.734525: step: 692/527, loss: 0.0015736257191747427
2023-01-24 07:01:33.784331: step: 696/527, loss: 0.0007043908117339015
2023-01-24 07:01:34.833070: step: 700/527, loss: 0.004315359517931938
2023-01-24 07:01:35.902374: step: 704/527, loss: 0.0061894189566373825
2023-01-24 07:01:36.956986: step: 708/527, loss: 0.007439267821609974
2023-01-24 07:01:37.998318: step: 712/527, loss: 0.004487603437155485
2023-01-24 07:01:39.042607: step: 716/527, loss: 0.005449655000120401
2023-01-24 07:01:40.087599: step: 720/527, loss: 0.0030286421533674
2023-01-24 07:01:41.154233: step: 724/527, loss: 0.00014306108641903847
2023-01-24 07:01:42.190722: step: 728/527, loss: 0.0013849989045411348
2023-01-24 07:01:43.245863: step: 732/527, loss: 7.165545684983954e-05
2023-01-24 07:01:44.288081: step: 736/527, loss: 0.0041424003429710865
2023-01-24 07:01:45.329969: step: 740/527, loss: 0.003762218402698636
2023-01-24 07:01:46.379347: step: 744/527, loss: 0.0012876322725787759
2023-01-24 07:01:47.420708: step: 748/527, loss: 0.002330939983949065
2023-01-24 07:01:48.469619: step: 752/527, loss: 0.01054556854069233
2023-01-24 07:01:49.530775: step: 756/527, loss: 0.0018435473321005702
2023-01-24 07:01:50.573554: step: 760/527, loss: 0.002357003279030323
2023-01-24 07:01:51.626229: step: 764/527, loss: 0.0005506074521690607
2023-01-24 07:01:52.676058: step: 768/527, loss: 0.004188058897852898
2023-01-24 07:01:53.721926: step: 772/527, loss: 0.0008292871643789113
2023-01-24 07:01:54.773242: step: 776/527, loss: 0.0024797916412353516
2023-01-24 07:01:55.819821: step: 780/527, loss: 0.004266451112926006
2023-01-24 07:01:56.860868: step: 784/527, loss: 0.06176600977778435
2023-01-24 07:01:57.911243: step: 788/527, loss: 0.0036624919157475233
2023-01-24 07:01:58.956628: step: 792/527, loss: 0.004840458743274212
2023-01-24 07:02:00.014358: step: 796/527, loss: 0.0023256016429513693
2023-01-24 07:02:01.078565: step: 800/527, loss: 0.00648619094863534
2023-01-24 07:02:02.145784: step: 804/527, loss: 0.0068627409636974335
2023-01-24 07:02:03.204417: step: 808/527, loss: 0.001807958702556789
2023-01-24 07:02:04.243622: step: 812/527, loss: 0.0010146456770598888
2023-01-24 07:02:05.313563: step: 816/527, loss: 0.011444950476288795
2023-01-24 07:02:06.371101: step: 820/527, loss: 0.004351429175585508
2023-01-24 07:02:07.439531: step: 824/527, loss: 0.003175140591338277
2023-01-24 07:02:08.501477: step: 828/527, loss: 0.002956350101158023
2023-01-24 07:02:09.556602: step: 832/527, loss: 0.001291818916797638
2023-01-24 07:02:10.616316: step: 836/527, loss: 0.005952575244009495
2023-01-24 07:02:11.687045: step: 840/527, loss: 0.002884318819269538
2023-01-24 07:02:12.771366: step: 844/527, loss: 0.02117699384689331
2023-01-24 07:02:13.813782: step: 848/527, loss: 0.009070572443306446
2023-01-24 07:02:14.863851: step: 852/527, loss: 0.002150001935660839
2023-01-24 07:02:15.917561: step: 856/527, loss: 0.0005330175627022982
2023-01-24 07:02:16.954787: step: 860/527, loss: 0.0032782384660094976
2023-01-24 07:02:18.018930: step: 864/527, loss: 0.00023411009169649333
2023-01-24 07:02:19.058650: step: 868/527, loss: 0.0014934978680685163
2023-01-24 07:02:20.116570: step: 872/527, loss: 0.0005229530506767333
2023-01-24 07:02:21.175358: step: 876/527, loss: 1.0392669537395705e-05
2023-01-24 07:02:22.208635: step: 880/527, loss: 0.0076842415146529675
2023-01-24 07:02:23.259370: step: 884/527, loss: 0.001741165528073907
2023-01-24 07:02:24.302713: step: 888/527, loss: 0.0063182697631418705
2023-01-24 07:02:25.359247: step: 892/527, loss: 0.013243038207292557
2023-01-24 07:02:26.422649: step: 896/527, loss: 0.029148589819669724
2023-01-24 07:02:27.459072: step: 900/527, loss: 0.005447585601359606
2023-01-24 07:02:28.500956: step: 904/527, loss: 0.01837785914540291
2023-01-24 07:02:29.546490: step: 908/527, loss: 0.0020566792227327824
2023-01-24 07:02:30.585815: step: 912/527, loss: 0.003916104324162006
2023-01-24 07:02:31.655194: step: 916/527, loss: 0.002611628035083413
2023-01-24 07:02:32.694120: step: 920/527, loss: 0.0010981709929183125
2023-01-24 07:02:33.760397: step: 924/527, loss: 0.00297788018360734
2023-01-24 07:02:34.811946: step: 928/527, loss: 0.0043276394717395306
2023-01-24 07:02:35.861615: step: 932/527, loss: 0.0031342708971351385
2023-01-24 07:02:36.912382: step: 936/527, loss: 0.0028929393738508224
2023-01-24 07:02:37.962671: step: 940/527, loss: 0.004579306114464998
2023-01-24 07:02:39.029953: step: 944/527, loss: 0.0030227333772927523
2023-01-24 07:02:40.087886: step: 948/527, loss: 0.004377361387014389
2023-01-24 07:02:41.129385: step: 952/527, loss: 0.010050162672996521
2023-01-24 07:02:42.184255: step: 956/527, loss: 0.00290341186337173
2023-01-24 07:02:43.238222: step: 960/527, loss: 0.00043574688606895506
2023-01-24 07:02:44.288908: step: 964/527, loss: 0.018408535048365593
2023-01-24 07:02:45.354362: step: 968/527, loss: 0.022258492186665535
2023-01-24 07:02:46.393236: step: 972/527, loss: 0.007590233348309994
2023-01-24 07:02:47.447404: step: 976/527, loss: 0.007303510792553425
2023-01-24 07:02:48.518374: step: 980/527, loss: 0.003910573199391365
2023-01-24 07:02:49.573020: step: 984/527, loss: 0.00604192353785038
2023-01-24 07:02:50.607045: step: 988/527, loss: 0.0021004544105380774
2023-01-24 07:02:51.665304: step: 992/527, loss: 0.004176327958703041
2023-01-24 07:02:52.732615: step: 996/527, loss: 0.005303438752889633
2023-01-24 07:02:53.781366: step: 1000/527, loss: 0.03525322303175926
2023-01-24 07:02:54.844458: step: 1004/527, loss: 0.005037392023950815
2023-01-24 07:02:55.898475: step: 1008/527, loss: 0.017468789592385292
2023-01-24 07:02:56.950639: step: 1012/527, loss: 0.004671341739594936
2023-01-24 07:02:58.007096: step: 1016/527, loss: 0.004056756384670734
2023-01-24 07:02:59.038227: step: 1020/527, loss: 0.00670308293774724
2023-01-24 07:03:00.079512: step: 1024/527, loss: 0.009855917654931545
2023-01-24 07:03:01.146933: step: 1028/527, loss: 0.0028353857342153788
2023-01-24 07:03:02.189139: step: 1032/527, loss: 0.0053049251437187195
2023-01-24 07:03:03.227828: step: 1036/527, loss: 0.0013734814710915089
2023-01-24 07:03:04.258159: step: 1040/527, loss: 0.008751742541790009
2023-01-24 07:03:05.303244: step: 1044/527, loss: 0.012873737141489983
2023-01-24 07:03:06.368224: step: 1048/527, loss: 0.0014865464763715863
2023-01-24 07:03:07.427178: step: 1052/527, loss: 0.0015398594550788403
2023-01-24 07:03:08.484086: step: 1056/527, loss: 0.0001848602551035583
2023-01-24 07:03:09.529462: step: 1060/527, loss: 0.0016110041178762913
2023-01-24 07:03:10.579516: step: 1064/527, loss: 0.005330005194991827
2023-01-24 07:03:11.629755: step: 1068/527, loss: 0.002192337065935135
2023-01-24 07:03:12.663794: step: 1072/527, loss: 0.0031953558791428804
2023-01-24 07:03:13.706984: step: 1076/527, loss: 0.002988615073263645
2023-01-24 07:03:14.754594: step: 1080/527, loss: 0.001418066443875432
2023-01-24 07:03:15.779334: step: 1084/527, loss: 0.0003354892542120069
2023-01-24 07:03:16.826172: step: 1088/527, loss: 0.0049008517526090145
2023-01-24 07:03:17.899808: step: 1092/527, loss: 0.004286483861505985
2023-01-24 07:03:18.964719: step: 1096/527, loss: 0.0003213726740796119
2023-01-24 07:03:20.025265: step: 1100/527, loss: 0.00027230611885897815
2023-01-24 07:03:21.084957: step: 1104/527, loss: 0.0024362134281545877
2023-01-24 07:03:22.148066: step: 1108/527, loss: 0.0031442472245544195
2023-01-24 07:03:23.193279: step: 1112/527, loss: 0.00042018588283099234
2023-01-24 07:03:24.242784: step: 1116/527, loss: 0.00230475515127182
2023-01-24 07:03:25.295415: step: 1120/527, loss: 0.0073813265189528465
2023-01-24 07:03:26.340901: step: 1124/527, loss: 0.0018790271133184433
2023-01-24 07:03:27.415463: step: 1128/527, loss: 0.009314043447375298
2023-01-24 07:03:28.459790: step: 1132/527, loss: 0.003457744373008609
2023-01-24 07:03:29.507010: step: 1136/527, loss: 0.00036238873144611716
2023-01-24 07:03:30.549393: step: 1140/527, loss: 0.004901781212538481
2023-01-24 07:03:31.635214: step: 1144/527, loss: 0.00927270483225584
2023-01-24 07:03:32.673616: step: 1148/527, loss: 0.009323596023023129
2023-01-24 07:03:33.721318: step: 1152/527, loss: 0.00012607510143425316
2023-01-24 07:03:34.777689: step: 1156/527, loss: 0.003918622620403767
2023-01-24 07:03:35.813961: step: 1160/527, loss: 0.0005425811978057027
2023-01-24 07:03:36.870654: step: 1164/527, loss: 0.0023384541273117065
2023-01-24 07:03:37.944071: step: 1168/527, loss: 0.004741017706692219
2023-01-24 07:03:38.986737: step: 1172/527, loss: 0.0015756604261696339
2023-01-24 07:03:40.036432: step: 1176/527, loss: 0.0015137273585423827
2023-01-24 07:03:41.086260: step: 1180/527, loss: 0.00488596735522151
2023-01-24 07:03:42.139260: step: 1184/527, loss: 0.005109952297061682
2023-01-24 07:03:43.200565: step: 1188/527, loss: 0.01632414013147354
2023-01-24 07:03:44.255481: step: 1192/527, loss: 0.007905122824013233
2023-01-24 07:03:45.308580: step: 1196/527, loss: 0.0050056991167366505
2023-01-24 07:03:46.363210: step: 1200/527, loss: 0.003703346010297537
2023-01-24 07:03:47.418937: step: 1204/527, loss: 0.02175176329910755
2023-01-24 07:03:48.468808: step: 1208/527, loss: 0.007691751234233379
2023-01-24 07:03:49.551997: step: 1212/527, loss: 0.00457302201539278
2023-01-24 07:03:50.598315: step: 1216/527, loss: 0.004537994973361492
2023-01-24 07:03:51.651277: step: 1220/527, loss: 3.433651363593526e-05
2023-01-24 07:03:52.696342: step: 1224/527, loss: 0.00292415963485837
2023-01-24 07:03:53.741327: step: 1228/527, loss: 0.01906370185315609
2023-01-24 07:03:54.799042: step: 1232/527, loss: 0.011376405134797096
2023-01-24 07:03:55.847456: step: 1236/527, loss: 0.0011853516334667802
2023-01-24 07:03:56.901433: step: 1240/527, loss: 0.028676720336079597
2023-01-24 07:03:57.951332: step: 1244/527, loss: 0.0014396763872355223
2023-01-24 07:03:59.003052: step: 1248/527, loss: 0.012249977327883244
2023-01-24 07:04:00.052918: step: 1252/527, loss: 0.00428337138146162
2023-01-24 07:04:01.112509: step: 1256/527, loss: 0.015964098274707794
2023-01-24 07:04:02.162990: step: 1260/527, loss: 0.01603492721915245
2023-01-24 07:04:03.214729: step: 1264/527, loss: 0.003757587866857648
2023-01-24 07:04:04.269381: step: 1268/527, loss: 0.004188335966318846
2023-01-24 07:04:05.316745: step: 1272/527, loss: 0.0010117783676832914
2023-01-24 07:04:06.386690: step: 1276/527, loss: 0.002257630694657564
2023-01-24 07:04:07.447828: step: 1280/527, loss: 0.0014187361812219024
2023-01-24 07:04:08.534343: step: 1284/527, loss: 0.005581737495958805
2023-01-24 07:04:09.596035: step: 1288/527, loss: 0.0009192198631353676
2023-01-24 07:04:10.647814: step: 1292/527, loss: 0.0068116397596895695
2023-01-24 07:04:11.714250: step: 1296/527, loss: 0.0033853058703243732
2023-01-24 07:04:12.777157: step: 1300/527, loss: 0.007141647394746542
2023-01-24 07:04:13.835282: step: 1304/527, loss: 0.0015104282647371292
2023-01-24 07:04:14.879073: step: 1308/527, loss: 8.462648838758469e-05
2023-01-24 07:04:15.948878: step: 1312/527, loss: 0.017198268324136734
2023-01-24 07:04:16.999563: step: 1316/527, loss: 4.7995759814511985e-05
2023-01-24 07:04:18.048497: step: 1320/527, loss: 0.00940526183694601
2023-01-24 07:04:19.118999: step: 1324/527, loss: 0.0032857030164450407
2023-01-24 07:04:20.208911: step: 1328/527, loss: 0.004373821895569563
2023-01-24 07:04:21.291533: step: 1332/527, loss: 0.0030779403168708086
2023-01-24 07:04:22.341778: step: 1336/527, loss: 0.003492555348202586
2023-01-24 07:04:23.383169: step: 1340/527, loss: 0.0011717055458575487
2023-01-24 07:04:24.438275: step: 1344/527, loss: 0.008130822330713272
2023-01-24 07:04:25.483533: step: 1348/527, loss: 0.009108836762607098
2023-01-24 07:04:26.534239: step: 1352/527, loss: 0.0008072527125477791
2023-01-24 07:04:27.582144: step: 1356/527, loss: 0.014012214727699757
2023-01-24 07:04:28.644712: step: 1360/527, loss: 0.011362689547240734
2023-01-24 07:04:29.696223: step: 1364/527, loss: 0.003630140097811818
2023-01-24 07:04:30.730328: step: 1368/527, loss: 0.0042950985953211784
2023-01-24 07:04:31.790942: step: 1372/527, loss: 0.0006355448858812451
2023-01-24 07:04:32.829513: step: 1376/527, loss: 0.0014422856038436294
2023-01-24 07:04:33.872039: step: 1380/527, loss: 0.0030392364133149385
2023-01-24 07:04:34.936285: step: 1384/527, loss: 0.004173503257334232
2023-01-24 07:04:35.999355: step: 1388/527, loss: 0.004709865897893906
2023-01-24 07:04:37.049038: step: 1392/527, loss: 0.0019907085224986076
2023-01-24 07:04:38.108695: step: 1396/527, loss: 0.005064527038484812
2023-01-24 07:04:39.164743: step: 1400/527, loss: 0.0015091727254912257
2023-01-24 07:04:40.212864: step: 1404/527, loss: 0.0030564062763005495
2023-01-24 07:04:41.254972: step: 1408/527, loss: 0.0012647153344005346
2023-01-24 07:04:42.293725: step: 1412/527, loss: 0.00022612253087572753
2023-01-24 07:04:43.340558: step: 1416/527, loss: 0.004740377888083458
2023-01-24 07:04:44.384062: step: 1420/527, loss: 0.0037263089325278997
2023-01-24 07:04:45.443014: step: 1424/527, loss: 0.0009227913105860353
2023-01-24 07:04:46.499436: step: 1428/527, loss: 0.006331590469926596
2023-01-24 07:04:47.542894: step: 1432/527, loss: 0.02578769437968731
2023-01-24 07:04:48.596160: step: 1436/527, loss: 0.00416067149490118
2023-01-24 07:04:49.657152: step: 1440/527, loss: 0.0
2023-01-24 07:04:50.689556: step: 1444/527, loss: 0.003131650621071458
2023-01-24 07:04:51.747239: step: 1448/527, loss: 0.042015351355075836
2023-01-24 07:04:52.793654: step: 1452/527, loss: 0.04288274049758911
2023-01-24 07:04:53.846758: step: 1456/527, loss: 0.0007513285963796079
2023-01-24 07:04:54.902451: step: 1460/527, loss: 0.004160204436630011
2023-01-24 07:04:55.956428: step: 1464/527, loss: 0.01646789163351059
2023-01-24 07:04:57.012027: step: 1468/527, loss: 0.006657102610915899
2023-01-24 07:04:58.065725: step: 1472/527, loss: 0.0161454938352108
2023-01-24 07:04:59.135344: step: 1476/527, loss: 0.0019072722643613815
2023-01-24 07:05:00.184980: step: 1480/527, loss: 0.0007143720868043602
2023-01-24 07:05:01.252554: step: 1484/527, loss: 0.027458615601062775
2023-01-24 07:05:02.332473: step: 1488/527, loss: 0.0007634982466697693
2023-01-24 07:05:03.374124: step: 1492/527, loss: 0.007612764835357666
2023-01-24 07:05:04.407295: step: 1496/527, loss: 0.010697748512029648
2023-01-24 07:05:05.462148: step: 1500/527, loss: 0.004767022095620632
2023-01-24 07:05:06.499644: step: 1504/527, loss: 0.003955787979066372
2023-01-24 07:05:07.540029: step: 1508/527, loss: 0.0014415780315175653
2023-01-24 07:05:08.594322: step: 1512/527, loss: 0.0030549075454473495
2023-01-24 07:05:09.640430: step: 1516/527, loss: 0.002484110416844487
2023-01-24 07:05:10.694996: step: 1520/527, loss: 0.0045503368601202965
2023-01-24 07:05:11.749927: step: 1524/527, loss: 0.008399713784456253
2023-01-24 07:05:12.788989: step: 1528/527, loss: 0.0025790345389395952
2023-01-24 07:05:13.826576: step: 1532/527, loss: 0.0015924338949844241
2023-01-24 07:05:14.876831: step: 1536/527, loss: 0.000288614712189883
2023-01-24 07:05:15.930310: step: 1540/527, loss: 0.0005859467783011496
2023-01-24 07:05:16.983880: step: 1544/527, loss: 0.013887022621929646
2023-01-24 07:05:18.036209: step: 1548/527, loss: 0.0018600106704980135
2023-01-24 07:05:19.087311: step: 1552/527, loss: 0.008629896678030491
2023-01-24 07:05:20.141949: step: 1556/527, loss: 0.0015319508966058493
2023-01-24 07:05:21.187477: step: 1560/527, loss: 0.004325922578573227
2023-01-24 07:05:22.232380: step: 1564/527, loss: 0.0072137825191020966
2023-01-24 07:05:23.278927: step: 1568/527, loss: 0.005579197313636541
2023-01-24 07:05:24.325292: step: 1572/527, loss: 0.000697479525115341
2023-01-24 07:05:25.374391: step: 1576/527, loss: 0.001068268553353846
2023-01-24 07:05:26.418982: step: 1580/527, loss: 0.005155193153768778
2023-01-24 07:05:27.453123: step: 1584/527, loss: 0.001507272943854332
2023-01-24 07:05:28.509567: step: 1588/527, loss: 0.004740849602967501
2023-01-24 07:05:29.559329: step: 1592/527, loss: 0.008445720188319683
2023-01-24 07:05:30.610235: step: 1596/527, loss: 0.001141395652666688
2023-01-24 07:05:31.645051: step: 1600/527, loss: 0.0009254674077965319
2023-01-24 07:05:32.702023: step: 1604/527, loss: 0.004802384413778782
2023-01-24 07:05:33.739861: step: 1608/527, loss: 0.0007032358553260565
2023-01-24 07:05:34.771845: step: 1612/527, loss: 0.00888037495315075
2023-01-24 07:05:35.817692: step: 1616/527, loss: 0.003867973340675235
2023-01-24 07:05:36.862503: step: 1620/527, loss: 0.001151920179836452
2023-01-24 07:05:37.916665: step: 1624/527, loss: 0.0069147152826189995
2023-01-24 07:05:38.961603: step: 1628/527, loss: 0.00042818597285076976
2023-01-24 07:05:40.013047: step: 1632/527, loss: 0.000888426264282316
2023-01-24 07:05:41.071500: step: 1636/527, loss: 0.00192177458666265
2023-01-24 07:05:42.125273: step: 1640/527, loss: 0.005601990036666393
2023-01-24 07:05:43.164820: step: 1644/527, loss: 0.01739492267370224
2023-01-24 07:05:44.221455: step: 1648/527, loss: 0.0011741763446480036
2023-01-24 07:05:45.271110: step: 1652/527, loss: 0.03272141516208649
2023-01-24 07:05:46.315469: step: 1656/527, loss: 0.01118404883891344
2023-01-24 07:05:47.361445: step: 1660/527, loss: 0.008036890998482704
2023-01-24 07:05:48.415292: step: 1664/527, loss: 0.002747524296864867
2023-01-24 07:05:49.470610: step: 1668/527, loss: 0.0027344771660864353
2023-01-24 07:05:50.520660: step: 1672/527, loss: 0.0010497388429939747
2023-01-24 07:05:51.575154: step: 1676/527, loss: 0.004042036831378937
2023-01-24 07:05:52.629323: step: 1680/527, loss: 0.01404307596385479
2023-01-24 07:05:53.668556: step: 1684/527, loss: 0.0013216814259067178
2023-01-24 07:05:54.715296: step: 1688/527, loss: 0.0011174700921401381
2023-01-24 07:05:55.776860: step: 1692/527, loss: 0.0011807511327788234
2023-01-24 07:05:56.821879: step: 1696/527, loss: 0.0033853594213724136
2023-01-24 07:05:57.871469: step: 1700/527, loss: 0.004801849834620953
2023-01-24 07:05:58.903113: step: 1704/527, loss: 0.00011519994586706161
2023-01-24 07:05:59.954799: step: 1708/527, loss: 0.025350751355290413
2023-01-24 07:06:01.022721: step: 1712/527, loss: 0.03762112930417061
2023-01-24 07:06:02.081340: step: 1716/527, loss: 0.0035009244456887245
2023-01-24 07:06:03.136394: step: 1720/527, loss: 0.0019672783091664314
2023-01-24 07:06:04.199951: step: 1724/527, loss: 0.0012699570506811142
2023-01-24 07:06:05.250828: step: 1728/527, loss: 0.001014609937556088
2023-01-24 07:06:06.300238: step: 1732/527, loss: 0.004141919314861298
2023-01-24 07:06:07.345079: step: 1736/527, loss: 0.006008971948176622
2023-01-24 07:06:08.420174: step: 1740/527, loss: 0.017608124762773514
2023-01-24 07:06:09.486347: step: 1744/527, loss: 0.0002709919062908739
2023-01-24 07:06:10.537913: step: 1748/527, loss: 0.015857547521591187
2023-01-24 07:06:11.595790: step: 1752/527, loss: 0.010998151265084743
2023-01-24 07:06:12.637264: step: 1756/527, loss: 0.001594930305145681
2023-01-24 07:06:13.713461: step: 1760/527, loss: 0.0054114446975290775
2023-01-24 07:06:14.761694: step: 1764/527, loss: 0.00354445306584239
2023-01-24 07:06:15.799384: step: 1768/527, loss: 0.004710740875452757
2023-01-24 07:06:16.861936: step: 1772/527, loss: 0.005172974895685911
2023-01-24 07:06:17.914339: step: 1776/527, loss: 0.006135033909231424
2023-01-24 07:06:18.971490: step: 1780/527, loss: 3.558532989700325e-05
2023-01-24 07:06:20.051862: step: 1784/527, loss: 0.0026814830489456654
2023-01-24 07:06:21.092804: step: 1788/527, loss: 0.0025886159855872393
2023-01-24 07:06:22.147100: step: 1792/527, loss: 0.0030488884076476097
2023-01-24 07:06:23.210810: step: 1796/527, loss: 0.0024280319921672344
2023-01-24 07:06:24.269321: step: 1800/527, loss: 0.0014610904036089778
2023-01-24 07:06:25.329166: step: 1804/527, loss: 0.05553878843784332
2023-01-24 07:06:26.375585: step: 1808/527, loss: 0.000567455543205142
2023-01-24 07:06:27.421860: step: 1812/527, loss: 0.004510463681071997
2023-01-24 07:06:28.479022: step: 1816/527, loss: 0.0047310334630310535
2023-01-24 07:06:29.533098: step: 1820/527, loss: 0.003958914428949356
2023-01-24 07:06:30.577474: step: 1824/527, loss: 0.017910659313201904
2023-01-24 07:06:31.615978: step: 1828/527, loss: 0.010180640034377575
2023-01-24 07:06:32.663397: step: 1832/527, loss: 0.0016555368201807141
2023-01-24 07:06:33.717542: step: 1836/527, loss: 0.005525160115212202
2023-01-24 07:06:34.773810: step: 1840/527, loss: 0.0062970309518277645
2023-01-24 07:06:35.817451: step: 1844/527, loss: 0.002770808292552829
2023-01-24 07:06:36.877454: step: 1848/527, loss: 0.001972703728824854
2023-01-24 07:06:37.928738: step: 1852/527, loss: 0.00023240938025992364
2023-01-24 07:06:38.975360: step: 1856/527, loss: 0.00856590922921896
2023-01-24 07:06:40.033898: step: 1860/527, loss: 0.004154106602072716
2023-01-24 07:06:41.080255: step: 1864/527, loss: 0.005443803034722805
2023-01-24 07:06:42.119186: step: 1868/527, loss: 0.0017447288846597075
2023-01-24 07:06:43.170952: step: 1872/527, loss: 0.00017517953529022634
2023-01-24 07:06:44.216423: step: 1876/527, loss: 0.0005201484309509397
2023-01-24 07:06:45.271066: step: 1880/527, loss: 0.0008196663111448288
2023-01-24 07:06:46.308926: step: 1884/527, loss: 0.003418135456740856
2023-01-24 07:06:47.374159: step: 1888/527, loss: 0.015642037615180016
2023-01-24 07:06:48.427151: step: 1892/527, loss: 0.006341900676488876
2023-01-24 07:06:49.474433: step: 1896/527, loss: 0.008579635992646217
2023-01-24 07:06:50.555146: step: 1900/527, loss: 0.01056369673460722
2023-01-24 07:06:51.606929: step: 1904/527, loss: 0.0050481874495744705
2023-01-24 07:06:52.641472: step: 1908/527, loss: 0.007153413724154234
2023-01-24 07:06:53.689444: step: 1912/527, loss: 0.006582628004252911
2023-01-24 07:06:54.752237: step: 1916/527, loss: 0.006622140295803547
2023-01-24 07:06:55.814596: step: 1920/527, loss: 0.005359706934541464
2023-01-24 07:06:56.869889: step: 1924/527, loss: 0.007415145635604858
2023-01-24 07:06:57.936064: step: 1928/527, loss: 0.04922202602028847
2023-01-24 07:06:58.979959: step: 1932/527, loss: 0.003483665408566594
2023-01-24 07:07:00.048413: step: 1936/527, loss: 0.006572945509105921
2023-01-24 07:07:01.108260: step: 1940/527, loss: 0.004526928532868624
2023-01-24 07:07:02.166808: step: 1944/527, loss: 0.005747731775045395
2023-01-24 07:07:03.221590: step: 1948/527, loss: 0.0029546748846769333
2023-01-24 07:07:04.264466: step: 1952/527, loss: 0.005977029446512461
2023-01-24 07:07:05.324924: step: 1956/527, loss: 0.008019886910915375
2023-01-24 07:07:06.373905: step: 1960/527, loss: 0.0030083435121923685
2023-01-24 07:07:07.424803: step: 1964/527, loss: 0.0013906039530411363
2023-01-24 07:07:08.476546: step: 1968/527, loss: 0.009009996429085732
2023-01-24 07:07:09.513850: step: 1972/527, loss: 0.023654289543628693
2023-01-24 07:07:10.589851: step: 1976/527, loss: 0.0029636144172400236
2023-01-24 07:07:11.638200: step: 1980/527, loss: 0.00697800749912858
2023-01-24 07:07:12.690535: step: 1984/527, loss: 0.0019071944989264011
2023-01-24 07:07:13.734800: step: 1988/527, loss: 0.002265317365527153
2023-01-24 07:07:14.778456: step: 1992/527, loss: 0.0013044317020103335
2023-01-24 07:07:15.827411: step: 1996/527, loss: 0.001633031410165131
2023-01-24 07:07:16.869450: step: 2000/527, loss: 0.0031928825192153454
2023-01-24 07:07:17.924963: step: 2004/527, loss: 0.0016749455826357007
2023-01-24 07:07:18.984687: step: 2008/527, loss: 0.004191864747554064
2023-01-24 07:07:20.024451: step: 2012/527, loss: 1.1844836990348995e-05
2023-01-24 07:07:21.066738: step: 2016/527, loss: 0.0002957037650048733
2023-01-24 07:07:22.114309: step: 2020/527, loss: 0.0029167046304792166
2023-01-24 07:07:23.144629: step: 2024/527, loss: 0.0004001189663540572
2023-01-24 07:07:24.192167: step: 2028/527, loss: 0.00020117717212997377
2023-01-24 07:07:25.234465: step: 2032/527, loss: 0.010397354140877724
2023-01-24 07:07:26.271889: step: 2036/527, loss: 0.006372228730469942
2023-01-24 07:07:27.326530: step: 2040/527, loss: 0.006984546780586243
2023-01-24 07:07:28.377566: step: 2044/527, loss: 0.013308129273355007
2023-01-24 07:07:29.431884: step: 2048/527, loss: 0.007427938748151064
2023-01-24 07:07:30.481443: step: 2052/527, loss: 0.00517807062715292
2023-01-24 07:07:31.536514: step: 2056/527, loss: 0.003048629965633154
2023-01-24 07:07:32.568459: step: 2060/527, loss: 0.001386835239827633
2023-01-24 07:07:33.601813: step: 2064/527, loss: 7.517064659623429e-07
2023-01-24 07:07:34.634064: step: 2068/527, loss: 0.000144703546538949
2023-01-24 07:07:35.684491: step: 2072/527, loss: 0.005975764710456133
2023-01-24 07:07:36.751251: step: 2076/527, loss: 0.006867633201181889
2023-01-24 07:07:37.798168: step: 2080/527, loss: 0.004074363503605127
2023-01-24 07:07:38.857518: step: 2084/527, loss: 0.0009200856438837945
2023-01-24 07:07:39.926674: step: 2088/527, loss: 0.07849445939064026
2023-01-24 07:07:40.971856: step: 2092/527, loss: 0.0019149655709043145
2023-01-24 07:07:42.035795: step: 2096/527, loss: 0.006038849242031574
2023-01-24 07:07:43.109489: step: 2100/527, loss: 0.009350918233394623
2023-01-24 07:07:44.149967: step: 2104/527, loss: 0.05594834312796593
2023-01-24 07:07:45.193940: step: 2108/527, loss: 0.01078872475773096
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33519016204670793, 'r': 0.32564964510040695, 'f1': 0.33035103554940226}, 'combined': 0.24341655251008587, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3721707681748068, 'r': 0.2916465474242577, 'f1': 0.32702467091405046}, 'combined': 0.20929578938499227, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35093537414965986, 'r': 0.33561940905394416, 'f1': 0.3431065539697935}, 'combined': 0.25281535555668994, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3735624760750238, 'r': 0.3053644218596925, 'f1': 0.33603820936284}, 'combined': 0.21506445399221757, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3630353895885245, 'r': 0.3299695476525678, 'f1': 0.34571362149682555}, 'combined': 0.25473635268187145, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3823311565177729, 'r': 0.3126262966239219, 'f1': 0.3439829963855991}, 'combined': 0.24662931816325975, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6, 'r': 0.20689655172413793, 'f1': 0.3076923076923077}, 'combined': 0.20512820512820512, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36325359749028163, 'r': 0.3260321662483932, 'f1': 0.3436379032258064}, 'combined': 0.25320687606112047, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827405873011607, 'r': 0.313309979395116, 'f1': 0.344562453530268}, 'combined': 0.24704477800283367, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
******************************
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
2023-01-24 07:10:19.800988: step: 4/527, loss: 0.0043526035733520985
2023-01-24 07:10:20.857920: step: 8/527, loss: 0.0023075598292052746
2023-01-24 07:10:21.919991: step: 12/527, loss: 0.0019912654533982277
2023-01-24 07:10:22.970429: step: 16/527, loss: 0.012579189613461494
2023-01-24 07:10:24.036719: step: 20/527, loss: 0.002191648120060563
2023-01-24 07:10:25.081970: step: 24/527, loss: 0.005206662230193615
2023-01-24 07:10:26.120470: step: 28/527, loss: 9.666178812040016e-06
2023-01-24 07:10:27.161150: step: 32/527, loss: 0.002191325882449746
2023-01-24 07:10:28.215590: step: 36/527, loss: 0.00243182759732008
2023-01-24 07:10:29.260243: step: 40/527, loss: 0.002461265306919813
2023-01-24 07:10:30.307350: step: 44/527, loss: 0.0010654813377186656
2023-01-24 07:10:31.364314: step: 48/527, loss: 0.0029627038165926933
2023-01-24 07:10:32.411963: step: 52/527, loss: 0.0016816186252981424
2023-01-24 07:10:33.474958: step: 56/527, loss: 0.011506606824696064
2023-01-24 07:10:34.528808: step: 60/527, loss: 0.0017763753421604633
2023-01-24 07:10:35.576910: step: 64/527, loss: 0.0005496774101629853
2023-01-24 07:10:36.613657: step: 68/527, loss: 0.006504182703793049
2023-01-24 07:10:37.676462: step: 72/527, loss: 0.0038948948495090008
2023-01-24 07:10:38.717172: step: 76/527, loss: 0.007334815338253975
2023-01-24 07:10:39.759484: step: 80/527, loss: 0.0004767587233800441
2023-01-24 07:10:40.820277: step: 84/527, loss: 0.0004721745499409735
2023-01-24 07:10:41.871426: step: 88/527, loss: 0.008727424778044224
2023-01-24 07:10:42.923427: step: 92/527, loss: 0.004020388703793287
2023-01-24 07:10:43.983391: step: 96/527, loss: 0.0025085019879043102
2023-01-24 07:10:45.037683: step: 100/527, loss: 0.0015356676885858178
2023-01-24 07:10:46.096862: step: 104/527, loss: 0.008122754283249378
2023-01-24 07:10:47.135722: step: 108/527, loss: 0.0042010401375591755
2023-01-24 07:10:48.198170: step: 112/527, loss: 0.010724453255534172
2023-01-24 07:10:49.294842: step: 116/527, loss: 0.005484436172991991
2023-01-24 07:10:50.343808: step: 120/527, loss: 0.003741045016795397
2023-01-24 07:10:51.385438: step: 124/527, loss: 0.00021263000962790102
2023-01-24 07:10:52.448962: step: 128/527, loss: 0.00572225684300065
2023-01-24 07:10:53.500107: step: 132/527, loss: 0.002912192139774561
2023-01-24 07:10:54.567570: step: 136/527, loss: 0.0014544990845024586
2023-01-24 07:10:55.613145: step: 140/527, loss: 0.0021721383091062307
2023-01-24 07:10:56.654959: step: 144/527, loss: 0.0064918044954538345
2023-01-24 07:10:57.703788: step: 148/527, loss: 0.02143397368490696
2023-01-24 07:10:58.737859: step: 152/527, loss: 0.0012229107087478042
2023-01-24 07:10:59.807497: step: 156/527, loss: 0.009608855471014977
2023-01-24 07:11:00.883254: step: 160/527, loss: 0.010895432904362679
2023-01-24 07:11:01.921227: step: 164/527, loss: 4.52004860562738e-05
2023-01-24 07:11:02.962752: step: 168/527, loss: 0.00017657164426054806
2023-01-24 07:11:03.996832: step: 172/527, loss: 0.004457660019397736
2023-01-24 07:11:05.039506: step: 176/527, loss: 0.010944776237010956
2023-01-24 07:11:06.079370: step: 180/527, loss: 0.005464617628604174
2023-01-24 07:11:07.129743: step: 184/527, loss: 0.0021822936832904816
2023-01-24 07:11:08.190316: step: 188/527, loss: 0.0020280620083212852
2023-01-24 07:11:09.257564: step: 192/527, loss: 0.005777272861450911
2023-01-24 07:11:10.305552: step: 196/527, loss: 0.0025322050787508488
2023-01-24 07:11:11.360258: step: 200/527, loss: 0.0053939190693199635
2023-01-24 07:11:12.431467: step: 204/527, loss: 0.005446792580187321
2023-01-24 07:11:13.481647: step: 208/527, loss: 0.005624681245535612
2023-01-24 07:11:14.541900: step: 212/527, loss: 0.0015547068323940039
2023-01-24 07:11:15.591720: step: 216/527, loss: 0.0020389468409121037
2023-01-24 07:11:16.626406: step: 220/527, loss: 0.0009207907714881003
2023-01-24 07:11:17.697518: step: 224/527, loss: 0.004429956432431936
2023-01-24 07:11:18.768201: step: 228/527, loss: 0.009660227224230766
2023-01-24 07:11:19.809479: step: 232/527, loss: 0.0010038953041657805
2023-01-24 07:11:20.867516: step: 236/527, loss: 0.0038022464141249657
2023-01-24 07:11:21.915269: step: 240/527, loss: 0.0037014468107372522
2023-01-24 07:11:22.955936: step: 244/527, loss: 0.0024868869222700596
2023-01-24 07:11:24.012802: step: 248/527, loss: 0.00047362822806462646
2023-01-24 07:11:25.084350: step: 252/527, loss: 0.02443956770002842
2023-01-24 07:11:26.134106: step: 256/527, loss: 0.005628102924674749
2023-01-24 07:11:27.187706: step: 260/527, loss: 0.0009129595127888024
2023-01-24 07:11:28.225306: step: 264/527, loss: 0.0025695806834846735
2023-01-24 07:11:29.283506: step: 268/527, loss: 0.004168948158621788
2023-01-24 07:11:30.338637: step: 272/527, loss: 0.001953809754922986
2023-01-24 07:11:31.386991: step: 276/527, loss: 0.0073697008192539215
2023-01-24 07:11:32.431580: step: 280/527, loss: 0.00013159932859707624
2023-01-24 07:11:33.484778: step: 284/527, loss: 0.0006879745051264763
2023-01-24 07:11:34.535582: step: 288/527, loss: 0.001803342835046351
2023-01-24 07:11:35.590060: step: 292/527, loss: 0.0006572796846739948
2023-01-24 07:11:36.642845: step: 296/527, loss: 0.0022013038396835327
2023-01-24 07:11:37.699072: step: 300/527, loss: 0.0012773108901455998
2023-01-24 07:11:38.774294: step: 304/527, loss: 2.185352786909789e-05
2023-01-24 07:11:39.830247: step: 308/527, loss: 0.004841454327106476
2023-01-24 07:11:40.893815: step: 312/527, loss: 0.02062935009598732
2023-01-24 07:11:41.981142: step: 316/527, loss: 0.008016521111130714
2023-01-24 07:11:43.030662: step: 320/527, loss: 0.002767492551356554
2023-01-24 07:11:44.096205: step: 324/527, loss: 0.0008753962465561926
2023-01-24 07:11:45.157372: step: 328/527, loss: 0.0010826876387000084
2023-01-24 07:11:46.204195: step: 332/527, loss: 0.006960335653275251
2023-01-24 07:11:47.262201: step: 336/527, loss: 0.00998025480657816
2023-01-24 07:11:48.317063: step: 340/527, loss: 0.012459678575396538
2023-01-24 07:11:49.381021: step: 344/527, loss: 0.006665992550551891
2023-01-24 07:11:50.438900: step: 348/527, loss: 0.0006250516162253916
2023-01-24 07:11:51.479272: step: 352/527, loss: 0.000537982617970556
2023-01-24 07:11:52.538659: step: 356/527, loss: 0.005042615812271833
2023-01-24 07:11:53.585919: step: 360/527, loss: 0.011064927093684673
2023-01-24 07:11:54.622182: step: 364/527, loss: 0.0042867474257946014
2023-01-24 07:11:55.670069: step: 368/527, loss: 1.4619061403209344e-05
2023-01-24 07:11:56.732973: step: 372/527, loss: 0.007952438667416573
2023-01-24 07:11:57.781285: step: 376/527, loss: 0.0026353937573730946
2023-01-24 07:11:58.838859: step: 380/527, loss: 0.0005096009699627757
2023-01-24 07:11:59.901766: step: 384/527, loss: 0.003215527394786477
2023-01-24 07:12:00.951548: step: 388/527, loss: 0.0015521569876000285
2023-01-24 07:12:02.005430: step: 392/527, loss: 0.017297156155109406
2023-01-24 07:12:03.055764: step: 396/527, loss: 0.0006201857468113303
2023-01-24 07:12:04.101313: step: 400/527, loss: 0.004360498394817114
2023-01-24 07:12:05.158640: step: 404/527, loss: 0.006486785132437944
2023-01-24 07:12:06.206866: step: 408/527, loss: 0.008071518503129482
2023-01-24 07:12:07.262335: step: 412/527, loss: 0.0024542007595300674
2023-01-24 07:12:08.325974: step: 416/527, loss: 0.0007408526726067066
2023-01-24 07:12:09.360562: step: 420/527, loss: 0.0022004658821970224
2023-01-24 07:12:10.412676: step: 424/527, loss: 0.0023798802867531776
2023-01-24 07:12:11.461302: step: 428/527, loss: 0.0014789014821872115
2023-01-24 07:12:12.527252: step: 432/527, loss: 0.0024607426021248102
2023-01-24 07:12:13.583854: step: 436/527, loss: 0.0018823177088052034
2023-01-24 07:12:14.648304: step: 440/527, loss: 0.009442086331546307
2023-01-24 07:12:15.696221: step: 444/527, loss: 0.0041308957152068615
2023-01-24 07:12:16.764375: step: 448/527, loss: 0.003608011407777667
2023-01-24 07:12:17.856370: step: 452/527, loss: 0.005427576135843992
2023-01-24 07:12:18.911387: step: 456/527, loss: 0.007602985482662916
2023-01-24 07:12:19.961327: step: 460/527, loss: 0.011451112106442451
2023-01-24 07:12:21.021361: step: 464/527, loss: 0.0002630161470733583
2023-01-24 07:12:22.055580: step: 468/527, loss: 0.0030766415875405073
2023-01-24 07:12:23.105007: step: 472/527, loss: 0.005387390032410622
2023-01-24 07:12:24.160699: step: 476/527, loss: 0.0015508156502619386
2023-01-24 07:12:25.207855: step: 480/527, loss: 0.007273146882653236
2023-01-24 07:12:26.260198: step: 484/527, loss: 0.002591175027191639
2023-01-24 07:12:27.311961: step: 488/527, loss: 0.0002340820647077635
2023-01-24 07:12:28.367404: step: 492/527, loss: 0.01507216040045023
2023-01-24 07:12:29.442981: step: 496/527, loss: 0.011896253563463688
2023-01-24 07:12:30.493632: step: 500/527, loss: 0.0026756778825074434
2023-01-24 07:12:31.548865: step: 504/527, loss: 0.001898287096992135
2023-01-24 07:12:32.607802: step: 508/527, loss: 0.002242229413241148
2023-01-24 07:12:33.665793: step: 512/527, loss: 0.002066503744572401
2023-01-24 07:12:34.714308: step: 516/527, loss: 0.0019434496061876416
2023-01-24 07:12:35.763323: step: 520/527, loss: 0.002433086046949029
2023-01-24 07:12:36.825047: step: 524/527, loss: 0.0019725847523659468
2023-01-24 07:12:37.856273: step: 528/527, loss: 0.0021631342824548483
2023-01-24 07:12:38.901554: step: 532/527, loss: 0.0002122735750162974
2023-01-24 07:12:39.955520: step: 536/527, loss: 0.003666941076517105
2023-01-24 07:12:41.012231: step: 540/527, loss: 0.0038509280420839787
2023-01-24 07:12:42.049706: step: 544/527, loss: 0.0008640268933959305
2023-01-24 07:12:43.102012: step: 548/527, loss: 0.0010096246842294931
2023-01-24 07:12:44.158538: step: 552/527, loss: 0.0038988187443464994
2023-01-24 07:12:45.215665: step: 556/527, loss: 0.0017615047981962562
2023-01-24 07:12:46.264849: step: 560/527, loss: 0.0041091907769441605
2023-01-24 07:12:47.317775: step: 564/527, loss: 0.06354616582393646
2023-01-24 07:12:48.377845: step: 568/527, loss: 0.0022531517315655947
2023-01-24 07:12:49.438346: step: 572/527, loss: 0.009618941694498062
2023-01-24 07:12:50.482878: step: 576/527, loss: 0.002705459948629141
2023-01-24 07:12:51.547603: step: 580/527, loss: 0.010746491141617298
2023-01-24 07:12:52.612629: step: 584/527, loss: 0.0004461625940166414
2023-01-24 07:12:53.666307: step: 588/527, loss: 0.001540738856419921
2023-01-24 07:12:54.734797: step: 592/527, loss: 0.004156941082328558
2023-01-24 07:12:55.772456: step: 596/527, loss: 0.0029327841475605965
2023-01-24 07:12:56.836943: step: 600/527, loss: 0.002596890786662698
2023-01-24 07:12:57.890135: step: 604/527, loss: 0.0054204463958740234
2023-01-24 07:12:58.937508: step: 608/527, loss: 0.0019639183301478624
2023-01-24 07:12:59.982178: step: 612/527, loss: 0.0015900291036814451
2023-01-24 07:13:01.044351: step: 616/527, loss: 0.004255213309079409
2023-01-24 07:13:02.081699: step: 620/527, loss: 0.014682373963296413
2023-01-24 07:13:03.134373: step: 624/527, loss: 0.0022347094491124153
2023-01-24 07:13:04.171013: step: 628/527, loss: 0.0032233865931630135
2023-01-24 07:13:05.219572: step: 632/527, loss: 0.00254452764056623
2023-01-24 07:13:06.284485: step: 636/527, loss: 0.002465637866407633
2023-01-24 07:13:07.348598: step: 640/527, loss: 0.00031317968387156725
2023-01-24 07:13:08.416617: step: 644/527, loss: 0.009111504070460796
2023-01-24 07:13:09.466139: step: 648/527, loss: 2.2168167561176233e-05
2023-01-24 07:13:10.537905: step: 652/527, loss: 0.005279306787997484
2023-01-24 07:13:11.592304: step: 656/527, loss: 0.0
2023-01-24 07:13:12.664521: step: 660/527, loss: 0.013738441281020641
2023-01-24 07:13:13.727810: step: 664/527, loss: 0.0006977031007409096
2023-01-24 07:13:14.781654: step: 668/527, loss: 0.0022768783383071423
2023-01-24 07:13:15.836226: step: 672/527, loss: 0.0042579504661262035
2023-01-24 07:13:16.898469: step: 676/527, loss: 0.0034059248864650726
2023-01-24 07:13:17.977181: step: 680/527, loss: 0.0010519471252337098
2023-01-24 07:13:19.040161: step: 684/527, loss: 0.005364408250898123
2023-01-24 07:13:20.094603: step: 688/527, loss: 0.0002478122478350997
2023-01-24 07:13:21.148067: step: 692/527, loss: 0.0005271011614240706
2023-01-24 07:13:22.211799: step: 696/527, loss: 0.0017791267018765211
2023-01-24 07:13:23.281733: step: 700/527, loss: 0.0022672144696116447
2023-01-24 07:13:24.331543: step: 704/527, loss: 0.003363115945830941
2023-01-24 07:13:25.385775: step: 708/527, loss: 0.005192456301301718
2023-01-24 07:13:26.452694: step: 712/527, loss: 0.0006168190157040954
2023-01-24 07:13:27.508920: step: 716/527, loss: 0.0028047868981957436
2023-01-24 07:13:28.551288: step: 720/527, loss: 0.001376513042487204
2023-01-24 07:13:29.609551: step: 724/527, loss: 0.00010021023626904935
2023-01-24 07:13:30.678887: step: 728/527, loss: 0.0011807429837062955
2023-01-24 07:13:31.732241: step: 732/527, loss: 0.00048385339323431253
2023-01-24 07:13:32.786137: step: 736/527, loss: 0.00017284642672166228
2023-01-24 07:13:33.821446: step: 740/527, loss: 0.00017498839588370174
2023-01-24 07:13:34.871253: step: 744/527, loss: 0.005302312783896923
2023-01-24 07:13:35.921456: step: 748/527, loss: 0.0014845379628241062
2023-01-24 07:13:36.974738: step: 752/527, loss: 0.01043526828289032
2023-01-24 07:13:38.026321: step: 756/527, loss: 0.0024213765282183886
2023-01-24 07:13:39.065278: step: 760/527, loss: 0.0011087879538536072
2023-01-24 07:13:40.130838: step: 764/527, loss: 0.00528079504147172
2023-01-24 07:13:41.177279: step: 768/527, loss: 6.313556514214724e-05
2023-01-24 07:13:42.234497: step: 772/527, loss: 0.0012994182761758566
2023-01-24 07:13:43.287150: step: 776/527, loss: 0.003603674005717039
2023-01-24 07:13:44.335663: step: 780/527, loss: 3.5160126572009176e-05
2023-01-24 07:13:45.393712: step: 784/527, loss: 0.006024331320077181
2023-01-24 07:13:46.440475: step: 788/527, loss: 0.00414207624271512
2023-01-24 07:13:47.525249: step: 792/527, loss: 0.000872282253112644
2023-01-24 07:13:48.591258: step: 796/527, loss: 0.0005333773442544043
2023-01-24 07:13:49.651821: step: 800/527, loss: 0.002157765906304121
2023-01-24 07:13:50.708884: step: 804/527, loss: 0.02121039852499962
2023-01-24 07:13:51.765666: step: 808/527, loss: 0.0024337389040738344
2023-01-24 07:13:52.827515: step: 812/527, loss: 0.0003536268195603043
2023-01-24 07:13:53.872678: step: 816/527, loss: 0.00033942601294256747
2023-01-24 07:13:54.920795: step: 820/527, loss: 0.006443643476814032
2023-01-24 07:13:55.974192: step: 824/527, loss: 0.0020841641817241907
2023-01-24 07:13:57.021513: step: 828/527, loss: 0.0006504695629701018
2023-01-24 07:13:58.075272: step: 832/527, loss: 0.013514254242181778
2023-01-24 07:13:59.129911: step: 836/527, loss: 0.006408346351236105
2023-01-24 07:14:00.182239: step: 840/527, loss: 0.009259113110601902
2023-01-24 07:14:01.236230: step: 844/527, loss: 0.03093450888991356
2023-01-24 07:14:02.304879: step: 848/527, loss: 0.006811351515352726
2023-01-24 07:14:03.371046: step: 852/527, loss: 0.0011162091977894306
2023-01-24 07:14:04.412192: step: 856/527, loss: 0.0030295744072645903
2023-01-24 07:14:05.459570: step: 860/527, loss: 0.002891014562919736
2023-01-24 07:14:06.521424: step: 864/527, loss: 0.001489816466346383
2023-01-24 07:14:07.592244: step: 868/527, loss: 0.0006352232885546982
2023-01-24 07:14:08.640216: step: 872/527, loss: 0.005036013666540384
2023-01-24 07:14:09.708876: step: 876/527, loss: 0.004445035010576248
2023-01-24 07:14:10.772523: step: 880/527, loss: 0.03216918557882309
2023-01-24 07:14:11.818468: step: 884/527, loss: 0.006238726433366537
2023-01-24 07:14:12.867427: step: 888/527, loss: 0.0025143115781247616
2023-01-24 07:14:13.944844: step: 892/527, loss: 0.010279372334480286
2023-01-24 07:14:14.981944: step: 896/527, loss: 0.0053979442454874516
2023-01-24 07:14:16.054652: step: 900/527, loss: 0.00488645862787962
2023-01-24 07:14:17.109219: step: 904/527, loss: 0.013648072257637978
2023-01-24 07:14:18.151434: step: 908/527, loss: 0.003178500337526202
2023-01-24 07:14:19.222997: step: 912/527, loss: 1.1075104339397512e-05
2023-01-24 07:14:20.277640: step: 916/527, loss: 0.0012122975895181298
2023-01-24 07:14:21.343724: step: 920/527, loss: 0.01264969538897276
2023-01-24 07:14:22.392142: step: 924/527, loss: 0.0016744674649089575
2023-01-24 07:14:23.445336: step: 928/527, loss: 0.0019454541616141796
2023-01-24 07:14:24.498501: step: 932/527, loss: 0.0008535322267562151
2023-01-24 07:14:25.537696: step: 936/527, loss: 0.011696591973304749
2023-01-24 07:14:26.593606: step: 940/527, loss: 0.012296185828745365
2023-01-24 07:14:27.669846: step: 944/527, loss: 0.0055004507303237915
2023-01-24 07:14:28.728165: step: 948/527, loss: 0.047577809542417526
2023-01-24 07:14:29.775937: step: 952/527, loss: 0.009579057805240154
2023-01-24 07:14:30.845761: step: 956/527, loss: 0.0096200630068779
2023-01-24 07:14:31.897823: step: 960/527, loss: 0.0025058332830667496
2023-01-24 07:14:32.962310: step: 964/527, loss: 0.005407311022281647
2023-01-24 07:14:34.013416: step: 968/527, loss: 0.00035533253685571253
2023-01-24 07:14:35.068967: step: 972/527, loss: 0.003501267870888114
2023-01-24 07:14:36.122946: step: 976/527, loss: 0.00415364233776927
2023-01-24 07:14:37.172613: step: 980/527, loss: 0.0027824013959616423
2023-01-24 07:14:38.234167: step: 984/527, loss: 0.001865458209067583
2023-01-24 07:14:39.297396: step: 988/527, loss: 0.004339116159826517
2023-01-24 07:14:40.337443: step: 992/527, loss: 0.006068643648177385
2023-01-24 07:14:41.397049: step: 996/527, loss: 0.003729678923264146
2023-01-24 07:14:42.442471: step: 1000/527, loss: 0.004127271473407745
2023-01-24 07:14:43.490831: step: 1004/527, loss: 0.001441058237105608
2023-01-24 07:14:44.555042: step: 1008/527, loss: 0.02191963605582714
2023-01-24 07:14:45.625965: step: 1012/527, loss: 0.0009864723542705178
2023-01-24 07:14:46.695985: step: 1016/527, loss: 0.006173207890242338
2023-01-24 07:14:47.771277: step: 1020/527, loss: 0.004782783333212137
2023-01-24 07:14:48.810887: step: 1024/527, loss: 0.00021754145564045757
2023-01-24 07:14:49.871912: step: 1028/527, loss: 0.017618104815483093
2023-01-24 07:14:50.920265: step: 1032/527, loss: 0.000496803259011358
2023-01-24 07:14:51.975534: step: 1036/527, loss: 0.0011742659844458103
2023-01-24 07:14:53.031068: step: 1040/527, loss: 0.0009261745144613087
2023-01-24 07:14:54.085515: step: 1044/527, loss: 0.05287783965468407
2023-01-24 07:14:55.130734: step: 1048/527, loss: 0.0008137134136632085
2023-01-24 07:14:56.175863: step: 1052/527, loss: 0.02463652566075325
2023-01-24 07:14:57.230704: step: 1056/527, loss: 0.00018551468383520842
2023-01-24 07:14:58.274653: step: 1060/527, loss: 0.011669578962028027
2023-01-24 07:14:59.330465: step: 1064/527, loss: 0.004068742040544748
2023-01-24 07:15:00.377540: step: 1068/527, loss: 0.0034586458932608366
2023-01-24 07:15:01.433589: step: 1072/527, loss: 0.004754193127155304
2023-01-24 07:15:02.498015: step: 1076/527, loss: 0.006056899204850197
2023-01-24 07:15:03.540560: step: 1080/527, loss: 0.0077989427372813225
2023-01-24 07:15:04.593368: step: 1084/527, loss: 0.0011496876832097769
2023-01-24 07:15:05.648200: step: 1088/527, loss: 0.007621351163834333
2023-01-24 07:15:06.684720: step: 1092/527, loss: 0.0016001664334908128
2023-01-24 07:15:07.730526: step: 1096/527, loss: 0.0009155957377515733
2023-01-24 07:15:08.787008: step: 1100/527, loss: 0.0011686549987643957
2023-01-24 07:15:09.843500: step: 1104/527, loss: 0.004579978995025158
2023-01-24 07:15:10.897243: step: 1108/527, loss: 0.0007663153228349984
2023-01-24 07:15:11.964323: step: 1112/527, loss: 0.0001973050821106881
2023-01-24 07:15:13.017905: step: 1116/527, loss: 0.005455676931887865
2023-01-24 07:15:14.061946: step: 1120/527, loss: 0.0017178180860355496
2023-01-24 07:15:15.122294: step: 1124/527, loss: 0.0034558384213596582
2023-01-24 07:15:16.194068: step: 1128/527, loss: 0.0024458167608827353
2023-01-24 07:15:17.245372: step: 1132/527, loss: 0.0037678834050893784
2023-01-24 07:15:18.306628: step: 1136/527, loss: 0.007445403374731541
2023-01-24 07:15:19.354836: step: 1140/527, loss: 0.00038117272197268903
2023-01-24 07:15:20.403479: step: 1144/527, loss: 0.005706341937184334
2023-01-24 07:15:21.453988: step: 1148/527, loss: 0.0030229093972593546
2023-01-24 07:15:22.519850: step: 1152/527, loss: 0.006949125323444605
2023-01-24 07:15:23.573770: step: 1156/527, loss: 0.008406054228544235
2023-01-24 07:15:24.625237: step: 1160/527, loss: 0.00869454350322485
2023-01-24 07:15:25.689238: step: 1164/527, loss: 0.010242755524814129
2023-01-24 07:15:26.737009: step: 1168/527, loss: 0.002660030033439398
2023-01-24 07:15:27.806070: step: 1172/527, loss: 0.008592398837208748
2023-01-24 07:15:28.846054: step: 1176/527, loss: 0.008411075919866562
2023-01-24 07:15:29.920858: step: 1180/527, loss: 0.01542226318269968
2023-01-24 07:15:30.990513: step: 1184/527, loss: 0.008960546925663948
2023-01-24 07:15:32.040933: step: 1188/527, loss: 0.006315885577350855
2023-01-24 07:15:33.098503: step: 1192/527, loss: 0.007986439391970634
2023-01-24 07:15:34.161546: step: 1196/527, loss: 0.005045855883508921
2023-01-24 07:15:35.219678: step: 1200/527, loss: 0.0020497306250035763
2023-01-24 07:15:36.265943: step: 1204/527, loss: 0.007824450731277466
2023-01-24 07:15:37.328396: step: 1208/527, loss: 0.005716984160244465
2023-01-24 07:15:38.381662: step: 1212/527, loss: 0.0019280440174043179
2023-01-24 07:15:39.425338: step: 1216/527, loss: 0.01253961119800806
2023-01-24 07:15:40.486359: step: 1220/527, loss: 0.02188253402709961
2023-01-24 07:15:41.536210: step: 1224/527, loss: 0.00019145748228766024
2023-01-24 07:15:42.593299: step: 1228/527, loss: 0.003739667357876897
2023-01-24 07:15:43.648839: step: 1232/527, loss: 0.020722458139061928
2023-01-24 07:15:44.709692: step: 1236/527, loss: 0.021839477121829987
2023-01-24 07:15:45.759390: step: 1240/527, loss: 0.005633394233882427
2023-01-24 07:15:46.804530: step: 1244/527, loss: 0.0013857269659638405
2023-01-24 07:15:47.859739: step: 1248/527, loss: 0.008683423511683941
2023-01-24 07:15:48.930111: step: 1252/527, loss: 0.006105201318860054
2023-01-24 07:15:49.980164: step: 1256/527, loss: 3.8500882510561496e-05
2023-01-24 07:15:51.028727: step: 1260/527, loss: 0.0009859050624072552
2023-01-24 07:15:52.060343: step: 1264/527, loss: 0.0005384812830016017
2023-01-24 07:15:53.112667: step: 1268/527, loss: 0.01527114026248455
2023-01-24 07:15:54.165077: step: 1272/527, loss: 0.013376198709011078
2023-01-24 07:15:55.209197: step: 1276/527, loss: 0.004428771790117025
2023-01-24 07:15:56.274661: step: 1280/527, loss: 0.0067210509441792965
2023-01-24 07:15:57.338046: step: 1284/527, loss: 0.00804841797798872
2023-01-24 07:15:58.386782: step: 1288/527, loss: 0.0025202713441103697
2023-01-24 07:15:59.442272: step: 1292/527, loss: 0.0035377750173211098
2023-01-24 07:16:00.491377: step: 1296/527, loss: 0.0032801826018840075
2023-01-24 07:16:01.537281: step: 1300/527, loss: 0.0031494859140366316
2023-01-24 07:16:02.603171: step: 1304/527, loss: 0.0032288830261677504
2023-01-24 07:16:03.642910: step: 1308/527, loss: 0.004604824353009462
2023-01-24 07:16:04.700722: step: 1312/527, loss: 0.002553367055952549
2023-01-24 07:16:05.760933: step: 1316/527, loss: 0.017564352601766586
2023-01-24 07:16:06.823290: step: 1320/527, loss: 0.010695389471948147
2023-01-24 07:16:07.872648: step: 1324/527, loss: 0.0026875792536884546
2023-01-24 07:16:08.942329: step: 1328/527, loss: 0.012935048900544643
2023-01-24 07:16:09.996962: step: 1332/527, loss: 0.030531177297234535
2023-01-24 07:16:11.037199: step: 1336/527, loss: 0.0018842265708371997
2023-01-24 07:16:12.093823: step: 1340/527, loss: 0.0009928299114108086
2023-01-24 07:16:13.149599: step: 1344/527, loss: 0.08753965049982071
2023-01-24 07:16:14.208012: step: 1348/527, loss: 0.00033283248194493353
2023-01-24 07:16:15.263790: step: 1352/527, loss: 0.0019588300492614508
2023-01-24 07:16:16.321524: step: 1356/527, loss: 0.0076537844724953175
2023-01-24 07:16:17.375644: step: 1360/527, loss: 0.0036690644919872284
2023-01-24 07:16:18.420084: step: 1364/527, loss: 0.0029536555521190166
2023-01-24 07:16:19.478384: step: 1368/527, loss: 0.004815292079001665
2023-01-24 07:16:20.517048: step: 1372/527, loss: 0.005803946405649185
2023-01-24 07:16:21.568488: step: 1376/527, loss: 0.0026500229723751545
2023-01-24 07:16:22.607228: step: 1380/527, loss: 0.00893679540604353
2023-01-24 07:16:23.656492: step: 1384/527, loss: 0.0014254737179726362
2023-01-24 07:16:24.709005: step: 1388/527, loss: 0.002962946891784668
2023-01-24 07:16:25.747790: step: 1392/527, loss: 0.0010838632006198168
2023-01-24 07:16:26.800797: step: 1396/527, loss: 0.0016842987388372421
2023-01-24 07:16:27.844757: step: 1400/527, loss: 0.0007154577760957181
2023-01-24 07:16:28.898413: step: 1404/527, loss: 0.009588307701051235
2023-01-24 07:16:29.953245: step: 1408/527, loss: 0.006933812517672777
2023-01-24 07:16:31.008132: step: 1412/527, loss: 0.001652062637731433
2023-01-24 07:16:32.072195: step: 1416/527, loss: 0.0175021942704916
2023-01-24 07:16:33.113565: step: 1420/527, loss: 0.007716262713074684
2023-01-24 07:16:34.165956: step: 1424/527, loss: 0.0044432831928133965
2023-01-24 07:16:35.218932: step: 1428/527, loss: 0.00327146053314209
2023-01-24 07:16:36.260311: step: 1432/527, loss: 7.69982289057225e-05
2023-01-24 07:16:37.316484: step: 1436/527, loss: 0.015095869079232216
2023-01-24 07:16:38.387570: step: 1440/527, loss: 0.005716430023312569
2023-01-24 07:16:39.440257: step: 1444/527, loss: 0.014631562866270542
2023-01-24 07:16:40.491508: step: 1448/527, loss: 0.00968735758215189
2023-01-24 07:16:41.537357: step: 1452/527, loss: 0.0002707011008169502
2023-01-24 07:16:42.591287: step: 1456/527, loss: 0.013000497594475746
2023-01-24 07:16:43.655723: step: 1460/527, loss: 0.005486202891916037
2023-01-24 07:16:44.729336: step: 1464/527, loss: 3.6374767660163343e-06
2023-01-24 07:16:45.791106: step: 1468/527, loss: 0.0021635941229760647
2023-01-24 07:16:46.830394: step: 1472/527, loss: 0.0036381848622113466
2023-01-24 07:16:47.875097: step: 1476/527, loss: 0.0100374361500144
2023-01-24 07:16:48.930345: step: 1480/527, loss: 0.00924387015402317
2023-01-24 07:16:49.976395: step: 1484/527, loss: 0.0057376474142074585
2023-01-24 07:16:51.028062: step: 1488/527, loss: 0.002657095668837428
2023-01-24 07:16:52.078171: step: 1492/527, loss: 0.010364815592765808
2023-01-24 07:16:53.129959: step: 1496/527, loss: 0.003379128174856305
2023-01-24 07:16:54.185192: step: 1500/527, loss: 0.00571554247289896
2023-01-24 07:16:55.237486: step: 1504/527, loss: 0.0032677853014320135
2023-01-24 07:16:56.279348: step: 1508/527, loss: 5.5866941693238914e-05
2023-01-24 07:16:57.331510: step: 1512/527, loss: 0.000800703011918813
2023-01-24 07:16:58.367014: step: 1516/527, loss: 0.0036062246654182673
2023-01-24 07:16:59.422976: step: 1520/527, loss: 0.002597344573587179
2023-01-24 07:17:00.478697: step: 1524/527, loss: 0.00915090087801218
2023-01-24 07:17:01.527256: step: 1528/527, loss: 0.003382542170584202
2023-01-24 07:17:02.577411: step: 1532/527, loss: 0.00884362030774355
2023-01-24 07:17:03.629469: step: 1536/527, loss: 0.008724585175514221
2023-01-24 07:17:04.680917: step: 1540/527, loss: 0.011519985273480415
2023-01-24 07:17:05.716013: step: 1544/527, loss: 0.0047426363453269005
2023-01-24 07:17:06.761663: step: 1548/527, loss: 0.010204588994383812
2023-01-24 07:17:07.845511: step: 1552/527, loss: 0.013213660567998886
2023-01-24 07:17:08.887884: step: 1556/527, loss: 0.0013982506934553385
2023-01-24 07:17:09.937335: step: 1560/527, loss: 0.0009502901812084019
2023-01-24 07:17:10.998829: step: 1564/527, loss: 0.0009792763739824295
2023-01-24 07:17:12.039192: step: 1568/527, loss: 0.0003333989589009434
2023-01-24 07:17:13.106520: step: 1572/527, loss: 3.688324795803055e-05
2023-01-24 07:17:14.157781: step: 1576/527, loss: 0.006057139951735735
2023-01-24 07:17:15.204077: step: 1580/527, loss: 0.004469339735805988
2023-01-24 07:17:16.261393: step: 1584/527, loss: 0.0034449677914381027
2023-01-24 07:17:17.312612: step: 1588/527, loss: 0.007865716703236103
2023-01-24 07:17:18.367207: step: 1592/527, loss: 0.0003162748762406409
2023-01-24 07:17:19.418445: step: 1596/527, loss: 0.010795745067298412
2023-01-24 07:17:20.466361: step: 1600/527, loss: 0.0028588275890797377
2023-01-24 07:17:21.513611: step: 1604/527, loss: 0.0023156236857175827
2023-01-24 07:17:22.554997: step: 1608/527, loss: 0.009255464188754559
2023-01-24 07:17:23.616480: step: 1612/527, loss: 0.021274641156196594
2023-01-24 07:17:24.655650: step: 1616/527, loss: 0.014407042413949966
2023-01-24 07:17:25.719028: step: 1620/527, loss: 0.014995587058365345
2023-01-24 07:17:26.781592: step: 1624/527, loss: 2.666874206624925e-05
2023-01-24 07:17:27.835005: step: 1628/527, loss: 0.038134440779685974
2023-01-24 07:17:28.901043: step: 1632/527, loss: 0.020040687173604965
2023-01-24 07:17:29.983454: step: 1636/527, loss: 0.005989911966025829
2023-01-24 07:17:31.045569: step: 1640/527, loss: 0.002983721671625972
2023-01-24 07:17:32.103615: step: 1644/527, loss: 0.015931863337755203
2023-01-24 07:17:33.146250: step: 1648/527, loss: 0.0021516289561986923
2023-01-24 07:17:34.203048: step: 1652/527, loss: 0.02262815274298191
2023-01-24 07:17:35.254054: step: 1656/527, loss: 0.0024789704475551844
2023-01-24 07:17:36.314535: step: 1660/527, loss: 0.017011869698762894
2023-01-24 07:17:37.375068: step: 1664/527, loss: 0.034133926033973694
2023-01-24 07:17:38.418199: step: 1668/527, loss: 0.023153837770223618
2023-01-24 07:17:39.472553: step: 1672/527, loss: 0.011968724429607391
2023-01-24 07:17:40.511461: step: 1676/527, loss: 0.005910203792154789
2023-01-24 07:17:41.580097: step: 1680/527, loss: 0.0025056428276002407
2023-01-24 07:17:42.618718: step: 1684/527, loss: 0.0
2023-01-24 07:17:43.687789: step: 1688/527, loss: 0.003497748402878642
2023-01-24 07:17:44.738327: step: 1692/527, loss: 0.0023310959804803133
2023-01-24 07:17:45.784660: step: 1696/527, loss: 0.003858437528833747
2023-01-24 07:17:46.836631: step: 1700/527, loss: 0.005956585053354502
2023-01-24 07:17:47.887807: step: 1704/527, loss: 0.04720918834209442
2023-01-24 07:17:48.939022: step: 1708/527, loss: 0.005280202720314264
2023-01-24 07:17:50.012794: step: 1712/527, loss: 0.004693740513175726
2023-01-24 07:17:51.058418: step: 1716/527, loss: 0.011267592199146748
2023-01-24 07:17:52.106161: step: 1720/527, loss: 0.0010155562777072191
2023-01-24 07:17:53.156836: step: 1724/527, loss: 0.004556070081889629
2023-01-24 07:17:54.217360: step: 1728/527, loss: 0.008643990382552147
2023-01-24 07:17:55.287870: step: 1732/527, loss: 0.012633326463401318
2023-01-24 07:17:56.337022: step: 1736/527, loss: 0.008252976462244987
2023-01-24 07:17:57.389707: step: 1740/527, loss: 0.0008520284900441766
2023-01-24 07:17:58.438970: step: 1744/527, loss: 0.0012677937047556043
2023-01-24 07:17:59.504323: step: 1748/527, loss: 0.0010938954073935747
2023-01-24 07:18:00.547652: step: 1752/527, loss: 0.011090392246842384
2023-01-24 07:18:01.597353: step: 1756/527, loss: 0.0
2023-01-24 07:18:02.629961: step: 1760/527, loss: 0.009472419507801533
2023-01-24 07:18:03.667794: step: 1764/527, loss: 0.0035333549603819847
2023-01-24 07:18:04.725946: step: 1768/527, loss: 0.009755841456353664
2023-01-24 07:18:05.778718: step: 1772/527, loss: 0.005978620611131191
2023-01-24 07:18:06.842021: step: 1776/527, loss: 0.004433545283973217
2023-01-24 07:18:07.878365: step: 1780/527, loss: 0.003584163961932063
2023-01-24 07:18:08.947686: step: 1784/527, loss: 0.0029540956020355225
2023-01-24 07:18:09.991145: step: 1788/527, loss: 0.005422653630375862
2023-01-24 07:18:11.044481: step: 1792/527, loss: 0.0014488842571154237
2023-01-24 07:18:12.080931: step: 1796/527, loss: 8.900416105461773e-06
2023-01-24 07:18:13.134209: step: 1800/527, loss: 0.013409025967121124
2023-01-24 07:18:14.171841: step: 1804/527, loss: 0.0002003545523621142
2023-01-24 07:18:15.235522: step: 1808/527, loss: 0.00795035157352686
2023-01-24 07:18:16.292856: step: 1812/527, loss: 0.02246682345867157
2023-01-24 07:18:17.353368: step: 1816/527, loss: 0.010253187268972397
2023-01-24 07:18:18.406702: step: 1820/527, loss: 0.02941504307091236
2023-01-24 07:18:19.461045: step: 1824/527, loss: 1.8626450382086546e-09
2023-01-24 07:18:20.505171: step: 1828/527, loss: 9.63321053859545e-06
2023-01-24 07:18:21.548387: step: 1832/527, loss: 0.0004840172769036144
2023-01-24 07:18:22.599998: step: 1836/527, loss: 0.0017071020556613803
2023-01-24 07:18:23.631415: step: 1840/527, loss: 0.005629593972116709
2023-01-24 07:18:24.679833: step: 1844/527, loss: 0.0036395310889929533
2023-01-24 07:18:25.728721: step: 1848/527, loss: 0.016531143337488174
2023-01-24 07:18:26.767892: step: 1852/527, loss: 0.0003981611516792327
2023-01-24 07:18:27.818584: step: 1856/527, loss: 0.002332820789888501
2023-01-24 07:18:28.889694: step: 1860/527, loss: 0.004095232114195824
2023-01-24 07:18:29.951096: step: 1864/527, loss: 0.00022128420823719352
2023-01-24 07:18:31.012070: step: 1868/527, loss: 0.0004512519226409495
2023-01-24 07:18:32.080141: step: 1872/527, loss: 0.07282253354787827
2023-01-24 07:18:33.117256: step: 1876/527, loss: 0.006818498019129038
2023-01-24 07:18:34.171980: step: 1880/527, loss: 0.000982586294412613
2023-01-24 07:18:35.223954: step: 1884/527, loss: 0.0008853274630382657
2023-01-24 07:18:36.303131: step: 1888/527, loss: 0.003433793317526579
2023-01-24 07:18:37.361279: step: 1892/527, loss: 0.006716647185385227
2023-01-24 07:18:38.409621: step: 1896/527, loss: 0.0017021086532622576
2023-01-24 07:18:39.456047: step: 1900/527, loss: 0.00382750341668725
2023-01-24 07:18:40.500030: step: 1904/527, loss: 0.0021611934062093496
2023-01-24 07:18:41.552818: step: 1908/527, loss: 0.011224180459976196
2023-01-24 07:18:42.616657: step: 1912/527, loss: 0.008924460969865322
2023-01-24 07:18:43.669513: step: 1916/527, loss: 0.007336306385695934
2023-01-24 07:18:44.724951: step: 1920/527, loss: 0.001474024960771203
2023-01-24 07:18:45.763775: step: 1924/527, loss: 0.007357365917414427
2023-01-24 07:18:46.806272: step: 1928/527, loss: 0.00017077891970984638
2023-01-24 07:18:47.853635: step: 1932/527, loss: 0.006330475211143494
2023-01-24 07:18:48.898958: step: 1936/527, loss: 0.007395185064524412
2023-01-24 07:18:49.974094: step: 1940/527, loss: 0.00021674064919352531
2023-01-24 07:18:51.025933: step: 1944/527, loss: 0.01223550271242857
2023-01-24 07:18:52.081473: step: 1948/527, loss: 0.12603196501731873
2023-01-24 07:18:53.125015: step: 1952/527, loss: 0.0003739767416846007
2023-01-24 07:18:54.194698: step: 1956/527, loss: 0.0018462217412889004
2023-01-24 07:18:55.253981: step: 1960/527, loss: 0.006662336643785238
2023-01-24 07:18:56.302378: step: 1964/527, loss: 0.003399134613573551
2023-01-24 07:18:57.362464: step: 1968/527, loss: 0.02375180274248123
2023-01-24 07:18:58.420706: step: 1972/527, loss: 0.002270856872200966
2023-01-24 07:18:59.471552: step: 1976/527, loss: 0.006422302220016718
2023-01-24 07:19:00.531154: step: 1980/527, loss: 0.04472963139414787
2023-01-24 07:19:01.588823: step: 1984/527, loss: 0.006703260354697704
2023-01-24 07:19:02.647053: step: 1988/527, loss: 0.00034308084286749363
2023-01-24 07:19:03.701500: step: 1992/527, loss: 0.00012687459820881486
2023-01-24 07:19:04.742968: step: 1996/527, loss: 0.0035361372865736485
2023-01-24 07:19:05.797745: step: 2000/527, loss: 0.006403637584298849
2023-01-24 07:19:06.854912: step: 2004/527, loss: 0.0037350535858422518
2023-01-24 07:19:07.918757: step: 2008/527, loss: 0.0022046868689358234
2023-01-24 07:19:08.982984: step: 2012/527, loss: 0.001493731397204101
2023-01-24 07:19:10.022325: step: 2016/527, loss: 0.0017241832101717591
2023-01-24 07:19:11.064206: step: 2020/527, loss: 0.0029128578025847673
2023-01-24 07:19:12.130248: step: 2024/527, loss: 0.0016437429003417492
2023-01-24 07:19:13.183336: step: 2028/527, loss: 0.005673205945640802
2023-01-24 07:19:14.223016: step: 2032/527, loss: 0.002791368868201971
2023-01-24 07:19:15.277052: step: 2036/527, loss: 0.0009393185609951615
2023-01-24 07:19:16.338174: step: 2040/527, loss: 0.0020621151197701693
2023-01-24 07:19:17.412681: step: 2044/527, loss: 0.007466120179742575
2023-01-24 07:19:18.462315: step: 2048/527, loss: 0.009691721759736538
2023-01-24 07:19:19.547528: step: 2052/527, loss: 0.005073025822639465
2023-01-24 07:19:20.586142: step: 2056/527, loss: 0.0054930225014686584
2023-01-24 07:19:21.631631: step: 2060/527, loss: 0.007369012571871281
2023-01-24 07:19:22.679649: step: 2064/527, loss: 0.0012249633437022567
2023-01-24 07:19:23.744024: step: 2068/527, loss: 0.0011255674762651324
2023-01-24 07:19:24.785741: step: 2072/527, loss: 0.002401367761194706
2023-01-24 07:19:25.834785: step: 2076/527, loss: 0.0006509974482469261
2023-01-24 07:19:26.878978: step: 2080/527, loss: 0.0022482527419924736
2023-01-24 07:19:27.928552: step: 2084/527, loss: 0.0009043293539434671
2023-01-24 07:19:28.980717: step: 2088/527, loss: 0.00888520572334528
2023-01-24 07:19:30.037329: step: 2092/527, loss: 0.002215207554399967
2023-01-24 07:19:31.084036: step: 2096/527, loss: 0.00013173124170862138
2023-01-24 07:19:32.143425: step: 2100/527, loss: 0.0006686710985377431
2023-01-24 07:19:33.193011: step: 2104/527, loss: 0.0010806603822857141
2023-01-24 07:19:34.241765: step: 2108/527, loss: 0.025548676028847694
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34441654411764705, 'r': 0.32677091472262526, 'f1': 0.33536177616129215}, 'combined': 0.2471086771714784, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3794837672549217, 'r': 0.2932374565151668, 'f1': 0.33083200222223946}, 'combined': 0.21173248142223322, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35957230142566193, 'r': 0.33500948766603417, 'f1': 0.3468565815324165}, 'combined': 0.2555785337607279, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37873037902298035, 'r': 0.30718095228657716, 'f1': 0.3392239001680255}, 'combined': 0.2171032961075363, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3633951957540667, 'r': 0.32271148313643877, 'f1': 0.3418471389204085}, 'combined': 0.251887365520301, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3860778437389428, 'r': 0.3121705081097924, 'f1': 0.3452127493915749}, 'combined': 0.2475110278656575, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36325359749028163, 'r': 0.3260321662483932, 'f1': 0.3436379032258064}, 'combined': 0.25320687606112047, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827405873011607, 'r': 0.313309979395116, 'f1': 0.344562453530268}, 'combined': 0.24704477800283367, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
******************************
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
2023-01-24 07:22:04.879960: step: 4/527, loss: 0.007619322277605534
2023-01-24 07:22:05.932216: step: 8/527, loss: 0.005011274013668299
2023-01-24 07:22:06.983711: step: 12/527, loss: 0.010464202612638474
2023-01-24 07:22:08.027770: step: 16/527, loss: 0.005930216051638126
2023-01-24 07:22:09.074346: step: 20/527, loss: 0.0049021546728909016
2023-01-24 07:22:10.110874: step: 24/527, loss: 0.000686881598085165
2023-01-24 07:22:11.153217: step: 28/527, loss: 2.834871156665031e-05
2023-01-24 07:22:12.205416: step: 32/527, loss: 0.0025016057770699263
2023-01-24 07:22:13.253890: step: 36/527, loss: 0.0003890406514983624
2023-01-24 07:22:14.310572: step: 40/527, loss: 0.0021663017105311155
2023-01-24 07:22:15.362993: step: 44/527, loss: 0.0022376582492142916
2023-01-24 07:22:16.417991: step: 48/527, loss: 0.003644646843895316
2023-01-24 07:22:17.471727: step: 52/527, loss: 0.0018524817423895001
2023-01-24 07:22:18.537606: step: 56/527, loss: 0.003466264344751835
2023-01-24 07:22:19.582109: step: 60/527, loss: 0.00041731770033948123
2023-01-24 07:22:20.629678: step: 64/527, loss: 0.0034938897006213665
2023-01-24 07:22:21.658156: step: 68/527, loss: 0.003241848200559616
2023-01-24 07:22:22.721238: step: 72/527, loss: 0.005263487342745066
2023-01-24 07:22:23.773731: step: 76/527, loss: 0.00880734995007515
2023-01-24 07:22:24.810986: step: 80/527, loss: 0.0012290183221921325
2023-01-24 07:22:25.848006: step: 84/527, loss: 0.005908619612455368
2023-01-24 07:22:26.896850: step: 88/527, loss: 0.0076753199100494385
2023-01-24 07:22:27.961965: step: 92/527, loss: 0.014141412451863289
2023-01-24 07:22:29.027547: step: 96/527, loss: 0.0033978584688156843
2023-01-24 07:22:30.091310: step: 100/527, loss: 0.00019484110816847533
2023-01-24 07:22:31.148308: step: 104/527, loss: 0.003944715950638056
2023-01-24 07:22:32.209830: step: 108/527, loss: 0.0020148225594311953
2023-01-24 07:22:33.271440: step: 112/527, loss: 0.005602751858532429
2023-01-24 07:22:34.322708: step: 116/527, loss: 0.0020726402290165424
2023-01-24 07:22:35.381427: step: 120/527, loss: 0.00225808285176754
2023-01-24 07:22:36.439498: step: 124/527, loss: 0.001250948291271925
2023-01-24 07:22:37.490371: step: 128/527, loss: 0.03231208398938179
2023-01-24 07:22:38.536892: step: 132/527, loss: 0.001055886852554977
2023-01-24 07:22:39.585786: step: 136/527, loss: 0.018326491117477417
2023-01-24 07:22:40.650788: step: 140/527, loss: 0.0023968794848769903
2023-01-24 07:22:41.703146: step: 144/527, loss: 0.0008112549548968673
2023-01-24 07:22:42.751829: step: 148/527, loss: 0.002209191909059882
2023-01-24 07:22:43.794785: step: 152/527, loss: 0.0023432201705873013
2023-01-24 07:22:44.828747: step: 156/527, loss: 0.009897831827402115
2023-01-24 07:22:45.889679: step: 160/527, loss: 0.004624166525900364
2023-01-24 07:22:46.922290: step: 164/527, loss: 0.007766325492411852
2023-01-24 07:22:47.995803: step: 168/527, loss: 0.005127053242176771
2023-01-24 07:22:49.037011: step: 172/527, loss: 0.008108958601951599
2023-01-24 07:22:50.083976: step: 176/527, loss: 0.0010407913941890001
2023-01-24 07:22:51.136225: step: 180/527, loss: 0.0027981160674244165
2023-01-24 07:22:52.189939: step: 184/527, loss: 0.0007031296263448894
2023-01-24 07:22:53.238106: step: 188/527, loss: 0.0025272162165492773
2023-01-24 07:22:54.290735: step: 192/527, loss: 0.00016711748321540654
2023-01-24 07:22:55.325437: step: 196/527, loss: 1.261873148905579e-05
2023-01-24 07:22:56.389347: step: 200/527, loss: 0.0031699826940894127
2023-01-24 07:22:57.429318: step: 204/527, loss: 0.0019168907310813665
2023-01-24 07:22:58.477404: step: 208/527, loss: 0.001322442665696144
2023-01-24 07:22:59.541975: step: 212/527, loss: 0.014579384587705135
2023-01-24 07:23:00.583025: step: 216/527, loss: 0.0036112028174102306
2023-01-24 07:23:01.640669: step: 220/527, loss: 0.02042965032160282
2023-01-24 07:23:02.709104: step: 224/527, loss: 0.0037181549705564976
2023-01-24 07:23:03.778216: step: 228/527, loss: 0.003545230021700263
2023-01-24 07:23:04.824668: step: 232/527, loss: 0.00016019395843613893
2023-01-24 07:23:05.880284: step: 236/527, loss: 0.005952728446573019
2023-01-24 07:23:06.937723: step: 240/527, loss: 0.0032371790148317814
2023-01-24 07:23:07.991673: step: 244/527, loss: 0.0030368592124432325
2023-01-24 07:23:09.053813: step: 248/527, loss: 0.001996848499402404
2023-01-24 07:23:10.096979: step: 252/527, loss: 0.0027342450339347124
2023-01-24 07:23:11.159840: step: 256/527, loss: 0.0003024438628926873
2023-01-24 07:23:12.228540: step: 260/527, loss: 0.003370189107954502
2023-01-24 07:23:13.292978: step: 264/527, loss: 0.0047250972129404545
2023-01-24 07:23:14.355279: step: 268/527, loss: 0.004215765278786421
2023-01-24 07:23:15.405967: step: 272/527, loss: 0.000495637534186244
2023-01-24 07:23:16.473565: step: 276/527, loss: 0.010135481134057045
2023-01-24 07:23:17.519626: step: 280/527, loss: 0.0017686393111944199
2023-01-24 07:23:18.576499: step: 284/527, loss: 0.009661720134317875
2023-01-24 07:23:19.638781: step: 288/527, loss: 0.00840539950877428
2023-01-24 07:23:20.704398: step: 292/527, loss: 0.0058349426835775375
2023-01-24 07:23:21.751748: step: 296/527, loss: 0.002013220451772213
2023-01-24 07:23:22.839167: step: 300/527, loss: 0.0010815411806106567
2023-01-24 07:23:23.885219: step: 304/527, loss: 0.0010543304961174726
2023-01-24 07:23:24.930914: step: 308/527, loss: 0.0016437410376966
2023-01-24 07:23:25.980727: step: 312/527, loss: 0.0036136480048298836
2023-01-24 07:23:27.036094: step: 316/527, loss: 0.008142869919538498
2023-01-24 07:23:28.085523: step: 320/527, loss: 0.0016600724775344133
2023-01-24 07:23:29.136187: step: 324/527, loss: 0.0037983183283358812
2023-01-24 07:23:30.195740: step: 328/527, loss: 0.0028913291171193123
2023-01-24 07:23:31.248018: step: 332/527, loss: 0.010967910289764404
2023-01-24 07:23:32.304876: step: 336/527, loss: 0.018941832706332207
2023-01-24 07:23:33.358947: step: 340/527, loss: 0.0037054328713566065
2023-01-24 07:23:34.414348: step: 344/527, loss: 0.00010407343506813049
2023-01-24 07:23:35.467426: step: 348/527, loss: 0.0033731076400727034
2023-01-24 07:23:36.512168: step: 352/527, loss: 0.003104487666860223
2023-01-24 07:23:37.565038: step: 356/527, loss: 0.002900853054597974
2023-01-24 07:23:38.621734: step: 360/527, loss: 0.0010574869811534882
2023-01-24 07:23:39.687649: step: 364/527, loss: 0.00032582986750639975
2023-01-24 07:23:40.738853: step: 368/527, loss: 0.0008039302774704993
2023-01-24 07:23:41.797158: step: 372/527, loss: 0.0005461260443553329
2023-01-24 07:23:42.854289: step: 376/527, loss: 0.002027584007009864
2023-01-24 07:23:43.924959: step: 380/527, loss: 0.0006290959427133203
2023-01-24 07:23:44.973219: step: 384/527, loss: 0.005801249761134386
2023-01-24 07:23:46.044601: step: 388/527, loss: 0.005603089462965727
2023-01-24 07:23:47.097227: step: 392/527, loss: 0.008031330071389675
2023-01-24 07:23:48.153469: step: 396/527, loss: 0.003185323206707835
2023-01-24 07:23:49.225132: step: 400/527, loss: 0.0005803056410513818
2023-01-24 07:23:50.278423: step: 404/527, loss: 0.009660094976425171
2023-01-24 07:23:51.337817: step: 408/527, loss: 6.6267039073864e-06
2023-01-24 07:23:52.388824: step: 412/527, loss: 0.0030033146031200886
2023-01-24 07:23:53.438685: step: 416/527, loss: 9.05255728866905e-05
2023-01-24 07:23:54.500729: step: 420/527, loss: 0.01953630894422531
2023-01-24 07:23:55.558767: step: 424/527, loss: 0.0003336553636472672
2023-01-24 07:23:56.624284: step: 428/527, loss: 0.0024180535692721605
2023-01-24 07:23:57.700446: step: 432/527, loss: 0.004492941312491894
2023-01-24 07:23:58.760212: step: 436/527, loss: 0.0039434912614524364
2023-01-24 07:23:59.804013: step: 440/527, loss: 0.00026417331537231803
2023-01-24 07:24:00.859665: step: 444/527, loss: 0.001785318716429174
2023-01-24 07:24:01.920189: step: 448/527, loss: 0.0029834997840225697
2023-01-24 07:24:02.960381: step: 452/527, loss: 0.005437122192233801
2023-01-24 07:24:04.015039: step: 456/527, loss: 0.003403643611818552
2023-01-24 07:24:05.067852: step: 460/527, loss: 0.003753100521862507
2023-01-24 07:24:06.107864: step: 464/527, loss: 0.010964242741465569
2023-01-24 07:24:07.168330: step: 468/527, loss: 0.011434354819357395
2023-01-24 07:24:08.225770: step: 472/527, loss: 9.458821295993403e-05
2023-01-24 07:24:09.288403: step: 476/527, loss: 0.002572170225903392
2023-01-24 07:24:10.344051: step: 480/527, loss: 0.00017540385306347162
2023-01-24 07:24:11.416582: step: 484/527, loss: 0.005281957797706127
2023-01-24 07:24:12.459158: step: 488/527, loss: 0.004321059677749872
2023-01-24 07:24:13.517925: step: 492/527, loss: 0.002527425065636635
2023-01-24 07:24:14.555810: step: 496/527, loss: 0.010908177122473717
2023-01-24 07:24:15.614116: step: 500/527, loss: 0.0002724303340073675
2023-01-24 07:24:16.670060: step: 504/527, loss: 0.0001880708005046472
2023-01-24 07:24:17.720779: step: 508/527, loss: 0.0011116022942587733
2023-01-24 07:24:18.802038: step: 512/527, loss: 0.034606996923685074
2023-01-24 07:24:19.866022: step: 516/527, loss: 0.005533210933208466
2023-01-24 07:24:20.920644: step: 520/527, loss: 0.0018650231650099158
2023-01-24 07:24:21.978270: step: 524/527, loss: 0.003876227419823408
2023-01-24 07:24:23.038316: step: 528/527, loss: 0.002837592037394643
2023-01-24 07:24:24.082794: step: 532/527, loss: 0.008782900869846344
2023-01-24 07:24:25.145718: step: 536/527, loss: 0.004077088087797165
2023-01-24 07:24:26.223136: step: 540/527, loss: 0.002331398893147707
2023-01-24 07:24:27.273386: step: 544/527, loss: 0.014300593174993992
2023-01-24 07:24:28.324170: step: 548/527, loss: 0.0003353523788973689
2023-01-24 07:24:29.371138: step: 552/527, loss: 0.010083137080073357
2023-01-24 07:24:30.435766: step: 556/527, loss: 0.01390083134174347
2023-01-24 07:24:31.508638: step: 560/527, loss: 0.0004276926629245281
2023-01-24 07:24:32.563583: step: 564/527, loss: 0.007978932932019234
2023-01-24 07:24:33.620429: step: 568/527, loss: 0.061783596873283386
2023-01-24 07:24:34.676789: step: 572/527, loss: 0.0029477113857865334
2023-01-24 07:24:35.750072: step: 576/527, loss: 0.005164923146367073
2023-01-24 07:24:36.810401: step: 580/527, loss: 0.006764416582882404
2023-01-24 07:24:37.854842: step: 584/527, loss: 0.0011231843382120132
2023-01-24 07:24:38.903070: step: 588/527, loss: 0.0010017876047641039
2023-01-24 07:24:39.952394: step: 592/527, loss: 0.004956105258315802
2023-01-24 07:24:41.000439: step: 596/527, loss: 0.0014087819727137685
2023-01-24 07:24:42.063914: step: 600/527, loss: 0.010600045323371887
2023-01-24 07:24:43.117683: step: 604/527, loss: 0.00046931247925385833
2023-01-24 07:24:44.182235: step: 608/527, loss: 0.006964202504605055
2023-01-24 07:24:45.217860: step: 612/527, loss: 0.0026729705277830362
2023-01-24 07:24:46.258679: step: 616/527, loss: 0.0
2023-01-24 07:24:47.319170: step: 620/527, loss: 0.0014651769306510687
2023-01-24 07:24:48.380581: step: 624/527, loss: 0.00011985751916654408
2023-01-24 07:24:49.459014: step: 628/527, loss: 8.332579454872757e-05
2023-01-24 07:24:50.520042: step: 632/527, loss: 0.002799414563924074
2023-01-24 07:24:51.564108: step: 636/527, loss: 0.0007252858486026525
2023-01-24 07:24:52.601130: step: 640/527, loss: 0.0027340000960975885
2023-01-24 07:24:53.659510: step: 644/527, loss: 0.0022030228283256292
2023-01-24 07:24:54.744950: step: 648/527, loss: 0.002237871289253235
2023-01-24 07:24:55.804892: step: 652/527, loss: 0.0017605915199965239
2023-01-24 07:24:56.849144: step: 656/527, loss: 0.0027358876541256905
2023-01-24 07:24:57.902480: step: 660/527, loss: 0.004454437177628279
2023-01-24 07:24:58.955068: step: 664/527, loss: 0.002043404383584857
2023-01-24 07:25:00.006676: step: 668/527, loss: 0.00566945131868124
2023-01-24 07:25:01.049799: step: 672/527, loss: 0.009340194053947926
2023-01-24 07:25:02.110219: step: 676/527, loss: 0.008716157637536526
2023-01-24 07:25:03.157592: step: 680/527, loss: 0.021269943565130234
2023-01-24 07:25:04.222229: step: 684/527, loss: 0.0001597239461261779
2023-01-24 07:25:05.292691: step: 688/527, loss: 0.008474440313875675
2023-01-24 07:25:06.338484: step: 692/527, loss: 0.005262911319732666
2023-01-24 07:25:07.392318: step: 696/527, loss: 0.003303262172266841
2023-01-24 07:25:08.449214: step: 700/527, loss: 0.011588364839553833
2023-01-24 07:25:09.509424: step: 704/527, loss: 0.001971333986148238
2023-01-24 07:25:10.570106: step: 708/527, loss: 0.000131136694108136
2023-01-24 07:25:11.614401: step: 712/527, loss: 0.013067991472780704
2023-01-24 07:25:12.667581: step: 716/527, loss: 0.010408147238194942
2023-01-24 07:25:13.735998: step: 720/527, loss: 0.005840797442942858
2023-01-24 07:25:14.793005: step: 724/527, loss: 0.0010175163624808192
2023-01-24 07:25:15.836189: step: 728/527, loss: 0.003741353750228882
2023-01-24 07:25:16.883139: step: 732/527, loss: 0.0028500924818217754
2023-01-24 07:25:17.947997: step: 736/527, loss: 0.013644230552017689
2023-01-24 07:25:19.006331: step: 740/527, loss: 0.004073255229741335
2023-01-24 07:25:20.060571: step: 744/527, loss: 0.002723877551034093
2023-01-24 07:25:21.112656: step: 748/527, loss: 0.005280986428260803
2023-01-24 07:25:22.180927: step: 752/527, loss: 0.008070048876106739
2023-01-24 07:25:23.234264: step: 756/527, loss: 0.0037095113657414913
2023-01-24 07:25:24.278836: step: 760/527, loss: 0.0026983425486832857
2023-01-24 07:25:25.312224: step: 764/527, loss: 0.0002139671560144052
2023-01-24 07:25:26.352387: step: 768/527, loss: 6.828071946074488e-06
2023-01-24 07:25:27.419730: step: 772/527, loss: 0.013572442345321178
2023-01-24 07:25:28.473893: step: 776/527, loss: 0.003095896914601326
2023-01-24 07:25:29.529602: step: 780/527, loss: 0.010774532333016396
2023-01-24 07:25:30.600983: step: 784/527, loss: 0.008064789697527885
2023-01-24 07:25:31.649373: step: 788/527, loss: 0.006426256150007248
2023-01-24 07:25:32.685915: step: 792/527, loss: 5.289889770665468e-08
2023-01-24 07:25:33.741889: step: 796/527, loss: 0.0007420787587761879
2023-01-24 07:25:34.800540: step: 800/527, loss: 0.006745407823473215
2023-01-24 07:25:35.861612: step: 804/527, loss: 0.001343736657872796
2023-01-24 07:25:36.908473: step: 808/527, loss: 0.00011648951476672664
2023-01-24 07:25:37.980663: step: 812/527, loss: 8.425141277257353e-05
2023-01-24 07:25:39.039535: step: 816/527, loss: 0.011028146371245384
2023-01-24 07:25:40.096021: step: 820/527, loss: 0.005218501202762127
2023-01-24 07:25:41.146610: step: 824/527, loss: 0.014840721152722836
2023-01-24 07:25:42.205891: step: 828/527, loss: 7.502801963710226e-06
2023-01-24 07:25:43.277150: step: 832/527, loss: 0.0010546231642365456
2023-01-24 07:25:44.328225: step: 836/527, loss: 0.000891447183676064
2023-01-24 07:25:45.396314: step: 840/527, loss: 0.01074120495468378
2023-01-24 07:25:46.437738: step: 844/527, loss: 0.004925885703414679
2023-01-24 07:25:47.482179: step: 848/527, loss: 0.024480372667312622
2023-01-24 07:25:48.522277: step: 852/527, loss: 0.010799067094922066
2023-01-24 07:25:49.571167: step: 856/527, loss: 0.0032312916591763496
2023-01-24 07:25:50.614224: step: 860/527, loss: 0.0007931143627502024
2023-01-24 07:25:51.647142: step: 864/527, loss: 0.011013202369213104
2023-01-24 07:25:52.688829: step: 868/527, loss: 0.005142250098288059
2023-01-24 07:25:53.758885: step: 872/527, loss: 0.005670530721545219
2023-01-24 07:25:54.809452: step: 876/527, loss: 0.004671367816627026
2023-01-24 07:25:55.871819: step: 880/527, loss: 0.000959213706664741
2023-01-24 07:25:56.942059: step: 884/527, loss: 0.006375072058290243
2023-01-24 07:25:57.999000: step: 888/527, loss: 0.03924502432346344
2023-01-24 07:25:59.078285: step: 892/527, loss: 0.005271376576274633
2023-01-24 07:26:00.120445: step: 896/527, loss: 0.0026893827598541975
2023-01-24 07:26:01.169650: step: 900/527, loss: 0.026787694543600082
2023-01-24 07:26:02.202346: step: 904/527, loss: 0.001120428554713726
2023-01-24 07:26:03.252764: step: 908/527, loss: 0.0062246788293123245
2023-01-24 07:26:04.297465: step: 912/527, loss: 0.005336942616850138
2023-01-24 07:26:05.353101: step: 916/527, loss: 0.0066856094636023045
2023-01-24 07:26:06.402137: step: 920/527, loss: 0.008613454177975655
2023-01-24 07:26:07.449463: step: 924/527, loss: 0.007455340586602688
2023-01-24 07:26:08.517344: step: 928/527, loss: 0.009863438084721565
2023-01-24 07:26:09.562827: step: 932/527, loss: 0.00613413518294692
2023-01-24 07:26:10.616123: step: 936/527, loss: 0.001392399426549673
2023-01-24 07:26:11.661360: step: 940/527, loss: 0.026021713390946388
2023-01-24 07:26:12.719780: step: 944/527, loss: 0.01770760491490364
2023-01-24 07:26:13.776748: step: 948/527, loss: 0.001510394155047834
2023-01-24 07:26:14.824169: step: 952/527, loss: 0.0011424239492043853
2023-01-24 07:26:15.870675: step: 956/527, loss: 0.0014410935109481215
2023-01-24 07:26:16.905026: step: 960/527, loss: 0.008240103721618652
2023-01-24 07:26:17.962919: step: 964/527, loss: 0.00755185866728425
2023-01-24 07:26:19.011990: step: 968/527, loss: 0.017570147290825844
2023-01-24 07:26:20.073996: step: 972/527, loss: 0.0007693552761338651
2023-01-24 07:26:21.127544: step: 976/527, loss: 0.01756575144827366
2023-01-24 07:26:22.169167: step: 980/527, loss: 0.0020110842306166887
2023-01-24 07:26:23.231717: step: 984/527, loss: 0.03568197041749954
2023-01-24 07:26:24.278773: step: 988/527, loss: 0.003300323849543929
2023-01-24 07:26:25.324012: step: 992/527, loss: 0.0
2023-01-24 07:26:26.386039: step: 996/527, loss: 0.00432737497612834
2023-01-24 07:26:27.431647: step: 1000/527, loss: 0.008678669109940529
2023-01-24 07:26:28.503219: step: 1004/527, loss: 0.0007442276692017913
2023-01-24 07:26:29.538101: step: 1008/527, loss: 0.003179546445608139
2023-01-24 07:26:30.593871: step: 1012/527, loss: 0.013082008808851242
2023-01-24 07:26:31.638661: step: 1016/527, loss: 0.0035641989670693874
2023-01-24 07:26:32.690451: step: 1020/527, loss: 0.003280684817582369
2023-01-24 07:26:33.733470: step: 1024/527, loss: 0.005581994540989399
2023-01-24 07:26:34.792418: step: 1028/527, loss: 0.0002273622085340321
2023-01-24 07:26:35.844695: step: 1032/527, loss: 0.005484454333782196
2023-01-24 07:26:36.886206: step: 1036/527, loss: 0.0009807702153921127
2023-01-24 07:26:37.944597: step: 1040/527, loss: 0.0002478167007211596
2023-01-24 07:26:38.989772: step: 1044/527, loss: 0.00014708031085319817
2023-01-24 07:26:40.041005: step: 1048/527, loss: 0.003240023972466588
2023-01-24 07:26:41.099150: step: 1052/527, loss: 0.0016205157153308392
2023-01-24 07:26:42.152073: step: 1056/527, loss: 0.011959646828472614
2023-01-24 07:26:43.194874: step: 1060/527, loss: 0.0013968355488032103
2023-01-24 07:26:44.238242: step: 1064/527, loss: 0.004498990252614021
2023-01-24 07:26:45.280070: step: 1068/527, loss: 0.0038817673921585083
2023-01-24 07:26:46.345112: step: 1072/527, loss: 0.002550655510276556
2023-01-24 07:26:47.393159: step: 1076/527, loss: 0.007548233028501272
2023-01-24 07:26:48.437211: step: 1080/527, loss: 0.007035511080175638
2023-01-24 07:26:49.488239: step: 1084/527, loss: 0.0053145186975598335
2023-01-24 07:26:50.532941: step: 1088/527, loss: 0.010060529224574566
2023-01-24 07:26:51.578581: step: 1092/527, loss: 0.02936890535056591
2023-01-24 07:26:52.606965: step: 1096/527, loss: 0.008506453596055508
2023-01-24 07:26:53.658470: step: 1100/527, loss: 4.393312337924726e-05
2023-01-24 07:26:54.715589: step: 1104/527, loss: 0.0011915852082893252
2023-01-24 07:26:55.767891: step: 1108/527, loss: 0.004857954103499651
2023-01-24 07:26:56.816220: step: 1112/527, loss: 0.021052666008472443
2023-01-24 07:26:57.854963: step: 1116/527, loss: 0.001208293717354536
2023-01-24 07:26:58.908896: step: 1120/527, loss: 0.005073441658169031
2023-01-24 07:26:59.952795: step: 1124/527, loss: 0.0018664358649402857
2023-01-24 07:27:01.012551: step: 1128/527, loss: 0.008032937534153461
2023-01-24 07:27:02.066762: step: 1132/527, loss: 0.0012455241521820426
2023-01-24 07:27:03.110126: step: 1136/527, loss: 0.009927546605467796
2023-01-24 07:27:04.150350: step: 1140/527, loss: 0.005889351014047861
2023-01-24 07:27:05.201633: step: 1144/527, loss: 0.0036864392459392548
2023-01-24 07:27:06.249042: step: 1148/527, loss: 0.00022810317750554532
2023-01-24 07:27:07.307913: step: 1152/527, loss: 0.004580994602292776
2023-01-24 07:27:08.362809: step: 1156/527, loss: 0.00515025295317173
2023-01-24 07:27:09.409526: step: 1160/527, loss: 0.0056029437109827995
2023-01-24 07:27:10.471686: step: 1164/527, loss: 0.001773229567334056
2023-01-24 07:27:11.542198: step: 1168/527, loss: 0.005558577831834555
2023-01-24 07:27:12.607556: step: 1172/527, loss: 0.001237261458300054
2023-01-24 07:27:13.649086: step: 1176/527, loss: 0.010743043385446072
2023-01-24 07:27:14.700807: step: 1180/527, loss: 0.010249967686831951
2023-01-24 07:27:15.746624: step: 1184/527, loss: 0.010876132175326347
2023-01-24 07:27:16.787653: step: 1188/527, loss: 0.0008464209968224168
2023-01-24 07:27:17.848551: step: 1192/527, loss: 0.002634631237015128
2023-01-24 07:27:18.890049: step: 1196/527, loss: 0.013846343383193016
2023-01-24 07:27:19.959922: step: 1200/527, loss: 0.002021439140662551
2023-01-24 07:27:21.027862: step: 1204/527, loss: 0.009759816341102123
2023-01-24 07:27:22.068209: step: 1208/527, loss: 0.0010770554654300213
2023-01-24 07:27:23.126592: step: 1212/527, loss: 0.00042460692930035293
2023-01-24 07:27:24.189126: step: 1216/527, loss: 0.0009167081443592906
2023-01-24 07:27:25.237358: step: 1220/527, loss: 0.0001087384152924642
2023-01-24 07:27:26.284782: step: 1224/527, loss: 0.004979348741471767
2023-01-24 07:27:27.311657: step: 1228/527, loss: 3.911551971214067e-08
2023-01-24 07:27:28.365255: step: 1232/527, loss: 0.0026819936465471983
2023-01-24 07:27:29.423492: step: 1236/527, loss: 0.03157117962837219
2023-01-24 07:27:30.469669: step: 1240/527, loss: 0.0099434033036232
2023-01-24 07:27:31.500699: step: 1244/527, loss: 0.010909296572208405
2023-01-24 07:27:32.575659: step: 1248/527, loss: 0.0003375186352059245
2023-01-24 07:27:33.636436: step: 1252/527, loss: 0.009656017646193504
2023-01-24 07:27:34.676730: step: 1256/527, loss: 0.007953505031764507
2023-01-24 07:27:35.729222: step: 1260/527, loss: 0.000923018204048276
2023-01-24 07:27:36.772223: step: 1264/527, loss: 0.0007859493489377201
2023-01-24 07:27:37.838601: step: 1268/527, loss: 0.00659319618716836
2023-01-24 07:27:38.895605: step: 1272/527, loss: 0.005343630909919739
2023-01-24 07:27:39.953457: step: 1276/527, loss: 0.0026983299758285284
2023-01-24 07:27:41.006143: step: 1280/527, loss: 0.004379732999950647
2023-01-24 07:27:42.062652: step: 1284/527, loss: 0.005964973941445351
2023-01-24 07:27:43.121023: step: 1288/527, loss: 0.016330217942595482
2023-01-24 07:27:44.172255: step: 1292/527, loss: 0.014876273460686207
2023-01-24 07:27:45.224085: step: 1296/527, loss: 0.0007380720926448703
2023-01-24 07:27:46.283679: step: 1300/527, loss: 0.001835113624110818
2023-01-24 07:27:47.353372: step: 1304/527, loss: 0.006024368107318878
2023-01-24 07:27:48.401130: step: 1308/527, loss: 0.006383189000189304
2023-01-24 07:27:49.464305: step: 1312/527, loss: 0.0031941768247634172
2023-01-24 07:27:50.507188: step: 1316/527, loss: 0.0003681556845549494
2023-01-24 07:27:51.550794: step: 1320/527, loss: 0.005898060742765665
2023-01-24 07:27:52.600068: step: 1324/527, loss: 0.0002862276742234826
2023-01-24 07:27:53.658389: step: 1328/527, loss: 0.0005839465302415192
2023-01-24 07:27:54.703459: step: 1332/527, loss: 0.005359964445233345
2023-01-24 07:27:55.744054: step: 1336/527, loss: 0.0004397186858113855
2023-01-24 07:27:56.778536: step: 1340/527, loss: 0.02376655861735344
2023-01-24 07:27:57.817959: step: 1344/527, loss: 0.004204253200441599
2023-01-24 07:27:58.860423: step: 1348/527, loss: 0.003517820965498686
2023-01-24 07:27:59.905027: step: 1352/527, loss: 0.003728880314156413
2023-01-24 07:28:00.945416: step: 1356/527, loss: 0.002548638265579939
2023-01-24 07:28:01.979245: step: 1360/527, loss: 0.0005844628321938217
2023-01-24 07:28:03.028300: step: 1364/527, loss: 0.0010275651002302766
2023-01-24 07:28:04.081898: step: 1368/527, loss: 0.004601018503308296
2023-01-24 07:28:05.138036: step: 1372/527, loss: 0.01771286316215992
2023-01-24 07:28:06.167638: step: 1376/527, loss: 6.794201681259437e-07
2023-01-24 07:28:07.220738: step: 1380/527, loss: 0.004671482834964991
2023-01-24 07:28:08.274984: step: 1384/527, loss: 0.00662675965577364
2023-01-24 07:28:09.348833: step: 1388/527, loss: 0.006327507551759481
2023-01-24 07:28:10.391734: step: 1392/527, loss: 0.006102381274104118
2023-01-24 07:28:11.444252: step: 1396/527, loss: 0.006286056712269783
2023-01-24 07:28:12.505560: step: 1400/527, loss: 0.0021835649386048317
2023-01-24 07:28:13.547896: step: 1404/527, loss: 0.011712766252458096
2023-01-24 07:28:14.590338: step: 1408/527, loss: 0.0
2023-01-24 07:28:15.658847: step: 1412/527, loss: 0.006227034144103527
2023-01-24 07:28:16.702399: step: 1416/527, loss: 0.004639971069991589
2023-01-24 07:28:17.758503: step: 1420/527, loss: 0.0032423525117337704
2023-01-24 07:28:18.822913: step: 1424/527, loss: 6.131846475909697e-06
2023-01-24 07:28:19.847507: step: 1428/527, loss: 0.003998455125838518
2023-01-24 07:28:20.897115: step: 1432/527, loss: 0.009648646228015423
2023-01-24 07:28:21.957776: step: 1436/527, loss: 0.004501263611018658
2023-01-24 07:28:23.002794: step: 1440/527, loss: 0.00038856532773934305
2023-01-24 07:28:24.052569: step: 1444/527, loss: 0.0039667836390435696
2023-01-24 07:28:25.093644: step: 1448/527, loss: 0.0003916067071259022
2023-01-24 07:28:26.139946: step: 1452/527, loss: 0.0006529375095851719
2023-01-24 07:28:27.192229: step: 1456/527, loss: 0.0014505956787616014
2023-01-24 07:28:28.234622: step: 1460/527, loss: 0.0055475723929703236
2023-01-24 07:28:29.294398: step: 1464/527, loss: 0.018042156472802162
2023-01-24 07:28:30.347387: step: 1468/527, loss: 0.004778545815497637
2023-01-24 07:28:31.395801: step: 1472/527, loss: 0.0015699844807386398
2023-01-24 07:28:32.449698: step: 1476/527, loss: 0.005329108331352472
2023-01-24 07:28:33.498909: step: 1480/527, loss: 0.003789538284763694
2023-01-24 07:28:34.547027: step: 1484/527, loss: 0.00029249233193695545
2023-01-24 07:28:35.607002: step: 1488/527, loss: 0.013323414139449596
2023-01-24 07:28:36.640708: step: 1492/527, loss: 0.00016153963224496692
2023-01-24 07:28:37.692175: step: 1496/527, loss: 0.005620854906737804
2023-01-24 07:28:38.744887: step: 1500/527, loss: 0.004473687149584293
2023-01-24 07:28:39.789546: step: 1504/527, loss: 0.012032121419906616
2023-01-24 07:28:40.840281: step: 1508/527, loss: 0.00602019764482975
2023-01-24 07:28:41.891429: step: 1512/527, loss: 0.000493289902806282
2023-01-24 07:28:42.940711: step: 1516/527, loss: 0.025164194405078888
2023-01-24 07:28:43.975253: step: 1520/527, loss: 0.0006302927504293621
2023-01-24 07:28:45.025045: step: 1524/527, loss: 0.0003442306478973478
2023-01-24 07:28:46.073511: step: 1528/527, loss: 0.000919578829780221
2023-01-24 07:28:47.124844: step: 1532/527, loss: 0.002080704551190138
2023-01-24 07:28:48.168466: step: 1536/527, loss: 0.00034298747777938843
2023-01-24 07:28:49.247365: step: 1540/527, loss: 0.0028959952760487795
2023-01-24 07:28:50.289237: step: 1544/527, loss: 0.0007091228035278618
2023-01-24 07:28:51.338416: step: 1548/527, loss: 0.003251128364354372
2023-01-24 07:28:52.375564: step: 1552/527, loss: 0.0013161341194063425
2023-01-24 07:28:53.432370: step: 1556/527, loss: 0.0005920772673562169
2023-01-24 07:28:54.474766: step: 1560/527, loss: 0.00036366027779877186
2023-01-24 07:28:55.514631: step: 1564/527, loss: 0.0036223935894668102
2023-01-24 07:28:56.558395: step: 1568/527, loss: 0.006960890721529722
2023-01-24 07:28:57.631765: step: 1572/527, loss: 0.01042530033737421
2023-01-24 07:28:58.676939: step: 1576/527, loss: 0.0
2023-01-24 07:28:59.718438: step: 1580/527, loss: 0.0010661283740773797
2023-01-24 07:29:00.759191: step: 1584/527, loss: 0.03677280247211456
2023-01-24 07:29:01.812429: step: 1588/527, loss: 0.001318818423897028
2023-01-24 07:29:02.851036: step: 1592/527, loss: 0.00014960371481720358
2023-01-24 07:29:03.917686: step: 1596/527, loss: 0.009377187117934227
2023-01-24 07:29:04.973066: step: 1600/527, loss: 0.004860251676291227
2023-01-24 07:29:06.006478: step: 1604/527, loss: 8.306769450427964e-05
2023-01-24 07:29:07.050274: step: 1608/527, loss: 0.002958378754556179
2023-01-24 07:29:08.102397: step: 1612/527, loss: 0.010559827089309692
2023-01-24 07:29:09.142363: step: 1616/527, loss: 0.0012714501935988665
2023-01-24 07:29:10.178214: step: 1620/527, loss: 0.0003085932694375515
2023-01-24 07:29:11.230353: step: 1624/527, loss: 0.0036669885739684105
2023-01-24 07:29:12.286071: step: 1628/527, loss: 0.0044968402944505215
2023-01-24 07:29:13.326269: step: 1632/527, loss: 0.004391274880617857
2023-01-24 07:29:14.365644: step: 1636/527, loss: 0.0003657602646853775
2023-01-24 07:29:15.416944: step: 1640/527, loss: 0.0005517423851415515
2023-01-24 07:29:16.454038: step: 1644/527, loss: 0.008376365527510643
2023-01-24 07:29:17.498282: step: 1648/527, loss: 0.000498554261866957
2023-01-24 07:29:18.540287: step: 1652/527, loss: 0.0016641139518469572
2023-01-24 07:29:19.599853: step: 1656/527, loss: 0.0016360287554562092
2023-01-24 07:29:20.669709: step: 1660/527, loss: 2.3104164938558824e-05
2023-01-24 07:29:21.718056: step: 1664/527, loss: 3.766153326978383e-07
2023-01-24 07:29:22.763097: step: 1668/527, loss: 0.000569180294405669
2023-01-24 07:29:23.819311: step: 1672/527, loss: 0.006972864270210266
2023-01-24 07:29:24.886663: step: 1676/527, loss: 0.0032602990977466106
2023-01-24 07:29:25.924884: step: 1680/527, loss: 0.015513749793171883
2023-01-24 07:29:26.983898: step: 1684/527, loss: 0.00356738967821002
2023-01-24 07:29:28.028461: step: 1688/527, loss: 0.004443651530891657
2023-01-24 07:29:29.079574: step: 1692/527, loss: 0.0014096458908170462
2023-01-24 07:29:30.136760: step: 1696/527, loss: 0.01340903714299202
2023-01-24 07:29:31.205156: step: 1700/527, loss: 0.005242456216365099
2023-01-24 07:29:32.249605: step: 1704/527, loss: 0.0007230520131997764
2023-01-24 07:29:33.291641: step: 1708/527, loss: 0.024347959086298943
2023-01-24 07:29:34.343900: step: 1712/527, loss: 0.002077270532026887
2023-01-24 07:29:35.395334: step: 1716/527, loss: 0.0036248930264264345
2023-01-24 07:29:36.442233: step: 1720/527, loss: 0.004900793079286814
2023-01-24 07:29:37.489426: step: 1724/527, loss: 0.0042923809960484505
2023-01-24 07:29:38.526078: step: 1728/527, loss: 0.0019345434848219156
2023-01-24 07:29:39.580637: step: 1732/527, loss: 0.0027310873847454786
2023-01-24 07:29:40.631330: step: 1736/527, loss: 0.005460775922983885
2023-01-24 07:29:41.687441: step: 1740/527, loss: 0.01553793903440237
2023-01-24 07:29:42.735239: step: 1744/527, loss: 0.000788163160905242
2023-01-24 07:29:43.773480: step: 1748/527, loss: 0.0005869740853086114
2023-01-24 07:29:44.820697: step: 1752/527, loss: 0.0021611275151371956
2023-01-24 07:29:45.879028: step: 1756/527, loss: 0.02036934532225132
2023-01-24 07:29:46.917854: step: 1760/527, loss: 0.0011394410394132137
2023-01-24 07:29:47.980995: step: 1764/527, loss: 0.0004443641228135675
2023-01-24 07:29:49.059715: step: 1768/527, loss: 0.0020099368412047625
2023-01-24 07:29:50.106772: step: 1772/527, loss: 0.006575481500476599
2023-01-24 07:29:51.170919: step: 1776/527, loss: 0.001949939876794815
2023-01-24 07:29:52.205773: step: 1780/527, loss: 0.0010158447548747063
2023-01-24 07:29:53.245887: step: 1784/527, loss: 0.001385521492920816
2023-01-24 07:29:54.291941: step: 1788/527, loss: 0.0015559963649138808
2023-01-24 07:29:55.337524: step: 1792/527, loss: 0.00010657988605089486
2023-01-24 07:29:56.385828: step: 1796/527, loss: 0.017425308004021645
2023-01-24 07:29:57.435976: step: 1800/527, loss: 0.012123212218284607
2023-01-24 07:29:58.490159: step: 1804/527, loss: 0.00530658895149827
2023-01-24 07:29:59.547194: step: 1808/527, loss: 0.001094582723453641
2023-01-24 07:30:00.583610: step: 1812/527, loss: 0.00027986016357317567
2023-01-24 07:30:01.634629: step: 1816/527, loss: 0.0004496570909395814
2023-01-24 07:30:02.670107: step: 1820/527, loss: 0.0002132516383426264
2023-01-24 07:30:03.725678: step: 1824/527, loss: 0.0047562518157064915
2023-01-24 07:30:04.773840: step: 1828/527, loss: 0.00100448087323457
2023-01-24 07:30:05.843976: step: 1832/527, loss: 0.005904084537178278
2023-01-24 07:30:06.895708: step: 1836/527, loss: 0.008406324312090874
2023-01-24 07:30:07.938968: step: 1840/527, loss: 0.00170095672365278
2023-01-24 07:30:08.993643: step: 1844/527, loss: 0.018389154225587845
2023-01-24 07:30:10.054863: step: 1848/527, loss: 0.007688975892961025
2023-01-24 07:30:11.121490: step: 1852/527, loss: 0.0021261251531541348
2023-01-24 07:30:12.170871: step: 1856/527, loss: 0.0011606162879616022
2023-01-24 07:30:13.211977: step: 1860/527, loss: 0.0007913933368399739
2023-01-24 07:30:14.272671: step: 1864/527, loss: 0.005645437631756067
2023-01-24 07:30:15.332374: step: 1868/527, loss: 0.004314650781452656
2023-01-24 07:30:16.385327: step: 1872/527, loss: 0.0006230800063349307
2023-01-24 07:30:17.443512: step: 1876/527, loss: 0.003027730155736208
2023-01-24 07:30:18.490521: step: 1880/527, loss: 0.0027935155667364597
2023-01-24 07:30:19.552705: step: 1884/527, loss: 0.0033874711953103542
2023-01-24 07:30:20.596501: step: 1888/527, loss: 0.0004291182558517903
2023-01-24 07:30:21.632247: step: 1892/527, loss: 0.005484543740749359
2023-01-24 07:30:22.663037: step: 1896/527, loss: 0.0005467801238410175
2023-01-24 07:30:23.743254: step: 1900/527, loss: 0.0017408350249752402
2023-01-24 07:30:24.791875: step: 1904/527, loss: 0.00661687646061182
2023-01-24 07:30:25.865310: step: 1908/527, loss: 0.004403543658554554
2023-01-24 07:30:26.918674: step: 1912/527, loss: 0.004321379121392965
2023-01-24 07:30:27.959540: step: 1916/527, loss: 0.005980567075312138
2023-01-24 07:30:28.991974: step: 1920/527, loss: 0.00015836532111279666
2023-01-24 07:30:30.044061: step: 1924/527, loss: 0.0017614540411159396
2023-01-24 07:30:31.110998: step: 1928/527, loss: 0.005670016165822744
2023-01-24 07:30:32.157921: step: 1932/527, loss: 0.012916527688503265
2023-01-24 07:30:33.201664: step: 1936/527, loss: 0.002517060609534383
2023-01-24 07:30:34.247681: step: 1940/527, loss: 0.002991416957229376
2023-01-24 07:30:35.305603: step: 1944/527, loss: 0.001949058030731976
2023-01-24 07:30:36.365781: step: 1948/527, loss: 0.007145324721932411
2023-01-24 07:30:37.413088: step: 1952/527, loss: 0.025982271879911423
2023-01-24 07:30:38.457313: step: 1956/527, loss: 0.004791861865669489
2023-01-24 07:30:39.522517: step: 1960/527, loss: 0.004748423118144274
2023-01-24 07:30:40.565648: step: 1964/527, loss: 0.0008997737313620746
2023-01-24 07:30:41.613186: step: 1968/527, loss: 0.0038349067326635122
2023-01-24 07:30:42.676017: step: 1972/527, loss: 0.0122023681178689
2023-01-24 07:30:43.724662: step: 1976/527, loss: 0.004679364152252674
2023-01-24 07:30:44.766223: step: 1980/527, loss: 0.003038185415789485
2023-01-24 07:30:45.823039: step: 1984/527, loss: 0.016883159056305885
2023-01-24 07:30:46.877379: step: 1988/527, loss: 0.03122745454311371
2023-01-24 07:30:47.931685: step: 1992/527, loss: 0.0015301862731575966
2023-01-24 07:30:48.986945: step: 1996/527, loss: 0.00023105574655346572
2023-01-24 07:30:50.035424: step: 2000/527, loss: 0.016663668677210808
2023-01-24 07:30:51.090327: step: 2004/527, loss: 0.031381573528051376
2023-01-24 07:30:52.122908: step: 2008/527, loss: 0.001840645563788712
2023-01-24 07:30:53.174430: step: 2012/527, loss: 0.02474190667271614
2023-01-24 07:30:54.225831: step: 2016/527, loss: 0.005741769913583994
2023-01-24 07:30:55.269719: step: 2020/527, loss: 0.00014354994345922023
2023-01-24 07:30:56.303030: step: 2024/527, loss: 0.013231417164206505
2023-01-24 07:30:57.347418: step: 2028/527, loss: 0.002164565958082676
2023-01-24 07:30:58.394899: step: 2032/527, loss: 0.001787404646165669
2023-01-24 07:30:59.452626: step: 2036/527, loss: 0.00047837159945629537
2023-01-24 07:31:00.499391: step: 2040/527, loss: 0.0003927461802959442
2023-01-24 07:31:01.543983: step: 2044/527, loss: 0.002115048933774233
2023-01-24 07:31:02.579650: step: 2048/527, loss: 0.001096814638003707
2023-01-24 07:31:03.649814: step: 2052/527, loss: 0.006315071601420641
2023-01-24 07:31:04.703010: step: 2056/527, loss: 0.0017492563929408789
2023-01-24 07:31:05.749543: step: 2060/527, loss: 0.009951732121407986
2023-01-24 07:31:06.802108: step: 2064/527, loss: 0.005994449369609356
2023-01-24 07:31:07.847663: step: 2068/527, loss: 0.0024943272583186626
2023-01-24 07:31:08.902578: step: 2072/527, loss: 0.0025179623626172543
2023-01-24 07:31:09.954201: step: 2076/527, loss: 0.04178306460380554
2023-01-24 07:31:10.988078: step: 2080/527, loss: 0.0008779895724728703
2023-01-24 07:31:12.030791: step: 2084/527, loss: 0.0015356200747191906
2023-01-24 07:31:13.080273: step: 2088/527, loss: 0.012282346375286579
2023-01-24 07:31:14.139272: step: 2092/527, loss: 0.010887503623962402
2023-01-24 07:31:15.178038: step: 2096/527, loss: 0.002622022060677409
2023-01-24 07:31:16.253651: step: 2100/527, loss: 0.0020813436713069677
2023-01-24 07:31:17.293002: step: 2104/527, loss: 0.004574185702949762
2023-01-24 07:31:18.348156: step: 2108/527, loss: 0.012098906561732292
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3409165590539368, 'r': 0.32280334529016025, 'f1': 0.3316127933097747}, 'combined': 0.24434626875457083, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3695856837952465, 'r': 0.29096472924243955, 'f1': 0.3255963399457614}, 'combined': 0.2083816575652873, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3526803824978267, 'r': 0.32992680943345076, 'f1': 0.3409243697478991}, 'combined': 0.2512074303405572, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.377022875772924, 'r': 0.3051111555982518, 'f1': 0.3372764882667422}, 'combined': 0.215856952490715, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3629126630061771, 'r': 0.3236602497398543, 'f1': 0.3421643964150516}, 'combined': 0.2521211342005643, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38393376111959804, 'r': 0.3114868253385982, 'f1': 0.3439366355273702}, 'combined': 0.2465960783026428, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6, 'r': 0.20689655172413793, 'f1': 0.3076923076923077}, 'combined': 0.20512820512820512, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36325359749028163, 'r': 0.3260321662483932, 'f1': 0.3436379032258064}, 'combined': 0.25320687606112047, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827405873011607, 'r': 0.313309979395116, 'f1': 0.344562453530268}, 'combined': 0.24704477800283367, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
******************************
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
2023-01-24 07:33:48.096541: step: 4/527, loss: 0.00047966433339752257
2023-01-24 07:33:49.148792: step: 8/527, loss: 0.12679523229599
2023-01-24 07:33:50.197024: step: 12/527, loss: 0.005931123625487089
2023-01-24 07:33:51.248780: step: 16/527, loss: 0.006797137204557657
2023-01-24 07:33:52.311449: step: 20/527, loss: 0.0046298932284116745
2023-01-24 07:33:53.358330: step: 24/527, loss: 0.00021893317170906812
2023-01-24 07:33:54.391503: step: 28/527, loss: 0.0015516445273533463
2023-01-24 07:33:55.443160: step: 32/527, loss: 0.005914092529565096
2023-01-24 07:33:56.491887: step: 36/527, loss: 0.0003633471787907183
2023-01-24 07:33:57.568932: step: 40/527, loss: 0.0033023653086274862
2023-01-24 07:33:58.619315: step: 44/527, loss: 0.0027280061040073633
2023-01-24 07:33:59.673186: step: 48/527, loss: 0.003142612287774682
2023-01-24 07:34:00.716876: step: 52/527, loss: 0.0048146843910217285
2023-01-24 07:34:01.778821: step: 56/527, loss: 0.0027329442091286182
2023-01-24 07:34:02.828289: step: 60/527, loss: 0.00626673549413681
2023-01-24 07:34:03.875794: step: 64/527, loss: 0.011355612426996231
2023-01-24 07:34:04.918640: step: 68/527, loss: 0.006362869404256344
2023-01-24 07:34:05.966487: step: 72/527, loss: 0.0031870645470917225
2023-01-24 07:34:07.002647: step: 76/527, loss: 0.0051883733831346035
2023-01-24 07:34:08.037903: step: 80/527, loss: 0.0031207758001983166
2023-01-24 07:34:09.087695: step: 84/527, loss: 5.671257895301096e-05
2023-01-24 07:34:10.136873: step: 88/527, loss: 0.0016243119025602937
2023-01-24 07:34:11.186771: step: 92/527, loss: 0.0014474587514996529
2023-01-24 07:34:12.230020: step: 96/527, loss: 0.0004649146576412022
2023-01-24 07:34:13.279566: step: 100/527, loss: 0.0012905211187899113
2023-01-24 07:34:14.335848: step: 104/527, loss: 0.004177778493613005
2023-01-24 07:34:15.380940: step: 108/527, loss: 0.003395121544599533
2023-01-24 07:34:16.426121: step: 112/527, loss: 0.009098974987864494
2023-01-24 07:34:17.476561: step: 116/527, loss: 0.006990011315792799
2023-01-24 07:34:18.558901: step: 120/527, loss: 0.017712267115712166
2023-01-24 07:34:19.616285: step: 124/527, loss: 0.002568305702880025
2023-01-24 07:34:20.660493: step: 128/527, loss: 0.02214146964251995
2023-01-24 07:34:21.717758: step: 132/527, loss: 0.0020087631419301033
2023-01-24 07:34:22.780436: step: 136/527, loss: 0.0016258673276752234
2023-01-24 07:34:23.818326: step: 140/527, loss: 0.006468077190220356
2023-01-24 07:34:24.873531: step: 144/527, loss: 0.004438657313585281
2023-01-24 07:34:25.914638: step: 148/527, loss: 0.019502557814121246
2023-01-24 07:34:26.964902: step: 152/527, loss: 0.0023263217881321907
2023-01-24 07:34:28.040038: step: 156/527, loss: 0.010414495132863522
2023-01-24 07:34:29.090962: step: 160/527, loss: 0.010374199599027634
2023-01-24 07:34:30.134709: step: 164/527, loss: 0.00040748337050899863
2023-01-24 07:34:31.179729: step: 168/527, loss: 0.012541718780994415
2023-01-24 07:34:32.234527: step: 172/527, loss: 0.002299034036695957
2023-01-24 07:34:33.277987: step: 176/527, loss: 0.0919279158115387
2023-01-24 07:34:34.336054: step: 180/527, loss: 2.3659185899305157e-06
2023-01-24 07:34:35.372869: step: 184/527, loss: 0.001996793784201145
2023-01-24 07:34:36.424559: step: 188/527, loss: 0.008163457736372948
2023-01-24 07:34:37.482874: step: 192/527, loss: 0.002465104917064309
2023-01-24 07:34:38.543776: step: 196/527, loss: 0.005428884644061327
2023-01-24 07:34:39.595435: step: 200/527, loss: 0.003700327593833208
2023-01-24 07:34:40.650937: step: 204/527, loss: 0.0035851493012160063
2023-01-24 07:34:41.699071: step: 208/527, loss: 0.0030758383218199015
2023-01-24 07:34:42.747600: step: 212/527, loss: 0.00011749286204576492
2023-01-24 07:34:43.799366: step: 216/527, loss: 0.0030023108702152967
2023-01-24 07:34:44.845715: step: 220/527, loss: 0.00010859598114620894
2023-01-24 07:34:45.899457: step: 224/527, loss: 0.002482845913618803
2023-01-24 07:34:46.960232: step: 228/527, loss: 0.0008771735010668635
2023-01-24 07:34:48.004394: step: 232/527, loss: 0.0006597733008675277
2023-01-24 07:34:49.083925: step: 236/527, loss: 0.0026779011823236942
2023-01-24 07:34:50.126684: step: 240/527, loss: 0.004704420454800129
2023-01-24 07:34:51.170909: step: 244/527, loss: 0.0011582281440496445
2023-01-24 07:34:52.222093: step: 248/527, loss: 0.004860404413193464
2023-01-24 07:34:53.269254: step: 252/527, loss: 0.0033757255878299475
2023-01-24 07:34:54.316862: step: 256/527, loss: 0.005320724565535784
2023-01-24 07:34:55.372582: step: 260/527, loss: 0.002112730871886015
2023-01-24 07:34:56.407335: step: 264/527, loss: 0.00735299801453948
2023-01-24 07:34:57.460753: step: 268/527, loss: 0.00027587651857174933
2023-01-24 07:34:58.504184: step: 272/527, loss: 0.0026921499520540237
2023-01-24 07:34:59.550980: step: 276/527, loss: 0.007181172259151936
2023-01-24 07:35:00.584016: step: 280/527, loss: 0.0008219439769163728
2023-01-24 07:35:01.638062: step: 284/527, loss: 0.0031848468352109194
2023-01-24 07:35:02.701449: step: 288/527, loss: 0.012136109173297882
2023-01-24 07:35:03.749987: step: 292/527, loss: 0.0013794435653835535
2023-01-24 07:35:04.797972: step: 296/527, loss: 0.0041949208825826645
2023-01-24 07:35:05.840638: step: 300/527, loss: 0.005405834876000881
2023-01-24 07:35:06.906543: step: 304/527, loss: 0.014825263060629368
2023-01-24 07:35:07.943948: step: 308/527, loss: 0.002000151900574565
2023-01-24 07:35:09.019756: step: 312/527, loss: 0.001867753453552723
2023-01-24 07:35:10.082198: step: 316/527, loss: 0.006596806459128857
2023-01-24 07:35:11.125630: step: 320/527, loss: 0.000626065768301487
2023-01-24 07:35:12.195165: step: 324/527, loss: 0.0012385525042191148
2023-01-24 07:35:13.237448: step: 328/527, loss: 0.009825015440583229
2023-01-24 07:35:14.282643: step: 332/527, loss: 0.00412285840138793
2023-01-24 07:35:15.333042: step: 336/527, loss: 3.9639278838876635e-05
2023-01-24 07:35:16.393044: step: 340/527, loss: 0.0099570881575346
2023-01-24 07:35:17.419735: step: 344/527, loss: 0.0038917972706258297
2023-01-24 07:35:18.474569: step: 348/527, loss: 0.005468165036290884
2023-01-24 07:35:19.541714: step: 352/527, loss: 0.016557637602090836
2023-01-24 07:35:20.585604: step: 356/527, loss: 0.02072323113679886
2023-01-24 07:35:21.632905: step: 360/527, loss: 0.00039233139250427485
2023-01-24 07:35:22.682321: step: 364/527, loss: 0.00015779142268002033
2023-01-24 07:35:23.728317: step: 368/527, loss: 0.004482398275285959
2023-01-24 07:35:24.765734: step: 372/527, loss: 0.00025002469192259014
2023-01-24 07:35:25.839606: step: 376/527, loss: 0.011141078546643257
2023-01-24 07:35:26.907769: step: 380/527, loss: 0.0016537305200472474
2023-01-24 07:35:27.971760: step: 384/527, loss: 0.00703157065436244
2023-01-24 07:35:29.032222: step: 388/527, loss: 0.000436004571383819
2023-01-24 07:35:30.108993: step: 392/527, loss: 0.004214850720018148
2023-01-24 07:35:31.166691: step: 396/527, loss: 0.0041285110637545586
2023-01-24 07:35:32.223080: step: 400/527, loss: 0.0056310053914785385
2023-01-24 07:35:33.274412: step: 404/527, loss: 0.003791823284700513
2023-01-24 07:35:34.318955: step: 408/527, loss: 0.0010202594567090273
2023-01-24 07:35:35.358896: step: 412/527, loss: 0.000974743627011776
2023-01-24 07:35:36.416305: step: 416/527, loss: 0.049156296998262405
2023-01-24 07:35:37.462984: step: 420/527, loss: 0.004324521869421005
2023-01-24 07:35:38.514142: step: 424/527, loss: 0.0003029952058568597
2023-01-24 07:35:39.588494: step: 428/527, loss: 0.001004286459647119
2023-01-24 07:35:40.634930: step: 432/527, loss: 0.007104435004293919
2023-01-24 07:35:41.680633: step: 436/527, loss: 0.0003585568629205227
2023-01-24 07:35:42.741899: step: 440/527, loss: 0.0039218151941895485
2023-01-24 07:35:43.776713: step: 444/527, loss: 0.01423337496817112
2023-01-24 07:35:44.819088: step: 448/527, loss: 0.0015733834588900208
2023-01-24 07:35:45.870199: step: 452/527, loss: 0.004013628698885441
2023-01-24 07:35:46.937251: step: 456/527, loss: 0.003590354695916176
2023-01-24 07:35:47.972890: step: 460/527, loss: 0.008774403482675552
2023-01-24 07:35:49.032152: step: 464/527, loss: 0.000348780769854784
2023-01-24 07:35:50.063921: step: 468/527, loss: 8.557185356039554e-05
2023-01-24 07:35:51.124094: step: 472/527, loss: 0.0004322062595747411
2023-01-24 07:35:52.174263: step: 476/527, loss: 0.0011674977140501142
2023-01-24 07:35:53.220881: step: 480/527, loss: 0.0034263022243976593
2023-01-24 07:35:54.276409: step: 484/527, loss: 0.0002531966019887477
2023-01-24 07:35:55.339399: step: 488/527, loss: 0.0034450851380825043
2023-01-24 07:35:56.397723: step: 492/527, loss: 0.002794889733195305
2023-01-24 07:35:57.447744: step: 496/527, loss: 0.006746026687324047
2023-01-24 07:35:58.500765: step: 500/527, loss: 0.005788684822618961
2023-01-24 07:35:59.549700: step: 504/527, loss: 0.0032613726798444986
2023-01-24 07:36:00.588218: step: 508/527, loss: 0.014688258990645409
2023-01-24 07:36:01.643244: step: 512/527, loss: 0.00046264310367405415
2023-01-24 07:36:02.687877: step: 516/527, loss: 0.0029617997352033854
2023-01-24 07:36:03.742403: step: 520/527, loss: 0.0032303743064403534
2023-01-24 07:36:04.771112: step: 524/527, loss: 6.718641088809818e-05
2023-01-24 07:36:05.811437: step: 528/527, loss: 0.002313081407919526
2023-01-24 07:36:06.853225: step: 532/527, loss: 6.916584970895201e-05
2023-01-24 07:36:07.891898: step: 536/527, loss: 0.00029460343648679554
2023-01-24 07:36:08.948636: step: 540/527, loss: 0.011031667701900005
2023-01-24 07:36:10.024333: step: 544/527, loss: 0.004498671740293503
2023-01-24 07:36:11.081652: step: 548/527, loss: 0.001042934600263834
2023-01-24 07:36:12.139726: step: 552/527, loss: 0.0025397450663149357
2023-01-24 07:36:13.193356: step: 556/527, loss: 0.00864452589303255
2023-01-24 07:36:14.244131: step: 560/527, loss: 0.0022043746430426836
2023-01-24 07:36:15.302577: step: 564/527, loss: 0.00486398721113801
2023-01-24 07:36:16.372784: step: 568/527, loss: 0.0031027125660330057
2023-01-24 07:36:17.400671: step: 572/527, loss: 0.00041250884532928467
2023-01-24 07:36:18.442181: step: 576/527, loss: 0.0039843907579779625
2023-01-24 07:36:19.502927: step: 580/527, loss: 3.87683576263953e-05
2023-01-24 07:36:20.555952: step: 584/527, loss: 0.0005696567241102457
2023-01-24 07:36:21.623126: step: 588/527, loss: 0.009698409587144852
2023-01-24 07:36:22.662202: step: 592/527, loss: 0.004264072980731726
2023-01-24 07:36:23.726902: step: 596/527, loss: 0.0003863092861138284
2023-01-24 07:36:24.771112: step: 600/527, loss: 0.005400056950747967
2023-01-24 07:36:25.812531: step: 604/527, loss: 5.98683618591167e-05
2023-01-24 07:36:26.864567: step: 608/527, loss: 0.0002464533317834139
2023-01-24 07:36:27.921625: step: 612/527, loss: 0.002514599123969674
2023-01-24 07:36:28.981868: step: 616/527, loss: 0.002618327271193266
2023-01-24 07:36:30.033850: step: 620/527, loss: 0.003062386065721512
2023-01-24 07:36:31.096070: step: 624/527, loss: 0.0033916831016540527
2023-01-24 07:36:32.141793: step: 628/527, loss: 0.01238814927637577
2023-01-24 07:36:33.192219: step: 632/527, loss: 0.005368268582969904
2023-01-24 07:36:34.231812: step: 636/527, loss: 0.001293156761676073
2023-01-24 07:36:35.286440: step: 640/527, loss: 0.005739733576774597
2023-01-24 07:36:36.327487: step: 644/527, loss: 0.00011344454105710611
2023-01-24 07:36:37.363045: step: 648/527, loss: 0.00027888751355931163
2023-01-24 07:36:38.431620: step: 652/527, loss: 0.001399198197759688
2023-01-24 07:36:39.479156: step: 656/527, loss: 0.0036111478693783283
2023-01-24 07:36:40.523516: step: 660/527, loss: 6.151192064862698e-05
2023-01-24 07:36:41.569542: step: 664/527, loss: 0.004169187508523464
2023-01-24 07:36:42.630545: step: 668/527, loss: 0.03293965011835098
2023-01-24 07:36:43.693676: step: 672/527, loss: 0.026547370478510857
2023-01-24 07:36:44.750323: step: 676/527, loss: 0.0018172883428633213
2023-01-24 07:36:45.797803: step: 680/527, loss: 0.004993759095668793
2023-01-24 07:36:46.840775: step: 684/527, loss: 0.0005401379894465208
2023-01-24 07:36:47.873843: step: 688/527, loss: 0.003349890233948827
2023-01-24 07:36:48.924043: step: 692/527, loss: 0.004341718275099993
2023-01-24 07:36:49.976297: step: 696/527, loss: 0.02069842629134655
2023-01-24 07:36:51.025716: step: 700/527, loss: 0.006068716291338205
2023-01-24 07:36:52.074055: step: 704/527, loss: 0.04438595473766327
2023-01-24 07:36:53.120402: step: 708/527, loss: 0.03625955432653427
2023-01-24 07:36:54.149205: step: 712/527, loss: 0.009529301896691322
2023-01-24 07:36:55.198781: step: 716/527, loss: 0.00020313216373324394
2023-01-24 07:36:56.245683: step: 720/527, loss: 0.001596994698047638
2023-01-24 07:36:57.312150: step: 724/527, loss: 0.0011845908593386412
2023-01-24 07:36:58.371050: step: 728/527, loss: 0.0021616287995129824
2023-01-24 07:36:59.441281: step: 732/527, loss: 0.0030026764143258333
2023-01-24 07:37:00.484583: step: 736/527, loss: 0.01383097842335701
2023-01-24 07:37:01.532478: step: 740/527, loss: 0.006477289833128452
2023-01-24 07:37:02.575616: step: 744/527, loss: 0.035857681185007095
2023-01-24 07:37:03.622180: step: 748/527, loss: 0.005030815023928881
2023-01-24 07:37:04.675701: step: 752/527, loss: 0.004621890839189291
2023-01-24 07:37:05.733172: step: 756/527, loss: 0.01211671531200409
2023-01-24 07:37:06.787053: step: 760/527, loss: 0.018070314079523087
2023-01-24 07:37:07.851816: step: 764/527, loss: 0.007683371193706989
2023-01-24 07:37:08.899600: step: 768/527, loss: 0.023442300036549568
2023-01-24 07:37:09.979050: step: 772/527, loss: 0.0005778574850410223
2023-01-24 07:37:11.067276: step: 776/527, loss: 0.01411820761859417
2023-01-24 07:37:12.129018: step: 780/527, loss: 0.0008859537192620337
2023-01-24 07:37:13.167756: step: 784/527, loss: 0.0003062605392187834
2023-01-24 07:37:14.230788: step: 788/527, loss: 0.00015818291285540909
2023-01-24 07:37:15.273355: step: 792/527, loss: 4.957219061907381e-06
2023-01-24 07:37:16.333531: step: 796/527, loss: 0.030652323737740517
2023-01-24 07:37:17.371088: step: 800/527, loss: 0.023049531504511833
2023-01-24 07:37:18.420078: step: 804/527, loss: 4.4695683754980564e-05
2023-01-24 07:37:19.477167: step: 808/527, loss: 0.0038705794140696526
2023-01-24 07:37:20.537282: step: 812/527, loss: 0.009528076276183128
2023-01-24 07:37:21.593772: step: 816/527, loss: 0.0004005462396889925
2023-01-24 07:37:22.644046: step: 820/527, loss: 0.0013192713959142566
2023-01-24 07:37:23.691659: step: 824/527, loss: 0.00320342555642128
2023-01-24 07:37:24.771223: step: 828/527, loss: 0.0022633594926446676
2023-01-24 07:37:25.827846: step: 832/527, loss: 0.002621921943500638
2023-01-24 07:37:26.896354: step: 836/527, loss: 0.014133133925497532
2023-01-24 07:37:27.945154: step: 840/527, loss: 0.00785229355096817
2023-01-24 07:37:29.002459: step: 844/527, loss: 0.00226704403758049
2023-01-24 07:37:30.068983: step: 848/527, loss: 0.021022062748670578
2023-01-24 07:37:31.123330: step: 852/527, loss: 0.00106845295522362
2023-01-24 07:37:32.191054: step: 856/527, loss: 0.006896406412124634
2023-01-24 07:37:33.249799: step: 860/527, loss: 0.0008146132458932698
2023-01-24 07:37:34.311704: step: 864/527, loss: 0.0014657324645668268
2023-01-24 07:37:35.348612: step: 868/527, loss: 0.0035612343344837427
2023-01-24 07:37:36.393877: step: 872/527, loss: 0.006471499800682068
2023-01-24 07:37:37.449580: step: 876/527, loss: 0.000636056181974709
2023-01-24 07:37:38.499991: step: 880/527, loss: 0.000731413543689996
2023-01-24 07:37:39.551510: step: 884/527, loss: 0.005597101524472237
2023-01-24 07:37:40.588462: step: 888/527, loss: 0.0018012278014793992
2023-01-24 07:37:41.644981: step: 892/527, loss: 0.0015583968488499522
2023-01-24 07:37:42.705623: step: 896/527, loss: 0.00021445844322443008
2023-01-24 07:37:43.748504: step: 900/527, loss: 0.004209148231893778
2023-01-24 07:37:44.809580: step: 904/527, loss: 0.0020082229748368263
2023-01-24 07:37:45.861042: step: 908/527, loss: 0.029260389506816864
2023-01-24 07:37:46.917234: step: 912/527, loss: 0.026747386902570724
2023-01-24 07:37:47.965936: step: 916/527, loss: 0.0013539609499275684
2023-01-24 07:37:49.013246: step: 920/527, loss: 0.002039816463366151
2023-01-24 07:37:50.053970: step: 924/527, loss: 0.006380030419677496
2023-01-24 07:37:51.105353: step: 928/527, loss: 0.002951527712866664
2023-01-24 07:37:52.191533: step: 932/527, loss: 0.0035444144159555435
2023-01-24 07:37:53.257800: step: 936/527, loss: 0.007331428583711386
2023-01-24 07:37:54.300561: step: 940/527, loss: 0.001937823137268424
2023-01-24 07:37:55.352937: step: 944/527, loss: 0.004884100519120693
2023-01-24 07:37:56.385894: step: 948/527, loss: 0.003096437081694603
2023-01-24 07:37:57.428909: step: 952/527, loss: 0.00049392826622352
2023-01-24 07:37:58.489684: step: 956/527, loss: 0.001529772998765111
2023-01-24 07:37:59.523636: step: 960/527, loss: 0.0034300293773412704
2023-01-24 07:38:00.585441: step: 964/527, loss: 0.006670809350907803
2023-01-24 07:38:01.627585: step: 968/527, loss: 0.0070527647621929646
2023-01-24 07:38:02.692959: step: 972/527, loss: 0.004473906476050615
2023-01-24 07:38:03.736184: step: 976/527, loss: 0.009639867581427097
2023-01-24 07:38:04.792447: step: 980/527, loss: 9.810461779125035e-05
2023-01-24 07:38:05.849915: step: 984/527, loss: 0.053507447242736816
2023-01-24 07:38:06.912438: step: 988/527, loss: 0.006516705732792616
2023-01-24 07:38:07.955020: step: 992/527, loss: 0.00079623784404248
2023-01-24 07:38:09.022595: step: 996/527, loss: 0.001361334347166121
2023-01-24 07:38:10.064439: step: 1000/527, loss: 0.002607665490359068
2023-01-24 07:38:11.119316: step: 1004/527, loss: 0.005556870251893997
2023-01-24 07:38:12.181305: step: 1008/527, loss: 0.0016048513352870941
2023-01-24 07:38:13.238084: step: 1012/527, loss: 0.0065682721324265
2023-01-24 07:38:14.291049: step: 1016/527, loss: 0.002197975292801857
2023-01-24 07:38:15.332746: step: 1020/527, loss: 0.019346218556165695
2023-01-24 07:38:16.388180: step: 1024/527, loss: 0.00048493093345314264
2023-01-24 07:38:17.437845: step: 1028/527, loss: 0.037749119102954865
2023-01-24 07:38:18.499257: step: 1032/527, loss: 0.003849076572805643
2023-01-24 07:38:19.548762: step: 1036/527, loss: 0.0023239452857524157
2023-01-24 07:38:20.606580: step: 1040/527, loss: 0.004615205805748701
2023-01-24 07:38:21.650179: step: 1044/527, loss: 0.00832344125956297
2023-01-24 07:38:22.701011: step: 1048/527, loss: 0.003352670231834054
2023-01-24 07:38:23.747981: step: 1052/527, loss: 0.0014569121412932873
2023-01-24 07:38:24.782617: step: 1056/527, loss: 0.0007146981661207974
2023-01-24 07:38:25.826054: step: 1060/527, loss: 0.0008186764316633344
2023-01-24 07:38:26.877662: step: 1064/527, loss: 0.004233731888234615
2023-01-24 07:38:27.931648: step: 1068/527, loss: 0.0007094976026564837
2023-01-24 07:38:28.980798: step: 1072/527, loss: 0.0015996926231309772
2023-01-24 07:38:30.047820: step: 1076/527, loss: 0.0025237714871764183
2023-01-24 07:38:31.127704: step: 1080/527, loss: 0.009845957159996033
2023-01-24 07:38:32.214583: step: 1084/527, loss: 0.0008140782592818141
2023-01-24 07:38:33.262660: step: 1088/527, loss: 0.0001628329191589728
2023-01-24 07:38:34.325409: step: 1092/527, loss: 0.000677892763633281
2023-01-24 07:38:35.381730: step: 1096/527, loss: 0.017683546990156174
2023-01-24 07:38:36.440299: step: 1100/527, loss: 0.004512401297688484
2023-01-24 07:38:37.506544: step: 1104/527, loss: 0.012557548470795155
2023-01-24 07:38:38.558458: step: 1108/527, loss: 0.0024149129167199135
2023-01-24 07:38:39.609735: step: 1112/527, loss: 0.0062912022694945335
2023-01-24 07:38:40.672767: step: 1116/527, loss: 0.0020975188817828894
2023-01-24 07:38:41.734059: step: 1120/527, loss: 0.006300954148173332
2023-01-24 07:38:42.784378: step: 1124/527, loss: 0.00213739275932312
2023-01-24 07:38:43.834241: step: 1128/527, loss: 0.002461416181176901
2023-01-24 07:38:44.880076: step: 1132/527, loss: 0.003327315906062722
2023-01-24 07:38:45.934924: step: 1136/527, loss: 0.005420952569693327
2023-01-24 07:38:46.989489: step: 1140/527, loss: 0.0037704408168792725
2023-01-24 07:38:48.054706: step: 1144/527, loss: 0.08022844046354294
2023-01-24 07:38:49.109574: step: 1148/527, loss: 0.00016010383842512965
2023-01-24 07:38:50.213138: step: 1152/527, loss: 0.02749839425086975
2023-01-24 07:38:51.259915: step: 1156/527, loss: 9.632661385694519e-05
2023-01-24 07:38:52.337571: step: 1160/527, loss: 0.0013591231545433402
2023-01-24 07:38:53.386188: step: 1164/527, loss: 0.0029064109548926353
2023-01-24 07:38:54.438197: step: 1168/527, loss: 0.0025018402375280857
2023-01-24 07:38:55.484400: step: 1172/527, loss: 0.0017730684485286474
2023-01-24 07:38:56.526039: step: 1176/527, loss: 3.7252898543727042e-09
2023-01-24 07:38:57.576744: step: 1180/527, loss: 0.0036277053877711296
2023-01-24 07:38:58.636588: step: 1184/527, loss: 0.0032393040601164103
2023-01-24 07:38:59.685000: step: 1188/527, loss: 0.00472364854067564
2023-01-24 07:39:00.725539: step: 1192/527, loss: 0.008162073791027069
2023-01-24 07:39:01.776676: step: 1196/527, loss: 0.018864743411540985
2023-01-24 07:39:02.837366: step: 1200/527, loss: 0.0028245439752936363
2023-01-24 07:39:03.900513: step: 1204/527, loss: 0.005585981998592615
2023-01-24 07:39:04.959537: step: 1208/527, loss: 0.000987582840025425
2023-01-24 07:39:05.997100: step: 1212/527, loss: 0.007033372763544321
2023-01-24 07:39:07.055347: step: 1216/527, loss: 0.018273040652275085
2023-01-24 07:39:08.106851: step: 1220/527, loss: 0.0035938937216997147
2023-01-24 07:39:09.153463: step: 1224/527, loss: 0.016538042575120926
2023-01-24 07:39:10.198434: step: 1228/527, loss: 0.0042722695507109165
2023-01-24 07:39:11.247204: step: 1232/527, loss: 0.0024743378162384033
2023-01-24 07:39:12.313120: step: 1236/527, loss: 0.0037654361221939325
2023-01-24 07:39:13.385623: step: 1240/527, loss: 0.00030759748187847435
2023-01-24 07:39:14.435608: step: 1244/527, loss: 0.0016991720767691731
2023-01-24 07:39:15.477401: step: 1248/527, loss: 0.005908094346523285
2023-01-24 07:39:16.510946: step: 1252/527, loss: 0.003163701854646206
2023-01-24 07:39:17.566658: step: 1256/527, loss: 0.009016034193336964
2023-01-24 07:39:18.621859: step: 1260/527, loss: 0.0025383138563483953
2023-01-24 07:39:19.695263: step: 1264/527, loss: 0.000447107624495402
2023-01-24 07:39:20.748631: step: 1268/527, loss: 6.376469536917284e-05
2023-01-24 07:39:21.790189: step: 1272/527, loss: 0.027500247582793236
2023-01-24 07:39:22.830872: step: 1276/527, loss: 4.464551238925196e-05
2023-01-24 07:39:23.875098: step: 1280/527, loss: 0.0036577354185283184
2023-01-24 07:39:24.921571: step: 1284/527, loss: 0.0011909445747733116
2023-01-24 07:39:25.990529: step: 1288/527, loss: 0.0076804026030004025
2023-01-24 07:39:27.041260: step: 1292/527, loss: 0.011143893003463745
2023-01-24 07:39:28.103120: step: 1296/527, loss: 0.019095083698630333
2023-01-24 07:39:29.150489: step: 1300/527, loss: 0.001601521740667522
2023-01-24 07:39:30.210593: step: 1304/527, loss: 0.0014019741211086512
2023-01-24 07:39:31.266423: step: 1308/527, loss: 0.005991935729980469
2023-01-24 07:39:32.311287: step: 1312/527, loss: 0.0016050265403464437
2023-01-24 07:39:33.360190: step: 1316/527, loss: 0.000516237283591181
2023-01-24 07:39:34.406791: step: 1320/527, loss: 0.0013739397982135415
2023-01-24 07:39:35.451016: step: 1324/527, loss: 9.797236089070793e-07
2023-01-24 07:39:36.496650: step: 1328/527, loss: 0.0001518372300779447
2023-01-24 07:39:37.536346: step: 1332/527, loss: 2.3228280099374388e-07
2023-01-24 07:39:38.590430: step: 1336/527, loss: 0.012522008270025253
2023-01-24 07:39:39.638485: step: 1340/527, loss: 3.1365692620966e-07
2023-01-24 07:39:40.695550: step: 1344/527, loss: 0.007189786992967129
2023-01-24 07:39:41.757332: step: 1348/527, loss: 0.0028326334431767464
2023-01-24 07:39:42.810192: step: 1352/527, loss: 0.003496192628517747
2023-01-24 07:39:43.863175: step: 1356/527, loss: 0.000181456096470356
2023-01-24 07:39:44.910127: step: 1360/527, loss: 0.0009919545846059918
2023-01-24 07:39:45.959804: step: 1364/527, loss: 0.002171309432014823
2023-01-24 07:39:47.017268: step: 1368/527, loss: 0.0022930451668798923
2023-01-24 07:39:48.101288: step: 1372/527, loss: 0.01480209082365036
2023-01-24 07:39:49.165258: step: 1376/527, loss: 0.0024100271984934807
2023-01-24 07:39:50.209783: step: 1380/527, loss: 9.323685662820935e-05
2023-01-24 07:39:51.256785: step: 1384/527, loss: 0.009930646046996117
2023-01-24 07:39:52.302117: step: 1388/527, loss: 0.0022097628097981215
2023-01-24 07:39:53.341363: step: 1392/527, loss: 0.00019306884496472776
2023-01-24 07:39:54.400247: step: 1396/527, loss: 0.006641766522079706
2023-01-24 07:39:55.441428: step: 1400/527, loss: 4.484779856284149e-05
2023-01-24 07:39:56.503508: step: 1404/527, loss: 0.0023347761016339064
2023-01-24 07:39:57.543840: step: 1408/527, loss: 0.0018095102859660983
2023-01-24 07:39:58.593656: step: 1412/527, loss: 0.0008096770034171641
2023-01-24 07:39:59.646083: step: 1416/527, loss: 0.0023772353306412697
2023-01-24 07:40:00.686243: step: 1420/527, loss: 0.002142679877579212
2023-01-24 07:40:01.739191: step: 1424/527, loss: 0.012929125688970089
2023-01-24 07:40:02.787529: step: 1428/527, loss: 0.0007798751466907561
2023-01-24 07:40:03.835864: step: 1432/527, loss: 0.0028679780662059784
2023-01-24 07:40:04.876924: step: 1436/527, loss: 0.0013708813348785043
2023-01-24 07:40:05.919295: step: 1440/527, loss: 0.0011231850367039442
2023-01-24 07:40:06.957918: step: 1444/527, loss: 0.0053117242641747
2023-01-24 07:40:07.993184: step: 1448/527, loss: 1.5033860108815134e-05
2023-01-24 07:40:09.046245: step: 1452/527, loss: 0.0025865137577056885
2023-01-24 07:40:10.106245: step: 1456/527, loss: 0.0006940962630324066
2023-01-24 07:40:11.160097: step: 1460/527, loss: 0.008366623893380165
2023-01-24 07:40:12.211928: step: 1464/527, loss: 0.005322176031768322
2023-01-24 07:40:13.257021: step: 1468/527, loss: 0.005060556810349226
2023-01-24 07:40:14.320711: step: 1472/527, loss: 0.004776624031364918
2023-01-24 07:40:15.364660: step: 1476/527, loss: 0.0036280089989304543
2023-01-24 07:40:16.417682: step: 1480/527, loss: 0.0009317616350017488
2023-01-24 07:40:17.462386: step: 1484/527, loss: 0.0012273200554773211
2023-01-24 07:40:18.514207: step: 1488/527, loss: 0.0038714574184268713
2023-01-24 07:40:19.569853: step: 1492/527, loss: 0.0029744389466941357
2023-01-24 07:40:20.624849: step: 1496/527, loss: 0.0015907816123217344
2023-01-24 07:40:21.676181: step: 1500/527, loss: 0.0036565284244716167
2023-01-24 07:40:22.713444: step: 1504/527, loss: 0.0011274943826720119
2023-01-24 07:40:23.744451: step: 1508/527, loss: 0.002733144210651517
2023-01-24 07:40:24.794950: step: 1512/527, loss: 6.684953405056149e-05
2023-01-24 07:40:25.854690: step: 1516/527, loss: 0.004166835453361273
2023-01-24 07:40:26.898973: step: 1520/527, loss: 0.010164335370063782
2023-01-24 07:40:27.928115: step: 1524/527, loss: 0.0057418206706643105
2023-01-24 07:40:28.979596: step: 1528/527, loss: 0.00045034760842099786
2023-01-24 07:40:30.034057: step: 1532/527, loss: 0.0056198593229055405
2023-01-24 07:40:31.060343: step: 1536/527, loss: 0.00041610983316786587
2023-01-24 07:40:32.110026: step: 1540/527, loss: 0.0018941520247608423
2023-01-24 07:40:33.174261: step: 1544/527, loss: 0.011884275823831558
2023-01-24 07:40:34.219446: step: 1548/527, loss: 2.437141301925294e-05
2023-01-24 07:40:35.276976: step: 1552/527, loss: 0.003413716796785593
2023-01-24 07:40:36.333436: step: 1556/527, loss: 0.001881950069218874
2023-01-24 07:40:37.388467: step: 1560/527, loss: 0.003129188669845462
2023-01-24 07:40:38.443975: step: 1564/527, loss: 0.014781621284782887
2023-01-24 07:40:39.480486: step: 1568/527, loss: 0.0030736452899873257
2023-01-24 07:40:40.521802: step: 1572/527, loss: 0.00018176525190938264
2023-01-24 07:40:41.568234: step: 1576/527, loss: 0.00010842136543942615
2023-01-24 07:40:42.630519: step: 1580/527, loss: 0.004571137484163046
2023-01-24 07:40:43.690957: step: 1584/527, loss: 0.0005612316308543086
2023-01-24 07:40:44.742581: step: 1588/527, loss: 0.0025629668962210417
2023-01-24 07:40:45.790071: step: 1592/527, loss: 0.0004188601451460272
2023-01-24 07:40:46.827775: step: 1596/527, loss: 0.000501289265230298
2023-01-24 07:40:47.876478: step: 1600/527, loss: 0.02022780291736126
2023-01-24 07:40:48.920880: step: 1604/527, loss: 0.0006575792795047164
2023-01-24 07:40:49.967285: step: 1608/527, loss: 0.006200199481099844
2023-01-24 07:40:51.019026: step: 1612/527, loss: 0.001498966827057302
2023-01-24 07:40:52.065594: step: 1616/527, loss: 0.010210379958152771
2023-01-24 07:40:53.110647: step: 1620/527, loss: 0.0006134926225058734
2023-01-24 07:40:54.151607: step: 1624/527, loss: 0.006125845946371555
2023-01-24 07:40:55.206255: step: 1628/527, loss: 0.0005284885410219431
2023-01-24 07:40:56.270429: step: 1632/527, loss: 0.0023907991126179695
2023-01-24 07:40:57.308203: step: 1636/527, loss: 0.0030004247091710567
2023-01-24 07:40:58.348286: step: 1640/527, loss: 0.024753417819738388
2023-01-24 07:40:59.396828: step: 1644/527, loss: 0.00994983222335577
2023-01-24 07:41:00.456041: step: 1648/527, loss: 0.0014266620855778456
2023-01-24 07:41:01.501977: step: 1652/527, loss: 0.002152681350708008
2023-01-24 07:41:02.548921: step: 1656/527, loss: 0.0014415646437555552
2023-01-24 07:41:03.600154: step: 1660/527, loss: 0.015801381319761276
2023-01-24 07:41:04.653477: step: 1664/527, loss: 0.0010134992189705372
2023-01-24 07:41:05.709233: step: 1668/527, loss: 0.0028500196058303118
2023-01-24 07:41:06.747228: step: 1672/527, loss: 0.008396395482122898
2023-01-24 07:41:07.791456: step: 1676/527, loss: 0.0019125572871416807
2023-01-24 07:41:08.847447: step: 1680/527, loss: 0.00570964440703392
2023-01-24 07:41:09.889967: step: 1684/527, loss: 0.001295329537242651
2023-01-24 07:41:10.948862: step: 1688/527, loss: 0.006018343847244978
2023-01-24 07:41:12.006010: step: 1692/527, loss: 0.0012415233068168163
2023-01-24 07:41:13.071180: step: 1696/527, loss: 0.0037210476584732533
2023-01-24 07:41:14.115060: step: 1700/527, loss: 0.010629287920892239
2023-01-24 07:41:15.170339: step: 1704/527, loss: 0.0008832578314468265
2023-01-24 07:41:16.229221: step: 1708/527, loss: 0.0023887231945991516
2023-01-24 07:41:17.284438: step: 1712/527, loss: 0.008467582985758781
2023-01-24 07:41:18.308611: step: 1716/527, loss: 0.0008527770405635238
2023-01-24 07:41:19.357598: step: 1720/527, loss: 0.0028490840923041105
2023-01-24 07:41:20.410797: step: 1724/527, loss: 0.0015733069740235806
2023-01-24 07:41:21.451445: step: 1728/527, loss: 0.002432249952107668
2023-01-24 07:41:22.516004: step: 1732/527, loss: 0.0011606188490986824
2023-01-24 07:41:23.561031: step: 1736/527, loss: 0.00139420700725168
2023-01-24 07:41:24.595774: step: 1740/527, loss: 0.006411610636860132
2023-01-24 07:41:25.646247: step: 1744/527, loss: 0.0023196344263851643
2023-01-24 07:41:26.702467: step: 1748/527, loss: 0.004349843133240938
2023-01-24 07:41:27.740700: step: 1752/527, loss: 0.0021164407953619957
2023-01-24 07:41:28.770014: step: 1756/527, loss: 0.0013786342460662127
2023-01-24 07:41:29.820846: step: 1760/527, loss: 0.0019900633487850428
2023-01-24 07:41:30.885763: step: 1764/527, loss: 0.005306210368871689
2023-01-24 07:41:31.936073: step: 1768/527, loss: 0.0003959077876061201
2023-01-24 07:41:32.974925: step: 1772/527, loss: 0.004017258062958717
2023-01-24 07:41:34.018644: step: 1776/527, loss: 0.0037442147731781006
2023-01-24 07:41:35.057001: step: 1780/527, loss: 0.002976828021928668
2023-01-24 07:41:36.100216: step: 1784/527, loss: 0.001570437685586512
2023-01-24 07:41:37.141859: step: 1788/527, loss: 0.0003771288029383868
2023-01-24 07:41:38.195923: step: 1792/527, loss: 0.005642472300678492
2023-01-24 07:41:39.239631: step: 1796/527, loss: 0.0005993598024360836
2023-01-24 07:41:40.283201: step: 1800/527, loss: 0.001115448772907257
2023-01-24 07:41:41.345511: step: 1804/527, loss: 0.007068478502333164
2023-01-24 07:41:42.403526: step: 1808/527, loss: 0.00014667969662696123
2023-01-24 07:41:43.450217: step: 1812/527, loss: 0.0027813890483230352
2023-01-24 07:41:44.504217: step: 1816/527, loss: 0.001548566622659564
2023-01-24 07:41:45.540087: step: 1820/527, loss: 0.0014729787362739444
2023-01-24 07:41:46.592265: step: 1824/527, loss: 0.00013281393330544233
2023-01-24 07:41:47.642316: step: 1828/527, loss: 0.006314554251730442
2023-01-24 07:41:48.686899: step: 1832/527, loss: 0.010976334102451801
2023-01-24 07:41:49.742059: step: 1836/527, loss: 0.002326847752556205
2023-01-24 07:41:50.788612: step: 1840/527, loss: 0.004039890132844448
2023-01-24 07:41:51.847155: step: 1844/527, loss: 0.002230801386758685
2023-01-24 07:41:52.898201: step: 1848/527, loss: 6.312626646831632e-05
2023-01-24 07:41:53.965790: step: 1852/527, loss: 0.007334005553275347
2023-01-24 07:41:55.005767: step: 1856/527, loss: 0.00029763008933514357
2023-01-24 07:41:56.059374: step: 1860/527, loss: 0.0032405529636889696
2023-01-24 07:41:57.095566: step: 1864/527, loss: 0.0008879650849848986
2023-01-24 07:41:58.136285: step: 1868/527, loss: 0.0005904252175241709
2023-01-24 07:41:59.185587: step: 1872/527, loss: 0.0007783591863699257
2023-01-24 07:42:00.238946: step: 1876/527, loss: 0.014928046613931656
2023-01-24 07:42:01.315803: step: 1880/527, loss: 0.000410371896577999
2023-01-24 07:42:02.363471: step: 1884/527, loss: 0.0034347092732787132
2023-01-24 07:42:03.395804: step: 1888/527, loss: 0.0009367514867335558
2023-01-24 07:42:04.447629: step: 1892/527, loss: 0.0008500413969159126
2023-01-24 07:42:05.496443: step: 1896/527, loss: 0.004298130515962839
2023-01-24 07:42:06.544669: step: 1900/527, loss: 0.0014246077043935657
2023-01-24 07:42:07.583969: step: 1904/527, loss: 0.005420645698904991
2023-01-24 07:42:08.636500: step: 1908/527, loss: 0.001716962899081409
2023-01-24 07:42:09.682552: step: 1912/527, loss: 0.003293792949989438
2023-01-24 07:42:10.732808: step: 1916/527, loss: 0.006339459680020809
2023-01-24 07:42:11.802330: step: 1920/527, loss: 8.171771332854405e-05
2023-01-24 07:42:12.851524: step: 1924/527, loss: 0.0005772780859842896
2023-01-24 07:42:13.903661: step: 1928/527, loss: 0.0004736421979032457
2023-01-24 07:42:14.932892: step: 1932/527, loss: 0.0027515755500644445
2023-01-24 07:42:15.965474: step: 1936/527, loss: 0.003235356416553259
2023-01-24 07:42:17.014018: step: 1940/527, loss: 0.0015790046891197562
2023-01-24 07:42:18.069785: step: 1944/527, loss: 0.003959468100219965
2023-01-24 07:42:19.140527: step: 1948/527, loss: 0.009757568128407001
2023-01-24 07:42:20.192050: step: 1952/527, loss: 0.0024745729751884937
2023-01-24 07:42:21.235738: step: 1956/527, loss: 0.0031782081350684166
2023-01-24 07:42:22.295259: step: 1960/527, loss: 0.0016110064461827278
2023-01-24 07:42:23.347230: step: 1964/527, loss: 0.004924602806568146
2023-01-24 07:42:24.390796: step: 1968/527, loss: 0.009240970946848392
2023-01-24 07:42:25.413515: step: 1972/527, loss: 0.0002643048937898129
2023-01-24 07:42:26.458829: step: 1976/527, loss: 0.00017130047490354627
2023-01-24 07:42:27.507541: step: 1980/527, loss: 0.007659686263650656
2023-01-24 07:42:28.556621: step: 1984/527, loss: 0.0033778122160583735
2023-01-24 07:42:29.617798: step: 1988/527, loss: 0.0025927498936653137
2023-01-24 07:42:30.678282: step: 1992/527, loss: 0.003156978404149413
2023-01-24 07:42:31.717869: step: 1996/527, loss: 0.009291576221585274
2023-01-24 07:42:32.768069: step: 2000/527, loss: 0.0014566507888957858
2023-01-24 07:42:33.811109: step: 2004/527, loss: 0.0353391095995903
2023-01-24 07:42:34.879337: step: 2008/527, loss: 0.002842916175723076
2023-01-24 07:42:35.953385: step: 2012/527, loss: 0.00791760440915823
2023-01-24 07:42:37.002981: step: 2016/527, loss: 0.00882710050791502
2023-01-24 07:42:38.043168: step: 2020/527, loss: 0.0035401280038058758
2023-01-24 07:42:39.084843: step: 2024/527, loss: 0.0005623472388833761
2023-01-24 07:42:40.140988: step: 2028/527, loss: 0.0023368163965642452
2023-01-24 07:42:41.194242: step: 2032/527, loss: 0.00010127259156433865
2023-01-24 07:42:42.241202: step: 2036/527, loss: 0.004729969892650843
2023-01-24 07:42:43.304827: step: 2040/527, loss: 0.0022714941296726465
2023-01-24 07:42:44.350086: step: 2044/527, loss: 0.0016250937478616834
2023-01-24 07:42:45.402722: step: 2048/527, loss: 0.0029007631819695234
2023-01-24 07:42:46.454751: step: 2052/527, loss: 0.0026187445037066936
2023-01-24 07:42:47.508105: step: 2056/527, loss: 0.014578443951904774
2023-01-24 07:42:48.566313: step: 2060/527, loss: 0.00037389600765891373
2023-01-24 07:42:49.611438: step: 2064/527, loss: 1.5922822058200836e-05
2023-01-24 07:42:50.666988: step: 2068/527, loss: 0.0005649236845783889
2023-01-24 07:42:51.714182: step: 2072/527, loss: 0.0036380284000188112
2023-01-24 07:42:52.772278: step: 2076/527, loss: 0.007161274552345276
2023-01-24 07:42:53.809113: step: 2080/527, loss: 4.421605990501121e-05
2023-01-24 07:42:54.850367: step: 2084/527, loss: 0.0026107062585651875
2023-01-24 07:42:55.886906: step: 2088/527, loss: 0.0009592160931788385
2023-01-24 07:42:56.932474: step: 2092/527, loss: 0.00039406042196787894
2023-01-24 07:42:57.967671: step: 2096/527, loss: 0.005230220500379801
2023-01-24 07:42:59.034724: step: 2100/527, loss: 0.0021274436730891466
2023-01-24 07:43:00.083601: step: 2104/527, loss: 0.002505266573280096
2023-01-24 07:43:01.148454: step: 2108/527, loss: 0.006490703206509352
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34329449289318803, 'r': 0.32375211189357583, 'f1': 0.333237037046708}, 'combined': 0.24554307992915325, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3715425907843335, 'r': 0.28710109287880314, 'f1': 0.32390892529916254}, 'combined': 0.20730171219146398, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3602868733700377, 'r': 0.3370425589590675, 'f1': 0.34827731092436975}, 'combined': 0.256625386996904, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3759046023829484, 'r': 0.302840492564646, 'f1': 0.33544002244836546}, 'combined': 0.21468161436695385, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36528561111493224, 'r': 0.3250833996449776, 'f1': 0.3440139590620546}, 'combined': 0.2534839698351981, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38429823967850596, 'r': 0.3089799885108863, 'f1': 0.3425477992889765}, 'combined': 0.24560030892417184, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6, 'r': 0.20689655172413793, 'f1': 0.3076923076923077}, 'combined': 0.20512820512820512, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36325359749028163, 'r': 0.3260321662483932, 'f1': 0.3436379032258064}, 'combined': 0.25320687606112047, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3827405873011607, 'r': 0.313309979395116, 'f1': 0.344562453530268}, 'combined': 0.24704477800283367, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 8}
******************************
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
2023-01-24 07:45:29.053833: step: 4/527, loss: 0.0034385870676487684
2023-01-24 07:45:30.096340: step: 8/527, loss: 0.00029713299591094255
2023-01-24 07:45:31.141184: step: 12/527, loss: 0.001968927448615432
2023-01-24 07:45:32.174257: step: 16/527, loss: 0.003574621630832553
2023-01-24 07:45:33.222891: step: 20/527, loss: 0.0016944973031058908
2023-01-24 07:45:34.293878: step: 24/527, loss: 0.0005614277324639261
2023-01-24 07:45:35.348069: step: 28/527, loss: 0.00016602064715698361
2023-01-24 07:45:36.383028: step: 32/527, loss: 0.0004911221330985427
2023-01-24 07:45:37.423483: step: 36/527, loss: 0.0036268248222768307
2023-01-24 07:45:38.460240: step: 40/527, loss: 0.00653064763173461
2023-01-24 07:45:39.534278: step: 44/527, loss: 0.004089450463652611
2023-01-24 07:45:40.595662: step: 48/527, loss: 0.005078588612377644
2023-01-24 07:45:41.640239: step: 52/527, loss: 0.0001291111548198387
2023-01-24 07:45:42.689703: step: 56/527, loss: 0.0007841204642318189
2023-01-24 07:45:43.746881: step: 60/527, loss: 0.013271546922624111
2023-01-24 07:45:44.787538: step: 64/527, loss: 0.009134400635957718
2023-01-24 07:45:45.835390: step: 68/527, loss: 0.0009942364413291216
2023-01-24 07:45:46.890248: step: 72/527, loss: 0.007302484009414911
2023-01-24 07:45:47.951197: step: 76/527, loss: 0.0002903318381868303
2023-01-24 07:45:48.995454: step: 80/527, loss: 0.0009116778965108097
2023-01-24 07:45:50.067675: step: 84/527, loss: 0.0031148213893175125
2023-01-24 07:45:51.121217: step: 88/527, loss: 0.008291029371321201
2023-01-24 07:45:52.153595: step: 92/527, loss: 4.698391057900153e-05
2023-01-24 07:45:53.185314: step: 96/527, loss: 0.0007949414430186152
2023-01-24 07:45:54.226134: step: 100/527, loss: 0.004479155410081148
2023-01-24 07:45:55.296317: step: 104/527, loss: 0.003892976325005293
2023-01-24 07:45:56.383148: step: 108/527, loss: 2.17921297007706e-06
2023-01-24 07:45:57.426549: step: 112/527, loss: 0.0015464965254068375
2023-01-24 07:45:58.462656: step: 116/527, loss: 0.00213803444057703
2023-01-24 07:45:59.512098: step: 120/527, loss: 0.0022411756217479706
2023-01-24 07:46:00.561894: step: 124/527, loss: 0.006723572965711355
2023-01-24 07:46:01.614053: step: 128/527, loss: 0.006680222228169441
2023-01-24 07:46:02.653546: step: 132/527, loss: 0.0024505641777068377
2023-01-24 07:46:03.713586: step: 136/527, loss: 0.003457698505371809
2023-01-24 07:46:04.766505: step: 140/527, loss: 0.011755745857954025
2023-01-24 07:46:05.817546: step: 144/527, loss: 0.002054257085546851
2023-01-24 07:46:06.886256: step: 148/527, loss: 0.003046763828024268
2023-01-24 07:46:07.934485: step: 152/527, loss: 0.001982923364266753
2023-01-24 07:46:08.970009: step: 156/527, loss: 0.00019219951354898512
2023-01-24 07:46:10.022577: step: 160/527, loss: 0.002451239386573434
2023-01-24 07:46:11.065728: step: 164/527, loss: 0.00036641009501181543
2023-01-24 07:46:12.135402: step: 168/527, loss: 0.0019364228937774897
2023-01-24 07:46:13.179951: step: 172/527, loss: 0.0002594398392830044
2023-01-24 07:46:14.215999: step: 176/527, loss: 3.2482847700521233e-07
2023-01-24 07:46:15.286721: step: 180/527, loss: 0.005977904889732599
2023-01-24 07:46:16.333159: step: 184/527, loss: 0.0014887494035065174
2023-01-24 07:46:17.383679: step: 188/527, loss: 0.00010262204887112603
2023-01-24 07:46:18.445961: step: 192/527, loss: 0.0014058399247005582
2023-01-24 07:46:19.483806: step: 196/527, loss: 0.012003547511994839
2023-01-24 07:46:20.538337: step: 200/527, loss: 0.00013779512664768845
2023-01-24 07:46:21.591414: step: 204/527, loss: 0.0018862533615902066
2023-01-24 07:46:22.653266: step: 208/527, loss: 0.006187452934682369
2023-01-24 07:46:23.707724: step: 212/527, loss: 0.001590660191141069
2023-01-24 07:46:24.763884: step: 216/527, loss: 0.003272171365097165
2023-01-24 07:46:25.803173: step: 220/527, loss: 0.00725686177611351
2023-01-24 07:46:26.863719: step: 224/527, loss: 0.00021836531232111156
2023-01-24 07:46:27.929213: step: 228/527, loss: 0.007154582068324089
2023-01-24 07:46:28.989060: step: 232/527, loss: 0.00036996594280935824
2023-01-24 07:46:30.044112: step: 236/527, loss: 0.0007595289498567581
2023-01-24 07:46:31.090226: step: 240/527, loss: 0.00024765549460425973
2023-01-24 07:46:32.137669: step: 244/527, loss: 0.005371781066060066
2023-01-24 07:46:33.196427: step: 248/527, loss: 0.003217507852241397
2023-01-24 07:46:34.254446: step: 252/527, loss: 0.0028972842264920473
2023-01-24 07:46:35.308701: step: 256/527, loss: 0.00028066636878065765
2023-01-24 07:46:36.364280: step: 260/527, loss: 0.0032610679045319557
2023-01-24 07:46:37.413272: step: 264/527, loss: 0.003325643250718713
2023-01-24 07:46:38.457454: step: 268/527, loss: 0.0
2023-01-24 07:46:39.519975: step: 272/527, loss: 0.014231090433895588
2023-01-24 07:46:40.570745: step: 276/527, loss: 0.005514030810445547
2023-01-24 07:46:41.619541: step: 280/527, loss: 0.0004978215438313782
2023-01-24 07:46:42.683109: step: 284/527, loss: 0.004339766688644886
2023-01-24 07:46:43.739746: step: 288/527, loss: 0.0029256227426230907
2023-01-24 07:46:44.808052: step: 292/527, loss: 0.0005764540401287377
2023-01-24 07:46:45.864385: step: 296/527, loss: 0.0019375586416572332
2023-01-24 07:46:46.913878: step: 300/527, loss: 0.004870260134339333
2023-01-24 07:46:47.981704: step: 304/527, loss: 0.004647491499781609
2023-01-24 07:46:49.034733: step: 308/527, loss: 0.0006293188198469579
2023-01-24 07:46:50.079056: step: 312/527, loss: 0.00012084191257599741
2023-01-24 07:46:51.135879: step: 316/527, loss: 0.007480214815586805
2023-01-24 07:46:52.182102: step: 320/527, loss: 1.3044937077211216e-05
2023-01-24 07:46:53.235043: step: 324/527, loss: 0.0016710786148905754
2023-01-24 07:46:54.285505: step: 328/527, loss: 7.654158980585635e-05
2023-01-24 07:46:55.364974: step: 332/527, loss: 3.666698103188537e-05
2023-01-24 07:46:56.407379: step: 336/527, loss: 0.007356188725680113
2023-01-24 07:46:57.462690: step: 340/527, loss: 0.0016076359897851944
2023-01-24 07:46:58.509739: step: 344/527, loss: 0.0037754394579678774
2023-01-24 07:46:59.577106: step: 348/527, loss: 0.006621331907808781
2023-01-24 07:47:00.626218: step: 352/527, loss: 6.784845754737034e-05
2023-01-24 07:47:01.678654: step: 356/527, loss: 0.009478322230279446
2023-01-24 07:47:02.724493: step: 360/527, loss: 6.330499218165642e-06
2023-01-24 07:47:03.764662: step: 364/527, loss: 0.013975173234939575
2023-01-24 07:47:04.822715: step: 368/527, loss: 0.0041032824665308
2023-01-24 07:47:05.872618: step: 372/527, loss: 0.012271531857550144
2023-01-24 07:47:06.937280: step: 376/527, loss: 0.0003107993397861719
2023-01-24 07:47:07.994280: step: 380/527, loss: 0.0013480093330144882
2023-01-24 07:47:09.033958: step: 384/527, loss: 0.0015534843550994992
2023-01-24 07:47:10.077955: step: 388/527, loss: 0.0010218905517831445
2023-01-24 07:47:11.147596: step: 392/527, loss: 0.0012761206598952413
2023-01-24 07:47:12.201006: step: 396/527, loss: 0.005255566444247961
2023-01-24 07:47:13.252661: step: 400/527, loss: 0.0009776563383638859
2023-01-24 07:47:14.323562: step: 404/527, loss: 0.0006973003037273884
2023-01-24 07:47:15.375465: step: 408/527, loss: 0.0029390431009233
2023-01-24 07:47:16.417803: step: 412/527, loss: 0.0001560229720780626
2023-01-24 07:47:17.472975: step: 416/527, loss: 0.0025680658873170614
2023-01-24 07:47:18.526175: step: 420/527, loss: 0.010235791094601154
2023-01-24 07:47:19.601352: step: 424/527, loss: 0.0027746185660362244
2023-01-24 07:47:20.654731: step: 428/527, loss: 0.01127717923372984
2023-01-24 07:47:21.714669: step: 432/527, loss: 0.009032091125845909
2023-01-24 07:47:22.755532: step: 436/527, loss: 0.0017111834604293108
2023-01-24 07:47:23.806522: step: 440/527, loss: 0.00027508108178153634
2023-01-24 07:47:24.866008: step: 444/527, loss: 0.004775597248226404
2023-01-24 07:47:25.914497: step: 448/527, loss: 0.014230608940124512
2023-01-24 07:47:26.984414: step: 452/527, loss: 0.0013496255269274116
2023-01-24 07:47:28.035053: step: 456/527, loss: 0.012655236758291721
2023-01-24 07:47:29.086586: step: 460/527, loss: 0.0008285652147606015
2023-01-24 07:47:30.152060: step: 464/527, loss: 0.0006113981362432241
2023-01-24 07:47:31.192792: step: 468/527, loss: 3.422592271817848e-05
2023-01-24 07:47:32.271161: step: 472/527, loss: 0.012131537310779095
2023-01-24 07:47:33.331105: step: 476/527, loss: 0.002359824487939477
2023-01-24 07:47:34.388176: step: 480/527, loss: 0.002012055367231369
2023-01-24 07:47:35.415072: step: 484/527, loss: 0.0
2023-01-24 07:47:36.486001: step: 488/527, loss: 0.00022573393653146923
2023-01-24 07:47:37.546321: step: 492/527, loss: 0.0004634474462363869
2023-01-24 07:47:38.611179: step: 496/527, loss: 0.0024044073652476072
2023-01-24 07:47:39.649381: step: 500/527, loss: 0.002115800743922591
2023-01-24 07:47:40.708291: step: 504/527, loss: 0.0043561081402003765
2023-01-24 07:47:41.769059: step: 508/527, loss: 0.0012777147348970175
2023-01-24 07:47:42.820289: step: 512/527, loss: 0.0017793085426092148
2023-01-24 07:47:43.866990: step: 516/527, loss: 0.028184030205011368
2023-01-24 07:47:44.922655: step: 520/527, loss: 0.007247556932270527
2023-01-24 07:47:45.970080: step: 524/527, loss: 8.568251359974965e-05
2023-01-24 07:47:47.026712: step: 528/527, loss: 0.003138698171824217
2023-01-24 07:47:48.086356: step: 532/527, loss: 0.0005081011913716793
2023-01-24 07:47:49.133087: step: 536/527, loss: 0.0
2023-01-24 07:47:50.206281: step: 540/527, loss: 0.0001450574054615572
2023-01-24 07:47:51.270037: step: 544/527, loss: 0.0062448144890367985
2023-01-24 07:47:52.323765: step: 548/527, loss: 0.007234330754727125
2023-01-24 07:47:53.376348: step: 552/527, loss: 0.001055950648151338
2023-01-24 07:47:54.435886: step: 556/527, loss: 0.00021663459483534098
2023-01-24 07:47:55.490261: step: 560/527, loss: 0.0018378297099843621
2023-01-24 07:47:56.547954: step: 564/527, loss: 0.0019507826073095202
2023-01-24 07:47:57.619314: step: 568/527, loss: 0.0020837734919041395
2023-01-24 07:47:58.668929: step: 572/527, loss: 0.003399675013497472
2023-01-24 07:47:59.712895: step: 576/527, loss: 0.0036772252060472965
2023-01-24 07:48:00.774596: step: 580/527, loss: 0.00118359609041363
2023-01-24 07:48:01.826800: step: 584/527, loss: 0.00029811804415658116
2023-01-24 07:48:02.875176: step: 588/527, loss: 0.002658726880326867
2023-01-24 07:48:03.926247: step: 592/527, loss: 0.01457090862095356
2023-01-24 07:48:04.994558: step: 596/527, loss: 0.004640995059162378
2023-01-24 07:48:06.040250: step: 600/527, loss: 0.0015015759272500873
2023-01-24 07:48:07.095126: step: 604/527, loss: 0.0032119008246809244
2023-01-24 07:48:08.139422: step: 608/527, loss: 0.0036756584886461496
2023-01-24 07:48:09.187759: step: 612/527, loss: 0.000626731722149998
2023-01-24 07:48:10.247946: step: 616/527, loss: 0.00037523164064623415
2023-01-24 07:48:11.298234: step: 620/527, loss: 0.0007973259780555964
2023-01-24 07:48:12.366734: step: 624/527, loss: 0.0056456513702869415
2023-01-24 07:48:13.421588: step: 628/527, loss: 0.026532448828220367
2023-01-24 07:48:14.464781: step: 632/527, loss: 0.0005014989874325693
2023-01-24 07:48:15.540742: step: 636/527, loss: 0.0015794503269717097
2023-01-24 07:48:16.598981: step: 640/527, loss: 0.0008615500410087407
2023-01-24 07:48:17.650505: step: 644/527, loss: 0.006188173778355122
2023-01-24 07:48:18.697735: step: 648/527, loss: 0.0024688735138624907
2023-01-24 07:48:19.763072: step: 652/527, loss: 0.00021416146773844957
2023-01-24 07:48:20.819222: step: 656/527, loss: 0.005300307646393776
2023-01-24 07:48:21.858003: step: 660/527, loss: 0.012360951863229275
2023-01-24 07:48:22.897259: step: 664/527, loss: 0.00018883055599872023
2023-01-24 07:48:23.927147: step: 668/527, loss: 0.001723723253235221
2023-01-24 07:48:24.979395: step: 672/527, loss: 0.0009996925946325064
2023-01-24 07:48:26.026385: step: 676/527, loss: 0.0186931025236845
2023-01-24 07:48:27.098370: step: 680/527, loss: 0.006850207690149546
2023-01-24 07:48:28.145621: step: 684/527, loss: 0.0041246963664889336
2023-01-24 07:48:29.188453: step: 688/527, loss: 0.00033193855779245496
2023-01-24 07:48:30.226752: step: 692/527, loss: 0.001357655506581068
2023-01-24 07:48:31.273665: step: 696/527, loss: 0.00399990938603878
2023-01-24 07:48:32.326272: step: 700/527, loss: 0.00022381976305041462
2023-01-24 07:48:33.367465: step: 704/527, loss: 0.00813576765358448
2023-01-24 07:48:34.414477: step: 708/527, loss: 6.659329665126279e-05
2023-01-24 07:48:35.474753: step: 712/527, loss: 0.004132091533392668
2023-01-24 07:48:36.524038: step: 716/527, loss: 0.004225397016853094
2023-01-24 07:48:37.569459: step: 720/527, loss: 0.0027986590284854174
2023-01-24 07:48:38.605240: step: 724/527, loss: 0.005259071476757526
2023-01-24 07:48:39.632581: step: 728/527, loss: 0.004428376909345388
2023-01-24 07:48:40.696106: step: 732/527, loss: 0.0061376020312309265
2023-01-24 07:48:41.729071: step: 736/527, loss: 0.00029465576517395675
2023-01-24 07:48:42.778034: step: 740/527, loss: 0.003344725351780653
2023-01-24 07:48:43.813298: step: 744/527, loss: 0.007926919497549534
2023-01-24 07:48:44.871280: step: 748/527, loss: 0.00021887487673666328
2023-01-24 07:48:45.922062: step: 752/527, loss: 6.21903091087006e-05
2023-01-24 07:48:46.969742: step: 756/527, loss: 0.0005317451432347298
2023-01-24 07:48:48.019705: step: 760/527, loss: 0.002144468016922474
2023-01-24 07:48:49.074231: step: 764/527, loss: 0.0006259052315726876
2023-01-24 07:48:50.132217: step: 768/527, loss: 0.02363005466759205
2023-01-24 07:48:51.181669: step: 772/527, loss: 0.0034788320772349834
2023-01-24 07:48:52.247347: step: 776/527, loss: 0.0005750986165367067
2023-01-24 07:48:53.291440: step: 780/527, loss: 0.010245602577924728
2023-01-24 07:48:54.343654: step: 784/527, loss: 0.001477353274822235
2023-01-24 07:48:55.404050: step: 788/527, loss: 0.004400107078254223
2023-01-24 07:48:56.442126: step: 792/527, loss: 0.03304194286465645
2023-01-24 07:48:57.490430: step: 796/527, loss: 0.001029366278089583
2023-01-24 07:48:58.544376: step: 800/527, loss: 0.0012383551802486181
2023-01-24 07:48:59.595122: step: 804/527, loss: 0.008803913369774818
2023-01-24 07:49:00.636277: step: 808/527, loss: 0.00018131342949345708
2023-01-24 07:49:01.681605: step: 812/527, loss: 0.005063209682703018
2023-01-24 07:49:02.726510: step: 816/527, loss: 0.0001871378335636109
2023-01-24 07:49:03.769108: step: 820/527, loss: 0.0017088191816583276
2023-01-24 07:49:04.796899: step: 824/527, loss: 0.000313976634060964
2023-01-24 07:49:05.869067: step: 828/527, loss: 8.94362383405678e-05
2023-01-24 07:49:06.937434: step: 832/527, loss: 0.0009407568722963333
2023-01-24 07:49:07.983367: step: 836/527, loss: 0.004834346938878298
2023-01-24 07:49:09.029605: step: 840/527, loss: 2.4350756575586274e-05
2023-01-24 07:49:10.068105: step: 844/527, loss: 0.006917926017194986
2023-01-24 07:49:11.124843: step: 848/527, loss: 0.0005837543285451829
2023-01-24 07:49:12.182356: step: 852/527, loss: 0.0008525578887201846
2023-01-24 07:49:13.238576: step: 856/527, loss: 0.027686726301908493
2023-01-24 07:49:14.298383: step: 860/527, loss: 0.0026730350218713284
2023-01-24 07:49:15.358101: step: 864/527, loss: 0.004414840135723352
2023-01-24 07:49:16.408474: step: 868/527, loss: 0.00095394003437832
2023-01-24 07:49:17.453550: step: 872/527, loss: 0.001670580473728478
2023-01-24 07:49:18.514247: step: 876/527, loss: 0.00013169716112315655
2023-01-24 07:49:19.569643: step: 880/527, loss: 0.0005274789873510599
2023-01-24 07:49:20.616468: step: 884/527, loss: 0.00881276000291109
2023-01-24 07:49:21.671822: step: 888/527, loss: 2.3202443117043003e-05
2023-01-24 07:49:22.708214: step: 892/527, loss: 0.0013199002714827657
2023-01-24 07:49:23.761241: step: 896/527, loss: 0.0034865480847656727
2023-01-24 07:49:24.812280: step: 900/527, loss: 2.6759513275464997e-05
2023-01-24 07:49:25.848190: step: 904/527, loss: 0.00742027023807168
2023-01-24 07:49:26.890013: step: 908/527, loss: 0.0054139369167387486
2023-01-24 07:49:27.934690: step: 912/527, loss: 0.0008490922045893967
2023-01-24 07:49:28.986887: step: 916/527, loss: 0.0002286379021825269
2023-01-24 07:49:30.043520: step: 920/527, loss: 0.005094374530017376
2023-01-24 07:49:31.097532: step: 924/527, loss: 0.0010047341929748654
2023-01-24 07:49:32.147581: step: 928/527, loss: 0.0021650586277246475
2023-01-24 07:49:33.193239: step: 932/527, loss: 0.0035606506280601025
2023-01-24 07:49:34.242279: step: 936/527, loss: 0.0003091662365477532
2023-01-24 07:49:35.290786: step: 940/527, loss: 0.003999793436378241
2023-01-24 07:49:36.331175: step: 944/527, loss: 0.027652982622385025
2023-01-24 07:49:37.384722: step: 948/527, loss: 0.0031255122739821672
2023-01-24 07:49:38.417017: step: 952/527, loss: 0.0034520861227065325
2023-01-24 07:49:39.470452: step: 956/527, loss: 0.0015175495063886046
2023-01-24 07:49:40.516127: step: 960/527, loss: 0.003083609975874424
2023-01-24 07:49:41.574609: step: 964/527, loss: 0.0034182965755462646
2023-01-24 07:49:42.631457: step: 968/527, loss: 0.0019579913932830095
2023-01-24 07:49:43.676900: step: 972/527, loss: 0.003388741984963417
2023-01-24 07:49:44.736079: step: 976/527, loss: 0.0004289007920306176
2023-01-24 07:49:45.772119: step: 980/527, loss: 0.008413110859692097
2023-01-24 07:49:46.807486: step: 984/527, loss: 0.033625949174165726
2023-01-24 07:49:47.844003: step: 988/527, loss: 0.0008374184253625572
2023-01-24 07:49:48.879223: step: 992/527, loss: 7.134010957088321e-05
2023-01-24 07:49:49.948502: step: 996/527, loss: 0.0016638896195217967
2023-01-24 07:49:50.996573: step: 1000/527, loss: 0.01010317075997591
2023-01-24 07:49:52.050291: step: 1004/527, loss: 0.0029414936434477568
2023-01-24 07:49:53.095522: step: 1008/527, loss: 0.004308727104216814
2023-01-24 07:49:54.145874: step: 1012/527, loss: 0.0016412204131484032
2023-01-24 07:49:55.209594: step: 1016/527, loss: 0.007245340384542942
2023-01-24 07:49:56.277714: step: 1020/527, loss: 0.00031418513390235603
2023-01-24 07:49:57.316571: step: 1024/527, loss: 0.00016337065608240664
2023-01-24 07:49:58.348223: step: 1028/527, loss: 0.002298986306414008
2023-01-24 07:49:59.407462: step: 1032/527, loss: 0.0015857777325436473
2023-01-24 07:50:00.467261: step: 1036/527, loss: 0.029947228729724884
2023-01-24 07:50:01.543140: step: 1040/527, loss: 0.004765619989484549
2023-01-24 07:50:02.595072: step: 1044/527, loss: 0.009243758395314217
2023-01-24 07:50:03.641307: step: 1048/527, loss: 0.001570431748405099
2023-01-24 07:50:04.688117: step: 1052/527, loss: 0.0003034933761227876
2023-01-24 07:50:05.716624: step: 1056/527, loss: 0.0003016614937223494
2023-01-24 07:50:06.778573: step: 1060/527, loss: 0.00451872032135725
2023-01-24 07:50:07.830796: step: 1064/527, loss: 0.004765608813613653
2023-01-24 07:50:08.891112: step: 1068/527, loss: 0.009984379634261131
2023-01-24 07:50:09.933871: step: 1072/527, loss: 0.011205597780644894
2023-01-24 07:50:10.995140: step: 1076/527, loss: 0.0015372848138213158
2023-01-24 07:50:12.047179: step: 1080/527, loss: 0.0028527549002319574
2023-01-24 07:50:13.115238: step: 1084/527, loss: 0.009391309693455696
2023-01-24 07:50:14.160793: step: 1088/527, loss: 0.0016450384864583611
2023-01-24 07:50:15.200274: step: 1092/527, loss: 0.0005399346118792892
2023-01-24 07:50:16.263503: step: 1096/527, loss: 0.0003490214003250003
2023-01-24 07:50:17.301804: step: 1100/527, loss: 0.010700157843530178
2023-01-24 07:50:18.373427: step: 1104/527, loss: 0.004406277555972338
2023-01-24 07:50:19.456288: step: 1108/527, loss: 0.00541723845526576
2023-01-24 07:50:20.510649: step: 1112/527, loss: 1.115364739234792e-05
2023-01-24 07:50:21.558974: step: 1116/527, loss: 0.0011980623239651322
2023-01-24 07:50:22.603917: step: 1120/527, loss: 0.009564312174916267
2023-01-24 07:50:23.667125: step: 1124/527, loss: 0.006887249648571014
2023-01-24 07:50:24.737609: step: 1128/527, loss: 0.0001486936234869063
2023-01-24 07:50:25.805912: step: 1132/527, loss: 0.002974584000185132
2023-01-24 07:50:26.861727: step: 1136/527, loss: 0.0036571312230080366
2023-01-24 07:50:27.913071: step: 1140/527, loss: 0.002105077961459756
2023-01-24 07:50:28.981331: step: 1144/527, loss: 0.00019063902436755598
2023-01-24 07:50:30.042531: step: 1148/527, loss: 0.006378160789608955
2023-01-24 07:50:31.092012: step: 1152/527, loss: 0.0002467613376211375
2023-01-24 07:50:32.130740: step: 1156/527, loss: 0.0039273472502827644
2023-01-24 07:50:33.179986: step: 1160/527, loss: 0.003809248795732856
2023-01-24 07:50:34.247364: step: 1164/527, loss: 0.011625951156020164
2023-01-24 07:50:35.282584: step: 1168/527, loss: 0.003630966879427433
2023-01-24 07:50:36.343540: step: 1172/527, loss: 0.008686323650181293
2023-01-24 07:50:37.401303: step: 1176/527, loss: 0.0007059941999614239
2023-01-24 07:50:38.454210: step: 1180/527, loss: 2.5776464099180885e-05
2023-01-24 07:50:39.512605: step: 1184/527, loss: 0.0026349988766014576
2023-01-24 07:50:40.550308: step: 1188/527, loss: 0.001742327818647027
2023-01-24 07:50:41.592540: step: 1192/527, loss: 2.044104576270911e-06
2023-01-24 07:50:42.652898: step: 1196/527, loss: 0.0019598728977143764
2023-01-24 07:50:43.693254: step: 1200/527, loss: 0.0006487110513262451
2023-01-24 07:50:44.732848: step: 1204/527, loss: 0.000515613064635545
2023-01-24 07:50:45.797134: step: 1208/527, loss: 0.003136194311082363
2023-01-24 07:50:46.841583: step: 1212/527, loss: 0.000336171971866861
2023-01-24 07:50:47.908950: step: 1216/527, loss: 0.028238510712981224
2023-01-24 07:50:48.944223: step: 1220/527, loss: 0.0007461044006049633
2023-01-24 07:50:50.020086: step: 1224/527, loss: 0.00046366697642952204
2023-01-24 07:50:51.059557: step: 1228/527, loss: 0.0033446340821683407
2023-01-24 07:50:52.134694: step: 1232/527, loss: 0.0006776587688364089
2023-01-24 07:50:53.176457: step: 1236/527, loss: 0.008448583073914051
2023-01-24 07:50:54.221086: step: 1240/527, loss: 0.004112632479518652
2023-01-24 07:50:55.260956: step: 1244/527, loss: 0.0035975042264908552
2023-01-24 07:50:56.301621: step: 1248/527, loss: 0.007639944553375244
2023-01-24 07:50:57.355491: step: 1252/527, loss: 0.00027725001564249396
2023-01-24 07:50:58.406112: step: 1256/527, loss: 0.0019933138974010944
2023-01-24 07:50:59.464416: step: 1260/527, loss: 0.005885405000299215
2023-01-24 07:51:00.510686: step: 1264/527, loss: 0.00020798925834242254
2023-01-24 07:51:01.574335: step: 1268/527, loss: 0.0014467276632785797
2023-01-24 07:51:02.622084: step: 1272/527, loss: 0.0012812019558623433
2023-01-24 07:51:03.667942: step: 1276/527, loss: 0.0016509346896782517
2023-01-24 07:51:04.712245: step: 1280/527, loss: 0.029428355395793915
2023-01-24 07:51:05.764995: step: 1284/527, loss: 0.0003505543863866478
2023-01-24 07:51:06.825975: step: 1288/527, loss: 0.003971409518271685
2023-01-24 07:51:07.872989: step: 1292/527, loss: 0.0041485680267214775
2023-01-24 07:51:08.916299: step: 1296/527, loss: 6.258472421905026e-05
2023-01-24 07:51:09.984461: step: 1300/527, loss: 0.0056670717895030975
2023-01-24 07:51:11.036120: step: 1304/527, loss: 0.0008777391631156206
2023-01-24 07:51:12.087211: step: 1308/527, loss: 0.006410645321011543
2023-01-24 07:51:13.133765: step: 1312/527, loss: 0.001781641156412661
2023-01-24 07:51:14.184223: step: 1316/527, loss: 0.002438068389892578
2023-01-24 07:51:15.232940: step: 1320/527, loss: 0.002560111228376627
2023-01-24 07:51:16.277056: step: 1324/527, loss: 0.0008724459912627935
2023-01-24 07:51:17.331325: step: 1328/527, loss: 0.0013217119267210364
2023-01-24 07:51:18.385645: step: 1332/527, loss: 0.00022965823882259429
2023-01-24 07:51:19.456435: step: 1336/527, loss: 0.00047675950918346643
2023-01-24 07:51:20.497157: step: 1340/527, loss: 0.0002364874235354364
2023-01-24 07:51:21.551461: step: 1344/527, loss: 0.012648622505366802
2023-01-24 07:51:22.608405: step: 1348/527, loss: 0.009509393014013767
2023-01-24 07:51:23.664656: step: 1352/527, loss: 0.005710206925868988
2023-01-24 07:51:24.713696: step: 1356/527, loss: 0.005535817239433527
2023-01-24 07:51:25.782813: step: 1360/527, loss: 0.004796273075044155
2023-01-24 07:51:26.828278: step: 1364/527, loss: 0.02941475808620453
2023-01-24 07:51:27.858035: step: 1368/527, loss: 0.0031732227653265
2023-01-24 07:51:28.930533: step: 1372/527, loss: 0.009113037027418613
2023-01-24 07:51:29.981879: step: 1376/527, loss: 0.00972342025488615
2023-01-24 07:51:31.036210: step: 1380/527, loss: 0.004497257526963949
2023-01-24 07:51:32.098527: step: 1384/527, loss: 0.010309236124157906
2023-01-24 07:51:33.145108: step: 1388/527, loss: 0.0024991300888359547
2023-01-24 07:51:34.206758: step: 1392/527, loss: 0.000653493101708591
2023-01-24 07:51:35.256330: step: 1396/527, loss: 0.003460506908595562
2023-01-24 07:51:36.302393: step: 1400/527, loss: 0.001133756130002439
2023-01-24 07:51:37.341502: step: 1404/527, loss: 0.0015325575368478894
2023-01-24 07:51:38.397050: step: 1408/527, loss: 0.00836519617587328
2023-01-24 07:51:39.451896: step: 1412/527, loss: 0.002205162076279521
2023-01-24 07:51:40.535308: step: 1416/527, loss: 0.08566229045391083
2023-01-24 07:51:41.593052: step: 1420/527, loss: 0.007607208099216223
2023-01-24 07:51:42.639789: step: 1424/527, loss: 0.0006425183382816613
2023-01-24 07:51:43.699328: step: 1428/527, loss: 0.001953200437128544
2023-01-24 07:51:44.756423: step: 1432/527, loss: 0.0045538912527263165
2023-01-24 07:51:45.799534: step: 1436/527, loss: 0.00012479489669203758
2023-01-24 07:51:46.850038: step: 1440/527, loss: 0.005342176649719477
2023-01-24 07:51:47.912039: step: 1444/527, loss: 0.009013012051582336
2023-01-24 07:51:48.951876: step: 1448/527, loss: 0.004276537336409092
2023-01-24 07:51:50.028447: step: 1452/527, loss: 0.005824533756822348
2023-01-24 07:51:51.070757: step: 1456/527, loss: 0.0006591712008230388
2023-01-24 07:51:52.130657: step: 1460/527, loss: 0.005048574414104223
2023-01-24 07:51:53.180549: step: 1464/527, loss: 0.004408989567309618
2023-01-24 07:51:54.210353: step: 1468/527, loss: 0.0023100601974874735
2023-01-24 07:51:55.247294: step: 1472/527, loss: 0.018858449533581734
2023-01-24 07:51:56.290969: step: 1476/527, loss: 0.0025698766112327576
2023-01-24 07:51:57.339625: step: 1480/527, loss: 0.004582853987812996
2023-01-24 07:51:58.378691: step: 1484/527, loss: 0.0024459497071802616
2023-01-24 07:51:59.423900: step: 1488/527, loss: 0.001870372798293829
2023-01-24 07:52:00.504217: step: 1492/527, loss: 0.0007779135485179722
2023-01-24 07:52:01.580195: step: 1496/527, loss: 0.0033443497959524393
2023-01-24 07:52:02.614552: step: 1500/527, loss: 0.0025116491597145796
2023-01-24 07:52:03.652429: step: 1504/527, loss: 0.006434546783566475
2023-01-24 07:52:04.696674: step: 1508/527, loss: 0.002134869573637843
2023-01-24 07:52:05.740193: step: 1512/527, loss: 0.005965932738035917
2023-01-24 07:52:06.781935: step: 1516/527, loss: 0.0032697084825485945
2023-01-24 07:52:07.814259: step: 1520/527, loss: 0.011707708239555359
2023-01-24 07:52:08.862073: step: 1524/527, loss: 0.003924786113202572
2023-01-24 07:52:09.898508: step: 1528/527, loss: 0.005687150172889233
2023-01-24 07:52:10.941807: step: 1532/527, loss: 0.0015920015284791589
2023-01-24 07:52:12.002955: step: 1536/527, loss: 0.015378007665276527
2023-01-24 07:52:13.063049: step: 1540/527, loss: 0.004583601839840412
2023-01-24 07:52:14.107963: step: 1544/527, loss: 0.0028360383585095406
2023-01-24 07:52:15.154610: step: 1548/527, loss: 0.0021851013880223036
2023-01-24 07:52:16.192029: step: 1552/527, loss: 0.003037082962691784
2023-01-24 07:52:17.258673: step: 1556/527, loss: 0.012514110654592514
2023-01-24 07:52:18.310969: step: 1560/527, loss: 0.0019110996508970857
2023-01-24 07:52:19.361645: step: 1564/527, loss: 0.0006105828797444701
2023-01-24 07:52:20.404527: step: 1568/527, loss: 0.0004732580855488777
2023-01-24 07:52:21.437285: step: 1572/527, loss: 0.003760196967050433
2023-01-24 07:52:22.488383: step: 1576/527, loss: 0.003763664746657014
2023-01-24 07:52:23.531742: step: 1580/527, loss: 0.0012006523320451379
2023-01-24 07:52:24.580792: step: 1584/527, loss: 0.00037941866321489215
2023-01-24 07:52:25.642426: step: 1588/527, loss: 0.006562489550560713
2023-01-24 07:52:26.673442: step: 1592/527, loss: 0.03608640655875206
2023-01-24 07:52:27.715683: step: 1596/527, loss: 0.0073776342906057835
2023-01-24 07:52:28.769658: step: 1600/527, loss: 0.005907274316996336
2023-01-24 07:52:29.801667: step: 1604/527, loss: 0.0006821455899626017
2023-01-24 07:52:30.868669: step: 1608/527, loss: 0.01251176092773676
2023-01-24 07:52:31.912896: step: 1612/527, loss: 0.0009520926978439093
2023-01-24 07:52:32.961505: step: 1616/527, loss: 0.0037912847474217415
2023-01-24 07:52:34.009157: step: 1620/527, loss: 8.045620779739693e-05
2023-01-24 07:52:35.059020: step: 1624/527, loss: 0.006598693784326315
2023-01-24 07:52:36.096585: step: 1628/527, loss: 0.0012025644537061453
2023-01-24 07:52:37.128753: step: 1632/527, loss: 4.749703293782659e-05
2023-01-24 07:52:38.171386: step: 1636/527, loss: 0.0009005185565911233
2023-01-24 07:52:39.217416: step: 1640/527, loss: 0.0019350543152540922
2023-01-24 07:52:40.262973: step: 1644/527, loss: 0.00863682385534048
2023-01-24 07:52:41.328833: step: 1648/527, loss: 0.0019152669701725245
2023-01-24 07:52:42.374319: step: 1652/527, loss: 0.0007904738886281848
2023-01-24 07:52:43.433389: step: 1656/527, loss: 0.004350421484559774
2023-01-24 07:52:44.494933: step: 1660/527, loss: 0.006533185951411724
2023-01-24 07:52:45.534204: step: 1664/527, loss: 0.00529212411493063
2023-01-24 07:52:46.581572: step: 1668/527, loss: 0.007193727884441614
2023-01-24 07:52:47.627688: step: 1672/527, loss: 0.0003473594842944294
2023-01-24 07:52:48.674551: step: 1676/527, loss: 0.014090189710259438
2023-01-24 07:52:49.726626: step: 1680/527, loss: 0.0037139994092285633
2023-01-24 07:52:50.782746: step: 1684/527, loss: 0.0020392511505633593
2023-01-24 07:52:51.831941: step: 1688/527, loss: 0.003827287582680583
2023-01-24 07:52:52.886228: step: 1692/527, loss: 0.003518494078889489
2023-01-24 07:52:53.928236: step: 1696/527, loss: 0.0015186556847766042
2023-01-24 07:52:54.991971: step: 1700/527, loss: 0.003926885314285755
2023-01-24 07:52:56.034926: step: 1704/527, loss: 0.002102620666846633
2023-01-24 07:52:57.073603: step: 1708/527, loss: 0.004677518270909786
2023-01-24 07:52:58.117319: step: 1712/527, loss: 0.017792485654354095
2023-01-24 07:52:59.185332: step: 1716/527, loss: 0.0030138115398585796
2023-01-24 07:53:00.232295: step: 1720/527, loss: 0.0008383300737477839
2023-01-24 07:53:01.278077: step: 1724/527, loss: 0.005080461036413908
2023-01-24 07:53:02.319114: step: 1728/527, loss: 0.0003374902589712292
2023-01-24 07:53:03.381026: step: 1732/527, loss: 0.006319050677120686
2023-01-24 07:53:04.429624: step: 1736/527, loss: 0.00012671062722802162
2023-01-24 07:53:05.463518: step: 1740/527, loss: 0.0003456561535131186
2023-01-24 07:53:06.514788: step: 1744/527, loss: 0.042993925511837006
2023-01-24 07:53:07.548136: step: 1748/527, loss: 0.008083181455731392
2023-01-24 07:53:08.601925: step: 1752/527, loss: 0.003613003296777606
2023-01-24 07:53:09.635987: step: 1756/527, loss: 0.006234684959053993
2023-01-24 07:53:10.690252: step: 1760/527, loss: 0.006225149147212505
2023-01-24 07:53:11.725216: step: 1764/527, loss: 0.005681393668055534
2023-01-24 07:53:12.778020: step: 1768/527, loss: 0.0005418686778284609
2023-01-24 07:53:13.839765: step: 1772/527, loss: 0.0031710597686469555
2023-01-24 07:53:14.883885: step: 1776/527, loss: 0.0025270304176956415
2023-01-24 07:53:15.938121: step: 1780/527, loss: 0.0029379629995673895
2023-01-24 07:53:16.992482: step: 1784/527, loss: 0.004091819282621145
2023-01-24 07:53:18.037185: step: 1788/527, loss: 0.004152192268520594
2023-01-24 07:53:19.073444: step: 1792/527, loss: 0.0006632282165810466
2023-01-24 07:53:20.125962: step: 1796/527, loss: 0.006866875104606152
2023-01-24 07:53:21.167254: step: 1800/527, loss: 0.005559556186199188
2023-01-24 07:53:22.215034: step: 1804/527, loss: 0.000458006834378466
2023-01-24 07:53:23.250713: step: 1808/527, loss: 0.0033429362811148167
2023-01-24 07:53:24.296833: step: 1812/527, loss: 0.009467796422541142
2023-01-24 07:53:25.332640: step: 1816/527, loss: 0.004855016712099314
2023-01-24 07:53:26.383420: step: 1820/527, loss: 0.007009300868958235
2023-01-24 07:53:27.441638: step: 1824/527, loss: 0.002213296014815569
2023-01-24 07:53:28.504306: step: 1828/527, loss: 0.036922577768564224
2023-01-24 07:53:29.556723: step: 1832/527, loss: 0.0022862209007143974
2023-01-24 07:53:30.601321: step: 1836/527, loss: 0.0054118698462843895
2023-01-24 07:53:31.655298: step: 1840/527, loss: 0.004481484182178974
2023-01-24 07:53:32.702536: step: 1844/527, loss: 0.002876381389796734
2023-01-24 07:53:33.753093: step: 1848/527, loss: 0.004492246545851231
2023-01-24 07:53:34.801476: step: 1852/527, loss: 5.41856097697746e-05
2023-01-24 07:53:35.843332: step: 1856/527, loss: 0.004717900417745113
2023-01-24 07:53:36.888490: step: 1860/527, loss: 0.0037742636632174253
2023-01-24 07:53:37.923908: step: 1864/527, loss: 0.0008915414218790829
2023-01-24 07:53:38.968300: step: 1868/527, loss: 0.0014861089875921607
2023-01-24 07:53:40.011183: step: 1872/527, loss: 0.0006288950680755079
2023-01-24 07:53:41.048407: step: 1876/527, loss: 0.005388900637626648
2023-01-24 07:53:42.101864: step: 1880/527, loss: 0.003864086465910077
2023-01-24 07:53:43.144426: step: 1884/527, loss: 0.006012776400893927
2023-01-24 07:53:44.216679: step: 1888/527, loss: 0.019474459812045097
2023-01-24 07:53:45.262105: step: 1892/527, loss: 0.004927025642246008
2023-01-24 07:53:46.301815: step: 1896/527, loss: 0.0017890379531309009
2023-01-24 07:53:47.356199: step: 1900/527, loss: 0.0036250848788768053
2023-01-24 07:53:48.403241: step: 1904/527, loss: 0.0021174089051783085
2023-01-24 07:53:49.464357: step: 1908/527, loss: 0.004929032642394304
2023-01-24 07:53:50.502525: step: 1912/527, loss: 0.013725148513913155
2023-01-24 07:53:51.534831: step: 1916/527, loss: 0.011531383730471134
2023-01-24 07:53:52.584516: step: 1920/527, loss: 0.003347012447193265
2023-01-24 07:53:53.623986: step: 1924/527, loss: 0.009026437066495419
2023-01-24 07:53:54.679418: step: 1928/527, loss: 0.0001847794046625495
2023-01-24 07:53:55.728585: step: 1932/527, loss: 0.015622053295373917
2023-01-24 07:53:56.778676: step: 1936/527, loss: 0.0037039590533822775
2023-01-24 07:53:57.826324: step: 1940/527, loss: 0.005754625424742699
2023-01-24 07:53:58.863738: step: 1944/527, loss: 0.004106899257749319
2023-01-24 07:53:59.900036: step: 1948/527, loss: 0.0010922342771664262
2023-01-24 07:54:00.957264: step: 1952/527, loss: 0.011303143575787544
2023-01-24 07:54:02.002905: step: 1956/527, loss: 0.0007308688363991678
2023-01-24 07:54:03.063016: step: 1960/527, loss: 0.0007425081566907465
2023-01-24 07:54:04.120052: step: 1964/527, loss: 0.0027463282458484173
2023-01-24 07:54:05.157923: step: 1968/527, loss: 0.0021160945761948824
2023-01-24 07:54:06.201578: step: 1972/527, loss: 1.5059528095662245e-06
2023-01-24 07:54:07.256661: step: 1976/527, loss: 0.0024889616761356592
2023-01-24 07:54:08.315110: step: 1980/527, loss: 0.062308456748723984
2023-01-24 07:54:09.355699: step: 1984/527, loss: 0.0007120163645595312
2023-01-24 07:54:10.398095: step: 1988/527, loss: 0.000993556110188365
2023-01-24 07:54:11.448898: step: 1992/527, loss: 0.0003347903548274189
2023-01-24 07:54:12.486646: step: 1996/527, loss: 0.0061900257132947445
2023-01-24 07:54:13.544943: step: 2000/527, loss: 0.012815129943192005
2023-01-24 07:54:14.580318: step: 2004/527, loss: 2.3776488887961023e-05
2023-01-24 07:54:15.645906: step: 2008/527, loss: 0.013798339292407036
2023-01-24 07:54:16.711253: step: 2012/527, loss: 0.001623197109438479
2023-01-24 07:54:17.757770: step: 2016/527, loss: 0.000656258431263268
2023-01-24 07:54:18.839766: step: 2020/527, loss: 1.8884347809944302e-05
2023-01-24 07:54:19.890524: step: 2024/527, loss: 0.0037832241505384445
2023-01-24 07:54:20.922741: step: 2028/527, loss: 0.00029103129054419696
2023-01-24 07:54:21.992807: step: 2032/527, loss: 0.001067739212885499
2023-01-24 07:54:23.042437: step: 2036/527, loss: 0.01484745554625988
2023-01-24 07:54:24.069561: step: 2040/527, loss: 0.005156759172677994
2023-01-24 07:54:25.135321: step: 2044/527, loss: 0.004316109698265791
2023-01-24 07:54:26.184886: step: 2048/527, loss: 0.0006669743452221155
2023-01-24 07:54:27.228963: step: 2052/527, loss: 0.007700266782194376
2023-01-24 07:54:28.312014: step: 2056/527, loss: 0.003209709655493498
2023-01-24 07:54:29.359861: step: 2060/527, loss: 0.002674531890079379
2023-01-24 07:54:30.400389: step: 2064/527, loss: 0.002433930989354849
2023-01-24 07:54:31.460044: step: 2068/527, loss: 0.0015503098256886005
2023-01-24 07:54:32.498759: step: 2072/527, loss: 0.004364384338259697
2023-01-24 07:54:33.570442: step: 2076/527, loss: 0.006797038484364748
2023-01-24 07:54:34.606281: step: 2080/527, loss: 7.489960262319073e-05
2023-01-24 07:54:35.661082: step: 2084/527, loss: 0.010618247091770172
2023-01-24 07:54:36.705300: step: 2088/527, loss: 0.00022566843836102635
2023-01-24 07:54:37.769204: step: 2092/527, loss: 0.0012280181981623173
2023-01-24 07:54:38.815459: step: 2096/527, loss: 0.0008603253518231213
2023-01-24 07:54:39.867624: step: 2100/527, loss: 0.005899379495531321
2023-01-24 07:54:40.923952: step: 2104/527, loss: 0.005639920011162758
2023-01-24 07:54:41.979066: step: 2108/527, loss: 0.0020226570777595043
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34228568686510746, 'r': 0.3234502316106708, 'f1': 0.33260150645624104}, 'combined': 0.24507479423091444, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37684539263201355, 'r': 0.2898283656060759, 'f1': 0.3276579672833334}, 'combined': 0.20970109906133336, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35987997658079623, 'r': 0.33324749254540526, 'f1': 0.3460520760028149}, 'combined': 0.25498574021260045, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37392682028728796, 'r': 0.30016125664879567, 'f1': 0.33300794988772087}, 'combined': 0.21312508792814133, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36581866015544395, 'r': 0.3255577829466854, 'f1': 0.34451596709418314}, 'combined': 0.2538538704904507, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38617866598002537, 'r': 0.30943577702501573, 'f1': 0.3435739346117837}, 'combined': 0.24633602858958079, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 14}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36581866015544395, 'r': 0.3255577829466854, 'f1': 0.34451596709418314}, 'combined': 0.2538538704904507, 'stategy': 1, 'epoch': 14}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38617866598002537, 'r': 0.30943577702501573, 'f1': 0.3435739346117837}, 'combined': 0.24633602858958079, 'stategy': 1, 'epoch': 14}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 14}
******************************
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
2023-01-24 07:57:13.892938: step: 4/527, loss: 0.0021173562854528427
2023-01-24 07:57:14.942148: step: 8/527, loss: 0.0038845541421324015
2023-01-24 07:57:15.992073: step: 12/527, loss: 0.0003737553779501468
2023-01-24 07:57:17.032396: step: 16/527, loss: 0.0037679087836295366
2023-01-24 07:57:18.064870: step: 20/527, loss: 0.00017279670282732695
2023-01-24 07:57:19.103335: step: 24/527, loss: 0.0021214622538536787
2023-01-24 07:57:20.182987: step: 28/527, loss: 0.002036649500951171
2023-01-24 07:57:21.228235: step: 32/527, loss: 0.004870116710662842
2023-01-24 07:57:22.268968: step: 36/527, loss: 0.0015003933804109693
2023-01-24 07:57:23.313162: step: 40/527, loss: 0.0008034825441427529
2023-01-24 07:57:24.365568: step: 44/527, loss: 7.095889304764569e-05
2023-01-24 07:57:25.423599: step: 48/527, loss: 0.005036995280534029
2023-01-24 07:57:26.463476: step: 52/527, loss: 0.008235444314777851
2023-01-24 07:57:27.522404: step: 56/527, loss: 0.003923624753952026
2023-01-24 07:57:28.572818: step: 60/527, loss: 0.003509890753775835
2023-01-24 07:57:29.635366: step: 64/527, loss: 0.00109007116407156
2023-01-24 07:57:30.702978: step: 68/527, loss: 0.009756636805832386
2023-01-24 07:57:31.745918: step: 72/527, loss: 0.0007047755643725395
2023-01-24 07:57:32.801744: step: 76/527, loss: 0.00788839440792799
2023-01-24 07:57:33.866965: step: 80/527, loss: 0.004746593534946442
2023-01-24 07:57:34.933229: step: 84/527, loss: 0.004120721016079187
2023-01-24 07:57:35.997585: step: 88/527, loss: 0.001955896383151412
2023-01-24 07:57:37.026002: step: 92/527, loss: 9.483610483584926e-06
2023-01-24 07:57:38.069890: step: 96/527, loss: 0.005657796747982502
2023-01-24 07:57:39.124144: step: 100/527, loss: 0.0008424916304647923
2023-01-24 07:57:40.167272: step: 104/527, loss: 0.004253414925187826
2023-01-24 07:57:41.228685: step: 108/527, loss: 0.03129945695400238
2023-01-24 07:57:42.264596: step: 112/527, loss: 0.10999766737222672
2023-01-24 07:57:43.323436: step: 116/527, loss: 0.003163097659125924
2023-01-24 07:57:44.379939: step: 120/527, loss: 0.003660310059785843
2023-01-24 07:57:45.451305: step: 124/527, loss: 0.0016737651312723756
2023-01-24 07:57:46.513384: step: 128/527, loss: 0.023412086069583893
2023-01-24 07:57:47.564970: step: 132/527, loss: 0.0010352160315960646
2023-01-24 07:57:48.604856: step: 136/527, loss: 0.0007334492402151227
2023-01-24 07:57:49.653403: step: 140/527, loss: 0.0011000334052368999
2023-01-24 07:57:50.700993: step: 144/527, loss: 3.7636273191310465e-05
2023-01-24 07:57:51.770785: step: 148/527, loss: 0.0012713746400550008
2023-01-24 07:57:52.830858: step: 152/527, loss: 0.001818284043110907
2023-01-24 07:57:53.890501: step: 156/527, loss: 0.001599849434569478
2023-01-24 07:57:54.924632: step: 160/527, loss: 0.0005812745075672865
2023-01-24 07:57:55.977138: step: 164/527, loss: 0.010420789010822773
2023-01-24 07:57:57.031220: step: 168/527, loss: 0.0021030320785939693
2023-01-24 07:57:58.084564: step: 172/527, loss: 0.0006419811979867518
2023-01-24 07:57:59.115349: step: 176/527, loss: 0.00936819612979889
2023-01-24 07:58:00.153742: step: 180/527, loss: 0.006638983730226755
2023-01-24 07:58:01.196427: step: 184/527, loss: 0.0007522262167185545
2023-01-24 07:58:02.236219: step: 188/527, loss: 0.001532741473056376
2023-01-24 07:58:03.276086: step: 192/527, loss: 0.002265756484121084
2023-01-24 07:58:04.306313: step: 196/527, loss: 0.0009916160488501191
2023-01-24 07:58:05.358698: step: 200/527, loss: 0.0014992932556197047
2023-01-24 07:58:06.402309: step: 204/527, loss: 0.00023226144548971206
2023-01-24 07:58:07.461109: step: 208/527, loss: 0.002908761613070965
2023-01-24 07:58:08.509530: step: 212/527, loss: 0.00032628432381898165
2023-01-24 07:58:09.577592: step: 216/527, loss: 0.004422122612595558
2023-01-24 07:58:10.642138: step: 220/527, loss: 0.0019195893546566367
2023-01-24 07:58:11.673262: step: 224/527, loss: 3.886927879648283e-05
2023-01-24 07:58:12.721813: step: 228/527, loss: 0.0025922805070877075
2023-01-24 07:58:13.750483: step: 232/527, loss: 0.0059373872354626656
2023-01-24 07:58:14.801397: step: 236/527, loss: 0.0002580052532721311
2023-01-24 07:58:15.868819: step: 240/527, loss: 0.0038165636360645294
2023-01-24 07:58:16.925684: step: 244/527, loss: 0.0033947532065212727
2023-01-24 07:58:17.981151: step: 248/527, loss: 0.0008480420801788568
2023-01-24 07:58:19.039656: step: 252/527, loss: 0.011438749730587006
2023-01-24 07:58:20.085453: step: 256/527, loss: 0.002159717259928584
2023-01-24 07:58:21.136175: step: 260/527, loss: 0.005551984068006277
2023-01-24 07:58:22.185848: step: 264/527, loss: 0.0006147713284008205
2023-01-24 07:58:23.237174: step: 268/527, loss: 0.0032075196504592896
2023-01-24 07:58:24.308446: step: 272/527, loss: 0.006498089991509914
2023-01-24 07:58:25.347797: step: 276/527, loss: 0.0014903396368026733
2023-01-24 07:58:26.418306: step: 280/527, loss: 0.0015536813298240304
2023-01-24 07:58:27.466378: step: 284/527, loss: 0.00019825789786409587
2023-01-24 07:58:28.536574: step: 288/527, loss: 0.01223039161413908
2023-01-24 07:58:29.573875: step: 292/527, loss: 0.003496290883049369
2023-01-24 07:58:30.628403: step: 296/527, loss: 0.0032782205380499363
2023-01-24 07:58:31.687120: step: 300/527, loss: 0.0006147643434815109
2023-01-24 07:58:32.728893: step: 304/527, loss: 0.002437482587993145
2023-01-24 07:58:33.799811: step: 308/527, loss: 3.440062573645264e-05
2023-01-24 07:58:34.859415: step: 312/527, loss: 0.0014014571206644177
2023-01-24 07:58:35.905054: step: 316/527, loss: 0.0056559550575912
2023-01-24 07:58:36.945423: step: 320/527, loss: 0.0009812063071876764
2023-01-24 07:58:38.011701: step: 324/527, loss: 8.941252599470317e-05
2023-01-24 07:58:39.062666: step: 328/527, loss: 0.0015465703327208757
2023-01-24 07:58:40.130210: step: 332/527, loss: 0.008679852820932865
2023-01-24 07:58:41.224925: step: 336/527, loss: 0.0019940112251788378
2023-01-24 07:58:42.285037: step: 340/527, loss: 0.004313911776989698
2023-01-24 07:58:43.333444: step: 344/527, loss: 0.010324474424123764
2023-01-24 07:58:44.387961: step: 348/527, loss: 3.7121339119039476e-05
2023-01-24 07:58:45.432581: step: 352/527, loss: 0.0029345473740249872
2023-01-24 07:58:46.488465: step: 356/527, loss: 0.0031653819605708122
2023-01-24 07:58:47.538256: step: 360/527, loss: 0.005418699234724045
2023-01-24 07:58:48.580230: step: 364/527, loss: 0.007249964401125908
2023-01-24 07:58:49.630302: step: 368/527, loss: 0.0008257487206719816
2023-01-24 07:58:50.693023: step: 372/527, loss: 0.0064759342931210995
2023-01-24 07:58:51.754403: step: 376/527, loss: 0.010194957256317139
2023-01-24 07:58:52.793878: step: 380/527, loss: 0.004651610739529133
2023-01-24 07:58:53.847552: step: 384/527, loss: 0.004355348646640778
2023-01-24 07:58:54.918385: step: 388/527, loss: 0.004689054097980261
2023-01-24 07:58:55.975649: step: 392/527, loss: 0.004069014452397823
2023-01-24 07:58:57.017488: step: 396/527, loss: 0.0035764339845627546
2023-01-24 07:58:58.063970: step: 400/527, loss: 0.0006211921572685242
2023-01-24 07:58:59.125342: step: 404/527, loss: 0.0020920531824231148
2023-01-24 07:59:00.172451: step: 408/527, loss: 0.0018426136812195182
2023-01-24 07:59:01.224349: step: 412/527, loss: 0.007245170418173075
2023-01-24 07:59:02.259214: step: 416/527, loss: 0.000667760381475091
2023-01-24 07:59:03.302935: step: 420/527, loss: 0.0025722994469106197
2023-01-24 07:59:04.348306: step: 424/527, loss: 0.0002297269820701331
2023-01-24 07:59:05.403211: step: 428/527, loss: 0.008032325655221939
2023-01-24 07:59:06.462733: step: 432/527, loss: 0.0023289441596716642
2023-01-24 07:59:07.511570: step: 436/527, loss: 0.015587732195854187
2023-01-24 07:59:08.545147: step: 440/527, loss: 0.0001631863706279546
2023-01-24 07:59:09.589512: step: 444/527, loss: 0.008715753443539143
2023-01-24 07:59:10.652516: step: 448/527, loss: 0.001279518473893404
2023-01-24 07:59:11.702825: step: 452/527, loss: 0.004508857149630785
2023-01-24 07:59:12.756542: step: 456/527, loss: 0.003289333777502179
2023-01-24 07:59:13.780811: step: 460/527, loss: 0.0036076297983527184
2023-01-24 07:59:14.816021: step: 464/527, loss: 0.0005100186681374907
2023-01-24 07:59:15.861200: step: 468/527, loss: 0.0017917719669640064
2023-01-24 07:59:16.919037: step: 472/527, loss: 0.0031433936674147844
2023-01-24 07:59:17.966439: step: 476/527, loss: 0.001392496284097433
2023-01-24 07:59:19.025217: step: 480/527, loss: 0.016258245334029198
2023-01-24 07:59:20.066200: step: 484/527, loss: 0.0006095237913541496
2023-01-24 07:59:21.109375: step: 488/527, loss: 0.0002444768906570971
2023-01-24 07:59:22.169775: step: 492/527, loss: 0.005289440508931875
2023-01-24 07:59:23.217137: step: 496/527, loss: 0.0002598441205918789
2023-01-24 07:59:24.263177: step: 500/527, loss: 0.0010381884640082717
2023-01-24 07:59:25.295965: step: 504/527, loss: 0.0034570619463920593
2023-01-24 07:59:26.342855: step: 508/527, loss: 0.009726104326546192
2023-01-24 07:59:27.398564: step: 512/527, loss: 0.004402461927384138
2023-01-24 07:59:28.442461: step: 516/527, loss: 0.0024160800967365503
2023-01-24 07:59:29.472049: step: 520/527, loss: 0.002171527361497283
2023-01-24 07:59:30.512705: step: 524/527, loss: 0.001062641036696732
2023-01-24 07:59:31.575486: step: 528/527, loss: 0.003841681405901909
2023-01-24 07:59:32.619947: step: 532/527, loss: 0.0008453569607809186
2023-01-24 07:59:33.663439: step: 536/527, loss: 0.0037636910565197468
2023-01-24 07:59:34.724942: step: 540/527, loss: 0.0033669352997094393
2023-01-24 07:59:35.786134: step: 544/527, loss: 0.002339624334126711
2023-01-24 07:59:36.811656: step: 548/527, loss: 0.0001866282691480592
2023-01-24 07:59:37.848291: step: 552/527, loss: 0.0022400973830372095
2023-01-24 07:59:38.892511: step: 556/527, loss: 0.007030345033854246
2023-01-24 07:59:39.922670: step: 560/527, loss: 0.006746623665094376
2023-01-24 07:59:40.970281: step: 564/527, loss: 0.0021641217172145844
2023-01-24 07:59:42.005417: step: 568/527, loss: 0.0008133139344863594
2023-01-24 07:59:43.037938: step: 572/527, loss: 0.001131757628172636
2023-01-24 07:59:44.085880: step: 576/527, loss: 0.00015711480227764696
2023-01-24 07:59:45.137911: step: 580/527, loss: 0.0031663328409194946
2023-01-24 07:59:46.197176: step: 584/527, loss: 0.002116158837452531
2023-01-24 07:59:47.253145: step: 588/527, loss: 0.015910262241959572
2023-01-24 07:59:48.301976: step: 592/527, loss: 0.00416777515783906
2023-01-24 07:59:49.390682: step: 596/527, loss: 6.097747245803475e-06
2023-01-24 07:59:50.459129: step: 600/527, loss: 0.0007248894544318318
2023-01-24 07:59:51.509368: step: 604/527, loss: 0.0027450760826468468
2023-01-24 07:59:52.547359: step: 608/527, loss: 0.0002297362661920488
2023-01-24 07:59:53.597066: step: 612/527, loss: 1.8520691810408607e-05
2023-01-24 07:59:54.650489: step: 616/527, loss: 0.003238700795918703
2023-01-24 07:59:55.690705: step: 620/527, loss: 0.0013879031175747514
2023-01-24 07:59:56.750203: step: 624/527, loss: 0.000962061167228967
2023-01-24 07:59:57.793067: step: 628/527, loss: 0.00020007911371067166
2023-01-24 07:59:58.828573: step: 632/527, loss: 3.51524940924719e-05
2023-01-24 07:59:59.876421: step: 636/527, loss: 3.9784629279893124e-07
2023-01-24 08:00:00.951230: step: 640/527, loss: 0.00030874053481966257
2023-01-24 08:00:02.000264: step: 644/527, loss: 0.0042197974398732185
2023-01-24 08:00:03.048201: step: 648/527, loss: 0.0009705985430628061
2023-01-24 08:00:04.091648: step: 652/527, loss: 0.00011235095007577911
2023-01-24 08:00:05.143020: step: 656/527, loss: 3.7596757465507835e-05
2023-01-24 08:00:06.189005: step: 660/527, loss: 0.0017915163189172745
2023-01-24 08:00:07.240461: step: 664/527, loss: 0.004214459098875523
2023-01-24 08:00:08.298086: step: 668/527, loss: 0.0016442033229395747
2023-01-24 08:00:09.345455: step: 672/527, loss: 0.0005432349862530828
2023-01-24 08:00:10.396757: step: 676/527, loss: 0.002872044686228037
2023-01-24 08:00:11.438971: step: 680/527, loss: 0.0011923682177439332
2023-01-24 08:00:12.503539: step: 684/527, loss: 0.002298399806022644
2023-01-24 08:00:13.563225: step: 688/527, loss: 0.002548930235207081
2023-01-24 08:00:14.637654: step: 692/527, loss: 0.005912081338465214
2023-01-24 08:00:15.688349: step: 696/527, loss: 0.004460288677364588
2023-01-24 08:00:16.752434: step: 700/527, loss: 0.009003069251775742
2023-01-24 08:00:17.795526: step: 704/527, loss: 0.0005650835810229182
2023-01-24 08:00:18.839721: step: 708/527, loss: 0.013968323357403278
2023-01-24 08:00:19.886890: step: 712/527, loss: 0.0002604085602797568
2023-01-24 08:00:20.933640: step: 716/527, loss: 3.4992392556887353e-06
2023-01-24 08:00:21.979792: step: 720/527, loss: 7.81009566708235e-06
2023-01-24 08:00:23.025951: step: 724/527, loss: 0.0014599731657654047
2023-01-24 08:00:24.082892: step: 728/527, loss: 0.0009206855320371687
2023-01-24 08:00:25.134072: step: 732/527, loss: 0.009889381006360054
2023-01-24 08:00:26.203953: step: 736/527, loss: 0.0003968965320382267
2023-01-24 08:00:27.247021: step: 740/527, loss: 0.00223132548853755
2023-01-24 08:00:28.297025: step: 744/527, loss: 0.0017901671817526221
2023-01-24 08:00:29.337241: step: 748/527, loss: 0.00043798726983368397
2023-01-24 08:00:30.399087: step: 752/527, loss: 0.00037257245276123285
2023-01-24 08:00:31.448825: step: 756/527, loss: 0.0026608763728290796
2023-01-24 08:00:32.506200: step: 760/527, loss: 0.004231521859765053
2023-01-24 08:00:33.568013: step: 764/527, loss: 0.009577380493283272
2023-01-24 08:00:34.632027: step: 768/527, loss: 0.0030072766821831465
2023-01-24 08:00:35.664143: step: 772/527, loss: 0.0008830654551275074
2023-01-24 08:00:36.717648: step: 776/527, loss: 0.02823844738304615
2023-01-24 08:00:37.766212: step: 780/527, loss: 0.004664203617721796
2023-01-24 08:00:38.818787: step: 784/527, loss: 0.00011153092054883018
2023-01-24 08:00:39.869642: step: 788/527, loss: 0.0011218494037166238
2023-01-24 08:00:40.935052: step: 792/527, loss: 0.023258119821548462
2023-01-24 08:00:42.013063: step: 796/527, loss: 0.00047314699622802436
2023-01-24 08:00:43.079846: step: 800/527, loss: 0.0074291592463850975
2023-01-24 08:00:44.156380: step: 804/527, loss: 0.01370174903422594
2023-01-24 08:00:45.189578: step: 808/527, loss: 0.0008737801108509302
2023-01-24 08:00:46.237567: step: 812/527, loss: 0.0002674296556506306
2023-01-24 08:00:47.290923: step: 816/527, loss: 0.001801965176127851
2023-01-24 08:00:48.350408: step: 820/527, loss: 0.015570897608995438
2023-01-24 08:00:49.455127: step: 824/527, loss: 0.004089339170604944
2023-01-24 08:00:50.498146: step: 828/527, loss: 0.019110364839434624
2023-01-24 08:00:51.531577: step: 832/527, loss: 0.00032402921351604164
2023-01-24 08:00:52.573532: step: 836/527, loss: 0.004586229100823402
2023-01-24 08:00:53.639657: step: 840/527, loss: 0.00522241648286581
2023-01-24 08:00:54.690063: step: 844/527, loss: 0.007909129373729229
2023-01-24 08:00:55.726009: step: 848/527, loss: 5.823296669404954e-05
2023-01-24 08:00:56.773145: step: 852/527, loss: 0.0026080021634697914
2023-01-24 08:00:57.816249: step: 856/527, loss: 0.0010545202530920506
2023-01-24 08:00:58.867575: step: 860/527, loss: 0.013986063189804554
2023-01-24 08:00:59.926565: step: 864/527, loss: 0.011676576919853687
2023-01-24 08:01:00.976592: step: 868/527, loss: 0.0025391425006091595
2023-01-24 08:01:02.043864: step: 872/527, loss: 0.01674940623342991
2023-01-24 08:01:03.092112: step: 876/527, loss: 0.0009539996972307563
2023-01-24 08:01:04.156317: step: 880/527, loss: 0.0036104826722294092
2023-01-24 08:01:05.227831: step: 884/527, loss: 0.008421748876571655
2023-01-24 08:01:06.273301: step: 888/527, loss: 0.017133517190814018
2023-01-24 08:01:07.346719: step: 892/527, loss: 0.004269172437489033
2023-01-24 08:01:08.380532: step: 896/527, loss: 0.006812944542616606
2023-01-24 08:01:09.419316: step: 900/527, loss: 0.0011456196662038565
2023-01-24 08:01:10.471686: step: 904/527, loss: 0.00023756176233291626
2023-01-24 08:01:11.527396: step: 908/527, loss: 0.00012250669533386827
2023-01-24 08:01:12.581078: step: 912/527, loss: 0.0055575892329216
2023-01-24 08:01:13.618587: step: 916/527, loss: 0.004770447500050068
2023-01-24 08:01:14.655804: step: 920/527, loss: 0.006210679188370705
2023-01-24 08:01:15.727699: step: 924/527, loss: 0.002885744906961918
2023-01-24 08:01:16.788799: step: 928/527, loss: 0.000533028447534889
2023-01-24 08:01:17.847328: step: 932/527, loss: 0.00919250026345253
2023-01-24 08:01:18.880939: step: 936/527, loss: 0.0027735168114304543
2023-01-24 08:01:19.939269: step: 940/527, loss: 0.004798294045031071
2023-01-24 08:01:20.977324: step: 944/527, loss: 0.001187857473269105
2023-01-24 08:01:22.040794: step: 948/527, loss: 0.0014265469508245587
2023-01-24 08:01:23.098117: step: 952/527, loss: 0.0018891862127929926
2023-01-24 08:01:24.143817: step: 956/527, loss: 0.00039537055999971926
2023-01-24 08:01:25.194547: step: 960/527, loss: 0.0005955604137852788
2023-01-24 08:01:26.233744: step: 964/527, loss: 0.003503769636154175
2023-01-24 08:01:27.281876: step: 968/527, loss: 0.0010721046710386872
2023-01-24 08:01:28.364774: step: 972/527, loss: 0.005274656228721142
2023-01-24 08:01:29.417565: step: 976/527, loss: 0.00016638064698781818
2023-01-24 08:01:30.473064: step: 980/527, loss: 0.0013780973386019468
2023-01-24 08:01:31.540896: step: 984/527, loss: 0.009462487883865833
2023-01-24 08:01:32.596432: step: 988/527, loss: 0.0006571573321707547
2023-01-24 08:01:33.648433: step: 992/527, loss: 0.000539962318725884
2023-01-24 08:01:34.685265: step: 996/527, loss: 0.012506379745900631
2023-01-24 08:01:35.739666: step: 1000/527, loss: 0.0006122874328866601
2023-01-24 08:01:36.793592: step: 1004/527, loss: 0.0007009954424574971
2023-01-24 08:01:37.836959: step: 1008/527, loss: 0.00013026964734308422
2023-01-24 08:01:38.892399: step: 1012/527, loss: 0.0017491503385826945
2023-01-24 08:01:39.975351: step: 1016/527, loss: 0.0003133631544187665
2023-01-24 08:01:41.028464: step: 1020/527, loss: 0.0021452170331031084
2023-01-24 08:01:42.079348: step: 1024/527, loss: 0.009732971899211407
2023-01-24 08:01:43.131706: step: 1028/527, loss: 0.0016120981890708208
2023-01-24 08:01:44.167292: step: 1032/527, loss: 0.00114544911775738
2023-01-24 08:01:45.215920: step: 1036/527, loss: 8.31125071272254e-05
2023-01-24 08:01:46.274714: step: 1040/527, loss: 0.00758141977712512
2023-01-24 08:01:47.338989: step: 1044/527, loss: 0.0008135505486279726
2023-01-24 08:01:48.385694: step: 1048/527, loss: 0.0019955255556851625
2023-01-24 08:01:49.459635: step: 1052/527, loss: 0.006410179194062948
2023-01-24 08:01:50.509416: step: 1056/527, loss: 0.0026326850056648254
2023-01-24 08:01:51.556455: step: 1060/527, loss: 0.029356464743614197
2023-01-24 08:01:52.612659: step: 1064/527, loss: 0.0008149564964696765
2023-01-24 08:01:53.654308: step: 1068/527, loss: 0.0008090647752396762
2023-01-24 08:01:54.695068: step: 1072/527, loss: 0.002092592651024461
2023-01-24 08:01:55.761675: step: 1076/527, loss: 0.00047904730308800936
2023-01-24 08:01:56.824500: step: 1080/527, loss: 0.0025993366725742817
2023-01-24 08:01:57.882243: step: 1084/527, loss: 0.01467125490307808
2023-01-24 08:01:58.932362: step: 1088/527, loss: 0.0022456017322838306
2023-01-24 08:02:00.001867: step: 1092/527, loss: 6.169895641505718e-05
2023-01-24 08:02:01.058621: step: 1096/527, loss: 0.01206066831946373
2023-01-24 08:02:02.095329: step: 1100/527, loss: 0.0032102654222398996
2023-01-24 08:02:03.148849: step: 1104/527, loss: 0.0017116570379585028
2023-01-24 08:02:04.200359: step: 1108/527, loss: 0.006274400744587183
2023-01-24 08:02:05.258949: step: 1112/527, loss: 0.0005220805178396404
2023-01-24 08:02:06.302318: step: 1116/527, loss: 4.4285923650022596e-05
2023-01-24 08:02:07.351529: step: 1120/527, loss: 0.002910742536187172
2023-01-24 08:02:08.428227: step: 1124/527, loss: 0.008637990802526474
2023-01-24 08:02:09.489032: step: 1128/527, loss: 3.064343400183134e-05
2023-01-24 08:02:10.546739: step: 1132/527, loss: 0.002794864820316434
2023-01-24 08:02:11.607152: step: 1136/527, loss: 0.0001063033560058102
2023-01-24 08:02:12.651173: step: 1140/527, loss: 0.003263834398239851
2023-01-24 08:02:13.695677: step: 1144/527, loss: 0.023214466869831085
2023-01-24 08:02:14.747801: step: 1148/527, loss: 0.006799470167607069
2023-01-24 08:02:15.802954: step: 1152/527, loss: 0.007932424545288086
2023-01-24 08:02:16.844416: step: 1156/527, loss: 0.004795227665454149
2023-01-24 08:02:17.904148: step: 1160/527, loss: 0.0021390633191913366
2023-01-24 08:02:18.948654: step: 1164/527, loss: 0.00022273171634878963
2023-01-24 08:02:20.019887: step: 1168/527, loss: 0.0035889961291104555
2023-01-24 08:02:21.074724: step: 1172/527, loss: 0.008758141659200191
2023-01-24 08:02:22.127981: step: 1176/527, loss: 0.0005906281294301152
2023-01-24 08:02:23.180974: step: 1180/527, loss: 0.0007719207787886262
2023-01-24 08:02:24.220872: step: 1184/527, loss: 0.0002030876639764756
2023-01-24 08:02:25.266905: step: 1188/527, loss: 0.002123411512002349
2023-01-24 08:02:26.316180: step: 1192/527, loss: 0.001337147201411426
2023-01-24 08:02:27.359455: step: 1196/527, loss: 0.00352330319583416
2023-01-24 08:02:28.432792: step: 1200/527, loss: 0.0020758798345923424
2023-01-24 08:02:29.506795: step: 1204/527, loss: 0.0015972491819411516
2023-01-24 08:02:30.545128: step: 1208/527, loss: 0.003596015740185976
2023-01-24 08:02:31.607366: step: 1212/527, loss: 0.003209357848390937
2023-01-24 08:02:32.653769: step: 1216/527, loss: 0.011255135759711266
2023-01-24 08:02:33.688959: step: 1220/527, loss: 9.44964776863344e-05
2023-01-24 08:02:34.756412: step: 1224/527, loss: 0.0042476835660636425
2023-01-24 08:02:35.817190: step: 1228/527, loss: 0.003568338230252266
2023-01-24 08:02:36.850670: step: 1232/527, loss: 1.5678507452321355e-06
2023-01-24 08:02:37.894986: step: 1236/527, loss: 0.013276586309075356
2023-01-24 08:02:38.959796: step: 1240/527, loss: 0.0020281258039176464
2023-01-24 08:02:40.003222: step: 1244/527, loss: 0.00019491919374559075
2023-01-24 08:02:41.060714: step: 1248/527, loss: 0.0005673468112945557
2023-01-24 08:02:42.131221: step: 1252/527, loss: 0.003406813135370612
2023-01-24 08:02:43.183589: step: 1256/527, loss: 0.002462834119796753
2023-01-24 08:02:44.242110: step: 1260/527, loss: 0.004317640792578459
2023-01-24 08:02:45.323050: step: 1264/527, loss: 0.0018103390466421843
2023-01-24 08:02:46.370440: step: 1268/527, loss: 0.00046188171836547554
2023-01-24 08:02:47.422364: step: 1272/527, loss: 0.004303985740989447
2023-01-24 08:02:48.466126: step: 1276/527, loss: 0.00015098131552804261
2023-01-24 08:02:49.541046: step: 1280/527, loss: 7.784442277625203e-05
2023-01-24 08:02:50.590813: step: 1284/527, loss: 0.0012205367675051093
2023-01-24 08:02:51.652061: step: 1288/527, loss: 2.8824190394516336e-06
2023-01-24 08:02:52.722536: step: 1292/527, loss: 0.009323973208665848
2023-01-24 08:02:53.778866: step: 1296/527, loss: 0.0011361275101080537
2023-01-24 08:02:54.828546: step: 1300/527, loss: 0.008245636709034443
2023-01-24 08:02:55.875620: step: 1304/527, loss: 0.0014456275384873152
2023-01-24 08:02:56.914977: step: 1308/527, loss: 0.00014965976879466325
2023-01-24 08:02:57.967437: step: 1312/527, loss: 0.0015570215182378888
2023-01-24 08:02:59.015802: step: 1316/527, loss: 0.003109920769929886
2023-01-24 08:03:00.069535: step: 1320/527, loss: 0.006661924067884684
2023-01-24 08:03:01.116258: step: 1324/527, loss: 0.0045791869051754475
2023-01-24 08:03:02.192795: step: 1328/527, loss: 0.009706941433250904
2023-01-24 08:03:03.241797: step: 1332/527, loss: 0.0008802172960713506
2023-01-24 08:03:04.299006: step: 1336/527, loss: 0.005875221453607082
2023-01-24 08:03:05.346087: step: 1340/527, loss: 0.015969112515449524
2023-01-24 08:03:06.404287: step: 1344/527, loss: 0.004202917218208313
2023-01-24 08:03:07.453889: step: 1348/527, loss: 0.0037117262836545706
2023-01-24 08:03:08.506923: step: 1352/527, loss: 5.7789413403952494e-05
2023-01-24 08:03:09.542322: step: 1356/527, loss: 0.00034378370037302375
2023-01-24 08:03:10.595360: step: 1360/527, loss: 0.0006365476292558014
2023-01-24 08:03:11.652279: step: 1364/527, loss: 0.006595726124942303
2023-01-24 08:03:12.687773: step: 1368/527, loss: 0.0015415733214467764
2023-01-24 08:03:13.743663: step: 1372/527, loss: 0.0033396631479263306
2023-01-24 08:03:14.800543: step: 1376/527, loss: 0.0010558458743616939
2023-01-24 08:03:15.865480: step: 1380/527, loss: 0.0034323404543101788
2023-01-24 08:03:16.941094: step: 1384/527, loss: 0.004915494471788406
2023-01-24 08:03:17.992327: step: 1388/527, loss: 0.0061089713126420975
2023-01-24 08:03:19.067220: step: 1392/527, loss: 0.004875743295997381
2023-01-24 08:03:20.127963: step: 1396/527, loss: 0.0006867261254228652
2023-01-24 08:03:21.192514: step: 1400/527, loss: 0.005687988828867674
2023-01-24 08:03:22.224938: step: 1404/527, loss: 0.00036953826202079654
2023-01-24 08:03:23.272130: step: 1408/527, loss: 0.000939302786719054
2023-01-24 08:03:24.329120: step: 1412/527, loss: 0.0013568548019975424
2023-01-24 08:03:25.385592: step: 1416/527, loss: 0.004481145180761814
2023-01-24 08:03:26.432410: step: 1420/527, loss: 0.0006092854891903698
2023-01-24 08:03:27.468603: step: 1424/527, loss: 0.0004368473601061851
2023-01-24 08:03:28.520706: step: 1428/527, loss: 0.004806303884834051
2023-01-24 08:03:29.561853: step: 1432/527, loss: 0.00019386038184165955
2023-01-24 08:03:30.616165: step: 1436/527, loss: 0.02582375518977642
2023-01-24 08:03:31.654858: step: 1440/527, loss: 0.0035245653707534075
2023-01-24 08:03:32.718386: step: 1444/527, loss: 0.012158765457570553
2023-01-24 08:03:33.769086: step: 1448/527, loss: 0.004373760428279638
2023-01-24 08:03:34.821378: step: 1452/527, loss: 0.004735062830150127
2023-01-24 08:03:35.842809: step: 1456/527, loss: 3.1292182711695204e-07
2023-01-24 08:03:36.887003: step: 1460/527, loss: 0.0021914043463766575
2023-01-24 08:03:37.941154: step: 1464/527, loss: 0.006319602485746145
2023-01-24 08:03:38.997117: step: 1468/527, loss: 0.004506241995841265
2023-01-24 08:03:40.042412: step: 1472/527, loss: 0.0023842931259423494
2023-01-24 08:03:41.075434: step: 1476/527, loss: 5.1615957090689335e-06
2023-01-24 08:03:42.128353: step: 1480/527, loss: 0.0025207032449543476
2023-01-24 08:03:43.179819: step: 1484/527, loss: 0.013974564149975777
2023-01-24 08:03:44.227150: step: 1488/527, loss: 0.004074737895280123
2023-01-24 08:03:45.270587: step: 1492/527, loss: 0.011669040657579899
2023-01-24 08:03:46.309125: step: 1496/527, loss: 0.0002378278149990365
2023-01-24 08:03:47.361342: step: 1500/527, loss: 0.0023171287029981613
2023-01-24 08:03:48.429001: step: 1504/527, loss: 0.02757694199681282
2023-01-24 08:03:49.466040: step: 1508/527, loss: 0.005107685457915068
2023-01-24 08:03:50.511079: step: 1512/527, loss: 0.0011398512870073318
2023-01-24 08:03:51.561123: step: 1516/527, loss: 0.00486304797232151
2023-01-24 08:03:52.598567: step: 1520/527, loss: 3.814215597230941e-05
2023-01-24 08:03:53.652166: step: 1524/527, loss: 0.001960632624104619
2023-01-24 08:03:54.705804: step: 1528/527, loss: 0.00026713087572716177
2023-01-24 08:03:55.749988: step: 1532/527, loss: 0.0035333430860191584
2023-01-24 08:03:56.796889: step: 1536/527, loss: 0.0002909427566919476
2023-01-24 08:03:57.834206: step: 1540/527, loss: 0.0012683109380304813
2023-01-24 08:03:58.878363: step: 1544/527, loss: 0.0005423807888291776
2023-01-24 08:03:59.921894: step: 1548/527, loss: 0.0007960903458297253
2023-01-24 08:04:00.960351: step: 1552/527, loss: 0.0023042315151542425
2023-01-24 08:04:02.010182: step: 1556/527, loss: 0.005188549403101206
2023-01-24 08:04:03.064530: step: 1560/527, loss: 0.00650202389806509
2023-01-24 08:04:04.105215: step: 1564/527, loss: 0.0007333987159654498
2023-01-24 08:04:05.155907: step: 1568/527, loss: 0.0034712692722678185
2023-01-24 08:04:06.205284: step: 1572/527, loss: 0.0027577606961131096
2023-01-24 08:04:07.235227: step: 1576/527, loss: 0.006949407979846001
2023-01-24 08:04:08.288202: step: 1580/527, loss: 0.028929319232702255
2023-01-24 08:04:09.332680: step: 1584/527, loss: 0.0057602147571742535
2023-01-24 08:04:10.382864: step: 1588/527, loss: 0.0018962372560054064
2023-01-24 08:04:11.436170: step: 1592/527, loss: 0.002414478687569499
2023-01-24 08:04:12.493364: step: 1596/527, loss: 0.0008136029355227947
2023-01-24 08:04:13.554169: step: 1600/527, loss: 0.0027432541828602552
2023-01-24 08:04:14.599583: step: 1604/527, loss: 0.005107726436108351
2023-01-24 08:04:15.641463: step: 1608/527, loss: 0.000485397526063025
2023-01-24 08:04:16.683605: step: 1612/527, loss: 0.0010145938722416759
2023-01-24 08:04:17.735597: step: 1616/527, loss: 0.0005520945996977389
2023-01-24 08:04:18.779584: step: 1620/527, loss: 0.0016862843185663223
2023-01-24 08:04:19.818568: step: 1624/527, loss: 0.0020822121296077967
2023-01-24 08:04:20.860095: step: 1628/527, loss: 2.6072260880027898e-05
2023-01-24 08:04:21.912713: step: 1632/527, loss: 0.005904187448322773
2023-01-24 08:04:22.940534: step: 1636/527, loss: 0.0014026776188984513
2023-01-24 08:04:23.980558: step: 1640/527, loss: 4.109400470042601e-05
2023-01-24 08:04:25.037132: step: 1644/527, loss: 0.0068221245892345905
2023-01-24 08:04:26.079050: step: 1648/527, loss: 0.009566273540258408
2023-01-24 08:04:27.114547: step: 1652/527, loss: 2.149449755961541e-07
2023-01-24 08:04:28.151058: step: 1656/527, loss: 7.826236833352596e-05
2023-01-24 08:04:29.209257: step: 1660/527, loss: 0.0042329756543040276
2023-01-24 08:04:30.263042: step: 1664/527, loss: 2.2546907985088183e-07
2023-01-24 08:04:31.309668: step: 1668/527, loss: 0.00874702725559473
2023-01-24 08:04:32.352678: step: 1672/527, loss: 0.0005634386907331645
2023-01-24 08:04:33.393043: step: 1676/527, loss: 0.0007338403956964612
2023-01-24 08:04:34.430317: step: 1680/527, loss: 0.0010113079333677888
2023-01-24 08:04:35.471617: step: 1684/527, loss: 0.004578796215355396
2023-01-24 08:04:36.518303: step: 1688/527, loss: 0.005295844282954931
2023-01-24 08:04:37.557036: step: 1692/527, loss: 0.004416812676936388
2023-01-24 08:04:38.595256: step: 1696/527, loss: 1.257691292266827e-05
2023-01-24 08:04:39.650686: step: 1700/527, loss: 0.0014993668301030993
2023-01-24 08:04:40.695467: step: 1704/527, loss: 8.849309233482927e-05
2023-01-24 08:04:41.734570: step: 1708/527, loss: 0.0017898413352668285
2023-01-24 08:04:42.780538: step: 1712/527, loss: 0.001130671356804669
2023-01-24 08:04:43.845903: step: 1716/527, loss: 0.009923440404236317
2023-01-24 08:04:44.892635: step: 1720/527, loss: 0.00018083699978888035
2023-01-24 08:04:45.928951: step: 1724/527, loss: 3.8295198464766145e-05
2023-01-24 08:04:46.979617: step: 1728/527, loss: 0.00010048371768789366
2023-01-24 08:04:48.030628: step: 1732/527, loss: 0.003804548876360059
2023-01-24 08:04:49.086855: step: 1736/527, loss: 0.0009665421093814075
2023-01-24 08:04:50.144261: step: 1740/527, loss: 0.00425344705581665
2023-01-24 08:04:51.202752: step: 1744/527, loss: 0.019550809636712074
2023-01-24 08:04:52.254294: step: 1748/527, loss: 0.0010442856000736356
2023-01-24 08:04:53.313000: step: 1752/527, loss: 0.03415495529770851
2023-01-24 08:04:54.357029: step: 1756/527, loss: 0.008795936591923237
2023-01-24 08:04:55.399406: step: 1760/527, loss: 0.002059955382719636
2023-01-24 08:04:56.455054: step: 1764/527, loss: 0.004015587270259857
2023-01-24 08:04:57.497805: step: 1768/527, loss: 0.0015639765188097954
2023-01-24 08:04:58.548474: step: 1772/527, loss: 0.0009359652176499367
2023-01-24 08:04:59.601971: step: 1776/527, loss: 1.968520564332721e-06
2023-01-24 08:05:00.646113: step: 1780/527, loss: 0.0054413070902228355
2023-01-24 08:05:01.695567: step: 1784/527, loss: 0.004592582117766142
2023-01-24 08:05:02.732820: step: 1788/527, loss: 0.004925496876239777
2023-01-24 08:05:03.782587: step: 1792/527, loss: 0.0009588312823325396
2023-01-24 08:05:04.830020: step: 1796/527, loss: 0.00028223529807291925
2023-01-24 08:05:05.905802: step: 1800/527, loss: 0.002428020816296339
2023-01-24 08:05:06.935755: step: 1804/527, loss: 0.00016602493997197598
2023-01-24 08:05:07.993718: step: 1808/527, loss: 0.001802899525500834
2023-01-24 08:05:09.044183: step: 1812/527, loss: 0.00035033110179938376
2023-01-24 08:05:10.110319: step: 1816/527, loss: 0.0053513795137405396
2023-01-24 08:05:11.154903: step: 1820/527, loss: 0.003625335171818733
2023-01-24 08:05:12.204105: step: 1824/527, loss: 0.009387193247675896
2023-01-24 08:05:13.271330: step: 1828/527, loss: 0.002989468863233924
2023-01-24 08:05:14.301254: step: 1832/527, loss: 0.001374842133373022
2023-01-24 08:05:15.344418: step: 1836/527, loss: 0.0033459945116192102
2023-01-24 08:05:16.404645: step: 1840/527, loss: 0.006262794137001038
2023-01-24 08:05:17.451243: step: 1844/527, loss: 0.0005649627419188619
2023-01-24 08:05:18.500652: step: 1848/527, loss: 0.0008230971870943904
2023-01-24 08:05:19.544353: step: 1852/527, loss: 0.0003535388095770031
2023-01-24 08:05:20.592188: step: 1856/527, loss: 0.0004460073832888156
2023-01-24 08:05:21.649040: step: 1860/527, loss: 4.401613477966748e-05
2023-01-24 08:05:22.684823: step: 1864/527, loss: 0.008959745988249779
2023-01-24 08:05:23.744858: step: 1868/527, loss: 0.001183580025099218
2023-01-24 08:05:24.803856: step: 1872/527, loss: 0.0006281028036028147
2023-01-24 08:05:25.845935: step: 1876/527, loss: 0.003985380753874779
2023-01-24 08:05:26.888455: step: 1880/527, loss: 0.004234537947922945
2023-01-24 08:05:27.949783: step: 1884/527, loss: 0.0033803682308644056
2023-01-24 08:05:28.983007: step: 1888/527, loss: 4.754704423248768e-05
2023-01-24 08:05:30.019662: step: 1892/527, loss: 0.0007918642950244248
2023-01-24 08:05:31.063671: step: 1896/527, loss: 0.004291980993002653
2023-01-24 08:05:32.095351: step: 1900/527, loss: 0.00036677898606285453
2023-01-24 08:05:33.136502: step: 1904/527, loss: 0.003098508110269904
2023-01-24 08:05:34.185368: step: 1908/527, loss: 0.005191630683839321
2023-01-24 08:05:35.223699: step: 1912/527, loss: 0.003917275927960873
2023-01-24 08:05:36.263719: step: 1916/527, loss: 0.003572305664420128
2023-01-24 08:05:37.321161: step: 1920/527, loss: 0.010544898919761181
2023-01-24 08:05:38.398128: step: 1924/527, loss: 3.4832566598197445e-05
2023-01-24 08:05:39.445146: step: 1928/527, loss: 0.009234145283699036
2023-01-24 08:05:40.494707: step: 1932/527, loss: 7.381310297205346e-06
2023-01-24 08:05:41.537250: step: 1936/527, loss: 5.0361388275632635e-05
2023-01-24 08:05:42.596177: step: 1940/527, loss: 0.00017151280189864337
2023-01-24 08:05:43.634316: step: 1944/527, loss: 4.3363597796997055e-05
2023-01-24 08:05:44.688836: step: 1948/527, loss: 0.0003087032528128475
2023-01-24 08:05:45.738162: step: 1952/527, loss: 0.004083825740963221
2023-01-24 08:05:46.789573: step: 1956/527, loss: 0.014585692435503006
2023-01-24 08:05:47.828149: step: 1960/527, loss: 0.0009473394602537155
2023-01-24 08:05:48.880816: step: 1964/527, loss: 0.00018962068133987486
2023-01-24 08:05:49.966981: step: 1968/527, loss: 0.0055191777646541595
2023-01-24 08:05:51.025900: step: 1972/527, loss: 0.000298607861623168
2023-01-24 08:05:52.069148: step: 1976/527, loss: 0.0019782360177487135
2023-01-24 08:05:53.113541: step: 1980/527, loss: 0.004785608034580946
2023-01-24 08:05:54.164923: step: 1984/527, loss: 0.007510562427341938
2023-01-24 08:05:55.225895: step: 1988/527, loss: 0.0012440590653568506
2023-01-24 08:05:56.281292: step: 1992/527, loss: 0.0020376089960336685
2023-01-24 08:05:57.322834: step: 1996/527, loss: 0.0005846908898092806
2023-01-24 08:05:58.364395: step: 2000/527, loss: 0.001342321396805346
2023-01-24 08:05:59.405180: step: 2004/527, loss: 0.00015501210873480886
2023-01-24 08:06:00.464178: step: 2008/527, loss: 0.0002958698896691203
2023-01-24 08:06:01.518314: step: 2012/527, loss: 0.0005573519156314433
2023-01-24 08:06:02.558103: step: 2016/527, loss: 0.004240536130964756
2023-01-24 08:06:03.628597: step: 2020/527, loss: 0.001750120078213513
2023-01-24 08:06:04.686320: step: 2024/527, loss: 0.01017381064593792
2023-01-24 08:06:05.746960: step: 2028/527, loss: 0.0007594551425427198
2023-01-24 08:06:06.804754: step: 2032/527, loss: 0.0028292520437389612
2023-01-24 08:06:07.843018: step: 2036/527, loss: 0.005003438331186771
2023-01-24 08:06:08.890170: step: 2040/527, loss: 0.001561109209433198
2023-01-24 08:06:09.942341: step: 2044/527, loss: 0.005150608718395233
2023-01-24 08:06:10.995203: step: 2048/527, loss: 0.0023214875254780054
2023-01-24 08:06:12.048640: step: 2052/527, loss: 0.003653744701296091
2023-01-24 08:06:13.095295: step: 2056/527, loss: 0.006593538913875818
2023-01-24 08:06:14.151890: step: 2060/527, loss: 0.0036782920360565186
2023-01-24 08:06:15.199185: step: 2064/527, loss: 0.005909407511353493
2023-01-24 08:06:16.254519: step: 2068/527, loss: 0.00043682128307409585
2023-01-24 08:06:17.318876: step: 2072/527, loss: 0.001568496460095048
2023-01-24 08:06:18.364330: step: 2076/527, loss: 0.0002973460068460554
2023-01-24 08:06:19.405184: step: 2080/527, loss: 0.0007467272807843983
2023-01-24 08:06:20.450981: step: 2084/527, loss: 0.000901336723472923
2023-01-24 08:06:21.489812: step: 2088/527, loss: 0.000655244046356529
2023-01-24 08:06:22.543933: step: 2092/527, loss: 0.0003568140382412821
2023-01-24 08:06:23.582787: step: 2096/527, loss: 0.0023579972330480814
2023-01-24 08:06:24.624348: step: 2100/527, loss: 0.0003425839531701058
2023-01-24 08:06:25.674863: step: 2104/527, loss: 0.005569449160248041
2023-01-24 08:06:26.737217: step: 2108/527, loss: 0.004380214028060436
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34023472593582893, 'r': 0.32280334529016025, 'f1': 0.33128989867169323}, 'combined': 0.2441083463896687, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3731709966861795, 'r': 0.29005563833334863, 'f1': 0.3264053219096506}, 'combined': 0.20889940602217635, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3562300782381918, 'r': 0.33324749254540526, 'f1': 0.34435574229691873}, 'combined': 0.25373581011351903, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3751993059704216, 'r': 0.3032946251713672, 'f1': 0.3354368481302614}, 'combined': 0.21467958280336727, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36368646399339705, 'r': 0.3236602497398543, 'f1': 0.34250793496566906}, 'combined': 0.25237426786944034, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.388645251295415, 'r': 0.3135378736521807, 'f1': 0.3470747198753201}, 'combined': 0.24884602557098426, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36581866015544395, 'r': 0.3255577829466854, 'f1': 0.34451596709418314}, 'combined': 0.2538538704904507, 'stategy': 1, 'epoch': 14}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38617866598002537, 'r': 0.30943577702501573, 'f1': 0.3435739346117837}, 'combined': 0.24633602858958079, 'stategy': 1, 'epoch': 14}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 14}
******************************
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
2023-01-24 08:08:56.362146: step: 4/527, loss: 0.00029362630448304117
2023-01-24 08:08:57.406384: step: 8/527, loss: 0.0023124818690121174
2023-01-24 08:08:58.444411: step: 12/527, loss: 0.0027675018645823
2023-01-24 08:08:59.505888: step: 16/527, loss: 0.001018871902488172
2023-01-24 08:09:00.536767: step: 20/527, loss: 0.0007350272499024868
2023-01-24 08:09:01.578980: step: 24/527, loss: 0.00016680097905918956
2023-01-24 08:09:02.625885: step: 28/527, loss: 1.1699240531015676e-05
2023-01-24 08:09:03.653629: step: 32/527, loss: 1.8017859474639408e-05
2023-01-24 08:09:04.692669: step: 36/527, loss: 8.809982682578266e-05
2023-01-24 08:09:05.744442: step: 40/527, loss: 0.000953048758674413
2023-01-24 08:09:06.811627: step: 44/527, loss: 0.0010760682635009289
2023-01-24 08:09:07.880058: step: 48/527, loss: 0.005208818707615137
2023-01-24 08:09:08.933075: step: 52/527, loss: 0.0007013630820438266
2023-01-24 08:09:09.975126: step: 56/527, loss: 0.0017439085058867931
2023-01-24 08:09:11.023655: step: 60/527, loss: 0.0005885157152079046
2023-01-24 08:09:12.066659: step: 64/527, loss: 0.0013615426141768694
2023-01-24 08:09:13.106925: step: 68/527, loss: 0.0001540377998026088
2023-01-24 08:09:14.166368: step: 72/527, loss: 0.0004917402984574437
2023-01-24 08:09:15.218496: step: 76/527, loss: 0.010568968020379543
2023-01-24 08:09:16.256625: step: 80/527, loss: 2.7583815608522855e-05
2023-01-24 08:09:17.302185: step: 84/527, loss: 0.0027480798307806253
2023-01-24 08:09:18.358116: step: 88/527, loss: 0.0013642244739457965
2023-01-24 08:09:19.430182: step: 92/527, loss: 4.709641871158965e-05
2023-01-24 08:09:20.485453: step: 96/527, loss: 6.708733053528704e-06
2023-01-24 08:09:21.529798: step: 100/527, loss: 0.005249525420367718
2023-01-24 08:09:22.564853: step: 104/527, loss: 3.4182542094640667e-06
2023-01-24 08:09:23.607257: step: 108/527, loss: 0.0024652304127812386
2023-01-24 08:09:24.660359: step: 112/527, loss: 0.0014432478928938508
2023-01-24 08:09:25.695992: step: 116/527, loss: 0.008281020447611809
2023-01-24 08:09:26.764140: step: 120/527, loss: 0.0021952250972390175
2023-01-24 08:09:27.815549: step: 124/527, loss: 0.002521294867619872
2023-01-24 08:09:28.860699: step: 128/527, loss: 0.004664104897528887
2023-01-24 08:09:29.920220: step: 132/527, loss: 0.0003241867816541344
2023-01-24 08:09:30.964744: step: 136/527, loss: 0.0032002637162804604
2023-01-24 08:09:32.038675: step: 140/527, loss: 0.0007822461775504053
2023-01-24 08:09:33.093587: step: 144/527, loss: 0.0006887163617648184
2023-01-24 08:09:34.143188: step: 148/527, loss: 0.00031078883330337703
2023-01-24 08:09:35.183999: step: 152/527, loss: 0.00018609754624776542
2023-01-24 08:09:36.226367: step: 156/527, loss: 0.0006201851647347212
2023-01-24 08:09:37.284752: step: 160/527, loss: 8.416463242610916e-05
2023-01-24 08:09:38.335898: step: 164/527, loss: 1.5695754882472102e-06
2023-01-24 08:09:39.390695: step: 168/527, loss: 0.0015502817695960402
2023-01-24 08:09:40.446450: step: 172/527, loss: 1.1131889550597407e-05
2023-01-24 08:09:41.503512: step: 176/527, loss: 0.0031404956243932247
2023-01-24 08:09:42.548275: step: 180/527, loss: 0.0008724552462808788
2023-01-24 08:09:43.608260: step: 184/527, loss: 0.009682309813797474
2023-01-24 08:09:44.646573: step: 188/527, loss: 0.00014177162665873766
2023-01-24 08:09:45.697214: step: 192/527, loss: 0.00023851713922340423
2023-01-24 08:09:46.739870: step: 196/527, loss: 0.0005552918883040547
2023-01-24 08:09:47.789322: step: 200/527, loss: 0.0029399204067885876
2023-01-24 08:09:48.854153: step: 204/527, loss: 0.00013852686970494688
2023-01-24 08:09:49.944486: step: 208/527, loss: 0.0038106085266917944
2023-01-24 08:09:50.978372: step: 212/527, loss: 4.388735305838054e-06
2023-01-24 08:09:52.041474: step: 216/527, loss: 0.006033284589648247
2023-01-24 08:09:53.104869: step: 220/527, loss: 0.0008205191697925329
2023-01-24 08:09:54.166659: step: 224/527, loss: 8.755196176934987e-05
2023-01-24 08:09:55.217427: step: 228/527, loss: 0.0008250846876762807
2023-01-24 08:09:56.277086: step: 232/527, loss: 0.00026991195045411587
2023-01-24 08:09:57.337878: step: 236/527, loss: 0.0038986585568636656
2023-01-24 08:09:58.398673: step: 240/527, loss: 0.010525080375373363
2023-01-24 08:09:59.448344: step: 244/527, loss: 2.4819946702336892e-05
2023-01-24 08:10:00.502814: step: 248/527, loss: 0.0006389497430063784
2023-01-24 08:10:01.553087: step: 252/527, loss: 0.0002910917974077165
2023-01-24 08:10:02.590114: step: 256/527, loss: 0.002244743285700679
2023-01-24 08:10:03.669889: step: 260/527, loss: 0.011275527998805046
2023-01-24 08:10:04.728569: step: 264/527, loss: 0.0006012019002810121
2023-01-24 08:10:05.781440: step: 268/527, loss: 0.000831753306556493
2023-01-24 08:10:06.833115: step: 272/527, loss: 0.00048162139137275517
2023-01-24 08:10:07.880135: step: 276/527, loss: 0.00014099193504080176
2023-01-24 08:10:08.924856: step: 280/527, loss: 0.008294143714010715
2023-01-24 08:10:09.974941: step: 284/527, loss: 0.0004632599593605846
2023-01-24 08:10:11.022776: step: 288/527, loss: 0.00790327787399292
2023-01-24 08:10:12.092178: step: 292/527, loss: 0.0026350372936576605
2023-01-24 08:10:13.140325: step: 296/527, loss: 0.001936080981977284
2023-01-24 08:10:14.214053: step: 300/527, loss: 0.00014472243492491543
2023-01-24 08:10:15.253720: step: 304/527, loss: 0.002501201583072543
2023-01-24 08:10:16.310828: step: 308/527, loss: 0.0032947431318461895
2023-01-24 08:10:17.358743: step: 312/527, loss: 0.00435211043804884
2023-01-24 08:10:18.403624: step: 316/527, loss: 0.0003964546776842326
2023-01-24 08:10:19.466245: step: 320/527, loss: 0.00017366201791446656
2023-01-24 08:10:20.518171: step: 324/527, loss: 0.0015467011835426092
2023-01-24 08:10:21.568323: step: 328/527, loss: 0.011085574515163898
2023-01-24 08:10:22.618134: step: 332/527, loss: 0.00216551311314106
2023-01-24 08:10:23.647182: step: 336/527, loss: 0.0003555732255335897
2023-01-24 08:10:24.712615: step: 340/527, loss: 0.0002360201469855383
2023-01-24 08:10:25.752891: step: 344/527, loss: 0.0004038470215164125
2023-01-24 08:10:26.792715: step: 348/527, loss: 0.001179668353870511
2023-01-24 08:10:27.844814: step: 352/527, loss: 0.00355441402643919
2023-01-24 08:10:28.884269: step: 356/527, loss: 0.002574915299192071
2023-01-24 08:10:29.948417: step: 360/527, loss: 4.936311233905144e-05
2023-01-24 08:10:31.001689: step: 364/527, loss: 1.4885632481309585e-05
2023-01-24 08:10:32.066868: step: 368/527, loss: 0.0017851099837571383
2023-01-24 08:10:33.126562: step: 372/527, loss: 0.0005334490560926497
2023-01-24 08:10:34.168952: step: 376/527, loss: 0.0009558703750371933
2023-01-24 08:10:35.222733: step: 380/527, loss: 0.006907467730343342
2023-01-24 08:10:36.259135: step: 384/527, loss: 0.0038654108066111803
2023-01-24 08:10:37.319713: step: 388/527, loss: 0.0008677334990352392
2023-01-24 08:10:38.407289: step: 392/527, loss: 2.391696398262866e-06
2023-01-24 08:10:39.458233: step: 396/527, loss: 0.005411786027252674
2023-01-24 08:10:40.497419: step: 400/527, loss: 3.6597964935936034e-05
2023-01-24 08:10:41.544919: step: 404/527, loss: 0.0027184037026017904
2023-01-24 08:10:42.608939: step: 408/527, loss: 0.005789011716842651
2023-01-24 08:10:43.662101: step: 412/527, loss: 0.00034568869159556925
2023-01-24 08:10:44.707617: step: 416/527, loss: 0.002663221675902605
2023-01-24 08:10:45.770480: step: 420/527, loss: 4.014531077700667e-05
2023-01-24 08:10:46.828477: step: 424/527, loss: 0.0023471759632229805
2023-01-24 08:10:47.863369: step: 428/527, loss: 0.0010860760230571032
2023-01-24 08:10:48.923969: step: 432/527, loss: 0.001893392764031887
2023-01-24 08:10:49.971415: step: 436/527, loss: 0.01324647106230259
2023-01-24 08:10:51.014473: step: 440/527, loss: 0.021253157407045364
2023-01-24 08:10:52.060131: step: 444/527, loss: 0.0019748907070606947
2023-01-24 08:10:53.097748: step: 448/527, loss: 0.00029857363551855087
2023-01-24 08:10:54.132341: step: 452/527, loss: 9.424844904515339e-08
2023-01-24 08:10:55.183439: step: 456/527, loss: 0.003209330141544342
2023-01-24 08:10:56.232969: step: 460/527, loss: 0.0001931208826135844
2023-01-24 08:10:57.286636: step: 464/527, loss: 0.0003605674428399652
2023-01-24 08:10:58.342771: step: 468/527, loss: 0.002870088443160057
2023-01-24 08:10:59.381859: step: 472/527, loss: 0.001728259609080851
2023-01-24 08:11:00.436092: step: 476/527, loss: 0.0019172728061676025
2023-01-24 08:11:01.489125: step: 480/527, loss: 0.003202020190656185
2023-01-24 08:11:02.530499: step: 484/527, loss: 0.0026045667473226786
2023-01-24 08:11:03.584473: step: 488/527, loss: 0.004719897639006376
2023-01-24 08:11:04.624618: step: 492/527, loss: 0.0013467278331518173
2023-01-24 08:11:05.696119: step: 496/527, loss: 0.0006678794743493199
2023-01-24 08:11:06.738786: step: 500/527, loss: 0.009689641185104847
2023-01-24 08:11:07.787902: step: 504/527, loss: 0.00015618542965967208
2023-01-24 08:11:08.852232: step: 508/527, loss: 0.006487994454801083
2023-01-24 08:11:09.908828: step: 512/527, loss: 0.0011897038202732801
2023-01-24 08:11:10.958346: step: 516/527, loss: 0.003776845522224903
2023-01-24 08:11:12.034859: step: 520/527, loss: 0.005213642027229071
2023-01-24 08:11:13.091580: step: 524/527, loss: 0.0017803956288844347
2023-01-24 08:11:14.151599: step: 528/527, loss: 0.00786628108471632
2023-01-24 08:11:15.221794: step: 532/527, loss: 0.0012076753191649914
2023-01-24 08:11:16.270102: step: 536/527, loss: 0.007799945771694183
2023-01-24 08:11:17.322061: step: 540/527, loss: 0.0019610016606748104
2023-01-24 08:11:18.384045: step: 544/527, loss: 0.006803759839385748
2023-01-24 08:11:19.456490: step: 548/527, loss: 0.002024806337431073
2023-01-24 08:11:20.524770: step: 552/527, loss: 0.0012042023008689284
2023-01-24 08:11:21.574442: step: 556/527, loss: 0.0009109866223298013
2023-01-24 08:11:22.633856: step: 560/527, loss: 0.001502372557297349
2023-01-24 08:11:23.704480: step: 564/527, loss: 0.01679421029984951
2023-01-24 08:11:24.753135: step: 568/527, loss: 0.00010982996900565922
2023-01-24 08:11:25.818043: step: 572/527, loss: 0.001854610163718462
2023-01-24 08:11:26.867307: step: 576/527, loss: 0.0024343417026102543
2023-01-24 08:11:27.916445: step: 580/527, loss: 0.007088626269251108
2023-01-24 08:11:28.971892: step: 584/527, loss: 0.005327480845153332
2023-01-24 08:11:30.027247: step: 588/527, loss: 0.0033573138061910868
2023-01-24 08:11:31.064462: step: 592/527, loss: 0.0027347393333911896
2023-01-24 08:11:32.134357: step: 596/527, loss: 0.01130823977291584
2023-01-24 08:11:33.185288: step: 600/527, loss: 0.00041065970435738564
2023-01-24 08:11:34.227429: step: 604/527, loss: 0.0006110537797212601
2023-01-24 08:11:35.261026: step: 608/527, loss: 2.780222985165892e-06
2023-01-24 08:11:36.333778: step: 612/527, loss: 0.002098517958074808
2023-01-24 08:11:37.388382: step: 616/527, loss: 0.0049666548147797585
2023-01-24 08:11:38.445744: step: 620/527, loss: 0.0011582697043195367
2023-01-24 08:11:39.478713: step: 624/527, loss: 0.001068922458216548
2023-01-24 08:11:40.529393: step: 628/527, loss: 0.0009036035626195371
2023-01-24 08:11:41.587833: step: 632/527, loss: 0.0040367040783166885
2023-01-24 08:11:42.651593: step: 636/527, loss: 0.03547500818967819
2023-01-24 08:11:43.682295: step: 640/527, loss: 0.00039093123632483184
2023-01-24 08:11:44.728827: step: 644/527, loss: 0.009030251763761044
2023-01-24 08:11:45.827057: step: 648/527, loss: 0.00578329199925065
2023-01-24 08:11:46.895647: step: 652/527, loss: 0.0007094664615578949
2023-01-24 08:11:47.938287: step: 656/527, loss: 9.087818762054667e-05
2023-01-24 08:11:48.975318: step: 660/527, loss: 0.0010494156740605831
2023-01-24 08:11:50.018584: step: 664/527, loss: 1.5628816981916316e-05
2023-01-24 08:11:51.064250: step: 668/527, loss: 0.00026448926655575633
2023-01-24 08:11:52.102531: step: 672/527, loss: 0.002680274425074458
2023-01-24 08:11:53.151614: step: 676/527, loss: 0.004019627813249826
2023-01-24 08:11:54.189284: step: 680/527, loss: 0.003811656264588237
2023-01-24 08:11:55.226675: step: 684/527, loss: 1.1421186172810849e-05
2023-01-24 08:11:56.283458: step: 688/527, loss: 0.0013235409278422594
2023-01-24 08:11:57.332851: step: 692/527, loss: 0.0001925052492879331
2023-01-24 08:11:58.373231: step: 696/527, loss: 0.0002155368565581739
2023-01-24 08:11:59.419134: step: 700/527, loss: 0.0025221812538802624
2023-01-24 08:12:00.463591: step: 704/527, loss: 0.004898042418062687
2023-01-24 08:12:01.520978: step: 708/527, loss: 0.0017057096119970083
2023-01-24 08:12:02.583203: step: 712/527, loss: 0.0035163576249033213
2023-01-24 08:12:03.657620: step: 716/527, loss: 0.010717121884226799
2023-01-24 08:12:04.735684: step: 720/527, loss: 0.002483958378434181
2023-01-24 08:12:05.807889: step: 724/527, loss: 0.0004091110604349524
2023-01-24 08:12:06.880410: step: 728/527, loss: 0.00719792116433382
2023-01-24 08:12:07.923040: step: 732/527, loss: 0.0010332348756492138
2023-01-24 08:12:08.955630: step: 736/527, loss: 0.002130708657205105
2023-01-24 08:12:10.004602: step: 740/527, loss: 0.00012908552889712155
2023-01-24 08:12:11.050902: step: 744/527, loss: 0.00020655262051150203
2023-01-24 08:12:12.092938: step: 748/527, loss: 0.0029447698034346104
2023-01-24 08:12:13.137043: step: 752/527, loss: 0.0021500212606042624
2023-01-24 08:12:14.202519: step: 756/527, loss: 0.0029845640528947115
2023-01-24 08:12:15.256414: step: 760/527, loss: 0.0031347903423011303
2023-01-24 08:12:16.287770: step: 764/527, loss: 9.04018379515037e-05
2023-01-24 08:12:17.340481: step: 768/527, loss: 0.0017972232308238745
2023-01-24 08:12:18.385193: step: 772/527, loss: 0.0014094715006649494
2023-01-24 08:12:19.459821: step: 776/527, loss: 0.007548716384917498
2023-01-24 08:12:20.503306: step: 780/527, loss: 4.1050832805922255e-05
2023-01-24 08:12:21.553348: step: 784/527, loss: 0.00357470172457397
2023-01-24 08:12:22.587469: step: 788/527, loss: 0.0010819025337696075
2023-01-24 08:12:23.646378: step: 792/527, loss: 0.018882377073168755
2023-01-24 08:12:24.708840: step: 796/527, loss: 0.0008510814514011145
2023-01-24 08:12:25.785502: step: 800/527, loss: 0.009258330799639225
2023-01-24 08:12:26.827264: step: 804/527, loss: 0.00013602181570604444
2023-01-24 08:12:27.888880: step: 808/527, loss: 0.0019705870654433966
2023-01-24 08:12:28.931470: step: 812/527, loss: 0.0008956373785622418
2023-01-24 08:12:29.983908: step: 816/527, loss: 0.003238560166209936
2023-01-24 08:12:31.042923: step: 820/527, loss: 0.004095160868018866
2023-01-24 08:12:32.084706: step: 824/527, loss: 0.00010957848280668259
2023-01-24 08:12:33.138737: step: 828/527, loss: 0.00027631016564555466
2023-01-24 08:12:34.187074: step: 832/527, loss: 0.007950243540108204
2023-01-24 08:12:35.257827: step: 836/527, loss: 0.0019664480350911617
2023-01-24 08:12:36.299667: step: 840/527, loss: 0.00014651849051006138
2023-01-24 08:12:37.349483: step: 844/527, loss: 0.0019699432887136936
2023-01-24 08:12:38.398396: step: 848/527, loss: 0.004299804102629423
2023-01-24 08:12:39.448012: step: 852/527, loss: 0.0016341921873390675
2023-01-24 08:12:40.501262: step: 856/527, loss: 0.0005780266947112978
2023-01-24 08:12:41.545619: step: 860/527, loss: 0.013584185391664505
2023-01-24 08:12:42.593413: step: 864/527, loss: 0.01736573502421379
2023-01-24 08:12:43.654130: step: 868/527, loss: 0.0060394564643502235
2023-01-24 08:12:44.712458: step: 872/527, loss: 0.0038760933093726635
2023-01-24 08:12:45.768548: step: 876/527, loss: 0.018327057361602783
2023-01-24 08:12:46.811842: step: 880/527, loss: 0.001958887092769146
2023-01-24 08:12:47.851597: step: 884/527, loss: 9.681533265393227e-05
2023-01-24 08:12:48.892957: step: 888/527, loss: 0.0038818400353193283
2023-01-24 08:12:49.947232: step: 892/527, loss: 0.0013985522091388702
2023-01-24 08:12:50.985230: step: 896/527, loss: 7.033974543446675e-05
2023-01-24 08:12:52.032246: step: 900/527, loss: 0.0055928910151124
2023-01-24 08:12:53.087078: step: 904/527, loss: 0.002146197482943535
2023-01-24 08:12:54.126543: step: 908/527, loss: 0.0023259862791746855
2023-01-24 08:12:55.177348: step: 912/527, loss: 0.006990176159888506
2023-01-24 08:12:56.211665: step: 916/527, loss: 0.0005071528721600771
2023-01-24 08:12:57.258770: step: 920/527, loss: 2.55736867984524e-05
2023-01-24 08:12:58.306430: step: 924/527, loss: 0.0015783029375597835
2023-01-24 08:12:59.352335: step: 928/527, loss: 0.0014483754057437181
2023-01-24 08:13:00.393763: step: 932/527, loss: 0.003942243754863739
2023-01-24 08:13:01.447269: step: 936/527, loss: 0.0016141952946782112
2023-01-24 08:13:02.493283: step: 940/527, loss: 0.000732183747459203
2023-01-24 08:13:03.538433: step: 944/527, loss: 0.0011083107674494386
2023-01-24 08:13:04.583344: step: 948/527, loss: 0.014129206538200378
2023-01-24 08:13:05.623404: step: 952/527, loss: 4.784448174177669e-05
2023-01-24 08:13:06.662499: step: 956/527, loss: 0.005685660056769848
2023-01-24 08:13:07.711189: step: 960/527, loss: 0.0021032216027379036
2023-01-24 08:13:08.751765: step: 964/527, loss: 0.0010349677177146077
2023-01-24 08:13:09.795338: step: 968/527, loss: 0.0005158516578376293
2023-01-24 08:13:10.857678: step: 972/527, loss: 0.005445067770779133
2023-01-24 08:13:11.919873: step: 976/527, loss: 0.00667544174939394
2023-01-24 08:13:12.980265: step: 980/527, loss: 0.0009074313566088676
2023-01-24 08:13:14.022482: step: 984/527, loss: 0.0011769848642870784
2023-01-24 08:13:15.073035: step: 988/527, loss: 0.001433023950085044
2023-01-24 08:13:16.135105: step: 992/527, loss: 0.0006545026553794742
2023-01-24 08:13:17.188229: step: 996/527, loss: 0.0005731495330110192
2023-01-24 08:13:18.242296: step: 1000/527, loss: 0.00036194580025039613
2023-01-24 08:13:19.299138: step: 1004/527, loss: 0.0013803731417283416
2023-01-24 08:13:20.358384: step: 1008/527, loss: 0.00251230550929904
2023-01-24 08:13:21.425873: step: 1012/527, loss: 5.7000743254320696e-05
2023-01-24 08:13:22.464826: step: 1016/527, loss: 0.000785976939368993
2023-01-24 08:13:23.509271: step: 1020/527, loss: 3.270840898039751e-05
2023-01-24 08:13:24.548464: step: 1024/527, loss: 0.00022950013226363808
2023-01-24 08:13:25.600748: step: 1028/527, loss: 2.7459434932097793e-05
2023-01-24 08:13:26.640993: step: 1032/527, loss: 0.001861344208009541
2023-01-24 08:13:27.687617: step: 1036/527, loss: 0.0004174953792244196
2023-01-24 08:13:28.736054: step: 1040/527, loss: 0.0025279626715928316
2023-01-24 08:13:29.779815: step: 1044/527, loss: 0.0008298912434838712
2023-01-24 08:13:30.824147: step: 1048/527, loss: 0.0006148685934022069
2023-01-24 08:13:31.873711: step: 1052/527, loss: 0.0020226824562996626
2023-01-24 08:13:32.917166: step: 1056/527, loss: 0.0016761821461841464
2023-01-24 08:13:33.946695: step: 1060/527, loss: 0.00027071317890658975
2023-01-24 08:13:34.997396: step: 1064/527, loss: 0.0019281964050605893
2023-01-24 08:13:36.047651: step: 1068/527, loss: 0.002859218046069145
2023-01-24 08:13:37.094199: step: 1072/527, loss: 0.0043061599135398865
2023-01-24 08:13:38.121902: step: 1076/527, loss: 0.0018398403190076351
2023-01-24 08:13:39.178554: step: 1080/527, loss: 0.00013586811837740242
2023-01-24 08:13:40.218556: step: 1084/527, loss: 0.0031078208703547716
2023-01-24 08:13:41.283373: step: 1088/527, loss: 0.0012761126272380352
2023-01-24 08:13:42.344217: step: 1092/527, loss: 0.004461658652871847
2023-01-24 08:13:43.384159: step: 1096/527, loss: 0.0008428000728599727
2023-01-24 08:13:44.430722: step: 1100/527, loss: 0.002554000820964575
2023-01-24 08:13:45.474124: step: 1104/527, loss: 0.00128261954523623
2023-01-24 08:13:46.530219: step: 1108/527, loss: 0.004220184404402971
2023-01-24 08:13:47.589761: step: 1112/527, loss: 0.006126233376562595
2023-01-24 08:13:48.641323: step: 1116/527, loss: 0.0021530345547944307
2023-01-24 08:13:49.729994: step: 1120/527, loss: 0.00011001452367054299
2023-01-24 08:13:50.779555: step: 1124/527, loss: 0.01634375937283039
2023-01-24 08:13:51.826487: step: 1128/527, loss: 0.0018732628086581826
2023-01-24 08:13:52.881206: step: 1132/527, loss: 0.00157389126252383
2023-01-24 08:13:53.917382: step: 1136/527, loss: 0.005545373074710369
2023-01-24 08:13:54.954022: step: 1140/527, loss: 0.0014116261154413223
2023-01-24 08:13:56.003200: step: 1144/527, loss: 0.0025831719394773245
2023-01-24 08:13:57.050088: step: 1148/527, loss: 0.007299414835870266
2023-01-24 08:13:58.094841: step: 1152/527, loss: 0.00012536680151242763
2023-01-24 08:13:59.155013: step: 1156/527, loss: 0.0029293829575181007
2023-01-24 08:14:00.208200: step: 1160/527, loss: 0.006933015305548906
2023-01-24 08:14:01.244490: step: 1164/527, loss: 0.0013301861472427845
2023-01-24 08:14:02.301243: step: 1168/527, loss: 0.002368565648794174
2023-01-24 08:14:03.347921: step: 1172/527, loss: 0.00046372567885555327
2023-01-24 08:14:04.405699: step: 1176/527, loss: 0.0009666255209594965
2023-01-24 08:14:05.446752: step: 1180/527, loss: 0.02743571810424328
2023-01-24 08:14:06.500820: step: 1184/527, loss: 0.0012554955901578069
2023-01-24 08:14:07.560128: step: 1188/527, loss: 0.0012396962847560644
2023-01-24 08:14:08.621356: step: 1192/527, loss: 0.0015350612811744213
2023-01-24 08:14:09.660342: step: 1196/527, loss: 0.0013064832892268896
2023-01-24 08:14:10.717902: step: 1200/527, loss: 0.003098790068179369
2023-01-24 08:14:11.775000: step: 1204/527, loss: 0.003295590402558446
2023-01-24 08:14:12.832606: step: 1208/527, loss: 0.0037896924186497927
2023-01-24 08:14:13.887541: step: 1212/527, loss: 0.0008170441724359989
2023-01-24 08:14:14.935027: step: 1216/527, loss: 0.013305151835083961
2023-01-24 08:14:15.977268: step: 1220/527, loss: 0.002453046850860119
2023-01-24 08:14:17.032428: step: 1224/527, loss: 0.0016749334754422307
2023-01-24 08:14:18.090948: step: 1228/527, loss: 0.004733951762318611
2023-01-24 08:14:19.154580: step: 1232/527, loss: 0.004380635917186737
2023-01-24 08:14:20.200786: step: 1236/527, loss: 0.001545277307741344
2023-01-24 08:14:21.250286: step: 1240/527, loss: 0.0009487916249781847
2023-01-24 08:14:22.298996: step: 1244/527, loss: 0.0031318538822233677
2023-01-24 08:14:23.365757: step: 1248/527, loss: 0.0031580699142068624
2023-01-24 08:14:24.405668: step: 1252/527, loss: 0.006127608008682728
2023-01-24 08:14:25.451831: step: 1256/527, loss: 0.004966470412909985
2023-01-24 08:14:26.492666: step: 1260/527, loss: 0.0005209269002079964
2023-01-24 08:14:27.542898: step: 1264/527, loss: 0.016081875190138817
2023-01-24 08:14:28.583913: step: 1268/527, loss: 7.874284165154677e-06
2023-01-24 08:14:29.650671: step: 1272/527, loss: 0.003223120467737317
2023-01-24 08:14:30.676786: step: 1276/527, loss: 2.6775867809192277e-05
2023-01-24 08:14:31.710110: step: 1280/527, loss: 3.3527435050473287e-08
2023-01-24 08:14:32.757206: step: 1284/527, loss: 0.0012703973334282637
2023-01-24 08:14:33.797757: step: 1288/527, loss: 0.0019685172010213137
2023-01-24 08:14:34.845177: step: 1292/527, loss: 0.0008686878136359155
2023-01-24 08:14:35.901046: step: 1296/527, loss: 0.0032676798291504383
2023-01-24 08:14:36.944656: step: 1300/527, loss: 0.0025982388760894537
2023-01-24 08:14:37.994734: step: 1304/527, loss: 0.0014656097628176212
2023-01-24 08:14:39.051757: step: 1308/527, loss: 2.2512227587867528e-05
2023-01-24 08:14:40.096164: step: 1312/527, loss: 1.3594108168035746e-05
2023-01-24 08:14:41.164353: step: 1316/527, loss: 0.010524352081120014
2023-01-24 08:14:42.203097: step: 1320/527, loss: 0.0001336935965809971
2023-01-24 08:14:43.262993: step: 1324/527, loss: 0.009151014499366283
2023-01-24 08:14:44.320695: step: 1328/527, loss: 0.005606172140687704
2023-01-24 08:14:45.376097: step: 1332/527, loss: 0.0004165508144069463
2023-01-24 08:14:46.437192: step: 1336/527, loss: 0.014254912734031677
2023-01-24 08:14:47.510018: step: 1340/527, loss: 0.06589920818805695
2023-01-24 08:14:48.543564: step: 1344/527, loss: 0.00764111615717411
2023-01-24 08:14:49.579589: step: 1348/527, loss: 5.8863155572908e-05
2023-01-24 08:14:50.624581: step: 1352/527, loss: 0.0009382255375385284
2023-01-24 08:14:51.685948: step: 1356/527, loss: 0.0018174120923504233
2023-01-24 08:14:52.741077: step: 1360/527, loss: 0.00689328508451581
2023-01-24 08:14:53.809907: step: 1364/527, loss: 0.003093535779044032
2023-01-24 08:14:54.852471: step: 1368/527, loss: 0.005622304044663906
2023-01-24 08:14:55.898481: step: 1372/527, loss: 0.004492186475545168
2023-01-24 08:14:56.960708: step: 1376/527, loss: 0.0008804639219306409
2023-01-24 08:14:58.023490: step: 1380/527, loss: 0.00939116720110178
2023-01-24 08:14:59.065797: step: 1384/527, loss: 0.00021086931519676
2023-01-24 08:15:00.118373: step: 1388/527, loss: 0.0021975624840706587
2023-01-24 08:15:01.182016: step: 1392/527, loss: 0.00034912340925075114
2023-01-24 08:15:02.237285: step: 1396/527, loss: 0.0005080234259366989
2023-01-24 08:15:03.298967: step: 1400/527, loss: 0.0031887295190244913
2023-01-24 08:15:04.363067: step: 1404/527, loss: 0.007273495197296143
2023-01-24 08:15:05.395396: step: 1408/527, loss: 0.0002891934709623456
2023-01-24 08:15:06.443662: step: 1412/527, loss: 0.014580144546926022
2023-01-24 08:15:07.491638: step: 1416/527, loss: 0.012143217958509922
2023-01-24 08:15:08.550161: step: 1420/527, loss: 0.004270481877028942
2023-01-24 08:15:09.602693: step: 1424/527, loss: 0.0005022920668125153
2023-01-24 08:15:10.652111: step: 1428/527, loss: 0.0002557813422754407
2023-01-24 08:15:11.701825: step: 1432/527, loss: 0.0016120565123856068
2023-01-24 08:15:12.748506: step: 1436/527, loss: 0.0076289186254143715
2023-01-24 08:15:13.802085: step: 1440/527, loss: 8.200816228054464e-05
2023-01-24 08:15:14.833390: step: 1444/527, loss: 0.004389632027596235
2023-01-24 08:15:15.876492: step: 1448/527, loss: 0.0009060506708920002
2023-01-24 08:15:16.907477: step: 1452/527, loss: 0.0001369757519569248
2023-01-24 08:15:17.967213: step: 1456/527, loss: 0.0022664363496005535
2023-01-24 08:15:19.016324: step: 1460/527, loss: 0.0013233617646619678
2023-01-24 08:15:20.085347: step: 1464/527, loss: 0.0007728933705948293
2023-01-24 08:15:21.134235: step: 1468/527, loss: 0.008598643355071545
2023-01-24 08:15:22.179387: step: 1472/527, loss: 0.001011152402497828
2023-01-24 08:15:23.233293: step: 1476/527, loss: 0.0009209024137817323
2023-01-24 08:15:24.277015: step: 1480/527, loss: 0.003898451803252101
2023-01-24 08:15:25.333928: step: 1484/527, loss: 0.00012030980724375695
2023-01-24 08:15:26.374222: step: 1488/527, loss: 0.002065537730231881
2023-01-24 08:15:27.431530: step: 1492/527, loss: 0.0005661601317115128
2023-01-24 08:15:28.493759: step: 1496/527, loss: 0.01004037819802761
2023-01-24 08:15:29.532274: step: 1500/527, loss: 0.00013328928616829216
2023-01-24 08:15:30.583939: step: 1504/527, loss: 0.000822470523416996
2023-01-24 08:15:31.634853: step: 1508/527, loss: 0.0015469376230612397
2023-01-24 08:15:32.689999: step: 1512/527, loss: 0.00015309768787119538
2023-01-24 08:15:33.732205: step: 1516/527, loss: 0.0027208777610212564
2023-01-24 08:15:34.788277: step: 1520/527, loss: 0.014285986311733723
2023-01-24 08:15:35.863569: step: 1524/527, loss: 0.0011215906124562025
2023-01-24 08:15:36.905794: step: 1528/527, loss: 0.0038153373170644045
2023-01-24 08:15:37.946459: step: 1532/527, loss: 0.0010606846772134304
2023-01-24 08:15:39.001516: step: 1536/527, loss: 0.001296634436585009
2023-01-24 08:15:40.065210: step: 1540/527, loss: 0.000129408435896039
2023-01-24 08:15:41.117780: step: 1544/527, loss: 0.0003812714130617678
2023-01-24 08:15:42.164613: step: 1548/527, loss: 0.00238376809284091
2023-01-24 08:15:43.197332: step: 1552/527, loss: 3.984607246820815e-06
2023-01-24 08:15:44.235948: step: 1556/527, loss: 0.0020203213207423687
2023-01-24 08:15:45.285188: step: 1560/527, loss: 0.0006290975143201649
2023-01-24 08:15:46.340889: step: 1564/527, loss: 0.0007898035692051053
2023-01-24 08:15:47.397554: step: 1568/527, loss: 0.0012622260255739093
2023-01-24 08:15:48.454794: step: 1572/527, loss: 0.01949235238134861
2023-01-24 08:15:49.522133: step: 1576/527, loss: 0.001242632046341896
2023-01-24 08:15:50.557924: step: 1580/527, loss: 0.002744571538642049
2023-01-24 08:15:51.617653: step: 1584/527, loss: 0.007959005422890186
2023-01-24 08:15:52.655761: step: 1588/527, loss: 0.0020091719925403595
2023-01-24 08:15:53.704094: step: 1592/527, loss: 0.0029118042439222336
2023-01-24 08:15:54.754095: step: 1596/527, loss: 0.002775674918666482
2023-01-24 08:15:55.802108: step: 1600/527, loss: 0.0007360588060691953
2023-01-24 08:15:56.856932: step: 1604/527, loss: 0.00424512242898345
2023-01-24 08:15:57.885558: step: 1608/527, loss: 0.010320118628442287
2023-01-24 08:15:58.947435: step: 1612/527, loss: 0.009204443544149399
2023-01-24 08:16:00.018563: step: 1616/527, loss: 0.0011702415067702532
2023-01-24 08:16:01.064146: step: 1620/527, loss: 0.005007266066968441
2023-01-24 08:16:02.105047: step: 1624/527, loss: 0.0002038608508883044
2023-01-24 08:16:03.141188: step: 1628/527, loss: 0.00031367206247523427
2023-01-24 08:16:04.186514: step: 1632/527, loss: 0.008467496372759342
2023-01-24 08:16:05.235609: step: 1636/527, loss: 0.00010893603757722303
2023-01-24 08:16:06.296011: step: 1640/527, loss: 0.0016561344964429736
2023-01-24 08:16:07.335763: step: 1644/527, loss: 0.0007026864914223552
2023-01-24 08:16:08.401231: step: 1648/527, loss: 0.0011646036291494966
2023-01-24 08:16:09.450017: step: 1652/527, loss: 0.002971925539895892
2023-01-24 08:16:10.498292: step: 1656/527, loss: 0.0030424208380281925
2023-01-24 08:16:11.552566: step: 1660/527, loss: 0.003456540172919631
2023-01-24 08:16:12.599007: step: 1664/527, loss: 1.034628803608939e-05
2023-01-24 08:16:13.660116: step: 1668/527, loss: 0.00371265085414052
2023-01-24 08:16:14.707650: step: 1672/527, loss: 0.00026763565256260335
2023-01-24 08:16:15.751701: step: 1676/527, loss: 0.0009885570034384727
2023-01-24 08:16:16.807412: step: 1680/527, loss: 0.005801874212920666
2023-01-24 08:16:17.869767: step: 1684/527, loss: 0.0013081826036795974
2023-01-24 08:16:18.917297: step: 1688/527, loss: 0.0062445118092000484
2023-01-24 08:16:19.972077: step: 1692/527, loss: 0.002816456602886319
2023-01-24 08:16:21.042060: step: 1696/527, loss: 0.0014937644591555
2023-01-24 08:16:22.079191: step: 1700/527, loss: 0.003085699863731861
2023-01-24 08:16:23.112242: step: 1704/527, loss: 0.007946365512907505
2023-01-24 08:16:24.158787: step: 1708/527, loss: 0.0004169502353761345
2023-01-24 08:16:25.220641: step: 1712/527, loss: 7.149171779019525e-06
2023-01-24 08:16:26.262160: step: 1716/527, loss: 0.0016616551438346505
2023-01-24 08:16:27.322304: step: 1720/527, loss: 0.002102398546412587
2023-01-24 08:16:28.363299: step: 1724/527, loss: 0.001694452133961022
2023-01-24 08:16:29.406149: step: 1728/527, loss: 0.00022139368229545653
2023-01-24 08:16:30.465831: step: 1732/527, loss: 0.0016899596666917205
2023-01-24 08:16:31.509863: step: 1736/527, loss: 0.00739193195477128
2023-01-24 08:16:32.559756: step: 1740/527, loss: 0.0026599145494401455
2023-01-24 08:16:33.616071: step: 1744/527, loss: 0.0028823530301451683
2023-01-24 08:16:34.647798: step: 1748/527, loss: 0.0035008941777050495
2023-01-24 08:16:35.696752: step: 1752/527, loss: 0.0006669954746030271
2023-01-24 08:16:36.771941: step: 1756/527, loss: 0.004123222082853317
2023-01-24 08:16:37.820220: step: 1760/527, loss: 0.0007911069551482797
2023-01-24 08:16:38.875245: step: 1764/527, loss: 0.00013549445429816842
2023-01-24 08:16:39.931095: step: 1768/527, loss: 0.0032816200982779264
2023-01-24 08:16:40.976608: step: 1772/527, loss: 3.7371108192019165e-05
2023-01-24 08:16:42.019165: step: 1776/527, loss: 0.0025543083902448416
2023-01-24 08:16:43.078692: step: 1780/527, loss: 0.0006150593399070203
2023-01-24 08:16:44.138941: step: 1784/527, loss: 0.004138999618589878
2023-01-24 08:16:45.165125: step: 1788/527, loss: 0.0059545328840613365
2023-01-24 08:16:46.218721: step: 1792/527, loss: 0.0018221656791865826
2023-01-24 08:16:47.276790: step: 1796/527, loss: 0.0017388710984960198
2023-01-24 08:16:48.320457: step: 1800/527, loss: 0.005599758122116327
2023-01-24 08:16:49.378283: step: 1804/527, loss: 0.0015350151807069778
2023-01-24 08:16:50.418522: step: 1808/527, loss: 8.094310760498047e-05
2023-01-24 08:16:51.468237: step: 1812/527, loss: 0.0026168099138885736
2023-01-24 08:16:52.531173: step: 1816/527, loss: 0.0019348643254488707
2023-01-24 08:16:53.584942: step: 1820/527, loss: 0.00017550966003909707
2023-01-24 08:16:54.652283: step: 1824/527, loss: 0.013700728304684162
2023-01-24 08:16:55.700453: step: 1828/527, loss: 0.0001688016636762768
2023-01-24 08:16:56.767044: step: 1832/527, loss: 0.0015950825763866305
2023-01-24 08:16:57.816014: step: 1836/527, loss: 1.219684872921789e-05
2023-01-24 08:16:58.847307: step: 1840/527, loss: 0.0003127841337118298
2023-01-24 08:16:59.886589: step: 1844/527, loss: 0.0002476734225638211
2023-01-24 08:17:00.957235: step: 1848/527, loss: 0.0010338386055082083
2023-01-24 08:17:01.985685: step: 1852/527, loss: 1.3261893627714016e-07
2023-01-24 08:17:03.062814: step: 1856/527, loss: 0.004176266025751829
2023-01-24 08:17:04.091626: step: 1860/527, loss: 0.0016247236635535955
2023-01-24 08:17:05.147076: step: 1864/527, loss: 1.639852962398436e-05
2023-01-24 08:17:06.192723: step: 1868/527, loss: 0.0005950375343672931
2023-01-24 08:17:07.253722: step: 1872/527, loss: 0.0014178777346387506
2023-01-24 08:17:08.293163: step: 1876/527, loss: 0.004773005843162537
2023-01-24 08:17:09.333096: step: 1880/527, loss: 0.004941659048199654
2023-01-24 08:17:10.391884: step: 1884/527, loss: 0.0016353186219930649
2023-01-24 08:17:11.449590: step: 1888/527, loss: 0.00267813540995121
2023-01-24 08:17:12.498359: step: 1892/527, loss: 0.0004583675181493163
2023-01-24 08:17:13.556599: step: 1896/527, loss: 1.6559828509343788e-05
2023-01-24 08:17:14.609917: step: 1900/527, loss: 0.011262011714279652
2023-01-24 08:17:15.682499: step: 1904/527, loss: 0.005704472307115793
2023-01-24 08:17:16.732149: step: 1908/527, loss: 0.003000969300046563
2023-01-24 08:17:17.785432: step: 1912/527, loss: 0.0037674221675843
2023-01-24 08:17:18.854170: step: 1916/527, loss: 2.5114111394941574e-06
2023-01-24 08:17:19.925631: step: 1920/527, loss: 0.0037444119807332754
2023-01-24 08:17:20.987071: step: 1924/527, loss: 0.000938969780690968
2023-01-24 08:17:22.017530: step: 1928/527, loss: 0.00048538894043304026
2023-01-24 08:17:23.055795: step: 1932/527, loss: 0.002088862005621195
2023-01-24 08:17:24.098843: step: 1936/527, loss: 0.0019746271427720785
2023-01-24 08:17:25.139390: step: 1940/527, loss: 0.0009496750426478684
2023-01-24 08:17:26.185386: step: 1944/527, loss: 0.012048965319991112
2023-01-24 08:17:27.220739: step: 1948/527, loss: 0.0006005605682730675
2023-01-24 08:17:28.251700: step: 1952/527, loss: 1.349917147308588e-05
2023-01-24 08:17:29.298070: step: 1956/527, loss: 0.0011753793805837631
2023-01-24 08:17:30.354480: step: 1960/527, loss: 0.0021249542478471994
2023-01-24 08:17:31.404399: step: 1964/527, loss: 0.0
2023-01-24 08:17:32.448064: step: 1968/527, loss: 0.0018118249718099833
2023-01-24 08:17:33.511718: step: 1972/527, loss: 0.0015378339448943734
2023-01-24 08:17:34.561560: step: 1976/527, loss: 0.0018951488891616464
2023-01-24 08:17:35.602096: step: 1980/527, loss: 0.00018530042143538594
2023-01-24 08:17:36.658899: step: 1984/527, loss: 0.0005694652791135013
2023-01-24 08:17:37.731609: step: 1988/527, loss: 0.002592280972748995
2023-01-24 08:17:38.808598: step: 1992/527, loss: 0.0043168882839381695
2023-01-24 08:17:39.863237: step: 1996/527, loss: 0.005359608214348555
2023-01-24 08:17:40.898573: step: 2000/527, loss: 0.0006978489109314978
2023-01-24 08:17:41.938839: step: 2004/527, loss: 0.0007975762709975243
2023-01-24 08:17:42.985003: step: 2008/527, loss: 0.00542910723015666
2023-01-24 08:17:44.037474: step: 2012/527, loss: 0.003369407495483756
2023-01-24 08:17:45.078853: step: 2016/527, loss: 0.0007041924982331693
2023-01-24 08:17:46.108128: step: 2020/527, loss: 0.007848531007766724
2023-01-24 08:17:47.163396: step: 2024/527, loss: 0.00813689548522234
2023-01-24 08:17:48.195176: step: 2028/527, loss: 0.00015928182983770967
2023-01-24 08:17:49.255166: step: 2032/527, loss: 0.007226400077342987
2023-01-24 08:17:50.308675: step: 2036/527, loss: 0.0002228067460237071
2023-01-24 08:17:51.362659: step: 2040/527, loss: 0.0009319009841419756
2023-01-24 08:17:52.398632: step: 2044/527, loss: 0.00029925076523795724
2023-01-24 08:17:53.473522: step: 2048/527, loss: 0.0014323658542707562
2023-01-24 08:17:54.515990: step: 2052/527, loss: 0.0007146685966290534
2023-01-24 08:17:55.560215: step: 2056/527, loss: 0.0019790895748883486
2023-01-24 08:17:56.615512: step: 2060/527, loss: 0.0036417196970432997
2023-01-24 08:17:57.671338: step: 2064/527, loss: 0.002148517407476902
2023-01-24 08:17:58.731880: step: 2068/527, loss: 0.00200413865968585
2023-01-24 08:17:59.790312: step: 2072/527, loss: 0.0006660969229415059
2023-01-24 08:18:00.838795: step: 2076/527, loss: 7.027556421235204e-05
2023-01-24 08:18:01.884403: step: 2080/527, loss: 0.00011406470002839342
2023-01-24 08:18:02.918824: step: 2084/527, loss: 0.004062335472553968
2023-01-24 08:18:03.981373: step: 2088/527, loss: 0.002328714355826378
2023-01-24 08:18:05.006303: step: 2092/527, loss: 0.001281658886000514
2023-01-24 08:18:06.061938: step: 2096/527, loss: 0.009096404537558556
2023-01-24 08:18:07.117350: step: 2100/527, loss: 0.010397693142294884
2023-01-24 08:18:08.165878: step: 2104/527, loss: 0.0037924263160675764
2023-01-24 08:18:09.244768: step: 2108/527, loss: 0.0032025922555476427
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34158617478961584, 'r': 0.32991909481577697, 'f1': 0.3356512798608387}, 'combined': 0.24732199568693378, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3733152250195357, 'r': 0.2898283656060759, 'f1': 0.32631648123509055}, 'combined': 0.20884254799045793, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35660000000000003, 'r': 0.33833017077798866, 'f1': 0.34722492697176244}, 'combined': 0.2558499461897197, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3746706597169523, 'r': 0.30354789143280786, 'f1': 0.3353800586728765}, 'combined': 0.21464323755064094, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3628279908027321, 'r': 0.3284040827569321, 'f1': 0.3447588677547873}, 'combined': 0.2540328499245801, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38594926342713576, 'r': 0.311714719595663, 'f1': 0.34488254906348187}, 'combined': 0.24727428046060967, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.34615384615384615, 'r': 0.391304347826087, 'f1': 0.36734693877551017}, 'combined': 0.18367346938775508, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6, 'r': 0.20689655172413793, 'f1': 0.3076923076923077}, 'combined': 0.20512820512820512, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36581866015544395, 'r': 0.3255577829466854, 'f1': 0.34451596709418314}, 'combined': 0.2538538704904507, 'stategy': 1, 'epoch': 14}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38617866598002537, 'r': 0.30943577702501573, 'f1': 0.3435739346117837}, 'combined': 0.24633602858958079, 'stategy': 1, 'epoch': 14}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 14}
******************************
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
2023-01-24 08:20:40.795540: step: 4/527, loss: 0.0007385834469459951
2023-01-24 08:20:41.817958: step: 8/527, loss: 7.566889689769596e-05
2023-01-24 08:20:42.857779: step: 12/527, loss: 0.002061741193756461
2023-01-24 08:20:43.900357: step: 16/527, loss: 0.007281259633600712
2023-01-24 08:20:44.937320: step: 20/527, loss: 0.001498526195064187
2023-01-24 08:20:46.009515: step: 24/527, loss: 0.006120241712778807
2023-01-24 08:20:47.057414: step: 28/527, loss: 0.0037715183570981026
2023-01-24 08:20:48.107965: step: 32/527, loss: 0.0003009985957760364
2023-01-24 08:20:49.169450: step: 36/527, loss: 0.002797679742798209
2023-01-24 08:20:50.212923: step: 40/527, loss: 0.0009264907566830516
2023-01-24 08:20:51.258925: step: 44/527, loss: 0.0005430293967947364
2023-01-24 08:20:52.303254: step: 48/527, loss: 0.0029236916452646255
2023-01-24 08:20:53.384562: step: 52/527, loss: 3.919340451830067e-05
2023-01-24 08:20:54.424514: step: 56/527, loss: 0.003953401930630207
2023-01-24 08:20:55.487594: step: 60/527, loss: 0.009120556525886059
2023-01-24 08:20:56.520303: step: 64/527, loss: 0.0010347375646233559
2023-01-24 08:20:57.562961: step: 68/527, loss: 0.0024913973174989223
2023-01-24 08:20:58.600672: step: 72/527, loss: 0.0021327282302081585
2023-01-24 08:20:59.643413: step: 76/527, loss: 8.736936433706433e-05
2023-01-24 08:21:00.675599: step: 80/527, loss: 0.0011106831952929497
2023-01-24 08:21:01.721535: step: 84/527, loss: 0.0003124057548120618
2023-01-24 08:21:02.773686: step: 88/527, loss: 9.769913594936952e-05
2023-01-24 08:21:03.809620: step: 92/527, loss: 0.0005332036525942385
2023-01-24 08:21:04.860558: step: 96/527, loss: 0.0022758450359106064
2023-01-24 08:21:05.913147: step: 100/527, loss: 0.010797334834933281
2023-01-24 08:21:06.960992: step: 104/527, loss: 3.991198536823504e-05
2023-01-24 08:21:08.018464: step: 108/527, loss: 0.000525469018612057
2023-01-24 08:21:09.080179: step: 112/527, loss: 0.009158259257674217
2023-01-24 08:21:10.131842: step: 116/527, loss: 8.067589806159958e-05
2023-01-24 08:21:11.179256: step: 120/527, loss: 0.002118610544130206
2023-01-24 08:21:12.209624: step: 124/527, loss: 0.0003959763271268457
2023-01-24 08:21:13.277427: step: 128/527, loss: 0.00016932042490225285
2023-01-24 08:21:14.340611: step: 132/527, loss: 0.00047335567069239914
2023-01-24 08:21:15.381707: step: 136/527, loss: 0.0010694164084270597
2023-01-24 08:21:16.415569: step: 140/527, loss: 2.9593074941658415e-05
2023-01-24 08:21:17.469650: step: 144/527, loss: 0.0033024856820702553
2023-01-24 08:21:18.528075: step: 148/527, loss: 5.019260788685642e-05
2023-01-24 08:21:19.602976: step: 152/527, loss: 0.004528303164988756
2023-01-24 08:21:20.657639: step: 156/527, loss: 0.0010507629485800862
2023-01-24 08:21:21.689625: step: 160/527, loss: 0.0018949442310258746
2023-01-24 08:21:22.745880: step: 164/527, loss: 0.0019545438699424267
2023-01-24 08:21:23.796187: step: 168/527, loss: 0.0003531578404363245
2023-01-24 08:21:24.848900: step: 172/527, loss: 0.0012351747136563063
2023-01-24 08:21:25.892487: step: 176/527, loss: 0.002788713900372386
2023-01-24 08:21:26.942684: step: 180/527, loss: 0.00013697060057893395
2023-01-24 08:21:27.986138: step: 184/527, loss: 0.003158178413286805
2023-01-24 08:21:29.030926: step: 188/527, loss: 0.0007997386856004596
2023-01-24 08:21:30.089182: step: 192/527, loss: 0.0033517109695822
2023-01-24 08:21:31.156988: step: 196/527, loss: 0.00019482173956930637
2023-01-24 08:21:32.203571: step: 200/527, loss: 0.0005644794437102973
2023-01-24 08:21:33.254002: step: 204/527, loss: 0.004306257236748934
2023-01-24 08:21:34.315931: step: 208/527, loss: 0.0041702790185809135
2023-01-24 08:21:35.360806: step: 212/527, loss: 0.00025611784076318145
2023-01-24 08:21:36.419698: step: 216/527, loss: 8.235286077251658e-05
2023-01-24 08:21:37.482387: step: 220/527, loss: 0.00876015517860651
2023-01-24 08:21:38.528937: step: 224/527, loss: 5.538315963349305e-05
2023-01-24 08:21:39.586180: step: 228/527, loss: 1.4116752026893664e-05
2023-01-24 08:21:40.630686: step: 232/527, loss: 0.005121900700032711
2023-01-24 08:21:41.679642: step: 236/527, loss: 0.00302768568508327
2023-01-24 08:21:42.741996: step: 240/527, loss: 0.00013844345812685788
2023-01-24 08:21:43.792738: step: 244/527, loss: 0.00010792484681587666
2023-01-24 08:21:44.842302: step: 248/527, loss: 6.812847004766809e-06
2023-01-24 08:21:45.897880: step: 252/527, loss: 0.00043967936653643847
2023-01-24 08:21:46.950024: step: 256/527, loss: 0.009949934668838978
2023-01-24 08:21:48.000607: step: 260/527, loss: 0.014512544497847557
2023-01-24 08:21:49.059721: step: 264/527, loss: 0.0088998693972826
2023-01-24 08:21:50.094388: step: 268/527, loss: 0.0
2023-01-24 08:21:51.155685: step: 272/527, loss: 0.000379995908588171
2023-01-24 08:21:52.210249: step: 276/527, loss: 0.0005721896886825562
2023-01-24 08:21:53.254009: step: 280/527, loss: 0.0
2023-01-24 08:21:54.301944: step: 284/527, loss: 0.000567822193261236
2023-01-24 08:21:55.349141: step: 288/527, loss: 0.000545126385986805
2023-01-24 08:21:56.397153: step: 292/527, loss: 0.0008908218587748706
2023-01-24 08:21:57.455972: step: 296/527, loss: 0.0011619164142757654
2023-01-24 08:21:58.518623: step: 300/527, loss: 4.666535915021086e-06
2023-01-24 08:21:59.584526: step: 304/527, loss: 0.00024077262787614018
2023-01-24 08:22:00.619606: step: 308/527, loss: 0.008198456838726997
2023-01-24 08:22:01.663149: step: 312/527, loss: 0.00014882342657074332
2023-01-24 08:22:02.705771: step: 316/527, loss: 0.01991664059460163
2023-01-24 08:22:03.752854: step: 320/527, loss: 0.0007206673617474735
2023-01-24 08:22:04.802661: step: 324/527, loss: 1.54581375682028e-05
2023-01-24 08:22:05.854843: step: 328/527, loss: 0.0007106658886186779
2023-01-24 08:22:06.891049: step: 332/527, loss: 0.0008417748613283038
2023-01-24 08:22:07.943356: step: 336/527, loss: 5.6455177400493994e-05
2023-01-24 08:22:08.994732: step: 340/527, loss: 0.0004986902349628508
2023-01-24 08:22:10.046323: step: 344/527, loss: 0.012939785607159138
2023-01-24 08:22:11.097609: step: 348/527, loss: 0.0008990991627797484
2023-01-24 08:22:12.149087: step: 352/527, loss: 0.00113282713573426
2023-01-24 08:22:13.179921: step: 356/527, loss: 0.000905814697034657
2023-01-24 08:22:14.239060: step: 360/527, loss: 0.005928993225097656
2023-01-24 08:22:15.273556: step: 364/527, loss: 0.0030011930502951145
2023-01-24 08:22:16.331704: step: 368/527, loss: 0.0012308614095672965
2023-01-24 08:22:17.387962: step: 372/527, loss: 0.003234598319977522
2023-01-24 08:22:18.433162: step: 376/527, loss: 0.001276619965210557
2023-01-24 08:22:19.492859: step: 380/527, loss: 9.043971658684313e-05
2023-01-24 08:22:20.549447: step: 384/527, loss: 0.008655059151351452
2023-01-24 08:22:21.605669: step: 388/527, loss: 0.004100115038454533
2023-01-24 08:22:22.665074: step: 392/527, loss: 0.002560308435931802
2023-01-24 08:22:23.722128: step: 396/527, loss: 0.0014232817338779569
2023-01-24 08:22:24.771157: step: 400/527, loss: 0.000847894640173763
2023-01-24 08:22:25.814661: step: 404/527, loss: 0.00013682078861165792
2023-01-24 08:22:26.869662: step: 408/527, loss: 0.0008552788058295846
2023-01-24 08:22:27.923454: step: 412/527, loss: 6.0212445532670245e-05
2023-01-24 08:22:28.952959: step: 416/527, loss: 0.0006469315267167985
2023-01-24 08:22:30.001030: step: 420/527, loss: 0.0019429450621828437
2023-01-24 08:22:31.046490: step: 424/527, loss: 0.0016383810434490442
2023-01-24 08:22:32.090998: step: 428/527, loss: 0.0018456102116033435
2023-01-24 08:22:33.144107: step: 432/527, loss: 0.0020110278856009245
2023-01-24 08:22:34.183459: step: 436/527, loss: 0.002694170456379652
2023-01-24 08:22:35.234332: step: 440/527, loss: 7.465425005648285e-05
2023-01-24 08:22:36.280963: step: 444/527, loss: 0.00019459918257780373
2023-01-24 08:22:37.324444: step: 448/527, loss: 0.0004426784289535135
2023-01-24 08:22:38.364516: step: 452/527, loss: 0.004749386105686426
2023-01-24 08:22:39.406246: step: 456/527, loss: 0.0016682259738445282
2023-01-24 08:22:40.456380: step: 460/527, loss: 0.0029491796158254147
2023-01-24 08:22:41.499762: step: 464/527, loss: 0.000469332211650908
2023-01-24 08:22:42.539211: step: 468/527, loss: 0.00018809053290169686
2023-01-24 08:22:43.594336: step: 472/527, loss: 0.0013134346809238195
2023-01-24 08:22:44.646060: step: 476/527, loss: 0.00023439782671630383
2023-01-24 08:22:45.694307: step: 480/527, loss: 0.004121716134250164
2023-01-24 08:22:46.743462: step: 484/527, loss: 0.001431083888746798
2023-01-24 08:22:47.816409: step: 488/527, loss: 0.0058966707438230515
2023-01-24 08:22:48.857021: step: 492/527, loss: 0.0005907844752073288
2023-01-24 08:22:49.934705: step: 496/527, loss: 0.006532412488013506
2023-01-24 08:22:50.974967: step: 500/527, loss: 0.0030911448411643505
2023-01-24 08:22:52.004224: step: 504/527, loss: 0.00021066353656351566
2023-01-24 08:22:53.052784: step: 508/527, loss: 0.0025344612076878548
2023-01-24 08:22:54.091738: step: 512/527, loss: 0.0011053717462345958
2023-01-24 08:22:55.138832: step: 516/527, loss: 0.0032064008992165327
2023-01-24 08:22:56.176906: step: 520/527, loss: 0.002280354965478182
2023-01-24 08:22:57.218826: step: 524/527, loss: 0.00021155075228307396
2023-01-24 08:22:58.255484: step: 528/527, loss: 2.7550872800929938e-06
2023-01-24 08:22:59.304499: step: 532/527, loss: 0.002412882400676608
2023-01-24 08:23:00.355360: step: 536/527, loss: 0.0037573096342384815
2023-01-24 08:23:01.404178: step: 540/527, loss: 0.0037381730508059263
2023-01-24 08:23:02.461008: step: 544/527, loss: 0.010366102680563927
2023-01-24 08:23:03.504110: step: 548/527, loss: 0.004930758383125067
2023-01-24 08:23:04.560151: step: 552/527, loss: 0.00021737173665314913
2023-01-24 08:23:05.608411: step: 556/527, loss: 0.0007519605569541454
2023-01-24 08:23:06.652055: step: 560/527, loss: 0.0010421059560030699
2023-01-24 08:23:07.716123: step: 564/527, loss: 0.003788598347455263
2023-01-24 08:23:08.758806: step: 568/527, loss: 0.002252707490697503
2023-01-24 08:23:09.805961: step: 572/527, loss: 0.0028377401176840067
2023-01-24 08:23:10.856629: step: 576/527, loss: 0.000956843898165971
2023-01-24 08:23:11.910969: step: 580/527, loss: 0.0004477793991100043
2023-01-24 08:23:12.964937: step: 584/527, loss: 0.0011237958678975701
2023-01-24 08:23:13.999184: step: 588/527, loss: 7.421124610118568e-05
2023-01-24 08:23:15.062861: step: 592/527, loss: 0.0006340961554087698
2023-01-24 08:23:16.119716: step: 596/527, loss: 0.004716572817414999
2023-01-24 08:23:17.172291: step: 600/527, loss: 0.0007542010862380266
2023-01-24 08:23:18.214605: step: 604/527, loss: 0.0019124950049445033
2023-01-24 08:23:19.263958: step: 608/527, loss: 0.0008903234265744686
2023-01-24 08:23:20.310501: step: 612/527, loss: 0.00029588781762868166
2023-01-24 08:23:21.349393: step: 616/527, loss: 0.0002638907462824136
2023-01-24 08:23:22.387176: step: 620/527, loss: 0.004279885906726122
2023-01-24 08:23:23.432554: step: 624/527, loss: 0.003448769450187683
2023-01-24 08:23:24.473812: step: 628/527, loss: 0.0011539554689079523
2023-01-24 08:23:25.533110: step: 632/527, loss: 0.0005331645952537656
2023-01-24 08:23:26.592843: step: 636/527, loss: 7.054158777464181e-05
2023-01-24 08:23:27.643647: step: 640/527, loss: 5.5627657275181264e-05
2023-01-24 08:23:28.697658: step: 644/527, loss: 0.0007396565051749349
2023-01-24 08:23:29.732459: step: 648/527, loss: 0.006331439595669508
2023-01-24 08:23:30.773994: step: 652/527, loss: 0.00035678475978784263
2023-01-24 08:23:31.811288: step: 656/527, loss: 0.0032871002331376076
2023-01-24 08:23:32.849055: step: 660/527, loss: 0.00025014832499437034
2023-01-24 08:23:33.900296: step: 664/527, loss: 0.0011277494486421347
2023-01-24 08:23:34.940824: step: 668/527, loss: 0.0015809549950063229
2023-01-24 08:23:35.991959: step: 672/527, loss: 0.003566933562979102
2023-01-24 08:23:37.040896: step: 676/527, loss: 0.004508631303906441
2023-01-24 08:23:38.081201: step: 680/527, loss: 0.0001808066008379683
2023-01-24 08:23:39.143230: step: 684/527, loss: 0.00018901760631706566
2023-01-24 08:23:40.186589: step: 688/527, loss: 0.0022870684042572975
2023-01-24 08:23:41.250193: step: 692/527, loss: 0.0013621466932818294
2023-01-24 08:23:42.292646: step: 696/527, loss: 0.0015201774658635259
2023-01-24 08:23:43.319945: step: 700/527, loss: 0.000568160496186465
2023-01-24 08:23:44.357355: step: 704/527, loss: 0.0032007326371967793
2023-01-24 08:23:45.399872: step: 708/527, loss: 0.0016230453038588166
2023-01-24 08:23:46.457004: step: 712/527, loss: 0.0005796492332592607
2023-01-24 08:23:47.518254: step: 716/527, loss: 0.0009226712863892317
2023-01-24 08:23:48.562010: step: 720/527, loss: 0.0028949675615876913
2023-01-24 08:23:49.614193: step: 724/527, loss: 0.001731087570078671
2023-01-24 08:23:50.675876: step: 728/527, loss: 0.0026178890839219093
2023-01-24 08:23:51.734964: step: 732/527, loss: 0.002597362268716097
2023-01-24 08:23:52.807013: step: 736/527, loss: 0.006035243161022663
2023-01-24 08:23:53.858065: step: 740/527, loss: 0.0012200167402625084
2023-01-24 08:23:54.924949: step: 744/527, loss: 0.02378031611442566
2023-01-24 08:23:55.978125: step: 748/527, loss: 0.0023233520332723856
2023-01-24 08:23:57.041046: step: 752/527, loss: 0.0026843021623790264
2023-01-24 08:23:58.094840: step: 756/527, loss: 3.931805258616805e-05
2023-01-24 08:23:59.172676: step: 760/527, loss: 0.003764260094612837
2023-01-24 08:24:00.229021: step: 764/527, loss: 0.0035821055062115192
2023-01-24 08:24:01.280362: step: 768/527, loss: 0.0018697303021326661
2023-01-24 08:24:02.322364: step: 772/527, loss: 0.0004802238254342228
2023-01-24 08:24:03.374335: step: 776/527, loss: 0.0024648287799209356
2023-01-24 08:24:04.421526: step: 780/527, loss: 0.005739917512983084
2023-01-24 08:24:05.485749: step: 784/527, loss: 0.004004983697086573
2023-01-24 08:24:06.536519: step: 788/527, loss: 0.004859437234699726
2023-01-24 08:24:07.577696: step: 792/527, loss: 0.0023412094451487064
2023-01-24 08:24:08.642957: step: 796/527, loss: 0.0016801258316263556
2023-01-24 08:24:09.682023: step: 800/527, loss: 0.0012225111713632941
2023-01-24 08:24:10.731573: step: 804/527, loss: 0.0011696823639795184
2023-01-24 08:24:11.799191: step: 808/527, loss: 0.00355927599593997
2023-01-24 08:24:12.857694: step: 812/527, loss: 0.002963677980005741
2023-01-24 08:24:13.900728: step: 816/527, loss: 0.00018926951452158391
2023-01-24 08:24:14.936041: step: 820/527, loss: 0.0026075481437146664
2023-01-24 08:24:15.982519: step: 824/527, loss: 0.0004882774665020406
2023-01-24 08:24:17.023962: step: 828/527, loss: 0.00041456532198935747
2023-01-24 08:24:18.081510: step: 832/527, loss: 0.0016185598215088248
2023-01-24 08:24:19.121954: step: 836/527, loss: 3.3528027415741235e-05
2023-01-24 08:24:20.208629: step: 840/527, loss: 0.00012909978977404535
2023-01-24 08:24:21.266832: step: 844/527, loss: 0.0009344768477603793
2023-01-24 08:24:22.343159: step: 848/527, loss: 0.00044836910092271864
2023-01-24 08:24:23.400897: step: 852/527, loss: 0.0013338637072592974
2023-01-24 08:24:24.451038: step: 856/527, loss: 0.025258412584662437
2023-01-24 08:24:25.495517: step: 860/527, loss: 3.928777005057782e-05
2023-01-24 08:24:26.540984: step: 864/527, loss: 0.0017782094655558467
2023-01-24 08:24:27.586699: step: 868/527, loss: 0.001507895765826106
2023-01-24 08:24:28.640064: step: 872/527, loss: 9.579635661793873e-05
2023-01-24 08:24:29.679097: step: 876/527, loss: 0.00045015112846158445
2023-01-24 08:24:30.727804: step: 880/527, loss: 3.941454997402616e-05
2023-01-24 08:24:31.778837: step: 884/527, loss: 0.00019927287939935923
2023-01-24 08:24:32.829778: step: 888/527, loss: 0.0004476940957829356
2023-01-24 08:24:33.880546: step: 892/527, loss: 0.002160863019526005
2023-01-24 08:24:34.922100: step: 896/527, loss: 1.286247879761504e-06
2023-01-24 08:24:35.967228: step: 900/527, loss: 0.0018993709236383438
2023-01-24 08:24:37.022108: step: 904/527, loss: 0.003663277020677924
2023-01-24 08:24:38.065468: step: 908/527, loss: 0.0005014063790440559
2023-01-24 08:24:39.116186: step: 912/527, loss: 0.0011812280863523483
2023-01-24 08:24:40.162834: step: 916/527, loss: 0.00021897708938922733
2023-01-24 08:24:41.215575: step: 920/527, loss: 0.004858082160353661
2023-01-24 08:24:42.270508: step: 924/527, loss: 3.419330141696264e-06
2023-01-24 08:24:43.347505: step: 928/527, loss: 9.689629223430529e-05
2023-01-24 08:24:44.383871: step: 932/527, loss: 0.004934093914926052
2023-01-24 08:24:45.448867: step: 936/527, loss: 0.007146681193262339
2023-01-24 08:24:46.509594: step: 940/527, loss: 0.005228206980973482
2023-01-24 08:24:47.555386: step: 944/527, loss: 0.005892444867640734
2023-01-24 08:24:48.603701: step: 948/527, loss: 0.0036787502467632294
2023-01-24 08:24:49.674530: step: 952/527, loss: 0.005641875322908163
2023-01-24 08:24:50.736692: step: 956/527, loss: 0.005650161299854517
2023-01-24 08:24:51.792371: step: 960/527, loss: 0.00016518983466085047
2023-01-24 08:24:52.853839: step: 964/527, loss: 0.002716799033805728
2023-01-24 08:24:53.899690: step: 968/527, loss: 0.0016688454197719693
2023-01-24 08:24:54.951782: step: 972/527, loss: 0.0004956090124323964
2023-01-24 08:24:55.993376: step: 976/527, loss: 0.0014253997942432761
2023-01-24 08:24:57.062571: step: 980/527, loss: 0.000839250860735774
2023-01-24 08:24:58.115241: step: 984/527, loss: 9.638193887440138e-07
2023-01-24 08:24:59.171347: step: 988/527, loss: 0.008759046904742718
2023-01-24 08:25:00.215355: step: 992/527, loss: 0.004515122622251511
2023-01-24 08:25:01.276558: step: 996/527, loss: 0.008989899419248104
2023-01-24 08:25:02.348728: step: 1000/527, loss: 0.008065260015428066
2023-01-24 08:25:03.396707: step: 1004/527, loss: 0.00015686292317695916
2023-01-24 08:25:04.461172: step: 1008/527, loss: 0.0011779895285144448
2023-01-24 08:25:05.504866: step: 1012/527, loss: 8.751158748054877e-05
2023-01-24 08:25:06.560385: step: 1016/527, loss: 0.00015617186727467924
2023-01-24 08:25:07.612851: step: 1020/527, loss: 0.0562683567404747
2023-01-24 08:25:08.666994: step: 1024/527, loss: 4.730817636300344e-06
2023-01-24 08:25:09.714740: step: 1028/527, loss: 0.00033617194276303053
2023-01-24 08:25:10.762886: step: 1032/527, loss: 1.543375401524827e-05
2023-01-24 08:25:11.809935: step: 1036/527, loss: 0.0001290388172492385
2023-01-24 08:25:12.860748: step: 1040/527, loss: 0.008686935529112816
2023-01-24 08:25:13.893491: step: 1044/527, loss: 0.00023880135267972946
2023-01-24 08:25:14.946182: step: 1048/527, loss: 3.96492141589988e-05
2023-01-24 08:25:15.991163: step: 1052/527, loss: 0.0100388303399086
2023-01-24 08:25:17.040973: step: 1056/527, loss: 0.010499967262148857
2023-01-24 08:25:18.089651: step: 1060/527, loss: 0.0038951095193624496
2023-01-24 08:25:19.141395: step: 1064/527, loss: 0.00046576434397138655
2023-01-24 08:25:20.205662: step: 1068/527, loss: 0.0043186829425394535
2023-01-24 08:25:21.259959: step: 1072/527, loss: 0.0074883801862597466
2023-01-24 08:25:22.324078: step: 1076/527, loss: 0.0035053847823292017
2023-01-24 08:25:23.380193: step: 1080/527, loss: 0.0016175603959709406
2023-01-24 08:25:24.441978: step: 1084/527, loss: 0.0016296030953526497
2023-01-24 08:25:25.489726: step: 1088/527, loss: 0.006884086411446333
2023-01-24 08:25:26.542253: step: 1092/527, loss: 0.011091403663158417
2023-01-24 08:25:27.583177: step: 1096/527, loss: 0.0017351646674796939
2023-01-24 08:25:28.657549: step: 1100/527, loss: 0.0030168371740728617
2023-01-24 08:25:29.715256: step: 1104/527, loss: 0.0003128311946056783
2023-01-24 08:25:30.768827: step: 1108/527, loss: 0.0008832140010781586
2023-01-24 08:25:31.813182: step: 1112/527, loss: 0.0081856120377779
2023-01-24 08:25:32.850974: step: 1116/527, loss: 0.004840338137000799
2023-01-24 08:25:33.897878: step: 1120/527, loss: 0.030308624729514122
2023-01-24 08:25:34.945456: step: 1124/527, loss: 0.0027085395995527506
2023-01-24 08:25:35.999677: step: 1128/527, loss: 0.002785088960081339
2023-01-24 08:25:37.053228: step: 1132/527, loss: 0.0023589825723320246
2023-01-24 08:25:38.116390: step: 1136/527, loss: 0.005080981645733118
2023-01-24 08:25:39.165328: step: 1140/527, loss: 4.106581036467105e-05
2023-01-24 08:25:40.203349: step: 1144/527, loss: 1.889448321890086e-05
2023-01-24 08:25:41.242915: step: 1148/527, loss: 0.002939001889899373
2023-01-24 08:25:42.302187: step: 1152/527, loss: 0.000601550389546901
2023-01-24 08:25:43.385984: step: 1156/527, loss: 0.003312253626063466
2023-01-24 08:25:44.434755: step: 1160/527, loss: 0.0007136150379665196
2023-01-24 08:25:45.500032: step: 1164/527, loss: 0.0018060844158753753
2023-01-24 08:25:46.552620: step: 1168/527, loss: 0.0014226859202608466
2023-01-24 08:25:47.631136: step: 1172/527, loss: 0.0006509943632408977
2023-01-24 08:25:48.698533: step: 1176/527, loss: 0.014781204983592033
2023-01-24 08:25:49.753744: step: 1180/527, loss: 8.681502549734432e-06
2023-01-24 08:25:50.803608: step: 1184/527, loss: 0.00023267757205758244
2023-01-24 08:25:51.843750: step: 1188/527, loss: 0.00045446064905263484
2023-01-24 08:25:52.887502: step: 1192/527, loss: 0.004257341381162405
2023-01-24 08:25:53.930544: step: 1196/527, loss: 0.0013183987466618419
2023-01-24 08:25:54.976191: step: 1200/527, loss: 0.00014054019993636757
2023-01-24 08:25:56.006111: step: 1204/527, loss: 0.0008084220462478697
2023-01-24 08:25:57.062921: step: 1208/527, loss: 0.007088435348123312
2023-01-24 08:25:58.126988: step: 1212/527, loss: 0.0014545589219778776
2023-01-24 08:25:59.180786: step: 1216/527, loss: 0.002247134456411004
2023-01-24 08:26:00.223064: step: 1220/527, loss: 0.0033124717883765697
2023-01-24 08:26:01.280593: step: 1224/527, loss: 0.002531507983803749
2023-01-24 08:26:02.329819: step: 1228/527, loss: 0.00119197356980294
2023-01-24 08:26:03.406660: step: 1232/527, loss: 0.032387636601924896
2023-01-24 08:26:04.485630: step: 1236/527, loss: 0.0016946601681411266
2023-01-24 08:26:05.536911: step: 1240/527, loss: 0.00012360351684037596
2023-01-24 08:26:06.583481: step: 1244/527, loss: 0.008430695161223412
2023-01-24 08:26:07.637422: step: 1248/527, loss: 0.0037241019308567047
2023-01-24 08:26:08.703479: step: 1252/527, loss: 0.039327334612607956
2023-01-24 08:26:09.777332: step: 1256/527, loss: 0.011953353881835938
2023-01-24 08:26:10.842827: step: 1260/527, loss: 5.241167309577577e-05
2023-01-24 08:26:11.898641: step: 1264/527, loss: 0.00523105263710022
2023-01-24 08:26:12.945318: step: 1268/527, loss: 0.030929936096072197
2023-01-24 08:26:14.022677: step: 1272/527, loss: 0.004271724261343479
2023-01-24 08:26:15.071723: step: 1276/527, loss: 0.007714667357504368
2023-01-24 08:26:16.129867: step: 1280/527, loss: 0.0
2023-01-24 08:26:17.180537: step: 1284/527, loss: 0.018863724544644356
2023-01-24 08:26:18.237476: step: 1288/527, loss: 0.005001505371183157
2023-01-24 08:26:19.299320: step: 1292/527, loss: 0.0053301602602005005
2023-01-24 08:26:20.355429: step: 1296/527, loss: 0.00012269285798538476
2023-01-24 08:26:21.407301: step: 1300/527, loss: 5.226344910624903e-06
2023-01-24 08:26:22.462597: step: 1304/527, loss: 0.014397171325981617
2023-01-24 08:26:23.487033: step: 1308/527, loss: 0.002376345219090581
2023-01-24 08:26:24.523704: step: 1312/527, loss: 5.384029645938426e-05
2023-01-24 08:26:25.561430: step: 1316/527, loss: 3.4901979688584106e-06
2023-01-24 08:26:26.611709: step: 1320/527, loss: 0.002286794362589717
2023-01-24 08:26:27.649595: step: 1324/527, loss: 0.0006541643524542451
2023-01-24 08:26:28.697568: step: 1328/527, loss: 0.00814491044729948
2023-01-24 08:26:29.765342: step: 1332/527, loss: 0.00011340711353113875
2023-01-24 08:26:30.809145: step: 1336/527, loss: 0.011391766369342804
2023-01-24 08:26:31.870519: step: 1340/527, loss: 0.001479583908803761
2023-01-24 08:26:32.926057: step: 1344/527, loss: 0.0030467596370726824
2023-01-24 08:26:33.967046: step: 1348/527, loss: 1.1043883887396078e-06
2023-01-24 08:26:35.006015: step: 1352/527, loss: 0.003084165044128895
2023-01-24 08:26:36.067395: step: 1356/527, loss: 0.0051566725596785545
2023-01-24 08:26:37.111226: step: 1360/527, loss: 6.126777589088306e-05
2023-01-24 08:26:38.156905: step: 1364/527, loss: 1.410919821864809e-06
2023-01-24 08:26:39.210557: step: 1368/527, loss: 0.0009264004183933139
2023-01-24 08:26:40.247929: step: 1372/527, loss: 0.014048118144273758
2023-01-24 08:26:41.299619: step: 1376/527, loss: 0.00014146050671115518
2023-01-24 08:26:42.348757: step: 1380/527, loss: 7.282990850399074e-07
2023-01-24 08:26:43.405706: step: 1384/527, loss: 0.0011171610094606876
2023-01-24 08:26:44.456994: step: 1388/527, loss: 0.0029004269745200872
2023-01-24 08:26:45.506715: step: 1392/527, loss: 0.0001176630103145726
2023-01-24 08:26:46.538967: step: 1396/527, loss: 0.003521586302667856
2023-01-24 08:26:47.573102: step: 1400/527, loss: 0.001106196898035705
2023-01-24 08:26:48.618368: step: 1404/527, loss: 0.0018420495325699449
2023-01-24 08:26:49.699592: step: 1408/527, loss: 0.0001412111014360562
2023-01-24 08:26:50.754285: step: 1412/527, loss: 0.0028781823348253965
2023-01-24 08:26:51.794611: step: 1416/527, loss: 0.008627197705209255
2023-01-24 08:26:52.839229: step: 1420/527, loss: 0.00126778578851372
2023-01-24 08:26:53.912908: step: 1424/527, loss: 0.0029198392294347286
2023-01-24 08:26:54.957906: step: 1428/527, loss: 0.0020186915062367916
2023-01-24 08:26:55.997689: step: 1432/527, loss: 0.0007028497639112175
2023-01-24 08:26:57.035539: step: 1436/527, loss: 6.912242952239467e-06
2023-01-24 08:26:58.073259: step: 1440/527, loss: 0.00014145876048132777
2023-01-24 08:26:59.113183: step: 1444/527, loss: 0.0044008237309753895
2023-01-24 08:27:00.156674: step: 1448/527, loss: 0.005445878952741623
2023-01-24 08:27:01.209261: step: 1452/527, loss: 0.001045777229592204
2023-01-24 08:27:02.254840: step: 1456/527, loss: 3.6557183193508536e-05
2023-01-24 08:27:03.327101: step: 1460/527, loss: 0.03554559126496315
2023-01-24 08:27:04.384590: step: 1464/527, loss: 0.002275254810228944
2023-01-24 08:27:05.422015: step: 1468/527, loss: 0.006344575900584459
2023-01-24 08:27:06.470718: step: 1472/527, loss: 0.004299920052289963
2023-01-24 08:27:07.533265: step: 1476/527, loss: 0.0009293946204707026
2023-01-24 08:27:08.563666: step: 1480/527, loss: 0.0008743713842704892
2023-01-24 08:27:09.627436: step: 1484/527, loss: 0.007850652560591698
2023-01-24 08:27:10.682715: step: 1488/527, loss: 0.0010376196587458253
2023-01-24 08:27:11.719562: step: 1492/527, loss: 0.007174760103225708
2023-01-24 08:27:12.798701: step: 1496/527, loss: 0.0016052037244662642
2023-01-24 08:27:13.870497: step: 1500/527, loss: 0.04143362119793892
2023-01-24 08:27:14.914269: step: 1504/527, loss: 0.0004749679355882108
2023-01-24 08:27:15.969887: step: 1508/527, loss: 0.004666943568736315
2023-01-24 08:27:17.000778: step: 1512/527, loss: 0.0032719543669372797
2023-01-24 08:27:18.047310: step: 1516/527, loss: 0.013074143789708614
2023-01-24 08:27:19.109774: step: 1520/527, loss: 0.020387792959809303
2023-01-24 08:27:20.182159: step: 1524/527, loss: 0.0011136516695842147
2023-01-24 08:27:21.237488: step: 1528/527, loss: 4.0213461716120946e-07
2023-01-24 08:27:22.280332: step: 1532/527, loss: 0.09360566735267639
2023-01-24 08:27:23.333286: step: 1536/527, loss: 0.0027380732353776693
2023-01-24 08:27:24.392530: step: 1540/527, loss: 0.007201777305454016
2023-01-24 08:27:25.443442: step: 1544/527, loss: 0.0003845072351396084
2023-01-24 08:27:26.497475: step: 1548/527, loss: 0.0040751309134066105
2023-01-24 08:27:27.553879: step: 1552/527, loss: 0.0005427770665846765
2023-01-24 08:27:28.605941: step: 1556/527, loss: 0.0007876624003984034
2023-01-24 08:27:29.651763: step: 1560/527, loss: 0.0078010959550738335
2023-01-24 08:27:30.686607: step: 1564/527, loss: 0.011258622631430626
2023-01-24 08:27:31.735586: step: 1568/527, loss: 0.008774255402386189
2023-01-24 08:27:32.789066: step: 1572/527, loss: 0.0
2023-01-24 08:27:33.851916: step: 1576/527, loss: 0.0004778808797709644
2023-01-24 08:27:34.910234: step: 1580/527, loss: 0.0011181411100551486
2023-01-24 08:27:35.966412: step: 1584/527, loss: 0.0010481381323188543
2023-01-24 08:27:37.007605: step: 1588/527, loss: 9.526356734568253e-07
2023-01-24 08:27:38.046846: step: 1592/527, loss: 0.0029680703300982714
2023-01-24 08:27:39.096227: step: 1596/527, loss: 0.00012218925985507667
2023-01-24 08:27:40.136953: step: 1600/527, loss: 0.005882780533283949
2023-01-24 08:27:41.198356: step: 1604/527, loss: 0.004306986927986145
2023-01-24 08:27:42.243775: step: 1608/527, loss: 0.0011997794499620795
2023-01-24 08:27:43.305244: step: 1612/527, loss: 6.15232638665475e-05
2023-01-24 08:27:44.358194: step: 1616/527, loss: 0.0039931898936629295
2023-01-24 08:27:45.416946: step: 1620/527, loss: 0.0048449719324707985
2023-01-24 08:27:46.457510: step: 1624/527, loss: 0.0028302224818617105
2023-01-24 08:27:47.499226: step: 1628/527, loss: 0.0024578245356678963
2023-01-24 08:27:48.546217: step: 1632/527, loss: 1.6769845387898386e-05
2023-01-24 08:27:49.605014: step: 1636/527, loss: 5.4790330068499316e-06
2023-01-24 08:27:50.668115: step: 1640/527, loss: 0.0010549993021413684
2023-01-24 08:27:51.714613: step: 1644/527, loss: 0.00018326147983316332
2023-01-24 08:27:52.768391: step: 1648/527, loss: 3.9530550566269085e-05
2023-01-24 08:27:53.871706: step: 1652/527, loss: 0.0008924430585466325
2023-01-24 08:27:54.918497: step: 1656/527, loss: 0.0
2023-01-24 08:27:55.973772: step: 1660/527, loss: 0.00019519409397616982
2023-01-24 08:27:57.034586: step: 1664/527, loss: 0.0007686466560699046
2023-01-24 08:27:58.069824: step: 1668/527, loss: 0.003471133764833212
2023-01-24 08:27:59.152068: step: 1672/527, loss: 6.953163392608985e-05
2023-01-24 08:28:00.199077: step: 1676/527, loss: 0.0005026942235417664
2023-01-24 08:28:01.250194: step: 1680/527, loss: 0.0006109153619036078
2023-01-24 08:28:02.298663: step: 1684/527, loss: 0.0005501993582583964
2023-01-24 08:28:03.344117: step: 1688/527, loss: 0.01132991909980774
2023-01-24 08:28:04.401838: step: 1692/527, loss: 0.0029809074476361275
2023-01-24 08:28:05.450046: step: 1696/527, loss: 0.0014878124929964542
2023-01-24 08:28:06.502168: step: 1700/527, loss: 0.0013360537122935057
2023-01-24 08:28:07.547508: step: 1704/527, loss: 0.017990943044424057
2023-01-24 08:28:08.601551: step: 1708/527, loss: 0.006154506001621485
2023-01-24 08:28:09.675310: step: 1712/527, loss: 0.0006551499245688319
2023-01-24 08:28:10.721763: step: 1716/527, loss: 0.008096030913293362
2023-01-24 08:28:11.760427: step: 1720/527, loss: 0.00020135923114139587
2023-01-24 08:28:12.812033: step: 1724/527, loss: 0.0013545985566452146
2023-01-24 08:28:13.856949: step: 1728/527, loss: 0.005859773140400648
2023-01-24 08:28:14.897158: step: 1732/527, loss: 0.0001550184824736789
2023-01-24 08:28:15.937255: step: 1736/527, loss: 0.005643974523991346
2023-01-24 08:28:16.984696: step: 1740/527, loss: 0.00018664108938537538
2023-01-24 08:28:18.036328: step: 1744/527, loss: 3.70259876945056e-05
2023-01-24 08:28:19.114969: step: 1748/527, loss: 0.0004678943078033626
2023-01-24 08:28:20.188759: step: 1752/527, loss: 6.744949496351182e-05
2023-01-24 08:28:21.236969: step: 1756/527, loss: 0.0021448186598718166
2023-01-24 08:28:22.289118: step: 1760/527, loss: 0.008603259921073914
2023-01-24 08:28:23.330863: step: 1764/527, loss: 0.0006919324514456093
2023-01-24 08:28:24.374749: step: 1768/527, loss: 0.002849181182682514
2023-01-24 08:28:25.430419: step: 1772/527, loss: 0.004121398087590933
2023-01-24 08:28:26.493796: step: 1776/527, loss: 0.00426100566983223
2023-01-24 08:28:27.564182: step: 1780/527, loss: 4.67739264422562e-05
2023-01-24 08:28:28.610313: step: 1784/527, loss: 0.009063458070158958
2023-01-24 08:28:29.658281: step: 1788/527, loss: 0.00182454998139292
2023-01-24 08:28:30.700643: step: 1792/527, loss: 0.0035536442883312702
2023-01-24 08:28:31.755569: step: 1796/527, loss: 0.0037197452038526535
2023-01-24 08:28:32.811536: step: 1800/527, loss: 0.00019455174333415926
2023-01-24 08:28:33.871559: step: 1804/527, loss: 0.0026370801497250795
2023-01-24 08:28:34.923032: step: 1808/527, loss: 0.0030652715358883142
2023-01-24 08:28:35.963479: step: 1812/527, loss: 0.0024316839408129454
2023-01-24 08:28:37.007100: step: 1816/527, loss: 0.0007326296181418002
2023-01-24 08:28:38.055164: step: 1820/527, loss: 0.00016146816778928041
2023-01-24 08:28:39.126664: step: 1824/527, loss: 0.0012475645635277033
2023-01-24 08:28:40.163840: step: 1828/527, loss: 2.08992696570931e-06
2023-01-24 08:28:41.198702: step: 1832/527, loss: 0.0008731891284696758
2023-01-24 08:28:42.237488: step: 1836/527, loss: 0.0005046541336923838
2023-01-24 08:28:43.293773: step: 1840/527, loss: 0.0033859414979815483
2023-01-24 08:28:44.339781: step: 1844/527, loss: 3.524941348587163e-06
2023-01-24 08:28:45.422440: step: 1848/527, loss: 0.00437305448576808
2023-01-24 08:28:46.485274: step: 1852/527, loss: 0.004508023150265217
2023-01-24 08:28:47.529094: step: 1856/527, loss: 0.014133771881461143
2023-01-24 08:28:48.565396: step: 1860/527, loss: 0.004224679432809353
2023-01-24 08:28:49.613898: step: 1864/527, loss: 7.189463940449059e-05
2023-01-24 08:28:50.660627: step: 1868/527, loss: 0.0002129123458871618
2023-01-24 08:28:51.695533: step: 1872/527, loss: 4.143520709476434e-05
2023-01-24 08:28:52.748348: step: 1876/527, loss: 0.0001666843018028885
2023-01-24 08:28:53.796777: step: 1880/527, loss: 0.0004542075330391526
2023-01-24 08:28:54.834803: step: 1884/527, loss: 2.9606893804157153e-05
2023-01-24 08:28:55.886114: step: 1888/527, loss: 0.012230230495333672
2023-01-24 08:28:56.938483: step: 1892/527, loss: 0.001827106112614274
2023-01-24 08:28:57.973614: step: 1896/527, loss: 0.0001150547104771249
2023-01-24 08:28:59.015864: step: 1900/527, loss: 0.0006541578331962228
2023-01-24 08:29:00.087939: step: 1904/527, loss: 0.0063913846388459206
2023-01-24 08:29:01.133324: step: 1908/527, loss: 0.0004467086400836706
2023-01-24 08:29:02.176203: step: 1912/527, loss: 0.0026143663562834263
2023-01-24 08:29:03.225571: step: 1916/527, loss: 0.0013308327179402113
2023-01-24 08:29:04.280149: step: 1920/527, loss: 0.0015405912417918444
2023-01-24 08:29:05.329163: step: 1924/527, loss: 0.0022682996932417154
2023-01-24 08:29:06.373992: step: 1928/527, loss: 0.0005238543380983174
2023-01-24 08:29:07.431411: step: 1932/527, loss: 0.0022057874593883753
2023-01-24 08:29:08.472829: step: 1936/527, loss: 0.0024064078461378813
2023-01-24 08:29:09.516335: step: 1940/527, loss: 0.0006565373041667044
2023-01-24 08:29:10.577152: step: 1944/527, loss: 0.003322137054055929
2023-01-24 08:29:11.630934: step: 1948/527, loss: 1.83789488801267e-05
2023-01-24 08:29:12.694668: step: 1952/527, loss: 0.00410924106836319
2023-01-24 08:29:13.731333: step: 1956/527, loss: 0.0014497730880975723
2023-01-24 08:29:14.781418: step: 1960/527, loss: 0.0027992953546345234
2023-01-24 08:29:15.826294: step: 1964/527, loss: 0.0007170918397605419
2023-01-24 08:29:16.875175: step: 1968/527, loss: 0.0007623176206834614
2023-01-24 08:29:17.917357: step: 1972/527, loss: 0.0001059624701156281
2023-01-24 08:29:18.969288: step: 1976/527, loss: 0.010869506746530533
2023-01-24 08:29:20.039418: step: 1980/527, loss: 0.0006414271192625165
2023-01-24 08:29:21.098547: step: 1984/527, loss: 0.0020719636231660843
2023-01-24 08:29:22.149808: step: 1988/527, loss: 0.002771086758002639
2023-01-24 08:29:23.201110: step: 1992/527, loss: 0.001135596539825201
2023-01-24 08:29:24.252495: step: 1996/527, loss: 0.004010528326034546
2023-01-24 08:29:25.298158: step: 2000/527, loss: 0.0009158113971352577
2023-01-24 08:29:26.355397: step: 2004/527, loss: 0.009799730964004993
2023-01-24 08:29:27.396535: step: 2008/527, loss: 0.0047936225309967995
2023-01-24 08:29:28.432129: step: 2012/527, loss: 9.768518066266552e-05
2023-01-24 08:29:29.483362: step: 2016/527, loss: 0.003521579783409834
2023-01-24 08:29:30.525294: step: 2020/527, loss: 0.00020912880427204072
2023-01-24 08:29:31.579925: step: 2024/527, loss: 0.017368612810969353
2023-01-24 08:29:32.645894: step: 2028/527, loss: 0.0022687832824885845
2023-01-24 08:29:33.698854: step: 2032/527, loss: 0.0034930668771266937
2023-01-24 08:29:34.751110: step: 2036/527, loss: 0.0024059948045760393
2023-01-24 08:29:35.817502: step: 2040/527, loss: 0.012159084901213646
2023-01-24 08:29:36.866350: step: 2044/527, loss: 0.0008363500237464905
2023-01-24 08:29:37.913108: step: 2048/527, loss: 0.01804187521338463
2023-01-24 08:29:38.973282: step: 2052/527, loss: 0.008290478028357029
2023-01-24 08:29:40.038621: step: 2056/527, loss: 0.005115034058690071
2023-01-24 08:29:41.089297: step: 2060/527, loss: 0.0006204050732776523
2023-01-24 08:29:42.136669: step: 2064/527, loss: 0.003309947904199362
2023-01-24 08:29:43.183774: step: 2068/527, loss: 0.0009271318558603525
2023-01-24 08:29:44.237343: step: 2072/527, loss: 0.00034452686668373644
2023-01-24 08:29:45.285875: step: 2076/527, loss: 0.008648416958749294
2023-01-24 08:29:46.342940: step: 2080/527, loss: 0.009088486433029175
2023-01-24 08:29:47.390573: step: 2084/527, loss: 0.0010447161039337516
2023-01-24 08:29:48.443062: step: 2088/527, loss: 3.9994196413317695e-05
2023-01-24 08:29:49.503343: step: 2092/527, loss: 0.006336606573313475
2023-01-24 08:29:50.539522: step: 2096/527, loss: 0.0005672467523254454
2023-01-24 08:29:51.593146: step: 2100/527, loss: 2.3187178157968447e-05
2023-01-24 08:29:52.663579: step: 2104/527, loss: 0.002323734574019909
2023-01-24 08:29:53.704157: step: 2108/527, loss: 0.002846564631909132
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33758506620063145, 'r': 0.319008278876498, 'f1': 0.32803387896178426}, 'combined': 0.24170917397184102, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3744861852068893, 'r': 0.2907374565151668, 'f1': 0.3273400226885194}, 'combined': 0.20949761452065238, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35513529240616815, 'r': 0.33087557603686635, 'f1': 0.3425764804939658}, 'combined': 0.25242477510081684, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37829660170458923, 'r': 0.3051111555982518, 'f1': 0.33778520091872827}, 'combined': 0.21618252858798606, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3629126630061771, 'r': 0.3236602497398543, 'f1': 0.3421643964150516}, 'combined': 0.2521211342005643, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.3901604634771812, 'r': 0.3126262966239219, 'f1': 0.34711644473324116}, 'combined': 0.24887594150685216, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36581866015544395, 'r': 0.3255577829466854, 'f1': 0.34451596709418314}, 'combined': 0.2538538704904507, 'stategy': 1, 'epoch': 14}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38617866598002537, 'r': 0.30943577702501573, 'f1': 0.3435739346117837}, 'combined': 0.24633602858958079, 'stategy': 1, 'epoch': 14}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 14}
******************************
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
2023-01-24 08:32:19.773341: step: 4/527, loss: 0.011261706240475178
2023-01-24 08:32:20.808224: step: 8/527, loss: 0.007827507331967354
2023-01-24 08:32:21.837877: step: 12/527, loss: 0.0005057792877778411
2023-01-24 08:32:22.866669: step: 16/527, loss: 0.0031134795863181353
2023-01-24 08:32:23.914099: step: 20/527, loss: 0.0002868354495149106
2023-01-24 08:32:24.965474: step: 24/527, loss: 0.00013468989345710725
2023-01-24 08:32:26.010713: step: 28/527, loss: 0.00035649139317683876
2023-01-24 08:32:27.056175: step: 32/527, loss: 0.007232986390590668
2023-01-24 08:32:28.109878: step: 36/527, loss: 0.020374814048409462
2023-01-24 08:32:29.171241: step: 40/527, loss: 0.00356986653059721
2023-01-24 08:32:30.230875: step: 44/527, loss: 0.0034938640892505646
2023-01-24 08:32:31.292421: step: 48/527, loss: 0.0009810571791604161
2023-01-24 08:32:32.324350: step: 52/527, loss: 0.000971794652286917
2023-01-24 08:32:33.352036: step: 56/527, loss: 0.0008649771334603429
2023-01-24 08:32:34.391667: step: 60/527, loss: 0.003525777952745557
2023-01-24 08:32:35.426316: step: 64/527, loss: 0.0004003901267424226
2023-01-24 08:32:36.470962: step: 68/527, loss: 0.007757800631225109
2023-01-24 08:32:37.504641: step: 72/527, loss: 0.0007056635222397745
2023-01-24 08:32:38.551363: step: 76/527, loss: 0.007265494205057621
2023-01-24 08:32:39.601388: step: 80/527, loss: 0.00485927565023303
2023-01-24 08:32:40.660212: step: 84/527, loss: 0.004400272388011217
2023-01-24 08:32:41.716607: step: 88/527, loss: 0.0017845943802967668
2023-01-24 08:32:42.757947: step: 92/527, loss: 7.837722660042346e-05
2023-01-24 08:32:43.808875: step: 96/527, loss: 0.0011207901407033205
2023-01-24 08:32:44.888870: step: 100/527, loss: 0.007879658602178097
2023-01-24 08:32:45.944686: step: 104/527, loss: 0.002716157818213105
2023-01-24 08:32:46.998384: step: 108/527, loss: 0.00211011222563684
2023-01-24 08:32:48.053874: step: 112/527, loss: 0.0021566858049482107
2023-01-24 08:32:49.106625: step: 116/527, loss: 0.0031201073434203863
2023-01-24 08:32:50.165061: step: 120/527, loss: 0.0018939109286293387
2023-01-24 08:32:51.211738: step: 124/527, loss: 0.0017479229718446732
2023-01-24 08:32:52.248294: step: 128/527, loss: 0.003500449238345027
2023-01-24 08:32:53.292867: step: 132/527, loss: 0.0022102457005530596
2023-01-24 08:32:54.350738: step: 136/527, loss: 0.002419518306851387
2023-01-24 08:32:55.408691: step: 140/527, loss: 0.00331366085447371
2023-01-24 08:32:56.442609: step: 144/527, loss: 0.005694258026778698
2023-01-24 08:32:57.484002: step: 148/527, loss: 0.00029967943555675447
2023-01-24 08:32:58.541701: step: 152/527, loss: 0.007360564079135656
2023-01-24 08:32:59.601535: step: 156/527, loss: 0.00010553120955592021
2023-01-24 08:33:00.630537: step: 160/527, loss: 8.596931729698554e-05
2023-01-24 08:33:01.680528: step: 164/527, loss: 0.009812051430344582
2023-01-24 08:33:02.736700: step: 168/527, loss: 0.001967881340533495
2023-01-24 08:33:03.781621: step: 172/527, loss: 0.0009837568504735827
2023-01-24 08:33:04.839038: step: 176/527, loss: 0.006486051715910435
2023-01-24 08:33:05.875065: step: 180/527, loss: 0.0006882317829877138
2023-01-24 08:33:06.918424: step: 184/527, loss: 0.0006137872114777565
2023-01-24 08:33:07.952340: step: 188/527, loss: 0.003966742195188999
2023-01-24 08:33:08.995566: step: 192/527, loss: 0.006401519291102886
2023-01-24 08:33:10.060339: step: 196/527, loss: 0.0017023910768330097
2023-01-24 08:33:11.113439: step: 200/527, loss: 0.004381560254842043
2023-01-24 08:33:12.179890: step: 204/527, loss: 0.005285480059683323
2023-01-24 08:33:13.231127: step: 208/527, loss: 0.004323142580688
2023-01-24 08:33:14.289858: step: 212/527, loss: 0.0036660742480307817
2023-01-24 08:33:15.334066: step: 216/527, loss: 0.005077271722257137
2023-01-24 08:33:16.391093: step: 220/527, loss: 0.007291702553629875
2023-01-24 08:33:17.441785: step: 224/527, loss: 0.0116579569876194
2023-01-24 08:33:18.494724: step: 228/527, loss: 0.0016320302383974195
2023-01-24 08:33:19.544540: step: 232/527, loss: 2.220473788838717e-06
2023-01-24 08:33:20.598213: step: 236/527, loss: 0.0007793892291374505
2023-01-24 08:33:21.645815: step: 240/527, loss: 0.004000134766101837
2023-01-24 08:33:22.689838: step: 244/527, loss: 0.0030275590252131224
2023-01-24 08:33:23.741419: step: 248/527, loss: 0.0005204488406889141
2023-01-24 08:33:24.796638: step: 252/527, loss: 0.004279037471860647
2023-01-24 08:33:25.845356: step: 256/527, loss: 0.0012941262684762478
2023-01-24 08:33:26.906021: step: 260/527, loss: 0.021386077627539635
2023-01-24 08:33:27.960189: step: 264/527, loss: 0.0
2023-01-24 08:33:28.998005: step: 268/527, loss: 0.004563114605844021
2023-01-24 08:33:30.033419: step: 272/527, loss: 0.0032641792204231024
2023-01-24 08:33:31.085130: step: 276/527, loss: 0.0034787629265338182
2023-01-24 08:33:32.126783: step: 280/527, loss: 7.203911422948295e-07
2023-01-24 08:33:33.191954: step: 284/527, loss: 0.005714936647564173
2023-01-24 08:33:34.245264: step: 288/527, loss: 0.0068635642528533936
2023-01-24 08:33:35.298338: step: 292/527, loss: 0.00025991679285652936
2023-01-24 08:33:36.344397: step: 296/527, loss: 0.00034005078487098217
2023-01-24 08:33:37.415196: step: 300/527, loss: 0.0003228568530175835
2023-01-24 08:33:38.501486: step: 304/527, loss: 0.0027501615695655346
2023-01-24 08:33:39.562566: step: 308/527, loss: 0.00044289312791079283
2023-01-24 08:33:40.610780: step: 312/527, loss: 0.0012972698314115405
2023-01-24 08:33:41.667634: step: 316/527, loss: 4.294528116588481e-05
2023-01-24 08:33:42.715142: step: 320/527, loss: 0.0016187088331207633
2023-01-24 08:33:43.759243: step: 324/527, loss: 0.001886602258309722
2023-01-24 08:33:44.827728: step: 328/527, loss: 0.00041173017234541476
2023-01-24 08:33:45.879436: step: 332/527, loss: 0.00908797699958086
2023-01-24 08:33:46.941904: step: 336/527, loss: 0.0031279101967811584
2023-01-24 08:33:47.996411: step: 340/527, loss: 0.003237391822040081
2023-01-24 08:33:49.062450: step: 344/527, loss: 0.0006014609825797379
2023-01-24 08:33:50.105738: step: 348/527, loss: 0.006200805772095919
2023-01-24 08:33:51.162542: step: 352/527, loss: 3.4257038350915536e-05
2023-01-24 08:33:52.212410: step: 356/527, loss: 0.0026047881692647934
2023-01-24 08:33:53.281005: step: 360/527, loss: 0.002926249522715807
2023-01-24 08:33:54.326721: step: 364/527, loss: 0.005548285320401192
2023-01-24 08:33:55.387462: step: 368/527, loss: 0.0015369912143796682
2023-01-24 08:33:56.429202: step: 372/527, loss: 0.0007180180982686579
2023-01-24 08:33:57.490542: step: 376/527, loss: 0.0023291881661862135
2023-01-24 08:33:58.560299: step: 380/527, loss: 0.001962601672858
2023-01-24 08:33:59.594165: step: 384/527, loss: 0.0001735069090500474
2023-01-24 08:34:00.626461: step: 388/527, loss: 1.769583650457207e-05
2023-01-24 08:34:01.683221: step: 392/527, loss: 0.001420636777766049
2023-01-24 08:34:02.731564: step: 396/527, loss: 0.0038051907904446125
2023-01-24 08:34:03.786827: step: 400/527, loss: 1.4776895113755018e-05
2023-01-24 08:34:04.853097: step: 404/527, loss: 0.002415335038676858
2023-01-24 08:34:05.886222: step: 408/527, loss: 0.00101672881282866
2023-01-24 08:34:06.925178: step: 412/527, loss: 2.6096904548467137e-05
2023-01-24 08:34:07.996643: step: 416/527, loss: 0.0011835232144221663
2023-01-24 08:34:09.052199: step: 420/527, loss: 2.0749389761931525e-07
2023-01-24 08:34:10.104537: step: 424/527, loss: 0.0001908017002278939
2023-01-24 08:34:11.160430: step: 428/527, loss: 0.0003264683182351291
2023-01-24 08:34:12.221138: step: 432/527, loss: 0.0069307913072407246
2023-01-24 08:34:13.272209: step: 436/527, loss: 5.950718332314864e-05
2023-01-24 08:34:14.329206: step: 440/527, loss: 0.00037366163451224566
2023-01-24 08:34:15.370597: step: 444/527, loss: 0.007055746391415596
2023-01-24 08:34:16.428693: step: 448/527, loss: 0.005293744616210461
2023-01-24 08:34:17.476390: step: 452/527, loss: 0.00457759527489543
2023-01-24 08:34:18.519623: step: 456/527, loss: 0.002662491286173463
2023-01-24 08:34:19.564711: step: 460/527, loss: 0.0017520569963380694
2023-01-24 08:34:20.608302: step: 464/527, loss: 1.9040302504436113e-05
2023-01-24 08:34:21.658892: step: 468/527, loss: 0.004375122487545013
2023-01-24 08:34:22.707399: step: 472/527, loss: 0.0033195202704519033
2023-01-24 08:34:23.769427: step: 476/527, loss: 0.001407897681929171
2023-01-24 08:34:24.828159: step: 480/527, loss: 4.7310624040619587e-07
2023-01-24 08:34:25.868864: step: 484/527, loss: 0.002464229241013527
2023-01-24 08:34:26.923697: step: 488/527, loss: 0.0007762182503938675
2023-01-24 08:34:27.971991: step: 492/527, loss: 0.0002021499240072444
2023-01-24 08:34:29.036927: step: 496/527, loss: 0.0002783610252663493
2023-01-24 08:34:30.092086: step: 500/527, loss: 0.0013571904273703694
2023-01-24 08:34:31.151851: step: 504/527, loss: 5.23435628565494e-05
2023-01-24 08:34:32.202337: step: 508/527, loss: 2.8305730666033924e-06
2023-01-24 08:34:33.241861: step: 512/527, loss: 0.0001591030159033835
2023-01-24 08:34:34.277169: step: 516/527, loss: 0.0044831144623458385
2023-01-24 08:34:35.329772: step: 520/527, loss: 0.0010674312943592668
2023-01-24 08:34:36.402250: step: 524/527, loss: 0.003954194951802492
2023-01-24 08:34:37.470415: step: 528/527, loss: 0.0017508434830233455
2023-01-24 08:34:38.527276: step: 532/527, loss: 0.0006341824773699045
2023-01-24 08:34:39.594778: step: 536/527, loss: 0.00486591923981905
2023-01-24 08:34:40.661507: step: 540/527, loss: 0.00433970894664526
2023-01-24 08:34:41.717448: step: 544/527, loss: 0.0010744610335677862
2023-01-24 08:34:42.771386: step: 548/527, loss: 0.0036163392942398787
2023-01-24 08:34:43.833813: step: 552/527, loss: 0.02207617089152336
2023-01-24 08:34:44.876891: step: 556/527, loss: 0.00313242943957448
2023-01-24 08:34:45.934173: step: 560/527, loss: 0.00038497979403473437
2023-01-24 08:34:46.981469: step: 564/527, loss: 0.00024970690719783306
2023-01-24 08:34:48.037058: step: 568/527, loss: 0.00084322300972417
2023-01-24 08:34:49.087582: step: 572/527, loss: 0.0023775636218488216
2023-01-24 08:34:50.145963: step: 576/527, loss: 0.0017343329964205623
2023-01-24 08:34:51.190536: step: 580/527, loss: 0.004927433095872402
2023-01-24 08:34:52.233057: step: 584/527, loss: 0.013437094166874886
2023-01-24 08:34:53.278603: step: 588/527, loss: 1.7793741790228523e-05
2023-01-24 08:34:54.356848: step: 592/527, loss: 0.0005915320361964405
2023-01-24 08:34:55.409883: step: 596/527, loss: 0.00019877108570653945
2023-01-24 08:34:56.455598: step: 600/527, loss: 2.1326741261873394e-06
2023-01-24 08:34:57.505112: step: 604/527, loss: 0.00016095442697405815
2023-01-24 08:34:58.560789: step: 608/527, loss: 0.0004485376994125545
2023-01-24 08:34:59.616486: step: 612/527, loss: 0.0027129605878144503
2023-01-24 08:35:00.674426: step: 616/527, loss: 0.03259887173771858
2023-01-24 08:35:01.713532: step: 620/527, loss: 0.00031563080847263336
2023-01-24 08:35:02.757544: step: 624/527, loss: 0.0004695482784882188
2023-01-24 08:35:03.800410: step: 628/527, loss: 0.0002783761010505259
2023-01-24 08:35:04.860118: step: 632/527, loss: 0.0011548263719305396
2023-01-24 08:35:05.912563: step: 636/527, loss: 0.0016849065432325006
2023-01-24 08:35:06.974256: step: 640/527, loss: 2.7085836336482316e-05
2023-01-24 08:35:08.024104: step: 644/527, loss: 0.0014276590663939714
2023-01-24 08:35:09.071816: step: 648/527, loss: 5.37309460924007e-05
2023-01-24 08:35:10.125123: step: 652/527, loss: 0.007701796945184469
2023-01-24 08:35:11.167503: step: 656/527, loss: 2.6031635570689104e-05
2023-01-24 08:35:12.223401: step: 660/527, loss: 0.0036622625775635242
2023-01-24 08:35:13.269071: step: 664/527, loss: 0.00011755112063838169
2023-01-24 08:35:14.316833: step: 668/527, loss: 0.0024309426080435514
2023-01-24 08:35:15.363203: step: 672/527, loss: 0.0012158105382695794
2023-01-24 08:35:16.414569: step: 676/527, loss: 2.2279873519437388e-05
2023-01-24 08:35:17.473289: step: 680/527, loss: 0.0004120093653909862
2023-01-24 08:35:18.522277: step: 684/527, loss: 3.1589790978614474e-06
2023-01-24 08:35:19.567133: step: 688/527, loss: 4.0119130062521435e-06
2023-01-24 08:35:20.627535: step: 692/527, loss: 0.050491150468587875
2023-01-24 08:35:21.675258: step: 696/527, loss: 0.0008703861385583878
2023-01-24 08:35:22.707310: step: 700/527, loss: 6.0658403526758775e-06
2023-01-24 08:35:23.753204: step: 704/527, loss: 0.001171291689388454
2023-01-24 08:35:24.794096: step: 708/527, loss: 0.00017714528075885028
2023-01-24 08:35:25.856110: step: 712/527, loss: 0.0013673767680302262
2023-01-24 08:35:26.916116: step: 716/527, loss: 1.5917910786811262e-05
2023-01-24 08:35:27.951369: step: 720/527, loss: 9.810196206672117e-05
2023-01-24 08:35:29.002758: step: 724/527, loss: 0.0015008054906502366
2023-01-24 08:35:30.053415: step: 728/527, loss: 0.00011717055895132944
2023-01-24 08:35:31.096014: step: 732/527, loss: 0.007250685710459948
2023-01-24 08:35:32.154905: step: 736/527, loss: 0.0011059186654165387
2023-01-24 08:35:33.199439: step: 740/527, loss: 0.00849692989140749
2023-01-24 08:35:34.262952: step: 744/527, loss: 0.010815619491040707
2023-01-24 08:35:35.310113: step: 748/527, loss: 5.814937139803078e-06
2023-01-24 08:35:36.371236: step: 752/527, loss: 0.0013137535424903035
2023-01-24 08:35:37.437969: step: 756/527, loss: 0.0046137734316289425
2023-01-24 08:35:38.500271: step: 760/527, loss: 0.002077428624033928
2023-01-24 08:35:39.556403: step: 764/527, loss: 6.667820002803637e-07
2023-01-24 08:35:40.596433: step: 768/527, loss: 5.586838233284652e-05
2023-01-24 08:35:41.654872: step: 772/527, loss: 0.0035405403468757868
2023-01-24 08:35:42.709145: step: 776/527, loss: 0.0010661783162504435
2023-01-24 08:35:43.752948: step: 780/527, loss: 0.0040255035273730755
2023-01-24 08:35:44.823729: step: 784/527, loss: 0.0009912264067679644
2023-01-24 08:35:45.873257: step: 788/527, loss: 0.001652727136388421
2023-01-24 08:35:46.926929: step: 792/527, loss: 0.012306630611419678
2023-01-24 08:35:47.988070: step: 796/527, loss: 0.00010299119458068162
2023-01-24 08:35:49.037643: step: 800/527, loss: 0.002049674978479743
2023-01-24 08:35:50.091412: step: 804/527, loss: 0.0006292650941759348
2023-01-24 08:35:51.150501: step: 808/527, loss: 0.0022838767617940903
2023-01-24 08:35:52.194868: step: 812/527, loss: 0.0011064389254897833
2023-01-24 08:35:53.247718: step: 816/527, loss: 0.008143662475049496
2023-01-24 08:35:54.316154: step: 820/527, loss: 0.0031659628730267286
2023-01-24 08:35:55.359242: step: 824/527, loss: 0.0007954881293699145
2023-01-24 08:35:56.397020: step: 828/527, loss: 0.003833244787529111
2023-01-24 08:35:57.442574: step: 832/527, loss: 0.00012441465514712036
2023-01-24 08:35:58.515223: step: 836/527, loss: 0.011709059588611126
2023-01-24 08:35:59.572579: step: 840/527, loss: 0.0006156121380627155
2023-01-24 08:36:00.613877: step: 844/527, loss: 0.0008509125909768045
2023-01-24 08:36:01.660575: step: 848/527, loss: 0.002553958911448717
2023-01-24 08:36:02.701796: step: 852/527, loss: 0.0012988821836188436
2023-01-24 08:36:03.747673: step: 856/527, loss: 0.001448391703888774
2023-01-24 08:36:04.785687: step: 860/527, loss: 0.005387177225202322
2023-01-24 08:36:05.843786: step: 864/527, loss: 0.0032352798152714968
2023-01-24 08:36:06.893719: step: 868/527, loss: 2.0577674149535596e-05
2023-01-24 08:36:07.970742: step: 872/527, loss: 0.006032809615135193
2023-01-24 08:36:09.017430: step: 876/527, loss: 0.00037293307832442224
2023-01-24 08:36:10.056415: step: 880/527, loss: 0.003305136226117611
2023-01-24 08:36:11.097872: step: 884/527, loss: 0.00038551806937903166
2023-01-24 08:36:12.152816: step: 888/527, loss: 4.1722552850842476e-05
2023-01-24 08:36:13.193095: step: 892/527, loss: 0.0010745628969743848
2023-01-24 08:36:14.265360: step: 896/527, loss: 0.005216544959694147
2023-01-24 08:36:15.302649: step: 900/527, loss: 0.00011049064778489992
2023-01-24 08:36:16.370833: step: 904/527, loss: 0.0010446091182529926
2023-01-24 08:36:17.426654: step: 908/527, loss: 0.0003392371581867337
2023-01-24 08:36:18.477813: step: 912/527, loss: 0.0019092380534857512
2023-01-24 08:36:19.545746: step: 916/527, loss: 0.022000303491950035
2023-01-24 08:36:20.589627: step: 920/527, loss: 0.00014837730850558728
2023-01-24 08:36:21.631823: step: 924/527, loss: 0.00032418363844044507
2023-01-24 08:36:22.675732: step: 928/527, loss: 0.0003856219700537622
2023-01-24 08:36:23.714063: step: 932/527, loss: 0.0023811610881239176
2023-01-24 08:36:24.773794: step: 936/527, loss: 0.006616069469600916
2023-01-24 08:36:25.813827: step: 940/527, loss: 0.0033610640093684196
2023-01-24 08:36:26.862003: step: 944/527, loss: 5.9387686633272097e-05
2023-01-24 08:36:27.913306: step: 948/527, loss: 0.003283826168626547
2023-01-24 08:36:28.959957: step: 952/527, loss: 1.4413566304938286e-06
2023-01-24 08:36:29.994420: step: 956/527, loss: 0.002506200922653079
2023-01-24 08:36:31.046612: step: 960/527, loss: 0.012610760517418385
2023-01-24 08:36:32.105336: step: 964/527, loss: 0.0002610202645882964
2023-01-24 08:36:33.169027: step: 968/527, loss: 0.0027775494381785393
2023-01-24 08:36:34.209471: step: 972/527, loss: 0.0091815534979105
2023-01-24 08:36:35.240684: step: 976/527, loss: 0.0007585881976410747
2023-01-24 08:36:36.305768: step: 980/527, loss: 0.0005991409416310489
2023-01-24 08:36:37.350295: step: 984/527, loss: 0.005170310381799936
2023-01-24 08:36:38.403255: step: 988/527, loss: 0.0005469053285196424
2023-01-24 08:36:39.434712: step: 992/527, loss: 6.986831380118019e-08
2023-01-24 08:36:40.504463: step: 996/527, loss: 0.0006740324315614998
2023-01-24 08:36:41.562318: step: 1000/527, loss: 0.004166469909250736
2023-01-24 08:36:42.640051: step: 1004/527, loss: 0.015780463814735413
2023-01-24 08:36:43.695588: step: 1008/527, loss: 0.0010006852680817246
2023-01-24 08:36:44.747110: step: 1012/527, loss: 0.00028155665495432913
2023-01-24 08:36:45.791817: step: 1016/527, loss: 0.0023961327970027924
2023-01-24 08:36:46.865038: step: 1020/527, loss: 0.007497671525925398
2023-01-24 08:36:47.916201: step: 1024/527, loss: 1.2643513400689699e-05
2023-01-24 08:36:48.961388: step: 1028/527, loss: 0.00046470618690364063
2023-01-24 08:36:50.030581: step: 1032/527, loss: 0.0005937237874604762
2023-01-24 08:36:51.083030: step: 1036/527, loss: 0.0007247515604831278
2023-01-24 08:36:52.137005: step: 1040/527, loss: 0.005062410607933998
2023-01-24 08:36:53.192054: step: 1044/527, loss: 0.0003088737139478326
2023-01-24 08:36:54.238187: step: 1048/527, loss: 0.003685701172798872
2023-01-24 08:36:55.282873: step: 1052/527, loss: 2.4098208086797968e-05
2023-01-24 08:36:56.341318: step: 1056/527, loss: 0.0008553850348107517
2023-01-24 08:36:57.376609: step: 1060/527, loss: 3.414911770960316e-05
2023-01-24 08:36:58.422543: step: 1064/527, loss: 0.002141993958503008
2023-01-24 08:36:59.467217: step: 1068/527, loss: 0.0014887830475345254
2023-01-24 08:37:00.508938: step: 1072/527, loss: 0.0001108280339394696
2023-01-24 08:37:01.577808: step: 1076/527, loss: 0.006828743033111095
2023-01-24 08:37:02.641208: step: 1080/527, loss: 0.0014793355949223042
2023-01-24 08:37:03.703513: step: 1084/527, loss: 0.0053122928366065025
2023-01-24 08:37:04.746423: step: 1088/527, loss: 3.907622385668219e-07
2023-01-24 08:37:05.795286: step: 1092/527, loss: 0.00038304715417325497
2023-01-24 08:37:06.840172: step: 1096/527, loss: 0.007987931370735168
2023-01-24 08:37:07.878400: step: 1100/527, loss: 0.000761221454013139
2023-01-24 08:37:08.914519: step: 1104/527, loss: 0.002285123337060213
2023-01-24 08:37:09.957586: step: 1108/527, loss: 0.00020992501231376082
2023-01-24 08:37:11.021954: step: 1112/527, loss: 0.002256684470921755
2023-01-24 08:37:12.058360: step: 1116/527, loss: 0.0017977760871872306
2023-01-24 08:37:13.107413: step: 1120/527, loss: 1.6256830349448137e-05
2023-01-24 08:37:14.160763: step: 1124/527, loss: 0.00013809015217702836
2023-01-24 08:37:15.220799: step: 1128/527, loss: 0.0009146074880845845
2023-01-24 08:37:16.260013: step: 1132/527, loss: 0.0007422657799907029
2023-01-24 08:37:17.304487: step: 1136/527, loss: 0.0015519816661253572
2023-01-24 08:37:18.346437: step: 1140/527, loss: 0.0028769036289304495
2023-01-24 08:37:19.396935: step: 1144/527, loss: 0.0008431297610513866
2023-01-24 08:37:20.454042: step: 1148/527, loss: 0.004372154828161001
2023-01-24 08:37:21.490948: step: 1152/527, loss: 0.004091321956366301
2023-01-24 08:37:22.550711: step: 1156/527, loss: 0.0028877772856503725
2023-01-24 08:37:23.618410: step: 1160/527, loss: 0.004787031561136246
2023-01-24 08:37:24.660047: step: 1164/527, loss: 0.00459287641569972
2023-01-24 08:37:25.701061: step: 1168/527, loss: 0.0001046439865604043
2023-01-24 08:37:26.744745: step: 1172/527, loss: 0.0019880258478224277
2023-01-24 08:37:27.805616: step: 1176/527, loss: 0.0023924100678414106
2023-01-24 08:37:28.865331: step: 1180/527, loss: 0.0019450971158221364
2023-01-24 08:37:29.918328: step: 1184/527, loss: 0.003473397344350815
2023-01-24 08:37:30.954008: step: 1188/527, loss: 0.0009338706149719656
2023-01-24 08:37:31.994086: step: 1192/527, loss: 0.0057705966755747795
2023-01-24 08:37:33.054927: step: 1196/527, loss: 0.0032657638657838106
2023-01-24 08:37:34.091690: step: 1200/527, loss: 0.0001672745420364663
2023-01-24 08:37:35.145982: step: 1204/527, loss: 4.521968730841763e-05
2023-01-24 08:37:36.195960: step: 1208/527, loss: 0.0006788073224015534
2023-01-24 08:37:37.245697: step: 1212/527, loss: 0.0013681717682629824
2023-01-24 08:37:38.286657: step: 1216/527, loss: 0.00452857231721282
2023-01-24 08:37:39.344059: step: 1220/527, loss: 0.0027870971243828535
2023-01-24 08:37:40.404732: step: 1224/527, loss: 0.0003170997661072761
2023-01-24 08:37:41.468988: step: 1228/527, loss: 0.004468757193535566
2023-01-24 08:37:42.513828: step: 1232/527, loss: 0.005184211768209934
2023-01-24 08:37:43.569685: step: 1236/527, loss: 0.008863546885550022
2023-01-24 08:37:44.613083: step: 1240/527, loss: 0.0035912180319428444
2023-01-24 08:37:45.660126: step: 1244/527, loss: 4.855155566474423e-06
2023-01-24 08:37:46.702262: step: 1248/527, loss: 0.00031607714481651783
2023-01-24 08:37:47.747497: step: 1252/527, loss: 0.011201917193830013
2023-01-24 08:37:48.792078: step: 1256/527, loss: 0.0002935648080892861
2023-01-24 08:37:49.843971: step: 1260/527, loss: 0.004082835279405117
2023-01-24 08:37:50.898801: step: 1264/527, loss: 0.00207423884421587
2023-01-24 08:37:51.935802: step: 1268/527, loss: 3.5839930205838755e-05
2023-01-24 08:37:52.973641: step: 1272/527, loss: 0.0013217636151239276
2023-01-24 08:37:54.023736: step: 1276/527, loss: 0.005046289414167404
2023-01-24 08:37:55.064315: step: 1280/527, loss: 0.007760475389659405
2023-01-24 08:37:56.117614: step: 1284/527, loss: 0.0017032703617587686
2023-01-24 08:37:57.163895: step: 1288/527, loss: 0.0016244613798335195
2023-01-24 08:37:58.206377: step: 1292/527, loss: 0.0006418933044187725
2023-01-24 08:37:59.258448: step: 1296/527, loss: 0.0006541475304402411
2023-01-24 08:38:00.351303: step: 1300/527, loss: 3.2418229238828644e-05
2023-01-24 08:38:01.407685: step: 1304/527, loss: 0.006008618976920843
2023-01-24 08:38:02.441223: step: 1308/527, loss: 1.408158459526021e-05
2023-01-24 08:38:03.502617: step: 1312/527, loss: 0.006421650294214487
2023-01-24 08:38:04.593133: step: 1316/527, loss: 0.0005681291804648936
2023-01-24 08:38:05.646730: step: 1320/527, loss: 0.0045060706324875355
2023-01-24 08:38:06.711917: step: 1324/527, loss: 0.000765451870393008
2023-01-24 08:38:07.758889: step: 1328/527, loss: 0.0011825101682916284
2023-01-24 08:38:08.809960: step: 1332/527, loss: 0.00046062367619015276
2023-01-24 08:38:09.856409: step: 1336/527, loss: 0.001797602977603674
2023-01-24 08:38:10.903790: step: 1340/527, loss: 0.000636327313259244
2023-01-24 08:38:11.960523: step: 1344/527, loss: 0.005077186971902847
2023-01-24 08:38:13.011849: step: 1348/527, loss: 0.0006306004361249506
2023-01-24 08:38:14.060372: step: 1352/527, loss: 0.0021776664070785046
2023-01-24 08:38:15.119434: step: 1356/527, loss: 0.005362347699701786
2023-01-24 08:38:16.165547: step: 1360/527, loss: 0.0010280520655214787
2023-01-24 08:38:17.210050: step: 1364/527, loss: 0.0006861954461783171
2023-01-24 08:38:18.258926: step: 1368/527, loss: 0.0011999312555417418
2023-01-24 08:38:19.307238: step: 1372/527, loss: 5.817090641357936e-05
2023-01-24 08:38:20.368400: step: 1376/527, loss: 0.008044160902500153
2023-01-24 08:38:21.410997: step: 1380/527, loss: 0.008972223848104477
2023-01-24 08:38:22.460201: step: 1384/527, loss: 0.0053023421205580235
2023-01-24 08:38:23.505425: step: 1388/527, loss: 0.0014283547643572092
2023-01-24 08:38:24.548492: step: 1392/527, loss: 0.0010214076610282063
2023-01-24 08:38:25.604765: step: 1396/527, loss: 2.2226422515814193e-06
2023-01-24 08:38:26.658335: step: 1400/527, loss: 1.7482507246313617e-05
2023-01-24 08:38:27.698595: step: 1404/527, loss: 0.009437872096896172
2023-01-24 08:38:28.746187: step: 1408/527, loss: 0.00046466320054605603
2023-01-24 08:38:29.798155: step: 1412/527, loss: 0.0034083391074091196
2023-01-24 08:38:30.839811: step: 1416/527, loss: 0.0037251217290759087
2023-01-24 08:38:31.888233: step: 1420/527, loss: 1.007645005302038e-05
2023-01-24 08:38:32.934639: step: 1424/527, loss: 0.031078273430466652
2023-01-24 08:38:33.984920: step: 1428/527, loss: 0.0002833573380485177
2023-01-24 08:38:35.034937: step: 1432/527, loss: 0.0001809260866139084
2023-01-24 08:38:36.096900: step: 1436/527, loss: 0.0010621907422319055
2023-01-24 08:38:37.134005: step: 1440/527, loss: 0.00285606412217021
2023-01-24 08:38:38.185529: step: 1444/527, loss: 0.0023035320919007063
2023-01-24 08:38:39.242605: step: 1448/527, loss: 0.0015488736098632216
2023-01-24 08:38:40.300377: step: 1452/527, loss: 0.004599835257977247
2023-01-24 08:38:41.344427: step: 1456/527, loss: 0.00031104570371098816
2023-01-24 08:38:42.405848: step: 1460/527, loss: 0.0003392311336938292
2023-01-24 08:38:43.467550: step: 1464/527, loss: 0.005277723539620638
2023-01-24 08:38:44.507897: step: 1468/527, loss: 0.0029554502107203007
2023-01-24 08:38:45.553327: step: 1472/527, loss: 0.007661787327378988
2023-01-24 08:38:46.600217: step: 1476/527, loss: 0.001034824294038117
2023-01-24 08:38:47.667889: step: 1480/527, loss: 0.0006689594592899084
2023-01-24 08:38:48.710520: step: 1484/527, loss: 0.0005348111735656857
2023-01-24 08:38:49.795674: step: 1488/527, loss: 0.0002198615693487227
2023-01-24 08:38:50.853646: step: 1492/527, loss: 0.004154730122536421
2023-01-24 08:38:51.909431: step: 1496/527, loss: 0.001539296586997807
2023-01-24 08:38:52.945237: step: 1500/527, loss: 0.0052877916023135185
2023-01-24 08:38:53.991472: step: 1504/527, loss: 0.0005687348893843591
2023-01-24 08:38:55.027721: step: 1508/527, loss: 0.001015132642351091
2023-01-24 08:38:56.089280: step: 1512/527, loss: 0.005576721392571926
2023-01-24 08:38:57.134528: step: 1516/527, loss: 0.004879264626652002
2023-01-24 08:38:58.189107: step: 1520/527, loss: 2.0850655346293934e-05
2023-01-24 08:38:59.237540: step: 1524/527, loss: 1.3965835023554973e-05
2023-01-24 08:39:00.263201: step: 1528/527, loss: 7.156129140639678e-05
2023-01-24 08:39:01.313975: step: 1532/527, loss: 0.005885554477572441
2023-01-24 08:39:02.372075: step: 1536/527, loss: 0.0009074464906007051
2023-01-24 08:39:03.417201: step: 1540/527, loss: 0.000120040203910321
2023-01-24 08:39:04.459340: step: 1544/527, loss: 0.0029545798897743225
2023-01-24 08:39:05.528556: step: 1548/527, loss: 0.0016912698047235608
2023-01-24 08:39:06.565323: step: 1552/527, loss: 0.0014268854865804315
2023-01-24 08:39:07.613279: step: 1556/527, loss: 0.0007121383096091449
2023-01-24 08:39:08.644439: step: 1560/527, loss: 0.00015426863683387637
2023-01-24 08:39:09.681437: step: 1564/527, loss: 0.0033097732812166214
2023-01-24 08:39:10.720055: step: 1568/527, loss: 0.00015040584548842162
2023-01-24 08:39:11.798508: step: 1572/527, loss: 0.0015933648683130741
2023-01-24 08:39:12.851718: step: 1576/527, loss: 6.192333239596337e-05
2023-01-24 08:39:13.894749: step: 1580/527, loss: 0.004694094881415367
2023-01-24 08:39:14.932346: step: 1584/527, loss: 1.016172973322682e-06
2023-01-24 08:39:16.003156: step: 1588/527, loss: 0.006731739267706871
2023-01-24 08:39:17.043912: step: 1592/527, loss: 0.004267525393515825
2023-01-24 08:39:18.093365: step: 1596/527, loss: 0.002919580554589629
2023-01-24 08:39:19.127618: step: 1600/527, loss: 2.624107764859218e-05
2023-01-24 08:39:20.189277: step: 1604/527, loss: 0.0014190643560141325
2023-01-24 08:39:21.224769: step: 1608/527, loss: 0.005656504072248936
2023-01-24 08:39:22.284053: step: 1612/527, loss: 0.002449168125167489
2023-01-24 08:39:23.328401: step: 1616/527, loss: 0.00012716201308649033
2023-01-24 08:39:24.376477: step: 1620/527, loss: 0.004341351334005594
2023-01-24 08:39:25.425951: step: 1624/527, loss: 0.002037436468526721
2023-01-24 08:39:26.464936: step: 1628/527, loss: 0.0003117645683232695
2023-01-24 08:39:27.505052: step: 1632/527, loss: 0.008488630875945091
2023-01-24 08:39:28.559592: step: 1636/527, loss: 0.0006238708738237619
2023-01-24 08:39:29.614724: step: 1640/527, loss: 0.0010127301793545485
2023-01-24 08:39:30.671908: step: 1644/527, loss: 0.0006312818150036037
2023-01-24 08:39:31.733009: step: 1648/527, loss: 0.0028209786396473646
2023-01-24 08:39:32.778390: step: 1652/527, loss: 0.0011543591972440481
2023-01-24 08:39:33.830289: step: 1656/527, loss: 0.0042038727551698685
2023-01-24 08:39:34.879798: step: 1660/527, loss: 9.735648927744478e-05
2023-01-24 08:39:35.927921: step: 1664/527, loss: 0.0005225081695243716
2023-01-24 08:39:36.950570: step: 1668/527, loss: 0.0014535379596054554
2023-01-24 08:39:37.998418: step: 1672/527, loss: 0.002702996600419283
2023-01-24 08:39:39.050415: step: 1676/527, loss: 0.0007068762206472456
2023-01-24 08:39:40.104118: step: 1680/527, loss: 0.00045997535926289856
2023-01-24 08:39:41.150644: step: 1684/527, loss: 0.005568930879235268
2023-01-24 08:39:42.190799: step: 1688/527, loss: 0.0003073079860769212
2023-01-24 08:39:43.254093: step: 1692/527, loss: 0.00324672251008451
2023-01-24 08:39:44.294669: step: 1696/527, loss: 0.019653594121336937
2023-01-24 08:39:45.324575: step: 1700/527, loss: 0.0020069205202162266
2023-01-24 08:39:46.378279: step: 1704/527, loss: 4.546020500129089e-05
2023-01-24 08:39:47.415632: step: 1708/527, loss: 0.005134729202836752
2023-01-24 08:39:48.472116: step: 1712/527, loss: 0.0071292417123913765
2023-01-24 08:39:49.542356: step: 1716/527, loss: 0.0008487878949381411
2023-01-24 08:39:50.598253: step: 1720/527, loss: 0.0006661211373284459
2023-01-24 08:39:51.633406: step: 1724/527, loss: 1.3112735075537785e-07
2023-01-24 08:39:52.684218: step: 1728/527, loss: 0.0023526421282440424
2023-01-24 08:39:53.744150: step: 1732/527, loss: 0.00288003240711987
2023-01-24 08:39:54.793149: step: 1736/527, loss: 0.003220154670998454
2023-01-24 08:39:55.838072: step: 1740/527, loss: 0.00033792390604503453
2023-01-24 08:39:56.912923: step: 1744/527, loss: 0.0013501038774847984
2023-01-24 08:39:57.981216: step: 1748/527, loss: 0.0032438391353935003
2023-01-24 08:39:59.015161: step: 1752/527, loss: 0.0019076818134635687
2023-01-24 08:40:00.078286: step: 1756/527, loss: 0.0029315834399312735
2023-01-24 08:40:01.129843: step: 1760/527, loss: 0.005770647898316383
2023-01-24 08:40:02.168848: step: 1764/527, loss: 0.0015866488683968782
2023-01-24 08:40:03.205421: step: 1768/527, loss: 0.0017280466854572296
2023-01-24 08:40:04.235689: step: 1772/527, loss: 0.00023242375755216926
2023-01-24 08:40:05.311047: step: 1776/527, loss: 0.0003622903604991734
2023-01-24 08:40:06.373401: step: 1780/527, loss: 0.0002585754555184394
2023-01-24 08:40:07.415892: step: 1784/527, loss: 1.1205937653357978e-06
2023-01-24 08:40:08.466281: step: 1788/527, loss: 0.0006304820999503136
2023-01-24 08:40:09.514002: step: 1792/527, loss: 3.418372943997383e-05
2023-01-24 08:40:10.560840: step: 1796/527, loss: 0.0012672650627791882
2023-01-24 08:40:11.625972: step: 1800/527, loss: 0.0007200216059572995
2023-01-24 08:40:12.663121: step: 1804/527, loss: 0.00011137048568343744
2023-01-24 08:40:13.713379: step: 1808/527, loss: 5.687983843927213e-07
2023-01-24 08:40:14.769831: step: 1812/527, loss: 0.006658437196165323
2023-01-24 08:40:15.827304: step: 1816/527, loss: 0.00527238380163908
2023-01-24 08:40:16.887843: step: 1820/527, loss: 0.00021178860333748162
2023-01-24 08:40:17.932586: step: 1824/527, loss: 0.003967908676713705
2023-01-24 08:40:18.972049: step: 1828/527, loss: 0.005592267494648695
2023-01-24 08:40:20.031718: step: 1832/527, loss: 0.0018116970313712955
2023-01-24 08:40:21.090222: step: 1836/527, loss: 0.01934591494500637
2023-01-24 08:40:22.141037: step: 1840/527, loss: 0.0032278557773679495
2023-01-24 08:40:23.191597: step: 1844/527, loss: 0.002874411642551422
2023-01-24 08:40:24.217286: step: 1848/527, loss: 0.00033622575574554503
2023-01-24 08:40:25.266752: step: 1852/527, loss: 0.00011412279127398506
2023-01-24 08:40:26.306370: step: 1856/527, loss: 8.078530663624406e-05
2023-01-24 08:40:27.339627: step: 1860/527, loss: 0.000843316491227597
2023-01-24 08:40:28.383214: step: 1864/527, loss: 0.0012733396142721176
2023-01-24 08:40:29.443411: step: 1868/527, loss: 1.2450468602764886e-05
2023-01-24 08:40:30.480259: step: 1872/527, loss: 2.2452379198512062e-05
2023-01-24 08:40:31.546682: step: 1876/527, loss: 0.00019721922581084073
2023-01-24 08:40:32.586964: step: 1880/527, loss: 7.26453508832492e-05
2023-01-24 08:40:33.658206: step: 1884/527, loss: 0.003527124645188451
2023-01-24 08:40:34.712487: step: 1888/527, loss: 0.003966258838772774
2023-01-24 08:40:35.760936: step: 1892/527, loss: 0.0007713859085924923
2023-01-24 08:40:36.814477: step: 1896/527, loss: 6.938435399206355e-05
2023-01-24 08:40:37.866731: step: 1900/527, loss: 0.004803159739822149
2023-01-24 08:40:38.921608: step: 1904/527, loss: 0.005313303787261248
2023-01-24 08:40:39.989835: step: 1908/527, loss: 0.0019289851188659668
2023-01-24 08:40:41.020732: step: 1912/527, loss: 0.00029375249869190156
2023-01-24 08:40:42.088082: step: 1916/527, loss: 0.004166670609265566
2023-01-24 08:40:43.129116: step: 1920/527, loss: 0.002013293793424964
2023-01-24 08:40:44.193914: step: 1924/527, loss: 0.0016988266725093126
2023-01-24 08:40:45.256192: step: 1928/527, loss: 0.013844682835042477
2023-01-24 08:40:46.289012: step: 1932/527, loss: 0.00011055077629862353
2023-01-24 08:40:47.331265: step: 1936/527, loss: 0.0004986055428162217
2023-01-24 08:40:48.382739: step: 1940/527, loss: 0.010252727195620537
2023-01-24 08:40:49.447663: step: 1944/527, loss: 0.0001969645672943443
2023-01-24 08:40:50.494502: step: 1948/527, loss: 0.002018288942053914
2023-01-24 08:40:51.547598: step: 1952/527, loss: 0.0037547845859080553
2023-01-24 08:40:52.603885: step: 1956/527, loss: 0.006840241141617298
2023-01-24 08:40:53.669371: step: 1960/527, loss: 0.0001857568131526932
2023-01-24 08:40:54.718498: step: 1964/527, loss: 0.0017966602463275194
2023-01-24 08:40:55.755055: step: 1968/527, loss: 5.301878900354495e-06
2023-01-24 08:40:56.795460: step: 1972/527, loss: 0.004468115046620369
2023-01-24 08:40:57.848576: step: 1976/527, loss: 0.0003128977259621024
2023-01-24 08:40:58.881796: step: 1980/527, loss: 0.0002397177304374054
2023-01-24 08:40:59.964898: step: 1984/527, loss: 2.9411758077912964e-05
2023-01-24 08:41:01.025038: step: 1988/527, loss: 0.0008412637980654836
2023-01-24 08:41:02.086157: step: 1992/527, loss: 0.0022850714158266783
2023-01-24 08:41:03.142810: step: 1996/527, loss: 0.005549891386181116
2023-01-24 08:41:04.200131: step: 2000/527, loss: 2.835552550095599e-05
2023-01-24 08:41:05.253659: step: 2004/527, loss: 0.0046391962096095085
2023-01-24 08:41:06.293852: step: 2008/527, loss: 0.0006525303469970822
2023-01-24 08:41:07.342297: step: 2012/527, loss: 0.002201656810939312
2023-01-24 08:41:08.371157: step: 2016/527, loss: 0.0007904057274572551
2023-01-24 08:41:09.420061: step: 2020/527, loss: 0.0010330856312066317
2023-01-24 08:41:10.476240: step: 2024/527, loss: 0.0034384645987302065
2023-01-24 08:41:11.523485: step: 2028/527, loss: 0.00357083510607481
2023-01-24 08:41:12.572140: step: 2032/527, loss: 0.0002955727686639875
2023-01-24 08:41:13.630815: step: 2036/527, loss: 0.00017469891463406384
2023-01-24 08:41:14.689511: step: 2040/527, loss: 8.343283116118982e-05
2023-01-24 08:41:15.741682: step: 2044/527, loss: 0.0060574873350560665
2023-01-24 08:41:16.776918: step: 2048/527, loss: 0.0006648603593930602
2023-01-24 08:41:17.833220: step: 2052/527, loss: 0.0028812591917812824
2023-01-24 08:41:18.874459: step: 2056/527, loss: 3.7751582567580044e-05
2023-01-24 08:41:19.947200: step: 2060/527, loss: 6.585026312677655e-06
2023-01-24 08:41:21.002062: step: 2064/527, loss: 7.432147685904056e-05
2023-01-24 08:41:22.036545: step: 2068/527, loss: 0.0036748573184013367
2023-01-24 08:41:23.070057: step: 2072/527, loss: 2.025092726398725e-05
2023-01-24 08:41:24.121859: step: 2076/527, loss: 1.7522803318570368e-05
2023-01-24 08:41:25.172254: step: 2080/527, loss: 0.0021762517280876637
2023-01-24 08:41:26.225941: step: 2084/527, loss: 0.012593290768563747
2023-01-24 08:41:27.273438: step: 2088/527, loss: 0.00239157909527421
2023-01-24 08:41:28.326512: step: 2092/527, loss: 0.009583374485373497
2023-01-24 08:41:29.374568: step: 2096/527, loss: 0.0018814709037542343
2023-01-24 08:41:30.415360: step: 2100/527, loss: 0.0006606135866604745
2023-01-24 08:41:31.480302: step: 2104/527, loss: 0.0029243845492601395
2023-01-24 08:41:32.533676: step: 2108/527, loss: 0.0023297909647226334
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34055361869843204, 'r': 0.32375211189357583, 'f1': 0.33194039487921095}, 'combined': 0.24458765938468174, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.37172433313932884, 'r': 0.2902829110606213, 'f1': 0.32599408082356657}, 'combined': 0.20863621172708258, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3539907460960092, 'r': 0.33182434264028193, 'f1': 0.3425493213935917}, 'combined': 0.2524047631321202, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3728190171485725, 'r': 0.30238635995792484, 'f1': 0.3339291698231447}, 'combined': 0.21371466868681258, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3658576467365249, 'r': 0.3269809328518088, 'f1': 0.34532856034649945}, 'combined': 0.2544526234132101, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.388109906451237, 'r': 0.3123984023668571, 'f1': 0.3461626741378205}, 'combined': 0.24819210598560715, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34990019960079843, 'r': 0.33263757115749526, 'f1': 0.34105058365758756}, 'combined': 0.25130043006348557, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.35790717366614877, 'r': 0.30036896318575973, 'f1': 0.32662343552347795}, 'combined': 0.20903899873502585, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3611111111111111, 'r': 0.42391304347826086, 'f1': 0.39}, 'combined': 0.195, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3658576467365249, 'r': 0.3269809328518088, 'f1': 0.34532856034649945}, 'combined': 0.2544526234132101, 'stategy': 1, 'epoch': 18}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.388109906451237, 'r': 0.3123984023668571, 'f1': 0.3461626741378205}, 'combined': 0.24819210598560715, 'stategy': 1, 'epoch': 18}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, '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
2023-01-24 08:44:05.847842: step: 4/527, loss: 0.0012393163051456213
2023-01-24 08:44:06.881243: step: 8/527, loss: 0.001668137963861227
2023-01-24 08:44:07.928046: step: 12/527, loss: 0.0013730472419410944
2023-01-24 08:44:08.975719: step: 16/527, loss: 0.0001025743258651346
2023-01-24 08:44:10.014033: step: 20/527, loss: 0.005866795778274536
2023-01-24 08:44:11.066496: step: 24/527, loss: 0.0011849747970700264
2023-01-24 08:44:12.095258: step: 28/527, loss: 0.00010535146429901943
2023-01-24 08:44:13.150531: step: 32/527, loss: 0.0010365002090111375
2023-01-24 08:44:14.194610: step: 36/527, loss: 0.0003773421049118042
2023-01-24 08:44:15.244511: step: 40/527, loss: 0.00015154900029301643
2023-01-24 08:44:16.288529: step: 44/527, loss: 0.0026596004609018564
2023-01-24 08:44:17.347056: step: 48/527, loss: 0.0011559603735804558
2023-01-24 08:44:18.393759: step: 52/527, loss: 0.0005941126146353781
2023-01-24 08:44:19.458749: step: 56/527, loss: 8.071144111454487e-05
2023-01-24 08:44:20.504714: step: 60/527, loss: 0.00029380040359683335
2023-01-24 08:44:21.547613: step: 64/527, loss: 0.0012946843635290861
2023-01-24 08:44:22.583466: step: 68/527, loss: 0.0021294057369232178
2023-01-24 08:44:23.634750: step: 72/527, loss: 0.003071783110499382
2023-01-24 08:44:24.699210: step: 76/527, loss: 0.00020624000171665102
2023-01-24 08:44:25.734317: step: 80/527, loss: 1.1482097761472687e-05
2023-01-24 08:44:26.771504: step: 84/527, loss: 4.327096030465327e-05
2023-01-24 08:44:27.832933: step: 88/527, loss: 0.006353351287543774
2023-01-24 08:44:28.887143: step: 92/527, loss: 0.001649137120693922
2023-01-24 08:44:29.930148: step: 96/527, loss: 0.003263617865741253
2023-01-24 08:44:30.969486: step: 100/527, loss: 6.91613831804716e-06
2023-01-24 08:44:32.032433: step: 104/527, loss: 0.001814564922824502
2023-01-24 08:44:33.069232: step: 108/527, loss: 0.00041870994027704
2023-01-24 08:44:34.111385: step: 112/527, loss: 2.533192144937857e-08
2023-01-24 08:44:35.161960: step: 116/527, loss: 6.717953510815278e-05
2023-01-24 08:44:36.208670: step: 120/527, loss: 0.0004616727528627962
2023-01-24 08:44:37.270042: step: 124/527, loss: 2.3032212993712164e-05
2023-01-24 08:44:38.316501: step: 128/527, loss: 0.00010797198774525896
2023-01-24 08:44:39.365150: step: 132/527, loss: 0.0011410361621528864
2023-01-24 08:44:40.416539: step: 136/527, loss: 6.943832704564556e-05
2023-01-24 08:44:41.483823: step: 140/527, loss: 0.00871986709535122
2023-01-24 08:44:42.543962: step: 144/527, loss: 0.007103199139237404
2023-01-24 08:44:43.593678: step: 148/527, loss: 0.0017820658395066857
2023-01-24 08:44:44.633711: step: 152/527, loss: 0.0008899192907847464
2023-01-24 08:44:45.671848: step: 156/527, loss: 0.001032595057040453
2023-01-24 08:44:46.715270: step: 160/527, loss: 0.006584180053323507
2023-01-24 08:44:47.794291: step: 164/527, loss: 0.022114116698503494
2023-01-24 08:44:48.873737: step: 168/527, loss: 2.8217245926498435e-05
2023-01-24 08:44:49.939841: step: 172/527, loss: 5.427113501355052e-05
2023-01-24 08:44:50.983302: step: 176/527, loss: 0.005832976195961237
2023-01-24 08:44:52.058047: step: 180/527, loss: 0.0005348074482753873
2023-01-24 08:44:53.115195: step: 184/527, loss: 0.0005475258803926408
2023-01-24 08:44:54.155899: step: 188/527, loss: 0.0034367882180958986
2023-01-24 08:44:55.209772: step: 192/527, loss: 0.01249935757368803
2023-01-24 08:44:56.249835: step: 196/527, loss: 0.003440217347815633
2023-01-24 08:44:57.299137: step: 200/527, loss: 0.0019034104188904166
2023-01-24 08:44:58.348873: step: 204/527, loss: 0.0001961662492249161
2023-01-24 08:44:59.391402: step: 208/527, loss: 0.00039003996062092483
2023-01-24 08:45:00.462121: step: 212/527, loss: 0.00047087660641409457
2023-01-24 08:45:01.512217: step: 216/527, loss: 0.0008117057150229812
2023-01-24 08:45:02.557708: step: 220/527, loss: 3.443819451831587e-08
2023-01-24 08:45:03.596323: step: 224/527, loss: 0.00013562387903220952
2023-01-24 08:45:04.649377: step: 228/527, loss: 4.772007741848938e-05
2023-01-24 08:45:05.699480: step: 232/527, loss: 0.001068068784661591
2023-01-24 08:45:06.741046: step: 236/527, loss: 0.003395429579541087
2023-01-24 08:45:07.783158: step: 240/527, loss: 3.142968125757761e-05
2023-01-24 08:45:08.836649: step: 244/527, loss: 0.0021795129869133234
2023-01-24 08:45:09.871648: step: 248/527, loss: 0.002297371858730912
2023-01-24 08:45:10.947920: step: 252/527, loss: 0.0033480070997029543
2023-01-24 08:45:12.013511: step: 256/527, loss: 0.0017592310905456543
2023-01-24 08:45:13.079165: step: 260/527, loss: 0.001415460603311658
2023-01-24 08:45:14.121122: step: 264/527, loss: 0.00047951177111826837
2023-01-24 08:45:15.159893: step: 268/527, loss: 0.0005498563405126333
2023-01-24 08:45:16.203865: step: 272/527, loss: 0.0012244456447660923
2023-01-24 08:45:17.243774: step: 276/527, loss: 0.000846775365062058
2023-01-24 08:45:18.289448: step: 280/527, loss: 0.00033961687586270273
2023-01-24 08:45:19.332374: step: 284/527, loss: 0.0019173154141753912
2023-01-24 08:45:20.389824: step: 288/527, loss: 0.0016494457377120852
2023-01-24 08:45:21.451513: step: 292/527, loss: 0.009514926932752132
2023-01-24 08:45:22.509119: step: 296/527, loss: 0.00250768824480474
2023-01-24 08:45:23.550432: step: 300/527, loss: 6.756501534255221e-05
2023-01-24 08:45:24.592627: step: 304/527, loss: 0.005551945883780718
2023-01-24 08:45:25.644590: step: 308/527, loss: 0.000883370463270694
2023-01-24 08:45:26.706037: step: 312/527, loss: 0.0013449033722281456
2023-01-24 08:45:27.765045: step: 316/527, loss: 0.002774510532617569
2023-01-24 08:45:28.829516: step: 320/527, loss: 0.0018426378956064582
2023-01-24 08:45:29.877534: step: 324/527, loss: 0.005076187662780285
2023-01-24 08:45:30.920126: step: 328/527, loss: 0.0018949778750538826
2023-01-24 08:45:31.956594: step: 332/527, loss: 0.00202022772282362
2023-01-24 08:45:33.017795: step: 336/527, loss: 0.004244535695761442
2023-01-24 08:45:34.060321: step: 340/527, loss: 0.01657724380493164
2023-01-24 08:45:35.097685: step: 344/527, loss: 0.000595480902120471
2023-01-24 08:45:36.135684: step: 348/527, loss: 0.002139325486496091
2023-01-24 08:45:37.179237: step: 352/527, loss: 0.002683040453121066
2023-01-24 08:45:38.243079: step: 356/527, loss: 0.0012539754388853908
2023-01-24 08:45:39.301593: step: 360/527, loss: 0.00020126922754570842
2023-01-24 08:45:40.359724: step: 364/527, loss: 0.000298401020700112
2023-01-24 08:45:41.406734: step: 368/527, loss: 9.195306483888999e-05
2023-01-24 08:45:42.477536: step: 372/527, loss: 0.0031211546156555414
2023-01-24 08:45:43.535055: step: 376/527, loss: 0.005753985606133938
2023-01-24 08:45:44.579193: step: 380/527, loss: 0.002090310677886009
2023-01-24 08:45:45.630226: step: 384/527, loss: 0.0022221228573471308
2023-01-24 08:45:46.673835: step: 388/527, loss: 0.0011999725829809904
2023-01-24 08:45:47.715594: step: 392/527, loss: 0.0005783041706308722
2023-01-24 08:45:48.755944: step: 396/527, loss: 0.00258005247451365
2023-01-24 08:45:49.800754: step: 400/527, loss: 5.942715233686613e-06
2023-01-24 08:45:50.858037: step: 404/527, loss: 0.0026857468765228987
2023-01-24 08:45:51.925212: step: 408/527, loss: 0.0059359935112297535
2023-01-24 08:45:53.002317: step: 412/527, loss: 0.0042375195771455765
2023-01-24 08:45:54.052059: step: 416/527, loss: 0.00048120314022526145
2023-01-24 08:45:55.093111: step: 420/527, loss: 8.708888344699517e-05
2023-01-24 08:45:56.134881: step: 424/527, loss: 0.0029994065407663584
2023-01-24 08:45:57.189663: step: 428/527, loss: 0.0015182868810370564
2023-01-24 08:45:58.239238: step: 432/527, loss: 3.7191013689152896e-05
2023-01-24 08:45:59.304929: step: 436/527, loss: 0.00016880700422916561
2023-01-24 08:46:00.354450: step: 440/527, loss: 0.0013599247904494405
2023-01-24 08:46:01.395076: step: 444/527, loss: 0.00019048615649808198
2023-01-24 08:46:02.464906: step: 448/527, loss: 0.0003872607776429504
2023-01-24 08:46:03.519652: step: 452/527, loss: 0.0013334158575162292
2023-01-24 08:46:04.577964: step: 456/527, loss: 7.332026871154085e-05
2023-01-24 08:46:05.656727: step: 460/527, loss: 0.001446189940907061
2023-01-24 08:46:06.707508: step: 464/527, loss: 0.0022368559148162603
2023-01-24 08:46:07.745701: step: 468/527, loss: 6.024682443239726e-05
2023-01-24 08:46:08.815157: step: 472/527, loss: 7.729869685135782e-05
2023-01-24 08:46:09.850042: step: 476/527, loss: 0.0002613368851598352
2023-01-24 08:46:10.903008: step: 480/527, loss: 0.006399987265467644
2023-01-24 08:46:11.954719: step: 484/527, loss: 0.007528561633080244
2023-01-24 08:46:13.022212: step: 488/527, loss: 0.0013660388067364693
2023-01-24 08:46:14.070133: step: 492/527, loss: 0.013562928885221481
2023-01-24 08:46:15.126574: step: 496/527, loss: 1.701518522168044e-05
2023-01-24 08:46:16.188361: step: 500/527, loss: 0.006754598114639521
2023-01-24 08:46:17.236972: step: 504/527, loss: 0.001777896424755454
2023-01-24 08:46:18.277389: step: 508/527, loss: 1.0649610885593574e-05
2023-01-24 08:46:19.337151: step: 512/527, loss: 0.00164675188716501
2023-01-24 08:46:20.391917: step: 516/527, loss: 0.003189191222190857
2023-01-24 08:46:21.447194: step: 520/527, loss: 0.003578462637960911
2023-01-24 08:46:22.494138: step: 524/527, loss: 5.015205715608317e-06
2023-01-24 08:46:23.534728: step: 528/527, loss: 0.003162672510370612
2023-01-24 08:46:24.602755: step: 532/527, loss: 0.004469267092645168
2023-01-24 08:46:25.654041: step: 536/527, loss: 0.0009819627739489079
2023-01-24 08:46:26.696392: step: 540/527, loss: 9.191578283207491e-05
2023-01-24 08:46:27.738896: step: 544/527, loss: 0.0013240796979516745
2023-01-24 08:46:28.786122: step: 548/527, loss: 0.0007591333123855293
2023-01-24 08:46:29.847588: step: 552/527, loss: 0.0029395802412182093
2023-01-24 08:46:30.883192: step: 556/527, loss: 4.936066034133546e-05
2023-01-24 08:46:31.929393: step: 560/527, loss: 0.004814940970391035
2023-01-24 08:46:32.981525: step: 564/527, loss: 0.0009860022692009807
2023-01-24 08:46:34.025574: step: 568/527, loss: 0.0013154047774150968
2023-01-24 08:46:35.062500: step: 572/527, loss: 0.006313377991318703
2023-01-24 08:46:36.107649: step: 576/527, loss: 0.0011334414593875408
2023-01-24 08:46:37.155988: step: 580/527, loss: 5.056536247138865e-05
2023-01-24 08:46:38.205695: step: 584/527, loss: 0.010912892408668995
2023-01-24 08:46:39.262607: step: 588/527, loss: 0.0018342194380238652
2023-01-24 08:46:40.341079: step: 592/527, loss: 0.016050726175308228
2023-01-24 08:46:41.417822: step: 596/527, loss: 0.007237738464027643
2023-01-24 08:46:42.480783: step: 600/527, loss: 0.007710401900112629
2023-01-24 08:46:43.528609: step: 604/527, loss: 0.016605515033006668
2023-01-24 08:46:44.576657: step: 608/527, loss: 0.0030788287986069918
2023-01-24 08:46:45.639602: step: 612/527, loss: 0.003960038535296917
2023-01-24 08:46:46.697495: step: 616/527, loss: 0.003155391663312912
2023-01-24 08:46:47.745615: step: 620/527, loss: 7.007442036410794e-06
2023-01-24 08:46:48.802137: step: 624/527, loss: 0.001937654335051775
2023-01-24 08:46:49.859674: step: 628/527, loss: 0.001230320893228054
2023-01-24 08:46:50.906841: step: 632/527, loss: 0.00011873915354954079
2023-01-24 08:46:51.962318: step: 636/527, loss: 0.0004122651880607009
2023-01-24 08:46:53.013645: step: 640/527, loss: 0.0002402549871476367
2023-01-24 08:46:54.063132: step: 644/527, loss: 0.0036423199344426394
2023-01-24 08:46:55.138073: step: 648/527, loss: 0.008505094796419144
2023-01-24 08:46:56.182690: step: 652/527, loss: 0.0008511111373081803
2023-01-24 08:46:57.225819: step: 656/527, loss: 0.002602958818897605
2023-01-24 08:46:58.287589: step: 660/527, loss: 0.0005923251737840474
2023-01-24 08:46:59.327200: step: 664/527, loss: 0.004444273188710213
2023-01-24 08:47:00.373950: step: 668/527, loss: 0.009440780617296696
2023-01-24 08:47:01.414741: step: 672/527, loss: 0.0002954047522507608
2023-01-24 08:47:02.485896: step: 676/527, loss: 0.003022101242095232
2023-01-24 08:47:03.538079: step: 680/527, loss: 0.01764003373682499
2023-01-24 08:47:04.590705: step: 684/527, loss: 0.004426365718245506
2023-01-24 08:47:05.626833: step: 688/527, loss: 0.0019974445458501577
2023-01-24 08:47:06.688208: step: 692/527, loss: 0.007651088293641806
2023-01-24 08:47:07.732285: step: 696/527, loss: 0.0015032695373520255
2023-01-24 08:47:08.794702: step: 700/527, loss: 0.0008799569914117455
2023-01-24 08:47:09.834221: step: 704/527, loss: 0.0004755274567287415
2023-01-24 08:47:10.870676: step: 708/527, loss: 0.0008689530077390373
2023-01-24 08:47:11.920456: step: 712/527, loss: 0.0157427079975605
2023-01-24 08:47:12.969876: step: 716/527, loss: 3.6249301047064364e-05
2023-01-24 08:47:14.026145: step: 720/527, loss: 0.0026661697775125504
2023-01-24 08:47:15.095003: step: 724/527, loss: 2.8307691536610946e-05
2023-01-24 08:47:16.149098: step: 728/527, loss: 0.0038091603200882673
2023-01-24 08:47:17.192456: step: 732/527, loss: 0.0006250269361771643
2023-01-24 08:47:18.238978: step: 736/527, loss: 0.0007497102487832308
2023-01-24 08:47:19.304682: step: 740/527, loss: 0.002172625856474042
2023-01-24 08:47:20.343056: step: 744/527, loss: 0.000501350499689579
2023-01-24 08:47:21.387492: step: 748/527, loss: 0.0019868682138621807
2023-01-24 08:47:22.443067: step: 752/527, loss: 0.0036213842686265707
2023-01-24 08:47:23.501161: step: 756/527, loss: 0.00031979562481865287
2023-01-24 08:47:24.545094: step: 760/527, loss: 0.0024259802885353565
2023-01-24 08:47:25.598612: step: 764/527, loss: 0.006235196255147457
2023-01-24 08:47:26.650337: step: 768/527, loss: 0.0011328222462907434
2023-01-24 08:47:27.701314: step: 772/527, loss: 0.00012106696522096172
2023-01-24 08:47:28.743265: step: 776/527, loss: 0.00025138421915471554
2023-01-24 08:47:29.794890: step: 780/527, loss: 0.01238225121051073
2023-01-24 08:47:30.846627: step: 784/527, loss: 0.0004550678131636232
2023-01-24 08:47:31.886326: step: 788/527, loss: 2.82932273876213e-06
2023-01-24 08:47:32.932410: step: 792/527, loss: 0.0011900421231985092
2023-01-24 08:47:33.960770: step: 796/527, loss: 6.91200839355588e-05
2023-01-24 08:47:35.020686: step: 800/527, loss: 0.004691252484917641
2023-01-24 08:47:36.079116: step: 804/527, loss: 0.0010085974354296923
2023-01-24 08:47:37.112530: step: 808/527, loss: 0.008152823895215988
2023-01-24 08:47:38.152271: step: 812/527, loss: 0.00807062815874815
2023-01-24 08:47:39.215218: step: 816/527, loss: 1.3631123692903202e-05
2023-01-24 08:47:40.244755: step: 820/527, loss: 0.005123987793922424
2023-01-24 08:47:41.290928: step: 824/527, loss: 0.0033120696898549795
2023-01-24 08:47:42.334915: step: 828/527, loss: 0.0063436562195420265
2023-01-24 08:47:43.371719: step: 832/527, loss: 6.582572677871212e-05
2023-01-24 08:47:44.416152: step: 836/527, loss: 0.00024775636848062277
2023-01-24 08:47:45.466275: step: 840/527, loss: 2.0115967913625354e-07
2023-01-24 08:47:46.523335: step: 844/527, loss: 0.00951346941292286
2023-01-24 08:47:47.584325: step: 848/527, loss: 3.1762217531650094e-06
2023-01-24 08:47:48.646808: step: 852/527, loss: 0.0008680623141117394
2023-01-24 08:47:49.703270: step: 856/527, loss: 0.0043319519609212875
2023-01-24 08:47:50.758732: step: 860/527, loss: 0.0007460839697159827
2023-01-24 08:47:51.798468: step: 864/527, loss: 9.48703373637727e-08
2023-01-24 08:47:52.847108: step: 868/527, loss: 0.0004374379350338131
2023-01-24 08:47:53.887005: step: 872/527, loss: 0.0009586404194124043
2023-01-24 08:47:54.944109: step: 876/527, loss: 0.00013020262122154236
2023-01-24 08:47:55.986924: step: 880/527, loss: 0.002522791502997279
2023-01-24 08:47:57.041989: step: 884/527, loss: 0.00538159953430295
2023-01-24 08:47:58.097445: step: 888/527, loss: 0.006419092882424593
2023-01-24 08:47:59.138110: step: 892/527, loss: 0.00014779398043174297
2023-01-24 08:48:00.176472: step: 896/527, loss: 0.0045568374916911125
2023-01-24 08:48:01.238362: step: 900/527, loss: 0.00011253288539592177
2023-01-24 08:48:02.292975: step: 904/527, loss: 0.002130964072421193
2023-01-24 08:48:03.358125: step: 908/527, loss: 0.0011638252763077617
2023-01-24 08:48:04.397019: step: 912/527, loss: 0.006363779306411743
2023-01-24 08:48:05.456975: step: 916/527, loss: 0.002493562176823616
2023-01-24 08:48:06.498172: step: 920/527, loss: 0.0005775331519544125
2023-01-24 08:48:07.546951: step: 924/527, loss: 0.004621920641511679
2023-01-24 08:48:08.592745: step: 928/527, loss: 0.0003266993735451251
2023-01-24 08:48:09.652403: step: 932/527, loss: 0.010942189954221249
2023-01-24 08:48:10.683045: step: 936/527, loss: 0.0062476713210344315
2023-01-24 08:48:11.738204: step: 940/527, loss: 8.588809578213841e-05
2023-01-24 08:48:12.772766: step: 944/527, loss: 0.002256619744002819
2023-01-24 08:48:13.825737: step: 948/527, loss: 2.1804205971420743e-05
2023-01-24 08:48:14.890691: step: 952/527, loss: 0.0013602168764919043
2023-01-24 08:48:15.930414: step: 956/527, loss: 0.006134110502898693
2023-01-24 08:48:16.969075: step: 960/527, loss: 0.0008929233299568295
2023-01-24 08:48:18.022777: step: 964/527, loss: 6.780452622479061e-06
2023-01-24 08:48:19.084215: step: 968/527, loss: 0.002485042903572321
2023-01-24 08:48:20.130133: step: 972/527, loss: 0.011737249791622162
2023-01-24 08:48:21.170492: step: 976/527, loss: 0.0009258139180019498
2023-01-24 08:48:22.237110: step: 980/527, loss: 0.0020467867143452168
2023-01-24 08:48:23.289087: step: 984/527, loss: 0.0028028034139424562
2023-01-24 08:48:24.338349: step: 988/527, loss: 5.340408733900404e-06
2023-01-24 08:48:25.389673: step: 992/527, loss: 0.0038469380233436823
2023-01-24 08:48:26.429708: step: 996/527, loss: 0.0021962637547403574
2023-01-24 08:48:27.462478: step: 1000/527, loss: 2.3065311324899085e-05
2023-01-24 08:48:28.496905: step: 1004/527, loss: 0.0004613810742739588
2023-01-24 08:48:29.555288: step: 1008/527, loss: 0.0035618823021650314
2023-01-24 08:48:30.622856: step: 1012/527, loss: 0.002384168328717351
2023-01-24 08:48:31.667757: step: 1016/527, loss: 0.0014826449332758784
2023-01-24 08:48:32.716157: step: 1020/527, loss: 0.005574486218392849
2023-01-24 08:48:33.778941: step: 1024/527, loss: 0.0006855381652712822
2023-01-24 08:48:34.840141: step: 1028/527, loss: 0.005032646469771862
2023-01-24 08:48:35.882766: step: 1032/527, loss: 0.0015608366811648011
2023-01-24 08:48:36.924407: step: 1036/527, loss: 0.001605068682692945
2023-01-24 08:48:37.987636: step: 1040/527, loss: 0.003436075057834387
2023-01-24 08:48:39.045217: step: 1044/527, loss: 0.0031761922873556614
2023-01-24 08:48:40.095613: step: 1048/527, loss: 0.0008537526009604335
2023-01-24 08:48:41.145800: step: 1052/527, loss: 1.8670356212169281e-06
2023-01-24 08:48:42.183538: step: 1056/527, loss: 0.0014661593595519662
2023-01-24 08:48:43.238950: step: 1060/527, loss: 0.000408306485041976
2023-01-24 08:48:44.306104: step: 1064/527, loss: 0.007527798414230347
2023-01-24 08:48:45.360612: step: 1068/527, loss: 0.0035662695299834013
2023-01-24 08:48:46.413711: step: 1072/527, loss: 0.00035162357380613685
2023-01-24 08:48:47.478159: step: 1076/527, loss: 0.004577164072543383
2023-01-24 08:48:48.533762: step: 1080/527, loss: 0.004323754925280809
2023-01-24 08:48:49.587652: step: 1084/527, loss: 0.0015620216727256775
2023-01-24 08:48:50.643668: step: 1088/527, loss: 0.0012194564333185554
2023-01-24 08:48:51.698786: step: 1092/527, loss: 0.0008272723644040525
2023-01-24 08:48:52.749212: step: 1096/527, loss: 0.0002586627670098096
2023-01-24 08:48:53.785618: step: 1100/527, loss: 0.0014147049514576793
2023-01-24 08:48:54.834549: step: 1104/527, loss: 0.0031121924985200167
2023-01-24 08:48:55.889492: step: 1108/527, loss: 0.0015481087611988187
2023-01-24 08:48:56.944592: step: 1112/527, loss: 0.0032255493570119143
2023-01-24 08:48:58.010503: step: 1116/527, loss: 0.00031022404436953366
2023-01-24 08:48:59.051780: step: 1120/527, loss: 2.6629679268808104e-05
2023-01-24 08:49:00.097347: step: 1124/527, loss: 6.249231955735013e-05
2023-01-24 08:49:01.140944: step: 1128/527, loss: 0.002924679545685649
2023-01-24 08:49:02.187793: step: 1132/527, loss: 7.6822210814953e-08
2023-01-24 08:49:03.243719: step: 1136/527, loss: 0.0010430047987028956
2023-01-24 08:49:04.298151: step: 1140/527, loss: 0.012654827907681465
2023-01-24 08:49:05.356664: step: 1144/527, loss: 0.000333455391228199
2023-01-24 08:49:06.404349: step: 1148/527, loss: 0.0035042453091591597
2023-01-24 08:49:07.468283: step: 1152/527, loss: 0.00010978797217831016
2023-01-24 08:49:08.500150: step: 1156/527, loss: 0.003062382573261857
2023-01-24 08:49:09.555324: step: 1160/527, loss: 0.0026928072329610586
2023-01-24 08:49:10.592166: step: 1164/527, loss: 0.006670788396149874
2023-01-24 08:49:11.624408: step: 1168/527, loss: 0.0007052342407405376
2023-01-24 08:49:12.670035: step: 1172/527, loss: 0.004666665568947792
2023-01-24 08:49:13.713474: step: 1176/527, loss: 0.0010123377433046699
2023-01-24 08:49:14.771335: step: 1180/527, loss: 0.0037816185504198074
2023-01-24 08:49:15.827765: step: 1184/527, loss: 0.0001525060215499252
2023-01-24 08:49:16.879465: step: 1188/527, loss: 0.0025169977452605963
2023-01-24 08:49:17.930152: step: 1192/527, loss: 0.00012606343079824
2023-01-24 08:49:18.985042: step: 1196/527, loss: 2.4665872842888348e-05
2023-01-24 08:49:20.053030: step: 1200/527, loss: 0.00500092888250947
2023-01-24 08:49:21.094702: step: 1204/527, loss: 0.0004313973186071962
2023-01-24 08:49:22.151157: step: 1208/527, loss: 2.3957663870532997e-05
2023-01-24 08:49:23.202951: step: 1212/527, loss: 0.0010529181454330683
2023-01-24 08:49:24.242630: step: 1216/527, loss: 0.005117418710142374
2023-01-24 08:49:25.295631: step: 1220/527, loss: 0.003962759859859943
2023-01-24 08:49:26.336362: step: 1224/527, loss: 0.002335237804800272
2023-01-24 08:49:27.381871: step: 1228/527, loss: 6.1323125919443555e-06
2023-01-24 08:49:28.404585: step: 1232/527, loss: 5.526906534214504e-06
2023-01-24 08:49:29.457669: step: 1236/527, loss: 0.0014403240056708455
2023-01-24 08:49:30.507318: step: 1240/527, loss: 0.002028381684795022
2023-01-24 08:49:31.561186: step: 1244/527, loss: 0.0
2023-01-24 08:49:32.610484: step: 1248/527, loss: 0.003549149027094245
2023-01-24 08:49:33.669508: step: 1252/527, loss: 0.0037129230331629515
2023-01-24 08:49:34.722561: step: 1256/527, loss: 9.775270882528275e-05
2023-01-24 08:49:35.752780: step: 1260/527, loss: 0.0012692835880443454
2023-01-24 08:49:36.793400: step: 1264/527, loss: 0.0012526670470833778
2023-01-24 08:49:37.847182: step: 1268/527, loss: 5.402339593274519e-05
2023-01-24 08:49:38.911303: step: 1272/527, loss: 0.0003336283261887729
2023-01-24 08:49:39.953943: step: 1276/527, loss: 0.00010477061732672155
2023-01-24 08:49:40.995096: step: 1280/527, loss: 2.9147046006983146e-05
2023-01-24 08:49:42.052644: step: 1284/527, loss: 0.0015880458522588015
2023-01-24 08:49:43.112824: step: 1288/527, loss: 0.0010953820310533047
2023-01-24 08:49:44.154139: step: 1292/527, loss: 0.005162387620657682
2023-01-24 08:49:45.209904: step: 1296/527, loss: 0.004462041892111301
2023-01-24 08:49:46.253527: step: 1300/527, loss: 6.654114258708432e-05
2023-01-24 08:49:47.312760: step: 1304/527, loss: 0.003579207230359316
2023-01-24 08:49:48.380135: step: 1308/527, loss: 0.00016542966477572918
2023-01-24 08:49:49.400103: step: 1312/527, loss: 0.002684644190594554
2023-01-24 08:49:50.454052: step: 1316/527, loss: 0.0028139713685959578
2023-01-24 08:49:51.499075: step: 1320/527, loss: 0.003680672263726592
2023-01-24 08:49:52.543271: step: 1324/527, loss: 0.0003247192653361708
2023-01-24 08:49:53.592785: step: 1328/527, loss: 0.0030806330032646656
2023-01-24 08:49:54.626518: step: 1332/527, loss: 1.2632013749680482e-05
2023-01-24 08:49:55.672190: step: 1336/527, loss: 0.004294706042855978
2023-01-24 08:49:56.709973: step: 1340/527, loss: 0.0018163361819460988
2023-01-24 08:49:57.735127: step: 1344/527, loss: 0.00025633646873757243
2023-01-24 08:49:58.802562: step: 1348/527, loss: 0.00563449552282691
2023-01-24 08:49:59.850502: step: 1352/527, loss: 0.005428878124803305
2023-01-24 08:50:00.904204: step: 1356/527, loss: 4.700622412201483e-06
2023-01-24 08:50:01.958568: step: 1360/527, loss: 0.005340092815458775
2023-01-24 08:50:03.016432: step: 1364/527, loss: 0.0005966530297882855
2023-01-24 08:50:04.055659: step: 1368/527, loss: 0.00013318641867954284
2023-01-24 08:50:05.102578: step: 1372/527, loss: 0.00233738892711699
2023-01-24 08:50:06.161412: step: 1376/527, loss: 0.003912246786057949
2023-01-24 08:50:07.224937: step: 1380/527, loss: 0.0018200697377324104
2023-01-24 08:50:08.270815: step: 1384/527, loss: 2.5607803763705306e-05
2023-01-24 08:50:09.314913: step: 1388/527, loss: 4.2003670387202874e-05
2023-01-24 08:50:10.354747: step: 1392/527, loss: 0.0015089877415448427
2023-01-24 08:50:11.388294: step: 1396/527, loss: 0.007157751824706793
2023-01-24 08:50:12.440263: step: 1400/527, loss: 1.2665627764363308e-05
2023-01-24 08:50:13.501939: step: 1404/527, loss: 3.931358878617175e-05
2023-01-24 08:50:14.546711: step: 1408/527, loss: 0.03956862911581993
2023-01-24 08:50:15.590861: step: 1412/527, loss: 0.000365585699910298
2023-01-24 08:50:16.622216: step: 1416/527, loss: 0.0005526355816982687
2023-01-24 08:50:17.658479: step: 1420/527, loss: 0.0015575216384604573
2023-01-24 08:50:18.693802: step: 1424/527, loss: 1.2718452126136981e-05
2023-01-24 08:50:19.737849: step: 1428/527, loss: 0.00046149728586897254
2023-01-24 08:50:20.791752: step: 1432/527, loss: 0.004653729498386383
2023-01-24 08:50:21.838490: step: 1436/527, loss: 0.003615268040448427
2023-01-24 08:50:22.895450: step: 1440/527, loss: 0.006307728588581085
2023-01-24 08:50:23.942084: step: 1444/527, loss: 0.0027707230765372515
2023-01-24 08:50:25.006728: step: 1448/527, loss: 0.0022308225743472576
2023-01-24 08:50:26.049889: step: 1452/527, loss: 0.0006430679350160062
2023-01-24 08:50:27.081825: step: 1456/527, loss: 0.00419104378670454
2023-01-24 08:50:28.148025: step: 1460/527, loss: 0.001885966514237225
2023-01-24 08:50:29.169874: step: 1464/527, loss: 0.000985346850939095
2023-01-24 08:50:30.212445: step: 1468/527, loss: 0.0016185510903596878
2023-01-24 08:50:31.247514: step: 1472/527, loss: 6.160890916362405e-05
2023-01-24 08:50:32.297570: step: 1476/527, loss: 0.0028298243414610624
2023-01-24 08:50:33.359581: step: 1480/527, loss: 0.0005574751412495971
2023-01-24 08:50:34.417416: step: 1484/527, loss: 0.0027861001435667276
2023-01-24 08:50:35.454349: step: 1488/527, loss: 0.005466966889798641
2023-01-24 08:50:36.517033: step: 1492/527, loss: 0.0019355129916220903
2023-01-24 08:50:37.554681: step: 1496/527, loss: 0.012011715210974216
2023-01-24 08:50:38.611599: step: 1500/527, loss: 0.0005386918783187866
2023-01-24 08:50:39.679324: step: 1504/527, loss: 0.0015762910479679704
2023-01-24 08:50:40.729807: step: 1508/527, loss: 0.00025125424144789577
2023-01-24 08:50:41.762164: step: 1512/527, loss: 0.024186281487345695
2023-01-24 08:50:42.813157: step: 1516/527, loss: 0.005063135642558336
2023-01-24 08:50:43.845769: step: 1520/527, loss: 8.045582944760099e-06
2023-01-24 08:50:44.891130: step: 1524/527, loss: 0.0009615349699743092
2023-01-24 08:50:45.939638: step: 1528/527, loss: 0.001116161816753447
2023-01-24 08:50:46.992220: step: 1532/527, loss: 0.005001375917345285
2023-01-24 08:50:48.071040: step: 1536/527, loss: 0.033579546958208084
2023-01-24 08:50:49.121077: step: 1540/527, loss: 6.994607701926725e-06
2023-01-24 08:50:50.208266: step: 1544/527, loss: 0.0018394087674096227
2023-01-24 08:50:51.262632: step: 1548/527, loss: 0.0
2023-01-24 08:50:52.286376: step: 1552/527, loss: 0.0006510919774882495
2023-01-24 08:50:53.334670: step: 1556/527, loss: 0.007867393083870411
2023-01-24 08:50:54.389200: step: 1560/527, loss: 0.0037666717544198036
2023-01-24 08:50:55.437088: step: 1564/527, loss: 0.006869942881166935
2023-01-24 08:50:56.472669: step: 1568/527, loss: 0.002938494784757495
2023-01-24 08:50:57.507444: step: 1572/527, loss: 0.00018845383601728827
2023-01-24 08:50:58.560889: step: 1576/527, loss: 0.0011116010136902332
2023-01-24 08:50:59.633306: step: 1580/527, loss: 0.00599554181098938
2023-01-24 08:51:00.670817: step: 1584/527, loss: 0.004423385951668024
2023-01-24 08:51:01.706416: step: 1588/527, loss: 1.0651147022144869e-05
2023-01-24 08:51:02.765294: step: 1592/527, loss: 0.0038971113972365856
2023-01-24 08:51:03.819542: step: 1596/527, loss: 0.004415752831846476
2023-01-24 08:51:04.873776: step: 1600/527, loss: 0.0003099293098784983
2023-01-24 08:51:05.903337: step: 1604/527, loss: 5.83291839575395e-05
2023-01-24 08:51:06.953500: step: 1608/527, loss: 3.6457729493122315e-06
2023-01-24 08:51:07.993132: step: 1612/527, loss: 0.0012275920016691089
2023-01-24 08:51:09.037898: step: 1616/527, loss: 0.0040814257226884365
2023-01-24 08:51:10.078343: step: 1620/527, loss: 0.0012814562069252133
2023-01-24 08:51:11.119594: step: 1624/527, loss: 0.016061807051301003
2023-01-24 08:51:12.159571: step: 1628/527, loss: 0.0001078935238183476
2023-01-24 08:51:13.243077: step: 1632/527, loss: 0.001117355190217495
2023-01-24 08:51:14.285301: step: 1636/527, loss: 0.004430884029716253
2023-01-24 08:51:15.360206: step: 1640/527, loss: 1.7523252608953044e-05
2023-01-24 08:51:16.424995: step: 1644/527, loss: 0.004557272884994745
2023-01-24 08:51:17.483888: step: 1648/527, loss: 0.00830384623259306
2023-01-24 08:51:18.550045: step: 1652/527, loss: 0.003626681864261627
2023-01-24 08:51:19.602945: step: 1656/527, loss: 0.03567762300372124
2023-01-24 08:51:20.677962: step: 1660/527, loss: 0.0004545130068436265
2023-01-24 08:51:21.733476: step: 1664/527, loss: 0.02203032560646534
2023-01-24 08:51:22.778410: step: 1668/527, loss: 0.00022432518017012626
2023-01-24 08:51:23.828826: step: 1672/527, loss: 0.0010281819850206375
2023-01-24 08:51:24.870715: step: 1676/527, loss: 0.0035206147003918886
2023-01-24 08:51:25.918837: step: 1680/527, loss: 0.004395316820591688
2023-01-24 08:51:26.952396: step: 1684/527, loss: 0.0016096860636025667
2023-01-24 08:51:27.994851: step: 1688/527, loss: 0.00018072074453812093
2023-01-24 08:51:29.026151: step: 1692/527, loss: 0.0030670149717479944
2023-01-24 08:51:30.073969: step: 1696/527, loss: 0.004104304127395153
2023-01-24 08:51:31.128148: step: 1700/527, loss: 0.0007212538621388376
2023-01-24 08:51:32.172780: step: 1704/527, loss: 0.00014768936671316624
2023-01-24 08:51:33.218823: step: 1708/527, loss: 5.3126379498280585e-05
2023-01-24 08:51:34.271998: step: 1712/527, loss: 0.0012064295588061213
2023-01-24 08:51:35.312236: step: 1716/527, loss: 0.00042510218918323517
2023-01-24 08:51:36.360122: step: 1720/527, loss: 0.012853904627263546
2023-01-24 08:51:37.406848: step: 1724/527, loss: 0.0009649721905589104
2023-01-24 08:51:38.442575: step: 1728/527, loss: 0.0005003859987482429
2023-01-24 08:51:39.499714: step: 1732/527, loss: 0.0003828062617685646
2023-01-24 08:51:40.551607: step: 1736/527, loss: 0.0009010783978737891
2023-01-24 08:51:41.593530: step: 1740/527, loss: 0.0007870363770052791
2023-01-24 08:51:42.640600: step: 1744/527, loss: 0.00410768948495388
2023-01-24 08:51:43.690629: step: 1748/527, loss: 0.010180222801864147
2023-01-24 08:51:44.734034: step: 1752/527, loss: 0.0013522646622732282
2023-01-24 08:51:45.776805: step: 1756/527, loss: 0.0009956457652151585
2023-01-24 08:51:46.839726: step: 1760/527, loss: 0.0099768852815032
2023-01-24 08:51:47.880302: step: 1764/527, loss: 0.001871144981123507
2023-01-24 08:51:48.939966: step: 1768/527, loss: 0.002563879359513521
2023-01-24 08:51:49.981471: step: 1772/527, loss: 0.0002177686692448333
2023-01-24 08:51:51.020943: step: 1776/527, loss: 0.0009041694574989378
2023-01-24 08:51:52.087766: step: 1780/527, loss: 0.0027366108261048794
2023-01-24 08:51:53.135464: step: 1784/527, loss: 0.004141340497881174
2023-01-24 08:51:54.173484: step: 1788/527, loss: 0.0003586003149393946
2023-01-24 08:51:55.224560: step: 1792/527, loss: 0.0013359743170440197
2023-01-24 08:51:56.269491: step: 1796/527, loss: 7.661720701435115e-06
2023-01-24 08:51:57.330514: step: 1800/527, loss: 0.00013234731159172952
2023-01-24 08:51:58.371362: step: 1804/527, loss: 0.00033974600955843925
2023-01-24 08:51:59.428541: step: 1808/527, loss: 0.0012891377555206418
2023-01-24 08:52:00.491038: step: 1812/527, loss: 0.0012205014936625957
2023-01-24 08:52:01.524866: step: 1816/527, loss: 0.0007151333265937865
2023-01-24 08:52:02.558087: step: 1820/527, loss: 0.0007523277890868485
2023-01-24 08:52:03.605076: step: 1824/527, loss: 3.2562133128521964e-05
2023-01-24 08:52:04.639669: step: 1828/527, loss: 0.0050446949899196625
2023-01-24 08:52:05.712757: step: 1832/527, loss: 0.0033479370176792145
2023-01-24 08:52:06.749064: step: 1836/527, loss: 0.0017451625317335129
2023-01-24 08:52:07.778387: step: 1840/527, loss: 0.00017647819186095148
2023-01-24 08:52:08.833676: step: 1844/527, loss: 0.0006519692833535373
2023-01-24 08:52:09.887592: step: 1848/527, loss: 0.0008623186149634421
2023-01-24 08:52:10.940187: step: 1852/527, loss: 0.027156250551342964
2023-01-24 08:52:12.001782: step: 1856/527, loss: 0.01807195320725441
2023-01-24 08:52:13.065229: step: 1860/527, loss: 0.0
2023-01-24 08:52:14.121173: step: 1864/527, loss: 0.0044976333156228065
2023-01-24 08:52:15.180361: step: 1868/527, loss: 0.045675795525312424
2023-01-24 08:52:16.239622: step: 1872/527, loss: 0.0031930566765367985
2023-01-24 08:52:17.279718: step: 1876/527, loss: 0.006232208106666803
2023-01-24 08:52:18.360560: step: 1880/527, loss: 0.001527534332126379
2023-01-24 08:52:19.455585: step: 1884/527, loss: 0.001108763855881989
2023-01-24 08:52:20.501479: step: 1888/527, loss: 0.038114871829748154
2023-01-24 08:52:21.546055: step: 1892/527, loss: 0.0012414919910952449
2023-01-24 08:52:22.600310: step: 1896/527, loss: 0.0015107031213119626
2023-01-24 08:52:23.643331: step: 1900/527, loss: 0.00016629492165520787
2023-01-24 08:52:24.682250: step: 1904/527, loss: 0.0011715586297214031
2023-01-24 08:52:25.716958: step: 1908/527, loss: 0.0042213695123791695
2023-01-24 08:52:26.770276: step: 1912/527, loss: 0.0029871773440390825
2023-01-24 08:52:27.817500: step: 1916/527, loss: 0.0007310773362405598
2023-01-24 08:52:28.863898: step: 1920/527, loss: 0.012977833859622478
2023-01-24 08:52:29.905561: step: 1924/527, loss: 4.216387969790958e-05
2023-01-24 08:52:30.946626: step: 1928/527, loss: 0.0013348968932405114
2023-01-24 08:52:31.998076: step: 1932/527, loss: 0.014834019355475903
2023-01-24 08:52:33.039264: step: 1936/527, loss: 0.001326092635281384
2023-01-24 08:52:34.078021: step: 1940/527, loss: 0.002689038636162877
2023-01-24 08:52:35.141463: step: 1944/527, loss: 0.00825933925807476
2023-01-24 08:52:36.181126: step: 1948/527, loss: 0.0022235976066440344
2023-01-24 08:52:37.217711: step: 1952/527, loss: 0.0003668357676360756
2023-01-24 08:52:38.269864: step: 1956/527, loss: 1.2783289093931671e-06
2023-01-24 08:52:39.309607: step: 1960/527, loss: 0.0014351533027365804
2023-01-24 08:52:40.356903: step: 1964/527, loss: 0.0022870164830237627
2023-01-24 08:52:41.401310: step: 1968/527, loss: 0.012237445451319218
2023-01-24 08:52:42.438327: step: 1972/527, loss: 0.0007594622438773513
2023-01-24 08:52:43.490668: step: 1976/527, loss: 0.0004911799915134907
2023-01-24 08:52:44.536883: step: 1980/527, loss: 0.00017619550635572523
2023-01-24 08:52:45.569219: step: 1984/527, loss: 0.0012059074360877275
2023-01-24 08:52:46.607983: step: 1988/527, loss: 4.7138968511717394e-05
2023-01-24 08:52:47.659866: step: 1992/527, loss: 0.001019878312945366
2023-01-24 08:52:48.697312: step: 1996/527, loss: 0.004965396597981453
2023-01-24 08:52:49.768815: step: 2000/527, loss: 0.00016408351075369865
2023-01-24 08:52:50.834443: step: 2004/527, loss: 0.0015512191457673907
2023-01-24 08:52:51.898163: step: 2008/527, loss: 0.0007798252627253532
2023-01-24 08:52:52.941884: step: 2012/527, loss: 0.0022085695527493954
2023-01-24 08:52:53.993736: step: 2016/527, loss: 0.010480586439371109
2023-01-24 08:52:55.043569: step: 2020/527, loss: 0.004361104220151901
2023-01-24 08:52:56.104500: step: 2024/527, loss: 8.108156180242077e-05
2023-01-24 08:52:57.134619: step: 2028/527, loss: 8.581471774959937e-05
2023-01-24 08:52:58.175318: step: 2032/527, loss: 0.0011279636528342962
2023-01-24 08:52:59.229475: step: 2036/527, loss: 0.0008524759323336184
2023-01-24 08:53:00.275633: step: 2040/527, loss: 0.00021893046505283564
2023-01-24 08:53:01.311600: step: 2044/527, loss: 0.0031472290866076946
2023-01-24 08:53:02.374747: step: 2048/527, loss: 0.0006272197933867574
2023-01-24 08:53:03.425743: step: 2052/527, loss: 0.00047079287469387054
2023-01-24 08:53:04.469802: step: 2056/527, loss: 0.002419366966933012
2023-01-24 08:53:05.503867: step: 2060/527, loss: 9.186561510432512e-05
2023-01-24 08:53:06.561831: step: 2064/527, loss: 0.004477875307202339
2023-01-24 08:53:07.608968: step: 2068/527, loss: 0.0025092202704399824
2023-01-24 08:53:08.647297: step: 2072/527, loss: 0.008459429256618023
2023-01-24 08:53:09.705575: step: 2076/527, loss: 0.003929312340915203
2023-01-24 08:53:10.762557: step: 2080/527, loss: 0.002372551243752241
2023-01-24 08:53:11.816529: step: 2084/527, loss: 5.1264149078633636e-05
2023-01-24 08:53:12.860045: step: 2088/527, loss: 6.1019814893370494e-05
2023-01-24 08:53:13.886251: step: 2092/527, loss: 0.0013485817471519113
2023-01-24 08:53:14.918636: step: 2096/527, loss: 0.00022381541202776134
2023-01-24 08:53:15.958029: step: 2100/527, loss: 0.00043240704690106213
2023-01-24 08:53:17.001602: step: 2104/527, loss: 0.005764584988355637
2023-01-24 08:53:18.053184: step: 2108/527, loss: 0.00040122956852428615
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34360375162088885, 'r': 0.32534776481750194, 'f1': 0.3342266511867905}, 'combined': 0.24627226929552984, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3733191614096769, 'r': 0.290510183787894, 'f1': 0.3267496954669564}, 'combined': 0.20911980509885209, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3579008746355685, 'r': 0.33277310924369746, 'f1': 0.3448798988621998}, 'combined': 0.2541220307405682, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3780218762005364, 'r': 0.3042028903848095, 'f1': 0.33711865356182713}, 'combined': 0.21575593827956932, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3622724283538696, 'r': 0.32033956662789986, 'f1': 0.34001802943182924}, 'combined': 0.2505396006339794, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.38836276541970877, 'r': 0.313309979395116, 'f1': 0.346822449441415}, 'combined': 0.24866515242969378, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.42391304347826086, 'f1': 0.39795918367346944}, 'combined': 0.19897959183673472, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 19}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34829264109294833, 'r': 0.32582214811920973, 'f1': 0.33668288638985006}, 'combined': 0.24808212681357372, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3765609549603375, 'r': 0.28755563833334863, 'f1': 0.32609402285225103}, 'combined': 0.20870017462544063, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.38095238095238093, 'f1': 0.35555555555555557}, 'combined': 0.23703703703703705, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3579008746355685, 'r': 0.33277310924369746, 'f1': 0.3448798988621998}, 'combined': 0.2541220307405682, 'stategy': 1, 'epoch': 19}
Test for Korean: {'template': {'p': 0.927536231884058, 'r': 0.48854961832061067, 'f1': 0.6399999999999999}, 'slot': {'p': 0.3780218762005364, 'r': 0.3042028903848095, 'f1': 0.33711865356182713}, 'combined': 0.21575593827956932, 'stategy': 1, 'epoch': 19}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.42391304347826086, 'f1': 0.39795918367346944}, 'combined': 0.19897959183673472, 'stategy': 1, 'epoch': 19}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3658576467365249, 'r': 0.3269809328518088, 'f1': 0.34532856034649945}, 'combined': 0.2544526234132101, 'stategy': 1, 'epoch': 18}
Test for Russian: {'template': {'p': 0.9382716049382716, 'r': 0.5801526717557252, 'f1': 0.7169811320754718}, 'slot': {'p': 0.388109906451237, 'r': 0.3123984023668571, 'f1': 0.3461626741378205}, 'combined': 0.24819210598560715, 'stategy': 1, 'epoch': 18}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 18}