Command that produces this log: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --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])
>>> basic_gcn.T_T.0.weight: torch.Size([1024, 1024])
>>> basic_gcn.T_T.0.bias: torch.Size([1024])
>>> basic_gcn.T_T.1.weight: torch.Size([1024, 1024])
>>> basic_gcn.T_T.1.bias: torch.Size([1024])
>>> basic_gcn.T_T.2.weight: torch.Size([1024, 1024])
>>> basic_gcn.T_T.2.bias: torch.Size([1024])
>>> basic_gcn.T_E.0.weight: torch.Size([1024, 1024])
>>> basic_gcn.T_E.0.bias: torch.Size([1024])
>>> basic_gcn.T_E.1.weight: torch.Size([1024, 1024])
>>> basic_gcn.T_E.1.bias: torch.Size([1024])
>>> basic_gcn.T_E.2.weight: torch.Size([1024, 1024])
>>> basic_gcn.T_E.2.bias: torch.Size([1024])
>>> basic_gcn.E_T.0.weight: torch.Size([1024, 1024])
>>> basic_gcn.E_T.0.bias: torch.Size([1024])
>>> basic_gcn.E_T.1.weight: torch.Size([1024, 1024])
>>> basic_gcn.E_T.1.bias: torch.Size([1024])
>>> basic_gcn.E_T.2.weight: torch.Size([1024, 1024])
>>> basic_gcn.E_T.2.bias: torch.Size([1024])
>>> basic_gcn.E_E.0.weight: torch.Size([1024, 1024])
>>> basic_gcn.E_E.0.bias: torch.Size([1024])
>>> basic_gcn.E_E.1.weight: torch.Size([1024, 1024])
>>> basic_gcn.E_E.1.bias: torch.Size([1024])
>>> basic_gcn.E_E.2.weight: torch.Size([1024, 1024])
>>> basic_gcn.E_E.2.bias: torch.Size([1024])
>>> basic_gcn.f_t.0.weight: torch.Size([1024, 2048])
>>> basic_gcn.f_t.0.bias: torch.Size([1024])
>>> basic_gcn.f_e.0.weight: torch.Size([1024, 2048])
>>> basic_gcn.f_e.0.bias: torch.Size([1024])
>>> name2classifier.occupy-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.occupy-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.occupy-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.occupy-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.outcome-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.outcome-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.outcome-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.outcome-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.protest-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.protest-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.protest-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.protest-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.when-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.when-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.when-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.when-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.where-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.where-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.where-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.where-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.who-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.who-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.who-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.who-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.protest-against-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.protest-against-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.protest-against-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.protest-against-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.protest-for-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.protest-for-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.protest-for-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.protest-for-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.organizer-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.organizer-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.organizer-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.organizer-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.wounded-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.wounded-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.wounded-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.wounded-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.arrested-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.arrested-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.arrested-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.arrested-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.killed-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.killed-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.killed-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.killed-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.imprisoned-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.imprisoned-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.imprisoned-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.imprisoned-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.corrupt-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.corrupt-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.corrupt-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.corrupt-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.judicial-actions-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.judicial-actions-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.judicial-actions-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.judicial-actions-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.charged-with-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.charged-with-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.charged-with-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.charged-with-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.prison-term-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.prison-term-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.prison-term-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.prison-term-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.fine-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.fine-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.fine-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.fine-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.npi-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.npi-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.npi-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.npi-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.disease-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.disease-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.disease-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.disease-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.infected-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.infected-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.infected-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.infected-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.killed-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.killed-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.killed-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.killed-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.killed-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.killed-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.killed-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.killed-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.outbreak-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.outbreak-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.outbreak-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.outbreak-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.infected-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.infected-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.infected-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.infected-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.killed-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.killed-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.killed-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.killed-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.hospitalized-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.hospitalized-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.hospitalized-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.hospitalized-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.hospitalized-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.hospitalized-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.hospitalized-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.hospitalized-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.infected-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.infected-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.infected-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.infected-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.tested-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.tested-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.tested-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.tested-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.vaccinated-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.vaccinated-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.vaccinated-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.vaccinated-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.tested-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.tested-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.tested-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.tested-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.exposed-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.exposed-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.exposed-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.exposed-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.recovered-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.recovered-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.recovered-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.recovered-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.tested-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.tested-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.tested-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.tested-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.recovered-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.recovered-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.recovered-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.recovered-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.exposed-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.exposed-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.exposed-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.exposed-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.vaccinated-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.vaccinated-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.vaccinated-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.vaccinated-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.vaccinated-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.vaccinated-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.vaccinated-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.vaccinated-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.exposed-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.exposed-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.exposed-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.exposed-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.recovered-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.recovered-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.recovered-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.recovered-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.blamed-by-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.blamed-by-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.blamed-by-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.blamed-by-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.claimed-by-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.claimed-by-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.claimed-by-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.claimed-by-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.terror-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.terror-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.terror-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.terror-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.kidnapped-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.kidnapped-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.kidnapped-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.kidnapped-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.named-perp-org-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.named-perp-org-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.named-perp-org-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.named-perp-org-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.target-physical-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.target-physical-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.target-physical-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.target-physical-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.named-perp-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.named-perp-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.named-perp-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.named-perp-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perp-killed-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perp-killed-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perp-killed-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perp-killed-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.target-human-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.target-human-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.target-human-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.target-human-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perp-captured-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perp-captured-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perp-captured-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perp-captured-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perp-objective-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perp-objective-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perp-objective-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perp-objective-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.weapon-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.weapon-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.weapon-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.weapon-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.named-organizer-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.named-organizer-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.named-organizer-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.named-organizer-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.affected-cumulative-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.affected-cumulative-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.affected-cumulative-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.affected-cumulative-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.damage-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.damage-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.damage-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.damage-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.human-displacement-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.human-displacement-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.human-displacement-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.human-displacement-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.major-disaster-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.major-disaster-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.major-disaster-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.major-disaster-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.related-natural-phenomena-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.related-natural-phenomena-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.related-natural-phenomena-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.related-natural-phenomena-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.responders-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.responders-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.responders-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.responders-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.assistance-provided-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.assistance-provided-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.assistance-provided-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.assistance-provided-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.rescue-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.rescue-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.rescue-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.rescue-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.individuals-affected-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.individuals-affected-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.individuals-affected-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.individuals-affected-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.missing-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.missing-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.missing-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.missing-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.injured-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.injured-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.injured-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.injured-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.rescued-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.rescued-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.rescued-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.rescued-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.assistance-needed-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.assistance-needed-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.assistance-needed-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.assistance-needed-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.repair-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.repair-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.repair-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.repair-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.declare-emergency-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.declare-emergency-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.declare-emergency-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.declare-emergency-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.announce-disaster-warnings-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.announce-disaster-warnings-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.announce-disaster-warnings-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.announce-disaster-warnings-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.disease-outbreak-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.disease-outbreak-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.disease-outbreak-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.disease-outbreak-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.current-location-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.current-location-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.current-location-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.current-location-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.group-identity-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.group-identity-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.group-identity-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.group-identity-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.human-displacement-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.human-displacement-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.human-displacement-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.human-displacement-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.origin-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.origin-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.origin-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.origin-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.total-displaced-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.total-displaced-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.total-displaced-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.total-displaced-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.transitory-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.transitory-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.transitory-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.transitory-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.destination-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.destination-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.destination-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.destination-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.transiting-location-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.transiting-location-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.transiting-location-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.transiting-location-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.detained-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.detained-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.detained-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.detained-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.blocked-migration-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.blocked-migration-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.blocked-migration-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.blocked-migration-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.cybercrime-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.cybercrime-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.cybercrime-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.cybercrime-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perpetrator-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perpetrator-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perpetrator-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perpetrator-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.victim-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.victim-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.victim-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.victim-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.response-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.response-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.response-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.response-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.information-stolen-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.information-stolen-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.information-stolen-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.information-stolen-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.related-crimes-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.related-crimes-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.related-crimes-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.related-crimes-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.victim-impact-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.victim-impact-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.victim-impact-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.victim-impact-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.etip-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.etip-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.etip-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.etip-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.project-location-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.project-location-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.project-location-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.project-location-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.project-name-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.project-name-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.project-name-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.project-name-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.funding-amount-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.funding-amount-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.funding-amount-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.funding-amount-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.funding-recipient-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.funding-recipient-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.funding-recipient-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.funding-recipient-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.funding-source-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.funding-source-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.funding-source-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.funding-source-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.overall-project-value-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.overall-project-value-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.overall-project-value-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.overall-project-value-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.signatories-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.signatories-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.signatories-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.signatories-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.contract-amount-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.contract-amount-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.contract-amount-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.contract-amount-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.contract-awardee-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.contract-awardee-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.contract-awardee-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.contract-awardee-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.contract-awarder-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.contract-awarder-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.contract-awarder-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.contract-awarder-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.agreement-length-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.agreement-length-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.agreement-length-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.agreement-length-ffn.layers.1.bias: torch.Size([2])
>>> irrealis_classifier.layers.0.weight: torch.Size([350, 1127])
>>> irrealis_classifier.layers.0.bias: torch.Size([350])
>>> irrealis_classifier.layers.1.weight: torch.Size([7, 350])
>>> irrealis_classifier.layers.1.bias: torch.Size([7])
n_trainable_params: 613743345, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 16:27:23.188532: step: 2/470, loss: 18.837427139282227
2023-01-22 16:27:23.928473: step: 4/470, loss: 6.08452033996582
2023-01-22 16:27:24.682540: step: 6/470, loss: 14.960529327392578
2023-01-22 16:27:25.382974: step: 8/470, loss: 9.693341255187988
2023-01-22 16:27:26.082320: step: 10/470, loss: 20.36423683166504
2023-01-22 16:27:26.906731: step: 12/470, loss: 12.639719009399414
2023-01-22 16:27:27.683800: step: 14/470, loss: 10.887170791625977
2023-01-22 16:27:28.549523: step: 16/470, loss: 30.509140014648438
2023-01-22 16:27:29.303140: step: 18/470, loss: 21.185964584350586
2023-01-22 16:27:30.008308: step: 20/470, loss: 22.507814407348633
2023-01-22 16:27:30.748837: step: 22/470, loss: 13.584888458251953
2023-01-22 16:27:31.435133: step: 24/470, loss: 10.651383399963379
2023-01-22 16:27:32.239185: step: 26/470, loss: 19.368906021118164
2023-01-22 16:27:32.983728: step: 28/470, loss: 14.308650970458984
2023-01-22 16:27:33.760010: step: 30/470, loss: 7.055563926696777
2023-01-22 16:27:34.577458: step: 32/470, loss: 14.257768630981445
2023-01-22 16:27:35.298869: step: 34/470, loss: 8.895671844482422
2023-01-22 16:27:35.990386: step: 36/470, loss: 26.354061126708984
2023-01-22 16:27:36.708135: step: 38/470, loss: 8.183581352233887
2023-01-22 16:27:37.452019: step: 40/470, loss: 23.308879852294922
2023-01-22 16:27:38.162965: step: 42/470, loss: 9.376198768615723
2023-01-22 16:27:38.937739: step: 44/470, loss: 40.81726837158203
2023-01-22 16:27:39.677703: step: 46/470, loss: 15.613691329956055
2023-01-22 16:27:40.352485: step: 48/470, loss: 13.526906967163086
2023-01-22 16:27:41.102713: step: 50/470, loss: 24.901996612548828
2023-01-22 16:27:41.891856: step: 52/470, loss: 12.065844535827637
2023-01-22 16:27:42.587691: step: 54/470, loss: 42.65087127685547
2023-01-22 16:27:43.451164: step: 56/470, loss: 27.784313201904297
2023-01-22 16:27:44.162427: step: 58/470, loss: 16.313859939575195
2023-01-22 16:27:44.899937: step: 60/470, loss: 23.540321350097656
2023-01-22 16:27:45.731984: step: 62/470, loss: 13.617783546447754
2023-01-22 16:27:46.456987: step: 64/470, loss: 22.79100799560547
2023-01-22 16:27:47.179711: step: 66/470, loss: 19.00048065185547
2023-01-22 16:27:47.993737: step: 68/470, loss: 19.12494468688965
2023-01-22 16:27:48.675237: step: 70/470, loss: 12.588727951049805
2023-01-22 16:27:49.396308: step: 72/470, loss: 16.181161880493164
2023-01-22 16:27:50.161263: step: 74/470, loss: 17.37213897705078
2023-01-22 16:27:50.990736: step: 76/470, loss: 13.227319717407227
2023-01-22 16:27:51.709336: step: 78/470, loss: 21.182538986206055
2023-01-22 16:27:52.491492: step: 80/470, loss: 16.062942504882812
2023-01-22 16:27:53.239410: step: 82/470, loss: 10.652351379394531
2023-01-22 16:27:53.989607: step: 84/470, loss: 5.419546604156494
2023-01-22 16:27:54.758943: step: 86/470, loss: 10.083927154541016
2023-01-22 16:27:55.524953: step: 88/470, loss: 6.871520042419434
2023-01-22 16:27:56.197567: step: 90/470, loss: 11.351171493530273
2023-01-22 16:27:56.996164: step: 92/470, loss: 20.639118194580078
2023-01-22 16:27:57.720791: step: 94/470, loss: 4.432590484619141
2023-01-22 16:27:58.491136: step: 96/470, loss: 18.61043357849121
2023-01-22 16:27:59.381480: step: 98/470, loss: 5.183197021484375
2023-01-22 16:28:00.068143: step: 100/470, loss: 22.156150817871094
2023-01-22 16:28:00.844068: step: 102/470, loss: 11.253484725952148
2023-01-22 16:28:01.541074: step: 104/470, loss: 9.191667556762695
2023-01-22 16:28:02.187121: step: 106/470, loss: 17.978792190551758
2023-01-22 16:28:02.859419: step: 108/470, loss: 26.32501983642578
2023-01-22 16:28:03.571578: step: 110/470, loss: 15.27033805847168
2023-01-22 16:28:04.489190: step: 112/470, loss: 18.11617660522461
2023-01-22 16:28:05.259528: step: 114/470, loss: 5.689704895019531
2023-01-22 16:28:06.007020: step: 116/470, loss: 17.882823944091797
2023-01-22 16:28:06.809628: step: 118/470, loss: 14.880837440490723
2023-01-22 16:28:07.535154: step: 120/470, loss: 3.9773387908935547
2023-01-22 16:28:08.512757: step: 122/470, loss: 17.60595703125
2023-01-22 16:28:09.228130: step: 124/470, loss: 13.977578163146973
2023-01-22 16:28:09.919190: step: 126/470, loss: 7.939039707183838
2023-01-22 16:28:10.712887: step: 128/470, loss: 5.822059631347656
2023-01-22 16:28:11.401094: step: 130/470, loss: 4.221154689788818
2023-01-22 16:28:12.066365: step: 132/470, loss: 11.863361358642578
2023-01-22 16:28:12.832178: step: 134/470, loss: 7.579117774963379
2023-01-22 16:28:13.507370: step: 136/470, loss: 16.241559982299805
2023-01-22 16:28:14.232419: step: 138/470, loss: 13.835257530212402
2023-01-22 16:28:14.964643: step: 140/470, loss: 11.795804977416992
2023-01-22 16:28:15.713329: step: 142/470, loss: 10.111894607543945
2023-01-22 16:28:16.554334: step: 144/470, loss: 3.8433728218078613
2023-01-22 16:28:17.347879: step: 146/470, loss: 8.96932315826416
2023-01-22 16:28:18.118820: step: 148/470, loss: 3.0903584957122803
2023-01-22 16:28:18.891588: step: 150/470, loss: 9.47050666809082
2023-01-22 16:28:19.576388: step: 152/470, loss: 12.27602767944336
2023-01-22 16:28:20.273841: step: 154/470, loss: 5.426934242248535
2023-01-22 16:28:20.988554: step: 156/470, loss: 12.116996765136719
2023-01-22 16:28:21.685073: step: 158/470, loss: 9.07990550994873
2023-01-22 16:28:22.407529: step: 160/470, loss: 4.529577732086182
2023-01-22 16:28:23.177636: step: 162/470, loss: 10.44383430480957
2023-01-22 16:28:23.896487: step: 164/470, loss: 6.473989963531494
2023-01-22 16:28:24.649490: step: 166/470, loss: 4.3379807472229
2023-01-22 16:28:25.464335: step: 168/470, loss: 9.986034393310547
2023-01-22 16:28:26.283094: step: 170/470, loss: 3.3363029956817627
2023-01-22 16:28:27.020335: step: 172/470, loss: 7.920467376708984
2023-01-22 16:28:27.849067: step: 174/470, loss: 8.45045280456543
2023-01-22 16:28:28.630175: step: 176/470, loss: 12.504642486572266
2023-01-22 16:28:29.337500: step: 178/470, loss: 5.040508270263672
2023-01-22 16:28:30.074902: step: 180/470, loss: 7.040112018585205
2023-01-22 16:28:30.879465: step: 182/470, loss: 10.85146713256836
2023-01-22 16:28:31.682333: step: 184/470, loss: 10.689022064208984
2023-01-22 16:28:32.450454: step: 186/470, loss: 3.291524648666382
2023-01-22 16:28:33.195383: step: 188/470, loss: 6.111932277679443
2023-01-22 16:28:33.866935: step: 190/470, loss: 2.9675354957580566
2023-01-22 16:28:34.697411: step: 192/470, loss: 4.350892066955566
2023-01-22 16:28:35.429128: step: 194/470, loss: 6.658123970031738
2023-01-22 16:28:36.183075: step: 196/470, loss: 7.661910057067871
2023-01-22 16:28:36.889397: step: 198/470, loss: 4.766957759857178
2023-01-22 16:28:37.678148: step: 200/470, loss: 4.938291549682617
2023-01-22 16:28:38.373913: step: 202/470, loss: 12.754507064819336
2023-01-22 16:28:39.208218: step: 204/470, loss: 8.91333293914795
2023-01-22 16:28:40.003633: step: 206/470, loss: 17.913904190063477
2023-01-22 16:28:40.712404: step: 208/470, loss: 5.756092071533203
2023-01-22 16:28:41.472342: step: 210/470, loss: 7.458624839782715
2023-01-22 16:28:42.248374: step: 212/470, loss: 15.039164543151855
2023-01-22 16:28:42.987571: step: 214/470, loss: 7.663404941558838
2023-01-22 16:28:43.691446: step: 216/470, loss: 2.9406890869140625
2023-01-22 16:28:44.530191: step: 218/470, loss: 7.196639060974121
2023-01-22 16:28:45.265493: step: 220/470, loss: 11.003211975097656
2023-01-22 16:28:45.952031: step: 222/470, loss: 2.7577972412109375
2023-01-22 16:28:46.710761: step: 224/470, loss: 13.001374244689941
2023-01-22 16:28:47.488612: step: 226/470, loss: 8.773453712463379
2023-01-22 16:28:48.160728: step: 228/470, loss: 8.044055938720703
2023-01-22 16:28:48.870435: step: 230/470, loss: 3.6388256549835205
2023-01-22 16:28:49.597482: step: 232/470, loss: 10.504514694213867
2023-01-22 16:28:50.380633: step: 234/470, loss: 8.363357543945312
2023-01-22 16:28:51.046537: step: 236/470, loss: 13.068225860595703
2023-01-22 16:28:51.765012: step: 238/470, loss: 9.169629096984863
2023-01-22 16:28:52.453797: step: 240/470, loss: 10.499161720275879
2023-01-22 16:28:53.252635: step: 242/470, loss: 2.7228548526763916
2023-01-22 16:28:53.988321: step: 244/470, loss: 2.8359575271606445
2023-01-22 16:28:54.649786: step: 246/470, loss: 11.094869613647461
2023-01-22 16:28:55.375917: step: 248/470, loss: 6.501433849334717
2023-01-22 16:28:56.087563: step: 250/470, loss: 5.333680629730225
2023-01-22 16:28:56.889556: step: 252/470, loss: 8.988299369812012
2023-01-22 16:28:57.652488: step: 254/470, loss: 3.2130463123321533
2023-01-22 16:28:58.401825: step: 256/470, loss: 6.5167083740234375
2023-01-22 16:28:59.155204: step: 258/470, loss: 5.343503952026367
2023-01-22 16:28:59.950275: step: 260/470, loss: 4.025961399078369
2023-01-22 16:29:00.662541: step: 262/470, loss: 5.961394786834717
2023-01-22 16:29:01.355804: step: 264/470, loss: 2.129112482070923
2023-01-22 16:29:02.020693: step: 266/470, loss: 3.658996820449829
2023-01-22 16:29:02.742560: step: 268/470, loss: 6.239549160003662
2023-01-22 16:29:03.485714: step: 270/470, loss: 10.180370330810547
2023-01-22 16:29:04.228993: step: 272/470, loss: 7.914863586425781
2023-01-22 16:29:05.073304: step: 274/470, loss: 6.526845932006836
2023-01-22 16:29:05.809096: step: 276/470, loss: 9.641494750976562
2023-01-22 16:29:06.499254: step: 278/470, loss: 8.146503448486328
2023-01-22 16:29:07.197110: step: 280/470, loss: 2.807060480117798
2023-01-22 16:29:07.829879: step: 282/470, loss: 7.910976409912109
2023-01-22 16:29:08.646478: step: 284/470, loss: 9.166391372680664
2023-01-22 16:29:09.533059: step: 286/470, loss: 12.144872665405273
2023-01-22 16:29:10.252539: step: 288/470, loss: 12.169351577758789
2023-01-22 16:29:10.966573: step: 290/470, loss: 5.240389823913574
2023-01-22 16:29:11.611659: step: 292/470, loss: 11.680598258972168
2023-01-22 16:29:12.390791: step: 294/470, loss: 5.746752738952637
2023-01-22 16:29:13.205692: step: 296/470, loss: 4.9092020988464355
2023-01-22 16:29:13.923262: step: 298/470, loss: 4.1507954597473145
2023-01-22 16:29:14.670115: step: 300/470, loss: 13.095625877380371
2023-01-22 16:29:15.421897: step: 302/470, loss: 7.79514217376709
2023-01-22 16:29:16.242091: step: 304/470, loss: 1.9198462963104248
2023-01-22 16:29:16.999039: step: 306/470, loss: 4.214913845062256
2023-01-22 16:29:17.728738: step: 308/470, loss: 5.49434757232666
2023-01-22 16:29:18.479185: step: 310/470, loss: 2.4591972827911377
2023-01-22 16:29:19.245714: step: 312/470, loss: 7.487868309020996
2023-01-22 16:29:20.101303: step: 314/470, loss: 7.941952228546143
2023-01-22 16:29:20.855168: step: 316/470, loss: 12.883258819580078
2023-01-22 16:29:21.636823: step: 318/470, loss: 12.775262832641602
2023-01-22 16:29:22.380116: step: 320/470, loss: 5.390825271606445
2023-01-22 16:29:23.137230: step: 322/470, loss: 7.754670143127441
2023-01-22 16:29:23.834271: step: 324/470, loss: 8.214757919311523
2023-01-22 16:29:24.522749: step: 326/470, loss: 8.570985794067383
2023-01-22 16:29:25.267945: step: 328/470, loss: 2.6725447177886963
2023-01-22 16:29:26.114588: step: 330/470, loss: 2.4087343215942383
2023-01-22 16:29:26.949310: step: 332/470, loss: 8.013860702514648
2023-01-22 16:29:27.685708: step: 334/470, loss: 7.368355751037598
2023-01-22 16:29:28.506755: step: 336/470, loss: 2.468770742416382
2023-01-22 16:29:29.234250: step: 338/470, loss: 11.629497528076172
2023-01-22 16:29:29.928776: step: 340/470, loss: 3.3276002407073975
2023-01-22 16:29:30.823570: step: 342/470, loss: 19.408966064453125
2023-01-22 16:29:31.520897: step: 344/470, loss: 2.7381513118743896
2023-01-22 16:29:32.351441: step: 346/470, loss: 12.861856460571289
2023-01-22 16:29:33.074814: step: 348/470, loss: 5.905899524688721
2023-01-22 16:29:33.866485: step: 350/470, loss: 8.441301345825195
2023-01-22 16:29:34.632993: step: 352/470, loss: 3.920839309692383
2023-01-22 16:29:35.399534: step: 354/470, loss: 9.670235633850098
2023-01-22 16:29:36.252348: step: 356/470, loss: 1.8189231157302856
2023-01-22 16:29:37.045720: step: 358/470, loss: 1.7387617826461792
2023-01-22 16:29:37.837546: step: 360/470, loss: 10.194907188415527
2023-01-22 16:29:38.524034: step: 362/470, loss: 2.97975492477417
2023-01-22 16:29:39.318213: step: 364/470, loss: 5.879580497741699
2023-01-22 16:29:40.131944: step: 366/470, loss: 6.046767711639404
2023-01-22 16:29:40.898824: step: 368/470, loss: 5.067502975463867
2023-01-22 16:29:41.664476: step: 370/470, loss: 9.547842025756836
2023-01-22 16:29:42.460262: step: 372/470, loss: 8.196964263916016
2023-01-22 16:29:43.135825: step: 374/470, loss: 5.261054992675781
2023-01-22 16:29:43.828395: step: 376/470, loss: 2.565000534057617
2023-01-22 16:29:44.522886: step: 378/470, loss: 2.8714776039123535
2023-01-22 16:29:45.202679: step: 380/470, loss: 3.206409454345703
2023-01-22 16:29:45.974493: step: 382/470, loss: 6.930261611938477
2023-01-22 16:29:46.811889: step: 384/470, loss: 2.868443012237549
2023-01-22 16:29:47.529632: step: 386/470, loss: 3.763054132461548
2023-01-22 16:29:48.233470: step: 388/470, loss: 5.591135025024414
2023-01-22 16:29:48.994970: step: 390/470, loss: 6.832804203033447
2023-01-22 16:29:49.706770: step: 392/470, loss: 2.2691705226898193
2023-01-22 16:29:50.464897: step: 394/470, loss: 2.894192695617676
2023-01-22 16:29:51.250484: step: 396/470, loss: 3.6917879581451416
2023-01-22 16:29:51.986949: step: 398/470, loss: 1.6198911666870117
2023-01-22 16:29:52.754094: step: 400/470, loss: 2.115755558013916
2023-01-22 16:29:53.490915: step: 402/470, loss: 3.108741283416748
2023-01-22 16:29:54.209066: step: 404/470, loss: 0.9105663895606995
2023-01-22 16:29:55.011807: step: 406/470, loss: 4.219695091247559
2023-01-22 16:29:55.756999: step: 408/470, loss: 2.287531852722168
2023-01-22 16:29:56.493274: step: 410/470, loss: 4.253011226654053
2023-01-22 16:29:57.215899: step: 412/470, loss: 4.190493106842041
2023-01-22 16:29:57.907376: step: 414/470, loss: 2.540191411972046
2023-01-22 16:29:58.665468: step: 416/470, loss: 1.3966948986053467
2023-01-22 16:29:59.452729: step: 418/470, loss: 2.3591842651367188
2023-01-22 16:30:00.224830: step: 420/470, loss: 2.5741522312164307
2023-01-22 16:30:01.091795: step: 422/470, loss: 0.9306092262268066
2023-01-22 16:30:01.847055: step: 424/470, loss: 1.9692203998565674
2023-01-22 16:30:02.609863: step: 426/470, loss: 6.810105323791504
2023-01-22 16:30:03.262593: step: 428/470, loss: 3.282905101776123
2023-01-22 16:30:04.028854: step: 430/470, loss: 1.8343316316604614
2023-01-22 16:30:04.752933: step: 432/470, loss: 1.6074039936065674
2023-01-22 16:30:05.481926: step: 434/470, loss: 0.9173816442489624
2023-01-22 16:30:06.184416: step: 436/470, loss: 2.9239602088928223
2023-01-22 16:30:06.906799: step: 438/470, loss: 2.229067802429199
2023-01-22 16:30:07.571028: step: 440/470, loss: 6.852571487426758
2023-01-22 16:30:08.304921: step: 442/470, loss: 3.8243494033813477
2023-01-22 16:30:09.019601: step: 444/470, loss: 5.331119537353516
2023-01-22 16:30:09.792816: step: 446/470, loss: 1.5648657083511353
2023-01-22 16:30:10.543117: step: 448/470, loss: 5.23274040222168
2023-01-22 16:30:11.339273: step: 450/470, loss: 2.8647255897521973
2023-01-22 16:30:12.070170: step: 452/470, loss: 4.566137790679932
2023-01-22 16:30:12.787693: step: 454/470, loss: 2.325453042984009
2023-01-22 16:30:13.479228: step: 456/470, loss: 1.3142560720443726
2023-01-22 16:30:14.268975: step: 458/470, loss: 1.2290973663330078
2023-01-22 16:30:15.000948: step: 460/470, loss: 0.9515959620475769
2023-01-22 16:30:15.718109: step: 462/470, loss: 0.4390300512313843
2023-01-22 16:30:16.646435: step: 464/470, loss: 5.895995140075684
2023-01-22 16:30:17.405628: step: 466/470, loss: 10.302230834960938
2023-01-22 16:30:18.198417: step: 468/470, loss: 0.4556967318058014
2023-01-22 16:30:19.025299: step: 470/470, loss: 4.270013332366943
2023-01-22 16:30:19.715443: step: 472/470, loss: 1.8166708946228027
2023-01-22 16:30:20.408166: step: 474/470, loss: 1.0261110067367554
2023-01-22 16:30:21.214472: step: 476/470, loss: 7.151349067687988
2023-01-22 16:30:22.022588: step: 478/470, loss: 1.8550636768341064
2023-01-22 16:30:22.783505: step: 480/470, loss: 4.943986415863037
2023-01-22 16:30:23.463961: step: 482/470, loss: 1.3664697408676147
2023-01-22 16:30:24.100662: step: 484/470, loss: 0.2491106390953064
2023-01-22 16:30:24.921499: step: 486/470, loss: 2.626844644546509
2023-01-22 16:30:25.616102: step: 488/470, loss: 2.570115804672241
2023-01-22 16:30:26.323434: step: 490/470, loss: 4.202301502227783
2023-01-22 16:30:27.086509: step: 492/470, loss: 0.742546021938324
2023-01-22 16:30:27.811807: step: 494/470, loss: 2.54813814163208
2023-01-22 16:30:28.559560: step: 496/470, loss: 2.840670585632324
2023-01-22 16:30:29.262445: step: 498/470, loss: 1.0759106874465942
2023-01-22 16:30:30.040558: step: 500/470, loss: 3.8876378536224365
2023-01-22 16:30:30.703454: step: 502/470, loss: 1.4235085248947144
2023-01-22 16:30:31.377426: step: 504/470, loss: 0.9331973195075989
2023-01-22 16:30:32.078520: step: 506/470, loss: 0.9420661926269531
2023-01-22 16:30:32.856341: step: 508/470, loss: 3.353362798690796
2023-01-22 16:30:33.666044: step: 510/470, loss: 7.415338516235352
2023-01-22 16:30:34.440345: step: 512/470, loss: 1.1503777503967285
2023-01-22 16:30:35.210540: step: 514/470, loss: 0.5799806118011475
2023-01-22 16:30:35.981582: step: 516/470, loss: 2.527512788772583
2023-01-22 16:30:36.810028: step: 518/470, loss: 3.385176181793213
2023-01-22 16:30:37.519092: step: 520/470, loss: 1.6425435543060303
2023-01-22 16:30:38.220403: step: 522/470, loss: 4.16226863861084
2023-01-22 16:30:39.114462: step: 524/470, loss: 6.3848772048950195
2023-01-22 16:30:39.861030: step: 526/470, loss: 4.581264019012451
2023-01-22 16:30:40.596644: step: 528/470, loss: 1.923591136932373
2023-01-22 16:30:41.402848: step: 530/470, loss: 4.6132893562316895
2023-01-22 16:30:42.199208: step: 532/470, loss: 2.3744194507598877
2023-01-22 16:30:42.933268: step: 534/470, loss: 1.7940552234649658
2023-01-22 16:30:43.707864: step: 536/470, loss: 1.6240293979644775
2023-01-22 16:30:44.393610: step: 538/470, loss: 5.111881256103516
2023-01-22 16:30:45.158489: step: 540/470, loss: 6.182251453399658
2023-01-22 16:30:45.902046: step: 542/470, loss: 5.470218181610107
2023-01-22 16:30:46.682547: step: 544/470, loss: 3.7869865894317627
2023-01-22 16:30:47.434421: step: 546/470, loss: 2.6353919506073
2023-01-22 16:30:48.136726: step: 548/470, loss: 3.2712767124176025
2023-01-22 16:30:48.975020: step: 550/470, loss: 6.047873497009277
2023-01-22 16:30:49.723292: step: 552/470, loss: 5.375014305114746
2023-01-22 16:30:50.387313: step: 554/470, loss: 4.62559175491333
2023-01-22 16:30:51.085633: step: 556/470, loss: 2.0044353008270264
2023-01-22 16:30:51.806604: step: 558/470, loss: 1.5262951850891113
2023-01-22 16:30:52.532422: step: 560/470, loss: 5.368670463562012
2023-01-22 16:30:53.374343: step: 562/470, loss: 4.242199897766113
2023-01-22 16:30:54.117420: step: 564/470, loss: 0.8480384349822998
2023-01-22 16:30:54.869162: step: 566/470, loss: 4.037248134613037
2023-01-22 16:30:55.547625: step: 568/470, loss: 3.518568515777588
2023-01-22 16:30:56.282705: step: 570/470, loss: 2.1327133178710938
2023-01-22 16:30:56.996615: step: 572/470, loss: 2.1160264015197754
2023-01-22 16:30:57.669873: step: 574/470, loss: 3.609269618988037
2023-01-22 16:30:58.371686: step: 576/470, loss: 1.870286226272583
2023-01-22 16:30:59.084207: step: 578/470, loss: 2.7097601890563965
2023-01-22 16:30:59.860679: step: 580/470, loss: 14.343367576599121
2023-01-22 16:31:00.644839: step: 582/470, loss: 2.831430196762085
2023-01-22 16:31:01.423512: step: 584/470, loss: 1.094900369644165
2023-01-22 16:31:02.165464: step: 586/470, loss: 1.2436193227767944
2023-01-22 16:31:02.920754: step: 588/470, loss: 2.6703548431396484
2023-01-22 16:31:03.764347: step: 590/470, loss: 5.652037143707275
2023-01-22 16:31:04.548369: step: 592/470, loss: 0.5362025499343872
2023-01-22 16:31:05.287076: step: 594/470, loss: 2.1328539848327637
2023-01-22 16:31:05.998940: step: 596/470, loss: 1.8717509508132935
2023-01-22 16:31:06.696600: step: 598/470, loss: 0.5863834619522095
2023-01-22 16:31:07.430776: step: 600/470, loss: 1.6512610912322998
2023-01-22 16:31:08.252931: step: 602/470, loss: 2.197679281234741
2023-01-22 16:31:08.991604: step: 604/470, loss: 1.5977303981781006
2023-01-22 16:31:09.722879: step: 606/470, loss: 0.8425391316413879
2023-01-22 16:31:10.492873: step: 608/470, loss: 2.4796876907348633
2023-01-22 16:31:11.272637: step: 610/470, loss: 0.7105655670166016
2023-01-22 16:31:12.041649: step: 612/470, loss: 4.145379066467285
2023-01-22 16:31:12.798499: step: 614/470, loss: 1.9634544849395752
2023-01-22 16:31:13.535670: step: 616/470, loss: 3.2371010780334473
2023-01-22 16:31:14.343769: step: 618/470, loss: 0.9649048447608948
2023-01-22 16:31:15.132795: step: 620/470, loss: 2.4109811782836914
2023-01-22 16:31:15.910393: step: 622/470, loss: 2.8423123359680176
2023-01-22 16:31:16.621541: step: 624/470, loss: 0.7191053628921509
2023-01-22 16:31:17.341439: step: 626/470, loss: 1.9427146911621094
2023-01-22 16:31:17.985096: step: 628/470, loss: 5.957315921783447
2023-01-22 16:31:18.725722: step: 630/470, loss: 1.467832088470459
2023-01-22 16:31:19.427851: step: 632/470, loss: 0.9858548641204834
2023-01-22 16:31:20.217627: step: 634/470, loss: 1.0836055278778076
2023-01-22 16:31:20.970959: step: 636/470, loss: 2.614570140838623
2023-01-22 16:31:21.649260: step: 638/470, loss: 0.810189425945282
2023-01-22 16:31:22.441410: step: 640/470, loss: 3.5685133934020996
2023-01-22 16:31:23.237034: step: 642/470, loss: 2.486414909362793
2023-01-22 16:31:23.907230: step: 644/470, loss: 1.3245995044708252
2023-01-22 16:31:24.667074: step: 646/470, loss: 1.389783263206482
2023-01-22 16:31:25.435723: step: 648/470, loss: 4.989058494567871
2023-01-22 16:31:26.121941: step: 650/470, loss: 0.5294803977012634
2023-01-22 16:31:26.783510: step: 652/470, loss: 2.751239776611328
2023-01-22 16:31:27.441769: step: 654/470, loss: 3.698434829711914
2023-01-22 16:31:28.216439: step: 656/470, loss: 1.105159878730774
2023-01-22 16:31:28.905011: step: 658/470, loss: 1.0109115839004517
2023-01-22 16:31:29.651101: step: 660/470, loss: 3.3653693199157715
2023-01-22 16:31:30.369297: step: 662/470, loss: 3.7181482315063477
2023-01-22 16:31:31.123494: step: 664/470, loss: 2.8250913619995117
2023-01-22 16:31:31.879566: step: 666/470, loss: 0.444732666015625
2023-01-22 16:31:32.575249: step: 668/470, loss: 1.967690348625183
2023-01-22 16:31:33.357618: step: 670/470, loss: 2.671586513519287
2023-01-22 16:31:34.094967: step: 672/470, loss: 0.917386531829834
2023-01-22 16:31:34.893735: step: 674/470, loss: 4.624493598937988
2023-01-22 16:31:35.586949: step: 676/470, loss: 1.2864645719528198
2023-01-22 16:31:36.356469: step: 678/470, loss: 2.9388926029205322
2023-01-22 16:31:37.106340: step: 680/470, loss: 2.476867437362671
2023-01-22 16:31:37.842192: step: 682/470, loss: 1.6455367803573608
2023-01-22 16:31:38.588505: step: 684/470, loss: 0.6645324230194092
2023-01-22 16:31:39.370172: step: 686/470, loss: 2.182851791381836
2023-01-22 16:31:40.092267: step: 688/470, loss: 3.1452040672302246
2023-01-22 16:31:40.839818: step: 690/470, loss: 0.7404079437255859
2023-01-22 16:31:41.616871: step: 692/470, loss: 0.627692461013794
2023-01-22 16:31:42.284344: step: 694/470, loss: 1.6905364990234375
2023-01-22 16:31:43.077003: step: 696/470, loss: 1.0452758073806763
2023-01-22 16:31:43.850733: step: 698/470, loss: 0.6959218382835388
2023-01-22 16:31:44.643254: step: 700/470, loss: 1.0421323776245117
2023-01-22 16:31:45.390008: step: 702/470, loss: 1.0812638998031616
2023-01-22 16:31:46.134785: step: 704/470, loss: 3.0148813724517822
2023-01-22 16:31:46.943820: step: 706/470, loss: 0.7072650790214539
2023-01-22 16:31:47.699108: step: 708/470, loss: 0.5093586444854736
2023-01-22 16:31:48.423684: step: 710/470, loss: 1.3678839206695557
2023-01-22 16:31:49.120486: step: 712/470, loss: 1.5004351139068604
2023-01-22 16:31:49.887001: step: 714/470, loss: 1.0333999395370483
2023-01-22 16:31:50.610095: step: 716/470, loss: 5.288928985595703
2023-01-22 16:31:51.392424: step: 718/470, loss: 4.261580467224121
2023-01-22 16:31:52.119851: step: 720/470, loss: 1.5531013011932373
2023-01-22 16:31:52.827818: step: 722/470, loss: 4.859399795532227
2023-01-22 16:31:53.582500: step: 724/470, loss: 7.980612754821777
2023-01-22 16:31:54.379342: step: 726/470, loss: 4.004562854766846
2023-01-22 16:31:55.107696: step: 728/470, loss: 2.1123268604278564
2023-01-22 16:31:55.923822: step: 730/470, loss: 0.8399812579154968
2023-01-22 16:31:56.756895: step: 732/470, loss: 0.6894631385803223
2023-01-22 16:31:57.501716: step: 734/470, loss: 6.760388374328613
2023-01-22 16:31:58.199683: step: 736/470, loss: 1.1757826805114746
2023-01-22 16:31:58.890396: step: 738/470, loss: 8.832976341247559
2023-01-22 16:31:59.653402: step: 740/470, loss: 2.382441997528076
2023-01-22 16:32:00.409764: step: 742/470, loss: 1.6580554246902466
2023-01-22 16:32:01.126756: step: 744/470, loss: 1.966712236404419
2023-01-22 16:32:01.761866: step: 746/470, loss: 0.506031334400177
2023-01-22 16:32:02.521690: step: 748/470, loss: 1.3848555088043213
2023-01-22 16:32:03.238906: step: 750/470, loss: 1.399755597114563
2023-01-22 16:32:03.974439: step: 752/470, loss: 2.190246343612671
2023-01-22 16:32:04.817809: step: 754/470, loss: 3.1123580932617188
2023-01-22 16:32:05.508410: step: 756/470, loss: 0.292216420173645
2023-01-22 16:32:06.232658: step: 758/470, loss: 5.910808086395264
2023-01-22 16:32:06.876528: step: 760/470, loss: 3.2733473777770996
2023-01-22 16:32:07.708278: step: 762/470, loss: 2.373502254486084
2023-01-22 16:32:08.430636: step: 764/470, loss: 1.994886875152588
2023-01-22 16:32:09.144739: step: 766/470, loss: 8.774368286132812
2023-01-22 16:32:09.812452: step: 768/470, loss: 1.556334376335144
2023-01-22 16:32:10.635718: step: 770/470, loss: 1.234019160270691
2023-01-22 16:32:11.513019: step: 772/470, loss: 2.650935649871826
2023-01-22 16:32:12.229966: step: 774/470, loss: 2.818275213241577
2023-01-22 16:32:12.933528: step: 776/470, loss: 1.808180570602417
2023-01-22 16:32:13.651253: step: 778/470, loss: 1.791804552078247
2023-01-22 16:32:14.374025: step: 780/470, loss: 6.736164569854736
2023-01-22 16:32:15.155031: step: 782/470, loss: 1.3359016180038452
2023-01-22 16:32:15.993911: step: 784/470, loss: 2.8063719272613525
2023-01-22 16:32:16.722229: step: 786/470, loss: 1.5591973066329956
2023-01-22 16:32:17.418800: step: 788/470, loss: 2.6075632572174072
2023-01-22 16:32:18.088539: step: 790/470, loss: 6.299186706542969
2023-01-22 16:32:18.882353: step: 792/470, loss: 2.2583096027374268
2023-01-22 16:32:19.685266: step: 794/470, loss: 0.5692673921585083
2023-01-22 16:32:20.460777: step: 796/470, loss: 1.2285269498825073
2023-01-22 16:32:21.287296: step: 798/470, loss: 3.3300468921661377
2023-01-22 16:32:22.022983: step: 800/470, loss: 0.6767564415931702
2023-01-22 16:32:22.782446: step: 802/470, loss: 1.033461570739746
2023-01-22 16:32:23.515708: step: 804/470, loss: 0.8145455121994019
2023-01-22 16:32:24.255500: step: 806/470, loss: 1.6333547830581665
2023-01-22 16:32:25.017180: step: 808/470, loss: 0.8114295601844788
2023-01-22 16:32:25.740039: step: 810/470, loss: 1.497851014137268
2023-01-22 16:32:26.432625: step: 812/470, loss: 6.200095176696777
2023-01-22 16:32:27.292376: step: 814/470, loss: 6.356876373291016
2023-01-22 16:32:27.996134: step: 816/470, loss: 1.4136056900024414
2023-01-22 16:32:28.735159: step: 818/470, loss: 0.7242187261581421
2023-01-22 16:32:29.480871: step: 820/470, loss: 4.6752166748046875
2023-01-22 16:32:30.202247: step: 822/470, loss: 1.517682433128357
2023-01-22 16:32:30.932655: step: 824/470, loss: 1.7950592041015625
2023-01-22 16:32:31.630654: step: 826/470, loss: 0.6983448266983032
2023-01-22 16:32:32.361197: step: 828/470, loss: 6.089503288269043
2023-01-22 16:32:33.167800: step: 830/470, loss: 0.9322970509529114
2023-01-22 16:32:33.848661: step: 832/470, loss: 1.1994924545288086
2023-01-22 16:32:34.563719: step: 834/470, loss: 7.563248157501221
2023-01-22 16:32:35.268991: step: 836/470, loss: 1.9371384382247925
2023-01-22 16:32:36.049996: step: 838/470, loss: 0.46454671025276184
2023-01-22 16:32:36.758405: step: 840/470, loss: 11.879871368408203
2023-01-22 16:32:37.463320: step: 842/470, loss: 1.3663816452026367
2023-01-22 16:32:38.193096: step: 844/470, loss: 1.1602144241333008
2023-01-22 16:32:38.903091: step: 846/470, loss: 1.8294084072113037
2023-01-22 16:32:39.729822: step: 848/470, loss: 1.413466453552246
2023-01-22 16:32:40.492514: step: 850/470, loss: 0.6919409036636353
2023-01-22 16:32:41.212288: step: 852/470, loss: 1.45651113986969
2023-01-22 16:32:41.908094: step: 854/470, loss: 1.881666898727417
2023-01-22 16:32:42.657191: step: 856/470, loss: 1.315659999847412
2023-01-22 16:32:43.347426: step: 858/470, loss: 1.2165385484695435
2023-01-22 16:32:44.127594: step: 860/470, loss: 0.6869033575057983
2023-01-22 16:32:44.888417: step: 862/470, loss: 4.98539924621582
2023-01-22 16:32:45.663258: step: 864/470, loss: 1.0015603303909302
2023-01-22 16:32:46.391415: step: 866/470, loss: 0.30697131156921387
2023-01-22 16:32:47.107423: step: 868/470, loss: 1.4575281143188477
2023-01-22 16:32:47.845475: step: 870/470, loss: 0.506115734577179
2023-01-22 16:32:48.585493: step: 872/470, loss: 8.884336471557617
2023-01-22 16:32:49.304712: step: 874/470, loss: 1.0489484071731567
2023-01-22 16:32:50.092137: step: 876/470, loss: 3.248522996902466
2023-01-22 16:32:50.877645: step: 878/470, loss: 0.8829824924468994
2023-01-22 16:32:51.685089: step: 880/470, loss: 2.079348564147949
2023-01-22 16:32:52.356020: step: 882/470, loss: 1.2602165937423706
2023-01-22 16:32:53.135681: step: 884/470, loss: 2.2233707904815674
2023-01-22 16:32:54.092858: step: 886/470, loss: 1.2698169946670532
2023-01-22 16:32:54.860337: step: 888/470, loss: 3.4488766193389893
2023-01-22 16:32:55.569146: step: 890/470, loss: 0.7761567831039429
2023-01-22 16:32:56.258650: step: 892/470, loss: 3.291733741760254
2023-01-22 16:32:56.972565: step: 894/470, loss: 1.81295907497406
2023-01-22 16:32:57.663074: step: 896/470, loss: 1.6111295223236084
2023-01-22 16:32:58.395846: step: 898/470, loss: 1.894487977027893
2023-01-22 16:32:59.145052: step: 900/470, loss: 0.7100313901901245
2023-01-22 16:32:59.857498: step: 902/470, loss: 5.061795234680176
2023-01-22 16:33:00.605170: step: 904/470, loss: 1.990469217300415
2023-01-22 16:33:01.376509: step: 906/470, loss: 0.8769509196281433
2023-01-22 16:33:02.168573: step: 908/470, loss: 1.2958335876464844
2023-01-22 16:33:02.863280: step: 910/470, loss: 1.5320318937301636
2023-01-22 16:33:03.635387: step: 912/470, loss: 8.486604690551758
2023-01-22 16:33:04.368716: step: 914/470, loss: 0.8106694221496582
2023-01-22 16:33:05.060248: step: 916/470, loss: 0.887906551361084
2023-01-22 16:33:05.705194: step: 918/470, loss: 2.665186882019043
2023-01-22 16:33:06.373978: step: 920/470, loss: 1.0016103982925415
2023-01-22 16:33:07.149438: step: 922/470, loss: 0.6781519651412964
2023-01-22 16:33:08.017337: step: 924/470, loss: 3.2051515579223633
2023-01-22 16:33:08.784486: step: 926/470, loss: 1.7840149402618408
2023-01-22 16:33:09.461718: step: 928/470, loss: 2.064391851425171
2023-01-22 16:33:10.241116: step: 930/470, loss: 2.9013218879699707
2023-01-22 16:33:10.975961: step: 932/470, loss: 0.4819917678833008
2023-01-22 16:33:11.738411: step: 934/470, loss: 4.124395847320557
2023-01-22 16:33:12.505384: step: 936/470, loss: 2.3460421562194824
2023-01-22 16:33:13.236799: step: 938/470, loss: 8.79629135131836
2023-01-22 16:33:13.990526: step: 940/470, loss: 1.3817631006240845
2023-01-22 16:33:14.699665: step: 942/470, loss: 1.4883410930633545
==================================================
Loss: 5.731
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33518311838624343, 'r': 0.09124077324691691, 'f1': 0.14343646076558408}, 'combined': 0.10569002372200932, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.2739053126711471, 'r': 0.09969733602972788, 'f1': 0.1461854196840392}, 'combined': 0.10182069032719149, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30097601784718353, 'r': 0.0927393022856161, 'f1': 0.1417892800840778}, 'combined': 0.10447631164089942, 'epoch': 0}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.27416930397516703, 'r': 0.10845969592121071, 'f1': 0.1554316026654001}, 'combined': 0.1082608177768956, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31097432659932656, 'r': 0.09523221343873517, 'f1': 0.14581140639389553}, 'combined': 0.10743998365865987, 'epoch': 0}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.2418413267358432, 'r': 0.10470524874003939, 'f1': 0.14613941134304964}, 'combined': 0.101788644716552, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.578125, 'r': 0.13214285714285715, 'f1': 0.21511627906976744}, 'combined': 0.14341085271317827, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.06896551724137931, 'f1': 0.1212121212121212}, 'combined': 0.0808080808080808, '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': 0.33518311838624343, 'r': 0.09124077324691691, 'f1': 0.14343646076558408}, 'combined': 0.10569002372200932, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.2739053126711471, 'r': 0.09969733602972788, 'f1': 0.1461854196840392}, 'combined': 0.10182069032719149, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.578125, 'r': 0.13214285714285715, 'f1': 0.21511627906976744}, 'combined': 0.14341085271317827, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30097601784718353, 'r': 0.0927393022856161, 'f1': 0.1417892800840778}, 'combined': 0.10447631164089942, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.27416930397516703, 'r': 0.10845969592121071, 'f1': 0.1554316026654001}, 'combined': 0.1082608177768956, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31097432659932656, 'r': 0.09523221343873517, 'f1': 0.14581140639389553}, 'combined': 0.10743998365865987, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.2418413267358432, 'r': 0.10470524874003939, 'f1': 0.14613941134304964}, 'combined': 0.101788644716552, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.06896551724137931, 'f1': 0.1212121212121212}, 'combined': 0.0808080808080808, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 16:36:16.480651: step: 2/470, loss: 1.862076997756958
2023-01-22 16:36:17.243062: step: 4/470, loss: 8.447455406188965
2023-01-22 16:36:17.943504: step: 6/470, loss: 2.0555386543273926
2023-01-22 16:36:18.647672: step: 8/470, loss: 1.5882792472839355
2023-01-22 16:36:19.443746: step: 10/470, loss: 3.0211076736450195
2023-01-22 16:36:20.226033: step: 12/470, loss: 6.071506500244141
2023-01-22 16:36:20.930406: step: 14/470, loss: 2.025646209716797
2023-01-22 16:36:21.711121: step: 16/470, loss: 5.890591621398926
2023-01-22 16:36:22.453696: step: 18/470, loss: 0.7686997056007385
2023-01-22 16:36:23.137618: step: 20/470, loss: 0.4861363172531128
2023-01-22 16:36:23.889004: step: 22/470, loss: 4.2360734939575195
2023-01-22 16:36:24.675758: step: 24/470, loss: 2.479112386703491
2023-01-22 16:36:25.434981: step: 26/470, loss: 1.051332712173462
2023-01-22 16:36:26.155653: step: 28/470, loss: 1.299823522567749
2023-01-22 16:36:26.875184: step: 30/470, loss: 1.6598849296569824
2023-01-22 16:36:27.556974: step: 32/470, loss: 1.582511067390442
2023-01-22 16:36:28.311975: step: 34/470, loss: 2.467061758041382
2023-01-22 16:36:29.039736: step: 36/470, loss: 1.9889912605285645
2023-01-22 16:36:29.797325: step: 38/470, loss: 2.0867104530334473
2023-01-22 16:36:30.564853: step: 40/470, loss: 1.2533296346664429
2023-01-22 16:36:31.345157: step: 42/470, loss: 1.3080697059631348
2023-01-22 16:36:32.121979: step: 44/470, loss: 1.3241928815841675
2023-01-22 16:36:32.831472: step: 46/470, loss: 5.139832019805908
2023-01-22 16:36:33.584460: step: 48/470, loss: 0.5771458148956299
2023-01-22 16:36:34.309918: step: 50/470, loss: 0.29020386934280396
2023-01-22 16:36:35.021415: step: 52/470, loss: 0.8561909198760986
2023-01-22 16:36:35.817069: step: 54/470, loss: 1.4810162782669067
2023-01-22 16:36:36.579345: step: 56/470, loss: 2.2414615154266357
2023-01-22 16:36:37.598999: step: 58/470, loss: 2.6271400451660156
2023-01-22 16:36:38.346322: step: 60/470, loss: 17.625469207763672
2023-01-22 16:36:39.057294: step: 62/470, loss: 2.8227107524871826
2023-01-22 16:36:39.864386: step: 64/470, loss: 0.8661047220230103
2023-01-22 16:36:40.577751: step: 66/470, loss: 1.7071223258972168
2023-01-22 16:36:41.288113: step: 68/470, loss: 2.8164873123168945
2023-01-22 16:36:41.996801: step: 70/470, loss: 0.5790960788726807
2023-01-22 16:36:42.703320: step: 72/470, loss: 2.1545395851135254
2023-01-22 16:36:43.390082: step: 74/470, loss: 1.5863559246063232
2023-01-22 16:36:44.163005: step: 76/470, loss: 2.1607186794281006
2023-01-22 16:36:45.050838: step: 78/470, loss: 9.826147079467773
2023-01-22 16:36:45.872374: step: 80/470, loss: 0.798759937286377
2023-01-22 16:36:46.666782: step: 82/470, loss: 0.9904079437255859
2023-01-22 16:36:47.469221: step: 84/470, loss: 1.9608020782470703
2023-01-22 16:36:48.255117: step: 86/470, loss: 1.5990160703659058
2023-01-22 16:36:49.011709: step: 88/470, loss: 0.8718377351760864
2023-01-22 16:36:49.923266: step: 90/470, loss: 2.45064640045166
2023-01-22 16:36:50.577887: step: 92/470, loss: 1.367138385772705
2023-01-22 16:36:51.305732: step: 94/470, loss: 0.5553440451622009
2023-01-22 16:36:52.020158: step: 96/470, loss: 2.1003284454345703
2023-01-22 16:36:52.704784: step: 98/470, loss: 0.6784709692001343
2023-01-22 16:36:53.418185: step: 100/470, loss: 4.6824727058410645
2023-01-22 16:36:54.179187: step: 102/470, loss: 3.344106674194336
2023-01-22 16:36:54.870687: step: 104/470, loss: 2.412670612335205
2023-01-22 16:36:55.644845: step: 106/470, loss: 2.828399419784546
2023-01-22 16:36:56.441170: step: 108/470, loss: 6.7077202796936035
2023-01-22 16:36:57.173473: step: 110/470, loss: 0.7992213368415833
2023-01-22 16:36:57.854893: step: 112/470, loss: 2.1331422328948975
2023-01-22 16:36:58.691028: step: 114/470, loss: 3.3567557334899902
2023-01-22 16:36:59.434708: step: 116/470, loss: 0.6175652742385864
2023-01-22 16:37:00.177098: step: 118/470, loss: 1.5179295539855957
2023-01-22 16:37:00.908697: step: 120/470, loss: 10.409992218017578
2023-01-22 16:37:01.680010: step: 122/470, loss: 2.6204042434692383
2023-01-22 16:37:02.427872: step: 124/470, loss: 2.7609641551971436
2023-01-22 16:37:03.260865: step: 126/470, loss: 2.3943400382995605
2023-01-22 16:37:03.958394: step: 128/470, loss: 2.3017160892486572
2023-01-22 16:37:04.715156: step: 130/470, loss: 1.209132194519043
2023-01-22 16:37:05.533541: step: 132/470, loss: 0.7397157549858093
2023-01-22 16:37:06.253807: step: 134/470, loss: 0.7620857954025269
2023-01-22 16:37:06.990011: step: 136/470, loss: 1.7000327110290527
2023-01-22 16:37:07.680720: step: 138/470, loss: 10.088142395019531
2023-01-22 16:37:08.419747: step: 140/470, loss: 1.530067801475525
2023-01-22 16:37:09.109989: step: 142/470, loss: 2.131448984146118
2023-01-22 16:37:09.805160: step: 144/470, loss: 5.388104438781738
2023-01-22 16:37:10.507813: step: 146/470, loss: 0.946931004524231
2023-01-22 16:37:11.235671: step: 148/470, loss: 0.22896254062652588
2023-01-22 16:37:11.953197: step: 150/470, loss: 1.9135855436325073
2023-01-22 16:37:12.685474: step: 152/470, loss: 6.019766807556152
2023-01-22 16:37:13.414582: step: 154/470, loss: 1.4003325700759888
2023-01-22 16:37:14.200022: step: 156/470, loss: 2.2941765785217285
2023-01-22 16:37:15.017230: step: 158/470, loss: 1.0491797924041748
2023-01-22 16:37:15.725751: step: 160/470, loss: 4.415127754211426
2023-01-22 16:37:16.428412: step: 162/470, loss: 1.0620689392089844
2023-01-22 16:37:17.241300: step: 164/470, loss: 1.4155352115631104
2023-01-22 16:37:17.966728: step: 166/470, loss: 1.2267463207244873
2023-01-22 16:37:18.713181: step: 168/470, loss: 1.4995251893997192
2023-01-22 16:37:19.449004: step: 170/470, loss: 0.8310667872428894
2023-01-22 16:37:20.134312: step: 172/470, loss: 1.5570124387741089
2023-01-22 16:37:20.911733: step: 174/470, loss: 0.6260913610458374
2023-01-22 16:37:21.621370: step: 176/470, loss: 1.448913335800171
2023-01-22 16:37:22.351334: step: 178/470, loss: 1.0051169395446777
2023-01-22 16:37:23.074239: step: 180/470, loss: 1.780196189880371
2023-01-22 16:37:23.841874: step: 182/470, loss: 6.025088310241699
2023-01-22 16:37:24.650685: step: 184/470, loss: 0.4942382574081421
2023-01-22 16:37:25.448578: step: 186/470, loss: 1.7729337215423584
2023-01-22 16:37:26.229082: step: 188/470, loss: 3.7398040294647217
2023-01-22 16:37:26.964544: step: 190/470, loss: 1.550480604171753
2023-01-22 16:37:27.707941: step: 192/470, loss: 4.191380023956299
2023-01-22 16:37:28.477994: step: 194/470, loss: 6.224770545959473
2023-01-22 16:37:29.272164: step: 196/470, loss: 4.869048595428467
2023-01-22 16:37:29.961144: step: 198/470, loss: 4.839520454406738
2023-01-22 16:37:30.822519: step: 200/470, loss: 0.34329086542129517
2023-01-22 16:37:31.548507: step: 202/470, loss: 3.1021952629089355
2023-01-22 16:37:32.368864: step: 204/470, loss: 1.2622747421264648
2023-01-22 16:37:33.185121: step: 206/470, loss: 1.1812101602554321
2023-01-22 16:37:33.922310: step: 208/470, loss: 2.3265373706817627
2023-01-22 16:37:34.715657: step: 210/470, loss: 1.3936223983764648
2023-01-22 16:37:35.537620: step: 212/470, loss: 0.3111218810081482
2023-01-22 16:37:36.297423: step: 214/470, loss: 0.7424604892730713
2023-01-22 16:37:37.044623: step: 216/470, loss: 3.502570152282715
2023-01-22 16:37:37.810294: step: 218/470, loss: 0.8425999283790588
2023-01-22 16:37:38.600108: step: 220/470, loss: 5.331447601318359
2023-01-22 16:37:39.319989: step: 222/470, loss: 1.8785395622253418
2023-01-22 16:37:40.158038: step: 224/470, loss: 3.651517868041992
2023-01-22 16:37:40.874448: step: 226/470, loss: 1.545884370803833
2023-01-22 16:37:41.731970: step: 228/470, loss: 0.853326141834259
2023-01-22 16:37:42.479541: step: 230/470, loss: 0.5514891147613525
2023-01-22 16:37:43.287015: step: 232/470, loss: 7.522525787353516
2023-01-22 16:37:43.995357: step: 234/470, loss: 1.4783458709716797
2023-01-22 16:37:44.718938: step: 236/470, loss: 1.1576764583587646
2023-01-22 16:37:45.369881: step: 238/470, loss: 1.4029746055603027
2023-01-22 16:37:46.081386: step: 240/470, loss: 0.9465068578720093
2023-01-22 16:37:46.762277: step: 242/470, loss: 1.4843324422836304
2023-01-22 16:37:47.472108: step: 244/470, loss: 4.074316501617432
2023-01-22 16:37:48.227010: step: 246/470, loss: 0.47795766592025757
2023-01-22 16:37:48.991417: step: 248/470, loss: 0.9381461143493652
2023-01-22 16:37:49.753688: step: 250/470, loss: 1.1530299186706543
2023-01-22 16:37:50.507869: step: 252/470, loss: 5.419069290161133
2023-01-22 16:37:51.323636: step: 254/470, loss: 2.582890272140503
2023-01-22 16:37:52.029152: step: 256/470, loss: 0.4698558449745178
2023-01-22 16:37:52.787400: step: 258/470, loss: 1.4230782985687256
2023-01-22 16:37:53.525622: step: 260/470, loss: 2.6051998138427734
2023-01-22 16:37:54.279753: step: 262/470, loss: 6.613999366760254
2023-01-22 16:37:55.061803: step: 264/470, loss: 0.8363248705863953
2023-01-22 16:37:55.826763: step: 266/470, loss: 2.7337307929992676
2023-01-22 16:37:56.545468: step: 268/470, loss: 0.22095702588558197
2023-01-22 16:37:57.272338: step: 270/470, loss: 3.376373291015625
2023-01-22 16:37:57.996057: step: 272/470, loss: 2.5851681232452393
2023-01-22 16:37:58.747057: step: 274/470, loss: 2.131282091140747
2023-01-22 16:37:59.547735: step: 276/470, loss: 1.776853322982788
2023-01-22 16:38:00.266291: step: 278/470, loss: 1.506990909576416
2023-01-22 16:38:01.070104: step: 280/470, loss: 6.9677934646606445
2023-01-22 16:38:01.831167: step: 282/470, loss: 1.1140801906585693
2023-01-22 16:38:02.536032: step: 284/470, loss: 2.3784890174865723
2023-01-22 16:38:03.245122: step: 286/470, loss: 0.3859087824821472
2023-01-22 16:38:04.088481: step: 288/470, loss: 4.417560577392578
2023-01-22 16:38:04.858312: step: 290/470, loss: 2.1486141681671143
2023-01-22 16:38:05.607534: step: 292/470, loss: 1.0960376262664795
2023-01-22 16:38:06.308601: step: 294/470, loss: 3.9408044815063477
2023-01-22 16:38:07.045096: step: 296/470, loss: 0.7118826508522034
2023-01-22 16:38:07.744909: step: 298/470, loss: 0.3212831914424896
2023-01-22 16:38:08.462910: step: 300/470, loss: 1.278481364250183
2023-01-22 16:38:09.176845: step: 302/470, loss: 5.880828380584717
2023-01-22 16:38:09.867927: step: 304/470, loss: 0.6283556222915649
2023-01-22 16:38:10.705854: step: 306/470, loss: 2.122545003890991
2023-01-22 16:38:11.447865: step: 308/470, loss: 0.7743858098983765
2023-01-22 16:38:12.306976: step: 310/470, loss: 4.460456848144531
2023-01-22 16:38:13.188679: step: 312/470, loss: 2.6492180824279785
2023-01-22 16:38:13.928898: step: 314/470, loss: 1.6523792743682861
2023-01-22 16:38:14.652476: step: 316/470, loss: 0.35584282875061035
2023-01-22 16:38:15.368898: step: 318/470, loss: 0.9775692820549011
2023-01-22 16:38:16.083500: step: 320/470, loss: 1.9322388172149658
2023-01-22 16:38:16.895964: step: 322/470, loss: 1.2334778308868408
2023-01-22 16:38:17.617338: step: 324/470, loss: 0.7135185599327087
2023-01-22 16:38:18.361376: step: 326/470, loss: 2.28690242767334
2023-01-22 16:38:19.099702: step: 328/470, loss: 1.8421454429626465
2023-01-22 16:38:19.822964: step: 330/470, loss: 0.3285214900970459
2023-01-22 16:38:20.486833: step: 332/470, loss: 1.2045437097549438
2023-01-22 16:38:21.168430: step: 334/470, loss: 0.5976580381393433
2023-01-22 16:38:21.920847: step: 336/470, loss: 0.5577397346496582
2023-01-22 16:38:22.644772: step: 338/470, loss: 1.911345362663269
2023-01-22 16:38:23.423178: step: 340/470, loss: 1.0533931255340576
2023-01-22 16:38:24.139054: step: 342/470, loss: 1.1119427680969238
2023-01-22 16:38:24.833854: step: 344/470, loss: 3.2432820796966553
2023-01-22 16:38:25.662084: step: 346/470, loss: 1.752776861190796
2023-01-22 16:38:26.377238: step: 348/470, loss: 0.7811027765274048
2023-01-22 16:38:27.113963: step: 350/470, loss: 9.563486099243164
2023-01-22 16:38:27.833739: step: 352/470, loss: 1.5302809476852417
2023-01-22 16:38:28.595763: step: 354/470, loss: 0.256759375333786
2023-01-22 16:38:29.337535: step: 356/470, loss: 0.8103635311126709
2023-01-22 16:38:30.046702: step: 358/470, loss: 1.6359080076217651
2023-01-22 16:38:30.752202: step: 360/470, loss: 1.4214690923690796
2023-01-22 16:38:31.476896: step: 362/470, loss: 1.7611870765686035
2023-01-22 16:38:32.117941: step: 364/470, loss: 1.1694140434265137
2023-01-22 16:38:32.796208: step: 366/470, loss: 0.360617458820343
2023-01-22 16:38:33.577542: step: 368/470, loss: 1.3414287567138672
2023-01-22 16:38:34.368528: step: 370/470, loss: 3.1062469482421875
2023-01-22 16:38:35.131476: step: 372/470, loss: 1.2116090059280396
2023-01-22 16:38:35.923124: step: 374/470, loss: 2.1322052478790283
2023-01-22 16:38:36.736202: step: 376/470, loss: 2.370061159133911
2023-01-22 16:38:37.474454: step: 378/470, loss: 0.9331423044204712
2023-01-22 16:38:38.273222: step: 380/470, loss: 2.5580132007598877
2023-01-22 16:38:39.026412: step: 382/470, loss: 0.35974249243736267
2023-01-22 16:38:39.872905: step: 384/470, loss: 3.127124786376953
2023-01-22 16:38:40.603476: step: 386/470, loss: 0.8177119493484497
2023-01-22 16:38:41.388091: step: 388/470, loss: 2.3154079914093018
2023-01-22 16:38:42.097386: step: 390/470, loss: 1.1731178760528564
2023-01-22 16:38:42.892609: step: 392/470, loss: 2.1064229011535645
2023-01-22 16:38:43.644901: step: 394/470, loss: 2.3349862098693848
2023-01-22 16:38:44.432356: step: 396/470, loss: 1.1178443431854248
2023-01-22 16:38:45.125670: step: 398/470, loss: 0.28772637248039246
2023-01-22 16:38:45.914803: step: 400/470, loss: 0.7768524289131165
2023-01-22 16:38:46.615056: step: 402/470, loss: 1.5863418579101562
2023-01-22 16:38:47.320917: step: 404/470, loss: 2.128065347671509
2023-01-22 16:38:48.072209: step: 406/470, loss: 0.3368366062641144
2023-01-22 16:38:48.830776: step: 408/470, loss: 1.258863091468811
2023-01-22 16:38:49.561647: step: 410/470, loss: 2.4128575325012207
2023-01-22 16:38:50.297131: step: 412/470, loss: 1.5281002521514893
2023-01-22 16:38:50.944529: step: 414/470, loss: 1.2488266229629517
2023-01-22 16:38:51.666392: step: 416/470, loss: 3.86458683013916
2023-01-22 16:38:52.392572: step: 418/470, loss: 1.467484474182129
2023-01-22 16:38:53.128758: step: 420/470, loss: 6.8370680809021
2023-01-22 16:38:53.912977: step: 422/470, loss: 1.9299228191375732
2023-01-22 16:38:54.625262: step: 424/470, loss: 3.437924861907959
2023-01-22 16:38:55.359794: step: 426/470, loss: 3.256579875946045
2023-01-22 16:38:56.144839: step: 428/470, loss: 7.5270185470581055
2023-01-22 16:38:56.926836: step: 430/470, loss: 2.0738301277160645
2023-01-22 16:38:57.654696: step: 432/470, loss: 1.6853046417236328
2023-01-22 16:38:58.390263: step: 434/470, loss: 1.0764847993850708
2023-01-22 16:38:59.205039: step: 436/470, loss: 2.1314823627471924
2023-01-22 16:38:59.998476: step: 438/470, loss: 0.8061450719833374
2023-01-22 16:39:00.730704: step: 440/470, loss: 0.616207480430603
2023-01-22 16:39:01.546403: step: 442/470, loss: 3.1026275157928467
2023-01-22 16:39:02.379796: step: 444/470, loss: 2.10392689704895
2023-01-22 16:39:03.101934: step: 446/470, loss: 0.5284572839736938
2023-01-22 16:39:03.847071: step: 448/470, loss: 0.8803726434707642
2023-01-22 16:39:04.602063: step: 450/470, loss: 4.2363104820251465
2023-01-22 16:39:05.420261: step: 452/470, loss: 3.7615818977355957
2023-01-22 16:39:06.170882: step: 454/470, loss: 1.4120464324951172
2023-01-22 16:39:06.890624: step: 456/470, loss: 2.512500524520874
2023-01-22 16:39:07.698233: step: 458/470, loss: 0.9251059889793396
2023-01-22 16:39:08.404764: step: 460/470, loss: 1.114088535308838
2023-01-22 16:39:09.101020: step: 462/470, loss: 0.8354222178459167
2023-01-22 16:39:09.782504: step: 464/470, loss: 4.140608310699463
2023-01-22 16:39:10.554608: step: 466/470, loss: 1.2718843221664429
2023-01-22 16:39:11.365229: step: 468/470, loss: 0.8437068462371826
2023-01-22 16:39:12.174162: step: 470/470, loss: 0.7166956663131714
2023-01-22 16:39:12.844803: step: 472/470, loss: 0.8796911835670471
2023-01-22 16:39:13.587049: step: 474/470, loss: 1.966931700706482
2023-01-22 16:39:14.407797: step: 476/470, loss: 1.254460334777832
2023-01-22 16:39:15.092802: step: 478/470, loss: 0.2941884994506836
2023-01-22 16:39:15.859772: step: 480/470, loss: 0.5314381122589111
2023-01-22 16:39:16.687115: step: 482/470, loss: 0.2590300142765045
2023-01-22 16:39:17.528386: step: 484/470, loss: 0.6093426942825317
2023-01-22 16:39:18.239579: step: 486/470, loss: 0.6896905303001404
2023-01-22 16:39:19.087210: step: 488/470, loss: 6.51729679107666
2023-01-22 16:39:19.925379: step: 490/470, loss: 1.2721233367919922
2023-01-22 16:39:20.651677: step: 492/470, loss: 0.5004115700721741
2023-01-22 16:39:21.368082: step: 494/470, loss: 1.5959545373916626
2023-01-22 16:39:22.117633: step: 496/470, loss: 2.6702709197998047
2023-01-22 16:39:22.837111: step: 498/470, loss: 0.9216657876968384
2023-01-22 16:39:23.554869: step: 500/470, loss: 1.1959245204925537
2023-01-22 16:39:24.346099: step: 502/470, loss: 3.9152817726135254
2023-01-22 16:39:25.103867: step: 504/470, loss: 1.635777473449707
2023-01-22 16:39:25.815093: step: 506/470, loss: 0.926995038986206
2023-01-22 16:39:26.574470: step: 508/470, loss: 0.5806446075439453
2023-01-22 16:39:27.293021: step: 510/470, loss: 1.9550533294677734
2023-01-22 16:39:28.094116: step: 512/470, loss: 0.8963161706924438
2023-01-22 16:39:28.897136: step: 514/470, loss: 0.9910989999771118
2023-01-22 16:39:29.540477: step: 516/470, loss: 1.1451404094696045
2023-01-22 16:39:30.262389: step: 518/470, loss: 0.4220796227455139
2023-01-22 16:39:31.075924: step: 520/470, loss: 0.37119582295417786
2023-01-22 16:39:31.939219: step: 522/470, loss: 0.8361790180206299
2023-01-22 16:39:32.700795: step: 524/470, loss: 0.5909321308135986
2023-01-22 16:39:33.484287: step: 526/470, loss: 1.3367969989776611
2023-01-22 16:39:34.202730: step: 528/470, loss: 0.8631378412246704
2023-01-22 16:39:34.964166: step: 530/470, loss: 0.7489875555038452
2023-01-22 16:39:35.740248: step: 532/470, loss: 0.8519724607467651
2023-01-22 16:39:36.442662: step: 534/470, loss: 1.9926557540893555
2023-01-22 16:39:37.177999: step: 536/470, loss: 9.287836074829102
2023-01-22 16:39:37.867771: step: 538/470, loss: 0.34389472007751465
2023-01-22 16:39:38.649745: step: 540/470, loss: 0.8343438506126404
2023-01-22 16:39:39.396849: step: 542/470, loss: 0.582844614982605
2023-01-22 16:39:40.165118: step: 544/470, loss: 8.287338256835938
2023-01-22 16:39:40.868119: step: 546/470, loss: 0.3143865764141083
2023-01-22 16:39:41.605619: step: 548/470, loss: 2.0470499992370605
2023-01-22 16:39:42.296940: step: 550/470, loss: 0.6878257989883423
2023-01-22 16:39:43.035157: step: 552/470, loss: 0.37249213457107544
2023-01-22 16:39:43.781913: step: 554/470, loss: 0.5701853036880493
2023-01-22 16:39:44.540337: step: 556/470, loss: 0.40355125069618225
2023-01-22 16:39:45.215830: step: 558/470, loss: 3.7175612449645996
2023-01-22 16:39:45.844679: step: 560/470, loss: 0.47289979457855225
2023-01-22 16:39:46.587997: step: 562/470, loss: 0.6108911633491516
2023-01-22 16:39:47.301309: step: 564/470, loss: 3.1750166416168213
2023-01-22 16:39:48.099568: step: 566/470, loss: 0.4857003092765808
2023-01-22 16:39:48.824953: step: 568/470, loss: 2.3505191802978516
2023-01-22 16:39:49.619440: step: 570/470, loss: 1.422705888748169
2023-01-22 16:39:50.353230: step: 572/470, loss: 5.138402938842773
2023-01-22 16:39:51.108494: step: 574/470, loss: 3.7409205436706543
2023-01-22 16:39:51.853706: step: 576/470, loss: 4.080702781677246
2023-01-22 16:39:52.571907: step: 578/470, loss: 1.1940529346466064
2023-01-22 16:39:53.344435: step: 580/470, loss: 1.1898057460784912
2023-01-22 16:39:54.186976: step: 582/470, loss: 4.188379764556885
2023-01-22 16:39:55.117984: step: 584/470, loss: 2.8826589584350586
2023-01-22 16:39:55.820956: step: 586/470, loss: 2.7253611087799072
2023-01-22 16:39:56.507538: step: 588/470, loss: 1.339220643043518
2023-01-22 16:39:57.202162: step: 590/470, loss: 0.9713016748428345
2023-01-22 16:39:57.957761: step: 592/470, loss: 0.6565048098564148
2023-01-22 16:39:58.695598: step: 594/470, loss: 0.6998676061630249
2023-01-22 16:39:59.444234: step: 596/470, loss: 5.920351028442383
2023-01-22 16:40:00.169315: step: 598/470, loss: 1.8115699291229248
2023-01-22 16:40:00.897973: step: 600/470, loss: 1.0007771253585815
2023-01-22 16:40:01.651516: step: 602/470, loss: 0.6656914949417114
2023-01-22 16:40:02.377448: step: 604/470, loss: 1.722856879234314
2023-01-22 16:40:03.205231: step: 606/470, loss: 1.1696670055389404
2023-01-22 16:40:03.936984: step: 608/470, loss: 1.6859041452407837
2023-01-22 16:40:04.722245: step: 610/470, loss: 1.470185399055481
2023-01-22 16:40:05.573498: step: 612/470, loss: 1.2091671228408813
2023-01-22 16:40:06.245327: step: 614/470, loss: 0.2507552206516266
2023-01-22 16:40:07.055353: step: 616/470, loss: 0.7892252802848816
2023-01-22 16:40:07.871513: step: 618/470, loss: 5.00029182434082
2023-01-22 16:40:08.536833: step: 620/470, loss: 0.6601501703262329
2023-01-22 16:40:09.292391: step: 622/470, loss: 0.43022409081459045
2023-01-22 16:40:10.110239: step: 624/470, loss: 0.3008459806442261
2023-01-22 16:40:10.903048: step: 626/470, loss: 3.7314624786376953
2023-01-22 16:40:11.633637: step: 628/470, loss: 1.765567421913147
2023-01-22 16:40:12.490497: step: 630/470, loss: 1.6932260990142822
2023-01-22 16:40:13.313237: step: 632/470, loss: 1.9966813325881958
2023-01-22 16:40:14.041122: step: 634/470, loss: 0.7442370653152466
2023-01-22 16:40:14.759189: step: 636/470, loss: 0.33508580923080444
2023-01-22 16:40:15.524477: step: 638/470, loss: 0.5471466779708862
2023-01-22 16:40:16.359262: step: 640/470, loss: 0.6237709522247314
2023-01-22 16:40:17.137071: step: 642/470, loss: 1.7720106840133667
2023-01-22 16:40:17.989491: step: 644/470, loss: 0.4505968987941742
2023-01-22 16:40:18.671054: step: 646/470, loss: 1.4006216526031494
2023-01-22 16:40:19.442014: step: 648/470, loss: 2.9941649436950684
2023-01-22 16:40:20.217256: step: 650/470, loss: 0.3443487286567688
2023-01-22 16:40:20.902034: step: 652/470, loss: 0.7548519968986511
2023-01-22 16:40:21.641671: step: 654/470, loss: 7.085939884185791
2023-01-22 16:40:22.386029: step: 656/470, loss: 1.421372652053833
2023-01-22 16:40:23.133938: step: 658/470, loss: 0.9636402130126953
2023-01-22 16:40:23.809436: step: 660/470, loss: 5.655693054199219
2023-01-22 16:40:24.560409: step: 662/470, loss: 1.7296228408813477
2023-01-22 16:40:25.210168: step: 664/470, loss: 1.15548837184906
2023-01-22 16:40:26.015216: step: 666/470, loss: 5.414955139160156
2023-01-22 16:40:26.763097: step: 668/470, loss: 1.2120192050933838
2023-01-22 16:40:27.586784: step: 670/470, loss: 0.7238351106643677
2023-01-22 16:40:28.290061: step: 672/470, loss: 0.3124326169490814
2023-01-22 16:40:29.064118: step: 674/470, loss: 0.9182902574539185
2023-01-22 16:40:29.838223: step: 676/470, loss: 1.8736960887908936
2023-01-22 16:40:30.582066: step: 678/470, loss: 2.540367841720581
2023-01-22 16:40:31.268371: step: 680/470, loss: 3.663296699523926
2023-01-22 16:40:32.084071: step: 682/470, loss: 0.9578647613525391
2023-01-22 16:40:32.804228: step: 684/470, loss: 1.4884737730026245
2023-01-22 16:40:33.591825: step: 686/470, loss: 0.906496524810791
2023-01-22 16:40:34.300161: step: 688/470, loss: 1.3751282691955566
2023-01-22 16:40:35.054196: step: 690/470, loss: 0.4115382134914398
2023-01-22 16:40:35.867852: step: 692/470, loss: 1.414757251739502
2023-01-22 16:40:36.597172: step: 694/470, loss: 0.8882244825363159
2023-01-22 16:40:37.413530: step: 696/470, loss: 0.3683246076107025
2023-01-22 16:40:38.136134: step: 698/470, loss: 1.179138422012329
2023-01-22 16:40:38.822630: step: 700/470, loss: 1.4897336959838867
2023-01-22 16:40:39.656782: step: 702/470, loss: 0.3474949300289154
2023-01-22 16:40:40.489985: step: 704/470, loss: 2.322219133377075
2023-01-22 16:40:41.232433: step: 706/470, loss: 2.4184319972991943
2023-01-22 16:40:41.918011: step: 708/470, loss: 0.44905775785446167
2023-01-22 16:40:42.680462: step: 710/470, loss: 1.451400637626648
2023-01-22 16:40:43.375655: step: 712/470, loss: 2.693408489227295
2023-01-22 16:40:44.108014: step: 714/470, loss: 0.6166913509368896
2023-01-22 16:40:44.797719: step: 716/470, loss: 1.744429349899292
2023-01-22 16:40:45.559015: step: 718/470, loss: 0.4033623933792114
2023-01-22 16:40:46.251384: step: 720/470, loss: 1.1890370845794678
2023-01-22 16:40:46.958877: step: 722/470, loss: 1.769646406173706
2023-01-22 16:40:47.771597: step: 724/470, loss: 7.846860885620117
2023-01-22 16:40:48.481300: step: 726/470, loss: 1.7710165977478027
2023-01-22 16:40:49.274383: step: 728/470, loss: 0.9685930013656616
2023-01-22 16:40:50.018328: step: 730/470, loss: 1.263967514038086
2023-01-22 16:40:50.864383: step: 732/470, loss: 0.39430445432662964
2023-01-22 16:40:51.609329: step: 734/470, loss: 5.113945960998535
2023-01-22 16:40:52.374693: step: 736/470, loss: 0.29610970616340637
2023-01-22 16:40:53.049152: step: 738/470, loss: 0.3253304660320282
2023-01-22 16:40:53.813317: step: 740/470, loss: 0.6527763605117798
2023-01-22 16:40:54.593481: step: 742/470, loss: 1.0859628915786743
2023-01-22 16:40:55.337445: step: 744/470, loss: 0.3612285256385803
2023-01-22 16:40:56.040284: step: 746/470, loss: 1.7214696407318115
2023-01-22 16:40:56.759563: step: 748/470, loss: 3.29121470451355
2023-01-22 16:40:57.555948: step: 750/470, loss: 2.983771324157715
2023-01-22 16:40:58.298680: step: 752/470, loss: 1.9223625659942627
2023-01-22 16:40:58.990225: step: 754/470, loss: 1.0342754125595093
2023-01-22 16:40:59.727821: step: 756/470, loss: 0.21807289123535156
2023-01-22 16:41:00.458394: step: 758/470, loss: 0.3551430106163025
2023-01-22 16:41:01.160133: step: 760/470, loss: 6.2613372802734375
2023-01-22 16:41:01.856556: step: 762/470, loss: 2.6288414001464844
2023-01-22 16:41:02.510366: step: 764/470, loss: 0.3011544942855835
2023-01-22 16:41:03.230366: step: 766/470, loss: 1.0295944213867188
2023-01-22 16:41:04.020502: step: 768/470, loss: 1.5300159454345703
2023-01-22 16:41:04.803411: step: 770/470, loss: 1.7910230159759521
2023-01-22 16:41:05.580752: step: 772/470, loss: 3.126624584197998
2023-01-22 16:41:06.315093: step: 774/470, loss: 1.3450465202331543
2023-01-22 16:41:07.078216: step: 776/470, loss: 2.3319666385650635
2023-01-22 16:41:07.830642: step: 778/470, loss: 0.3326357901096344
2023-01-22 16:41:08.606111: step: 780/470, loss: 3.0053279399871826
2023-01-22 16:41:09.412323: step: 782/470, loss: 1.9255592823028564
2023-01-22 16:41:10.124161: step: 784/470, loss: 3.3029167652130127
2023-01-22 16:41:10.871759: step: 786/470, loss: 1.8911656141281128
2023-01-22 16:41:11.662456: step: 788/470, loss: 1.2011070251464844
2023-01-22 16:41:12.375729: step: 790/470, loss: 1.5344570875167847
2023-01-22 16:41:13.085648: step: 792/470, loss: 0.8595614433288574
2023-01-22 16:41:13.861565: step: 794/470, loss: 0.2718544006347656
2023-01-22 16:41:14.638311: step: 796/470, loss: 0.30841192603111267
2023-01-22 16:41:15.419287: step: 798/470, loss: 2.8022773265838623
2023-01-22 16:41:16.176594: step: 800/470, loss: 1.4509482383728027
2023-01-22 16:41:16.981681: step: 802/470, loss: 0.4220521152019501
2023-01-22 16:41:17.721390: step: 804/470, loss: 3.620166301727295
2023-01-22 16:41:18.469097: step: 806/470, loss: 0.8263979554176331
2023-01-22 16:41:19.288530: step: 808/470, loss: 3.336337089538574
2023-01-22 16:41:20.093274: step: 810/470, loss: 0.8141534924507141
2023-01-22 16:41:20.856087: step: 812/470, loss: 1.7943094968795776
2023-01-22 16:41:21.685692: step: 814/470, loss: 3.9635958671569824
2023-01-22 16:41:22.435318: step: 816/470, loss: 1.4038106203079224
2023-01-22 16:41:23.113727: step: 818/470, loss: 0.2446841448545456
2023-01-22 16:41:23.846775: step: 820/470, loss: 0.7909644246101379
2023-01-22 16:41:24.542201: step: 822/470, loss: 1.7075693607330322
2023-01-22 16:41:25.253390: step: 824/470, loss: 1.881824254989624
2023-01-22 16:41:25.989064: step: 826/470, loss: 0.8060756325721741
2023-01-22 16:41:26.725231: step: 828/470, loss: 1.0279686450958252
2023-01-22 16:41:27.487315: step: 830/470, loss: 0.47068899869918823
2023-01-22 16:41:28.208745: step: 832/470, loss: 0.6771692633628845
2023-01-22 16:41:28.976221: step: 834/470, loss: 1.3380112648010254
2023-01-22 16:41:29.669634: step: 836/470, loss: 1.1310175657272339
2023-01-22 16:41:30.368588: step: 838/470, loss: 0.6593484878540039
2023-01-22 16:41:31.075063: step: 840/470, loss: 2.9913806915283203
2023-01-22 16:41:31.826241: step: 842/470, loss: 2.463867664337158
2023-01-22 16:41:32.543529: step: 844/470, loss: 1.755760669708252
2023-01-22 16:41:33.291778: step: 846/470, loss: 0.5958117246627808
2023-01-22 16:41:34.049013: step: 848/470, loss: 1.926990032196045
2023-01-22 16:41:34.799749: step: 850/470, loss: 1.5289037227630615
2023-01-22 16:41:35.527099: step: 852/470, loss: 4.594353199005127
2023-01-22 16:41:36.299770: step: 854/470, loss: 1.013411283493042
2023-01-22 16:41:37.095653: step: 856/470, loss: 14.002585411071777
2023-01-22 16:41:37.796822: step: 858/470, loss: 0.3551334738731384
2023-01-22 16:41:38.633821: step: 860/470, loss: 3.323481559753418
2023-01-22 16:41:39.384518: step: 862/470, loss: 0.4271811842918396
2023-01-22 16:41:40.096011: step: 864/470, loss: 2.759626865386963
2023-01-22 16:41:40.747969: step: 866/470, loss: 2.3287715911865234
2023-01-22 16:41:41.476176: step: 868/470, loss: 1.9157121181488037
2023-01-22 16:41:42.288617: step: 870/470, loss: 0.848456859588623
2023-01-22 16:41:42.999863: step: 872/470, loss: 9.034523963928223
2023-01-22 16:41:43.759967: step: 874/470, loss: 3.3581533432006836
2023-01-22 16:41:44.517449: step: 876/470, loss: 0.41928038001060486
2023-01-22 16:41:45.161043: step: 878/470, loss: 4.671534538269043
2023-01-22 16:41:45.965089: step: 880/470, loss: 1.3843767642974854
2023-01-22 16:41:46.743902: step: 882/470, loss: 0.8925577998161316
2023-01-22 16:41:47.458195: step: 884/470, loss: 0.2983015179634094
2023-01-22 16:41:48.127601: step: 886/470, loss: 1.8470473289489746
2023-01-22 16:41:48.867931: step: 888/470, loss: 2.3493099212646484
2023-01-22 16:41:49.653195: step: 890/470, loss: 1.196245551109314
2023-01-22 16:41:50.364962: step: 892/470, loss: 1.8996955156326294
2023-01-22 16:41:51.119935: step: 894/470, loss: 4.634321212768555
2023-01-22 16:41:51.888415: step: 896/470, loss: 2.013730764389038
2023-01-22 16:41:52.730426: step: 898/470, loss: 0.5299916863441467
2023-01-22 16:41:53.462327: step: 900/470, loss: 1.3865522146224976
2023-01-22 16:41:54.205229: step: 902/470, loss: 0.5649352073669434
2023-01-22 16:41:54.938985: step: 904/470, loss: 0.6543347835540771
2023-01-22 16:41:55.600907: step: 906/470, loss: 1.2292380332946777
2023-01-22 16:41:56.345373: step: 908/470, loss: 0.953291654586792
2023-01-22 16:41:57.038126: step: 910/470, loss: 5.457536220550537
2023-01-22 16:41:57.787227: step: 912/470, loss: 3.373645782470703
2023-01-22 16:41:58.445121: step: 914/470, loss: 3.1682276725769043
2023-01-22 16:41:59.151155: step: 916/470, loss: 1.7389862537384033
2023-01-22 16:41:59.876527: step: 918/470, loss: 0.5257987976074219
2023-01-22 16:42:00.646478: step: 920/470, loss: 0.9832305908203125
2023-01-22 16:42:01.386751: step: 922/470, loss: 1.7744770050048828
2023-01-22 16:42:02.135966: step: 924/470, loss: 0.5747044086456299
2023-01-22 16:42:02.916331: step: 926/470, loss: 0.39155885577201843
2023-01-22 16:42:03.727205: step: 928/470, loss: 0.668175220489502
2023-01-22 16:42:04.447596: step: 930/470, loss: 0.4773980975151062
2023-01-22 16:42:05.284718: step: 932/470, loss: 0.8903824090957642
2023-01-22 16:42:06.041042: step: 934/470, loss: 1.2178103923797607
2023-01-22 16:42:06.795271: step: 936/470, loss: 2.6373496055603027
2023-01-22 16:42:07.586132: step: 938/470, loss: 1.7452850341796875
2023-01-22 16:42:08.253538: step: 940/470, loss: 0.6965129375457764
2023-01-22 16:42:08.886575: step: 942/470, loss: 0.40335753560066223
==================================================
Loss: 2.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2259406997788764, 'r': 0.2511401351039307, 'f1': 0.23787489967767114}, 'combined': 0.17527624186775767, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.29535803921270615, 'r': 0.2254122715372139, 'f1': 0.2556878729889223}, 'combined': 0.17809105581317974, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2176302451673739, 'r': 0.2493079935187686, 'f1': 0.23239458779106356}, 'combined': 0.17123811731973104, 'epoch': 1}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.29179700553582955, 'r': 0.22856965821934105, 'f1': 0.25634210056212126}, 'combined': 0.1785467367099352, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.20295208490866637, 'r': 0.24783940803591395, 'f1': 0.22316093081021016}, 'combined': 0.16443437007068115, 'epoch': 1}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.279769607766213, 'r': 0.2325601629274273, 'f1': 0.25398979050608034}, 'combined': 0.17690831179527985, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.15079365079365079, 'r': 0.2714285714285714, 'f1': 0.19387755102040818}, 'combined': 0.1292517006802721, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.16176470588235295, 'r': 0.2391304347826087, 'f1': 0.1929824561403509}, 'combined': 0.09649122807017545, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2259406997788764, 'r': 0.2511401351039307, 'f1': 0.23787489967767114}, 'combined': 0.17527624186775767, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.29535803921270615, 'r': 0.2254122715372139, 'f1': 0.2556878729889223}, 'combined': 0.17809105581317974, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.15079365079365079, 'r': 0.2714285714285714, 'f1': 0.19387755102040818}, 'combined': 0.1292517006802721, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2176302451673739, 'r': 0.2493079935187686, 'f1': 0.23239458779106356}, 'combined': 0.17123811731973104, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.29179700553582955, 'r': 0.22856965821934105, 'f1': 0.25634210056212126}, 'combined': 0.1785467367099352, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.16176470588235295, 'r': 0.2391304347826087, 'f1': 0.1929824561403509}, 'combined': 0.09649122807017545, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.20295208490866637, 'r': 0.24783940803591395, 'f1': 0.22316093081021016}, 'combined': 0.16443437007068115, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.279769607766213, 'r': 0.2325601629274273, 'f1': 0.25398979050608034}, 'combined': 0.17690831179527985, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 16:45:16.664772: step: 2/470, loss: 2.46811842918396
2023-01-22 16:45:17.460751: step: 4/470, loss: 1.7362735271453857
2023-01-22 16:45:18.179607: step: 6/470, loss: 0.5531305074691772
2023-01-22 16:45:18.945327: step: 8/470, loss: 1.096218228340149
2023-01-22 16:45:19.715510: step: 10/470, loss: 0.9702210426330566
2023-01-22 16:45:20.459498: step: 12/470, loss: 1.731630802154541
2023-01-22 16:45:21.179657: step: 14/470, loss: 2.6520066261291504
2023-01-22 16:45:21.995681: step: 16/470, loss: 0.960263729095459
2023-01-22 16:45:22.626672: step: 18/470, loss: 2.0434067249298096
2023-01-22 16:45:23.343549: step: 20/470, loss: 1.127629280090332
2023-01-22 16:45:24.075024: step: 22/470, loss: 0.27968132495880127
2023-01-22 16:45:24.783281: step: 24/470, loss: 0.7146601676940918
2023-01-22 16:45:25.552160: step: 26/470, loss: 0.5010353922843933
2023-01-22 16:45:26.334503: step: 28/470, loss: 0.7857263088226318
2023-01-22 16:45:27.053639: step: 30/470, loss: 6.040136337280273
2023-01-22 16:45:27.922762: step: 32/470, loss: 0.8596094846725464
2023-01-22 16:45:28.693604: step: 34/470, loss: 0.8374332189559937
2023-01-22 16:45:29.447761: step: 36/470, loss: 0.49315130710601807
2023-01-22 16:45:30.212324: step: 38/470, loss: 0.49098867177963257
2023-01-22 16:45:30.957558: step: 40/470, loss: 0.5622952580451965
2023-01-22 16:45:31.701586: step: 42/470, loss: 0.7310096621513367
2023-01-22 16:45:32.528326: step: 44/470, loss: 0.5263378024101257
2023-01-22 16:45:33.291912: step: 46/470, loss: 1.4505245685577393
2023-01-22 16:45:34.061245: step: 48/470, loss: 0.34201517701148987
2023-01-22 16:45:34.840968: step: 50/470, loss: 8.089656829833984
2023-01-22 16:45:35.617162: step: 52/470, loss: 0.4995441138744354
2023-01-22 16:45:36.568161: step: 54/470, loss: 2.23051118850708
2023-01-22 16:45:37.375644: step: 56/470, loss: 0.6585686206817627
2023-01-22 16:45:38.079660: step: 58/470, loss: 1.034457802772522
2023-01-22 16:45:38.872008: step: 60/470, loss: 1.8960305452346802
2023-01-22 16:45:39.649072: step: 62/470, loss: 1.0263447761535645
2023-01-22 16:45:40.441378: step: 64/470, loss: 1.5714144706726074
2023-01-22 16:45:41.183356: step: 66/470, loss: 2.10054612159729
2023-01-22 16:45:41.950117: step: 68/470, loss: 0.5159252882003784
2023-01-22 16:45:42.699549: step: 70/470, loss: 0.5332794189453125
2023-01-22 16:45:43.539223: step: 72/470, loss: 1.1697885990142822
2023-01-22 16:45:44.241700: step: 74/470, loss: 0.3312620222568512
2023-01-22 16:45:44.921672: step: 76/470, loss: 1.2939296960830688
2023-01-22 16:45:45.656438: step: 78/470, loss: 1.7509288787841797
2023-01-22 16:45:46.312975: step: 80/470, loss: 0.5027635097503662
2023-01-22 16:45:47.091652: step: 82/470, loss: 1.1433383226394653
2023-01-22 16:45:47.833744: step: 84/470, loss: 0.35809245705604553
2023-01-22 16:45:48.566917: step: 86/470, loss: 0.18918129801750183
2023-01-22 16:45:49.375712: step: 88/470, loss: 0.9970061779022217
2023-01-22 16:45:50.120790: step: 90/470, loss: 3.602595090866089
2023-01-22 16:45:50.846612: step: 92/470, loss: 0.8049639463424683
2023-01-22 16:45:51.590277: step: 94/470, loss: 0.3445468544960022
2023-01-22 16:45:52.377373: step: 96/470, loss: 4.520965576171875
2023-01-22 16:45:53.162394: step: 98/470, loss: 1.303832769393921
2023-01-22 16:45:53.888483: step: 100/470, loss: 1.4521981477737427
2023-01-22 16:45:54.556047: step: 102/470, loss: 0.2904055118560791
2023-01-22 16:45:55.313007: step: 104/470, loss: 1.4000365734100342
2023-01-22 16:45:56.090474: step: 106/470, loss: 0.7857203483581543
2023-01-22 16:45:56.914970: step: 108/470, loss: 0.29761266708374023
2023-01-22 16:45:57.666561: step: 110/470, loss: 1.4033076763153076
2023-01-22 16:45:58.386875: step: 112/470, loss: 1.4501266479492188
2023-01-22 16:45:59.148969: step: 114/470, loss: 1.0425773859024048
2023-01-22 16:45:59.854770: step: 116/470, loss: 0.5747327208518982
2023-01-22 16:46:00.562925: step: 118/470, loss: 1.055211067199707
2023-01-22 16:46:01.314134: step: 120/470, loss: 2.8011343479156494
2023-01-22 16:46:02.076401: step: 122/470, loss: 1.3757091760635376
2023-01-22 16:46:02.927559: step: 124/470, loss: 0.9192894101142883
2023-01-22 16:46:03.649847: step: 126/470, loss: 1.9871468544006348
2023-01-22 16:46:04.470186: step: 128/470, loss: 0.4054987132549286
2023-01-22 16:46:05.198885: step: 130/470, loss: 0.4849776327610016
2023-01-22 16:46:05.974132: step: 132/470, loss: 1.0256551504135132
2023-01-22 16:46:06.616585: step: 134/470, loss: 0.4269829988479614
2023-01-22 16:46:07.414300: step: 136/470, loss: 0.9165063500404358
2023-01-22 16:46:08.175107: step: 138/470, loss: 1.5846391916275024
2023-01-22 16:46:08.973714: step: 140/470, loss: 0.4875439703464508
2023-01-22 16:46:09.653024: step: 142/470, loss: 4.090658187866211
2023-01-22 16:46:10.376594: step: 144/470, loss: 2.0160574913024902
2023-01-22 16:46:11.095519: step: 146/470, loss: 0.6893378496170044
2023-01-22 16:46:11.946596: step: 148/470, loss: 9.704105377197266
2023-01-22 16:46:12.708908: step: 150/470, loss: 2.638101100921631
2023-01-22 16:46:13.413871: step: 152/470, loss: 1.744828462600708
2023-01-22 16:46:14.153405: step: 154/470, loss: 0.3475514054298401
2023-01-22 16:46:14.864351: step: 156/470, loss: 0.37182146310806274
2023-01-22 16:46:15.669818: step: 158/470, loss: 2.7568507194519043
2023-01-22 16:46:16.346653: step: 160/470, loss: 4.175437927246094
2023-01-22 16:46:17.157382: step: 162/470, loss: 0.8821776509284973
2023-01-22 16:46:17.907379: step: 164/470, loss: 1.03183913230896
2023-01-22 16:46:18.640631: step: 166/470, loss: 1.8309249877929688
2023-01-22 16:46:19.352362: step: 168/470, loss: 0.4933227300643921
2023-01-22 16:46:20.126633: step: 170/470, loss: 1.0841269493103027
2023-01-22 16:46:20.852654: step: 172/470, loss: 5.927791595458984
2023-01-22 16:46:21.700043: step: 174/470, loss: 1.4856324195861816
2023-01-22 16:46:22.436466: step: 176/470, loss: 0.46990150213241577
2023-01-22 16:46:23.147908: step: 178/470, loss: 1.1630284786224365
2023-01-22 16:46:23.901623: step: 180/470, loss: 0.9261336922645569
2023-01-22 16:46:24.614088: step: 182/470, loss: 0.8008025884628296
2023-01-22 16:46:25.428501: step: 184/470, loss: 6.333198547363281
2023-01-22 16:46:26.226209: step: 186/470, loss: 0.42174702882766724
2023-01-22 16:46:26.974621: step: 188/470, loss: 0.4755881726741791
2023-01-22 16:46:27.748140: step: 190/470, loss: 1.147223949432373
2023-01-22 16:46:28.549111: step: 192/470, loss: 0.19824132323265076
2023-01-22 16:46:29.274847: step: 194/470, loss: 4.473010540008545
2023-01-22 16:46:29.957562: step: 196/470, loss: 0.8954963684082031
2023-01-22 16:46:30.662748: step: 198/470, loss: 0.2654518783092499
2023-01-22 16:46:31.410483: step: 200/470, loss: 2.4173974990844727
2023-01-22 16:46:32.202745: step: 202/470, loss: 0.2253369241952896
2023-01-22 16:46:33.060930: step: 204/470, loss: 0.5632342100143433
2023-01-22 16:46:33.871325: step: 206/470, loss: 1.0098700523376465
2023-01-22 16:46:34.565547: step: 208/470, loss: 0.7151339054107666
2023-01-22 16:46:35.297248: step: 210/470, loss: 1.4566631317138672
2023-01-22 16:46:36.004820: step: 212/470, loss: 1.1144832372665405
2023-01-22 16:46:36.763192: step: 214/470, loss: 0.6245443224906921
2023-01-22 16:46:37.479495: step: 216/470, loss: 3.356032371520996
2023-01-22 16:46:38.223434: step: 218/470, loss: 0.36491915583610535
2023-01-22 16:46:38.968292: step: 220/470, loss: 0.3796614408493042
2023-01-22 16:46:39.748784: step: 222/470, loss: 9.564358711242676
2023-01-22 16:46:40.528899: step: 224/470, loss: 1.751694679260254
2023-01-22 16:46:41.217077: step: 226/470, loss: 0.19614216685295105
2023-01-22 16:46:42.027165: step: 228/470, loss: 1.9366538524627686
2023-01-22 16:46:42.780918: step: 230/470, loss: 2.795724391937256
2023-01-22 16:46:43.456326: step: 232/470, loss: 1.4865249395370483
2023-01-22 16:46:44.169767: step: 234/470, loss: 0.4379088282585144
2023-01-22 16:46:44.903756: step: 236/470, loss: 0.5391400456428528
2023-01-22 16:46:45.707821: step: 238/470, loss: 1.4847371578216553
2023-01-22 16:46:46.537123: step: 240/470, loss: 3.0173943042755127
2023-01-22 16:46:47.315063: step: 242/470, loss: 2.1348071098327637
2023-01-22 16:46:47.978476: step: 244/470, loss: 0.5090938806533813
2023-01-22 16:46:48.743346: step: 246/470, loss: 2.2077693939208984
2023-01-22 16:46:49.492678: step: 248/470, loss: 1.9846214056015015
2023-01-22 16:46:50.279947: step: 250/470, loss: 0.22293855249881744
2023-01-22 16:46:50.980131: step: 252/470, loss: 7.160884857177734
2023-01-22 16:46:51.742296: step: 254/470, loss: 1.7741347551345825
2023-01-22 16:46:52.543465: step: 256/470, loss: 1.3045562505722046
2023-01-22 16:46:53.266679: step: 258/470, loss: 1.059791922569275
2023-01-22 16:46:54.062686: step: 260/470, loss: 1.5100021362304688
2023-01-22 16:46:54.872524: step: 262/470, loss: 0.9539613723754883
2023-01-22 16:46:55.650928: step: 264/470, loss: 0.6949822902679443
2023-01-22 16:46:56.400392: step: 266/470, loss: 0.7878126502037048
2023-01-22 16:46:57.183372: step: 268/470, loss: 0.5556519031524658
2023-01-22 16:46:57.953216: step: 270/470, loss: 0.49442341923713684
2023-01-22 16:46:58.815799: step: 272/470, loss: 1.6977099180221558
2023-01-22 16:46:59.555398: step: 274/470, loss: 0.9501678347587585
2023-01-22 16:47:00.359047: step: 276/470, loss: 0.25947466492652893
2023-01-22 16:47:01.195677: step: 278/470, loss: 8.976275444030762
2023-01-22 16:47:01.973996: step: 280/470, loss: 0.5047112703323364
2023-01-22 16:47:02.751764: step: 282/470, loss: 1.2007783651351929
2023-01-22 16:47:03.563291: step: 284/470, loss: 3.0851497650146484
2023-01-22 16:47:04.407408: step: 286/470, loss: 1.024082064628601
2023-01-22 16:47:05.189433: step: 288/470, loss: 0.8622781038284302
2023-01-22 16:47:05.919796: step: 290/470, loss: 0.44212666153907776
2023-01-22 16:47:06.683615: step: 292/470, loss: 1.0162142515182495
2023-01-22 16:47:07.439857: step: 294/470, loss: 1.515852689743042
2023-01-22 16:47:08.202335: step: 296/470, loss: 0.5383193492889404
2023-01-22 16:47:08.937781: step: 298/470, loss: 1.2464834451675415
2023-01-22 16:47:09.687042: step: 300/470, loss: 4.228458881378174
2023-01-22 16:47:10.539840: step: 302/470, loss: 2.1866626739501953
2023-01-22 16:47:11.224681: step: 304/470, loss: 2.0377941131591797
2023-01-22 16:47:11.942966: step: 306/470, loss: 1.7903894186019897
2023-01-22 16:47:12.687434: step: 308/470, loss: 2.7119550704956055
2023-01-22 16:47:13.531081: step: 310/470, loss: 4.348893642425537
2023-01-22 16:47:14.255732: step: 312/470, loss: 0.4842892289161682
2023-01-22 16:47:15.049579: step: 314/470, loss: 2.1156063079833984
2023-01-22 16:47:15.754398: step: 316/470, loss: 0.7636069059371948
2023-01-22 16:47:16.465761: step: 318/470, loss: 1.8225529193878174
2023-01-22 16:47:17.210282: step: 320/470, loss: 1.8462271690368652
2023-01-22 16:47:17.867670: step: 322/470, loss: 1.2222322225570679
2023-01-22 16:47:18.644975: step: 324/470, loss: 1.3601785898208618
2023-01-22 16:47:19.425498: step: 326/470, loss: 1.628795862197876
2023-01-22 16:47:20.131496: step: 328/470, loss: 0.41737183928489685
2023-01-22 16:47:20.935340: step: 330/470, loss: 0.7214322686195374
2023-01-22 16:47:21.726155: step: 332/470, loss: 0.3991130590438843
2023-01-22 16:47:22.360664: step: 334/470, loss: 1.107088565826416
2023-01-22 16:47:23.087918: step: 336/470, loss: 0.8664273023605347
2023-01-22 16:47:23.774504: step: 338/470, loss: 1.5518001317977905
2023-01-22 16:47:24.501173: step: 340/470, loss: 0.44015198945999146
2023-01-22 16:47:25.263280: step: 342/470, loss: 0.8017760515213013
2023-01-22 16:47:25.946079: step: 344/470, loss: 2.1953208446502686
2023-01-22 16:47:26.689985: step: 346/470, loss: 0.18744251132011414
2023-01-22 16:47:27.412680: step: 348/470, loss: 0.693583071231842
2023-01-22 16:47:28.188304: step: 350/470, loss: 3.926697015762329
2023-01-22 16:47:28.927522: step: 352/470, loss: 2.6467742919921875
2023-01-22 16:47:29.716124: step: 354/470, loss: 0.4489498734474182
2023-01-22 16:47:30.496382: step: 356/470, loss: 0.6220064163208008
2023-01-22 16:47:31.202032: step: 358/470, loss: 0.6211023330688477
2023-01-22 16:47:32.056868: step: 360/470, loss: 1.920097827911377
2023-01-22 16:47:32.787877: step: 362/470, loss: 0.7365934252738953
2023-01-22 16:47:33.515784: step: 364/470, loss: 0.5808885097503662
2023-01-22 16:47:34.259180: step: 366/470, loss: 0.21604259312152863
2023-01-22 16:47:35.037346: step: 368/470, loss: 0.4554995000362396
2023-01-22 16:47:35.775713: step: 370/470, loss: 0.5395200848579407
2023-01-22 16:47:36.579245: step: 372/470, loss: 3.7871570587158203
2023-01-22 16:47:37.318971: step: 374/470, loss: 1.1446315050125122
2023-01-22 16:47:38.042105: step: 376/470, loss: 3.1051321029663086
2023-01-22 16:47:38.758559: step: 378/470, loss: 0.9708766341209412
2023-01-22 16:47:39.494713: step: 380/470, loss: 5.53814697265625
2023-01-22 16:47:40.259706: step: 382/470, loss: 1.891498327255249
2023-01-22 16:47:40.985069: step: 384/470, loss: 0.2550835609436035
2023-01-22 16:47:41.768054: step: 386/470, loss: 0.6128339171409607
2023-01-22 16:47:42.483583: step: 388/470, loss: 0.6527276635169983
2023-01-22 16:47:43.182053: step: 390/470, loss: 1.466606855392456
2023-01-22 16:47:43.924244: step: 392/470, loss: 0.995391845703125
2023-01-22 16:47:44.656721: step: 394/470, loss: 1.0292932987213135
2023-01-22 16:47:45.411679: step: 396/470, loss: 0.5598565340042114
2023-01-22 16:47:46.159185: step: 398/470, loss: 5.429760932922363
2023-01-22 16:47:46.958284: step: 400/470, loss: 0.38686808943748474
2023-01-22 16:47:47.677216: step: 402/470, loss: 1.3042653799057007
2023-01-22 16:47:48.362056: step: 404/470, loss: 0.5991760492324829
2023-01-22 16:47:49.103177: step: 406/470, loss: 0.37910622358322144
2023-01-22 16:47:49.804721: step: 408/470, loss: 1.0450007915496826
2023-01-22 16:47:50.548711: step: 410/470, loss: 0.5937882661819458
2023-01-22 16:47:51.278479: step: 412/470, loss: 9.856136322021484
2023-01-22 16:47:51.969258: step: 414/470, loss: 1.9305442571640015
2023-01-22 16:47:52.691638: step: 416/470, loss: 0.7384703159332275
2023-01-22 16:47:53.477406: step: 418/470, loss: 0.9498000144958496
2023-01-22 16:47:54.274564: step: 420/470, loss: 0.6850473880767822
2023-01-22 16:47:54.998117: step: 422/470, loss: 6.5229716300964355
2023-01-22 16:47:55.707383: step: 424/470, loss: 1.0934593677520752
2023-01-22 16:47:56.459741: step: 426/470, loss: 1.6166236400604248
2023-01-22 16:47:57.153934: step: 428/470, loss: 2.7700743675231934
2023-01-22 16:47:57.915976: step: 430/470, loss: 1.4552366733551025
2023-01-22 16:47:58.597091: step: 432/470, loss: 1.5347661972045898
2023-01-22 16:47:59.331094: step: 434/470, loss: 0.6893869042396545
2023-01-22 16:48:00.157384: step: 436/470, loss: 0.4312663972377777
2023-01-22 16:48:00.924525: step: 438/470, loss: 0.7760770320892334
2023-01-22 16:48:01.621369: step: 440/470, loss: 0.6980346441268921
2023-01-22 16:48:02.409664: step: 442/470, loss: 4.75489616394043
2023-01-22 16:48:03.208715: step: 444/470, loss: 0.6150807738304138
2023-01-22 16:48:04.142138: step: 446/470, loss: 0.39284422993659973
2023-01-22 16:48:04.933273: step: 448/470, loss: 0.1718873381614685
2023-01-22 16:48:05.701288: step: 450/470, loss: 0.7158945798873901
2023-01-22 16:48:06.427759: step: 452/470, loss: 1.1925913095474243
2023-01-22 16:48:07.167962: step: 454/470, loss: 0.5722603797912598
2023-01-22 16:48:07.887175: step: 456/470, loss: 0.9510567784309387
2023-01-22 16:48:08.678351: step: 458/470, loss: 1.4540069103240967
2023-01-22 16:48:09.391150: step: 460/470, loss: 0.47908085584640503
2023-01-22 16:48:10.120182: step: 462/470, loss: 0.5568799376487732
2023-01-22 16:48:10.815306: step: 464/470, loss: 0.4244616627693176
2023-01-22 16:48:11.553303: step: 466/470, loss: 4.02734899520874
2023-01-22 16:48:12.366547: step: 468/470, loss: 0.6745584011077881
2023-01-22 16:48:13.156043: step: 470/470, loss: 1.6514837741851807
2023-01-22 16:48:13.886100: step: 472/470, loss: 1.545167326927185
2023-01-22 16:48:14.655076: step: 474/470, loss: 0.4058355391025543
2023-01-22 16:48:15.406998: step: 476/470, loss: 1.8532984256744385
2023-01-22 16:48:16.129617: step: 478/470, loss: 1.1376888751983643
2023-01-22 16:48:16.888799: step: 480/470, loss: 0.7555640339851379
2023-01-22 16:48:17.661842: step: 482/470, loss: 0.19936880469322205
2023-01-22 16:48:18.424424: step: 484/470, loss: 0.494382381439209
2023-01-22 16:48:19.172815: step: 486/470, loss: 1.0066436529159546
2023-01-22 16:48:20.072950: step: 488/470, loss: 0.6097040772438049
2023-01-22 16:48:20.932692: step: 490/470, loss: 0.35165679454803467
2023-01-22 16:48:21.648491: step: 492/470, loss: 0.39196884632110596
2023-01-22 16:48:22.366240: step: 494/470, loss: 2.287322998046875
2023-01-22 16:48:23.128854: step: 496/470, loss: 3.783491611480713
2023-01-22 16:48:23.843542: step: 498/470, loss: 2.2058379650115967
2023-01-22 16:48:24.651853: step: 500/470, loss: 1.644723653793335
2023-01-22 16:48:25.378720: step: 502/470, loss: 1.0776886940002441
2023-01-22 16:48:26.170243: step: 504/470, loss: 0.33019930124282837
2023-01-22 16:48:26.907795: step: 506/470, loss: 1.2233861684799194
2023-01-22 16:48:27.548170: step: 508/470, loss: 1.0420408248901367
2023-01-22 16:48:28.241555: step: 510/470, loss: 1.1336497068405151
2023-01-22 16:48:28.914754: step: 512/470, loss: 0.4762951731681824
2023-01-22 16:48:29.724914: step: 514/470, loss: 1.8861290216445923
2023-01-22 16:48:30.419106: step: 516/470, loss: 0.4970181882381439
2023-01-22 16:48:31.099806: step: 518/470, loss: 1.4443624019622803
2023-01-22 16:48:31.840208: step: 520/470, loss: 0.6937436461448669
2023-01-22 16:48:32.624412: step: 522/470, loss: 0.9865797758102417
2023-01-22 16:48:33.378387: step: 524/470, loss: 1.8651926517486572
2023-01-22 16:48:34.096785: step: 526/470, loss: 1.1333483457565308
2023-01-22 16:48:34.815927: step: 528/470, loss: 0.9567941427230835
2023-01-22 16:48:35.578392: step: 530/470, loss: 5.231558322906494
2023-01-22 16:48:36.356331: step: 532/470, loss: 2.1264209747314453
2023-01-22 16:48:37.078568: step: 534/470, loss: 1.152343511581421
2023-01-22 16:48:37.849490: step: 536/470, loss: 1.2699055671691895
2023-01-22 16:48:38.612848: step: 538/470, loss: 2.440457820892334
2023-01-22 16:48:39.348578: step: 540/470, loss: 12.110101699829102
2023-01-22 16:48:40.054287: step: 542/470, loss: 0.8827940225601196
2023-01-22 16:48:40.805168: step: 544/470, loss: 4.373961925506592
2023-01-22 16:48:41.545494: step: 546/470, loss: 0.31021592020988464
2023-01-22 16:48:42.225856: step: 548/470, loss: 4.370842456817627
2023-01-22 16:48:42.969507: step: 550/470, loss: 1.5527100563049316
2023-01-22 16:48:43.728335: step: 552/470, loss: 0.6078340411186218
2023-01-22 16:48:44.537604: step: 554/470, loss: 0.5594943761825562
2023-01-22 16:48:45.209979: step: 556/470, loss: 0.26643770933151245
2023-01-22 16:48:45.992292: step: 558/470, loss: 0.5052505731582642
2023-01-22 16:48:46.953989: step: 560/470, loss: 2.0178771018981934
2023-01-22 16:48:47.737293: step: 562/470, loss: 5.040163993835449
2023-01-22 16:48:48.479302: step: 564/470, loss: 1.0909911394119263
2023-01-22 16:48:49.240533: step: 566/470, loss: 0.4415287375450134
2023-01-22 16:48:50.076686: step: 568/470, loss: 2.973421096801758
2023-01-22 16:48:50.727905: step: 570/470, loss: 0.12367182970046997
2023-01-22 16:48:51.550923: step: 572/470, loss: 1.0943719148635864
2023-01-22 16:48:52.320944: step: 574/470, loss: 0.7173348069190979
2023-01-22 16:48:53.040583: step: 576/470, loss: 1.5143998861312866
2023-01-22 16:48:53.761118: step: 578/470, loss: 1.2005535364151
2023-01-22 16:48:54.496932: step: 580/470, loss: 1.2034974098205566
2023-01-22 16:48:55.175883: step: 582/470, loss: 1.0075057744979858
2023-01-22 16:48:55.881779: step: 584/470, loss: 1.3117833137512207
2023-01-22 16:48:56.626069: step: 586/470, loss: 0.3217265009880066
2023-01-22 16:48:57.365051: step: 588/470, loss: 1.2585625648498535
2023-01-22 16:48:58.161874: step: 590/470, loss: 1.6573166847229004
2023-01-22 16:48:58.862339: step: 592/470, loss: 0.7473699450492859
2023-01-22 16:48:59.670027: step: 594/470, loss: 1.4826210737228394
2023-01-22 16:49:00.429787: step: 596/470, loss: 3.1206932067871094
2023-01-22 16:49:01.219332: step: 598/470, loss: 1.286102056503296
2023-01-22 16:49:01.924283: step: 600/470, loss: 0.4325481653213501
2023-01-22 16:49:02.645895: step: 602/470, loss: 0.6148621439933777
2023-01-22 16:49:03.462766: step: 604/470, loss: 0.8197581768035889
2023-01-22 16:49:04.142001: step: 606/470, loss: 1.3260382413864136
2023-01-22 16:49:04.927925: step: 608/470, loss: 0.716848611831665
2023-01-22 16:49:05.598466: step: 610/470, loss: 1.1792848110198975
2023-01-22 16:49:06.395310: step: 612/470, loss: 1.3996143341064453
2023-01-22 16:49:07.085037: step: 614/470, loss: 1.7410094738006592
2023-01-22 16:49:07.875104: step: 616/470, loss: 3.7007956504821777
2023-01-22 16:49:08.577824: step: 618/470, loss: 0.2247745543718338
2023-01-22 16:49:09.360488: step: 620/470, loss: 2.267205238342285
2023-01-22 16:49:10.067911: step: 622/470, loss: 0.4186290204524994
2023-01-22 16:49:10.789386: step: 624/470, loss: 0.8166482448577881
2023-01-22 16:49:11.465073: step: 626/470, loss: 0.4580449163913727
2023-01-22 16:49:12.285706: step: 628/470, loss: 2.071941375732422
2023-01-22 16:49:13.106678: step: 630/470, loss: 1.0789272785186768
2023-01-22 16:49:13.872331: step: 632/470, loss: 1.5344969034194946
2023-01-22 16:49:14.676872: step: 634/470, loss: 1.948580026626587
2023-01-22 16:49:15.425895: step: 636/470, loss: 3.033902168273926
2023-01-22 16:49:16.212890: step: 638/470, loss: 0.23131220042705536
2023-01-22 16:49:16.886598: step: 640/470, loss: 5.123125076293945
2023-01-22 16:49:17.652069: step: 642/470, loss: 0.3747403919696808
2023-01-22 16:49:18.341181: step: 644/470, loss: 0.9803649187088013
2023-01-22 16:49:19.068257: step: 646/470, loss: 1.3845829963684082
2023-01-22 16:49:19.806671: step: 648/470, loss: 0.9319378137588501
2023-01-22 16:49:20.565371: step: 650/470, loss: 1.185803771018982
2023-01-22 16:49:21.314683: step: 652/470, loss: 1.5447531938552856
2023-01-22 16:49:22.052791: step: 654/470, loss: 0.3655240833759308
2023-01-22 16:49:22.713824: step: 656/470, loss: 1.5592364072799683
2023-01-22 16:49:23.466131: step: 658/470, loss: 0.8640881776809692
2023-01-22 16:49:24.214419: step: 660/470, loss: 2.0770931243896484
2023-01-22 16:49:24.982146: step: 662/470, loss: 0.6485579013824463
2023-01-22 16:49:25.747202: step: 664/470, loss: 0.644680380821228
2023-01-22 16:49:26.406102: step: 666/470, loss: 1.5386685132980347
2023-01-22 16:49:27.176717: step: 668/470, loss: 1.689470648765564
2023-01-22 16:49:27.880049: step: 670/470, loss: 0.8974085450172424
2023-01-22 16:49:28.584893: step: 672/470, loss: 2.1679720878601074
2023-01-22 16:49:29.272679: step: 674/470, loss: 0.3004220426082611
2023-01-22 16:49:30.083114: step: 676/470, loss: 1.7437026500701904
2023-01-22 16:49:30.835719: step: 678/470, loss: 1.1159954071044922
2023-01-22 16:49:31.558251: step: 680/470, loss: 0.47660908102989197
2023-01-22 16:49:32.311565: step: 682/470, loss: 7.534053325653076
2023-01-22 16:49:33.084753: step: 684/470, loss: 0.7392002940177917
2023-01-22 16:49:33.809888: step: 686/470, loss: 4.810300350189209
2023-01-22 16:49:34.579906: step: 688/470, loss: 0.2002626359462738
2023-01-22 16:49:35.392996: step: 690/470, loss: 0.3717239499092102
2023-01-22 16:49:36.099607: step: 692/470, loss: 0.9321846961975098
2023-01-22 16:49:36.827077: step: 694/470, loss: 0.8831678032875061
2023-01-22 16:49:37.524009: step: 696/470, loss: 1.0070817470550537
2023-01-22 16:49:38.247026: step: 698/470, loss: 1.1700540781021118
2023-01-22 16:49:38.982005: step: 700/470, loss: 1.3304771184921265
2023-01-22 16:49:39.700192: step: 702/470, loss: 1.0372437238693237
2023-01-22 16:49:40.426629: step: 704/470, loss: 0.636731743812561
2023-01-22 16:49:41.177082: step: 706/470, loss: 0.39378777146339417
2023-01-22 16:49:41.934643: step: 708/470, loss: 2.0515360832214355
2023-01-22 16:49:42.687206: step: 710/470, loss: 0.6573086977005005
2023-01-22 16:49:43.446238: step: 712/470, loss: 2.0945732593536377
2023-01-22 16:49:44.150070: step: 714/470, loss: 0.41838696599006653
2023-01-22 16:49:44.874506: step: 716/470, loss: 0.5202152729034424
2023-01-22 16:49:45.654954: step: 718/470, loss: 1.1282581090927124
2023-01-22 16:49:46.370598: step: 720/470, loss: 0.8712818622589111
2023-01-22 16:49:47.091897: step: 722/470, loss: 0.28079456090927124
2023-01-22 16:49:47.898650: step: 724/470, loss: 1.146299123764038
2023-01-22 16:49:48.608596: step: 726/470, loss: 2.3962433338165283
2023-01-22 16:49:49.340298: step: 728/470, loss: 1.109757423400879
2023-01-22 16:49:50.064993: step: 730/470, loss: 0.8224062323570251
2023-01-22 16:49:50.779120: step: 732/470, loss: 0.716911792755127
2023-01-22 16:49:51.506555: step: 734/470, loss: 0.7856378555297852
2023-01-22 16:49:52.201324: step: 736/470, loss: 0.9323542714118958
2023-01-22 16:49:52.926032: step: 738/470, loss: 1.7010040283203125
2023-01-22 16:49:53.771665: step: 740/470, loss: 0.9458099603652954
2023-01-22 16:49:54.496914: step: 742/470, loss: 0.4535662531852722
2023-01-22 16:49:55.287095: step: 744/470, loss: 1.6949098110198975
2023-01-22 16:49:56.204156: step: 746/470, loss: 0.36973050236701965
2023-01-22 16:49:57.073351: step: 748/470, loss: 1.6900949478149414
2023-01-22 16:49:57.821082: step: 750/470, loss: 0.700052797794342
2023-01-22 16:49:58.701454: step: 752/470, loss: 2.680393934249878
2023-01-22 16:49:59.536635: step: 754/470, loss: 2.4601190090179443
2023-01-22 16:50:00.287815: step: 756/470, loss: 1.6700736284255981
2023-01-22 16:50:01.085950: step: 758/470, loss: 1.34128737449646
2023-01-22 16:50:01.876756: step: 760/470, loss: 1.392914056777954
2023-01-22 16:50:02.676777: step: 762/470, loss: 0.7549951076507568
2023-01-22 16:50:03.380591: step: 764/470, loss: 3.097191333770752
2023-01-22 16:50:04.024930: step: 766/470, loss: 1.1415493488311768
2023-01-22 16:50:04.755224: step: 768/470, loss: 1.2913892269134521
2023-01-22 16:50:05.444411: step: 770/470, loss: 1.9585628509521484
2023-01-22 16:50:06.219182: step: 772/470, loss: 1.1048572063446045
2023-01-22 16:50:06.914161: step: 774/470, loss: 1.6778151988983154
2023-01-22 16:50:07.671228: step: 776/470, loss: 0.4695655107498169
2023-01-22 16:50:08.321872: step: 778/470, loss: 1.7176390886306763
2023-01-22 16:50:09.146810: step: 780/470, loss: 0.1662791669368744
2023-01-22 16:50:09.899080: step: 782/470, loss: 3.580739736557007
2023-01-22 16:50:10.615384: step: 784/470, loss: 0.5405029058456421
2023-01-22 16:50:11.353940: step: 786/470, loss: 0.7567795515060425
2023-01-22 16:50:12.132606: step: 788/470, loss: 1.8015867471694946
2023-01-22 16:50:12.845011: step: 790/470, loss: 3.115386724472046
2023-01-22 16:50:13.607575: step: 792/470, loss: 1.5635459423065186
2023-01-22 16:50:14.350423: step: 794/470, loss: 0.3208344578742981
2023-01-22 16:50:15.118453: step: 796/470, loss: 3.5830130577087402
2023-01-22 16:50:15.846574: step: 798/470, loss: 1.7164645195007324
2023-01-22 16:50:16.588941: step: 800/470, loss: 0.2683294117450714
2023-01-22 16:50:17.259273: step: 802/470, loss: 9.538615226745605
2023-01-22 16:50:18.058307: step: 804/470, loss: 4.4917073249816895
2023-01-22 16:50:18.797985: step: 806/470, loss: 2.0354855060577393
2023-01-22 16:50:19.520375: step: 808/470, loss: 1.513418197631836
2023-01-22 16:50:20.235014: step: 810/470, loss: 1.2347862720489502
2023-01-22 16:50:21.005639: step: 812/470, loss: 2.0256099700927734
2023-01-22 16:50:21.713354: step: 814/470, loss: 2.208359718322754
2023-01-22 16:50:22.473059: step: 816/470, loss: 0.9855014681816101
2023-01-22 16:50:23.212086: step: 818/470, loss: 0.9821873903274536
2023-01-22 16:50:23.993277: step: 820/470, loss: 17.047348022460938
2023-01-22 16:50:24.743323: step: 822/470, loss: 1.7741284370422363
2023-01-22 16:50:25.489331: step: 824/470, loss: 0.6360207200050354
2023-01-22 16:50:26.223565: step: 826/470, loss: 1.1706583499908447
2023-01-22 16:50:27.027321: step: 828/470, loss: 1.1831610202789307
2023-01-22 16:50:27.765275: step: 830/470, loss: 0.9164629578590393
2023-01-22 16:50:28.565788: step: 832/470, loss: 0.7324165105819702
2023-01-22 16:50:29.270988: step: 834/470, loss: 2.8356175422668457
2023-01-22 16:50:29.963208: step: 836/470, loss: 1.6835747957229614
2023-01-22 16:50:30.661194: step: 838/470, loss: 1.1602541208267212
2023-01-22 16:50:31.378727: step: 840/470, loss: 0.8675392866134644
2023-01-22 16:50:32.115063: step: 842/470, loss: 0.9252186417579651
2023-01-22 16:50:32.877515: step: 844/470, loss: 2.3158793449401855
2023-01-22 16:50:33.630949: step: 846/470, loss: 6.0092453956604
2023-01-22 16:50:34.280750: step: 848/470, loss: 1.1773701906204224
2023-01-22 16:50:35.010549: step: 850/470, loss: 2.684903144836426
2023-01-22 16:50:35.802268: step: 852/470, loss: 1.871997356414795
2023-01-22 16:50:36.641077: step: 854/470, loss: 3.4746434688568115
2023-01-22 16:50:37.401720: step: 856/470, loss: 3.444838523864746
2023-01-22 16:50:38.121560: step: 858/470, loss: 2.6179463863372803
2023-01-22 16:50:38.908517: step: 860/470, loss: 0.5549417734146118
2023-01-22 16:50:39.674573: step: 862/470, loss: 1.6258676052093506
2023-01-22 16:50:40.355811: step: 864/470, loss: 0.6284773349761963
2023-01-22 16:50:41.079066: step: 866/470, loss: 2.572608232498169
2023-01-22 16:50:41.745898: step: 868/470, loss: 1.005090594291687
2023-01-22 16:50:42.455391: step: 870/470, loss: 0.31928566098213196
2023-01-22 16:50:43.193877: step: 872/470, loss: 0.3751024603843689
2023-01-22 16:50:43.955087: step: 874/470, loss: 2.8960084915161133
2023-01-22 16:50:44.714753: step: 876/470, loss: 0.4217081069946289
2023-01-22 16:50:45.472320: step: 878/470, loss: 2.551321029663086
2023-01-22 16:50:46.197453: step: 880/470, loss: 5.909186363220215
2023-01-22 16:50:46.975290: step: 882/470, loss: 2.9134228229522705
2023-01-22 16:50:47.806633: step: 884/470, loss: 2.1783947944641113
2023-01-22 16:50:48.546663: step: 886/470, loss: 0.5688473582267761
2023-01-22 16:50:49.298381: step: 888/470, loss: 3.83414888381958
2023-01-22 16:50:50.036664: step: 890/470, loss: 1.6998573541641235
2023-01-22 16:50:50.964272: step: 892/470, loss: 1.6830124855041504
2023-01-22 16:50:51.764611: step: 894/470, loss: 1.0185949802398682
2023-01-22 16:50:52.454568: step: 896/470, loss: 1.8073221445083618
2023-01-22 16:50:53.186981: step: 898/470, loss: 0.8843210339546204
2023-01-22 16:50:53.960777: step: 900/470, loss: 4.365537166595459
2023-01-22 16:50:54.702892: step: 902/470, loss: 0.808355987071991
2023-01-22 16:50:55.583384: step: 904/470, loss: 1.7078111171722412
2023-01-22 16:50:56.344435: step: 906/470, loss: 0.526005208492279
2023-01-22 16:50:57.110576: step: 908/470, loss: 0.30686283111572266
2023-01-22 16:50:57.856907: step: 910/470, loss: 0.9184078574180603
2023-01-22 16:50:58.614122: step: 912/470, loss: 0.605542778968811
2023-01-22 16:50:59.359385: step: 914/470, loss: 0.6337424516677856
2023-01-22 16:51:00.074604: step: 916/470, loss: 1.6130006313323975
2023-01-22 16:51:00.858632: step: 918/470, loss: 4.33975887298584
2023-01-22 16:51:01.684683: step: 920/470, loss: 3.3465535640716553
2023-01-22 16:51:02.478729: step: 922/470, loss: 0.68430495262146
2023-01-22 16:51:03.218735: step: 924/470, loss: 1.328958511352539
2023-01-22 16:51:04.015816: step: 926/470, loss: 2.2398757934570312
2023-01-22 16:51:04.779356: step: 928/470, loss: 1.0955443382263184
2023-01-22 16:51:05.377670: step: 930/470, loss: 1.5726451873779297
2023-01-22 16:51:06.069577: step: 932/470, loss: 1.2137433290481567
2023-01-22 16:51:06.809633: step: 934/470, loss: 1.729867935180664
2023-01-22 16:51:07.707372: step: 936/470, loss: 0.5839881300926208
2023-01-22 16:51:08.401954: step: 938/470, loss: 0.5170664191246033
2023-01-22 16:51:09.146441: step: 940/470, loss: 0.8649019002914429
2023-01-22 16:51:09.924160: step: 942/470, loss: 2.5765528678894043
==================================================
Loss: 1.597
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27756423515352086, 'r': 0.27282404897442847, 'f1': 0.2751737297789929}, 'combined': 0.20275959036346844, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3282026888474822, 'r': 0.25190581017208286, 'f1': 0.28503690042297636}, 'combined': 0.19853316447371488, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2694339847182892, 'r': 0.2719902843835481, 'f1': 0.2707060998491593}, 'combined': 0.19946765252043314, 'epoch': 2}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32578715195855573, 'r': 0.2528684138160548, 'f1': 0.2847333897052602}, 'combined': 0.19832176397381307, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.24997564703352598, 'r': 0.268000456497044, 'f1': 0.2586744332856084}, 'combined': 0.19060221399992197, 'epoch': 2}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32089141554509126, 'r': 0.2626315908207663, 'f1': 0.28885312841459876}, 'combined': 0.2011912337216111, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24695121951219512, 'r': 0.2892857142857143, 'f1': 0.2664473684210527}, 'combined': 0.17763157894736847, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.21153846153846154, 'r': 0.2391304347826087, 'f1': 0.22448979591836737}, 'combined': 0.11224489795918369, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35, 'r': 0.2413793103448276, 'f1': 0.2857142857142857}, 'combined': 0.19047619047619047, 'epoch': 2}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27756423515352086, 'r': 0.27282404897442847, 'f1': 0.2751737297789929}, 'combined': 0.20275959036346844, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3282026888474822, 'r': 0.25190581017208286, 'f1': 0.28503690042297636}, 'combined': 0.19853316447371488, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24695121951219512, 'r': 0.2892857142857143, 'f1': 0.2664473684210527}, 'combined': 0.17763157894736847, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2694339847182892, 'r': 0.2719902843835481, 'f1': 0.2707060998491593}, 'combined': 0.19946765252043314, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32578715195855573, 'r': 0.2528684138160548, 'f1': 0.2847333897052602}, 'combined': 0.19832176397381307, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.21153846153846154, 'r': 0.2391304347826087, 'f1': 0.22448979591836737}, 'combined': 0.11224489795918369, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.20295208490866637, 'r': 0.24783940803591395, 'f1': 0.22316093081021016}, 'combined': 0.16443437007068115, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.279769607766213, 'r': 0.2325601629274273, 'f1': 0.25398979050608034}, 'combined': 0.17690831179527985, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 16:54:08.458371: step: 2/470, loss: 0.36363697052001953
2023-01-22 16:54:09.203976: step: 4/470, loss: 1.200259804725647
2023-01-22 16:54:09.898907: step: 6/470, loss: 0.9495527744293213
2023-01-22 16:54:10.661096: step: 8/470, loss: 6.474288463592529
2023-01-22 16:54:11.426638: step: 10/470, loss: 0.4756370186805725
2023-01-22 16:54:12.184026: step: 12/470, loss: 0.5976176261901855
2023-01-22 16:54:12.915743: step: 14/470, loss: 1.184709906578064
2023-01-22 16:54:13.647706: step: 16/470, loss: 0.3212374746799469
2023-01-22 16:54:14.369824: step: 18/470, loss: 0.17789015173912048
2023-01-22 16:54:15.062485: step: 20/470, loss: 1.2034302949905396
2023-01-22 16:54:15.868036: step: 22/470, loss: 0.7665480375289917
2023-01-22 16:54:16.570729: step: 24/470, loss: 0.40206414461135864
2023-01-22 16:54:17.297221: step: 26/470, loss: 1.6805636882781982
2023-01-22 16:54:18.092256: step: 28/470, loss: 1.1735949516296387
2023-01-22 16:54:18.838141: step: 30/470, loss: 1.2147589921951294
2023-01-22 16:54:19.524715: step: 32/470, loss: 1.4510881900787354
2023-01-22 16:54:20.208098: step: 34/470, loss: 0.7579923272132874
2023-01-22 16:54:20.900316: step: 36/470, loss: 0.22519704699516296
2023-01-22 16:54:21.753219: step: 38/470, loss: 0.5341430306434631
2023-01-22 16:54:22.490532: step: 40/470, loss: 0.6423546075820923
2023-01-22 16:54:23.158413: step: 42/470, loss: 0.5371485948562622
2023-01-22 16:54:23.882928: step: 44/470, loss: 1.21221923828125
2023-01-22 16:54:24.640312: step: 46/470, loss: 2.2409815788269043
2023-01-22 16:54:25.392288: step: 48/470, loss: 2.1587605476379395
2023-01-22 16:54:26.084168: step: 50/470, loss: 0.41026097536087036
2023-01-22 16:54:26.835993: step: 52/470, loss: 1.3984534740447998
2023-01-22 16:54:27.653697: step: 54/470, loss: 0.902085542678833
2023-01-22 16:54:28.424165: step: 56/470, loss: 0.4346156120300293
2023-01-22 16:54:29.184736: step: 58/470, loss: 1.1000165939331055
2023-01-22 16:54:29.958012: step: 60/470, loss: 0.9447662830352783
2023-01-22 16:54:30.614794: step: 62/470, loss: 4.6900763511657715
2023-01-22 16:54:31.330863: step: 64/470, loss: 1.7766426801681519
2023-01-22 16:54:32.065526: step: 66/470, loss: 0.977912187576294
2023-01-22 16:54:32.811410: step: 68/470, loss: 0.8247696161270142
2023-01-22 16:54:33.521916: step: 70/470, loss: 2.7817070484161377
2023-01-22 16:54:34.236756: step: 72/470, loss: 3.9839916229248047
2023-01-22 16:54:35.085210: step: 74/470, loss: 1.374387264251709
2023-01-22 16:54:35.809245: step: 76/470, loss: 0.7330376505851746
2023-01-22 16:54:36.653829: step: 78/470, loss: 2.2703309059143066
2023-01-22 16:54:37.376223: step: 80/470, loss: 0.8914951682090759
2023-01-22 16:54:38.102250: step: 82/470, loss: 1.1255903244018555
2023-01-22 16:54:38.916268: step: 84/470, loss: 2.9205687046051025
2023-01-22 16:54:39.692776: step: 86/470, loss: 0.7798607349395752
2023-01-22 16:54:40.382948: step: 88/470, loss: 1.1443251371383667
2023-01-22 16:54:41.117653: step: 90/470, loss: 1.046618938446045
2023-01-22 16:54:41.870100: step: 92/470, loss: 4.348773956298828
2023-01-22 16:54:42.568803: step: 94/470, loss: 3.3680717945098877
2023-01-22 16:54:43.339918: step: 96/470, loss: 1.9639177322387695
2023-01-22 16:54:44.078196: step: 98/470, loss: 0.4387917220592499
2023-01-22 16:54:44.795592: step: 100/470, loss: 0.3733503222465515
2023-01-22 16:54:45.542425: step: 102/470, loss: 0.8334224224090576
2023-01-22 16:54:46.282724: step: 104/470, loss: 0.9581044912338257
2023-01-22 16:54:47.016630: step: 106/470, loss: 1.0296529531478882
2023-01-22 16:54:47.801773: step: 108/470, loss: 5.17448091506958
2023-01-22 16:54:48.515727: step: 110/470, loss: 0.4054220914840698
2023-01-22 16:54:49.281759: step: 112/470, loss: 0.47016581892967224
2023-01-22 16:54:50.014527: step: 114/470, loss: 0.7138015031814575
2023-01-22 16:54:50.718072: step: 116/470, loss: 0.9061262607574463
2023-01-22 16:54:51.402512: step: 118/470, loss: 0.30310964584350586
2023-01-22 16:54:52.169172: step: 120/470, loss: 0.6186302304267883
2023-01-22 16:54:52.934153: step: 122/470, loss: 1.7593357563018799
2023-01-22 16:54:53.601873: step: 124/470, loss: 0.7808341979980469
2023-01-22 16:54:54.316485: step: 126/470, loss: 1.6488226652145386
2023-01-22 16:54:55.180845: step: 128/470, loss: 0.45947107672691345
2023-01-22 16:54:55.955149: step: 130/470, loss: 1.057709813117981
2023-01-22 16:54:56.621631: step: 132/470, loss: 0.8940787315368652
2023-01-22 16:54:57.356623: step: 134/470, loss: 0.5826739072799683
2023-01-22 16:54:58.103720: step: 136/470, loss: 1.4600317478179932
2023-01-22 16:54:58.879149: step: 138/470, loss: 0.3595348298549652
2023-01-22 16:54:59.681019: step: 140/470, loss: 1.4183976650238037
2023-01-22 16:55:00.382789: step: 142/470, loss: 0.9755016565322876
2023-01-22 16:55:01.137790: step: 144/470, loss: 0.27329689264297485
2023-01-22 16:55:01.876212: step: 146/470, loss: 1.2449324131011963
2023-01-22 16:55:02.619939: step: 148/470, loss: 0.7816654443740845
2023-01-22 16:55:03.471443: step: 150/470, loss: 0.28573817014694214
2023-01-22 16:55:04.266693: step: 152/470, loss: 0.9601019620895386
2023-01-22 16:55:05.061692: step: 154/470, loss: 0.4332647919654846
2023-01-22 16:55:05.820168: step: 156/470, loss: 0.21661068499088287
2023-01-22 16:55:06.470888: step: 158/470, loss: 1.6688331365585327
2023-01-22 16:55:07.206830: step: 160/470, loss: 0.8690783977508545
2023-01-22 16:55:07.879838: step: 162/470, loss: 0.490153968334198
2023-01-22 16:55:08.674468: step: 164/470, loss: 1.6668365001678467
2023-01-22 16:55:09.428850: step: 166/470, loss: 0.7929226160049438
2023-01-22 16:55:10.141740: step: 168/470, loss: 1.0394725799560547
2023-01-22 16:55:10.943651: step: 170/470, loss: 0.30205702781677246
2023-01-22 16:55:11.701839: step: 172/470, loss: 0.9545096158981323
2023-01-22 16:55:12.433073: step: 174/470, loss: 0.2452886998653412
2023-01-22 16:55:13.181172: step: 176/470, loss: 0.3460700213909149
2023-01-22 16:55:13.990481: step: 178/470, loss: 1.1051923036575317
2023-01-22 16:55:14.702219: step: 180/470, loss: 1.239685297012329
2023-01-22 16:55:15.523086: step: 182/470, loss: 0.9798608422279358
2023-01-22 16:55:16.236899: step: 184/470, loss: 2.91426420211792
2023-01-22 16:55:16.960531: step: 186/470, loss: 1.605899453163147
2023-01-22 16:55:17.777311: step: 188/470, loss: 0.4200703501701355
2023-01-22 16:55:18.489947: step: 190/470, loss: 2.6780664920806885
2023-01-22 16:55:19.305244: step: 192/470, loss: 0.3517438471317291
2023-01-22 16:55:20.040710: step: 194/470, loss: 0.46974340081214905
2023-01-22 16:55:20.850891: step: 196/470, loss: 0.29148203134536743
2023-01-22 16:55:21.571462: step: 198/470, loss: 1.264331579208374
2023-01-22 16:55:22.260355: step: 200/470, loss: 0.47580063343048096
2023-01-22 16:55:23.001212: step: 202/470, loss: 1.759827971458435
2023-01-22 16:55:23.714455: step: 204/470, loss: 1.8886005878448486
2023-01-22 16:55:24.440175: step: 206/470, loss: 1.2642725706100464
2023-01-22 16:55:25.206844: step: 208/470, loss: 1.3302885293960571
2023-01-22 16:55:26.003964: step: 210/470, loss: 0.262773334980011
2023-01-22 16:55:26.729162: step: 212/470, loss: 0.39958715438842773
2023-01-22 16:55:27.459638: step: 214/470, loss: 1.108762264251709
2023-01-22 16:55:28.310830: step: 216/470, loss: 0.5211945176124573
2023-01-22 16:55:29.092099: step: 218/470, loss: 0.5695528984069824
2023-01-22 16:55:29.898957: step: 220/470, loss: 0.9404783248901367
2023-01-22 16:55:30.635883: step: 222/470, loss: 5.394157409667969
2023-01-22 16:55:31.445008: step: 224/470, loss: 0.3269270658493042
2023-01-22 16:55:32.172699: step: 226/470, loss: 0.12120553106069565
2023-01-22 16:55:32.853566: step: 228/470, loss: 2.013479232788086
2023-01-22 16:55:33.609554: step: 230/470, loss: 0.7474368810653687
2023-01-22 16:55:34.328784: step: 232/470, loss: 0.8971037864685059
2023-01-22 16:55:35.042542: step: 234/470, loss: 0.8100451827049255
2023-01-22 16:55:35.821010: step: 236/470, loss: 0.3806197941303253
2023-01-22 16:55:36.589129: step: 238/470, loss: 0.3603185713291168
2023-01-22 16:55:37.415629: step: 240/470, loss: 8.618203163146973
2023-01-22 16:55:38.179447: step: 242/470, loss: 0.440914511680603
2023-01-22 16:55:39.024700: step: 244/470, loss: 0.538329005241394
2023-01-22 16:55:39.751318: step: 246/470, loss: 0.6860210299491882
2023-01-22 16:55:40.468459: step: 248/470, loss: 0.5581848621368408
2023-01-22 16:55:41.248147: step: 250/470, loss: 1.4989908933639526
2023-01-22 16:55:41.985802: step: 252/470, loss: 0.3475220799446106
2023-01-22 16:55:42.725558: step: 254/470, loss: 0.6883515119552612
2023-01-22 16:55:43.447521: step: 256/470, loss: 0.3571469783782959
2023-01-22 16:55:44.168973: step: 258/470, loss: 1.115850567817688
2023-01-22 16:55:44.959127: step: 260/470, loss: 0.4317207932472229
2023-01-22 16:55:45.715849: step: 262/470, loss: 0.49563005566596985
2023-01-22 16:55:46.447929: step: 264/470, loss: 0.5665435791015625
2023-01-22 16:55:47.177059: step: 266/470, loss: 0.4394031763076782
2023-01-22 16:55:47.932248: step: 268/470, loss: 1.2470353841781616
2023-01-22 16:55:48.685510: step: 270/470, loss: 0.5768090486526489
2023-01-22 16:55:49.396229: step: 272/470, loss: 1.6476483345031738
2023-01-22 16:55:50.142614: step: 274/470, loss: 1.6945419311523438
2023-01-22 16:55:50.868767: step: 276/470, loss: 0.6581287980079651
2023-01-22 16:55:51.664137: step: 278/470, loss: 0.7141035199165344
2023-01-22 16:55:52.438309: step: 280/470, loss: 1.2979902029037476
2023-01-22 16:55:53.205486: step: 282/470, loss: 2.7254929542541504
2023-01-22 16:55:54.048327: step: 284/470, loss: 3.011003017425537
2023-01-22 16:55:54.801334: step: 286/470, loss: 0.907600998878479
2023-01-22 16:55:55.700058: step: 288/470, loss: 1.4326318502426147
2023-01-22 16:55:56.566812: step: 290/470, loss: 1.6391098499298096
2023-01-22 16:55:57.259009: step: 292/470, loss: 0.27279168367385864
2023-01-22 16:55:57.951183: step: 294/470, loss: 1.117002248764038
2023-01-22 16:55:58.728741: step: 296/470, loss: 0.19795672595500946
2023-01-22 16:55:59.404024: step: 298/470, loss: 0.3689045011997223
2023-01-22 16:56:00.111705: step: 300/470, loss: 2.757559061050415
2023-01-22 16:56:00.878967: step: 302/470, loss: 0.2532775402069092
2023-01-22 16:56:01.658145: step: 304/470, loss: 0.5779852271080017
2023-01-22 16:56:02.329908: step: 306/470, loss: 0.2892742156982422
2023-01-22 16:56:03.084734: step: 308/470, loss: 6.725302696228027
2023-01-22 16:56:03.738756: step: 310/470, loss: 0.16188186407089233
2023-01-22 16:56:04.583886: step: 312/470, loss: 0.713376522064209
2023-01-22 16:56:05.359918: step: 314/470, loss: 0.9798615574836731
2023-01-22 16:56:06.042653: step: 316/470, loss: 0.2618459463119507
2023-01-22 16:56:06.898689: step: 318/470, loss: 0.3729875385761261
2023-01-22 16:56:07.592609: step: 320/470, loss: 1.94132399559021
2023-01-22 16:56:08.375291: step: 322/470, loss: 0.37356746196746826
2023-01-22 16:56:09.077437: step: 324/470, loss: 5.201150417327881
2023-01-22 16:56:09.820991: step: 326/470, loss: 0.7417845129966736
2023-01-22 16:56:10.546220: step: 328/470, loss: 1.832114815711975
2023-01-22 16:56:11.254941: step: 330/470, loss: 1.1253231763839722
2023-01-22 16:56:12.016117: step: 332/470, loss: 0.22344562411308289
2023-01-22 16:56:12.800774: step: 334/470, loss: 0.8852127194404602
2023-01-22 16:56:13.566480: step: 336/470, loss: 0.9841639399528503
2023-01-22 16:56:14.327634: step: 338/470, loss: 1.8902114629745483
2023-01-22 16:56:15.056433: step: 340/470, loss: 0.27074041962623596
2023-01-22 16:56:15.738450: step: 342/470, loss: 0.16591957211494446
2023-01-22 16:56:16.521990: step: 344/470, loss: 0.5446414947509766
2023-01-22 16:56:17.296753: step: 346/470, loss: 1.8010767698287964
2023-01-22 16:56:18.034429: step: 348/470, loss: 0.44357505440711975
2023-01-22 16:56:18.743174: step: 350/470, loss: 4.071453094482422
2023-01-22 16:56:19.735979: step: 352/470, loss: 1.5298190116882324
2023-01-22 16:56:20.578755: step: 354/470, loss: 0.6060335636138916
2023-01-22 16:56:21.273691: step: 356/470, loss: 0.4127192497253418
2023-01-22 16:56:22.013114: step: 358/470, loss: 1.532690167427063
2023-01-22 16:56:22.810677: step: 360/470, loss: 0.8012219667434692
2023-01-22 16:56:23.551809: step: 362/470, loss: 0.5713666677474976
2023-01-22 16:56:24.339806: step: 364/470, loss: 2.333641529083252
2023-01-22 16:56:25.076598: step: 366/470, loss: 1.080212116241455
2023-01-22 16:56:25.753919: step: 368/470, loss: 1.0552024841308594
2023-01-22 16:56:26.458596: step: 370/470, loss: 2.2088849544525146
2023-01-22 16:56:27.216819: step: 372/470, loss: 0.6469262838363647
2023-01-22 16:56:27.944037: step: 374/470, loss: 0.5959089994430542
2023-01-22 16:56:28.716003: step: 376/470, loss: 0.6726745963096619
2023-01-22 16:56:29.375454: step: 378/470, loss: 0.41327551007270813
2023-01-22 16:56:30.193815: step: 380/470, loss: 1.2673792839050293
2023-01-22 16:56:30.925284: step: 382/470, loss: 1.0747371912002563
2023-01-22 16:56:31.707177: step: 384/470, loss: 0.8380264043807983
2023-01-22 16:56:32.418721: step: 386/470, loss: 0.47480469942092896
2023-01-22 16:56:33.172584: step: 388/470, loss: 0.09107540547847748
2023-01-22 16:56:33.893375: step: 390/470, loss: 1.519758939743042
2023-01-22 16:56:34.548526: step: 392/470, loss: 0.8037975430488586
2023-01-22 16:56:35.238994: step: 394/470, loss: 0.9735026359558105
2023-01-22 16:56:36.251570: step: 396/470, loss: 0.7729388475418091
2023-01-22 16:56:36.989273: step: 398/470, loss: 0.43985089659690857
2023-01-22 16:56:37.741629: step: 400/470, loss: 1.1569021940231323
2023-01-22 16:56:38.531676: step: 402/470, loss: 0.90910404920578
2023-01-22 16:56:39.277388: step: 404/470, loss: 1.4025219678878784
2023-01-22 16:56:39.963858: step: 406/470, loss: 0.174116849899292
2023-01-22 16:56:40.729026: step: 408/470, loss: 0.9569568634033203
2023-01-22 16:56:41.521730: step: 410/470, loss: 0.889129638671875
2023-01-22 16:56:42.224580: step: 412/470, loss: 0.5545390844345093
2023-01-22 16:56:42.978803: step: 414/470, loss: 2.280895709991455
2023-01-22 16:56:43.669895: step: 416/470, loss: 0.6171635389328003
2023-01-22 16:56:44.498169: step: 418/470, loss: 2.749620199203491
2023-01-22 16:56:45.205463: step: 420/470, loss: 0.6688118577003479
2023-01-22 16:56:45.930573: step: 422/470, loss: 0.48191848397254944
2023-01-22 16:56:46.662723: step: 424/470, loss: 0.9727869629859924
2023-01-22 16:56:47.396221: step: 426/470, loss: 1.0109034776687622
2023-01-22 16:56:48.186320: step: 428/470, loss: 1.8949697017669678
2023-01-22 16:56:48.993791: step: 430/470, loss: 0.29387497901916504
2023-01-22 16:56:49.728898: step: 432/470, loss: 1.4768874645233154
2023-01-22 16:56:50.523515: step: 434/470, loss: 0.6072927117347717
2023-01-22 16:56:51.291889: step: 436/470, loss: 2.1941230297088623
2023-01-22 16:56:51.935726: step: 438/470, loss: 0.42255786061286926
2023-01-22 16:56:52.639386: step: 440/470, loss: 0.3252505660057068
2023-01-22 16:56:53.391375: step: 442/470, loss: 0.7017578482627869
2023-01-22 16:56:54.105601: step: 444/470, loss: 0.40087300539016724
2023-01-22 16:56:54.897431: step: 446/470, loss: 1.6672818660736084
2023-01-22 16:56:55.637225: step: 448/470, loss: 1.3076132535934448
2023-01-22 16:56:56.402866: step: 450/470, loss: 1.0871223211288452
2023-01-22 16:56:57.202819: step: 452/470, loss: 4.525178909301758
2023-01-22 16:56:58.010844: step: 454/470, loss: 0.15165036916732788
2023-01-22 16:56:58.798644: step: 456/470, loss: 0.9667521715164185
2023-01-22 16:56:59.651479: step: 458/470, loss: 0.9113951325416565
2023-01-22 16:57:00.406860: step: 460/470, loss: 0.8675466775894165
2023-01-22 16:57:01.152875: step: 462/470, loss: 1.114274263381958
2023-01-22 16:57:01.899119: step: 464/470, loss: 0.7635269165039062
2023-01-22 16:57:02.728822: step: 466/470, loss: 0.9710996747016907
2023-01-22 16:57:03.405980: step: 468/470, loss: 0.2852608561515808
2023-01-22 16:57:04.206712: step: 470/470, loss: 0.7204350233078003
2023-01-22 16:57:05.124435: step: 472/470, loss: 9.467118263244629
2023-01-22 16:57:05.870391: step: 474/470, loss: 0.6275573372840881
2023-01-22 16:57:06.637928: step: 476/470, loss: 1.6595731973648071
2023-01-22 16:57:07.502233: step: 478/470, loss: 1.0893810987472534
2023-01-22 16:57:08.306070: step: 480/470, loss: 0.4000731408596039
2023-01-22 16:57:09.036301: step: 482/470, loss: 11.773370742797852
2023-01-22 16:57:09.764914: step: 484/470, loss: 3.65254545211792
2023-01-22 16:57:10.514006: step: 486/470, loss: 1.3855931758880615
2023-01-22 16:57:11.360288: step: 488/470, loss: 0.3679276406764984
2023-01-22 16:57:12.042453: step: 490/470, loss: 0.6360776424407959
2023-01-22 16:57:12.768778: step: 492/470, loss: 3.5798442363739014
2023-01-22 16:57:13.481940: step: 494/470, loss: 0.6142995357513428
2023-01-22 16:57:14.251811: step: 496/470, loss: 2.273555278778076
2023-01-22 16:57:15.028791: step: 498/470, loss: 0.5966622233390808
2023-01-22 16:57:15.798829: step: 500/470, loss: 0.5236387848854065
2023-01-22 16:57:16.589892: step: 502/470, loss: 0.5399066209793091
2023-01-22 16:57:17.291369: step: 504/470, loss: 1.1629985570907593
2023-01-22 16:57:18.169524: step: 506/470, loss: 0.5488350987434387
2023-01-22 16:57:18.852751: step: 508/470, loss: 0.6530537009239197
2023-01-22 16:57:19.650151: step: 510/470, loss: 0.6670851707458496
2023-01-22 16:57:20.412702: step: 512/470, loss: 1.0367801189422607
2023-01-22 16:57:21.130305: step: 514/470, loss: 1.2847917079925537
2023-01-22 16:57:21.953869: step: 516/470, loss: 0.6694021821022034
2023-01-22 16:57:22.629659: step: 518/470, loss: 2.218747138977051
2023-01-22 16:57:23.378622: step: 520/470, loss: 0.42207273840904236
2023-01-22 16:57:24.179029: step: 522/470, loss: 1.1089502573013306
2023-01-22 16:57:24.798497: step: 524/470, loss: 1.3500819206237793
2023-01-22 16:57:25.573241: step: 526/470, loss: 0.6098719835281372
2023-01-22 16:57:26.345734: step: 528/470, loss: 1.7950224876403809
2023-01-22 16:57:27.121413: step: 530/470, loss: 0.34178969264030457
2023-01-22 16:57:27.925345: step: 532/470, loss: 4.002415657043457
2023-01-22 16:57:28.607590: step: 534/470, loss: 0.6252081394195557
2023-01-22 16:57:29.306395: step: 536/470, loss: 1.957798719406128
2023-01-22 16:57:30.086676: step: 538/470, loss: 0.6906619071960449
2023-01-22 16:57:30.892650: step: 540/470, loss: 0.5147668123245239
2023-01-22 16:57:31.650385: step: 542/470, loss: 1.0314600467681885
2023-01-22 16:57:32.414217: step: 544/470, loss: 0.37217873334884644
2023-01-22 16:57:33.177787: step: 546/470, loss: 1.1730372905731201
2023-01-22 16:57:33.882293: step: 548/470, loss: 0.7325170636177063
2023-01-22 16:57:34.636321: step: 550/470, loss: 0.49213165044784546
2023-01-22 16:57:35.421025: step: 552/470, loss: 0.47592616081237793
2023-01-22 16:57:36.295818: step: 554/470, loss: 0.8138816952705383
2023-01-22 16:57:37.091966: step: 556/470, loss: 0.5806734561920166
2023-01-22 16:57:37.865452: step: 558/470, loss: 1.703600525856018
2023-01-22 16:57:38.547678: step: 560/470, loss: 2.787195920944214
2023-01-22 16:57:39.272010: step: 562/470, loss: 0.3978123664855957
2023-01-22 16:57:40.027857: step: 564/470, loss: 1.3924106359481812
2023-01-22 16:57:40.791701: step: 566/470, loss: 0.9471191167831421
2023-01-22 16:57:41.520525: step: 568/470, loss: 0.41248780488967896
2023-01-22 16:57:42.346893: step: 570/470, loss: 1.1843392848968506
2023-01-22 16:57:43.054906: step: 572/470, loss: 1.386232852935791
2023-01-22 16:57:43.774313: step: 574/470, loss: 0.30617228150367737
2023-01-22 16:57:44.580376: step: 576/470, loss: 0.6840832233428955
2023-01-22 16:57:45.352536: step: 578/470, loss: 0.8363122940063477
2023-01-22 16:57:46.087781: step: 580/470, loss: 0.6774252653121948
2023-01-22 16:57:46.911773: step: 582/470, loss: 0.34732234477996826
2023-01-22 16:57:47.620238: step: 584/470, loss: 3.143740653991699
2023-01-22 16:57:48.336714: step: 586/470, loss: 1.0732841491699219
2023-01-22 16:57:49.074721: step: 588/470, loss: 0.6088477373123169
2023-01-22 16:57:49.850699: step: 590/470, loss: 1.6710162162780762
2023-01-22 16:57:50.515259: step: 592/470, loss: 0.8715441226959229
2023-01-22 16:57:51.252856: step: 594/470, loss: 1.7189347743988037
2023-01-22 16:57:51.985875: step: 596/470, loss: 7.218348979949951
2023-01-22 16:57:52.649698: step: 598/470, loss: 2.807617664337158
2023-01-22 16:57:53.394301: step: 600/470, loss: 1.4759058952331543
2023-01-22 16:57:54.195033: step: 602/470, loss: 7.785268306732178
2023-01-22 16:57:54.924764: step: 604/470, loss: 1.1287786960601807
2023-01-22 16:57:55.662666: step: 606/470, loss: 0.3461344242095947
2023-01-22 16:57:56.368064: step: 608/470, loss: 0.34514838457107544
2023-01-22 16:57:57.080780: step: 610/470, loss: 0.30250078439712524
2023-01-22 16:57:57.831067: step: 612/470, loss: 0.9699506163597107
2023-01-22 16:57:58.571155: step: 614/470, loss: 0.9597812294960022
2023-01-22 16:57:59.280701: step: 616/470, loss: 0.7912279963493347
2023-01-22 16:57:59.965542: step: 618/470, loss: 1.2856942415237427
2023-01-22 16:58:00.689350: step: 620/470, loss: 1.5808870792388916
2023-01-22 16:58:01.498708: step: 622/470, loss: 2.507807731628418
2023-01-22 16:58:02.263882: step: 624/470, loss: 0.46560168266296387
2023-01-22 16:58:03.016079: step: 626/470, loss: 0.5538115501403809
2023-01-22 16:58:03.831627: step: 628/470, loss: 0.9292363524436951
2023-01-22 16:58:04.660175: step: 630/470, loss: 0.7725551724433899
2023-01-22 16:58:05.447473: step: 632/470, loss: 1.3639918565750122
2023-01-22 16:58:06.177236: step: 634/470, loss: 1.2045042514801025
2023-01-22 16:58:07.029994: step: 636/470, loss: 1.0402116775512695
2023-01-22 16:58:07.737665: step: 638/470, loss: 1.0203620195388794
2023-01-22 16:58:08.515091: step: 640/470, loss: 1.0372285842895508
2023-01-22 16:58:09.217540: step: 642/470, loss: 4.547273635864258
2023-01-22 16:58:09.879456: step: 644/470, loss: 0.877484917640686
2023-01-22 16:58:10.594806: step: 646/470, loss: 1.7687321901321411
2023-01-22 16:58:11.367037: step: 648/470, loss: 1.9696149826049805
2023-01-22 16:58:12.041599: step: 650/470, loss: 1.9689509868621826
2023-01-22 16:58:12.753847: step: 652/470, loss: 0.36682435870170593
2023-01-22 16:58:13.562624: step: 654/470, loss: 1.2010406255722046
2023-01-22 16:58:14.276800: step: 656/470, loss: 0.7754824757575989
2023-01-22 16:58:15.061327: step: 658/470, loss: 0.16382497549057007
2023-01-22 16:58:15.784739: step: 660/470, loss: 0.6597549915313721
2023-01-22 16:58:16.574082: step: 662/470, loss: 1.6874454021453857
2023-01-22 16:58:17.382601: step: 664/470, loss: 1.7826333045959473
2023-01-22 16:58:18.073327: step: 666/470, loss: 1.3918657302856445
2023-01-22 16:58:18.822695: step: 668/470, loss: 0.9533292055130005
2023-01-22 16:58:19.489801: step: 670/470, loss: 0.17870013415813446
2023-01-22 16:58:20.216277: step: 672/470, loss: 0.4774816632270813
2023-01-22 16:58:20.943047: step: 674/470, loss: 1.4324686527252197
2023-01-22 16:58:21.685867: step: 676/470, loss: 1.8398833274841309
2023-01-22 16:58:22.437269: step: 678/470, loss: 0.42002177238464355
2023-01-22 16:58:23.154904: step: 680/470, loss: 0.953679621219635
2023-01-22 16:58:23.837366: step: 682/470, loss: 0.5611454248428345
2023-01-22 16:58:24.602872: step: 684/470, loss: 0.5755783319473267
2023-01-22 16:58:25.383801: step: 686/470, loss: 0.5575564503669739
2023-01-22 16:58:26.080056: step: 688/470, loss: 0.7334228157997131
2023-01-22 16:58:26.796114: step: 690/470, loss: 4.685910224914551
2023-01-22 16:58:27.520470: step: 692/470, loss: 0.306856632232666
2023-01-22 16:58:28.211856: step: 694/470, loss: 0.8744876980781555
2023-01-22 16:58:28.903335: step: 696/470, loss: 1.340862512588501
2023-01-22 16:58:29.673332: step: 698/470, loss: 2.6037561893463135
2023-01-22 16:58:30.402018: step: 700/470, loss: 0.3846321403980255
2023-01-22 16:58:31.263077: step: 702/470, loss: 1.2338802814483643
2023-01-22 16:58:32.050459: step: 704/470, loss: 0.6107156872749329
2023-01-22 16:58:32.801203: step: 706/470, loss: 1.1513054370880127
2023-01-22 16:58:33.580989: step: 708/470, loss: 1.4285832643508911
2023-01-22 16:58:34.402733: step: 710/470, loss: 1.7846858501434326
2023-01-22 16:58:35.117502: step: 712/470, loss: 0.536953330039978
2023-01-22 16:58:35.900540: step: 714/470, loss: 0.8060521483421326
2023-01-22 16:58:36.636608: step: 716/470, loss: 1.0133894681930542
2023-01-22 16:58:37.380156: step: 718/470, loss: 0.5618113875389099
2023-01-22 16:58:38.111566: step: 720/470, loss: 3.355659246444702
2023-01-22 16:58:38.876451: step: 722/470, loss: 0.5400373935699463
2023-01-22 16:58:39.578480: step: 724/470, loss: 9.46622085571289
2023-01-22 16:58:40.323704: step: 726/470, loss: 1.4518628120422363
2023-01-22 16:58:41.145522: step: 728/470, loss: 0.7577975988388062
2023-01-22 16:58:41.909788: step: 730/470, loss: 3.8897013664245605
2023-01-22 16:58:42.723775: step: 732/470, loss: 0.8022290468215942
2023-01-22 16:58:43.504425: step: 734/470, loss: 1.1684952974319458
2023-01-22 16:58:44.252346: step: 736/470, loss: 1.0844392776489258
2023-01-22 16:58:45.001101: step: 738/470, loss: 1.2642875909805298
2023-01-22 16:58:45.743077: step: 740/470, loss: 0.4668574333190918
2023-01-22 16:58:46.425706: step: 742/470, loss: 0.4412175118923187
2023-01-22 16:58:47.130673: step: 744/470, loss: 0.6135561466217041
2023-01-22 16:58:47.838842: step: 746/470, loss: 2.345003604888916
2023-01-22 16:58:48.591432: step: 748/470, loss: 0.6416370868682861
2023-01-22 16:58:49.371622: step: 750/470, loss: 0.5936519503593445
2023-01-22 16:58:50.112094: step: 752/470, loss: 1.1450408697128296
2023-01-22 16:58:50.805080: step: 754/470, loss: 1.5515800714492798
2023-01-22 16:58:51.575826: step: 756/470, loss: 3.4162683486938477
2023-01-22 16:58:52.251237: step: 758/470, loss: 0.24610131978988647
2023-01-22 16:58:52.962936: step: 760/470, loss: 1.518908977508545
2023-01-22 16:58:53.701607: step: 762/470, loss: 2.093191146850586
2023-01-22 16:58:54.407495: step: 764/470, loss: 0.7881523370742798
2023-01-22 16:58:55.118816: step: 766/470, loss: 1.1381288766860962
2023-01-22 16:58:55.841613: step: 768/470, loss: 0.9814718961715698
2023-01-22 16:58:56.554771: step: 770/470, loss: 1.3323256969451904
2023-01-22 16:58:57.296386: step: 772/470, loss: 2.680574655532837
2023-01-22 16:58:58.058597: step: 774/470, loss: 2.739765167236328
2023-01-22 16:58:58.804040: step: 776/470, loss: 1.2006040811538696
2023-01-22 16:58:59.560955: step: 778/470, loss: 0.9175070524215698
2023-01-22 16:59:00.292041: step: 780/470, loss: 1.995614767074585
2023-01-22 16:59:01.037557: step: 782/470, loss: 0.7214681506156921
2023-01-22 16:59:01.868245: step: 784/470, loss: 1.2614259719848633
2023-01-22 16:59:02.660445: step: 786/470, loss: 1.1801100969314575
2023-01-22 16:59:03.369570: step: 788/470, loss: 1.3768471479415894
2023-01-22 16:59:04.091036: step: 790/470, loss: 0.4173336625099182
2023-01-22 16:59:04.872725: step: 792/470, loss: 0.45784080028533936
2023-01-22 16:59:05.622508: step: 794/470, loss: 1.0468000173568726
2023-01-22 16:59:06.406806: step: 796/470, loss: 2.4224095344543457
2023-01-22 16:59:07.099835: step: 798/470, loss: 2.1978325843811035
2023-01-22 16:59:07.911710: step: 800/470, loss: 0.6861466765403748
2023-01-22 16:59:08.637022: step: 802/470, loss: 2.6235058307647705
2023-01-22 16:59:09.424610: step: 804/470, loss: 1.106905221939087
2023-01-22 16:59:10.150655: step: 806/470, loss: 3.2012083530426025
2023-01-22 16:59:10.908356: step: 808/470, loss: 1.7539875507354736
2023-01-22 16:59:11.633821: step: 810/470, loss: 0.43845510482788086
2023-01-22 16:59:12.377370: step: 812/470, loss: 1.7235209941864014
2023-01-22 16:59:13.191580: step: 814/470, loss: 1.9387578964233398
2023-01-22 16:59:13.930428: step: 816/470, loss: 0.919151782989502
2023-01-22 16:59:14.672913: step: 818/470, loss: 2.7217369079589844
2023-01-22 16:59:15.377530: step: 820/470, loss: 0.5926926732063293
2023-01-22 16:59:16.126616: step: 822/470, loss: 2.346853494644165
2023-01-22 16:59:16.887977: step: 824/470, loss: 0.5080801844596863
2023-01-22 16:59:17.573591: step: 826/470, loss: 1.3107140064239502
2023-01-22 16:59:18.357470: step: 828/470, loss: 0.6457303166389465
2023-01-22 16:59:19.148383: step: 830/470, loss: 0.620394229888916
2023-01-22 16:59:19.902783: step: 832/470, loss: 1.6627405881881714
2023-01-22 16:59:20.618899: step: 834/470, loss: 0.5543290376663208
2023-01-22 16:59:21.385806: step: 836/470, loss: 0.7170817852020264
2023-01-22 16:59:22.160908: step: 838/470, loss: 0.6219049096107483
2023-01-22 16:59:22.925845: step: 840/470, loss: 0.889132022857666
2023-01-22 16:59:23.726482: step: 842/470, loss: 0.6863826513290405
2023-01-22 16:59:24.454471: step: 844/470, loss: 3.6622161865234375
2023-01-22 16:59:25.223572: step: 846/470, loss: 0.48640185594558716
2023-01-22 16:59:25.970247: step: 848/470, loss: 0.3788396418094635
2023-01-22 16:59:26.710692: step: 850/470, loss: 0.2160799503326416
2023-01-22 16:59:27.406427: step: 852/470, loss: 0.4344361126422882
2023-01-22 16:59:28.248044: step: 854/470, loss: 2.5788564682006836
2023-01-22 16:59:29.033962: step: 856/470, loss: 0.9327910542488098
2023-01-22 16:59:29.773823: step: 858/470, loss: 0.6671287417411804
2023-01-22 16:59:30.399871: step: 860/470, loss: 0.8870024085044861
2023-01-22 16:59:31.054385: step: 862/470, loss: 1.443222999572754
2023-01-22 16:59:31.830543: step: 864/470, loss: 0.40049707889556885
2023-01-22 16:59:32.526983: step: 866/470, loss: 0.6292204260826111
2023-01-22 16:59:33.261744: step: 868/470, loss: 0.7831001877784729
2023-01-22 16:59:33.959512: step: 870/470, loss: 1.5764271020889282
2023-01-22 16:59:34.684537: step: 872/470, loss: 0.44661274552345276
2023-01-22 16:59:35.391196: step: 874/470, loss: 1.3428727388381958
2023-01-22 16:59:36.180161: step: 876/470, loss: 0.4933682084083557
2023-01-22 16:59:36.883199: step: 878/470, loss: 3.2525839805603027
2023-01-22 16:59:37.695969: step: 880/470, loss: 2.814858913421631
2023-01-22 16:59:38.578135: step: 882/470, loss: 0.4872850775718689
2023-01-22 16:59:39.392332: step: 884/470, loss: 0.6432516574859619
2023-01-22 16:59:40.163622: step: 886/470, loss: 3.085758924484253
2023-01-22 16:59:40.979752: step: 888/470, loss: 0.3077142834663391
2023-01-22 16:59:41.753826: step: 890/470, loss: 0.7868139743804932
2023-01-22 16:59:42.487169: step: 892/470, loss: 0.7199787497520447
2023-01-22 16:59:43.270896: step: 894/470, loss: 0.8233124017715454
2023-01-22 16:59:44.019177: step: 896/470, loss: 1.426706075668335
2023-01-22 16:59:44.733501: step: 898/470, loss: 3.785362720489502
2023-01-22 16:59:45.534300: step: 900/470, loss: 0.2815132439136505
2023-01-22 16:59:46.278913: step: 902/470, loss: 0.5339265465736389
2023-01-22 16:59:46.971602: step: 904/470, loss: 2.60254168510437
2023-01-22 16:59:47.715654: step: 906/470, loss: 1.4491829872131348
2023-01-22 16:59:48.556911: step: 908/470, loss: 2.853203058242798
2023-01-22 16:59:49.333801: step: 910/470, loss: 0.6764827966690063
2023-01-22 16:59:50.146638: step: 912/470, loss: 1.3102974891662598
2023-01-22 16:59:50.878278: step: 914/470, loss: 1.3560751676559448
2023-01-22 16:59:51.620684: step: 916/470, loss: 1.378153681755066
2023-01-22 16:59:52.349740: step: 918/470, loss: 1.9102532863616943
2023-01-22 16:59:53.037241: step: 920/470, loss: 0.6327913999557495
2023-01-22 16:59:53.738967: step: 922/470, loss: 1.337106466293335
2023-01-22 16:59:54.483384: step: 924/470, loss: 0.5834131836891174
2023-01-22 16:59:55.190173: step: 926/470, loss: 1.6707696914672852
2023-01-22 16:59:55.899248: step: 928/470, loss: 1.1640057563781738
2023-01-22 16:59:56.746363: step: 930/470, loss: 0.6929572224617004
2023-01-22 16:59:57.495300: step: 932/470, loss: 0.8510525226593018
2023-01-22 16:59:58.262274: step: 934/470, loss: 1.042264461517334
2023-01-22 16:59:59.080635: step: 936/470, loss: 2.107961654663086
2023-01-22 16:59:59.948138: step: 938/470, loss: 0.5670161247253418
2023-01-22 17:00:00.727018: step: 940/470, loss: 1.541463017463684
2023-01-22 17:00:01.383375: step: 942/470, loss: 2.885584592819214
==================================================
Loss: 1.284
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30298576732673266, 'r': 0.23139177693761814, 'f1': 0.26239281886387994}, 'combined': 0.19334207705759573, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.38174946184187203, 'r': 0.24166464491238587, 'f1': 0.2959681121809337}, 'combined': 0.20614694380761553, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29876193317422434, 'r': 0.23663752362948962, 'f1': 0.2640954641350211}, 'combined': 0.19459665778369975, 'epoch': 3}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.39738219832697874, 'r': 0.2515608729082411, 'f1': 0.30808808082056355}, 'combined': 0.21458871300934776, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2790948275862069, 'r': 0.2295014177693762, 'f1': 0.2518801867219917}, 'combined': 0.18559592705830966, 'epoch': 3}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.38381273403571387, 'r': 0.24752606264107457, 'f1': 0.3009593433745621}, 'combined': 0.20962342324596367, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2099056603773585, 'r': 0.31785714285714284, 'f1': 0.2528409090909091}, 'combined': 0.16856060606060608, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.23214285714285715, 'r': 0.2826086956521739, 'f1': 0.2549019607843137}, 'combined': 0.12745098039215685, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4411764705882353, 'r': 0.25862068965517243, 'f1': 0.32608695652173914}, 'combined': 0.21739130434782608, 'epoch': 3}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27756423515352086, 'r': 0.27282404897442847, 'f1': 0.2751737297789929}, 'combined': 0.20275959036346844, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3282026888474822, 'r': 0.25190581017208286, 'f1': 0.28503690042297636}, 'combined': 0.19853316447371488, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24695121951219512, 'r': 0.2892857142857143, 'f1': 0.2664473684210527}, 'combined': 0.17763157894736847, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29876193317422434, 'r': 0.23663752362948962, 'f1': 0.2640954641350211}, 'combined': 0.19459665778369975, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.39738219832697874, 'r': 0.2515608729082411, 'f1': 0.30808808082056355}, 'combined': 0.21458871300934776, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.23214285714285715, 'r': 0.2826086956521739, 'f1': 0.2549019607843137}, 'combined': 0.12745098039215685, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.20295208490866637, 'r': 0.24783940803591395, 'f1': 0.22316093081021016}, 'combined': 0.16443437007068115, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.279769607766213, 'r': 0.2325601629274273, 'f1': 0.25398979050608034}, 'combined': 0.17690831179527985, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 1}
******************************
Epoch: 4
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 17:02:44.134532: step: 2/470, loss: 1.2434356212615967
2023-01-22 17:02:44.807854: step: 4/470, loss: 1.2220540046691895
2023-01-22 17:02:45.488020: step: 6/470, loss: 1.7187833786010742
2023-01-22 17:02:46.349722: step: 8/470, loss: 1.2707059383392334
2023-01-22 17:02:47.036983: step: 10/470, loss: 1.190471887588501
2023-01-22 17:02:47.782992: step: 12/470, loss: 0.3669613301753998
2023-01-22 17:02:48.510567: step: 14/470, loss: 2.916283130645752
2023-01-22 17:02:49.349019: step: 16/470, loss: 1.854135513305664
2023-01-22 17:02:50.126509: step: 18/470, loss: 0.7268097400665283
2023-01-22 17:02:50.890671: step: 20/470, loss: 0.864444375038147
2023-01-22 17:02:51.669050: step: 22/470, loss: 0.24146677553653717
2023-01-22 17:02:52.492058: step: 24/470, loss: 1.435685634613037
2023-01-22 17:02:53.223374: step: 26/470, loss: 0.8564450144767761
2023-01-22 17:02:53.904661: step: 28/470, loss: 1.2398236989974976
2023-01-22 17:02:54.655691: step: 30/470, loss: 0.5465511679649353
2023-01-22 17:02:55.324953: step: 32/470, loss: 1.0255184173583984
2023-01-22 17:02:56.059294: step: 34/470, loss: 1.3359484672546387
2023-01-22 17:02:56.730343: step: 36/470, loss: 0.2009323537349701
2023-01-22 17:02:57.550695: step: 38/470, loss: 0.4609377980232239
2023-01-22 17:02:58.285985: step: 40/470, loss: 0.290250301361084
2023-01-22 17:02:59.052800: step: 42/470, loss: 0.2391287386417389
2023-01-22 17:02:59.787130: step: 44/470, loss: 1.3748838901519775
2023-01-22 17:03:00.542605: step: 46/470, loss: 0.31518200039863586
2023-01-22 17:03:01.300102: step: 48/470, loss: 1.317157506942749
2023-01-22 17:03:02.051226: step: 50/470, loss: 0.3318483829498291
2023-01-22 17:03:02.788720: step: 52/470, loss: 2.242248296737671
2023-01-22 17:03:03.520923: step: 54/470, loss: 0.5057197213172913
2023-01-22 17:03:04.221738: step: 56/470, loss: 1.300000786781311
2023-01-22 17:03:04.922606: step: 58/470, loss: 0.9471038579940796
2023-01-22 17:03:05.686526: step: 60/470, loss: 0.8389618992805481
2023-01-22 17:03:06.383683: step: 62/470, loss: 0.5545322895050049
2023-01-22 17:03:07.128938: step: 64/470, loss: 0.9042381048202515
2023-01-22 17:03:07.848710: step: 66/470, loss: 1.5064542293548584
2023-01-22 17:03:08.551935: step: 68/470, loss: 0.651218056678772
2023-01-22 17:03:09.287344: step: 70/470, loss: 4.524369239807129
2023-01-22 17:03:10.015017: step: 72/470, loss: 0.3224298655986786
2023-01-22 17:03:10.662390: step: 74/470, loss: 0.5799638628959656
2023-01-22 17:03:11.411424: step: 76/470, loss: 1.0132986307144165
2023-01-22 17:03:12.165398: step: 78/470, loss: 0.2071341574192047
2023-01-22 17:03:12.959432: step: 80/470, loss: 0.13997377455234528
2023-01-22 17:03:13.707417: step: 82/470, loss: 0.8105186223983765
2023-01-22 17:03:14.319399: step: 84/470, loss: 0.37218907475471497
2023-01-22 17:03:15.004826: step: 86/470, loss: 0.5148276090621948
2023-01-22 17:03:15.743944: step: 88/470, loss: 0.8321148753166199
2023-01-22 17:03:16.466978: step: 90/470, loss: 0.889289379119873
2023-01-22 17:03:17.173624: step: 92/470, loss: 0.5049362182617188
2023-01-22 17:03:17.886834: step: 94/470, loss: 0.9081429243087769
2023-01-22 17:03:18.630390: step: 96/470, loss: 0.8203686475753784
2023-01-22 17:03:19.444464: step: 98/470, loss: 1.3147096633911133
2023-01-22 17:03:20.164473: step: 100/470, loss: 0.49650490283966064
2023-01-22 17:03:20.836768: step: 102/470, loss: 0.6795364022254944
2023-01-22 17:03:21.709986: step: 104/470, loss: 5.672989845275879
2023-01-22 17:03:22.514039: step: 106/470, loss: 0.5761081576347351
2023-01-22 17:03:23.214712: step: 108/470, loss: 0.8563786149024963
2023-01-22 17:03:23.923997: step: 110/470, loss: 1.6315613985061646
2023-01-22 17:03:24.732802: step: 112/470, loss: 0.5608785152435303
2023-01-22 17:03:25.502058: step: 114/470, loss: 0.5131690502166748
2023-01-22 17:03:26.232578: step: 116/470, loss: 0.20318368077278137
2023-01-22 17:03:26.917866: step: 118/470, loss: 0.45412278175354004
2023-01-22 17:03:27.675620: step: 120/470, loss: 0.656235933303833
2023-01-22 17:03:28.383170: step: 122/470, loss: 0.1925651729106903
2023-01-22 17:03:29.038845: step: 124/470, loss: 0.43493232131004333
2023-01-22 17:03:29.814084: step: 126/470, loss: 0.27077344059944153
2023-01-22 17:03:30.535944: step: 128/470, loss: 0.3672603666782379
2023-01-22 17:03:31.288980: step: 130/470, loss: 0.9226909875869751
2023-01-22 17:03:32.000527: step: 132/470, loss: 0.32075291872024536
2023-01-22 17:03:32.795208: step: 134/470, loss: 0.6723787784576416
2023-01-22 17:03:33.476403: step: 136/470, loss: 1.2128407955169678
2023-01-22 17:03:34.195376: step: 138/470, loss: 0.8287149667739868
2023-01-22 17:03:34.905214: step: 140/470, loss: 0.4041156768798828
2023-01-22 17:03:35.619891: step: 142/470, loss: 0.16680775582790375
2023-01-22 17:03:36.382910: step: 144/470, loss: 2.376657485961914
2023-01-22 17:03:37.099210: step: 146/470, loss: 0.47927552461624146
2023-01-22 17:03:37.787996: step: 148/470, loss: 1.4806530475616455
2023-01-22 17:03:38.548142: step: 150/470, loss: 0.7680869698524475
2023-01-22 17:03:39.225129: step: 152/470, loss: 0.3706393539905548
2023-01-22 17:03:39.892359: step: 154/470, loss: 2.1673104763031006
2023-01-22 17:03:40.617338: step: 156/470, loss: 0.905188798904419
2023-01-22 17:03:41.367012: step: 158/470, loss: 0.19686326384544373
2023-01-22 17:03:42.096475: step: 160/470, loss: 1.0826082229614258
2023-01-22 17:03:42.842060: step: 162/470, loss: 1.3279461860656738
2023-01-22 17:03:43.696669: step: 164/470, loss: 0.796668291091919
2023-01-22 17:03:44.611270: step: 166/470, loss: 0.6903431415557861
2023-01-22 17:03:45.345472: step: 168/470, loss: 0.4284389317035675
2023-01-22 17:03:46.065338: step: 170/470, loss: 1.0535764694213867
2023-01-22 17:03:46.823526: step: 172/470, loss: 0.5381697416305542
2023-01-22 17:03:47.525340: step: 174/470, loss: 0.5848957896232605
2023-01-22 17:03:48.196057: step: 176/470, loss: 1.5677191019058228
2023-01-22 17:03:48.970800: step: 178/470, loss: 1.2079250812530518
2023-01-22 17:03:49.803903: step: 180/470, loss: 0.6007267236709595
2023-01-22 17:03:50.598703: step: 182/470, loss: 1.3235710859298706
2023-01-22 17:03:51.513546: step: 184/470, loss: 1.0727261304855347
2023-01-22 17:03:52.262196: step: 186/470, loss: 3.2140517234802246
2023-01-22 17:03:52.962884: step: 188/470, loss: 2.628072500228882
2023-01-22 17:03:53.663096: step: 190/470, loss: 0.410220205783844
2023-01-22 17:03:54.408532: step: 192/470, loss: 1.1373114585876465
2023-01-22 17:03:55.096975: step: 194/470, loss: 1.4659881591796875
2023-01-22 17:03:55.783172: step: 196/470, loss: 0.6437451839447021
2023-01-22 17:03:56.478362: step: 198/470, loss: 0.30417031049728394
2023-01-22 17:03:57.178890: step: 200/470, loss: 1.0152573585510254
2023-01-22 17:03:57.846358: step: 202/470, loss: 0.33993643522262573
2023-01-22 17:03:58.662720: step: 204/470, loss: 1.0089237689971924
2023-01-22 17:03:59.395141: step: 206/470, loss: 0.37781351804733276
2023-01-22 17:04:00.075403: step: 208/470, loss: 0.689214825630188
2023-01-22 17:04:00.783935: step: 210/470, loss: 0.4352153539657593
2023-01-22 17:04:01.498132: step: 212/470, loss: 1.1648905277252197
2023-01-22 17:04:02.316168: step: 214/470, loss: 0.3460136651992798
2023-01-22 17:04:03.109929: step: 216/470, loss: 0.7107413411140442
2023-01-22 17:04:03.837262: step: 218/470, loss: 0.08092077076435089
2023-01-22 17:04:04.564458: step: 220/470, loss: 1.2060343027114868
2023-01-22 17:04:05.210053: step: 222/470, loss: 1.078926920890808
2023-01-22 17:04:05.896719: step: 224/470, loss: 0.8819116950035095
2023-01-22 17:04:06.691572: step: 226/470, loss: 0.7317195534706116
2023-01-22 17:04:07.401515: step: 228/470, loss: 0.30972084403038025
2023-01-22 17:04:08.212876: step: 230/470, loss: 1.6904860734939575
2023-01-22 17:04:08.936605: step: 232/470, loss: 1.5937964916229248
2023-01-22 17:04:09.627264: step: 234/470, loss: 0.4739353656768799
2023-01-22 17:04:10.453292: step: 236/470, loss: 0.939883828163147
2023-01-22 17:04:11.217865: step: 238/470, loss: 0.4551941752433777
2023-01-22 17:04:11.936805: step: 240/470, loss: 0.5418661832809448
2023-01-22 17:04:12.714769: step: 242/470, loss: 1.2252233028411865
2023-01-22 17:04:13.561887: step: 244/470, loss: 1.1485824584960938
2023-01-22 17:04:14.301179: step: 246/470, loss: 0.8404242992401123
2023-01-22 17:04:15.044286: step: 248/470, loss: 0.6991187334060669
2023-01-22 17:04:15.834186: step: 250/470, loss: 1.8893976211547852
2023-01-22 17:04:16.534813: step: 252/470, loss: 0.6644213795661926
2023-01-22 17:04:17.344000: step: 254/470, loss: 0.8386790752410889
2023-01-22 17:04:18.071533: step: 256/470, loss: 1.4650182723999023
2023-01-22 17:04:18.731158: step: 258/470, loss: 0.5462832450866699
2023-01-22 17:04:19.558279: step: 260/470, loss: 5.154643535614014
2023-01-22 17:04:20.294585: step: 262/470, loss: 0.7503474354743958
2023-01-22 17:04:20.978590: step: 264/470, loss: 0.34197211265563965
2023-01-22 17:04:21.700980: step: 266/470, loss: 0.46603813767433167
2023-01-22 17:04:22.499680: step: 268/470, loss: 0.20978543162345886
2023-01-22 17:04:23.218169: step: 270/470, loss: 0.8326939344406128
2023-01-22 17:04:23.949350: step: 272/470, loss: 1.0488128662109375
2023-01-22 17:04:24.696792: step: 274/470, loss: 1.5846171379089355
2023-01-22 17:04:25.450959: step: 276/470, loss: 0.6706929802894592
2023-01-22 17:04:26.135491: step: 278/470, loss: 2.744781732559204
2023-01-22 17:04:26.925391: step: 280/470, loss: 0.7086952328681946
2023-01-22 17:04:27.783118: step: 282/470, loss: 1.4308860301971436
2023-01-22 17:04:28.584909: step: 284/470, loss: 0.30105042457580566
2023-01-22 17:04:29.365919: step: 286/470, loss: 0.7560703754425049
2023-01-22 17:04:30.088629: step: 288/470, loss: 1.4897514581680298
2023-01-22 17:04:30.879557: step: 290/470, loss: 0.583710253238678
2023-01-22 17:04:31.523692: step: 292/470, loss: 0.9798109531402588
2023-01-22 17:04:32.283964: step: 294/470, loss: 1.5323822498321533
2023-01-22 17:04:33.032650: step: 296/470, loss: 2.428147792816162
2023-01-22 17:04:33.724179: step: 298/470, loss: 0.5572175979614258
2023-01-22 17:04:34.444891: step: 300/470, loss: 0.8898938894271851
2023-01-22 17:04:35.171532: step: 302/470, loss: 1.1512093544006348
2023-01-22 17:04:35.997712: step: 304/470, loss: 2.286986827850342
2023-01-22 17:04:36.775725: step: 306/470, loss: 1.5244067907333374
2023-01-22 17:04:37.582280: step: 308/470, loss: 0.6587584018707275
2023-01-22 17:04:38.352255: step: 310/470, loss: 0.5230644345283508
2023-01-22 17:04:39.049050: step: 312/470, loss: 0.8668720126152039
2023-01-22 17:04:39.789251: step: 314/470, loss: 0.6899608373641968
2023-01-22 17:04:40.526827: step: 316/470, loss: 0.9593360424041748
2023-01-22 17:04:41.199490: step: 318/470, loss: 0.6568881869316101
2023-01-22 17:04:41.967466: step: 320/470, loss: 0.8749952912330627
2023-01-22 17:04:42.702381: step: 322/470, loss: 0.46149203181266785
2023-01-22 17:04:43.396069: step: 324/470, loss: 1.287691354751587
2023-01-22 17:04:44.178511: step: 326/470, loss: 0.5143733620643616
2023-01-22 17:04:44.889712: step: 328/470, loss: 0.423993319272995
2023-01-22 17:04:45.590271: step: 330/470, loss: 1.9649615287780762
2023-01-22 17:04:46.316807: step: 332/470, loss: 1.341388463973999
2023-01-22 17:04:47.118226: step: 334/470, loss: 0.20511598885059357
2023-01-22 17:04:47.975616: step: 336/470, loss: 0.7076253890991211
2023-01-22 17:04:48.734522: step: 338/470, loss: 0.2398476004600525
2023-01-22 17:04:49.529914: step: 340/470, loss: 0.43527939915657043
2023-01-22 17:04:50.176083: step: 342/470, loss: 0.27098989486694336
2023-01-22 17:04:50.870906: step: 344/470, loss: 0.42461445927619934
2023-01-22 17:04:51.642995: step: 346/470, loss: 0.6119195222854614
2023-01-22 17:04:52.463403: step: 348/470, loss: 0.5161367058753967
2023-01-22 17:04:53.254095: step: 350/470, loss: 0.35241755843162537
2023-01-22 17:04:54.014922: step: 352/470, loss: 0.33312055468559265
2023-01-22 17:04:54.836946: step: 354/470, loss: 2.3488333225250244
2023-01-22 17:04:55.637537: step: 356/470, loss: 2.8952274322509766
2023-01-22 17:04:56.366231: step: 358/470, loss: 1.2893620729446411
2023-01-22 17:04:57.077494: step: 360/470, loss: 0.3711218535900116
2023-01-22 17:04:57.799743: step: 362/470, loss: 0.2599567174911499
2023-01-22 17:04:58.535449: step: 364/470, loss: 5.034658908843994
2023-01-22 17:04:59.345240: step: 366/470, loss: 0.35741162300109863
2023-01-22 17:05:00.078358: step: 368/470, loss: 0.5050439238548279
2023-01-22 17:05:00.938811: step: 370/470, loss: 0.46297574043273926
2023-01-22 17:05:01.720601: step: 372/470, loss: 1.4221333265304565
2023-01-22 17:05:02.463045: step: 374/470, loss: 0.3796398341655731
2023-01-22 17:05:03.173874: step: 376/470, loss: 0.4562537372112274
2023-01-22 17:05:03.964049: step: 378/470, loss: 0.6173561811447144
2023-01-22 17:05:04.735694: step: 380/470, loss: 1.5535647869110107
2023-01-22 17:05:05.518403: step: 382/470, loss: 0.6625960469245911
2023-01-22 17:05:06.246004: step: 384/470, loss: 2.1780447959899902
2023-01-22 17:05:06.938278: step: 386/470, loss: 1.2066243886947632
2023-01-22 17:05:07.810466: step: 388/470, loss: 0.383740097284317
2023-01-22 17:05:08.618922: step: 390/470, loss: 0.36354339122772217
2023-01-22 17:05:09.443862: step: 392/470, loss: 0.3574196994304657
2023-01-22 17:05:10.264874: step: 394/470, loss: 1.139248251914978
2023-01-22 17:05:10.992652: step: 396/470, loss: 0.5587860345840454
2023-01-22 17:05:11.797856: step: 398/470, loss: 1.277011513710022
2023-01-22 17:05:12.581314: step: 400/470, loss: 0.6317623257637024
2023-01-22 17:05:13.454041: step: 402/470, loss: 1.273547649383545
2023-01-22 17:05:14.143107: step: 404/470, loss: 5.302393913269043
2023-01-22 17:05:14.818103: step: 406/470, loss: 0.3220556676387787
2023-01-22 17:05:15.544135: step: 408/470, loss: 1.9869134426116943
2023-01-22 17:05:16.288323: step: 410/470, loss: 0.33363187313079834
2023-01-22 17:05:17.027726: step: 412/470, loss: 0.9794175624847412
2023-01-22 17:05:17.825594: step: 414/470, loss: 1.7475107908248901
2023-01-22 17:05:18.521734: step: 416/470, loss: 1.0983277559280396
2023-01-22 17:05:19.285497: step: 418/470, loss: 2.780597686767578
2023-01-22 17:05:20.086932: step: 420/470, loss: 0.28116825222969055
2023-01-22 17:05:20.820783: step: 422/470, loss: 0.4581286311149597
2023-01-22 17:05:21.550922: step: 424/470, loss: 0.6359933018684387
2023-01-22 17:05:22.214104: step: 426/470, loss: 0.4756195843219757
2023-01-22 17:05:22.928841: step: 428/470, loss: 0.43690595030784607
2023-01-22 17:05:23.645947: step: 430/470, loss: 0.886446475982666
2023-01-22 17:05:24.411029: step: 432/470, loss: 1.1900947093963623
2023-01-22 17:05:25.148308: step: 434/470, loss: 0.9924726486206055
2023-01-22 17:05:25.858875: step: 436/470, loss: 1.7097697257995605
2023-01-22 17:05:26.553204: step: 438/470, loss: 0.9539413452148438
2023-01-22 17:05:27.295179: step: 440/470, loss: 1.100608229637146
2023-01-22 17:05:28.042318: step: 442/470, loss: 1.6105233430862427
2023-01-22 17:05:28.750155: step: 444/470, loss: 0.42767927050590515
2023-01-22 17:05:29.490146: step: 446/470, loss: 0.4778148829936981
2023-01-22 17:05:30.288331: step: 448/470, loss: 1.9240278005599976
2023-01-22 17:05:31.036121: step: 450/470, loss: 0.6379396319389343
2023-01-22 17:05:31.864684: step: 452/470, loss: 0.8942621350288391
2023-01-22 17:05:32.608508: step: 454/470, loss: 2.3800547122955322
2023-01-22 17:05:33.428148: step: 456/470, loss: 1.0691368579864502
2023-01-22 17:05:34.180377: step: 458/470, loss: 0.7086570858955383
2023-01-22 17:05:34.994921: step: 460/470, loss: 0.39457079768180847
2023-01-22 17:05:35.719755: step: 462/470, loss: 0.27901706099510193
2023-01-22 17:05:36.408970: step: 464/470, loss: 0.8260778784751892
2023-01-22 17:05:37.150920: step: 466/470, loss: 1.605619192123413
2023-01-22 17:05:37.934120: step: 468/470, loss: 0.8436158299446106
2023-01-22 17:05:38.657334: step: 470/470, loss: 1.076684832572937
2023-01-22 17:05:39.344272: step: 472/470, loss: 1.1909767389297485
2023-01-22 17:05:40.123050: step: 474/470, loss: 0.6028439998626709
2023-01-22 17:05:40.796198: step: 476/470, loss: 2.0072274208068848
2023-01-22 17:05:41.476692: step: 478/470, loss: 2.010789155960083
2023-01-22 17:05:42.245530: step: 480/470, loss: 0.4975433945655823
2023-01-22 17:05:43.034782: step: 482/470, loss: 0.9296523928642273
2023-01-22 17:05:43.766186: step: 484/470, loss: 0.5860471725463867
2023-01-22 17:05:44.531405: step: 486/470, loss: 0.750137209892273
2023-01-22 17:05:45.266930: step: 488/470, loss: 1.2189258337020874
2023-01-22 17:05:46.072920: step: 490/470, loss: 3.423570156097412
2023-01-22 17:05:46.874643: step: 492/470, loss: 1.0367627143859863
2023-01-22 17:05:47.631062: step: 494/470, loss: 1.586470365524292
2023-01-22 17:05:48.349888: step: 496/470, loss: 0.3984842300415039
2023-01-22 17:05:49.107703: step: 498/470, loss: 1.551780104637146
2023-01-22 17:05:49.837321: step: 500/470, loss: 0.6801697015762329
2023-01-22 17:05:50.555863: step: 502/470, loss: 0.6109309792518616
2023-01-22 17:05:51.322631: step: 504/470, loss: 2.4782888889312744
2023-01-22 17:05:52.171712: step: 506/470, loss: 1.3563328981399536
2023-01-22 17:05:52.876040: step: 508/470, loss: 1.7630181312561035
2023-01-22 17:05:53.627578: step: 510/470, loss: 0.9129251837730408
2023-01-22 17:05:54.344247: step: 512/470, loss: 1.837816834449768
2023-01-22 17:05:55.264820: step: 514/470, loss: 1.0328463315963745
2023-01-22 17:05:56.057587: step: 516/470, loss: 0.43190184235572815
2023-01-22 17:05:56.809326: step: 518/470, loss: 0.677377462387085
2023-01-22 17:05:57.612360: step: 520/470, loss: 1.7360193729400635
2023-01-22 17:05:58.345513: step: 522/470, loss: 1.5820202827453613
2023-01-22 17:05:59.093695: step: 524/470, loss: 3.5445146560668945
2023-01-22 17:05:59.927326: step: 526/470, loss: 9.609672546386719
2023-01-22 17:06:00.778570: step: 528/470, loss: 2.3321354389190674
2023-01-22 17:06:01.580073: step: 530/470, loss: 0.533820629119873
2023-01-22 17:06:02.381726: step: 532/470, loss: 0.19819556176662445
2023-01-22 17:06:03.108212: step: 534/470, loss: 1.0940450429916382
2023-01-22 17:06:03.837956: step: 536/470, loss: 0.9480574727058411
2023-01-22 17:06:04.545106: step: 538/470, loss: 0.29331231117248535
2023-01-22 17:06:05.225592: step: 540/470, loss: 0.4723627269268036
2023-01-22 17:06:05.906596: step: 542/470, loss: 0.6444365978240967
2023-01-22 17:06:06.694768: step: 544/470, loss: 0.3107144236564636
2023-01-22 17:06:07.475576: step: 546/470, loss: 0.4428755044937134
2023-01-22 17:06:08.228660: step: 548/470, loss: 0.4551246762275696
2023-01-22 17:06:08.935707: step: 550/470, loss: 0.9456477165222168
2023-01-22 17:06:09.821542: step: 552/470, loss: 0.4225022792816162
2023-01-22 17:06:10.563885: step: 554/470, loss: 0.21875688433647156
2023-01-22 17:06:11.272214: step: 556/470, loss: 0.5006171464920044
2023-01-22 17:06:12.045777: step: 558/470, loss: 0.7604213953018188
2023-01-22 17:06:13.007819: step: 560/470, loss: 1.2393240928649902
2023-01-22 17:06:13.758655: step: 562/470, loss: 1.712594985961914
2023-01-22 17:06:14.554309: step: 564/470, loss: 0.17193198204040527
2023-01-22 17:06:15.374590: step: 566/470, loss: 0.7961640357971191
2023-01-22 17:06:16.162137: step: 568/470, loss: 0.5501372218132019
2023-01-22 17:06:16.917008: step: 570/470, loss: 0.4883258044719696
2023-01-22 17:06:17.645917: step: 572/470, loss: 0.6990291476249695
2023-01-22 17:06:18.404425: step: 574/470, loss: 1.1884771585464478
2023-01-22 17:06:19.177182: step: 576/470, loss: 1.0261270999908447
2023-01-22 17:06:19.862069: step: 578/470, loss: 0.6111153960227966
2023-01-22 17:06:20.598937: step: 580/470, loss: 0.7478018403053284
2023-01-22 17:06:21.293014: step: 582/470, loss: 1.9652400016784668
2023-01-22 17:06:22.076567: step: 584/470, loss: 0.6027696132659912
2023-01-22 17:06:22.827326: step: 586/470, loss: 0.38277050852775574
2023-01-22 17:06:23.663582: step: 588/470, loss: 0.5123499035835266
2023-01-22 17:06:24.402365: step: 590/470, loss: 0.3519931137561798
2023-01-22 17:06:25.197763: step: 592/470, loss: 0.7184064984321594
2023-01-22 17:06:25.885754: step: 594/470, loss: 1.8940832614898682
2023-01-22 17:06:26.600366: step: 596/470, loss: 0.23110346496105194
2023-01-22 17:06:27.361622: step: 598/470, loss: 0.5986997485160828
2023-01-22 17:06:28.150848: step: 600/470, loss: 0.29345154762268066
2023-01-22 17:06:28.910526: step: 602/470, loss: 0.6144067645072937
2023-01-22 17:06:29.678686: step: 604/470, loss: 0.31155356764793396
2023-01-22 17:06:30.408539: step: 606/470, loss: 0.4316118359565735
2023-01-22 17:06:31.192295: step: 608/470, loss: 1.4895285367965698
2023-01-22 17:06:31.917075: step: 610/470, loss: 0.3460380434989929
2023-01-22 17:06:32.616032: step: 612/470, loss: 4.381056308746338
2023-01-22 17:06:33.338242: step: 614/470, loss: 0.26738184690475464
2023-01-22 17:06:34.064454: step: 616/470, loss: 1.009708285331726
2023-01-22 17:06:34.802664: step: 618/470, loss: 1.4514302015304565
2023-01-22 17:06:35.637501: step: 620/470, loss: 0.7399471998214722
2023-01-22 17:06:36.368175: step: 622/470, loss: 2.295945644378662
2023-01-22 17:06:37.150142: step: 624/470, loss: 0.5105316638946533
2023-01-22 17:06:37.844100: step: 626/470, loss: 0.2828077971935272
2023-01-22 17:06:38.594655: step: 628/470, loss: 1.003699541091919
2023-01-22 17:06:39.315037: step: 630/470, loss: 0.38585180044174194
2023-01-22 17:06:40.033498: step: 632/470, loss: 1.3301163911819458
2023-01-22 17:06:40.804574: step: 634/470, loss: 1.180068016052246
2023-01-22 17:06:41.535727: step: 636/470, loss: 0.9667542576789856
2023-01-22 17:06:42.269382: step: 638/470, loss: 0.6113733649253845
2023-01-22 17:06:43.120957: step: 640/470, loss: 1.1039268970489502
2023-01-22 17:06:43.916143: step: 642/470, loss: 0.7926710844039917
2023-01-22 17:06:44.666740: step: 644/470, loss: 1.8398045301437378
2023-01-22 17:06:45.486606: step: 646/470, loss: 0.5182595252990723
2023-01-22 17:06:46.255341: step: 648/470, loss: 1.8043544292449951
2023-01-22 17:06:46.986281: step: 650/470, loss: 1.3427050113677979
2023-01-22 17:06:47.761931: step: 652/470, loss: 0.2207910120487213
2023-01-22 17:06:48.515521: step: 654/470, loss: 0.7075690031051636
2023-01-22 17:06:49.185054: step: 656/470, loss: 1.3858473300933838
2023-01-22 17:06:49.913997: step: 658/470, loss: 0.40335145592689514
2023-01-22 17:06:50.646823: step: 660/470, loss: 0.8443214893341064
2023-01-22 17:06:51.425322: step: 662/470, loss: 1.4021592140197754
2023-01-22 17:06:52.126143: step: 664/470, loss: 0.8110883235931396
2023-01-22 17:06:52.915696: step: 666/470, loss: 0.2092544585466385
2023-01-22 17:06:53.627285: step: 668/470, loss: 4.8981614112854
2023-01-22 17:06:54.354490: step: 670/470, loss: 0.4453684389591217
2023-01-22 17:06:55.128289: step: 672/470, loss: 0.47258445620536804
2023-01-22 17:06:55.825618: step: 674/470, loss: 0.7400813102722168
2023-01-22 17:06:56.548465: step: 676/470, loss: 0.281443327665329
2023-01-22 17:06:57.254919: step: 678/470, loss: 0.5487380027770996
2023-01-22 17:06:57.983919: step: 680/470, loss: 0.4541553854942322
2023-01-22 17:06:58.723043: step: 682/470, loss: 0.6198228597640991
2023-01-22 17:06:59.470017: step: 684/470, loss: 0.6936663389205933
2023-01-22 17:07:00.210545: step: 686/470, loss: 1.3587620258331299
2023-01-22 17:07:01.024479: step: 688/470, loss: 1.5153071880340576
2023-01-22 17:07:01.705962: step: 690/470, loss: 1.0358877182006836
2023-01-22 17:07:02.409498: step: 692/470, loss: 1.0552879571914673
2023-01-22 17:07:03.125063: step: 694/470, loss: 1.0266014337539673
2023-01-22 17:07:03.840530: step: 696/470, loss: 1.048282504081726
2023-01-22 17:07:04.607467: step: 698/470, loss: 1.082366943359375
2023-01-22 17:07:05.344688: step: 700/470, loss: 3.19528865814209
2023-01-22 17:07:06.074899: step: 702/470, loss: 0.5113957524299622
2023-01-22 17:07:06.777972: step: 704/470, loss: 0.6064223051071167
2023-01-22 17:07:07.538638: step: 706/470, loss: 0.29762303829193115
2023-01-22 17:07:08.277461: step: 708/470, loss: 1.149381399154663
2023-01-22 17:07:09.089454: step: 710/470, loss: 0.45705515146255493
2023-01-22 17:07:09.809098: step: 712/470, loss: 0.4075102210044861
2023-01-22 17:07:10.558508: step: 714/470, loss: 0.7546180486679077
2023-01-22 17:07:11.263633: step: 716/470, loss: 0.7100285291671753
2023-01-22 17:07:11.971438: step: 718/470, loss: 2.0336670875549316
2023-01-22 17:07:12.762108: step: 720/470, loss: 0.505089521408081
2023-01-22 17:07:13.528016: step: 722/470, loss: 0.5286163091659546
2023-01-22 17:07:14.244408: step: 724/470, loss: 3.978087902069092
2023-01-22 17:07:14.947543: step: 726/470, loss: 1.456428050994873
2023-01-22 17:07:15.737840: step: 728/470, loss: 6.835483551025391
2023-01-22 17:07:16.464183: step: 730/470, loss: 1.0272594690322876
2023-01-22 17:07:17.124302: step: 732/470, loss: 1.0365326404571533
2023-01-22 17:07:17.857370: step: 734/470, loss: 0.3310011327266693
2023-01-22 17:07:18.655474: step: 736/470, loss: 0.6663587689399719
2023-01-22 17:07:19.444252: step: 738/470, loss: 0.6486376523971558
2023-01-22 17:07:20.189833: step: 740/470, loss: 0.29191356897354126
2023-01-22 17:07:20.965292: step: 742/470, loss: 0.32745280861854553
2023-01-22 17:07:21.735366: step: 744/470, loss: 2.1090571880340576
2023-01-22 17:07:22.506530: step: 746/470, loss: 1.205168604850769
2023-01-22 17:07:23.220589: step: 748/470, loss: 0.9146398901939392
2023-01-22 17:07:23.958410: step: 750/470, loss: 8.422287940979004
2023-01-22 17:07:24.764658: step: 752/470, loss: 1.7295546531677246
2023-01-22 17:07:25.536419: step: 754/470, loss: 1.0920233726501465
2023-01-22 17:07:26.239460: step: 756/470, loss: 2.5528173446655273
2023-01-22 17:07:27.050044: step: 758/470, loss: 0.6946008801460266
2023-01-22 17:07:27.817307: step: 760/470, loss: 0.9669357538223267
2023-01-22 17:07:28.517832: step: 762/470, loss: 3.9733476638793945
2023-01-22 17:07:29.206122: step: 764/470, loss: 0.6126687526702881
2023-01-22 17:07:29.988753: step: 766/470, loss: 1.2648811340332031
2023-01-22 17:07:30.747925: step: 768/470, loss: 1.0761961936950684
2023-01-22 17:07:31.448575: step: 770/470, loss: 0.36128804087638855
2023-01-22 17:07:32.159831: step: 772/470, loss: 2.7535998821258545
2023-01-22 17:07:32.872279: step: 774/470, loss: 1.588283658027649
2023-01-22 17:07:33.718347: step: 776/470, loss: 1.3686546087265015
2023-01-22 17:07:34.563682: step: 778/470, loss: 0.6748623847961426
2023-01-22 17:07:35.332620: step: 780/470, loss: 0.4505867660045624
2023-01-22 17:07:36.082439: step: 782/470, loss: 0.2927594780921936
2023-01-22 17:07:36.780030: step: 784/470, loss: 0.8455650806427002
2023-01-22 17:07:37.469905: step: 786/470, loss: 0.3428768515586853
2023-01-22 17:07:38.217070: step: 788/470, loss: 1.1048076152801514
2023-01-22 17:07:38.948072: step: 790/470, loss: 3.1269044876098633
2023-01-22 17:07:39.701420: step: 792/470, loss: 1.0847244262695312
2023-01-22 17:07:40.603615: step: 794/470, loss: 5.910243511199951
2023-01-22 17:07:41.348018: step: 796/470, loss: 0.3136829137802124
2023-01-22 17:07:42.179812: step: 798/470, loss: 0.6312191486358643
2023-01-22 17:07:42.849656: step: 800/470, loss: 1.0586059093475342
2023-01-22 17:07:43.565533: step: 802/470, loss: 0.7780605554580688
2023-01-22 17:07:44.272734: step: 804/470, loss: 0.42219239473342896
2023-01-22 17:07:44.985854: step: 806/470, loss: 0.661794900894165
2023-01-22 17:07:45.683101: step: 808/470, loss: 0.5359216332435608
2023-01-22 17:07:46.401832: step: 810/470, loss: 0.20118995010852814
2023-01-22 17:07:47.155898: step: 812/470, loss: 2.887706995010376
2023-01-22 17:07:47.920219: step: 814/470, loss: 0.8478198051452637
2023-01-22 17:07:48.637742: step: 816/470, loss: 0.7324924468994141
2023-01-22 17:07:49.375433: step: 818/470, loss: 1.24992835521698
2023-01-22 17:07:50.133734: step: 820/470, loss: 0.47944867610931396
2023-01-22 17:07:50.886575: step: 822/470, loss: 3.812171459197998
2023-01-22 17:07:51.656953: step: 824/470, loss: 1.0839214324951172
2023-01-22 17:07:52.378140: step: 826/470, loss: 0.307800829410553
2023-01-22 17:07:53.117644: step: 828/470, loss: 0.6476705074310303
2023-01-22 17:07:53.977416: step: 830/470, loss: 0.3994646668434143
2023-01-22 17:07:54.750390: step: 832/470, loss: 1.0658934116363525
2023-01-22 17:07:55.493191: step: 834/470, loss: 0.22010746598243713
2023-01-22 17:07:56.226292: step: 836/470, loss: 0.7103077173233032
2023-01-22 17:07:57.100368: step: 838/470, loss: 0.9640560150146484
2023-01-22 17:07:57.811652: step: 840/470, loss: 1.359990119934082
2023-01-22 17:07:58.666883: step: 842/470, loss: 1.2544822692871094
2023-01-22 17:07:59.507089: step: 844/470, loss: 1.0046195983886719
2023-01-22 17:08:00.182523: step: 846/470, loss: 1.0893107652664185
2023-01-22 17:08:00.915090: step: 848/470, loss: 0.3106290102005005
2023-01-22 17:08:01.697034: step: 850/470, loss: 3.447446346282959
2023-01-22 17:08:02.394740: step: 852/470, loss: 1.2170885801315308
2023-01-22 17:08:03.087639: step: 854/470, loss: 0.2806965112686157
2023-01-22 17:08:03.898926: step: 856/470, loss: 4.124128341674805
2023-01-22 17:08:04.664428: step: 858/470, loss: 1.0237302780151367
2023-01-22 17:08:05.403057: step: 860/470, loss: 1.629802942276001
2023-01-22 17:08:06.150534: step: 862/470, loss: 6.174650192260742
2023-01-22 17:08:06.946483: step: 864/470, loss: 0.9307006001472473
2023-01-22 17:08:07.745510: step: 866/470, loss: 0.4283657371997833
2023-01-22 17:08:08.563485: step: 868/470, loss: 2.484179973602295
2023-01-22 17:08:09.234561: step: 870/470, loss: 0.7242858409881592
2023-01-22 17:08:09.942271: step: 872/470, loss: 0.5142600536346436
2023-01-22 17:08:10.679004: step: 874/470, loss: 0.43242359161376953
2023-01-22 17:08:11.365454: step: 876/470, loss: 1.1232759952545166
2023-01-22 17:08:12.066265: step: 878/470, loss: 0.9467688798904419
2023-01-22 17:08:12.789677: step: 880/470, loss: 0.1361820548772812
2023-01-22 17:08:13.605185: step: 882/470, loss: 2.624424934387207
2023-01-22 17:08:14.265785: step: 884/470, loss: 1.0939950942993164
2023-01-22 17:08:14.985040: step: 886/470, loss: 0.4590575098991394
2023-01-22 17:08:15.687311: step: 888/470, loss: 0.7806578874588013
2023-01-22 17:08:16.477615: step: 890/470, loss: 0.7640312910079956
2023-01-22 17:08:17.245214: step: 892/470, loss: 7.197998046875
2023-01-22 17:08:17.979361: step: 894/470, loss: 0.49443161487579346
2023-01-22 17:08:18.710758: step: 896/470, loss: 0.8511555790901184
2023-01-22 17:08:19.380568: step: 898/470, loss: 2.684095621109009
2023-01-22 17:08:20.113759: step: 900/470, loss: 0.8094006776809692
2023-01-22 17:08:20.776792: step: 902/470, loss: 0.8172462582588196
2023-01-22 17:08:21.566085: step: 904/470, loss: 3.9463624954223633
2023-01-22 17:08:22.280943: step: 906/470, loss: 2.681535243988037
2023-01-22 17:08:23.013259: step: 908/470, loss: 1.012972116470337
2023-01-22 17:08:23.767414: step: 910/470, loss: 2.3120675086975098
2023-01-22 17:08:24.535294: step: 912/470, loss: 1.2887799739837646
2023-01-22 17:08:25.322599: step: 914/470, loss: 0.8099074959754944
2023-01-22 17:08:26.099114: step: 916/470, loss: 0.5998104810714722
2023-01-22 17:08:26.778208: step: 918/470, loss: 1.7960407733917236
2023-01-22 17:08:27.517927: step: 920/470, loss: 0.6787109971046448
2023-01-22 17:08:28.244193: step: 922/470, loss: 1.4123334884643555
2023-01-22 17:08:28.904908: step: 924/470, loss: 0.24107448756694794
2023-01-22 17:08:29.605797: step: 926/470, loss: 0.34054338932037354
2023-01-22 17:08:30.321388: step: 928/470, loss: 0.6413167119026184
2023-01-22 17:08:31.084591: step: 930/470, loss: 0.6883243322372437
2023-01-22 17:08:31.780759: step: 932/470, loss: 0.3803039491176605
2023-01-22 17:08:32.502065: step: 934/470, loss: 0.22277651727199554
2023-01-22 17:08:33.258509: step: 936/470, loss: 1.7990632057189941
2023-01-22 17:08:34.139680: step: 938/470, loss: 0.1533496081829071
2023-01-22 17:08:34.860097: step: 940/470, loss: 0.6035867929458618
2023-01-22 17:08:35.580572: step: 942/470, loss: 0.27842485904693604
==================================================
Loss: 1.112
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3099720927445607, 'r': 0.24233112373958068, 'f1': 0.2720095893732887}, 'combined': 0.20042811848558112, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3270647422029072, 'r': 0.26611319562522806, 'f1': 0.2934574540740068}, 'combined': 0.2043982267182137, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28632789500190714, 'r': 0.21624004214565282, 'f1': 0.24639676153677628}, 'combined': 0.1815555085007825, 'epoch': 4}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3345971660892728, 'r': 0.26806343565653556, 'f1': 0.2976576389530171}, 'combined': 0.20732372862399204, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2650408878504673, 'r': 0.2152514231499051, 'f1': 0.23756544502617802}, 'combined': 0.175048222650868, 'epoch': 4}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.31248242935600457, 'r': 0.26835666843829786, 'f1': 0.28874345410260266}, 'combined': 0.20111484365355412, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21875, 'r': 0.25, 'f1': 0.23333333333333334}, 'combined': 0.15555555555555556, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.32407407407407407, 'r': 0.3804347826086957, 'f1': 0.35000000000000003}, 'combined': 0.17500000000000002, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3409090909090909, 'r': 0.12931034482758622, 'f1': 0.1875}, 'combined': 0.125, 'epoch': 4}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27756423515352086, 'r': 0.27282404897442847, 'f1': 0.2751737297789929}, 'combined': 0.20275959036346844, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3282026888474822, 'r': 0.25190581017208286, 'f1': 0.28503690042297636}, 'combined': 0.19853316447371488, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24695121951219512, 'r': 0.2892857142857143, 'f1': 0.2664473684210527}, 'combined': 0.17763157894736847, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28632789500190714, 'r': 0.21624004214565282, 'f1': 0.24639676153677628}, 'combined': 0.1815555085007825, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3345971660892728, 'r': 0.26806343565653556, 'f1': 0.2976576389530171}, 'combined': 0.20732372862399204, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.32407407407407407, 'r': 0.3804347826086957, 'f1': 0.35000000000000003}, 'combined': 0.17500000000000002, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.20295208490866637, 'r': 0.24783940803591395, 'f1': 0.22316093081021016}, 'combined': 0.16443437007068115, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.279769607766213, 'r': 0.2325601629274273, 'f1': 0.25398979050608034}, 'combined': 0.17690831179527985, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 1}
******************************
Epoch: 5
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 17:11:17.752399: step: 2/470, loss: 0.22235730290412903
2023-01-22 17:11:18.464197: step: 4/470, loss: 0.21198546886444092
2023-01-22 17:11:19.251499: step: 6/470, loss: 0.49766987562179565
2023-01-22 17:11:19.971012: step: 8/470, loss: 0.3908613622188568
2023-01-22 17:11:20.755623: step: 10/470, loss: 0.16270841658115387
2023-01-22 17:11:21.579161: step: 12/470, loss: 0.20050539076328278
2023-01-22 17:11:22.288222: step: 14/470, loss: 0.7683029174804688
2023-01-22 17:11:23.074921: step: 16/470, loss: 0.3124810755252838
2023-01-22 17:11:23.845623: step: 18/470, loss: 1.0326603651046753
2023-01-22 17:11:24.532850: step: 20/470, loss: 0.4175031781196594
2023-01-22 17:11:25.274128: step: 22/470, loss: 0.8004642724990845
2023-01-22 17:11:26.087336: step: 24/470, loss: 0.31021180748939514
2023-01-22 17:11:26.796140: step: 26/470, loss: 0.43700122833251953
2023-01-22 17:11:27.630688: step: 28/470, loss: 0.9346105456352234
2023-01-22 17:11:28.366915: step: 30/470, loss: 0.3246211111545563
2023-01-22 17:11:29.069167: step: 32/470, loss: 0.7316885590553284
2023-01-22 17:11:29.848898: step: 34/470, loss: 0.9466471076011658
2023-01-22 17:11:30.616334: step: 36/470, loss: 0.294159471988678
2023-01-22 17:11:31.402790: step: 38/470, loss: 2.3637757301330566
2023-01-22 17:11:32.161300: step: 40/470, loss: 0.3901894688606262
2023-01-22 17:11:32.974667: step: 42/470, loss: 0.89076167345047
2023-01-22 17:11:33.705002: step: 44/470, loss: 1.0623388290405273
2023-01-22 17:11:34.530667: step: 46/470, loss: 0.1770210862159729
2023-01-22 17:11:35.327218: step: 48/470, loss: 0.3942860960960388
2023-01-22 17:11:36.050704: step: 50/470, loss: 0.8177869915962219
2023-01-22 17:11:36.766064: step: 52/470, loss: 1.5779149532318115
2023-01-22 17:11:37.600834: step: 54/470, loss: 1.26964271068573
2023-01-22 17:11:38.478384: step: 56/470, loss: 1.0765001773834229
2023-01-22 17:11:39.216749: step: 58/470, loss: 0.8852806091308594
2023-01-22 17:11:39.905741: step: 60/470, loss: 0.265352338552475
2023-01-22 17:11:40.584083: step: 62/470, loss: 0.4972139298915863
2023-01-22 17:11:41.283179: step: 64/470, loss: 0.9439274668693542
2023-01-22 17:11:42.040011: step: 66/470, loss: 1.225905179977417
2023-01-22 17:11:42.802111: step: 68/470, loss: 0.6210903525352478
2023-01-22 17:11:43.565623: step: 70/470, loss: 0.33965161442756653
2023-01-22 17:11:44.304070: step: 72/470, loss: 0.17134492099285126
2023-01-22 17:11:44.971884: step: 74/470, loss: 0.3916568458080292
2023-01-22 17:11:45.696338: step: 76/470, loss: 0.5033536553382874
2023-01-22 17:11:46.485862: step: 78/470, loss: 0.39052829146385193
2023-01-22 17:11:47.288349: step: 80/470, loss: 0.5496810078620911
2023-01-22 17:11:48.142697: step: 82/470, loss: 0.7038556337356567
2023-01-22 17:11:48.842925: step: 84/470, loss: 2.2712252140045166
2023-01-22 17:11:49.554911: step: 86/470, loss: 0.3298700749874115
2023-01-22 17:11:50.354623: step: 88/470, loss: 0.6470965147018433
2023-01-22 17:11:51.145017: step: 90/470, loss: 0.3787349760532379
2023-01-22 17:11:51.919496: step: 92/470, loss: 0.6228494644165039
2023-01-22 17:11:52.706205: step: 94/470, loss: 0.611712634563446
2023-01-22 17:11:53.387400: step: 96/470, loss: 0.8371176719665527
2023-01-22 17:11:54.090992: step: 98/470, loss: 0.6518052220344543
2023-01-22 17:11:54.804507: step: 100/470, loss: 0.47128623723983765
2023-01-22 17:11:55.506958: step: 102/470, loss: 0.8628720045089722
2023-01-22 17:11:56.300162: step: 104/470, loss: 0.4808705747127533
2023-01-22 17:11:57.082482: step: 106/470, loss: 0.4174078702926636
2023-01-22 17:11:57.894841: step: 108/470, loss: 0.3857043981552124
2023-01-22 17:11:58.602627: step: 110/470, loss: 0.21693837642669678
2023-01-22 17:11:59.398437: step: 112/470, loss: 0.6489458084106445
2023-01-22 17:12:00.102750: step: 114/470, loss: 0.5416321158409119
2023-01-22 17:12:00.942223: step: 116/470, loss: 0.19514138996601105
2023-01-22 17:12:01.663750: step: 118/470, loss: 0.3536219596862793
2023-01-22 17:12:02.473650: step: 120/470, loss: 1.3784006834030151
2023-01-22 17:12:03.216514: step: 122/470, loss: 2.3029212951660156
2023-01-22 17:12:03.974338: step: 124/470, loss: 1.3331398963928223
2023-01-22 17:12:04.728636: step: 126/470, loss: 0.3695890009403229
2023-01-22 17:12:05.410108: step: 128/470, loss: 1.1727420091629028
2023-01-22 17:12:06.158989: step: 130/470, loss: 1.360120415687561
2023-01-22 17:12:06.896492: step: 132/470, loss: 0.36498603224754333
2023-01-22 17:12:07.640538: step: 134/470, loss: 0.5842001438140869
2023-01-22 17:12:08.459065: step: 136/470, loss: 0.5986462235450745
2023-01-22 17:12:09.287388: step: 138/470, loss: 0.48415353894233704
2023-01-22 17:12:10.023464: step: 140/470, loss: 0.2749024033546448
2023-01-22 17:12:10.820365: step: 142/470, loss: 1.0702927112579346
2023-01-22 17:12:11.636841: step: 144/470, loss: 0.2774654030799866
2023-01-22 17:12:12.406803: step: 146/470, loss: 0.38094377517700195
2023-01-22 17:12:13.184198: step: 148/470, loss: 0.20257362723350525
2023-01-22 17:12:13.924061: step: 150/470, loss: 1.267014503479004
2023-01-22 17:12:14.647154: step: 152/470, loss: 1.0668094158172607
2023-01-22 17:12:15.419344: step: 154/470, loss: 1.20293128490448
2023-01-22 17:12:16.147744: step: 156/470, loss: 0.724846363067627
2023-01-22 17:12:16.834078: step: 158/470, loss: 0.979896068572998
2023-01-22 17:12:17.564290: step: 160/470, loss: 0.9010365605354309
2023-01-22 17:12:18.268463: step: 162/470, loss: 0.7949374914169312
2023-01-22 17:12:19.008447: step: 164/470, loss: 0.45920002460479736
2023-01-22 17:12:19.698600: step: 166/470, loss: 2.250549077987671
2023-01-22 17:12:20.454753: step: 168/470, loss: 0.19924406707286835
2023-01-22 17:12:21.252660: step: 170/470, loss: 0.7295480966567993
2023-01-22 17:12:22.017767: step: 172/470, loss: 1.2707566022872925
2023-01-22 17:12:22.698904: step: 174/470, loss: 0.5840062499046326
2023-01-22 17:12:23.482493: step: 176/470, loss: 0.5518929362297058
2023-01-22 17:12:24.340763: step: 178/470, loss: 1.6353731155395508
2023-01-22 17:12:25.171659: step: 180/470, loss: 0.9040023684501648
2023-01-22 17:12:25.925599: step: 182/470, loss: 1.9166462421417236
2023-01-22 17:12:26.651547: step: 184/470, loss: 0.33155763149261475
2023-01-22 17:12:27.402828: step: 186/470, loss: 0.1614404320716858
2023-01-22 17:12:28.144723: step: 188/470, loss: 0.4751662313938141
2023-01-22 17:12:28.838415: step: 190/470, loss: 0.3759790360927582
2023-01-22 17:12:29.579138: step: 192/470, loss: 0.6819899678230286
2023-01-22 17:12:30.349202: step: 194/470, loss: 2.1987533569335938
2023-01-22 17:12:31.109247: step: 196/470, loss: 0.6992949843406677
2023-01-22 17:12:31.880148: step: 198/470, loss: 1.0487316846847534
2023-01-22 17:12:32.586338: step: 200/470, loss: 0.5224685072898865
2023-01-22 17:12:33.285195: step: 202/470, loss: 0.9172898530960083
2023-01-22 17:12:34.041619: step: 204/470, loss: 0.6186913847923279
2023-01-22 17:12:34.786282: step: 206/470, loss: 3.2034780979156494
2023-01-22 17:12:35.527499: step: 208/470, loss: 0.720175564289093
2023-01-22 17:12:36.280322: step: 210/470, loss: 2.231804847717285
2023-01-22 17:12:36.976913: step: 212/470, loss: 0.12492244690656662
2023-01-22 17:12:37.826523: step: 214/470, loss: 0.5483446717262268
2023-01-22 17:12:38.596035: step: 216/470, loss: 1.2820593118667603
2023-01-22 17:12:39.310509: step: 218/470, loss: 0.47009074687957764
2023-01-22 17:12:40.039845: step: 220/470, loss: 0.3459213972091675
2023-01-22 17:12:40.686062: step: 222/470, loss: 0.20750129222869873
2023-01-22 17:12:41.428908: step: 224/470, loss: 0.8360021114349365
2023-01-22 17:12:42.208164: step: 226/470, loss: 0.3708805739879608
2023-01-22 17:12:42.980664: step: 228/470, loss: 0.7422099709510803
2023-01-22 17:12:43.718777: step: 230/470, loss: 0.4704272449016571
2023-01-22 17:12:44.402207: step: 232/470, loss: 0.7870251536369324
2023-01-22 17:12:45.227474: step: 234/470, loss: 0.8178002238273621
2023-01-22 17:12:45.869920: step: 236/470, loss: 0.5741672515869141
2023-01-22 17:12:46.596053: step: 238/470, loss: 0.3935246467590332
2023-01-22 17:12:47.263558: step: 240/470, loss: 0.7990236878395081
2023-01-22 17:12:48.033667: step: 242/470, loss: 1.1086221933364868
2023-01-22 17:12:48.682965: step: 244/470, loss: 1.578269124031067
2023-01-22 17:12:49.427441: step: 246/470, loss: 1.1762317419052124
2023-01-22 17:12:50.090017: step: 248/470, loss: 0.1974961757659912
2023-01-22 17:12:50.855695: step: 250/470, loss: 1.7104171514511108
2023-01-22 17:12:51.608950: step: 252/470, loss: 0.31335341930389404
2023-01-22 17:12:52.371192: step: 254/470, loss: 0.48065751791000366
2023-01-22 17:12:53.051270: step: 256/470, loss: 0.8966016173362732
2023-01-22 17:12:53.791512: step: 258/470, loss: 0.5578399896621704
2023-01-22 17:12:54.518901: step: 260/470, loss: 2.122208833694458
2023-01-22 17:12:55.248026: step: 262/470, loss: 1.1785131692886353
2023-01-22 17:12:56.017781: step: 264/470, loss: 0.5294274091720581
2023-01-22 17:12:56.787733: step: 266/470, loss: 0.9701927900314331
2023-01-22 17:12:57.520720: step: 268/470, loss: 0.23452767729759216
2023-01-22 17:12:58.230966: step: 270/470, loss: 0.6140098571777344
2023-01-22 17:12:58.961946: step: 272/470, loss: 0.4548776149749756
2023-01-22 17:12:59.747065: step: 274/470, loss: 0.9099631309509277
2023-01-22 17:13:00.552224: step: 276/470, loss: 0.5374931693077087
2023-01-22 17:13:01.336661: step: 278/470, loss: 1.1470648050308228
2023-01-22 17:13:02.097638: step: 280/470, loss: 0.719149649143219
2023-01-22 17:13:02.853234: step: 282/470, loss: 1.6352453231811523
2023-01-22 17:13:03.671090: step: 284/470, loss: 0.3871826231479645
2023-01-22 17:13:04.435558: step: 286/470, loss: 0.7986884117126465
2023-01-22 17:13:05.134282: step: 288/470, loss: 1.6879855394363403
2023-01-22 17:13:05.934797: step: 290/470, loss: 0.24217256903648376
2023-01-22 17:13:06.663197: step: 292/470, loss: 0.7460265755653381
2023-01-22 17:13:07.480906: step: 294/470, loss: 2.9903945922851562
2023-01-22 17:13:08.251465: step: 296/470, loss: 0.8292760848999023
2023-01-22 17:13:08.968630: step: 298/470, loss: 1.7127366065979004
2023-01-22 17:13:09.674200: step: 300/470, loss: 1.0309264659881592
2023-01-22 17:13:10.413497: step: 302/470, loss: 0.19080205261707306
2023-01-22 17:13:11.192784: step: 304/470, loss: 0.7009590864181519
2023-01-22 17:13:12.030861: step: 306/470, loss: 0.6426486968994141
2023-01-22 17:13:12.779233: step: 308/470, loss: 0.7753332853317261
2023-01-22 17:13:13.463890: step: 310/470, loss: 0.6057764887809753
2023-01-22 17:13:14.186171: step: 312/470, loss: 0.5348176956176758
2023-01-22 17:13:14.907068: step: 314/470, loss: 0.1700417399406433
2023-01-22 17:13:15.643338: step: 316/470, loss: 1.0512360334396362
2023-01-22 17:13:16.393020: step: 318/470, loss: 2.0664336681365967
2023-01-22 17:13:17.108263: step: 320/470, loss: 1.663642168045044
2023-01-22 17:13:17.883781: step: 322/470, loss: 0.18958774209022522
2023-01-22 17:13:18.644376: step: 324/470, loss: 0.4568879008293152
2023-01-22 17:13:19.279950: step: 326/470, loss: 1.1089987754821777
2023-01-22 17:13:20.075341: step: 328/470, loss: 0.6072306632995605
2023-01-22 17:13:20.805574: step: 330/470, loss: 0.9218146800994873
2023-01-22 17:13:21.562252: step: 332/470, loss: 0.6980925798416138
2023-01-22 17:13:22.400068: step: 334/470, loss: 0.33780360221862793
2023-01-22 17:13:23.122171: step: 336/470, loss: 0.2144942283630371
2023-01-22 17:13:23.748346: step: 338/470, loss: 0.5171912908554077
2023-01-22 17:13:24.482363: step: 340/470, loss: 0.2723813056945801
2023-01-22 17:13:25.141695: step: 342/470, loss: 1.158375859260559
2023-01-22 17:13:25.863402: step: 344/470, loss: 1.1009371280670166
2023-01-22 17:13:26.626913: step: 346/470, loss: 0.8941398859024048
2023-01-22 17:13:27.463912: step: 348/470, loss: 0.8668206334114075
2023-01-22 17:13:28.321786: step: 350/470, loss: 0.43403181433677673
2023-01-22 17:13:29.067220: step: 352/470, loss: 0.3821115791797638
2023-01-22 17:13:29.823374: step: 354/470, loss: 0.5914931893348694
2023-01-22 17:13:30.567766: step: 356/470, loss: 0.8853386640548706
2023-01-22 17:13:31.328623: step: 358/470, loss: 1.1184029579162598
2023-01-22 17:13:32.106172: step: 360/470, loss: 0.33806416392326355
2023-01-22 17:13:32.864277: step: 362/470, loss: 0.4669269323348999
2023-01-22 17:13:33.602317: step: 364/470, loss: 1.3949357271194458
2023-01-22 17:13:34.267889: step: 366/470, loss: 0.25456702709198
2023-01-22 17:13:35.026157: step: 368/470, loss: 0.23126432299613953
2023-01-22 17:13:35.683489: step: 370/470, loss: 0.48816195130348206
2023-01-22 17:13:36.489070: step: 372/470, loss: 0.9824779629707336
2023-01-22 17:13:37.414986: step: 374/470, loss: 0.9794360399246216
2023-01-22 17:13:38.181038: step: 376/470, loss: 0.8073421120643616
2023-01-22 17:13:38.853364: step: 378/470, loss: 1.1331653594970703
2023-01-22 17:13:39.530899: step: 380/470, loss: 0.23539990186691284
2023-01-22 17:13:40.251559: step: 382/470, loss: 1.2172232866287231
2023-01-22 17:13:40.928435: step: 384/470, loss: 0.4674474000930786
2023-01-22 17:13:41.677973: step: 386/470, loss: 1.1901929378509521
2023-01-22 17:13:42.426641: step: 388/470, loss: 0.27445924282073975
2023-01-22 17:13:43.188016: step: 390/470, loss: 0.4656749665737152
2023-01-22 17:13:43.958186: step: 392/470, loss: 0.29722970724105835
2023-01-22 17:13:44.677430: step: 394/470, loss: 0.16318340599536896
2023-01-22 17:13:45.338697: step: 396/470, loss: 0.7538102865219116
2023-01-22 17:13:46.060067: step: 398/470, loss: 0.34675395488739014
2023-01-22 17:13:46.823513: step: 400/470, loss: 1.1929813623428345
2023-01-22 17:13:47.548694: step: 402/470, loss: 0.44265463948249817
2023-01-22 17:13:48.333891: step: 404/470, loss: 8.768211364746094
2023-01-22 17:13:49.164060: step: 406/470, loss: 0.8950780034065247
2023-01-22 17:13:49.955440: step: 408/470, loss: 0.7870341539382935
2023-01-22 17:13:50.642029: step: 410/470, loss: 2.6422438621520996
2023-01-22 17:13:51.357138: step: 412/470, loss: 1.0197150707244873
2023-01-22 17:13:52.239926: step: 414/470, loss: 1.3697253465652466
2023-01-22 17:13:53.016496: step: 416/470, loss: 1.2400399446487427
2023-01-22 17:13:53.789704: step: 418/470, loss: 0.4381885826587677
2023-01-22 17:13:54.542451: step: 420/470, loss: 0.4691491425037384
2023-01-22 17:13:55.273708: step: 422/470, loss: 0.3527713418006897
2023-01-22 17:13:55.981719: step: 424/470, loss: 0.6151089072227478
2023-01-22 17:13:56.782403: step: 426/470, loss: 0.35179460048675537
2023-01-22 17:13:57.454472: step: 428/470, loss: 0.31551289558410645
2023-01-22 17:13:58.151498: step: 430/470, loss: 0.3387365937232971
2023-01-22 17:13:58.833813: step: 432/470, loss: 0.9518783092498779
2023-01-22 17:13:59.499678: step: 434/470, loss: 0.33223646879196167
2023-01-22 17:14:00.284792: step: 436/470, loss: 0.948758065700531
2023-01-22 17:14:01.147495: step: 438/470, loss: 0.7131083607673645
2023-01-22 17:14:01.857491: step: 440/470, loss: 0.22820569574832916
2023-01-22 17:14:02.635697: step: 442/470, loss: 1.1058170795440674
2023-01-22 17:14:03.366651: step: 444/470, loss: 0.5581318140029907
2023-01-22 17:14:04.118906: step: 446/470, loss: 0.977337658405304
2023-01-22 17:14:04.903655: step: 448/470, loss: 0.9387962222099304
2023-01-22 17:14:05.638337: step: 450/470, loss: 0.45336490869522095
2023-01-22 17:14:06.323404: step: 452/470, loss: 0.7090914249420166
2023-01-22 17:14:07.063462: step: 454/470, loss: 1.7675325870513916
2023-01-22 17:14:07.915196: step: 456/470, loss: 0.7944380044937134
2023-01-22 17:14:08.620197: step: 458/470, loss: 0.595599353313446
2023-01-22 17:14:09.369351: step: 460/470, loss: 0.7079035043716431
2023-01-22 17:14:10.090000: step: 462/470, loss: 1.0472602844238281
2023-01-22 17:14:10.844721: step: 464/470, loss: 0.6768998503684998
2023-01-22 17:14:11.624678: step: 466/470, loss: 0.6595719456672668
2023-01-22 17:14:12.430221: step: 468/470, loss: 1.1421606540679932
2023-01-22 17:14:13.237226: step: 470/470, loss: 0.4721830487251282
2023-01-22 17:14:13.945522: step: 472/470, loss: 0.27509674429893494
2023-01-22 17:14:14.711470: step: 474/470, loss: 2.248384714126587
2023-01-22 17:14:15.445333: step: 476/470, loss: 0.5151785016059875
2023-01-22 17:14:16.245591: step: 478/470, loss: 1.4433629512786865
2023-01-22 17:14:16.954742: step: 480/470, loss: 0.573886513710022
2023-01-22 17:14:17.687129: step: 482/470, loss: 0.4885188937187195
2023-01-22 17:14:18.382805: step: 484/470, loss: 0.9017962217330933
2023-01-22 17:14:19.132093: step: 486/470, loss: 0.47882330417633057
2023-01-22 17:14:19.869920: step: 488/470, loss: 0.43378081917762756
2023-01-22 17:14:20.712583: step: 490/470, loss: 1.083345890045166
2023-01-22 17:14:21.431938: step: 492/470, loss: 0.5740756392478943
2023-01-22 17:14:22.190560: step: 494/470, loss: 0.7037774324417114
2023-01-22 17:14:22.955036: step: 496/470, loss: 1.5782699584960938
2023-01-22 17:14:23.674377: step: 498/470, loss: 1.1951762437820435
2023-01-22 17:14:24.350229: step: 500/470, loss: 3.3578271865844727
2023-01-22 17:14:25.061486: step: 502/470, loss: 0.5678948760032654
2023-01-22 17:14:25.711938: step: 504/470, loss: 0.7719627022743225
2023-01-22 17:14:26.421887: step: 506/470, loss: 0.2801421284675598
2023-01-22 17:14:27.122585: step: 508/470, loss: 0.18048332631587982
2023-01-22 17:14:27.800071: step: 510/470, loss: 1.8545786142349243
2023-01-22 17:14:28.556701: step: 512/470, loss: 1.0798882246017456
2023-01-22 17:14:29.320111: step: 514/470, loss: 1.414536952972412
2023-01-22 17:14:30.075444: step: 516/470, loss: 0.5196714997291565
2023-01-22 17:14:30.836558: step: 518/470, loss: 0.41817137598991394
2023-01-22 17:14:31.594521: step: 520/470, loss: 0.5657111406326294
2023-01-22 17:14:32.347831: step: 522/470, loss: 0.34673720598220825
2023-01-22 17:14:33.067251: step: 524/470, loss: 0.7128427028656006
2023-01-22 17:14:33.777698: step: 526/470, loss: 0.45498931407928467
2023-01-22 17:14:34.504535: step: 528/470, loss: 0.45157119631767273
2023-01-22 17:14:35.189932: step: 530/470, loss: 0.4576375186443329
2023-01-22 17:14:35.979517: step: 532/470, loss: 0.33187219500541687
2023-01-22 17:14:36.764802: step: 534/470, loss: 0.35542771220207214
2023-01-22 17:14:37.519522: step: 536/470, loss: 0.6708710193634033
2023-01-22 17:14:38.304334: step: 538/470, loss: 0.8843319416046143
2023-01-22 17:14:38.954342: step: 540/470, loss: 0.8301752805709839
2023-01-22 17:14:39.714885: step: 542/470, loss: 0.2672118842601776
2023-01-22 17:14:40.537007: step: 544/470, loss: 0.3918260335922241
2023-01-22 17:14:41.371615: step: 546/470, loss: 0.4030534029006958
2023-01-22 17:14:42.207919: step: 548/470, loss: 3.20204496383667
2023-01-22 17:14:42.940567: step: 550/470, loss: 2.8569650650024414
2023-01-22 17:14:43.603315: step: 552/470, loss: 0.45698219537734985
2023-01-22 17:14:44.300649: step: 554/470, loss: 0.2088402956724167
2023-01-22 17:14:45.170829: step: 556/470, loss: 0.5278826951980591
2023-01-22 17:14:45.829681: step: 558/470, loss: 0.3262355327606201
2023-01-22 17:14:46.558185: step: 560/470, loss: 0.48174381256103516
2023-01-22 17:14:47.380486: step: 562/470, loss: 0.8578274250030518
2023-01-22 17:14:48.107292: step: 564/470, loss: 2.5235321521759033
2023-01-22 17:14:48.862959: step: 566/470, loss: 0.13515417277812958
2023-01-22 17:14:49.657251: step: 568/470, loss: 0.5105624794960022
2023-01-22 17:14:50.407449: step: 570/470, loss: 1.3545113801956177
2023-01-22 17:14:51.104315: step: 572/470, loss: 0.43925705552101135
2023-01-22 17:14:51.817353: step: 574/470, loss: 0.8375481367111206
2023-01-22 17:14:52.549940: step: 576/470, loss: 1.22329580783844
2023-01-22 17:14:53.277635: step: 578/470, loss: 1.2642005681991577
2023-01-22 17:14:54.018965: step: 580/470, loss: 0.7364957332611084
2023-01-22 17:14:54.796039: step: 582/470, loss: 12.388585090637207
2023-01-22 17:14:55.514752: step: 584/470, loss: 0.9263208508491516
2023-01-22 17:14:56.243210: step: 586/470, loss: 0.48008114099502563
2023-01-22 17:14:56.944512: step: 588/470, loss: 5.323960781097412
2023-01-22 17:14:57.644580: step: 590/470, loss: 0.3100872337818146
2023-01-22 17:14:58.471580: step: 592/470, loss: 0.39643803238868713
2023-01-22 17:14:59.153325: step: 594/470, loss: 0.5192726254463196
2023-01-22 17:14:59.869160: step: 596/470, loss: 0.08385767787694931
2023-01-22 17:15:00.646096: step: 598/470, loss: 0.23493848741054535
2023-01-22 17:15:01.407864: step: 600/470, loss: 0.8058767914772034
2023-01-22 17:15:02.154141: step: 602/470, loss: 0.7003133296966553
2023-01-22 17:15:02.897566: step: 604/470, loss: 0.3727822005748749
2023-01-22 17:15:03.644764: step: 606/470, loss: 1.2153240442276
2023-01-22 17:15:04.384436: step: 608/470, loss: 1.3041852712631226
2023-01-22 17:15:05.118681: step: 610/470, loss: 1.750708818435669
2023-01-22 17:15:05.856348: step: 612/470, loss: 2.3848016262054443
2023-01-22 17:15:06.704340: step: 614/470, loss: 0.21485082805156708
2023-01-22 17:15:07.453593: step: 616/470, loss: 1.353153109550476
2023-01-22 17:15:08.184476: step: 618/470, loss: 0.9749501347541809
2023-01-22 17:15:09.002580: step: 620/470, loss: 1.2679924964904785
2023-01-22 17:15:09.705047: step: 622/470, loss: 0.6863827705383301
2023-01-22 17:15:10.449431: step: 624/470, loss: 0.29089784622192383
2023-01-22 17:15:11.162170: step: 626/470, loss: 0.26793599128723145
2023-01-22 17:15:12.040568: step: 628/470, loss: 0.4520954489707947
2023-01-22 17:15:12.739284: step: 630/470, loss: 0.6169873476028442
2023-01-22 17:15:13.581583: step: 632/470, loss: 0.570949375629425
2023-01-22 17:15:14.286534: step: 634/470, loss: 0.278425008058548
2023-01-22 17:15:15.080131: step: 636/470, loss: 1.7957154512405396
2023-01-22 17:15:15.843588: step: 638/470, loss: 0.29361969232559204
2023-01-22 17:15:16.710050: step: 640/470, loss: 0.5023148059844971
2023-01-22 17:15:17.415395: step: 642/470, loss: 0.48273128271102905
2023-01-22 17:15:18.173336: step: 644/470, loss: 1.2374017238616943
2023-01-22 17:15:18.968965: step: 646/470, loss: 0.22361309826374054
2023-01-22 17:15:19.699188: step: 648/470, loss: 0.7312672734260559
2023-01-22 17:15:20.454449: step: 650/470, loss: 0.360087126493454
2023-01-22 17:15:21.138364: step: 652/470, loss: 1.0528044700622559
2023-01-22 17:15:21.867136: step: 654/470, loss: 1.5701942443847656
2023-01-22 17:15:22.572846: step: 656/470, loss: 0.09973641484975815
2023-01-22 17:15:23.248734: step: 658/470, loss: 0.39809560775756836
2023-01-22 17:15:23.962986: step: 660/470, loss: 0.2803775668144226
2023-01-22 17:15:24.839378: step: 662/470, loss: 0.5510927438735962
2023-01-22 17:15:25.519592: step: 664/470, loss: 0.28761452436447144
2023-01-22 17:15:26.190064: step: 666/470, loss: 1.0456538200378418
2023-01-22 17:15:26.938486: step: 668/470, loss: 1.3108751773834229
2023-01-22 17:15:27.658705: step: 670/470, loss: 0.3738193213939667
2023-01-22 17:15:28.421575: step: 672/470, loss: 0.9928417205810547
2023-01-22 17:15:29.137281: step: 674/470, loss: 1.9106264114379883
2023-01-22 17:15:29.855059: step: 676/470, loss: 1.6555376052856445
2023-01-22 17:15:30.509097: step: 678/470, loss: 0.9879150390625
2023-01-22 17:15:31.163194: step: 680/470, loss: 1.1278126239776611
2023-01-22 17:15:31.928919: step: 682/470, loss: 0.7462809085845947
2023-01-22 17:15:32.609083: step: 684/470, loss: 0.2949332594871521
2023-01-22 17:15:33.312422: step: 686/470, loss: 0.5867691040039062
2023-01-22 17:15:34.074554: step: 688/470, loss: 0.783571720123291
2023-01-22 17:15:34.783911: step: 690/470, loss: 0.28259211778640747
2023-01-22 17:15:35.622274: step: 692/470, loss: 2.536674976348877
2023-01-22 17:15:36.373491: step: 694/470, loss: 0.3623759150505066
2023-01-22 17:15:37.062156: step: 696/470, loss: 0.904730498790741
2023-01-22 17:15:37.777099: step: 698/470, loss: 0.15288175642490387
2023-01-22 17:15:38.519855: step: 700/470, loss: 0.5689459443092346
2023-01-22 17:15:39.242905: step: 702/470, loss: 0.19390466809272766
2023-01-22 17:15:39.988996: step: 704/470, loss: 5.31660270690918
2023-01-22 17:15:40.730401: step: 706/470, loss: 3.0160305500030518
2023-01-22 17:15:41.441012: step: 708/470, loss: 0.5570680499076843
2023-01-22 17:15:42.159638: step: 710/470, loss: 0.6179437637329102
2023-01-22 17:15:42.922891: step: 712/470, loss: 0.9332218170166016
2023-01-22 17:15:43.604189: step: 714/470, loss: 0.5039190649986267
2023-01-22 17:15:44.305324: step: 716/470, loss: 2.8622703552246094
2023-01-22 17:15:45.144030: step: 718/470, loss: 1.5712451934814453
2023-01-22 17:15:45.851882: step: 720/470, loss: 0.47472241520881653
2023-01-22 17:15:46.584166: step: 722/470, loss: 0.4161088764667511
2023-01-22 17:15:47.335412: step: 724/470, loss: 0.408611923456192
2023-01-22 17:15:48.164716: step: 726/470, loss: 0.4773179292678833
2023-01-22 17:15:49.004520: step: 728/470, loss: 0.8895754814147949
2023-01-22 17:15:49.772002: step: 730/470, loss: 0.5631923675537109
2023-01-22 17:15:50.502280: step: 732/470, loss: 2.1085853576660156
2023-01-22 17:15:51.277432: step: 734/470, loss: 0.3119111657142639
2023-01-22 17:15:52.046230: step: 736/470, loss: 1.9866414070129395
2023-01-22 17:15:52.811734: step: 738/470, loss: 4.040884494781494
2023-01-22 17:15:53.496958: step: 740/470, loss: 1.7604376077651978
2023-01-22 17:15:54.324365: step: 742/470, loss: 1.824992060661316
2023-01-22 17:15:55.060968: step: 744/470, loss: 1.3587254285812378
2023-01-22 17:15:55.775964: step: 746/470, loss: 0.6129835844039917
2023-01-22 17:15:56.496907: step: 748/470, loss: 0.756197988986969
2023-01-22 17:15:57.288121: step: 750/470, loss: 1.2754197120666504
2023-01-22 17:15:58.175794: step: 752/470, loss: 2.0039122104644775
2023-01-22 17:15:58.922788: step: 754/470, loss: 0.694054365158081
2023-01-22 17:15:59.739905: step: 756/470, loss: 1.3741402626037598
2023-01-22 17:16:00.469370: step: 758/470, loss: 1.2446845769882202
2023-01-22 17:16:01.176782: step: 760/470, loss: 1.1512802839279175
2023-01-22 17:16:01.957396: step: 762/470, loss: 0.31948322057724
2023-01-22 17:16:02.683544: step: 764/470, loss: 0.9004114866256714
2023-01-22 17:16:03.495289: step: 766/470, loss: 0.7966269254684448
2023-01-22 17:16:04.268967: step: 768/470, loss: 0.5935583114624023
2023-01-22 17:16:05.028993: step: 770/470, loss: 1.2309718132019043
2023-01-22 17:16:05.742185: step: 772/470, loss: 0.7194991707801819
2023-01-22 17:16:06.458008: step: 774/470, loss: 0.9128872156143188
2023-01-22 17:16:07.175901: step: 776/470, loss: 0.262151837348938
2023-01-22 17:16:07.913831: step: 778/470, loss: 0.8558886051177979
2023-01-22 17:16:08.709845: step: 780/470, loss: 0.5099863409996033
2023-01-22 17:16:09.555580: step: 782/470, loss: 0.5506338477134705
2023-01-22 17:16:10.248498: step: 784/470, loss: 1.1489386558532715
2023-01-22 17:16:10.916556: step: 786/470, loss: 0.35874584317207336
2023-01-22 17:16:11.842807: step: 788/470, loss: 0.16319824755191803
2023-01-22 17:16:12.492305: step: 790/470, loss: 2.4045443534851074
2023-01-22 17:16:13.230484: step: 792/470, loss: 0.33701398968696594
2023-01-22 17:16:13.956672: step: 794/470, loss: 0.24340465664863586
2023-01-22 17:16:14.693180: step: 796/470, loss: 0.34215545654296875
2023-01-22 17:16:15.461847: step: 798/470, loss: 0.5952900648117065
2023-01-22 17:16:16.223351: step: 800/470, loss: 0.30067580938339233
2023-01-22 17:16:16.970197: step: 802/470, loss: 0.27011197805404663
2023-01-22 17:16:17.678802: step: 804/470, loss: 0.5309256315231323
2023-01-22 17:16:18.399887: step: 806/470, loss: 0.8290297985076904
2023-01-22 17:16:19.137489: step: 808/470, loss: 0.8590260148048401
2023-01-22 17:16:20.079520: step: 810/470, loss: 0.4753422737121582
2023-01-22 17:16:20.842895: step: 812/470, loss: 1.0361976623535156
2023-01-22 17:16:21.532530: step: 814/470, loss: 0.4226698577404022
2023-01-22 17:16:22.336656: step: 816/470, loss: 0.7795215249061584
2023-01-22 17:16:23.129532: step: 818/470, loss: 0.30003947019577026
2023-01-22 17:16:23.845501: step: 820/470, loss: 0.40043067932128906
2023-01-22 17:16:24.676196: step: 822/470, loss: 1.1841524839401245
2023-01-22 17:16:25.388756: step: 824/470, loss: 0.3702228367328644
2023-01-22 17:16:26.109954: step: 826/470, loss: 0.14006973803043365
2023-01-22 17:16:26.795670: step: 828/470, loss: 2.2968199253082275
2023-01-22 17:16:27.516227: step: 830/470, loss: 0.25178012251853943
2023-01-22 17:16:28.243089: step: 832/470, loss: 3.981785774230957
2023-01-22 17:16:28.963419: step: 834/470, loss: 0.2811685800552368
2023-01-22 17:16:29.731988: step: 836/470, loss: 1.4167596101760864
2023-01-22 17:16:30.568511: step: 838/470, loss: 1.3315188884735107
2023-01-22 17:16:31.287005: step: 840/470, loss: 0.20409701764583588
2023-01-22 17:16:32.018683: step: 842/470, loss: 0.794757604598999
2023-01-22 17:16:32.824780: step: 844/470, loss: 0.4948848485946655
2023-01-22 17:16:33.538492: step: 846/470, loss: 2.682526111602783
2023-01-22 17:16:34.314993: step: 848/470, loss: 0.9555333852767944
2023-01-22 17:16:35.074816: step: 850/470, loss: 1.1651482582092285
2023-01-22 17:16:35.801703: step: 852/470, loss: 0.5566208362579346
2023-01-22 17:16:36.525765: step: 854/470, loss: 0.6673471927642822
2023-01-22 17:16:37.255731: step: 856/470, loss: 0.4028908610343933
2023-01-22 17:16:37.998522: step: 858/470, loss: 1.8048272132873535
2023-01-22 17:16:38.750153: step: 860/470, loss: 2.100435972213745
2023-01-22 17:16:39.445271: step: 862/470, loss: 0.656417965888977
2023-01-22 17:16:40.215283: step: 864/470, loss: 0.5497065186500549
2023-01-22 17:16:40.973452: step: 866/470, loss: 0.4357500970363617
2023-01-22 17:16:41.634060: step: 868/470, loss: 0.40799766778945923
2023-01-22 17:16:42.342560: step: 870/470, loss: 1.0405466556549072
2023-01-22 17:16:43.069920: step: 872/470, loss: 1.2654999494552612
2023-01-22 17:16:43.830258: step: 874/470, loss: 0.4379280209541321
2023-01-22 17:16:44.637857: step: 876/470, loss: 1.0722965002059937
2023-01-22 17:16:45.351109: step: 878/470, loss: 0.22580832242965698
2023-01-22 17:16:46.061435: step: 880/470, loss: 0.5495216846466064
2023-01-22 17:16:46.828260: step: 882/470, loss: 0.23686954379081726
2023-01-22 17:16:47.532254: step: 884/470, loss: 0.6185952425003052
2023-01-22 17:16:48.311161: step: 886/470, loss: 1.4941705465316772
2023-01-22 17:16:49.030121: step: 888/470, loss: 6.853786945343018
2023-01-22 17:16:49.762451: step: 890/470, loss: 0.35840287804603577
2023-01-22 17:16:50.553174: step: 892/470, loss: 0.45041191577911377
2023-01-22 17:16:51.262690: step: 894/470, loss: 0.6162185668945312
2023-01-22 17:16:51.990284: step: 896/470, loss: 0.2759486436843872
2023-01-22 17:16:52.732123: step: 898/470, loss: 0.5360721349716187
2023-01-22 17:16:53.531879: step: 900/470, loss: 0.7364007234573364
2023-01-22 17:16:54.257988: step: 902/470, loss: 1.1799520254135132
2023-01-22 17:16:55.046422: step: 904/470, loss: 0.29465073347091675
2023-01-22 17:16:55.802689: step: 906/470, loss: 0.6081302165985107
2023-01-22 17:16:56.620137: step: 908/470, loss: 1.4914206266403198
2023-01-22 17:16:57.303574: step: 910/470, loss: 0.7673165202140808
2023-01-22 17:16:58.253816: step: 912/470, loss: 0.6707650423049927
2023-01-22 17:16:59.085693: step: 914/470, loss: 0.4942966103553772
2023-01-22 17:16:59.823511: step: 916/470, loss: 1.598168969154358
2023-01-22 17:17:00.639722: step: 918/470, loss: 1.6423366069793701
2023-01-22 17:17:01.526867: step: 920/470, loss: 1.2543729543685913
2023-01-22 17:17:02.268016: step: 922/470, loss: 0.7959638237953186
2023-01-22 17:17:03.028492: step: 924/470, loss: 1.5553340911865234
2023-01-22 17:17:03.826275: step: 926/470, loss: 1.098331093788147
2023-01-22 17:17:04.522212: step: 928/470, loss: 0.5700544118881226
2023-01-22 17:17:05.301937: step: 930/470, loss: 0.5074666738510132
2023-01-22 17:17:05.989000: step: 932/470, loss: 0.383233904838562
2023-01-22 17:17:06.684657: step: 934/470, loss: 1.1787450313568115
2023-01-22 17:17:07.391287: step: 936/470, loss: 5.3494744300842285
2023-01-22 17:17:08.132298: step: 938/470, loss: 1.421501636505127
2023-01-22 17:17:08.837979: step: 940/470, loss: 1.8558794260025024
2023-01-22 17:17:09.543019: step: 942/470, loss: 0.21680720150470734
==================================================
Loss: 0.910
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2642533988207765, 'r': 0.3093820627560135, 'f1': 0.2850425648119215}, 'combined': 0.21003136354562635, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32274736699326, 'r': 0.3286437131210215, 'f1': 0.3256688534024415}, 'combined': 0.22683402724548166, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.25691603610707214, 'r': 0.3115167876136985, 'f1': 0.281594077311182}, 'combined': 0.2074903727556078, 'epoch': 5}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32750994948956674, 'r': 0.33097399703224484, 'f1': 0.32923286170591554}, 'combined': 0.2293164210886974, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.24098832417994995, 'r': 0.31278180975158587, 'f1': 0.27223123656331255}, 'combined': 0.20059143746770397, 'epoch': 5}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3105387015499828, 'r': 0.33621786340892373, 'f1': 0.3228684930242665}, 'combined': 0.22488352747958862, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21323529411764705, 'r': 0.4142857142857143, 'f1': 0.28155339805825247}, 'combined': 0.1877022653721683, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.22058823529411764, 'r': 0.32608695652173914, 'f1': 0.2631578947368421}, 'combined': 0.13157894736842105, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35526315789473684, 'r': 0.23275862068965517, 'f1': 0.28125}, 'combined': 0.1875, 'epoch': 5}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2642533988207765, 'r': 0.3093820627560135, 'f1': 0.2850425648119215}, 'combined': 0.21003136354562635, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32274736699326, 'r': 0.3286437131210215, 'f1': 0.3256688534024415}, 'combined': 0.22683402724548166, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21323529411764705, 'r': 0.4142857142857143, 'f1': 0.28155339805825247}, 'combined': 0.1877022653721683, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28632789500190714, 'r': 0.21624004214565282, 'f1': 0.24639676153677628}, 'combined': 0.1815555085007825, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3345971660892728, 'r': 0.26806343565653556, 'f1': 0.2976576389530171}, 'combined': 0.20732372862399204, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.32407407407407407, 'r': 0.3804347826086957, 'f1': 0.35000000000000003}, 'combined': 0.17500000000000002, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.20295208490866637, 'r': 0.24783940803591395, 'f1': 0.22316093081021016}, 'combined': 0.16443437007068115, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.279769607766213, 'r': 0.2325601629274273, 'f1': 0.25398979050608034}, 'combined': 0.17690831179527985, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 1}
******************************
Epoch: 6
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 17:19:54.065028: step: 2/470, loss: 0.46913114190101624
2023-01-22 17:19:54.807215: step: 4/470, loss: 0.3887912929058075
2023-01-22 17:19:55.497540: step: 6/470, loss: 0.4061891436576843
2023-01-22 17:19:56.153411: step: 8/470, loss: 0.3760465979576111
2023-01-22 17:19:56.839623: step: 10/470, loss: 0.7916153073310852
2023-01-22 17:19:57.598154: step: 12/470, loss: 0.27006056904792786
2023-01-22 17:19:58.381528: step: 14/470, loss: 0.5665428042411804
2023-01-22 17:19:59.071192: step: 16/470, loss: 1.7454071044921875
2023-01-22 17:19:59.813031: step: 18/470, loss: 0.7772339582443237
2023-01-22 17:20:00.673423: step: 20/470, loss: 0.10461916774511337
2023-01-22 17:20:01.460462: step: 22/470, loss: 0.2878537178039551
2023-01-22 17:20:02.226250: step: 24/470, loss: 0.647771418094635
2023-01-22 17:20:02.982165: step: 26/470, loss: 0.3383640646934509
2023-01-22 17:20:03.709914: step: 28/470, loss: 0.6665865778923035
2023-01-22 17:20:04.483671: step: 30/470, loss: 0.4555095434188843
2023-01-22 17:20:05.252725: step: 32/470, loss: 0.3503432273864746
2023-01-22 17:20:05.963417: step: 34/470, loss: 0.2352353185415268
2023-01-22 17:20:06.641018: step: 36/470, loss: 1.3757781982421875
2023-01-22 17:20:07.332191: step: 38/470, loss: 0.4522511959075928
2023-01-22 17:20:08.152690: step: 40/470, loss: 0.2714459002017975
2023-01-22 17:20:08.875770: step: 42/470, loss: 0.26817435026168823
2023-01-22 17:20:09.599995: step: 44/470, loss: 0.6385064125061035
2023-01-22 17:20:10.372612: step: 46/470, loss: 0.2124578356742859
2023-01-22 17:20:11.135092: step: 48/470, loss: 0.12701259553432465
2023-01-22 17:20:11.865758: step: 50/470, loss: 0.8603786826133728
2023-01-22 17:20:12.666904: step: 52/470, loss: 0.4419752061367035
2023-01-22 17:20:13.396184: step: 54/470, loss: 3.501265287399292
2023-01-22 17:20:14.050863: step: 56/470, loss: 1.0722558498382568
2023-01-22 17:20:14.895151: step: 58/470, loss: 0.18907511234283447
2023-01-22 17:20:15.587335: step: 60/470, loss: 3.298689842224121
2023-01-22 17:20:16.305228: step: 62/470, loss: 0.30768173933029175
2023-01-22 17:20:17.014368: step: 64/470, loss: 0.3563343286514282
2023-01-22 17:20:17.752709: step: 66/470, loss: 0.727003276348114
2023-01-22 17:20:18.473198: step: 68/470, loss: 0.4526892602443695
2023-01-22 17:20:19.265142: step: 70/470, loss: 0.3136780560016632
2023-01-22 17:20:20.018652: step: 72/470, loss: 0.8561743497848511
2023-01-22 17:20:20.810790: step: 74/470, loss: 0.3809729814529419
2023-01-22 17:20:21.615112: step: 76/470, loss: 0.3150908648967743
2023-01-22 17:20:22.310650: step: 78/470, loss: 0.3166169822216034
2023-01-22 17:20:23.076459: step: 80/470, loss: 1.1344679594039917
2023-01-22 17:20:23.824620: step: 82/470, loss: 0.2568296790122986
2023-01-22 17:20:24.573812: step: 84/470, loss: 0.19643135368824005
2023-01-22 17:20:25.215262: step: 86/470, loss: 0.7549906373023987
2023-01-22 17:20:25.997728: step: 88/470, loss: 1.3208808898925781
2023-01-22 17:20:26.743314: step: 90/470, loss: 0.7214917540550232
2023-01-22 17:20:27.496983: step: 92/470, loss: 0.5928862690925598
2023-01-22 17:20:28.263841: step: 94/470, loss: 1.5356335639953613
2023-01-22 17:20:28.961857: step: 96/470, loss: 0.336683452129364
2023-01-22 17:20:29.723008: step: 98/470, loss: 5.519505500793457
2023-01-22 17:20:30.455249: step: 100/470, loss: 0.6986427307128906
2023-01-22 17:20:31.178377: step: 102/470, loss: 1.0318654775619507
2023-01-22 17:20:31.960891: step: 104/470, loss: 0.5973689556121826
2023-01-22 17:20:32.701215: step: 106/470, loss: 0.46960803866386414
2023-01-22 17:20:33.407835: step: 108/470, loss: 0.45779475569725037
2023-01-22 17:20:34.166560: step: 110/470, loss: 1.0601186752319336
2023-01-22 17:20:34.887364: step: 112/470, loss: 0.5745185613632202
2023-01-22 17:20:35.636767: step: 114/470, loss: 0.34605327248573303
2023-01-22 17:20:36.354530: step: 116/470, loss: 0.9498859643936157
2023-01-22 17:20:37.083246: step: 118/470, loss: 0.25999417901039124
2023-01-22 17:20:37.908026: step: 120/470, loss: 0.32462361454963684
2023-01-22 17:20:38.654181: step: 122/470, loss: 0.1615123152732849
2023-01-22 17:20:39.328663: step: 124/470, loss: 0.34102755784988403
2023-01-22 17:20:40.116013: step: 126/470, loss: 0.18280981481075287
2023-01-22 17:20:40.909616: step: 128/470, loss: 0.6337746977806091
2023-01-22 17:20:41.669703: step: 130/470, loss: 0.35255953669548035
2023-01-22 17:20:42.418524: step: 132/470, loss: 0.36493754386901855
2023-01-22 17:20:43.140596: step: 134/470, loss: 0.4938736855983734
2023-01-22 17:20:43.913855: step: 136/470, loss: 0.8310595154762268
2023-01-22 17:20:44.757410: step: 138/470, loss: 0.36032968759536743
2023-01-22 17:20:45.518849: step: 140/470, loss: 0.6380537748336792
2023-01-22 17:20:46.205710: step: 142/470, loss: 0.634308397769928
2023-01-22 17:20:46.924444: step: 144/470, loss: 0.3668132722377777
2023-01-22 17:20:47.675257: step: 146/470, loss: 0.263011634349823
2023-01-22 17:20:48.457075: step: 148/470, loss: 0.5096966624259949
2023-01-22 17:20:49.253695: step: 150/470, loss: 0.811173141002655
2023-01-22 17:20:49.969926: step: 152/470, loss: 0.5178455114364624
2023-01-22 17:20:50.696528: step: 154/470, loss: 0.7749607563018799
2023-01-22 17:20:51.469032: step: 156/470, loss: 0.5281555652618408
2023-01-22 17:20:52.301719: step: 158/470, loss: 0.7538830637931824
2023-01-22 17:20:53.058417: step: 160/470, loss: 0.13230903446674347
2023-01-22 17:20:53.879530: step: 162/470, loss: 1.0788747072219849
2023-01-22 17:20:54.646704: step: 164/470, loss: 0.6544629335403442
2023-01-22 17:20:55.340509: step: 166/470, loss: 0.6774575114250183
2023-01-22 17:20:55.982659: step: 168/470, loss: 0.5532941818237305
2023-01-22 17:20:56.729725: step: 170/470, loss: 0.3752504289150238
2023-01-22 17:20:57.500511: step: 172/470, loss: 1.2700722217559814
2023-01-22 17:20:58.205350: step: 174/470, loss: 0.4598991572856903
2023-01-22 17:20:59.046370: step: 176/470, loss: 2.486417293548584
2023-01-22 17:20:59.750262: step: 178/470, loss: 1.1655266284942627
2023-01-22 17:21:00.475774: step: 180/470, loss: 0.5170928239822388
2023-01-22 17:21:01.245330: step: 182/470, loss: 0.3279862403869629
2023-01-22 17:21:02.005982: step: 184/470, loss: 0.6931787729263306
2023-01-22 17:21:02.674336: step: 186/470, loss: 3.434424877166748
2023-01-22 17:21:03.384651: step: 188/470, loss: 0.5698443055152893
2023-01-22 17:21:04.009004: step: 190/470, loss: 0.19923467934131622
2023-01-22 17:21:04.661563: step: 192/470, loss: 0.250698983669281
2023-01-22 17:21:05.329561: step: 194/470, loss: 0.8043193817138672
2023-01-22 17:21:06.004919: step: 196/470, loss: 0.6029735803604126
2023-01-22 17:21:06.776715: step: 198/470, loss: 0.30597418546676636
2023-01-22 17:21:07.432492: step: 200/470, loss: 0.4779759645462036
2023-01-22 17:21:08.172761: step: 202/470, loss: 0.23415221273899078
2023-01-22 17:21:08.878662: step: 204/470, loss: 0.5951058268547058
2023-01-22 17:21:09.598794: step: 206/470, loss: 1.3589835166931152
2023-01-22 17:21:10.298876: step: 208/470, loss: 0.26382386684417725
2023-01-22 17:21:11.055544: step: 210/470, loss: 0.6494569182395935
2023-01-22 17:21:11.734139: step: 212/470, loss: 0.566684365272522
2023-01-22 17:21:12.478295: step: 214/470, loss: 0.5304621458053589
2023-01-22 17:21:13.269013: step: 216/470, loss: 0.36520957946777344
2023-01-22 17:21:14.021257: step: 218/470, loss: 1.9913074970245361
2023-01-22 17:21:14.702170: step: 220/470, loss: 0.5152336955070496
2023-01-22 17:21:15.454195: step: 222/470, loss: 0.7162929773330688
2023-01-22 17:21:16.238200: step: 224/470, loss: 0.4547756612300873
2023-01-22 17:21:17.005154: step: 226/470, loss: 1.3032582998275757
2023-01-22 17:21:17.714194: step: 228/470, loss: 0.29936328530311584
2023-01-22 17:21:18.514480: step: 230/470, loss: 0.4857710599899292
2023-01-22 17:21:19.280735: step: 232/470, loss: 0.701897382736206
2023-01-22 17:21:20.002364: step: 234/470, loss: 1.8443883657455444
2023-01-22 17:21:20.745333: step: 236/470, loss: 0.3022279441356659
2023-01-22 17:21:21.430727: step: 238/470, loss: 0.4773560166358948
2023-01-22 17:21:22.115801: step: 240/470, loss: 0.23034065961837769
2023-01-22 17:21:22.823111: step: 242/470, loss: 0.5290822386741638
2023-01-22 17:21:23.652992: step: 244/470, loss: 0.9485624432563782
2023-01-22 17:21:24.366992: step: 246/470, loss: 0.16987621784210205
2023-01-22 17:21:25.151697: step: 248/470, loss: 0.24645563960075378
2023-01-22 17:21:25.905402: step: 250/470, loss: 0.35188791155815125
2023-01-22 17:21:26.758082: step: 252/470, loss: 0.45709526538848877
2023-01-22 17:21:27.443127: step: 254/470, loss: 0.9818328022956848
2023-01-22 17:21:28.217550: step: 256/470, loss: 0.13087573647499084
2023-01-22 17:21:28.982558: step: 258/470, loss: 0.2843538224697113
2023-01-22 17:21:29.643477: step: 260/470, loss: 0.8852912783622742
2023-01-22 17:21:30.344149: step: 262/470, loss: 0.7009601593017578
2023-01-22 17:21:31.048626: step: 264/470, loss: 0.623857855796814
2023-01-22 17:21:31.760826: step: 266/470, loss: 0.18668121099472046
2023-01-22 17:21:32.503528: step: 268/470, loss: 0.9859969615936279
2023-01-22 17:21:33.213322: step: 270/470, loss: 0.6130749583244324
2023-01-22 17:21:33.906700: step: 272/470, loss: 0.7168523669242859
2023-01-22 17:21:34.696981: step: 274/470, loss: 0.4143531620502472
2023-01-22 17:21:35.470342: step: 276/470, loss: 0.7964304089546204
2023-01-22 17:21:36.201588: step: 278/470, loss: 0.6704311370849609
2023-01-22 17:21:36.937129: step: 280/470, loss: 1.371323823928833
2023-01-22 17:21:37.762704: step: 282/470, loss: 0.8651912212371826
2023-01-22 17:21:38.539655: step: 284/470, loss: 0.3530345559120178
2023-01-22 17:21:39.285399: step: 286/470, loss: 0.3043641448020935
2023-01-22 17:21:39.991141: step: 288/470, loss: 0.1724073439836502
2023-01-22 17:21:40.786703: step: 290/470, loss: 0.2577505111694336
2023-01-22 17:21:41.585747: step: 292/470, loss: 0.3419148623943329
2023-01-22 17:21:42.383018: step: 294/470, loss: 0.2580012083053589
2023-01-22 17:21:43.163635: step: 296/470, loss: 0.7738077044487
2023-01-22 17:21:43.987334: step: 298/470, loss: 1.5503582954406738
2023-01-22 17:21:44.830928: step: 300/470, loss: 0.36178097128868103
2023-01-22 17:21:45.606529: step: 302/470, loss: 3.4303958415985107
2023-01-22 17:21:46.388295: step: 304/470, loss: 1.861863374710083
2023-01-22 17:21:47.199688: step: 306/470, loss: 0.3691105246543884
2023-01-22 17:21:48.054466: step: 308/470, loss: 0.2734450399875641
2023-01-22 17:21:48.889222: step: 310/470, loss: 1.402500033378601
2023-01-22 17:21:49.783114: step: 312/470, loss: 0.5831880569458008
2023-01-22 17:21:50.547366: step: 314/470, loss: 0.6897637844085693
2023-01-22 17:21:51.265524: step: 316/470, loss: 0.45082640647888184
2023-01-22 17:21:52.079461: step: 318/470, loss: 0.24482515454292297
2023-01-22 17:21:52.816826: step: 320/470, loss: 0.731791615486145
2023-01-22 17:21:53.563157: step: 322/470, loss: 0.4253387749195099
2023-01-22 17:21:54.269598: step: 324/470, loss: 0.7619374394416809
2023-01-22 17:21:54.981522: step: 326/470, loss: 0.3442683815956116
2023-01-22 17:21:55.847939: step: 328/470, loss: 0.7861752510070801
2023-01-22 17:21:56.597449: step: 330/470, loss: 0.6463299989700317
2023-01-22 17:21:57.321814: step: 332/470, loss: 0.7153461575508118
2023-01-22 17:21:58.076837: step: 334/470, loss: 0.2146746665239334
2023-01-22 17:21:58.805094: step: 336/470, loss: 0.26649871468544006
2023-01-22 17:21:59.500280: step: 338/470, loss: 0.24172751605510712
2023-01-22 17:22:00.232686: step: 340/470, loss: 0.26765137910842896
2023-01-22 17:22:00.987882: step: 342/470, loss: 0.253934770822525
2023-01-22 17:22:01.815921: step: 344/470, loss: 0.4995259940624237
2023-01-22 17:22:02.648610: step: 346/470, loss: 0.9960381388664246
2023-01-22 17:22:03.504486: step: 348/470, loss: 0.3678852617740631
2023-01-22 17:22:04.299564: step: 350/470, loss: 1.4511865377426147
2023-01-22 17:22:05.045189: step: 352/470, loss: 0.4098103940486908
2023-01-22 17:22:05.780214: step: 354/470, loss: 0.8686992526054382
2023-01-22 17:22:06.652529: step: 356/470, loss: 0.3895498514175415
2023-01-22 17:22:07.435225: step: 358/470, loss: 0.4124021828174591
2023-01-22 17:22:08.115125: step: 360/470, loss: 0.39607658982276917
2023-01-22 17:22:08.869088: step: 362/470, loss: 0.5164311528205872
2023-01-22 17:22:09.653736: step: 364/470, loss: 0.38875195384025574
2023-01-22 17:22:10.415555: step: 366/470, loss: 1.0487358570098877
2023-01-22 17:22:11.151972: step: 368/470, loss: 0.2708939015865326
2023-01-22 17:22:12.020427: step: 370/470, loss: 0.3877793848514557
2023-01-22 17:22:12.878893: step: 372/470, loss: 1.2002607583999634
2023-01-22 17:22:13.630474: step: 374/470, loss: 0.542573869228363
2023-01-22 17:22:14.347596: step: 376/470, loss: 0.11055511236190796
2023-01-22 17:22:15.176234: step: 378/470, loss: 0.9897867441177368
2023-01-22 17:22:15.916705: step: 380/470, loss: 1.5830128192901611
2023-01-22 17:22:16.667853: step: 382/470, loss: 0.3970726430416107
2023-01-22 17:22:17.457480: step: 384/470, loss: 0.5450624227523804
2023-01-22 17:22:18.167961: step: 386/470, loss: 0.47805434465408325
2023-01-22 17:22:18.960022: step: 388/470, loss: 0.5078467130661011
2023-01-22 17:22:19.714187: step: 390/470, loss: 0.8410879969596863
2023-01-22 17:22:20.404429: step: 392/470, loss: 0.564120352268219
2023-01-22 17:22:21.164233: step: 394/470, loss: 0.4679042398929596
2023-01-22 17:22:21.892081: step: 396/470, loss: 0.3612174689769745
2023-01-22 17:22:22.670058: step: 398/470, loss: 0.36533409357070923
2023-01-22 17:22:23.385975: step: 400/470, loss: 1.2119630575180054
2023-01-22 17:22:24.140842: step: 402/470, loss: 0.5056576132774353
2023-01-22 17:22:24.889654: step: 404/470, loss: 0.634218156337738
2023-01-22 17:22:25.558393: step: 406/470, loss: 3.289701223373413
2023-01-22 17:22:26.304846: step: 408/470, loss: 0.0705670490860939
2023-01-22 17:22:27.075343: step: 410/470, loss: 0.584409773349762
2023-01-22 17:22:27.829975: step: 412/470, loss: 0.5824598073959351
2023-01-22 17:22:28.563400: step: 414/470, loss: 1.616589069366455
2023-01-22 17:22:29.356184: step: 416/470, loss: 0.17866788804531097
2023-01-22 17:22:30.079197: step: 418/470, loss: 0.4966486692428589
2023-01-22 17:22:30.823225: step: 420/470, loss: 0.14873385429382324
2023-01-22 17:22:31.615669: step: 422/470, loss: 0.6694574952125549
2023-01-22 17:22:32.277152: step: 424/470, loss: 0.6328750848770142
2023-01-22 17:22:33.003072: step: 426/470, loss: 0.42485523223876953
2023-01-22 17:22:33.761451: step: 428/470, loss: 0.36120638251304626
2023-01-22 17:22:34.569803: step: 430/470, loss: 0.38846999406814575
2023-01-22 17:22:35.304499: step: 432/470, loss: 1.087398886680603
2023-01-22 17:22:36.090208: step: 434/470, loss: 0.24200265109539032
2023-01-22 17:22:36.812082: step: 436/470, loss: 0.44511035084724426
2023-01-22 17:22:37.583451: step: 438/470, loss: 0.578136146068573
2023-01-22 17:22:38.307929: step: 440/470, loss: 0.04400842636823654
2023-01-22 17:22:39.064769: step: 442/470, loss: 0.42095282673835754
2023-01-22 17:22:39.807591: step: 444/470, loss: 0.2756405174732208
2023-01-22 17:22:40.569469: step: 446/470, loss: 0.6643534302711487
2023-01-22 17:22:41.295235: step: 448/470, loss: 0.5027168989181519
2023-01-22 17:22:41.963637: step: 450/470, loss: 0.5610426664352417
2023-01-22 17:22:42.720144: step: 452/470, loss: 0.7037179470062256
2023-01-22 17:22:43.446650: step: 454/470, loss: 1.122239112854004
2023-01-22 17:22:44.339859: step: 456/470, loss: 0.4908750653266907
2023-01-22 17:22:45.080797: step: 458/470, loss: 0.4792795181274414
2023-01-22 17:22:45.826711: step: 460/470, loss: 0.3053261637687683
2023-01-22 17:22:46.541323: step: 462/470, loss: 0.5884460806846619
2023-01-22 17:22:47.243542: step: 464/470, loss: 2.739895820617676
2023-01-22 17:22:48.026603: step: 466/470, loss: 0.8006578683853149
2023-01-22 17:22:48.740566: step: 468/470, loss: 1.319366455078125
2023-01-22 17:22:49.540678: step: 470/470, loss: 2.922891139984131
2023-01-22 17:22:50.260965: step: 472/470, loss: 0.2505470812320709
2023-01-22 17:22:51.093657: step: 474/470, loss: 0.4484995901584625
2023-01-22 17:22:51.833367: step: 476/470, loss: 0.5939066410064697
2023-01-22 17:22:52.572258: step: 478/470, loss: 0.27172547578811646
2023-01-22 17:22:53.492072: step: 480/470, loss: 0.3544227182865143
2023-01-22 17:22:54.093928: step: 482/470, loss: 0.19915227591991425
2023-01-22 17:22:54.801866: step: 484/470, loss: 0.5538665056228638
2023-01-22 17:22:55.673976: step: 486/470, loss: 1.7567211389541626
2023-01-22 17:22:56.475212: step: 488/470, loss: 0.23877158761024475
2023-01-22 17:22:57.221673: step: 490/470, loss: 0.37857306003570557
2023-01-22 17:22:57.923065: step: 492/470, loss: 0.2932409346103668
2023-01-22 17:22:58.791767: step: 494/470, loss: 0.3827472925186157
2023-01-22 17:22:59.497216: step: 496/470, loss: 1.6333781480789185
2023-01-22 17:23:00.308303: step: 498/470, loss: 0.33791467547416687
2023-01-22 17:23:01.013620: step: 500/470, loss: 0.32591983675956726
2023-01-22 17:23:01.753459: step: 502/470, loss: 0.4133923649787903
2023-01-22 17:23:02.527722: step: 504/470, loss: 1.181382417678833
2023-01-22 17:23:03.320054: step: 506/470, loss: 5.112921237945557
2023-01-22 17:23:04.091980: step: 508/470, loss: 0.24143043160438538
2023-01-22 17:23:04.797933: step: 510/470, loss: 0.14529116451740265
2023-01-22 17:23:05.536901: step: 512/470, loss: 0.4227316975593567
2023-01-22 17:23:06.288917: step: 514/470, loss: 1.3871934413909912
2023-01-22 17:23:07.037489: step: 516/470, loss: 1.0044560432434082
2023-01-22 17:23:07.787690: step: 518/470, loss: 0.29355016350746155
2023-01-22 17:23:08.548763: step: 520/470, loss: 0.29415249824523926
2023-01-22 17:23:09.262895: step: 522/470, loss: 1.2313815355300903
2023-01-22 17:23:09.976071: step: 524/470, loss: 0.27359142899513245
2023-01-22 17:23:10.698707: step: 526/470, loss: 0.9681866765022278
2023-01-22 17:23:11.418886: step: 528/470, loss: 0.4213339388370514
2023-01-22 17:23:12.176798: step: 530/470, loss: 0.6697089672088623
2023-01-22 17:23:12.911504: step: 532/470, loss: 1.0336536169052124
2023-01-22 17:23:13.667364: step: 534/470, loss: 0.18524248898029327
2023-01-22 17:23:14.440020: step: 536/470, loss: 0.5117719173431396
2023-01-22 17:23:15.235170: step: 538/470, loss: 0.563843846321106
2023-01-22 17:23:16.060917: step: 540/470, loss: 0.42840808629989624
2023-01-22 17:23:16.881139: step: 542/470, loss: 1.106241226196289
2023-01-22 17:23:17.575202: step: 544/470, loss: 0.27418795228004456
2023-01-22 17:23:18.261156: step: 546/470, loss: 0.1472853273153305
2023-01-22 17:23:19.058473: step: 548/470, loss: 7.418033599853516
2023-01-22 17:23:19.782419: step: 550/470, loss: 0.27359166741371155
2023-01-22 17:23:20.649129: step: 552/470, loss: 0.23063817620277405
2023-01-22 17:23:21.417356: step: 554/470, loss: 1.2608001232147217
2023-01-22 17:23:22.136610: step: 556/470, loss: 0.40279632806777954
2023-01-22 17:23:22.903295: step: 558/470, loss: 1.5408741235733032
2023-01-22 17:23:23.650026: step: 560/470, loss: 0.8065625429153442
2023-01-22 17:23:24.402236: step: 562/470, loss: 0.20651859045028687
2023-01-22 17:23:25.141606: step: 564/470, loss: 1.4523169994354248
2023-01-22 17:23:25.843509: step: 566/470, loss: 0.589959442615509
2023-01-22 17:23:26.537061: step: 568/470, loss: 1.7879338264465332
2023-01-22 17:23:27.201451: step: 570/470, loss: 1.0214474201202393
2023-01-22 17:23:27.972703: step: 572/470, loss: 0.5045061707496643
2023-01-22 17:23:28.709994: step: 574/470, loss: 1.857149600982666
2023-01-22 17:23:29.459541: step: 576/470, loss: 0.49319571256637573
2023-01-22 17:23:30.156962: step: 578/470, loss: 1.0521998405456543
2023-01-22 17:23:30.849884: step: 580/470, loss: 0.8370808362960815
2023-01-22 17:23:31.707421: step: 582/470, loss: 0.752477765083313
2023-01-22 17:23:32.422736: step: 584/470, loss: 0.2725905478000641
2023-01-22 17:23:33.178164: step: 586/470, loss: 1.0730834007263184
2023-01-22 17:23:33.892742: step: 588/470, loss: 0.5087326765060425
2023-01-22 17:23:34.615112: step: 590/470, loss: 0.23478223383426666
2023-01-22 17:23:35.481990: step: 592/470, loss: 0.5487679243087769
2023-01-22 17:23:36.253347: step: 594/470, loss: 0.7396395206451416
2023-01-22 17:23:37.049703: step: 596/470, loss: 1.1245198249816895
2023-01-22 17:23:37.795382: step: 598/470, loss: 0.6135616302490234
2023-01-22 17:23:38.596068: step: 600/470, loss: 1.019770622253418
2023-01-22 17:23:39.337413: step: 602/470, loss: 0.26452648639678955
2023-01-22 17:23:40.042419: step: 604/470, loss: 1.3409970998764038
2023-01-22 17:23:40.739824: step: 606/470, loss: 0.41237398982048035
2023-01-22 17:23:41.482257: step: 608/470, loss: 0.1840699464082718
2023-01-22 17:23:42.318486: step: 610/470, loss: 1.9304275512695312
2023-01-22 17:23:43.107784: step: 612/470, loss: 0.3491050899028778
2023-01-22 17:23:43.886867: step: 614/470, loss: 0.7268772721290588
2023-01-22 17:23:44.875607: step: 616/470, loss: 0.4124700129032135
2023-01-22 17:23:45.602618: step: 618/470, loss: 0.2458016574382782
2023-01-22 17:23:46.350536: step: 620/470, loss: 0.25328996777534485
2023-01-22 17:23:47.101809: step: 622/470, loss: 0.3315480351448059
2023-01-22 17:23:47.803326: step: 624/470, loss: 0.4825563430786133
2023-01-22 17:23:48.495429: step: 626/470, loss: 0.6606676578521729
2023-01-22 17:23:49.323729: step: 628/470, loss: 0.5025643110275269
2023-01-22 17:23:50.093650: step: 630/470, loss: 0.3678370714187622
2023-01-22 17:23:50.936305: step: 632/470, loss: 0.4976312816143036
2023-01-22 17:23:51.650369: step: 634/470, loss: 0.22208793461322784
2023-01-22 17:23:52.392024: step: 636/470, loss: 1.0294278860092163
2023-01-22 17:23:53.127006: step: 638/470, loss: 1.9563071727752686
2023-01-22 17:23:53.937095: step: 640/470, loss: 2.2986676692962646
2023-01-22 17:23:54.655746: step: 642/470, loss: 1.1405041217803955
2023-01-22 17:23:55.433289: step: 644/470, loss: 0.3489605784416199
2023-01-22 17:23:56.210874: step: 646/470, loss: 0.9580307602882385
2023-01-22 17:23:56.933653: step: 648/470, loss: 0.27914896607398987
2023-01-22 17:23:57.616918: step: 650/470, loss: 0.983113169670105
2023-01-22 17:23:58.223145: step: 652/470, loss: 0.4380299746990204
2023-01-22 17:23:58.967747: step: 654/470, loss: 2.07478666305542
2023-01-22 17:23:59.639722: step: 656/470, loss: 0.8824518918991089
2023-01-22 17:24:00.328131: step: 658/470, loss: 0.3353792130947113
2023-01-22 17:24:01.115685: step: 660/470, loss: 0.4645380675792694
2023-01-22 17:24:01.912842: step: 662/470, loss: 0.8738151788711548
2023-01-22 17:24:02.616276: step: 664/470, loss: 0.2929144501686096
2023-01-22 17:24:03.324544: step: 666/470, loss: 0.2078137993812561
2023-01-22 17:24:04.122017: step: 668/470, loss: 0.3449633717536926
2023-01-22 17:24:04.934103: step: 670/470, loss: 4.962142467498779
2023-01-22 17:24:05.685480: step: 672/470, loss: 0.266704261302948
2023-01-22 17:24:06.447369: step: 674/470, loss: 0.7107980847358704
2023-01-22 17:24:07.235888: step: 676/470, loss: 0.7811194658279419
2023-01-22 17:24:08.047013: step: 678/470, loss: 0.6608456969261169
2023-01-22 17:24:08.738635: step: 680/470, loss: 0.36729899048805237
2023-01-22 17:24:09.557839: step: 682/470, loss: 1.2359304428100586
2023-01-22 17:24:10.310107: step: 684/470, loss: 0.6000874638557434
2023-01-22 17:24:11.004497: step: 686/470, loss: 0.30050334334373474
2023-01-22 17:24:11.676564: step: 688/470, loss: 1.0338342189788818
2023-01-22 17:24:12.374274: step: 690/470, loss: 0.6685682535171509
2023-01-22 17:24:13.140518: step: 692/470, loss: 2.2404136657714844
2023-01-22 17:24:13.932361: step: 694/470, loss: 0.9425269365310669
2023-01-22 17:24:14.700934: step: 696/470, loss: 0.9702392220497131
2023-01-22 17:24:15.459209: step: 698/470, loss: 0.9032459259033203
2023-01-22 17:24:16.191048: step: 700/470, loss: 0.46420717239379883
2023-01-22 17:24:16.942728: step: 702/470, loss: 0.16542571783065796
2023-01-22 17:24:17.636534: step: 704/470, loss: 0.4053605794906616
2023-01-22 17:24:18.380053: step: 706/470, loss: 0.5979849100112915
2023-01-22 17:24:19.061084: step: 708/470, loss: 0.4328975975513458
2023-01-22 17:24:19.804969: step: 710/470, loss: 0.603645920753479
2023-01-22 17:24:20.510145: step: 712/470, loss: 0.6759111881256104
2023-01-22 17:24:21.303053: step: 714/470, loss: 0.17363420128822327
2023-01-22 17:24:22.105587: step: 716/470, loss: 0.45107150077819824
2023-01-22 17:24:22.777783: step: 718/470, loss: 0.30570104718208313
2023-01-22 17:24:23.519665: step: 720/470, loss: 0.8583315014839172
2023-01-22 17:24:24.345883: step: 722/470, loss: 1.9609408378601074
2023-01-22 17:24:25.039844: step: 724/470, loss: 0.3080098032951355
2023-01-22 17:24:25.810593: step: 726/470, loss: 0.6534498333930969
2023-01-22 17:24:26.449393: step: 728/470, loss: 0.9306233525276184
2023-01-22 17:24:27.226453: step: 730/470, loss: 0.4405674934387207
2023-01-22 17:24:27.997367: step: 732/470, loss: 1.8319543600082397
2023-01-22 17:24:28.739228: step: 734/470, loss: 0.3661953806877136
2023-01-22 17:24:29.458385: step: 736/470, loss: 1.5648008584976196
2023-01-22 17:24:30.151863: step: 738/470, loss: 1.1446764469146729
2023-01-22 17:24:30.849475: step: 740/470, loss: 0.5488044619560242
2023-01-22 17:24:31.581024: step: 742/470, loss: 0.7896547913551331
2023-01-22 17:24:32.268866: step: 744/470, loss: 0.2640857994556427
2023-01-22 17:24:33.017843: step: 746/470, loss: 0.12843212485313416
2023-01-22 17:24:33.743687: step: 748/470, loss: 0.7997981905937195
2023-01-22 17:24:34.557285: step: 750/470, loss: 0.9078993797302246
2023-01-22 17:24:35.287587: step: 752/470, loss: 0.5914628505706787
2023-01-22 17:24:36.000532: step: 754/470, loss: 0.6052213311195374
2023-01-22 17:24:36.748805: step: 756/470, loss: 0.16759061813354492
2023-01-22 17:24:37.488241: step: 758/470, loss: 0.423061728477478
2023-01-22 17:24:38.309432: step: 760/470, loss: 0.9458290934562683
2023-01-22 17:24:39.102885: step: 762/470, loss: 0.44426000118255615
2023-01-22 17:24:39.842191: step: 764/470, loss: 0.48349910974502563
2023-01-22 17:24:40.623114: step: 766/470, loss: 1.0650396347045898
2023-01-22 17:24:41.452148: step: 768/470, loss: 0.9286936521530151
2023-01-22 17:24:42.236379: step: 770/470, loss: 0.5421870946884155
2023-01-22 17:24:42.932497: step: 772/470, loss: 0.6645587682723999
2023-01-22 17:24:43.678255: step: 774/470, loss: 0.3658778965473175
2023-01-22 17:24:44.402751: step: 776/470, loss: 0.4753032624721527
2023-01-22 17:24:45.109668: step: 778/470, loss: 3.5970163345336914
2023-01-22 17:24:46.029773: step: 780/470, loss: 0.8341478109359741
2023-01-22 17:24:46.935804: step: 782/470, loss: 0.875688910484314
2023-01-22 17:24:47.719058: step: 784/470, loss: 0.44907113909721375
2023-01-22 17:24:48.481112: step: 786/470, loss: 0.9514230489730835
2023-01-22 17:24:49.296285: step: 788/470, loss: 0.46913057565689087
2023-01-22 17:24:50.192807: step: 790/470, loss: 1.4260585308074951
2023-01-22 17:24:51.087926: step: 792/470, loss: 0.3309740424156189
2023-01-22 17:24:51.838975: step: 794/470, loss: 0.2095767855644226
2023-01-22 17:24:52.543769: step: 796/470, loss: 1.0972883701324463
2023-01-22 17:24:53.284847: step: 798/470, loss: 0.6162765026092529
2023-01-22 17:24:53.997923: step: 800/470, loss: 2.2116286754608154
2023-01-22 17:24:54.790282: step: 802/470, loss: 0.3036021888256073
2023-01-22 17:24:55.583553: step: 804/470, loss: 0.762950599193573
2023-01-22 17:24:56.340956: step: 806/470, loss: 0.6544211506843567
2023-01-22 17:24:57.033299: step: 808/470, loss: 0.37966063618659973
2023-01-22 17:24:57.818775: step: 810/470, loss: 1.9399421215057373
2023-01-22 17:24:58.592805: step: 812/470, loss: 1.2812671661376953
2023-01-22 17:24:59.410525: step: 814/470, loss: 0.187590554356575
2023-01-22 17:25:00.143329: step: 816/470, loss: 0.9980336427688599
2023-01-22 17:25:00.847350: step: 818/470, loss: 0.3564274311065674
2023-01-22 17:25:01.496130: step: 820/470, loss: 0.34761491417884827
2023-01-22 17:25:02.261651: step: 822/470, loss: 0.26210886240005493
2023-01-22 17:25:02.973881: step: 824/470, loss: 0.43427425622940063
2023-01-22 17:25:03.671629: step: 826/470, loss: 0.3225962817668915
2023-01-22 17:25:04.448907: step: 828/470, loss: 1.4615715742111206
2023-01-22 17:25:05.208974: step: 830/470, loss: 0.1873364895582199
2023-01-22 17:25:06.038612: step: 832/470, loss: 0.9489684104919434
2023-01-22 17:25:06.725217: step: 834/470, loss: 0.24692928791046143
2023-01-22 17:25:07.523191: step: 836/470, loss: 0.5066057443618774
2023-01-22 17:25:08.330149: step: 838/470, loss: 0.8843993544578552
2023-01-22 17:25:09.080880: step: 840/470, loss: 1.108005166053772
2023-01-22 17:25:09.832117: step: 842/470, loss: 0.8157863616943359
2023-01-22 17:25:10.590446: step: 844/470, loss: 0.5103515386581421
2023-01-22 17:25:11.375334: step: 846/470, loss: 0.9719839096069336
2023-01-22 17:25:12.057420: step: 848/470, loss: 0.6897994875907898
2023-01-22 17:25:12.787723: step: 850/470, loss: 0.6400911211967468
2023-01-22 17:25:13.565126: step: 852/470, loss: 0.7998232841491699
2023-01-22 17:25:14.388290: step: 854/470, loss: 1.2332285642623901
2023-01-22 17:25:15.185569: step: 856/470, loss: 0.7018003463745117
2023-01-22 17:25:15.948129: step: 858/470, loss: 0.46146655082702637
2023-01-22 17:25:16.787605: step: 860/470, loss: 0.7082826495170593
2023-01-22 17:25:17.514670: step: 862/470, loss: 1.376923680305481
2023-01-22 17:25:18.178930: step: 864/470, loss: 0.12437704205513
2023-01-22 17:25:18.855672: step: 866/470, loss: 1.9006187915802002
2023-01-22 17:25:19.619890: step: 868/470, loss: 0.4418231248855591
2023-01-22 17:25:20.384381: step: 870/470, loss: 0.7229202389717102
2023-01-22 17:25:21.184834: step: 872/470, loss: 0.44860169291496277
2023-01-22 17:25:21.944878: step: 874/470, loss: 0.46400347352027893
2023-01-22 17:25:22.665548: step: 876/470, loss: 0.865450918674469
2023-01-22 17:25:23.385176: step: 878/470, loss: 0.2543260157108307
2023-01-22 17:25:24.250662: step: 880/470, loss: 0.8604297041893005
2023-01-22 17:25:25.084131: step: 882/470, loss: 0.4274219274520874
2023-01-22 17:25:25.897098: step: 884/470, loss: 0.669735848903656
2023-01-22 17:25:26.610104: step: 886/470, loss: 0.3069272041320801
2023-01-22 17:25:27.421520: step: 888/470, loss: 1.567513346672058
2023-01-22 17:25:28.153415: step: 890/470, loss: 0.3045634925365448
2023-01-22 17:25:28.982041: step: 892/470, loss: 0.5335885286331177
2023-01-22 17:25:29.699168: step: 894/470, loss: 1.0912373065948486
2023-01-22 17:25:30.466721: step: 896/470, loss: 0.39587855339050293
2023-01-22 17:25:31.246590: step: 898/470, loss: 0.22928422689437866
2023-01-22 17:25:31.992648: step: 900/470, loss: 0.5208638906478882
2023-01-22 17:25:32.777648: step: 902/470, loss: 1.4234001636505127
2023-01-22 17:25:33.610728: step: 904/470, loss: 0.8621724247932434
2023-01-22 17:25:34.363478: step: 906/470, loss: 0.5629292726516724
2023-01-22 17:25:35.179672: step: 908/470, loss: 0.2364557683467865
2023-01-22 17:25:35.948612: step: 910/470, loss: 0.18407753109931946
2023-01-22 17:25:36.648939: step: 912/470, loss: 1.1533396244049072
2023-01-22 17:25:37.375172: step: 914/470, loss: 0.2399020940065384
2023-01-22 17:25:38.135697: step: 916/470, loss: 0.565222978591919
2023-01-22 17:25:38.944248: step: 918/470, loss: 0.31371474266052246
2023-01-22 17:25:39.600968: step: 920/470, loss: 0.29471805691719055
2023-01-22 17:25:40.309966: step: 922/470, loss: 0.6195104718208313
2023-01-22 17:25:41.106599: step: 924/470, loss: 0.24831870198249817
2023-01-22 17:25:41.844789: step: 926/470, loss: 0.25780385732650757
2023-01-22 17:25:42.707953: step: 928/470, loss: 0.13444189727306366
2023-01-22 17:25:43.389344: step: 930/470, loss: 0.08237230777740479
2023-01-22 17:25:44.118952: step: 932/470, loss: 1.3069645166397095
2023-01-22 17:25:44.887418: step: 934/470, loss: 0.43915003538131714
2023-01-22 17:25:45.630631: step: 936/470, loss: 0.34764325618743896
2023-01-22 17:25:46.438110: step: 938/470, loss: 0.43518635630607605
2023-01-22 17:25:47.192733: step: 940/470, loss: 0.7495778799057007
2023-01-22 17:25:47.830899: step: 942/470, loss: 2.3461673259735107
==================================================
Loss: 0.732
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2934608531199441, 'r': 0.2756415982815414, 'f1': 0.28427225497920217}, 'combined': 0.20946376682678053, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32719529096896893, 'r': 0.3297097600638313, 'f1': 0.32844771313535726}, 'combined': 0.22876955143756228, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2955410500853728, 'r': 0.28152107617240446, 'f1': 0.28836075246425097}, 'combined': 0.21247634392102702, 'epoch': 6}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3323852737507508, 'r': 0.32759586058431345, 'f1': 0.32997318903557843}, 'combined': 0.22983207196507952, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2762745365321701, 'r': 0.2747018162103551, 'f1': 0.2754859317656653}, 'combined': 0.2029896339325955, 'epoch': 6}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32108673446573915, 'r': 0.32818086980936256, 'f1': 0.3245950455786664}, 'combined': 0.22608610139807614, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21816037735849056, 'r': 0.33035714285714285, 'f1': 0.26278409090909094}, 'combined': 0.17518939393939395, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25757575757575757, 'r': 0.3695652173913043, 'f1': 0.30357142857142855}, 'combined': 0.15178571428571427, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 6}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2642533988207765, 'r': 0.3093820627560135, 'f1': 0.2850425648119215}, 'combined': 0.21003136354562635, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32274736699326, 'r': 0.3286437131210215, 'f1': 0.3256688534024415}, 'combined': 0.22683402724548166, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21323529411764705, 'r': 0.4142857142857143, 'f1': 0.28155339805825247}, 'combined': 0.1877022653721683, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28632789500190714, 'r': 0.21624004214565282, 'f1': 0.24639676153677628}, 'combined': 0.1815555085007825, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3345971660892728, 'r': 0.26806343565653556, 'f1': 0.2976576389530171}, 'combined': 0.20732372862399204, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.32407407407407407, 'r': 0.3804347826086957, 'f1': 0.35000000000000003}, 'combined': 0.17500000000000002, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2762745365321701, 'r': 0.2747018162103551, 'f1': 0.2754859317656653}, 'combined': 0.2029896339325955, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32108673446573915, 'r': 0.32818086980936256, 'f1': 0.3245950455786664}, 'combined': 0.22608610139807614, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 6}
******************************
Epoch: 7
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 17:28:34.758786: step: 2/470, loss: 0.3670995235443115
2023-01-22 17:28:35.530162: step: 4/470, loss: 0.4737393856048584
2023-01-22 17:28:36.294163: step: 6/470, loss: 0.24018116295337677
2023-01-22 17:28:36.983301: step: 8/470, loss: 2.259197473526001
2023-01-22 17:28:37.759651: step: 10/470, loss: 0.07207592576742172
2023-01-22 17:28:38.493675: step: 12/470, loss: 0.2164432555437088
2023-01-22 17:28:39.273141: step: 14/470, loss: 0.33616185188293457
2023-01-22 17:28:39.981182: step: 16/470, loss: 0.23780158162117004
2023-01-22 17:28:40.778192: step: 18/470, loss: 0.8281857371330261
2023-01-22 17:28:41.580598: step: 20/470, loss: 0.6098978519439697
2023-01-22 17:28:42.337455: step: 22/470, loss: 0.8348177671432495
2023-01-22 17:28:43.198921: step: 24/470, loss: 0.13545599579811096
2023-01-22 17:28:43.958569: step: 26/470, loss: 1.4059125185012817
2023-01-22 17:28:44.809526: step: 28/470, loss: 0.25741472840309143
2023-01-22 17:28:45.508043: step: 30/470, loss: 0.3914801776409149
2023-01-22 17:28:46.274396: step: 32/470, loss: 0.2636181116104126
2023-01-22 17:28:47.047884: step: 34/470, loss: 0.3287275433540344
2023-01-22 17:28:47.837126: step: 36/470, loss: 1.114621877670288
2023-01-22 17:28:48.566455: step: 38/470, loss: 0.4752127230167389
2023-01-22 17:28:49.296482: step: 40/470, loss: 0.4046996235847473
2023-01-22 17:28:49.993197: step: 42/470, loss: 1.4045734405517578
2023-01-22 17:28:50.789554: step: 44/470, loss: 0.22467926144599915
2023-01-22 17:28:51.627032: step: 46/470, loss: 0.46707257628440857
2023-01-22 17:28:52.372608: step: 48/470, loss: 0.8245423436164856
2023-01-22 17:28:53.144804: step: 50/470, loss: 0.4884158968925476
2023-01-22 17:28:53.920370: step: 52/470, loss: 0.38864484429359436
2023-01-22 17:28:54.780018: step: 54/470, loss: 0.3698347210884094
2023-01-22 17:28:55.506858: step: 56/470, loss: 0.5932155847549438
2023-01-22 17:28:56.247352: step: 58/470, loss: 0.5183910131454468
2023-01-22 17:28:57.014097: step: 60/470, loss: 0.20385155081748962
2023-01-22 17:28:57.746496: step: 62/470, loss: 0.35150226950645447
2023-01-22 17:28:58.552604: step: 64/470, loss: 2.04789400100708
2023-01-22 17:28:59.297508: step: 66/470, loss: 0.38406845927238464
2023-01-22 17:29:00.012038: step: 68/470, loss: 0.18193836510181427
2023-01-22 17:29:00.826085: step: 70/470, loss: 0.5214804410934448
2023-01-22 17:29:01.559719: step: 72/470, loss: 0.5263029336929321
2023-01-22 17:29:02.350498: step: 74/470, loss: 0.3935713469982147
2023-01-22 17:29:03.152198: step: 76/470, loss: 0.43086206912994385
2023-01-22 17:29:03.979799: step: 78/470, loss: 0.2726958990097046
2023-01-22 17:29:04.683322: step: 80/470, loss: 0.23460204899311066
2023-01-22 17:29:05.452025: step: 82/470, loss: 0.3521403968334198
2023-01-22 17:29:06.155238: step: 84/470, loss: 0.3516944646835327
2023-01-22 17:29:06.826677: step: 86/470, loss: 1.4504263401031494
2023-01-22 17:29:07.581712: step: 88/470, loss: 0.3307155668735504
2023-01-22 17:29:08.351193: step: 90/470, loss: 0.9473370313644409
2023-01-22 17:29:09.136651: step: 92/470, loss: 0.19111379981040955
2023-01-22 17:29:09.914034: step: 94/470, loss: 0.723115861415863
2023-01-22 17:29:10.715370: step: 96/470, loss: 0.24940860271453857
2023-01-22 17:29:11.497962: step: 98/470, loss: 0.276034414768219
2023-01-22 17:29:12.382860: step: 100/470, loss: 0.7983378171920776
2023-01-22 17:29:13.146050: step: 102/470, loss: 0.6610528826713562
2023-01-22 17:29:13.908370: step: 104/470, loss: 0.3130510449409485
2023-01-22 17:29:14.685806: step: 106/470, loss: 1.4086874723434448
2023-01-22 17:29:15.345958: step: 108/470, loss: 0.41898658871650696
2023-01-22 17:29:16.087597: step: 110/470, loss: 0.28429749608039856
2023-01-22 17:29:16.851785: step: 112/470, loss: 0.3643468916416168
2023-01-22 17:29:17.595146: step: 114/470, loss: 0.07166903465986252
2023-01-22 17:29:18.413126: step: 116/470, loss: 0.2408754527568817
2023-01-22 17:29:19.205621: step: 118/470, loss: 0.5108166933059692
2023-01-22 17:29:19.985431: step: 120/470, loss: 1.3073979616165161
2023-01-22 17:29:20.767761: step: 122/470, loss: 0.13918791711330414
2023-01-22 17:29:21.530181: step: 124/470, loss: 0.22650255262851715
2023-01-22 17:29:22.314222: step: 126/470, loss: 0.3875696361064911
2023-01-22 17:29:23.082257: step: 128/470, loss: 0.9161421060562134
2023-01-22 17:29:23.850934: step: 130/470, loss: 0.273093581199646
2023-01-22 17:29:24.719689: step: 132/470, loss: 0.5050501227378845
2023-01-22 17:29:25.472053: step: 134/470, loss: 0.2323817014694214
2023-01-22 17:29:26.170434: step: 136/470, loss: 0.4136822521686554
2023-01-22 17:29:26.928802: step: 138/470, loss: 0.6526037454605103
2023-01-22 17:29:27.682295: step: 140/470, loss: 0.17813269793987274
2023-01-22 17:29:28.457139: step: 142/470, loss: 0.4769699275493622
2023-01-22 17:29:29.227590: step: 144/470, loss: 0.40157580375671387
2023-01-22 17:29:30.038376: step: 146/470, loss: 0.8085362911224365
2023-01-22 17:29:30.801348: step: 148/470, loss: 0.33716344833374023
2023-01-22 17:29:31.586217: step: 150/470, loss: 1.0862269401550293
2023-01-22 17:29:32.392046: step: 152/470, loss: 0.640563428401947
2023-01-22 17:29:33.170873: step: 154/470, loss: 0.4485277235507965
2023-01-22 17:29:34.019400: step: 156/470, loss: 0.5932475328445435
2023-01-22 17:29:34.794724: step: 158/470, loss: 0.26284921169281006
2023-01-22 17:29:35.610381: step: 160/470, loss: 0.22903652489185333
2023-01-22 17:29:36.407011: step: 162/470, loss: 1.9001516103744507
2023-01-22 17:29:37.147135: step: 164/470, loss: 1.4668172597885132
2023-01-22 17:29:37.953074: step: 166/470, loss: 0.4874824285507202
2023-01-22 17:29:38.677683: step: 168/470, loss: 0.8743273019790649
2023-01-22 17:29:39.425591: step: 170/470, loss: 0.4101831614971161
2023-01-22 17:29:40.080954: step: 172/470, loss: 0.362973153591156
2023-01-22 17:29:40.821769: step: 174/470, loss: 0.43648961186408997
2023-01-22 17:29:41.664005: step: 176/470, loss: 0.13790124654769897
2023-01-22 17:29:42.424827: step: 178/470, loss: 0.08411405980587006
2023-01-22 17:29:43.167215: step: 180/470, loss: 0.24036382138729095
2023-01-22 17:29:44.003655: step: 182/470, loss: 0.6687015891075134
2023-01-22 17:29:44.789149: step: 184/470, loss: 0.35721492767333984
2023-01-22 17:29:45.624154: step: 186/470, loss: 0.48564645648002625
2023-01-22 17:29:46.355625: step: 188/470, loss: 1.280880331993103
2023-01-22 17:29:47.078380: step: 190/470, loss: 0.5749147534370422
2023-01-22 17:29:47.898765: step: 192/470, loss: 3.5238230228424072
2023-01-22 17:29:48.747914: step: 194/470, loss: 0.6828189492225647
2023-01-22 17:29:49.601406: step: 196/470, loss: 1.2112079858779907
2023-01-22 17:29:50.337548: step: 198/470, loss: 0.612357497215271
2023-01-22 17:29:51.096072: step: 200/470, loss: 0.1848372370004654
2023-01-22 17:29:51.854803: step: 202/470, loss: 0.24752122163772583
2023-01-22 17:29:52.636790: step: 204/470, loss: 0.7347160577774048
2023-01-22 17:29:53.378555: step: 206/470, loss: 0.28709715604782104
2023-01-22 17:29:54.117016: step: 208/470, loss: 1.068163514137268
2023-01-22 17:29:54.886295: step: 210/470, loss: 0.9789504408836365
2023-01-22 17:29:55.690232: step: 212/470, loss: 0.8234558701515198
2023-01-22 17:29:56.474958: step: 214/470, loss: 1.2307389974594116
2023-01-22 17:29:57.215733: step: 216/470, loss: 0.13372446596622467
2023-01-22 17:29:57.902342: step: 218/470, loss: 0.11340329051017761
2023-01-22 17:29:58.661850: step: 220/470, loss: 0.5686858892440796
2023-01-22 17:29:59.392851: step: 222/470, loss: 0.3490334451198578
2023-01-22 17:30:00.302936: step: 224/470, loss: 0.43614357709884644
2023-01-22 17:30:01.059780: step: 226/470, loss: 0.44121402502059937
2023-01-22 17:30:01.894474: step: 228/470, loss: 0.9783852100372314
2023-01-22 17:30:02.703917: step: 230/470, loss: 0.8979207873344421
2023-01-22 17:30:03.435802: step: 232/470, loss: 0.3936818242073059
2023-01-22 17:30:04.117487: step: 234/470, loss: 0.7134736776351929
2023-01-22 17:30:04.862443: step: 236/470, loss: 0.35246771574020386
2023-01-22 17:30:05.633591: step: 238/470, loss: 1.3471710681915283
2023-01-22 17:30:06.407451: step: 240/470, loss: 0.5043021440505981
2023-01-22 17:30:07.123812: step: 242/470, loss: 1.0671354532241821
2023-01-22 17:30:07.875521: step: 244/470, loss: 0.628767728805542
2023-01-22 17:30:08.685041: step: 246/470, loss: 0.5917458534240723
2023-01-22 17:30:09.399022: step: 248/470, loss: 0.9961802363395691
2023-01-22 17:30:10.177933: step: 250/470, loss: 0.8598777651786804
2023-01-22 17:30:10.987026: step: 252/470, loss: 0.2611555755138397
2023-01-22 17:30:11.727509: step: 254/470, loss: 0.2617139518260956
2023-01-22 17:30:12.506633: step: 256/470, loss: 1.007016897201538
2023-01-22 17:30:13.247233: step: 258/470, loss: 0.6046254634857178
2023-01-22 17:30:14.046399: step: 260/470, loss: 0.4044310450553894
2023-01-22 17:30:14.753850: step: 262/470, loss: 1.1649810075759888
2023-01-22 17:30:15.500335: step: 264/470, loss: 0.6738048195838928
2023-01-22 17:30:16.204541: step: 266/470, loss: 1.02718186378479
2023-01-22 17:30:16.933813: step: 268/470, loss: 1.9333301782608032
2023-01-22 17:30:17.908004: step: 270/470, loss: 0.3444717824459076
2023-01-22 17:30:18.672673: step: 272/470, loss: 1.909464955329895
2023-01-22 17:30:19.484778: step: 274/470, loss: 0.5475513935089111
2023-01-22 17:30:20.244364: step: 276/470, loss: 0.24307137727737427
2023-01-22 17:30:21.016085: step: 278/470, loss: 0.22565793991088867
2023-01-22 17:30:21.707170: step: 280/470, loss: 0.11121651530265808
2023-01-22 17:30:22.585437: step: 282/470, loss: 0.6998484134674072
2023-01-22 17:30:23.321995: step: 284/470, loss: 0.8299077749252319
2023-01-22 17:30:24.017172: step: 286/470, loss: 0.19652137160301208
2023-01-22 17:30:24.806418: step: 288/470, loss: 0.29388874769210815
2023-01-22 17:30:25.558893: step: 290/470, loss: 0.4312860369682312
2023-01-22 17:30:26.297328: step: 292/470, loss: 0.6240105032920837
2023-01-22 17:30:27.042997: step: 294/470, loss: 0.16214123368263245
2023-01-22 17:30:27.798879: step: 296/470, loss: 0.5396556854248047
2023-01-22 17:30:28.522439: step: 298/470, loss: 0.5401109457015991
2023-01-22 17:30:29.258436: step: 300/470, loss: 0.9766262769699097
2023-01-22 17:30:29.980889: step: 302/470, loss: 0.8032498359680176
2023-01-22 17:30:30.836099: step: 304/470, loss: 0.5323628783226013
2023-01-22 17:30:31.602973: step: 306/470, loss: 0.35838931798934937
2023-01-22 17:30:32.450756: step: 308/470, loss: 0.15917706489562988
2023-01-22 17:30:33.288353: step: 310/470, loss: 0.825878381729126
2023-01-22 17:30:34.083721: step: 312/470, loss: 0.5406302213668823
2023-01-22 17:30:34.856515: step: 314/470, loss: 0.8202871680259705
2023-01-22 17:30:35.559146: step: 316/470, loss: 0.14145931601524353
2023-01-22 17:30:36.294022: step: 318/470, loss: 1.2496742010116577
2023-01-22 17:30:37.012914: step: 320/470, loss: 0.45300769805908203
2023-01-22 17:30:37.716602: step: 322/470, loss: 0.2567143440246582
2023-01-22 17:30:38.438574: step: 324/470, loss: 0.3849056363105774
2023-01-22 17:30:39.278738: step: 326/470, loss: 0.17785045504570007
2023-01-22 17:30:40.022594: step: 328/470, loss: 0.5878977179527283
2023-01-22 17:30:40.722546: step: 330/470, loss: 0.3370095491409302
2023-01-22 17:30:41.425132: step: 332/470, loss: 0.2186794877052307
2023-01-22 17:30:42.218069: step: 334/470, loss: 0.30272671580314636
2023-01-22 17:30:42.955914: step: 336/470, loss: 0.4330812394618988
2023-01-22 17:30:43.704181: step: 338/470, loss: 0.1457645744085312
2023-01-22 17:30:44.405437: step: 340/470, loss: 0.5812200307846069
2023-01-22 17:30:45.078636: step: 342/470, loss: 0.4354366958141327
2023-01-22 17:30:45.864735: step: 344/470, loss: 1.0845625400543213
2023-01-22 17:30:46.621058: step: 346/470, loss: 0.5721340775489807
2023-01-22 17:30:47.357077: step: 348/470, loss: 0.5678675174713135
2023-01-22 17:30:48.148526: step: 350/470, loss: 0.46091604232788086
2023-01-22 17:30:48.955057: step: 352/470, loss: 1.013948678970337
2023-01-22 17:30:49.714521: step: 354/470, loss: 0.4761132597923279
2023-01-22 17:30:50.459314: step: 356/470, loss: 0.34836894273757935
2023-01-22 17:30:51.187792: step: 358/470, loss: 0.24478018283843994
2023-01-22 17:30:51.919540: step: 360/470, loss: 2.375002384185791
2023-01-22 17:30:52.607521: step: 362/470, loss: 0.3373410105705261
2023-01-22 17:30:53.339820: step: 364/470, loss: 0.435524046421051
2023-01-22 17:30:54.136291: step: 366/470, loss: 0.9048151969909668
2023-01-22 17:30:54.898983: step: 368/470, loss: 0.6413469314575195
2023-01-22 17:30:55.679779: step: 370/470, loss: 0.27448025345802307
2023-01-22 17:30:56.507927: step: 372/470, loss: 1.3750803470611572
2023-01-22 17:30:57.306191: step: 374/470, loss: 0.48742660880088806
2023-01-22 17:30:58.078276: step: 376/470, loss: 0.8035762310028076
2023-01-22 17:30:58.856536: step: 378/470, loss: 0.5545987486839294
2023-01-22 17:30:59.603723: step: 380/470, loss: 0.28187888860702515
2023-01-22 17:31:00.309114: step: 382/470, loss: 0.30163049697875977
2023-01-22 17:31:01.087180: step: 384/470, loss: 0.9044409990310669
2023-01-22 17:31:01.825014: step: 386/470, loss: 1.142310619354248
2023-01-22 17:31:02.576397: step: 388/470, loss: 1.2953393459320068
2023-01-22 17:31:03.316028: step: 390/470, loss: 0.15360940992832184
2023-01-22 17:31:04.082431: step: 392/470, loss: 0.46768492460250854
2023-01-22 17:31:04.839253: step: 394/470, loss: 0.44785362482070923
2023-01-22 17:31:05.587517: step: 396/470, loss: 0.46685466170310974
2023-01-22 17:31:06.381468: step: 398/470, loss: 0.939845085144043
2023-01-22 17:31:07.086700: step: 400/470, loss: 0.7884602546691895
2023-01-22 17:31:07.851276: step: 402/470, loss: 1.0477254390716553
2023-01-22 17:31:08.630328: step: 404/470, loss: 0.7993929982185364
2023-01-22 17:31:09.410035: step: 406/470, loss: 0.8812851905822754
2023-01-22 17:31:10.133691: step: 408/470, loss: 0.2269768863916397
2023-01-22 17:31:10.822087: step: 410/470, loss: 1.8129310607910156
2023-01-22 17:31:11.568577: step: 412/470, loss: 0.3134598731994629
2023-01-22 17:31:12.299907: step: 414/470, loss: 0.1766653060913086
2023-01-22 17:31:13.067475: step: 416/470, loss: 0.9808623194694519
2023-01-22 17:31:13.910958: step: 418/470, loss: 0.9330800175666809
2023-01-22 17:31:14.660175: step: 420/470, loss: 0.4644604027271271
2023-01-22 17:31:15.454638: step: 422/470, loss: 0.5063079595565796
2023-01-22 17:31:16.217579: step: 424/470, loss: 0.5117875933647156
2023-01-22 17:31:16.928015: step: 426/470, loss: 0.3270796537399292
2023-01-22 17:31:17.637862: step: 428/470, loss: 0.7015947103500366
2023-01-22 17:31:18.406876: step: 430/470, loss: 0.3183510899543762
2023-01-22 17:31:19.128352: step: 432/470, loss: 0.8972214460372925
2023-01-22 17:31:19.905129: step: 434/470, loss: 0.9476366639137268
2023-01-22 17:31:20.608658: step: 436/470, loss: 0.8914029002189636
2023-01-22 17:31:21.340525: step: 438/470, loss: 0.702813446521759
2023-01-22 17:31:22.080673: step: 440/470, loss: 1.0427266359329224
2023-01-22 17:31:22.919600: step: 442/470, loss: 0.3731694221496582
2023-01-22 17:31:23.615420: step: 444/470, loss: 0.3855333924293518
2023-01-22 17:31:24.481871: step: 446/470, loss: 0.382285475730896
2023-01-22 17:31:25.169686: step: 448/470, loss: 0.3315264880657196
2023-01-22 17:31:26.028203: step: 450/470, loss: 0.6684935092926025
2023-01-22 17:31:26.927522: step: 452/470, loss: 0.30676472187042236
2023-01-22 17:31:27.722017: step: 454/470, loss: 0.5190876126289368
2023-01-22 17:31:28.550448: step: 456/470, loss: 0.26106128096580505
2023-01-22 17:31:29.316983: step: 458/470, loss: 1.2300512790679932
2023-01-22 17:31:30.192260: step: 460/470, loss: 0.28473010659217834
2023-01-22 17:31:30.935565: step: 462/470, loss: 0.5453563332557678
2023-01-22 17:31:31.704082: step: 464/470, loss: 0.6540701985359192
2023-01-22 17:31:32.396543: step: 466/470, loss: 0.8440691232681274
2023-01-22 17:31:33.264413: step: 468/470, loss: 0.5105758309364319
2023-01-22 17:31:34.092419: step: 470/470, loss: 0.20678004622459412
2023-01-22 17:31:34.866850: step: 472/470, loss: 0.45606935024261475
2023-01-22 17:31:35.590103: step: 474/470, loss: 1.512797236442566
2023-01-22 17:31:36.454555: step: 476/470, loss: 0.2980559766292572
2023-01-22 17:31:37.217573: step: 478/470, loss: 0.6002671718597412
2023-01-22 17:31:37.920692: step: 480/470, loss: 0.27965351939201355
2023-01-22 17:31:38.666998: step: 482/470, loss: 0.5044351816177368
2023-01-22 17:31:39.415828: step: 484/470, loss: 0.1443350464105606
2023-01-22 17:31:40.111567: step: 486/470, loss: 2.0403623580932617
2023-01-22 17:31:40.865230: step: 488/470, loss: 0.4997430443763733
2023-01-22 17:31:41.620043: step: 490/470, loss: 0.14253254234790802
2023-01-22 17:31:42.371104: step: 492/470, loss: 1.0414563417434692
2023-01-22 17:31:43.106788: step: 494/470, loss: 2.314917802810669
2023-01-22 17:31:43.887688: step: 496/470, loss: 0.8212421536445618
2023-01-22 17:31:44.610699: step: 498/470, loss: 0.17680610716342926
2023-01-22 17:31:45.321544: step: 500/470, loss: 0.41409242153167725
2023-01-22 17:31:46.077921: step: 502/470, loss: 0.43370938301086426
2023-01-22 17:31:46.840239: step: 504/470, loss: 0.8938826322555542
2023-01-22 17:31:47.595123: step: 506/470, loss: 0.12901009619235992
2023-01-22 17:31:48.363898: step: 508/470, loss: 0.2584211528301239
2023-01-22 17:31:49.179522: step: 510/470, loss: 0.46783918142318726
2023-01-22 17:31:49.972861: step: 512/470, loss: 0.5496209263801575
2023-01-22 17:31:50.732506: step: 514/470, loss: 0.3696674108505249
2023-01-22 17:31:51.532392: step: 516/470, loss: 0.31152698397636414
2023-01-22 17:31:52.305665: step: 518/470, loss: 0.3273497223854065
2023-01-22 17:31:53.033782: step: 520/470, loss: 1.6968348026275635
2023-01-22 17:31:53.743886: step: 522/470, loss: 0.9195625185966492
2023-01-22 17:31:54.442385: step: 524/470, loss: 0.1977846920490265
2023-01-22 17:31:55.258397: step: 526/470, loss: 0.2801767587661743
2023-01-22 17:31:55.966108: step: 528/470, loss: 0.9938501715660095
2023-01-22 17:31:56.700429: step: 530/470, loss: 0.26219820976257324
2023-01-22 17:31:57.539218: step: 532/470, loss: 0.6336964964866638
2023-01-22 17:31:58.289794: step: 534/470, loss: 2.7305359840393066
2023-01-22 17:31:59.092347: step: 536/470, loss: 0.3516845703125
2023-01-22 17:31:59.799642: step: 538/470, loss: 0.5453897714614868
2023-01-22 17:32:00.586868: step: 540/470, loss: 0.6060112118721008
2023-01-22 17:32:01.323849: step: 542/470, loss: 0.27010199427604675
2023-01-22 17:32:02.024166: step: 544/470, loss: 2.1664516925811768
2023-01-22 17:32:02.800964: step: 546/470, loss: 0.24300040304660797
2023-01-22 17:32:03.541635: step: 548/470, loss: 0.11754722148180008
2023-01-22 17:32:04.369457: step: 550/470, loss: 0.48181718587875366
2023-01-22 17:32:05.127107: step: 552/470, loss: 0.7739644050598145
2023-01-22 17:32:05.896213: step: 554/470, loss: 0.6491574048995972
2023-01-22 17:32:06.656186: step: 556/470, loss: 0.49489882588386536
2023-01-22 17:32:07.402145: step: 558/470, loss: 1.208168625831604
2023-01-22 17:32:08.156738: step: 560/470, loss: 0.798096239566803
2023-01-22 17:32:08.868497: step: 562/470, loss: 0.31834012269973755
2023-01-22 17:32:09.670145: step: 564/470, loss: 2.36625337600708
2023-01-22 17:32:10.456093: step: 566/470, loss: 0.34011802077293396
2023-01-22 17:32:11.214779: step: 568/470, loss: 0.841728687286377
2023-01-22 17:32:11.999841: step: 570/470, loss: 0.7265416383743286
2023-01-22 17:32:12.744430: step: 572/470, loss: 0.9253761768341064
2023-01-22 17:32:13.620574: step: 574/470, loss: 0.23297470808029175
2023-01-22 17:32:14.336818: step: 576/470, loss: 1.5338727235794067
2023-01-22 17:32:15.015035: step: 578/470, loss: 1.0285563468933105
2023-01-22 17:32:15.732913: step: 580/470, loss: 0.3040406107902527
2023-01-22 17:32:16.400307: step: 582/470, loss: 1.5267548561096191
2023-01-22 17:32:17.113934: step: 584/470, loss: 0.6100663542747498
2023-01-22 17:32:17.824939: step: 586/470, loss: 1.353019118309021
2023-01-22 17:32:18.589089: step: 588/470, loss: 0.6592656970024109
2023-01-22 17:32:19.328450: step: 590/470, loss: 0.1781897246837616
2023-01-22 17:32:20.136727: step: 592/470, loss: 0.27507659792900085
2023-01-22 17:32:20.848605: step: 594/470, loss: 0.3861004710197449
2023-01-22 17:32:21.690034: step: 596/470, loss: 0.4841284453868866
2023-01-22 17:32:22.439593: step: 598/470, loss: 3.2577338218688965
2023-01-22 17:32:23.207142: step: 600/470, loss: 0.2953993082046509
2023-01-22 17:32:24.015632: step: 602/470, loss: 0.5135447382926941
2023-01-22 17:32:24.769931: step: 604/470, loss: 0.3044143617153168
2023-01-22 17:32:25.621100: step: 606/470, loss: 0.5463592410087585
2023-01-22 17:32:26.378792: step: 608/470, loss: 0.32110247015953064
2023-01-22 17:32:27.137003: step: 610/470, loss: 0.3176352381706238
2023-01-22 17:32:27.919858: step: 612/470, loss: 0.2889813184738159
2023-01-22 17:32:28.692143: step: 614/470, loss: 0.11909591406583786
2023-01-22 17:32:29.450953: step: 616/470, loss: 0.6773265600204468
2023-01-22 17:32:30.357467: step: 618/470, loss: 0.5883302092552185
2023-01-22 17:32:31.091979: step: 620/470, loss: 0.2453279346227646
2023-01-22 17:32:31.795537: step: 622/470, loss: 0.7039670944213867
2023-01-22 17:32:32.564621: step: 624/470, loss: 0.38650938868522644
2023-01-22 17:32:33.308359: step: 626/470, loss: 0.34423843026161194
2023-01-22 17:32:34.034597: step: 628/470, loss: 0.939646303653717
2023-01-22 17:32:34.836163: step: 630/470, loss: 0.3436138927936554
2023-01-22 17:32:35.599073: step: 632/470, loss: 1.440124750137329
2023-01-22 17:32:36.417002: step: 634/470, loss: 0.5489599704742432
2023-01-22 17:32:37.106226: step: 636/470, loss: 1.5086581707000732
2023-01-22 17:32:37.877233: step: 638/470, loss: 0.39192065596580505
2023-01-22 17:32:38.621624: step: 640/470, loss: 1.1574674844741821
2023-01-22 17:32:39.365807: step: 642/470, loss: 1.1345126628875732
2023-01-22 17:32:40.257137: step: 644/470, loss: 0.14073410630226135
2023-01-22 17:32:41.061842: step: 646/470, loss: 0.8759070038795471
2023-01-22 17:32:41.815560: step: 648/470, loss: 0.3100970983505249
2023-01-22 17:32:42.498909: step: 650/470, loss: 0.4851211607456207
2023-01-22 17:32:43.252621: step: 652/470, loss: 0.8310330510139465
2023-01-22 17:32:43.964206: step: 654/470, loss: 0.20696614682674408
2023-01-22 17:32:44.863677: step: 656/470, loss: 0.4490260183811188
2023-01-22 17:32:45.573399: step: 658/470, loss: 0.7504600286483765
2023-01-22 17:32:46.378331: step: 660/470, loss: 9.698339462280273
2023-01-22 17:32:47.163438: step: 662/470, loss: 0.3065306544303894
2023-01-22 17:32:47.966730: step: 664/470, loss: 0.46533751487731934
2023-01-22 17:32:48.777234: step: 666/470, loss: 0.24716587364673615
2023-01-22 17:32:49.591335: step: 668/470, loss: 0.4091520309448242
2023-01-22 17:32:50.339119: step: 670/470, loss: 0.44841229915618896
2023-01-22 17:32:51.106046: step: 672/470, loss: 0.17277362942695618
2023-01-22 17:32:51.872398: step: 674/470, loss: 0.3857150375843048
2023-01-22 17:32:52.726895: step: 676/470, loss: 0.36999809741973877
2023-01-22 17:32:53.489651: step: 678/470, loss: 0.21060891449451447
2023-01-22 17:32:54.197756: step: 680/470, loss: 0.23017674684524536
2023-01-22 17:32:54.894250: step: 682/470, loss: 0.40644142031669617
2023-01-22 17:32:55.651259: step: 684/470, loss: 0.6531462073326111
2023-01-22 17:32:56.411436: step: 686/470, loss: 0.062062717974185944
2023-01-22 17:32:57.236378: step: 688/470, loss: 0.45378008484840393
2023-01-22 17:32:58.010259: step: 690/470, loss: 0.6536173224449158
2023-01-22 17:32:58.773602: step: 692/470, loss: 0.8225758075714111
2023-01-22 17:32:59.548151: step: 694/470, loss: 0.27153313159942627
2023-01-22 17:33:00.279338: step: 696/470, loss: 0.19550104439258575
2023-01-22 17:33:00.983982: step: 698/470, loss: 0.28255999088287354
2023-01-22 17:33:01.770904: step: 700/470, loss: 0.9339784979820251
2023-01-22 17:33:02.513500: step: 702/470, loss: 0.9983887672424316
2023-01-22 17:33:03.298502: step: 704/470, loss: 0.7024455070495605
2023-01-22 17:33:04.067298: step: 706/470, loss: 0.24352699518203735
2023-01-22 17:33:04.833185: step: 708/470, loss: 0.8246220350265503
2023-01-22 17:33:05.619200: step: 710/470, loss: 0.5286746621131897
2023-01-22 17:33:06.305166: step: 712/470, loss: 0.4412599802017212
2023-01-22 17:33:07.096055: step: 714/470, loss: 0.7559401988983154
2023-01-22 17:33:07.818684: step: 716/470, loss: 0.6777728796005249
2023-01-22 17:33:08.592169: step: 718/470, loss: 0.5251533389091492
2023-01-22 17:33:09.469653: step: 720/470, loss: 0.5137686729431152
2023-01-22 17:33:10.213300: step: 722/470, loss: 0.2733078598976135
2023-01-22 17:33:11.009210: step: 724/470, loss: 0.5248976349830627
2023-01-22 17:33:11.730299: step: 726/470, loss: 0.9532487988471985
2023-01-22 17:33:12.476168: step: 728/470, loss: 0.1258946657180786
2023-01-22 17:33:13.368453: step: 730/470, loss: 0.9458543658256531
2023-01-22 17:33:14.152992: step: 732/470, loss: 1.3671302795410156
2023-01-22 17:33:14.892107: step: 734/470, loss: 0.15608762204647064
2023-01-22 17:33:15.670709: step: 736/470, loss: 0.7429428100585938
2023-01-22 17:33:16.395406: step: 738/470, loss: 0.2898152768611908
2023-01-22 17:33:17.164086: step: 740/470, loss: 1.8488043546676636
2023-01-22 17:33:17.913271: step: 742/470, loss: 0.16220681369304657
2023-01-22 17:33:18.664673: step: 744/470, loss: 0.5282084345817566
2023-01-22 17:33:19.496453: step: 746/470, loss: 0.7009122371673584
2023-01-22 17:33:20.243599: step: 748/470, loss: 0.4774022698402405
2023-01-22 17:33:20.971345: step: 750/470, loss: 0.8804485201835632
2023-01-22 17:33:21.803343: step: 752/470, loss: 0.2241060435771942
2023-01-22 17:33:22.555940: step: 754/470, loss: 0.3125775158405304
2023-01-22 17:33:23.270345: step: 756/470, loss: 3.320235013961792
2023-01-22 17:33:24.053119: step: 758/470, loss: 0.3262557089328766
2023-01-22 17:33:24.807527: step: 760/470, loss: 0.7048736214637756
2023-01-22 17:33:25.544020: step: 762/470, loss: 0.39851272106170654
2023-01-22 17:33:26.351647: step: 764/470, loss: 0.2439843863248825
2023-01-22 17:33:27.103136: step: 766/470, loss: 0.309922993183136
2023-01-22 17:33:27.793193: step: 768/470, loss: 0.19634529948234558
2023-01-22 17:33:28.554003: step: 770/470, loss: 0.46125590801239014
2023-01-22 17:33:29.357719: step: 772/470, loss: 0.9932135343551636
2023-01-22 17:33:30.100410: step: 774/470, loss: 0.3272228240966797
2023-01-22 17:33:30.902881: step: 776/470, loss: 0.6332528591156006
2023-01-22 17:33:31.663301: step: 778/470, loss: 0.6290199160575867
2023-01-22 17:33:32.417574: step: 780/470, loss: 0.17212772369384766
2023-01-22 17:33:33.242167: step: 782/470, loss: 0.4054405689239502
2023-01-22 17:33:33.962500: step: 784/470, loss: 0.21502184867858887
2023-01-22 17:33:34.756630: step: 786/470, loss: 0.2917923927307129
2023-01-22 17:33:35.537541: step: 788/470, loss: 0.39834240078926086
2023-01-22 17:33:36.276334: step: 790/470, loss: 0.7714516520500183
2023-01-22 17:33:36.991298: step: 792/470, loss: 1.9584661722183228
2023-01-22 17:33:37.769071: step: 794/470, loss: 1.415565013885498
2023-01-22 17:33:38.516457: step: 796/470, loss: 0.8934961557388306
2023-01-22 17:33:39.488791: step: 798/470, loss: 0.19620083272457123
2023-01-22 17:33:40.204897: step: 800/470, loss: 1.1191173791885376
2023-01-22 17:33:41.001211: step: 802/470, loss: 0.15313296020030975
2023-01-22 17:33:41.770085: step: 804/470, loss: 0.5882033109664917
2023-01-22 17:33:42.511172: step: 806/470, loss: 0.44391781091690063
2023-01-22 17:33:43.295992: step: 808/470, loss: 0.5112501382827759
2023-01-22 17:33:44.064654: step: 810/470, loss: 0.6775764226913452
2023-01-22 17:33:44.807214: step: 812/470, loss: 0.6724539399147034
2023-01-22 17:33:45.613912: step: 814/470, loss: 0.7998963594436646
2023-01-22 17:33:46.309355: step: 816/470, loss: 0.40762490034103394
2023-01-22 17:33:47.068389: step: 818/470, loss: 0.32030996680259705
2023-01-22 17:33:47.802209: step: 820/470, loss: 0.15251174569129944
2023-01-22 17:33:48.534923: step: 822/470, loss: 0.2601527273654938
2023-01-22 17:33:49.366330: step: 824/470, loss: 0.21793058514595032
2023-01-22 17:33:50.194451: step: 826/470, loss: 0.7894784808158875
2023-01-22 17:33:50.947985: step: 828/470, loss: 0.30823183059692383
2023-01-22 17:33:51.696811: step: 830/470, loss: 0.25014978647232056
2023-01-22 17:33:52.487806: step: 832/470, loss: 0.3014823794364929
2023-01-22 17:33:53.273690: step: 834/470, loss: 0.16695991158485413
2023-01-22 17:33:54.017159: step: 836/470, loss: 0.4740227162837982
2023-01-22 17:33:54.800123: step: 838/470, loss: 0.6113675236701965
2023-01-22 17:33:55.506340: step: 840/470, loss: 0.5166838765144348
2023-01-22 17:33:56.284470: step: 842/470, loss: 0.8357441425323486
2023-01-22 17:33:57.035956: step: 844/470, loss: 0.07860533893108368
2023-01-22 17:33:57.838085: step: 846/470, loss: 0.90674889087677
2023-01-22 17:33:58.647169: step: 848/470, loss: 0.928524374961853
2023-01-22 17:33:59.434612: step: 850/470, loss: 0.3567863702774048
2023-01-22 17:34:00.182779: step: 852/470, loss: 0.1565251648426056
2023-01-22 17:34:00.928130: step: 854/470, loss: 0.9612409472465515
2023-01-22 17:34:01.697576: step: 856/470, loss: 0.7247118353843689
2023-01-22 17:34:02.441320: step: 858/470, loss: 0.47365325689315796
2023-01-22 17:34:03.175599: step: 860/470, loss: 0.716667652130127
2023-01-22 17:34:03.923682: step: 862/470, loss: 0.808570384979248
2023-01-22 17:34:04.707759: step: 864/470, loss: 0.3732510507106781
2023-01-22 17:34:05.545818: step: 866/470, loss: 0.23475761711597443
2023-01-22 17:34:06.290446: step: 868/470, loss: 0.642833948135376
2023-01-22 17:34:07.012235: step: 870/470, loss: 0.1018008217215538
2023-01-22 17:34:07.769990: step: 872/470, loss: 0.676296591758728
2023-01-22 17:34:08.507449: step: 874/470, loss: 1.0268975496292114
2023-01-22 17:34:09.258394: step: 876/470, loss: 0.5832228064537048
2023-01-22 17:34:09.941955: step: 878/470, loss: 0.17225563526153564
2023-01-22 17:34:10.689010: step: 880/470, loss: 0.3411220908164978
2023-01-22 17:34:11.517244: step: 882/470, loss: 0.9757616519927979
2023-01-22 17:34:12.213346: step: 884/470, loss: 0.26120713353157043
2023-01-22 17:34:12.955928: step: 886/470, loss: 1.29201340675354
2023-01-22 17:34:13.651924: step: 888/470, loss: 0.48865917325019836
2023-01-22 17:34:14.456383: step: 890/470, loss: 0.9293355345726013
2023-01-22 17:34:15.201836: step: 892/470, loss: 0.2673357129096985
2023-01-22 17:34:15.921039: step: 894/470, loss: 0.4621124565601349
2023-01-22 17:34:16.729967: step: 896/470, loss: 0.4767850935459137
2023-01-22 17:34:17.466702: step: 898/470, loss: 0.9976144433021545
2023-01-22 17:34:18.192144: step: 900/470, loss: 0.17807906866073608
2023-01-22 17:34:19.062215: step: 902/470, loss: 0.3325049877166748
2023-01-22 17:34:19.859914: step: 904/470, loss: 0.32338327169418335
2023-01-22 17:34:20.574828: step: 906/470, loss: 0.3096674680709839
2023-01-22 17:34:21.391160: step: 908/470, loss: 1.2738778591156006
2023-01-22 17:34:22.146806: step: 910/470, loss: 0.6537337899208069
2023-01-22 17:34:22.901515: step: 912/470, loss: 0.7893470525741577
2023-01-22 17:34:23.715500: step: 914/470, loss: 0.5990859270095825
2023-01-22 17:34:24.406572: step: 916/470, loss: 0.527148425579071
2023-01-22 17:34:25.205772: step: 918/470, loss: 0.2752528786659241
2023-01-22 17:34:25.884656: step: 920/470, loss: 0.40670332312583923
2023-01-22 17:34:26.644309: step: 922/470, loss: 0.9234625101089478
2023-01-22 17:34:27.421243: step: 924/470, loss: 0.8040624856948853
2023-01-22 17:34:28.168043: step: 926/470, loss: 0.4370003640651703
2023-01-22 17:34:28.877256: step: 928/470, loss: 0.2960697412490845
2023-01-22 17:34:29.609942: step: 930/470, loss: 1.2495319843292236
2023-01-22 17:34:30.380660: step: 932/470, loss: 0.8773002624511719
2023-01-22 17:34:31.179562: step: 934/470, loss: 0.43924665451049805
2023-01-22 17:34:31.944548: step: 936/470, loss: 0.423836350440979
2023-01-22 17:34:32.752086: step: 938/470, loss: 0.36395108699798584
2023-01-22 17:34:33.598323: step: 940/470, loss: 0.4329916536808014
2023-01-22 17:34:34.263372: step: 942/470, loss: 0.15708792209625244
==================================================
Loss: 0.632
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2656935345053647, 'r': 0.3241763618348188, 'f1': 0.29203579946487096}, 'combined': 0.21518427328990491, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32047864894407607, 'r': 0.339584106861896, 'f1': 0.32975487501061795}, 'combined': 0.22968001244520656, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26474047961800956, 'r': 0.3240182340675829, 'f1': 0.29139523780480575}, 'combined': 0.2147122804877516, 'epoch': 7}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32541475117674507, 'r': 0.34573363573629207, 'f1': 0.33526661835256644}, 'combined': 0.23351903765850401, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.24530443812582606, 'r': 0.33095152847715814, 'f1': 0.2817632560702138}, 'combined': 0.20761503078857857, 'epoch': 7}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.31375791500059286, 'r': 0.35297765437566697, 'f1': 0.33221426294180423}, 'combined': 0.23139301896444078, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21774193548387097, 'r': 0.38571428571428573, 'f1': 0.27835051546391754}, 'combined': 0.18556701030927836, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2722222222222222, 'r': 0.532608695652174, 'f1': 0.36029411764705876}, 'combined': 0.18014705882352938, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38333333333333336, 'r': 0.19827586206896552, 'f1': 0.2613636363636364}, 'combined': 0.17424242424242425, 'epoch': 7}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2656935345053647, 'r': 0.3241763618348188, 'f1': 0.29203579946487096}, 'combined': 0.21518427328990491, 'epoch': 7}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32047864894407607, 'r': 0.339584106861896, 'f1': 0.32975487501061795}, 'combined': 0.22968001244520656, 'epoch': 7}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21774193548387097, 'r': 0.38571428571428573, 'f1': 0.27835051546391754}, 'combined': 0.18556701030927836, 'epoch': 7}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26474047961800956, 'r': 0.3240182340675829, 'f1': 0.29139523780480575}, 'combined': 0.2147122804877516, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32541475117674507, 'r': 0.34573363573629207, 'f1': 0.33526661835256644}, 'combined': 0.23351903765850401, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2722222222222222, 'r': 0.532608695652174, 'f1': 0.36029411764705876}, 'combined': 0.18014705882352938, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2762745365321701, 'r': 0.2747018162103551, 'f1': 0.2754859317656653}, 'combined': 0.2029896339325955, 'epoch': 6}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32108673446573915, 'r': 0.32818086980936256, 'f1': 0.3245950455786664}, 'combined': 0.22608610139807614, 'epoch': 6}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45, 'r': 0.3103448275862069, 'f1': 0.3673469387755102}, 'combined': 0.24489795918367346, 'epoch': 6}
******************************
Epoch: 8
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 17:37:31.372698: step: 2/470, loss: 0.439403235912323
2023-01-22 17:37:32.183716: step: 4/470, loss: 0.4706476330757141
2023-01-22 17:37:32.960572: step: 6/470, loss: 0.16600431501865387
2023-01-22 17:37:33.706239: step: 8/470, loss: 0.3319374620914459
2023-01-22 17:37:34.398690: step: 10/470, loss: 0.3293440639972687
2023-01-22 17:37:35.169656: step: 12/470, loss: 0.5663127899169922
2023-01-22 17:37:35.932189: step: 14/470, loss: 0.45440736413002014
2023-01-22 17:37:36.746546: step: 16/470, loss: 0.5999109745025635
2023-01-22 17:37:37.506511: step: 18/470, loss: 0.3009253442287445
2023-01-22 17:37:38.190912: step: 20/470, loss: 0.1967972069978714
2023-01-22 17:37:38.947222: step: 22/470, loss: 0.26259857416152954
2023-01-22 17:37:39.684534: step: 24/470, loss: 0.492567241191864
2023-01-22 17:37:40.413991: step: 26/470, loss: 0.24835701286792755
2023-01-22 17:37:41.156542: step: 28/470, loss: 0.11328727006912231
2023-01-22 17:37:41.913062: step: 30/470, loss: 0.38536766171455383
2023-01-22 17:37:42.775330: step: 32/470, loss: 0.14614824950695038
2023-01-22 17:37:43.593310: step: 34/470, loss: 0.8179748058319092
2023-01-22 17:37:44.364839: step: 36/470, loss: 0.6151262521743774
2023-01-22 17:37:45.104004: step: 38/470, loss: 0.11764610558748245
2023-01-22 17:37:45.867816: step: 40/470, loss: 0.6587837338447571
2023-01-22 17:37:46.607274: step: 42/470, loss: 0.168352410197258
2023-01-22 17:37:47.319821: step: 44/470, loss: 0.2563874423503876
2023-01-22 17:37:48.071373: step: 46/470, loss: 0.6100096702575684
2023-01-22 17:37:48.853047: step: 48/470, loss: 1.589992880821228
2023-01-22 17:37:49.712471: step: 50/470, loss: 0.5913103222846985
2023-01-22 17:37:50.466106: step: 52/470, loss: 0.4870699942111969
2023-01-22 17:37:51.273590: step: 54/470, loss: 0.1689032018184662
2023-01-22 17:37:52.041673: step: 56/470, loss: 0.1719590425491333
2023-01-22 17:37:52.831809: step: 58/470, loss: 0.3236994743347168
2023-01-22 17:37:53.613728: step: 60/470, loss: 0.4069594740867615
2023-01-22 17:37:54.287566: step: 62/470, loss: 0.25249919295310974
2023-01-22 17:37:55.074143: step: 64/470, loss: 0.6021767854690552
2023-01-22 17:37:55.790918: step: 66/470, loss: 1.9965308904647827
2023-01-22 17:37:56.509526: step: 68/470, loss: 0.6415644884109497
2023-01-22 17:37:57.222228: step: 70/470, loss: 0.22782424092292786
2023-01-22 17:37:57.979297: step: 72/470, loss: 0.39690855145454407
2023-01-22 17:37:58.742757: step: 74/470, loss: 0.31533282995224
2023-01-22 17:37:59.530710: step: 76/470, loss: 0.1685294210910797
2023-01-22 17:38:00.380014: step: 78/470, loss: 0.2691434323787689
2023-01-22 17:38:01.186415: step: 80/470, loss: 0.16956226527690887
2023-01-22 17:38:01.966847: step: 82/470, loss: 1.0252076387405396
2023-01-22 17:38:02.701677: step: 84/470, loss: 0.39817947149276733
2023-01-22 17:38:03.529044: step: 86/470, loss: 0.23661364614963531
2023-01-22 17:38:04.229237: step: 88/470, loss: 0.4424164593219757
2023-01-22 17:38:05.029995: step: 90/470, loss: 0.2330237776041031
2023-01-22 17:38:05.923763: step: 92/470, loss: 0.5269856452941895
2023-01-22 17:38:06.711598: step: 94/470, loss: 0.7007234692573547
2023-01-22 17:38:07.412595: step: 96/470, loss: 0.29682648181915283
2023-01-22 17:38:08.141332: step: 98/470, loss: 0.23675212264060974
2023-01-22 17:38:08.839496: step: 100/470, loss: 0.3501730263233185
2023-01-22 17:38:09.546085: step: 102/470, loss: 0.1919550895690918
2023-01-22 17:38:10.338760: step: 104/470, loss: 1.0851826667785645
2023-01-22 17:38:11.160050: step: 106/470, loss: 0.4781433343887329
2023-01-22 17:38:11.878547: step: 108/470, loss: 0.1578303575515747
2023-01-22 17:38:12.660284: step: 110/470, loss: 0.9350889325141907
2023-01-22 17:38:13.403822: step: 112/470, loss: 0.3748646378517151
2023-01-22 17:38:14.097087: step: 114/470, loss: 0.16980983316898346
2023-01-22 17:38:14.916470: step: 116/470, loss: 0.30513840913772583
2023-01-22 17:38:15.696765: step: 118/470, loss: 0.15757113695144653
2023-01-22 17:38:16.404816: step: 120/470, loss: 0.23493137955665588
2023-01-22 17:38:17.134187: step: 122/470, loss: 0.06003459915518761
2023-01-22 17:38:17.944647: step: 124/470, loss: 0.7464461326599121
2023-01-22 17:38:18.683455: step: 126/470, loss: 0.4456807076931
2023-01-22 17:38:19.514851: step: 128/470, loss: 0.14154116809368134
2023-01-22 17:38:20.295820: step: 130/470, loss: 0.3404453992843628
2023-01-22 17:38:21.038914: step: 132/470, loss: 0.27857649326324463
2023-01-22 17:38:21.847109: step: 134/470, loss: 0.029560066759586334
2023-01-22 17:38:22.587871: step: 136/470, loss: 0.18978171050548553
2023-01-22 17:38:23.364812: step: 138/470, loss: 0.5333614349365234
2023-01-22 17:38:24.093397: step: 140/470, loss: 0.13952665030956268
2023-01-22 17:38:24.795167: step: 142/470, loss: 1.607400894165039
2023-01-22 17:38:25.559420: step: 144/470, loss: 0.4059104919433594
2023-01-22 17:38:26.282976: step: 146/470, loss: 0.7796083688735962
2023-01-22 17:38:27.049411: step: 148/470, loss: 0.24871180951595306
2023-01-22 17:38:27.947771: step: 150/470, loss: 0.38717377185821533
2023-01-22 17:38:28.685534: step: 152/470, loss: 0.8463844656944275
2023-01-22 17:38:29.512990: step: 154/470, loss: 0.4317239820957184
2023-01-22 17:38:30.236000: step: 156/470, loss: 0.2562013864517212
2023-01-22 17:38:30.993584: step: 158/470, loss: 0.2918889820575714
2023-01-22 17:38:31.770243: step: 160/470, loss: 0.16746020317077637
2023-01-22 17:38:32.513615: step: 162/470, loss: 0.8833320140838623
2023-01-22 17:38:33.253637: step: 164/470, loss: 0.19680127501487732
2023-01-22 17:38:33.965794: step: 166/470, loss: 0.21358007192611694
2023-01-22 17:38:34.779398: step: 168/470, loss: 1.5736429691314697
2023-01-22 17:38:35.617553: step: 170/470, loss: 0.2858242094516754
2023-01-22 17:38:36.310302: step: 172/470, loss: 0.436594158411026
2023-01-22 17:38:37.099744: step: 174/470, loss: 0.25975707173347473
2023-01-22 17:38:37.853521: step: 176/470, loss: 0.5039308071136475
2023-01-22 17:38:38.618002: step: 178/470, loss: 0.5124750137329102
2023-01-22 17:38:39.421964: step: 180/470, loss: 0.3290499746799469
2023-01-22 17:38:40.163342: step: 182/470, loss: 0.3273886740207672
2023-01-22 17:38:40.950933: step: 184/470, loss: 0.18152934312820435
2023-01-22 17:38:41.619732: step: 186/470, loss: 0.14718110859394073
2023-01-22 17:38:42.355585: step: 188/470, loss: 0.18126271665096283
2023-01-22 17:38:43.191040: step: 190/470, loss: 0.34319642186164856
2023-01-22 17:38:43.885906: step: 192/470, loss: 0.179406076669693
2023-01-22 17:38:44.617429: step: 194/470, loss: 0.38715943694114685
2023-01-22 17:38:45.380433: step: 196/470, loss: 0.42315950989723206
2023-01-22 17:38:46.138807: step: 198/470, loss: 0.4406783878803253
2023-01-22 17:38:46.917325: step: 200/470, loss: 1.8089121580123901
2023-01-22 17:38:47.685357: step: 202/470, loss: 0.11779771745204926
2023-01-22 17:38:48.390434: step: 204/470, loss: 0.19911624491214752
2023-01-22 17:38:49.166834: step: 206/470, loss: 0.8379590511322021
2023-01-22 17:38:49.981299: step: 208/470, loss: 0.1292008012533188
2023-01-22 17:38:50.722270: step: 210/470, loss: 1.0208288431167603
2023-01-22 17:38:51.587230: step: 212/470, loss: 0.29888206720352173
2023-01-22 17:38:52.301494: step: 214/470, loss: 0.5137273073196411
2023-01-22 17:38:53.129924: step: 216/470, loss: 0.16628697514533997
2023-01-22 17:38:53.871069: step: 218/470, loss: 1.1978864669799805
2023-01-22 17:38:54.574027: step: 220/470, loss: 0.34227266907691956
2023-01-22 17:38:55.307677: step: 222/470, loss: 0.4677780866622925
2023-01-22 17:38:56.074535: step: 224/470, loss: 0.7787224054336548
2023-01-22 17:38:56.875099: step: 226/470, loss: 0.5353028178215027
2023-01-22 17:38:57.671522: step: 228/470, loss: 0.8215941786766052
2023-01-22 17:38:58.363436: step: 230/470, loss: 0.46585798263549805
2023-01-22 17:38:59.173968: step: 232/470, loss: 0.2040032297372818
2023-01-22 17:38:59.924662: step: 234/470, loss: 0.4652753174304962
2023-01-22 17:39:00.630927: step: 236/470, loss: 0.4290299713611603
2023-01-22 17:39:01.380645: step: 238/470, loss: 0.7905390858650208
2023-01-22 17:39:02.139833: step: 240/470, loss: 0.8647803664207458
2023-01-22 17:39:02.952865: step: 242/470, loss: 0.4174932837486267
2023-01-22 17:39:03.678101: step: 244/470, loss: 0.27988308668136597
2023-01-22 17:39:04.437501: step: 246/470, loss: 0.5162237882614136
2023-01-22 17:39:05.199826: step: 248/470, loss: 0.5198226571083069
2023-01-22 17:39:05.968317: step: 250/470, loss: 0.9243934154510498
2023-01-22 17:39:06.744189: step: 252/470, loss: 0.9011183977127075
2023-01-22 17:39:07.490275: step: 254/470, loss: 0.1754419207572937
2023-01-22 17:39:08.249000: step: 256/470, loss: 0.5413885712623596
2023-01-22 17:39:08.966575: step: 258/470, loss: 0.28291255235671997
2023-01-22 17:39:09.725591: step: 260/470, loss: 0.3509974181652069
2023-01-22 17:39:10.591057: step: 262/470, loss: 0.22708922624588013
2023-01-22 17:39:11.308772: step: 264/470, loss: 0.22111210227012634
2023-01-22 17:39:12.087219: step: 266/470, loss: 0.19584240019321442
2023-01-22 17:39:12.878658: step: 268/470, loss: 0.3218596279621124
2023-01-22 17:39:13.588255: step: 270/470, loss: 0.5958482623100281
2023-01-22 17:39:14.326189: step: 272/470, loss: 0.6783241629600525
2023-01-22 17:39:15.010063: step: 274/470, loss: 0.40668368339538574
2023-01-22 17:39:15.844156: step: 276/470, loss: 0.3130112290382385
2023-01-22 17:39:16.621920: step: 278/470, loss: 0.26188164949417114
2023-01-22 17:39:17.517647: step: 280/470, loss: 0.21814662218093872
2023-01-22 17:39:18.345504: step: 282/470, loss: 0.5404313206672668
2023-01-22 17:39:19.087608: step: 284/470, loss: 0.9255490303039551
2023-01-22 17:39:19.840345: step: 286/470, loss: 1.064405918121338
2023-01-22 17:39:20.712650: step: 288/470, loss: 0.6848692893981934
2023-01-22 17:39:21.445266: step: 290/470, loss: 0.1509696990251541
2023-01-22 17:39:22.221291: step: 292/470, loss: 0.4635472297668457
2023-01-22 17:39:23.018959: step: 294/470, loss: 0.6151084899902344
2023-01-22 17:39:23.769308: step: 296/470, loss: 0.11453315615653992
2023-01-22 17:39:24.556588: step: 298/470, loss: 0.1999867707490921
2023-01-22 17:39:25.329555: step: 300/470, loss: 0.21419981122016907
2023-01-22 17:39:26.150892: step: 302/470, loss: 0.46333491802215576
2023-01-22 17:39:26.987631: step: 304/470, loss: 0.8135701417922974
2023-01-22 17:39:27.708675: step: 306/470, loss: 0.2585707902908325
2023-01-22 17:39:28.548832: step: 308/470, loss: 0.46079540252685547
2023-01-22 17:39:29.319570: step: 310/470, loss: 0.27376070618629456
2023-01-22 17:39:30.098818: step: 312/470, loss: 0.4137362837791443
2023-01-22 17:39:30.816418: step: 314/470, loss: 0.24535976350307465
2023-01-22 17:39:31.601072: step: 316/470, loss: 0.349854052066803
2023-01-22 17:39:32.407170: step: 318/470, loss: 0.4655457139015198
2023-01-22 17:39:33.142875: step: 320/470, loss: 0.2523977756500244
2023-01-22 17:39:33.988760: step: 322/470, loss: 0.4521579146385193
2023-01-22 17:39:34.738848: step: 324/470, loss: 0.4393160045146942
2023-01-22 17:39:35.526749: step: 326/470, loss: 0.8228650689125061
2023-01-22 17:39:36.314937: step: 328/470, loss: 0.4634270966053009
2023-01-22 17:39:37.098705: step: 330/470, loss: 0.6964781284332275
2023-01-22 17:39:37.809294: step: 332/470, loss: 0.45030978322029114
2023-01-22 17:39:38.591976: step: 334/470, loss: 0.3737616539001465
2023-01-22 17:39:39.444570: step: 336/470, loss: 0.8672752976417542
2023-01-22 17:39:40.209105: step: 338/470, loss: 0.14447632431983948
2023-01-22 17:39:40.944156: step: 340/470, loss: 0.5296969413757324
2023-01-22 17:39:41.686664: step: 342/470, loss: 0.7490493655204773
2023-01-22 17:39:42.523520: step: 344/470, loss: 0.28861531615257263
2023-01-22 17:39:43.337404: step: 346/470, loss: 0.5648653507232666
2023-01-22 17:39:44.142982: step: 348/470, loss: 0.964550256729126
2023-01-22 17:39:44.838853: step: 350/470, loss: 0.8278896808624268
2023-01-22 17:39:45.519843: step: 352/470, loss: 0.17448605597019196
2023-01-22 17:39:46.269242: step: 354/470, loss: 0.6799153089523315
2023-01-22 17:39:46.948972: step: 356/470, loss: 0.4022669792175293
2023-01-22 17:39:47.699433: step: 358/470, loss: 0.2065814882516861
2023-01-22 17:39:48.531981: step: 360/470, loss: 0.3100614845752716
2023-01-22 17:39:49.360878: step: 362/470, loss: 0.3368839919567108
2023-01-22 17:39:50.046023: step: 364/470, loss: 1.1598883867263794
2023-01-22 17:39:50.837956: step: 366/470, loss: 0.31141793727874756
2023-01-22 17:39:51.612097: step: 368/470, loss: 0.23780982196331024
2023-01-22 17:39:52.399121: step: 370/470, loss: 0.22582471370697021
2023-01-22 17:39:53.222487: step: 372/470, loss: 0.803047239780426
2023-01-22 17:39:54.027101: step: 374/470, loss: 0.3405497670173645
2023-01-22 17:39:54.800057: step: 376/470, loss: 0.7714990973472595
2023-01-22 17:39:55.563147: step: 378/470, loss: 0.1867769956588745
2023-01-22 17:39:56.326984: step: 380/470, loss: 0.3200242519378662
2023-01-22 17:39:57.075049: step: 382/470, loss: 0.16745364665985107
2023-01-22 17:39:57.746306: step: 384/470, loss: 0.09259352087974548
2023-01-22 17:39:58.496926: step: 386/470, loss: 0.4721934497356415
2023-01-22 17:39:59.224028: step: 388/470, loss: 0.26353833079338074
2023-01-22 17:40:00.081903: step: 390/470, loss: 0.2055242657661438
2023-01-22 17:40:00.955352: step: 392/470, loss: 0.9652345180511475
2023-01-22 17:40:01.738175: step: 394/470, loss: 0.3389044404029846
2023-01-22 17:40:02.439574: step: 396/470, loss: 0.24200768768787384
2023-01-22 17:40:03.188129: step: 398/470, loss: 0.17797183990478516
2023-01-22 17:40:03.951811: step: 400/470, loss: 0.15373848378658295
2023-01-22 17:40:04.697482: step: 402/470, loss: 0.7525474429130554
2023-01-22 17:40:05.450976: step: 404/470, loss: 0.8085270524024963
2023-01-22 17:40:06.172336: step: 406/470, loss: 0.13830354809761047
2023-01-22 17:40:06.991424: step: 408/470, loss: 0.14868831634521484
2023-01-22 17:40:07.758619: step: 410/470, loss: 0.14518840610980988
2023-01-22 17:40:08.703515: step: 412/470, loss: 0.4489766061306
2023-01-22 17:40:09.456812: step: 414/470, loss: 0.24416552484035492
2023-01-22 17:40:10.175202: step: 416/470, loss: 0.2164216786623001
2023-01-22 17:40:10.890632: step: 418/470, loss: 0.0824371725320816
2023-01-22 17:40:11.729047: step: 420/470, loss: 0.09185123443603516
2023-01-22 17:40:12.542840: step: 422/470, loss: 0.3424897789955139
2023-01-22 17:40:13.272741: step: 424/470, loss: 0.3741994798183441
2023-01-22 17:40:14.027338: step: 426/470, loss: 0.14311550557613373
2023-01-22 17:40:14.736701: step: 428/470, loss: 0.22634892165660858
2023-01-22 17:40:15.519957: step: 430/470, loss: 0.2907640337944031
2023-01-22 17:40:16.299619: step: 432/470, loss: 0.1375235915184021
2023-01-22 17:40:17.012406: step: 434/470, loss: 0.27444496750831604
2023-01-22 17:40:17.718421: step: 436/470, loss: 0.18194928765296936
2023-01-22 17:40:18.449346: step: 438/470, loss: 0.3027937412261963
2023-01-22 17:40:19.188972: step: 440/470, loss: 0.22203978896141052
2023-01-22 17:40:19.962078: step: 442/470, loss: 0.40211665630340576
2023-01-22 17:40:20.718619: step: 444/470, loss: 0.9534308910369873
2023-01-22 17:40:21.571106: step: 446/470, loss: 0.3148941993713379
2023-01-22 17:40:22.328756: step: 448/470, loss: 0.25301098823547363
2023-01-22 17:40:23.055731: step: 450/470, loss: 0.283833384513855
2023-01-22 17:40:23.868279: step: 452/470, loss: 0.33523184061050415
2023-01-22 17:40:24.674303: step: 454/470, loss: 0.15356293320655823
2023-01-22 17:40:25.341876: step: 456/470, loss: 0.5051017999649048
2023-01-22 17:40:26.140524: step: 458/470, loss: 0.4202573895454407
2023-01-22 17:40:26.879847: step: 460/470, loss: 0.12335009127855301
2023-01-22 17:40:27.635996: step: 462/470, loss: 0.4301653504371643
2023-01-22 17:40:28.327195: step: 464/470, loss: 1.2519079446792603
2023-01-22 17:40:29.073422: step: 466/470, loss: 0.2109188437461853
2023-01-22 17:40:29.845703: step: 468/470, loss: 0.3727503716945648
2023-01-22 17:40:30.619171: step: 470/470, loss: 0.46644580364227295
2023-01-22 17:40:31.472818: step: 472/470, loss: 0.8295896649360657
2023-01-22 17:40:32.171415: step: 474/470, loss: 0.5774760246276855
2023-01-22 17:40:32.905308: step: 476/470, loss: 0.9126483201980591
2023-01-22 17:40:33.637523: step: 478/470, loss: 0.31328561902046204
2023-01-22 17:40:34.364594: step: 480/470, loss: 0.22493775188922882
2023-01-22 17:40:35.129774: step: 482/470, loss: 0.36869755387306213
2023-01-22 17:40:35.937110: step: 484/470, loss: 0.2161940336227417
2023-01-22 17:40:36.634069: step: 486/470, loss: 0.6317044496536255
2023-01-22 17:40:37.378465: step: 488/470, loss: 0.5619537234306335
2023-01-22 17:40:38.149258: step: 490/470, loss: 1.1349985599517822
2023-01-22 17:40:38.970355: step: 492/470, loss: 0.09379585087299347
2023-01-22 17:40:39.803399: step: 494/470, loss: 0.9672868847846985
2023-01-22 17:40:40.557639: step: 496/470, loss: 1.1263362169265747
2023-01-22 17:40:41.330876: step: 498/470, loss: 0.2689302861690521
2023-01-22 17:40:42.132567: step: 500/470, loss: 0.3239392042160034
2023-01-22 17:40:42.909047: step: 502/470, loss: 0.2518550157546997
2023-01-22 17:40:43.620139: step: 504/470, loss: 0.6391338109970093
2023-01-22 17:40:44.370026: step: 506/470, loss: 0.3393190801143646
2023-01-22 17:40:45.081048: step: 508/470, loss: 0.6354091763496399
2023-01-22 17:40:45.823255: step: 510/470, loss: 0.26952916383743286
2023-01-22 17:40:46.568935: step: 512/470, loss: 0.839598536491394
2023-01-22 17:40:47.351713: step: 514/470, loss: 0.41435518860816956
2023-01-22 17:40:48.132758: step: 516/470, loss: 0.5042211413383484
2023-01-22 17:40:48.901858: step: 518/470, loss: 1.5641471147537231
2023-01-22 17:40:49.654884: step: 520/470, loss: 0.34855765104293823
2023-01-22 17:40:50.423055: step: 522/470, loss: 0.521365761756897
2023-01-22 17:40:51.272483: step: 524/470, loss: 0.33301544189453125
2023-01-22 17:40:51.953863: step: 526/470, loss: 0.5081035494804382
2023-01-22 17:40:52.701893: step: 528/470, loss: 0.20576249063014984
2023-01-22 17:40:53.410047: step: 530/470, loss: 0.10231142491102219
2023-01-22 17:40:54.180743: step: 532/470, loss: 0.46384578943252563
2023-01-22 17:40:54.930888: step: 534/470, loss: 4.53569221496582
2023-01-22 17:40:55.706703: step: 536/470, loss: 0.2767690420150757
2023-01-22 17:40:56.515670: step: 538/470, loss: 0.24536767601966858
2023-01-22 17:40:57.266285: step: 540/470, loss: 0.5284467935562134
2023-01-22 17:40:58.141260: step: 542/470, loss: 1.4372402429580688
2023-01-22 17:40:58.911200: step: 544/470, loss: 0.2401868849992752
2023-01-22 17:40:59.718931: step: 546/470, loss: 0.6595420837402344
2023-01-22 17:41:00.509061: step: 548/470, loss: 0.8081770539283752
2023-01-22 17:41:01.249685: step: 550/470, loss: 0.17885182797908783
2023-01-22 17:41:02.083147: step: 552/470, loss: 0.21516308188438416
2023-01-22 17:41:02.826012: step: 554/470, loss: 0.5545898675918579
2023-01-22 17:41:03.510128: step: 556/470, loss: 0.20706087350845337
2023-01-22 17:41:04.281878: step: 558/470, loss: 0.13563042879104614
2023-01-22 17:41:04.989901: step: 560/470, loss: 0.2453116625547409
2023-01-22 17:41:05.727295: step: 562/470, loss: 0.7842438817024231
2023-01-22 17:41:06.602318: step: 564/470, loss: 0.2593076229095459
2023-01-22 17:41:07.383418: step: 566/470, loss: 0.12692120671272278
2023-01-22 17:41:08.081145: step: 568/470, loss: 0.4532640874385834
2023-01-22 17:41:08.825638: step: 570/470, loss: 0.3847683072090149
2023-01-22 17:41:09.664000: step: 572/470, loss: 0.19840320944786072
2023-01-22 17:41:10.399337: step: 574/470, loss: 0.15931807458400726
2023-01-22 17:41:11.192050: step: 576/470, loss: 0.2908623516559601
2023-01-22 17:41:11.927584: step: 578/470, loss: 0.6550799608230591
2023-01-22 17:41:12.652264: step: 580/470, loss: 0.6560707688331604
2023-01-22 17:41:13.435596: step: 582/470, loss: 0.41067826747894287
2023-01-22 17:41:14.197078: step: 584/470, loss: 0.11992362141609192
2023-01-22 17:41:14.904418: step: 586/470, loss: 0.460469126701355
2023-01-22 17:41:15.723882: step: 588/470, loss: 0.8359988331794739
2023-01-22 17:41:16.466191: step: 590/470, loss: 0.36444351077079773
2023-01-22 17:41:17.251781: step: 592/470, loss: 0.2154173105955124
2023-01-22 17:41:17.999955: step: 594/470, loss: 0.5687950849533081
2023-01-22 17:41:18.725766: step: 596/470, loss: 0.9395169615745544
2023-01-22 17:41:19.468369: step: 598/470, loss: 0.49935394525527954
2023-01-22 17:41:20.226733: step: 600/470, loss: 0.49853333830833435
2023-01-22 17:41:20.955041: step: 602/470, loss: 1.7896212339401245
2023-01-22 17:41:21.676224: step: 604/470, loss: 0.1358480155467987
2023-01-22 17:41:22.432416: step: 606/470, loss: 0.7760083079338074
2023-01-22 17:41:23.148417: step: 608/470, loss: 0.3000049293041229
2023-01-22 17:41:23.891884: step: 610/470, loss: 0.4000217616558075
2023-01-22 17:41:24.624273: step: 612/470, loss: 0.3303145170211792
2023-01-22 17:41:25.414868: step: 614/470, loss: 0.517999529838562
2023-01-22 17:41:26.184225: step: 616/470, loss: 0.37297362089157104
2023-01-22 17:41:26.961310: step: 618/470, loss: 0.2246372401714325
2023-01-22 17:41:27.720044: step: 620/470, loss: 0.9546456336975098
2023-01-22 17:41:28.486582: step: 622/470, loss: 0.9173968434333801
2023-01-22 17:41:29.257960: step: 624/470, loss: 0.35250478982925415
2023-01-22 17:41:30.111491: step: 626/470, loss: 0.8878437280654907
2023-01-22 17:41:30.781157: step: 628/470, loss: 0.49247634410858154
2023-01-22 17:41:31.494816: step: 630/470, loss: 0.3329099416732788
2023-01-22 17:41:32.269383: step: 632/470, loss: 1.0935202836990356
2023-01-22 17:41:33.009428: step: 634/470, loss: 0.2755989730358124
2023-01-22 17:41:33.704923: step: 636/470, loss: 0.6668111085891724
2023-01-22 17:41:34.444196: step: 638/470, loss: 0.24469828605651855
2023-01-22 17:41:35.238549: step: 640/470, loss: 0.22104227542877197
2023-01-22 17:41:35.999224: step: 642/470, loss: 0.16912305355072021
2023-01-22 17:41:36.720623: step: 644/470, loss: 0.10374326258897781
2023-01-22 17:41:37.466803: step: 646/470, loss: 0.20086267590522766
2023-01-22 17:41:38.254549: step: 648/470, loss: 0.1727813482284546
2023-01-22 17:41:39.046068: step: 650/470, loss: 0.13764482736587524
2023-01-22 17:41:39.824412: step: 652/470, loss: 0.3168490529060364
2023-01-22 17:41:40.683388: step: 654/470, loss: 0.5362805128097534
2023-01-22 17:41:41.401204: step: 656/470, loss: 0.40005090832710266
2023-01-22 17:41:42.145028: step: 658/470, loss: 2.0221118927001953
2023-01-22 17:41:42.908958: step: 660/470, loss: 0.46189936995506287
2023-01-22 17:41:43.623474: step: 662/470, loss: 0.6272675395011902
2023-01-22 17:41:44.396473: step: 664/470, loss: 0.44351091980934143
2023-01-22 17:41:45.161393: step: 666/470, loss: 0.31063738465309143
2023-01-22 17:41:45.949708: step: 668/470, loss: 0.41334736347198486
2023-01-22 17:41:46.683837: step: 670/470, loss: 0.10286879539489746
2023-01-22 17:41:47.434605: step: 672/470, loss: 0.5979005098342896
2023-01-22 17:41:48.148364: step: 674/470, loss: 4.1260666847229
2023-01-22 17:41:48.955058: step: 676/470, loss: 0.8004294633865356
2023-01-22 17:41:49.682082: step: 678/470, loss: 0.24940814077854156
2023-01-22 17:41:50.429193: step: 680/470, loss: 0.16425098478794098
2023-01-22 17:41:51.159809: step: 682/470, loss: 0.671233594417572
2023-01-22 17:41:51.942098: step: 684/470, loss: 0.15050573647022247
2023-01-22 17:41:52.773532: step: 686/470, loss: 0.36023542284965515
2023-01-22 17:41:53.547425: step: 688/470, loss: 1.1040581464767456
2023-01-22 17:41:54.326992: step: 690/470, loss: 0.3097226321697235
2023-01-22 17:41:55.025295: step: 692/470, loss: 0.27629736065864563
2023-01-22 17:41:55.740296: step: 694/470, loss: 2.556936264038086
2023-01-22 17:41:56.535616: step: 696/470, loss: 0.2204158753156662
2023-01-22 17:41:57.297817: step: 698/470, loss: 0.7285110950469971
2023-01-22 17:41:58.135066: step: 700/470, loss: 4.453820705413818
2023-01-22 17:41:58.922061: step: 702/470, loss: 0.6035624742507935
2023-01-22 17:41:59.689483: step: 704/470, loss: 0.21447139978408813
2023-01-22 17:42:00.394362: step: 706/470, loss: 0.23186089098453522
2023-01-22 17:42:01.238705: step: 708/470, loss: 0.40758103132247925
2023-01-22 17:42:02.014059: step: 710/470, loss: 0.13845710456371307
2023-01-22 17:42:02.841953: step: 712/470, loss: 3.9527015686035156
2023-01-22 17:42:03.621122: step: 714/470, loss: 0.26543423533439636
2023-01-22 17:42:04.370356: step: 716/470, loss: 0.45242205262184143
2023-01-22 17:42:05.091377: step: 718/470, loss: 2.2168221473693848
2023-01-22 17:42:05.868496: step: 720/470, loss: 0.22453352808952332
2023-01-22 17:42:06.593811: step: 722/470, loss: 0.5967671871185303
2023-01-22 17:42:07.365301: step: 724/470, loss: 0.45324817299842834
2023-01-22 17:42:08.141521: step: 726/470, loss: 1.0313066244125366
2023-01-22 17:42:08.887148: step: 728/470, loss: 0.11269115656614304
2023-01-22 17:42:09.726001: step: 730/470, loss: 0.49560102820396423
2023-01-22 17:42:10.519821: step: 732/470, loss: 0.2794017791748047
2023-01-22 17:42:11.219145: step: 734/470, loss: 0.6522477865219116
2023-01-22 17:42:11.966469: step: 736/470, loss: 0.28647884726524353
2023-01-22 17:42:12.696725: step: 738/470, loss: 0.20137378573417664
2023-01-22 17:42:13.462971: step: 740/470, loss: 0.6079099178314209
2023-01-22 17:42:14.253444: step: 742/470, loss: 0.7093207240104675
2023-01-22 17:42:15.092319: step: 744/470, loss: 0.21907228231430054
2023-01-22 17:42:15.851958: step: 746/470, loss: 0.131643146276474
2023-01-22 17:42:16.649521: step: 748/470, loss: 0.4653341472148895
2023-01-22 17:42:17.380720: step: 750/470, loss: 5.116756916046143
2023-01-22 17:42:18.129832: step: 752/470, loss: 0.3567095100879669
2023-01-22 17:42:18.900533: step: 754/470, loss: 0.18065395951271057
2023-01-22 17:42:19.617720: step: 756/470, loss: 0.2523786723613739
2023-01-22 17:42:20.375832: step: 758/470, loss: 0.9525728225708008
2023-01-22 17:42:21.105536: step: 760/470, loss: 0.30923041701316833
2023-01-22 17:42:21.923071: step: 762/470, loss: 0.32964733242988586
2023-01-22 17:42:22.733234: step: 764/470, loss: 0.2381993532180786
2023-01-22 17:42:23.487178: step: 766/470, loss: 0.18978539109230042
2023-01-22 17:42:24.299888: step: 768/470, loss: 0.7485260963439941
2023-01-22 17:42:25.036307: step: 770/470, loss: 0.25674277544021606
2023-01-22 17:42:25.828358: step: 772/470, loss: 0.22901327908039093
2023-01-22 17:42:26.545711: step: 774/470, loss: 0.2624027729034424
2023-01-22 17:42:27.327555: step: 776/470, loss: 0.14591439068317413
2023-01-22 17:42:28.160491: step: 778/470, loss: 1.4718310832977295
2023-01-22 17:42:28.928676: step: 780/470, loss: 0.26930221915245056
2023-01-22 17:42:29.684904: step: 782/470, loss: 0.7424861192703247
2023-01-22 17:42:30.400481: step: 784/470, loss: 0.29697778820991516
2023-01-22 17:42:31.123463: step: 786/470, loss: 1.1480909585952759
2023-01-22 17:42:31.829029: step: 788/470, loss: 0.8097434639930725
2023-01-22 17:42:32.576741: step: 790/470, loss: 0.5420349836349487
2023-01-22 17:42:33.291654: step: 792/470, loss: 0.21315941214561462
2023-01-22 17:42:34.021510: step: 794/470, loss: 0.2593609094619751
2023-01-22 17:42:34.725117: step: 796/470, loss: 0.21246762573719025
2023-01-22 17:42:35.497225: step: 798/470, loss: 0.45392927527427673
2023-01-22 17:42:36.252213: step: 800/470, loss: 0.4097192883491516
2023-01-22 17:42:37.065490: step: 802/470, loss: 0.9928512573242188
2023-01-22 17:42:37.809340: step: 804/470, loss: 0.5397576689720154
2023-01-22 17:42:38.548008: step: 806/470, loss: 0.0932132676243782
2023-01-22 17:42:39.331525: step: 808/470, loss: 0.43611350655555725
2023-01-22 17:42:40.104431: step: 810/470, loss: 0.5918594598770142
2023-01-22 17:42:40.875905: step: 812/470, loss: 0.23620811104774475
2023-01-22 17:42:41.712776: step: 814/470, loss: 0.5560216307640076
2023-01-22 17:42:42.498671: step: 816/470, loss: 0.598693311214447
2023-01-22 17:42:43.284442: step: 818/470, loss: 0.40362799167633057
2023-01-22 17:42:44.089610: step: 820/470, loss: 0.23154190182685852
2023-01-22 17:42:44.809957: step: 822/470, loss: 0.5826197266578674
2023-01-22 17:42:45.518215: step: 824/470, loss: 0.2394208461046219
2023-01-22 17:42:46.176320: step: 826/470, loss: 0.17906901240348816
2023-01-22 17:42:46.982467: step: 828/470, loss: 0.372158408164978
2023-01-22 17:42:47.705077: step: 830/470, loss: 1.067903757095337
2023-01-22 17:42:48.463981: step: 832/470, loss: 0.1843709796667099
2023-01-22 17:42:49.267034: step: 834/470, loss: 0.2733551263809204
2023-01-22 17:42:50.171416: step: 836/470, loss: 1.0208349227905273
2023-01-22 17:42:50.906495: step: 838/470, loss: 0.6295246481895447
2023-01-22 17:42:51.642303: step: 840/470, loss: 0.357212096452713
2023-01-22 17:42:52.430736: step: 842/470, loss: 0.20953968167304993
2023-01-22 17:42:53.237568: step: 844/470, loss: 0.630314290523529
2023-01-22 17:42:54.109001: step: 846/470, loss: 1.2299977540969849
2023-01-22 17:42:54.880492: step: 848/470, loss: 0.599105179309845
2023-01-22 17:42:55.747249: step: 850/470, loss: 0.8288000226020813
2023-01-22 17:42:56.548523: step: 852/470, loss: 0.1812320500612259
2023-01-22 17:42:57.350599: step: 854/470, loss: 0.23691441118717194
2023-01-22 17:42:58.057135: step: 856/470, loss: 0.3210389316082001
2023-01-22 17:42:58.744638: step: 858/470, loss: 0.5429426431655884
2023-01-22 17:42:59.510538: step: 860/470, loss: 0.13180933892726898
2023-01-22 17:43:00.224554: step: 862/470, loss: 1.8928117752075195
2023-01-22 17:43:00.972928: step: 864/470, loss: 0.7599416971206665
2023-01-22 17:43:01.742981: step: 866/470, loss: 0.5055848360061646
2023-01-22 17:43:02.499256: step: 868/470, loss: 0.1821976751089096
2023-01-22 17:43:03.200340: step: 870/470, loss: 1.22907555103302
2023-01-22 17:43:04.022285: step: 872/470, loss: 0.3916356861591339
2023-01-22 17:43:04.696056: step: 874/470, loss: 0.26299530267715454
2023-01-22 17:43:05.410491: step: 876/470, loss: 0.25578999519348145
2023-01-22 17:43:06.172916: step: 878/470, loss: 0.37457263469696045
2023-01-22 17:43:06.847962: step: 880/470, loss: 0.3378101885318756
2023-01-22 17:43:07.502649: step: 882/470, loss: 1.6557979583740234
2023-01-22 17:43:08.279438: step: 884/470, loss: 0.39262452721595764
2023-01-22 17:43:09.052855: step: 886/470, loss: 0.4881884753704071
2023-01-22 17:43:09.749047: step: 888/470, loss: 0.19406718015670776
2023-01-22 17:43:10.577445: step: 890/470, loss: 0.2705124318599701
2023-01-22 17:43:11.290167: step: 892/470, loss: 0.34521085023880005
2023-01-22 17:43:12.052474: step: 894/470, loss: 0.45954829454421997
2023-01-22 17:43:12.807961: step: 896/470, loss: 0.14961890876293182
2023-01-22 17:43:13.558721: step: 898/470, loss: 1.0215060710906982
2023-01-22 17:43:14.325515: step: 900/470, loss: 1.122787594795227
2023-01-22 17:43:15.084171: step: 902/470, loss: 0.2572832703590393
2023-01-22 17:43:15.946650: step: 904/470, loss: 0.19345666468143463
2023-01-22 17:43:16.719611: step: 906/470, loss: 0.4549930989742279
2023-01-22 17:43:17.453464: step: 908/470, loss: 0.32068750262260437
2023-01-22 17:43:18.196037: step: 910/470, loss: 0.5561640858650208
2023-01-22 17:43:19.194105: step: 912/470, loss: 0.2232218235731125
2023-01-22 17:43:19.961314: step: 914/470, loss: 0.2716374099254608
2023-01-22 17:43:20.666436: step: 916/470, loss: 0.1163991242647171
2023-01-22 17:43:21.524329: step: 918/470, loss: 0.3325546085834503
2023-01-22 17:43:22.219645: step: 920/470, loss: 0.5324735641479492
2023-01-22 17:43:22.958733: step: 922/470, loss: 0.1445450484752655
2023-01-22 17:43:23.786584: step: 924/470, loss: 0.61869215965271
2023-01-22 17:43:24.540797: step: 926/470, loss: 0.2812950611114502
2023-01-22 17:43:25.363236: step: 928/470, loss: 0.8153495192527771
2023-01-22 17:43:26.095337: step: 930/470, loss: 0.4129032492637634
2023-01-22 17:43:26.875885: step: 932/470, loss: 0.3423391282558441
2023-01-22 17:43:27.714052: step: 934/470, loss: 1.508226752281189
2023-01-22 17:43:28.506167: step: 936/470, loss: 0.32150372862815857
2023-01-22 17:43:29.264434: step: 938/470, loss: 0.3547199070453644
2023-01-22 17:43:30.034330: step: 940/470, loss: 0.3670746386051178
2023-01-22 17:43:30.725561: step: 942/470, loss: 0.5506512522697449
==================================================
Loss: 0.508
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3049308236808237, 'r': 0.3211320818650041, 'f1': 0.3128218246633219}, 'combined': 0.23050029185718457, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32065206847366756, 'r': 0.3490174437617227, 'f1': 0.3342340161254067}, 'combined': 0.23279981222665144, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29067732698296866, 'r': 0.3182558210041232, 'f1': 0.3038420609948785}, 'combined': 0.22388362389096308, 'epoch': 8}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3310886777617448, 'r': 0.3488994039429722, 'f1': 0.3397607853177119}, 'combined': 0.23664930320636654, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27751515331590204, 'r': 0.3164831255082678, 'f1': 0.29572093465045596}, 'combined': 0.2178996360582307, 'epoch': 8}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3162120582663088, 'r': 0.3614719974417939, 'f1': 0.3373306583029202}, 'combined': 0.23495667742491955, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24523809523809523, 'r': 0.31530612244897954, 'f1': 0.27589285714285716}, 'combined': 0.18392857142857144, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27941176470588236, 'r': 0.41304347826086957, 'f1': 0.33333333333333337}, 'combined': 0.16666666666666669, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 8}
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': 0.3049308236808237, 'r': 0.3211320818650041, 'f1': 0.3128218246633219}, 'combined': 0.23050029185718457, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32065206847366756, 'r': 0.3490174437617227, 'f1': 0.3342340161254067}, 'combined': 0.23279981222665144, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24523809523809523, 'r': 0.31530612244897954, 'f1': 0.27589285714285716}, 'combined': 0.18392857142857144, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26474047961800956, 'r': 0.3240182340675829, 'f1': 0.29139523780480575}, 'combined': 0.2147122804877516, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32541475117674507, 'r': 0.34573363573629207, 'f1': 0.33526661835256644}, 'combined': 0.23351903765850401, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2722222222222222, 'r': 0.532608695652174, 'f1': 0.36029411764705876}, 'combined': 0.18014705882352938, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27751515331590204, 'r': 0.3164831255082678, 'f1': 0.29572093465045596}, 'combined': 0.2178996360582307, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3162120582663088, 'r': 0.3614719974417939, 'f1': 0.3373306583029202}, 'combined': 0.23495667742491955, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 8}
******************************
Epoch: 9
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 17:46:25.632716: step: 2/470, loss: 0.5447205901145935
2023-01-22 17:46:26.400413: step: 4/470, loss: 0.22318868339061737
2023-01-22 17:46:27.154100: step: 6/470, loss: 0.3136242926120758
2023-01-22 17:46:27.924777: step: 8/470, loss: 0.28907865285873413
2023-01-22 17:46:28.713580: step: 10/470, loss: 0.2637608051300049
2023-01-22 17:46:29.511978: step: 12/470, loss: 0.5738874077796936
2023-01-22 17:46:30.250794: step: 14/470, loss: 1.0422797203063965
2023-01-22 17:46:31.053478: step: 16/470, loss: 0.602383553981781
2023-01-22 17:46:31.822810: step: 18/470, loss: 0.08700596541166306
2023-01-22 17:46:32.631403: step: 20/470, loss: 0.6579717993736267
2023-01-22 17:46:33.476470: step: 22/470, loss: 0.17143812775611877
2023-01-22 17:46:34.263178: step: 24/470, loss: 0.21379876136779785
2023-01-22 17:46:35.090068: step: 26/470, loss: 0.6119391322135925
2023-01-22 17:46:35.872371: step: 28/470, loss: 0.23522713780403137
2023-01-22 17:46:36.614362: step: 30/470, loss: 0.5445173978805542
2023-01-22 17:46:37.389709: step: 32/470, loss: 3.121372938156128
2023-01-22 17:46:38.136405: step: 34/470, loss: 0.2587936520576477
2023-01-22 17:46:38.908979: step: 36/470, loss: 0.5228575468063354
2023-01-22 17:46:39.753192: step: 38/470, loss: 0.3780156075954437
2023-01-22 17:46:40.450468: step: 40/470, loss: 0.4384208023548126
2023-01-22 17:46:41.248395: step: 42/470, loss: 0.2887096107006073
2023-01-22 17:46:41.982801: step: 44/470, loss: 0.2585183382034302
2023-01-22 17:46:42.740925: step: 46/470, loss: 0.2520710825920105
2023-01-22 17:46:43.440282: step: 48/470, loss: 0.7488427758216858
2023-01-22 17:46:44.184320: step: 50/470, loss: 0.10620920360088348
2023-01-22 17:46:45.028050: step: 52/470, loss: 0.14906106889247894
2023-01-22 17:46:45.782572: step: 54/470, loss: 0.6837480068206787
2023-01-22 17:46:46.634025: step: 56/470, loss: 0.15488582849502563
2023-01-22 17:46:47.375070: step: 58/470, loss: 0.9800782203674316
2023-01-22 17:46:48.156814: step: 60/470, loss: 0.2453881949186325
2023-01-22 17:46:48.884363: step: 62/470, loss: 0.25628599524497986
2023-01-22 17:46:49.661954: step: 64/470, loss: 0.5019969940185547
2023-01-22 17:46:50.367498: step: 66/470, loss: 0.15023790299892426
2023-01-22 17:46:51.210724: step: 68/470, loss: 0.39702898263931274
2023-01-22 17:46:51.961601: step: 70/470, loss: 0.5472665429115295
2023-01-22 17:46:52.669055: step: 72/470, loss: 0.5863292217254639
2023-01-22 17:46:53.421958: step: 74/470, loss: 0.13345842063426971
2023-01-22 17:46:54.319071: step: 76/470, loss: 0.1856902539730072
2023-01-22 17:46:55.081290: step: 78/470, loss: 0.19066360592842102
2023-01-22 17:46:55.843903: step: 80/470, loss: 0.2122010886669159
2023-01-22 17:46:56.625935: step: 82/470, loss: 0.49828097224235535
2023-01-22 17:46:57.327161: step: 84/470, loss: 0.15491345524787903
2023-01-22 17:46:58.117211: step: 86/470, loss: 0.1964101791381836
2023-01-22 17:46:58.860608: step: 88/470, loss: 0.1925598680973053
2023-01-22 17:46:59.621447: step: 90/470, loss: 0.5155028700828552
2023-01-22 17:47:00.318947: step: 92/470, loss: 0.21076497435569763
2023-01-22 17:47:01.065732: step: 94/470, loss: 0.18973298370838165
2023-01-22 17:47:01.882321: step: 96/470, loss: 0.5644153356552124
2023-01-22 17:47:02.675054: step: 98/470, loss: 0.10288572311401367
2023-01-22 17:47:03.411847: step: 100/470, loss: 0.07585206627845764
2023-01-22 17:47:04.174021: step: 102/470, loss: 0.3527693748474121
2023-01-22 17:47:04.941167: step: 104/470, loss: 0.14347948133945465
2023-01-22 17:47:05.779890: step: 106/470, loss: 0.36973798274993896
2023-01-22 17:47:06.496208: step: 108/470, loss: 0.38219624757766724
2023-01-22 17:47:07.216139: step: 110/470, loss: 0.744696319103241
2023-01-22 17:47:07.996152: step: 112/470, loss: 0.36855944991111755
2023-01-22 17:47:08.856438: step: 114/470, loss: 0.1453740894794464
2023-01-22 17:47:09.625702: step: 116/470, loss: 1.321637511253357
2023-01-22 17:47:10.384790: step: 118/470, loss: 0.9926891922950745
2023-01-22 17:47:11.108880: step: 120/470, loss: 0.15449316799640656
2023-01-22 17:47:11.927135: step: 122/470, loss: 0.14840567111968994
2023-01-22 17:47:12.697705: step: 124/470, loss: 0.18444156646728516
2023-01-22 17:47:13.448586: step: 126/470, loss: 0.3966729938983917
2023-01-22 17:47:14.173189: step: 128/470, loss: 1.7696688175201416
2023-01-22 17:47:14.871800: step: 130/470, loss: 0.30441614985466003
2023-01-22 17:47:15.613842: step: 132/470, loss: 0.17320138216018677
2023-01-22 17:47:16.324708: step: 134/470, loss: 0.2448633313179016
2023-01-22 17:47:17.120704: step: 136/470, loss: 0.2567095458507538
2023-01-22 17:47:17.933169: step: 138/470, loss: 0.04755272716283798
2023-01-22 17:47:18.619290: step: 140/470, loss: 0.15079620480537415
2023-01-22 17:47:19.425073: step: 142/470, loss: 0.5248032212257385
2023-01-22 17:47:20.142785: step: 144/470, loss: 0.3448765277862549
2023-01-22 17:47:20.902224: step: 146/470, loss: 0.45058566331863403
2023-01-22 17:47:21.626654: step: 148/470, loss: 0.1982106864452362
2023-01-22 17:47:22.376893: step: 150/470, loss: 0.17295490205287933
2023-01-22 17:47:23.141535: step: 152/470, loss: 1.0078809261322021
2023-01-22 17:47:23.913043: step: 154/470, loss: 0.33238446712493896
2023-01-22 17:47:24.658531: step: 156/470, loss: 0.15200795233249664
2023-01-22 17:47:25.428858: step: 158/470, loss: 0.07408700883388519
2023-01-22 17:47:26.227874: step: 160/470, loss: 0.26883095502853394
2023-01-22 17:47:26.963333: step: 162/470, loss: 0.9753660559654236
2023-01-22 17:47:27.770636: step: 164/470, loss: 0.3113194704055786
2023-01-22 17:47:28.479886: step: 166/470, loss: 0.25497275590896606
2023-01-22 17:47:29.302480: step: 168/470, loss: 0.4309341311454773
2023-01-22 17:47:30.092685: step: 170/470, loss: 0.07410217821598053
2023-01-22 17:47:30.800642: step: 172/470, loss: 0.8484674096107483
2023-01-22 17:47:31.555398: step: 174/470, loss: 0.28762853145599365
2023-01-22 17:47:32.346686: step: 176/470, loss: 0.14900214970111847
2023-01-22 17:47:33.130139: step: 178/470, loss: 0.14563746750354767
2023-01-22 17:47:33.918197: step: 180/470, loss: 0.2309417426586151
2023-01-22 17:47:34.694399: step: 182/470, loss: 0.7100458145141602
2023-01-22 17:47:35.483583: step: 184/470, loss: 0.2716662287712097
2023-01-22 17:47:36.250902: step: 186/470, loss: 0.28548765182495117
2023-01-22 17:47:37.036562: step: 188/470, loss: 0.8044639229774475
2023-01-22 17:47:37.987294: step: 190/470, loss: 0.19010743498802185
2023-01-22 17:47:38.674321: step: 192/470, loss: 0.2690931558609009
2023-01-22 17:47:39.403786: step: 194/470, loss: 0.1267169564962387
2023-01-22 17:47:40.187113: step: 196/470, loss: 0.9669914245605469
2023-01-22 17:47:41.019038: step: 198/470, loss: 0.5740648508071899
2023-01-22 17:47:41.785300: step: 200/470, loss: 0.16114988923072815
2023-01-22 17:47:42.538199: step: 202/470, loss: 0.14519870281219482
2023-01-22 17:47:43.292245: step: 204/470, loss: 0.18535593152046204
2023-01-22 17:47:44.044836: step: 206/470, loss: 0.34165194630622864
2023-01-22 17:47:44.813652: step: 208/470, loss: 0.1012420654296875
2023-01-22 17:47:45.633003: step: 210/470, loss: 0.35992568731307983
2023-01-22 17:47:46.456834: step: 212/470, loss: 1.1616597175598145
2023-01-22 17:47:47.263850: step: 214/470, loss: 0.3503967523574829
2023-01-22 17:47:48.048793: step: 216/470, loss: 0.5987624526023865
2023-01-22 17:47:48.860452: step: 218/470, loss: 0.17567022144794464
2023-01-22 17:47:49.626360: step: 220/470, loss: 0.16215509176254272
2023-01-22 17:47:50.441062: step: 222/470, loss: 0.3935254216194153
2023-01-22 17:47:51.166071: step: 224/470, loss: 0.45323100686073303
2023-01-22 17:47:51.994924: step: 226/470, loss: 1.0208436250686646
2023-01-22 17:47:52.773879: step: 228/470, loss: 0.39432036876678467
2023-01-22 17:47:53.598035: step: 230/470, loss: 0.2786700129508972
2023-01-22 17:47:54.312507: step: 232/470, loss: 0.19462734460830688
2023-01-22 17:47:55.177646: step: 234/470, loss: 0.12101204693317413
2023-01-22 17:47:55.953094: step: 236/470, loss: 0.17866027355194092
2023-01-22 17:47:56.708557: step: 238/470, loss: 0.2924273610115051
2023-01-22 17:47:57.514247: step: 240/470, loss: 0.5252290368080139
2023-01-22 17:47:58.236284: step: 242/470, loss: 0.13447031378746033
2023-01-22 17:47:59.018161: step: 244/470, loss: 0.08729273080825806
2023-01-22 17:47:59.858533: step: 246/470, loss: 0.13195963203907013
2023-01-22 17:48:00.543905: step: 248/470, loss: 0.40723153948783875
2023-01-22 17:48:01.320884: step: 250/470, loss: 0.8148595094680786
2023-01-22 17:48:02.063285: step: 252/470, loss: 0.10905633121728897
2023-01-22 17:48:02.885189: step: 254/470, loss: 0.3877982497215271
2023-01-22 17:48:03.623082: step: 256/470, loss: 0.6170598864555359
2023-01-22 17:48:04.296344: step: 258/470, loss: 0.3111323416233063
2023-01-22 17:48:05.012655: step: 260/470, loss: 0.24980317056179047
2023-01-22 17:48:05.727688: step: 262/470, loss: 0.26733797788619995
2023-01-22 17:48:06.560474: step: 264/470, loss: 0.04581334814429283
2023-01-22 17:48:07.372865: step: 266/470, loss: 0.3556976616382599
2023-01-22 17:48:08.137375: step: 268/470, loss: 0.20936265587806702
2023-01-22 17:48:08.834312: step: 270/470, loss: 0.07905016839504242
2023-01-22 17:48:09.616085: step: 272/470, loss: 0.5653750896453857
2023-01-22 17:48:10.302406: step: 274/470, loss: 0.15013067424297333
2023-01-22 17:48:11.024658: step: 276/470, loss: 0.25626760721206665
2023-01-22 17:48:11.795604: step: 278/470, loss: 0.19960841536521912
2023-01-22 17:48:12.597530: step: 280/470, loss: 0.302801251411438
2023-01-22 17:48:13.312556: step: 282/470, loss: 0.2810971140861511
2023-01-22 17:48:14.068407: step: 284/470, loss: 0.22355952858924866
2023-01-22 17:48:14.825991: step: 286/470, loss: 0.7538304924964905
2023-01-22 17:48:15.571005: step: 288/470, loss: 0.9847416281700134
2023-01-22 17:48:16.396541: step: 290/470, loss: 0.12261106073856354
2023-01-22 17:48:17.134423: step: 292/470, loss: 0.3926984667778015
2023-01-22 17:48:17.897497: step: 294/470, loss: 0.6225259900093079
2023-01-22 17:48:18.698095: step: 296/470, loss: 0.5642341375350952
2023-01-22 17:48:19.493434: step: 298/470, loss: 0.3781619668006897
2023-01-22 17:48:20.229577: step: 300/470, loss: 0.6121640205383301
2023-01-22 17:48:20.995010: step: 302/470, loss: 0.4178549647331238
2023-01-22 17:48:21.651795: step: 304/470, loss: 0.3481173515319824
2023-01-22 17:48:22.425467: step: 306/470, loss: 0.48398879170417786
2023-01-22 17:48:23.192388: step: 308/470, loss: 1.0851445198059082
2023-01-22 17:48:23.948797: step: 310/470, loss: 0.42979589104652405
2023-01-22 17:48:24.678677: step: 312/470, loss: 0.3409073054790497
2023-01-22 17:48:25.562427: step: 314/470, loss: 0.1891537755727768
2023-01-22 17:48:26.299833: step: 316/470, loss: 0.08484365046024323
2023-01-22 17:48:27.055121: step: 318/470, loss: 0.08334700763225555
2023-01-22 17:48:27.778634: step: 320/470, loss: 0.13253387808799744
2023-01-22 17:48:28.531715: step: 322/470, loss: 0.18955287337303162
2023-01-22 17:48:29.279943: step: 324/470, loss: 0.4056585729122162
2023-01-22 17:48:30.092807: step: 326/470, loss: 0.398506224155426
2023-01-22 17:48:30.864209: step: 328/470, loss: 0.4494258165359497
2023-01-22 17:48:31.612996: step: 330/470, loss: 0.5383342504501343
2023-01-22 17:48:32.375965: step: 332/470, loss: 0.3049156665802002
2023-01-22 17:48:33.084510: step: 334/470, loss: 0.3931887745857239
2023-01-22 17:48:33.800728: step: 336/470, loss: 0.3626604676246643
2023-01-22 17:48:34.600482: step: 338/470, loss: 0.19436430931091309
2023-01-22 17:48:35.321370: step: 340/470, loss: 0.12340643256902695
2023-01-22 17:48:36.087977: step: 342/470, loss: 0.10149870067834854
2023-01-22 17:48:36.881993: step: 344/470, loss: 0.26956290006637573
2023-01-22 17:48:37.679264: step: 346/470, loss: 0.35809779167175293
2023-01-22 17:48:38.488875: step: 348/470, loss: 0.2530977129936218
2023-01-22 17:48:39.134584: step: 350/470, loss: 0.20895856618881226
2023-01-22 17:48:39.989885: step: 352/470, loss: 0.1304413229227066
2023-01-22 17:48:40.713877: step: 354/470, loss: 0.31440871953964233
2023-01-22 17:48:41.444842: step: 356/470, loss: 0.09652471542358398
2023-01-22 17:48:42.257910: step: 358/470, loss: 0.8130881786346436
2023-01-22 17:48:42.992985: step: 360/470, loss: 0.2621191740036011
2023-01-22 17:48:43.689433: step: 362/470, loss: 0.2604580819606781
2023-01-22 17:48:44.391344: step: 364/470, loss: 0.27661120891571045
2023-01-22 17:48:45.118125: step: 366/470, loss: 0.23585830628871918
2023-01-22 17:48:45.859503: step: 368/470, loss: 0.2118925154209137
2023-01-22 17:48:46.554158: step: 370/470, loss: 0.9197829365730286
2023-01-22 17:48:47.339612: step: 372/470, loss: 0.3997812867164612
2023-01-22 17:48:48.117705: step: 374/470, loss: 0.20830069482326508
2023-01-22 17:48:48.848871: step: 376/470, loss: 0.3739283084869385
2023-01-22 17:48:49.668169: step: 378/470, loss: 0.3728155195713043
2023-01-22 17:48:50.491833: step: 380/470, loss: 0.1496754288673401
2023-01-22 17:48:51.197750: step: 382/470, loss: 0.08371566236019135
2023-01-22 17:48:52.003078: step: 384/470, loss: 0.33781763911247253
2023-01-22 17:48:52.865879: step: 386/470, loss: 0.1618962287902832
2023-01-22 17:48:53.585512: step: 388/470, loss: 0.42494645714759827
2023-01-22 17:48:54.335911: step: 390/470, loss: 0.19731223583221436
2023-01-22 17:48:55.081143: step: 392/470, loss: 0.21920977532863617
2023-01-22 17:48:55.919819: step: 394/470, loss: 0.767740786075592
2023-01-22 17:48:56.716970: step: 396/470, loss: 0.29436159133911133
2023-01-22 17:48:57.492833: step: 398/470, loss: 0.1768275797367096
2023-01-22 17:48:58.179765: step: 400/470, loss: 0.27189314365386963
2023-01-22 17:48:58.929969: step: 402/470, loss: 0.6092924475669861
2023-01-22 17:48:59.681705: step: 404/470, loss: 0.31457844376564026
2023-01-22 17:49:00.540398: step: 406/470, loss: 0.18229728937149048
2023-01-22 17:49:01.282725: step: 408/470, loss: 0.24030300974845886
2023-01-22 17:49:02.067409: step: 410/470, loss: 0.2986292243003845
2023-01-22 17:49:02.872341: step: 412/470, loss: 0.3573097586631775
2023-01-22 17:49:03.591188: step: 414/470, loss: 0.25912851095199585
2023-01-22 17:49:04.374233: step: 416/470, loss: 0.42473936080932617
2023-01-22 17:49:05.158615: step: 418/470, loss: 0.1592417061328888
2023-01-22 17:49:05.912102: step: 420/470, loss: 0.18681542575359344
2023-01-22 17:49:06.611026: step: 422/470, loss: 0.7109906077384949
2023-01-22 17:49:07.365513: step: 424/470, loss: 0.18564318120479584
2023-01-22 17:49:08.163896: step: 426/470, loss: 0.2508256137371063
2023-01-22 17:49:08.922490: step: 428/470, loss: 0.8340566158294678
2023-01-22 17:49:09.713183: step: 430/470, loss: 0.2437361627817154
2023-01-22 17:49:10.467077: step: 432/470, loss: 0.5458521246910095
2023-01-22 17:49:11.327397: step: 434/470, loss: 0.4009840786457062
2023-01-22 17:49:12.070623: step: 436/470, loss: 0.2011309266090393
2023-01-22 17:49:12.820313: step: 438/470, loss: 0.20616890490055084
2023-01-22 17:49:13.539858: step: 440/470, loss: 0.3620125651359558
2023-01-22 17:49:14.324781: step: 442/470, loss: 0.2353145331144333
2023-01-22 17:49:15.080358: step: 444/470, loss: 0.6447851657867432
2023-01-22 17:49:15.812686: step: 446/470, loss: 1.2982354164123535
2023-01-22 17:49:16.633759: step: 448/470, loss: 0.16182303428649902
2023-01-22 17:49:17.417255: step: 450/470, loss: 0.9789178371429443
2023-01-22 17:49:18.185956: step: 452/470, loss: 0.23408180475234985
2023-01-22 17:49:18.943892: step: 454/470, loss: 0.44805386662483215
2023-01-22 17:49:19.669839: step: 456/470, loss: 0.24204997718334198
2023-01-22 17:49:20.428896: step: 458/470, loss: 2.4867639541625977
2023-01-22 17:49:21.212001: step: 460/470, loss: 0.21604380011558533
2023-01-22 17:49:22.013474: step: 462/470, loss: 0.11348915100097656
2023-01-22 17:49:22.680991: step: 464/470, loss: 0.6297299265861511
2023-01-22 17:49:23.473380: step: 466/470, loss: 1.2539268732070923
2023-01-22 17:49:24.214020: step: 468/470, loss: 0.3964780867099762
2023-01-22 17:49:24.999733: step: 470/470, loss: 0.3635796904563904
2023-01-22 17:49:25.844908: step: 472/470, loss: 0.15717843174934387
2023-01-22 17:49:26.581674: step: 474/470, loss: 0.17565882205963135
2023-01-22 17:49:27.421173: step: 476/470, loss: 0.3112245202064514
2023-01-22 17:49:28.204723: step: 478/470, loss: 0.18767109513282776
2023-01-22 17:49:28.940996: step: 480/470, loss: 0.5524680018424988
2023-01-22 17:49:29.678076: step: 482/470, loss: 0.2581130266189575
2023-01-22 17:49:30.374925: step: 484/470, loss: 0.27895861864089966
2023-01-22 17:49:31.121890: step: 486/470, loss: 0.42541971802711487
2023-01-22 17:49:31.773782: step: 488/470, loss: 0.23396803438663483
2023-01-22 17:49:32.475232: step: 490/470, loss: 0.8111799359321594
2023-01-22 17:49:33.177801: step: 492/470, loss: 0.5374805331230164
2023-01-22 17:49:33.951814: step: 494/470, loss: 0.1266305297613144
2023-01-22 17:49:34.671442: step: 496/470, loss: 0.5135464668273926
2023-01-22 17:49:35.457627: step: 498/470, loss: 0.19670523703098297
2023-01-22 17:49:36.098313: step: 500/470, loss: 0.3329498767852783
2023-01-22 17:49:36.861515: step: 502/470, loss: 0.09014225006103516
2023-01-22 17:49:37.563187: step: 504/470, loss: 0.15468470752239227
2023-01-22 17:49:38.274062: step: 506/470, loss: 0.9147515296936035
2023-01-22 17:49:39.003835: step: 508/470, loss: 0.2802393138408661
2023-01-22 17:49:39.877660: step: 510/470, loss: 0.30511119961738586
2023-01-22 17:49:40.590488: step: 512/470, loss: 0.20601776242256165
2023-01-22 17:49:41.304807: step: 514/470, loss: 0.6622411012649536
2023-01-22 17:49:42.101610: step: 516/470, loss: 0.30970463156700134
2023-01-22 17:49:42.781606: step: 518/470, loss: 0.18782645463943481
2023-01-22 17:49:43.481045: step: 520/470, loss: 0.3975909948348999
2023-01-22 17:49:44.243764: step: 522/470, loss: 0.2327815592288971
2023-01-22 17:49:44.998283: step: 524/470, loss: 0.09739214926958084
2023-01-22 17:49:45.759379: step: 526/470, loss: 0.8930928111076355
2023-01-22 17:49:46.559044: step: 528/470, loss: 0.365343302488327
2023-01-22 17:49:47.295445: step: 530/470, loss: 0.203633651137352
2023-01-22 17:49:48.090481: step: 532/470, loss: 1.6148757934570312
2023-01-22 17:49:48.837733: step: 534/470, loss: 0.30228936672210693
2023-01-22 17:49:49.784011: step: 536/470, loss: 0.23546025156974792
2023-01-22 17:49:50.478353: step: 538/470, loss: 0.1620427817106247
2023-01-22 17:49:51.140044: step: 540/470, loss: 0.16190826892852783
2023-01-22 17:49:51.891101: step: 542/470, loss: 0.0964878499507904
2023-01-22 17:49:52.701710: step: 544/470, loss: 0.12071750313043594
2023-01-22 17:49:53.537339: step: 546/470, loss: 0.43174058198928833
2023-01-22 17:49:54.360431: step: 548/470, loss: 1.1310662031173706
2023-01-22 17:49:55.127631: step: 550/470, loss: 0.5546995401382446
2023-01-22 17:49:56.011167: step: 552/470, loss: 0.7945947051048279
2023-01-22 17:49:56.756271: step: 554/470, loss: 0.5049540996551514
2023-01-22 17:49:57.507772: step: 556/470, loss: 0.09438646584749222
2023-01-22 17:49:58.236883: step: 558/470, loss: 0.9007434844970703
2023-01-22 17:49:58.923826: step: 560/470, loss: 0.10236416757106781
2023-01-22 17:49:59.647314: step: 562/470, loss: 0.957366406917572
2023-01-22 17:50:00.453776: step: 564/470, loss: 0.2416938692331314
2023-01-22 17:50:01.218885: step: 566/470, loss: 0.7880321145057678
2023-01-22 17:50:01.979921: step: 568/470, loss: 0.5304555296897888
2023-01-22 17:50:02.746372: step: 570/470, loss: 0.3842546045780182
2023-01-22 17:50:03.594743: step: 572/470, loss: 0.22081181406974792
2023-01-22 17:50:04.412172: step: 574/470, loss: 0.10166381299495697
2023-01-22 17:50:05.199495: step: 576/470, loss: 0.19878722727298737
2023-01-22 17:50:05.975251: step: 578/470, loss: 0.3669015169143677
2023-01-22 17:50:06.800684: step: 580/470, loss: 0.27071359753608704
2023-01-22 17:50:07.588427: step: 582/470, loss: 0.1869358867406845
2023-01-22 17:50:08.372138: step: 584/470, loss: 0.2697611451148987
2023-01-22 17:50:09.065632: step: 586/470, loss: 0.27031758427619934
2023-01-22 17:50:09.861343: step: 588/470, loss: 0.9854125380516052
2023-01-22 17:50:10.606550: step: 590/470, loss: 0.14197781682014465
2023-01-22 17:50:11.365857: step: 592/470, loss: 0.3427768051624298
2023-01-22 17:50:12.155460: step: 594/470, loss: 0.5351526141166687
2023-01-22 17:50:12.885903: step: 596/470, loss: 0.14945143461227417
2023-01-22 17:50:13.574115: step: 598/470, loss: 0.47398558259010315
2023-01-22 17:50:14.336543: step: 600/470, loss: 0.4863567650318146
2023-01-22 17:50:15.071013: step: 602/470, loss: 0.48081153631210327
2023-01-22 17:50:15.821322: step: 604/470, loss: 0.13413645327091217
2023-01-22 17:50:16.629520: step: 606/470, loss: 0.5402474403381348
2023-01-22 17:50:17.404249: step: 608/470, loss: 0.5544330477714539
2023-01-22 17:50:18.130567: step: 610/470, loss: 0.388392835855484
2023-01-22 17:50:18.864535: step: 612/470, loss: 1.0991339683532715
2023-01-22 17:50:19.679000: step: 614/470, loss: 0.35932278633117676
2023-01-22 17:50:20.454061: step: 616/470, loss: 0.26169684529304504
2023-01-22 17:50:21.231485: step: 618/470, loss: 0.15292510390281677
2023-01-22 17:50:22.111478: step: 620/470, loss: 0.503343939781189
2023-01-22 17:50:22.775340: step: 622/470, loss: 0.2210429310798645
2023-01-22 17:50:23.600437: step: 624/470, loss: 0.11323003470897675
2023-01-22 17:50:24.360336: step: 626/470, loss: 0.49351710081100464
2023-01-22 17:50:25.080739: step: 628/470, loss: 0.19296793639659882
2023-01-22 17:50:25.842007: step: 630/470, loss: 0.17127367854118347
2023-01-22 17:50:26.528798: step: 632/470, loss: 0.3556111454963684
2023-01-22 17:50:27.299219: step: 634/470, loss: 0.31057944893836975
2023-01-22 17:50:27.950351: step: 636/470, loss: 0.42370232939720154
2023-01-22 17:50:28.760805: step: 638/470, loss: 0.8841353058815002
2023-01-22 17:50:29.527948: step: 640/470, loss: 0.24589870870113373
2023-01-22 17:50:30.276092: step: 642/470, loss: 0.1649733930826187
2023-01-22 17:50:30.977507: step: 644/470, loss: 0.6155900955200195
2023-01-22 17:50:31.751765: step: 646/470, loss: 0.36966732144355774
2023-01-22 17:50:32.488882: step: 648/470, loss: 0.2079157680273056
2023-01-22 17:50:33.379342: step: 650/470, loss: 0.8073568344116211
2023-01-22 17:50:34.075852: step: 652/470, loss: 0.19634874165058136
2023-01-22 17:50:34.860919: step: 654/470, loss: 0.3249640166759491
2023-01-22 17:50:35.657694: step: 656/470, loss: 1.5049084424972534
2023-01-22 17:50:36.442487: step: 658/470, loss: 0.42330726981163025
2023-01-22 17:50:37.193362: step: 660/470, loss: 0.20834825932979584
2023-01-22 17:50:37.973571: step: 662/470, loss: 0.4067968428134918
2023-01-22 17:50:38.663535: step: 664/470, loss: 0.3112955093383789
2023-01-22 17:50:39.421490: step: 666/470, loss: 1.358984351158142
2023-01-22 17:50:40.197374: step: 668/470, loss: 0.25829464197158813
2023-01-22 17:50:40.979755: step: 670/470, loss: 0.4780522286891937
2023-01-22 17:50:41.707637: step: 672/470, loss: 0.18391302227973938
2023-01-22 17:50:42.523184: step: 674/470, loss: 0.32501521706581116
2023-01-22 17:50:43.431454: step: 676/470, loss: 0.11137870699167252
2023-01-22 17:50:44.159576: step: 678/470, loss: 1.4713650941848755
2023-01-22 17:50:45.024727: step: 680/470, loss: 1.0248942375183105
2023-01-22 17:50:45.801985: step: 682/470, loss: 0.17500053346157074
2023-01-22 17:50:46.556080: step: 684/470, loss: 0.5887848734855652
2023-01-22 17:50:47.291916: step: 686/470, loss: 0.3135591149330139
2023-01-22 17:50:48.054854: step: 688/470, loss: 0.47807666659355164
2023-01-22 17:50:48.835517: step: 690/470, loss: 0.15201377868652344
2023-01-22 17:50:49.686449: step: 692/470, loss: 0.1818476915359497
2023-01-22 17:50:50.414639: step: 694/470, loss: 0.15883833169937134
2023-01-22 17:50:51.219253: step: 696/470, loss: 0.2723800539970398
2023-01-22 17:50:52.091685: step: 698/470, loss: 0.9609336853027344
2023-01-22 17:50:52.774076: step: 700/470, loss: 0.14401142299175262
2023-01-22 17:50:53.492898: step: 702/470, loss: 0.3710044026374817
2023-01-22 17:50:54.292074: step: 704/470, loss: 0.49077916145324707
2023-01-22 17:50:55.061434: step: 706/470, loss: 0.19224616885185242
2023-01-22 17:50:55.757865: step: 708/470, loss: 0.09910887479782104
2023-01-22 17:50:56.633846: step: 710/470, loss: 2.2329654693603516
2023-01-22 17:50:57.389604: step: 712/470, loss: 0.3099704384803772
2023-01-22 17:50:58.061151: step: 714/470, loss: 0.07138052582740784
2023-01-22 17:50:58.862702: step: 716/470, loss: 0.21385283768177032
2023-01-22 17:50:59.578210: step: 718/470, loss: 0.6778049468994141
2023-01-22 17:51:00.359536: step: 720/470, loss: 0.43242332339286804
2023-01-22 17:51:01.160814: step: 722/470, loss: 0.4446261525154114
2023-01-22 17:51:01.917798: step: 724/470, loss: 0.2377616912126541
2023-01-22 17:51:02.670230: step: 726/470, loss: 0.1549036204814911
2023-01-22 17:51:03.425163: step: 728/470, loss: 0.25162452459335327
2023-01-22 17:51:04.134422: step: 730/470, loss: 0.6771296262741089
2023-01-22 17:51:04.926863: step: 732/470, loss: 0.7284178137779236
2023-01-22 17:51:05.683811: step: 734/470, loss: 0.8691809177398682
2023-01-22 17:51:06.461230: step: 736/470, loss: 0.19968397915363312
2023-01-22 17:51:07.203822: step: 738/470, loss: 0.1259831339120865
2023-01-22 17:51:08.006142: step: 740/470, loss: 0.10791204124689102
2023-01-22 17:51:08.761249: step: 742/470, loss: 0.31472277641296387
2023-01-22 17:51:09.521266: step: 744/470, loss: 0.19977986812591553
2023-01-22 17:51:10.244752: step: 746/470, loss: 0.15267623960971832
2023-01-22 17:51:11.010676: step: 748/470, loss: 2.1145780086517334
2023-01-22 17:51:11.723088: step: 750/470, loss: 0.2913758456707001
2023-01-22 17:51:12.506154: step: 752/470, loss: 0.16115057468414307
2023-01-22 17:51:13.259075: step: 754/470, loss: 0.1917055994272232
2023-01-22 17:51:14.039608: step: 756/470, loss: 0.13388597965240479
2023-01-22 17:51:14.778378: step: 758/470, loss: 0.8417869210243225
2023-01-22 17:51:15.597648: step: 760/470, loss: 0.259040892124176
2023-01-22 17:51:16.425809: step: 762/470, loss: 1.860278606414795
2023-01-22 17:51:17.249442: step: 764/470, loss: 0.15627700090408325
2023-01-22 17:51:17.966801: step: 766/470, loss: 0.2632465958595276
2023-01-22 17:51:18.659002: step: 768/470, loss: 0.5329182147979736
2023-01-22 17:51:19.401112: step: 770/470, loss: 0.17463798820972443
2023-01-22 17:51:20.137312: step: 772/470, loss: 0.3025292158126831
2023-01-22 17:51:20.935671: step: 774/470, loss: 0.0922599583864212
2023-01-22 17:51:21.769032: step: 776/470, loss: 0.17804045975208282
2023-01-22 17:51:22.466721: step: 778/470, loss: 0.5846086740493774
2023-01-22 17:51:23.239248: step: 780/470, loss: 1.0991511344909668
2023-01-22 17:51:23.940771: step: 782/470, loss: 0.20432426035404205
2023-01-22 17:51:24.588733: step: 784/470, loss: 0.1008855476975441
2023-01-22 17:51:25.355935: step: 786/470, loss: 1.1069185733795166
2023-01-22 17:51:26.140283: step: 788/470, loss: 0.32851848006248474
2023-01-22 17:51:26.895861: step: 790/470, loss: 0.3457392454147339
2023-01-22 17:51:27.633053: step: 792/470, loss: 0.14442162215709686
2023-01-22 17:51:28.396549: step: 794/470, loss: 0.12679028511047363
2023-01-22 17:51:29.144596: step: 796/470, loss: 0.12389878928661346
2023-01-22 17:51:29.853638: step: 798/470, loss: 0.4223572909832001
2023-01-22 17:51:30.632669: step: 800/470, loss: 0.9779374599456787
2023-01-22 17:51:31.368081: step: 802/470, loss: 0.849580705165863
2023-01-22 17:51:32.069589: step: 804/470, loss: 0.32323935627937317
2023-01-22 17:51:32.829698: step: 806/470, loss: 0.3388105034828186
2023-01-22 17:51:33.598529: step: 808/470, loss: 0.7310128211975098
2023-01-22 17:51:34.411305: step: 810/470, loss: 0.24826985597610474
2023-01-22 17:51:35.185352: step: 812/470, loss: 0.2552504539489746
2023-01-22 17:51:35.948388: step: 814/470, loss: 0.2834188938140869
2023-01-22 17:51:36.678371: step: 816/470, loss: 0.6483306884765625
2023-01-22 17:51:37.414677: step: 818/470, loss: 0.4713938236236572
2023-01-22 17:51:38.218524: step: 820/470, loss: 0.26083284616470337
2023-01-22 17:51:38.978849: step: 822/470, loss: 0.20542579889297485
2023-01-22 17:51:39.697123: step: 824/470, loss: 0.2176228165626526
2023-01-22 17:51:40.401030: step: 826/470, loss: 0.2208702117204666
2023-01-22 17:51:41.248932: step: 828/470, loss: 0.27593034505844116
2023-01-22 17:51:41.962741: step: 830/470, loss: 0.4739680588245392
2023-01-22 17:51:42.712755: step: 832/470, loss: 0.2514054477214813
2023-01-22 17:51:43.509262: step: 834/470, loss: 0.250079482793808
2023-01-22 17:51:44.263833: step: 836/470, loss: 0.17073297500610352
2023-01-22 17:51:45.078163: step: 838/470, loss: 1.1584669351577759
2023-01-22 17:51:45.822925: step: 840/470, loss: 0.38292911648750305
2023-01-22 17:51:46.563651: step: 842/470, loss: 0.2206546664237976
2023-01-22 17:51:47.352153: step: 844/470, loss: 0.49227169156074524
2023-01-22 17:51:48.174241: step: 846/470, loss: 0.2030370980501175
2023-01-22 17:51:48.961058: step: 848/470, loss: 0.5499109625816345
2023-01-22 17:51:49.805790: step: 850/470, loss: 0.3381698727607727
2023-01-22 17:51:50.500665: step: 852/470, loss: 0.6527577638626099
2023-01-22 17:51:51.311899: step: 854/470, loss: 0.22261139750480652
2023-01-22 17:51:52.180848: step: 856/470, loss: 0.6786369681358337
2023-01-22 17:51:52.932623: step: 858/470, loss: 0.3246194124221802
2023-01-22 17:51:53.788428: step: 860/470, loss: 0.17136085033416748
2023-01-22 17:51:54.543852: step: 862/470, loss: 0.7740350365638733
2023-01-22 17:51:55.432819: step: 864/470, loss: 6.283660888671875
2023-01-22 17:51:56.175355: step: 866/470, loss: 0.3030953109264374
2023-01-22 17:51:57.051984: step: 868/470, loss: 0.5647780299186707
2023-01-22 17:51:57.770355: step: 870/470, loss: 0.3866567313671112
2023-01-22 17:51:58.515975: step: 872/470, loss: 1.285661220550537
2023-01-22 17:51:59.242548: step: 874/470, loss: 0.18321466445922852
2023-01-22 17:51:59.981197: step: 876/470, loss: 0.2706562876701355
2023-01-22 17:52:00.788490: step: 878/470, loss: 0.30584192276000977
2023-01-22 17:52:01.570454: step: 880/470, loss: 0.143959641456604
2023-01-22 17:52:02.386762: step: 882/470, loss: 0.4257970452308655
2023-01-22 17:52:03.156167: step: 884/470, loss: 0.32551464438438416
2023-01-22 17:52:03.952494: step: 886/470, loss: 0.21082256734371185
2023-01-22 17:52:04.744754: step: 888/470, loss: 0.2381884753704071
2023-01-22 17:52:05.533954: step: 890/470, loss: 0.30021804571151733
2023-01-22 17:52:06.379066: step: 892/470, loss: 0.33029264211654663
2023-01-22 17:52:07.181141: step: 894/470, loss: 0.11910691857337952
2023-01-22 17:52:07.925896: step: 896/470, loss: 0.3467719554901123
2023-01-22 17:52:08.691778: step: 898/470, loss: 0.7879258394241333
2023-01-22 17:52:09.448883: step: 900/470, loss: 0.2893523871898651
2023-01-22 17:52:10.222544: step: 902/470, loss: 0.25279688835144043
2023-01-22 17:52:10.924456: step: 904/470, loss: 0.15351781249046326
2023-01-22 17:52:11.632051: step: 906/470, loss: 0.41283392906188965
2023-01-22 17:52:12.369232: step: 908/470, loss: 0.14755499362945557
2023-01-22 17:52:13.114484: step: 910/470, loss: 0.07284556329250336
2023-01-22 17:52:13.841885: step: 912/470, loss: 0.21138407289981842
2023-01-22 17:52:14.725849: step: 914/470, loss: 0.503731906414032
2023-01-22 17:52:15.499881: step: 916/470, loss: 0.367249995470047
2023-01-22 17:52:16.196991: step: 918/470, loss: 0.2869451344013214
2023-01-22 17:52:16.958991: step: 920/470, loss: 0.5139609575271606
2023-01-22 17:52:17.701856: step: 922/470, loss: 0.4172641932964325
2023-01-22 17:52:18.402189: step: 924/470, loss: 0.1905202567577362
2023-01-22 17:52:19.184358: step: 926/470, loss: 0.16458773612976074
2023-01-22 17:52:19.992005: step: 928/470, loss: 0.20133328437805176
2023-01-22 17:52:20.706502: step: 930/470, loss: 0.2865738272666931
2023-01-22 17:52:21.432735: step: 932/470, loss: 0.10317887365818024
2023-01-22 17:52:22.107898: step: 934/470, loss: 0.2089749574661255
2023-01-22 17:52:22.875884: step: 936/470, loss: 0.7139807939529419
2023-01-22 17:52:23.553306: step: 938/470, loss: 5.944061279296875
2023-01-22 17:52:24.340468: step: 940/470, loss: 0.49773871898651123
2023-01-22 17:52:25.001770: step: 942/470, loss: 0.29733988642692566
==================================================
Loss: 0.424
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2720285818408996, 'r': 0.3541017213336948, 'f1': 0.3076860793781651}, 'combined': 0.22671605848917428, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.319785163193168, 'r': 0.3627918133824509, 'f1': 0.33993364332235054}, 'combined': 0.2367697018165626, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26970405278248755, 'r': 0.3546582705469903, 'f1': 0.30640148947256374}, 'combined': 0.22576951855873117, 'epoch': 9}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3172264650103097, 'r': 0.3602350530549767, 'f1': 0.337365560717853}, 'combined': 0.23498098756467375, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2503801155740811, 'r': 0.3582288560585525, 'f1': 0.2947488011598082}, 'combined': 0.217183327170385, 'epoch': 9}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3054672020186251, 'r': 0.36802923473974736, 'f1': 0.33384248070592}, 'combined': 0.23252710098919802, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.19333333333333333, 'r': 0.4142857142857143, 'f1': 0.2636363636363636}, 'combined': 0.17575757575757572, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25, 'r': 0.5, 'f1': 0.3333333333333333}, 'combined': 0.16666666666666666, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25, 'r': 0.25862068965517243, 'f1': 0.25423728813559326}, 'combined': 0.16949152542372883, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3049308236808237, 'r': 0.3211320818650041, 'f1': 0.3128218246633219}, 'combined': 0.23050029185718457, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32065206847366756, 'r': 0.3490174437617227, 'f1': 0.3342340161254067}, 'combined': 0.23279981222665144, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24523809523809523, 'r': 0.31530612244897954, 'f1': 0.27589285714285716}, 'combined': 0.18392857142857144, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26474047961800956, 'r': 0.3240182340675829, 'f1': 0.29139523780480575}, 'combined': 0.2147122804877516, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32541475117674507, 'r': 0.34573363573629207, 'f1': 0.33526661835256644}, 'combined': 0.23351903765850401, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2722222222222222, 'r': 0.532608695652174, 'f1': 0.36029411764705876}, 'combined': 0.18014705882352938, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27751515331590204, 'r': 0.3164831255082678, 'f1': 0.29572093465045596}, 'combined': 0.2178996360582307, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3162120582663088, 'r': 0.3614719974417939, 'f1': 0.3373306583029202}, 'combined': 0.23495667742491955, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 8}
******************************
Epoch: 10
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 17:55:08.797906: step: 2/470, loss: 0.056591589003801346
2023-01-22 17:55:09.557241: step: 4/470, loss: 0.13280236721038818
2023-01-22 17:55:10.291229: step: 6/470, loss: 0.4893929958343506
2023-01-22 17:55:10.979047: step: 8/470, loss: 0.2868712842464447
2023-01-22 17:55:11.708062: step: 10/470, loss: 0.157928004860878
2023-01-22 17:55:12.416697: step: 12/470, loss: 0.7920506000518799
2023-01-22 17:55:13.198954: step: 14/470, loss: 0.37678074836730957
2023-01-22 17:55:13.986077: step: 16/470, loss: 0.29826444387435913
2023-01-22 17:55:14.704516: step: 18/470, loss: 0.0674176812171936
2023-01-22 17:55:15.415572: step: 20/470, loss: 0.08113688230514526
2023-01-22 17:55:16.169027: step: 22/470, loss: 0.13426075875759125
2023-01-22 17:55:16.914706: step: 24/470, loss: 0.1328933835029602
2023-01-22 17:55:17.644401: step: 26/470, loss: 0.06381936371326447
2023-01-22 17:55:18.534787: step: 28/470, loss: 0.07034029066562653
2023-01-22 17:55:19.272578: step: 30/470, loss: 0.06103328615427017
2023-01-22 17:55:20.087451: step: 32/470, loss: 0.045456431806087494
2023-01-22 17:55:20.833478: step: 34/470, loss: 0.373674601316452
2023-01-22 17:55:21.630874: step: 36/470, loss: 0.04646005108952522
2023-01-22 17:55:22.451595: step: 38/470, loss: 0.5150260329246521
2023-01-22 17:55:23.237939: step: 40/470, loss: 0.3609604835510254
2023-01-22 17:55:23.981166: step: 42/470, loss: 0.34102901816368103
2023-01-22 17:55:24.787412: step: 44/470, loss: 0.293104887008667
2023-01-22 17:55:25.533571: step: 46/470, loss: 0.2512171268463135
2023-01-22 17:55:26.309410: step: 48/470, loss: 0.2921146750450134
2023-01-22 17:55:27.165006: step: 50/470, loss: 0.14088846743106842
2023-01-22 17:55:27.810625: step: 52/470, loss: 0.3724920451641083
2023-01-22 17:55:28.553463: step: 54/470, loss: 0.2027990221977234
2023-01-22 17:55:29.262488: step: 56/470, loss: 0.19799435138702393
2023-01-22 17:55:30.043297: step: 58/470, loss: 0.3948134779930115
2023-01-22 17:55:30.890925: step: 60/470, loss: 0.08492279052734375
2023-01-22 17:55:31.595656: step: 62/470, loss: 0.12444708496332169
2023-01-22 17:55:32.334027: step: 64/470, loss: 0.08406122028827667
2023-01-22 17:55:33.079093: step: 66/470, loss: 5.688138008117676
2023-01-22 17:55:33.814492: step: 68/470, loss: 0.10036779195070267
2023-01-22 17:55:34.537071: step: 70/470, loss: 0.14819800853729248
2023-01-22 17:55:35.318574: step: 72/470, loss: 0.4329559803009033
2023-01-22 17:55:36.057742: step: 74/470, loss: 0.3488907814025879
2023-01-22 17:55:36.762337: step: 76/470, loss: 0.3759381175041199
2023-01-22 17:55:37.527268: step: 78/470, loss: 0.49098092317581177
2023-01-22 17:55:38.237250: step: 80/470, loss: 0.5063804984092712
2023-01-22 17:55:39.037986: step: 82/470, loss: 0.14004996418952942
2023-01-22 17:55:39.826337: step: 84/470, loss: 0.09356193989515305
2023-01-22 17:55:40.584914: step: 86/470, loss: 0.17746534943580627
2023-01-22 17:55:41.388580: step: 88/470, loss: 0.09610351175069809
2023-01-22 17:55:42.157277: step: 90/470, loss: 0.14981889724731445
2023-01-22 17:55:42.889694: step: 92/470, loss: 1.6448625326156616
2023-01-22 17:55:43.668921: step: 94/470, loss: 0.2239532321691513
2023-01-22 17:55:44.371022: step: 96/470, loss: 0.1338728666305542
2023-01-22 17:55:45.168837: step: 98/470, loss: 0.2755134701728821
2023-01-22 17:55:45.943370: step: 100/470, loss: 0.18865349888801575
2023-01-22 17:55:46.711727: step: 102/470, loss: 0.06774507462978363
2023-01-22 17:55:47.503539: step: 104/470, loss: 0.8064208030700684
2023-01-22 17:55:48.273981: step: 106/470, loss: 0.08489122241735458
2023-01-22 17:55:49.029970: step: 108/470, loss: 0.08381538838148117
2023-01-22 17:55:49.773492: step: 110/470, loss: 0.3395574390888214
2023-01-22 17:55:50.641820: step: 112/470, loss: 0.15705344080924988
2023-01-22 17:55:51.353799: step: 114/470, loss: 0.4517096281051636
2023-01-22 17:55:52.064895: step: 116/470, loss: 0.1848120093345642
2023-01-22 17:55:52.773931: step: 118/470, loss: 0.2923411726951599
2023-01-22 17:55:53.476739: step: 120/470, loss: 0.24967914819717407
2023-01-22 17:55:54.206976: step: 122/470, loss: 0.8194922804832458
2023-01-22 17:55:55.010160: step: 124/470, loss: 0.44352638721466064
2023-01-22 17:55:55.804059: step: 126/470, loss: 0.319720059633255
2023-01-22 17:55:56.559647: step: 128/470, loss: 0.652948796749115
2023-01-22 17:55:57.346593: step: 130/470, loss: 0.6255174279212952
2023-01-22 17:55:58.114355: step: 132/470, loss: 0.5446348190307617
2023-01-22 17:55:58.832818: step: 134/470, loss: 0.3582460284233093
2023-01-22 17:55:59.658277: step: 136/470, loss: 0.655910074710846
2023-01-22 17:56:00.455272: step: 138/470, loss: 0.08800873160362244
2023-01-22 17:56:01.149811: step: 140/470, loss: 0.09775952994823456
2023-01-22 17:56:01.887133: step: 142/470, loss: 0.6266007423400879
2023-01-22 17:56:02.666519: step: 144/470, loss: 0.3636000454425812
2023-01-22 17:56:03.412626: step: 146/470, loss: 0.1658439189195633
2023-01-22 17:56:04.144517: step: 148/470, loss: 0.059976786375045776
2023-01-22 17:56:04.847531: step: 150/470, loss: 0.11647554486989975
2023-01-22 17:56:05.594996: step: 152/470, loss: 0.14295542240142822
2023-01-22 17:56:06.414680: step: 154/470, loss: 0.7250072956085205
2023-01-22 17:56:07.128437: step: 156/470, loss: 0.12420438975095749
2023-01-22 17:56:07.895341: step: 158/470, loss: 0.22176730632781982
2023-01-22 17:56:08.693220: step: 160/470, loss: 0.13311302661895752
2023-01-22 17:56:09.421169: step: 162/470, loss: 0.1882036328315735
2023-01-22 17:56:10.160641: step: 164/470, loss: 0.3161405920982361
2023-01-22 17:56:10.929015: step: 166/470, loss: 0.38165828585624695
2023-01-22 17:56:11.838727: step: 168/470, loss: 0.5611687302589417
2023-01-22 17:56:12.594303: step: 170/470, loss: 0.7891055941581726
2023-01-22 17:56:13.342255: step: 172/470, loss: 0.2864110469818115
2023-01-22 17:56:14.086861: step: 174/470, loss: 1.51108717918396
2023-01-22 17:56:14.819652: step: 176/470, loss: 0.3315257430076599
2023-01-22 17:56:15.593770: step: 178/470, loss: 0.8074526190757751
2023-01-22 17:56:16.311993: step: 180/470, loss: 0.13533882796764374
2023-01-22 17:56:16.998359: step: 182/470, loss: 0.6222794055938721
2023-01-22 17:56:17.733286: step: 184/470, loss: 1.3589999675750732
2023-01-22 17:56:18.534070: step: 186/470, loss: 0.250261515378952
2023-01-22 17:56:19.330091: step: 188/470, loss: 0.1996300369501114
2023-01-22 17:56:20.106070: step: 190/470, loss: 0.8840703368186951
2023-01-22 17:56:20.824492: step: 192/470, loss: 0.5001525282859802
2023-01-22 17:56:21.643845: step: 194/470, loss: 0.20161223411560059
2023-01-22 17:56:22.391940: step: 196/470, loss: 0.5042540431022644
2023-01-22 17:56:23.122376: step: 198/470, loss: 0.28795769810676575
2023-01-22 17:56:23.983964: step: 200/470, loss: 0.6410402655601501
2023-01-22 17:56:24.723306: step: 202/470, loss: 0.2731340527534485
2023-01-22 17:56:25.482916: step: 204/470, loss: 0.12334098666906357
2023-01-22 17:56:26.190705: step: 206/470, loss: 0.22625799477100372
2023-01-22 17:56:26.913254: step: 208/470, loss: 0.5543537735939026
2023-01-22 17:56:27.668553: step: 210/470, loss: 0.2280716747045517
2023-01-22 17:56:28.442520: step: 212/470, loss: 0.08557216078042984
2023-01-22 17:56:29.197084: step: 214/470, loss: 0.18337619304656982
2023-01-22 17:56:29.965983: step: 216/470, loss: 1.1990138292312622
2023-01-22 17:56:30.703535: step: 218/470, loss: 0.13386143743991852
2023-01-22 17:56:31.467164: step: 220/470, loss: 0.5193535685539246
2023-01-22 17:56:32.319026: step: 222/470, loss: 0.17291080951690674
2023-01-22 17:56:33.138230: step: 224/470, loss: 0.2032584249973297
2023-01-22 17:56:33.963538: step: 226/470, loss: 0.6475588083267212
2023-01-22 17:56:34.700099: step: 228/470, loss: 0.26753678917884827
2023-01-22 17:56:35.541383: step: 230/470, loss: 0.46687716245651245
2023-01-22 17:56:36.351254: step: 232/470, loss: 0.2332172989845276
2023-01-22 17:56:37.180744: step: 234/470, loss: 0.3625449240207672
2023-01-22 17:56:37.942378: step: 236/470, loss: 13.1072359085083
2023-01-22 17:56:38.651808: step: 238/470, loss: 0.16786223649978638
2023-01-22 17:56:39.397827: step: 240/470, loss: 0.1498054563999176
2023-01-22 17:56:40.155041: step: 242/470, loss: 0.7497914433479309
2023-01-22 17:56:40.819319: step: 244/470, loss: 0.7256143093109131
2023-01-22 17:56:41.623871: step: 246/470, loss: 0.9502539038658142
2023-01-22 17:56:42.417546: step: 248/470, loss: 0.6548596620559692
2023-01-22 17:56:43.197968: step: 250/470, loss: 0.21729148924350739
2023-01-22 17:56:43.901636: step: 252/470, loss: 0.17379331588745117
2023-01-22 17:56:44.665314: step: 254/470, loss: 0.10878202319145203
2023-01-22 17:56:45.386041: step: 256/470, loss: 0.342523455619812
2023-01-22 17:56:46.259829: step: 258/470, loss: 1.1544556617736816
2023-01-22 17:56:46.970995: step: 260/470, loss: 0.23245486617088318
2023-01-22 17:56:47.753887: step: 262/470, loss: 0.543807864189148
2023-01-22 17:56:48.537925: step: 264/470, loss: 0.154671311378479
2023-01-22 17:56:49.320544: step: 266/470, loss: 0.2436520904302597
2023-01-22 17:56:50.047165: step: 268/470, loss: 0.11845968663692474
2023-01-22 17:56:50.826769: step: 270/470, loss: 0.5449745655059814
2023-01-22 17:56:51.514284: step: 272/470, loss: 0.3452926278114319
2023-01-22 17:56:52.254386: step: 274/470, loss: 0.2843412756919861
2023-01-22 17:56:53.020165: step: 276/470, loss: 0.2615320682525635
2023-01-22 17:56:53.697726: step: 278/470, loss: 0.12062683701515198
2023-01-22 17:56:54.500154: step: 280/470, loss: 0.08838797360658646
2023-01-22 17:56:55.258240: step: 282/470, loss: 0.5510808229446411
2023-01-22 17:56:56.069708: step: 284/470, loss: 0.18408583104610443
2023-01-22 17:56:56.849733: step: 286/470, loss: 0.3631865084171295
2023-01-22 17:56:57.648008: step: 288/470, loss: 0.1815035343170166
2023-01-22 17:56:58.424886: step: 290/470, loss: 0.13083362579345703
2023-01-22 17:56:59.155441: step: 292/470, loss: 0.18467651307582855
2023-01-22 17:56:59.907842: step: 294/470, loss: 0.28844454884529114
2023-01-22 17:57:00.631187: step: 296/470, loss: 0.11280845105648041
2023-01-22 17:57:01.458030: step: 298/470, loss: 0.1065002903342247
2023-01-22 17:57:02.261883: step: 300/470, loss: 0.13871590793132782
2023-01-22 17:57:02.986970: step: 302/470, loss: 0.7692720890045166
2023-01-22 17:57:03.772731: step: 304/470, loss: 0.42822524905204773
2023-01-22 17:57:04.536767: step: 306/470, loss: 0.17703254520893097
2023-01-22 17:57:05.385529: step: 308/470, loss: 0.6865633130073547
2023-01-22 17:57:06.186517: step: 310/470, loss: 0.17033447325229645
2023-01-22 17:57:06.963384: step: 312/470, loss: 0.1849544495344162
2023-01-22 17:57:07.822723: step: 314/470, loss: 0.5009557604789734
2023-01-22 17:57:08.654666: step: 316/470, loss: 0.1985601931810379
2023-01-22 17:57:09.400663: step: 318/470, loss: 0.7720727920532227
2023-01-22 17:57:10.154181: step: 320/470, loss: 0.5260408520698547
2023-01-22 17:57:10.962327: step: 322/470, loss: 0.5189958810806274
2023-01-22 17:57:11.870261: step: 324/470, loss: 0.34944188594818115
2023-01-22 17:57:12.593624: step: 326/470, loss: 0.309198260307312
2023-01-22 17:57:13.355732: step: 328/470, loss: 1.9898673295974731
2023-01-22 17:57:14.084998: step: 330/470, loss: 0.07750724256038666
2023-01-22 17:57:14.831073: step: 332/470, loss: 0.26930928230285645
2023-01-22 17:57:15.598210: step: 334/470, loss: 0.3827114403247833
2023-01-22 17:57:16.298469: step: 336/470, loss: 0.18784800171852112
2023-01-22 17:57:17.097943: step: 338/470, loss: 0.5030959844589233
2023-01-22 17:57:17.774132: step: 340/470, loss: 0.17444992065429688
2023-01-22 17:57:18.705468: step: 342/470, loss: 0.16230079531669617
2023-01-22 17:57:19.518312: step: 344/470, loss: 0.7461163997650146
2023-01-22 17:57:20.266955: step: 346/470, loss: 0.3461681008338928
2023-01-22 17:57:21.091323: step: 348/470, loss: 0.9509586691856384
2023-01-22 17:57:21.854242: step: 350/470, loss: 0.23319120705127716
2023-01-22 17:57:22.599886: step: 352/470, loss: 0.2624581456184387
2023-01-22 17:57:23.363973: step: 354/470, loss: 0.09867286682128906
2023-01-22 17:57:24.083251: step: 356/470, loss: 0.3626404404640198
2023-01-22 17:57:24.900309: step: 358/470, loss: 0.1559712439775467
2023-01-22 17:57:25.570592: step: 360/470, loss: 0.2118682861328125
2023-01-22 17:57:26.309661: step: 362/470, loss: 0.1414262056350708
2023-01-22 17:57:27.022351: step: 364/470, loss: 0.21667654812335968
2023-01-22 17:57:27.808012: step: 366/470, loss: 0.36082273721694946
2023-01-22 17:57:28.558481: step: 368/470, loss: 0.12949353456497192
2023-01-22 17:57:29.321394: step: 370/470, loss: 1.4123237133026123
2023-01-22 17:57:30.010053: step: 372/470, loss: 0.3567815124988556
2023-01-22 17:57:30.817018: step: 374/470, loss: 0.958263635635376
2023-01-22 17:57:31.549392: step: 376/470, loss: 0.40245184302330017
2023-01-22 17:57:32.295130: step: 378/470, loss: 0.412080854177475
2023-01-22 17:57:33.058836: step: 380/470, loss: 0.02421180158853531
2023-01-22 17:57:33.861601: step: 382/470, loss: 0.1654946208000183
2023-01-22 17:57:34.740172: step: 384/470, loss: 0.12343335151672363
2023-01-22 17:57:35.487217: step: 386/470, loss: 0.1281142681837082
2023-01-22 17:57:36.201875: step: 388/470, loss: 0.36397942900657654
2023-01-22 17:57:37.104806: step: 390/470, loss: 0.5486847162246704
2023-01-22 17:57:37.819124: step: 392/470, loss: 0.3194306790828705
2023-01-22 17:57:38.581875: step: 394/470, loss: 0.061125390231609344
2023-01-22 17:57:39.349053: step: 396/470, loss: 0.21372345089912415
2023-01-22 17:57:40.074393: step: 398/470, loss: 0.38437792658805847
2023-01-22 17:57:40.868965: step: 400/470, loss: 0.1892595738172531
2023-01-22 17:57:41.578988: step: 402/470, loss: 0.3131447732448578
2023-01-22 17:57:42.458508: step: 404/470, loss: 0.12467707693576813
2023-01-22 17:57:43.211561: step: 406/470, loss: 0.18171878159046173
2023-01-22 17:57:43.949958: step: 408/470, loss: 0.41719669103622437
2023-01-22 17:57:44.730044: step: 410/470, loss: 1.214868426322937
2023-01-22 17:57:45.485544: step: 412/470, loss: 0.30766603350639343
2023-01-22 17:57:46.148356: step: 414/470, loss: 0.28935831785202026
2023-01-22 17:57:46.902781: step: 416/470, loss: 0.27082717418670654
2023-01-22 17:57:47.635115: step: 418/470, loss: 0.17194396257400513
2023-01-22 17:57:48.471547: step: 420/470, loss: 0.36183246970176697
2023-01-22 17:57:49.304977: step: 422/470, loss: 0.4918966591358185
2023-01-22 17:57:50.109452: step: 424/470, loss: 0.5111696720123291
2023-01-22 17:57:50.859510: step: 426/470, loss: 2.1021931171417236
2023-01-22 17:57:51.602954: step: 428/470, loss: 0.24027954041957855
2023-01-22 17:57:52.321371: step: 430/470, loss: 0.47709715366363525
2023-01-22 17:57:53.150398: step: 432/470, loss: 0.3914461135864258
2023-01-22 17:57:53.798839: step: 434/470, loss: 0.26286399364471436
2023-01-22 17:57:54.562478: step: 436/470, loss: 0.21852940320968628
2023-01-22 17:57:55.323188: step: 438/470, loss: 0.1935357004404068
2023-01-22 17:57:56.183566: step: 440/470, loss: 0.21522024273872375
2023-01-22 17:57:56.968143: step: 442/470, loss: 6.902156829833984
2023-01-22 17:57:57.828940: step: 444/470, loss: 0.3409741222858429
2023-01-22 17:57:58.569334: step: 446/470, loss: 0.24355652928352356
2023-01-22 17:57:59.336716: step: 448/470, loss: 0.6423745155334473
2023-01-22 17:58:00.137034: step: 450/470, loss: 0.24495574831962585
2023-01-22 17:58:00.949234: step: 452/470, loss: 0.22389310598373413
2023-01-22 17:58:01.732678: step: 454/470, loss: 0.3068379759788513
2023-01-22 17:58:02.456156: step: 456/470, loss: 0.11338848620653152
2023-01-22 17:58:03.200948: step: 458/470, loss: 0.29847270250320435
2023-01-22 17:58:03.957454: step: 460/470, loss: 0.42329713702201843
2023-01-22 17:58:04.659744: step: 462/470, loss: 0.046367011964321136
2023-01-22 17:58:05.390971: step: 464/470, loss: 0.3115167021751404
2023-01-22 17:58:06.197848: step: 466/470, loss: 0.22372061014175415
2023-01-22 17:58:06.884573: step: 468/470, loss: 0.15685810148715973
2023-01-22 17:58:07.733583: step: 470/470, loss: 0.340934157371521
2023-01-22 17:58:08.573040: step: 472/470, loss: 0.3756090998649597
2023-01-22 17:58:09.376325: step: 474/470, loss: 0.4003685712814331
2023-01-22 17:58:10.090529: step: 476/470, loss: 0.565597414970398
2023-01-22 17:58:10.829615: step: 478/470, loss: 0.35876619815826416
2023-01-22 17:58:11.589415: step: 480/470, loss: 0.10507578402757645
2023-01-22 17:58:12.272570: step: 482/470, loss: 0.12312311679124832
2023-01-22 17:58:13.023930: step: 484/470, loss: 0.07300717383623123
2023-01-22 17:58:13.772660: step: 486/470, loss: 0.5644948482513428
2023-01-22 17:58:14.526100: step: 488/470, loss: 0.20122499763965607
2023-01-22 17:58:15.344517: step: 490/470, loss: 0.25764524936676025
2023-01-22 17:58:16.114760: step: 492/470, loss: 0.843420684337616
2023-01-22 17:58:16.870323: step: 494/470, loss: 0.22662875056266785
2023-01-22 17:58:17.644650: step: 496/470, loss: 0.37807315587997437
2023-01-22 17:58:18.415906: step: 498/470, loss: 0.15613622963428497
2023-01-22 17:58:19.176045: step: 500/470, loss: 0.20546023547649384
2023-01-22 17:58:19.992906: step: 502/470, loss: 0.26250770688056946
2023-01-22 17:58:20.770427: step: 504/470, loss: 0.5560357570648193
2023-01-22 17:58:21.564303: step: 506/470, loss: 0.2005891352891922
2023-01-22 17:58:22.334318: step: 508/470, loss: 0.08451083302497864
2023-01-22 17:58:23.037258: step: 510/470, loss: 0.09619811177253723
2023-01-22 17:58:23.752496: step: 512/470, loss: 1.73138427734375
2023-01-22 17:58:24.482042: step: 514/470, loss: 0.9232888221740723
2023-01-22 17:58:25.246726: step: 516/470, loss: 0.4726581573486328
2023-01-22 17:58:25.960175: step: 518/470, loss: 0.1541184037923813
2023-01-22 17:58:26.739264: step: 520/470, loss: 0.1253805309534073
2023-01-22 17:58:27.608215: step: 522/470, loss: 0.6628063321113586
2023-01-22 17:58:28.375029: step: 524/470, loss: 1.1210182905197144
2023-01-22 17:58:29.174012: step: 526/470, loss: 0.4437292218208313
2023-01-22 17:58:29.964592: step: 528/470, loss: 1.0097692012786865
2023-01-22 17:58:30.697613: step: 530/470, loss: 0.398298054933548
2023-01-22 17:58:31.416241: step: 532/470, loss: 0.1273142546415329
2023-01-22 17:58:32.168900: step: 534/470, loss: 0.3876824378967285
2023-01-22 17:58:33.015708: step: 536/470, loss: 0.31943345069885254
2023-01-22 17:58:33.784118: step: 538/470, loss: 0.5478048920631409
2023-01-22 17:58:34.464777: step: 540/470, loss: 0.06618456542491913
2023-01-22 17:58:35.226231: step: 542/470, loss: 0.14831160008907318
2023-01-22 17:58:35.988634: step: 544/470, loss: 0.11674753576517105
2023-01-22 17:58:36.762164: step: 546/470, loss: 0.6683562994003296
2023-01-22 17:58:37.529258: step: 548/470, loss: 0.2430974245071411
2023-01-22 17:58:38.233995: step: 550/470, loss: 0.2425515353679657
2023-01-22 17:58:38.961658: step: 552/470, loss: 0.5050057768821716
2023-01-22 17:58:39.683111: step: 554/470, loss: 0.11187369376420975
2023-01-22 17:58:40.347116: step: 556/470, loss: 0.5013543963432312
2023-01-22 17:58:41.099264: step: 558/470, loss: 0.36751458048820496
2023-01-22 17:58:41.902175: step: 560/470, loss: 0.28177356719970703
2023-01-22 17:58:42.664322: step: 562/470, loss: 0.576210618019104
2023-01-22 17:58:43.437516: step: 564/470, loss: 0.3474891781806946
2023-01-22 17:58:44.200077: step: 566/470, loss: 0.30152004957199097
2023-01-22 17:58:44.859402: step: 568/470, loss: 0.3646096885204315
2023-01-22 17:58:45.605182: step: 570/470, loss: 0.35699066519737244
2023-01-22 17:58:46.324987: step: 572/470, loss: 0.13822859525680542
2023-01-22 17:58:47.062081: step: 574/470, loss: 0.3227802515029907
2023-01-22 17:58:47.766061: step: 576/470, loss: 0.10874330252408981
2023-01-22 17:58:48.505705: step: 578/470, loss: 0.08362071961164474
2023-01-22 17:58:49.239936: step: 580/470, loss: 0.2959776222705841
2023-01-22 17:58:50.002233: step: 582/470, loss: 0.09202943742275238
2023-01-22 17:58:50.815299: step: 584/470, loss: 0.12419924139976501
2023-01-22 17:58:51.487644: step: 586/470, loss: 0.4467095732688904
2023-01-22 17:58:52.202809: step: 588/470, loss: 0.17356723546981812
2023-01-22 17:58:53.177764: step: 590/470, loss: 0.18288274109363556
2023-01-22 17:58:53.972917: step: 592/470, loss: 0.2276880443096161
2023-01-22 17:58:54.783036: step: 594/470, loss: 0.10493405163288116
2023-01-22 17:58:55.510338: step: 596/470, loss: 0.13986705243587494
2023-01-22 17:58:56.250530: step: 598/470, loss: 0.18077510595321655
2023-01-22 17:58:56.953955: step: 600/470, loss: 0.12601624429225922
2023-01-22 17:58:57.620321: step: 602/470, loss: 0.3344309628009796
2023-01-22 17:58:58.434592: step: 604/470, loss: 0.3879287838935852
2023-01-22 17:58:59.273374: step: 606/470, loss: 0.16008992493152618
2023-01-22 17:59:00.205209: step: 608/470, loss: 0.19730323553085327
2023-01-22 17:59:00.858072: step: 610/470, loss: 1.7209839820861816
2023-01-22 17:59:01.521301: step: 612/470, loss: 0.17242218554019928
2023-01-22 17:59:02.279026: step: 614/470, loss: 0.42183101177215576
2023-01-22 17:59:03.005656: step: 616/470, loss: 0.1833951324224472
2023-01-22 17:59:03.731747: step: 618/470, loss: 0.1907496601343155
2023-01-22 17:59:04.472688: step: 620/470, loss: 0.21647794544696808
2023-01-22 17:59:05.259861: step: 622/470, loss: 0.39642030000686646
2023-01-22 17:59:06.022386: step: 624/470, loss: 0.20872657001018524
2023-01-22 17:59:06.736370: step: 626/470, loss: 0.16940362751483917
2023-01-22 17:59:07.457554: step: 628/470, loss: 0.29818278551101685
2023-01-22 17:59:08.133084: step: 630/470, loss: 0.12899573147296906
2023-01-22 17:59:08.831123: step: 632/470, loss: 0.08327148109674454
2023-01-22 17:59:09.538907: step: 634/470, loss: 0.2249470353126526
2023-01-22 17:59:10.456417: step: 636/470, loss: 0.1515919417142868
2023-01-22 17:59:11.240787: step: 638/470, loss: 0.8622671365737915
2023-01-22 17:59:12.038581: step: 640/470, loss: 0.37675124406814575
2023-01-22 17:59:12.743849: step: 642/470, loss: 0.2437460869550705
2023-01-22 17:59:13.466067: step: 644/470, loss: 0.4033161997795105
2023-01-22 17:59:14.256048: step: 646/470, loss: 0.24557210505008698
2023-01-22 17:59:15.059262: step: 648/470, loss: 0.25930410623550415
2023-01-22 17:59:15.712019: step: 650/470, loss: 0.49194440245628357
2023-01-22 17:59:16.516270: step: 652/470, loss: 0.4548197090625763
2023-01-22 17:59:17.264036: step: 654/470, loss: 0.2559857666492462
2023-01-22 17:59:17.939198: step: 656/470, loss: 0.3703431189060211
2023-01-22 17:59:18.692939: step: 658/470, loss: 0.0801117792725563
2023-01-22 17:59:19.454325: step: 660/470, loss: 0.23692208528518677
2023-01-22 17:59:20.196785: step: 662/470, loss: 0.8581908941268921
2023-01-22 17:59:20.930919: step: 664/470, loss: 0.09321422874927521
2023-01-22 17:59:21.617018: step: 666/470, loss: 0.5431147217750549
2023-01-22 17:59:22.350337: step: 668/470, loss: 0.17868438363075256
2023-01-22 17:59:23.013496: step: 670/470, loss: 0.2592407763004303
2023-01-22 17:59:23.750965: step: 672/470, loss: 0.22203195095062256
2023-01-22 17:59:24.501961: step: 674/470, loss: 0.2031756341457367
2023-01-22 17:59:25.246509: step: 676/470, loss: 1.166580319404602
2023-01-22 17:59:25.986573: step: 678/470, loss: 0.20502953231334686
2023-01-22 17:59:26.692475: step: 680/470, loss: 0.14193998277187347
2023-01-22 17:59:27.404768: step: 682/470, loss: 0.16833271086215973
2023-01-22 17:59:28.151145: step: 684/470, loss: 0.20455804467201233
2023-01-22 17:59:28.805111: step: 686/470, loss: 0.7733557224273682
2023-01-22 17:59:29.576236: step: 688/470, loss: 0.20254459977149963
2023-01-22 17:59:30.364737: step: 690/470, loss: 0.8873804211616516
2023-01-22 17:59:31.096394: step: 692/470, loss: 0.4637981057167053
2023-01-22 17:59:31.825596: step: 694/470, loss: 0.4916077256202698
2023-01-22 17:59:32.575463: step: 696/470, loss: 0.826230525970459
2023-01-22 17:59:33.351841: step: 698/470, loss: 0.3543017506599426
2023-01-22 17:59:34.062864: step: 700/470, loss: 0.10216841101646423
2023-01-22 17:59:34.797600: step: 702/470, loss: 0.21498167514801025
2023-01-22 17:59:35.539521: step: 704/470, loss: 0.10220889002084732
2023-01-22 17:59:36.335998: step: 706/470, loss: 0.08111105859279633
2023-01-22 17:59:37.049471: step: 708/470, loss: 0.24107980728149414
2023-01-22 17:59:37.818800: step: 710/470, loss: 0.21305520832538605
2023-01-22 17:59:38.570818: step: 712/470, loss: 0.14277955889701843
2023-01-22 17:59:39.303875: step: 714/470, loss: 0.9436085224151611
2023-01-22 17:59:40.047559: step: 716/470, loss: 0.6749270558357239
2023-01-22 17:59:40.740916: step: 718/470, loss: 0.14690832793712616
2023-01-22 17:59:41.500281: step: 720/470, loss: 0.1711893379688263
2023-01-22 17:59:42.236938: step: 722/470, loss: 0.22402094304561615
2023-01-22 17:59:42.997723: step: 724/470, loss: 0.3463267683982849
2023-01-22 17:59:43.701663: step: 726/470, loss: 0.34018969535827637
2023-01-22 17:59:44.464176: step: 728/470, loss: 0.5446484088897705
2023-01-22 17:59:45.185403: step: 730/470, loss: 0.11589177697896957
2023-01-22 17:59:45.920747: step: 732/470, loss: 1.1572738885879517
2023-01-22 17:59:46.735732: step: 734/470, loss: 0.20397549867630005
2023-01-22 17:59:47.567702: step: 736/470, loss: 0.6422154307365417
2023-01-22 17:59:48.254677: step: 738/470, loss: 0.19147703051567078
2023-01-22 17:59:48.890844: step: 740/470, loss: 0.520534336566925
2023-01-22 17:59:49.739870: step: 742/470, loss: 0.14674602448940277
2023-01-22 17:59:50.550511: step: 744/470, loss: 0.8777087926864624
2023-01-22 17:59:51.267383: step: 746/470, loss: 1.0014443397521973
2023-01-22 17:59:51.929844: step: 748/470, loss: 0.3216632306575775
2023-01-22 17:59:52.734080: step: 750/470, loss: 0.20832213759422302
2023-01-22 17:59:53.481083: step: 752/470, loss: 0.5051476359367371
2023-01-22 17:59:54.277928: step: 754/470, loss: 0.2241048663854599
2023-01-22 17:59:55.065136: step: 756/470, loss: 0.8101214170455933
2023-01-22 17:59:55.859912: step: 758/470, loss: 0.12697064876556396
2023-01-22 17:59:56.587130: step: 760/470, loss: 1.2407550811767578
2023-01-22 17:59:57.369322: step: 762/470, loss: 0.39389562606811523
2023-01-22 17:59:58.122964: step: 764/470, loss: 0.4802873730659485
2023-01-22 17:59:58.875842: step: 766/470, loss: 0.7842137813568115
2023-01-22 17:59:59.625495: step: 768/470, loss: 0.204922616481781
2023-01-22 18:00:00.402939: step: 770/470, loss: 0.25310850143432617
2023-01-22 18:00:01.102543: step: 772/470, loss: 0.07442860305309296
2023-01-22 18:00:01.839746: step: 774/470, loss: 0.16630667448043823
2023-01-22 18:00:02.651249: step: 776/470, loss: 0.4407159388065338
2023-01-22 18:00:03.440342: step: 778/470, loss: 0.2151498794555664
2023-01-22 18:00:04.165409: step: 780/470, loss: 0.4645977020263672
2023-01-22 18:00:04.916388: step: 782/470, loss: 0.4509057104587555
2023-01-22 18:00:05.587782: step: 784/470, loss: 0.4268851578235626
2023-01-22 18:00:06.282876: step: 786/470, loss: 0.2786135971546173
2023-01-22 18:00:07.124009: step: 788/470, loss: 0.42344367504119873
2023-01-22 18:00:07.828753: step: 790/470, loss: 0.22360637784004211
2023-01-22 18:00:08.541355: step: 792/470, loss: 0.2640346884727478
2023-01-22 18:00:09.299732: step: 794/470, loss: 1.436629056930542
2023-01-22 18:00:10.117675: step: 796/470, loss: 0.168908953666687
2023-01-22 18:00:10.789837: step: 798/470, loss: 0.2268424928188324
2023-01-22 18:00:11.527843: step: 800/470, loss: 0.16930358111858368
2023-01-22 18:00:12.280402: step: 802/470, loss: 0.19378112256526947
2023-01-22 18:00:13.116613: step: 804/470, loss: 0.4183207154273987
2023-01-22 18:00:13.828365: step: 806/470, loss: 0.39443352818489075
2023-01-22 18:00:14.558999: step: 808/470, loss: 0.22412896156311035
2023-01-22 18:00:15.282123: step: 810/470, loss: 0.23135864734649658
2023-01-22 18:00:16.036741: step: 812/470, loss: 0.3557632863521576
2023-01-22 18:00:16.852600: step: 814/470, loss: 0.23979082703590393
2023-01-22 18:00:17.603023: step: 816/470, loss: 0.4324354827404022
2023-01-22 18:00:18.312618: step: 818/470, loss: 0.20390821993350983
2023-01-22 18:00:18.991979: step: 820/470, loss: 0.11008242517709732
2023-01-22 18:00:19.764297: step: 822/470, loss: 0.7956212759017944
2023-01-22 18:00:20.575247: step: 824/470, loss: 0.09564602375030518
2023-01-22 18:00:21.360982: step: 826/470, loss: 0.10002394765615463
2023-01-22 18:00:22.170223: step: 828/470, loss: 0.12996633350849152
2023-01-22 18:00:22.985050: step: 830/470, loss: 0.16086608171463013
2023-01-22 18:00:23.703305: step: 832/470, loss: 0.32509753108024597
2023-01-22 18:00:24.475117: step: 834/470, loss: 0.6973584890365601
2023-01-22 18:00:25.200723: step: 836/470, loss: 0.5293657779693604
2023-01-22 18:00:25.967937: step: 838/470, loss: 0.4230278730392456
2023-01-22 18:00:26.778583: step: 840/470, loss: 0.26785650849342346
2023-01-22 18:00:27.505801: step: 842/470, loss: 0.10598357021808624
2023-01-22 18:00:28.314629: step: 844/470, loss: 0.08085938543081284
2023-01-22 18:00:29.036902: step: 846/470, loss: 0.0774892121553421
2023-01-22 18:00:29.757913: step: 848/470, loss: 0.3891444206237793
2023-01-22 18:00:30.519996: step: 850/470, loss: 0.20412513613700867
2023-01-22 18:00:31.263560: step: 852/470, loss: 0.7257307171821594
2023-01-22 18:00:32.038556: step: 854/470, loss: 0.19312706589698792
2023-01-22 18:00:32.809371: step: 856/470, loss: 0.2457079440355301
2023-01-22 18:00:33.546401: step: 858/470, loss: 0.22375904023647308
2023-01-22 18:00:34.229216: step: 860/470, loss: 0.07559472322463989
2023-01-22 18:00:35.037335: step: 862/470, loss: 5.461023330688477
2023-01-22 18:00:35.791424: step: 864/470, loss: 0.28360649943351746
2023-01-22 18:00:36.560172: step: 866/470, loss: 0.1746789664030075
2023-01-22 18:00:37.400176: step: 868/470, loss: 0.2900182604789734
2023-01-22 18:00:38.120827: step: 870/470, loss: 0.5256376266479492
2023-01-22 18:00:38.872967: step: 872/470, loss: 0.5666700601577759
2023-01-22 18:00:39.674376: step: 874/470, loss: 0.3807283341884613
2023-01-22 18:00:40.514023: step: 876/470, loss: 0.39703118801116943
2023-01-22 18:00:41.389350: step: 878/470, loss: 0.3907458186149597
2023-01-22 18:00:42.160171: step: 880/470, loss: 0.2166074514389038
2023-01-22 18:00:42.907509: step: 882/470, loss: 0.6513550281524658
2023-01-22 18:00:43.654494: step: 884/470, loss: 0.17348910868167877
2023-01-22 18:00:44.381907: step: 886/470, loss: 0.5899196863174438
2023-01-22 18:00:45.022787: step: 888/470, loss: 0.33359190821647644
2023-01-22 18:00:45.803640: step: 890/470, loss: 0.2644504904747009
2023-01-22 18:00:46.533355: step: 892/470, loss: 0.0992155447602272
2023-01-22 18:00:47.278897: step: 894/470, loss: 0.07050655782222748
2023-01-22 18:00:48.171791: step: 896/470, loss: 0.15530425310134888
2023-01-22 18:00:48.879027: step: 898/470, loss: 1.7606289386749268
2023-01-22 18:00:49.652973: step: 900/470, loss: 0.39144524931907654
2023-01-22 18:00:50.508988: step: 902/470, loss: 0.10359073430299759
2023-01-22 18:00:51.236707: step: 904/470, loss: 0.5953198075294495
2023-01-22 18:00:51.972857: step: 906/470, loss: 0.07822130620479584
2023-01-22 18:00:52.635805: step: 908/470, loss: 0.16700084507465363
2023-01-22 18:00:53.493773: step: 910/470, loss: 0.48216283321380615
2023-01-22 18:00:54.294884: step: 912/470, loss: 0.14438587427139282
2023-01-22 18:00:55.086667: step: 914/470, loss: 0.28868240118026733
2023-01-22 18:00:55.844704: step: 916/470, loss: 0.15756703913211823
2023-01-22 18:00:56.542784: step: 918/470, loss: 0.25201234221458435
2023-01-22 18:00:57.318677: step: 920/470, loss: 0.13608524203300476
2023-01-22 18:00:58.073940: step: 922/470, loss: 0.11261554062366486
2023-01-22 18:00:58.758477: step: 924/470, loss: 0.12380633503198624
2023-01-22 18:00:59.549838: step: 926/470, loss: 0.3758620023727417
2023-01-22 18:01:00.280146: step: 928/470, loss: 0.11808370053768158
2023-01-22 18:01:01.007273: step: 930/470, loss: 0.5944559574127197
2023-01-22 18:01:01.751513: step: 932/470, loss: 0.38902971148490906
2023-01-22 18:01:02.520827: step: 934/470, loss: 0.08703064173460007
2023-01-22 18:01:03.316508: step: 936/470, loss: 0.1778847724199295
2023-01-22 18:01:04.081308: step: 938/470, loss: 0.3809297978878021
2023-01-22 18:01:04.776706: step: 940/470, loss: 0.24091286957263947
2023-01-22 18:01:05.459972: step: 942/470, loss: 0.10962583124637604
==================================================
Loss: 0.416
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2976010690414319, 'r': 0.3218835092098979, 'f1': 0.3092663798607405}, 'combined': 0.22788049042370354, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3549763417163531, 'r': 0.32667371312609633, 'f1': 0.34023745409131195}, 'combined': 0.23698131130738148, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29295514959330793, 'r': 0.32074975581658194, 'f1': 0.3062230458611208}, 'combined': 0.2256380337924048, 'epoch': 10}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35643838707889336, 'r': 0.31295358865524353, 'f1': 0.3332835660256865}, 'combined': 0.2321378071820702, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27696660863807243, 'r': 0.31953642894107787, 'f1': 0.2967325075805252}, 'combined': 0.21864500558565014, 'epoch': 10}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34185545824681857, 'r': 0.32870717139117167, 'f1': 0.3351524100459005}, 'combined': 0.23343948958420932, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21568627450980393, 'r': 0.3142857142857143, 'f1': 0.2558139534883721}, 'combined': 0.17054263565891473, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.234375, 'r': 0.32608695652173914, 'f1': 0.2727272727272727}, 'combined': 0.13636363636363635, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4318181818181818, 'r': 0.3275862068965517, 'f1': 0.3725490196078432}, 'combined': 0.24836601307189546, 'epoch': 10}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3049308236808237, 'r': 0.3211320818650041, 'f1': 0.3128218246633219}, 'combined': 0.23050029185718457, 'epoch': 8}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32065206847366756, 'r': 0.3490174437617227, 'f1': 0.3342340161254067}, 'combined': 0.23279981222665144, 'epoch': 8}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24523809523809523, 'r': 0.31530612244897954, 'f1': 0.27589285714285716}, 'combined': 0.18392857142857144, 'epoch': 8}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26474047961800956, 'r': 0.3240182340675829, 'f1': 0.29139523780480575}, 'combined': 0.2147122804877516, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32541475117674507, 'r': 0.34573363573629207, 'f1': 0.33526661835256644}, 'combined': 0.23351903765850401, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2722222222222222, 'r': 0.532608695652174, 'f1': 0.36029411764705876}, 'combined': 0.18014705882352938, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27696660863807243, 'r': 0.31953642894107787, 'f1': 0.2967325075805252}, 'combined': 0.21864500558565014, 'epoch': 10}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34185545824681857, 'r': 0.32870717139117167, 'f1': 0.3351524100459005}, 'combined': 0.23343948958420932, 'epoch': 10}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4318181818181818, 'r': 0.3275862068965517, 'f1': 0.3725490196078432}, 'combined': 0.24836601307189546, 'epoch': 10}
******************************
Epoch: 11
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 18:03:52.946054: step: 2/470, loss: 0.3994400203227997
2023-01-22 18:03:53.692797: step: 4/470, loss: 0.10796771198511124
2023-01-22 18:03:54.394307: step: 6/470, loss: 0.06982637196779251
2023-01-22 18:03:55.150299: step: 8/470, loss: 0.6267420649528503
2023-01-22 18:03:55.851131: step: 10/470, loss: 0.12536020576953888
2023-01-22 18:03:56.541728: step: 12/470, loss: 0.2619161605834961
2023-01-22 18:03:57.330625: step: 14/470, loss: 0.1946829855442047
2023-01-22 18:03:58.006514: step: 16/470, loss: 0.20657046139240265
2023-01-22 18:03:58.718662: step: 18/470, loss: 0.369625061750412
2023-01-22 18:03:59.445252: step: 20/470, loss: 0.24612738192081451
2023-01-22 18:04:00.228428: step: 22/470, loss: 0.17834819853305817
2023-01-22 18:04:00.994516: step: 24/470, loss: 0.18645793199539185
2023-01-22 18:04:01.789387: step: 26/470, loss: 0.22116416692733765
2023-01-22 18:04:02.604363: step: 28/470, loss: 0.12848031520843506
2023-01-22 18:04:03.326362: step: 30/470, loss: 0.2887888252735138
2023-01-22 18:04:04.064305: step: 32/470, loss: 0.09650327265262604
2023-01-22 18:04:04.889716: step: 34/470, loss: 0.1269495189189911
2023-01-22 18:04:05.653256: step: 36/470, loss: 0.05965163931250572
2023-01-22 18:04:06.340386: step: 38/470, loss: 0.09995022416114807
2023-01-22 18:04:07.154355: step: 40/470, loss: 0.1404799371957779
2023-01-22 18:04:07.933161: step: 42/470, loss: 0.07613828033208847
2023-01-22 18:04:08.728995: step: 44/470, loss: 0.21182122826576233
2023-01-22 18:04:09.561963: step: 46/470, loss: 0.5042648911476135
2023-01-22 18:04:10.324701: step: 48/470, loss: 0.5012888312339783
2023-01-22 18:04:11.003490: step: 50/470, loss: 0.4014410972595215
2023-01-22 18:04:11.742753: step: 52/470, loss: 1.0104151964187622
2023-01-22 18:04:12.589431: step: 54/470, loss: 0.5547516942024231
2023-01-22 18:04:13.405382: step: 56/470, loss: 1.227064847946167
2023-01-22 18:04:14.179356: step: 58/470, loss: 0.4300103783607483
2023-01-22 18:04:14.832143: step: 60/470, loss: 0.20219558477401733
2023-01-22 18:04:15.552527: step: 62/470, loss: 0.13512657582759857
2023-01-22 18:04:16.345837: step: 64/470, loss: 0.1292756050825119
2023-01-22 18:04:17.082513: step: 66/470, loss: 0.3424178957939148
2023-01-22 18:04:17.886578: step: 68/470, loss: 0.8694711327552795
2023-01-22 18:04:18.699085: step: 70/470, loss: 0.10702022910118103
2023-01-22 18:04:19.396131: step: 72/470, loss: 0.07732173800468445
2023-01-22 18:04:20.094203: step: 74/470, loss: 0.21523575484752655
2023-01-22 18:04:20.828859: step: 76/470, loss: 0.9190123081207275
2023-01-22 18:04:21.490691: step: 78/470, loss: 0.09142867475748062
2023-01-22 18:04:22.230823: step: 80/470, loss: 0.2203410565853119
2023-01-22 18:04:22.933198: step: 82/470, loss: 0.21649318933486938
2023-01-22 18:04:23.639185: step: 84/470, loss: 0.13063064217567444
2023-01-22 18:04:24.485661: step: 86/470, loss: 0.3328152596950531
2023-01-22 18:04:25.333734: step: 88/470, loss: 0.2513705790042877
2023-01-22 18:04:26.155377: step: 90/470, loss: 0.20509395003318787
2023-01-22 18:04:27.010977: step: 92/470, loss: 0.07670695334672928
2023-01-22 18:04:27.748168: step: 94/470, loss: 0.10654658079147339
2023-01-22 18:04:28.463050: step: 96/470, loss: 0.44697830080986023
2023-01-22 18:04:29.204324: step: 98/470, loss: 0.13903780281543732
2023-01-22 18:04:29.956764: step: 100/470, loss: 0.028267454355955124
2023-01-22 18:04:30.747810: step: 102/470, loss: 0.15167954564094543
2023-01-22 18:04:31.584343: step: 104/470, loss: 0.284242182970047
2023-01-22 18:04:32.255772: step: 106/470, loss: 0.3138585090637207
2023-01-22 18:04:33.150275: step: 108/470, loss: 0.07407403737306595
2023-01-22 18:04:33.966940: step: 110/470, loss: 0.6403460502624512
2023-01-22 18:04:34.676498: step: 112/470, loss: 0.11428175866603851
2023-01-22 18:04:35.430243: step: 114/470, loss: 0.26986491680145264
2023-01-22 18:04:36.246522: step: 116/470, loss: 0.1651705801486969
2023-01-22 18:04:37.023362: step: 118/470, loss: 0.07059428840875626
2023-01-22 18:04:37.777803: step: 120/470, loss: 0.0850813016295433
2023-01-22 18:04:38.520757: step: 122/470, loss: 0.23236671090126038
2023-01-22 18:04:39.302194: step: 124/470, loss: 1.0825673341751099
2023-01-22 18:04:40.023623: step: 126/470, loss: 0.18390889465808868
2023-01-22 18:04:40.748409: step: 128/470, loss: 0.12133748084306717
2023-01-22 18:04:41.443333: step: 130/470, loss: 0.26943790912628174
2023-01-22 18:04:42.183520: step: 132/470, loss: 0.059222038835287094
2023-01-22 18:04:42.924263: step: 134/470, loss: 0.4377175569534302
2023-01-22 18:04:43.629585: step: 136/470, loss: 0.1320364624261856
2023-01-22 18:04:44.407022: step: 138/470, loss: 0.2063646763563156
2023-01-22 18:04:45.106192: step: 140/470, loss: 0.17360788583755493
2023-01-22 18:04:45.821863: step: 142/470, loss: 0.17847619950771332
2023-01-22 18:04:46.593567: step: 144/470, loss: 0.4014095664024353
2023-01-22 18:04:47.328872: step: 146/470, loss: 0.26048025488853455
2023-01-22 18:04:48.120605: step: 148/470, loss: 0.4044667184352875
2023-01-22 18:04:48.874486: step: 150/470, loss: 0.6233318448066711
2023-01-22 18:04:49.541126: step: 152/470, loss: 0.10592886805534363
2023-01-22 18:04:50.345503: step: 154/470, loss: 0.6332147121429443
2023-01-22 18:04:51.148638: step: 156/470, loss: 0.4474610686302185
2023-01-22 18:04:51.792977: step: 158/470, loss: 0.22585195302963257
2023-01-22 18:04:52.509336: step: 160/470, loss: 0.10840116441249847
2023-01-22 18:04:53.255025: step: 162/470, loss: 0.17162242531776428
2023-01-22 18:04:54.032219: step: 164/470, loss: 0.1772492676973343
2023-01-22 18:04:54.704023: step: 166/470, loss: 0.3632153868675232
2023-01-22 18:04:55.463380: step: 168/470, loss: 0.14816507697105408
2023-01-22 18:04:56.175241: step: 170/470, loss: 0.9186021089553833
2023-01-22 18:04:56.934675: step: 172/470, loss: 0.22490334510803223
2023-01-22 18:04:57.635811: step: 174/470, loss: 0.20037584006786346
2023-01-22 18:04:58.318582: step: 176/470, loss: 0.13259491324424744
2023-01-22 18:04:58.993265: step: 178/470, loss: 0.42409461736679077
2023-01-22 18:04:59.739394: step: 180/470, loss: 0.12134432792663574
2023-01-22 18:05:00.462666: step: 182/470, loss: 0.10569081455469131
2023-01-22 18:05:01.160374: step: 184/470, loss: 0.07015454769134521
2023-01-22 18:05:01.927521: step: 186/470, loss: 0.18518798053264618
2023-01-22 18:05:02.714132: step: 188/470, loss: 0.1714620441198349
2023-01-22 18:05:03.399435: step: 190/470, loss: 0.5320131182670593
2023-01-22 18:05:04.097214: step: 192/470, loss: 0.09196509420871735
2023-01-22 18:05:04.771712: step: 194/470, loss: 0.24720802903175354
2023-01-22 18:05:05.564288: step: 196/470, loss: 0.381684273481369
2023-01-22 18:05:06.336649: step: 198/470, loss: 0.4392554759979248
2023-01-22 18:05:07.142121: step: 200/470, loss: 0.1657257229089737
2023-01-22 18:05:07.912143: step: 202/470, loss: 0.9423061013221741
2023-01-22 18:05:08.591910: step: 204/470, loss: 0.22993268072605133
2023-01-22 18:05:09.288981: step: 206/470, loss: 0.08702653646469116
2023-01-22 18:05:09.957391: step: 208/470, loss: 0.4365525543689728
2023-01-22 18:05:10.747386: step: 210/470, loss: 0.21688061952590942
2023-01-22 18:05:11.446156: step: 212/470, loss: 0.37000590562820435
2023-01-22 18:05:12.213766: step: 214/470, loss: 0.1840032935142517
2023-01-22 18:05:12.951836: step: 216/470, loss: 0.21828442811965942
2023-01-22 18:05:13.681959: step: 218/470, loss: 0.6175702214241028
2023-01-22 18:05:14.470187: step: 220/470, loss: 0.3277837038040161
2023-01-22 18:05:15.281408: step: 222/470, loss: 0.20514245331287384
2023-01-22 18:05:15.985402: step: 224/470, loss: 0.27700185775756836
2023-01-22 18:05:16.640829: step: 226/470, loss: 0.8384249210357666
2023-01-22 18:05:17.415422: step: 228/470, loss: 0.3489769697189331
2023-01-22 18:05:18.197720: step: 230/470, loss: 0.167975515127182
2023-01-22 18:05:18.974511: step: 232/470, loss: 0.12696748971939087
2023-01-22 18:05:19.737077: step: 234/470, loss: 0.36338022351264954
2023-01-22 18:05:20.537829: step: 236/470, loss: 0.17215953767299652
2023-01-22 18:05:21.257973: step: 238/470, loss: 0.14851003885269165
2023-01-22 18:05:21.950081: step: 240/470, loss: 0.5321226119995117
2023-01-22 18:05:22.709385: step: 242/470, loss: 0.37152212858200073
2023-01-22 18:05:23.521568: step: 244/470, loss: 0.11287014931440353
2023-01-22 18:05:24.217149: step: 246/470, loss: 0.1164015606045723
2023-01-22 18:05:25.042217: step: 248/470, loss: 0.3851315379142761
2023-01-22 18:05:25.856110: step: 250/470, loss: 0.5415903925895691
2023-01-22 18:05:26.575762: step: 252/470, loss: 0.07699915021657944
2023-01-22 18:05:27.348477: step: 254/470, loss: 0.10870891064405441
2023-01-22 18:05:28.115627: step: 256/470, loss: 0.18335126340389252
2023-01-22 18:05:28.874489: step: 258/470, loss: 0.1485547423362732
2023-01-22 18:05:29.595596: step: 260/470, loss: 0.440429151058197
2023-01-22 18:05:30.224489: step: 262/470, loss: 0.16356483101844788
2023-01-22 18:05:30.931123: step: 264/470, loss: 0.5098501443862915
2023-01-22 18:05:31.682959: step: 266/470, loss: 0.49232688546180725
2023-01-22 18:05:32.481013: step: 268/470, loss: 0.22366316616535187
2023-01-22 18:05:33.234573: step: 270/470, loss: 2.619814395904541
2023-01-22 18:05:33.915837: step: 272/470, loss: 0.2295650839805603
2023-01-22 18:05:34.646296: step: 274/470, loss: 0.11074075847864151
2023-01-22 18:05:35.375060: step: 276/470, loss: 0.3683517873287201
2023-01-22 18:05:36.146673: step: 278/470, loss: 0.13178575038909912
2023-01-22 18:05:36.836425: step: 280/470, loss: 0.16775688529014587
2023-01-22 18:05:37.530247: step: 282/470, loss: 0.0917547270655632
2023-01-22 18:05:38.254512: step: 284/470, loss: 0.24330279231071472
2023-01-22 18:05:38.964398: step: 286/470, loss: 0.21394579112529755
2023-01-22 18:05:39.665790: step: 288/470, loss: 0.16779950261116028
2023-01-22 18:05:40.418116: step: 290/470, loss: 0.21933045983314514
2023-01-22 18:05:41.192423: step: 292/470, loss: 0.16219143569469452
2023-01-22 18:05:41.955729: step: 294/470, loss: 0.11340250819921494
2023-01-22 18:05:42.686888: step: 296/470, loss: 0.26899465918540955
2023-01-22 18:05:43.422153: step: 298/470, loss: 0.15036383271217346
2023-01-22 18:05:44.174826: step: 300/470, loss: 0.20359119772911072
2023-01-22 18:05:44.933641: step: 302/470, loss: 0.08829786628484726
2023-01-22 18:05:45.718537: step: 304/470, loss: 0.32991862297058105
2023-01-22 18:05:46.464060: step: 306/470, loss: 0.09574191272258759
2023-01-22 18:05:47.152368: step: 308/470, loss: 0.1676369309425354
2023-01-22 18:05:47.868355: step: 310/470, loss: 0.07528150081634521
2023-01-22 18:05:48.593347: step: 312/470, loss: 0.2053246796131134
2023-01-22 18:05:49.348823: step: 314/470, loss: 0.5107622146606445
2023-01-22 18:05:50.119016: step: 316/470, loss: 0.2811824381351471
2023-01-22 18:05:50.972769: step: 318/470, loss: 1.0416152477264404
2023-01-22 18:05:51.763532: step: 320/470, loss: 0.24820706248283386
2023-01-22 18:05:52.496956: step: 322/470, loss: 0.1375453770160675
2023-01-22 18:05:53.170119: step: 324/470, loss: 0.2664700448513031
2023-01-22 18:05:53.968030: step: 326/470, loss: 0.9418017864227295
2023-01-22 18:05:54.685742: step: 328/470, loss: 1.100771427154541
2023-01-22 18:05:55.499500: step: 330/470, loss: 0.1819295734167099
2023-01-22 18:05:56.289828: step: 332/470, loss: 0.17129111289978027
2023-01-22 18:05:57.098294: step: 334/470, loss: 0.38183021545410156
2023-01-22 18:05:57.826919: step: 336/470, loss: 0.1744094341993332
2023-01-22 18:05:58.586433: step: 338/470, loss: 0.21806088089942932
2023-01-22 18:05:59.260163: step: 340/470, loss: 0.1362285017967224
2023-01-22 18:06:00.029363: step: 342/470, loss: 0.08650539070367813
2023-01-22 18:06:00.833797: step: 344/470, loss: 0.14947454631328583
2023-01-22 18:06:01.572867: step: 346/470, loss: 0.04758727550506592
2023-01-22 18:06:02.316408: step: 348/470, loss: 0.09763923287391663
2023-01-22 18:06:03.044078: step: 350/470, loss: 0.12080357223749161
2023-01-22 18:06:03.786412: step: 352/470, loss: 0.6871947050094604
2023-01-22 18:06:04.557940: step: 354/470, loss: 0.24329255521297455
2023-01-22 18:06:05.319276: step: 356/470, loss: 0.4151495099067688
2023-01-22 18:06:05.992473: step: 358/470, loss: 0.1159839779138565
2023-01-22 18:06:06.729867: step: 360/470, loss: 0.42312848567962646
2023-01-22 18:06:07.476088: step: 362/470, loss: 0.19960635900497437
2023-01-22 18:06:08.243422: step: 364/470, loss: 0.5251233577728271
2023-01-22 18:06:08.901118: step: 366/470, loss: 0.4900449514389038
2023-01-22 18:06:09.587194: step: 368/470, loss: 0.45938706398010254
2023-01-22 18:06:10.356439: step: 370/470, loss: 0.12873217463493347
2023-01-22 18:06:11.053242: step: 372/470, loss: 0.20823711156845093
2023-01-22 18:06:11.822316: step: 374/470, loss: 0.30151286721229553
2023-01-22 18:06:12.583801: step: 376/470, loss: 0.4461778700351715
2023-01-22 18:06:13.406902: step: 378/470, loss: 1.0548112392425537
2023-01-22 18:06:14.145060: step: 380/470, loss: 0.4324851632118225
2023-01-22 18:06:14.871087: step: 382/470, loss: 0.9602062702178955
2023-01-22 18:06:15.606330: step: 384/470, loss: 0.6398365497589111
2023-01-22 18:06:16.389263: step: 386/470, loss: 0.22366558015346527
2023-01-22 18:06:17.187985: step: 388/470, loss: 0.21046940982341766
2023-01-22 18:06:17.935069: step: 390/470, loss: 0.22315052151679993
2023-01-22 18:06:18.631085: step: 392/470, loss: 0.22419774532318115
2023-01-22 18:06:19.411739: step: 394/470, loss: 0.71689373254776
2023-01-22 18:06:20.161910: step: 396/470, loss: 0.16539393365383148
2023-01-22 18:06:20.942444: step: 398/470, loss: 0.37051236629486084
2023-01-22 18:06:21.723288: step: 400/470, loss: 0.17021459341049194
2023-01-22 18:06:22.430236: step: 402/470, loss: 0.23352442681789398
2023-01-22 18:06:23.177735: step: 404/470, loss: 0.13187989592552185
2023-01-22 18:06:23.946146: step: 406/470, loss: 0.6370197534561157
2023-01-22 18:06:24.752187: step: 408/470, loss: 0.1171882152557373
2023-01-22 18:06:25.498180: step: 410/470, loss: 0.2786184549331665
2023-01-22 18:06:26.246323: step: 412/470, loss: 0.6290634870529175
2023-01-22 18:06:26.937795: step: 414/470, loss: 0.1813952922821045
2023-01-22 18:06:27.662719: step: 416/470, loss: 0.3490357995033264
2023-01-22 18:06:28.412767: step: 418/470, loss: 0.23016490042209625
2023-01-22 18:06:29.126015: step: 420/470, loss: 1.1225723028182983
2023-01-22 18:06:29.888588: step: 422/470, loss: 0.7987148761749268
2023-01-22 18:06:30.728353: step: 424/470, loss: 0.1776483952999115
2023-01-22 18:06:31.423192: step: 426/470, loss: 0.2515849769115448
2023-01-22 18:06:32.182861: step: 428/470, loss: 0.22037197649478912
2023-01-22 18:06:32.973110: step: 430/470, loss: 0.1036430150270462
2023-01-22 18:06:33.738928: step: 432/470, loss: 0.2177654653787613
2023-01-22 18:06:34.500680: step: 434/470, loss: 0.1274358332157135
2023-01-22 18:06:35.240828: step: 436/470, loss: 0.33280283212661743
2023-01-22 18:06:36.018578: step: 438/470, loss: 0.26393696665763855
2023-01-22 18:06:36.733527: step: 440/470, loss: 0.13263751566410065
2023-01-22 18:06:37.468955: step: 442/470, loss: 0.13120940327644348
2023-01-22 18:06:38.174378: step: 444/470, loss: 0.4707326292991638
2023-01-22 18:06:39.024327: step: 446/470, loss: 0.46750926971435547
2023-01-22 18:06:39.693456: step: 448/470, loss: 0.06135157495737076
2023-01-22 18:06:40.398167: step: 450/470, loss: 0.09700169414281845
2023-01-22 18:06:41.175858: step: 452/470, loss: 0.23718973994255066
2023-01-22 18:06:41.861199: step: 454/470, loss: 0.3361484706401825
2023-01-22 18:06:42.655295: step: 456/470, loss: 0.13764187693595886
2023-01-22 18:06:43.423948: step: 458/470, loss: 0.14335286617279053
2023-01-22 18:06:44.202054: step: 460/470, loss: 0.12495262920856476
2023-01-22 18:06:44.945296: step: 462/470, loss: 0.881492018699646
2023-01-22 18:06:45.671122: step: 464/470, loss: 0.4301450848579407
2023-01-22 18:06:46.362498: step: 466/470, loss: 1.3912532329559326
2023-01-22 18:06:47.148511: step: 468/470, loss: 0.11058748513460159
2023-01-22 18:06:47.877288: step: 470/470, loss: 0.4207277297973633
2023-01-22 18:06:48.644361: step: 472/470, loss: 0.15675045549869537
2023-01-22 18:06:49.407242: step: 474/470, loss: 0.32435324788093567
2023-01-22 18:06:50.098507: step: 476/470, loss: 0.21787133812904358
2023-01-22 18:06:50.829958: step: 478/470, loss: 0.4728389382362366
2023-01-22 18:06:51.552939: step: 480/470, loss: 0.29139944911003113
2023-01-22 18:06:52.344002: step: 482/470, loss: 0.19343923032283783
2023-01-22 18:06:53.074389: step: 484/470, loss: 0.15642260015010834
2023-01-22 18:06:53.853026: step: 486/470, loss: 0.2686142027378082
2023-01-22 18:06:54.592667: step: 488/470, loss: 0.03354679420590401
2023-01-22 18:06:55.259292: step: 490/470, loss: 0.14455752074718475
2023-01-22 18:06:55.962215: step: 492/470, loss: 0.29530078172683716
2023-01-22 18:06:56.704331: step: 494/470, loss: 0.21259760856628418
2023-01-22 18:06:57.398573: step: 496/470, loss: 0.12661580741405487
2023-01-22 18:06:58.124889: step: 498/470, loss: 0.24475648999214172
2023-01-22 18:06:58.915600: step: 500/470, loss: 0.5884524583816528
2023-01-22 18:06:59.657439: step: 502/470, loss: 0.21985645592212677
2023-01-22 18:07:00.384622: step: 504/470, loss: 0.12764428555965424
2023-01-22 18:07:01.102057: step: 506/470, loss: 0.2050672471523285
2023-01-22 18:07:01.789911: step: 508/470, loss: 0.22950823605060577
2023-01-22 18:07:02.522586: step: 510/470, loss: 0.10886823385953903
2023-01-22 18:07:03.320571: step: 512/470, loss: 0.3298364281654358
2023-01-22 18:07:04.075421: step: 514/470, loss: 0.45132243633270264
2023-01-22 18:07:04.794595: step: 516/470, loss: 0.03829793632030487
2023-01-22 18:07:05.547129: step: 518/470, loss: 0.2860611081123352
2023-01-22 18:07:06.300458: step: 520/470, loss: 0.18205812573432922
2023-01-22 18:07:07.118350: step: 522/470, loss: 0.2330647110939026
2023-01-22 18:07:07.911338: step: 524/470, loss: 0.16605840623378754
2023-01-22 18:07:08.614313: step: 526/470, loss: 0.1584710031747818
2023-01-22 18:07:09.328016: step: 528/470, loss: 0.28219524025917053
2023-01-22 18:07:10.096175: step: 530/470, loss: 0.1415386199951172
2023-01-22 18:07:10.889747: step: 532/470, loss: 0.187623992562294
2023-01-22 18:07:11.618253: step: 534/470, loss: 0.20938031375408173
2023-01-22 18:07:12.384513: step: 536/470, loss: 0.3544868528842926
2023-01-22 18:07:13.252255: step: 538/470, loss: 0.11445646733045578
2023-01-22 18:07:14.062617: step: 540/470, loss: 0.4840231239795685
2023-01-22 18:07:14.759733: step: 542/470, loss: 0.32870981097221375
2023-01-22 18:07:15.586557: step: 544/470, loss: 0.2359415590763092
2023-01-22 18:07:16.319500: step: 546/470, loss: 0.14783021807670593
2023-01-22 18:07:17.041558: step: 548/470, loss: 0.16923844814300537
2023-01-22 18:07:17.740390: step: 550/470, loss: 0.14774803817272186
2023-01-22 18:07:18.484486: step: 552/470, loss: 0.20552322268486023
2023-01-22 18:07:19.207012: step: 554/470, loss: 0.12092557549476624
2023-01-22 18:07:19.936152: step: 556/470, loss: 0.5868374705314636
2023-01-22 18:07:20.635678: step: 558/470, loss: 0.2626172602176666
2023-01-22 18:07:21.417114: step: 560/470, loss: 0.27606257796287537
2023-01-22 18:07:22.111604: step: 562/470, loss: 0.08012336492538452
2023-01-22 18:07:22.928674: step: 564/470, loss: 1.1808509826660156
2023-01-22 18:07:23.696254: step: 566/470, loss: 1.3284801244735718
2023-01-22 18:07:24.460094: step: 568/470, loss: 2.19006609916687
2023-01-22 18:07:25.177082: step: 570/470, loss: 0.13095425069332123
2023-01-22 18:07:25.921163: step: 572/470, loss: 0.461041122674942
2023-01-22 18:07:26.629438: step: 574/470, loss: 0.2042723149061203
2023-01-22 18:07:27.409652: step: 576/470, loss: 0.32484281063079834
2023-01-22 18:07:28.366078: step: 578/470, loss: 0.2067028135061264
2023-01-22 18:07:29.032821: step: 580/470, loss: 0.32187509536743164
2023-01-22 18:07:29.795343: step: 582/470, loss: 0.21868886053562164
2023-01-22 18:07:30.633598: step: 584/470, loss: 0.2576506733894348
2023-01-22 18:07:31.426894: step: 586/470, loss: 0.7114197611808777
2023-01-22 18:07:32.158433: step: 588/470, loss: 0.1497022956609726
2023-01-22 18:07:32.931850: step: 590/470, loss: 0.10337451845407486
2023-01-22 18:07:33.668629: step: 592/470, loss: 0.30149146914482117
2023-01-22 18:07:34.429337: step: 594/470, loss: 0.11470700055360794
2023-01-22 18:07:35.140162: step: 596/470, loss: 0.1277574747800827
2023-01-22 18:07:35.877991: step: 598/470, loss: 0.09452803432941437
2023-01-22 18:07:36.709310: step: 600/470, loss: 0.25843483209609985
2023-01-22 18:07:37.398993: step: 602/470, loss: 0.8243882060050964
2023-01-22 18:07:38.260759: step: 604/470, loss: 0.27867597341537476
2023-01-22 18:07:38.974829: step: 606/470, loss: 0.2572006583213806
2023-01-22 18:07:39.733614: step: 608/470, loss: 0.08993202447891235
2023-01-22 18:07:40.566694: step: 610/470, loss: 0.23165597021579742
2023-01-22 18:07:41.308977: step: 612/470, loss: 0.4315301179885864
2023-01-22 18:07:42.132455: step: 614/470, loss: 0.17089776694774628
2023-01-22 18:07:42.879252: step: 616/470, loss: 0.1850140392780304
2023-01-22 18:07:43.594456: step: 618/470, loss: 0.37521472573280334
2023-01-22 18:07:44.309922: step: 620/470, loss: 0.1793273687362671
2023-01-22 18:07:45.057271: step: 622/470, loss: 0.2895492911338806
2023-01-22 18:07:45.767905: step: 624/470, loss: 0.1320488601922989
2023-01-22 18:07:46.537840: step: 626/470, loss: 0.15132221579551697
2023-01-22 18:07:47.334573: step: 628/470, loss: 0.15033775568008423
2023-01-22 18:07:48.051736: step: 630/470, loss: 0.0726805329322815
2023-01-22 18:07:48.794054: step: 632/470, loss: 0.225330650806427
2023-01-22 18:07:49.618952: step: 634/470, loss: 0.19526013731956482
2023-01-22 18:07:50.310332: step: 636/470, loss: 0.18398520350456238
2023-01-22 18:07:51.032793: step: 638/470, loss: 0.6068989634513855
2023-01-22 18:07:51.719036: step: 640/470, loss: 0.1774880290031433
2023-01-22 18:07:52.413908: step: 642/470, loss: 0.04690373316407204
2023-01-22 18:07:53.070011: step: 644/470, loss: 0.08224115520715714
2023-01-22 18:07:53.900409: step: 646/470, loss: 0.20977337658405304
2023-01-22 18:07:54.679608: step: 648/470, loss: 0.6167982220649719
2023-01-22 18:07:55.388535: step: 650/470, loss: 2.5424869060516357
2023-01-22 18:07:56.167631: step: 652/470, loss: 0.26920145750045776
2023-01-22 18:07:56.903178: step: 654/470, loss: 0.09911765903234482
2023-01-22 18:07:57.646186: step: 656/470, loss: 1.6140161752700806
2023-01-22 18:07:58.341420: step: 658/470, loss: 0.07306616753339767
2023-01-22 18:07:59.161188: step: 660/470, loss: 0.13788312673568726
2023-01-22 18:07:59.860587: step: 662/470, loss: 0.2710290551185608
2023-01-22 18:08:00.678869: step: 664/470, loss: 0.6698711514472961
2023-01-22 18:08:01.399083: step: 666/470, loss: 4.250461578369141
2023-01-22 18:08:02.084103: step: 668/470, loss: 0.44460374116897583
2023-01-22 18:08:02.761524: step: 670/470, loss: 0.23895730078220367
2023-01-22 18:08:03.488635: step: 672/470, loss: 0.13557671010494232
2023-01-22 18:08:04.202360: step: 674/470, loss: 0.0696479007601738
2023-01-22 18:08:04.882072: step: 676/470, loss: 0.061501167714595795
2023-01-22 18:08:05.647630: step: 678/470, loss: 0.18382152915000916
2023-01-22 18:08:06.395156: step: 680/470, loss: 0.1674911230802536
2023-01-22 18:08:07.124438: step: 682/470, loss: 0.5173250436782837
2023-01-22 18:08:07.820180: step: 684/470, loss: 0.1093844622373581
2023-01-22 18:08:08.691750: step: 686/470, loss: 0.5219208598136902
2023-01-22 18:08:09.464837: step: 688/470, loss: 0.16668257117271423
2023-01-22 18:08:10.174098: step: 690/470, loss: 0.5589529871940613
2023-01-22 18:08:10.921504: step: 692/470, loss: 0.16195274889469147
2023-01-22 18:08:11.630445: step: 694/470, loss: 0.17775781452655792
2023-01-22 18:08:12.354121: step: 696/470, loss: 14.064286231994629
2023-01-22 18:08:13.098448: step: 698/470, loss: 1.6122430562973022
2023-01-22 18:08:13.796657: step: 700/470, loss: 0.1364855021238327
2023-01-22 18:08:14.514475: step: 702/470, loss: 0.2651909291744232
2023-01-22 18:08:15.161718: step: 704/470, loss: 0.10258844494819641
2023-01-22 18:08:15.913320: step: 706/470, loss: 0.4878748059272766
2023-01-22 18:08:16.622032: step: 708/470, loss: 0.09945238381624222
2023-01-22 18:08:17.476723: step: 710/470, loss: 0.25955334305763245
2023-01-22 18:08:18.176304: step: 712/470, loss: 0.3970111906528473
2023-01-22 18:08:18.939326: step: 714/470, loss: 0.5209802985191345
2023-01-22 18:08:19.652572: step: 716/470, loss: 0.11759445071220398
2023-01-22 18:08:20.392456: step: 718/470, loss: 0.15108118951320648
2023-01-22 18:08:21.089699: step: 720/470, loss: 0.36267387866973877
2023-01-22 18:08:21.904618: step: 722/470, loss: 0.07263346761465073
2023-01-22 18:08:22.703572: step: 724/470, loss: 0.10593510419130325
2023-01-22 18:08:23.398773: step: 726/470, loss: 0.26219284534454346
2023-01-22 18:08:24.230609: step: 728/470, loss: 0.17348651587963104
2023-01-22 18:08:24.940659: step: 730/470, loss: 0.1823439598083496
2023-01-22 18:08:25.682655: step: 732/470, loss: 0.20073945820331573
2023-01-22 18:08:26.454327: step: 734/470, loss: 0.27448293566703796
2023-01-22 18:08:27.261559: step: 736/470, loss: 0.33971887826919556
2023-01-22 18:08:28.063085: step: 738/470, loss: 0.1402978003025055
2023-01-22 18:08:28.853846: step: 740/470, loss: 0.5981901288032532
2023-01-22 18:08:29.616542: step: 742/470, loss: 0.04211556911468506
2023-01-22 18:08:30.410175: step: 744/470, loss: 0.11189659684896469
2023-01-22 18:08:31.015574: step: 746/470, loss: 0.12144724279642105
2023-01-22 18:08:31.667416: step: 748/470, loss: 0.3307271897792816
2023-01-22 18:08:32.382920: step: 750/470, loss: 0.2954995632171631
2023-01-22 18:08:33.045625: step: 752/470, loss: 0.4646444022655487
2023-01-22 18:08:33.707321: step: 754/470, loss: 0.06638015806674957
2023-01-22 18:08:34.522440: step: 756/470, loss: 0.07224085181951523
2023-01-22 18:08:35.170840: step: 758/470, loss: 0.2975500822067261
2023-01-22 18:08:35.886399: step: 760/470, loss: 0.8255310654640198
2023-01-22 18:08:36.604014: step: 762/470, loss: 0.12929823994636536
2023-01-22 18:08:37.352945: step: 764/470, loss: 0.1628466248512268
2023-01-22 18:08:38.100309: step: 766/470, loss: 0.14177992939949036
2023-01-22 18:08:38.865854: step: 768/470, loss: 0.393669992685318
2023-01-22 18:08:39.613038: step: 770/470, loss: 0.04610329121351242
2023-01-22 18:08:40.424317: step: 772/470, loss: 0.45871657133102417
2023-01-22 18:08:41.173157: step: 774/470, loss: 0.3327120244503021
2023-01-22 18:08:41.897652: step: 776/470, loss: 0.43813204765319824
2023-01-22 18:08:42.796128: step: 778/470, loss: 1.1366257667541504
2023-01-22 18:08:43.524943: step: 780/470, loss: 0.23157668113708496
2023-01-22 18:08:44.267147: step: 782/470, loss: 0.3343833088874817
2023-01-22 18:08:44.995453: step: 784/470, loss: 0.06032833456993103
2023-01-22 18:08:45.872621: step: 786/470, loss: 0.18906527757644653
2023-01-22 18:08:46.545507: step: 788/470, loss: 0.2094613015651703
2023-01-22 18:08:47.284431: step: 790/470, loss: 0.26915594935417175
2023-01-22 18:08:48.061659: step: 792/470, loss: 0.21122537553310394
2023-01-22 18:08:48.807645: step: 794/470, loss: 0.07323165982961655
2023-01-22 18:08:49.581174: step: 796/470, loss: 0.21279887855052948
2023-01-22 18:08:50.338139: step: 798/470, loss: 0.561419665813446
2023-01-22 18:08:51.030442: step: 800/470, loss: 0.16097694635391235
2023-01-22 18:08:51.852560: step: 802/470, loss: 0.2642227113246918
2023-01-22 18:08:52.615322: step: 804/470, loss: 0.2735598385334015
2023-01-22 18:08:53.310770: step: 806/470, loss: 0.1263493448495865
2023-01-22 18:08:54.070796: step: 808/470, loss: 0.33118510246276855
2023-01-22 18:08:54.731753: step: 810/470, loss: 0.3240700960159302
2023-01-22 18:08:55.541905: step: 812/470, loss: 0.09242391586303711
2023-01-22 18:08:56.298799: step: 814/470, loss: 0.15188434720039368
2023-01-22 18:08:57.107203: step: 816/470, loss: 0.5113020539283752
2023-01-22 18:08:57.798521: step: 818/470, loss: 0.1256381869316101
2023-01-22 18:08:58.545393: step: 820/470, loss: 0.08072460442781448
2023-01-22 18:08:59.224228: step: 822/470, loss: 0.4400816559791565
2023-01-22 18:08:59.971000: step: 824/470, loss: 0.22420644760131836
2023-01-22 18:09:00.742679: step: 826/470, loss: 0.13756045699119568
2023-01-22 18:09:01.526944: step: 828/470, loss: 0.05152636021375656
2023-01-22 18:09:02.529922: step: 830/470, loss: 0.1861773133277893
2023-01-22 18:09:03.193632: step: 832/470, loss: 0.08842433243989944
2023-01-22 18:09:03.902736: step: 834/470, loss: 0.1939559429883957
2023-01-22 18:09:04.637006: step: 836/470, loss: 0.06441611051559448
2023-01-22 18:09:05.522285: step: 838/470, loss: 0.18977122008800507
2023-01-22 18:09:06.183382: step: 840/470, loss: 0.02858108840882778
2023-01-22 18:09:06.985737: step: 842/470, loss: 0.2794545888900757
2023-01-22 18:09:07.707208: step: 844/470, loss: 0.666828453540802
2023-01-22 18:09:08.465764: step: 846/470, loss: 0.5264043807983398
2023-01-22 18:09:09.196048: step: 848/470, loss: 0.2906803488731384
2023-01-22 18:09:09.953876: step: 850/470, loss: 0.4317677617073059
2023-01-22 18:09:10.734985: step: 852/470, loss: 0.05206689238548279
2023-01-22 18:09:11.439673: step: 854/470, loss: 0.3372666537761688
2023-01-22 18:09:12.242258: step: 856/470, loss: 0.22663447260856628
2023-01-22 18:09:12.977185: step: 858/470, loss: 0.35830050706863403
2023-01-22 18:09:13.731665: step: 860/470, loss: 0.28675583004951477
2023-01-22 18:09:14.468228: step: 862/470, loss: 0.1459394097328186
2023-01-22 18:09:15.186651: step: 864/470, loss: 0.2950734496116638
2023-01-22 18:09:15.919331: step: 866/470, loss: 0.18734970688819885
2023-01-22 18:09:16.597741: step: 868/470, loss: 0.08804669976234436
2023-01-22 18:09:17.302755: step: 870/470, loss: 0.18895027041435242
2023-01-22 18:09:18.113227: step: 872/470, loss: 0.2600648105144501
2023-01-22 18:09:18.893797: step: 874/470, loss: 0.44221991300582886
2023-01-22 18:09:19.633366: step: 876/470, loss: 0.17826533317565918
2023-01-22 18:09:20.352203: step: 878/470, loss: 0.17969872057437897
2023-01-22 18:09:21.081095: step: 880/470, loss: 0.2378416508436203
2023-01-22 18:09:21.913569: step: 882/470, loss: 0.12380614876747131
2023-01-22 18:09:22.674709: step: 884/470, loss: 0.35380885004997253
2023-01-22 18:09:23.494991: step: 886/470, loss: 0.18434365093708038
2023-01-22 18:09:24.289092: step: 888/470, loss: 0.09525241702795029
2023-01-22 18:09:24.941600: step: 890/470, loss: 0.05519452691078186
2023-01-22 18:09:25.667055: step: 892/470, loss: 0.12015210837125778
2023-01-22 18:09:26.362181: step: 894/470, loss: 0.15597781538963318
2023-01-22 18:09:27.086632: step: 896/470, loss: 0.052873898297548294
2023-01-22 18:09:27.839292: step: 898/470, loss: 0.587254524230957
2023-01-22 18:09:28.605687: step: 900/470, loss: 0.21591414511203766
2023-01-22 18:09:29.280642: step: 902/470, loss: 0.1420390009880066
2023-01-22 18:09:30.105786: step: 904/470, loss: 0.5451937317848206
2023-01-22 18:09:30.972999: step: 906/470, loss: 0.4762882590293884
2023-01-22 18:09:31.643588: step: 908/470, loss: 0.08040604740381241
2023-01-22 18:09:32.382350: step: 910/470, loss: 0.1304711103439331
2023-01-22 18:09:33.118956: step: 912/470, loss: 0.43863868713378906
2023-01-22 18:09:33.869449: step: 914/470, loss: 0.07513883709907532
2023-01-22 18:09:34.584811: step: 916/470, loss: 1.0359426736831665
2023-01-22 18:09:35.331547: step: 918/470, loss: 0.2730335593223572
2023-01-22 18:09:36.110004: step: 920/470, loss: 0.16464608907699585
2023-01-22 18:09:36.845537: step: 922/470, loss: 0.5824774503707886
2023-01-22 18:09:37.669792: step: 924/470, loss: 0.6275187134742737
2023-01-22 18:09:38.428237: step: 926/470, loss: 0.1604541540145874
2023-01-22 18:09:39.174794: step: 928/470, loss: 0.27200543880462646
2023-01-22 18:09:39.842197: step: 930/470, loss: 0.886191189289093
2023-01-22 18:09:40.598766: step: 932/470, loss: 0.22329403460025787
2023-01-22 18:09:41.325740: step: 934/470, loss: 0.12522681057453156
2023-01-22 18:09:41.986663: step: 936/470, loss: 0.1403811126947403
2023-01-22 18:09:42.707865: step: 938/470, loss: 0.22944138944149017
2023-01-22 18:09:43.421101: step: 940/470, loss: 0.12413433194160461
2023-01-22 18:09:44.102174: step: 942/470, loss: 0.30450427532196045
==================================================
Loss: 0.340
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3091249669923422, 'r': 0.3173370154513418, 'f1': 0.3131771669341894}, 'combined': 0.23076212300413954, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3375444187463703, 'r': 0.3472812769794387, 'f1': 0.3423436284915794}, 'combined': 0.23844829845184637, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30646887258908145, 'r': 0.32100724415402837, 'f1': 0.3135696342338702}, 'combined': 0.23105130943548327, 'epoch': 11}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3411388045021567, 'r': 0.33851465985214013, 'f1': 0.33982166626083565}, 'combined': 0.23669170784336813, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2912099494097808, 'r': 0.327680265654649, 'f1': 0.3083705357142857}, 'combined': 0.22722039473684208, 'epoch': 11}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33296624392136376, 'r': 0.355377433416071, 'f1': 0.34380700535136166}, 'combined': 0.23946756591637133, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2288135593220339, 'r': 0.38571428571428573, 'f1': 0.2872340425531915}, 'combined': 0.19148936170212766, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25757575757575757, 'r': 0.3695652173913043, 'f1': 0.30357142857142855}, 'combined': 0.15178571428571427, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.27586206896551724, 'f1': 0.3018867924528302}, 'combined': 0.2012578616352201, 'epoch': 11}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3091249669923422, 'r': 0.3173370154513418, 'f1': 0.3131771669341894}, 'combined': 0.23076212300413954, 'epoch': 11}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3375444187463703, 'r': 0.3472812769794387, 'f1': 0.3423436284915794}, 'combined': 0.23844829845184637, 'epoch': 11}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2288135593220339, 'r': 0.38571428571428573, 'f1': 0.2872340425531915}, 'combined': 0.19148936170212766, 'epoch': 11}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26474047961800956, 'r': 0.3240182340675829, 'f1': 0.29139523780480575}, 'combined': 0.2147122804877516, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32541475117674507, 'r': 0.34573363573629207, 'f1': 0.33526661835256644}, 'combined': 0.23351903765850401, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2722222222222222, 'r': 0.532608695652174, 'f1': 0.36029411764705876}, 'combined': 0.18014705882352938, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27696660863807243, 'r': 0.31953642894107787, 'f1': 0.2967325075805252}, 'combined': 0.21864500558565014, 'epoch': 10}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34185545824681857, 'r': 0.32870717139117167, 'f1': 0.3351524100459005}, 'combined': 0.23343948958420932, 'epoch': 10}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4318181818181818, 'r': 0.3275862068965517, 'f1': 0.3725490196078432}, 'combined': 0.24836601307189546, 'epoch': 10}
******************************
Epoch: 12
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 18:12:31.537144: step: 2/470, loss: 1.6027824878692627
2023-01-22 18:12:32.288275: step: 4/470, loss: 0.513495922088623
2023-01-22 18:12:33.003171: step: 6/470, loss: 0.4840008020401001
2023-01-22 18:12:33.775028: step: 8/470, loss: 0.2687922716140747
2023-01-22 18:12:34.555335: step: 10/470, loss: 0.8560855388641357
2023-01-22 18:12:35.444248: step: 12/470, loss: 0.17021265625953674
2023-01-22 18:12:36.227771: step: 14/470, loss: 0.18634700775146484
2023-01-22 18:12:36.917051: step: 16/470, loss: 0.05369818955659866
2023-01-22 18:12:37.688471: step: 18/470, loss: 0.19231680035591125
2023-01-22 18:12:38.442025: step: 20/470, loss: 0.19430579245090485
2023-01-22 18:12:39.173962: step: 22/470, loss: 0.7491946220397949
2023-01-22 18:12:39.984393: step: 24/470, loss: 0.19225333631038666
2023-01-22 18:12:40.718683: step: 26/470, loss: 0.32709619402885437
2023-01-22 18:12:41.406870: step: 28/470, loss: 0.1636715531349182
2023-01-22 18:12:42.211823: step: 30/470, loss: 0.08695600926876068
2023-01-22 18:12:42.930852: step: 32/470, loss: 0.33848845958709717
2023-01-22 18:12:43.687991: step: 34/470, loss: 0.039047807455062866
2023-01-22 18:12:44.481509: step: 36/470, loss: 0.09349209070205688
2023-01-22 18:12:45.203818: step: 38/470, loss: 0.12132520228624344
2023-01-22 18:12:45.977897: step: 40/470, loss: 0.24875620007514954
2023-01-22 18:12:46.814774: step: 42/470, loss: 0.37038731575012207
2023-01-22 18:12:47.539647: step: 44/470, loss: 0.14126403629779816
2023-01-22 18:12:48.279711: step: 46/470, loss: 0.41059553623199463
2023-01-22 18:12:48.997436: step: 48/470, loss: 0.09567522257566452
2023-01-22 18:12:49.810987: step: 50/470, loss: 0.20272527635097504
2023-01-22 18:12:50.588528: step: 52/470, loss: 0.13555192947387695
2023-01-22 18:12:51.356294: step: 54/470, loss: 0.08126991242170334
2023-01-22 18:12:52.122844: step: 56/470, loss: 0.13052316009998322
2023-01-22 18:12:52.825028: step: 58/470, loss: 0.08066800236701965
2023-01-22 18:12:53.583323: step: 60/470, loss: 0.17245280742645264
2023-01-22 18:12:54.311518: step: 62/470, loss: 0.3052728772163391
2023-01-22 18:12:55.115318: step: 64/470, loss: 0.3907634913921356
2023-01-22 18:12:55.919770: step: 66/470, loss: 0.2599896192550659
2023-01-22 18:12:56.632461: step: 68/470, loss: 0.141568124294281
2023-01-22 18:12:57.359191: step: 70/470, loss: 0.10497156530618668
2023-01-22 18:12:58.147225: step: 72/470, loss: 0.2574126124382019
2023-01-22 18:12:58.869845: step: 74/470, loss: 0.18920814990997314
2023-01-22 18:12:59.606753: step: 76/470, loss: 0.20635807514190674
2023-01-22 18:13:00.277853: step: 78/470, loss: 0.11566061526536942
2023-01-22 18:13:01.088973: step: 80/470, loss: 0.11462550610303879
2023-01-22 18:13:01.847800: step: 82/470, loss: 0.3002080023288727
2023-01-22 18:13:02.552987: step: 84/470, loss: 0.13464710116386414
2023-01-22 18:13:03.291821: step: 86/470, loss: 0.044168468564748764
2023-01-22 18:13:04.128668: step: 88/470, loss: 0.29472196102142334
2023-01-22 18:13:04.914211: step: 90/470, loss: 0.20468667149543762
2023-01-22 18:13:05.686867: step: 92/470, loss: 0.2128215730190277
2023-01-22 18:13:06.428851: step: 94/470, loss: 0.03551870957016945
2023-01-22 18:13:07.091656: step: 96/470, loss: 0.050920166075229645
2023-01-22 18:13:07.870726: step: 98/470, loss: 0.13329026103019714
2023-01-22 18:13:08.610663: step: 100/470, loss: 0.04325414076447487
2023-01-22 18:13:09.332443: step: 102/470, loss: 0.5133774876594543
2023-01-22 18:13:10.052122: step: 104/470, loss: 0.19939365983009338
2023-01-22 18:13:10.769594: step: 106/470, loss: 0.14586398005485535
2023-01-22 18:13:11.408620: step: 108/470, loss: 0.49300411343574524
2023-01-22 18:13:12.119230: step: 110/470, loss: 0.22268635034561157
2023-01-22 18:13:12.872413: step: 112/470, loss: 0.07112699747085571
2023-01-22 18:13:13.662649: step: 114/470, loss: 0.8724595308303833
2023-01-22 18:13:14.416892: step: 116/470, loss: 0.040853098034858704
2023-01-22 18:13:15.177766: step: 118/470, loss: 0.11627252399921417
2023-01-22 18:13:15.859491: step: 120/470, loss: 0.44871455430984497
2023-01-22 18:13:16.591361: step: 122/470, loss: 0.10901898890733719
2023-01-22 18:13:17.296176: step: 124/470, loss: 0.1313031166791916
2023-01-22 18:13:18.022330: step: 126/470, loss: 0.35010117292404175
2023-01-22 18:13:18.775411: step: 128/470, loss: 0.20002852380275726
2023-01-22 18:13:19.507213: step: 130/470, loss: 0.21068109571933746
2023-01-22 18:13:20.238217: step: 132/470, loss: 0.07485038787126541
2023-01-22 18:13:20.998323: step: 134/470, loss: 0.20554983615875244
2023-01-22 18:13:21.775344: step: 136/470, loss: 0.09597218781709671
2023-01-22 18:13:22.549749: step: 138/470, loss: 0.1307460069656372
2023-01-22 18:13:23.310269: step: 140/470, loss: 0.0812094509601593
2023-01-22 18:13:24.027440: step: 142/470, loss: 0.2051864117383957
2023-01-22 18:13:24.751501: step: 144/470, loss: 0.22790312767028809
2023-01-22 18:13:25.410164: step: 146/470, loss: 0.07648234069347382
2023-01-22 18:13:26.138567: step: 148/470, loss: 0.45176663994789124
2023-01-22 18:13:26.905712: step: 150/470, loss: 0.17060501873493195
2023-01-22 18:13:27.609990: step: 152/470, loss: 0.1733158975839615
2023-01-22 18:13:28.453634: step: 154/470, loss: 0.10912138223648071
2023-01-22 18:13:29.213215: step: 156/470, loss: 0.15763217210769653
2023-01-22 18:13:29.955207: step: 158/470, loss: 0.40257176756858826
2023-01-22 18:13:30.706772: step: 160/470, loss: 0.30875569581985474
2023-01-22 18:13:31.467264: step: 162/470, loss: 0.8680994510650635
2023-01-22 18:13:32.242206: step: 164/470, loss: 0.2595478892326355
2023-01-22 18:13:32.994840: step: 166/470, loss: 0.06596395373344421
2023-01-22 18:13:33.712494: step: 168/470, loss: 0.12518943846225739
2023-01-22 18:13:34.432383: step: 170/470, loss: 0.24903565645217896
2023-01-22 18:13:35.218198: step: 172/470, loss: 0.1930832415819168
2023-01-22 18:13:35.957308: step: 174/470, loss: 0.021100223064422607
2023-01-22 18:13:36.725868: step: 176/470, loss: 0.23497158288955688
2023-01-22 18:13:37.579861: step: 178/470, loss: 0.1109008640050888
2023-01-22 18:13:38.330370: step: 180/470, loss: 0.35954418778419495
2023-01-22 18:13:39.062655: step: 182/470, loss: 0.11698159575462341
2023-01-22 18:13:39.742008: step: 184/470, loss: 0.10983223468065262
2023-01-22 18:13:40.496304: step: 186/470, loss: 0.12484107166528702
2023-01-22 18:13:41.262591: step: 188/470, loss: 0.19515368342399597
2023-01-22 18:13:41.994779: step: 190/470, loss: 0.26054152846336365
2023-01-22 18:13:42.691412: step: 192/470, loss: 0.14039883017539978
2023-01-22 18:13:43.352640: step: 194/470, loss: 0.16187353432178497
2023-01-22 18:13:44.025659: step: 196/470, loss: 0.14299781620502472
2023-01-22 18:13:44.741411: step: 198/470, loss: 0.21850766241550446
2023-01-22 18:13:45.505448: step: 200/470, loss: 0.18616288900375366
2023-01-22 18:13:46.222567: step: 202/470, loss: 0.08063409477472305
2023-01-22 18:13:46.896678: step: 204/470, loss: 0.061108168214559555
2023-01-22 18:13:47.605609: step: 206/470, loss: 0.10571593791246414
2023-01-22 18:13:48.383947: step: 208/470, loss: 0.5858561992645264
2023-01-22 18:13:49.070159: step: 210/470, loss: 0.0865621417760849
2023-01-22 18:13:49.768124: step: 212/470, loss: 0.3058476150035858
2023-01-22 18:13:50.434789: step: 214/470, loss: 0.30787721276283264
2023-01-22 18:13:51.168055: step: 216/470, loss: 0.05481060966849327
2023-01-22 18:13:51.837337: step: 218/470, loss: 0.1102779284119606
2023-01-22 18:13:52.592505: step: 220/470, loss: 0.21178603172302246
2023-01-22 18:13:53.376474: step: 222/470, loss: 0.10403713583946228
2023-01-22 18:13:54.241194: step: 224/470, loss: 0.6571042537689209
2023-01-22 18:13:54.971723: step: 226/470, loss: 0.10259111225605011
2023-01-22 18:13:55.650033: step: 228/470, loss: 0.1595088392496109
2023-01-22 18:13:56.422279: step: 230/470, loss: 0.17050521075725555
2023-01-22 18:13:57.181457: step: 232/470, loss: 0.5048624873161316
2023-01-22 18:13:57.989767: step: 234/470, loss: 0.20384322106838226
2023-01-22 18:13:58.732008: step: 236/470, loss: 0.11227284371852875
2023-01-22 18:13:59.496798: step: 238/470, loss: 0.07610318064689636
2023-01-22 18:14:00.221149: step: 240/470, loss: 0.4045836627483368
2023-01-22 18:14:00.965009: step: 242/470, loss: 0.068994902074337
2023-01-22 18:14:01.672204: step: 244/470, loss: 0.14514769613742828
2023-01-22 18:14:02.447251: step: 246/470, loss: 0.06832067668437958
2023-01-22 18:14:03.194508: step: 248/470, loss: 0.415750116109848
2023-01-22 18:14:03.932197: step: 250/470, loss: 0.2067742943763733
2023-01-22 18:14:04.747594: step: 252/470, loss: 0.3949142098426819
2023-01-22 18:14:05.492270: step: 254/470, loss: 0.09282752871513367
2023-01-22 18:14:06.261480: step: 256/470, loss: 0.2223929464817047
2023-01-22 18:14:07.007911: step: 258/470, loss: 0.252516508102417
2023-01-22 18:14:07.779311: step: 260/470, loss: 2.0077507495880127
2023-01-22 18:14:08.586139: step: 262/470, loss: 0.5033937096595764
2023-01-22 18:14:09.288165: step: 264/470, loss: 0.14328442513942719
2023-01-22 18:14:09.992658: step: 266/470, loss: 0.30592918395996094
2023-01-22 18:14:10.723949: step: 268/470, loss: 0.15917566418647766
2023-01-22 18:14:11.411566: step: 270/470, loss: 0.14353780448436737
2023-01-22 18:14:12.161821: step: 272/470, loss: 0.064031682908535
2023-01-22 18:14:13.052319: step: 274/470, loss: 0.19164782762527466
2023-01-22 18:14:13.740613: step: 276/470, loss: 0.1831219345331192
2023-01-22 18:14:14.565437: step: 278/470, loss: 0.10314060747623444
2023-01-22 18:14:15.312831: step: 280/470, loss: 0.11051566898822784
2023-01-22 18:14:16.095694: step: 282/470, loss: 0.12450094521045685
2023-01-22 18:14:17.005277: step: 284/470, loss: 0.19194933772087097
2023-01-22 18:14:17.742309: step: 286/470, loss: 0.3615543842315674
2023-01-22 18:14:18.432034: step: 288/470, loss: 0.07781562954187393
2023-01-22 18:14:19.195737: step: 290/470, loss: 0.12711076438426971
2023-01-22 18:14:19.921430: step: 292/470, loss: 0.5902228951454163
2023-01-22 18:14:20.631058: step: 294/470, loss: 0.4633359909057617
2023-01-22 18:14:21.462091: step: 296/470, loss: 0.14595328271389008
2023-01-22 18:14:22.187563: step: 298/470, loss: 0.18961495161056519
2023-01-22 18:14:22.879496: step: 300/470, loss: 1.7901432514190674
2023-01-22 18:14:23.656196: step: 302/470, loss: 0.1573238968849182
2023-01-22 18:14:24.428666: step: 304/470, loss: 2.244335651397705
2023-01-22 18:14:25.078698: step: 306/470, loss: 0.12172958999872208
2023-01-22 18:14:25.845123: step: 308/470, loss: 0.07545558363199234
2023-01-22 18:14:26.596498: step: 310/470, loss: 0.0413089245557785
2023-01-22 18:14:27.323657: step: 312/470, loss: 0.3559807538986206
2023-01-22 18:14:28.063896: step: 314/470, loss: 0.08101952075958252
2023-01-22 18:14:28.775759: step: 316/470, loss: 0.1672833114862442
2023-01-22 18:14:29.446201: step: 318/470, loss: 0.16862982511520386
2023-01-22 18:14:30.207740: step: 320/470, loss: 0.06150231882929802
2023-01-22 18:14:31.024306: step: 322/470, loss: 0.10682566463947296
2023-01-22 18:14:31.762402: step: 324/470, loss: 0.233676478266716
2023-01-22 18:14:32.627618: step: 326/470, loss: 0.17197014391422272
2023-01-22 18:14:33.375538: step: 328/470, loss: 0.3912794589996338
2023-01-22 18:14:34.140630: step: 330/470, loss: 0.4253474771976471
2023-01-22 18:14:34.845077: step: 332/470, loss: 0.15210644900798798
2023-01-22 18:14:35.657345: step: 334/470, loss: 0.2834761440753937
2023-01-22 18:14:36.420972: step: 336/470, loss: 0.09623689949512482
2023-01-22 18:14:37.248332: step: 338/470, loss: 0.32247433066368103
2023-01-22 18:14:37.933117: step: 340/470, loss: 0.059781987220048904
2023-01-22 18:14:38.646017: step: 342/470, loss: 0.2658904492855072
2023-01-22 18:14:39.428579: step: 344/470, loss: 0.3153829872608185
2023-01-22 18:14:40.148868: step: 346/470, loss: 0.08230673521757126
2023-01-22 18:14:40.934470: step: 348/470, loss: 0.17258965969085693
2023-01-22 18:14:41.650331: step: 350/470, loss: 0.28981152176856995
2023-01-22 18:14:42.255623: step: 352/470, loss: 0.1635764241218567
2023-01-22 18:14:42.994632: step: 354/470, loss: 0.21193452179431915
2023-01-22 18:14:43.669443: step: 356/470, loss: 0.07874863594770432
2023-01-22 18:14:44.409748: step: 358/470, loss: 0.09164706617593765
2023-01-22 18:14:45.168441: step: 360/470, loss: 5.99439811706543
2023-01-22 18:14:45.898108: step: 362/470, loss: 0.16293644905090332
2023-01-22 18:14:46.628516: step: 364/470, loss: 0.09890060126781464
2023-01-22 18:14:47.328034: step: 366/470, loss: 0.21786588430404663
2023-01-22 18:14:48.064312: step: 368/470, loss: 0.33316826820373535
2023-01-22 18:14:48.823254: step: 370/470, loss: 0.055760059505701065
2023-01-22 18:14:49.522529: step: 372/470, loss: 0.3406805098056793
2023-01-22 18:14:50.304430: step: 374/470, loss: 0.6691519021987915
2023-01-22 18:14:50.979094: step: 376/470, loss: 0.0685260146856308
2023-01-22 18:14:51.734401: step: 378/470, loss: 0.12233281135559082
2023-01-22 18:14:52.374373: step: 380/470, loss: 0.14288434386253357
2023-01-22 18:14:53.100473: step: 382/470, loss: 0.19023549556732178
2023-01-22 18:14:53.807078: step: 384/470, loss: 0.08775024116039276
2023-01-22 18:14:54.485537: step: 386/470, loss: 0.27361616492271423
2023-01-22 18:14:55.262078: step: 388/470, loss: 0.13204854726791382
2023-01-22 18:14:55.993164: step: 390/470, loss: 0.18165439367294312
2023-01-22 18:14:56.868985: step: 392/470, loss: 0.12773683667182922
2023-01-22 18:14:57.639613: step: 394/470, loss: 0.0818340927362442
2023-01-22 18:14:58.385165: step: 396/470, loss: 0.1057894304394722
2023-01-22 18:14:59.107510: step: 398/470, loss: 0.5085698366165161
2023-01-22 18:14:59.800485: step: 400/470, loss: 0.05038611590862274
2023-01-22 18:15:00.493810: step: 402/470, loss: 0.168458491563797
2023-01-22 18:15:01.269380: step: 404/470, loss: 0.18103928864002228
2023-01-22 18:15:01.950820: step: 406/470, loss: 0.18114416301250458
2023-01-22 18:15:02.702144: step: 408/470, loss: 0.13039417564868927
2023-01-22 18:15:03.439248: step: 410/470, loss: 0.12932468950748444
2023-01-22 18:15:04.172476: step: 412/470, loss: 0.30325838923454285
2023-01-22 18:15:04.939894: step: 414/470, loss: 0.3485577702522278
2023-01-22 18:15:05.626540: step: 416/470, loss: 0.2910950183868408
2023-01-22 18:15:06.373003: step: 418/470, loss: 0.12932966649532318
2023-01-22 18:15:07.081214: step: 420/470, loss: 0.08383800089359283
2023-01-22 18:15:07.767677: step: 422/470, loss: 0.17576591670513153
2023-01-22 18:15:08.451479: step: 424/470, loss: 0.1013016402721405
2023-01-22 18:15:09.122963: step: 426/470, loss: 0.2601459324359894
2023-01-22 18:15:10.029948: step: 428/470, loss: 0.09860192984342575
2023-01-22 18:15:10.731861: step: 430/470, loss: 0.12635904550552368
2023-01-22 18:15:11.495857: step: 432/470, loss: 0.08993472903966904
2023-01-22 18:15:12.160839: step: 434/470, loss: 0.2409133017063141
2023-01-22 18:15:12.963911: step: 436/470, loss: 0.7562994956970215
2023-01-22 18:15:13.684817: step: 438/470, loss: 0.14493654668331146
2023-01-22 18:15:14.426297: step: 440/470, loss: 0.2697089910507202
2023-01-22 18:15:15.133700: step: 442/470, loss: 0.17629806697368622
2023-01-22 18:15:15.879406: step: 444/470, loss: 0.3165607452392578
2023-01-22 18:15:16.632326: step: 446/470, loss: 0.24010397493839264
2023-01-22 18:15:17.367725: step: 448/470, loss: 0.08545230329036713
2023-01-22 18:15:18.111349: step: 450/470, loss: 0.24912571907043457
2023-01-22 18:15:18.953924: step: 452/470, loss: 0.42028677463531494
2023-01-22 18:15:19.664672: step: 454/470, loss: 0.12412894517183304
2023-01-22 18:15:20.397866: step: 456/470, loss: 0.07028322666883469
2023-01-22 18:15:21.060521: step: 458/470, loss: 0.045641541481018066
2023-01-22 18:15:21.770459: step: 460/470, loss: 0.2509128451347351
2023-01-22 18:15:22.497615: step: 462/470, loss: 0.7367977499961853
2023-01-22 18:15:23.183304: step: 464/470, loss: 0.09236481040716171
2023-01-22 18:15:23.977018: step: 466/470, loss: 0.1762775182723999
2023-01-22 18:15:24.673299: step: 468/470, loss: 0.12322688847780228
2023-01-22 18:15:25.420682: step: 470/470, loss: 0.1871875375509262
2023-01-22 18:15:26.197583: step: 472/470, loss: 0.17395652830600739
2023-01-22 18:15:26.936920: step: 474/470, loss: 0.5580199956893921
2023-01-22 18:15:27.676250: step: 476/470, loss: 0.11032622307538986
2023-01-22 18:15:28.380428: step: 478/470, loss: 0.0684078112244606
2023-01-22 18:15:29.107805: step: 480/470, loss: 0.12853725254535675
2023-01-22 18:15:29.835725: step: 482/470, loss: 0.11245977878570557
2023-01-22 18:15:30.586236: step: 484/470, loss: 0.44150134921073914
2023-01-22 18:15:31.300207: step: 486/470, loss: 0.10275861620903015
2023-01-22 18:15:31.997174: step: 488/470, loss: 1.2313703298568726
2023-01-22 18:15:32.777895: step: 490/470, loss: 0.16322949528694153
2023-01-22 18:15:33.461229: step: 492/470, loss: 0.23350676894187927
2023-01-22 18:15:34.171616: step: 494/470, loss: 0.16384433209896088
2023-01-22 18:15:34.922211: step: 496/470, loss: 0.22567422688007355
2023-01-22 18:15:35.680538: step: 498/470, loss: 0.568155825138092
2023-01-22 18:15:36.525394: step: 500/470, loss: 0.2018314152956009
2023-01-22 18:15:37.251959: step: 502/470, loss: 0.30602437257766724
2023-01-22 18:15:37.962522: step: 504/470, loss: 0.5151650905609131
2023-01-22 18:15:38.689860: step: 506/470, loss: 0.1632133275270462
2023-01-22 18:15:39.412186: step: 508/470, loss: 0.39310041069984436
2023-01-22 18:15:40.264002: step: 510/470, loss: 0.32889223098754883
2023-01-22 18:15:41.041029: step: 512/470, loss: 0.16092555224895477
2023-01-22 18:15:41.773260: step: 514/470, loss: 0.0802043080329895
2023-01-22 18:15:42.418937: step: 516/470, loss: 0.4701124131679535
2023-01-22 18:15:43.136626: step: 518/470, loss: 0.33139216899871826
2023-01-22 18:15:43.857401: step: 520/470, loss: 0.19706635177135468
2023-01-22 18:15:44.631286: step: 522/470, loss: 1.2813704013824463
2023-01-22 18:15:45.314722: step: 524/470, loss: 0.16043278574943542
2023-01-22 18:15:46.025942: step: 526/470, loss: 0.2318851202726364
2023-01-22 18:15:46.798311: step: 528/470, loss: 0.5282825827598572
2023-01-22 18:15:47.577621: step: 530/470, loss: 0.19871442019939423
2023-01-22 18:15:48.272845: step: 532/470, loss: 0.08099329471588135
2023-01-22 18:15:48.996894: step: 534/470, loss: 0.03250506892800331
2023-01-22 18:15:49.679968: step: 536/470, loss: 0.25197839736938477
2023-01-22 18:15:50.453160: step: 538/470, loss: 0.11561629921197891
2023-01-22 18:15:51.201066: step: 540/470, loss: 0.24496881663799286
2023-01-22 18:15:51.944403: step: 542/470, loss: 0.13660961389541626
2023-01-22 18:15:52.624144: step: 544/470, loss: 0.15981179475784302
2023-01-22 18:15:53.310572: step: 546/470, loss: 0.5604614019393921
2023-01-22 18:15:54.070571: step: 548/470, loss: 0.1567903310060501
2023-01-22 18:15:54.814510: step: 550/470, loss: 0.3064483404159546
2023-01-22 18:15:55.551226: step: 552/470, loss: 0.2242286205291748
2023-01-22 18:15:56.286138: step: 554/470, loss: 0.06868718564510345
2023-01-22 18:15:57.057402: step: 556/470, loss: 0.40813806653022766
2023-01-22 18:15:57.789376: step: 558/470, loss: 0.36897414922714233
2023-01-22 18:15:58.502525: step: 560/470, loss: 0.1006973534822464
2023-01-22 18:15:59.280921: step: 562/470, loss: 0.09448845684528351
2023-01-22 18:16:00.067186: step: 564/470, loss: 0.7840608954429626
2023-01-22 18:16:00.845821: step: 566/470, loss: 0.22917340695858002
2023-01-22 18:16:01.564170: step: 568/470, loss: 0.07258880138397217
2023-01-22 18:16:02.288409: step: 570/470, loss: 0.17850033938884735
2023-01-22 18:16:03.090745: step: 572/470, loss: 0.19725555181503296
2023-01-22 18:16:03.853776: step: 574/470, loss: 0.08748982846736908
2023-01-22 18:16:04.773270: step: 576/470, loss: 0.1885845810174942
2023-01-22 18:16:05.486898: step: 578/470, loss: 0.21629391610622406
2023-01-22 18:16:06.205758: step: 580/470, loss: 0.1099558100104332
2023-01-22 18:16:06.915773: step: 582/470, loss: 0.07752203196287155
2023-01-22 18:16:07.735798: step: 584/470, loss: 0.21718913316726685
2023-01-22 18:16:08.519213: step: 586/470, loss: 0.11684189736843109
2023-01-22 18:16:09.212615: step: 588/470, loss: 0.14402146637439728
2023-01-22 18:16:10.058843: step: 590/470, loss: 0.30400651693344116
2023-01-22 18:16:10.737128: step: 592/470, loss: 0.14186808466911316
2023-01-22 18:16:11.424156: step: 594/470, loss: 0.15555933117866516
2023-01-22 18:16:12.139768: step: 596/470, loss: 0.1906273365020752
2023-01-22 18:16:12.956461: step: 598/470, loss: 1.0738638639450073
2023-01-22 18:16:13.706108: step: 600/470, loss: 0.3519884943962097
2023-01-22 18:16:14.453470: step: 602/470, loss: 0.1826198250055313
2023-01-22 18:16:15.154584: step: 604/470, loss: 0.07761722803115845
2023-01-22 18:16:16.182286: step: 606/470, loss: 0.15749958157539368
2023-01-22 18:16:16.978171: step: 608/470, loss: 0.3068345785140991
2023-01-22 18:16:17.675652: step: 610/470, loss: 0.12547728419303894
2023-01-22 18:16:18.384908: step: 612/470, loss: 0.2842352092266083
2023-01-22 18:16:19.094394: step: 614/470, loss: 0.6424673795700073
2023-01-22 18:16:19.845829: step: 616/470, loss: 0.13101936876773834
2023-01-22 18:16:20.663450: step: 618/470, loss: 0.12014391273260117
2023-01-22 18:16:21.368453: step: 620/470, loss: 0.33476048707962036
2023-01-22 18:16:22.097685: step: 622/470, loss: 0.1459568589925766
2023-01-22 18:16:23.038847: step: 624/470, loss: 0.1385248303413391
2023-01-22 18:16:23.770611: step: 626/470, loss: 0.21259213984012604
2023-01-22 18:16:24.469772: step: 628/470, loss: 0.4322361946105957
2023-01-22 18:16:25.175134: step: 630/470, loss: 0.03826691210269928
2023-01-22 18:16:25.889459: step: 632/470, loss: 0.23468813300132751
2023-01-22 18:16:26.593299: step: 634/470, loss: 0.7665181756019592
2023-01-22 18:16:27.338876: step: 636/470, loss: 0.4738726317882538
2023-01-22 18:16:27.996710: step: 638/470, loss: 0.12215352058410645
2023-01-22 18:16:28.688387: step: 640/470, loss: 0.0886230543255806
2023-01-22 18:16:29.401387: step: 642/470, loss: 0.25113239884376526
2023-01-22 18:16:30.172655: step: 644/470, loss: 1.358510136604309
2023-01-22 18:16:30.915324: step: 646/470, loss: 0.02677135542035103
2023-01-22 18:16:31.616578: step: 648/470, loss: 0.0627710297703743
2023-01-22 18:16:32.365910: step: 650/470, loss: 0.17032356560230255
2023-01-22 18:16:33.074214: step: 652/470, loss: 0.14521194994449615
2023-01-22 18:16:33.802347: step: 654/470, loss: 0.10609611868858337
2023-01-22 18:16:34.589307: step: 656/470, loss: 0.18908576667308807
2023-01-22 18:16:35.353153: step: 658/470, loss: 0.2079189121723175
2023-01-22 18:16:36.106597: step: 660/470, loss: 1.0469714403152466
2023-01-22 18:16:36.865776: step: 662/470, loss: 0.32972848415374756
2023-01-22 18:16:37.655069: step: 664/470, loss: 0.28195086121559143
2023-01-22 18:16:38.426238: step: 666/470, loss: 0.16927146911621094
2023-01-22 18:16:39.225198: step: 668/470, loss: 0.0880625993013382
2023-01-22 18:16:40.021297: step: 670/470, loss: 0.3091566264629364
2023-01-22 18:16:40.759665: step: 672/470, loss: 0.13625238835811615
2023-01-22 18:16:41.524358: step: 674/470, loss: 0.16259387135505676
2023-01-22 18:16:42.311500: step: 676/470, loss: 0.10333267599344254
2023-01-22 18:16:43.089235: step: 678/470, loss: 0.08288844674825668
2023-01-22 18:16:43.743305: step: 680/470, loss: 0.1420072615146637
2023-01-22 18:16:44.468514: step: 682/470, loss: 0.23318932950496674
2023-01-22 18:16:45.289652: step: 684/470, loss: 0.16551189124584198
2023-01-22 18:16:46.128707: step: 686/470, loss: 0.1825304627418518
2023-01-22 18:16:46.816071: step: 688/470, loss: 0.3301374614238739
2023-01-22 18:16:47.555125: step: 690/470, loss: 0.24686174094676971
2023-01-22 18:16:48.268492: step: 692/470, loss: 0.1321008801460266
2023-01-22 18:16:48.902874: step: 694/470, loss: 0.163587749004364
2023-01-22 18:16:49.570862: step: 696/470, loss: 0.24472731351852417
2023-01-22 18:16:50.270812: step: 698/470, loss: 0.05031857639551163
2023-01-22 18:16:50.990322: step: 700/470, loss: 0.5361093282699585
2023-01-22 18:16:51.693665: step: 702/470, loss: 0.12264763563871384
2023-01-22 18:16:52.390914: step: 704/470, loss: 0.6803569197654724
2023-01-22 18:16:53.156410: step: 706/470, loss: 0.14722055196762085
2023-01-22 18:16:53.886055: step: 708/470, loss: 0.33901581168174744
2023-01-22 18:16:54.629174: step: 710/470, loss: 0.10217005759477615
2023-01-22 18:16:55.330462: step: 712/470, loss: 0.11541683226823807
2023-01-22 18:16:56.073633: step: 714/470, loss: 0.19055843353271484
2023-01-22 18:16:56.812101: step: 716/470, loss: 0.14943887293338776
2023-01-22 18:16:57.566925: step: 718/470, loss: 0.5411022901535034
2023-01-22 18:16:58.236991: step: 720/470, loss: 0.10385146737098694
2023-01-22 18:16:58.954074: step: 722/470, loss: 0.1555739790201187
2023-01-22 18:16:59.630608: step: 724/470, loss: 0.27904900908470154
2023-01-22 18:17:00.431265: step: 726/470, loss: 0.13543671369552612
2023-01-22 18:17:01.183844: step: 728/470, loss: 0.0534023754298687
2023-01-22 18:17:01.877712: step: 730/470, loss: 0.23771588504314423
2023-01-22 18:17:02.667842: step: 732/470, loss: 0.12300637364387512
2023-01-22 18:17:03.371460: step: 734/470, loss: 0.08528205752372742
2023-01-22 18:17:04.124417: step: 736/470, loss: 0.41384363174438477
2023-01-22 18:17:04.912027: step: 738/470, loss: 0.11085784435272217
2023-01-22 18:17:05.682591: step: 740/470, loss: 0.4100949168205261
2023-01-22 18:17:06.440847: step: 742/470, loss: 0.5684028267860413
2023-01-22 18:17:07.236230: step: 744/470, loss: 0.21597033739089966
2023-01-22 18:17:07.942319: step: 746/470, loss: 0.1797659546136856
2023-01-22 18:17:08.672825: step: 748/470, loss: 0.12278896570205688
2023-01-22 18:17:09.390562: step: 750/470, loss: 0.06112644821405411
2023-01-22 18:17:10.053407: step: 752/470, loss: 0.13294389843940735
2023-01-22 18:17:10.706487: step: 754/470, loss: 0.4018506109714508
2023-01-22 18:17:11.453433: step: 756/470, loss: 0.312796026468277
2023-01-22 18:17:12.172548: step: 758/470, loss: 0.17056278884410858
2023-01-22 18:17:12.871831: step: 760/470, loss: 0.12827859818935394
2023-01-22 18:17:13.674896: step: 762/470, loss: 0.3029170036315918
2023-01-22 18:17:14.314080: step: 764/470, loss: 0.08240678906440735
2023-01-22 18:17:14.988176: step: 766/470, loss: 0.18388421833515167
2023-01-22 18:17:15.745485: step: 768/470, loss: 0.05635695904493332
2023-01-22 18:17:16.462629: step: 770/470, loss: 0.3035624027252197
2023-01-22 18:17:17.271606: step: 772/470, loss: 0.0933908224105835
2023-01-22 18:17:18.015780: step: 774/470, loss: 0.15930312871932983
2023-01-22 18:17:18.747627: step: 776/470, loss: 0.5322938561439514
2023-01-22 18:17:19.560968: step: 778/470, loss: 0.34571999311447144
2023-01-22 18:17:20.330371: step: 780/470, loss: 0.14167526364326477
2023-01-22 18:17:21.071538: step: 782/470, loss: 0.08634297549724579
2023-01-22 18:17:21.769123: step: 784/470, loss: 3.5037174224853516
2023-01-22 18:17:22.576909: step: 786/470, loss: 0.16057580709457397
2023-01-22 18:17:23.264752: step: 788/470, loss: 0.10480234026908875
2023-01-22 18:17:23.963002: step: 790/470, loss: 0.40698543190956116
2023-01-22 18:17:24.700753: step: 792/470, loss: 0.2794446647167206
2023-01-22 18:17:25.405198: step: 794/470, loss: 0.14553791284561157
2023-01-22 18:17:26.086221: step: 796/470, loss: 0.05922282487154007
2023-01-22 18:17:26.816402: step: 798/470, loss: 0.25358933210372925
2023-01-22 18:17:27.544605: step: 800/470, loss: 0.07599953562021255
2023-01-22 18:17:28.217745: step: 802/470, loss: 0.11059369891881943
2023-01-22 18:17:28.882387: step: 804/470, loss: 0.22309422492980957
2023-01-22 18:17:29.599515: step: 806/470, loss: 0.07817824929952621
2023-01-22 18:17:30.337983: step: 808/470, loss: 0.24265766143798828
2023-01-22 18:17:31.109711: step: 810/470, loss: 0.02267645113170147
2023-01-22 18:17:31.900329: step: 812/470, loss: 0.16064167022705078
2023-01-22 18:17:32.571286: step: 814/470, loss: 0.18023733794689178
2023-01-22 18:17:33.340850: step: 816/470, loss: 0.13179604709148407
2023-01-22 18:17:34.104358: step: 818/470, loss: 0.28788211941719055
2023-01-22 18:17:34.846215: step: 820/470, loss: 0.11537092179059982
2023-01-22 18:17:35.619635: step: 822/470, loss: 0.12304264307022095
2023-01-22 18:17:36.381195: step: 824/470, loss: 0.20748859643936157
2023-01-22 18:17:37.190351: step: 826/470, loss: 0.19135302305221558
2023-01-22 18:17:37.930470: step: 828/470, loss: 0.1294027864933014
2023-01-22 18:17:38.614063: step: 830/470, loss: 0.15381257236003876
2023-01-22 18:17:39.352051: step: 832/470, loss: 0.09458699077367783
2023-01-22 18:17:40.066588: step: 834/470, loss: 0.10095732659101486
2023-01-22 18:17:40.799678: step: 836/470, loss: 0.12210088223218918
2023-01-22 18:17:41.494829: step: 838/470, loss: 0.12754324078559875
2023-01-22 18:17:42.243920: step: 840/470, loss: 0.12278389185667038
2023-01-22 18:17:43.044397: step: 842/470, loss: 0.10551811009645462
2023-01-22 18:17:43.806519: step: 844/470, loss: 0.13036848604679108
2023-01-22 18:17:44.532498: step: 846/470, loss: 0.598879873752594
2023-01-22 18:17:45.306108: step: 848/470, loss: 0.10476802289485931
2023-01-22 18:17:46.015731: step: 850/470, loss: 0.16438759863376617
2023-01-22 18:17:46.661588: step: 852/470, loss: 0.06739547103643417
2023-01-22 18:17:47.499781: step: 854/470, loss: 0.11674723029136658
2023-01-22 18:17:48.289873: step: 856/470, loss: 0.17071661353111267
2023-01-22 18:17:49.058220: step: 858/470, loss: 0.16365188360214233
2023-01-22 18:17:49.743456: step: 860/470, loss: 0.15071061253547668
2023-01-22 18:17:50.486952: step: 862/470, loss: 0.46078917384147644
2023-01-22 18:17:51.154986: step: 864/470, loss: 0.08874162286520004
2023-01-22 18:17:51.833720: step: 866/470, loss: 0.08609306067228317
2023-01-22 18:17:52.640883: step: 868/470, loss: 0.13420622050762177
2023-01-22 18:17:53.458510: step: 870/470, loss: 0.5047072172164917
2023-01-22 18:17:54.198792: step: 872/470, loss: 0.4354456961154938
2023-01-22 18:17:54.891878: step: 874/470, loss: 0.5482062101364136
2023-01-22 18:17:55.752493: step: 876/470, loss: 0.22582288086414337
2023-01-22 18:17:56.567684: step: 878/470, loss: 0.1643458604812622
2023-01-22 18:17:57.346093: step: 880/470, loss: 0.0947733074426651
2023-01-22 18:17:58.181075: step: 882/470, loss: 0.059879835695028305
2023-01-22 18:17:58.937035: step: 884/470, loss: 0.10321329534053802
2023-01-22 18:17:59.685653: step: 886/470, loss: 0.11775056272745132
2023-01-22 18:18:00.399657: step: 888/470, loss: 0.12950459122657776
2023-01-22 18:18:01.150930: step: 890/470, loss: 0.3330346941947937
2023-01-22 18:18:01.884974: step: 892/470, loss: 0.14579877257347107
2023-01-22 18:18:02.622518: step: 894/470, loss: 0.12271419167518616
2023-01-22 18:18:03.405429: step: 896/470, loss: 0.23777388036251068
2023-01-22 18:18:04.218686: step: 898/470, loss: 0.20127157866954803
2023-01-22 18:18:04.845684: step: 900/470, loss: 0.033625878393650055
2023-01-22 18:18:05.595608: step: 902/470, loss: 0.21832531690597534
2023-01-22 18:18:06.360316: step: 904/470, loss: 0.19224612414836884
2023-01-22 18:18:07.092715: step: 906/470, loss: 0.11556744575500488
2023-01-22 18:18:07.840113: step: 908/470, loss: 0.11261487007141113
2023-01-22 18:18:08.607739: step: 910/470, loss: 0.1271752119064331
2023-01-22 18:18:09.355858: step: 912/470, loss: 0.1272096335887909
2023-01-22 18:18:10.166765: step: 914/470, loss: 0.19481460750102997
2023-01-22 18:18:10.890187: step: 916/470, loss: 0.445446252822876
2023-01-22 18:18:11.698016: step: 918/470, loss: 0.1915096789598465
2023-01-22 18:18:12.383619: step: 920/470, loss: 0.11832750588655472
2023-01-22 18:18:13.112811: step: 922/470, loss: 0.43603986501693726
2023-01-22 18:18:13.945379: step: 924/470, loss: 0.20713625848293304
2023-01-22 18:18:14.745573: step: 926/470, loss: 0.3290116488933563
2023-01-22 18:18:15.561287: step: 928/470, loss: 1.042456865310669
2023-01-22 18:18:16.302494: step: 930/470, loss: 0.13364510238170624
2023-01-22 18:18:17.052147: step: 932/470, loss: 0.5061575770378113
2023-01-22 18:18:17.677840: step: 934/470, loss: 1.4723851680755615
2023-01-22 18:18:18.433273: step: 936/470, loss: 0.20052802562713623
2023-01-22 18:18:19.135735: step: 938/470, loss: 0.7012951970100403
2023-01-22 18:18:19.939977: step: 940/470, loss: 0.3045251667499542
2023-01-22 18:18:20.605626: step: 942/470, loss: 0.33923205733299255
==================================================
Loss: 0.263
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29459497821253666, 'r': 0.3281352034359754, 'f1': 0.31046185316114727}, 'combined': 0.22876136548716114, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34264664713865695, 'r': 0.34363505092848, 'f1': 0.3431401372689575}, 'combined': 0.23900308068484602, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2866659190590112, 'r': 0.3263748604087414, 'f1': 0.3052343415002781}, 'combined': 0.2249095147896786, 'epoch': 12}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3434021966950355, 'r': 0.3351473361975587, 'f1': 0.33922455439947546}, 'combined': 0.23627580903446055, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27355769230769234, 'r': 0.3337715297036929, 'f1': 0.3006796515450362}, 'combined': 0.22155342745423717, 'epoch': 12}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33771028169806255, 'r': 0.35621940290651405, 'f1': 0.34671799627774885}, 'combined': 0.24149512178549673, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20218894009216587, 'r': 0.3581632653061224, 'f1': 0.25846833578792333}, 'combined': 0.17231222385861555, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2236842105263158, 'r': 0.3695652173913043, 'f1': 0.2786885245901639}, 'combined': 0.13934426229508196, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3091249669923422, 'r': 0.3173370154513418, 'f1': 0.3131771669341894}, 'combined': 0.23076212300413954, 'epoch': 11}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3375444187463703, 'r': 0.3472812769794387, 'f1': 0.3423436284915794}, 'combined': 0.23844829845184637, 'epoch': 11}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2288135593220339, 'r': 0.38571428571428573, 'f1': 0.2872340425531915}, 'combined': 0.19148936170212766, 'epoch': 11}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26474047961800956, 'r': 0.3240182340675829, 'f1': 0.29139523780480575}, 'combined': 0.2147122804877516, 'epoch': 7}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32541475117674507, 'r': 0.34573363573629207, 'f1': 0.33526661835256644}, 'combined': 0.23351903765850401, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2722222222222222, 'r': 0.532608695652174, 'f1': 0.36029411764705876}, 'combined': 0.18014705882352938, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27696660863807243, 'r': 0.31953642894107787, 'f1': 0.2967325075805252}, 'combined': 0.21864500558565014, 'epoch': 10}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34185545824681857, 'r': 0.32870717139117167, 'f1': 0.3351524100459005}, 'combined': 0.23343948958420932, 'epoch': 10}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4318181818181818, 'r': 0.3275862068965517, 'f1': 0.3725490196078432}, 'combined': 0.24836601307189546, 'epoch': 10}
******************************
Epoch: 13
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 18:20:58.084099: step: 2/470, loss: 0.11869052797555923
2023-01-22 18:20:58.789040: step: 4/470, loss: 0.087203748524189
2023-01-22 18:20:59.505557: step: 6/470, loss: 0.1547858864068985
2023-01-22 18:21:00.250981: step: 8/470, loss: 0.24847088754177094
2023-01-22 18:21:00.942086: step: 10/470, loss: 0.4256363809108734
2023-01-22 18:21:01.704265: step: 12/470, loss: 0.09074677526950836
2023-01-22 18:21:02.438246: step: 14/470, loss: 0.19883684813976288
2023-01-22 18:21:03.157646: step: 16/470, loss: 0.2916736602783203
2023-01-22 18:21:03.973560: step: 18/470, loss: 0.08487699925899506
2023-01-22 18:21:04.894049: step: 20/470, loss: 0.37382224202156067
2023-01-22 18:21:05.641174: step: 22/470, loss: 0.05458125099539757
2023-01-22 18:21:06.433214: step: 24/470, loss: 0.07370239496231079
2023-01-22 18:21:07.195379: step: 26/470, loss: 0.19649724662303925
2023-01-22 18:21:07.949299: step: 28/470, loss: 0.14036303758621216
2023-01-22 18:21:08.679343: step: 30/470, loss: 0.12299536913633347
2023-01-22 18:21:09.425251: step: 32/470, loss: 0.13496029376983643
2023-01-22 18:21:10.182954: step: 34/470, loss: 0.07654550671577454
2023-01-22 18:21:10.918479: step: 36/470, loss: 0.12526889145374298
2023-01-22 18:21:11.697734: step: 38/470, loss: 0.08467797935009003
2023-01-22 18:21:12.447082: step: 40/470, loss: 0.10701703280210495
2023-01-22 18:21:13.116038: step: 42/470, loss: 0.30219635367393494
2023-01-22 18:21:13.847899: step: 44/470, loss: 0.09338068217039108
2023-01-22 18:21:14.539996: step: 46/470, loss: 0.5995178818702698
2023-01-22 18:21:15.332370: step: 48/470, loss: 0.10941080749034882
2023-01-22 18:21:16.087422: step: 50/470, loss: 0.20678047835826874
2023-01-22 18:21:16.794744: step: 52/470, loss: 0.05293460562825203
2023-01-22 18:21:17.469756: step: 54/470, loss: 0.7169974446296692
2023-01-22 18:21:18.181229: step: 56/470, loss: 0.12911155819892883
2023-01-22 18:21:18.942454: step: 58/470, loss: 0.10857953131198883
2023-01-22 18:21:19.706189: step: 60/470, loss: 0.11933538317680359
2023-01-22 18:21:20.449847: step: 62/470, loss: 0.09998290985822678
2023-01-22 18:21:21.203429: step: 64/470, loss: 0.14585649967193604
2023-01-22 18:21:21.986276: step: 66/470, loss: 0.1499679684638977
2023-01-22 18:21:22.839947: step: 68/470, loss: 0.05815058946609497
2023-01-22 18:21:23.568485: step: 70/470, loss: 0.060805968940258026
2023-01-22 18:21:24.310206: step: 72/470, loss: 0.6332342624664307
2023-01-22 18:21:24.986196: step: 74/470, loss: 0.03274387866258621
2023-01-22 18:21:25.754631: step: 76/470, loss: 0.15731528401374817
2023-01-22 18:21:26.429162: step: 78/470, loss: 0.12228990346193314
2023-01-22 18:21:27.226691: step: 80/470, loss: 0.2630844712257385
2023-01-22 18:21:27.933386: step: 82/470, loss: 0.285457044839859
2023-01-22 18:21:28.668001: step: 84/470, loss: 0.06887723505496979
2023-01-22 18:21:29.417345: step: 86/470, loss: 0.17145711183547974
2023-01-22 18:21:30.139881: step: 88/470, loss: 0.16493162512779236
2023-01-22 18:21:30.834721: step: 90/470, loss: 0.9345531463623047
2023-01-22 18:21:31.582185: step: 92/470, loss: 0.08099890500307083
2023-01-22 18:21:32.302272: step: 94/470, loss: 0.13539457321166992
2023-01-22 18:21:33.031983: step: 96/470, loss: 0.2658799886703491
2023-01-22 18:21:33.714715: step: 98/470, loss: 0.4507644772529602
2023-01-22 18:21:34.443698: step: 100/470, loss: 0.06587552279233932
2023-01-22 18:21:35.180753: step: 102/470, loss: 0.9483935832977295
2023-01-22 18:21:35.849696: step: 104/470, loss: 0.15638364851474762
2023-01-22 18:21:36.664033: step: 106/470, loss: 0.23561960458755493
2023-01-22 18:21:37.383283: step: 108/470, loss: 0.08107713609933853
2023-01-22 18:21:38.131622: step: 110/470, loss: 0.4484912157058716
2023-01-22 18:21:38.822746: step: 112/470, loss: 0.17864054441452026
2023-01-22 18:21:39.577615: step: 114/470, loss: 0.11197991669178009
2023-01-22 18:21:40.265497: step: 116/470, loss: 1.0874292850494385
2023-01-22 18:21:41.004306: step: 118/470, loss: 0.19661211967468262
2023-01-22 18:21:41.798210: step: 120/470, loss: 0.09106841683387756
2023-01-22 18:21:42.559778: step: 122/470, loss: 0.6079081296920776
2023-01-22 18:21:43.286312: step: 124/470, loss: 0.14605315029621124
2023-01-22 18:21:44.048889: step: 126/470, loss: 0.9814774990081787
2023-01-22 18:21:44.915733: step: 128/470, loss: 0.16904780268669128
2023-01-22 18:21:45.716713: step: 130/470, loss: 0.1599675416946411
2023-01-22 18:21:46.436702: step: 132/470, loss: 0.2830541431903839
2023-01-22 18:21:47.166225: step: 134/470, loss: 0.031339630484580994
2023-01-22 18:21:47.847048: step: 136/470, loss: 0.15232618153095245
2023-01-22 18:21:48.575849: step: 138/470, loss: 0.17885567247867584
2023-01-22 18:21:49.325724: step: 140/470, loss: 0.13249598443508148
2023-01-22 18:21:50.042698: step: 142/470, loss: 0.07661613076925278
2023-01-22 18:21:50.804076: step: 144/470, loss: 0.13011841475963593
2023-01-22 18:21:51.481645: step: 146/470, loss: 0.10363959521055222
2023-01-22 18:21:52.307286: step: 148/470, loss: 0.04361295700073242
2023-01-22 18:21:53.023177: step: 150/470, loss: 0.12805719673633575
2023-01-22 18:21:53.759868: step: 152/470, loss: 0.09809063374996185
2023-01-22 18:21:54.446544: step: 154/470, loss: 0.09070705622434616
2023-01-22 18:21:55.206321: step: 156/470, loss: 0.44800418615341187
2023-01-22 18:21:55.978120: step: 158/470, loss: 0.15312308073043823
2023-01-22 18:21:56.713739: step: 160/470, loss: 0.06737309694290161
2023-01-22 18:21:57.441148: step: 162/470, loss: 0.3796755075454712
2023-01-22 18:21:58.185714: step: 164/470, loss: 0.18876059353351593
2023-01-22 18:21:58.910364: step: 166/470, loss: 0.25417694449424744
2023-01-22 18:21:59.672748: step: 168/470, loss: 0.17342378199100494
2023-01-22 18:22:00.447650: step: 170/470, loss: 0.10127972066402435
2023-01-22 18:22:01.158205: step: 172/470, loss: 0.16987819969654083
2023-01-22 18:22:01.821488: step: 174/470, loss: 0.3513706624507904
2023-01-22 18:22:02.700722: step: 176/470, loss: 0.10086065530776978
2023-01-22 18:22:03.373339: step: 178/470, loss: 0.09717612713575363
2023-01-22 18:22:04.114576: step: 180/470, loss: 0.02228609286248684
2023-01-22 18:22:04.867812: step: 182/470, loss: 0.08578619360923767
2023-01-22 18:22:05.605440: step: 184/470, loss: 0.6068621277809143
2023-01-22 18:22:06.324544: step: 186/470, loss: 0.026224324479699135
2023-01-22 18:22:07.059829: step: 188/470, loss: 0.34837964177131653
2023-01-22 18:22:07.872590: step: 190/470, loss: 0.28307831287384033
2023-01-22 18:22:08.592788: step: 192/470, loss: 0.21804864704608917
2023-01-22 18:22:09.471389: step: 194/470, loss: 0.10385201871395111
2023-01-22 18:22:10.183242: step: 196/470, loss: 0.06404811888933182
2023-01-22 18:22:10.886132: step: 198/470, loss: 0.13678865134716034
2023-01-22 18:22:11.598732: step: 200/470, loss: 0.2867162823677063
2023-01-22 18:22:12.344535: step: 202/470, loss: 0.12509754300117493
2023-01-22 18:22:13.087114: step: 204/470, loss: 0.21526752412319183
2023-01-22 18:22:13.828082: step: 206/470, loss: 0.410299688577652
2023-01-22 18:22:14.518973: step: 208/470, loss: 0.1994316130876541
2023-01-22 18:22:15.317844: step: 210/470, loss: 0.21224021911621094
2023-01-22 18:22:16.146388: step: 212/470, loss: 1.471451759338379
2023-01-22 18:22:16.844241: step: 214/470, loss: 0.040065914392471313
2023-01-22 18:22:17.605118: step: 216/470, loss: 0.1329803615808487
2023-01-22 18:22:18.425700: step: 218/470, loss: 0.05075236037373543
2023-01-22 18:22:19.266281: step: 220/470, loss: 0.25361740589141846
2023-01-22 18:22:20.041901: step: 222/470, loss: 1.064577341079712
2023-01-22 18:22:20.799497: step: 224/470, loss: 0.13827519118785858
2023-01-22 18:22:21.526315: step: 226/470, loss: 0.13590987026691437
2023-01-22 18:22:22.214971: step: 228/470, loss: 0.20364883542060852
2023-01-22 18:22:22.903675: step: 230/470, loss: 0.2405257523059845
2023-01-22 18:22:23.663562: step: 232/470, loss: 0.11050628870725632
2023-01-22 18:22:24.473873: step: 234/470, loss: 0.18924807012081146
2023-01-22 18:22:25.216595: step: 236/470, loss: 0.18803924322128296
2023-01-22 18:22:25.990821: step: 238/470, loss: 0.1766262650489807
2023-01-22 18:22:26.935022: step: 240/470, loss: 0.24651962518692017
2023-01-22 18:22:27.618446: step: 242/470, loss: 0.5090709924697876
2023-01-22 18:22:28.443674: step: 244/470, loss: 0.07496100664138794
2023-01-22 18:22:29.157388: step: 246/470, loss: 0.39603158831596375
2023-01-22 18:22:29.832734: step: 248/470, loss: 0.09065035730600357
2023-01-22 18:22:30.605471: step: 250/470, loss: 0.662716269493103
2023-01-22 18:22:31.347855: step: 252/470, loss: 0.11193042248487473
2023-01-22 18:22:32.113320: step: 254/470, loss: 0.24775205552577972
2023-01-22 18:22:32.986037: step: 256/470, loss: 20.37836456298828
2023-01-22 18:22:33.696114: step: 258/470, loss: 0.34449484944343567
2023-01-22 18:22:34.456758: step: 260/470, loss: 0.07279616594314575
2023-01-22 18:22:35.262048: step: 262/470, loss: 0.18098340928554535
2023-01-22 18:22:36.007250: step: 264/470, loss: 0.16679392755031586
2023-01-22 18:22:36.756240: step: 266/470, loss: 0.4016364812850952
2023-01-22 18:22:37.510023: step: 268/470, loss: 0.22494986653327942
2023-01-22 18:22:38.184515: step: 270/470, loss: 0.05715346336364746
2023-01-22 18:22:38.926462: step: 272/470, loss: 0.2364903837442398
2023-01-22 18:22:39.637834: step: 274/470, loss: 0.09979073703289032
2023-01-22 18:22:40.353333: step: 276/470, loss: 0.08214342594146729
2023-01-22 18:22:41.175362: step: 278/470, loss: 0.1216912716627121
2023-01-22 18:22:41.823686: step: 280/470, loss: 0.07261183857917786
2023-01-22 18:22:42.587041: step: 282/470, loss: 0.1756569743156433
2023-01-22 18:22:43.350256: step: 284/470, loss: 0.6266811490058899
2023-01-22 18:22:44.036429: step: 286/470, loss: 0.1553003340959549
2023-01-22 18:22:44.746648: step: 288/470, loss: 0.33585941791534424
2023-01-22 18:22:45.415875: step: 290/470, loss: 0.05042559280991554
2023-01-22 18:22:46.135373: step: 292/470, loss: 0.2024879902601242
2023-01-22 18:22:46.793632: step: 294/470, loss: 0.026582282036542892
2023-01-22 18:22:47.496644: step: 296/470, loss: 0.11875536292791367
2023-01-22 18:22:48.317296: step: 298/470, loss: 0.16971439123153687
2023-01-22 18:22:49.083235: step: 300/470, loss: 0.34994009137153625
2023-01-22 18:22:49.839826: step: 302/470, loss: 0.1329270601272583
2023-01-22 18:22:50.661687: step: 304/470, loss: 0.30022162199020386
2023-01-22 18:22:51.433754: step: 306/470, loss: 0.16325759887695312
2023-01-22 18:22:52.198382: step: 308/470, loss: 0.15821513533592224
2023-01-22 18:22:52.921859: step: 310/470, loss: 0.11898909509181976
2023-01-22 18:22:53.665773: step: 312/470, loss: 0.11442035436630249
2023-01-22 18:22:54.345968: step: 314/470, loss: 0.2317693531513214
2023-01-22 18:22:55.067025: step: 316/470, loss: 0.210124209523201
2023-01-22 18:22:55.780952: step: 318/470, loss: 0.22964359819889069
2023-01-22 18:22:56.533053: step: 320/470, loss: 0.06219105422496796
2023-01-22 18:22:57.246850: step: 322/470, loss: 0.12114651501178741
2023-01-22 18:22:58.033454: step: 324/470, loss: 0.36422327160835266
2023-01-22 18:22:58.773446: step: 326/470, loss: 0.10115069150924683
2023-01-22 18:22:59.486475: step: 328/470, loss: 0.9817755818367004
2023-01-22 18:23:00.184006: step: 330/470, loss: 0.02880793623626232
2023-01-22 18:23:00.978600: step: 332/470, loss: 0.1212698295712471
2023-01-22 18:23:01.790853: step: 334/470, loss: 0.10181504487991333
2023-01-22 18:23:02.555639: step: 336/470, loss: 0.049668557941913605
2023-01-22 18:23:03.331924: step: 338/470, loss: 8.260157585144043
2023-01-22 18:23:04.119143: step: 340/470, loss: 0.1510852873325348
2023-01-22 18:23:04.905728: step: 342/470, loss: 0.2651934027671814
2023-01-22 18:23:05.644943: step: 344/470, loss: 0.2363731414079666
2023-01-22 18:23:06.393753: step: 346/470, loss: 0.28845059871673584
2023-01-22 18:23:07.251001: step: 348/470, loss: 0.17618459463119507
2023-01-22 18:23:07.981548: step: 350/470, loss: 0.3283766210079193
2023-01-22 18:23:08.682265: step: 352/470, loss: 0.3739703595638275
2023-01-22 18:23:09.484147: step: 354/470, loss: 0.06648049503564835
2023-01-22 18:23:10.213797: step: 356/470, loss: 0.1445521116256714
2023-01-22 18:23:10.903402: step: 358/470, loss: 0.06190051883459091
2023-01-22 18:23:11.645014: step: 360/470, loss: 0.12461217492818832
2023-01-22 18:23:12.310086: step: 362/470, loss: 0.033573780208826065
2023-01-22 18:23:13.022309: step: 364/470, loss: 0.13312368094921112
2023-01-22 18:23:13.756013: step: 366/470, loss: 0.1520005315542221
2023-01-22 18:23:14.531624: step: 368/470, loss: 0.9422814249992371
2023-01-22 18:23:15.319713: step: 370/470, loss: 0.1411898136138916
2023-01-22 18:23:16.053779: step: 372/470, loss: 0.051140353083610535
2023-01-22 18:23:16.779280: step: 374/470, loss: 0.3242073357105255
2023-01-22 18:23:17.483350: step: 376/470, loss: 0.16489548981189728
2023-01-22 18:23:18.270730: step: 378/470, loss: 1.8228318691253662
2023-01-22 18:23:19.125443: step: 380/470, loss: 1.1325253248214722
2023-01-22 18:23:19.881156: step: 382/470, loss: 0.36451154947280884
2023-01-22 18:23:20.567012: step: 384/470, loss: 0.0645284503698349
2023-01-22 18:23:21.300513: step: 386/470, loss: 0.10189077258110046
2023-01-22 18:23:21.967021: step: 388/470, loss: 0.18132157623767853
2023-01-22 18:23:22.717393: step: 390/470, loss: 0.24271626770496368
2023-01-22 18:23:23.398215: step: 392/470, loss: 0.11971033364534378
2023-01-22 18:23:24.097881: step: 394/470, loss: 0.1440243124961853
2023-01-22 18:23:24.887348: step: 396/470, loss: 0.12291662395000458
2023-01-22 18:23:25.594203: step: 398/470, loss: 0.07444258779287338
2023-01-22 18:23:26.373140: step: 400/470, loss: 0.7031933069229126
2023-01-22 18:23:27.157069: step: 402/470, loss: 0.16021253168582916
2023-01-22 18:23:27.829001: step: 404/470, loss: 0.2858032286167145
2023-01-22 18:23:28.590243: step: 406/470, loss: 0.15188010036945343
2023-01-22 18:23:29.355190: step: 408/470, loss: 0.5649017691612244
2023-01-22 18:23:30.075444: step: 410/470, loss: 0.06190142035484314
2023-01-22 18:23:30.809114: step: 412/470, loss: 0.18122579157352448
2023-01-22 18:23:31.501642: step: 414/470, loss: 0.11591540277004242
2023-01-22 18:23:32.149208: step: 416/470, loss: 0.07641121000051498
2023-01-22 18:23:32.866511: step: 418/470, loss: 0.07922433316707611
2023-01-22 18:23:33.562116: step: 420/470, loss: 0.04138394817709923
2023-01-22 18:23:34.353581: step: 422/470, loss: 0.30484187602996826
2023-01-22 18:23:35.110854: step: 424/470, loss: 0.11592315137386322
2023-01-22 18:23:35.963751: step: 426/470, loss: 0.47379979491233826
2023-01-22 18:23:36.700780: step: 428/470, loss: 0.05659574270248413
2023-01-22 18:23:37.395372: step: 430/470, loss: 0.10657653957605362
2023-01-22 18:23:38.073392: step: 432/470, loss: 0.14987456798553467
2023-01-22 18:23:38.761459: step: 434/470, loss: 0.526384174823761
2023-01-22 18:23:39.534052: step: 436/470, loss: 0.1093791201710701
2023-01-22 18:23:40.205673: step: 438/470, loss: 0.16932667791843414
2023-01-22 18:23:40.978906: step: 440/470, loss: 0.2574578523635864
2023-01-22 18:23:41.718180: step: 442/470, loss: 0.06636017560958862
2023-01-22 18:23:42.452602: step: 444/470, loss: 0.7201718091964722
2023-01-22 18:23:43.207984: step: 446/470, loss: 0.11673801392316818
2023-01-22 18:23:43.911991: step: 448/470, loss: 0.1540815830230713
2023-01-22 18:23:44.619799: step: 450/470, loss: 0.2399187535047531
2023-01-22 18:23:45.347439: step: 452/470, loss: 0.1115301102399826
2023-01-22 18:23:46.185900: step: 454/470, loss: 0.3593323230743408
2023-01-22 18:23:46.956267: step: 456/470, loss: 1.4198927879333496
2023-01-22 18:23:47.689879: step: 458/470, loss: 0.6755783557891846
2023-01-22 18:23:48.361258: step: 460/470, loss: 0.050497036427259445
2023-01-22 18:23:49.064817: step: 462/470, loss: 0.10053464025259018
2023-01-22 18:23:49.797039: step: 464/470, loss: 0.03807546943426132
2023-01-22 18:23:50.508053: step: 466/470, loss: 0.3850559592247009
2023-01-22 18:23:51.260122: step: 468/470, loss: 0.06416615843772888
2023-01-22 18:23:52.053028: step: 470/470, loss: 0.06735183298587799
2023-01-22 18:23:52.733743: step: 472/470, loss: 0.0959152951836586
2023-01-22 18:23:53.417400: step: 474/470, loss: 0.49368205666542053
2023-01-22 18:23:54.176414: step: 476/470, loss: 0.13260005414485931
2023-01-22 18:23:54.883427: step: 478/470, loss: 0.17261973023414612
2023-01-22 18:23:55.586915: step: 480/470, loss: 0.08892907947301865
2023-01-22 18:23:56.361449: step: 482/470, loss: 0.15367530286312103
2023-01-22 18:23:57.111532: step: 484/470, loss: 0.11208932101726532
2023-01-22 18:23:57.756274: step: 486/470, loss: 0.15923534333705902
2023-01-22 18:23:58.505356: step: 488/470, loss: 0.09813371300697327
2023-01-22 18:23:59.155976: step: 490/470, loss: 0.46980464458465576
2023-01-22 18:23:59.876527: step: 492/470, loss: 0.14123369753360748
2023-01-22 18:24:00.565931: step: 494/470, loss: 0.105765201151371
2023-01-22 18:24:01.242633: step: 496/470, loss: 0.21727946400642395
2023-01-22 18:24:01.952457: step: 498/470, loss: 0.13507087528705597
2023-01-22 18:24:02.714239: step: 500/470, loss: 0.12536272406578064
2023-01-22 18:24:03.476625: step: 502/470, loss: 0.06248565390706062
2023-01-22 18:24:04.248406: step: 504/470, loss: 0.29726463556289673
2023-01-22 18:24:04.941310: step: 506/470, loss: 0.10283642262220383
2023-01-22 18:24:05.691984: step: 508/470, loss: 0.88539719581604
2023-01-22 18:24:06.425893: step: 510/470, loss: 0.14810267090797424
2023-01-22 18:24:07.200594: step: 512/470, loss: 0.18709732592105865
2023-01-22 18:24:07.936300: step: 514/470, loss: 0.043946363031864166
2023-01-22 18:24:08.664837: step: 516/470, loss: 0.20995289087295532
2023-01-22 18:24:09.441892: step: 518/470, loss: 0.19275762140750885
2023-01-22 18:24:10.174293: step: 520/470, loss: 0.3477177619934082
2023-01-22 18:24:11.009712: step: 522/470, loss: 0.3986015319824219
2023-01-22 18:24:11.723296: step: 524/470, loss: 0.1369524747133255
2023-01-22 18:24:12.465973: step: 526/470, loss: 0.07624433934688568
2023-01-22 18:24:13.179358: step: 528/470, loss: 0.29792025685310364
2023-01-22 18:24:13.888712: step: 530/470, loss: 0.17045418918132782
2023-01-22 18:24:14.639791: step: 532/470, loss: 0.3308311998844147
2023-01-22 18:24:15.337861: step: 534/470, loss: 0.11802157014608383
2023-01-22 18:24:16.061269: step: 536/470, loss: 0.510388195514679
2023-01-22 18:24:16.709098: step: 538/470, loss: 0.22368597984313965
2023-01-22 18:24:17.408478: step: 540/470, loss: 0.13283610343933105
2023-01-22 18:24:18.227948: step: 542/470, loss: 0.6673287153244019
2023-01-22 18:24:18.914901: step: 544/470, loss: 0.25879979133605957
2023-01-22 18:24:19.630051: step: 546/470, loss: 0.13402698934078217
2023-01-22 18:24:20.357410: step: 548/470, loss: 0.28232210874557495
2023-01-22 18:24:21.112878: step: 550/470, loss: 0.1593974232673645
2023-01-22 18:24:21.836376: step: 552/470, loss: 0.15679427981376648
2023-01-22 18:24:22.487304: step: 554/470, loss: 0.5649197101593018
2023-01-22 18:24:23.133556: step: 556/470, loss: 0.1094643771648407
2023-01-22 18:24:23.862726: step: 558/470, loss: 0.21649640798568726
2023-01-22 18:24:24.591257: step: 560/470, loss: 0.4756641089916229
2023-01-22 18:24:25.286334: step: 562/470, loss: 0.17450223863124847
2023-01-22 18:24:25.989976: step: 564/470, loss: 0.15516166388988495
2023-01-22 18:24:26.707447: step: 566/470, loss: 0.15304596722126007
2023-01-22 18:24:27.460976: step: 568/470, loss: 0.15756924450397491
2023-01-22 18:24:28.245938: step: 570/470, loss: 0.17908306419849396
2023-01-22 18:24:28.919133: step: 572/470, loss: 0.1460331678390503
2023-01-22 18:24:29.680860: step: 574/470, loss: 0.5658903121948242
2023-01-22 18:24:30.431424: step: 576/470, loss: 0.12265262007713318
2023-01-22 18:24:31.186070: step: 578/470, loss: 0.22960016131401062
2023-01-22 18:24:31.936463: step: 580/470, loss: 0.10772555321455002
2023-01-22 18:24:32.638658: step: 582/470, loss: 0.36096444725990295
2023-01-22 18:24:33.365527: step: 584/470, loss: 0.19996917247772217
2023-01-22 18:24:34.156497: step: 586/470, loss: 0.09180688112974167
2023-01-22 18:24:34.797920: step: 588/470, loss: 0.18549667298793793
2023-01-22 18:24:35.594727: step: 590/470, loss: 0.09706774353981018
2023-01-22 18:24:36.358372: step: 592/470, loss: 0.128683939576149
2023-01-22 18:24:37.164821: step: 594/470, loss: 0.11436925083398819
2023-01-22 18:24:37.976131: step: 596/470, loss: 0.1896413415670395
2023-01-22 18:24:38.695384: step: 598/470, loss: 0.06010688096284866
2023-01-22 18:24:39.440004: step: 600/470, loss: 0.2670471966266632
2023-01-22 18:24:40.167583: step: 602/470, loss: 0.11307162046432495
2023-01-22 18:24:40.973357: step: 604/470, loss: 0.11850042641162872
2023-01-22 18:24:41.695759: step: 606/470, loss: 0.444345623254776
2023-01-22 18:24:42.433481: step: 608/470, loss: 0.15307031571865082
2023-01-22 18:24:43.221218: step: 610/470, loss: 0.20294825732707977
2023-01-22 18:24:43.955071: step: 612/470, loss: 0.1727193295955658
2023-01-22 18:24:44.792661: step: 614/470, loss: 0.1558392196893692
2023-01-22 18:24:45.500425: step: 616/470, loss: 0.11232329159975052
2023-01-22 18:24:46.271464: step: 618/470, loss: 0.4051525294780731
2023-01-22 18:24:46.953436: step: 620/470, loss: 0.18653224408626556
2023-01-22 18:24:47.678248: step: 622/470, loss: 0.07225558906793594
2023-01-22 18:24:48.459276: step: 624/470, loss: 0.21247851848602295
2023-01-22 18:24:49.149970: step: 626/470, loss: 0.1073872521519661
2023-01-22 18:24:49.911132: step: 628/470, loss: 0.1231706514954567
2023-01-22 18:24:50.679799: step: 630/470, loss: 0.03070944733917713
2023-01-22 18:24:51.378119: step: 632/470, loss: 0.3459760546684265
2023-01-22 18:24:52.153427: step: 634/470, loss: 0.14295950531959534
2023-01-22 18:24:52.887516: step: 636/470, loss: 0.17095544934272766
2023-01-22 18:24:53.563580: step: 638/470, loss: 0.08782177418470383
2023-01-22 18:24:54.255270: step: 640/470, loss: 2.7348151206970215
2023-01-22 18:24:55.040130: step: 642/470, loss: 0.18300358951091766
2023-01-22 18:24:55.728337: step: 644/470, loss: 0.610358715057373
2023-01-22 18:24:56.573117: step: 646/470, loss: 0.07318799197673798
2023-01-22 18:24:57.305373: step: 648/470, loss: 0.2117634117603302
2023-01-22 18:24:58.106935: step: 650/470, loss: 1.6853128671646118
2023-01-22 18:24:58.878022: step: 652/470, loss: 0.3203961253166199
2023-01-22 18:24:59.621646: step: 654/470, loss: 0.10503191500902176
2023-01-22 18:25:00.348015: step: 656/470, loss: 0.12326573580503464
2023-01-22 18:25:01.055514: step: 658/470, loss: 0.0717514380812645
2023-01-22 18:25:01.797479: step: 660/470, loss: 0.04833994433283806
2023-01-22 18:25:02.561079: step: 662/470, loss: 0.025357216596603394
2023-01-22 18:25:03.329415: step: 664/470, loss: 0.0652332752943039
2023-01-22 18:25:04.101370: step: 666/470, loss: 0.1199808269739151
2023-01-22 18:25:04.802581: step: 668/470, loss: 0.09009598940610886
2023-01-22 18:25:05.545543: step: 670/470, loss: 0.5139247179031372
2023-01-22 18:25:06.227302: step: 672/470, loss: 0.05846283957362175
2023-01-22 18:25:06.940262: step: 674/470, loss: 0.1617492139339447
2023-01-22 18:25:07.715691: step: 676/470, loss: 0.06745065003633499
2023-01-22 18:25:08.496741: step: 678/470, loss: 0.14190346002578735
2023-01-22 18:25:09.253742: step: 680/470, loss: 0.04410451278090477
2023-01-22 18:25:10.024677: step: 682/470, loss: 0.35122886300086975
2023-01-22 18:25:10.803422: step: 684/470, loss: 0.1424378901720047
2023-01-22 18:25:11.558960: step: 686/470, loss: 0.13077247142791748
2023-01-22 18:25:12.346517: step: 688/470, loss: 0.067043736577034
2023-01-22 18:25:13.079823: step: 690/470, loss: 0.22250400483608246
2023-01-22 18:25:13.814006: step: 692/470, loss: 0.07035396248102188
2023-01-22 18:25:14.520263: step: 694/470, loss: 0.18889664113521576
2023-01-22 18:25:15.206570: step: 696/470, loss: 0.15015734732151031
2023-01-22 18:25:16.038067: step: 698/470, loss: 0.16164840757846832
2023-01-22 18:25:16.832790: step: 700/470, loss: 0.0613911971449852
2023-01-22 18:25:17.601962: step: 702/470, loss: 0.2514897584915161
2023-01-22 18:25:18.473384: step: 704/470, loss: 0.09639281034469604
2023-01-22 18:25:19.202917: step: 706/470, loss: 0.4936193525791168
2023-01-22 18:25:19.956306: step: 708/470, loss: 0.23112571239471436
2023-01-22 18:25:20.665558: step: 710/470, loss: 0.21785999834537506
2023-01-22 18:25:21.365364: step: 712/470, loss: 0.26574963331222534
2023-01-22 18:25:22.121861: step: 714/470, loss: 0.1496441513299942
2023-01-22 18:25:22.921467: step: 716/470, loss: 0.13528425991535187
2023-01-22 18:25:23.793187: step: 718/470, loss: 0.4600887894630432
2023-01-22 18:25:24.531574: step: 720/470, loss: 0.3019505739212036
2023-01-22 18:25:25.213423: step: 722/470, loss: 0.2099757045507431
2023-01-22 18:25:25.970065: step: 724/470, loss: 0.22414270043373108
2023-01-22 18:25:26.788185: step: 726/470, loss: 0.10880865156650543
2023-01-22 18:25:27.562965: step: 728/470, loss: 0.2567862272262573
2023-01-22 18:25:28.276084: step: 730/470, loss: 0.12142646312713623
2023-01-22 18:25:29.042110: step: 732/470, loss: 0.1998579055070877
2023-01-22 18:25:29.766003: step: 734/470, loss: 0.13268613815307617
2023-01-22 18:25:30.481109: step: 736/470, loss: 0.14437507092952728
2023-01-22 18:25:31.289921: step: 738/470, loss: 0.16617853939533234
2023-01-22 18:25:32.064677: step: 740/470, loss: 0.10675939172506332
2023-01-22 18:25:32.904974: step: 742/470, loss: 0.20530328154563904
2023-01-22 18:25:33.718941: step: 744/470, loss: 0.23302339017391205
2023-01-22 18:25:34.482819: step: 746/470, loss: 0.13051211833953857
2023-01-22 18:25:35.189996: step: 748/470, loss: 0.04546245560050011
2023-01-22 18:25:35.914692: step: 750/470, loss: 0.16170257329940796
2023-01-22 18:25:36.646768: step: 752/470, loss: 0.3879983723163605
2023-01-22 18:25:37.492896: step: 754/470, loss: 0.17441397905349731
2023-01-22 18:25:38.196890: step: 756/470, loss: 0.12725909054279327
2023-01-22 18:25:38.940186: step: 758/470, loss: 0.11163493990898132
2023-01-22 18:25:39.674804: step: 760/470, loss: 0.2151859700679779
2023-01-22 18:25:40.432711: step: 762/470, loss: 0.3291402757167816
2023-01-22 18:25:41.176822: step: 764/470, loss: 0.10096342861652374
2023-01-22 18:25:42.036808: step: 766/470, loss: 0.10235702246427536
2023-01-22 18:25:42.737319: step: 768/470, loss: 0.03586709871888161
2023-01-22 18:25:43.563276: step: 770/470, loss: 0.5148991346359253
2023-01-22 18:25:44.265740: step: 772/470, loss: 0.2516341507434845
2023-01-22 18:25:45.058472: step: 774/470, loss: 0.33739376068115234
2023-01-22 18:25:45.727928: step: 776/470, loss: 0.09920867532491684
2023-01-22 18:25:46.484891: step: 778/470, loss: 0.15994364023208618
2023-01-22 18:25:47.274925: step: 780/470, loss: 0.08426479995250702
2023-01-22 18:25:48.142562: step: 782/470, loss: 0.18891899287700653
2023-01-22 18:25:48.862251: step: 784/470, loss: 0.07184939086437225
2023-01-22 18:25:49.688146: step: 786/470, loss: 0.16742153465747833
2023-01-22 18:25:50.418893: step: 788/470, loss: 0.42684534192085266
2023-01-22 18:25:51.178130: step: 790/470, loss: 0.12125355750322342
2023-01-22 18:25:51.910135: step: 792/470, loss: 0.08575651794672012
2023-01-22 18:25:52.659392: step: 794/470, loss: 0.11674223095178604
2023-01-22 18:25:53.336143: step: 796/470, loss: 0.10641640424728394
2023-01-22 18:25:54.006164: step: 798/470, loss: 0.4802986681461334
2023-01-22 18:25:54.757452: step: 800/470, loss: 0.08506816625595093
2023-01-22 18:25:55.506851: step: 802/470, loss: 0.057946957647800446
2023-01-22 18:25:56.235230: step: 804/470, loss: 0.16969476640224457
2023-01-22 18:25:56.918664: step: 806/470, loss: 0.1266757696866989
2023-01-22 18:25:57.651238: step: 808/470, loss: 0.22330895066261292
2023-01-22 18:25:58.427963: step: 810/470, loss: 0.14940103888511658
2023-01-22 18:25:59.172918: step: 812/470, loss: 0.10136136412620544
2023-01-22 18:25:59.894256: step: 814/470, loss: 0.3054467439651489
2023-01-22 18:26:00.662741: step: 816/470, loss: 0.32518401741981506
2023-01-22 18:26:01.380014: step: 818/470, loss: 0.16174927353858948
2023-01-22 18:26:02.162545: step: 820/470, loss: 0.0795656368136406
2023-01-22 18:26:02.905212: step: 822/470, loss: 0.45578598976135254
2023-01-22 18:26:03.610199: step: 824/470, loss: 0.13583436608314514
2023-01-22 18:26:04.301254: step: 826/470, loss: 0.22682815790176392
2023-01-22 18:26:05.018806: step: 828/470, loss: 0.06597944349050522
2023-01-22 18:26:05.746437: step: 830/470, loss: 0.06516607105731964
2023-01-22 18:26:06.447192: step: 832/470, loss: 0.18027722835540771
2023-01-22 18:26:07.163965: step: 834/470, loss: 0.11800383776426315
2023-01-22 18:26:07.878444: step: 836/470, loss: 0.12889358401298523
2023-01-22 18:26:08.647605: step: 838/470, loss: 0.04844401776790619
2023-01-22 18:26:09.317964: step: 840/470, loss: 0.12319555133581161
2023-01-22 18:26:10.055495: step: 842/470, loss: 0.06649138778448105
2023-01-22 18:26:10.815534: step: 844/470, loss: 0.11697138100862503
2023-01-22 18:26:11.575154: step: 846/470, loss: 0.4858449399471283
2023-01-22 18:26:12.337785: step: 848/470, loss: 0.18316267430782318
2023-01-22 18:26:13.133682: step: 850/470, loss: 0.2892132103443146
2023-01-22 18:26:13.904819: step: 852/470, loss: 0.1974104344844818
2023-01-22 18:26:14.618538: step: 854/470, loss: 0.1520778387784958
2023-01-22 18:26:15.353151: step: 856/470, loss: 0.2704646587371826
2023-01-22 18:26:16.154921: step: 858/470, loss: 0.2902047634124756
2023-01-22 18:26:16.791683: step: 860/470, loss: 0.08880189806222916
2023-01-22 18:26:17.627587: step: 862/470, loss: 0.11974621564149857
2023-01-22 18:26:18.382128: step: 864/470, loss: 0.09045007079839706
2023-01-22 18:26:19.109642: step: 866/470, loss: 0.22416849434375763
2023-01-22 18:26:19.842917: step: 868/470, loss: 0.19987420737743378
2023-01-22 18:26:20.589348: step: 870/470, loss: 0.17100857198238373
2023-01-22 18:26:21.372192: step: 872/470, loss: 0.3392637073993683
2023-01-22 18:26:22.131950: step: 874/470, loss: 0.1819869726896286
2023-01-22 18:26:22.814409: step: 876/470, loss: 0.16775751113891602
2023-01-22 18:26:23.588386: step: 878/470, loss: 0.5377464890480042
2023-01-22 18:26:24.314167: step: 880/470, loss: 1.2753757238388062
2023-01-22 18:26:25.109659: step: 882/470, loss: 0.5215312838554382
2023-01-22 18:26:25.838239: step: 884/470, loss: 0.18393318355083466
2023-01-22 18:26:26.550566: step: 886/470, loss: 0.10737390071153641
2023-01-22 18:26:27.272639: step: 888/470, loss: 0.15539099276065826
2023-01-22 18:26:28.104499: step: 890/470, loss: 0.9249545335769653
2023-01-22 18:26:28.781704: step: 892/470, loss: 0.29865944385528564
2023-01-22 18:26:29.528772: step: 894/470, loss: 0.31313595175743103
2023-01-22 18:26:30.257697: step: 896/470, loss: 0.09606197476387024
2023-01-22 18:26:31.009939: step: 898/470, loss: 0.308594286441803
2023-01-22 18:26:31.837007: step: 900/470, loss: 0.11458901315927505
2023-01-22 18:26:32.654352: step: 902/470, loss: 0.07904741168022156
2023-01-22 18:26:33.437104: step: 904/470, loss: 0.1473604291677475
2023-01-22 18:26:34.160746: step: 906/470, loss: 0.22174973785877228
2023-01-22 18:26:34.908590: step: 908/470, loss: 1.0358433723449707
2023-01-22 18:26:35.663639: step: 910/470, loss: 0.49611371755599976
2023-01-22 18:26:36.407391: step: 912/470, loss: 0.15608665347099304
2023-01-22 18:26:37.138804: step: 914/470, loss: 0.15466263890266418
2023-01-22 18:26:37.906993: step: 916/470, loss: 0.20168907940387726
2023-01-22 18:26:38.640995: step: 918/470, loss: 0.4854433536529541
2023-01-22 18:26:39.370507: step: 920/470, loss: 0.2656620144844055
2023-01-22 18:26:40.108380: step: 922/470, loss: 0.17299237847328186
2023-01-22 18:26:40.853680: step: 924/470, loss: 0.41194406151771545
2023-01-22 18:26:41.569577: step: 926/470, loss: 0.11019831150770187
2023-01-22 18:26:42.221313: step: 928/470, loss: 0.17341381311416626
2023-01-22 18:26:43.068980: step: 930/470, loss: 0.11898980289697647
2023-01-22 18:26:43.881869: step: 932/470, loss: 0.0407705120742321
2023-01-22 18:26:44.695919: step: 934/470, loss: 0.16358143091201782
2023-01-22 18:26:45.414004: step: 936/470, loss: 0.148806631565094
2023-01-22 18:26:46.138418: step: 938/470, loss: 0.08406595140695572
2023-01-22 18:26:46.829644: step: 940/470, loss: 0.17969819903373718
2023-01-22 18:26:47.534639: step: 942/470, loss: 0.07237522304058075
==================================================
Loss: 0.291
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3059714988425926, 'r': 0.3344204617330803, 'f1': 0.31956406769416745}, 'combined': 0.23546826040622865, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33907906154280193, 'r': 0.3579710745778476, 'f1': 0.34826905479956943}, 'combined': 0.24257546105442648, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3023461521070718, 'r': 0.33390030460401476, 'f1': 0.31734077642257125}, 'combined': 0.23383004578505248, 'epoch': 13}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34556379475902327, 'r': 0.3591869828216386, 'f1': 0.35224371724139947}, 'combined': 0.24534388265570115, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28835685483870965, 'r': 0.3392433586337761, 'f1': 0.3117371403661726}, 'combined': 0.22970105079612718, 'epoch': 13}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3398584075592588, 'r': 0.3712299528724211, 'f1': 0.35485216083393195}, 'combined': 0.24716070903855958, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23039215686274508, 'r': 0.3357142857142857, 'f1': 0.27325581395348836}, 'combined': 0.1821705426356589, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2692307692307692, 'r': 0.45652173913043476, 'f1': 0.3387096774193548}, 'combined': 0.1693548387096774, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34782608695652173, 'r': 0.27586206896551724, 'f1': 0.3076923076923077}, 'combined': 0.20512820512820512, 'epoch': 13}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3091249669923422, 'r': 0.3173370154513418, 'f1': 0.3131771669341894}, 'combined': 0.23076212300413954, 'epoch': 11}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3375444187463703, 'r': 0.3472812769794387, 'f1': 0.3423436284915794}, 'combined': 0.23844829845184637, 'epoch': 11}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2288135593220339, 'r': 0.38571428571428573, 'f1': 0.2872340425531915}, 'combined': 0.19148936170212766, 'epoch': 11}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3023461521070718, 'r': 0.33390030460401476, 'f1': 0.31734077642257125}, 'combined': 0.23383004578505248, 'epoch': 13}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34556379475902327, 'r': 0.3591869828216386, 'f1': 0.35224371724139947}, 'combined': 0.24534388265570115, 'epoch': 13}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2692307692307692, 'r': 0.45652173913043476, 'f1': 0.3387096774193548}, 'combined': 0.1693548387096774, 'epoch': 13}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27696660863807243, 'r': 0.31953642894107787, 'f1': 0.2967325075805252}, 'combined': 0.21864500558565014, 'epoch': 10}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34185545824681857, 'r': 0.32870717139117167, 'f1': 0.3351524100459005}, 'combined': 0.23343948958420932, 'epoch': 10}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4318181818181818, 'r': 0.3275862068965517, 'f1': 0.3725490196078432}, 'combined': 0.24836601307189546, 'epoch': 10}
******************************
Epoch: 14
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 18:29:34.180021: step: 2/470, loss: 0.11083290725946426
2023-01-22 18:29:34.901119: step: 4/470, loss: 0.11919131875038147
2023-01-22 18:29:35.596675: step: 6/470, loss: 0.22162587940692902
2023-01-22 18:29:36.376635: step: 8/470, loss: 0.1282801777124405
2023-01-22 18:29:37.160923: step: 10/470, loss: 0.05915132537484169
2023-01-22 18:29:37.874340: step: 12/470, loss: 0.03638844937086105
2023-01-22 18:29:38.772651: step: 14/470, loss: 0.12631765007972717
2023-01-22 18:29:39.593733: step: 16/470, loss: 0.30836811661720276
2023-01-22 18:29:40.301761: step: 18/470, loss: 0.08455128967761993
2023-01-22 18:29:41.034064: step: 20/470, loss: 0.4171124994754791
2023-01-22 18:29:41.756988: step: 22/470, loss: 0.12701795995235443
2023-01-22 18:29:42.582140: step: 24/470, loss: 0.06594716012477875
2023-01-22 18:29:43.271412: step: 26/470, loss: 0.15928548574447632
2023-01-22 18:29:44.069533: step: 28/470, loss: 0.0775287002325058
2023-01-22 18:29:44.862156: step: 30/470, loss: 0.11700832098722458
2023-01-22 18:29:45.612986: step: 32/470, loss: 0.11270631104707718
2023-01-22 18:29:46.463251: step: 34/470, loss: 0.14612014591693878
2023-01-22 18:29:47.178812: step: 36/470, loss: 0.12699899077415466
2023-01-22 18:29:47.960788: step: 38/470, loss: 0.20811907947063446
2023-01-22 18:29:48.730393: step: 40/470, loss: 0.12297671288251877
2023-01-22 18:29:49.684927: step: 42/470, loss: 0.11870261281728745
2023-01-22 18:29:50.371118: step: 44/470, loss: 0.20325523614883423
2023-01-22 18:29:51.068833: step: 46/470, loss: 0.07447163760662079
2023-01-22 18:29:51.785299: step: 48/470, loss: 0.10491825640201569
2023-01-22 18:29:52.577667: step: 50/470, loss: 0.09760572761297226
2023-01-22 18:29:53.312614: step: 52/470, loss: 0.3343038856983185
2023-01-22 18:29:54.041498: step: 54/470, loss: 0.19771350920200348
2023-01-22 18:29:54.767797: step: 56/470, loss: 0.09543336182832718
2023-01-22 18:29:55.450957: step: 58/470, loss: 0.4951615333557129
2023-01-22 18:29:56.173806: step: 60/470, loss: 0.08876185119152069
2023-01-22 18:29:56.908734: step: 62/470, loss: 0.11803992092609406
2023-01-22 18:29:57.695496: step: 64/470, loss: 0.14623303711414337
2023-01-22 18:29:58.428784: step: 66/470, loss: 0.24651095271110535
2023-01-22 18:29:59.214927: step: 68/470, loss: 0.119205541908741
2023-01-22 18:29:59.946209: step: 70/470, loss: 0.10121873021125793
2023-01-22 18:30:00.663668: step: 72/470, loss: 0.2187107503414154
2023-01-22 18:30:01.382482: step: 74/470, loss: 0.07482891529798508
2023-01-22 18:30:02.108976: step: 76/470, loss: 0.8483836650848389
2023-01-22 18:30:02.911817: step: 78/470, loss: 0.04838128015398979
2023-01-22 18:30:03.669765: step: 80/470, loss: 0.1129889115691185
2023-01-22 18:30:04.406267: step: 82/470, loss: 0.16097694635391235
2023-01-22 18:30:05.183456: step: 84/470, loss: 0.08617453277111053
2023-01-22 18:30:05.951195: step: 86/470, loss: 0.12346760928630829
2023-01-22 18:30:06.782208: step: 88/470, loss: 0.763508677482605
2023-01-22 18:30:07.531192: step: 90/470, loss: 0.09003492444753647
2023-01-22 18:30:08.254752: step: 92/470, loss: 0.11231306940317154
2023-01-22 18:30:08.964933: step: 94/470, loss: 0.3491142988204956
2023-01-22 18:30:09.686092: step: 96/470, loss: 0.4276227653026581
2023-01-22 18:30:10.546391: step: 98/470, loss: 1.9698024988174438
2023-01-22 18:30:11.318482: step: 100/470, loss: 0.16232357919216156
2023-01-22 18:30:12.093404: step: 102/470, loss: 0.07967112213373184
2023-01-22 18:30:12.799351: step: 104/470, loss: 0.04950232803821564
2023-01-22 18:30:13.552747: step: 106/470, loss: 0.10787200182676315
2023-01-22 18:30:14.278117: step: 108/470, loss: 0.10786844789981842
2023-01-22 18:30:14.992201: step: 110/470, loss: 0.10731559991836548
2023-01-22 18:30:15.791655: step: 112/470, loss: 0.07661902159452438
2023-01-22 18:30:16.539648: step: 114/470, loss: 0.030627790838479996
2023-01-22 18:30:17.234189: step: 116/470, loss: 0.13857971131801605
2023-01-22 18:30:18.038969: step: 118/470, loss: 0.10013086348772049
2023-01-22 18:30:18.771495: step: 120/470, loss: 0.15490609407424927
2023-01-22 18:30:19.537994: step: 122/470, loss: 1.2364153861999512
2023-01-22 18:30:20.229275: step: 124/470, loss: 0.12906284630298615
2023-01-22 18:30:20.975979: step: 126/470, loss: 0.1098984032869339
2023-01-22 18:30:21.698318: step: 128/470, loss: 0.11757684499025345
2023-01-22 18:30:22.429567: step: 130/470, loss: 0.07572782039642334
2023-01-22 18:30:23.133225: step: 132/470, loss: 0.1737520694732666
2023-01-22 18:30:23.857860: step: 134/470, loss: 0.13601481914520264
2023-01-22 18:30:24.611311: step: 136/470, loss: 0.09237069636583328
2023-01-22 18:30:25.299122: step: 138/470, loss: 0.3090798258781433
2023-01-22 18:30:26.032908: step: 140/470, loss: 0.14041438698768616
2023-01-22 18:30:26.790636: step: 142/470, loss: 0.17475241422653198
2023-01-22 18:30:27.525389: step: 144/470, loss: 0.11330439150333405
2023-01-22 18:30:28.295183: step: 146/470, loss: 0.17179451882839203
2023-01-22 18:30:29.070534: step: 148/470, loss: 0.1465025544166565
2023-01-22 18:30:29.778203: step: 150/470, loss: 0.013929449953138828
2023-01-22 18:30:30.539919: step: 152/470, loss: 0.08549786359071732
2023-01-22 18:30:31.291791: step: 154/470, loss: 0.03197602927684784
2023-01-22 18:30:31.988875: step: 156/470, loss: 0.5165415406227112
2023-01-22 18:30:32.732642: step: 158/470, loss: 0.05465986579656601
2023-01-22 18:30:33.543260: step: 160/470, loss: 0.08515684306621552
2023-01-22 18:30:34.308529: step: 162/470, loss: 0.12424996495246887
2023-01-22 18:30:35.001008: step: 164/470, loss: 0.12669268250465393
2023-01-22 18:30:35.675611: step: 166/470, loss: 0.03578896448016167
2023-01-22 18:30:36.389251: step: 168/470, loss: 0.07446733117103577
2023-01-22 18:30:37.184829: step: 170/470, loss: 0.14528201520442963
2023-01-22 18:30:37.837362: step: 172/470, loss: 0.06307399272918701
2023-01-22 18:30:38.644509: step: 174/470, loss: 0.08100112527608871
2023-01-22 18:30:39.330892: step: 176/470, loss: 0.06932196021080017
2023-01-22 18:30:40.052336: step: 178/470, loss: 0.10252606868743896
2023-01-22 18:30:40.747207: step: 180/470, loss: 0.05974116176366806
2023-01-22 18:30:41.449518: step: 182/470, loss: 0.0428239107131958
2023-01-22 18:30:42.284685: step: 184/470, loss: 0.1692391037940979
2023-01-22 18:30:42.994415: step: 186/470, loss: 0.06524728983640671
2023-01-22 18:30:43.749345: step: 188/470, loss: 0.1310448795557022
2023-01-22 18:30:44.476680: step: 190/470, loss: 0.07662883400917053
2023-01-22 18:30:45.160382: step: 192/470, loss: 0.08161720633506775
2023-01-22 18:30:45.889098: step: 194/470, loss: 0.20154725015163422
2023-01-22 18:30:46.563252: step: 196/470, loss: 0.17144368588924408
2023-01-22 18:30:47.239189: step: 198/470, loss: 0.05600402504205704
2023-01-22 18:30:47.934561: step: 200/470, loss: 0.1903025358915329
2023-01-22 18:30:48.768089: step: 202/470, loss: 0.10436660796403885
2023-01-22 18:30:49.539608: step: 204/470, loss: 0.23059800267219543
2023-01-22 18:30:50.290510: step: 206/470, loss: 0.17381146550178528
2023-01-22 18:30:50.981935: step: 208/470, loss: 0.3720693588256836
2023-01-22 18:30:51.679573: step: 210/470, loss: 0.0502849817276001
2023-01-22 18:30:52.400958: step: 212/470, loss: 0.13139395415782928
2023-01-22 18:30:53.137579: step: 214/470, loss: 0.038059886544942856
2023-01-22 18:30:53.879654: step: 216/470, loss: 0.09123457223176956
2023-01-22 18:30:54.627685: step: 218/470, loss: 0.2840889096260071
2023-01-22 18:30:55.322870: step: 220/470, loss: 0.022772392258048058
2023-01-22 18:30:56.001128: step: 222/470, loss: 0.10895684361457825
2023-01-22 18:30:56.713604: step: 224/470, loss: 0.1379581242799759
2023-01-22 18:30:57.421349: step: 226/470, loss: 0.08646092563867569
2023-01-22 18:30:58.162484: step: 228/470, loss: 0.06485362350940704
2023-01-22 18:30:58.865200: step: 230/470, loss: 0.10785852372646332
2023-01-22 18:30:59.575028: step: 232/470, loss: 0.149741530418396
2023-01-22 18:31:00.296246: step: 234/470, loss: 0.2812889516353607
2023-01-22 18:31:01.057153: step: 236/470, loss: 0.11035189032554626
2023-01-22 18:31:01.823379: step: 238/470, loss: 0.42968517541885376
2023-01-22 18:31:02.541104: step: 240/470, loss: 0.014646702446043491
2023-01-22 18:31:03.245872: step: 242/470, loss: 0.09640643745660782
2023-01-22 18:31:04.010331: step: 244/470, loss: 0.02477741241455078
2023-01-22 18:31:04.803141: step: 246/470, loss: 0.17379818856716156
2023-01-22 18:31:05.541125: step: 248/470, loss: 0.27178406715393066
2023-01-22 18:31:06.232992: step: 250/470, loss: 0.12189687788486481
2023-01-22 18:31:06.975604: step: 252/470, loss: 0.020987318828701973
2023-01-22 18:31:07.695824: step: 254/470, loss: 0.09624991565942764
2023-01-22 18:31:08.391985: step: 256/470, loss: 0.15449093282222748
2023-01-22 18:31:09.197122: step: 258/470, loss: 0.14626288414001465
2023-01-22 18:31:09.923535: step: 260/470, loss: 0.28058895468711853
2023-01-22 18:31:10.677892: step: 262/470, loss: 0.06803245097398758
2023-01-22 18:31:11.387369: step: 264/470, loss: 0.19811493158340454
2023-01-22 18:31:12.128009: step: 266/470, loss: 0.04378509148955345
2023-01-22 18:31:12.870575: step: 268/470, loss: 0.43500596284866333
2023-01-22 18:31:13.630602: step: 270/470, loss: 0.5609925985336304
2023-01-22 18:31:14.361805: step: 272/470, loss: 0.4385612905025482
2023-01-22 18:31:15.061176: step: 274/470, loss: 0.14124025404453278
2023-01-22 18:31:15.776259: step: 276/470, loss: 0.08243583142757416
2023-01-22 18:31:16.491392: step: 278/470, loss: 0.2784011960029602
2023-01-22 18:31:17.233405: step: 280/470, loss: 0.3031136393547058
2023-01-22 18:31:17.935821: step: 282/470, loss: 0.09605658054351807
2023-01-22 18:31:18.667505: step: 284/470, loss: 0.07707042992115021
2023-01-22 18:31:19.427196: step: 286/470, loss: 0.03834238275885582
2023-01-22 18:31:20.209818: step: 288/470, loss: 0.13241738080978394
2023-01-22 18:31:20.888532: step: 290/470, loss: 0.06490999460220337
2023-01-22 18:31:21.572249: step: 292/470, loss: 0.07722263038158417
2023-01-22 18:31:22.307202: step: 294/470, loss: 0.1114049032330513
2023-01-22 18:31:23.038986: step: 296/470, loss: 0.25798553228378296
2023-01-22 18:31:23.731517: step: 298/470, loss: 0.09492284804582596
2023-01-22 18:31:24.422326: step: 300/470, loss: 0.06170547008514404
2023-01-22 18:31:25.198819: step: 302/470, loss: 0.0761180892586708
2023-01-22 18:31:25.963419: step: 304/470, loss: 0.17359501123428345
2023-01-22 18:31:26.695794: step: 306/470, loss: 0.08720303326845169
2023-01-22 18:31:27.462178: step: 308/470, loss: 0.037650175392627716
2023-01-22 18:31:28.154463: step: 310/470, loss: 0.042883120477199554
2023-01-22 18:31:28.882979: step: 312/470, loss: 0.14848671853542328
2023-01-22 18:31:29.701122: step: 314/470, loss: 0.5215410590171814
2023-01-22 18:31:30.424706: step: 316/470, loss: 0.016007540747523308
2023-01-22 18:31:31.115181: step: 318/470, loss: 0.11587570607662201
2023-01-22 18:31:31.856459: step: 320/470, loss: 0.32297030091285706
2023-01-22 18:31:32.574735: step: 322/470, loss: 0.1690657138824463
2023-01-22 18:31:33.395605: step: 324/470, loss: 0.030179066583514214
2023-01-22 18:31:34.110026: step: 326/470, loss: 0.0764576867222786
2023-01-22 18:31:34.819096: step: 328/470, loss: 0.11027715355157852
2023-01-22 18:31:35.566587: step: 330/470, loss: 0.09635484218597412
2023-01-22 18:31:36.212839: step: 332/470, loss: 0.26524147391319275
2023-01-22 18:31:36.914679: step: 334/470, loss: 0.48851656913757324
2023-01-22 18:31:37.615199: step: 336/470, loss: 0.12017401307821274
2023-01-22 18:31:38.434495: step: 338/470, loss: 0.3046230971813202
2023-01-22 18:31:39.310167: step: 340/470, loss: 0.0651002898812294
2023-01-22 18:31:40.058352: step: 342/470, loss: 0.5883811712265015
2023-01-22 18:31:40.748478: step: 344/470, loss: 0.20933616161346436
2023-01-22 18:31:41.541230: step: 346/470, loss: 0.08957860618829727
2023-01-22 18:31:42.292039: step: 348/470, loss: 0.13973873853683472
2023-01-22 18:31:42.975566: step: 350/470, loss: 0.4042279124259949
2023-01-22 18:31:43.664249: step: 352/470, loss: 0.09614955633878708
2023-01-22 18:31:44.329285: step: 354/470, loss: 0.023717915639281273
2023-01-22 18:31:45.068687: step: 356/470, loss: 0.2741442024707794
2023-01-22 18:31:45.824506: step: 358/470, loss: 0.13002316653728485
2023-01-22 18:31:46.477149: step: 360/470, loss: 0.30730727314949036
2023-01-22 18:31:47.196283: step: 362/470, loss: 0.23137405514717102
2023-01-22 18:31:47.862334: step: 364/470, loss: 0.283146470785141
2023-01-22 18:31:48.612734: step: 366/470, loss: 0.34386488795280457
2023-01-22 18:31:49.408933: step: 368/470, loss: 0.09826954454183578
2023-01-22 18:31:50.122520: step: 370/470, loss: 0.1936502754688263
2023-01-22 18:31:50.875032: step: 372/470, loss: 0.08318967372179031
2023-01-22 18:31:51.607582: step: 374/470, loss: 0.16155041754245758
2023-01-22 18:31:52.275326: step: 376/470, loss: 0.3982257843017578
2023-01-22 18:31:53.010438: step: 378/470, loss: 0.0868930071592331
2023-01-22 18:31:53.770477: step: 380/470, loss: 0.5517705082893372
2023-01-22 18:31:54.485235: step: 382/470, loss: 0.12113271653652191
2023-01-22 18:31:55.187846: step: 384/470, loss: 0.15076488256454468
2023-01-22 18:31:55.877617: step: 386/470, loss: 0.17827637493610382
2023-01-22 18:31:56.636246: step: 388/470, loss: 0.056175053119659424
2023-01-22 18:31:57.369830: step: 390/470, loss: 0.28909632563591003
2023-01-22 18:31:58.144983: step: 392/470, loss: 0.16936790943145752
2023-01-22 18:31:58.825544: step: 394/470, loss: 0.10315996408462524
2023-01-22 18:31:59.562269: step: 396/470, loss: 0.08916748315095901
2023-01-22 18:32:00.270007: step: 398/470, loss: 0.08588486909866333
2023-01-22 18:32:00.970818: step: 400/470, loss: 0.7330968976020813
2023-01-22 18:32:01.714787: step: 402/470, loss: 0.8898875117301941
2023-01-22 18:32:02.486281: step: 404/470, loss: 0.22537262737751007
2023-01-22 18:32:03.158811: step: 406/470, loss: 0.09088273346424103
2023-01-22 18:32:03.887812: step: 408/470, loss: 0.2716708183288574
2023-01-22 18:32:04.617046: step: 410/470, loss: 0.10589412599802017
2023-01-22 18:32:05.321505: step: 412/470, loss: 0.12420433014631271
2023-01-22 18:32:06.052352: step: 414/470, loss: 0.25589585304260254
2023-01-22 18:32:06.714452: step: 416/470, loss: 0.15810632705688477
2023-01-22 18:32:07.464891: step: 418/470, loss: 0.11597256362438202
2023-01-22 18:32:08.163028: step: 420/470, loss: 0.28290224075317383
2023-01-22 18:32:08.966858: step: 422/470, loss: 0.07624372839927673
2023-01-22 18:32:09.702057: step: 424/470, loss: 6.502451419830322
2023-01-22 18:32:10.395797: step: 426/470, loss: 0.054799798876047134
2023-01-22 18:32:11.141089: step: 428/470, loss: 0.29792070388793945
2023-01-22 18:32:11.978195: step: 430/470, loss: 0.20813298225402832
2023-01-22 18:32:12.757503: step: 432/470, loss: 0.04179874062538147
2023-01-22 18:32:13.497255: step: 434/470, loss: 0.0941062718629837
2023-01-22 18:32:14.276962: step: 436/470, loss: 0.21649214625358582
2023-01-22 18:32:14.983534: step: 438/470, loss: 0.12335845082998276
2023-01-22 18:32:15.711870: step: 440/470, loss: 0.0966825857758522
2023-01-22 18:32:16.528388: step: 442/470, loss: 0.07399679720401764
2023-01-22 18:32:17.354458: step: 444/470, loss: 0.12531259655952454
2023-01-22 18:32:18.097378: step: 446/470, loss: 0.08484052866697311
2023-01-22 18:32:18.848730: step: 448/470, loss: 0.13579043745994568
2023-01-22 18:32:19.632848: step: 450/470, loss: 0.1644921749830246
2023-01-22 18:32:20.320225: step: 452/470, loss: 0.11840783804655075
2023-01-22 18:32:21.001050: step: 454/470, loss: 0.05891914665699005
2023-01-22 18:32:21.723152: step: 456/470, loss: 0.23505060374736786
2023-01-22 18:32:22.426517: step: 458/470, loss: 0.15571844577789307
2023-01-22 18:32:23.135195: step: 460/470, loss: 0.19243013858795166
2023-01-22 18:32:24.009890: step: 462/470, loss: 0.14108626544475555
2023-01-22 18:32:24.769380: step: 464/470, loss: 0.15079638361930847
2023-01-22 18:32:25.549639: step: 466/470, loss: 0.25679388642311096
2023-01-22 18:32:26.368884: step: 468/470, loss: 0.110379159450531
2023-01-22 18:32:27.064665: step: 470/470, loss: 0.233668714761734
2023-01-22 18:32:27.815966: step: 472/470, loss: 0.1186995655298233
2023-01-22 18:32:28.500427: step: 474/470, loss: 0.4312833249568939
2023-01-22 18:32:29.233357: step: 476/470, loss: 0.1033293753862381
2023-01-22 18:32:29.970179: step: 478/470, loss: 0.32570046186447144
2023-01-22 18:32:30.759018: step: 480/470, loss: 0.09971433132886887
2023-01-22 18:32:31.529929: step: 482/470, loss: 1.5249170064926147
2023-01-22 18:32:32.264412: step: 484/470, loss: 0.4827004671096802
2023-01-22 18:32:32.939636: step: 486/470, loss: 0.06607785820960999
2023-01-22 18:32:33.711407: step: 488/470, loss: 0.10160824656486511
2023-01-22 18:32:34.386771: step: 490/470, loss: 0.04615769162774086
2023-01-22 18:32:35.104298: step: 492/470, loss: 0.1232377365231514
2023-01-22 18:32:35.886305: step: 494/470, loss: 0.15672165155410767
2023-01-22 18:32:36.621714: step: 496/470, loss: 0.1081511378288269
2023-01-22 18:32:37.434003: step: 498/470, loss: 0.2734154164791107
2023-01-22 18:32:38.246181: step: 500/470, loss: 0.2586720883846283
2023-01-22 18:32:38.934077: step: 502/470, loss: 0.48053133487701416
2023-01-22 18:32:39.675376: step: 504/470, loss: 0.2579320967197418
2023-01-22 18:32:40.406855: step: 506/470, loss: 0.3125365376472473
2023-01-22 18:32:41.104934: step: 508/470, loss: 0.04690413922071457
2023-01-22 18:32:41.874358: step: 510/470, loss: 0.184226855635643
2023-01-22 18:32:42.593325: step: 512/470, loss: 0.046648863703012466
2023-01-22 18:32:43.327011: step: 514/470, loss: 0.7336933016777039
2023-01-22 18:32:44.126530: step: 516/470, loss: 0.287691205739975
2023-01-22 18:32:44.860770: step: 518/470, loss: 0.2230347841978073
2023-01-22 18:32:45.586391: step: 520/470, loss: 0.15412744879722595
2023-01-22 18:32:46.284252: step: 522/470, loss: 0.2500941753387451
2023-01-22 18:32:46.914259: step: 524/470, loss: 0.19288751482963562
2023-01-22 18:32:47.824845: step: 526/470, loss: 0.216958686709404
2023-01-22 18:32:48.633096: step: 528/470, loss: 0.298077791929245
2023-01-22 18:32:49.426275: step: 530/470, loss: 0.25814521312713623
2023-01-22 18:32:50.128654: step: 532/470, loss: 0.07196559756994247
2023-01-22 18:32:50.844805: step: 534/470, loss: 0.05458388477563858
2023-01-22 18:32:51.558143: step: 536/470, loss: 0.355390727519989
2023-01-22 18:32:52.268499: step: 538/470, loss: 0.14116257429122925
2023-01-22 18:32:53.063373: step: 540/470, loss: 0.027166053652763367
2023-01-22 18:32:53.741978: step: 542/470, loss: 0.04634636268019676
2023-01-22 18:32:54.556150: step: 544/470, loss: 0.14489805698394775
2023-01-22 18:32:55.289626: step: 546/470, loss: 0.03581508621573448
2023-01-22 18:32:56.026353: step: 548/470, loss: 0.14004434645175934
2023-01-22 18:32:56.753332: step: 550/470, loss: 0.22724568843841553
2023-01-22 18:32:57.440609: step: 552/470, loss: 0.0776071846485138
2023-01-22 18:32:58.234404: step: 554/470, loss: 0.09695343673229218
2023-01-22 18:32:59.020396: step: 556/470, loss: 0.7682523131370544
2023-01-22 18:32:59.897894: step: 558/470, loss: 0.20350007712841034
2023-01-22 18:33:00.609663: step: 560/470, loss: 0.6482030749320984
2023-01-22 18:33:01.363787: step: 562/470, loss: 0.07920963317155838
2023-01-22 18:33:02.138378: step: 564/470, loss: 0.06108212471008301
2023-01-22 18:33:02.832252: step: 566/470, loss: 0.3057776391506195
2023-01-22 18:33:03.544254: step: 568/470, loss: 0.10524436086416245
2023-01-22 18:33:04.233242: step: 570/470, loss: 0.0752614364027977
2023-01-22 18:33:05.026611: step: 572/470, loss: 0.10594554245471954
2023-01-22 18:33:05.754764: step: 574/470, loss: 0.11854086071252823
2023-01-22 18:33:06.590933: step: 576/470, loss: 0.10533951222896576
2023-01-22 18:33:07.399732: step: 578/470, loss: 0.1088142916560173
2023-01-22 18:33:08.207300: step: 580/470, loss: 0.17378634214401245
2023-01-22 18:33:09.132336: step: 582/470, loss: 0.19175052642822266
2023-01-22 18:33:09.913567: step: 584/470, loss: 0.11666764318943024
2023-01-22 18:33:10.610409: step: 586/470, loss: 0.06512768566608429
2023-01-22 18:33:11.433998: step: 588/470, loss: 0.0760718509554863
2023-01-22 18:33:12.207743: step: 590/470, loss: 0.028491565957665443
2023-01-22 18:33:12.971503: step: 592/470, loss: 0.07426527142524719
2023-01-22 18:33:13.700637: step: 594/470, loss: 0.056701093912124634
2023-01-22 18:33:14.463054: step: 596/470, loss: 0.1391458362340927
2023-01-22 18:33:15.181300: step: 598/470, loss: 0.11566898971796036
2023-01-22 18:33:15.879689: step: 600/470, loss: 0.14809054136276245
2023-01-22 18:33:16.681097: step: 602/470, loss: 0.13627216219902039
2023-01-22 18:33:17.417936: step: 604/470, loss: 0.11067622900009155
2023-01-22 18:33:18.127546: step: 606/470, loss: 0.3479231595993042
2023-01-22 18:33:18.792657: step: 608/470, loss: 0.6823694109916687
2023-01-22 18:33:19.505217: step: 610/470, loss: 0.10552807152271271
2023-01-22 18:33:20.237330: step: 612/470, loss: 0.5463363528251648
2023-01-22 18:33:20.977414: step: 614/470, loss: 0.10402689129114151
2023-01-22 18:33:21.647420: step: 616/470, loss: 0.34647348523139954
2023-01-22 18:33:22.374799: step: 618/470, loss: 0.07819667458534241
2023-01-22 18:33:23.063708: step: 620/470, loss: 0.03418436273932457
2023-01-22 18:33:23.705914: step: 622/470, loss: 0.0040921662002801895
2023-01-22 18:33:24.442703: step: 624/470, loss: 0.06056486442685127
2023-01-22 18:33:25.200314: step: 626/470, loss: 0.142343208193779
2023-01-22 18:33:25.904083: step: 628/470, loss: 0.3498281240463257
2023-01-22 18:33:26.696827: step: 630/470, loss: 0.1718958616256714
2023-01-22 18:33:27.386145: step: 632/470, loss: 0.14138327538967133
2023-01-22 18:33:28.126239: step: 634/470, loss: 0.1276867389678955
2023-01-22 18:33:28.840214: step: 636/470, loss: 0.0756273865699768
2023-01-22 18:33:29.563166: step: 638/470, loss: 0.03293231502175331
2023-01-22 18:33:30.306459: step: 640/470, loss: 0.16658903658390045
2023-01-22 18:33:31.172043: step: 642/470, loss: 1.328713297843933
2023-01-22 18:33:31.907815: step: 644/470, loss: 0.14836126565933228
2023-01-22 18:33:32.587379: step: 646/470, loss: 0.12975986301898956
2023-01-22 18:33:33.420302: step: 648/470, loss: 0.2378319948911667
2023-01-22 18:33:34.146588: step: 650/470, loss: 0.1449371576309204
2023-01-22 18:33:34.854227: step: 652/470, loss: 0.0579066202044487
2023-01-22 18:33:35.572899: step: 654/470, loss: 0.17443352937698364
2023-01-22 18:33:36.242926: step: 656/470, loss: 0.08816853910684586
2023-01-22 18:33:36.989009: step: 658/470, loss: 0.19708070158958435
2023-01-22 18:33:37.753804: step: 660/470, loss: 0.3211943507194519
2023-01-22 18:33:38.453193: step: 662/470, loss: 0.08856945484876633
2023-01-22 18:33:39.276349: step: 664/470, loss: 0.14771507680416107
2023-01-22 18:33:40.018399: step: 666/470, loss: 0.6534758806228638
2023-01-22 18:33:40.807568: step: 668/470, loss: 0.5298561453819275
2023-01-22 18:33:41.524214: step: 670/470, loss: 0.3639879822731018
2023-01-22 18:33:42.273829: step: 672/470, loss: 0.06922122836112976
2023-01-22 18:33:43.031112: step: 674/470, loss: 0.44452109932899475
2023-01-22 18:33:43.727293: step: 676/470, loss: 0.10079913586378098
2023-01-22 18:33:44.454315: step: 678/470, loss: 0.12544503808021545
2023-01-22 18:33:45.183739: step: 680/470, loss: 0.14979170262813568
2023-01-22 18:33:45.932856: step: 682/470, loss: 0.10007375478744507
2023-01-22 18:33:46.721411: step: 684/470, loss: 0.015384846366941929
2023-01-22 18:33:47.474537: step: 686/470, loss: 0.04832969605922699
2023-01-22 18:33:48.119319: step: 688/470, loss: 0.1544710397720337
2023-01-22 18:33:48.960837: step: 690/470, loss: 0.3322787284851074
2023-01-22 18:33:49.703056: step: 692/470, loss: 0.3732565939426422
2023-01-22 18:33:50.477824: step: 694/470, loss: 0.13223111629486084
2023-01-22 18:33:51.223979: step: 696/470, loss: 0.301310271024704
2023-01-22 18:33:51.954556: step: 698/470, loss: 0.09329129755496979
2023-01-22 18:33:52.649738: step: 700/470, loss: 0.07543506473302841
2023-01-22 18:33:53.413790: step: 702/470, loss: 3.3870034217834473
2023-01-22 18:33:54.106315: step: 704/470, loss: 0.4438471496105194
2023-01-22 18:33:54.872783: step: 706/470, loss: 0.10665325820446014
2023-01-22 18:33:55.522274: step: 708/470, loss: 0.1168651431798935
2023-01-22 18:33:56.239036: step: 710/470, loss: 0.1690247803926468
2023-01-22 18:33:57.008445: step: 712/470, loss: 0.09398052096366882
2023-01-22 18:33:57.731056: step: 714/470, loss: 0.10398267954587936
2023-01-22 18:33:58.496580: step: 716/470, loss: 0.08926042914390564
2023-01-22 18:33:59.163621: step: 718/470, loss: 0.2242121696472168
2023-01-22 18:33:59.874594: step: 720/470, loss: 0.09120961278676987
2023-01-22 18:34:00.595854: step: 722/470, loss: 0.13982771337032318
2023-01-22 18:34:01.318260: step: 724/470, loss: 0.07675092667341232
2023-01-22 18:34:02.099148: step: 726/470, loss: 0.1070447787642479
2023-01-22 18:34:02.843769: step: 728/470, loss: 0.10396528244018555
2023-01-22 18:34:03.607391: step: 730/470, loss: 0.13090196251869202
2023-01-22 18:34:04.318222: step: 732/470, loss: 0.10720758885145187
2023-01-22 18:34:05.029911: step: 734/470, loss: 0.31446948647499084
2023-01-22 18:34:05.769144: step: 736/470, loss: 0.2971380054950714
2023-01-22 18:34:06.474777: step: 738/470, loss: 0.11717523634433746
2023-01-22 18:34:07.288639: step: 740/470, loss: 0.3187268376350403
2023-01-22 18:34:08.067475: step: 742/470, loss: 0.1835777312517166
2023-01-22 18:34:08.911798: step: 744/470, loss: 0.10451960563659668
2023-01-22 18:34:09.623700: step: 746/470, loss: 0.381958931684494
2023-01-22 18:34:10.399672: step: 748/470, loss: 0.14256399869918823
2023-01-22 18:34:11.161838: step: 750/470, loss: 0.1951764076948166
2023-01-22 18:34:11.865348: step: 752/470, loss: 0.08754151314496994
2023-01-22 18:34:12.639744: step: 754/470, loss: 0.11652766168117523
2023-01-22 18:34:13.342038: step: 756/470, loss: 0.029814664274454117
2023-01-22 18:34:14.126057: step: 758/470, loss: 0.14490105211734772
2023-01-22 18:34:14.736793: step: 760/470, loss: 0.08405127376317978
2023-01-22 18:34:15.538871: step: 762/470, loss: 0.10964828729629517
2023-01-22 18:34:16.274382: step: 764/470, loss: 0.08635842055082321
2023-01-22 18:34:17.036869: step: 766/470, loss: 0.18066643178462982
2023-01-22 18:34:17.796567: step: 768/470, loss: 0.3340843915939331
2023-01-22 18:34:18.522077: step: 770/470, loss: 0.20563696324825287
2023-01-22 18:34:19.309291: step: 772/470, loss: 0.4167340397834778
2023-01-22 18:34:20.083894: step: 774/470, loss: 0.07869897782802582
2023-01-22 18:34:20.843624: step: 776/470, loss: 0.12975147366523743
2023-01-22 18:34:21.633785: step: 778/470, loss: 0.06549026817083359
2023-01-22 18:34:22.373313: step: 780/470, loss: 0.6230465769767761
2023-01-22 18:34:23.123356: step: 782/470, loss: 0.09621866047382355
2023-01-22 18:34:23.883775: step: 784/470, loss: 0.38288676738739014
2023-01-22 18:34:24.674266: step: 786/470, loss: 0.13935059309005737
2023-01-22 18:34:25.393304: step: 788/470, loss: 0.13502168655395508
2023-01-22 18:34:26.161442: step: 790/470, loss: 0.10943473875522614
2023-01-22 18:34:26.890138: step: 792/470, loss: 0.11306705325841904
2023-01-22 18:34:27.620650: step: 794/470, loss: 0.15334700047969818
2023-01-22 18:34:28.415604: step: 796/470, loss: 0.19283847510814667
2023-01-22 18:34:29.120082: step: 798/470, loss: 0.2030116617679596
2023-01-22 18:34:29.874346: step: 800/470, loss: 0.20117712020874023
2023-01-22 18:34:30.615244: step: 802/470, loss: 0.021305864676833153
2023-01-22 18:34:31.373992: step: 804/470, loss: 0.5952919721603394
2023-01-22 18:34:32.115731: step: 806/470, loss: 0.11923728138208389
2023-01-22 18:34:32.778002: step: 808/470, loss: 0.12033215165138245
2023-01-22 18:34:33.536137: step: 810/470, loss: 0.1041664257645607
2023-01-22 18:34:34.378669: step: 812/470, loss: 0.07111985236406326
2023-01-22 18:34:35.230658: step: 814/470, loss: 0.25388404726982117
2023-01-22 18:34:36.093996: step: 816/470, loss: 0.3828502297401428
2023-01-22 18:34:36.836752: step: 818/470, loss: 0.4347081780433655
2023-01-22 18:34:37.621550: step: 820/470, loss: 0.041309136897325516
2023-01-22 18:34:38.349481: step: 822/470, loss: 0.08783011138439178
2023-01-22 18:34:39.124935: step: 824/470, loss: 0.49217742681503296
2023-01-22 18:34:39.848909: step: 826/470, loss: 0.24008692800998688
2023-01-22 18:34:40.628910: step: 828/470, loss: 0.11003921926021576
2023-01-22 18:34:41.343031: step: 830/470, loss: 0.15111075341701508
2023-01-22 18:34:42.079971: step: 832/470, loss: 0.14422738552093506
2023-01-22 18:34:42.777893: step: 834/470, loss: 0.31494441628456116
2023-01-22 18:34:43.454741: step: 836/470, loss: 0.09576459974050522
2023-01-22 18:34:44.149505: step: 838/470, loss: 0.07254704087972641
2023-01-22 18:34:44.901016: step: 840/470, loss: 0.1577906757593155
2023-01-22 18:34:45.642361: step: 842/470, loss: 1.3641383647918701
2023-01-22 18:34:46.379821: step: 844/470, loss: 0.16647478938102722
2023-01-22 18:34:47.129873: step: 846/470, loss: 0.06729204952716827
2023-01-22 18:34:47.924968: step: 848/470, loss: 0.6149294972419739
2023-01-22 18:34:48.629355: step: 850/470, loss: 0.058741990476846695
2023-01-22 18:34:49.382115: step: 852/470, loss: 0.13534869253635406
2023-01-22 18:34:50.174354: step: 854/470, loss: 0.11562196910381317
2023-01-22 18:34:50.890639: step: 856/470, loss: 0.14991667866706848
2023-01-22 18:34:51.614010: step: 858/470, loss: 0.12905238568782806
2023-01-22 18:34:52.392525: step: 860/470, loss: 0.0312718003988266
2023-01-22 18:34:53.171421: step: 862/470, loss: 0.1413513869047165
2023-01-22 18:34:53.865391: step: 864/470, loss: 0.2965477705001831
2023-01-22 18:34:54.601618: step: 866/470, loss: 0.1007094457745552
2023-01-22 18:34:55.395910: step: 868/470, loss: 0.1321275383234024
2023-01-22 18:34:56.239500: step: 870/470, loss: 0.1397213190793991
2023-01-22 18:34:56.986710: step: 872/470, loss: 0.5523156523704529
2023-01-22 18:34:57.724158: step: 874/470, loss: 0.03732849657535553
2023-01-22 18:34:58.581161: step: 876/470, loss: 0.17241162061691284
2023-01-22 18:34:59.356894: step: 878/470, loss: 0.5599587559700012
2023-01-22 18:35:00.083212: step: 880/470, loss: 0.1906861662864685
2023-01-22 18:35:00.857606: step: 882/470, loss: 0.07153639942407608
2023-01-22 18:35:01.740629: step: 884/470, loss: 0.17692595720291138
2023-01-22 18:35:02.441592: step: 886/470, loss: 0.08000165224075317
2023-01-22 18:35:03.251054: step: 888/470, loss: 7.325255870819092
2023-01-22 18:35:04.012136: step: 890/470, loss: 0.07783879339694977
2023-01-22 18:35:04.748414: step: 892/470, loss: 0.06207854673266411
2023-01-22 18:35:05.410236: step: 894/470, loss: 0.1321595311164856
2023-01-22 18:35:06.213646: step: 896/470, loss: 0.19343137741088867
2023-01-22 18:35:06.988115: step: 898/470, loss: 0.10653921216726303
2023-01-22 18:35:07.696910: step: 900/470, loss: 0.12337514758110046
2023-01-22 18:35:08.389942: step: 902/470, loss: 0.13530763983726501
2023-01-22 18:35:09.171163: step: 904/470, loss: 0.05055097118020058
2023-01-22 18:35:09.838165: step: 906/470, loss: 0.05119376629590988
2023-01-22 18:35:10.544770: step: 908/470, loss: 0.05396522581577301
2023-01-22 18:35:11.275889: step: 910/470, loss: 0.16279923915863037
2023-01-22 18:35:12.053764: step: 912/470, loss: 0.10443281382322311
2023-01-22 18:35:12.883434: step: 914/470, loss: 0.08299147337675095
2023-01-22 18:35:13.622024: step: 916/470, loss: 0.11369689553976059
2023-01-22 18:35:14.351793: step: 918/470, loss: 0.9923412799835205
2023-01-22 18:35:15.130875: step: 920/470, loss: 0.12374808639287949
2023-01-22 18:35:15.949770: step: 922/470, loss: 0.29581671953201294
2023-01-22 18:35:16.704783: step: 924/470, loss: 0.20488214492797852
2023-01-22 18:35:17.471704: step: 926/470, loss: 0.2639607787132263
2023-01-22 18:35:18.156248: step: 928/470, loss: 0.11370810866355896
2023-01-22 18:35:18.901149: step: 930/470, loss: 0.3266356289386749
2023-01-22 18:35:19.610237: step: 932/470, loss: 0.0699765533208847
2023-01-22 18:35:20.352927: step: 934/470, loss: 0.05949941277503967
2023-01-22 18:35:21.045420: step: 936/470, loss: 0.09237470477819443
2023-01-22 18:35:21.790969: step: 938/470, loss: 0.20467214286327362
2023-01-22 18:35:22.473434: step: 940/470, loss: 0.23523172736167908
2023-01-22 18:35:23.199115: step: 942/470, loss: 0.17894554138183594
==================================================
Loss: 0.225
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28994319242254574, 'r': 0.3102997353440527, 'f1': 0.2997762796082783}, 'combined': 0.22088778497452083, 'epoch': 14}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3507474812318518, 'r': 0.36187696861709323, 'f1': 0.3562253169538826}, 'combined': 0.2481171361867839, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2747616086235489, 'r': 0.31438567362428843, 'f1': 0.29324115044247784}, 'combined': 0.21607242664182577, 'epoch': 14}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3377919490575152, 'r': 0.368618303678518, 'f1': 0.3525325256126204}, 'combined': 0.24554504271525798, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.28846153846153844, 'r': 0.4891304347826087, 'f1': 0.3629032258064516}, 'combined': 0.1814516129032258, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5416666666666666, 'r': 0.33620689655172414, 'f1': 0.41489361702127664}, 'combined': 0.2765957446808511, 'epoch': 14}
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': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28994319242254574, 'r': 0.3102997353440527, 'f1': 0.2997762796082783}, 'combined': 0.22088778497452083, 'epoch': 14}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3507474812318518, 'r': 0.36187696861709323, 'f1': 0.3562253169538826}, 'combined': 0.2481171361867839, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.28846153846153844, 'r': 0.4891304347826087, 'f1': 0.3629032258064516}, 'combined': 0.1814516129032258, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2747616086235489, 'r': 0.31438567362428843, 'f1': 0.29324115044247784}, 'combined': 0.21607242664182577, 'epoch': 14}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3377919490575152, 'r': 0.368618303678518, 'f1': 0.3525325256126204}, 'combined': 0.24554504271525798, 'epoch': 14}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5416666666666666, 'r': 0.33620689655172414, 'f1': 0.41489361702127664}, 'combined': 0.2765957446808511, 'epoch': 14}
******************************
Epoch: 15
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 18:38:17.732373: step: 2/470, loss: 0.11473778635263443
2023-01-22 18:38:18.447360: step: 4/470, loss: 0.14706557989120483
2023-01-22 18:38:19.216206: step: 6/470, loss: 0.1552312821149826
2023-01-22 18:38:19.973172: step: 8/470, loss: 0.23627066612243652
2023-01-22 18:38:20.828198: step: 10/470, loss: 0.0939834862947464
2023-01-22 18:38:21.504151: step: 12/470, loss: 0.12837252020835876
2023-01-22 18:38:22.245559: step: 14/470, loss: 0.15545101463794708
2023-01-22 18:38:23.006293: step: 16/470, loss: 0.23269550502300262
2023-01-22 18:38:23.799190: step: 18/470, loss: 0.2941681742668152
2023-01-22 18:38:24.510845: step: 20/470, loss: 0.05719856545329094
2023-01-22 18:38:25.239891: step: 22/470, loss: 0.1427365392446518
2023-01-22 18:38:26.016893: step: 24/470, loss: 0.12609969079494476
2023-01-22 18:38:26.705118: step: 26/470, loss: 0.03879668563604355
2023-01-22 18:38:27.536119: step: 28/470, loss: 0.09652974456548691
2023-01-22 18:38:28.328946: step: 30/470, loss: 0.08992653340101242
2023-01-22 18:38:29.044397: step: 32/470, loss: 0.18987002968788147
2023-01-22 18:38:29.729254: step: 34/470, loss: 0.021707141771912575
2023-01-22 18:38:30.526383: step: 36/470, loss: 0.1298495978116989
2023-01-22 18:38:31.255065: step: 38/470, loss: 0.19483181834220886
2023-01-22 18:38:31.984781: step: 40/470, loss: 0.0935438945889473
2023-01-22 18:38:32.766689: step: 42/470, loss: 0.038643594831228256
2023-01-22 18:38:33.511509: step: 44/470, loss: 0.08340389281511307
2023-01-22 18:38:34.204484: step: 46/470, loss: 0.02248873934149742
2023-01-22 18:38:34.970063: step: 48/470, loss: 0.08780361711978912
2023-01-22 18:38:35.673223: step: 50/470, loss: 0.9724255204200745
2023-01-22 18:38:36.416557: step: 52/470, loss: 0.19970646500587463
2023-01-22 18:38:37.086923: step: 54/470, loss: 0.1309264898300171
2023-01-22 18:38:37.808575: step: 56/470, loss: 0.050499871373176575
2023-01-22 18:38:38.529689: step: 58/470, loss: 0.07953242212533951
2023-01-22 18:38:39.245755: step: 60/470, loss: 0.04383343458175659
2023-01-22 18:38:39.980134: step: 62/470, loss: 0.08836504071950912
2023-01-22 18:38:40.762393: step: 64/470, loss: 2.471203565597534
2023-01-22 18:38:41.482594: step: 66/470, loss: 0.03604745864868164
2023-01-22 18:38:42.232509: step: 68/470, loss: 0.0975373387336731
2023-01-22 18:38:42.954666: step: 70/470, loss: 0.06281895935535431
2023-01-22 18:38:43.803491: step: 72/470, loss: 0.1086447536945343
2023-01-22 18:38:44.573912: step: 74/470, loss: 0.058805786073207855
2023-01-22 18:38:45.338879: step: 76/470, loss: 0.14832088351249695
2023-01-22 18:38:46.165288: step: 78/470, loss: 0.30360713601112366
2023-01-22 18:38:47.002904: step: 80/470, loss: 2.0807321071624756
2023-01-22 18:38:47.712981: step: 82/470, loss: 0.15625305473804474
2023-01-22 18:38:48.468346: step: 84/470, loss: 0.3062744140625
2023-01-22 18:38:49.319833: step: 86/470, loss: 0.05567606911063194
2023-01-22 18:38:50.012851: step: 88/470, loss: 0.09600371867418289
2023-01-22 18:38:50.692834: step: 90/470, loss: 0.024420877918601036
2023-01-22 18:38:51.489625: step: 92/470, loss: 0.2148466855287552
2023-01-22 18:38:52.188701: step: 94/470, loss: 0.10316638648509979
2023-01-22 18:38:52.870665: step: 96/470, loss: 0.06793716549873352
2023-01-22 18:38:53.582575: step: 98/470, loss: 0.11314757913351059
2023-01-22 18:38:54.358545: step: 100/470, loss: 0.10866573452949524
2023-01-22 18:38:55.095533: step: 102/470, loss: 0.06647631525993347
2023-01-22 18:38:55.798299: step: 104/470, loss: 0.053145021200180054
2023-01-22 18:38:56.630469: step: 106/470, loss: 0.0989309549331665
2023-01-22 18:38:57.336426: step: 108/470, loss: 0.07991360872983932
2023-01-22 18:38:58.079186: step: 110/470, loss: 0.28862452507019043
2023-01-22 18:38:58.857546: step: 112/470, loss: 0.05426064506173134
2023-01-22 18:38:59.563460: step: 114/470, loss: 0.090945765376091
2023-01-22 18:39:00.292389: step: 116/470, loss: 0.05981391668319702
2023-01-22 18:39:00.967092: step: 118/470, loss: 0.04086308926343918
2023-01-22 18:39:01.699119: step: 120/470, loss: 0.279904305934906
2023-01-22 18:39:02.387573: step: 122/470, loss: 0.08591174334287643
2023-01-22 18:39:03.089497: step: 124/470, loss: 0.025589006021618843
2023-01-22 18:39:03.773570: step: 126/470, loss: 0.2623073160648346
2023-01-22 18:39:04.493596: step: 128/470, loss: 0.03692317008972168
2023-01-22 18:39:05.193010: step: 130/470, loss: 0.16277796030044556
2023-01-22 18:39:05.935760: step: 132/470, loss: 0.11714790016412735
2023-01-22 18:39:06.595108: step: 134/470, loss: 0.16155806183815002
2023-01-22 18:39:07.294032: step: 136/470, loss: 0.034791506826877594
2023-01-22 18:39:07.994975: step: 138/470, loss: 0.15954738855361938
2023-01-22 18:39:08.842417: step: 140/470, loss: 0.100949726998806
2023-01-22 18:39:09.685810: step: 142/470, loss: 0.08963809162378311
2023-01-22 18:39:10.456769: step: 144/470, loss: 0.597632884979248
2023-01-22 18:39:11.158178: step: 146/470, loss: 0.07044071704149246
2023-01-22 18:39:11.933503: step: 148/470, loss: 0.09197443723678589
2023-01-22 18:39:12.716673: step: 150/470, loss: 0.09861261397600174
2023-01-22 18:39:13.447623: step: 152/470, loss: 0.054308950901031494
2023-01-22 18:39:14.140829: step: 154/470, loss: 0.224558487534523
2023-01-22 18:39:14.842023: step: 156/470, loss: 1.2589021921157837
2023-01-22 18:39:15.595926: step: 158/470, loss: 0.6944888234138489
2023-01-22 18:39:16.277903: step: 160/470, loss: 0.2508222460746765
2023-01-22 18:39:17.071591: step: 162/470, loss: 0.16872183978557587
2023-01-22 18:39:17.776433: step: 164/470, loss: 0.13078132271766663
2023-01-22 18:39:18.407292: step: 166/470, loss: 0.09100139886140823
2023-01-22 18:39:19.160556: step: 168/470, loss: 0.05044722184538841
2023-01-22 18:39:19.877524: step: 170/470, loss: 0.13399793207645416
2023-01-22 18:39:20.555444: step: 172/470, loss: 0.6419817209243774
2023-01-22 18:39:21.327622: step: 174/470, loss: 0.01634124107658863
2023-01-22 18:39:22.000573: step: 176/470, loss: 0.025893285870552063
2023-01-22 18:39:22.704282: step: 178/470, loss: 0.11607389897108078
2023-01-22 18:39:23.438878: step: 180/470, loss: 0.07055290043354034
2023-01-22 18:39:24.176750: step: 182/470, loss: 0.11892832070589066
2023-01-22 18:39:24.855104: step: 184/470, loss: 0.04048566147685051
2023-01-22 18:39:25.563855: step: 186/470, loss: 0.06207974627614021
2023-01-22 18:39:26.313006: step: 188/470, loss: 0.026901859790086746
2023-01-22 18:39:27.060332: step: 190/470, loss: 0.15540508925914764
2023-01-22 18:39:27.875189: step: 192/470, loss: 0.05698360875248909
2023-01-22 18:39:28.609738: step: 194/470, loss: 0.9431207180023193
2023-01-22 18:39:29.370667: step: 196/470, loss: 0.5588711500167847
2023-01-22 18:39:30.107456: step: 198/470, loss: 0.6502451300621033
2023-01-22 18:39:30.949331: step: 200/470, loss: 0.08674420416355133
2023-01-22 18:39:31.692494: step: 202/470, loss: 0.04215487837791443
2023-01-22 18:39:32.466513: step: 204/470, loss: 0.11216975003480911
2023-01-22 18:39:33.116707: step: 206/470, loss: 0.016669681295752525
2023-01-22 18:39:33.964284: step: 208/470, loss: 0.11073028296232224
2023-01-22 18:39:34.726513: step: 210/470, loss: 0.26849380135536194
2023-01-22 18:39:35.508827: step: 212/470, loss: 0.13260619342327118
2023-01-22 18:39:36.289699: step: 214/470, loss: 0.0956636592745781
2023-01-22 18:39:36.997836: step: 216/470, loss: 0.04913400486111641
2023-01-22 18:39:37.798191: step: 218/470, loss: 0.11870007961988449
2023-01-22 18:39:38.530783: step: 220/470, loss: 0.051276322454214096
2023-01-22 18:39:39.262726: step: 222/470, loss: 0.15064826607704163
2023-01-22 18:39:39.968292: step: 224/470, loss: 0.0929044634103775
2023-01-22 18:39:40.829882: step: 226/470, loss: 0.09530377388000488
2023-01-22 18:39:41.684390: step: 228/470, loss: 0.5640994906425476
2023-01-22 18:39:42.370830: step: 230/470, loss: 0.0663192942738533
2023-01-22 18:39:43.134368: step: 232/470, loss: 0.10693991929292679
2023-01-22 18:39:43.861938: step: 234/470, loss: 0.05415727570652962
2023-01-22 18:39:44.745777: step: 236/470, loss: 0.048255015164613724
2023-01-22 18:39:45.519424: step: 238/470, loss: 0.12781493365764618
2023-01-22 18:39:46.238211: step: 240/470, loss: 0.06164423003792763
2023-01-22 18:39:46.972355: step: 242/470, loss: 1.3429557085037231
2023-01-22 18:39:47.685065: step: 244/470, loss: 0.14472408592700958
2023-01-22 18:39:48.644008: step: 246/470, loss: 0.2433803528547287
2023-01-22 18:39:49.353043: step: 248/470, loss: 0.17759829759597778
2023-01-22 18:39:50.099901: step: 250/470, loss: 0.15550030767917633
2023-01-22 18:39:50.813531: step: 252/470, loss: 0.1389748603105545
2023-01-22 18:39:51.533343: step: 254/470, loss: 0.11234139651060104
2023-01-22 18:39:52.237407: step: 256/470, loss: 0.0669410452246666
2023-01-22 18:39:53.080674: step: 258/470, loss: 0.1081426739692688
2023-01-22 18:39:53.837983: step: 260/470, loss: 0.048209790140390396
2023-01-22 18:39:54.567834: step: 262/470, loss: 0.09756072610616684
2023-01-22 18:39:55.350778: step: 264/470, loss: 0.07871279865503311
2023-01-22 18:39:56.088512: step: 266/470, loss: 0.04785219579935074
2023-01-22 18:39:56.848230: step: 268/470, loss: 0.1019335687160492
2023-01-22 18:39:57.551105: step: 270/470, loss: 0.16639164090156555
2023-01-22 18:39:58.361838: step: 272/470, loss: 0.18241894245147705
2023-01-22 18:39:59.139831: step: 274/470, loss: 0.024366773664951324
2023-01-22 18:39:59.916304: step: 276/470, loss: 0.5418151021003723
2023-01-22 18:40:00.631538: step: 278/470, loss: 0.031031997874379158
2023-01-22 18:40:01.354998: step: 280/470, loss: 0.06488221883773804
2023-01-22 18:40:02.123678: step: 282/470, loss: 0.07829637080430984
2023-01-22 18:40:02.915091: step: 284/470, loss: 0.11502385139465332
2023-01-22 18:40:03.672356: step: 286/470, loss: 0.036991775035858154
2023-01-22 18:40:04.474023: step: 288/470, loss: 0.04660653695464134
2023-01-22 18:40:05.153159: step: 290/470, loss: 0.06741064786911011
2023-01-22 18:40:05.799719: step: 292/470, loss: 0.054885994642972946
2023-01-22 18:40:06.555420: step: 294/470, loss: 0.03092462196946144
2023-01-22 18:40:07.250856: step: 296/470, loss: 0.022188784554600716
2023-01-22 18:40:08.057599: step: 298/470, loss: 0.30903947353363037
2023-01-22 18:40:08.833008: step: 300/470, loss: 0.07914907485246658
2023-01-22 18:40:09.562276: step: 302/470, loss: 0.19007016718387604
2023-01-22 18:40:10.315468: step: 304/470, loss: 0.12614548206329346
2023-01-22 18:40:11.108871: step: 306/470, loss: 0.05936804041266441
2023-01-22 18:40:11.775439: step: 308/470, loss: 0.08794538676738739
2023-01-22 18:40:12.629987: step: 310/470, loss: 0.014910301193594933
2023-01-22 18:40:13.370399: step: 312/470, loss: 0.44476574659347534
2023-01-22 18:40:14.226702: step: 314/470, loss: 0.2262786328792572
2023-01-22 18:40:14.965028: step: 316/470, loss: 0.04540727660059929
2023-01-22 18:40:15.729861: step: 318/470, loss: 0.09350919723510742
2023-01-22 18:40:16.482734: step: 320/470, loss: 0.3775199353694916
2023-01-22 18:40:17.237092: step: 322/470, loss: 0.09253061562776566
2023-01-22 18:40:17.943038: step: 324/470, loss: 0.040534548461437225
2023-01-22 18:40:18.655621: step: 326/470, loss: 0.5241174697875977
2023-01-22 18:40:19.434592: step: 328/470, loss: 0.24729689955711365
2023-01-22 18:40:20.182652: step: 330/470, loss: 0.09145756810903549
2023-01-22 18:40:20.951389: step: 332/470, loss: 0.08529587835073471
2023-01-22 18:40:21.681369: step: 334/470, loss: 0.07263697683811188
2023-01-22 18:40:22.351687: step: 336/470, loss: 0.04024118930101395
2023-01-22 18:40:23.117413: step: 338/470, loss: 0.06803514063358307
2023-01-22 18:40:23.911902: step: 340/470, loss: 0.4728766679763794
2023-01-22 18:40:24.628416: step: 342/470, loss: 0.10786987096071243
2023-01-22 18:40:25.420973: step: 344/470, loss: 0.05304402485489845
2023-01-22 18:40:26.102541: step: 346/470, loss: 0.13090533018112183
2023-01-22 18:40:26.770861: step: 348/470, loss: 0.02692641317844391
2023-01-22 18:40:27.493236: step: 350/470, loss: 0.292754203081131
2023-01-22 18:40:28.226626: step: 352/470, loss: 0.10036718100309372
2023-01-22 18:40:28.891093: step: 354/470, loss: 0.08418302237987518
2023-01-22 18:40:29.689821: step: 356/470, loss: 0.8037522435188293
2023-01-22 18:40:30.514564: step: 358/470, loss: 0.10909231752157211
2023-01-22 18:40:31.251171: step: 360/470, loss: 0.15878289937973022
2023-01-22 18:40:31.958875: step: 362/470, loss: 0.41693437099456787
2023-01-22 18:40:32.620051: step: 364/470, loss: 0.526682436466217
2023-01-22 18:40:33.406351: step: 366/470, loss: 1.07395601272583
2023-01-22 18:40:34.083012: step: 368/470, loss: 0.10555024445056915
2023-01-22 18:40:34.863828: step: 370/470, loss: 0.06377702951431274
2023-01-22 18:40:35.671019: step: 372/470, loss: 0.06496112048625946
2023-01-22 18:40:36.385603: step: 374/470, loss: 0.28721484541893005
2023-01-22 18:40:37.111121: step: 376/470, loss: 0.06607744842767715
2023-01-22 18:40:37.817700: step: 378/470, loss: 0.10380702465772629
2023-01-22 18:40:38.549993: step: 380/470, loss: 0.545688807964325
2023-01-22 18:40:39.366609: step: 382/470, loss: 0.08570117503404617
2023-01-22 18:40:40.163882: step: 384/470, loss: 0.09269419312477112
2023-01-22 18:40:40.828262: step: 386/470, loss: 0.13103975355625153
2023-01-22 18:40:41.567449: step: 388/470, loss: 0.16990436613559723
2023-01-22 18:40:42.306256: step: 390/470, loss: 0.07417949289083481
2023-01-22 18:40:43.159876: step: 392/470, loss: 0.30628538131713867
2023-01-22 18:40:43.913043: step: 394/470, loss: 0.037749405950307846
2023-01-22 18:40:44.733922: step: 396/470, loss: 0.17938406765460968
2023-01-22 18:40:45.402848: step: 398/470, loss: 0.1570398360490799
2023-01-22 18:40:46.105092: step: 400/470, loss: 0.07525985687971115
2023-01-22 18:40:46.761461: step: 402/470, loss: 0.3523021340370178
2023-01-22 18:40:47.452049: step: 404/470, loss: 0.7962073087692261
2023-01-22 18:40:48.113801: step: 406/470, loss: 0.620932936668396
2023-01-22 18:40:48.836679: step: 408/470, loss: 0.1963292360305786
2023-01-22 18:40:49.526743: step: 410/470, loss: 0.29872724413871765
2023-01-22 18:40:50.235244: step: 412/470, loss: 0.20817507803440094
2023-01-22 18:40:51.000626: step: 414/470, loss: 0.12282727658748627
2023-01-22 18:40:51.610545: step: 416/470, loss: 0.10243619978427887
2023-01-22 18:40:52.369499: step: 418/470, loss: 0.17507648468017578
2023-01-22 18:40:53.142418: step: 420/470, loss: 0.17442834377288818
2023-01-22 18:40:53.931724: step: 422/470, loss: 0.25709930062294006
2023-01-22 18:40:54.744194: step: 424/470, loss: 0.08250849694013596
2023-01-22 18:40:55.451320: step: 426/470, loss: 0.09402203559875488
2023-01-22 18:40:56.148678: step: 428/470, loss: 0.11240358650684357
2023-01-22 18:40:56.976236: step: 430/470, loss: 0.1616356074810028
2023-01-22 18:40:57.711697: step: 432/470, loss: 0.048348795622587204
2023-01-22 18:40:58.417039: step: 434/470, loss: 0.06427058577537537
2023-01-22 18:40:59.131358: step: 436/470, loss: 0.10640700906515121
2023-01-22 18:40:59.847526: step: 438/470, loss: 0.23929402232170105
2023-01-22 18:41:00.674589: step: 440/470, loss: 0.12179520726203918
2023-01-22 18:41:01.452849: step: 442/470, loss: 0.10428435355424881
2023-01-22 18:41:02.219000: step: 444/470, loss: 0.06364937126636505
2023-01-22 18:41:02.872143: step: 446/470, loss: 0.18099617958068848
2023-01-22 18:41:03.558901: step: 448/470, loss: 0.19195039570331573
2023-01-22 18:41:04.264804: step: 450/470, loss: 0.11918045580387115
2023-01-22 18:41:05.027364: step: 452/470, loss: 0.24603021144866943
2023-01-22 18:41:05.722338: step: 454/470, loss: 0.09445057809352875
2023-01-22 18:41:06.486494: step: 456/470, loss: 0.0714806392788887
2023-01-22 18:41:07.239503: step: 458/470, loss: 0.06616587191820145
2023-01-22 18:41:07.990134: step: 460/470, loss: 0.23478007316589355
2023-01-22 18:41:08.812910: step: 462/470, loss: 0.10817045718431473
2023-01-22 18:41:09.447736: step: 464/470, loss: 0.12772588431835175
2023-01-22 18:41:10.132043: step: 466/470, loss: 0.11464595049619675
2023-01-22 18:41:10.882333: step: 468/470, loss: 0.4346560835838318
2023-01-22 18:41:11.591102: step: 470/470, loss: 0.055237311869859695
2023-01-22 18:41:12.315742: step: 472/470, loss: 0.13824693858623505
2023-01-22 18:41:13.055550: step: 474/470, loss: 0.1086035966873169
2023-01-22 18:41:13.778326: step: 476/470, loss: 0.26932814717292786
2023-01-22 18:41:14.533547: step: 478/470, loss: 3.1218864917755127
2023-01-22 18:41:15.305751: step: 480/470, loss: 0.06301096081733704
2023-01-22 18:41:16.002031: step: 482/470, loss: 0.21947330236434937
2023-01-22 18:41:16.744386: step: 484/470, loss: 0.0712946206331253
2023-01-22 18:41:17.549383: step: 486/470, loss: 0.35837650299072266
2023-01-22 18:41:18.276856: step: 488/470, loss: 0.05311376228928566
2023-01-22 18:41:19.063472: step: 490/470, loss: 0.07864044606685638
2023-01-22 18:41:19.914001: step: 492/470, loss: 0.15913601219654083
2023-01-22 18:41:20.606152: step: 494/470, loss: 0.49420005083084106
2023-01-22 18:41:21.294649: step: 496/470, loss: 0.07326009124517441
2023-01-22 18:41:21.978948: step: 498/470, loss: 0.09878735989332199
2023-01-22 18:41:22.750833: step: 500/470, loss: 0.18507295846939087
2023-01-22 18:41:23.598642: step: 502/470, loss: 0.23065824806690216
2023-01-22 18:41:24.363829: step: 504/470, loss: 0.056721873581409454
2023-01-22 18:41:25.062999: step: 506/470, loss: 0.04180415719747543
2023-01-22 18:41:25.789142: step: 508/470, loss: 0.4849397838115692
2023-01-22 18:41:26.535260: step: 510/470, loss: 0.12329412996768951
2023-01-22 18:41:27.242742: step: 512/470, loss: 0.4908522963523865
2023-01-22 18:41:28.064601: step: 514/470, loss: 0.42387697100639343
2023-01-22 18:41:28.803680: step: 516/470, loss: 0.07153800129890442
2023-01-22 18:41:29.548963: step: 518/470, loss: 0.0721924901008606
2023-01-22 18:41:30.280772: step: 520/470, loss: 0.6146575212478638
2023-01-22 18:41:31.023474: step: 522/470, loss: 0.10892462730407715
2023-01-22 18:41:31.762613: step: 524/470, loss: 0.06572824716567993
2023-01-22 18:41:32.518664: step: 526/470, loss: 0.15284620225429535
2023-01-22 18:41:33.280844: step: 528/470, loss: 0.18958349525928497
2023-01-22 18:41:33.968282: step: 530/470, loss: 0.03336469456553459
2023-01-22 18:41:34.705497: step: 532/470, loss: 0.1496352255344391
2023-01-22 18:41:35.429953: step: 534/470, loss: 0.13351905345916748
2023-01-22 18:41:36.120620: step: 536/470, loss: 0.08257067203521729
2023-01-22 18:41:36.856374: step: 538/470, loss: 0.7537316679954529
2023-01-22 18:41:37.571641: step: 540/470, loss: 0.3301614224910736
2023-01-22 18:41:38.252688: step: 542/470, loss: 0.08029845356941223
2023-01-22 18:41:38.996143: step: 544/470, loss: 0.08368469774723053
2023-01-22 18:41:39.756209: step: 546/470, loss: 0.054839249700307846
2023-01-22 18:41:40.475187: step: 548/470, loss: 0.0818573608994484
2023-01-22 18:41:41.219075: step: 550/470, loss: 0.09326575696468353
2023-01-22 18:41:42.009626: step: 552/470, loss: 0.08490006625652313
2023-01-22 18:41:42.675805: step: 554/470, loss: 0.2637978792190552
2023-01-22 18:41:43.402293: step: 556/470, loss: 0.02072441391646862
2023-01-22 18:41:44.121008: step: 558/470, loss: 0.07177267968654633
2023-01-22 18:41:44.921734: step: 560/470, loss: 0.17377981543540955
2023-01-22 18:41:45.630850: step: 562/470, loss: 0.10091854631900787
2023-01-22 18:41:46.342223: step: 564/470, loss: 0.07952025532722473
2023-01-22 18:41:47.037558: step: 566/470, loss: 0.021815728396177292
2023-01-22 18:41:47.819449: step: 568/470, loss: 0.1319160908460617
2023-01-22 18:41:48.444929: step: 570/470, loss: 0.03820590302348137
2023-01-22 18:41:49.189378: step: 572/470, loss: 0.05425729230046272
2023-01-22 18:41:49.880851: step: 574/470, loss: 0.07900302857160568
2023-01-22 18:41:50.653645: step: 576/470, loss: 0.10675648599863052
2023-01-22 18:41:51.380607: step: 578/470, loss: 0.13442978262901306
2023-01-22 18:41:52.123071: step: 580/470, loss: 0.16306370496749878
2023-01-22 18:41:52.834833: step: 582/470, loss: 0.22952473163604736
2023-01-22 18:41:53.630641: step: 584/470, loss: 0.2049272507429123
2023-01-22 18:41:54.403324: step: 586/470, loss: 0.01995740458369255
2023-01-22 18:41:55.155763: step: 588/470, loss: 0.10787932574748993
2023-01-22 18:41:55.905802: step: 590/470, loss: 0.06048334389925003
2023-01-22 18:41:56.698074: step: 592/470, loss: 0.23972097039222717
2023-01-22 18:41:57.373582: step: 594/470, loss: 0.3398410975933075
2023-01-22 18:41:58.062229: step: 596/470, loss: 0.23750761151313782
2023-01-22 18:41:58.805803: step: 598/470, loss: 0.07478002458810806
2023-01-22 18:41:59.601117: step: 600/470, loss: 0.046232108026742935
2023-01-22 18:42:00.393516: step: 602/470, loss: 0.18411901593208313
2023-01-22 18:42:01.215647: step: 604/470, loss: 0.249111145734787
2023-01-22 18:42:01.992301: step: 606/470, loss: 0.10080849379301071
2023-01-22 18:42:02.756650: step: 608/470, loss: 0.34081441164016724
2023-01-22 18:42:03.456719: step: 610/470, loss: 0.10482829064130783
2023-01-22 18:42:04.291651: step: 612/470, loss: 0.1037624180316925
2023-01-22 18:42:05.081597: step: 614/470, loss: 0.14347702264785767
2023-01-22 18:42:05.903051: step: 616/470, loss: 0.6947146654129028
2023-01-22 18:42:06.631841: step: 618/470, loss: 0.10346982628107071
2023-01-22 18:42:07.343505: step: 620/470, loss: 0.0636051818728447
2023-01-22 18:42:08.163053: step: 622/470, loss: 0.5542206168174744
2023-01-22 18:42:08.977529: step: 624/470, loss: 0.1027393713593483
2023-01-22 18:42:09.716339: step: 626/470, loss: 0.08677075058221817
2023-01-22 18:42:10.433024: step: 628/470, loss: 0.09158849716186523
2023-01-22 18:42:11.119487: step: 630/470, loss: 0.05454597622156143
2023-01-22 18:42:11.796740: step: 632/470, loss: 0.2582951486110687
2023-01-22 18:42:12.634984: step: 634/470, loss: 0.06388426572084427
2023-01-22 18:42:13.375616: step: 636/470, loss: 0.08858684450387955
2023-01-22 18:42:14.118112: step: 638/470, loss: 0.08609853684902191
2023-01-22 18:42:14.868775: step: 640/470, loss: 0.06940389424562454
2023-01-22 18:42:15.611105: step: 642/470, loss: 0.42918092012405396
2023-01-22 18:42:16.353469: step: 644/470, loss: 0.10172919929027557
2023-01-22 18:42:17.043298: step: 646/470, loss: 0.09180402010679245
2023-01-22 18:42:17.752447: step: 648/470, loss: 0.08429131656885147
2023-01-22 18:42:18.474477: step: 650/470, loss: 0.1133129671216011
2023-01-22 18:42:19.173446: step: 652/470, loss: 0.3817265033721924
2023-01-22 18:42:19.908040: step: 654/470, loss: 0.17819011211395264
2023-01-22 18:42:20.607393: step: 656/470, loss: 0.060797855257987976
2023-01-22 18:42:21.388675: step: 658/470, loss: 0.24461068212985992
2023-01-22 18:42:22.204163: step: 660/470, loss: 5.418313980102539
2023-01-22 18:42:22.933919: step: 662/470, loss: 0.05842447280883789
2023-01-22 18:42:23.636923: step: 664/470, loss: 1.0201159715652466
2023-01-22 18:42:24.461377: step: 666/470, loss: 0.44793573021888733
2023-01-22 18:42:25.177135: step: 668/470, loss: 0.16222833096981049
2023-01-22 18:42:25.869211: step: 670/470, loss: 0.13106600940227509
2023-01-22 18:42:26.622651: step: 672/470, loss: 0.07552053779363632
2023-01-22 18:42:27.338745: step: 674/470, loss: 0.043479401618242264
2023-01-22 18:42:28.131288: step: 676/470, loss: 0.16281522810459137
2023-01-22 18:42:28.919327: step: 678/470, loss: 0.07090484350919724
2023-01-22 18:42:29.644160: step: 680/470, loss: 0.8017717003822327
2023-01-22 18:42:30.382596: step: 682/470, loss: 0.2855534553527832
2023-01-22 18:42:31.119058: step: 684/470, loss: 0.12028669565916061
2023-01-22 18:42:31.854251: step: 686/470, loss: 0.20114941895008087
2023-01-22 18:42:32.607350: step: 688/470, loss: 0.08315178006887436
2023-01-22 18:42:33.313903: step: 690/470, loss: 0.06788298487663269
2023-01-22 18:42:34.110338: step: 692/470, loss: 0.2848212420940399
2023-01-22 18:42:34.866968: step: 694/470, loss: 0.21830137073993683
2023-01-22 18:42:35.583137: step: 696/470, loss: 0.04804154112935066
2023-01-22 18:42:36.246101: step: 698/470, loss: 0.1450975388288498
2023-01-22 18:42:36.903087: step: 700/470, loss: 0.12967953085899353
2023-01-22 18:42:37.664494: step: 702/470, loss: 0.09858199208974838
2023-01-22 18:42:38.388150: step: 704/470, loss: 0.06423236429691315
2023-01-22 18:42:39.128854: step: 706/470, loss: 0.08795824646949768
2023-01-22 18:42:39.862588: step: 708/470, loss: 0.08408377319574356
2023-01-22 18:42:40.591010: step: 710/470, loss: 0.6152773499488831
2023-01-22 18:42:41.255817: step: 712/470, loss: 0.08272521942853928
2023-01-22 18:42:42.045705: step: 714/470, loss: 0.07895615696907043
2023-01-22 18:42:42.827924: step: 716/470, loss: 0.06702841818332672
2023-01-22 18:42:43.633932: step: 718/470, loss: 0.1409570723772049
2023-01-22 18:42:44.294144: step: 720/470, loss: 0.7910665273666382
2023-01-22 18:42:45.006825: step: 722/470, loss: 0.0968073159456253
2023-01-22 18:42:45.855961: step: 724/470, loss: 0.12350492179393768
2023-01-22 18:42:46.555119: step: 726/470, loss: 0.18203213810920715
2023-01-22 18:42:47.270124: step: 728/470, loss: 0.12851355969905853
2023-01-22 18:42:48.029664: step: 730/470, loss: 0.22939978539943695
2023-01-22 18:42:48.731344: step: 732/470, loss: 0.05603186413645744
2023-01-22 18:42:49.482916: step: 734/470, loss: 0.16891199350357056
2023-01-22 18:42:50.177715: step: 736/470, loss: 0.14518122375011444
2023-01-22 18:42:50.902632: step: 738/470, loss: 0.12637437880039215
2023-01-22 18:42:51.601123: step: 740/470, loss: 0.9105393290519714
2023-01-22 18:42:52.358632: step: 742/470, loss: 0.7299985289573669
2023-01-22 18:42:53.119373: step: 744/470, loss: 0.11732316762208939
2023-01-22 18:42:53.835199: step: 746/470, loss: 0.1654384881258011
2023-01-22 18:42:54.581903: step: 748/470, loss: 0.16303178668022156
2023-01-22 18:42:55.269853: step: 750/470, loss: 0.03869093954563141
2023-01-22 18:42:56.030901: step: 752/470, loss: 0.33318397402763367
2023-01-22 18:42:56.741876: step: 754/470, loss: 0.2498822659254074
2023-01-22 18:42:57.459809: step: 756/470, loss: 0.19036591053009033
2023-01-22 18:42:58.178320: step: 758/470, loss: 0.24502049386501312
2023-01-22 18:42:58.890671: step: 760/470, loss: 0.05735207721590996
2023-01-22 18:42:59.571211: step: 762/470, loss: 0.1237659901380539
2023-01-22 18:43:00.282074: step: 764/470, loss: 0.05063727870583534
2023-01-22 18:43:01.074753: step: 766/470, loss: 0.09125498682260513
2023-01-22 18:43:01.743531: step: 768/470, loss: 0.09228543937206268
2023-01-22 18:43:02.563323: step: 770/470, loss: 0.09300341457128525
2023-01-22 18:43:03.303155: step: 772/470, loss: 0.12723006308078766
2023-01-22 18:43:04.017263: step: 774/470, loss: 0.19253137707710266
2023-01-22 18:43:04.760571: step: 776/470, loss: 0.16553926467895508
2023-01-22 18:43:05.530038: step: 778/470, loss: 0.08979497104883194
2023-01-22 18:43:06.254474: step: 780/470, loss: 0.29222023487091064
2023-01-22 18:43:06.966142: step: 782/470, loss: 0.1268426924943924
2023-01-22 18:43:07.712652: step: 784/470, loss: 0.10541335493326187
2023-01-22 18:43:08.495263: step: 786/470, loss: 0.14692994952201843
2023-01-22 18:43:09.206951: step: 788/470, loss: 0.06541899591684341
2023-01-22 18:43:09.932018: step: 790/470, loss: 0.07346995174884796
2023-01-22 18:43:10.695487: step: 792/470, loss: 0.13709881901741028
2023-01-22 18:43:11.377935: step: 794/470, loss: 0.09347955882549286
2023-01-22 18:43:12.120158: step: 796/470, loss: 0.08111049234867096
2023-01-22 18:43:12.932903: step: 798/470, loss: 0.07415740191936493
2023-01-22 18:43:13.658170: step: 800/470, loss: 0.05813341215252876
2023-01-22 18:43:14.400230: step: 802/470, loss: 0.09454671293497086
2023-01-22 18:43:15.052640: step: 804/470, loss: 0.037501685321331024
2023-01-22 18:43:15.815335: step: 806/470, loss: 0.1539684534072876
2023-01-22 18:43:16.656344: step: 808/470, loss: 0.11793018132448196
2023-01-22 18:43:17.370036: step: 810/470, loss: 0.1428481787443161
2023-01-22 18:43:18.082197: step: 812/470, loss: 0.1079527959227562
2023-01-22 18:43:18.781361: step: 814/470, loss: 0.1281379610300064
2023-01-22 18:43:19.553878: step: 816/470, loss: 0.1891109198331833
2023-01-22 18:43:20.335378: step: 818/470, loss: 0.34778857231140137
2023-01-22 18:43:21.093525: step: 820/470, loss: 0.07001124322414398
2023-01-22 18:43:21.830482: step: 822/470, loss: 0.04569976404309273
2023-01-22 18:43:22.585119: step: 824/470, loss: 0.04330173507332802
2023-01-22 18:43:23.303387: step: 826/470, loss: 0.09614764899015427
2023-01-22 18:43:24.097422: step: 828/470, loss: 0.35434603691101074
2023-01-22 18:43:24.832118: step: 830/470, loss: 0.35880136489868164
2023-01-22 18:43:25.698165: step: 832/470, loss: 0.15067602694034576
2023-01-22 18:43:26.438081: step: 834/470, loss: 0.0773734450340271
2023-01-22 18:43:27.195766: step: 836/470, loss: 0.14914895594120026
2023-01-22 18:43:27.969613: step: 838/470, loss: 0.21950659155845642
2023-01-22 18:43:28.742404: step: 840/470, loss: 0.03406314551830292
2023-01-22 18:43:29.490999: step: 842/470, loss: 0.07147298008203506
2023-01-22 18:43:30.203942: step: 844/470, loss: 0.07960271090269089
2023-01-22 18:43:30.863815: step: 846/470, loss: 0.04376105219125748
2023-01-22 18:43:31.586137: step: 848/470, loss: 0.13630259037017822
2023-01-22 18:43:32.287169: step: 850/470, loss: 0.09853252023458481
2023-01-22 18:43:33.026650: step: 852/470, loss: 0.05566703900694847
2023-01-22 18:43:33.811767: step: 854/470, loss: 0.09490513801574707
2023-01-22 18:43:34.551833: step: 856/470, loss: 0.11718861013650894
2023-01-22 18:43:35.383822: step: 858/470, loss: 0.05593058466911316
2023-01-22 18:43:36.117868: step: 860/470, loss: 0.5031771063804626
2023-01-22 18:43:36.856562: step: 862/470, loss: 0.1421380341053009
2023-01-22 18:43:37.696857: step: 864/470, loss: 0.20217017829418182
2023-01-22 18:43:38.369921: step: 866/470, loss: 0.08146615326404572
2023-01-22 18:43:39.115679: step: 868/470, loss: 0.07637915015220642
2023-01-22 18:43:39.851939: step: 870/470, loss: 0.6401387453079224
2023-01-22 18:43:40.646999: step: 872/470, loss: 0.1042008101940155
2023-01-22 18:43:41.371050: step: 874/470, loss: 0.18115811049938202
2023-01-22 18:43:42.044162: step: 876/470, loss: 0.1381768435239792
2023-01-22 18:43:42.745495: step: 878/470, loss: 0.1072993129491806
2023-01-22 18:43:43.481249: step: 880/470, loss: 0.055918753147125244
2023-01-22 18:43:44.247023: step: 882/470, loss: 0.12597472965717316
2023-01-22 18:43:44.950838: step: 884/470, loss: 2.0582730770111084
2023-01-22 18:43:45.721012: step: 886/470, loss: 0.03130277991294861
2023-01-22 18:43:46.496819: step: 888/470, loss: 0.11425133794546127
2023-01-22 18:43:47.269216: step: 890/470, loss: 0.1338731199502945
2023-01-22 18:43:48.036283: step: 892/470, loss: 0.29117199778556824
2023-01-22 18:43:48.770858: step: 894/470, loss: 0.40173524618148804
2023-01-22 18:43:49.556341: step: 896/470, loss: 0.24469105899333954
2023-01-22 18:43:50.226802: step: 898/470, loss: 0.07817135006189346
2023-01-22 18:43:50.964218: step: 900/470, loss: 0.1031189039349556
2023-01-22 18:43:51.782387: step: 902/470, loss: 0.5347837805747986
2023-01-22 18:43:52.530543: step: 904/470, loss: 0.223730206489563
2023-01-22 18:43:53.319027: step: 906/470, loss: 0.16207782924175262
2023-01-22 18:43:54.023167: step: 908/470, loss: 0.062290169298648834
2023-01-22 18:43:54.766198: step: 910/470, loss: 0.1052016094326973
2023-01-22 18:43:55.500598: step: 912/470, loss: 0.16469532251358032
2023-01-22 18:43:56.262217: step: 914/470, loss: 0.08949004858732224
2023-01-22 18:43:57.038226: step: 916/470, loss: 0.23239319026470184
2023-01-22 18:43:57.840145: step: 918/470, loss: 0.29859524965286255
2023-01-22 18:43:58.614148: step: 920/470, loss: 0.1092582494020462
2023-01-22 18:43:59.421809: step: 922/470, loss: 0.4721441864967346
2023-01-22 18:44:00.107042: step: 924/470, loss: 0.02895715832710266
2023-01-22 18:44:00.877795: step: 926/470, loss: 0.6657435894012451
2023-01-22 18:44:01.533718: step: 928/470, loss: 0.07168980687856674
2023-01-22 18:44:02.177877: step: 930/470, loss: 0.07691118121147156
2023-01-22 18:44:02.978181: step: 932/470, loss: 0.5273089408874512
2023-01-22 18:44:03.654631: step: 934/470, loss: 0.1843612641096115
2023-01-22 18:44:04.387826: step: 936/470, loss: 0.0656123235821724
2023-01-22 18:44:05.238977: step: 938/470, loss: 0.1719179004430771
2023-01-22 18:44:06.019110: step: 940/470, loss: 0.14247168600559235
2023-01-22 18:44:06.701475: step: 942/470, loss: 0.2547386884689331
==================================================
Loss: 0.204
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2855591748099892, 'r': 0.3327008222643897, 'f1': 0.3073327490505405}, 'combined': 0.22645570982671404, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3358431714808179, 'r': 0.35877092645691216, 'f1': 0.3469286504092875}, 'combined': 0.24164184605622016, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28976966759680817, 'r': 0.3403556437237652, 'f1': 0.3130321540007404}, 'combined': 0.2306552713689666, 'epoch': 15}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.336597090231335, 'r': 0.3537505957912011, 'f1': 0.34496073101064145}, 'combined': 0.24027115592780998, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2791196741854637, 'r': 0.3522098355471221, 'f1': 0.3114338646532439}, 'combined': 0.2294775844813376, 'epoch': 15}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32485481802107175, 'r': 0.36577403067564906, 'f1': 0.3441022088671868}, 'combined': 0.23967318030550325, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21774193548387097, 'r': 0.38571428571428573, 'f1': 0.27835051546391754}, 'combined': 0.18556701030927836, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.29545454545454547, 'r': 0.42391304347826086, 'f1': 0.3482142857142857}, 'combined': 0.17410714285714285, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42391304347826086, 'r': 0.33620689655172414, 'f1': 0.375}, 'combined': 0.25, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28994319242254574, 'r': 0.3102997353440527, 'f1': 0.2997762796082783}, 'combined': 0.22088778497452083, 'epoch': 14}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3507474812318518, 'r': 0.36187696861709323, 'f1': 0.3562253169538826}, 'combined': 0.2481171361867839, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.28846153846153844, 'r': 0.4891304347826087, 'f1': 0.3629032258064516}, 'combined': 0.1814516129032258, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2747616086235489, 'r': 0.31438567362428843, 'f1': 0.29324115044247784}, 'combined': 0.21607242664182577, 'epoch': 14}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3377919490575152, 'r': 0.368618303678518, 'f1': 0.3525325256126204}, 'combined': 0.24554504271525798, 'epoch': 14}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5416666666666666, 'r': 0.33620689655172414, 'f1': 0.41489361702127664}, 'combined': 0.2765957446808511, 'epoch': 14}
******************************
Epoch: 16
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 18:46:46.713321: step: 2/470, loss: 0.08884326368570328
2023-01-22 18:46:47.484479: step: 4/470, loss: 0.061807192862033844
2023-01-22 18:46:48.223594: step: 6/470, loss: 0.08429668098688126
2023-01-22 18:46:48.981201: step: 8/470, loss: 1.1761099100112915
2023-01-22 18:46:49.705240: step: 10/470, loss: 0.28416168689727783
2023-01-22 18:46:50.438386: step: 12/470, loss: 0.08847323060035706
2023-01-22 18:46:51.191846: step: 14/470, loss: 0.06219949573278427
2023-01-22 18:46:52.004093: step: 16/470, loss: 0.04178072139620781
2023-01-22 18:46:52.720854: step: 18/470, loss: 0.40100765228271484
2023-01-22 18:46:53.433854: step: 20/470, loss: 0.1000329926609993
2023-01-22 18:46:54.185332: step: 22/470, loss: 0.5311740040779114
2023-01-22 18:46:54.885944: step: 24/470, loss: 0.13259932398796082
2023-01-22 18:46:55.662090: step: 26/470, loss: 0.09883047640323639
2023-01-22 18:46:56.357386: step: 28/470, loss: 0.034732915461063385
2023-01-22 18:46:57.120700: step: 30/470, loss: 0.07482585310935974
2023-01-22 18:46:57.822479: step: 32/470, loss: 0.22222690284252167
2023-01-22 18:46:58.508937: step: 34/470, loss: 0.08215279877185822
2023-01-22 18:46:59.237415: step: 36/470, loss: 0.4559054970741272
2023-01-22 18:46:59.948824: step: 38/470, loss: 0.10464425384998322
2023-01-22 18:47:00.698832: step: 40/470, loss: 0.15875568985939026
2023-01-22 18:47:01.373688: step: 42/470, loss: 0.048225291073322296
2023-01-22 18:47:02.170572: step: 44/470, loss: 0.020997516810894012
2023-01-22 18:47:02.939248: step: 46/470, loss: 0.10919099301099777
2023-01-22 18:47:03.657389: step: 48/470, loss: 0.04074873775243759
2023-01-22 18:47:04.463064: step: 50/470, loss: 0.03056240826845169
2023-01-22 18:47:05.197096: step: 52/470, loss: 0.12954410910606384
2023-01-22 18:47:05.868588: step: 54/470, loss: 0.22133603692054749
2023-01-22 18:47:06.613524: step: 56/470, loss: 0.20818258821964264
2023-01-22 18:47:07.314040: step: 58/470, loss: 0.029186418280005455
2023-01-22 18:47:08.036357: step: 60/470, loss: 0.07272211462259293
2023-01-22 18:47:08.820110: step: 62/470, loss: 0.09152626991271973
2023-01-22 18:47:09.609103: step: 64/470, loss: 0.015041274018585682
2023-01-22 18:47:10.387037: step: 66/470, loss: 1.1043593883514404
2023-01-22 18:47:11.115161: step: 68/470, loss: 0.34245747327804565
2023-01-22 18:47:11.906769: step: 70/470, loss: 0.15388578176498413
2023-01-22 18:47:12.673781: step: 72/470, loss: 0.11390519142150879
2023-01-22 18:47:13.448899: step: 74/470, loss: 0.05043567717075348
2023-01-22 18:47:14.228223: step: 76/470, loss: 0.11875592917203903
2023-01-22 18:47:15.050666: step: 78/470, loss: 0.0501096136868
2023-01-22 18:47:15.767396: step: 80/470, loss: 0.3267119526863098
2023-01-22 18:47:16.583206: step: 82/470, loss: 0.04021922126412392
2023-01-22 18:47:17.310110: step: 84/470, loss: 0.14459112286567688
2023-01-22 18:47:18.035684: step: 86/470, loss: 0.09926001727581024
2023-01-22 18:47:18.785279: step: 88/470, loss: 0.8933921456336975
2023-01-22 18:47:19.567657: step: 90/470, loss: 0.06707798689603806
2023-01-22 18:47:20.308466: step: 92/470, loss: 0.41027313470840454
2023-01-22 18:47:21.040794: step: 94/470, loss: 0.0322352796792984
2023-01-22 18:47:21.722095: step: 96/470, loss: 0.029441189020872116
2023-01-22 18:47:22.418428: step: 98/470, loss: 0.21683290600776672
2023-01-22 18:47:23.059936: step: 100/470, loss: 0.06455568969249725
2023-01-22 18:47:23.884560: step: 102/470, loss: 0.050209976732730865
2023-01-22 18:47:24.627224: step: 104/470, loss: 0.036682043224573135
2023-01-22 18:47:25.332471: step: 106/470, loss: 0.14355768263339996
2023-01-22 18:47:26.027365: step: 108/470, loss: 0.023732803761959076
2023-01-22 18:47:26.747504: step: 110/470, loss: 0.02847733162343502
2023-01-22 18:47:27.465466: step: 112/470, loss: 0.1768191009759903
2023-01-22 18:47:28.178338: step: 114/470, loss: 0.06269264221191406
2023-01-22 18:47:28.928251: step: 116/470, loss: 0.008748441934585571
2023-01-22 18:47:29.674038: step: 118/470, loss: 0.10878868401050568
2023-01-22 18:47:30.455000: step: 120/470, loss: 0.09285591542720795
2023-01-22 18:47:31.231841: step: 122/470, loss: 0.6085570454597473
2023-01-22 18:47:31.965583: step: 124/470, loss: 0.06355506926774979
2023-01-22 18:47:32.691057: step: 126/470, loss: 0.11871222406625748
2023-01-22 18:47:33.448720: step: 128/470, loss: 0.08303084224462509
2023-01-22 18:47:34.234021: step: 130/470, loss: 0.11246610432863235
2023-01-22 18:47:34.999600: step: 132/470, loss: 0.25137367844581604
2023-01-22 18:47:35.780315: step: 134/470, loss: 0.24548359215259552
2023-01-22 18:47:36.472845: step: 136/470, loss: 0.12862925231456757
2023-01-22 18:47:37.129024: step: 138/470, loss: 0.059389956295490265
2023-01-22 18:47:37.818913: step: 140/470, loss: 0.05305398255586624
2023-01-22 18:47:38.554771: step: 142/470, loss: 0.12227759510278702
2023-01-22 18:47:39.346810: step: 144/470, loss: 0.12327904254198074
2023-01-22 18:47:40.053366: step: 146/470, loss: 0.05995366722345352
2023-01-22 18:47:40.771461: step: 148/470, loss: 0.13276717066764832
2023-01-22 18:47:41.480554: step: 150/470, loss: 0.050435952842235565
2023-01-22 18:47:42.176502: step: 152/470, loss: 0.32247716188430786
2023-01-22 18:47:42.905496: step: 154/470, loss: 0.06091221049427986
2023-01-22 18:47:43.604984: step: 156/470, loss: 0.2275611311197281
2023-01-22 18:47:44.274815: step: 158/470, loss: 0.28586113452911377
2023-01-22 18:47:44.931729: step: 160/470, loss: 0.0427815206348896
2023-01-22 18:47:45.729832: step: 162/470, loss: 0.4265275001525879
2023-01-22 18:47:46.389620: step: 164/470, loss: 0.06603558361530304
2023-01-22 18:47:47.205319: step: 166/470, loss: 0.08618386089801788
2023-01-22 18:47:47.914975: step: 168/470, loss: 0.13042916357517242
2023-01-22 18:47:48.646335: step: 170/470, loss: 0.10537727922201157
2023-01-22 18:47:49.342842: step: 172/470, loss: 0.025995755568146706
2023-01-22 18:47:50.175208: step: 174/470, loss: 0.07933039963245392
2023-01-22 18:47:50.824277: step: 176/470, loss: 0.026341214776039124
2023-01-22 18:47:51.531888: step: 178/470, loss: 0.07335160672664642
2023-01-22 18:47:52.234514: step: 180/470, loss: 0.012121165171265602
2023-01-22 18:47:52.917356: step: 182/470, loss: 0.11823894083499908
2023-01-22 18:47:53.627214: step: 184/470, loss: 0.1767769157886505
2023-01-22 18:47:54.362041: step: 186/470, loss: 2.089386224746704
2023-01-22 18:47:55.146159: step: 188/470, loss: 0.08466898649930954
2023-01-22 18:47:55.942927: step: 190/470, loss: 0.48831504583358765
2023-01-22 18:47:56.676447: step: 192/470, loss: 0.328980952501297
2023-01-22 18:47:57.333252: step: 194/470, loss: 0.18098825216293335
2023-01-22 18:47:58.038968: step: 196/470, loss: 0.10612848401069641
2023-01-22 18:47:58.754454: step: 198/470, loss: 0.09899935126304626
2023-01-22 18:47:59.449387: step: 200/470, loss: 0.06739851832389832
2023-01-22 18:48:00.487863: step: 202/470, loss: 0.6201255321502686
2023-01-22 18:48:01.198952: step: 204/470, loss: 0.031738992780447006
2023-01-22 18:48:01.953321: step: 206/470, loss: 0.03578285127878189
2023-01-22 18:48:02.611507: step: 208/470, loss: 0.024340057745575905
2023-01-22 18:48:03.374258: step: 210/470, loss: 0.7221086025238037
2023-01-22 18:48:04.154460: step: 212/470, loss: 0.06913825124502182
2023-01-22 18:48:05.013783: step: 214/470, loss: 0.11934089660644531
2023-01-22 18:48:05.759348: step: 216/470, loss: 0.31613805890083313
2023-01-22 18:48:06.434219: step: 218/470, loss: 0.08025716245174408
2023-01-22 18:48:07.196229: step: 220/470, loss: 0.07177558541297913
2023-01-22 18:48:07.921471: step: 222/470, loss: 0.38496649265289307
2023-01-22 18:48:08.636066: step: 224/470, loss: 0.20351849496364594
2023-01-22 18:48:09.331218: step: 226/470, loss: 0.1382501870393753
2023-01-22 18:48:10.107904: step: 228/470, loss: 0.08902169018983841
2023-01-22 18:48:10.947859: step: 230/470, loss: 0.1085016131401062
2023-01-22 18:48:11.643094: step: 232/470, loss: 0.084829181432724
2023-01-22 18:48:12.365895: step: 234/470, loss: 0.2627657353878021
2023-01-22 18:48:13.119766: step: 236/470, loss: 0.08875922858715057
2023-01-22 18:48:13.841411: step: 238/470, loss: 0.11912406980991364
2023-01-22 18:48:14.535683: step: 240/470, loss: 0.061584122478961945
2023-01-22 18:48:15.204836: step: 242/470, loss: 0.026997093111276627
2023-01-22 18:48:15.936758: step: 244/470, loss: 0.09223021566867828
2023-01-22 18:48:16.709151: step: 246/470, loss: 0.4238168001174927
2023-01-22 18:48:17.439557: step: 248/470, loss: 0.034468550235033035
2023-01-22 18:48:18.137675: step: 250/470, loss: 0.06773322820663452
2023-01-22 18:48:18.956386: step: 252/470, loss: 0.3193717300891876
2023-01-22 18:48:19.770514: step: 254/470, loss: 0.2410053014755249
2023-01-22 18:48:20.631754: step: 256/470, loss: 0.07392468303442001
2023-01-22 18:48:21.398645: step: 258/470, loss: 0.05369978025555611
2023-01-22 18:48:22.156130: step: 260/470, loss: 0.11789437383413315
2023-01-22 18:48:22.866109: step: 262/470, loss: 0.06956873089075089
2023-01-22 18:48:23.586284: step: 264/470, loss: 0.0506395660340786
2023-01-22 18:48:24.305856: step: 266/470, loss: 0.05074666440486908
2023-01-22 18:48:25.003628: step: 268/470, loss: 0.37575647234916687
2023-01-22 18:48:25.714185: step: 270/470, loss: 0.05577372387051582
2023-01-22 18:48:26.458471: step: 272/470, loss: 0.3809775114059448
2023-01-22 18:48:27.133883: step: 274/470, loss: 0.1822841912508011
2023-01-22 18:48:27.894743: step: 276/470, loss: 0.12010300159454346
2023-01-22 18:48:28.636328: step: 278/470, loss: 0.2520848214626312
2023-01-22 18:48:29.429368: step: 280/470, loss: 0.057388413697481155
2023-01-22 18:48:30.225333: step: 282/470, loss: 0.0458437018096447
2023-01-22 18:48:30.958791: step: 284/470, loss: 0.025038981810212135
2023-01-22 18:48:31.653529: step: 286/470, loss: 0.025928793475031853
2023-01-22 18:48:32.421252: step: 288/470, loss: 0.12468525022268295
2023-01-22 18:48:33.166598: step: 290/470, loss: 0.1737351417541504
2023-01-22 18:48:33.869473: step: 292/470, loss: 0.07722808420658112
2023-01-22 18:48:34.614013: step: 294/470, loss: 0.12904956936836243
2023-01-22 18:48:35.303223: step: 296/470, loss: 0.011522680521011353
2023-01-22 18:48:36.010304: step: 298/470, loss: 0.06235891208052635
2023-01-22 18:48:36.727238: step: 300/470, loss: 0.09630980342626572
2023-01-22 18:48:37.478045: step: 302/470, loss: 0.07960200309753418
2023-01-22 18:48:38.233321: step: 304/470, loss: 0.11289746314287186
2023-01-22 18:48:39.009857: step: 306/470, loss: 0.03673465922474861
2023-01-22 18:48:39.694601: step: 308/470, loss: 0.047929637134075165
2023-01-22 18:48:40.379777: step: 310/470, loss: 0.18434062600135803
2023-01-22 18:48:41.185281: step: 312/470, loss: 0.10890356451272964
2023-01-22 18:48:41.847545: step: 314/470, loss: 0.09170568734407425
2023-01-22 18:48:42.583789: step: 316/470, loss: 0.07127133011817932
2023-01-22 18:48:43.320556: step: 318/470, loss: 0.09422150999307632
2023-01-22 18:48:44.006419: step: 320/470, loss: 0.0380314365029335
2023-01-22 18:48:44.736195: step: 322/470, loss: 0.047910191118717194
2023-01-22 18:48:45.535579: step: 324/470, loss: 0.18401391804218292
2023-01-22 18:48:46.297389: step: 326/470, loss: 0.12445008754730225
2023-01-22 18:48:47.019821: step: 328/470, loss: 0.21150392293930054
2023-01-22 18:48:47.785230: step: 330/470, loss: 0.053453728556632996
2023-01-22 18:48:48.471638: step: 332/470, loss: 0.13986550271511078
2023-01-22 18:48:49.149571: step: 334/470, loss: 0.09363771975040436
2023-01-22 18:48:49.879891: step: 336/470, loss: 0.0591520257294178
2023-01-22 18:48:50.639722: step: 338/470, loss: 0.05675804242491722
2023-01-22 18:48:51.392063: step: 340/470, loss: 0.5691471695899963
2023-01-22 18:48:52.141034: step: 342/470, loss: 0.19100329279899597
2023-01-22 18:48:52.947533: step: 344/470, loss: 0.34803155064582825
2023-01-22 18:48:53.605316: step: 346/470, loss: 0.404619425535202
2023-01-22 18:48:54.346261: step: 348/470, loss: 0.04862171784043312
2023-01-22 18:48:55.097673: step: 350/470, loss: 0.15870419144630432
2023-01-22 18:48:55.799889: step: 352/470, loss: 0.0585881844162941
2023-01-22 18:48:56.545429: step: 354/470, loss: 0.09602773189544678
2023-01-22 18:48:57.290091: step: 356/470, loss: 0.0472840778529644
2023-01-22 18:48:58.049182: step: 358/470, loss: 0.05619442090392113
2023-01-22 18:48:58.901672: step: 360/470, loss: 0.11173807084560394
2023-01-22 18:48:59.594828: step: 362/470, loss: 0.26064473390579224
2023-01-22 18:49:00.318635: step: 364/470, loss: 0.17030306160449982
2023-01-22 18:49:01.198530: step: 366/470, loss: 0.06355582922697067
2023-01-22 18:49:01.897442: step: 368/470, loss: 0.6005545258522034
2023-01-22 18:49:02.643516: step: 370/470, loss: 0.24275268614292145
2023-01-22 18:49:03.441383: step: 372/470, loss: 0.09774607419967651
2023-01-22 18:49:04.151906: step: 374/470, loss: 0.2669150233268738
2023-01-22 18:49:04.864196: step: 376/470, loss: 0.10955331474542618
2023-01-22 18:49:05.549011: step: 378/470, loss: 0.28141841292381287
2023-01-22 18:49:06.316365: step: 380/470, loss: 0.05212775245308876
2023-01-22 18:49:06.994186: step: 382/470, loss: 0.1570778340101242
2023-01-22 18:49:07.700736: step: 384/470, loss: 0.09866324067115784
2023-01-22 18:49:08.378316: step: 386/470, loss: 0.17579655349254608
2023-01-22 18:49:09.091627: step: 388/470, loss: 0.17191143333911896
2023-01-22 18:49:09.774547: step: 390/470, loss: 0.10095331817865372
2023-01-22 18:49:10.492844: step: 392/470, loss: 0.07796035706996918
2023-01-22 18:49:11.295989: step: 394/470, loss: 0.10861441493034363
2023-01-22 18:49:12.025261: step: 396/470, loss: 0.15292930603027344
2023-01-22 18:49:12.757223: step: 398/470, loss: 0.058260828256607056
2023-01-22 18:49:13.551573: step: 400/470, loss: 0.058411069214344025
2023-01-22 18:49:14.288820: step: 402/470, loss: 0.0554041787981987
2023-01-22 18:49:14.987369: step: 404/470, loss: 1.0163735151290894
2023-01-22 18:49:15.805524: step: 406/470, loss: 0.3198876678943634
2023-01-22 18:49:16.510698: step: 408/470, loss: 0.0814136192202568
2023-01-22 18:49:17.254192: step: 410/470, loss: 0.7785913944244385
2023-01-22 18:49:18.022047: step: 412/470, loss: 0.06416447460651398
2023-01-22 18:49:18.864251: step: 414/470, loss: 0.26347091794013977
2023-01-22 18:49:19.608972: step: 416/470, loss: 0.08544527739286423
2023-01-22 18:49:20.370612: step: 418/470, loss: 0.45779088139533997
2023-01-22 18:49:21.105823: step: 420/470, loss: 0.9352731108665466
2023-01-22 18:49:21.922503: step: 422/470, loss: 0.1798955500125885
2023-01-22 18:49:22.723448: step: 424/470, loss: 0.04317692294716835
2023-01-22 18:49:23.533916: step: 426/470, loss: 0.152594193816185
2023-01-22 18:49:24.313082: step: 428/470, loss: 0.45149144530296326
2023-01-22 18:49:25.065368: step: 430/470, loss: 0.06854032725095749
2023-01-22 18:49:25.773188: step: 432/470, loss: 0.15352515876293182
2023-01-22 18:49:26.468949: step: 434/470, loss: 0.24940556287765503
2023-01-22 18:49:27.192756: step: 436/470, loss: 0.04720636084675789
2023-01-22 18:49:27.869636: step: 438/470, loss: 0.09284143149852753
2023-01-22 18:49:28.638739: step: 440/470, loss: 0.05546830594539642
2023-01-22 18:49:29.322648: step: 442/470, loss: 0.04827970266342163
2023-01-22 18:49:30.043807: step: 444/470, loss: 0.0933823436498642
2023-01-22 18:49:30.691488: step: 446/470, loss: 0.2462373822927475
2023-01-22 18:49:31.410046: step: 448/470, loss: 0.14782100915908813
2023-01-22 18:49:32.145174: step: 450/470, loss: 0.04853854700922966
2023-01-22 18:49:32.875492: step: 452/470, loss: 0.4875885844230652
2023-01-22 18:49:33.676933: step: 454/470, loss: 0.29292890429496765
2023-01-22 18:49:34.434920: step: 456/470, loss: 0.07768307626247406
2023-01-22 18:49:35.187537: step: 458/470, loss: 0.29037296772003174
2023-01-22 18:49:35.922122: step: 460/470, loss: 0.05874329432845116
2023-01-22 18:49:36.640632: step: 462/470, loss: 0.1875893473625183
2023-01-22 18:49:37.432340: step: 464/470, loss: 0.04672089219093323
2023-01-22 18:49:38.163031: step: 466/470, loss: 0.3265398144721985
2023-01-22 18:49:38.859735: step: 468/470, loss: 0.11972032487392426
2023-01-22 18:49:39.478353: step: 470/470, loss: 0.11014973372220993
2023-01-22 18:49:40.240175: step: 472/470, loss: 0.06904499232769012
2023-01-22 18:49:41.035081: step: 474/470, loss: 0.17454054951667786
2023-01-22 18:49:41.803172: step: 476/470, loss: 0.07249860465526581
2023-01-22 18:49:42.517590: step: 478/470, loss: 0.08408724516630173
2023-01-22 18:49:43.302703: step: 480/470, loss: 0.15881037712097168
2023-01-22 18:49:44.058900: step: 482/470, loss: 0.08231707662343979
2023-01-22 18:49:44.789105: step: 484/470, loss: 0.09459856152534485
2023-01-22 18:49:45.529196: step: 486/470, loss: 0.8342221975326538
2023-01-22 18:49:46.270525: step: 488/470, loss: 0.08584868907928467
2023-01-22 18:49:46.935901: step: 490/470, loss: 0.131908118724823
2023-01-22 18:49:47.664878: step: 492/470, loss: 0.06489690393209457
2023-01-22 18:49:48.448145: step: 494/470, loss: 0.1734696328639984
2023-01-22 18:49:49.174225: step: 496/470, loss: 0.17412090301513672
2023-01-22 18:49:49.995546: step: 498/470, loss: 0.01628013141453266
2023-01-22 18:49:50.671889: step: 500/470, loss: 0.02044498547911644
2023-01-22 18:49:51.356754: step: 502/470, loss: 0.1580786108970642
2023-01-22 18:49:52.045784: step: 504/470, loss: 0.0427110381424427
2023-01-22 18:49:52.800880: step: 506/470, loss: 0.06857065856456757
2023-01-22 18:49:53.474000: step: 508/470, loss: 0.9077308177947998
2023-01-22 18:49:54.136413: step: 510/470, loss: 0.12271424382925034
2023-01-22 18:49:54.866982: step: 512/470, loss: 0.08618942648172379
2023-01-22 18:49:55.585292: step: 514/470, loss: 0.09517448395490646
2023-01-22 18:49:56.310623: step: 516/470, loss: 0.0746607780456543
2023-01-22 18:49:56.990029: step: 518/470, loss: 0.06032832711935043
2023-01-22 18:49:57.770893: step: 520/470, loss: 0.07779128104448318
2023-01-22 18:49:58.573728: step: 522/470, loss: 0.2717607021331787
2023-01-22 18:49:59.228482: step: 524/470, loss: 0.1430988907814026
2023-01-22 18:49:59.944901: step: 526/470, loss: 0.0658825933933258
2023-01-22 18:50:00.706012: step: 528/470, loss: 0.1088942140340805
2023-01-22 18:50:01.480763: step: 530/470, loss: 0.12835966050624847
2023-01-22 18:50:02.206256: step: 532/470, loss: 0.055738162249326706
2023-01-22 18:50:02.987708: step: 534/470, loss: 0.0650675892829895
2023-01-22 18:50:03.814679: step: 536/470, loss: 0.03095190040767193
2023-01-22 18:50:04.661111: step: 538/470, loss: 0.21852679550647736
2023-01-22 18:50:05.443607: step: 540/470, loss: 0.050854191184043884
2023-01-22 18:50:06.179706: step: 542/470, loss: 0.07948761433362961
2023-01-22 18:50:06.914500: step: 544/470, loss: 0.7797904014587402
2023-01-22 18:50:07.609531: step: 546/470, loss: 0.07549011707305908
2023-01-22 18:50:08.373577: step: 548/470, loss: 0.07842864841222763
2023-01-22 18:50:09.129819: step: 550/470, loss: 0.0789763554930687
2023-01-22 18:50:09.799114: step: 552/470, loss: 0.07106094062328339
2023-01-22 18:50:10.492417: step: 554/470, loss: 0.397691935300827
2023-01-22 18:50:11.342628: step: 556/470, loss: 0.378380686044693
2023-01-22 18:50:12.015396: step: 558/470, loss: 0.07716850936412811
2023-01-22 18:50:12.691164: step: 560/470, loss: 0.08261480927467346
2023-01-22 18:50:13.448538: step: 562/470, loss: 0.1947333961725235
2023-01-22 18:50:14.250174: step: 564/470, loss: 0.07653369754552841
2023-01-22 18:50:15.008343: step: 566/470, loss: 0.13547946512699127
2023-01-22 18:50:15.750453: step: 568/470, loss: 0.03947483003139496
2023-01-22 18:50:16.543606: step: 570/470, loss: 0.543188750743866
2023-01-22 18:50:17.266652: step: 572/470, loss: 0.1665872037410736
2023-01-22 18:50:17.955417: step: 574/470, loss: 5.638265609741211
2023-01-22 18:50:18.629363: step: 576/470, loss: 0.11097951233386993
2023-01-22 18:50:19.358589: step: 578/470, loss: 0.2536165714263916
2023-01-22 18:50:20.059368: step: 580/470, loss: 0.029628895223140717
2023-01-22 18:50:20.762608: step: 582/470, loss: 0.19913624227046967
2023-01-22 18:50:21.526628: step: 584/470, loss: 0.2235163003206253
2023-01-22 18:50:22.306827: step: 586/470, loss: 0.10956007242202759
2023-01-22 18:50:23.021138: step: 588/470, loss: 0.039578016847372055
2023-01-22 18:50:23.728295: step: 590/470, loss: 0.12435401976108551
2023-01-22 18:50:24.445634: step: 592/470, loss: 0.21014420688152313
2023-01-22 18:50:25.087273: step: 594/470, loss: 0.012091286480426788
2023-01-22 18:50:25.883915: step: 596/470, loss: 0.08850495517253876
2023-01-22 18:50:26.656918: step: 598/470, loss: 0.05613786727190018
2023-01-22 18:50:27.442200: step: 600/470, loss: 0.3040921986103058
2023-01-22 18:50:28.160006: step: 602/470, loss: 0.24259580671787262
2023-01-22 18:50:28.974840: step: 604/470, loss: 0.006539918482303619
2023-01-22 18:50:29.681395: step: 606/470, loss: 0.029432980343699455
2023-01-22 18:50:30.443599: step: 608/470, loss: 0.3112735450267792
2023-01-22 18:50:31.247253: step: 610/470, loss: 0.18472446501255035
2023-01-22 18:50:32.063663: step: 612/470, loss: 0.03998330980539322
2023-01-22 18:50:32.806861: step: 614/470, loss: 0.028782224282622337
2023-01-22 18:50:33.546961: step: 616/470, loss: 0.10626031458377838
2023-01-22 18:50:34.348138: step: 618/470, loss: 0.03874929994344711
2023-01-22 18:50:35.160555: step: 620/470, loss: 0.05607333034276962
2023-01-22 18:50:35.869474: step: 622/470, loss: 0.03576376661658287
2023-01-22 18:50:36.615933: step: 624/470, loss: 0.10499916970729828
2023-01-22 18:50:37.383075: step: 626/470, loss: 0.09289852529764175
2023-01-22 18:50:38.122619: step: 628/470, loss: 0.1215863972902298
2023-01-22 18:50:38.837597: step: 630/470, loss: 0.02862360328435898
2023-01-22 18:50:39.617592: step: 632/470, loss: 0.05546386539936066
2023-01-22 18:50:40.307336: step: 634/470, loss: 0.0644495040178299
2023-01-22 18:50:41.097563: step: 636/470, loss: 0.3706085681915283
2023-01-22 18:50:41.834877: step: 638/470, loss: 0.057276401668787
2023-01-22 18:50:42.638840: step: 640/470, loss: 0.04506406560540199
2023-01-22 18:50:43.371949: step: 642/470, loss: 0.15678298473358154
2023-01-22 18:50:44.147555: step: 644/470, loss: 0.11337969452142715
2023-01-22 18:50:44.947793: step: 646/470, loss: 0.5968871116638184
2023-01-22 18:50:45.783763: step: 648/470, loss: 0.04819050803780556
2023-01-22 18:50:46.498556: step: 650/470, loss: 0.09025636315345764
2023-01-22 18:50:47.199774: step: 652/470, loss: 1.1916296482086182
2023-01-22 18:50:47.992206: step: 654/470, loss: 0.03702091798186302
2023-01-22 18:50:48.787008: step: 656/470, loss: 0.12011308968067169
2023-01-22 18:50:49.534009: step: 658/470, loss: 0.4539858102798462
2023-01-22 18:50:50.353936: step: 660/470, loss: 0.09682758152484894
2023-01-22 18:50:51.083882: step: 662/470, loss: 0.05873757600784302
2023-01-22 18:50:51.835863: step: 664/470, loss: 0.10081055015325546
2023-01-22 18:50:52.606911: step: 666/470, loss: 0.06736086308956146
2023-01-22 18:50:53.369513: step: 668/470, loss: 0.22437730431556702
2023-01-22 18:50:54.164444: step: 670/470, loss: 0.11580760031938553
2023-01-22 18:50:54.936760: step: 672/470, loss: 0.02462395839393139
2023-01-22 18:50:55.626521: step: 674/470, loss: 0.1718244105577469
2023-01-22 18:50:56.389588: step: 676/470, loss: 0.02999183163046837
2023-01-22 18:50:57.151629: step: 678/470, loss: 0.06906621158123016
2023-01-22 18:50:57.909281: step: 680/470, loss: 0.4289069175720215
2023-01-22 18:50:58.688129: step: 682/470, loss: 0.26691025495529175
2023-01-22 18:50:59.500173: step: 684/470, loss: 0.11220283061265945
2023-01-22 18:51:00.279536: step: 686/470, loss: 0.0480489581823349
2023-01-22 18:51:01.127825: step: 688/470, loss: 0.7784223556518555
2023-01-22 18:51:01.902138: step: 690/470, loss: 0.012960987165570259
2023-01-22 18:51:02.800985: step: 692/470, loss: 0.5317075252532959
2023-01-22 18:51:03.534592: step: 694/470, loss: 0.17809821665287018
2023-01-22 18:51:04.330582: step: 696/470, loss: 0.07087529450654984
2023-01-22 18:51:05.072611: step: 698/470, loss: 0.19641615450382233
2023-01-22 18:51:05.760672: step: 700/470, loss: 0.08749356865882874
2023-01-22 18:51:06.558586: step: 702/470, loss: 0.09865260124206543
2023-01-22 18:51:07.327831: step: 704/470, loss: 0.11657115072011948
2023-01-22 18:51:08.065417: step: 706/470, loss: 0.15794336795806885
2023-01-22 18:51:08.770053: step: 708/470, loss: 0.10114340484142303
2023-01-22 18:51:09.489025: step: 710/470, loss: 0.214201882481575
2023-01-22 18:51:10.296459: step: 712/470, loss: 0.04397993162274361
2023-01-22 18:51:10.976944: step: 714/470, loss: 0.1239086389541626
2023-01-22 18:51:11.679686: step: 716/470, loss: 0.11514618992805481
2023-01-22 18:51:12.411959: step: 718/470, loss: 0.09257897734642029
2023-01-22 18:51:13.127682: step: 720/470, loss: 0.25863686203956604
2023-01-22 18:51:13.876872: step: 722/470, loss: 0.03553589805960655
2023-01-22 18:51:14.660984: step: 724/470, loss: 0.16370436549186707
2023-01-22 18:51:15.383681: step: 726/470, loss: 0.06427986919879913
2023-01-22 18:51:16.152771: step: 728/470, loss: 0.08685880899429321
2023-01-22 18:51:16.937590: step: 730/470, loss: 0.08242062479257584
2023-01-22 18:51:17.769163: step: 732/470, loss: 0.03324902057647705
2023-01-22 18:51:18.525135: step: 734/470, loss: 0.044015150517225266
2023-01-22 18:51:19.299180: step: 736/470, loss: 0.06782012432813644
2023-01-22 18:51:19.978371: step: 738/470, loss: 0.06624935567378998
2023-01-22 18:51:20.691067: step: 740/470, loss: 0.09224491566419601
2023-01-22 18:51:21.439675: step: 742/470, loss: 0.10784140229225159
2023-01-22 18:51:22.115155: step: 744/470, loss: 0.0007243788568302989
2023-01-22 18:51:22.802035: step: 746/470, loss: 0.0974595695734024
2023-01-22 18:51:23.482817: step: 748/470, loss: 0.2744196653366089
2023-01-22 18:51:24.198244: step: 750/470, loss: 0.013780027627944946
2023-01-22 18:51:24.873903: step: 752/470, loss: 0.11913798004388809
2023-01-22 18:51:25.662685: step: 754/470, loss: 0.21007420122623444
2023-01-22 18:51:26.426459: step: 756/470, loss: 0.15533891320228577
2023-01-22 18:51:27.204777: step: 758/470, loss: 3.9849534034729004
2023-01-22 18:51:27.840403: step: 760/470, loss: 3.1590588092803955
2023-01-22 18:51:28.570587: step: 762/470, loss: 0.1593295782804489
2023-01-22 18:51:29.214447: step: 764/470, loss: 0.06664041429758072
2023-01-22 18:51:29.962885: step: 766/470, loss: 0.26761144399642944
2023-01-22 18:51:30.731385: step: 768/470, loss: 0.09391117095947266
2023-01-22 18:51:31.462511: step: 770/470, loss: 0.043674781918525696
2023-01-22 18:51:32.309089: step: 772/470, loss: 0.14461608231067657
2023-01-22 18:51:33.006785: step: 774/470, loss: 0.23033620417118073
2023-01-22 18:51:33.756469: step: 776/470, loss: 0.05211387947201729
2023-01-22 18:51:34.472642: step: 778/470, loss: 0.09210966527462006
2023-01-22 18:51:35.198906: step: 780/470, loss: 0.0924573689699173
2023-01-22 18:51:35.958445: step: 782/470, loss: 0.10759110748767853
2023-01-22 18:51:36.686607: step: 784/470, loss: 0.1636630892753601
2023-01-22 18:51:37.406952: step: 786/470, loss: 0.08606382459402084
2023-01-22 18:51:38.161173: step: 788/470, loss: 0.10852282494306564
2023-01-22 18:51:38.901861: step: 790/470, loss: 0.7059446573257446
2023-01-22 18:51:39.641639: step: 792/470, loss: 0.03020882047712803
2023-01-22 18:51:40.381164: step: 794/470, loss: 0.05972389131784439
2023-01-22 18:51:41.141583: step: 796/470, loss: 0.0445023775100708
2023-01-22 18:51:41.903868: step: 798/470, loss: 0.07505831122398376
2023-01-22 18:51:42.703317: step: 800/470, loss: 0.07195542752742767
2023-01-22 18:51:43.353328: step: 802/470, loss: 0.23525984585285187
2023-01-22 18:51:44.138811: step: 804/470, loss: 0.0642390102148056
2023-01-22 18:51:44.871265: step: 806/470, loss: 0.048134271055459976
2023-01-22 18:51:45.581533: step: 808/470, loss: 0.02630416862666607
2023-01-22 18:51:46.308905: step: 810/470, loss: 0.03595459833741188
2023-01-22 18:51:47.038144: step: 812/470, loss: 0.5879958868026733
2023-01-22 18:51:47.761974: step: 814/470, loss: 0.025413349270820618
2023-01-22 18:51:48.457428: step: 816/470, loss: 0.1703702062368393
2023-01-22 18:51:49.191062: step: 818/470, loss: 0.14653141796588898
2023-01-22 18:51:49.852308: step: 820/470, loss: 0.026079224422574043
2023-01-22 18:51:50.621382: step: 822/470, loss: 0.06979137659072876
2023-01-22 18:51:51.500906: step: 824/470, loss: 0.15548716485500336
2023-01-22 18:51:52.295834: step: 826/470, loss: 0.10300223529338837
2023-01-22 18:51:52.990263: step: 828/470, loss: 0.10399255156517029
2023-01-22 18:51:53.787474: step: 830/470, loss: 0.06566653400659561
2023-01-22 18:51:54.508207: step: 832/470, loss: 0.15286491811275482
2023-01-22 18:51:55.275739: step: 834/470, loss: 0.0035868631675839424
2023-01-22 18:51:56.108599: step: 836/470, loss: 0.10651691257953644
2023-01-22 18:51:56.834185: step: 838/470, loss: 0.08586788922548294
2023-01-22 18:51:57.577758: step: 840/470, loss: 0.09690944850444794
2023-01-22 18:51:58.349896: step: 842/470, loss: 0.08737190812826157
2023-01-22 18:51:59.120913: step: 844/470, loss: 0.5851885676383972
2023-01-22 18:51:59.761029: step: 846/470, loss: 0.05255848914384842
2023-01-22 18:52:00.548068: step: 848/470, loss: 0.055961720645427704
2023-01-22 18:52:01.292803: step: 850/470, loss: 0.1446704864501953
2023-01-22 18:52:02.044379: step: 852/470, loss: 0.19530963897705078
2023-01-22 18:52:02.730360: step: 854/470, loss: 0.10102560371160507
2023-01-22 18:52:03.446418: step: 856/470, loss: 0.047898419201374054
2023-01-22 18:52:04.130211: step: 858/470, loss: 0.2797347903251648
2023-01-22 18:52:04.858245: step: 860/470, loss: 0.021785497665405273
2023-01-22 18:52:05.550866: step: 862/470, loss: 0.08698924630880356
2023-01-22 18:52:06.260137: step: 864/470, loss: 0.06238389387726784
2023-01-22 18:52:06.969808: step: 866/470, loss: 0.03106139786541462
2023-01-22 18:52:07.784680: step: 868/470, loss: 0.40585944056510925
2023-01-22 18:52:08.565886: step: 870/470, loss: 0.40325307846069336
2023-01-22 18:52:09.274388: step: 872/470, loss: 0.04273195564746857
2023-01-22 18:52:10.030720: step: 874/470, loss: 0.04423359036445618
2023-01-22 18:52:10.809207: step: 876/470, loss: 0.052610598504543304
2023-01-22 18:52:11.570418: step: 878/470, loss: 0.06774067133665085
2023-01-22 18:52:12.347455: step: 880/470, loss: 0.14847953617572784
2023-01-22 18:52:13.040671: step: 882/470, loss: 0.24171356856822968
2023-01-22 18:52:13.732695: step: 884/470, loss: 0.03664424270391464
2023-01-22 18:52:14.483530: step: 886/470, loss: 0.32642123103141785
2023-01-22 18:52:15.229202: step: 888/470, loss: 0.09348136186599731
2023-01-22 18:52:15.964222: step: 890/470, loss: 0.07769238203763962
2023-01-22 18:52:16.722818: step: 892/470, loss: 0.02832121029496193
2023-01-22 18:52:17.527188: step: 894/470, loss: 0.07402808964252472
2023-01-22 18:52:18.186525: step: 896/470, loss: 0.04894760623574257
2023-01-22 18:52:18.897117: step: 898/470, loss: 0.04703076183795929
2023-01-22 18:52:19.637775: step: 900/470, loss: 0.037153225392103195
2023-01-22 18:52:20.371317: step: 902/470, loss: 0.21902887523174286
2023-01-22 18:52:21.080044: step: 904/470, loss: 0.0130607383325696
2023-01-22 18:52:21.786224: step: 906/470, loss: 0.08418157696723938
2023-01-22 18:52:22.601201: step: 908/470, loss: 0.036279212683439255
2023-01-22 18:52:23.348059: step: 910/470, loss: 0.05508041754364967
2023-01-22 18:52:24.087879: step: 912/470, loss: 0.07078361511230469
2023-01-22 18:52:24.758052: step: 914/470, loss: 0.050121258944272995
2023-01-22 18:52:25.460039: step: 916/470, loss: 0.05768989026546478
2023-01-22 18:52:26.246754: step: 918/470, loss: 0.2717893123626709
2023-01-22 18:52:26.952069: step: 920/470, loss: 0.1305137723684311
2023-01-22 18:52:27.752107: step: 922/470, loss: 0.10596335679292679
2023-01-22 18:52:28.521494: step: 924/470, loss: 0.16074761748313904
2023-01-22 18:52:29.203520: step: 926/470, loss: 0.34018227458000183
2023-01-22 18:52:29.946382: step: 928/470, loss: 0.05126188322901726
2023-01-22 18:52:30.625718: step: 930/470, loss: 0.15903814136981964
2023-01-22 18:52:31.420700: step: 932/470, loss: 0.0827934592962265
2023-01-22 18:52:32.178818: step: 934/470, loss: 0.19107471406459808
2023-01-22 18:52:32.903786: step: 936/470, loss: 0.11879337579011917
2023-01-22 18:52:33.622849: step: 938/470, loss: 0.07795053720474243
2023-01-22 18:52:34.356870: step: 940/470, loss: 0.026459183543920517
2023-01-22 18:52:35.164958: step: 942/470, loss: 0.029973674565553665
==================================================
Loss: 0.184
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29003706543967284, 'r': 0.35883143580012655, 'f1': 0.32078739044387905}, 'combined': 0.23636965611654245, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33212946596293325, 'r': 0.35892953814438033, 'f1': 0.34500983306398886}, 'combined': 0.24030535636297734, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2848654123876765, 'r': 0.35459527614101666, 'f1': 0.3159285046936869}, 'combined': 0.23278942451113768, 'epoch': 16}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34234948544882304, 'r': 0.36208144426431715, 'f1': 0.3519391068899666}, 'combined': 0.2451317162417678, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26665851803563667, 'r': 0.3582433221427529, 'f1': 0.3057396449704142}, 'combined': 0.22528184366241047, 'epoch': 16}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32380480189265964, 'r': 0.36890729591229043, 'f1': 0.34488773690587726}, 'combined': 0.2402203142628001, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20149253731343283, 'r': 0.38571428571428573, 'f1': 0.2647058823529412}, 'combined': 0.1764705882352941, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2804878048780488, 'r': 0.5, 'f1': 0.359375}, 'combined': 0.1796875, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.40625, 'r': 0.33620689655172414, 'f1': 0.36792452830188677}, 'combined': 0.2452830188679245, 'epoch': 16}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2848654123876765, 'r': 0.35459527614101666, 'f1': 0.3159285046936869}, 'combined': 0.23278942451113768, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34234948544882304, 'r': 0.36208144426431715, 'f1': 0.3519391068899666}, 'combined': 0.2451317162417678, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2804878048780488, 'r': 0.5, 'f1': 0.359375}, 'combined': 0.1796875, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2747616086235489, 'r': 0.31438567362428843, 'f1': 0.29324115044247784}, 'combined': 0.21607242664182577, 'epoch': 14}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3377919490575152, 'r': 0.368618303678518, 'f1': 0.3525325256126204}, 'combined': 0.24554504271525798, 'epoch': 14}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5416666666666666, 'r': 0.33620689655172414, 'f1': 0.41489361702127664}, 'combined': 0.2765957446808511, 'epoch': 14}
******************************
Epoch: 17
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 18:55:20.100406: step: 2/470, loss: 0.4924387037754059
2023-01-22 18:55:20.812458: step: 4/470, loss: 0.0939476415514946
2023-01-22 18:55:21.576743: step: 6/470, loss: 0.11822464317083359
2023-01-22 18:55:22.219545: step: 8/470, loss: 3.426934242248535
2023-01-22 18:55:22.932570: step: 10/470, loss: 0.07467096298933029
2023-01-22 18:55:23.643430: step: 12/470, loss: 0.107358917593956
2023-01-22 18:55:24.379236: step: 14/470, loss: 0.07628848403692245
2023-01-22 18:55:25.150204: step: 16/470, loss: 0.06268688291311264
2023-01-22 18:55:25.909141: step: 18/470, loss: 0.10565035790205002
2023-01-22 18:55:26.703069: step: 20/470, loss: 0.4389980733394623
2023-01-22 18:55:27.393748: step: 22/470, loss: 0.050272297114133835
2023-01-22 18:55:28.105423: step: 24/470, loss: 0.02019389532506466
2023-01-22 18:55:28.807774: step: 26/470, loss: 0.1535024642944336
2023-01-22 18:55:29.458710: step: 28/470, loss: 0.09952471405267715
2023-01-22 18:55:30.207236: step: 30/470, loss: 0.0704805925488472
2023-01-22 18:55:30.878778: step: 32/470, loss: 0.28921636939048767
2023-01-22 18:55:31.644058: step: 34/470, loss: 0.090544693171978
2023-01-22 18:55:32.425297: step: 36/470, loss: 0.16174203157424927
2023-01-22 18:55:33.127417: step: 38/470, loss: 0.01790589466691017
2023-01-22 18:55:33.988472: step: 40/470, loss: 0.06238782778382301
2023-01-22 18:55:34.763133: step: 42/470, loss: 0.017772074788808823
2023-01-22 18:55:35.481836: step: 44/470, loss: 0.17414626479148865
2023-01-22 18:55:36.207644: step: 46/470, loss: 0.08931662142276764
2023-01-22 18:55:36.949206: step: 48/470, loss: 0.1393406093120575
2023-01-22 18:55:37.783372: step: 50/470, loss: 0.0651363730430603
2023-01-22 18:55:38.511769: step: 52/470, loss: 0.0816269963979721
2023-01-22 18:55:39.215880: step: 54/470, loss: 0.057508260011672974
2023-01-22 18:55:39.967739: step: 56/470, loss: 0.04575724899768829
2023-01-22 18:55:40.635125: step: 58/470, loss: 0.059317465871572495
2023-01-22 18:55:41.379576: step: 60/470, loss: 0.016667962074279785
2023-01-22 18:55:42.081759: step: 62/470, loss: 0.04501299932599068
2023-01-22 18:55:43.035763: step: 64/470, loss: 0.04957332834601402
2023-01-22 18:55:43.754673: step: 66/470, loss: 0.06242368370294571
2023-01-22 18:55:44.434328: step: 68/470, loss: 0.3788084387779236
2023-01-22 18:55:45.132405: step: 70/470, loss: 0.01375067513436079
2023-01-22 18:55:45.877222: step: 72/470, loss: 0.010087433271110058
2023-01-22 18:55:46.643601: step: 74/470, loss: 0.04814882203936577
2023-01-22 18:55:47.290609: step: 76/470, loss: 0.025498254224658012
2023-01-22 18:55:48.032356: step: 78/470, loss: 0.03883810341358185
2023-01-22 18:55:48.713310: step: 80/470, loss: 0.020485306158661842
2023-01-22 18:55:49.443693: step: 82/470, loss: 0.09962893277406693
2023-01-22 18:55:50.219507: step: 84/470, loss: 0.08178018778562546
2023-01-22 18:55:50.898798: step: 86/470, loss: 0.058422110974788666
2023-01-22 18:55:51.626265: step: 88/470, loss: 0.073599673807621
2023-01-22 18:55:52.407382: step: 90/470, loss: 0.06374432146549225
2023-01-22 18:55:53.141745: step: 92/470, loss: 0.16310732066631317
2023-01-22 18:55:53.896947: step: 94/470, loss: 0.6309743523597717
2023-01-22 18:55:54.787260: step: 96/470, loss: 0.043083060532808304
2023-01-22 18:55:55.523786: step: 98/470, loss: 0.07802923768758774
2023-01-22 18:55:56.242817: step: 100/470, loss: 0.06232817471027374
2023-01-22 18:55:56.949942: step: 102/470, loss: 0.152653768658638
2023-01-22 18:55:57.688828: step: 104/470, loss: 0.054097384214401245
2023-01-22 18:55:58.484129: step: 106/470, loss: 0.04027635604143143
2023-01-22 18:55:59.206080: step: 108/470, loss: 0.03251076117157936
2023-01-22 18:55:59.906642: step: 110/470, loss: 0.0775684118270874
2023-01-22 18:56:00.718375: step: 112/470, loss: 0.04833029955625534
2023-01-22 18:56:01.423090: step: 114/470, loss: 0.07459627836942673
2023-01-22 18:56:02.141161: step: 116/470, loss: 0.01013647299259901
2023-01-22 18:56:02.877159: step: 118/470, loss: 0.07257718592882156
2023-01-22 18:56:03.639773: step: 120/470, loss: 0.22532156109809875
2023-01-22 18:56:04.328840: step: 122/470, loss: 0.5136581659317017
2023-01-22 18:56:04.991351: step: 124/470, loss: 0.02729104831814766
2023-01-22 18:56:05.801392: step: 126/470, loss: 0.07071585953235626
2023-01-22 18:56:06.581992: step: 128/470, loss: 0.06299882382154465
2023-01-22 18:56:07.260470: step: 130/470, loss: 0.07367923855781555
2023-01-22 18:56:07.977896: step: 132/470, loss: 0.10907070338726044
2023-01-22 18:56:08.753141: step: 134/470, loss: 0.10193345695734024
2023-01-22 18:56:09.449718: step: 136/470, loss: 0.4187318980693817
2023-01-22 18:56:10.157253: step: 138/470, loss: 0.07536610960960388
2023-01-22 18:56:10.925450: step: 140/470, loss: 0.14740565419197083
2023-01-22 18:56:11.637094: step: 142/470, loss: 0.13611826300621033
2023-01-22 18:56:12.415235: step: 144/470, loss: 0.5455102324485779
2023-01-22 18:56:13.132983: step: 146/470, loss: 0.11672738194465637
2023-01-22 18:56:13.821245: step: 148/470, loss: 0.07301642745733261
2023-01-22 18:56:14.624835: step: 150/470, loss: 0.07370822876691818
2023-01-22 18:56:15.342132: step: 152/470, loss: 0.24967250227928162
2023-01-22 18:56:16.150503: step: 154/470, loss: 0.012790908105671406
2023-01-22 18:56:16.844889: step: 156/470, loss: 0.1556771844625473
2023-01-22 18:56:17.557390: step: 158/470, loss: 0.06868446618318558
2023-01-22 18:56:18.314980: step: 160/470, loss: 0.06958885490894318
2023-01-22 18:56:19.093257: step: 162/470, loss: 0.03733561187982559
2023-01-22 18:56:19.791340: step: 164/470, loss: 0.1148039773106575
2023-01-22 18:56:20.458504: step: 166/470, loss: 0.5623202323913574
2023-01-22 18:56:21.219066: step: 168/470, loss: 0.6287685632705688
2023-01-22 18:56:21.953667: step: 170/470, loss: 0.11442598700523376
2023-01-22 18:56:22.694265: step: 172/470, loss: 0.06008310243487358
2023-01-22 18:56:23.474062: step: 174/470, loss: 0.06911762058734894
2023-01-22 18:56:24.210514: step: 176/470, loss: 0.005540335550904274
2023-01-22 18:56:24.905172: step: 178/470, loss: 0.07414489984512329
2023-01-22 18:56:25.633101: step: 180/470, loss: 0.07211507856845856
2023-01-22 18:56:26.512635: step: 182/470, loss: 0.050867147743701935
2023-01-22 18:56:27.194772: step: 184/470, loss: 0.013534078374505043
2023-01-22 18:56:27.976130: step: 186/470, loss: 0.05755781754851341
2023-01-22 18:56:28.740580: step: 188/470, loss: 0.7376323938369751
2023-01-22 18:56:29.429885: step: 190/470, loss: 0.023348214104771614
2023-01-22 18:56:30.218172: step: 192/470, loss: 0.1323942095041275
2023-01-22 18:56:30.934410: step: 194/470, loss: 0.5270007848739624
2023-01-22 18:56:31.661230: step: 196/470, loss: 0.01694687083363533
2023-01-22 18:56:32.462360: step: 198/470, loss: 0.04331256076693535
2023-01-22 18:56:33.297219: step: 200/470, loss: 0.1521039754152298
2023-01-22 18:56:33.973410: step: 202/470, loss: 0.05080660060048103
2023-01-22 18:56:34.627068: step: 204/470, loss: 0.23060721158981323
2023-01-22 18:56:35.272565: step: 206/470, loss: 0.08327927440404892
2023-01-22 18:56:35.977254: step: 208/470, loss: 0.1002572625875473
2023-01-22 18:56:36.676059: step: 210/470, loss: 0.051106516271829605
2023-01-22 18:56:37.439272: step: 212/470, loss: 0.05127272009849548
2023-01-22 18:56:38.163301: step: 214/470, loss: 0.0413568951189518
2023-01-22 18:56:38.955672: step: 216/470, loss: 0.04580258950591087
2023-01-22 18:56:39.708151: step: 218/470, loss: 0.10093220323324203
2023-01-22 18:56:40.467012: step: 220/470, loss: 0.12144112586975098
2023-01-22 18:56:41.211328: step: 222/470, loss: 0.06039506569504738
2023-01-22 18:56:41.905064: step: 224/470, loss: 0.028329022228717804
2023-01-22 18:56:42.584166: step: 226/470, loss: 0.16305898129940033
2023-01-22 18:56:43.309072: step: 228/470, loss: 0.10858103632926941
2023-01-22 18:56:44.003364: step: 230/470, loss: 0.05416190251708031
2023-01-22 18:56:44.803804: step: 232/470, loss: 0.03306606039404869
2023-01-22 18:56:45.601679: step: 234/470, loss: 0.08176732063293457
2023-01-22 18:56:46.325555: step: 236/470, loss: 0.4104897975921631
2023-01-22 18:56:47.069803: step: 238/470, loss: 0.257541686296463
2023-01-22 18:56:47.799706: step: 240/470, loss: 0.045913856476545334
2023-01-22 18:56:48.476606: step: 242/470, loss: 0.030991556122899055
2023-01-22 18:56:49.211744: step: 244/470, loss: 0.056961365044116974
2023-01-22 18:56:50.080207: step: 246/470, loss: 0.1344350129365921
2023-01-22 18:56:50.853876: step: 248/470, loss: 0.10876922309398651
2023-01-22 18:56:51.619350: step: 250/470, loss: 0.05064590647816658
2023-01-22 18:56:52.432740: step: 252/470, loss: 0.05507608503103256
2023-01-22 18:56:53.136738: step: 254/470, loss: 0.1291094422340393
2023-01-22 18:56:53.831397: step: 256/470, loss: 0.1127728670835495
2023-01-22 18:56:54.517429: step: 258/470, loss: 0.2618001699447632
2023-01-22 18:56:55.258533: step: 260/470, loss: 0.30301615595817566
2023-01-22 18:56:56.042768: step: 262/470, loss: 0.08459173142910004
2023-01-22 18:56:56.808970: step: 264/470, loss: 0.036896541714668274
2023-01-22 18:56:57.516320: step: 266/470, loss: 0.03432435914874077
2023-01-22 18:56:58.304883: step: 268/470, loss: 0.04738718271255493
2023-01-22 18:56:59.047915: step: 270/470, loss: 0.2793467342853546
2023-01-22 18:56:59.750582: step: 272/470, loss: 0.07192108035087585
2023-01-22 18:57:00.471379: step: 274/470, loss: 0.12388882040977478
2023-01-22 18:57:01.144894: step: 276/470, loss: 0.05751514807343483
2023-01-22 18:57:01.942637: step: 278/470, loss: 0.12290464341640472
2023-01-22 18:57:02.701755: step: 280/470, loss: 0.0717790424823761
2023-01-22 18:57:03.468256: step: 282/470, loss: 0.07550595700740814
2023-01-22 18:57:04.230012: step: 284/470, loss: 0.133597269654274
2023-01-22 18:57:04.966913: step: 286/470, loss: 0.14142487943172455
2023-01-22 18:57:05.618776: step: 288/470, loss: 0.17519471049308777
2023-01-22 18:57:06.426404: step: 290/470, loss: 0.04353666305541992
2023-01-22 18:57:07.215287: step: 292/470, loss: 1.747153639793396
2023-01-22 18:57:08.012949: step: 294/470, loss: 0.499929815530777
2023-01-22 18:57:08.838991: step: 296/470, loss: 0.07138823717832565
2023-01-22 18:57:09.645647: step: 298/470, loss: 0.03818880766630173
2023-01-22 18:57:10.357900: step: 300/470, loss: 0.29137733578681946
2023-01-22 18:57:11.096090: step: 302/470, loss: 0.43531379103660583
2023-01-22 18:57:11.932178: step: 304/470, loss: 0.06073610112071037
2023-01-22 18:57:12.646074: step: 306/470, loss: 0.12262983620166779
2023-01-22 18:57:13.385636: step: 308/470, loss: 0.2984396815299988
2023-01-22 18:57:14.125686: step: 310/470, loss: 0.5396106243133545
2023-01-22 18:57:14.947898: step: 312/470, loss: 0.14061273634433746
2023-01-22 18:57:15.687751: step: 314/470, loss: 0.28197863698005676
2023-01-22 18:57:16.391590: step: 316/470, loss: 0.04360943287611008
2023-01-22 18:57:17.065243: step: 318/470, loss: 0.0115542346611619
2023-01-22 18:57:17.775757: step: 320/470, loss: 0.1039966344833374
2023-01-22 18:57:18.527705: step: 322/470, loss: 0.08922134339809418
2023-01-22 18:57:19.234110: step: 324/470, loss: 0.08642390370368958
2023-01-22 18:57:20.011235: step: 326/470, loss: 0.05966321378946304
2023-01-22 18:57:20.882587: step: 328/470, loss: 0.0547308623790741
2023-01-22 18:57:21.624454: step: 330/470, loss: 0.08806410431861877
2023-01-22 18:57:22.369096: step: 332/470, loss: 0.07780762016773224
2023-01-22 18:57:23.040154: step: 334/470, loss: 0.08751654624938965
2023-01-22 18:57:23.800358: step: 336/470, loss: 0.07845862209796906
2023-01-22 18:57:24.565418: step: 338/470, loss: 0.034335438162088394
2023-01-22 18:57:25.387287: step: 340/470, loss: 0.028561709448695183
2023-01-22 18:57:26.145147: step: 342/470, loss: 0.10376818478107452
2023-01-22 18:57:26.877960: step: 344/470, loss: 0.05915750935673714
2023-01-22 18:57:27.643238: step: 346/470, loss: 0.25353285670280457
2023-01-22 18:57:28.401835: step: 348/470, loss: 0.13213659822940826
2023-01-22 18:57:29.121355: step: 350/470, loss: 0.31304770708084106
2023-01-22 18:57:29.831015: step: 352/470, loss: 0.1196952536702156
2023-01-22 18:57:30.691608: step: 354/470, loss: 0.11991266906261444
2023-01-22 18:57:31.408629: step: 356/470, loss: 0.03160081058740616
2023-01-22 18:57:32.121628: step: 358/470, loss: 0.11861895769834518
2023-01-22 18:57:32.900057: step: 360/470, loss: 0.06153372302651405
2023-01-22 18:57:33.641089: step: 362/470, loss: 0.08058642596006393
2023-01-22 18:57:34.387538: step: 364/470, loss: 0.13972775638103485
2023-01-22 18:57:35.150216: step: 366/470, loss: 0.12595215439796448
2023-01-22 18:57:35.891190: step: 368/470, loss: 0.05694999545812607
2023-01-22 18:57:36.635816: step: 370/470, loss: 0.08451858162879944
2023-01-22 18:57:37.359473: step: 372/470, loss: 0.09174233675003052
2023-01-22 18:57:38.073498: step: 374/470, loss: 0.00898781232535839
2023-01-22 18:57:38.825288: step: 376/470, loss: 0.025392355397343636
2023-01-22 18:57:39.591510: step: 378/470, loss: 0.04026934504508972
2023-01-22 18:57:40.338395: step: 380/470, loss: 0.01192416436970234
2023-01-22 18:57:41.108180: step: 382/470, loss: 0.0662471279501915
2023-01-22 18:57:41.862093: step: 384/470, loss: 0.08708631247282028
2023-01-22 18:57:42.580010: step: 386/470, loss: 0.01594570279121399
2023-01-22 18:57:43.340273: step: 388/470, loss: 0.15144769847393036
2023-01-22 18:57:44.133147: step: 390/470, loss: 0.03741728886961937
2023-01-22 18:57:44.857965: step: 392/470, loss: 1.6541204452514648
2023-01-22 18:57:45.518826: step: 394/470, loss: 0.07524050027132034
2023-01-22 18:57:46.284819: step: 396/470, loss: 0.004373232834041119
2023-01-22 18:57:47.030477: step: 398/470, loss: 0.12484033405780792
2023-01-22 18:57:47.830863: step: 400/470, loss: 0.1493765264749527
2023-01-22 18:57:48.478802: step: 402/470, loss: 0.029209822416305542
2023-01-22 18:57:49.174650: step: 404/470, loss: 0.07852840423583984
2023-01-22 18:57:49.881099: step: 406/470, loss: 0.03971928730607033
2023-01-22 18:57:50.511335: step: 408/470, loss: 0.027434857562184334
2023-01-22 18:57:51.247282: step: 410/470, loss: 0.149210125207901
2023-01-22 18:57:51.952787: step: 412/470, loss: 0.06711407005786896
2023-01-22 18:57:52.730136: step: 414/470, loss: 0.041621264070272446
2023-01-22 18:57:53.393634: step: 416/470, loss: 0.06607449799776077
2023-01-22 18:57:54.194928: step: 418/470, loss: 0.03028223291039467
2023-01-22 18:57:54.900602: step: 420/470, loss: 0.08194995671510696
2023-01-22 18:57:55.567822: step: 422/470, loss: 1.202500820159912
2023-01-22 18:57:56.194802: step: 424/470, loss: 0.03522910550236702
2023-01-22 18:57:56.874906: step: 426/470, loss: 0.11419682204723358
2023-01-22 18:57:57.636922: step: 428/470, loss: 0.027502695098519325
2023-01-22 18:57:58.294884: step: 430/470, loss: 0.1228659600019455
2023-01-22 18:57:58.991758: step: 432/470, loss: 0.013959257863461971
2023-01-22 18:57:59.800840: step: 434/470, loss: 0.12251380831003189
2023-01-22 18:58:00.603879: step: 436/470, loss: 0.03891543298959732
2023-01-22 18:58:01.396537: step: 438/470, loss: 0.058498311787843704
2023-01-22 18:58:02.131713: step: 440/470, loss: 0.02747928909957409
2023-01-22 18:58:02.863310: step: 442/470, loss: 0.10275592654943466
2023-01-22 18:58:03.607210: step: 444/470, loss: 0.5213198065757751
2023-01-22 18:58:04.291547: step: 446/470, loss: 0.19728517532348633
2023-01-22 18:58:05.041314: step: 448/470, loss: 0.4907250702381134
2023-01-22 18:58:05.789007: step: 450/470, loss: 0.10592763125896454
2023-01-22 18:58:06.509692: step: 452/470, loss: 0.0349123552441597
2023-01-22 18:58:07.308081: step: 454/470, loss: 0.05272674188017845
2023-01-22 18:58:08.031812: step: 456/470, loss: 0.0323164276778698
2023-01-22 18:58:08.772393: step: 458/470, loss: 0.08098090440034866
2023-01-22 18:58:09.506540: step: 460/470, loss: 0.07947229593992233
2023-01-22 18:58:10.282008: step: 462/470, loss: 0.194414883852005
2023-01-22 18:58:11.022793: step: 464/470, loss: 0.12346761673688889
2023-01-22 18:58:11.804641: step: 466/470, loss: 0.05517350882291794
2023-01-22 18:58:12.693053: step: 468/470, loss: 0.4561017155647278
2023-01-22 18:58:13.347507: step: 470/470, loss: 0.08983838558197021
2023-01-22 18:58:14.074529: step: 472/470, loss: 0.4218137264251709
2023-01-22 18:58:14.871289: step: 474/470, loss: 0.05566902086138725
2023-01-22 18:58:15.614238: step: 476/470, loss: 0.05252564325928688
2023-01-22 18:58:16.311933: step: 478/470, loss: 0.031113555654883385
2023-01-22 18:58:17.037928: step: 480/470, loss: 0.6434183716773987
2023-01-22 18:58:17.787282: step: 482/470, loss: 1.0721107721328735
2023-01-22 18:58:18.509911: step: 484/470, loss: 0.01686706766486168
2023-01-22 18:58:19.280923: step: 486/470, loss: 0.016208596527576447
2023-01-22 18:58:19.979494: step: 488/470, loss: 0.07484219968318939
2023-01-22 18:58:20.691664: step: 490/470, loss: 0.03733556717634201
2023-01-22 18:58:21.393384: step: 492/470, loss: 0.107573002576828
2023-01-22 18:58:22.042720: step: 494/470, loss: 0.06075252965092659
2023-01-22 18:58:22.830751: step: 496/470, loss: 0.058279551565647125
2023-01-22 18:58:23.638001: step: 498/470, loss: 0.05781916528940201
2023-01-22 18:58:24.434287: step: 500/470, loss: 0.13210691511631012
2023-01-22 18:58:25.173618: step: 502/470, loss: 1.0277457237243652
2023-01-22 18:58:25.889446: step: 504/470, loss: 0.04871448129415512
2023-01-22 18:58:26.608745: step: 506/470, loss: 0.5733938813209534
2023-01-22 18:58:27.353620: step: 508/470, loss: 0.016267672181129456
2023-01-22 18:58:28.088105: step: 510/470, loss: 0.05442097783088684
2023-01-22 18:58:28.856219: step: 512/470, loss: 1.0532729625701904
2023-01-22 18:58:29.643713: step: 514/470, loss: 0.0817883089184761
2023-01-22 18:58:30.453540: step: 516/470, loss: 0.08425731956958771
2023-01-22 18:58:31.217174: step: 518/470, loss: 0.1442107856273651
2023-01-22 18:58:32.052752: step: 520/470, loss: 0.5000361204147339
2023-01-22 18:58:32.796014: step: 522/470, loss: 0.05786876752972603
2023-01-22 18:58:33.464569: step: 524/470, loss: 0.1195589229464531
2023-01-22 18:58:34.225431: step: 526/470, loss: 0.06997283548116684
2023-01-22 18:58:34.964467: step: 528/470, loss: 0.020335132256150246
2023-01-22 18:58:35.693231: step: 530/470, loss: 0.08447545021772385
2023-01-22 18:58:36.445293: step: 532/470, loss: 0.04109674319624901
2023-01-22 18:58:37.188818: step: 534/470, loss: 0.11775404959917068
2023-01-22 18:58:37.917638: step: 536/470, loss: 0.1142866313457489
2023-01-22 18:58:38.676916: step: 538/470, loss: 0.3399909436702728
2023-01-22 18:58:39.363619: step: 540/470, loss: 0.04983226954936981
2023-01-22 18:58:40.082745: step: 542/470, loss: 0.038683708757162094
2023-01-22 18:58:40.792110: step: 544/470, loss: 0.00999883096665144
2023-01-22 18:58:41.519251: step: 546/470, loss: 0.03342743217945099
2023-01-22 18:58:42.292417: step: 548/470, loss: 0.11033465713262558
2023-01-22 18:58:43.107395: step: 550/470, loss: 0.04878013953566551
2023-01-22 18:58:43.870673: step: 552/470, loss: 0.09103644639253616
2023-01-22 18:58:44.544355: step: 554/470, loss: 0.015820780768990517
2023-01-22 18:58:45.308813: step: 556/470, loss: 0.07098133116960526
2023-01-22 18:58:46.059326: step: 558/470, loss: 0.5348267555236816
2023-01-22 18:58:46.824644: step: 560/470, loss: 0.06724416464567184
2023-01-22 18:58:47.622669: step: 562/470, loss: 0.05711890384554863
2023-01-22 18:58:48.378815: step: 564/470, loss: 0.025366008281707764
2023-01-22 18:58:49.085805: step: 566/470, loss: 0.030365778133273125
2023-01-22 18:58:49.817015: step: 568/470, loss: 0.08409339189529419
2023-01-22 18:58:50.532251: step: 570/470, loss: 1.9741016626358032
2023-01-22 18:58:51.180436: step: 572/470, loss: 0.0606938898563385
2023-01-22 18:58:51.991278: step: 574/470, loss: 0.08465118706226349
2023-01-22 18:58:52.707723: step: 576/470, loss: 0.03369426727294922
2023-01-22 18:58:53.503793: step: 578/470, loss: 0.042784154415130615
2023-01-22 18:58:54.152967: step: 580/470, loss: 0.11120610684156418
2023-01-22 18:58:54.865218: step: 582/470, loss: 0.11828941851854324
2023-01-22 18:58:55.534018: step: 584/470, loss: 0.08425047993659973
2023-01-22 18:58:56.274105: step: 586/470, loss: 0.03659561276435852
2023-01-22 18:58:56.982334: step: 588/470, loss: 0.050091128796339035
2023-01-22 18:58:57.643507: step: 590/470, loss: 0.022585172206163406
2023-01-22 18:58:58.450379: step: 592/470, loss: 0.1083977222442627
2023-01-22 18:58:59.138176: step: 594/470, loss: 0.008220894262194633
2023-01-22 18:58:59.813303: step: 596/470, loss: 0.12439019232988358
2023-01-22 18:59:00.644672: step: 598/470, loss: 0.027765508741140366
2023-01-22 18:59:01.347029: step: 600/470, loss: 0.036968786269426346
2023-01-22 18:59:02.161250: step: 602/470, loss: 0.07465256750583649
2023-01-22 18:59:02.830358: step: 604/470, loss: 0.01624050922691822
2023-01-22 18:59:03.575080: step: 606/470, loss: 0.012987270019948483
2023-01-22 18:59:04.448617: step: 608/470, loss: 0.05419148504734039
2023-01-22 18:59:05.214273: step: 610/470, loss: 0.1707671582698822
2023-01-22 18:59:05.945003: step: 612/470, loss: 0.08779844641685486
2023-01-22 18:59:06.783919: step: 614/470, loss: 0.12106174230575562
2023-01-22 18:59:07.512003: step: 616/470, loss: 0.5510255694389343
2023-01-22 18:59:08.329984: step: 618/470, loss: 0.07842077314853668
2023-01-22 18:59:09.006818: step: 620/470, loss: 0.08350328356027603
2023-01-22 18:59:09.691343: step: 622/470, loss: 0.1282799243927002
2023-01-22 18:59:10.429455: step: 624/470, loss: 0.08514758944511414
2023-01-22 18:59:11.174423: step: 626/470, loss: 0.08214154094457626
2023-01-22 18:59:11.853944: step: 628/470, loss: 0.02037135139107704
2023-01-22 18:59:12.601058: step: 630/470, loss: 0.0328313373029232
2023-01-22 18:59:13.354497: step: 632/470, loss: 0.12586846947669983
2023-01-22 18:59:14.156479: step: 634/470, loss: 1.1721528768539429
2023-01-22 18:59:14.952851: step: 636/470, loss: 0.06453651934862137
2023-01-22 18:59:15.708947: step: 638/470, loss: 0.12365590780973434
2023-01-22 18:59:16.430889: step: 640/470, loss: 0.23456744849681854
2023-01-22 18:59:17.166600: step: 642/470, loss: 0.06679598242044449
2023-01-22 18:59:18.070214: step: 644/470, loss: 0.30910104513168335
2023-01-22 18:59:18.786811: step: 646/470, loss: 0.06718228757381439
2023-01-22 18:59:19.579025: step: 648/470, loss: 0.07001607865095139
2023-01-22 18:59:20.225869: step: 650/470, loss: 0.05453366041183472
2023-01-22 18:59:21.013500: step: 652/470, loss: 0.08327239006757736
2023-01-22 18:59:21.723478: step: 654/470, loss: 0.4447418451309204
2023-01-22 18:59:22.432364: step: 656/470, loss: 0.08664055168628693
2023-01-22 18:59:23.184070: step: 658/470, loss: 0.038746707141399384
2023-01-22 18:59:24.063540: step: 660/470, loss: 0.8028762340545654
2023-01-22 18:59:24.768480: step: 662/470, loss: 0.03993918374180794
2023-01-22 18:59:25.499714: step: 664/470, loss: 0.029848841950297356
2023-01-22 18:59:26.159598: step: 666/470, loss: 0.09658187627792358
2023-01-22 18:59:26.879324: step: 668/470, loss: 0.06456496566534042
2023-01-22 18:59:27.642582: step: 670/470, loss: 0.04641230031847954
2023-01-22 18:59:28.381092: step: 672/470, loss: 0.09238805621862411
2023-01-22 18:59:29.079249: step: 674/470, loss: 0.056428153067827225
2023-01-22 18:59:29.777369: step: 676/470, loss: 0.16270509362220764
2023-01-22 18:59:30.493930: step: 678/470, loss: 0.07294663041830063
2023-01-22 18:59:31.271533: step: 680/470, loss: 0.1018824577331543
2023-01-22 18:59:32.023070: step: 682/470, loss: 0.3484339118003845
2023-01-22 18:59:32.798368: step: 684/470, loss: 0.10737051069736481
2023-01-22 18:59:33.570916: step: 686/470, loss: 0.05558640882372856
2023-01-22 18:59:34.266790: step: 688/470, loss: 0.13277633488178253
2023-01-22 18:59:35.020419: step: 690/470, loss: 0.08180245012044907
2023-01-22 18:59:35.754379: step: 692/470, loss: 0.06329744309186935
2023-01-22 18:59:36.485577: step: 694/470, loss: 0.14542846381664276
2023-01-22 18:59:37.194337: step: 696/470, loss: 0.0733979269862175
2023-01-22 18:59:37.936276: step: 698/470, loss: 0.08746114373207092
2023-01-22 18:59:38.740140: step: 700/470, loss: 0.0837959498167038
2023-01-22 18:59:39.447339: step: 702/470, loss: 0.20224621891975403
2023-01-22 18:59:40.143120: step: 704/470, loss: 0.35301804542541504
2023-01-22 18:59:40.923876: step: 706/470, loss: 0.06424695998430252
2023-01-22 18:59:41.683466: step: 708/470, loss: 0.08036937564611435
2023-01-22 18:59:42.385178: step: 710/470, loss: 0.022141428664326668
2023-01-22 18:59:43.124600: step: 712/470, loss: 0.16465261578559875
2023-01-22 18:59:43.868394: step: 714/470, loss: 0.03278358653187752
2023-01-22 18:59:44.593556: step: 716/470, loss: 0.1571766436100006
2023-01-22 18:59:45.295846: step: 718/470, loss: 0.24385596811771393
2023-01-22 18:59:45.997592: step: 720/470, loss: 0.11035379767417908
2023-01-22 18:59:46.716121: step: 722/470, loss: 0.1532362550497055
2023-01-22 18:59:47.528765: step: 724/470, loss: 0.11130030453205109
2023-01-22 18:59:48.290258: step: 726/470, loss: 0.3597228527069092
2023-01-22 18:59:49.159318: step: 728/470, loss: 0.02049565315246582
2023-01-22 18:59:49.993697: step: 730/470, loss: 0.11515626311302185
2023-01-22 18:59:50.750397: step: 732/470, loss: 0.020818457007408142
2023-01-22 18:59:51.489024: step: 734/470, loss: 0.06096053496003151
2023-01-22 18:59:52.200407: step: 736/470, loss: 0.061641495674848557
2023-01-22 18:59:52.888730: step: 738/470, loss: 0.09029534459114075
2023-01-22 18:59:53.543510: step: 740/470, loss: 0.07005026191473007
2023-01-22 18:59:54.270130: step: 742/470, loss: 0.07654117792844772
2023-01-22 18:59:54.987858: step: 744/470, loss: 0.06442206352949142
2023-01-22 18:59:55.714522: step: 746/470, loss: 0.6992735862731934
2023-01-22 18:59:56.459443: step: 748/470, loss: 0.060101427137851715
2023-01-22 18:59:57.179706: step: 750/470, loss: 0.25749671459198
2023-01-22 18:59:57.878544: step: 752/470, loss: 0.1867312639951706
2023-01-22 18:59:58.609130: step: 754/470, loss: 0.045231420546770096
2023-01-22 18:59:59.326573: step: 756/470, loss: 0.04085368663072586
2023-01-22 19:00:00.096943: step: 758/470, loss: 0.6277973055839539
2023-01-22 19:00:00.855046: step: 760/470, loss: 0.1876017451286316
2023-01-22 19:00:01.689343: step: 762/470, loss: 0.23550686240196228
2023-01-22 19:00:02.427205: step: 764/470, loss: 0.06056235358119011
2023-01-22 19:00:03.175541: step: 766/470, loss: 0.11358806490898132
2023-01-22 19:00:03.933788: step: 768/470, loss: 0.16502447426319122
2023-01-22 19:00:04.604264: step: 770/470, loss: 0.11180621385574341
2023-01-22 19:00:05.361241: step: 772/470, loss: 0.05992017686367035
2023-01-22 19:00:06.167582: step: 774/470, loss: 0.09332225471735
2023-01-22 19:00:06.892512: step: 776/470, loss: 0.1730080544948578
2023-01-22 19:00:07.638745: step: 778/470, loss: 0.9607817530632019
2023-01-22 19:00:08.402731: step: 780/470, loss: 0.11541511863470078
2023-01-22 19:00:09.198319: step: 782/470, loss: 0.028602128848433495
2023-01-22 19:00:09.931763: step: 784/470, loss: 0.060707904398441315
2023-01-22 19:00:10.643718: step: 786/470, loss: 0.01682162657380104
2023-01-22 19:00:11.401871: step: 788/470, loss: 0.05692780017852783
2023-01-22 19:00:12.101917: step: 790/470, loss: 0.23850642144680023
2023-01-22 19:00:12.767743: step: 792/470, loss: 0.0492679700255394
2023-01-22 19:00:13.477746: step: 794/470, loss: 0.058511458337306976
2023-01-22 19:00:14.214603: step: 796/470, loss: 0.06941919773817062
2023-01-22 19:00:14.945502: step: 798/470, loss: 0.07419852167367935
2023-01-22 19:00:15.633278: step: 800/470, loss: 0.0205177403986454
2023-01-22 19:00:16.378354: step: 802/470, loss: 0.08371607959270477
2023-01-22 19:00:17.123312: step: 804/470, loss: 0.03052728809416294
2023-01-22 19:00:17.815470: step: 806/470, loss: 0.040770161896944046
2023-01-22 19:00:18.575287: step: 808/470, loss: 0.09312587976455688
2023-01-22 19:00:19.330333: step: 810/470, loss: 0.33695071935653687
2023-01-22 19:00:20.088242: step: 812/470, loss: 0.1501253843307495
2023-01-22 19:00:20.848477: step: 814/470, loss: 0.05207722634077072
2023-01-22 19:00:21.532356: step: 816/470, loss: 0.026118360459804535
2023-01-22 19:00:22.317447: step: 818/470, loss: 0.029398392885923386
2023-01-22 19:00:23.099615: step: 820/470, loss: 0.10104161500930786
2023-01-22 19:00:23.922959: step: 822/470, loss: 0.05879708379507065
2023-01-22 19:00:24.590591: step: 824/470, loss: 0.07474382221698761
2023-01-22 19:00:25.288473: step: 826/470, loss: 0.038804251700639725
2023-01-22 19:00:26.013344: step: 828/470, loss: 0.09933701902627945
2023-01-22 19:00:26.748253: step: 830/470, loss: 0.03747892752289772
2023-01-22 19:00:27.623645: step: 832/470, loss: 0.21376895904541016
2023-01-22 19:00:28.303559: step: 834/470, loss: 0.11364637315273285
2023-01-22 19:00:29.016973: step: 836/470, loss: 0.22915977239608765
2023-01-22 19:00:29.757182: step: 838/470, loss: 0.10806091874837875
2023-01-22 19:00:30.562347: step: 840/470, loss: 0.15018446743488312
2023-01-22 19:00:31.448049: step: 842/470, loss: 0.11992557346820831
2023-01-22 19:00:32.182541: step: 844/470, loss: 0.08834873884916306
2023-01-22 19:00:32.945424: step: 846/470, loss: 0.08360497653484344
2023-01-22 19:00:33.678586: step: 848/470, loss: 0.04521460458636284
2023-01-22 19:00:34.415896: step: 850/470, loss: 0.07406667619943619
2023-01-22 19:00:35.116389: step: 852/470, loss: 0.1984773576259613
2023-01-22 19:00:35.867931: step: 854/470, loss: 0.07086524367332458
2023-01-22 19:00:36.550560: step: 856/470, loss: 2.956345319747925
2023-01-22 19:00:37.272063: step: 858/470, loss: 0.28626927733421326
2023-01-22 19:00:37.958746: step: 860/470, loss: 0.02902461588382721
2023-01-22 19:00:38.734549: step: 862/470, loss: 0.2611776292324066
2023-01-22 19:00:39.487926: step: 864/470, loss: 0.09869827330112457
2023-01-22 19:00:40.244116: step: 866/470, loss: 0.08181178569793701
2023-01-22 19:00:40.971349: step: 868/470, loss: 0.16328763961791992
2023-01-22 19:00:41.714731: step: 870/470, loss: 0.01159185916185379
2023-01-22 19:00:42.563900: step: 872/470, loss: 0.29373496770858765
2023-01-22 19:00:43.311501: step: 874/470, loss: 0.027659697458148003
2023-01-22 19:00:44.110199: step: 876/470, loss: 0.05898299440741539
2023-01-22 19:00:44.782710: step: 878/470, loss: 0.11096679419279099
2023-01-22 19:00:45.484563: step: 880/470, loss: 0.3364698886871338
2023-01-22 19:00:46.266141: step: 882/470, loss: 0.04068123549222946
2023-01-22 19:00:47.112897: step: 884/470, loss: 0.08637043088674545
2023-01-22 19:00:47.892770: step: 886/470, loss: 0.10517950356006622
2023-01-22 19:00:48.604014: step: 888/470, loss: 0.1388533115386963
2023-01-22 19:00:49.454606: step: 890/470, loss: 0.10692066699266434
2023-01-22 19:00:50.151328: step: 892/470, loss: 0.4482387900352478
2023-01-22 19:00:50.927613: step: 894/470, loss: 0.04289408028125763
2023-01-22 19:00:51.610011: step: 896/470, loss: 0.1445654332637787
2023-01-22 19:00:52.348543: step: 898/470, loss: 0.3577795922756195
2023-01-22 19:00:53.072319: step: 900/470, loss: 0.03457728773355484
2023-01-22 19:00:53.864870: step: 902/470, loss: 0.07262220978736877
2023-01-22 19:00:54.585435: step: 904/470, loss: 0.0956735610961914
2023-01-22 19:00:55.316507: step: 906/470, loss: 0.2117413431406021
2023-01-22 19:00:56.160722: step: 908/470, loss: 0.08425169438123703
2023-01-22 19:00:56.872379: step: 910/470, loss: 0.23610138893127441
2023-01-22 19:00:57.653227: step: 912/470, loss: 0.6577050685882568
2023-01-22 19:00:58.428210: step: 914/470, loss: 0.06360519677400589
2023-01-22 19:00:59.077379: step: 916/470, loss: 0.06351134926080704
2023-01-22 19:00:59.839727: step: 918/470, loss: 0.042916182428598404
2023-01-22 19:01:00.696886: step: 920/470, loss: 0.07389490306377411
2023-01-22 19:01:01.473602: step: 922/470, loss: 0.1284465193748474
2023-01-22 19:01:02.239070: step: 924/470, loss: 0.07059228420257568
2023-01-22 19:01:02.986814: step: 926/470, loss: 0.1461246758699417
2023-01-22 19:01:03.713630: step: 928/470, loss: 0.24688246846199036
2023-01-22 19:01:04.417993: step: 930/470, loss: 0.016211118549108505
2023-01-22 19:01:05.075980: step: 932/470, loss: 0.05001834034919739
2023-01-22 19:01:05.851619: step: 934/470, loss: 0.043632302433252335
2023-01-22 19:01:06.585183: step: 936/470, loss: 0.10320833325386047
2023-01-22 19:01:07.325269: step: 938/470, loss: 0.03066897578537464
2023-01-22 19:01:07.961770: step: 940/470, loss: 0.06406714022159576
2023-01-22 19:01:08.619388: step: 942/470, loss: 0.11159685254096985
==================================================
Loss: 0.157
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3107669293636895, 'r': 0.3367133143580013, 'f1': 0.3232202489374621}, 'combined': 0.23816228869076153, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.339832635684455, 'r': 0.33264386839112997, 'f1': 0.33619982811154053}, 'combined': 0.23416903450555063, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29978370937139087, 'r': 0.32993273517154975, 'f1': 0.3141364976249444}, 'combined': 0.231468998249959, 'epoch': 17}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3494487917344357, 'r': 0.33600845359080356, 'f1': 0.34259685464160367}, 'combined': 0.23862467487474884, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.22131147540983606, 'r': 0.38571428571428573, 'f1': 0.28125}, 'combined': 0.1875, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
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': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29978370937139087, 'r': 0.32993273517154975, 'f1': 0.3141364976249444}, 'combined': 0.231468998249959, 'epoch': 17}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3494487917344357, 'r': 0.33600845359080356, 'f1': 0.34259685464160367}, 'combined': 0.23862467487474884, 'epoch': 17}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 17}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 18
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 19:03:55.515436: step: 2/470, loss: 0.06617684662342072
2023-01-22 19:03:56.225143: step: 4/470, loss: 0.017266876995563507
2023-01-22 19:03:56.940202: step: 6/470, loss: 0.04035760834813118
2023-01-22 19:03:57.656841: step: 8/470, loss: 0.07709954679012299
2023-01-22 19:03:58.417589: step: 10/470, loss: 0.160027876496315
2023-01-22 19:03:59.149869: step: 12/470, loss: 0.06833804398775101
2023-01-22 19:03:59.872975: step: 14/470, loss: 0.4198529124259949
2023-01-22 19:04:00.729216: step: 16/470, loss: 0.1530308574438095
2023-01-22 19:04:01.499718: step: 18/470, loss: 0.3755422532558441
2023-01-22 19:04:02.300235: step: 20/470, loss: 0.14509013295173645
2023-01-22 19:04:03.064305: step: 22/470, loss: 0.10982964187860489
2023-01-22 19:04:03.751791: step: 24/470, loss: 0.038370661437511444
2023-01-22 19:04:04.453585: step: 26/470, loss: 0.0846431627869606
2023-01-22 19:04:05.224102: step: 28/470, loss: 0.11229250580072403
2023-01-22 19:04:06.001872: step: 30/470, loss: 0.7171079516410828
2023-01-22 19:04:06.709912: step: 32/470, loss: 0.08063667267560959
2023-01-22 19:04:07.370795: step: 34/470, loss: 0.026313627138733864
2023-01-22 19:04:08.103987: step: 36/470, loss: 0.07363957166671753
2023-01-22 19:04:08.834024: step: 38/470, loss: 1.1096469163894653
2023-01-22 19:04:09.562033: step: 40/470, loss: 0.07688609510660172
2023-01-22 19:04:10.280409: step: 42/470, loss: 0.18271422386169434
2023-01-22 19:04:11.038795: step: 44/470, loss: 0.07778210192918777
2023-01-22 19:04:11.795080: step: 46/470, loss: 0.04570697247982025
2023-01-22 19:04:12.680824: step: 48/470, loss: 0.19306838512420654
2023-01-22 19:04:13.429661: step: 50/470, loss: 0.01399903278797865
2023-01-22 19:04:14.135174: step: 52/470, loss: 0.12448009103536606
2023-01-22 19:04:14.992317: step: 54/470, loss: 0.08125516772270203
2023-01-22 19:04:15.786911: step: 56/470, loss: 0.0601322315633297
2023-01-22 19:04:16.605457: step: 58/470, loss: 0.5188689231872559
2023-01-22 19:04:17.299716: step: 60/470, loss: 0.03932400047779083
2023-01-22 19:04:17.994544: step: 62/470, loss: 0.027753813192248344
2023-01-22 19:04:18.741040: step: 64/470, loss: 0.019212109968066216
2023-01-22 19:04:19.406290: step: 66/470, loss: 0.003584251506254077
2023-01-22 19:04:20.241385: step: 68/470, loss: 0.09412702918052673
2023-01-22 19:04:20.919141: step: 70/470, loss: 0.038881633430719376
2023-01-22 19:04:21.655744: step: 72/470, loss: 0.0578327551484108
2023-01-22 19:04:22.364359: step: 74/470, loss: 0.23435544967651367
2023-01-22 19:04:23.157497: step: 76/470, loss: 0.034016791731119156
2023-01-22 19:04:23.794797: step: 78/470, loss: 0.011392496526241302
2023-01-22 19:04:24.648135: step: 80/470, loss: 0.07721582800149918
2023-01-22 19:04:25.345484: step: 82/470, loss: 0.025755221024155617
2023-01-22 19:04:26.031629: step: 84/470, loss: 0.03272271901369095
2023-01-22 19:04:26.630485: step: 86/470, loss: 0.013092340901494026
2023-01-22 19:04:27.448411: step: 88/470, loss: 0.057706430554389954
2023-01-22 19:04:28.179697: step: 90/470, loss: 0.05745483562350273
2023-01-22 19:04:28.945745: step: 92/470, loss: 0.04043126851320267
2023-01-22 19:04:29.658524: step: 94/470, loss: 0.09307193011045456
2023-01-22 19:04:30.371508: step: 96/470, loss: 0.10384157299995422
2023-01-22 19:04:31.144746: step: 98/470, loss: 0.058362387120723724
2023-01-22 19:04:31.871580: step: 100/470, loss: 0.08502303808927536
2023-01-22 19:04:32.701859: step: 102/470, loss: 0.1189383789896965
2023-01-22 19:04:33.371465: step: 104/470, loss: 0.005357891321182251
2023-01-22 19:04:34.144222: step: 106/470, loss: 0.07590699940919876
2023-01-22 19:04:34.860227: step: 108/470, loss: 0.010280979797244072
2023-01-22 19:04:35.594696: step: 110/470, loss: 0.033743537962436676
2023-01-22 19:04:36.286407: step: 112/470, loss: 0.053621165454387665
2023-01-22 19:04:36.993507: step: 114/470, loss: 0.2918620705604553
2023-01-22 19:04:37.772868: step: 116/470, loss: 0.08658783882856369
2023-01-22 19:04:38.492075: step: 118/470, loss: 0.0276590958237648
2023-01-22 19:04:39.189812: step: 120/470, loss: 0.08560670167207718
2023-01-22 19:04:39.917498: step: 122/470, loss: 0.3002013862133026
2023-01-22 19:04:40.625993: step: 124/470, loss: 0.2824411690235138
2023-01-22 19:04:41.361390: step: 126/470, loss: 0.03612075001001358
2023-01-22 19:04:42.034625: step: 128/470, loss: 0.06621766090393066
2023-01-22 19:04:42.725585: step: 130/470, loss: 0.039325080811977386
2023-01-22 19:04:43.423485: step: 132/470, loss: 0.042571116238832474
2023-01-22 19:04:44.212314: step: 134/470, loss: 0.09064992517232895
2023-01-22 19:04:44.917102: step: 136/470, loss: 0.08911306411027908
2023-01-22 19:04:45.733595: step: 138/470, loss: 0.241469144821167
2023-01-22 19:04:46.415562: step: 140/470, loss: 0.028448637574911118
2023-01-22 19:04:47.133195: step: 142/470, loss: 0.0016861435724422336
2023-01-22 19:04:47.909921: step: 144/470, loss: 0.04221523180603981
2023-01-22 19:04:48.542483: step: 146/470, loss: 0.18134230375289917
2023-01-22 19:04:49.310979: step: 148/470, loss: 0.030191145837306976
2023-01-22 19:04:50.114315: step: 150/470, loss: 0.16584885120391846
2023-01-22 19:04:50.923289: step: 152/470, loss: 0.08478162437677383
2023-01-22 19:04:51.689200: step: 154/470, loss: 0.08762053400278091
2023-01-22 19:04:52.409511: step: 156/470, loss: 0.11175291985273361
2023-01-22 19:04:53.092814: step: 158/470, loss: 0.3621843159198761
2023-01-22 19:04:53.789568: step: 160/470, loss: 0.1218324527144432
2023-01-22 19:04:54.471528: step: 162/470, loss: 0.043930042535066605
2023-01-22 19:04:55.180538: step: 164/470, loss: 0.07743663340806961
2023-01-22 19:04:55.832682: step: 166/470, loss: 0.015336059965193272
2023-01-22 19:04:56.599847: step: 168/470, loss: 0.04017908126115799
2023-01-22 19:04:57.343914: step: 170/470, loss: 0.21953128278255463
2023-01-22 19:04:57.964347: step: 172/470, loss: 0.04235304147005081
2023-01-22 19:04:58.773826: step: 174/470, loss: 0.12579070031642914
2023-01-22 19:04:59.561479: step: 176/470, loss: 0.07374074310064316
2023-01-22 19:05:00.303112: step: 178/470, loss: 0.08439971506595612
2023-01-22 19:05:00.971734: step: 180/470, loss: 0.15861716866493225
2023-01-22 19:05:01.688965: step: 182/470, loss: 0.01040814071893692
2023-01-22 19:05:02.376527: step: 184/470, loss: 0.027954377233982086
2023-01-22 19:05:03.121141: step: 186/470, loss: 0.04491977393627167
2023-01-22 19:05:03.826700: step: 188/470, loss: 0.05019805580377579
2023-01-22 19:05:04.516758: step: 190/470, loss: 0.0625576600432396
2023-01-22 19:05:05.216483: step: 192/470, loss: 0.06504880636930466
2023-01-22 19:05:06.040983: step: 194/470, loss: 0.1290799230337143
2023-01-22 19:05:06.996514: step: 196/470, loss: 0.08973461389541626
2023-01-22 19:05:07.716848: step: 198/470, loss: 0.09824441373348236
2023-01-22 19:05:08.548082: step: 200/470, loss: 0.08071193844079971
2023-01-22 19:05:09.300868: step: 202/470, loss: 0.1525980830192566
2023-01-22 19:05:10.071757: step: 204/470, loss: 0.0688774362206459
2023-01-22 19:05:10.753243: step: 206/470, loss: 0.034748729318380356
2023-01-22 19:05:11.406813: step: 208/470, loss: 0.05070429667830467
2023-01-22 19:05:12.126067: step: 210/470, loss: 0.07284100353717804
2023-01-22 19:05:12.959136: step: 212/470, loss: 0.18640294671058655
2023-01-22 19:05:13.710517: step: 214/470, loss: 0.04599619284272194
2023-01-22 19:05:14.417291: step: 216/470, loss: 0.045409638434648514
2023-01-22 19:05:15.173620: step: 218/470, loss: 0.1961684674024582
2023-01-22 19:05:15.835449: step: 220/470, loss: 0.040671225637197495
2023-01-22 19:05:16.778640: step: 222/470, loss: 0.1723230630159378
2023-01-22 19:05:17.474232: step: 224/470, loss: 0.011676449328660965
2023-01-22 19:05:18.231741: step: 226/470, loss: 0.04717397689819336
2023-01-22 19:05:19.029563: step: 228/470, loss: 0.08629091829061508
2023-01-22 19:05:19.809823: step: 230/470, loss: 0.06894738972187042
2023-01-22 19:05:20.457571: step: 232/470, loss: 0.747312605381012
2023-01-22 19:05:21.185801: step: 234/470, loss: 0.09399952739477158
2023-01-22 19:05:21.872685: step: 236/470, loss: 0.055615007877349854
2023-01-22 19:05:22.601906: step: 238/470, loss: 0.04675089567899704
2023-01-22 19:05:23.413529: step: 240/470, loss: 0.04450520500540733
2023-01-22 19:05:24.079454: step: 242/470, loss: 0.12249691784381866
2023-01-22 19:05:24.833674: step: 244/470, loss: 0.020723912864923477
2023-01-22 19:05:25.624008: step: 246/470, loss: 1.1003464460372925
2023-01-22 19:05:26.382019: step: 248/470, loss: 0.18243949115276337
2023-01-22 19:05:27.078262: step: 250/470, loss: 0.06836390495300293
2023-01-22 19:05:27.803392: step: 252/470, loss: 0.10224248468875885
2023-01-22 19:05:28.504118: step: 254/470, loss: 0.03016090951859951
2023-01-22 19:05:29.259652: step: 256/470, loss: 0.7845423221588135
2023-01-22 19:05:29.965357: step: 258/470, loss: 0.12435699254274368
2023-01-22 19:05:30.702792: step: 260/470, loss: 0.02161235734820366
2023-01-22 19:05:31.417284: step: 262/470, loss: 0.06350536644458771
2023-01-22 19:05:32.249031: step: 264/470, loss: 0.16371527314186096
2023-01-22 19:05:32.967628: step: 266/470, loss: 0.03186386078596115
2023-01-22 19:05:33.740325: step: 268/470, loss: 0.0583181194961071
2023-01-22 19:05:34.405227: step: 270/470, loss: 0.03716019168496132
2023-01-22 19:05:35.205305: step: 272/470, loss: 0.054880399256944656
2023-01-22 19:05:35.991333: step: 274/470, loss: 0.08905167132616043
2023-01-22 19:05:36.750810: step: 276/470, loss: 0.20153184235095978
2023-01-22 19:05:37.588608: step: 278/470, loss: 0.10790564119815826
2023-01-22 19:05:38.401880: step: 280/470, loss: 0.07056804746389389
2023-01-22 19:05:39.089929: step: 282/470, loss: 0.05816777050495148
2023-01-22 19:05:39.908515: step: 284/470, loss: 0.4308560788631439
2023-01-22 19:05:40.651840: step: 286/470, loss: 0.07634017616510391
2023-01-22 19:05:41.397753: step: 288/470, loss: 0.03175393491983414
2023-01-22 19:05:42.068443: step: 290/470, loss: 0.13919062912464142
2023-01-22 19:05:42.783329: step: 292/470, loss: 0.032145872712135315
2023-01-22 19:05:43.513315: step: 294/470, loss: 0.1720714420080185
2023-01-22 19:05:44.318561: step: 296/470, loss: 1.0381907224655151
2023-01-22 19:05:45.073004: step: 298/470, loss: 0.08752277493476868
2023-01-22 19:05:45.792619: step: 300/470, loss: 5.016946792602539
2023-01-22 19:05:46.577962: step: 302/470, loss: 0.048376813530921936
2023-01-22 19:05:47.395855: step: 304/470, loss: 0.020166104659438133
2023-01-22 19:05:48.137054: step: 306/470, loss: 0.3207864463329315
2023-01-22 19:05:48.895322: step: 308/470, loss: 0.42874202132225037
2023-01-22 19:05:49.656848: step: 310/470, loss: 0.04274129867553711
2023-01-22 19:05:50.371513: step: 312/470, loss: 0.012306938879191875
2023-01-22 19:05:51.140655: step: 314/470, loss: 0.03849383816123009
2023-01-22 19:05:51.920986: step: 316/470, loss: 0.6824967265129089
2023-01-22 19:05:52.622148: step: 318/470, loss: 0.055570270866155624
2023-01-22 19:05:53.330904: step: 320/470, loss: 0.06937985122203827
2023-01-22 19:05:54.095548: step: 322/470, loss: 0.044349320232868195
2023-01-22 19:05:54.849596: step: 324/470, loss: 0.09120985120534897
2023-01-22 19:05:55.529570: step: 326/470, loss: 0.025129251182079315
2023-01-22 19:05:56.235249: step: 328/470, loss: 0.06615206599235535
2023-01-22 19:05:56.948940: step: 330/470, loss: 0.13011448085308075
2023-01-22 19:05:57.705903: step: 332/470, loss: 1.3872214555740356
2023-01-22 19:05:58.432980: step: 334/470, loss: 0.03803999722003937
2023-01-22 19:05:59.202530: step: 336/470, loss: 0.0787554532289505
2023-01-22 19:05:59.925010: step: 338/470, loss: 0.05206383764743805
2023-01-22 19:06:00.645227: step: 340/470, loss: 0.08769537508487701
2023-01-22 19:06:01.453449: step: 342/470, loss: 0.28150492906570435
2023-01-22 19:06:02.221819: step: 344/470, loss: 0.3160443902015686
2023-01-22 19:06:03.032008: step: 346/470, loss: 0.01590467244386673
2023-01-22 19:06:03.797909: step: 348/470, loss: 0.08347859978675842
2023-01-22 19:06:04.467103: step: 350/470, loss: 0.18649937212467194
2023-01-22 19:06:05.159595: step: 352/470, loss: 0.06714587658643723
2023-01-22 19:06:05.910542: step: 354/470, loss: 0.2771860361099243
2023-01-22 19:06:06.652262: step: 356/470, loss: 0.10782112181186676
2023-01-22 19:06:07.381720: step: 358/470, loss: 0.04154413565993309
2023-01-22 19:06:08.184419: step: 360/470, loss: 0.16717395186424255
2023-01-22 19:06:08.859805: step: 362/470, loss: 0.06858609616756439
2023-01-22 19:06:09.616215: step: 364/470, loss: 0.09976839274168015
2023-01-22 19:06:10.275705: step: 366/470, loss: 0.04712813347578049
2023-01-22 19:06:10.982888: step: 368/470, loss: 0.004059855360537767
2023-01-22 19:06:11.715520: step: 370/470, loss: 0.04966858774423599
2023-01-22 19:06:12.466114: step: 372/470, loss: 0.05597155913710594
2023-01-22 19:06:13.212287: step: 374/470, loss: 0.03586982935667038
2023-01-22 19:06:13.916445: step: 376/470, loss: 0.07770383358001709
2023-01-22 19:06:14.696604: step: 378/470, loss: 2.023169994354248
2023-01-22 19:06:15.488836: step: 380/470, loss: 0.025740159675478935
2023-01-22 19:06:16.221422: step: 382/470, loss: 0.09446519613265991
2023-01-22 19:06:17.014021: step: 384/470, loss: 0.12673798203468323
2023-01-22 19:06:17.808021: step: 386/470, loss: 0.1375817209482193
2023-01-22 19:06:18.484295: step: 388/470, loss: 0.16045433282852173
2023-01-22 19:06:19.237270: step: 390/470, loss: 0.06736897677183151
2023-01-22 19:06:19.933443: step: 392/470, loss: 0.02480211667716503
2023-01-22 19:06:20.649135: step: 394/470, loss: 0.030097251757979393
2023-01-22 19:06:21.444454: step: 396/470, loss: 0.13856565952301025
2023-01-22 19:06:22.177879: step: 398/470, loss: 0.10427145659923553
2023-01-22 19:06:22.941286: step: 400/470, loss: 0.10263396799564362
2023-01-22 19:06:23.695675: step: 402/470, loss: 0.06050116941332817
2023-01-22 19:06:24.458633: step: 404/470, loss: 0.13885028660297394
2023-01-22 19:06:25.229784: step: 406/470, loss: 0.07277980446815491
2023-01-22 19:06:25.947545: step: 408/470, loss: 3.110565662384033
2023-01-22 19:06:26.639680: step: 410/470, loss: 0.10733214020729065
2023-01-22 19:06:27.293723: step: 412/470, loss: 0.12563331425189972
2023-01-22 19:06:28.000730: step: 414/470, loss: 0.04333885759115219
2023-01-22 19:06:28.848990: step: 416/470, loss: 0.0657099261879921
2023-01-22 19:06:29.675410: step: 418/470, loss: 0.07604394853115082
2023-01-22 19:06:30.401390: step: 420/470, loss: 0.06309117376804352
2023-01-22 19:06:31.149521: step: 422/470, loss: 0.07451029866933823
2023-01-22 19:06:31.929847: step: 424/470, loss: 0.2557286024093628
2023-01-22 19:06:32.639672: step: 426/470, loss: 0.021574387326836586
2023-01-22 19:06:33.362139: step: 428/470, loss: 0.16285766661167145
2023-01-22 19:06:34.135509: step: 430/470, loss: 0.13354262709617615
2023-01-22 19:06:34.783344: step: 432/470, loss: 0.01653607189655304
2023-01-22 19:06:35.460648: step: 434/470, loss: 0.052297040820121765
2023-01-22 19:06:36.203474: step: 436/470, loss: 0.0829712525010109
2023-01-22 19:06:37.026703: step: 438/470, loss: 0.06701302528381348
2023-01-22 19:06:37.691044: step: 440/470, loss: 0.08787357807159424
2023-01-22 19:06:38.343410: step: 442/470, loss: 0.013717160560190678
2023-01-22 19:06:39.055271: step: 444/470, loss: 0.028695937246084213
2023-01-22 19:06:39.808181: step: 446/470, loss: 0.16002628207206726
2023-01-22 19:06:40.520682: step: 448/470, loss: 0.08444713056087494
2023-01-22 19:06:41.205738: step: 450/470, loss: 0.02779926173388958
2023-01-22 19:06:41.888386: step: 452/470, loss: 0.07570282369852066
2023-01-22 19:06:42.623841: step: 454/470, loss: 0.053751636296510696
2023-01-22 19:06:43.350810: step: 456/470, loss: 0.20872299373149872
2023-01-22 19:06:44.113273: step: 458/470, loss: 0.02030782587826252
2023-01-22 19:06:44.726424: step: 460/470, loss: 0.10540497303009033
2023-01-22 19:06:45.449892: step: 462/470, loss: 0.07553648203611374
2023-01-22 19:06:46.237498: step: 464/470, loss: 0.03500121459364891
2023-01-22 19:06:47.000165: step: 466/470, loss: 1.096193790435791
2023-01-22 19:06:47.697969: step: 468/470, loss: 0.020026426762342453
2023-01-22 19:06:48.486785: step: 470/470, loss: 0.012369709089398384
2023-01-22 19:06:49.186195: step: 472/470, loss: 0.17361843585968018
2023-01-22 19:06:49.953340: step: 474/470, loss: 0.07756824046373367
2023-01-22 19:06:50.711591: step: 476/470, loss: 0.5463083386421204
2023-01-22 19:06:51.447171: step: 478/470, loss: 0.46463775634765625
2023-01-22 19:06:52.154487: step: 480/470, loss: 0.05993659421801567
2023-01-22 19:06:52.812976: step: 482/470, loss: 0.469533234834671
2023-01-22 19:06:53.532750: step: 484/470, loss: 0.0658133402466774
2023-01-22 19:06:54.278722: step: 486/470, loss: 0.03351491689682007
2023-01-22 19:06:55.093811: step: 488/470, loss: 1.313239336013794
2023-01-22 19:06:55.763734: step: 490/470, loss: 0.03160230442881584
2023-01-22 19:06:56.496400: step: 492/470, loss: 0.008728746324777603
2023-01-22 19:06:57.221005: step: 494/470, loss: 0.05184914916753769
2023-01-22 19:06:57.967761: step: 496/470, loss: 0.12218936532735825
2023-01-22 19:06:58.674406: step: 498/470, loss: 0.014416754245758057
2023-01-22 19:06:59.379342: step: 500/470, loss: 0.0723162293434143
2023-01-22 19:07:00.019659: step: 502/470, loss: 0.09827473759651184
2023-01-22 19:07:00.779721: step: 504/470, loss: 0.018960921093821526
2023-01-22 19:07:01.567615: step: 506/470, loss: 0.11824572086334229
2023-01-22 19:07:02.299971: step: 508/470, loss: 0.22170805931091309
2023-01-22 19:07:03.083520: step: 510/470, loss: 0.02900109253823757
2023-01-22 19:07:03.888107: step: 512/470, loss: 0.044659458100795746
2023-01-22 19:07:04.680215: step: 514/470, loss: 0.0988159105181694
2023-01-22 19:07:05.384235: step: 516/470, loss: 0.08702954649925232
2023-01-22 19:07:06.114092: step: 518/470, loss: 0.07674989104270935
2023-01-22 19:07:06.852481: step: 520/470, loss: 0.9716522693634033
2023-01-22 19:07:07.559142: step: 522/470, loss: 0.036884721368551254
2023-01-22 19:07:08.309488: step: 524/470, loss: 0.03706406056880951
2023-01-22 19:07:09.070478: step: 526/470, loss: 0.10544019937515259
2023-01-22 19:07:09.868265: step: 528/470, loss: 0.32073140144348145
2023-01-22 19:07:10.628726: step: 530/470, loss: 0.06953152269124985
2023-01-22 19:07:11.406346: step: 532/470, loss: 0.03154062107205391
2023-01-22 19:07:12.171433: step: 534/470, loss: 0.05240052565932274
2023-01-22 19:07:12.966667: step: 536/470, loss: 0.07844150811433792
2023-01-22 19:07:13.789283: step: 538/470, loss: 0.040399134159088135
2023-01-22 19:07:14.501669: step: 540/470, loss: 0.0194169282913208
2023-01-22 19:07:15.256430: step: 542/470, loss: 0.05020745098590851
2023-01-22 19:07:15.999727: step: 544/470, loss: 0.07957773655653
2023-01-22 19:07:16.756400: step: 546/470, loss: 0.08744139224290848
2023-01-22 19:07:17.513358: step: 548/470, loss: 0.026095112785696983
2023-01-22 19:07:18.251343: step: 550/470, loss: 0.2702293395996094
2023-01-22 19:07:18.981359: step: 552/470, loss: 0.10846442729234695
2023-01-22 19:07:19.748205: step: 554/470, loss: 0.3181234300136566
2023-01-22 19:07:20.485157: step: 556/470, loss: 0.0786203145980835
2023-01-22 19:07:21.206613: step: 558/470, loss: 0.0033358277287334204
2023-01-22 19:07:21.941326: step: 560/470, loss: 0.07501276582479477
2023-01-22 19:07:22.748031: step: 562/470, loss: 0.05452758073806763
2023-01-22 19:07:23.455203: step: 564/470, loss: 0.09366501122713089
2023-01-22 19:07:24.148395: step: 566/470, loss: 0.014939019456505775
2023-01-22 19:07:24.798024: step: 568/470, loss: 0.06117936596274376
2023-01-22 19:07:25.564547: step: 570/470, loss: 0.21456541121006012
2023-01-22 19:07:26.323650: step: 572/470, loss: 0.06580285727977753
2023-01-22 19:07:27.092935: step: 574/470, loss: 0.16548193991184235
2023-01-22 19:07:27.826145: step: 576/470, loss: 0.06566378474235535
2023-01-22 19:07:28.525779: step: 578/470, loss: 0.0672176256775856
2023-01-22 19:07:29.318793: step: 580/470, loss: 0.1079394519329071
2023-01-22 19:07:30.078757: step: 582/470, loss: 0.08780059963464737
2023-01-22 19:07:30.860589: step: 584/470, loss: 0.10914134234189987
2023-01-22 19:07:31.508178: step: 586/470, loss: 0.02274099551141262
2023-01-22 19:07:32.170904: step: 588/470, loss: 0.0968480110168457
2023-01-22 19:07:32.867776: step: 590/470, loss: 0.10516564548015594
2023-01-22 19:07:33.631183: step: 592/470, loss: 0.03458961844444275
2023-01-22 19:07:34.410615: step: 594/470, loss: 0.0399974063038826
2023-01-22 19:07:35.103992: step: 596/470, loss: 0.10185714811086655
2023-01-22 19:07:35.875696: step: 598/470, loss: 0.0844685435295105
2023-01-22 19:07:36.645940: step: 600/470, loss: 0.24795423448085785
2023-01-22 19:07:37.480918: step: 602/470, loss: 0.0773269459605217
2023-01-22 19:07:38.314612: step: 604/470, loss: 0.534523606300354
2023-01-22 19:07:39.161028: step: 606/470, loss: 0.09742405265569687
2023-01-22 19:07:39.961789: step: 608/470, loss: 0.06567207723855972
2023-01-22 19:07:40.772580: step: 610/470, loss: 0.14598585665225983
2023-01-22 19:07:41.544598: step: 612/470, loss: 0.1488225907087326
2023-01-22 19:07:42.285905: step: 614/470, loss: 0.038161151111125946
2023-01-22 19:07:42.996190: step: 616/470, loss: 0.05915544927120209
2023-01-22 19:07:43.756538: step: 618/470, loss: 0.1564996987581253
2023-01-22 19:07:44.515739: step: 620/470, loss: 0.05826148763298988
2023-01-22 19:07:45.272363: step: 622/470, loss: 0.011290734633803368
2023-01-22 19:07:46.029702: step: 624/470, loss: 0.09952137619256973
2023-01-22 19:07:46.693843: step: 626/470, loss: 0.030536210164427757
2023-01-22 19:07:47.429867: step: 628/470, loss: 0.10485729575157166
2023-01-22 19:07:48.249840: step: 630/470, loss: 0.05025089532136917
2023-01-22 19:07:49.043414: step: 632/470, loss: 0.022319285199046135
2023-01-22 19:07:49.836509: step: 634/470, loss: 0.24370166659355164
2023-01-22 19:07:50.578873: step: 636/470, loss: 0.060697052627801895
2023-01-22 19:07:51.312929: step: 638/470, loss: 0.11710238456726074
2023-01-22 19:07:52.032803: step: 640/470, loss: 0.028134386986494064
2023-01-22 19:07:52.790706: step: 642/470, loss: 0.1157449260354042
2023-01-22 19:07:53.554281: step: 644/470, loss: 0.5257167816162109
2023-01-22 19:07:54.253157: step: 646/470, loss: 0.09944950044155121
2023-01-22 19:07:55.039011: step: 648/470, loss: 0.019325170665979385
2023-01-22 19:07:55.715894: step: 650/470, loss: 0.2056947946548462
2023-01-22 19:07:56.465589: step: 652/470, loss: 0.09543462097644806
2023-01-22 19:07:57.282836: step: 654/470, loss: 0.06548590958118439
2023-01-22 19:07:57.982939: step: 656/470, loss: 0.06484925746917725
2023-01-22 19:07:58.701078: step: 658/470, loss: 0.3009560704231262
2023-01-22 19:07:59.449957: step: 660/470, loss: 0.08352717012166977
2023-01-22 19:08:00.179511: step: 662/470, loss: 0.0790558010339737
2023-01-22 19:08:00.950468: step: 664/470, loss: 0.18998511135578156
2023-01-22 19:08:01.824797: step: 666/470, loss: 0.15023095905780792
2023-01-22 19:08:02.526702: step: 668/470, loss: 0.14798638224601746
2023-01-22 19:08:03.393704: step: 670/470, loss: 0.03329675644636154
2023-01-22 19:08:04.129336: step: 672/470, loss: 0.0386032834649086
2023-01-22 19:08:04.831245: step: 674/470, loss: 0.373938649892807
2023-01-22 19:08:05.548064: step: 676/470, loss: 0.03455100581049919
2023-01-22 19:08:06.306668: step: 678/470, loss: 0.05225971341133118
2023-01-22 19:08:07.045314: step: 680/470, loss: 0.9394486546516418
2023-01-22 19:08:07.753272: step: 682/470, loss: 0.07498309016227722
2023-01-22 19:08:08.459471: step: 684/470, loss: 0.04044778645038605
2023-01-22 19:08:09.375310: step: 686/470, loss: 0.04468849301338196
2023-01-22 19:08:10.059632: step: 688/470, loss: 0.038324546068906784
2023-01-22 19:08:10.730048: step: 690/470, loss: 0.05637683719396591
2023-01-22 19:08:11.404373: step: 692/470, loss: 0.02472817339003086
2023-01-22 19:08:12.070507: step: 694/470, loss: 0.096453458070755
2023-01-22 19:08:12.822497: step: 696/470, loss: 0.03920508921146393
2023-01-22 19:08:13.464671: step: 698/470, loss: 0.007813246920704842
2023-01-22 19:08:14.201472: step: 700/470, loss: 0.04346537962555885
2023-01-22 19:08:14.973017: step: 702/470, loss: 0.038816504180431366
2023-01-22 19:08:15.637868: step: 704/470, loss: 0.030292358249425888
2023-01-22 19:08:16.347375: step: 706/470, loss: 0.016416076570749283
2023-01-22 19:08:17.057420: step: 708/470, loss: 0.2907312214374542
2023-01-22 19:08:17.761272: step: 710/470, loss: 0.06063879653811455
2023-01-22 19:08:18.568904: step: 712/470, loss: 0.041221536695957184
2023-01-22 19:08:19.323360: step: 714/470, loss: 0.07422397285699844
2023-01-22 19:08:20.022246: step: 716/470, loss: 0.040925491601228714
2023-01-22 19:08:20.702766: step: 718/470, loss: 0.806887149810791
2023-01-22 19:08:21.473154: step: 720/470, loss: 0.036033619195222855
2023-01-22 19:08:22.148998: step: 722/470, loss: 0.024567672982811928
2023-01-22 19:08:22.965480: step: 724/470, loss: 0.12131427973508835
2023-01-22 19:08:23.656598: step: 726/470, loss: 0.10178028047084808
2023-01-22 19:08:24.378051: step: 728/470, loss: 0.055488470941782
2023-01-22 19:08:25.044679: step: 730/470, loss: 0.0426790677011013
2023-01-22 19:08:25.823919: step: 732/470, loss: 0.13151328265666962
2023-01-22 19:08:26.513277: step: 734/470, loss: 0.1700894981622696
2023-01-22 19:08:27.264534: step: 736/470, loss: 0.0167455542832613
2023-01-22 19:08:28.012903: step: 738/470, loss: 0.041223183274269104
2023-01-22 19:08:28.624866: step: 740/470, loss: 1.210181713104248
2023-01-22 19:08:29.306604: step: 742/470, loss: 0.019830353558063507
2023-01-22 19:08:30.016490: step: 744/470, loss: 0.0577569454908371
2023-01-22 19:08:30.886048: step: 746/470, loss: 0.15902186930179596
2023-01-22 19:08:31.658943: step: 748/470, loss: 0.06879295408725739
2023-01-22 19:08:32.369615: step: 750/470, loss: 0.2863670587539673
2023-01-22 19:08:33.155089: step: 752/470, loss: 0.0369873046875
2023-01-22 19:08:33.939661: step: 754/470, loss: 0.06788759678602219
2023-01-22 19:08:34.725368: step: 756/470, loss: 0.06014617532491684
2023-01-22 19:08:35.510540: step: 758/470, loss: 0.12267798185348511
2023-01-22 19:08:36.293872: step: 760/470, loss: 2.288891553878784
2023-01-22 19:08:37.064152: step: 762/470, loss: 0.09062454104423523
2023-01-22 19:08:37.774315: step: 764/470, loss: 0.09816782921552658
2023-01-22 19:08:38.522388: step: 766/470, loss: 0.028900889679789543
2023-01-22 19:08:39.206902: step: 768/470, loss: 0.1546131819486618
2023-01-22 19:08:40.061512: step: 770/470, loss: 0.06838797777891159
2023-01-22 19:08:40.865874: step: 772/470, loss: 0.1268923431634903
2023-01-22 19:08:41.665679: step: 774/470, loss: 0.038736216723918915
2023-01-22 19:08:42.407040: step: 776/470, loss: 0.09154653549194336
2023-01-22 19:08:43.179909: step: 778/470, loss: 0.17325304448604584
2023-01-22 19:08:43.869201: step: 780/470, loss: 0.04542065039277077
2023-01-22 19:08:44.542421: step: 782/470, loss: 0.045644138008356094
2023-01-22 19:08:45.252116: step: 784/470, loss: 0.19901789724826813
2023-01-22 19:08:46.070231: step: 786/470, loss: 0.07332056015729904
2023-01-22 19:08:46.707055: step: 788/470, loss: 0.017355095595121384
2023-01-22 19:08:47.401390: step: 790/470, loss: 0.047633036971092224
2023-01-22 19:08:48.100134: step: 792/470, loss: 0.09777167439460754
2023-01-22 19:08:48.895276: step: 794/470, loss: 0.14233334362506866
2023-01-22 19:08:49.636366: step: 796/470, loss: 0.094623863697052
2023-01-22 19:08:50.378238: step: 798/470, loss: 0.04363381117582321
2023-01-22 19:08:51.042221: step: 800/470, loss: 0.03856759890913963
2023-01-22 19:08:51.828415: step: 802/470, loss: 0.047487128525972366
2023-01-22 19:08:52.611339: step: 804/470, loss: 0.08930141478776932
2023-01-22 19:08:53.493459: step: 806/470, loss: 0.05340230092406273
2023-01-22 19:08:54.184931: step: 808/470, loss: 0.02979603409767151
2023-01-22 19:08:54.912911: step: 810/470, loss: 0.07141705602407455
2023-01-22 19:08:55.614982: step: 812/470, loss: 0.05251197889447212
2023-01-22 19:08:56.313686: step: 814/470, loss: 0.02951197512447834
2023-01-22 19:08:57.051577: step: 816/470, loss: 0.016900768503546715
2023-01-22 19:08:57.779693: step: 818/470, loss: 0.028845131397247314
2023-01-22 19:08:58.598208: step: 820/470, loss: 0.10073421150445938
2023-01-22 19:08:59.334840: step: 822/470, loss: 0.2575160264968872
2023-01-22 19:09:00.103293: step: 824/470, loss: 2.035039186477661
2023-01-22 19:09:00.893444: step: 826/470, loss: 0.03579817712306976
2023-01-22 19:09:01.637838: step: 828/470, loss: 0.04633788764476776
2023-01-22 19:09:02.400988: step: 830/470, loss: 0.4512938857078552
2023-01-22 19:09:03.167212: step: 832/470, loss: 0.06470350176095963
2023-01-22 19:09:03.861469: step: 834/470, loss: 0.07506409287452698
2023-01-22 19:09:04.543150: step: 836/470, loss: 0.026313841342926025
2023-01-22 19:09:05.304371: step: 838/470, loss: 0.020502228289842606
2023-01-22 19:09:06.046597: step: 840/470, loss: 0.7991170883178711
2023-01-22 19:09:06.770055: step: 842/470, loss: 0.1815629005432129
2023-01-22 19:09:07.531451: step: 844/470, loss: 0.08853790909051895
2023-01-22 19:09:08.283476: step: 846/470, loss: 0.05072927847504616
2023-01-22 19:09:09.023131: step: 848/470, loss: 0.20891301333904266
2023-01-22 19:09:09.759023: step: 850/470, loss: 0.09082869440317154
2023-01-22 19:09:10.538530: step: 852/470, loss: 0.032474786043167114
2023-01-22 19:09:11.319501: step: 854/470, loss: 0.18315306305885315
2023-01-22 19:09:12.084884: step: 856/470, loss: 0.16794231534004211
2023-01-22 19:09:12.853077: step: 858/470, loss: 0.03778474032878876
2023-01-22 19:09:13.556912: step: 860/470, loss: 0.07641467452049255
2023-01-22 19:09:14.356981: step: 862/470, loss: 0.11089635640382767
2023-01-22 19:09:15.057241: step: 864/470, loss: 0.2194468230009079
2023-01-22 19:09:15.855921: step: 866/470, loss: 0.028484074398875237
2023-01-22 19:09:16.633220: step: 868/470, loss: 0.19141916930675507
2023-01-22 19:09:17.341543: step: 870/470, loss: 0.23752793669700623
2023-01-22 19:09:18.072870: step: 872/470, loss: 0.08412695676088333
2023-01-22 19:09:18.807234: step: 874/470, loss: 0.055731259286403656
2023-01-22 19:09:19.565926: step: 876/470, loss: 0.05968417599797249
2023-01-22 19:09:20.275428: step: 878/470, loss: 0.14127624034881592
2023-01-22 19:09:21.054171: step: 880/470, loss: 0.0697111114859581
2023-01-22 19:09:21.783220: step: 882/470, loss: 0.21765391528606415
2023-01-22 19:09:22.476151: step: 884/470, loss: 0.02833917923271656
2023-01-22 19:09:23.196299: step: 886/470, loss: 0.27807044982910156
2023-01-22 19:09:23.920884: step: 888/470, loss: 0.25375717878341675
2023-01-22 19:09:24.735764: step: 890/470, loss: 0.08540809154510498
2023-01-22 19:09:25.500382: step: 892/470, loss: 0.04102737829089165
2023-01-22 19:09:26.176778: step: 894/470, loss: 0.2897949516773224
2023-01-22 19:09:26.890883: step: 896/470, loss: 0.04384997487068176
2023-01-22 19:09:27.644793: step: 898/470, loss: 0.06272339075803757
2023-01-22 19:09:28.418865: step: 900/470, loss: 0.13991448283195496
2023-01-22 19:09:29.161226: step: 902/470, loss: 0.03492581099271774
2023-01-22 19:09:29.827744: step: 904/470, loss: 4.457045078277588
2023-01-22 19:09:30.620353: step: 906/470, loss: 0.05300872027873993
2023-01-22 19:09:31.464454: step: 908/470, loss: 0.17280398309230804
2023-01-22 19:09:32.168853: step: 910/470, loss: 0.12466652691364288
2023-01-22 19:09:32.852085: step: 912/470, loss: 0.05572166293859482
2023-01-22 19:09:33.619979: step: 914/470, loss: 0.11022337526082993
2023-01-22 19:09:34.394600: step: 916/470, loss: 0.15707486867904663
2023-01-22 19:09:35.112869: step: 918/470, loss: 0.03694531321525574
2023-01-22 19:09:35.829238: step: 920/470, loss: 0.05348490923643112
2023-01-22 19:09:36.605179: step: 922/470, loss: 0.04882257059216499
2023-01-22 19:09:37.306532: step: 924/470, loss: 0.08925341814756393
2023-01-22 19:09:38.005130: step: 926/470, loss: 0.06599713861942291
2023-01-22 19:09:38.720954: step: 928/470, loss: 0.024995747953653336
2023-01-22 19:09:39.449474: step: 930/470, loss: 0.1284753382205963
2023-01-22 19:09:40.212663: step: 932/470, loss: 0.5296043157577515
2023-01-22 19:09:41.002814: step: 934/470, loss: 0.07279351353645325
2023-01-22 19:09:41.685320: step: 936/470, loss: 0.23871983587741852
2023-01-22 19:09:42.419514: step: 938/470, loss: 0.14109857380390167
2023-01-22 19:09:43.147632: step: 940/470, loss: 0.015602878294885159
2023-01-22 19:09:43.964516: step: 942/470, loss: 0.18439671397209167
==================================================
Loss: 0.165
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3114274465080917, 'r': 0.3297467080673912, 'f1': 0.32032537355118}, 'combined': 0.23602922261665896, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3446986847487509, 'r': 0.3675461480029909, 'f1': 0.35575596473371784}, 'combined': 0.24779022419263932, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2966384955078422, 'r': 0.3360401932033811, 'f1': 0.3151124231640246}, 'combined': 0.23218810127875494, 'epoch': 18}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33645058944485723, 'r': 0.372002524928944, 'f1': 0.3533345150100645}, 'combined': 0.24610364229556733, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20599489795918366, 'r': 0.32959183673469383, 'f1': 0.25353218210361067}, 'combined': 0.16902145473574043, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4375, 'r': 0.3017241379310345, 'f1': 0.3571428571428571}, 'combined': 0.23809523809523805, 'epoch': 18}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 19
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 19:12:30.893821: step: 2/470, loss: 0.0112921092659235
2023-01-22 19:12:31.675931: step: 4/470, loss: 0.07280120998620987
2023-01-22 19:12:32.476235: step: 6/470, loss: 0.003984284121543169
2023-01-22 19:12:33.348567: step: 8/470, loss: 0.07252970337867737
2023-01-22 19:12:34.135689: step: 10/470, loss: 0.3424142301082611
2023-01-22 19:12:34.920654: step: 12/470, loss: 0.0439504012465477
2023-01-22 19:12:35.664424: step: 14/470, loss: 0.053510237485170364
2023-01-22 19:12:36.419977: step: 16/470, loss: 0.11842609941959381
2023-01-22 19:12:37.158320: step: 18/470, loss: 0.04970640316605568
2023-01-22 19:12:37.919374: step: 20/470, loss: 0.026285069063305855
2023-01-22 19:12:38.647001: step: 22/470, loss: 0.7065211534500122
2023-01-22 19:12:39.417989: step: 24/470, loss: 0.010196846909821033
2023-01-22 19:12:40.165212: step: 26/470, loss: 0.260796457529068
2023-01-22 19:12:40.882193: step: 28/470, loss: 0.067171610891819
2023-01-22 19:12:41.651769: step: 30/470, loss: 0.030061058700084686
2023-01-22 19:12:42.329689: step: 32/470, loss: 0.06347762048244476
2023-01-22 19:12:43.078023: step: 34/470, loss: 0.029726915061473846
2023-01-22 19:12:43.811345: step: 36/470, loss: 0.03759774938225746
2023-01-22 19:12:44.616354: step: 38/470, loss: 0.029163209721446037
2023-01-22 19:12:45.312509: step: 40/470, loss: 0.3536049723625183
2023-01-22 19:12:46.068544: step: 42/470, loss: 0.01684482768177986
2023-01-22 19:12:46.784397: step: 44/470, loss: 0.0455920547246933
2023-01-22 19:12:47.456523: step: 46/470, loss: 0.1695699840784073
2023-01-22 19:12:48.195768: step: 48/470, loss: 0.03408074751496315
2023-01-22 19:12:48.913095: step: 50/470, loss: 0.07696592807769775
2023-01-22 19:12:49.673392: step: 52/470, loss: 0.02807328663766384
2023-01-22 19:12:50.344801: step: 54/470, loss: 0.017425425350666046
2023-01-22 19:12:51.127744: step: 56/470, loss: 0.09263166040182114
2023-01-22 19:12:51.922949: step: 58/470, loss: 0.0654522031545639
2023-01-22 19:12:52.606907: step: 60/470, loss: 0.04144338145852089
2023-01-22 19:12:53.485795: step: 62/470, loss: 0.06384022533893585
2023-01-22 19:12:54.294509: step: 64/470, loss: 0.034149911254644394
2023-01-22 19:12:55.014853: step: 66/470, loss: 0.05268741771578789
2023-01-22 19:12:55.788785: step: 68/470, loss: 0.07051324099302292
2023-01-22 19:12:56.540377: step: 70/470, loss: 0.046795789152383804
2023-01-22 19:12:57.311847: step: 72/470, loss: 0.0369303859770298
2023-01-22 19:12:57.993332: step: 74/470, loss: 0.1018744483590126
2023-01-22 19:12:58.666147: step: 76/470, loss: 0.012132197618484497
2023-01-22 19:12:59.372996: step: 78/470, loss: 0.023422876372933388
2023-01-22 19:13:00.141664: step: 80/470, loss: 0.04017108678817749
2023-01-22 19:13:00.963622: step: 82/470, loss: 0.1267279088497162
2023-01-22 19:13:01.699571: step: 84/470, loss: 0.09292332828044891
2023-01-22 19:13:02.422211: step: 86/470, loss: 0.013976332731544971
2023-01-22 19:13:03.158829: step: 88/470, loss: 0.060683172196149826
2023-01-22 19:13:04.002265: step: 90/470, loss: 0.025250034406781197
2023-01-22 19:13:04.730751: step: 92/470, loss: 0.7996619343757629
2023-01-22 19:13:05.452795: step: 94/470, loss: 0.47412997484207153
2023-01-22 19:13:06.118976: step: 96/470, loss: 0.048665400594472885
2023-01-22 19:13:06.910661: step: 98/470, loss: 0.1110273227095604
2023-01-22 19:13:07.589940: step: 100/470, loss: 0.00958691630512476
2023-01-22 19:13:08.399654: step: 102/470, loss: 0.08475369215011597
2023-01-22 19:13:09.160473: step: 104/470, loss: 0.1207355335354805
2023-01-22 19:13:09.951456: step: 106/470, loss: 0.15649910271167755
2023-01-22 19:13:10.719027: step: 108/470, loss: 0.05611814185976982
2023-01-22 19:13:11.474032: step: 110/470, loss: 0.05005284771323204
2023-01-22 19:13:12.222379: step: 112/470, loss: 0.060722410678863525
2023-01-22 19:13:12.951564: step: 114/470, loss: 0.3491228520870209
2023-01-22 19:13:13.682148: step: 116/470, loss: 0.03365219384431839
2023-01-22 19:13:14.452560: step: 118/470, loss: 0.18201521039009094
2023-01-22 19:13:15.217413: step: 120/470, loss: 0.09609755873680115
2023-01-22 19:13:15.997453: step: 122/470, loss: 0.0444912314414978
2023-01-22 19:13:16.826399: step: 124/470, loss: 0.02517714537680149
2023-01-22 19:13:17.586517: step: 126/470, loss: 0.07190493494272232
2023-01-22 19:13:18.320897: step: 128/470, loss: 0.06636962294578552
2023-01-22 19:13:19.082858: step: 130/470, loss: 0.06659968942403793
2023-01-22 19:13:19.834637: step: 132/470, loss: 0.36475393176078796
2023-01-22 19:13:20.506171: step: 134/470, loss: 0.15585525333881378
2023-01-22 19:13:21.195759: step: 136/470, loss: 0.02720065414905548
2023-01-22 19:13:21.904542: step: 138/470, loss: 0.0021766903810203075
2023-01-22 19:13:22.782585: step: 140/470, loss: 0.023098669946193695
2023-01-22 19:13:23.524983: step: 142/470, loss: 0.09725446254014969
2023-01-22 19:13:24.228743: step: 144/470, loss: 0.0761142149567604
2023-01-22 19:13:24.984217: step: 146/470, loss: 0.03910772502422333
2023-01-22 19:13:25.677670: step: 148/470, loss: 0.045949943363666534
2023-01-22 19:13:26.371002: step: 150/470, loss: 0.18881461024284363
2023-01-22 19:13:27.127582: step: 152/470, loss: 0.08599704504013062
2023-01-22 19:13:27.843321: step: 154/470, loss: 0.09139792621135712
2023-01-22 19:13:28.568619: step: 156/470, loss: 0.023786649107933044
2023-01-22 19:13:29.299185: step: 158/470, loss: 0.0356992706656456
2023-01-22 19:13:30.051100: step: 160/470, loss: 0.20965898036956787
2023-01-22 19:13:30.763749: step: 162/470, loss: 0.05315234512090683
2023-01-22 19:13:31.560525: step: 164/470, loss: 0.09431155771017075
2023-01-22 19:13:32.257056: step: 166/470, loss: 0.08751388639211655
2023-01-22 19:13:33.041936: step: 168/470, loss: 0.035697486251592636
2023-01-22 19:13:33.858495: step: 170/470, loss: 0.08968447893857956
2023-01-22 19:13:34.672867: step: 172/470, loss: 0.04234302416443825
2023-01-22 19:13:35.453973: step: 174/470, loss: 0.03975873067975044
2023-01-22 19:13:36.369268: step: 176/470, loss: 0.03170318529009819
2023-01-22 19:13:37.080014: step: 178/470, loss: 0.032391466200351715
2023-01-22 19:13:37.828408: step: 180/470, loss: 0.0803714469075203
2023-01-22 19:13:38.537406: step: 182/470, loss: 0.06298526376485825
2023-01-22 19:13:39.271926: step: 184/470, loss: 0.10829924792051315
2023-01-22 19:13:40.133905: step: 186/470, loss: 0.046199098229408264
2023-01-22 19:13:40.979174: step: 188/470, loss: 8.178955078125
2023-01-22 19:13:41.706679: step: 190/470, loss: 0.04769464582204819
2023-01-22 19:13:42.443156: step: 192/470, loss: 0.0582704059779644
2023-01-22 19:13:43.230410: step: 194/470, loss: 0.08901997655630112
2023-01-22 19:13:43.927487: step: 196/470, loss: 0.0373103991150856
2023-01-22 19:13:44.628952: step: 198/470, loss: 0.028127502650022507
2023-01-22 19:13:45.404852: step: 200/470, loss: 0.07751333713531494
2023-01-22 19:13:46.160375: step: 202/470, loss: 0.04906482994556427
2023-01-22 19:13:46.829792: step: 204/470, loss: 0.04419788345694542
2023-01-22 19:13:47.609277: step: 206/470, loss: 0.044183794409036636
2023-01-22 19:13:48.368459: step: 208/470, loss: 0.026250679045915604
2023-01-22 19:13:49.125379: step: 210/470, loss: 0.03679383546113968
2023-01-22 19:13:49.871537: step: 212/470, loss: 0.04583572596311569
2023-01-22 19:13:50.744389: step: 214/470, loss: 0.07375669479370117
2023-01-22 19:13:51.523738: step: 216/470, loss: 0.2075904905796051
2023-01-22 19:13:52.302026: step: 218/470, loss: 0.050344791263341904
2023-01-22 19:13:53.012125: step: 220/470, loss: 0.7687535881996155
2023-01-22 19:13:53.772873: step: 222/470, loss: 0.01730995625257492
2023-01-22 19:13:54.567411: step: 224/470, loss: 0.0984438806772232
2023-01-22 19:13:55.300151: step: 226/470, loss: 0.014674522913992405
2023-01-22 19:13:56.027527: step: 228/470, loss: 0.07806924730539322
2023-01-22 19:13:56.836642: step: 230/470, loss: 0.10137531161308289
2023-01-22 19:13:57.591908: step: 232/470, loss: 0.021633736789226532
2023-01-22 19:13:58.350185: step: 234/470, loss: 0.02728520892560482
2023-01-22 19:13:59.008434: step: 236/470, loss: 0.023789340630173683
2023-01-22 19:13:59.698968: step: 238/470, loss: 0.08473862707614899
2023-01-22 19:14:00.426443: step: 240/470, loss: 0.5015853047370911
2023-01-22 19:14:01.157151: step: 242/470, loss: 0.3454964756965637
2023-01-22 19:14:01.980759: step: 244/470, loss: 0.104658342897892
2023-01-22 19:14:02.704238: step: 246/470, loss: 0.0792723074555397
2023-01-22 19:14:03.549026: step: 248/470, loss: 0.22262783348560333
2023-01-22 19:14:04.343929: step: 250/470, loss: 0.04709459841251373
2023-01-22 19:14:05.120278: step: 252/470, loss: 0.11567848920822144
2023-01-22 19:14:05.951645: step: 254/470, loss: 0.022635197266936302
2023-01-22 19:14:06.676793: step: 256/470, loss: 0.032210566103458405
2023-01-22 19:14:07.379407: step: 258/470, loss: 0.09060268104076385
2023-01-22 19:14:08.109850: step: 260/470, loss: 0.06221858039498329
2023-01-22 19:14:08.892258: step: 262/470, loss: 0.04487275332212448
2023-01-22 19:14:09.636498: step: 264/470, loss: 0.145310178399086
2023-01-22 19:14:10.356147: step: 266/470, loss: 0.025644149631261826
2023-01-22 19:14:11.246272: step: 268/470, loss: 0.03474476560950279
2023-01-22 19:14:11.956846: step: 270/470, loss: 0.06833195686340332
2023-01-22 19:14:12.665329: step: 272/470, loss: 0.1358962208032608
2023-01-22 19:14:13.422953: step: 274/470, loss: 0.08055564761161804
2023-01-22 19:14:14.146174: step: 276/470, loss: 0.060504548251628876
2023-01-22 19:14:14.937709: step: 278/470, loss: 0.1443237066268921
2023-01-22 19:14:15.671769: step: 280/470, loss: 0.0553126223385334
2023-01-22 19:14:16.417043: step: 282/470, loss: 0.047990117222070694
2023-01-22 19:14:17.132331: step: 284/470, loss: 0.053962647914886475
2023-01-22 19:14:17.849094: step: 286/470, loss: 0.06690418720245361
2023-01-22 19:14:18.560802: step: 288/470, loss: 0.02675960212945938
2023-01-22 19:14:19.275707: step: 290/470, loss: 0.10729622840881348
2023-01-22 19:14:19.980275: step: 292/470, loss: 0.009620921686291695
2023-01-22 19:14:20.627298: step: 294/470, loss: 0.017848452553153038
2023-01-22 19:14:21.422617: step: 296/470, loss: 0.0679577887058258
2023-01-22 19:14:22.181728: step: 298/470, loss: 0.009503382258117199
2023-01-22 19:14:22.926152: step: 300/470, loss: 0.008858383633196354
2023-01-22 19:14:23.629670: step: 302/470, loss: 6.043306827545166
2023-01-22 19:14:24.375091: step: 304/470, loss: 0.07553528249263763
2023-01-22 19:14:25.061270: step: 306/470, loss: 0.016572916880249977
2023-01-22 19:14:25.792363: step: 308/470, loss: 0.10772523283958435
2023-01-22 19:14:26.536975: step: 310/470, loss: 0.08887186646461487
2023-01-22 19:14:27.242463: step: 312/470, loss: 0.06254518777132034
2023-01-22 19:14:27.978847: step: 314/470, loss: 0.07799230515956879
2023-01-22 19:14:28.691054: step: 316/470, loss: 0.1513335406780243
2023-01-22 19:14:29.431674: step: 318/470, loss: 0.03515966981649399
2023-01-22 19:14:30.221013: step: 320/470, loss: 0.028799178078770638
2023-01-22 19:14:30.946391: step: 322/470, loss: 0.02126074954867363
2023-01-22 19:14:31.715557: step: 324/470, loss: 0.06063699349761009
2023-01-22 19:14:32.461624: step: 326/470, loss: 0.05479899421334267
2023-01-22 19:14:33.454445: step: 328/470, loss: 0.042343273758888245
2023-01-22 19:14:34.183525: step: 330/470, loss: 0.04537075757980347
2023-01-22 19:14:34.890809: step: 332/470, loss: 0.02867543324828148
2023-01-22 19:14:35.614886: step: 334/470, loss: 0.03638402745127678
2023-01-22 19:14:36.412086: step: 336/470, loss: 0.09336365759372711
2023-01-22 19:14:37.139595: step: 338/470, loss: 0.07571189105510712
2023-01-22 19:14:37.831242: step: 340/470, loss: 0.07789936661720276
2023-01-22 19:14:38.599100: step: 342/470, loss: 0.22282201051712036
2023-01-22 19:14:39.331719: step: 344/470, loss: 0.06214971840381622
2023-01-22 19:14:40.090410: step: 346/470, loss: 0.1050262525677681
2023-01-22 19:14:40.828607: step: 348/470, loss: 0.12013573199510574
2023-01-22 19:14:41.530674: step: 350/470, loss: 0.021225430071353912
2023-01-22 19:14:42.237537: step: 352/470, loss: 0.06574123352766037
2023-01-22 19:14:43.040281: step: 354/470, loss: 0.01238292921334505
2023-01-22 19:14:43.820889: step: 356/470, loss: 0.05769104138016701
2023-01-22 19:14:44.535606: step: 358/470, loss: 0.036605287343263626
2023-01-22 19:14:45.387385: step: 360/470, loss: 0.04926653951406479
2023-01-22 19:14:46.077439: step: 362/470, loss: 0.05047943815588951
2023-01-22 19:14:46.879068: step: 364/470, loss: 0.2702573835849762
2023-01-22 19:14:47.551182: step: 366/470, loss: 0.09223837405443192
2023-01-22 19:14:48.289012: step: 368/470, loss: 0.10138967633247375
2023-01-22 19:14:49.020236: step: 370/470, loss: 0.04373805224895477
2023-01-22 19:14:49.722342: step: 372/470, loss: 0.03066779114305973
2023-01-22 19:14:50.434242: step: 374/470, loss: 0.077591672539711
2023-01-22 19:14:51.093411: step: 376/470, loss: 0.196303129196167
2023-01-22 19:14:51.820023: step: 378/470, loss: 0.06719297915697098
2023-01-22 19:14:52.584214: step: 380/470, loss: 0.44437164068222046
2023-01-22 19:14:53.350299: step: 382/470, loss: 0.042737286537885666
2023-01-22 19:14:54.058765: step: 384/470, loss: 0.0069000255316495895
2023-01-22 19:14:54.822773: step: 386/470, loss: 0.05957155302166939
2023-01-22 19:14:55.510841: step: 388/470, loss: 0.08688811212778091
2023-01-22 19:14:56.305272: step: 390/470, loss: 0.05815081670880318
2023-01-22 19:14:57.019322: step: 392/470, loss: 0.016378343105316162
2023-01-22 19:14:57.754037: step: 394/470, loss: 0.035406243056058884
2023-01-22 19:14:58.505246: step: 396/470, loss: 0.008739456534385681
2023-01-22 19:14:59.253603: step: 398/470, loss: 0.18853512406349182
2023-01-22 19:14:59.995368: step: 400/470, loss: 0.03277993202209473
2023-01-22 19:15:00.771998: step: 402/470, loss: 0.13732224702835083
2023-01-22 19:15:01.424758: step: 404/470, loss: 0.008723941631615162
2023-01-22 19:15:02.102741: step: 406/470, loss: 0.06874186545610428
2023-01-22 19:15:02.854188: step: 408/470, loss: 0.7236286401748657
2023-01-22 19:15:03.557384: step: 410/470, loss: 0.28471216559410095
2023-01-22 19:15:04.318847: step: 412/470, loss: 0.08407147228717804
2023-01-22 19:15:05.065771: step: 414/470, loss: 0.038917530328035355
2023-01-22 19:15:05.766286: step: 416/470, loss: 0.08968863636255264
2023-01-22 19:15:06.477839: step: 418/470, loss: 0.1135501116514206
2023-01-22 19:15:07.204960: step: 420/470, loss: 0.051190122961997986
2023-01-22 19:15:07.901514: step: 422/470, loss: 0.06608197093009949
2023-01-22 19:15:08.616829: step: 424/470, loss: 0.005093181971460581
2023-01-22 19:15:09.351738: step: 426/470, loss: 0.04653076454997063
2023-01-22 19:15:10.136277: step: 428/470, loss: 0.01797359250485897
2023-01-22 19:15:10.842079: step: 430/470, loss: 0.12045972049236298
2023-01-22 19:15:11.550442: step: 432/470, loss: 0.04225793853402138
2023-01-22 19:15:12.274351: step: 434/470, loss: 0.3560810685157776
2023-01-22 19:15:12.940852: step: 436/470, loss: 0.03933987766504288
2023-01-22 19:15:13.634162: step: 438/470, loss: 0.10735952109098434
2023-01-22 19:15:14.322706: step: 440/470, loss: 0.04517611861228943
2023-01-22 19:15:15.098883: step: 442/470, loss: 0.04805009067058563
2023-01-22 19:15:15.815797: step: 444/470, loss: 0.034436922520399094
2023-01-22 19:15:16.606819: step: 446/470, loss: 0.0980946347117424
2023-01-22 19:15:17.328541: step: 448/470, loss: 0.02357635833323002
2023-01-22 19:15:18.077602: step: 450/470, loss: 0.40950459241867065
2023-01-22 19:15:18.778972: step: 452/470, loss: 0.09088637679815292
2023-01-22 19:15:19.531226: step: 454/470, loss: 0.06179659068584442
2023-01-22 19:15:20.192371: step: 456/470, loss: 0.024704836308956146
2023-01-22 19:15:20.947138: step: 458/470, loss: 0.013954793103039265
2023-01-22 19:15:21.671725: step: 460/470, loss: 0.012341751717031002
2023-01-22 19:15:22.336371: step: 462/470, loss: 0.4283565282821655
2023-01-22 19:15:23.055113: step: 464/470, loss: 0.12819719314575195
2023-01-22 19:15:23.861386: step: 466/470, loss: 0.10749958455562592
2023-01-22 19:15:24.570578: step: 468/470, loss: 0.0625910684466362
2023-01-22 19:15:25.325357: step: 470/470, loss: 0.0827048048377037
2023-01-22 19:15:25.978366: step: 472/470, loss: 0.05317022651433945
2023-01-22 19:15:26.696784: step: 474/470, loss: 0.020091721788048744
2023-01-22 19:15:27.399913: step: 476/470, loss: 0.06902855634689331
2023-01-22 19:15:28.102194: step: 478/470, loss: 0.044647008180618286
2023-01-22 19:15:28.823719: step: 480/470, loss: 0.061124030500650406
2023-01-22 19:15:29.576571: step: 482/470, loss: 0.09614740312099457
2023-01-22 19:15:30.316236: step: 484/470, loss: 0.09537113457918167
2023-01-22 19:15:31.181724: step: 486/470, loss: 0.1970382034778595
2023-01-22 19:15:31.933582: step: 488/470, loss: 0.08817904442548752
2023-01-22 19:15:32.718394: step: 490/470, loss: 0.19899365305900574
2023-01-22 19:15:33.451816: step: 492/470, loss: 0.010458926670253277
2023-01-22 19:15:34.171625: step: 494/470, loss: 0.09982287138700485
2023-01-22 19:15:34.876623: step: 496/470, loss: 0.02451414242386818
2023-01-22 19:15:35.541055: step: 498/470, loss: 0.05906842648983002
2023-01-22 19:15:36.322970: step: 500/470, loss: 0.02308048866689205
2023-01-22 19:15:37.171702: step: 502/470, loss: 0.4586753845214844
2023-01-22 19:15:37.952193: step: 504/470, loss: 0.001469065435230732
2023-01-22 19:15:38.644047: step: 506/470, loss: 0.39444416761398315
2023-01-22 19:15:39.342806: step: 508/470, loss: 0.07880131155252457
2023-01-22 19:15:40.099404: step: 510/470, loss: 0.34225597977638245
2023-01-22 19:15:40.834381: step: 512/470, loss: 0.07212910801172256
2023-01-22 19:15:41.665494: step: 514/470, loss: 0.0419406034052372
2023-01-22 19:15:42.343836: step: 516/470, loss: 0.24012605845928192
2023-01-22 19:15:43.064777: step: 518/470, loss: 0.02023383416235447
2023-01-22 19:15:43.777756: step: 520/470, loss: 0.2502630650997162
2023-01-22 19:15:44.532201: step: 522/470, loss: 0.2373182326555252
2023-01-22 19:15:45.262507: step: 524/470, loss: 0.07686462253332138
2023-01-22 19:15:46.018439: step: 526/470, loss: 0.11860328167676926
2023-01-22 19:15:46.765417: step: 528/470, loss: 0.07658058404922485
2023-01-22 19:15:47.544053: step: 530/470, loss: 0.033899374306201935
2023-01-22 19:15:48.239071: step: 532/470, loss: 0.010917163453996181
2023-01-22 19:15:48.972037: step: 534/470, loss: 0.017348704859614372
2023-01-22 19:15:49.716771: step: 536/470, loss: 0.32592514157295227
2023-01-22 19:15:50.427008: step: 538/470, loss: 0.12130807340145111
2023-01-22 19:15:51.081273: step: 540/470, loss: 0.06882882863283157
2023-01-22 19:15:51.932802: step: 542/470, loss: 0.009247006848454475
2023-01-22 19:15:52.721936: step: 544/470, loss: 0.05684985592961311
2023-01-22 19:15:53.529275: step: 546/470, loss: 0.08473062515258789
2023-01-22 19:15:54.274981: step: 548/470, loss: 0.0109866289421916
2023-01-22 19:15:54.970829: step: 550/470, loss: 0.04165481775999069
2023-01-22 19:15:55.738404: step: 552/470, loss: 0.01383355911821127
2023-01-22 19:15:56.424584: step: 554/470, loss: 0.08635249733924866
2023-01-22 19:15:57.168354: step: 556/470, loss: 0.05461049824953079
2023-01-22 19:15:57.830124: step: 558/470, loss: 0.015371817164123058
2023-01-22 19:15:58.486018: step: 560/470, loss: 0.6815204620361328
2023-01-22 19:15:59.230685: step: 562/470, loss: 0.09630201011896133
2023-01-22 19:15:59.891867: step: 564/470, loss: 0.05369073897600174
2023-01-22 19:16:00.581785: step: 566/470, loss: 0.058216556906700134
2023-01-22 19:16:01.344411: step: 568/470, loss: 0.02524617128074169
2023-01-22 19:16:02.021380: step: 570/470, loss: 0.04199972376227379
2023-01-22 19:16:02.668839: step: 572/470, loss: 0.015193572267889977
2023-01-22 19:16:03.411672: step: 574/470, loss: 0.039925094693899155
2023-01-22 19:16:04.207772: step: 576/470, loss: 0.13338324427604675
2023-01-22 19:16:04.916010: step: 578/470, loss: 0.062471386045217514
2023-01-22 19:16:05.668659: step: 580/470, loss: 0.09208384156227112
2023-01-22 19:16:06.397465: step: 582/470, loss: 0.030092593282461166
2023-01-22 19:16:07.108703: step: 584/470, loss: 0.06586410105228424
2023-01-22 19:16:07.836972: step: 586/470, loss: 0.02899825945496559
2023-01-22 19:16:08.559122: step: 588/470, loss: 0.10743267834186554
2023-01-22 19:16:09.258500: step: 590/470, loss: 0.10501951724290848
2023-01-22 19:16:09.979704: step: 592/470, loss: 1.813976526260376
2023-01-22 19:16:10.724427: step: 594/470, loss: 0.06850782036781311
2023-01-22 19:16:11.485753: step: 596/470, loss: 0.08768956363201141
2023-01-22 19:16:12.234853: step: 598/470, loss: 0.0878264382481575
2023-01-22 19:16:12.960736: step: 600/470, loss: 0.022833187133073807
2023-01-22 19:16:13.688286: step: 602/470, loss: 0.07362283021211624
2023-01-22 19:16:14.479629: step: 604/470, loss: 0.02391095831990242
2023-01-22 19:16:15.296942: step: 606/470, loss: 0.0804729014635086
2023-01-22 19:16:15.989518: step: 608/470, loss: 0.012506152503192425
2023-01-22 19:16:16.711700: step: 610/470, loss: 0.134328231215477
2023-01-22 19:16:17.410361: step: 612/470, loss: 0.10547507554292679
2023-01-22 19:16:18.173947: step: 614/470, loss: 0.12143544852733612
2023-01-22 19:16:18.973449: step: 616/470, loss: 0.08066742867231369
2023-01-22 19:16:19.726951: step: 618/470, loss: 0.03654317930340767
2023-01-22 19:16:20.502816: step: 620/470, loss: 0.03914722800254822
2023-01-22 19:16:21.262407: step: 622/470, loss: 0.05489708110690117
2023-01-22 19:16:22.082222: step: 624/470, loss: 0.06426960974931717
2023-01-22 19:16:22.807570: step: 626/470, loss: 0.06736937165260315
2023-01-22 19:16:23.537765: step: 628/470, loss: 0.11102497577667236
2023-01-22 19:16:24.289690: step: 630/470, loss: 0.012651097029447556
2023-01-22 19:16:25.013146: step: 632/470, loss: 2.867856502532959
2023-01-22 19:16:25.693945: step: 634/470, loss: 0.15367330610752106
2023-01-22 19:16:26.448546: step: 636/470, loss: 0.0965505912899971
2023-01-22 19:16:27.217108: step: 638/470, loss: 0.015126102603971958
2023-01-22 19:16:27.933854: step: 640/470, loss: 0.11571274697780609
2023-01-22 19:16:28.623615: step: 642/470, loss: 0.057073745876550674
2023-01-22 19:16:29.426185: step: 644/470, loss: 0.13571985065937042
2023-01-22 19:16:30.255348: step: 646/470, loss: 0.14553725719451904
2023-01-22 19:16:31.025859: step: 648/470, loss: 0.17457713186740875
2023-01-22 19:16:31.753179: step: 650/470, loss: 0.045833222568035126
2023-01-22 19:16:32.483774: step: 652/470, loss: 0.08109059184789658
2023-01-22 19:16:33.192824: step: 654/470, loss: 0.06932274252176285
2023-01-22 19:16:33.958008: step: 656/470, loss: 0.020560914650559425
2023-01-22 19:16:34.684502: step: 658/470, loss: 0.08866900950670242
2023-01-22 19:16:35.451616: step: 660/470, loss: 0.14196772873401642
2023-01-22 19:16:36.162638: step: 662/470, loss: 0.025075623765587807
2023-01-22 19:16:36.842088: step: 664/470, loss: 0.05653095617890358
2023-01-22 19:16:37.625660: step: 666/470, loss: 0.0553109236061573
2023-01-22 19:16:38.395956: step: 668/470, loss: 0.014820709824562073
2023-01-22 19:16:39.151044: step: 670/470, loss: 0.1057378500699997
2023-01-22 19:16:39.933059: step: 672/470, loss: 0.04209692403674126
2023-01-22 19:16:40.684481: step: 674/470, loss: 0.009847085922956467
2023-01-22 19:16:41.468044: step: 676/470, loss: 0.0047174664214253426
2023-01-22 19:16:42.140761: step: 678/470, loss: 0.04511541128158569
2023-01-22 19:16:42.929820: step: 680/470, loss: 0.04158242791891098
2023-01-22 19:16:43.640527: step: 682/470, loss: 0.02903454191982746
2023-01-22 19:16:44.404935: step: 684/470, loss: 0.015415815636515617
2023-01-22 19:16:45.072301: step: 686/470, loss: 0.050201885402202606
2023-01-22 19:16:45.953720: step: 688/470, loss: 0.05017707124352455
2023-01-22 19:16:46.632265: step: 690/470, loss: 0.09871582686901093
2023-01-22 19:16:47.356871: step: 692/470, loss: 0.12438881397247314
2023-01-22 19:16:48.061056: step: 694/470, loss: 1.1262582540512085
2023-01-22 19:16:48.798211: step: 696/470, loss: 0.15150487422943115
2023-01-22 19:16:49.530562: step: 698/470, loss: 0.8048862814903259
2023-01-22 19:16:50.221331: step: 700/470, loss: 0.04326051101088524
2023-01-22 19:16:50.965154: step: 702/470, loss: 0.05587514489889145
2023-01-22 19:16:51.720828: step: 704/470, loss: 0.07721059769392014
2023-01-22 19:16:52.479547: step: 706/470, loss: 0.06396961212158203
2023-01-22 19:16:53.261575: step: 708/470, loss: 0.057133980095386505
2023-01-22 19:16:54.142137: step: 710/470, loss: 0.14436408877372742
2023-01-22 19:16:54.888224: step: 712/470, loss: 0.058494627475738525
2023-01-22 19:16:55.657952: step: 714/470, loss: 0.6884530782699585
2023-01-22 19:16:56.432336: step: 716/470, loss: 0.07548058032989502
2023-01-22 19:16:57.155236: step: 718/470, loss: 0.020441729575395584
2023-01-22 19:16:57.874193: step: 720/470, loss: 0.23590579628944397
2023-01-22 19:16:58.538438: step: 722/470, loss: 0.05578876659274101
2023-01-22 19:16:59.267200: step: 724/470, loss: 0.12205921858549118
2023-01-22 19:16:59.958918: step: 726/470, loss: 0.08680590242147446
2023-01-22 19:17:00.712922: step: 728/470, loss: 0.07038237154483795
2023-01-22 19:17:01.468370: step: 730/470, loss: 0.0950479656457901
2023-01-22 19:17:02.254432: step: 732/470, loss: 0.019861508160829544
2023-01-22 19:17:02.988502: step: 734/470, loss: 0.014996448531746864
2023-01-22 19:17:03.708885: step: 736/470, loss: 0.10738176852464676
2023-01-22 19:17:04.471510: step: 738/470, loss: 0.07451841235160828
2023-01-22 19:17:05.253872: step: 740/470, loss: 0.1438053697347641
2023-01-22 19:17:05.970339: step: 742/470, loss: 0.11218611896038055
2023-01-22 19:17:06.710572: step: 744/470, loss: 0.06557218730449677
2023-01-22 19:17:07.434214: step: 746/470, loss: 0.04441092908382416
2023-01-22 19:17:08.234433: step: 748/470, loss: 0.09895999729633331
2023-01-22 19:17:09.035494: step: 750/470, loss: 0.22363828122615814
2023-01-22 19:17:09.866576: step: 752/470, loss: 0.029841436073184013
2023-01-22 19:17:10.592415: step: 754/470, loss: 0.14877954125404358
2023-01-22 19:17:11.342909: step: 756/470, loss: 0.025677978992462158
2023-01-22 19:17:11.968719: step: 758/470, loss: 0.05344592407345772
2023-01-22 19:17:12.670546: step: 760/470, loss: 0.029401803389191628
2023-01-22 19:17:13.352751: step: 762/470, loss: 0.03349433094263077
2023-01-22 19:17:14.082212: step: 764/470, loss: 0.08564404398202896
2023-01-22 19:17:14.814981: step: 766/470, loss: 0.04291162267327309
2023-01-22 19:17:15.500776: step: 768/470, loss: 0.02198793552815914
2023-01-22 19:17:16.231919: step: 770/470, loss: 0.04124632105231285
2023-01-22 19:17:16.997775: step: 772/470, loss: 0.07800045609474182
2023-01-22 19:17:17.786018: step: 774/470, loss: 0.008934520184993744
2023-01-22 19:17:18.468489: step: 776/470, loss: 0.006552144419401884
2023-01-22 19:17:19.359288: step: 778/470, loss: 0.008206459693610668
2023-01-22 19:17:20.007710: step: 780/470, loss: 0.07419215887784958
2023-01-22 19:17:20.743263: step: 782/470, loss: 0.07244870811700821
2023-01-22 19:17:21.522467: step: 784/470, loss: 0.010627111420035362
2023-01-22 19:17:22.337042: step: 786/470, loss: 0.02431710809469223
2023-01-22 19:17:23.089917: step: 788/470, loss: 0.053509872406721115
2023-01-22 19:17:23.851453: step: 790/470, loss: 0.030945895239710808
2023-01-22 19:17:24.602596: step: 792/470, loss: 0.03115873783826828
2023-01-22 19:17:25.359591: step: 794/470, loss: 0.07354782521724701
2023-01-22 19:17:26.084463: step: 796/470, loss: 0.04989173263311386
2023-01-22 19:17:26.836038: step: 798/470, loss: 0.047723811119794846
2023-01-22 19:17:27.610028: step: 800/470, loss: 0.15342743694782257
2023-01-22 19:17:28.371436: step: 802/470, loss: 0.018950236961245537
2023-01-22 19:17:29.069760: step: 804/470, loss: 0.12344154715538025
2023-01-22 19:17:29.825810: step: 806/470, loss: 0.04489344358444214
2023-01-22 19:17:30.528930: step: 808/470, loss: 0.013071177527308464
2023-01-22 19:17:31.272572: step: 810/470, loss: 0.1920340359210968
2023-01-22 19:17:31.976938: step: 812/470, loss: 0.041845425963401794
2023-01-22 19:17:32.749510: step: 814/470, loss: 0.031873006373643875
2023-01-22 19:17:33.439539: step: 816/470, loss: 0.008344985544681549
2023-01-22 19:17:34.220997: step: 818/470, loss: 0.4394215941429138
2023-01-22 19:17:34.978757: step: 820/470, loss: 0.046475548297166824
2023-01-22 19:17:35.869519: step: 822/470, loss: 0.023420801386237144
2023-01-22 19:17:36.540305: step: 824/470, loss: 0.046169888228178024
2023-01-22 19:17:37.296766: step: 826/470, loss: 0.0012928505893796682
2023-01-22 19:17:38.066800: step: 828/470, loss: 0.06589809060096741
2023-01-22 19:17:38.767875: step: 830/470, loss: 0.08819597214460373
2023-01-22 19:17:39.554641: step: 832/470, loss: 0.04559420421719551
2023-01-22 19:17:40.261647: step: 834/470, loss: 0.01821593940258026
2023-01-22 19:17:40.950821: step: 836/470, loss: 0.1270139217376709
2023-01-22 19:17:41.721348: step: 838/470, loss: 0.0652085393667221
2023-01-22 19:17:42.434508: step: 840/470, loss: 0.190468892455101
2023-01-22 19:17:43.218951: step: 842/470, loss: 0.4353700280189514
2023-01-22 19:17:44.008287: step: 844/470, loss: 0.08427219092845917
2023-01-22 19:17:44.790972: step: 846/470, loss: 0.044107187539339066
2023-01-22 19:17:45.486487: step: 848/470, loss: 0.025654705241322517
2023-01-22 19:17:46.271730: step: 850/470, loss: 0.06636069715023041
2023-01-22 19:17:47.030032: step: 852/470, loss: 0.10997164994478226
2023-01-22 19:17:47.722169: step: 854/470, loss: 0.006697851698845625
2023-01-22 19:17:48.494395: step: 856/470, loss: 0.07333116978406906
2023-01-22 19:17:49.164113: step: 858/470, loss: 0.05577976629137993
2023-01-22 19:17:49.843620: step: 860/470, loss: 0.5426846742630005
2023-01-22 19:17:50.665106: step: 862/470, loss: 0.11723057180643082
2023-01-22 19:17:51.467534: step: 864/470, loss: 0.2411772608757019
2023-01-22 19:17:52.153915: step: 866/470, loss: 0.05249849334359169
2023-01-22 19:17:52.845324: step: 868/470, loss: 0.03625642880797386
2023-01-22 19:17:53.628406: step: 870/470, loss: 0.04509961977601051
2023-01-22 19:17:54.388840: step: 872/470, loss: 0.013741428032517433
2023-01-22 19:17:55.118568: step: 874/470, loss: 0.04218994453549385
2023-01-22 19:17:55.882817: step: 876/470, loss: 0.055986031889915466
2023-01-22 19:17:56.680125: step: 878/470, loss: 0.048953864723443985
2023-01-22 19:17:57.349470: step: 880/470, loss: 0.09331956505775452
2023-01-22 19:17:58.120302: step: 882/470, loss: 0.6611769199371338
2023-01-22 19:17:58.819875: step: 884/470, loss: 0.07350049912929535
2023-01-22 19:17:59.628621: step: 886/470, loss: 0.18695667386054993
2023-01-22 19:18:00.446332: step: 888/470, loss: 0.07724187523126602
2023-01-22 19:18:01.179407: step: 890/470, loss: 0.06299719214439392
2023-01-22 19:18:01.969573: step: 892/470, loss: 0.10604791343212128
2023-01-22 19:18:02.688223: step: 894/470, loss: 0.04927706718444824
2023-01-22 19:18:03.405000: step: 896/470, loss: 0.1778610497713089
2023-01-22 19:18:04.091596: step: 898/470, loss: 0.10980663448572159
2023-01-22 19:18:04.838495: step: 900/470, loss: 0.05071067810058594
2023-01-22 19:18:05.571894: step: 902/470, loss: 0.14896638691425323
2023-01-22 19:18:06.308125: step: 904/470, loss: 0.09147992730140686
2023-01-22 19:18:07.065587: step: 906/470, loss: 0.054453279823064804
2023-01-22 19:18:07.809038: step: 908/470, loss: 0.11247234046459198
2023-01-22 19:18:08.621942: step: 910/470, loss: 0.05727868527173996
2023-01-22 19:18:09.499561: step: 912/470, loss: 0.050508055835962296
2023-01-22 19:18:10.211599: step: 914/470, loss: 0.03650575131177902
2023-01-22 19:18:11.054209: step: 916/470, loss: 0.08102092146873474
2023-01-22 19:18:11.808865: step: 918/470, loss: 0.06759768724441528
2023-01-22 19:18:12.568709: step: 920/470, loss: 0.1721310019493103
2023-01-22 19:18:13.366631: step: 922/470, loss: 0.03154829144477844
2023-01-22 19:18:14.181389: step: 924/470, loss: 0.21797621250152588
2023-01-22 19:18:14.842210: step: 926/470, loss: 0.06564341485500336
2023-01-22 19:18:15.734029: step: 928/470, loss: 0.09147854149341583
2023-01-22 19:18:16.489544: step: 930/470, loss: 0.014387188479304314
2023-01-22 19:18:17.173581: step: 932/470, loss: 0.08677081763744354
2023-01-22 19:18:17.886145: step: 934/470, loss: 0.003573360852897167
2023-01-22 19:18:18.644112: step: 936/470, loss: 0.19656676054000854
2023-01-22 19:18:19.412790: step: 938/470, loss: 0.19232219457626343
2023-01-22 19:18:20.180630: step: 940/470, loss: 0.13135120272636414
2023-01-22 19:18:20.779614: step: 942/470, loss: 0.04300255328416824
==================================================
Loss: 0.135
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2896543560606061, 'r': 0.3385713156230234, 'f1': 0.31220836978711}, 'combined': 0.2300482724747126, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34115630463621305, 'r': 0.3657589227590169, 'f1': 0.3530294938926938}, 'combined': 0.24589118977600563, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28973168685247336, 'r': 0.3425101345523547, 'f1': 0.31391798418972333}, 'combined': 0.23130798835032243, 'epoch': 19}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34471087975247255, 'r': 0.36592385696800933, 'f1': 0.35500075676000903}, 'combined': 0.24726420868856352, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27054796847397744, 'r': 0.34344704157322753, 'f1': 0.30266988446336274}, 'combined': 0.22301991486774095, 'epoch': 19}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3327365613721349, 'r': 0.376248265551568, 'f1': 0.3531572167632046}, 'combined': 0.2459801509793465, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23684210526315788, 'r': 0.38571428571428573, 'f1': 0.2934782608695652}, 'combined': 0.19565217391304346, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.23837209302325582, 'r': 0.44565217391304346, 'f1': 0.3106060606060606}, 'combined': 0.1553030303030303, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3522727272727273, 'r': 0.2672413793103448, 'f1': 0.303921568627451}, 'combined': 0.20261437908496732, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 20
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 19:20:58.707184: step: 2/470, loss: 0.0692053884267807
2023-01-22 19:20:59.418216: step: 4/470, loss: 0.011433595791459084
2023-01-22 19:21:00.122098: step: 6/470, loss: 0.01590590551495552
2023-01-22 19:21:00.888888: step: 8/470, loss: 0.33525508642196655
2023-01-22 19:21:01.591339: step: 10/470, loss: 0.005369840655475855
2023-01-22 19:21:02.314967: step: 12/470, loss: 0.0471285842359066
2023-01-22 19:21:03.023435: step: 14/470, loss: 0.06779136508703232
2023-01-22 19:21:03.809403: step: 16/470, loss: 0.08163978904485703
2023-01-22 19:21:04.557517: step: 18/470, loss: 0.03811454027891159
2023-01-22 19:21:05.278699: step: 20/470, loss: 0.0674220472574234
2023-01-22 19:21:06.010267: step: 22/470, loss: 0.08177307993173599
2023-01-22 19:21:06.676541: step: 24/470, loss: 0.18022318184375763
2023-01-22 19:21:07.416887: step: 26/470, loss: 0.00783989205956459
2023-01-22 19:21:08.158253: step: 28/470, loss: 0.10600445419549942
2023-01-22 19:21:08.836756: step: 30/470, loss: 0.026321159675717354
2023-01-22 19:21:09.585922: step: 32/470, loss: 0.022986600175499916
2023-01-22 19:21:10.342098: step: 34/470, loss: 0.11820484697818756
2023-01-22 19:21:11.099983: step: 36/470, loss: 0.011436332017183304
2023-01-22 19:21:11.770266: step: 38/470, loss: 0.020493147894740105
2023-01-22 19:21:12.513259: step: 40/470, loss: 0.05821879953145981
2023-01-22 19:21:13.242647: step: 42/470, loss: 0.0022761637810617685
2023-01-22 19:21:13.882987: step: 44/470, loss: 0.036995094269514084
2023-01-22 19:21:14.652886: step: 46/470, loss: 0.03528263792395592
2023-01-22 19:21:15.406991: step: 48/470, loss: 0.09343452751636505
2023-01-22 19:21:16.114311: step: 50/470, loss: 0.06097423657774925
2023-01-22 19:21:16.874370: step: 52/470, loss: 0.10285371541976929
2023-01-22 19:21:17.484197: step: 54/470, loss: 0.00979323498904705
2023-01-22 19:21:18.212498: step: 56/470, loss: 0.062471531331539154
2023-01-22 19:21:18.960710: step: 58/470, loss: 0.02455725520849228
2023-01-22 19:21:19.670548: step: 60/470, loss: 0.0015147414524108171
2023-01-22 19:21:20.399563: step: 62/470, loss: 0.01592283509671688
2023-01-22 19:21:21.118960: step: 64/470, loss: 0.09599973261356354
2023-01-22 19:21:21.842819: step: 66/470, loss: 0.033546753227710724
2023-01-22 19:21:22.596284: step: 68/470, loss: 0.04527419060468674
2023-01-22 19:21:23.254008: step: 70/470, loss: 0.01420632191002369
2023-01-22 19:21:24.046475: step: 72/470, loss: 0.03015095181763172
2023-01-22 19:21:24.850251: step: 74/470, loss: 0.021656258031725883
2023-01-22 19:21:25.678253: step: 76/470, loss: 0.05661938339471817
2023-01-22 19:21:26.453438: step: 78/470, loss: 0.08553628623485565
2023-01-22 19:21:27.193424: step: 80/470, loss: 0.017559433355927467
2023-01-22 19:21:27.917188: step: 82/470, loss: 0.17091146111488342
2023-01-22 19:21:28.625114: step: 84/470, loss: 0.022843779996037483
2023-01-22 19:21:29.318992: step: 86/470, loss: 0.04321271553635597
2023-01-22 19:21:30.005253: step: 88/470, loss: 0.01985297165811062
2023-01-22 19:21:30.718990: step: 90/470, loss: 0.05657010152935982
2023-01-22 19:21:31.482850: step: 92/470, loss: 0.039768945425748825
2023-01-22 19:21:32.298437: step: 94/470, loss: 0.03442995622754097
2023-01-22 19:21:33.070699: step: 96/470, loss: 0.06425513327121735
2023-01-22 19:21:33.780925: step: 98/470, loss: 0.061561282724142075
2023-01-22 19:21:34.460038: step: 100/470, loss: 0.04602031782269478
2023-01-22 19:21:35.123889: step: 102/470, loss: 0.09504874795675278
2023-01-22 19:21:35.813244: step: 104/470, loss: 0.11075009405612946
2023-01-22 19:21:36.532243: step: 106/470, loss: 0.3181428015232086
2023-01-22 19:21:37.245643: step: 108/470, loss: 0.006885759066790342
2023-01-22 19:21:37.984793: step: 110/470, loss: 0.012126323767006397
2023-01-22 19:21:38.692990: step: 112/470, loss: 0.04041305184364319
2023-01-22 19:21:39.404271: step: 114/470, loss: 0.053244318813085556
2023-01-22 19:21:40.117600: step: 116/470, loss: 0.06406726688146591
2023-01-22 19:21:40.856560: step: 118/470, loss: 0.276273250579834
2023-01-22 19:21:41.604082: step: 120/470, loss: 0.017418205738067627
2023-01-22 19:21:42.339246: step: 122/470, loss: 0.0642717108130455
2023-01-22 19:21:43.108765: step: 124/470, loss: 0.06656879186630249
2023-01-22 19:21:43.901260: step: 126/470, loss: 0.038813501596450806
2023-01-22 19:21:44.602613: step: 128/470, loss: 0.037797726690769196
2023-01-22 19:21:45.441408: step: 130/470, loss: 0.012955233454704285
2023-01-22 19:21:46.163233: step: 132/470, loss: 0.14164546132087708
2023-01-22 19:21:46.937604: step: 134/470, loss: 0.026768483221530914
2023-01-22 19:21:47.679495: step: 136/470, loss: 0.518687903881073
2023-01-22 19:21:48.443330: step: 138/470, loss: 0.08869636803865433
2023-01-22 19:21:49.159757: step: 140/470, loss: 0.4429130554199219
2023-01-22 19:21:49.908325: step: 142/470, loss: 0.03325126692652702
2023-01-22 19:21:50.639400: step: 144/470, loss: 0.046417348086833954
2023-01-22 19:21:51.385944: step: 146/470, loss: 0.022128436714410782
2023-01-22 19:21:52.055316: step: 148/470, loss: 0.08988092094659805
2023-01-22 19:21:52.803145: step: 150/470, loss: 0.05364342778921127
2023-01-22 19:21:53.515825: step: 152/470, loss: 0.017953716218471527
2023-01-22 19:21:54.304967: step: 154/470, loss: 0.09780565649271011
2023-01-22 19:21:55.007645: step: 156/470, loss: 0.009147114120423794
2023-01-22 19:21:55.684019: step: 158/470, loss: 0.09362566471099854
2023-01-22 19:21:56.371372: step: 160/470, loss: 0.013519582338631153
2023-01-22 19:21:57.045461: step: 162/470, loss: 0.45257019996643066
2023-01-22 19:21:57.703983: step: 164/470, loss: 0.08413586020469666
2023-01-22 19:21:58.484775: step: 166/470, loss: 0.04121706634759903
2023-01-22 19:21:59.237667: step: 168/470, loss: 0.026533417403697968
2023-01-22 19:22:00.017764: step: 170/470, loss: 0.21483860909938812
2023-01-22 19:22:00.828401: step: 172/470, loss: 0.024038920179009438
2023-01-22 19:22:01.545665: step: 174/470, loss: 0.2483181357383728
2023-01-22 19:22:02.242755: step: 176/470, loss: 0.030309997498989105
2023-01-22 19:22:03.014131: step: 178/470, loss: 0.02682347223162651
2023-01-22 19:22:03.801595: step: 180/470, loss: 0.17442865669727325
2023-01-22 19:22:04.509260: step: 182/470, loss: 0.27949750423431396
2023-01-22 19:22:05.277534: step: 184/470, loss: 0.035176832228899
2023-01-22 19:22:06.028869: step: 186/470, loss: 0.06619660556316376
2023-01-22 19:22:06.743419: step: 188/470, loss: 1.9417052268981934
2023-01-22 19:22:07.466248: step: 190/470, loss: 0.1208546981215477
2023-01-22 19:22:08.193593: step: 192/470, loss: 0.12052920460700989
2023-01-22 19:22:08.888187: step: 194/470, loss: 0.06708040833473206
2023-01-22 19:22:09.509185: step: 196/470, loss: 0.0005991773214191198
2023-01-22 19:22:10.237525: step: 198/470, loss: 0.18721455335617065
2023-01-22 19:22:10.936592: step: 200/470, loss: 0.031240878626704216
2023-01-22 19:22:11.664318: step: 202/470, loss: 0.2110924869775772
2023-01-22 19:22:12.397701: step: 204/470, loss: 0.11531258374452591
2023-01-22 19:22:13.165479: step: 206/470, loss: 0.04128406569361687
2023-01-22 19:22:13.939562: step: 208/470, loss: 0.07297002524137497
2023-01-22 19:22:14.639829: step: 210/470, loss: 0.04553265497088432
2023-01-22 19:22:15.423868: step: 212/470, loss: 0.02252204902470112
2023-01-22 19:22:16.267002: step: 214/470, loss: 0.25439098477363586
2023-01-22 19:22:17.034700: step: 216/470, loss: 0.7509600520133972
2023-01-22 19:22:17.699004: step: 218/470, loss: 0.034447189420461655
2023-01-22 19:22:18.383855: step: 220/470, loss: 0.01638934761285782
2023-01-22 19:22:19.099260: step: 222/470, loss: 0.04577914625406265
2023-01-22 19:22:19.902233: step: 224/470, loss: 0.04711466655135155
2023-01-22 19:22:20.638785: step: 226/470, loss: 0.30996254086494446
2023-01-22 19:22:21.387905: step: 228/470, loss: 0.00331405783072114
2023-01-22 19:22:22.114380: step: 230/470, loss: 0.07725219428539276
2023-01-22 19:22:22.759373: step: 232/470, loss: 0.5706613659858704
2023-01-22 19:22:23.522848: step: 234/470, loss: 0.03361904248595238
2023-01-22 19:22:24.280965: step: 236/470, loss: 0.04464048147201538
2023-01-22 19:22:25.018439: step: 238/470, loss: 0.024454206228256226
2023-01-22 19:22:25.723010: step: 240/470, loss: 0.012058422900736332
2023-01-22 19:22:26.495202: step: 242/470, loss: 0.07473550736904144
2023-01-22 19:22:27.229583: step: 244/470, loss: 0.06981978565454483
2023-01-22 19:22:27.951021: step: 246/470, loss: 0.06838370859622955
2023-01-22 19:22:28.653617: step: 248/470, loss: 1.1867821216583252
2023-01-22 19:22:29.361748: step: 250/470, loss: 0.1255021095275879
2023-01-22 19:22:30.113793: step: 252/470, loss: 0.009189283475279808
2023-01-22 19:22:30.887478: step: 254/470, loss: 0.060588739812374115
2023-01-22 19:22:31.658794: step: 256/470, loss: 0.08720239251852036
2023-01-22 19:22:32.436940: step: 258/470, loss: 0.04909271374344826
2023-01-22 19:22:33.275325: step: 260/470, loss: 0.018197335302829742
2023-01-22 19:22:33.969586: step: 262/470, loss: 0.034091971814632416
2023-01-22 19:22:34.694112: step: 264/470, loss: 0.036441948264837265
2023-01-22 19:22:35.407508: step: 266/470, loss: 0.00993148423731327
2023-01-22 19:22:36.171794: step: 268/470, loss: 0.053492508828639984
2023-01-22 19:22:37.002455: step: 270/470, loss: 0.04624278470873833
2023-01-22 19:22:37.688756: step: 272/470, loss: 0.17606455087661743
2023-01-22 19:22:38.402182: step: 274/470, loss: 0.018186697736382484
2023-01-22 19:22:39.137841: step: 276/470, loss: 0.059042301028966904
2023-01-22 19:22:39.926922: step: 278/470, loss: 0.05925830453634262
2023-01-22 19:22:40.650603: step: 280/470, loss: 0.017211155965924263
2023-01-22 19:22:41.445830: step: 282/470, loss: 1.1372332572937012
2023-01-22 19:22:42.183590: step: 284/470, loss: 0.011981363408267498
2023-01-22 19:22:42.947744: step: 286/470, loss: 0.0610564649105072
2023-01-22 19:22:43.767243: step: 288/470, loss: 0.016656432300806046
2023-01-22 19:22:44.605001: step: 290/470, loss: 0.04388560354709625
2023-01-22 19:22:45.296104: step: 292/470, loss: 0.03743298724293709
2023-01-22 19:22:46.027816: step: 294/470, loss: 0.021319955587387085
2023-01-22 19:22:46.798257: step: 296/470, loss: 0.08074367791414261
2023-01-22 19:22:47.485984: step: 298/470, loss: 0.14202333986759186
2023-01-22 19:22:48.232411: step: 300/470, loss: 0.09190955758094788
2023-01-22 19:22:49.011038: step: 302/470, loss: 0.053686317056417465
2023-01-22 19:22:49.710394: step: 304/470, loss: 0.05814488232135773
2023-01-22 19:22:50.443605: step: 306/470, loss: 0.028976615518331528
2023-01-22 19:22:51.187582: step: 308/470, loss: 0.03165995329618454
2023-01-22 19:22:51.958796: step: 310/470, loss: 0.18481889367103577
2023-01-22 19:22:52.691119: step: 312/470, loss: 0.06986112892627716
2023-01-22 19:22:53.401273: step: 314/470, loss: 0.08050384372472763
2023-01-22 19:22:54.090276: step: 316/470, loss: 0.03150481358170509
2023-01-22 19:22:54.794698: step: 318/470, loss: 0.027586523443460464
2023-01-22 19:22:55.531962: step: 320/470, loss: 0.00899940449744463
2023-01-22 19:22:56.247863: step: 322/470, loss: 0.02793573960661888
2023-01-22 19:22:57.051736: step: 324/470, loss: 0.04435381293296814
2023-01-22 19:22:57.723682: step: 326/470, loss: 0.037694673985242844
2023-01-22 19:22:58.493012: step: 328/470, loss: 0.8200516700744629
2023-01-22 19:22:59.237806: step: 330/470, loss: 0.02281474508345127
2023-01-22 19:23:00.003086: step: 332/470, loss: 0.09635286033153534
2023-01-22 19:23:00.784905: step: 334/470, loss: 0.15880021452903748
2023-01-22 19:23:01.503427: step: 336/470, loss: 0.00870030838996172
2023-01-22 19:23:02.225178: step: 338/470, loss: 0.0723002627491951
2023-01-22 19:23:03.054096: step: 340/470, loss: 0.07791668176651001
2023-01-22 19:23:03.807530: step: 342/470, loss: 0.041542887687683105
2023-01-22 19:23:04.544401: step: 344/470, loss: 0.07663816213607788
2023-01-22 19:23:05.247814: step: 346/470, loss: 0.02207820490002632
2023-01-22 19:23:05.981158: step: 348/470, loss: 0.11398249864578247
2023-01-22 19:23:06.765153: step: 350/470, loss: 0.06222032010555267
2023-01-22 19:23:07.457969: step: 352/470, loss: 0.7580427527427673
2023-01-22 19:23:08.132136: step: 354/470, loss: 0.31359562277793884
2023-01-22 19:23:08.856713: step: 356/470, loss: 0.09936029464006424
2023-01-22 19:23:09.538731: step: 358/470, loss: 0.10575620830059052
2023-01-22 19:23:10.213620: step: 360/470, loss: 0.08771451562643051
2023-01-22 19:23:10.993458: step: 362/470, loss: 0.045165304094552994
2023-01-22 19:23:11.736430: step: 364/470, loss: 0.08250702917575836
2023-01-22 19:23:12.486359: step: 366/470, loss: 0.036362942308187485
2023-01-22 19:23:13.259469: step: 368/470, loss: 0.035159844905138016
2023-01-22 19:23:13.936694: step: 370/470, loss: 0.06006016209721565
2023-01-22 19:23:14.694024: step: 372/470, loss: 0.11637677252292633
2023-01-22 19:23:15.474595: step: 374/470, loss: 0.012416702695190907
2023-01-22 19:23:16.233723: step: 376/470, loss: 0.1937997043132782
2023-01-22 19:23:16.937275: step: 378/470, loss: 0.0882231742143631
2023-01-22 19:23:17.655984: step: 380/470, loss: 0.015106822364032269
2023-01-22 19:23:18.356817: step: 382/470, loss: 0.1471942663192749
2023-01-22 19:23:19.079151: step: 384/470, loss: 0.024438517168164253
2023-01-22 19:23:19.822131: step: 386/470, loss: 0.015194579027593136
2023-01-22 19:23:20.536166: step: 388/470, loss: 0.18839724361896515
2023-01-22 19:23:21.380251: step: 390/470, loss: 0.05323400720953941
2023-01-22 19:23:22.069502: step: 392/470, loss: 0.06262640655040741
2023-01-22 19:23:22.774626: step: 394/470, loss: 0.052381135523319244
2023-01-22 19:23:23.472595: step: 396/470, loss: 0.1799657940864563
2023-01-22 19:23:24.182306: step: 398/470, loss: 0.004220017232000828
2023-01-22 19:23:24.939874: step: 400/470, loss: 0.4785889685153961
2023-01-22 19:23:25.626890: step: 402/470, loss: 0.03493707254528999
2023-01-22 19:23:26.328670: step: 404/470, loss: 0.07729945331811905
2023-01-22 19:23:27.141827: step: 406/470, loss: 0.1558285653591156
2023-01-22 19:23:28.059616: step: 408/470, loss: 0.14127235114574432
2023-01-22 19:23:28.828024: step: 410/470, loss: 0.24950149655342102
2023-01-22 19:23:29.589954: step: 412/470, loss: 0.041239332407712936
2023-01-22 19:23:30.272262: step: 414/470, loss: 0.2635876536369324
2023-01-22 19:23:31.040628: step: 416/470, loss: 0.10579922795295715
2023-01-22 19:23:31.763657: step: 418/470, loss: 0.03441992029547691
2023-01-22 19:23:32.599285: step: 420/470, loss: 0.032621387392282486
2023-01-22 19:23:33.422928: step: 422/470, loss: 0.05008916184306145
2023-01-22 19:23:34.156681: step: 424/470, loss: 0.13900715112686157
2023-01-22 19:23:34.878977: step: 426/470, loss: 0.023830300197005272
2023-01-22 19:23:35.647493: step: 428/470, loss: 0.03306613117456436
2023-01-22 19:23:36.339882: step: 430/470, loss: 0.014829058200120926
2023-01-22 19:23:37.136646: step: 432/470, loss: 0.042442865669727325
2023-01-22 19:23:37.899929: step: 434/470, loss: 0.32640278339385986
2023-01-22 19:23:38.639286: step: 436/470, loss: 0.010043848305940628
2023-01-22 19:23:39.377640: step: 438/470, loss: 0.017869826406240463
2023-01-22 19:23:40.088560: step: 440/470, loss: 0.1027931347489357
2023-01-22 19:23:40.807937: step: 442/470, loss: 0.0788130909204483
2023-01-22 19:23:41.506477: step: 444/470, loss: 0.12138024717569351
2023-01-22 19:23:42.244356: step: 446/470, loss: 0.01406558882445097
2023-01-22 19:23:42.976507: step: 448/470, loss: 0.004238845780491829
2023-01-22 19:23:43.812107: step: 450/470, loss: 0.0067049539647996426
2023-01-22 19:23:44.539949: step: 452/470, loss: 0.04448673129081726
2023-01-22 19:23:45.333396: step: 454/470, loss: 0.3222072422504425
2023-01-22 19:23:46.005063: step: 456/470, loss: 0.4006147086620331
2023-01-22 19:23:46.778755: step: 458/470, loss: 0.1256273090839386
2023-01-22 19:23:47.465175: step: 460/470, loss: 0.014067552983760834
2023-01-22 19:23:48.214471: step: 462/470, loss: 0.030554937198758125
2023-01-22 19:23:48.911074: step: 464/470, loss: 0.05165807902812958
2023-01-22 19:23:49.627001: step: 466/470, loss: 0.0559585839509964
2023-01-22 19:23:50.371735: step: 468/470, loss: 0.751693844795227
2023-01-22 19:23:51.105770: step: 470/470, loss: 0.042564861476421356
2023-01-22 19:23:51.828637: step: 472/470, loss: 0.04895629733800888
2023-01-22 19:23:52.636709: step: 474/470, loss: 0.037162844091653824
2023-01-22 19:23:53.397657: step: 476/470, loss: 0.025382233783602715
2023-01-22 19:23:54.145907: step: 478/470, loss: 0.06292865425348282
2023-01-22 19:23:54.926520: step: 480/470, loss: 0.014180587604641914
2023-01-22 19:23:55.782702: step: 482/470, loss: 0.027322018519043922
2023-01-22 19:23:56.553850: step: 484/470, loss: 0.1358848214149475
2023-01-22 19:23:57.235051: step: 486/470, loss: 0.050086334347724915
2023-01-22 19:23:57.959494: step: 488/470, loss: 0.01673760637640953
2023-01-22 19:23:58.660760: step: 490/470, loss: 0.021020902320742607
2023-01-22 19:23:59.356798: step: 492/470, loss: 0.015545294620096684
2023-01-22 19:24:00.092202: step: 494/470, loss: 0.3143145740032196
2023-01-22 19:24:00.844180: step: 496/470, loss: 0.0633402094244957
2023-01-22 19:24:01.582114: step: 498/470, loss: 0.018096817657351494
2023-01-22 19:24:02.327989: step: 500/470, loss: 0.0012216436443850398
2023-01-22 19:24:03.050670: step: 502/470, loss: 0.1902422159910202
2023-01-22 19:24:03.823157: step: 504/470, loss: 0.07036527991294861
2023-01-22 19:24:04.625708: step: 506/470, loss: 0.06424633413553238
2023-01-22 19:24:05.362567: step: 508/470, loss: 0.0811762586236
2023-01-22 19:24:06.094200: step: 510/470, loss: 0.06267711520195007
2023-01-22 19:24:06.960309: step: 512/470, loss: 0.023827198892831802
2023-01-22 19:24:07.696632: step: 514/470, loss: 0.028254536911845207
2023-01-22 19:24:08.393815: step: 516/470, loss: 0.012615739367902279
2023-01-22 19:24:09.048379: step: 518/470, loss: 0.12324491143226624
2023-01-22 19:24:09.754972: step: 520/470, loss: 0.08821484446525574
2023-01-22 19:24:10.477950: step: 522/470, loss: 0.01370615977793932
2023-01-22 19:24:11.219725: step: 524/470, loss: 0.02321157045662403
2023-01-22 19:24:11.889587: step: 526/470, loss: 0.02410917542874813
2023-01-22 19:24:12.636406: step: 528/470, loss: 0.052108101546764374
2023-01-22 19:24:13.356301: step: 530/470, loss: 0.0737091451883316
2023-01-22 19:24:14.070779: step: 532/470, loss: 0.05240051448345184
2023-01-22 19:24:14.750411: step: 534/470, loss: 0.14461572468280792
2023-01-22 19:24:15.443093: step: 536/470, loss: 0.06819018721580505
2023-01-22 19:24:16.200799: step: 538/470, loss: 0.08415396511554718
2023-01-22 19:24:16.874576: step: 540/470, loss: 0.039721451699733734
2023-01-22 19:24:17.623755: step: 542/470, loss: 0.24157670140266418
2023-01-22 19:24:18.323053: step: 544/470, loss: 0.05411506071686745
2023-01-22 19:24:19.228137: step: 546/470, loss: 0.07562316954135895
2023-01-22 19:24:19.961701: step: 548/470, loss: 0.1613171249628067
2023-01-22 19:24:20.634580: step: 550/470, loss: 0.04178428277373314
2023-01-22 19:24:21.364654: step: 552/470, loss: 0.014160760678350925
2023-01-22 19:24:22.114479: step: 554/470, loss: 0.04917175695300102
2023-01-22 19:24:22.823697: step: 556/470, loss: 0.01794840767979622
2023-01-22 19:24:23.595418: step: 558/470, loss: 0.07323423773050308
2023-01-22 19:24:24.342951: step: 560/470, loss: 0.014605486765503883
2023-01-22 19:24:25.008139: step: 562/470, loss: 0.07594714313745499
2023-01-22 19:24:25.704587: step: 564/470, loss: 0.029397977516055107
2023-01-22 19:24:26.455916: step: 566/470, loss: 0.01664639636874199
2023-01-22 19:24:27.315643: step: 568/470, loss: 0.02191932313144207
2023-01-22 19:24:27.986309: step: 570/470, loss: 0.06313026696443558
2023-01-22 19:24:28.741002: step: 572/470, loss: 0.022390831261873245
2023-01-22 19:24:29.472324: step: 574/470, loss: 0.16852179169654846
2023-01-22 19:24:30.185697: step: 576/470, loss: 0.041340142488479614
2023-01-22 19:24:30.963406: step: 578/470, loss: 0.0978948175907135
2023-01-22 19:24:31.868249: step: 580/470, loss: 0.10298915952444077
2023-01-22 19:24:32.654203: step: 582/470, loss: 0.051485490053892136
2023-01-22 19:24:33.526026: step: 584/470, loss: 0.03344123065471649
2023-01-22 19:24:34.325303: step: 586/470, loss: 0.03898704797029495
2023-01-22 19:24:35.022885: step: 588/470, loss: 0.15321972966194153
2023-01-22 19:24:35.712909: step: 590/470, loss: 0.3100159466266632
2023-01-22 19:24:36.490436: step: 592/470, loss: 0.03277548775076866
2023-01-22 19:24:37.175190: step: 594/470, loss: 0.06358427554368973
2023-01-22 19:24:38.056103: step: 596/470, loss: 0.21886910498142242
2023-01-22 19:24:38.766804: step: 598/470, loss: 0.06400435417890549
2023-01-22 19:24:39.580191: step: 600/470, loss: 0.021453171968460083
2023-01-22 19:24:40.287321: step: 602/470, loss: 0.029457837343215942
2023-01-22 19:24:41.078703: step: 604/470, loss: 0.06845896691083908
2023-01-22 19:24:41.828807: step: 606/470, loss: 0.33153408765792847
2023-01-22 19:24:42.587636: step: 608/470, loss: 0.40867775678634644
2023-01-22 19:24:43.364159: step: 610/470, loss: 0.8713477849960327
2023-01-22 19:24:44.069051: step: 612/470, loss: 0.05822436138987541
2023-01-22 19:24:44.797396: step: 614/470, loss: 0.01446563471108675
2023-01-22 19:24:45.569005: step: 616/470, loss: 0.05371719226241112
2023-01-22 19:24:46.396025: step: 618/470, loss: 0.22751787304878235
2023-01-22 19:24:47.151667: step: 620/470, loss: 0.20397146046161652
2023-01-22 19:24:47.901919: step: 622/470, loss: 0.041325464844703674
2023-01-22 19:24:48.628850: step: 624/470, loss: 0.0995861068367958
2023-01-22 19:24:49.318558: step: 626/470, loss: 0.4585106074810028
2023-01-22 19:24:50.028984: step: 628/470, loss: 0.11708439886569977
2023-01-22 19:24:50.756652: step: 630/470, loss: 0.07522755861282349
2023-01-22 19:24:51.498027: step: 632/470, loss: 0.9740254878997803
2023-01-22 19:24:52.224520: step: 634/470, loss: 0.32297220826148987
2023-01-22 19:24:53.091530: step: 636/470, loss: 0.03178303316235542
2023-01-22 19:24:53.876604: step: 638/470, loss: 0.07319549471139908
2023-01-22 19:24:54.611177: step: 640/470, loss: 0.02889355830848217
2023-01-22 19:24:55.352013: step: 642/470, loss: 0.10229209810495377
2023-01-22 19:24:56.051614: step: 644/470, loss: 0.039184339344501495
2023-01-22 19:24:56.795497: step: 646/470, loss: 0.07694227993488312
2023-01-22 19:24:57.511291: step: 648/470, loss: 0.10057219117879868
2023-01-22 19:24:58.221588: step: 650/470, loss: 0.05900505557656288
2023-01-22 19:24:58.974136: step: 652/470, loss: 0.03375502675771713
2023-01-22 19:24:59.673402: step: 654/470, loss: 0.011107545346021652
2023-01-22 19:25:00.453336: step: 656/470, loss: 0.04302780702710152
2023-01-22 19:25:01.153844: step: 658/470, loss: 0.05545317381620407
2023-01-22 19:25:01.850795: step: 660/470, loss: 0.1119319424033165
2023-01-22 19:25:02.637076: step: 662/470, loss: 0.043362777680158615
2023-01-22 19:25:03.380577: step: 664/470, loss: 0.1941765397787094
2023-01-22 19:25:04.106647: step: 666/470, loss: 0.06740397959947586
2023-01-22 19:25:04.777399: step: 668/470, loss: 0.04577159881591797
2023-01-22 19:25:05.490071: step: 670/470, loss: 0.11848827451467514
2023-01-22 19:25:06.237748: step: 672/470, loss: 0.03170297294855118
2023-01-22 19:25:06.927019: step: 674/470, loss: 0.14291562139987946
2023-01-22 19:25:07.604685: step: 676/470, loss: 0.07052916288375854
2023-01-22 19:25:08.336869: step: 678/470, loss: 0.08889731764793396
2023-01-22 19:25:09.057863: step: 680/470, loss: 0.18591055274009705
2023-01-22 19:25:09.798789: step: 682/470, loss: 0.058656156063079834
2023-01-22 19:25:10.552769: step: 684/470, loss: 0.06513772159814835
2023-01-22 19:25:11.282517: step: 686/470, loss: 0.10984183102846146
2023-01-22 19:25:12.000373: step: 688/470, loss: 0.07132207602262497
2023-01-22 19:25:12.727972: step: 690/470, loss: 0.020248308777809143
2023-01-22 19:25:13.368225: step: 692/470, loss: 0.07261063158512115
2023-01-22 19:25:14.176736: step: 694/470, loss: 0.03563803806900978
2023-01-22 19:25:15.000786: step: 696/470, loss: 0.0738886147737503
2023-01-22 19:25:15.807954: step: 698/470, loss: 0.06751029938459396
2023-01-22 19:25:16.578859: step: 700/470, loss: 0.23834992945194244
2023-01-22 19:25:17.262020: step: 702/470, loss: 0.013831811025738716
2023-01-22 19:25:18.001714: step: 704/470, loss: 0.3347160816192627
2023-01-22 19:25:18.762991: step: 706/470, loss: 0.05514927953481674
2023-01-22 19:25:19.516843: step: 708/470, loss: 0.16086360812187195
2023-01-22 19:25:20.239281: step: 710/470, loss: 0.011491565965116024
2023-01-22 19:25:21.066616: step: 712/470, loss: 0.09873014688491821
2023-01-22 19:25:21.812592: step: 714/470, loss: 0.10902773588895798
2023-01-22 19:25:22.503661: step: 716/470, loss: 0.018024688586592674
2023-01-22 19:25:23.218998: step: 718/470, loss: 0.046969544142484665
2023-01-22 19:25:23.889410: step: 720/470, loss: 0.4311079680919647
2023-01-22 19:25:24.613146: step: 722/470, loss: 0.0782650038599968
2023-01-22 19:25:25.247505: step: 724/470, loss: 0.35217511653900146
2023-01-22 19:25:25.989395: step: 726/470, loss: 0.07346347719430923
2023-01-22 19:25:26.743591: step: 728/470, loss: 0.09162180125713348
2023-01-22 19:25:27.579429: step: 730/470, loss: 0.10204845666885376
2023-01-22 19:25:28.323196: step: 732/470, loss: 0.009644899517297745
2023-01-22 19:25:29.158414: step: 734/470, loss: 0.0478099063038826
2023-01-22 19:25:29.854635: step: 736/470, loss: 0.07511983066797256
2023-01-22 19:25:30.503683: step: 738/470, loss: 0.06089290976524353
2023-01-22 19:25:31.235281: step: 740/470, loss: 0.05333712324500084
2023-01-22 19:25:32.000536: step: 742/470, loss: 0.04015492647886276
2023-01-22 19:25:32.721305: step: 744/470, loss: 0.04333452507853508
2023-01-22 19:25:33.487827: step: 746/470, loss: 0.11922835558652878
2023-01-22 19:25:34.217857: step: 748/470, loss: 0.03594861179590225
2023-01-22 19:25:34.884313: step: 750/470, loss: 0.06654554605484009
2023-01-22 19:25:35.680558: step: 752/470, loss: 0.07238250225782394
2023-01-22 19:25:36.505843: step: 754/470, loss: 0.08213133364915848
2023-01-22 19:25:37.272944: step: 756/470, loss: 0.08642800152301788
2023-01-22 19:25:37.986174: step: 758/470, loss: 0.06127552315592766
2023-01-22 19:25:38.762573: step: 760/470, loss: 0.05956351384520531
2023-01-22 19:25:39.451235: step: 762/470, loss: 0.03790678456425667
2023-01-22 19:25:40.125595: step: 764/470, loss: 0.00936797820031643
2023-01-22 19:25:40.967501: step: 766/470, loss: 0.07397977262735367
2023-01-22 19:25:41.703526: step: 768/470, loss: 0.049599699676036835
2023-01-22 19:25:42.449141: step: 770/470, loss: 0.04407091066241264
2023-01-22 19:25:43.308989: step: 772/470, loss: 0.02440464124083519
2023-01-22 19:25:44.085496: step: 774/470, loss: 0.015560795553028584
2023-01-22 19:25:44.826980: step: 776/470, loss: 0.03959346562623978
2023-01-22 19:25:45.614542: step: 778/470, loss: 0.014441375620663166
2023-01-22 19:25:46.371698: step: 780/470, loss: 0.02576235495507717
2023-01-22 19:25:47.030848: step: 782/470, loss: 0.06063159555196762
2023-01-22 19:25:47.733488: step: 784/470, loss: 0.005881750024855137
2023-01-22 19:25:48.550789: step: 786/470, loss: 0.019624939188361168
2023-01-22 19:25:49.366869: step: 788/470, loss: 0.016726138070225716
2023-01-22 19:25:50.200662: step: 790/470, loss: 0.044762153178453445
2023-01-22 19:25:50.978750: step: 792/470, loss: 0.017699047923088074
2023-01-22 19:25:51.719409: step: 794/470, loss: 0.03728308528661728
2023-01-22 19:25:52.436993: step: 796/470, loss: 0.01777748577296734
2023-01-22 19:25:53.166070: step: 798/470, loss: 0.20916269719600677
2023-01-22 19:25:53.924386: step: 800/470, loss: 0.13329799473285675
2023-01-22 19:25:54.676672: step: 802/470, loss: 0.01543135941028595
2023-01-22 19:25:55.385634: step: 804/470, loss: 0.0656021237373352
2023-01-22 19:25:56.127476: step: 806/470, loss: 0.027505187317728996
2023-01-22 19:25:56.885223: step: 808/470, loss: 0.10071372240781784
2023-01-22 19:25:57.638773: step: 810/470, loss: 0.10161048173904419
2023-01-22 19:25:58.395684: step: 812/470, loss: 0.006511330138891935
2023-01-22 19:25:59.227934: step: 814/470, loss: 0.05376344919204712
2023-01-22 19:25:59.941956: step: 816/470, loss: 0.07200208306312561
2023-01-22 19:26:00.639760: step: 818/470, loss: 0.05889580398797989
2023-01-22 19:26:01.357005: step: 820/470, loss: 0.009265481494367123
2023-01-22 19:26:02.118498: step: 822/470, loss: 0.12977077066898346
2023-01-22 19:26:02.820893: step: 824/470, loss: 0.041659578680992126
2023-01-22 19:26:03.698665: step: 826/470, loss: 0.29780128598213196
2023-01-22 19:26:04.436006: step: 828/470, loss: 0.027976591140031815
2023-01-22 19:26:05.219766: step: 830/470, loss: 0.1818331480026245
2023-01-22 19:26:06.024063: step: 832/470, loss: 0.04622675105929375
2023-01-22 19:26:06.713292: step: 834/470, loss: 0.061723433434963226
2023-01-22 19:26:07.411587: step: 836/470, loss: 0.1804792582988739
2023-01-22 19:26:08.219146: step: 838/470, loss: 0.08750531077384949
2023-01-22 19:26:09.018525: step: 840/470, loss: 0.12658429145812988
2023-01-22 19:26:09.804297: step: 842/470, loss: 0.029569925740361214
2023-01-22 19:26:10.528423: step: 844/470, loss: 0.01851717382669449
2023-01-22 19:26:11.339495: step: 846/470, loss: 0.0617799237370491
2023-01-22 19:26:12.100105: step: 848/470, loss: 0.016349801793694496
2023-01-22 19:26:12.799633: step: 850/470, loss: 0.11626914143562317
2023-01-22 19:26:13.467146: step: 852/470, loss: 0.24209186434745789
2023-01-22 19:26:14.170058: step: 854/470, loss: 0.056616343557834625
2023-01-22 19:26:14.955600: step: 856/470, loss: 0.18732884526252747
2023-01-22 19:26:15.696329: step: 858/470, loss: 0.05298414081335068
2023-01-22 19:26:16.450679: step: 860/470, loss: 0.42847129702568054
2023-01-22 19:26:17.238470: step: 862/470, loss: 0.033945754170417786
2023-01-22 19:26:18.018095: step: 864/470, loss: 0.026322832331061363
2023-01-22 19:26:18.740843: step: 866/470, loss: 0.02989846095442772
2023-01-22 19:26:19.464544: step: 868/470, loss: 0.3587307929992676
2023-01-22 19:26:20.242980: step: 870/470, loss: 0.05438103526830673
2023-01-22 19:26:20.971928: step: 872/470, loss: 0.04368476942181587
2023-01-22 19:26:21.751252: step: 874/470, loss: 0.03072342276573181
2023-01-22 19:26:22.527408: step: 876/470, loss: 0.21938635408878326
2023-01-22 19:26:23.189313: step: 878/470, loss: 0.08039675652980804
2023-01-22 19:26:23.881985: step: 880/470, loss: 0.010841970331966877
2023-01-22 19:26:24.613259: step: 882/470, loss: 0.043295301496982574
2023-01-22 19:26:25.338566: step: 884/470, loss: 0.013651460409164429
2023-01-22 19:26:26.045822: step: 886/470, loss: 0.2560485005378723
2023-01-22 19:26:26.736924: step: 888/470, loss: 0.021218927577137947
2023-01-22 19:26:27.425264: step: 890/470, loss: 0.054894767701625824
2023-01-22 19:26:28.145881: step: 892/470, loss: 0.0300539992749691
2023-01-22 19:26:28.869388: step: 894/470, loss: 0.0708957314491272
2023-01-22 19:26:29.565805: step: 896/470, loss: 0.09575964510440826
2023-01-22 19:26:30.272118: step: 898/470, loss: 0.031115295365452766
2023-01-22 19:26:31.008150: step: 900/470, loss: 0.06746406108140945
2023-01-22 19:26:31.788680: step: 902/470, loss: 0.06835021823644638
2023-01-22 19:26:32.511563: step: 904/470, loss: 0.021396541967988014
2023-01-22 19:26:33.252245: step: 906/470, loss: 0.02145826816558838
2023-01-22 19:26:33.961505: step: 908/470, loss: 0.1311969757080078
2023-01-22 19:26:34.773935: step: 910/470, loss: 0.13202637434005737
2023-01-22 19:26:35.462704: step: 912/470, loss: 0.04499669000506401
2023-01-22 19:26:36.242471: step: 914/470, loss: 0.11342813074588776
2023-01-22 19:26:36.911200: step: 916/470, loss: 0.898378849029541
2023-01-22 19:26:37.753117: step: 918/470, loss: 0.10744353383779526
2023-01-22 19:26:38.568255: step: 920/470, loss: 0.026462199166417122
2023-01-22 19:26:39.286728: step: 922/470, loss: 0.5927501916885376
2023-01-22 19:26:39.943236: step: 924/470, loss: 0.03971520811319351
2023-01-22 19:26:40.647310: step: 926/470, loss: 0.052058689296245575
2023-01-22 19:26:41.406869: step: 928/470, loss: 0.06348146498203278
2023-01-22 19:26:42.068594: step: 930/470, loss: 0.05130045861005783
2023-01-22 19:26:42.717494: step: 932/470, loss: 0.01657716929912567
2023-01-22 19:26:43.390175: step: 934/470, loss: 3.5439648628234863
2023-01-22 19:26:44.164325: step: 936/470, loss: 0.11058296263217926
2023-01-22 19:26:44.932370: step: 938/470, loss: 0.07302563637495041
2023-01-22 19:26:45.624156: step: 940/470, loss: 0.0987381637096405
2023-01-22 19:26:46.284137: step: 942/470, loss: 0.04440511763095856
==================================================
Loss: 0.110
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28893526058631924, 'r': 0.3366342504743833, 'f1': 0.31096625766871167}, 'combined': 0.2291330319664191, 'epoch': 20}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3276979133967761, 'r': 0.35322053934402503, 'f1': 0.3399808985819398}, 'combined': 0.23680261592771928, 'epoch': 20}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28683624356823917, 'r': 0.33691012290083505, 'f1': 0.30986323694369994}, 'combined': 0.22832027985325257, 'epoch': 20}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33326832341093904, 'r': 0.3589043482887036, 'f1': 0.34561159464838126}, 'combined': 0.24072449378494218, 'epoch': 20}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26346369760479044, 'r': 0.3339539848197344, 'f1': 0.29455020920502095}, 'combined': 0.21703699625633122, 'epoch': 20}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32420125946602074, 'r': 0.36815546868208704, 'f1': 0.3447831494186137}, 'combined': 0.24014746725674588, 'epoch': 20}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.19285714285714284, 'r': 0.3581632653061224, 'f1': 0.25071428571428567}, 'combined': 0.1671428571428571, 'epoch': 20}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2948717948717949, 'r': 0.5, 'f1': 0.3709677419354839}, 'combined': 0.18548387096774194, 'epoch': 20}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4642857142857143, 'r': 0.33620689655172414, 'f1': 0.39}, 'combined': 0.26, 'epoch': 20}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 21
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 19:29:24.828754: step: 2/470, loss: 0.030697286128997803
2023-01-22 19:29:25.660760: step: 4/470, loss: 0.8990464210510254
2023-01-22 19:29:26.364584: step: 6/470, loss: 0.012093383818864822
2023-01-22 19:29:27.052579: step: 8/470, loss: 0.04054703935980797
2023-01-22 19:29:27.805467: step: 10/470, loss: 0.0492924265563488
2023-01-22 19:29:28.563801: step: 12/470, loss: 0.043698910623788834
2023-01-22 19:29:29.361869: step: 14/470, loss: 0.052403904497623444
2023-01-22 19:29:30.036385: step: 16/470, loss: 0.04030047729611397
2023-01-22 19:29:30.884191: step: 18/470, loss: 0.04345276579260826
2023-01-22 19:29:31.630786: step: 20/470, loss: 0.07873324304819107
2023-01-22 19:29:32.389365: step: 22/470, loss: 0.020181206986308098
2023-01-22 19:29:33.151588: step: 24/470, loss: 0.013497297652065754
2023-01-22 19:29:33.937687: step: 26/470, loss: 0.017897669225931168
2023-01-22 19:29:34.857220: step: 28/470, loss: 0.0618402361869812
2023-01-22 19:29:35.578584: step: 30/470, loss: 0.07274410128593445
2023-01-22 19:29:36.270042: step: 32/470, loss: 0.020234020426869392
2023-01-22 19:29:37.096449: step: 34/470, loss: 0.06494118273258209
2023-01-22 19:29:37.825333: step: 36/470, loss: 0.021747954189777374
2023-01-22 19:29:38.595629: step: 38/470, loss: 0.05529887601733208
2023-01-22 19:29:39.361953: step: 40/470, loss: 1.0049673318862915
2023-01-22 19:29:40.148224: step: 42/470, loss: 0.11773818731307983
2023-01-22 19:29:40.869593: step: 44/470, loss: 0.04687252268195152
2023-01-22 19:29:41.553815: step: 46/470, loss: 0.09744272381067276
2023-01-22 19:29:42.270009: step: 48/470, loss: 0.039838120341300964
2023-01-22 19:29:43.026035: step: 50/470, loss: 0.06667645275592804
2023-01-22 19:29:43.864454: step: 52/470, loss: 0.023879552260041237
2023-01-22 19:29:44.586481: step: 54/470, loss: 0.008113712072372437
2023-01-22 19:29:45.313847: step: 56/470, loss: 0.03958437219262123
2023-01-22 19:29:46.099345: step: 58/470, loss: 0.1176476776599884
2023-01-22 19:29:46.895163: step: 60/470, loss: 0.07839195430278778
2023-01-22 19:29:47.564077: step: 62/470, loss: 0.02542118728160858
2023-01-22 19:29:48.292175: step: 64/470, loss: 0.680618166923523
2023-01-22 19:29:49.006436: step: 66/470, loss: 0.017299430444836617
2023-01-22 19:29:49.695845: step: 68/470, loss: 0.02113557793200016
2023-01-22 19:29:50.433614: step: 70/470, loss: 0.16099169850349426
2023-01-22 19:29:51.180853: step: 72/470, loss: 0.04751966521143913
2023-01-22 19:29:51.920061: step: 74/470, loss: 0.04941952973604202
2023-01-22 19:29:52.642857: step: 76/470, loss: 1.7027865648269653
2023-01-22 19:29:53.352004: step: 78/470, loss: 0.025158904492855072
2023-01-22 19:29:54.133981: step: 80/470, loss: 0.05669613182544708
2023-01-22 19:29:54.893899: step: 82/470, loss: 0.11963464319705963
2023-01-22 19:29:55.646415: step: 84/470, loss: 0.047465141862630844
2023-01-22 19:29:56.413729: step: 86/470, loss: 0.0787685364484787
2023-01-22 19:29:57.245225: step: 88/470, loss: 0.044626928865909576
2023-01-22 19:29:57.945829: step: 90/470, loss: 0.0552486777305603
2023-01-22 19:29:58.636617: step: 92/470, loss: 0.006156580988317728
2023-01-22 19:29:59.305495: step: 94/470, loss: 0.11764095723628998
2023-01-22 19:30:00.051506: step: 96/470, loss: 0.03031170181930065
2023-01-22 19:30:00.817572: step: 98/470, loss: 0.029158277437090874
2023-01-22 19:30:01.466201: step: 100/470, loss: 0.03246721625328064
2023-01-22 19:30:02.302918: step: 102/470, loss: 0.016130754724144936
2023-01-22 19:30:03.162916: step: 104/470, loss: 0.05944613739848137
2023-01-22 19:30:03.976766: step: 106/470, loss: 0.034837506711483
2023-01-22 19:30:04.717706: step: 108/470, loss: 0.19040045142173767
2023-01-22 19:30:05.419688: step: 110/470, loss: 0.04526451230049133
2023-01-22 19:30:06.138937: step: 112/470, loss: 0.02529776096343994
2023-01-22 19:30:06.767639: step: 114/470, loss: 0.030075442045927048
2023-01-22 19:30:07.500813: step: 116/470, loss: 0.2894465923309326
2023-01-22 19:30:08.216586: step: 118/470, loss: 0.02525232918560505
2023-01-22 19:30:09.026654: step: 120/470, loss: 1.0722471475601196
2023-01-22 19:30:09.727629: step: 122/470, loss: 0.020707713440060616
2023-01-22 19:30:10.412024: step: 124/470, loss: 0.015486765652894974
2023-01-22 19:30:11.089030: step: 126/470, loss: 0.031173061579465866
2023-01-22 19:30:11.877263: step: 128/470, loss: 0.02271159552037716
2023-01-22 19:30:12.619707: step: 130/470, loss: 0.035077158361673355
2023-01-22 19:30:13.394357: step: 132/470, loss: 0.024227894842624664
2023-01-22 19:30:14.265265: step: 134/470, loss: 0.03320540860295296
2023-01-22 19:30:15.019653: step: 136/470, loss: 0.03366602584719658
2023-01-22 19:30:15.673853: step: 138/470, loss: 0.28107237815856934
2023-01-22 19:30:16.385762: step: 140/470, loss: 0.06899859011173248
2023-01-22 19:30:17.048384: step: 142/470, loss: 0.008150143548846245
2023-01-22 19:30:17.790891: step: 144/470, loss: 0.03204032778739929
2023-01-22 19:30:18.407103: step: 146/470, loss: 0.0016799191944301128
2023-01-22 19:30:19.234610: step: 148/470, loss: 0.021955549716949463
2023-01-22 19:30:19.947374: step: 150/470, loss: 0.03780049830675125
2023-01-22 19:30:20.650690: step: 152/470, loss: 0.007639870513230562
2023-01-22 19:30:21.437746: step: 154/470, loss: 0.06269722431898117
2023-01-22 19:30:22.194983: step: 156/470, loss: 0.025132397189736366
2023-01-22 19:30:22.936233: step: 158/470, loss: 0.07948961853981018
2023-01-22 19:30:23.585679: step: 160/470, loss: 0.005530932452529669
2023-01-22 19:30:24.358812: step: 162/470, loss: 0.10777927935123444
2023-01-22 19:30:25.059373: step: 164/470, loss: 0.07513689249753952
2023-01-22 19:30:26.034196: step: 166/470, loss: 0.013257588259875774
2023-01-22 19:30:26.774295: step: 168/470, loss: 0.1652069240808487
2023-01-22 19:30:27.542879: step: 170/470, loss: 0.007435483392328024
2023-01-22 19:30:28.316841: step: 172/470, loss: 0.07258084416389465
2023-01-22 19:30:29.230700: step: 174/470, loss: 0.043368544429540634
2023-01-22 19:30:30.087181: step: 176/470, loss: 0.0565069355070591
2023-01-22 19:30:30.779742: step: 178/470, loss: 0.04345664754509926
2023-01-22 19:30:31.426331: step: 180/470, loss: 0.008021237328648567
2023-01-22 19:30:32.232487: step: 182/470, loss: 0.0683949664235115
2023-01-22 19:30:33.026399: step: 184/470, loss: 0.04733900725841522
2023-01-22 19:30:33.706471: step: 186/470, loss: 0.14194054901599884
2023-01-22 19:30:34.454037: step: 188/470, loss: 0.06841456145048141
2023-01-22 19:30:35.252236: step: 190/470, loss: 0.01492251455783844
2023-01-22 19:30:35.914837: step: 192/470, loss: 0.07086261361837387
2023-01-22 19:30:36.638908: step: 194/470, loss: 0.16320353746414185
2023-01-22 19:30:37.410915: step: 196/470, loss: 0.08280780166387558
2023-01-22 19:30:38.102373: step: 198/470, loss: 0.017911670729517937
2023-01-22 19:30:38.875257: step: 200/470, loss: 0.08260060846805573
2023-01-22 19:30:39.629995: step: 202/470, loss: 0.044123224914073944
2023-01-22 19:30:40.315590: step: 204/470, loss: 0.010030948556959629
2023-01-22 19:30:41.002820: step: 206/470, loss: 0.0387822724878788
2023-01-22 19:30:41.720360: step: 208/470, loss: 0.034351300448179245
2023-01-22 19:30:42.556713: step: 210/470, loss: 0.010738598182797432
2023-01-22 19:30:43.290100: step: 212/470, loss: 0.06208763271570206
2023-01-22 19:30:44.081214: step: 214/470, loss: 0.08142954856157303
2023-01-22 19:30:44.800270: step: 216/470, loss: 0.0489891953766346
2023-01-22 19:30:45.566872: step: 218/470, loss: 0.05691111460328102
2023-01-22 19:30:46.285085: step: 220/470, loss: 0.10647915303707123
2023-01-22 19:30:46.999998: step: 222/470, loss: 0.029838304966688156
2023-01-22 19:30:47.860497: step: 224/470, loss: 0.043678972870111465
2023-01-22 19:30:48.592560: step: 226/470, loss: 0.039795830845832825
2023-01-22 19:30:49.292865: step: 228/470, loss: 0.0034092552959918976
2023-01-22 19:30:50.027415: step: 230/470, loss: 0.05187808722257614
2023-01-22 19:30:50.829509: step: 232/470, loss: 0.022801529616117477
2023-01-22 19:30:51.562542: step: 234/470, loss: 0.0022835489362478256
2023-01-22 19:30:52.262073: step: 236/470, loss: 0.060452841222286224
2023-01-22 19:30:52.961652: step: 238/470, loss: 0.17915183305740356
2023-01-22 19:30:53.755491: step: 240/470, loss: 0.04132472351193428
2023-01-22 19:30:54.414850: step: 242/470, loss: 0.027403315529227257
2023-01-22 19:30:55.185576: step: 244/470, loss: 0.034430038183927536
2023-01-22 19:30:55.957383: step: 246/470, loss: 0.31158602237701416
2023-01-22 19:30:56.731659: step: 248/470, loss: 0.007013510912656784
2023-01-22 19:30:57.425983: step: 250/470, loss: 0.0664106085896492
2023-01-22 19:30:58.214148: step: 252/470, loss: 0.026947399601340294
2023-01-22 19:30:58.995864: step: 254/470, loss: 0.08892068266868591
2023-01-22 19:30:59.729279: step: 256/470, loss: 0.07869922369718552
2023-01-22 19:31:00.536501: step: 258/470, loss: 0.050374485552310944
2023-01-22 19:31:01.257676: step: 260/470, loss: 0.10828451067209244
2023-01-22 19:31:02.015980: step: 262/470, loss: 0.032886065542697906
2023-01-22 19:31:02.684887: step: 264/470, loss: 0.008889845572412014
2023-01-22 19:31:03.398374: step: 266/470, loss: 0.02972853183746338
2023-01-22 19:31:04.180462: step: 268/470, loss: 0.00936366431415081
2023-01-22 19:31:04.907825: step: 270/470, loss: 0.018172763288021088
2023-01-22 19:31:05.790092: step: 272/470, loss: 0.03780972212553024
2023-01-22 19:31:06.475118: step: 274/470, loss: 0.03203846141695976
2023-01-22 19:31:07.244360: step: 276/470, loss: 0.059636037796735764
2023-01-22 19:31:07.939034: step: 278/470, loss: 0.2443484216928482
2023-01-22 19:31:08.729305: step: 280/470, loss: 0.08666800707578659
2023-01-22 19:31:09.447126: step: 282/470, loss: 0.061435677111148834
2023-01-22 19:31:10.217448: step: 284/470, loss: 0.15919671952724457
2023-01-22 19:31:10.927000: step: 286/470, loss: 0.028493307530879974
2023-01-22 19:31:11.612713: step: 288/470, loss: 0.0469590425491333
2023-01-22 19:31:12.315622: step: 290/470, loss: 0.057702258229255676
2023-01-22 19:31:13.029862: step: 292/470, loss: 0.02364461123943329
2023-01-22 19:31:13.807909: step: 294/470, loss: 0.09106270968914032
2023-01-22 19:31:14.504530: step: 296/470, loss: 0.009492744691669941
2023-01-22 19:31:15.225992: step: 298/470, loss: 0.08927375078201294
2023-01-22 19:31:15.961187: step: 300/470, loss: 0.2396526336669922
2023-01-22 19:31:16.661315: step: 302/470, loss: 0.021701229736208916
2023-01-22 19:31:17.391783: step: 304/470, loss: 0.04955710098147392
2023-01-22 19:31:18.095024: step: 306/470, loss: 0.013163585215806961
2023-01-22 19:31:18.852037: step: 308/470, loss: 2.5453379154205322
2023-01-22 19:31:19.577148: step: 310/470, loss: 0.2919505834579468
2023-01-22 19:31:20.228307: step: 312/470, loss: 0.004827272146940231
2023-01-22 19:31:20.975387: step: 314/470, loss: 0.23596075177192688
2023-01-22 19:31:21.621917: step: 316/470, loss: 0.06390093266963959
2023-01-22 19:31:22.380436: step: 318/470, loss: 0.08488807827234268
2023-01-22 19:31:23.055523: step: 320/470, loss: 0.381671279668808
2023-01-22 19:31:23.734628: step: 322/470, loss: 1.292970061302185
2023-01-22 19:31:24.517263: step: 324/470, loss: 0.03118908405303955
2023-01-22 19:31:25.327255: step: 326/470, loss: 0.4090331196784973
2023-01-22 19:31:26.060229: step: 328/470, loss: 0.01948448270559311
2023-01-22 19:31:26.807996: step: 330/470, loss: 0.03427987918257713
2023-01-22 19:31:27.530490: step: 332/470, loss: 0.11818772554397583
2023-01-22 19:31:28.247129: step: 334/470, loss: 0.019033944234251976
2023-01-22 19:31:29.043235: step: 336/470, loss: 0.05994606763124466
2023-01-22 19:31:29.810516: step: 338/470, loss: 0.11957002431154251
2023-01-22 19:31:30.582292: step: 340/470, loss: 0.013482224196195602
2023-01-22 19:31:31.377410: step: 342/470, loss: 1.4503638744354248
2023-01-22 19:31:32.052046: step: 344/470, loss: 0.02695303224027157
2023-01-22 19:31:32.780342: step: 346/470, loss: 0.050801824778318405
2023-01-22 19:31:33.520662: step: 348/470, loss: 0.07081786543130875
2023-01-22 19:31:34.279858: step: 350/470, loss: 0.15673120319843292
2023-01-22 19:31:34.981022: step: 352/470, loss: 0.033411867916584015
2023-01-22 19:31:35.805083: step: 354/470, loss: 0.012247402220964432
2023-01-22 19:31:36.553458: step: 356/470, loss: 0.04690024256706238
2023-01-22 19:31:37.361854: step: 358/470, loss: 0.012932350859045982
2023-01-22 19:31:38.079475: step: 360/470, loss: 0.03173913061618805
2023-01-22 19:31:38.854761: step: 362/470, loss: 0.07606765627861023
2023-01-22 19:31:39.620363: step: 364/470, loss: 0.04719306901097298
2023-01-22 19:31:40.350437: step: 366/470, loss: 0.04025932401418686
2023-01-22 19:31:41.069717: step: 368/470, loss: 0.040751710534095764
2023-01-22 19:31:41.915585: step: 370/470, loss: 0.10012707859277725
2023-01-22 19:31:42.665471: step: 372/470, loss: 0.1372625231742859
2023-01-22 19:31:43.403394: step: 374/470, loss: 0.29762670397758484
2023-01-22 19:31:44.192636: step: 376/470, loss: 0.01679973676800728
2023-01-22 19:31:44.998318: step: 378/470, loss: 0.1596241146326065
2023-01-22 19:31:45.747056: step: 380/470, loss: 0.01258562970906496
2023-01-22 19:31:46.491618: step: 382/470, loss: 0.012428507208824158
2023-01-22 19:31:47.232746: step: 384/470, loss: 0.06731784343719482
2023-01-22 19:31:47.975446: step: 386/470, loss: 0.039965856820344925
2023-01-22 19:31:48.748450: step: 388/470, loss: 0.022317346185445786
2023-01-22 19:31:49.514135: step: 390/470, loss: 0.07760674506425858
2023-01-22 19:31:50.191476: step: 392/470, loss: 0.04869608208537102
2023-01-22 19:31:50.967875: step: 394/470, loss: 0.12491077929735184
2023-01-22 19:31:51.737536: step: 396/470, loss: 0.017211737111210823
2023-01-22 19:31:52.478117: step: 398/470, loss: 0.03493155539035797
2023-01-22 19:31:53.183138: step: 400/470, loss: 0.008576873689889908
2023-01-22 19:31:53.845192: step: 402/470, loss: 0.004653942305594683
2023-01-22 19:31:54.590101: step: 404/470, loss: 0.03935122489929199
2023-01-22 19:31:55.298953: step: 406/470, loss: 0.019616080448031425
2023-01-22 19:31:56.095182: step: 408/470, loss: 0.016680454835295677
2023-01-22 19:31:56.857615: step: 410/470, loss: 1.8669378757476807
2023-01-22 19:31:57.593526: step: 412/470, loss: 0.050840165466070175
2023-01-22 19:31:58.288331: step: 414/470, loss: 0.017026670277118683
2023-01-22 19:31:59.032584: step: 416/470, loss: 0.02777211181819439
2023-01-22 19:31:59.797834: step: 418/470, loss: 0.047070860862731934
2023-01-22 19:32:00.573423: step: 420/470, loss: 0.018415415659546852
2023-01-22 19:32:01.254217: step: 422/470, loss: 0.11197975277900696
2023-01-22 19:32:01.951598: step: 424/470, loss: 0.022071341052651405
2023-01-22 19:32:02.673251: step: 426/470, loss: 0.016471032053232193
2023-01-22 19:32:03.492653: step: 428/470, loss: 0.0054807537235319614
2023-01-22 19:32:04.238133: step: 430/470, loss: 0.025621192529797554
2023-01-22 19:32:04.991299: step: 432/470, loss: 0.029046742245554924
2023-01-22 19:32:05.703429: step: 434/470, loss: 0.014325280673801899
2023-01-22 19:32:06.420049: step: 436/470, loss: 0.0053360736928880215
2023-01-22 19:32:07.075437: step: 438/470, loss: 0.049321822822093964
2023-01-22 19:32:07.808857: step: 440/470, loss: 0.012010014615952969
2023-01-22 19:32:08.566554: step: 442/470, loss: 0.022885087877511978
2023-01-22 19:32:09.288601: step: 444/470, loss: 0.030774349346756935
2023-01-22 19:32:09.932268: step: 446/470, loss: 0.07810332626104355
2023-01-22 19:32:10.583708: step: 448/470, loss: 0.018929030746221542
2023-01-22 19:32:11.310060: step: 450/470, loss: 0.008509436622262001
2023-01-22 19:32:11.959311: step: 452/470, loss: 0.020978335291147232
2023-01-22 19:32:12.666637: step: 454/470, loss: 0.013563503511250019
2023-01-22 19:32:13.375772: step: 456/470, loss: 0.10911507159471512
2023-01-22 19:32:14.139175: step: 458/470, loss: 0.03588716313242912
2023-01-22 19:32:14.822646: step: 460/470, loss: 0.035442594438791275
2023-01-22 19:32:15.567158: step: 462/470, loss: 0.01282803900539875
2023-01-22 19:32:16.364558: step: 464/470, loss: 0.04582873731851578
2023-01-22 19:32:17.160529: step: 466/470, loss: 0.0383700355887413
2023-01-22 19:32:17.919276: step: 468/470, loss: 0.025660475715994835
2023-01-22 19:32:18.619134: step: 470/470, loss: 0.14962579309940338
2023-01-22 19:32:19.332863: step: 472/470, loss: 0.1222333088517189
2023-01-22 19:32:20.027065: step: 474/470, loss: 0.004696396645158529
2023-01-22 19:32:20.724923: step: 476/470, loss: 0.10672306269407272
2023-01-22 19:32:21.473585: step: 478/470, loss: 0.03075164370238781
2023-01-22 19:32:22.191261: step: 480/470, loss: 0.011191125959157944
2023-01-22 19:32:22.908155: step: 482/470, loss: 0.020779795944690704
2023-01-22 19:32:23.587709: step: 484/470, loss: 0.023522723466157913
2023-01-22 19:32:24.337809: step: 486/470, loss: 0.11427683383226395
2023-01-22 19:32:25.141634: step: 488/470, loss: 0.04714156314730644
2023-01-22 19:32:25.896939: step: 490/470, loss: 0.21134763956069946
2023-01-22 19:32:26.636678: step: 492/470, loss: 0.38170838356018066
2023-01-22 19:32:27.474347: step: 494/470, loss: 0.041793301701545715
2023-01-22 19:32:28.152482: step: 496/470, loss: 0.03228547051548958
2023-01-22 19:32:28.924673: step: 498/470, loss: 0.05064351484179497
2023-01-22 19:32:29.655249: step: 500/470, loss: 0.10985661298036575
2023-01-22 19:32:30.293019: step: 502/470, loss: 0.4626348614692688
2023-01-22 19:32:31.043170: step: 504/470, loss: 0.06298696249723434
2023-01-22 19:32:31.782977: step: 506/470, loss: 0.08736024796962738
2023-01-22 19:32:32.466858: step: 508/470, loss: 0.05532427132129669
2023-01-22 19:32:33.187740: step: 510/470, loss: 0.0031663402915000916
2023-01-22 19:32:33.860888: step: 512/470, loss: 0.1809593141078949
2023-01-22 19:32:34.658900: step: 514/470, loss: 0.031655311584472656
2023-01-22 19:32:35.461089: step: 516/470, loss: 0.0275458712130785
2023-01-22 19:32:36.252593: step: 518/470, loss: 0.046752817928791046
2023-01-22 19:32:37.011822: step: 520/470, loss: 0.024380570277571678
2023-01-22 19:32:37.763732: step: 522/470, loss: 0.03911636769771576
2023-01-22 19:32:38.501362: step: 524/470, loss: 0.011473782360553741
2023-01-22 19:32:39.292610: step: 526/470, loss: 0.03254931420087814
2023-01-22 19:32:40.027566: step: 528/470, loss: 0.04068319499492645
2023-01-22 19:32:40.790528: step: 530/470, loss: 0.07182002812623978
2023-01-22 19:32:41.551740: step: 532/470, loss: 0.18645454943180084
2023-01-22 19:32:42.242110: step: 534/470, loss: 0.005089792422950268
2023-01-22 19:32:42.965559: step: 536/470, loss: 0.02244439162313938
2023-01-22 19:32:43.709238: step: 538/470, loss: 0.02713472954928875
2023-01-22 19:32:44.487490: step: 540/470, loss: 0.09527122229337692
2023-01-22 19:32:45.298903: step: 542/470, loss: 0.04841366410255432
2023-01-22 19:32:46.050507: step: 544/470, loss: 0.03840105980634689
2023-01-22 19:32:46.755664: step: 546/470, loss: 0.003627850441262126
2023-01-22 19:32:47.575390: step: 548/470, loss: 0.06749998778104782
2023-01-22 19:32:48.324787: step: 550/470, loss: 0.058877523988485336
2023-01-22 19:32:49.023257: step: 552/470, loss: 0.018091080710291862
2023-01-22 19:32:49.768920: step: 554/470, loss: 0.12940962612628937
2023-01-22 19:32:50.536419: step: 556/470, loss: 0.1229933425784111
2023-01-22 19:32:51.242608: step: 558/470, loss: 0.024270979687571526
2023-01-22 19:32:51.927082: step: 560/470, loss: 0.10469833761453629
2023-01-22 19:32:52.724985: step: 562/470, loss: 0.05231137201189995
2023-01-22 19:32:53.404186: step: 564/470, loss: 0.04341939464211464
2023-01-22 19:32:54.132076: step: 566/470, loss: 0.06202490255236626
2023-01-22 19:32:54.817434: step: 568/470, loss: 0.2968774437904358
2023-01-22 19:32:55.562563: step: 570/470, loss: 0.22153881192207336
2023-01-22 19:32:56.373093: step: 572/470, loss: 0.07482737302780151
2023-01-22 19:32:57.159570: step: 574/470, loss: 0.049079857766628265
2023-01-22 19:32:57.894574: step: 576/470, loss: 0.015658581629395485
2023-01-22 19:32:58.593227: step: 578/470, loss: 0.016094373539090157
2023-01-22 19:32:59.308895: step: 580/470, loss: 0.05446375906467438
2023-01-22 19:33:00.017565: step: 582/470, loss: 0.08582345396280289
2023-01-22 19:33:00.681264: step: 584/470, loss: 0.055172644555568695
2023-01-22 19:33:01.384520: step: 586/470, loss: 0.03194602578878403
2023-01-22 19:33:02.244421: step: 588/470, loss: 0.06124107167124748
2023-01-22 19:33:03.005115: step: 590/470, loss: 0.06561607867479324
2023-01-22 19:33:03.738451: step: 592/470, loss: 0.387003630399704
2023-01-22 19:33:04.437203: step: 594/470, loss: 0.11961881816387177
2023-01-22 19:33:05.146408: step: 596/470, loss: 0.03727561980485916
2023-01-22 19:33:05.859027: step: 598/470, loss: 0.02133580483496189
2023-01-22 19:33:06.607710: step: 600/470, loss: 0.020184461027383804
2023-01-22 19:33:07.389890: step: 602/470, loss: 0.06725658476352692
2023-01-22 19:33:08.118339: step: 604/470, loss: 0.017879968509078026
2023-01-22 19:33:08.879209: step: 606/470, loss: 0.029784638434648514
2023-01-22 19:33:09.730434: step: 608/470, loss: 0.021767864003777504
2023-01-22 19:33:10.507481: step: 610/470, loss: 0.057398948818445206
2023-01-22 19:33:11.217310: step: 612/470, loss: 0.6706560254096985
2023-01-22 19:33:12.008448: step: 614/470, loss: 0.03931858763098717
2023-01-22 19:33:12.758022: step: 616/470, loss: 0.5221364498138428
2023-01-22 19:33:13.535158: step: 618/470, loss: 0.01334367971867323
2023-01-22 19:33:14.292210: step: 620/470, loss: 0.06150234863162041
2023-01-22 19:33:15.054327: step: 622/470, loss: 0.029126210138201714
2023-01-22 19:33:15.818333: step: 624/470, loss: 0.13291211426258087
2023-01-22 19:33:16.601946: step: 626/470, loss: 0.5435463786125183
2023-01-22 19:33:17.338563: step: 628/470, loss: 0.016903935000300407
2023-01-22 19:33:18.006311: step: 630/470, loss: 0.012967291288077831
2023-01-22 19:33:18.719587: step: 632/470, loss: 0.04698651283979416
2023-01-22 19:33:19.489757: step: 634/470, loss: 0.03846525028347969
2023-01-22 19:33:20.254277: step: 636/470, loss: 0.024630436673760414
2023-01-22 19:33:20.923258: step: 638/470, loss: 0.062395889312028885
2023-01-22 19:33:21.627974: step: 640/470, loss: 0.06373529881238937
2023-01-22 19:33:22.427138: step: 642/470, loss: 0.08350540697574615
2023-01-22 19:33:23.107211: step: 644/470, loss: 0.0395352728664875
2023-01-22 19:33:23.786212: step: 646/470, loss: 0.006685740314424038
2023-01-22 19:33:24.533730: step: 648/470, loss: 0.06376517564058304
2023-01-22 19:33:25.271132: step: 650/470, loss: 0.06809066981077194
2023-01-22 19:33:25.969083: step: 652/470, loss: 0.03920336440205574
2023-01-22 19:33:26.749847: step: 654/470, loss: 0.18704262375831604
2023-01-22 19:33:27.432962: step: 656/470, loss: 0.0032950390595942736
2023-01-22 19:33:28.233324: step: 658/470, loss: 0.06400889903306961
2023-01-22 19:33:29.007015: step: 660/470, loss: 0.026591304689645767
2023-01-22 19:33:29.723190: step: 662/470, loss: 0.006560401059687138
2023-01-22 19:33:30.463355: step: 664/470, loss: 0.08201814442873001
2023-01-22 19:33:31.181116: step: 666/470, loss: 0.059747278690338135
2023-01-22 19:33:31.944331: step: 668/470, loss: 0.11375654488801956
2023-01-22 19:33:32.673063: step: 670/470, loss: 0.028703976422548294
2023-01-22 19:33:33.414082: step: 672/470, loss: 0.19319429993629456
2023-01-22 19:33:34.173743: step: 674/470, loss: 0.07025258243083954
2023-01-22 19:33:34.939413: step: 676/470, loss: 0.032008834183216095
2023-01-22 19:33:35.636401: step: 678/470, loss: 0.13485921919345856
2023-01-22 19:33:36.317906: step: 680/470, loss: 0.050178226083517075
2023-01-22 19:33:37.051448: step: 682/470, loss: 0.04921692609786987
2023-01-22 19:33:37.833682: step: 684/470, loss: 0.022719813510775566
2023-01-22 19:33:38.495174: step: 686/470, loss: 0.04771514609456062
2023-01-22 19:33:39.280960: step: 688/470, loss: 0.033646490424871445
2023-01-22 19:33:40.036080: step: 690/470, loss: 0.07247103005647659
2023-01-22 19:33:40.835154: step: 692/470, loss: 0.05885102227330208
2023-01-22 19:33:41.558877: step: 694/470, loss: 0.005150055047124624
2023-01-22 19:33:42.428379: step: 696/470, loss: 0.0049107871018350124
2023-01-22 19:33:43.115946: step: 698/470, loss: 0.011220758780837059
2023-01-22 19:33:43.847987: step: 700/470, loss: 0.06259648501873016
2023-01-22 19:33:44.569855: step: 702/470, loss: 0.023064645007252693
2023-01-22 19:33:45.333592: step: 704/470, loss: 0.026079723611474037
2023-01-22 19:33:46.093461: step: 706/470, loss: 0.011188274249434471
2023-01-22 19:33:46.818784: step: 708/470, loss: 0.015496410429477692
2023-01-22 19:33:47.618935: step: 710/470, loss: 0.7063004374504089
2023-01-22 19:33:48.411119: step: 712/470, loss: 0.0391618087887764
2023-01-22 19:33:49.173246: step: 714/470, loss: 0.07354892045259476
2023-01-22 19:33:50.000612: step: 716/470, loss: 0.02870473451912403
2023-01-22 19:33:50.725238: step: 718/470, loss: 0.06522411108016968
2023-01-22 19:33:51.587654: step: 720/470, loss: 0.23585094511508942
2023-01-22 19:33:52.324196: step: 722/470, loss: 0.11705224961042404
2023-01-22 19:33:53.040028: step: 724/470, loss: 0.5201276540756226
2023-01-22 19:33:53.729199: step: 726/470, loss: 0.033718567341566086
2023-01-22 19:33:54.436307: step: 728/470, loss: 0.11925947666168213
2023-01-22 19:33:55.189797: step: 730/470, loss: 0.01283105555921793
2023-01-22 19:33:55.916450: step: 732/470, loss: 0.03227861598134041
2023-01-22 19:33:56.718651: step: 734/470, loss: 0.20628242194652557
2023-01-22 19:33:57.422397: step: 736/470, loss: 0.0496375747025013
2023-01-22 19:33:58.277221: step: 738/470, loss: 0.12754222750663757
2023-01-22 19:33:59.029225: step: 740/470, loss: 0.27654582262039185
2023-01-22 19:33:59.755741: step: 742/470, loss: 0.007181598339229822
2023-01-22 19:34:00.532062: step: 744/470, loss: 0.03585813194513321
2023-01-22 19:34:01.236536: step: 746/470, loss: 0.5074892044067383
2023-01-22 19:34:01.959251: step: 748/470, loss: 0.08907847851514816
2023-01-22 19:34:02.623022: step: 750/470, loss: 0.024945350363850594
2023-01-22 19:34:03.392360: step: 752/470, loss: 0.029513496905565262
2023-01-22 19:34:04.152857: step: 754/470, loss: 0.0634850412607193
2023-01-22 19:34:04.900121: step: 756/470, loss: 0.27008649706840515
2023-01-22 19:34:05.703864: step: 758/470, loss: 0.07133635878562927
2023-01-22 19:34:06.412953: step: 760/470, loss: 0.04460354521870613
2023-01-22 19:34:07.215756: step: 762/470, loss: 0.156412735581398
2023-01-22 19:34:07.926297: step: 764/470, loss: 0.020505452528595924
2023-01-22 19:34:08.651866: step: 766/470, loss: 0.020364558324217796
2023-01-22 19:34:09.338394: step: 768/470, loss: 0.12095355987548828
2023-01-22 19:34:10.112831: step: 770/470, loss: 0.05226239189505577
2023-01-22 19:34:10.899349: step: 772/470, loss: 0.04754621163010597
2023-01-22 19:34:11.609542: step: 774/470, loss: 0.056481197476387024
2023-01-22 19:34:12.362604: step: 776/470, loss: 0.02067723497748375
2023-01-22 19:34:13.154315: step: 778/470, loss: 0.02264983393251896
2023-01-22 19:34:13.933200: step: 780/470, loss: 0.01082298532128334
2023-01-22 19:34:14.663389: step: 782/470, loss: 0.01869276538491249
2023-01-22 19:34:15.370839: step: 784/470, loss: 0.030841980129480362
2023-01-22 19:34:16.084572: step: 786/470, loss: 0.01216953992843628
2023-01-22 19:34:16.825292: step: 788/470, loss: 0.32434332370758057
2023-01-22 19:34:17.584488: step: 790/470, loss: 0.07466316968202591
2023-01-22 19:34:18.317206: step: 792/470, loss: 0.020550915971398354
2023-01-22 19:34:19.059473: step: 794/470, loss: 0.012714998796582222
2023-01-22 19:34:19.820366: step: 796/470, loss: 0.07571426033973694
2023-01-22 19:34:20.607432: step: 798/470, loss: 0.05830766260623932
2023-01-22 19:34:21.346791: step: 800/470, loss: 0.06974931806325912
2023-01-22 19:34:22.077993: step: 802/470, loss: 0.042594559490680695
2023-01-22 19:34:22.811467: step: 804/470, loss: 0.0458582304418087
2023-01-22 19:34:23.511179: step: 806/470, loss: 0.024310944601893425
2023-01-22 19:34:24.242219: step: 808/470, loss: 0.06325914710760117
2023-01-22 19:34:24.957252: step: 810/470, loss: 0.2123449146747589
2023-01-22 19:34:25.770228: step: 812/470, loss: 0.08683294802904129
2023-01-22 19:34:26.538593: step: 814/470, loss: 0.0271016675978899
2023-01-22 19:34:27.302390: step: 816/470, loss: 0.06353487074375153
2023-01-22 19:34:28.106434: step: 818/470, loss: 0.028592655435204506
2023-01-22 19:34:28.796915: step: 820/470, loss: 0.013006173074245453
2023-01-22 19:34:29.537253: step: 822/470, loss: 0.030378835275769234
2023-01-22 19:34:30.256812: step: 824/470, loss: 0.001919006579555571
2023-01-22 19:34:30.996456: step: 826/470, loss: 0.03218744695186615
2023-01-22 19:34:31.706589: step: 828/470, loss: 0.06677714735269547
2023-01-22 19:34:32.398865: step: 830/470, loss: 0.016359543427824974
2023-01-22 19:34:33.143795: step: 832/470, loss: 0.013201995752751827
2023-01-22 19:34:33.838154: step: 834/470, loss: 0.023714501410722733
2023-01-22 19:34:34.538277: step: 836/470, loss: 0.06850353628396988
2023-01-22 19:34:35.325843: step: 838/470, loss: 0.05281051993370056
2023-01-22 19:34:36.068772: step: 840/470, loss: 0.08620928972959518
2023-01-22 19:34:36.783225: step: 842/470, loss: 0.04048202931880951
2023-01-22 19:34:37.641346: step: 844/470, loss: 0.11093959212303162
2023-01-22 19:34:38.352037: step: 846/470, loss: 0.11896642297506332
2023-01-22 19:34:39.047311: step: 848/470, loss: 0.8897960186004639
2023-01-22 19:34:39.695098: step: 850/470, loss: 0.0081399567425251
2023-01-22 19:34:40.404314: step: 852/470, loss: 0.013954234309494495
2023-01-22 19:34:41.095970: step: 854/470, loss: 0.05100409686565399
2023-01-22 19:34:41.839252: step: 856/470, loss: 0.2577970325946808
2023-01-22 19:34:42.511952: step: 858/470, loss: 0.07873797416687012
2023-01-22 19:34:43.194278: step: 860/470, loss: 0.06876885890960693
2023-01-22 19:34:43.973254: step: 862/470, loss: 0.03414501994848251
2023-01-22 19:34:44.834416: step: 864/470, loss: 0.05697346851229668
2023-01-22 19:34:45.524665: step: 866/470, loss: 0.07026387751102448
2023-01-22 19:34:46.279058: step: 868/470, loss: 0.06572747230529785
2023-01-22 19:34:47.014340: step: 870/470, loss: 0.4360022246837616
2023-01-22 19:34:47.764833: step: 872/470, loss: 0.03277615085244179
2023-01-22 19:34:48.457067: step: 874/470, loss: 0.04744017496705055
2023-01-22 19:34:49.214899: step: 876/470, loss: 0.03529006615281105
2023-01-22 19:34:49.915998: step: 878/470, loss: 0.04175432026386261
2023-01-22 19:34:50.680445: step: 880/470, loss: 0.035176780074834824
2023-01-22 19:34:51.425994: step: 882/470, loss: 0.037990227341651917
2023-01-22 19:34:52.181937: step: 884/470, loss: 0.0412430465221405
2023-01-22 19:34:52.995355: step: 886/470, loss: 0.059082094579935074
2023-01-22 19:34:53.805976: step: 888/470, loss: 0.0283492561429739
2023-01-22 19:34:54.577791: step: 890/470, loss: 0.08661621809005737
2023-01-22 19:34:55.241548: step: 892/470, loss: 0.04014264792203903
2023-01-22 19:34:56.026122: step: 894/470, loss: 0.016945162788033485
2023-01-22 19:34:56.739403: step: 896/470, loss: 0.020986400544643402
2023-01-22 19:34:57.409025: step: 898/470, loss: 0.06758707016706467
2023-01-22 19:34:58.116688: step: 900/470, loss: 0.10314557701349258
2023-01-22 19:34:58.811898: step: 902/470, loss: 0.12326005101203918
2023-01-22 19:34:59.592316: step: 904/470, loss: 0.047155629843473434
2023-01-22 19:35:00.369224: step: 906/470, loss: 0.025163166224956512
2023-01-22 19:35:01.078201: step: 908/470, loss: 0.032101456075906754
2023-01-22 19:35:01.784992: step: 910/470, loss: 0.0255853533744812
2023-01-22 19:35:02.589065: step: 912/470, loss: 0.031632889062166214
2023-01-22 19:35:03.347003: step: 914/470, loss: 0.07384685426950455
2023-01-22 19:35:04.162035: step: 916/470, loss: 0.09033031016588211
2023-01-22 19:35:04.875680: step: 918/470, loss: 0.061557587236166
2023-01-22 19:35:05.601337: step: 920/470, loss: 0.1455271691083908
2023-01-22 19:35:06.349529: step: 922/470, loss: 0.017164742574095726
2023-01-22 19:35:07.050730: step: 924/470, loss: 0.03933778777718544
2023-01-22 19:35:07.797111: step: 926/470, loss: 0.040244653820991516
2023-01-22 19:35:08.547065: step: 928/470, loss: 0.051455993205308914
2023-01-22 19:35:09.264607: step: 930/470, loss: 0.07561231404542923
2023-01-22 19:35:09.928505: step: 932/470, loss: 0.02452336624264717
2023-01-22 19:35:10.696153: step: 934/470, loss: 0.03766307979822159
2023-01-22 19:35:11.422752: step: 936/470, loss: 0.041747868061065674
2023-01-22 19:35:12.207486: step: 938/470, loss: 0.02425321564078331
2023-01-22 19:35:13.003081: step: 940/470, loss: 0.27364808320999146
2023-01-22 19:35:13.654420: step: 942/470, loss: 0.016857439652085304
==================================================
Loss: 0.097
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2877562566560171, 'r': 0.34181293485136, 'f1': 0.3124638623879735}, 'combined': 0.23023653018061205, 'epoch': 21}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3439033402557875, 'r': 0.3716801485072165, 'f1': 0.357252638121539}, 'combined': 0.24883268326873365, 'epoch': 21}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2824927887011563, 'r': 0.34306524624049345, 'f1': 0.3098464177699058}, 'combined': 0.22830788677782532, 'epoch': 21}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3453082771863508, 'r': 0.3662259901312932, 'f1': 0.3554596637765235}, 'combined': 0.24758384541648404, 'epoch': 21}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2699193305470839, 'r': 0.3487951880504063, 'f1': 0.3043295763287485}, 'combined': 0.22424284571591996, 'epoch': 21}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33252897285164096, 'r': 0.3747345732520415, 'f1': 0.3523724739440535}, 'combined': 0.24543356394113183, 'epoch': 21}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24305555555555555, 'r': 0.375, 'f1': 0.2949438202247191}, 'combined': 0.19662921348314605, 'epoch': 21}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2638888888888889, 'r': 0.41304347826086957, 'f1': 0.3220338983050847}, 'combined': 0.16101694915254236, 'epoch': 21}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3522727272727273, 'r': 0.2672413793103448, 'f1': 0.303921568627451}, 'combined': 0.20261437908496732, 'epoch': 21}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 22
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 19:37:52.188591: step: 2/470, loss: 0.07132654637098312
2023-01-22 19:37:52.891337: step: 4/470, loss: 0.04968281090259552
2023-01-22 19:37:53.642156: step: 6/470, loss: 0.025600193068385124
2023-01-22 19:37:54.418329: step: 8/470, loss: 0.11954417079687119
2023-01-22 19:37:55.158680: step: 10/470, loss: 0.004893624223768711
2023-01-22 19:37:55.937171: step: 12/470, loss: 0.032928865402936935
2023-01-22 19:37:56.714109: step: 14/470, loss: 0.01784546673297882
2023-01-22 19:37:57.467983: step: 16/470, loss: 0.02579541504383087
2023-01-22 19:37:58.184709: step: 18/470, loss: 0.0351317934691906
2023-01-22 19:37:58.860561: step: 20/470, loss: 0.009095302782952785
2023-01-22 19:37:59.539732: step: 22/470, loss: 0.004136822652071714
2023-01-22 19:38:00.166461: step: 24/470, loss: 0.014530248008668423
2023-01-22 19:38:00.842353: step: 26/470, loss: 0.03549989312887192
2023-01-22 19:38:01.659490: step: 28/470, loss: 0.04445575922727585
2023-01-22 19:38:02.377780: step: 30/470, loss: 0.01351911574602127
2023-01-22 19:38:03.232356: step: 32/470, loss: 0.12070487439632416
2023-01-22 19:38:04.001353: step: 34/470, loss: 0.007829630747437477
2023-01-22 19:38:04.666776: step: 36/470, loss: 0.06734476238489151
2023-01-22 19:38:05.363047: step: 38/470, loss: 0.016050485894083977
2023-01-22 19:38:06.082745: step: 40/470, loss: 0.025376321747899055
2023-01-22 19:38:06.799503: step: 42/470, loss: 0.005891892127692699
2023-01-22 19:38:07.446201: step: 44/470, loss: 0.1300346851348877
2023-01-22 19:38:08.160982: step: 46/470, loss: 0.03699648007750511
2023-01-22 19:38:08.868484: step: 48/470, loss: 0.014293630607426167
2023-01-22 19:38:09.610110: step: 50/470, loss: 0.02472846582531929
2023-01-22 19:38:10.329070: step: 52/470, loss: 0.020292188972234726
2023-01-22 19:38:11.098941: step: 54/470, loss: 0.0226434413343668
2023-01-22 19:38:11.786945: step: 56/470, loss: 0.09266740083694458
2023-01-22 19:38:12.516790: step: 58/470, loss: 0.01962917111814022
2023-01-22 19:38:13.311720: step: 60/470, loss: 0.03125033900141716
2023-01-22 19:38:14.103266: step: 62/470, loss: 0.02047717012465
2023-01-22 19:38:14.869433: step: 64/470, loss: 0.018749892711639404
2023-01-22 19:38:15.623108: step: 66/470, loss: 0.033666905015707016
2023-01-22 19:38:16.467887: step: 68/470, loss: 0.03922034800052643
2023-01-22 19:38:17.221711: step: 70/470, loss: 0.019506221637129784
2023-01-22 19:38:17.904767: step: 72/470, loss: 0.0295857060700655
2023-01-22 19:38:18.632448: step: 74/470, loss: 0.05708824843168259
2023-01-22 19:38:19.361190: step: 76/470, loss: 0.035686276853084564
2023-01-22 19:38:20.070575: step: 78/470, loss: 0.0031681691762059927
2023-01-22 19:38:20.795162: step: 80/470, loss: 0.06565077602863312
2023-01-22 19:38:21.543013: step: 82/470, loss: 0.013326709158718586
2023-01-22 19:38:22.223877: step: 84/470, loss: 0.059001680463552475
2023-01-22 19:38:22.937391: step: 86/470, loss: 0.04502973333001137
2023-01-22 19:38:23.643839: step: 88/470, loss: 0.05877036228775978
2023-01-22 19:38:24.482682: step: 90/470, loss: 0.03713955730199814
2023-01-22 19:38:25.204752: step: 92/470, loss: 0.4271875321865082
2023-01-22 19:38:25.951738: step: 94/470, loss: 0.0117900799959898
2023-01-22 19:38:26.769523: step: 96/470, loss: 0.023388944566249847
2023-01-22 19:38:27.594602: step: 98/470, loss: 0.042075708508491516
2023-01-22 19:38:28.269249: step: 100/470, loss: 0.023363204672932625
2023-01-22 19:38:29.006191: step: 102/470, loss: 0.04883814603090286
2023-01-22 19:38:29.679925: step: 104/470, loss: 0.02259974554181099
2023-01-22 19:38:30.377958: step: 106/470, loss: 0.06939293444156647
2023-01-22 19:38:31.089776: step: 108/470, loss: 0.07869086414575577
2023-01-22 19:38:31.836380: step: 110/470, loss: 0.01648254692554474
2023-01-22 19:38:32.516998: step: 112/470, loss: 2.4709521312615834e-05
2023-01-22 19:38:33.296696: step: 114/470, loss: 0.027162201702594757
2023-01-22 19:38:34.033629: step: 116/470, loss: 0.042458001524209976
2023-01-22 19:38:34.808933: step: 118/470, loss: 0.008122868835926056
2023-01-22 19:38:35.708895: step: 120/470, loss: 0.08594401180744171
2023-01-22 19:38:36.472979: step: 122/470, loss: 0.06479133665561676
2023-01-22 19:38:37.207757: step: 124/470, loss: 0.05414796248078346
2023-01-22 19:38:37.908159: step: 126/470, loss: 0.013639035634696484
2023-01-22 19:38:38.590647: step: 128/470, loss: 0.014860237948596478
2023-01-22 19:38:39.282198: step: 130/470, loss: 0.009585319086909294
2023-01-22 19:38:40.009801: step: 132/470, loss: 0.0008866112912073731
2023-01-22 19:38:40.742709: step: 134/470, loss: 0.07709459215402603
2023-01-22 19:38:41.602749: step: 136/470, loss: 0.08505282551050186
2023-01-22 19:38:42.294309: step: 138/470, loss: 0.03271591290831566
2023-01-22 19:38:43.056012: step: 140/470, loss: 0.36453869938850403
2023-01-22 19:38:43.788679: step: 142/470, loss: 0.06906229257583618
2023-01-22 19:38:44.560891: step: 144/470, loss: 0.09906693547964096
2023-01-22 19:38:45.343876: step: 146/470, loss: 0.15732789039611816
2023-01-22 19:38:46.088441: step: 148/470, loss: 0.0644831508398056
2023-01-22 19:38:46.818615: step: 150/470, loss: 0.0066782585345208645
2023-01-22 19:38:47.644310: step: 152/470, loss: 0.034233175218105316
2023-01-22 19:38:48.401033: step: 154/470, loss: 0.061225440353155136
2023-01-22 19:38:49.120463: step: 156/470, loss: 0.05808292329311371
2023-01-22 19:38:49.841687: step: 158/470, loss: 0.039374712854623795
2023-01-22 19:38:50.578903: step: 160/470, loss: 0.029254967346787453
2023-01-22 19:38:51.376707: step: 162/470, loss: 0.17803142964839935
2023-01-22 19:38:52.079942: step: 164/470, loss: 0.023453183472156525
2023-01-22 19:38:52.830176: step: 166/470, loss: 0.11502149701118469
2023-01-22 19:38:53.616087: step: 168/470, loss: 0.18725618720054626
2023-01-22 19:38:54.421468: step: 170/470, loss: 0.07862892746925354
2023-01-22 19:38:55.116308: step: 172/470, loss: 0.02760915271937847
2023-01-22 19:38:55.821417: step: 174/470, loss: 0.009849579073488712
2023-01-22 19:38:56.612711: step: 176/470, loss: 0.03337179869413376
2023-01-22 19:38:57.314815: step: 178/470, loss: 0.02945728227496147
2023-01-22 19:38:58.033804: step: 180/470, loss: 1.613263726234436
2023-01-22 19:38:58.720322: step: 182/470, loss: 0.03204035386443138
2023-01-22 19:38:59.398479: step: 184/470, loss: 0.04056650400161743
2023-01-22 19:39:00.135479: step: 186/470, loss: 0.06198835000395775
2023-01-22 19:39:00.849413: step: 188/470, loss: 0.013698305003345013
2023-01-22 19:39:01.570930: step: 190/470, loss: 0.26306137442588806
2023-01-22 19:39:02.438942: step: 192/470, loss: 0.007418145891278982
2023-01-22 19:39:03.204411: step: 194/470, loss: 0.45867234468460083
2023-01-22 19:39:03.969974: step: 196/470, loss: 0.014525515027344227
2023-01-22 19:39:04.703960: step: 198/470, loss: 0.06874248385429382
2023-01-22 19:39:05.426508: step: 200/470, loss: 1.0923312902450562
2023-01-22 19:39:06.114254: step: 202/470, loss: 0.012392209842801094
2023-01-22 19:39:06.843610: step: 204/470, loss: 0.10479408502578735
2023-01-22 19:39:07.590847: step: 206/470, loss: 0.013904137536883354
2023-01-22 19:39:08.285598: step: 208/470, loss: 0.03619790077209473
2023-01-22 19:39:09.021726: step: 210/470, loss: 0.36961981654167175
2023-01-22 19:39:09.724314: step: 212/470, loss: 0.08961759507656097
2023-01-22 19:39:10.527535: step: 214/470, loss: 0.14479438960552216
2023-01-22 19:39:11.187784: step: 216/470, loss: 0.027769066393375397
2023-01-22 19:39:11.876044: step: 218/470, loss: 0.11556971818208694
2023-01-22 19:39:12.600908: step: 220/470, loss: 0.03934004157781601
2023-01-22 19:39:13.379240: step: 222/470, loss: 0.08625157177448273
2023-01-22 19:39:14.130011: step: 224/470, loss: 2.8860392570495605
2023-01-22 19:39:14.895021: step: 226/470, loss: 0.03975597769021988
2023-01-22 19:39:15.663807: step: 228/470, loss: 0.013374090194702148
2023-01-22 19:39:16.427068: step: 230/470, loss: 0.035754621028900146
2023-01-22 19:39:17.189002: step: 232/470, loss: 0.19659562408924103
2023-01-22 19:39:17.909541: step: 234/470, loss: 0.23096928000450134
2023-01-22 19:39:18.583325: step: 236/470, loss: 0.04870816692709923
2023-01-22 19:39:19.409635: step: 238/470, loss: 0.05176544934511185
2023-01-22 19:39:20.153387: step: 240/470, loss: 0.034658364951610565
2023-01-22 19:39:20.907926: step: 242/470, loss: 0.06927529722452164
2023-01-22 19:39:21.590716: step: 244/470, loss: 0.010075340047478676
2023-01-22 19:39:22.401059: step: 246/470, loss: 0.03195039927959442
2023-01-22 19:39:23.199402: step: 248/470, loss: 0.02179635688662529
2023-01-22 19:39:23.958609: step: 250/470, loss: 0.13300231099128723
2023-01-22 19:39:24.691956: step: 252/470, loss: 0.04315396025776863
2023-01-22 19:39:25.466334: step: 254/470, loss: 0.02336571365594864
2023-01-22 19:39:26.222256: step: 256/470, loss: 0.04286831617355347
2023-01-22 19:39:26.822002: step: 258/470, loss: 0.17317862808704376
2023-01-22 19:39:27.591620: step: 260/470, loss: 0.15021666884422302
2023-01-22 19:39:28.225937: step: 262/470, loss: 0.039372485131025314
2023-01-22 19:39:29.072095: step: 264/470, loss: 0.014304211363196373
2023-01-22 19:39:29.800763: step: 266/470, loss: 0.04224678874015808
2023-01-22 19:39:30.521148: step: 268/470, loss: 0.0519757904112339
2023-01-22 19:39:31.259623: step: 270/470, loss: 0.018106307834386826
2023-01-22 19:39:31.967196: step: 272/470, loss: 0.22459372878074646
2023-01-22 19:39:32.635812: step: 274/470, loss: 0.00824404414743185
2023-01-22 19:39:33.398409: step: 276/470, loss: 0.020545797422528267
2023-01-22 19:39:34.077285: step: 278/470, loss: 0.013951159082353115
2023-01-22 19:39:34.889481: step: 280/470, loss: 0.0626802146434784
2023-01-22 19:39:35.651201: step: 282/470, loss: 0.0456269308924675
2023-01-22 19:39:36.362676: step: 284/470, loss: 1.7039402723312378
2023-01-22 19:39:37.081042: step: 286/470, loss: 0.024264952167868614
2023-01-22 19:39:37.818980: step: 288/470, loss: 0.060633957386016846
2023-01-22 19:39:38.563507: step: 290/470, loss: 0.01541169360280037
2023-01-22 19:39:39.295763: step: 292/470, loss: 0.02074408531188965
2023-01-22 19:39:40.014879: step: 294/470, loss: 0.008654659613966942
2023-01-22 19:39:40.740802: step: 296/470, loss: 0.03434770554304123
2023-01-22 19:39:41.466155: step: 298/470, loss: 0.1805637627840042
2023-01-22 19:39:42.219787: step: 300/470, loss: 0.1149728000164032
2023-01-22 19:39:42.950187: step: 302/470, loss: 0.015428435057401657
2023-01-22 19:39:43.670157: step: 304/470, loss: 0.018192537128925323
2023-01-22 19:39:44.442305: step: 306/470, loss: 0.0014132431242614985
2023-01-22 19:39:45.134393: step: 308/470, loss: 1.010900616645813
2023-01-22 19:39:45.844748: step: 310/470, loss: 0.025461159646511078
2023-01-22 19:39:46.624743: step: 312/470, loss: 0.031049776822328568
2023-01-22 19:39:47.433479: step: 314/470, loss: 0.04371613636612892
2023-01-22 19:39:48.146601: step: 316/470, loss: 0.11215726286172867
2023-01-22 19:39:48.932574: step: 318/470, loss: 0.002360484329983592
2023-01-22 19:39:49.656782: step: 320/470, loss: 0.04522380232810974
2023-01-22 19:39:50.322570: step: 322/470, loss: 0.048406392335891724
2023-01-22 19:39:50.999907: step: 324/470, loss: 0.002590734278783202
2023-01-22 19:39:51.723430: step: 326/470, loss: 0.17612895369529724
2023-01-22 19:39:52.457223: step: 328/470, loss: 0.04783718287944794
2023-01-22 19:39:53.235843: step: 330/470, loss: 0.08684522658586502
2023-01-22 19:39:53.994663: step: 332/470, loss: 0.0222398079931736
2023-01-22 19:39:54.683962: step: 334/470, loss: 0.09281022101640701
2023-01-22 19:39:55.437108: step: 336/470, loss: 0.018266357481479645
2023-01-22 19:39:56.231565: step: 338/470, loss: 0.05038531869649887
2023-01-22 19:39:56.915226: step: 340/470, loss: 0.12421422451734543
2023-01-22 19:39:57.591931: step: 342/470, loss: 0.030940696597099304
2023-01-22 19:39:58.385031: step: 344/470, loss: 0.0634685754776001
2023-01-22 19:39:59.133362: step: 346/470, loss: 0.06550871580839157
2023-01-22 19:39:59.940408: step: 348/470, loss: 0.02845531329512596
2023-01-22 19:40:00.774424: step: 350/470, loss: 0.03609459847211838
2023-01-22 19:40:01.568955: step: 352/470, loss: 0.0488816574215889
2023-01-22 19:40:02.355843: step: 354/470, loss: 0.013090868480503559
2023-01-22 19:40:02.991618: step: 356/470, loss: 0.009363566525280476
2023-01-22 19:40:03.687445: step: 358/470, loss: 0.06547439098358154
2023-01-22 19:40:04.418304: step: 360/470, loss: 0.11378369480371475
2023-01-22 19:40:05.170815: step: 362/470, loss: 0.10389399528503418
2023-01-22 19:40:05.877651: step: 364/470, loss: 0.1084824800491333
2023-01-22 19:40:06.665237: step: 366/470, loss: 0.03515470772981644
2023-01-22 19:40:07.374109: step: 368/470, loss: 0.03233461454510689
2023-01-22 19:40:08.068092: step: 370/470, loss: 0.010006394237279892
2023-01-22 19:40:08.795060: step: 372/470, loss: 0.0295244287699461
2023-01-22 19:40:09.532673: step: 374/470, loss: 0.006042733788490295
2023-01-22 19:40:10.250017: step: 376/470, loss: 0.06146341562271118
2023-01-22 19:40:11.168266: step: 378/470, loss: 0.03354865685105324
2023-01-22 19:40:11.930974: step: 380/470, loss: 0.024119818583130836
2023-01-22 19:40:12.684329: step: 382/470, loss: 0.12077596783638
2023-01-22 19:40:13.361785: step: 384/470, loss: 0.1539594531059265
2023-01-22 19:40:14.107412: step: 386/470, loss: 0.03286004438996315
2023-01-22 19:40:14.830780: step: 388/470, loss: 0.12388432770967484
2023-01-22 19:40:15.552646: step: 390/470, loss: 0.02824668027460575
2023-01-22 19:40:16.352473: step: 392/470, loss: 0.054188963025808334
2023-01-22 19:40:17.148983: step: 394/470, loss: 0.025531675666570663
2023-01-22 19:40:17.880453: step: 396/470, loss: 0.0763605609536171
2023-01-22 19:40:18.600677: step: 398/470, loss: 0.010550078935921192
2023-01-22 19:40:19.301784: step: 400/470, loss: 0.01099458895623684
2023-01-22 19:40:20.155437: step: 402/470, loss: 0.04127969220280647
2023-01-22 19:40:20.936684: step: 404/470, loss: 0.018147412687540054
2023-01-22 19:40:21.628037: step: 406/470, loss: 0.007162865251302719
2023-01-22 19:40:22.319361: step: 408/470, loss: 0.04229717701673508
2023-01-22 19:40:22.981365: step: 410/470, loss: 0.03728770837187767
2023-01-22 19:40:23.735522: step: 412/470, loss: 0.014461766928434372
2023-01-22 19:40:24.555387: step: 414/470, loss: 0.09930559992790222
2023-01-22 19:40:25.345084: step: 416/470, loss: 0.08320431411266327
2023-01-22 19:40:26.083723: step: 418/470, loss: 0.08579551428556442
2023-01-22 19:40:26.885994: step: 420/470, loss: 0.05773615464568138
2023-01-22 19:40:27.654124: step: 422/470, loss: 0.007528889924287796
2023-01-22 19:40:28.398178: step: 424/470, loss: 0.04420556128025055
2023-01-22 19:40:29.211797: step: 426/470, loss: 0.015755586326122284
2023-01-22 19:40:29.914112: step: 428/470, loss: 0.015585158951580524
2023-01-22 19:40:30.665335: step: 430/470, loss: 0.01235332153737545
2023-01-22 19:40:31.405414: step: 432/470, loss: 0.09456421434879303
2023-01-22 19:40:32.143530: step: 434/470, loss: 0.22690565884113312
2023-01-22 19:40:32.936471: step: 436/470, loss: 0.4971714913845062
2023-01-22 19:40:33.707624: step: 438/470, loss: 0.02801249548792839
2023-01-22 19:40:34.457721: step: 440/470, loss: 0.007650639396160841
2023-01-22 19:40:35.190803: step: 442/470, loss: 0.054860420525074005
2023-01-22 19:40:35.952228: step: 444/470, loss: 0.029611477628350258
2023-01-22 19:40:36.689439: step: 446/470, loss: 0.07205002754926682
2023-01-22 19:40:37.459443: step: 448/470, loss: 0.02133980020880699
2023-01-22 19:40:38.259920: step: 450/470, loss: 0.4700184762477875
2023-01-22 19:40:38.954775: step: 452/470, loss: 0.20984295010566711
2023-01-22 19:40:39.650346: step: 454/470, loss: 0.038992129266262054
2023-01-22 19:40:40.419792: step: 456/470, loss: 0.04633091017603874
2023-01-22 19:40:41.132670: step: 458/470, loss: 0.05490873381495476
2023-01-22 19:40:41.821579: step: 460/470, loss: 0.0526411309838295
2023-01-22 19:40:42.578709: step: 462/470, loss: 0.091351717710495
2023-01-22 19:40:43.295830: step: 464/470, loss: 0.008627299219369888
2023-01-22 19:40:43.967003: step: 466/470, loss: 0.00773763470351696
2023-01-22 19:40:44.707565: step: 468/470, loss: 0.004108825232833624
2023-01-22 19:40:45.455529: step: 470/470, loss: 0.06798605620861053
2023-01-22 19:40:46.231156: step: 472/470, loss: 0.04032795503735542
2023-01-22 19:40:46.975867: step: 474/470, loss: 0.03978598490357399
2023-01-22 19:40:47.728259: step: 476/470, loss: 0.022391952574253082
2023-01-22 19:40:48.489885: step: 478/470, loss: 0.08442055433988571
2023-01-22 19:40:49.366109: step: 480/470, loss: 0.041006091982126236
2023-01-22 19:40:50.109838: step: 482/470, loss: 0.054082486778497696
2023-01-22 19:40:50.899511: step: 484/470, loss: 0.056996893137693405
2023-01-22 19:40:51.671030: step: 486/470, loss: 0.21792449057102203
2023-01-22 19:40:52.462796: step: 488/470, loss: 0.09255671501159668
2023-01-22 19:40:53.182450: step: 490/470, loss: 0.0614955797791481
2023-01-22 19:40:53.974787: step: 492/470, loss: 0.034090857952833176
2023-01-22 19:40:54.645182: step: 494/470, loss: 0.27086207270622253
2023-01-22 19:40:55.453085: step: 496/470, loss: 0.3944252133369446
2023-01-22 19:40:56.126977: step: 498/470, loss: 0.06420669704675674
2023-01-22 19:40:56.899857: step: 500/470, loss: 2.5734214782714844
2023-01-22 19:40:57.594796: step: 502/470, loss: 0.16732986271381378
2023-01-22 19:40:58.331162: step: 504/470, loss: 0.0660572499036789
2023-01-22 19:40:59.095639: step: 506/470, loss: 0.03720968961715698
2023-01-22 19:40:59.868834: step: 508/470, loss: 0.10983237624168396
2023-01-22 19:41:00.590594: step: 510/470, loss: 0.09013104438781738
2023-01-22 19:41:01.292467: step: 512/470, loss: 0.020754126831889153
2023-01-22 19:41:01.978797: step: 514/470, loss: 0.017007894814014435
2023-01-22 19:41:02.678756: step: 516/470, loss: 0.035360775887966156
2023-01-22 19:41:03.445961: step: 518/470, loss: 0.04036063700914383
2023-01-22 19:41:04.172879: step: 520/470, loss: 0.08036433905363083
2023-01-22 19:41:04.934485: step: 522/470, loss: 0.06309843808412552
2023-01-22 19:41:05.765289: step: 524/470, loss: 0.03624216467142105
2023-01-22 19:41:06.444256: step: 526/470, loss: 0.016651665791869164
2023-01-22 19:41:07.247905: step: 528/470, loss: 0.03483118116855621
2023-01-22 19:41:07.967637: step: 530/470, loss: 0.0016926492098718882
2023-01-22 19:41:08.681282: step: 532/470, loss: 0.04679853096604347
2023-01-22 19:41:09.414301: step: 534/470, loss: 0.08570143580436707
2023-01-22 19:41:10.174681: step: 536/470, loss: 0.01729772239923477
2023-01-22 19:41:10.908419: step: 538/470, loss: 0.026970678940415382
2023-01-22 19:41:11.670816: step: 540/470, loss: 0.13230566680431366
2023-01-22 19:41:12.435870: step: 542/470, loss: 0.06809458136558533
2023-01-22 19:41:13.166208: step: 544/470, loss: 0.0313749760389328
2023-01-22 19:41:13.865821: step: 546/470, loss: 0.0077603161334991455
2023-01-22 19:41:14.673017: step: 548/470, loss: 0.031418073922395706
2023-01-22 19:41:15.482400: step: 550/470, loss: 0.0281534343957901
2023-01-22 19:41:16.265624: step: 552/470, loss: 1.547700047492981
2023-01-22 19:41:16.961961: step: 554/470, loss: 0.041558846831321716
2023-01-22 19:41:17.700759: step: 556/470, loss: 0.05451665446162224
2023-01-22 19:41:18.415619: step: 558/470, loss: 0.03179001063108444
2023-01-22 19:41:19.101140: step: 560/470, loss: 0.04917387664318085
2023-01-22 19:41:19.753936: step: 562/470, loss: 0.019586345180869102
2023-01-22 19:41:20.535654: step: 564/470, loss: 0.03305808827280998
2023-01-22 19:41:21.265790: step: 566/470, loss: 0.05808739736676216
2023-01-22 19:41:22.068039: step: 568/470, loss: 0.08200092613697052
2023-01-22 19:41:22.787662: step: 570/470, loss: 0.12195821106433868
2023-01-22 19:41:23.538055: step: 572/470, loss: 0.0011931839399039745
2023-01-22 19:41:24.265165: step: 574/470, loss: 0.06672245264053345
2023-01-22 19:41:25.035179: step: 576/470, loss: 0.10479816049337387
2023-01-22 19:41:25.705571: step: 578/470, loss: 0.09342262893915176
2023-01-22 19:41:26.498702: step: 580/470, loss: 0.04020530730485916
2023-01-22 19:41:27.227916: step: 582/470, loss: 0.058462418615818024
2023-01-22 19:41:27.989486: step: 584/470, loss: 0.03125924617052078
2023-01-22 19:41:28.726949: step: 586/470, loss: 0.12108433991670609
2023-01-22 19:41:29.422779: step: 588/470, loss: 0.008420255035161972
2023-01-22 19:41:30.209176: step: 590/470, loss: 0.03752874210476875
2023-01-22 19:41:31.049757: step: 592/470, loss: 0.30069804191589355
2023-01-22 19:41:31.795482: step: 594/470, loss: 0.050650861114263535
2023-01-22 19:41:32.511954: step: 596/470, loss: 0.06926306337118149
2023-01-22 19:41:33.221970: step: 598/470, loss: 0.052621450275182724
2023-01-22 19:41:34.021913: step: 600/470, loss: 0.05443857982754707
2023-01-22 19:41:34.718095: step: 602/470, loss: 0.0711992159485817
2023-01-22 19:41:35.445829: step: 604/470, loss: 0.005964161362498999
2023-01-22 19:41:36.300949: step: 606/470, loss: 0.18475210666656494
2023-01-22 19:41:37.001658: step: 608/470, loss: 0.09569357335567474
2023-01-22 19:41:37.781454: step: 610/470, loss: 0.07499527186155319
2023-01-22 19:41:38.493190: step: 612/470, loss: 0.13202105462551117
2023-01-22 19:41:39.208676: step: 614/470, loss: 0.04779544472694397
2023-01-22 19:41:40.190756: step: 616/470, loss: 0.04207386076450348
2023-01-22 19:41:40.928405: step: 618/470, loss: 0.08963283151388168
2023-01-22 19:41:41.677768: step: 620/470, loss: 0.02025291509926319
2023-01-22 19:41:42.393042: step: 622/470, loss: 0.22763288021087646
2023-01-22 19:41:43.189018: step: 624/470, loss: 0.0565686859190464
2023-01-22 19:41:43.811976: step: 626/470, loss: 0.07253819704055786
2023-01-22 19:41:44.474176: step: 628/470, loss: 0.1353847086429596
2023-01-22 19:41:45.169397: step: 630/470, loss: 0.1034807413816452
2023-01-22 19:41:45.954160: step: 632/470, loss: 0.04602696746587753
2023-01-22 19:41:46.674532: step: 634/470, loss: 0.0005324460798874497
2023-01-22 19:41:47.408938: step: 636/470, loss: 0.04955475404858589
2023-01-22 19:41:48.152749: step: 638/470, loss: 0.04272598400712013
2023-01-22 19:41:48.847078: step: 640/470, loss: 0.08605597168207169
2023-01-22 19:41:49.586741: step: 642/470, loss: 0.013445237651467323
2023-01-22 19:41:50.328938: step: 644/470, loss: 0.018981290981173515
2023-01-22 19:41:51.049024: step: 646/470, loss: 0.039564017206430435
2023-01-22 19:41:51.778289: step: 648/470, loss: 0.03769481182098389
2023-01-22 19:41:52.546969: step: 650/470, loss: 0.02641088329255581
2023-01-22 19:41:53.300367: step: 652/470, loss: 0.00315751601010561
2023-01-22 19:41:54.037284: step: 654/470, loss: 0.030088361352682114
2023-01-22 19:41:54.753773: step: 656/470, loss: 0.0600021593272686
2023-01-22 19:41:55.479282: step: 658/470, loss: 0.05731518939137459
2023-01-22 19:41:56.240477: step: 660/470, loss: 0.02242978662252426
2023-01-22 19:41:56.967747: step: 662/470, loss: 0.11539184302091599
2023-01-22 19:41:57.732620: step: 664/470, loss: 0.08133013546466827
2023-01-22 19:41:58.489729: step: 666/470, loss: 0.0326472632586956
2023-01-22 19:41:59.247626: step: 668/470, loss: 0.04640135541558266
2023-01-22 19:41:59.915185: step: 670/470, loss: 0.05912771821022034
2023-01-22 19:42:00.686535: step: 672/470, loss: 0.08168984949588776
2023-01-22 19:42:01.383948: step: 674/470, loss: 0.021860754117369652
2023-01-22 19:42:02.080570: step: 676/470, loss: 0.00997862871736288
2023-01-22 19:42:02.795414: step: 678/470, loss: 0.015150370076298714
2023-01-22 19:42:03.652389: step: 680/470, loss: 0.23191246390342712
2023-01-22 19:42:04.359419: step: 682/470, loss: 0.005268333945423365
2023-01-22 19:42:05.108412: step: 684/470, loss: 0.050369635224342346
2023-01-22 19:42:05.794924: step: 686/470, loss: 0.19161257147789001
2023-01-22 19:42:06.577321: step: 688/470, loss: 0.01200926210731268
2023-01-22 19:42:07.290037: step: 690/470, loss: 0.10803577303886414
2023-01-22 19:42:08.014181: step: 692/470, loss: 0.13654294610023499
2023-01-22 19:42:08.734563: step: 694/470, loss: 0.06747213006019592
2023-01-22 19:42:09.472206: step: 696/470, loss: 0.05152638256549835
2023-01-22 19:42:10.213845: step: 698/470, loss: 0.06810185313224792
2023-01-22 19:42:10.940649: step: 700/470, loss: 0.004062777850776911
2023-01-22 19:42:11.595625: step: 702/470, loss: 0.021000513806939125
2023-01-22 19:42:12.357541: step: 704/470, loss: 0.0744672566652298
2023-01-22 19:42:13.192106: step: 706/470, loss: 0.06481971591711044
2023-01-22 19:42:13.988629: step: 708/470, loss: 0.040443241596221924
2023-01-22 19:42:14.708193: step: 710/470, loss: 0.03952976316213608
2023-01-22 19:42:15.447415: step: 712/470, loss: 0.05129685252904892
2023-01-22 19:42:16.272666: step: 714/470, loss: 0.08018472790718079
2023-01-22 19:42:16.983620: step: 716/470, loss: 0.0011982826981693506
2023-01-22 19:42:17.672084: step: 718/470, loss: 0.01237798947840929
2023-01-22 19:42:18.346696: step: 720/470, loss: 0.030002785846590996
2023-01-22 19:42:19.012644: step: 722/470, loss: 0.029811648651957512
2023-01-22 19:42:19.759644: step: 724/470, loss: 0.028446856886148453
2023-01-22 19:42:20.537556: step: 726/470, loss: 0.03428805246949196
2023-01-22 19:42:21.229541: step: 728/470, loss: 0.04685278609395027
2023-01-22 19:42:22.021072: step: 730/470, loss: 0.011925329454243183
2023-01-22 19:42:22.839646: step: 732/470, loss: 0.10092224925756454
2023-01-22 19:42:23.512661: step: 734/470, loss: 0.014230447821319103
2023-01-22 19:42:24.259845: step: 736/470, loss: 0.06267601996660233
2023-01-22 19:42:24.991752: step: 738/470, loss: 0.0850699171423912
2023-01-22 19:42:25.794438: step: 740/470, loss: 0.014023186638951302
2023-01-22 19:42:26.494130: step: 742/470, loss: 0.11571689695119858
2023-01-22 19:42:27.168562: step: 744/470, loss: 0.05851830914616585
2023-01-22 19:42:27.885039: step: 746/470, loss: 0.7251389622688293
2023-01-22 19:42:28.685321: step: 748/470, loss: 0.21461817622184753
2023-01-22 19:42:29.429439: step: 750/470, loss: 0.056537434458732605
2023-01-22 19:42:30.146756: step: 752/470, loss: 0.06353659927845001
2023-01-22 19:42:30.999566: step: 754/470, loss: 0.14348191022872925
2023-01-22 19:42:31.704503: step: 756/470, loss: 0.021871326491236687
2023-01-22 19:42:32.508184: step: 758/470, loss: 0.059082724153995514
2023-01-22 19:42:33.276212: step: 760/470, loss: 0.0077812704257667065
2023-01-22 19:42:34.078844: step: 762/470, loss: 0.1153213232755661
2023-01-22 19:42:34.744283: step: 764/470, loss: 0.16919955611228943
2023-01-22 19:42:35.424507: step: 766/470, loss: 0.02236533723771572
2023-01-22 19:42:36.189153: step: 768/470, loss: 0.010637041181325912
2023-01-22 19:42:36.913213: step: 770/470, loss: 0.09718048572540283
2023-01-22 19:42:37.553805: step: 772/470, loss: 0.02509610913693905
2023-01-22 19:42:38.245345: step: 774/470, loss: 0.41436123847961426
2023-01-22 19:42:39.083301: step: 776/470, loss: 0.046184662729501724
2023-01-22 19:42:39.792362: step: 778/470, loss: 0.043335553258657455
2023-01-22 19:42:40.512214: step: 780/470, loss: 0.011558422818779945
2023-01-22 19:42:41.335890: step: 782/470, loss: 0.008647819980978966
2023-01-22 19:42:42.056075: step: 784/470, loss: 0.010468276217579842
2023-01-22 19:42:42.796339: step: 786/470, loss: 0.012684951536357403
2023-01-22 19:42:43.615946: step: 788/470, loss: 0.060763075947761536
2023-01-22 19:42:44.343336: step: 790/470, loss: 0.019749129191040993
2023-01-22 19:42:45.045616: step: 792/470, loss: 0.01861565373837948
2023-01-22 19:42:45.818670: step: 794/470, loss: 0.023979458957910538
2023-01-22 19:42:46.606614: step: 796/470, loss: 0.07430318742990494
2023-01-22 19:42:47.406483: step: 798/470, loss: 0.00071112992009148
2023-01-22 19:42:48.179008: step: 800/470, loss: 0.16077010333538055
2023-01-22 19:42:48.957690: step: 802/470, loss: 0.04622608423233032
2023-01-22 19:42:49.710815: step: 804/470, loss: 0.03751537576317787
2023-01-22 19:42:50.463727: step: 806/470, loss: 0.02206636592745781
2023-01-22 19:42:51.247229: step: 808/470, loss: 0.037656575441360474
2023-01-22 19:42:51.982613: step: 810/470, loss: 0.0038295581471174955
2023-01-22 19:42:52.693471: step: 812/470, loss: 0.007838837802410126
2023-01-22 19:42:53.348702: step: 814/470, loss: 0.0843760147690773
2023-01-22 19:42:54.121560: step: 816/470, loss: 0.12722979485988617
2023-01-22 19:42:54.827965: step: 818/470, loss: 0.004428504034876823
2023-01-22 19:42:55.576799: step: 820/470, loss: 0.017400939017534256
2023-01-22 19:42:56.306193: step: 822/470, loss: 0.11112985014915466
2023-01-22 19:42:57.112349: step: 824/470, loss: 0.06626398861408234
2023-01-22 19:42:57.864030: step: 826/470, loss: 0.006494198925793171
2023-01-22 19:42:58.564805: step: 828/470, loss: 0.003452116623520851
2023-01-22 19:42:59.311156: step: 830/470, loss: 0.04936700686812401
2023-01-22 19:43:00.035109: step: 832/470, loss: 0.06773626059293747
2023-01-22 19:43:00.784125: step: 834/470, loss: 0.25022315979003906
2023-01-22 19:43:01.499673: step: 836/470, loss: 0.09486892819404602
2023-01-22 19:43:02.263600: step: 838/470, loss: 0.06972448527812958
2023-01-22 19:43:03.110407: step: 840/470, loss: 0.05532016232609749
2023-01-22 19:43:03.793891: step: 842/470, loss: 0.06207747757434845
2023-01-22 19:43:04.473330: step: 844/470, loss: 0.07339915633201599
2023-01-22 19:43:05.256310: step: 846/470, loss: 0.04446965828537941
2023-01-22 19:43:06.007576: step: 848/470, loss: 0.1462089866399765
2023-01-22 19:43:06.719819: step: 850/470, loss: 0.06136621907353401
2023-01-22 19:43:07.450302: step: 852/470, loss: 0.08713188767433167
2023-01-22 19:43:08.168954: step: 854/470, loss: 0.06073979288339615
2023-01-22 19:43:08.795893: step: 856/470, loss: 0.024500612169504166
2023-01-22 19:43:09.508315: step: 858/470, loss: 0.0761837363243103
2023-01-22 19:43:10.264539: step: 860/470, loss: 0.037365589290857315
2023-01-22 19:43:11.033880: step: 862/470, loss: 0.018834102898836136
2023-01-22 19:43:11.692473: step: 864/470, loss: 0.009648923762142658
2023-01-22 19:43:12.445392: step: 866/470, loss: 0.006375704426318407
2023-01-22 19:43:13.237072: step: 868/470, loss: 0.047611527144908905
2023-01-22 19:43:13.961905: step: 870/470, loss: 0.009436516091227531
2023-01-22 19:43:14.739377: step: 872/470, loss: 0.1485144942998886
2023-01-22 19:43:15.463312: step: 874/470, loss: 0.030754825100302696
2023-01-22 19:43:16.188866: step: 876/470, loss: 0.03466818481683731
2023-01-22 19:43:16.962708: step: 878/470, loss: 0.05955606326460838
2023-01-22 19:43:17.703829: step: 880/470, loss: 0.036698900163173676
2023-01-22 19:43:18.449669: step: 882/470, loss: 0.03446055203676224
2023-01-22 19:43:19.283707: step: 884/470, loss: 0.04526906460523605
2023-01-22 19:43:19.955703: step: 886/470, loss: 0.015627926215529442
2023-01-22 19:43:20.739474: step: 888/470, loss: 0.0814151018857956
2023-01-22 19:43:21.462229: step: 890/470, loss: 0.25850528478622437
2023-01-22 19:43:22.287019: step: 892/470, loss: 0.18925324082374573
2023-01-22 19:43:23.016833: step: 894/470, loss: 0.04655158147215843
2023-01-22 19:43:23.747261: step: 896/470, loss: 0.08437757939100266
2023-01-22 19:43:24.480874: step: 898/470, loss: 0.04652692750096321
2023-01-22 19:43:25.273143: step: 900/470, loss: 3.10775089263916
2023-01-22 19:43:26.051170: step: 902/470, loss: 0.059189215302467346
2023-01-22 19:43:26.746343: step: 904/470, loss: 0.00953720137476921
2023-01-22 19:43:27.451598: step: 906/470, loss: 0.06070271134376526
2023-01-22 19:43:28.249949: step: 908/470, loss: 0.008491786196827888
2023-01-22 19:43:28.958060: step: 910/470, loss: 0.11616123467683792
2023-01-22 19:43:29.629287: step: 912/470, loss: 0.004306926857680082
2023-01-22 19:43:30.377258: step: 914/470, loss: 0.03736087679862976
2023-01-22 19:43:31.151740: step: 916/470, loss: 0.06064944341778755
2023-01-22 19:43:31.919245: step: 918/470, loss: 0.02283492125570774
2023-01-22 19:43:32.620864: step: 920/470, loss: 0.010427909903228283
2023-01-22 19:43:33.449531: step: 922/470, loss: 0.034641899168491364
2023-01-22 19:43:34.164034: step: 924/470, loss: 0.03633886203169823
2023-01-22 19:43:34.884569: step: 926/470, loss: 0.31999385356903076
2023-01-22 19:43:35.588567: step: 928/470, loss: 0.06611615419387817
2023-01-22 19:43:36.234468: step: 930/470, loss: 0.058460332453250885
2023-01-22 19:43:36.908288: step: 932/470, loss: 0.08226493000984192
2023-01-22 19:43:37.654060: step: 934/470, loss: 0.05760214105248451
2023-01-22 19:43:38.375980: step: 936/470, loss: 0.018661608919501305
2023-01-22 19:43:39.021879: step: 938/470, loss: 0.03469004109501839
2023-01-22 19:43:39.771635: step: 940/470, loss: 0.05704415589570999
2023-01-22 19:43:40.430838: step: 942/470, loss: 0.05449334532022476
==================================================
Loss: 0.096
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3092939210567948, 'r': 0.35331108249751514, 'f1': 0.32984046142814966}, 'combined': 0.24304033999968921, 'epoch': 22}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3275139861122523, 'r': 0.35869079825178396, 'f1': 0.3423941534482381}, 'combined': 0.23848348996394694, 'epoch': 22}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30467303045542077, 'r': 0.3543919690117134, 'f1': 0.3276571362617069}, 'combined': 0.2414315740875735, 'epoch': 22}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3318889213155725, 'r': 0.3532496876250282, 'f1': 0.3422363190485383}, 'combined': 0.23837355555619585, 'epoch': 22}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29258975351274114, 'r': 0.3586584075317472, 'f1': 0.3222727719850482}, 'combined': 0.23746414777845656, 'epoch': 22}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3165754369455721, 'r': 0.3649749508632124, 'f1': 0.3390566761033863}, 'combined': 0.23615887887798054, 'epoch': 22}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.19827586206896552, 'r': 0.32857142857142857, 'f1': 0.24731182795698925}, 'combined': 0.16487455197132617, 'epoch': 22}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.26282051282051283, 'r': 0.44565217391304346, 'f1': 0.3306451612903226}, 'combined': 0.1653225806451613, 'epoch': 22}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2980769230769231, 'r': 0.2672413793103448, 'f1': 0.2818181818181818}, 'combined': 0.18787878787878787, 'epoch': 22}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 23
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 19:46:16.807902: step: 2/470, loss: 0.020145274698734283
2023-01-22 19:46:17.562321: step: 4/470, loss: 0.012752152979373932
2023-01-22 19:46:18.239854: step: 6/470, loss: 0.018607724457979202
2023-01-22 19:46:19.006521: step: 8/470, loss: 0.04674272611737251
2023-01-22 19:46:19.734098: step: 10/470, loss: 0.08120296895503998
2023-01-22 19:46:20.510665: step: 12/470, loss: 0.04648889973759651
2023-01-22 19:46:21.314670: step: 14/470, loss: 0.041562411934137344
2023-01-22 19:46:22.071135: step: 16/470, loss: 0.24655379354953766
2023-01-22 19:46:22.835889: step: 18/470, loss: 0.02498440630733967
2023-01-22 19:46:23.516957: step: 20/470, loss: 0.05179232358932495
2023-01-22 19:46:24.243234: step: 22/470, loss: 0.03058280237019062
2023-01-22 19:46:25.044101: step: 24/470, loss: 0.11315041780471802
2023-01-22 19:46:25.723821: step: 26/470, loss: 0.018697861582040787
2023-01-22 19:46:26.407226: step: 28/470, loss: 0.006492226850241423
2023-01-22 19:46:27.144811: step: 30/470, loss: 0.09545272588729858
2023-01-22 19:46:27.873719: step: 32/470, loss: 0.024350939318537712
2023-01-22 19:46:28.592232: step: 34/470, loss: 0.5242292881011963
2023-01-22 19:46:29.286774: step: 36/470, loss: 0.017941568046808243
2023-01-22 19:46:30.015848: step: 38/470, loss: 0.08385952562093735
2023-01-22 19:46:30.696085: step: 40/470, loss: 0.03444410860538483
2023-01-22 19:46:31.509403: step: 42/470, loss: 0.007343780715018511
2023-01-22 19:46:32.198649: step: 44/470, loss: 0.08139993250370026
2023-01-22 19:46:33.049699: step: 46/470, loss: 0.029229672625660896
2023-01-22 19:46:33.774933: step: 48/470, loss: 0.031573113054037094
2023-01-22 19:46:34.637110: step: 50/470, loss: 0.01538156345486641
2023-01-22 19:46:35.371991: step: 52/470, loss: 0.01159243006259203
2023-01-22 19:46:36.102544: step: 54/470, loss: 0.08330456912517548
2023-01-22 19:46:36.833225: step: 56/470, loss: 0.004855206701904535
2023-01-22 19:46:37.548040: step: 58/470, loss: 0.12275192141532898
2023-01-22 19:46:38.375413: step: 60/470, loss: 0.07747679203748703
2023-01-22 19:46:39.081237: step: 62/470, loss: 0.009875631891191006
2023-01-22 19:46:39.854354: step: 64/470, loss: 0.016967376694083214
2023-01-22 19:46:40.526947: step: 66/470, loss: 0.003874419489875436
2023-01-22 19:46:41.298024: step: 68/470, loss: 0.018619472160935402
2023-01-22 19:46:42.069959: step: 70/470, loss: 0.08524934202432632
2023-01-22 19:46:42.783965: step: 72/470, loss: 0.027295870706439018
2023-01-22 19:46:43.530182: step: 74/470, loss: 0.0906219631433487
2023-01-22 19:46:44.306810: step: 76/470, loss: 0.04819449409842491
2023-01-22 19:46:45.058151: step: 78/470, loss: 0.0014960899716243148
2023-01-22 19:46:45.787761: step: 80/470, loss: 0.05570714548230171
2023-01-22 19:46:46.565310: step: 82/470, loss: 0.0980103462934494
2023-01-22 19:46:47.336618: step: 84/470, loss: 0.014589948579668999
2023-01-22 19:46:48.118907: step: 86/470, loss: 0.05184318125247955
2023-01-22 19:46:48.988653: step: 88/470, loss: 0.11208540946245193
2023-01-22 19:46:49.819905: step: 90/470, loss: 0.5855203866958618
2023-01-22 19:46:50.523063: step: 92/470, loss: 0.028581831604242325
2023-01-22 19:46:51.212159: step: 94/470, loss: 0.11515840142965317
2023-01-22 19:46:51.877369: step: 96/470, loss: 0.013613392598927021
2023-01-22 19:46:52.662454: step: 98/470, loss: 0.030206475406885147
2023-01-22 19:46:53.386049: step: 100/470, loss: 0.028599973767995834
2023-01-22 19:46:54.185794: step: 102/470, loss: 0.03127244487404823
2023-01-22 19:46:54.878848: step: 104/470, loss: 0.06208731234073639
2023-01-22 19:46:55.594862: step: 106/470, loss: 0.03612957522273064
2023-01-22 19:46:56.341099: step: 108/470, loss: 0.010129529982805252
2023-01-22 19:46:57.066577: step: 110/470, loss: 0.007978275418281555
2023-01-22 19:46:57.835663: step: 112/470, loss: 0.153214231133461
2023-01-22 19:46:58.614559: step: 114/470, loss: 0.022448312491178513
2023-01-22 19:46:59.389976: step: 116/470, loss: 0.035694267600774765
2023-01-22 19:47:00.157768: step: 118/470, loss: 0.10163560509681702
2023-01-22 19:47:00.933158: step: 120/470, loss: 0.015968233346939087
2023-01-22 19:47:01.651762: step: 122/470, loss: 0.025551877915859222
2023-01-22 19:47:02.307112: step: 124/470, loss: 0.019368741661310196
2023-01-22 19:47:03.056347: step: 126/470, loss: 0.027455579489469528
2023-01-22 19:47:03.757125: step: 128/470, loss: 0.052771057933568954
2023-01-22 19:47:04.665082: step: 130/470, loss: 0.007331357337534428
2023-01-22 19:47:05.446451: step: 132/470, loss: 0.05879795923829079
2023-01-22 19:47:06.265561: step: 134/470, loss: 0.013023512437939644
2023-01-22 19:47:06.971147: step: 136/470, loss: 0.009905382990837097
2023-01-22 19:47:07.655578: step: 138/470, loss: 0.0017207978526130319
2023-01-22 19:47:08.381113: step: 140/470, loss: 0.04617958515882492
2023-01-22 19:47:09.059245: step: 142/470, loss: 0.009676694869995117
2023-01-22 19:47:09.850377: step: 144/470, loss: 0.10442635416984558
2023-01-22 19:47:10.542682: step: 146/470, loss: 0.03223101794719696
2023-01-22 19:47:11.214719: step: 148/470, loss: 0.17558103799819946
2023-01-22 19:47:11.880671: step: 150/470, loss: 0.007184363901615143
2023-01-22 19:47:12.569852: step: 152/470, loss: 0.016059819608926773
2023-01-22 19:47:13.347419: step: 154/470, loss: 0.017226694151759148
2023-01-22 19:47:14.201322: step: 156/470, loss: 0.054372578859329224
2023-01-22 19:47:14.933392: step: 158/470, loss: 0.09041217714548111
2023-01-22 19:47:15.608609: step: 160/470, loss: 0.010833369567990303
2023-01-22 19:47:16.324026: step: 162/470, loss: 0.007517059799283743
2023-01-22 19:47:17.026197: step: 164/470, loss: 0.029931971803307533
2023-01-22 19:47:17.766191: step: 166/470, loss: 0.029189355671405792
2023-01-22 19:47:18.521749: step: 168/470, loss: 0.03147708997130394
2023-01-22 19:47:19.293119: step: 170/470, loss: 0.023568544536828995
2023-01-22 19:47:20.110565: step: 172/470, loss: 0.011535699479281902
2023-01-22 19:47:20.879882: step: 174/470, loss: 0.05071718618273735
2023-01-22 19:47:21.656568: step: 176/470, loss: 0.043926727026700974
2023-01-22 19:47:22.435036: step: 178/470, loss: 0.019493265077471733
2023-01-22 19:47:23.095903: step: 180/470, loss: 0.09586971253156662
2023-01-22 19:47:23.766626: step: 182/470, loss: 0.0498097725212574
2023-01-22 19:47:24.596760: step: 184/470, loss: 0.07411568611860275
2023-01-22 19:47:25.369315: step: 186/470, loss: 0.014985108748078346
2023-01-22 19:47:26.106169: step: 188/470, loss: 0.02051725424826145
2023-01-22 19:47:26.833736: step: 190/470, loss: 0.022670986130833626
2023-01-22 19:47:27.574121: step: 192/470, loss: 0.033521879464387894
2023-01-22 19:47:28.286518: step: 194/470, loss: 0.000296061800327152
2023-01-22 19:47:29.158047: step: 196/470, loss: 0.025557244196534157
2023-01-22 19:47:29.901914: step: 198/470, loss: 0.00772892776876688
2023-01-22 19:47:30.737533: step: 200/470, loss: 0.035560574382543564
2023-01-22 19:47:31.454194: step: 202/470, loss: 0.007423603907227516
2023-01-22 19:47:32.289383: step: 204/470, loss: 0.017200924456119537
2023-01-22 19:47:33.041396: step: 206/470, loss: 0.44262224435806274
2023-01-22 19:47:33.856279: step: 208/470, loss: 0.03299145773053169
2023-01-22 19:47:34.549640: step: 210/470, loss: 0.0001655942905927077
2023-01-22 19:47:35.313769: step: 212/470, loss: 0.01341554056853056
2023-01-22 19:47:36.054516: step: 214/470, loss: 0.3039006292819977
2023-01-22 19:47:36.826758: step: 216/470, loss: 0.0034072119742631912
2023-01-22 19:47:37.567171: step: 218/470, loss: 0.25233790278434753
2023-01-22 19:47:38.358791: step: 220/470, loss: 0.0021255554165691137
2023-01-22 19:47:39.073866: step: 222/470, loss: 0.7128084301948547
2023-01-22 19:47:39.837181: step: 224/470, loss: 0.0008448681910522282
2023-01-22 19:47:40.590057: step: 226/470, loss: 0.01992366835474968
2023-01-22 19:47:41.330851: step: 228/470, loss: 0.04137638583779335
2023-01-22 19:47:42.152764: step: 230/470, loss: 0.024264074862003326
2023-01-22 19:47:42.820195: step: 232/470, loss: 0.010322164744138718
2023-01-22 19:47:43.525345: step: 234/470, loss: 0.00993278156965971
2023-01-22 19:47:44.196324: step: 236/470, loss: 0.0286688432097435
2023-01-22 19:47:45.078676: step: 238/470, loss: 0.039216842502355576
2023-01-22 19:47:45.788080: step: 240/470, loss: 0.12787392735481262
2023-01-22 19:47:46.497193: step: 242/470, loss: 0.1834522932767868
2023-01-22 19:47:47.208678: step: 244/470, loss: 0.12740002572536469
2023-01-22 19:47:48.035206: step: 246/470, loss: 0.03960498049855232
2023-01-22 19:47:48.760890: step: 248/470, loss: 0.03761105611920357
2023-01-22 19:47:49.547074: step: 250/470, loss: 0.004436446353793144
2023-01-22 19:47:50.254354: step: 252/470, loss: 0.009433421306312084
2023-01-22 19:47:50.975438: step: 254/470, loss: 0.04656631872057915
2023-01-22 19:47:51.768380: step: 256/470, loss: 0.0027728108689188957
2023-01-22 19:47:52.562650: step: 258/470, loss: 0.9103434085845947
2023-01-22 19:47:53.220284: step: 260/470, loss: 0.04946238175034523
2023-01-22 19:47:53.932763: step: 262/470, loss: 0.0284775011241436
2023-01-22 19:47:54.660078: step: 264/470, loss: 0.12191655486822128
2023-01-22 19:47:55.389993: step: 266/470, loss: 0.07705827057361603
2023-01-22 19:47:56.099519: step: 268/470, loss: 0.05367019772529602
2023-01-22 19:47:56.841282: step: 270/470, loss: 0.03151824325323105
2023-01-22 19:47:57.586091: step: 272/470, loss: 0.0288032628595829
2023-01-22 19:47:58.333223: step: 274/470, loss: 0.02198009565472603
2023-01-22 19:47:59.015080: step: 276/470, loss: 0.3013882637023926
2023-01-22 19:47:59.847165: step: 278/470, loss: 0.00810268521308899
2023-01-22 19:48:00.554123: step: 280/470, loss: 0.3207792043685913
2023-01-22 19:48:01.314817: step: 282/470, loss: 0.03247154504060745
2023-01-22 19:48:02.087481: step: 284/470, loss: 0.11384246498346329
2023-01-22 19:48:02.856346: step: 286/470, loss: 0.06521860510110855
2023-01-22 19:48:03.562304: step: 288/470, loss: 0.08328651636838913
2023-01-22 19:48:04.183031: step: 290/470, loss: 0.004215493332594633
2023-01-22 19:48:04.946712: step: 292/470, loss: 0.08901931345462799
2023-01-22 19:48:05.725064: step: 294/470, loss: 0.00959330890327692
2023-01-22 19:48:06.446141: step: 296/470, loss: 0.6423669457435608
2023-01-22 19:48:07.182041: step: 298/470, loss: 0.032605089247226715
2023-01-22 19:48:07.956976: step: 300/470, loss: 0.02665814571082592
2023-01-22 19:48:08.604922: step: 302/470, loss: 0.04625895991921425
2023-01-22 19:48:09.290028: step: 304/470, loss: 0.19270682334899902
2023-01-22 19:48:09.985934: step: 306/470, loss: 0.005112417042255402
2023-01-22 19:48:10.684058: step: 308/470, loss: 0.01898195967078209
2023-01-22 19:48:11.451107: step: 310/470, loss: 0.007997587323188782
2023-01-22 19:48:12.239389: step: 312/470, loss: 0.03887288644909859
2023-01-22 19:48:12.949178: step: 314/470, loss: 0.03566152974963188
2023-01-22 19:48:13.675159: step: 316/470, loss: 0.017126863822340965
2023-01-22 19:48:14.494300: step: 318/470, loss: 0.16232366859912872
2023-01-22 19:48:15.284522: step: 320/470, loss: 0.005544004961848259
2023-01-22 19:48:16.008642: step: 322/470, loss: 0.02310621552169323
2023-01-22 19:48:16.765980: step: 324/470, loss: 0.0022491663694381714
2023-01-22 19:48:17.436073: step: 326/470, loss: 0.02474634349346161
2023-01-22 19:48:18.203166: step: 328/470, loss: 0.04117470234632492
2023-01-22 19:48:18.870398: step: 330/470, loss: 0.41619208455085754
2023-01-22 19:48:19.608893: step: 332/470, loss: 0.006768751889467239
2023-01-22 19:48:20.281204: step: 334/470, loss: 0.5537669062614441
2023-01-22 19:48:21.007540: step: 336/470, loss: 0.023046918213367462
2023-01-22 19:48:21.758696: step: 338/470, loss: 0.03325394541025162
2023-01-22 19:48:22.513727: step: 340/470, loss: 0.04114500433206558
2023-01-22 19:48:23.316142: step: 342/470, loss: 0.028026726096868515
2023-01-22 19:48:23.998970: step: 344/470, loss: 0.09893575310707092
2023-01-22 19:48:24.738128: step: 346/470, loss: 0.018749456852674484
2023-01-22 19:48:25.463398: step: 348/470, loss: 0.05088183283805847
2023-01-22 19:48:26.180328: step: 350/470, loss: 0.0032982854172587395
2023-01-22 19:48:26.899064: step: 352/470, loss: 0.054463837295770645
2023-01-22 19:48:27.650856: step: 354/470, loss: 0.11088722199201584
2023-01-22 19:48:28.406794: step: 356/470, loss: 0.13968579471111298
2023-01-22 19:48:29.090293: step: 358/470, loss: 0.030351005494594574
2023-01-22 19:48:29.776000: step: 360/470, loss: 0.03071235679090023
2023-01-22 19:48:30.472805: step: 362/470, loss: 0.0850130170583725
2023-01-22 19:48:31.127392: step: 364/470, loss: 0.759006679058075
2023-01-22 19:48:31.788921: step: 366/470, loss: 0.06871728599071503
2023-01-22 19:48:32.530376: step: 368/470, loss: 0.077363520860672
2023-01-22 19:48:33.194618: step: 370/470, loss: 0.01663314364850521
2023-01-22 19:48:33.886343: step: 372/470, loss: 0.03362368047237396
2023-01-22 19:48:34.642631: step: 374/470, loss: 0.01191516499966383
2023-01-22 19:48:35.324185: step: 376/470, loss: 0.029850145801901817
2023-01-22 19:48:36.001128: step: 378/470, loss: 0.007099964190274477
2023-01-22 19:48:36.708404: step: 380/470, loss: 0.9981684684753418
2023-01-22 19:48:37.563047: step: 382/470, loss: 0.018105922266840935
2023-01-22 19:48:38.220007: step: 384/470, loss: 0.07014259696006775
2023-01-22 19:48:38.990081: step: 386/470, loss: 0.04365800693631172
2023-01-22 19:48:39.775289: step: 388/470, loss: 0.10529167205095291
2023-01-22 19:48:40.460887: step: 390/470, loss: 0.07534227520227432
2023-01-22 19:48:41.180545: step: 392/470, loss: 0.07272927463054657
2023-01-22 19:48:41.885209: step: 394/470, loss: 0.06634674966335297
2023-01-22 19:48:42.636892: step: 396/470, loss: 0.04313298314809799
2023-01-22 19:48:43.338824: step: 398/470, loss: 0.0057480488903820515
2023-01-22 19:48:44.069417: step: 400/470, loss: 0.04004475101828575
2023-01-22 19:48:44.812311: step: 402/470, loss: 0.11582747101783752
2023-01-22 19:48:45.530347: step: 404/470, loss: 0.028773313388228416
2023-01-22 19:48:46.292295: step: 406/470, loss: 0.0024830615147948265
2023-01-22 19:48:47.048904: step: 408/470, loss: 0.07367391884326935
2023-01-22 19:48:47.846624: step: 410/470, loss: 0.08376302570104599
2023-01-22 19:48:48.570204: step: 412/470, loss: 0.021925557404756546
2023-01-22 19:48:49.267829: step: 414/470, loss: 0.0081571564078331
2023-01-22 19:48:49.959487: step: 416/470, loss: 0.01600341498851776
2023-01-22 19:48:50.678321: step: 418/470, loss: 0.07978179305791855
2023-01-22 19:48:51.396289: step: 420/470, loss: 0.03541692718863487
2023-01-22 19:48:52.109080: step: 422/470, loss: 0.0004405932268127799
2023-01-22 19:48:52.850537: step: 424/470, loss: 0.04251012206077576
2023-01-22 19:48:53.688158: step: 426/470, loss: 0.026230430230498314
2023-01-22 19:48:54.382388: step: 428/470, loss: 0.034719884395599365
2023-01-22 19:48:55.086639: step: 430/470, loss: 0.7030810117721558
2023-01-22 19:48:55.783311: step: 432/470, loss: 0.03227429836988449
2023-01-22 19:48:56.501073: step: 434/470, loss: 0.013126318342983723
2023-01-22 19:48:57.194323: step: 436/470, loss: 0.024919021874666214
2023-01-22 19:48:57.981023: step: 438/470, loss: 0.26918357610702515
2023-01-22 19:48:58.694923: step: 440/470, loss: 0.215628519654274
2023-01-22 19:48:59.395899: step: 442/470, loss: 0.03114582598209381
2023-01-22 19:49:00.073675: step: 444/470, loss: 0.0005924082943238318
2023-01-22 19:49:00.828103: step: 446/470, loss: 0.30109506845474243
2023-01-22 19:49:01.552737: step: 448/470, loss: 0.34661105275154114
2023-01-22 19:49:02.234800: step: 450/470, loss: 0.016731295734643936
2023-01-22 19:49:02.935705: step: 452/470, loss: 0.048470642417669296
2023-01-22 19:49:03.696704: step: 454/470, loss: 0.05453205108642578
2023-01-22 19:49:04.457528: step: 456/470, loss: 0.05783369764685631
2023-01-22 19:49:05.148369: step: 458/470, loss: 0.03494717925786972
2023-01-22 19:49:05.832229: step: 460/470, loss: 0.032794974744319916
2023-01-22 19:49:06.524850: step: 462/470, loss: 0.0035079510416835546
2023-01-22 19:49:07.217773: step: 464/470, loss: 0.06600449979305267
2023-01-22 19:49:07.943557: step: 466/470, loss: 0.0054876902140676975
2023-01-22 19:49:08.686532: step: 468/470, loss: 0.14131823182106018
2023-01-22 19:49:09.475560: step: 470/470, loss: 0.027415527030825615
2023-01-22 19:49:10.230943: step: 472/470, loss: 0.014964505098760128
2023-01-22 19:49:10.943671: step: 474/470, loss: 0.06728798151016235
2023-01-22 19:49:11.656499: step: 476/470, loss: 0.007798313163220882
2023-01-22 19:49:12.481500: step: 478/470, loss: 0.0030685949604958296
2023-01-22 19:49:13.199477: step: 480/470, loss: 0.07129280269145966
2023-01-22 19:49:13.922156: step: 482/470, loss: 0.03215346857905388
2023-01-22 19:49:14.652360: step: 484/470, loss: 0.0043903798796236515
2023-01-22 19:49:15.370528: step: 486/470, loss: 0.10907711833715439
2023-01-22 19:49:16.079402: step: 488/470, loss: 0.030243542045354843
2023-01-22 19:49:16.795818: step: 490/470, loss: 0.721255362033844
2023-01-22 19:49:17.621065: step: 492/470, loss: 0.030622025951743126
2023-01-22 19:49:18.325198: step: 494/470, loss: 0.026004338636994362
2023-01-22 19:49:19.105691: step: 496/470, loss: 0.03940839692950249
2023-01-22 19:49:19.822761: step: 498/470, loss: 0.08969125896692276
2023-01-22 19:49:20.544460: step: 500/470, loss: 0.016034258529543877
2023-01-22 19:49:21.327406: step: 502/470, loss: 0.054923348128795624
2023-01-22 19:49:22.076765: step: 504/470, loss: 0.03527640178799629
2023-01-22 19:49:22.848353: step: 506/470, loss: 0.05074672773480415
2023-01-22 19:49:23.570321: step: 508/470, loss: 0.019439974799752235
2023-01-22 19:49:24.442137: step: 510/470, loss: 0.029996780678629875
2023-01-22 19:49:25.163735: step: 512/470, loss: 0.0256869625300169
2023-01-22 19:49:25.977480: step: 514/470, loss: 0.03297635540366173
2023-01-22 19:49:26.738129: step: 516/470, loss: 0.01902947574853897
2023-01-22 19:49:27.415133: step: 518/470, loss: 0.1115870252251625
2023-01-22 19:49:28.091389: step: 520/470, loss: 0.013269971124827862
2023-01-22 19:49:28.875328: step: 522/470, loss: 0.030053507536649704
2023-01-22 19:49:29.575186: step: 524/470, loss: 0.4772378206253052
2023-01-22 19:49:30.373455: step: 526/470, loss: 0.12607523798942566
2023-01-22 19:49:31.108853: step: 528/470, loss: 0.007882537320256233
2023-01-22 19:49:31.897646: step: 530/470, loss: 0.041834231466054916
2023-01-22 19:49:32.686998: step: 532/470, loss: 0.13057224452495575
2023-01-22 19:49:33.496732: step: 534/470, loss: 0.14410966634750366
2023-01-22 19:49:34.235200: step: 536/470, loss: 0.03726746886968613
2023-01-22 19:49:34.981072: step: 538/470, loss: 0.023791544139385223
2023-01-22 19:49:35.757489: step: 540/470, loss: 0.01803162507712841
2023-01-22 19:49:36.562249: step: 542/470, loss: 0.1559169441461563
2023-01-22 19:49:37.363799: step: 544/470, loss: 0.024006202816963196
2023-01-22 19:49:38.098454: step: 546/470, loss: 0.018065424636006355
2023-01-22 19:49:38.758327: step: 548/470, loss: 0.01143345795571804
2023-01-22 19:49:39.449523: step: 550/470, loss: 0.13216164708137512
2023-01-22 19:49:40.171369: step: 552/470, loss: 0.09048359096050262
2023-01-22 19:49:40.943549: step: 554/470, loss: 0.016017138957977295
2023-01-22 19:49:41.667429: step: 556/470, loss: 0.028317036107182503
2023-01-22 19:49:42.397878: step: 558/470, loss: 0.01729518733918667
2023-01-22 19:49:43.075971: step: 560/470, loss: 0.01721752993762493
2023-01-22 19:49:43.818894: step: 562/470, loss: 0.0444251224398613
2023-01-22 19:49:44.628145: step: 564/470, loss: 0.005927725229412317
2023-01-22 19:49:45.398314: step: 566/470, loss: 0.027946837246418
2023-01-22 19:49:46.127919: step: 568/470, loss: 0.020798763260245323
2023-01-22 19:49:46.881985: step: 570/470, loss: 0.020342588424682617
2023-01-22 19:49:47.644455: step: 572/470, loss: 0.015030240640044212
2023-01-22 19:49:48.367499: step: 574/470, loss: 0.03206343948841095
2023-01-22 19:49:49.156164: step: 576/470, loss: 0.022603966295719147
2023-01-22 19:49:49.856826: step: 578/470, loss: 0.015919381752610207
2023-01-22 19:49:50.697944: step: 580/470, loss: 0.04253147542476654
2023-01-22 19:49:51.411158: step: 582/470, loss: 0.009290401823818684
2023-01-22 19:49:52.274774: step: 584/470, loss: 0.12215080112218857
2023-01-22 19:49:52.949156: step: 586/470, loss: 0.07029620558023453
2023-01-22 19:49:53.675075: step: 588/470, loss: 0.09041906893253326
2023-01-22 19:49:54.446719: step: 590/470, loss: 0.029489658772945404
2023-01-22 19:49:55.160695: step: 592/470, loss: 0.06253940612077713
2023-01-22 19:49:55.919148: step: 594/470, loss: 0.009752373211085796
2023-01-22 19:49:56.606326: step: 596/470, loss: 0.04571554809808731
2023-01-22 19:49:57.421382: step: 598/470, loss: 0.038326047360897064
2023-01-22 19:49:58.105106: step: 600/470, loss: 0.014072294346988201
2023-01-22 19:49:58.918590: step: 602/470, loss: 0.12891465425491333
2023-01-22 19:49:59.617089: step: 604/470, loss: 0.08130002021789551
2023-01-22 19:50:00.369843: step: 606/470, loss: 0.015089713968336582
2023-01-22 19:50:01.167443: step: 608/470, loss: 0.04352075606584549
2023-01-22 19:50:01.917879: step: 610/470, loss: 0.13570909202098846
2023-01-22 19:50:02.625588: step: 612/470, loss: 0.04086529463529587
2023-01-22 19:50:03.436138: step: 614/470, loss: 1.2370469570159912
2023-01-22 19:50:04.166986: step: 616/470, loss: 0.02251041680574417
2023-01-22 19:50:04.952159: step: 618/470, loss: 0.04271961376070976
2023-01-22 19:50:05.711835: step: 620/470, loss: 0.03870357945561409
2023-01-22 19:50:06.436938: step: 622/470, loss: 0.0048131453804671764
2023-01-22 19:50:07.149664: step: 624/470, loss: 0.05446334183216095
2023-01-22 19:50:08.086126: step: 626/470, loss: 0.025662001222372055
2023-01-22 19:50:08.796457: step: 628/470, loss: 0.036178234964609146
2023-01-22 19:50:09.522597: step: 630/470, loss: 0.05717697739601135
2023-01-22 19:50:10.332636: step: 632/470, loss: 0.030181117355823517
2023-01-22 19:50:11.089353: step: 634/470, loss: 0.013264654204249382
2023-01-22 19:50:11.816468: step: 636/470, loss: 0.26037362217903137
2023-01-22 19:50:12.598981: step: 638/470, loss: 0.10497309267520905
2023-01-22 19:50:13.282154: step: 640/470, loss: 0.0047654202207922935
2023-01-22 19:50:13.985834: step: 642/470, loss: 0.04302401840686798
2023-01-22 19:50:14.672927: step: 644/470, loss: 0.06489899009466171
2023-01-22 19:50:15.449954: step: 646/470, loss: 0.18413802981376648
2023-01-22 19:50:16.169271: step: 648/470, loss: 0.8595938682556152
2023-01-22 19:50:16.925370: step: 650/470, loss: 0.005972123239189386
2023-01-22 19:50:17.590608: step: 652/470, loss: 0.0459543913602829
2023-01-22 19:50:18.364784: step: 654/470, loss: 0.0675494596362114
2023-01-22 19:50:19.194407: step: 656/470, loss: 0.053448911756277084
2023-01-22 19:50:19.905799: step: 658/470, loss: 0.009192129597067833
2023-01-22 19:50:20.642914: step: 660/470, loss: 0.02981734089553356
2023-01-22 19:50:21.373599: step: 662/470, loss: 0.1048010066151619
2023-01-22 19:50:22.117407: step: 664/470, loss: 0.09085634350776672
2023-01-22 19:50:22.903070: step: 666/470, loss: 0.026635007932782173
2023-01-22 19:50:23.596770: step: 668/470, loss: 0.0010363566689193249
2023-01-22 19:50:24.230908: step: 670/470, loss: 0.009339814074337482
2023-01-22 19:50:24.920099: step: 672/470, loss: 0.0018867823528125882
2023-01-22 19:50:25.631979: step: 674/470, loss: 0.2046578824520111
2023-01-22 19:50:26.393879: step: 676/470, loss: 0.06945720314979553
2023-01-22 19:50:27.209084: step: 678/470, loss: 0.003970560152083635
2023-01-22 19:50:27.915853: step: 680/470, loss: 0.01167396642267704
2023-01-22 19:50:28.597210: step: 682/470, loss: 0.035459429025650024
2023-01-22 19:50:29.299195: step: 684/470, loss: 0.024924641475081444
2023-01-22 19:50:29.939194: step: 686/470, loss: 0.013809597119688988
2023-01-22 19:50:30.739608: step: 688/470, loss: 0.1835506558418274
2023-01-22 19:50:31.492177: step: 690/470, loss: 0.022687483578920364
2023-01-22 19:50:32.232338: step: 692/470, loss: 0.008208868093788624
2023-01-22 19:50:32.899732: step: 694/470, loss: 0.010190270841121674
2023-01-22 19:50:33.678596: step: 696/470, loss: 0.035994742065668106
2023-01-22 19:50:34.443104: step: 698/470, loss: 0.037245918065309525
2023-01-22 19:50:35.213764: step: 700/470, loss: 0.10593031346797943
2023-01-22 19:50:35.937574: step: 702/470, loss: 0.0002846399147529155
2023-01-22 19:50:36.629613: step: 704/470, loss: 0.01668049953877926
2023-01-22 19:50:37.368319: step: 706/470, loss: 0.15217755734920502
2023-01-22 19:50:38.053602: step: 708/470, loss: 0.02269909158349037
2023-01-22 19:50:38.875929: step: 710/470, loss: 0.02121802605688572
2023-01-22 19:50:39.584156: step: 712/470, loss: 0.06413817405700684
2023-01-22 19:50:40.251343: step: 714/470, loss: 0.026240617036819458
2023-01-22 19:50:40.948659: step: 716/470, loss: 0.04450815171003342
2023-01-22 19:50:41.691060: step: 718/470, loss: 0.012417121790349483
2023-01-22 19:50:42.440852: step: 720/470, loss: 0.053188763558864594
2023-01-22 19:50:43.178130: step: 722/470, loss: 0.006177571602165699
2023-01-22 19:50:43.869826: step: 724/470, loss: 0.007825598120689392
2023-01-22 19:50:44.632819: step: 726/470, loss: 0.808793306350708
2023-01-22 19:50:45.314639: step: 728/470, loss: 0.021689899265766144
2023-01-22 19:50:46.063570: step: 730/470, loss: 0.015059007331728935
2023-01-22 19:50:46.873533: step: 732/470, loss: 0.14715488255023956
2023-01-22 19:50:47.578516: step: 734/470, loss: 0.008766661398112774
2023-01-22 19:50:48.351529: step: 736/470, loss: 0.07060243934392929
2023-01-22 19:50:49.174137: step: 738/470, loss: 0.05194990336894989
2023-01-22 19:50:49.895490: step: 740/470, loss: 0.1445123255252838
2023-01-22 19:50:50.623112: step: 742/470, loss: 0.020801223814487457
2023-01-22 19:50:51.327007: step: 744/470, loss: 0.010486302897334099
2023-01-22 19:50:52.008168: step: 746/470, loss: 0.037710774689912796
2023-01-22 19:50:52.783198: step: 748/470, loss: 0.20508471131324768
2023-01-22 19:50:53.493512: step: 750/470, loss: 0.047555048018693924
2023-01-22 19:50:54.249142: step: 752/470, loss: 0.020251981914043427
2023-01-22 19:50:55.039390: step: 754/470, loss: 0.09589096158742905
2023-01-22 19:50:55.840133: step: 756/470, loss: 0.030110789462924004
2023-01-22 19:50:56.496892: step: 758/470, loss: 0.012403149157762527
2023-01-22 19:50:57.280279: step: 760/470, loss: 0.017901351675391197
2023-01-22 19:50:58.035306: step: 762/470, loss: 0.049641214311122894
2023-01-22 19:50:58.804259: step: 764/470, loss: 0.09870140254497528
2023-01-22 19:50:59.546252: step: 766/470, loss: 0.03105722926557064
2023-01-22 19:51:00.311824: step: 768/470, loss: 0.026463506743311882
2023-01-22 19:51:00.999906: step: 770/470, loss: 0.010589334182441235
2023-01-22 19:51:01.799338: step: 772/470, loss: 0.033002715557813644
2023-01-22 19:51:02.567562: step: 774/470, loss: 0.25736182928085327
2023-01-22 19:51:03.349957: step: 776/470, loss: 0.025068465620279312
2023-01-22 19:51:04.043686: step: 778/470, loss: 0.334775447845459
2023-01-22 19:51:04.725461: step: 780/470, loss: 0.042881835252046585
2023-01-22 19:51:05.432215: step: 782/470, loss: 0.04640914872288704
2023-01-22 19:51:06.108430: step: 784/470, loss: 0.009364593774080276
2023-01-22 19:51:06.751464: step: 786/470, loss: 0.04730172082781792
2023-01-22 19:51:07.481152: step: 788/470, loss: 0.1467842310667038
2023-01-22 19:51:08.281332: step: 790/470, loss: 0.09448494762182236
2023-01-22 19:51:09.049184: step: 792/470, loss: 0.03505510836839676
2023-01-22 19:51:09.826742: step: 794/470, loss: 0.1019258052110672
2023-01-22 19:51:10.621615: step: 796/470, loss: 0.2154480367898941
2023-01-22 19:51:11.258697: step: 798/470, loss: 0.04859409108757973
2023-01-22 19:51:11.986230: step: 800/470, loss: 0.005880818236619234
2023-01-22 19:51:12.667472: step: 802/470, loss: 0.0315140001475811
2023-01-22 19:51:13.383238: step: 804/470, loss: 0.023350920528173447
2023-01-22 19:51:14.097503: step: 806/470, loss: 0.0514444075524807
2023-01-22 19:51:14.836306: step: 808/470, loss: 0.004267614334821701
2023-01-22 19:51:15.583946: step: 810/470, loss: 0.12531037628650665
2023-01-22 19:51:16.313449: step: 812/470, loss: 0.15931852161884308
2023-01-22 19:51:17.043529: step: 814/470, loss: 0.028155192732810974
2023-01-22 19:51:17.750166: step: 816/470, loss: 0.013806957751512527
2023-01-22 19:51:18.439565: step: 818/470, loss: 0.014839094132184982
2023-01-22 19:51:19.136092: step: 820/470, loss: 0.01098904013633728
2023-01-22 19:51:19.861353: step: 822/470, loss: 0.06523977220058441
2023-01-22 19:51:20.555695: step: 824/470, loss: 0.022953085601329803
2023-01-22 19:51:21.309027: step: 826/470, loss: 0.019507238641381264
2023-01-22 19:51:22.128005: step: 828/470, loss: 0.036449965089559555
2023-01-22 19:51:22.837009: step: 830/470, loss: 0.368724524974823
2023-01-22 19:51:23.650325: step: 832/470, loss: 0.007018078118562698
2023-01-22 19:51:24.374036: step: 834/470, loss: 0.023230871185660362
2023-01-22 19:51:25.045088: step: 836/470, loss: 0.0515056848526001
2023-01-22 19:51:25.798154: step: 838/470, loss: 0.12788495421409607
2023-01-22 19:51:26.578506: step: 840/470, loss: 0.0066448175348341465
2023-01-22 19:51:27.265833: step: 842/470, loss: 0.01157106552273035
2023-01-22 19:51:28.005598: step: 844/470, loss: 0.002934497781097889
2023-01-22 19:51:28.726949: step: 846/470, loss: 0.023657750338315964
2023-01-22 19:51:29.430272: step: 848/470, loss: 0.050684839487075806
2023-01-22 19:51:30.217300: step: 850/470, loss: 0.016548197716474533
2023-01-22 19:51:30.994838: step: 852/470, loss: 0.042522866278886795
2023-01-22 19:51:31.685947: step: 854/470, loss: 0.41254308819770813
2023-01-22 19:51:32.395627: step: 856/470, loss: 0.0507955327630043
2023-01-22 19:51:33.177054: step: 858/470, loss: 0.023885458707809448
2023-01-22 19:51:33.926295: step: 860/470, loss: 0.02228032425045967
2023-01-22 19:51:34.656913: step: 862/470, loss: 0.034615080803632736
2023-01-22 19:51:35.370873: step: 864/470, loss: 0.09413474798202515
2023-01-22 19:51:36.204589: step: 866/470, loss: 0.03352166339755058
2023-01-22 19:51:36.929254: step: 868/470, loss: 0.05351152643561363
2023-01-22 19:51:37.642027: step: 870/470, loss: 0.024592425674200058
2023-01-22 19:51:38.311288: step: 872/470, loss: 0.06424624472856522
2023-01-22 19:51:39.074079: step: 874/470, loss: 0.0035424302332103252
2023-01-22 19:51:39.784233: step: 876/470, loss: 0.003755184356123209
2023-01-22 19:51:40.524411: step: 878/470, loss: 0.08013807982206345
2023-01-22 19:51:41.289061: step: 880/470, loss: 0.03286373242735863
2023-01-22 19:51:42.012599: step: 882/470, loss: 0.04773545265197754
2023-01-22 19:51:42.731882: step: 884/470, loss: 0.053945161402225494
2023-01-22 19:51:43.439924: step: 886/470, loss: 0.1546299159526825
2023-01-22 19:51:44.186491: step: 888/470, loss: 0.01916525699198246
2023-01-22 19:51:44.873968: step: 890/470, loss: 0.06273111701011658
2023-01-22 19:51:45.557700: step: 892/470, loss: 0.08657549321651459
2023-01-22 19:51:46.299089: step: 894/470, loss: 0.10691189765930176
2023-01-22 19:51:47.010565: step: 896/470, loss: 0.0036090798676013947
2023-01-22 19:51:47.744114: step: 898/470, loss: 0.05727309733629227
2023-01-22 19:51:48.584673: step: 900/470, loss: 0.04444019868969917
2023-01-22 19:51:49.319198: step: 902/470, loss: 0.06358946114778519
2023-01-22 19:51:50.046801: step: 904/470, loss: 0.0498536042869091
2023-01-22 19:51:50.791931: step: 906/470, loss: 0.03799587860703468
2023-01-22 19:51:51.540456: step: 908/470, loss: 0.0830104649066925
2023-01-22 19:51:52.386222: step: 910/470, loss: 0.0941431000828743
2023-01-22 19:51:53.078670: step: 912/470, loss: 0.01036920491605997
2023-01-22 19:51:53.803801: step: 914/470, loss: 0.05386245623230934
2023-01-22 19:51:54.566184: step: 916/470, loss: 0.02375110797584057
2023-01-22 19:51:55.283065: step: 918/470, loss: 0.033866845071315765
2023-01-22 19:51:55.968090: step: 920/470, loss: 0.02378959022462368
2023-01-22 19:51:56.674941: step: 922/470, loss: 0.07435478270053864
2023-01-22 19:51:57.391220: step: 924/470, loss: 0.004783568903803825
2023-01-22 19:51:58.112151: step: 926/470, loss: 0.015685396268963814
2023-01-22 19:51:58.813234: step: 928/470, loss: 0.056146442890167236
2023-01-22 19:51:59.548529: step: 930/470, loss: 0.05725179240107536
2023-01-22 19:52:00.439709: step: 932/470, loss: 0.05904132127761841
2023-01-22 19:52:01.173584: step: 934/470, loss: 0.015635449439287186
2023-01-22 19:52:01.979774: step: 936/470, loss: 0.04005289822816849
2023-01-22 19:52:02.684942: step: 938/470, loss: 0.018923653289675713
2023-01-22 19:52:03.322610: step: 940/470, loss: 0.011358820833265781
2023-01-22 19:52:04.071638: step: 942/470, loss: 0.037756726145744324
==================================================
Loss: 0.075
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3127608825283244, 'r': 0.3317520556609741, 'f1': 0.32197667280540215}, 'combined': 0.23724596943555948, 'epoch': 23}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3318102481602698, 'r': 0.36977699770937766, 'f1': 0.34976632798340407}, 'combined': 0.24361833789888843, 'epoch': 23}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29553775743707095, 'r': 0.32245580745031455, 'f1': 0.30841054541981083}, 'combined': 0.22724987557249218, 'epoch': 23}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3428697959566185, 'r': 0.3712224906222619, 'f1': 0.3564832781598822}, 'combined': 0.2482968106586244, 'epoch': 23}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2902272727272727, 'r': 0.3331831119544592, 'f1': 0.31022526501766784}, 'combined': 0.22858703738143946, 'epoch': 23}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32936868566543354, 'r': 0.38352449840465386, 'f1': 0.3543895853761351}, 'combined': 0.24683851717740754, 'epoch': 23}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23317307692307693, 'r': 0.3464285714285714, 'f1': 0.278735632183908}, 'combined': 0.185823754789272, 'epoch': 23}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2948717948717949, 'r': 0.5, 'f1': 0.3709677419354839}, 'combined': 0.18548387096774194, 'epoch': 23}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 23}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 24
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 19:54:40.229341: step: 2/470, loss: 0.09071078896522522
2023-01-22 19:54:41.008997: step: 4/470, loss: 0.025325173512101173
2023-01-22 19:54:41.805530: step: 6/470, loss: 0.08036006987094879
2023-01-22 19:54:42.542003: step: 8/470, loss: 0.021646693348884583
2023-01-22 19:54:43.304232: step: 10/470, loss: 0.049812790006399155
2023-01-22 19:54:44.059712: step: 12/470, loss: 0.01448730006814003
2023-01-22 19:54:44.755314: step: 14/470, loss: 0.030710160732269287
2023-01-22 19:54:45.519827: step: 16/470, loss: 0.019698522984981537
2023-01-22 19:54:46.244285: step: 18/470, loss: 0.007313847541809082
2023-01-22 19:54:47.094986: step: 20/470, loss: 0.058628715574741364
2023-01-22 19:54:47.755199: step: 22/470, loss: 0.008414885960519314
2023-01-22 19:54:48.500594: step: 24/470, loss: 0.04240531101822853
2023-01-22 19:54:49.221190: step: 26/470, loss: 0.011772439815104008
2023-01-22 19:54:49.907291: step: 28/470, loss: 0.018150269985198975
2023-01-22 19:54:50.516711: step: 30/470, loss: 0.1334639936685562
2023-01-22 19:54:51.247882: step: 32/470, loss: 0.006515135522931814
2023-01-22 19:54:51.919098: step: 34/470, loss: 0.0021217716857790947
2023-01-22 19:54:52.654395: step: 36/470, loss: 0.10562937706708908
2023-01-22 19:54:53.477053: step: 38/470, loss: 0.012553170323371887
2023-01-22 19:54:54.159041: step: 40/470, loss: 0.020525362342596054
2023-01-22 19:54:55.025488: step: 42/470, loss: 0.10595296323299408
2023-01-22 19:54:55.702936: step: 44/470, loss: 0.08366550505161285
2023-01-22 19:54:56.374935: step: 46/470, loss: 0.020429229363799095
2023-01-22 19:54:57.071190: step: 48/470, loss: 0.024408716708421707
2023-01-22 19:54:57.732127: step: 50/470, loss: 0.03457806631922722
2023-01-22 19:54:58.461058: step: 52/470, loss: 0.06466998159885406
2023-01-22 19:54:59.193850: step: 54/470, loss: 0.009562093764543533
2023-01-22 19:54:59.932287: step: 56/470, loss: 1.4924793243408203
2023-01-22 19:55:00.667329: step: 58/470, loss: 0.04375853016972542
2023-01-22 19:55:01.460620: step: 60/470, loss: 0.0036672528367489576
2023-01-22 19:55:02.154944: step: 62/470, loss: 0.0689840093255043
2023-01-22 19:55:02.970698: step: 64/470, loss: 0.342257022857666
2023-01-22 19:55:03.677246: step: 66/470, loss: 0.10635102540254593
2023-01-22 19:55:04.317241: step: 68/470, loss: 0.026408610865473747
2023-01-22 19:55:05.022738: step: 70/470, loss: 0.051238052546978
2023-01-22 19:55:05.813972: step: 72/470, loss: 0.036443691700696945
2023-01-22 19:55:06.543456: step: 74/470, loss: 0.06277167797088623
2023-01-22 19:55:07.280709: step: 76/470, loss: 0.01571185700595379
2023-01-22 19:55:08.044151: step: 78/470, loss: 0.0491529181599617
2023-01-22 19:55:08.836999: step: 80/470, loss: 0.04565410315990448
2023-01-22 19:55:09.543885: step: 82/470, loss: 0.00350984581746161
2023-01-22 19:55:10.239625: step: 84/470, loss: 0.011095493100583553
2023-01-22 19:55:10.902728: step: 86/470, loss: 0.09822019934654236
2023-01-22 19:55:11.692413: step: 88/470, loss: 0.007752100471407175
2023-01-22 19:55:12.404292: step: 90/470, loss: 0.031544268131256104
2023-01-22 19:55:13.076106: step: 92/470, loss: 0.017505712807178497
2023-01-22 19:55:13.796308: step: 94/470, loss: 0.008974706754088402
2023-01-22 19:55:14.483314: step: 96/470, loss: 0.004836901556700468
2023-01-22 19:55:15.143585: step: 98/470, loss: 0.026484636589884758
2023-01-22 19:55:15.910534: step: 100/470, loss: 0.3591688275337219
2023-01-22 19:55:16.579849: step: 102/470, loss: 0.030483385547995567
2023-01-22 19:55:17.313710: step: 104/470, loss: 0.0007766528287902474
2023-01-22 19:55:17.997075: step: 106/470, loss: 0.015138084068894386
2023-01-22 19:55:18.786032: step: 108/470, loss: 0.02235487848520279
2023-01-22 19:55:19.617685: step: 110/470, loss: 0.20309732854366302
2023-01-22 19:55:20.323160: step: 112/470, loss: 0.17128710448741913
2023-01-22 19:55:21.114067: step: 114/470, loss: 0.032276567071676254
2023-01-22 19:55:21.798281: step: 116/470, loss: 0.02128906175494194
2023-01-22 19:55:22.505736: step: 118/470, loss: 0.002846565330401063
2023-01-22 19:55:23.266667: step: 120/470, loss: 0.5752863883972168
2023-01-22 19:55:23.951490: step: 122/470, loss: 0.0021211388520896435
2023-01-22 19:55:24.662839: step: 124/470, loss: 0.01313631609082222
2023-01-22 19:55:25.339181: step: 126/470, loss: 0.009652921929955482
2023-01-22 19:55:26.089851: step: 128/470, loss: 0.07296048104763031
2023-01-22 19:55:26.791851: step: 130/470, loss: 0.01581062190234661
2023-01-22 19:55:27.670132: step: 132/470, loss: 0.032663170248270035
2023-01-22 19:55:28.401964: step: 134/470, loss: 0.19434767961502075
2023-01-22 19:55:29.147076: step: 136/470, loss: 0.03558581322431564
2023-01-22 19:55:29.951971: step: 138/470, loss: 0.02339303307235241
2023-01-22 19:55:30.675223: step: 140/470, loss: 0.015170947648584843
2023-01-22 19:55:31.331376: step: 142/470, loss: 0.1154085025191307
2023-01-22 19:55:32.117211: step: 144/470, loss: 0.007798160891979933
2023-01-22 19:55:32.898101: step: 146/470, loss: 0.01072743721306324
2023-01-22 19:55:33.641468: step: 148/470, loss: 0.018375081941485405
2023-01-22 19:55:34.407597: step: 150/470, loss: 0.06826124340295792
2023-01-22 19:55:35.066806: step: 152/470, loss: 0.020997071638703346
2023-01-22 19:55:35.743470: step: 154/470, loss: 0.20793934166431427
2023-01-22 19:55:36.528835: step: 156/470, loss: 0.015171626582741737
2023-01-22 19:55:37.354938: step: 158/470, loss: 0.026798272505402565
2023-01-22 19:55:38.087133: step: 160/470, loss: 0.027822552248835564
2023-01-22 19:55:38.822957: step: 162/470, loss: 0.0003175846068188548
2023-01-22 19:55:39.605717: step: 164/470, loss: 0.007902979850769043
2023-01-22 19:55:40.405012: step: 166/470, loss: 0.034732285887002945
2023-01-22 19:55:41.119097: step: 168/470, loss: 0.18924480676651
2023-01-22 19:55:41.897668: step: 170/470, loss: 0.08738310635089874
2023-01-22 19:55:42.719287: step: 172/470, loss: 0.018750211223959923
2023-01-22 19:55:43.449150: step: 174/470, loss: 0.05455208197236061
2023-01-22 19:55:44.117321: step: 176/470, loss: 0.014304988086223602
2023-01-22 19:55:44.914749: step: 178/470, loss: 0.015335150994360447
2023-01-22 19:55:45.610193: step: 180/470, loss: 0.0569082647562027
2023-01-22 19:55:46.445183: step: 182/470, loss: 0.07909173518419266
2023-01-22 19:55:47.117336: step: 184/470, loss: 0.014027910307049751
2023-01-22 19:55:47.851270: step: 186/470, loss: 0.018430842086672783
2023-01-22 19:55:48.605402: step: 188/470, loss: 0.004810623824596405
2023-01-22 19:55:49.357853: step: 190/470, loss: 0.03506871312856674
2023-01-22 19:55:50.097556: step: 192/470, loss: 0.05087616667151451
2023-01-22 19:55:50.759918: step: 194/470, loss: 0.025519607588648796
2023-01-22 19:55:51.603248: step: 196/470, loss: 0.010457420721650124
2023-01-22 19:55:52.257971: step: 198/470, loss: 0.010845007374882698
2023-01-22 19:55:52.909456: step: 200/470, loss: 0.015168682672083378
2023-01-22 19:55:53.684294: step: 202/470, loss: 0.026464076712727547
2023-01-22 19:55:54.441763: step: 204/470, loss: 0.015966270118951797
2023-01-22 19:55:55.230093: step: 206/470, loss: 0.011198129504919052
2023-01-22 19:55:55.943674: step: 208/470, loss: 0.0012512399116531014
2023-01-22 19:55:56.656882: step: 210/470, loss: 0.024326816201210022
2023-01-22 19:55:57.358533: step: 212/470, loss: 0.03241521865129471
2023-01-22 19:55:58.096948: step: 214/470, loss: 0.08937463164329529
2023-01-22 19:55:58.862754: step: 216/470, loss: 7.647789607290179e-05
2023-01-22 19:55:59.604969: step: 218/470, loss: 0.09640821069478989
2023-01-22 19:56:00.314557: step: 220/470, loss: 0.051727913320064545
2023-01-22 19:56:01.011796: step: 222/470, loss: 0.25078266859054565
2023-01-22 19:56:01.760143: step: 224/470, loss: 0.001110507408156991
2023-01-22 19:56:02.575851: step: 226/470, loss: 0.023081980645656586
2023-01-22 19:56:03.275104: step: 228/470, loss: 0.2709239721298218
2023-01-22 19:56:03.940003: step: 230/470, loss: 0.012674129568040371
2023-01-22 19:56:04.795075: step: 232/470, loss: 0.010699287056922913
2023-01-22 19:56:05.572806: step: 234/470, loss: 0.007047413848340511
2023-01-22 19:56:06.316289: step: 236/470, loss: 0.011672616936266422
2023-01-22 19:56:07.093094: step: 238/470, loss: 0.013916079886257648
2023-01-22 19:56:07.802819: step: 240/470, loss: 0.18569129705429077
2023-01-22 19:56:08.483274: step: 242/470, loss: 0.011190307326614857
2023-01-22 19:56:09.253647: step: 244/470, loss: 0.09461580961942673
2023-01-22 19:56:10.006129: step: 246/470, loss: 0.03384866937994957
2023-01-22 19:56:10.675548: step: 248/470, loss: 0.004926465917378664
2023-01-22 19:56:11.422591: step: 250/470, loss: 0.017905734479427338
2023-01-22 19:56:12.188837: step: 252/470, loss: 2.1755669116973877
2023-01-22 19:56:12.906747: step: 254/470, loss: 0.05439945310354233
2023-01-22 19:56:13.641926: step: 256/470, loss: 0.12149098515510559
2023-01-22 19:56:14.374883: step: 258/470, loss: 0.012873425148427486
2023-01-22 19:56:15.201521: step: 260/470, loss: 0.08463416993618011
2023-01-22 19:56:15.940709: step: 262/470, loss: 0.06308569759130478
2023-01-22 19:56:16.729415: step: 264/470, loss: 0.0345967635512352
2023-01-22 19:56:17.410896: step: 266/470, loss: 0.03556538745760918
2023-01-22 19:56:18.206766: step: 268/470, loss: 0.036040298640728
2023-01-22 19:56:18.945329: step: 270/470, loss: 0.02199576050043106
2023-01-22 19:56:19.631398: step: 272/470, loss: 0.04857220500707626
2023-01-22 19:56:20.360781: step: 274/470, loss: 0.009337391704320908
2023-01-22 19:56:21.181624: step: 276/470, loss: 0.017865784466266632
2023-01-22 19:56:21.892917: step: 278/470, loss: 0.05819854885339737
2023-01-22 19:56:22.686729: step: 280/470, loss: 0.03172709047794342
2023-01-22 19:56:23.446107: step: 282/470, loss: 0.017821263521909714
2023-01-22 19:56:24.279026: step: 284/470, loss: 0.12068352103233337
2023-01-22 19:56:24.994759: step: 286/470, loss: 0.010906575247645378
2023-01-22 19:56:25.721720: step: 288/470, loss: 0.017595164477825165
2023-01-22 19:56:26.410535: step: 290/470, loss: 0.01801401562988758
2023-01-22 19:56:27.208862: step: 292/470, loss: 0.012894317507743835
2023-01-22 19:56:28.017970: step: 294/470, loss: 2.5075581073760986
2023-01-22 19:56:28.739997: step: 296/470, loss: 0.053497977554798126
2023-01-22 19:56:29.478686: step: 298/470, loss: 0.007422546856105328
2023-01-22 19:56:30.204484: step: 300/470, loss: 0.30072087049484253
2023-01-22 19:56:30.914684: step: 302/470, loss: 0.08959358930587769
2023-01-22 19:56:31.674153: step: 304/470, loss: 0.009266148321330547
2023-01-22 19:56:32.392886: step: 306/470, loss: 0.014265595935285091
2023-01-22 19:56:33.102451: step: 308/470, loss: 0.010140521451830864
2023-01-22 19:56:33.766861: step: 310/470, loss: 0.07897411286830902
2023-01-22 19:56:34.556415: step: 312/470, loss: 0.025504056364297867
2023-01-22 19:56:35.326081: step: 314/470, loss: 0.02470008283853531
2023-01-22 19:56:36.268828: step: 316/470, loss: 0.07380572706460953
2023-01-22 19:56:36.975607: step: 318/470, loss: 0.013543383218348026
2023-01-22 19:56:37.755777: step: 320/470, loss: 0.05348219349980354
2023-01-22 19:56:38.440233: step: 322/470, loss: 0.03541599214076996
2023-01-22 19:56:39.131443: step: 324/470, loss: 0.01773747242987156
2023-01-22 19:56:39.873740: step: 326/470, loss: 0.7491196990013123
2023-01-22 19:56:40.554594: step: 328/470, loss: 0.03136305883526802
2023-01-22 19:56:41.288410: step: 330/470, loss: 0.042486634105443954
2023-01-22 19:56:42.138844: step: 332/470, loss: 0.025926154106855392
2023-01-22 19:56:42.828122: step: 334/470, loss: 0.02339969575405121
2023-01-22 19:56:43.568383: step: 336/470, loss: 0.04502348601818085
2023-01-22 19:56:44.314655: step: 338/470, loss: 0.014835294336080551
2023-01-22 19:56:45.005666: step: 340/470, loss: 0.04183325543999672
2023-01-22 19:56:45.753347: step: 342/470, loss: 0.0881599634885788
2023-01-22 19:56:46.473044: step: 344/470, loss: 0.0676642656326294
2023-01-22 19:56:47.247662: step: 346/470, loss: 0.05381879583001137
2023-01-22 19:56:47.936444: step: 348/470, loss: 0.056068144738674164
2023-01-22 19:56:48.682412: step: 350/470, loss: 0.03975946456193924
2023-01-22 19:56:49.427964: step: 352/470, loss: 0.004915451630949974
2023-01-22 19:56:50.120820: step: 354/470, loss: 0.037539318203926086
2023-01-22 19:56:50.835214: step: 356/470, loss: 0.017015933990478516
2023-01-22 19:56:51.625012: step: 358/470, loss: 0.01815337873995304
2023-01-22 19:56:52.276292: step: 360/470, loss: 0.011578904464840889
2023-01-22 19:56:52.976244: step: 362/470, loss: 0.0952455922961235
2023-01-22 19:56:53.715386: step: 364/470, loss: 0.029356520622968674
2023-01-22 19:56:54.383576: step: 366/470, loss: 0.03291197121143341
2023-01-22 19:56:55.085741: step: 368/470, loss: 0.044890958815813065
2023-01-22 19:56:55.880581: step: 370/470, loss: 0.014463989064097404
2023-01-22 19:56:56.580064: step: 372/470, loss: 0.029671261087059975
2023-01-22 19:56:57.382976: step: 374/470, loss: 0.1202852725982666
2023-01-22 19:56:58.106776: step: 376/470, loss: 0.02309921756386757
2023-01-22 19:56:58.811731: step: 378/470, loss: 0.0008545005111955106
2023-01-22 19:56:59.581743: step: 380/470, loss: 0.02537860907614231
2023-01-22 19:57:00.310236: step: 382/470, loss: 0.01265999861061573
2023-01-22 19:57:01.058959: step: 384/470, loss: 0.06934566795825958
2023-01-22 19:57:01.704201: step: 386/470, loss: 0.04263785108923912
2023-01-22 19:57:02.355502: step: 388/470, loss: 0.055505167692899704
2023-01-22 19:57:03.092026: step: 390/470, loss: 0.05536120757460594
2023-01-22 19:57:03.885370: step: 392/470, loss: 0.01172667182981968
2023-01-22 19:57:04.638407: step: 394/470, loss: 0.13547594845294952
2023-01-22 19:57:05.388414: step: 396/470, loss: 0.0048871287144720554
2023-01-22 19:57:06.140946: step: 398/470, loss: 0.22317151725292206
2023-01-22 19:57:06.865291: step: 400/470, loss: 0.02091968059539795
2023-01-22 19:57:07.591176: step: 402/470, loss: 0.0756245031952858
2023-01-22 19:57:08.265985: step: 404/470, loss: 0.08365000039339066
2023-01-22 19:57:09.000391: step: 406/470, loss: 0.021144846454262733
2023-01-22 19:57:09.700663: step: 408/470, loss: 0.02719028852880001
2023-01-22 19:57:10.373223: step: 410/470, loss: 0.002817704575136304
2023-01-22 19:57:11.093439: step: 412/470, loss: 0.020920658484101295
2023-01-22 19:57:11.923855: step: 414/470, loss: 0.037627965211868286
2023-01-22 19:57:12.591560: step: 416/470, loss: 0.0015627248212695122
2023-01-22 19:57:13.291207: step: 418/470, loss: 0.027174735441803932
2023-01-22 19:57:14.001537: step: 420/470, loss: 0.016970563679933548
2023-01-22 19:57:14.754881: step: 422/470, loss: 0.006052455864846706
2023-01-22 19:57:15.424135: step: 424/470, loss: 0.14455130696296692
2023-01-22 19:57:16.132196: step: 426/470, loss: 0.05896090343594551
2023-01-22 19:57:16.871270: step: 428/470, loss: 0.016825811937451363
2023-01-22 19:57:17.666002: step: 430/470, loss: 0.009072363376617432
2023-01-22 19:57:18.436040: step: 432/470, loss: 0.004168605897575617
2023-01-22 19:57:19.205023: step: 434/470, loss: 0.05164012685418129
2023-01-22 19:57:19.953853: step: 436/470, loss: 0.1026514321565628
2023-01-22 19:57:20.636125: step: 438/470, loss: 0.0008245318895205855
2023-01-22 19:57:21.330762: step: 440/470, loss: 0.001791208516806364
2023-01-22 19:57:22.061744: step: 442/470, loss: 0.042904458940029144
2023-01-22 19:57:22.828320: step: 444/470, loss: 0.007724056486040354
2023-01-22 19:57:23.556504: step: 446/470, loss: 0.043044883757829666
2023-01-22 19:57:24.265978: step: 448/470, loss: 0.011818325147032738
2023-01-22 19:57:24.981607: step: 450/470, loss: 0.061016157269477844
2023-01-22 19:57:25.755303: step: 452/470, loss: 0.06787383556365967
2023-01-22 19:57:26.505534: step: 454/470, loss: 0.03366108238697052
2023-01-22 19:57:27.324450: step: 456/470, loss: 0.042890019714832306
2023-01-22 19:57:28.070846: step: 458/470, loss: 0.0524488128721714
2023-01-22 19:57:28.853456: step: 460/470, loss: 0.013294907286763191
2023-01-22 19:57:29.579245: step: 462/470, loss: 0.05481591448187828
2023-01-22 19:57:30.266846: step: 464/470, loss: 0.01968459226191044
2023-01-22 19:57:31.041947: step: 466/470, loss: 0.011313038878142834
2023-01-22 19:57:31.919974: step: 468/470, loss: 0.18432138860225677
2023-01-22 19:57:32.632017: step: 470/470, loss: 0.04200728237628937
2023-01-22 19:57:33.437219: step: 472/470, loss: 0.03416682779788971
2023-01-22 19:57:34.153720: step: 474/470, loss: 0.013105719350278378
2023-01-22 19:57:34.882619: step: 476/470, loss: 0.008894217200577259
2023-01-22 19:57:35.598689: step: 478/470, loss: 0.03804539516568184
2023-01-22 19:57:36.239777: step: 480/470, loss: 0.0294265728443861
2023-01-22 19:57:36.961312: step: 482/470, loss: 0.021114999428391457
2023-01-22 19:57:37.681293: step: 484/470, loss: 0.049864597618579865
2023-01-22 19:57:38.448701: step: 486/470, loss: 0.021185453981161118
2023-01-22 19:57:39.175508: step: 488/470, loss: 0.0015564959030598402
2023-01-22 19:57:39.807089: step: 490/470, loss: 0.02223014645278454
2023-01-22 19:57:40.556948: step: 492/470, loss: 0.02108120173215866
2023-01-22 19:57:41.266127: step: 494/470, loss: 0.10416891425848007
2023-01-22 19:57:41.964884: step: 496/470, loss: 0.04583205655217171
2023-01-22 19:57:42.608338: step: 498/470, loss: 0.02937087044119835
2023-01-22 19:57:43.398565: step: 500/470, loss: 0.00716931140050292
2023-01-22 19:57:44.217453: step: 502/470, loss: 0.01689540222287178
2023-01-22 19:57:44.919855: step: 504/470, loss: 0.029801655560731888
2023-01-22 19:57:45.603431: step: 506/470, loss: 0.05905457213521004
2023-01-22 19:57:46.310792: step: 508/470, loss: 0.11677312850952148
2023-01-22 19:57:47.151944: step: 510/470, loss: 0.018942374736070633
2023-01-22 19:57:47.860378: step: 512/470, loss: 0.00495618861168623
2023-01-22 19:57:48.648251: step: 514/470, loss: 0.0023889688309282064
2023-01-22 19:57:49.383704: step: 516/470, loss: 0.07100418955087662
2023-01-22 19:57:50.128410: step: 518/470, loss: 0.021969538182020187
2023-01-22 19:57:50.905192: step: 520/470, loss: 0.05502269044518471
2023-01-22 19:57:51.604963: step: 522/470, loss: 0.15007732808589935
2023-01-22 19:57:52.318586: step: 524/470, loss: 0.11543755233287811
2023-01-22 19:57:53.066906: step: 526/470, loss: 0.051974616944789886
2023-01-22 19:57:53.791348: step: 528/470, loss: 0.04661441594362259
2023-01-22 19:57:54.519135: step: 530/470, loss: 0.010496355593204498
2023-01-22 19:57:55.266332: step: 532/470, loss: 0.022741319611668587
2023-01-22 19:57:55.997789: step: 534/470, loss: 0.0360884964466095
2023-01-22 19:57:56.614845: step: 536/470, loss: 0.28176605701446533
2023-01-22 19:57:57.357890: step: 538/470, loss: 0.000371862348401919
2023-01-22 19:57:58.129467: step: 540/470, loss: 0.016311364248394966
2023-01-22 19:57:58.817171: step: 542/470, loss: 0.6123561859130859
2023-01-22 19:57:59.529420: step: 544/470, loss: 0.06656290590763092
2023-01-22 19:58:00.329052: step: 546/470, loss: 0.00262643164023757
2023-01-22 19:58:01.166756: step: 548/470, loss: 0.07897511124610901
2023-01-22 19:58:01.906940: step: 550/470, loss: 0.06647037714719772
2023-01-22 19:58:02.581419: step: 552/470, loss: 0.06914768368005753
2023-01-22 19:58:03.309819: step: 554/470, loss: 0.023323729634284973
2023-01-22 19:58:04.034256: step: 556/470, loss: 0.05517176166176796
2023-01-22 19:58:04.807193: step: 558/470, loss: 0.01975119113922119
2023-01-22 19:58:05.514720: step: 560/470, loss: 0.010775907896459103
2023-01-22 19:58:06.250827: step: 562/470, loss: 0.06182064861059189
2023-01-22 19:58:06.888628: step: 564/470, loss: 0.0013573778560385108
2023-01-22 19:58:07.606092: step: 566/470, loss: 0.026441359892487526
2023-01-22 19:58:08.320684: step: 568/470, loss: 0.03428468853235245
2023-01-22 19:58:09.123829: step: 570/470, loss: 0.015539498068392277
2023-01-22 19:58:09.936214: step: 572/470, loss: 0.038939252495765686
2023-01-22 19:58:10.624730: step: 574/470, loss: 0.02000570483505726
2023-01-22 19:58:11.302225: step: 576/470, loss: 0.01621418446302414
2023-01-22 19:58:12.051973: step: 578/470, loss: 0.08785783499479294
2023-01-22 19:58:12.817029: step: 580/470, loss: 0.10585880279541016
2023-01-22 19:58:13.557509: step: 582/470, loss: 0.037938281893730164
2023-01-22 19:58:14.262846: step: 584/470, loss: 0.0022830679081380367
2023-01-22 19:58:15.007104: step: 586/470, loss: 0.007178565952926874
2023-01-22 19:58:15.812236: step: 588/470, loss: 0.009578043594956398
2023-01-22 19:58:16.586558: step: 590/470, loss: 0.06791942566633224
2023-01-22 19:58:17.427036: step: 592/470, loss: 0.3170134127140045
2023-01-22 19:58:18.048049: step: 594/470, loss: 0.00753396563231945
2023-01-22 19:58:18.781324: step: 596/470, loss: 0.04484763741493225
2023-01-22 19:58:19.510879: step: 598/470, loss: 0.013004643842577934
2023-01-22 19:58:20.226314: step: 600/470, loss: 0.02657913789153099
2023-01-22 19:58:20.982042: step: 602/470, loss: 0.0408782996237278
2023-01-22 19:58:21.732527: step: 604/470, loss: 0.012685599736869335
2023-01-22 19:58:22.478124: step: 606/470, loss: 0.003009774489328265
2023-01-22 19:58:23.200359: step: 608/470, loss: 0.2504468560218811
2023-01-22 19:58:23.856091: step: 610/470, loss: 0.0925365537405014
2023-01-22 19:58:24.584755: step: 612/470, loss: 0.018450234085321426
2023-01-22 19:58:25.333411: step: 614/470, loss: 0.04527146741747856
2023-01-22 19:58:26.039717: step: 616/470, loss: 0.03232667222619057
2023-01-22 19:58:26.727847: step: 618/470, loss: 0.037647586315870285
2023-01-22 19:58:27.501020: step: 620/470, loss: 0.02571326307952404
2023-01-22 19:58:28.285780: step: 622/470, loss: 0.054269880056381226
2023-01-22 19:58:29.029544: step: 624/470, loss: 0.028405921533703804
2023-01-22 19:58:29.731059: step: 626/470, loss: 0.020112626254558563
2023-01-22 19:58:30.500944: step: 628/470, loss: 0.005061836447566748
2023-01-22 19:58:31.216152: step: 630/470, loss: 0.14112667739391327
2023-01-22 19:58:31.935517: step: 632/470, loss: 0.006791027262806892
2023-01-22 19:58:32.641640: step: 634/470, loss: 0.009881870821118355
2023-01-22 19:58:33.375798: step: 636/470, loss: 0.06305323541164398
2023-01-22 19:58:34.088715: step: 638/470, loss: 0.05328913778066635
2023-01-22 19:58:34.765981: step: 640/470, loss: 0.002296677092090249
2023-01-22 19:58:35.507978: step: 642/470, loss: 0.007883894257247448
2023-01-22 19:58:36.334863: step: 644/470, loss: 0.05610523000359535
2023-01-22 19:58:37.065237: step: 646/470, loss: 0.022641412913799286
2023-01-22 19:58:37.736262: step: 648/470, loss: 0.025629589334130287
2023-01-22 19:58:38.489564: step: 650/470, loss: 0.047313909977674484
2023-01-22 19:58:39.158345: step: 652/470, loss: 0.02791016362607479
2023-01-22 19:58:39.847583: step: 654/470, loss: 0.01351831667125225
2023-01-22 19:58:40.682736: step: 656/470, loss: 0.01588682271540165
2023-01-22 19:58:41.369918: step: 658/470, loss: 0.04910393804311752
2023-01-22 19:58:42.190264: step: 660/470, loss: 0.11366312205791473
2023-01-22 19:58:42.924350: step: 662/470, loss: 0.12863023579120636
2023-01-22 19:58:43.569071: step: 664/470, loss: 0.09127775579690933
2023-01-22 19:58:44.334207: step: 666/470, loss: 0.21341535449028015
2023-01-22 19:58:45.066958: step: 668/470, loss: 0.015620485879480839
2023-01-22 19:58:45.763726: step: 670/470, loss: 0.03588823601603508
2023-01-22 19:58:46.475714: step: 672/470, loss: 0.025998149067163467
2023-01-22 19:58:47.283605: step: 674/470, loss: 0.06447438150644302
2023-01-22 19:58:47.934834: step: 676/470, loss: 0.06617400795221329
2023-01-22 19:58:48.647140: step: 678/470, loss: 0.2020503729581833
2023-01-22 19:58:49.441578: step: 680/470, loss: 0.03483056649565697
2023-01-22 19:58:50.171673: step: 682/470, loss: 0.017954112961888313
2023-01-22 19:58:50.897237: step: 684/470, loss: 0.01776493713259697
2023-01-22 19:58:51.601007: step: 686/470, loss: 0.018190190196037292
2023-01-22 19:58:52.358894: step: 688/470, loss: 0.0707760602235794
2023-01-22 19:58:53.117469: step: 690/470, loss: 0.06905476748943329
2023-01-22 19:58:53.970056: step: 692/470, loss: 0.08601033687591553
2023-01-22 19:58:54.737304: step: 694/470, loss: 0.007111764047294855
2023-01-22 19:58:55.463558: step: 696/470, loss: 0.026374198496341705
2023-01-22 19:58:56.162025: step: 698/470, loss: 0.03967350348830223
2023-01-22 19:58:56.915761: step: 700/470, loss: 0.03607969358563423
2023-01-22 19:58:57.626334: step: 702/470, loss: 0.017128845676779747
2023-01-22 19:58:58.363601: step: 704/470, loss: 0.04204748570919037
2023-01-22 19:58:59.191487: step: 706/470, loss: 0.17484718561172485
2023-01-22 19:58:59.917371: step: 708/470, loss: 0.0665166974067688
2023-01-22 19:59:00.549197: step: 710/470, loss: 0.03982820361852646
2023-01-22 19:59:01.384937: step: 712/470, loss: 0.015020914375782013
2023-01-22 19:59:02.079404: step: 714/470, loss: 0.014696701429784298
2023-01-22 19:59:02.842580: step: 716/470, loss: 0.2812211513519287
2023-01-22 19:59:03.574246: step: 718/470, loss: 2.2691924571990967
2023-01-22 19:59:04.368338: step: 720/470, loss: 0.06255054473876953
2023-01-22 19:59:05.151238: step: 722/470, loss: 0.025868145748972893
2023-01-22 19:59:05.904240: step: 724/470, loss: 0.0933215320110321
2023-01-22 19:59:06.629418: step: 726/470, loss: 0.156637504696846
2023-01-22 19:59:07.332374: step: 728/470, loss: 0.11742421239614487
2023-01-22 19:59:08.059243: step: 730/470, loss: 0.09174972772598267
2023-01-22 19:59:08.844087: step: 732/470, loss: 0.04268868640065193
2023-01-22 19:59:09.663391: step: 734/470, loss: 0.07636651396751404
2023-01-22 19:59:10.385503: step: 736/470, loss: 0.013568645343184471
2023-01-22 19:59:11.099377: step: 738/470, loss: 0.03813782334327698
2023-01-22 19:59:11.806486: step: 740/470, loss: 0.019819870591163635
2023-01-22 19:59:12.602217: step: 742/470, loss: 0.04321083426475525
2023-01-22 19:59:13.325795: step: 744/470, loss: 0.006098398473113775
2023-01-22 19:59:14.031538: step: 746/470, loss: 0.022449664771556854
2023-01-22 19:59:14.792787: step: 748/470, loss: 0.05610019341111183
2023-01-22 19:59:15.462287: step: 750/470, loss: 0.05538138747215271
2023-01-22 19:59:16.186513: step: 752/470, loss: 0.03515056148171425
2023-01-22 19:59:16.900483: step: 754/470, loss: 0.06996199488639832
2023-01-22 19:59:17.647898: step: 756/470, loss: 0.010419724509119987
2023-01-22 19:59:18.419828: step: 758/470, loss: 0.02060377597808838
2023-01-22 19:59:19.197476: step: 760/470, loss: 0.021778682246804237
2023-01-22 19:59:19.930111: step: 762/470, loss: 0.14664672315120697
2023-01-22 19:59:20.630653: step: 764/470, loss: 0.04197612777352333
2023-01-22 19:59:21.258375: step: 766/470, loss: 0.00862900447100401
2023-01-22 19:59:22.023815: step: 768/470, loss: 0.01935235597193241
2023-01-22 19:59:22.717485: step: 770/470, loss: 0.0040095048025250435
2023-01-22 19:59:23.421947: step: 772/470, loss: 0.03624457120895386
2023-01-22 19:59:24.144026: step: 774/470, loss: 0.10813373327255249
2023-01-22 19:59:24.871586: step: 776/470, loss: 0.019472643733024597
2023-01-22 19:59:25.645234: step: 778/470, loss: 0.03459063544869423
2023-01-22 19:59:26.390464: step: 780/470, loss: 0.055417634546756744
2023-01-22 19:59:27.153033: step: 782/470, loss: 0.0014409045688807964
2023-01-22 19:59:27.846036: step: 784/470, loss: 0.029017573222517967
2023-01-22 19:59:28.612616: step: 786/470, loss: 0.04178899899125099
2023-01-22 19:59:29.349514: step: 788/470, loss: 0.18817931413650513
2023-01-22 19:59:30.050041: step: 790/470, loss: 1.237821102142334
2023-01-22 19:59:30.890276: step: 792/470, loss: 0.05888526514172554
2023-01-22 19:59:31.595571: step: 794/470, loss: 0.04464132338762283
2023-01-22 19:59:32.330488: step: 796/470, loss: 0.03926714509725571
2023-01-22 19:59:33.045390: step: 798/470, loss: 0.003827402601018548
2023-01-22 19:59:33.724793: step: 800/470, loss: 0.02599688246846199
2023-01-22 19:59:34.451395: step: 802/470, loss: 0.03956460580229759
2023-01-22 19:59:35.179761: step: 804/470, loss: 0.025580542162060738
2023-01-22 19:59:35.973495: step: 806/470, loss: 0.07505716383457184
2023-01-22 19:59:36.678671: step: 808/470, loss: 0.019929545000195503
2023-01-22 19:59:37.382989: step: 810/470, loss: 0.04150541499257088
2023-01-22 19:59:38.248326: step: 812/470, loss: 0.2298429161310196
2023-01-22 19:59:39.009000: step: 814/470, loss: 0.14862318336963654
2023-01-22 19:59:39.737248: step: 816/470, loss: 0.4220031499862671
2023-01-22 19:59:40.448213: step: 818/470, loss: 0.018468687310814857
2023-01-22 19:59:41.100148: step: 820/470, loss: 0.08981668949127197
2023-01-22 19:59:41.913467: step: 822/470, loss: 0.08471503853797913
2023-01-22 19:59:42.654875: step: 824/470, loss: 0.021649127826094627
2023-01-22 19:59:43.477629: step: 826/470, loss: 0.2502903342247009
2023-01-22 19:59:44.273044: step: 828/470, loss: 0.01829441450536251
2023-01-22 19:59:44.933804: step: 830/470, loss: 0.011802778579294682
2023-01-22 19:59:45.655682: step: 832/470, loss: 0.14194156229496002
2023-01-22 19:59:46.361886: step: 834/470, loss: 0.007301392499357462
2023-01-22 19:59:47.079288: step: 836/470, loss: 0.012469622306525707
2023-01-22 19:59:47.749385: step: 838/470, loss: 0.07566139101982117
2023-01-22 19:59:48.448816: step: 840/470, loss: 0.033544205129146576
2023-01-22 19:59:49.228554: step: 842/470, loss: 0.6390538215637207
2023-01-22 19:59:50.044164: step: 844/470, loss: 0.0382160022854805
2023-01-22 19:59:50.704385: step: 846/470, loss: 0.1456291675567627
2023-01-22 19:59:51.460631: step: 848/470, loss: 0.019455960020422935
2023-01-22 19:59:52.210850: step: 850/470, loss: 0.05021538957953453
2023-01-22 19:59:52.983666: step: 852/470, loss: 0.03165812790393829
2023-01-22 19:59:53.671877: step: 854/470, loss: 0.03875069320201874
2023-01-22 19:59:54.354935: step: 856/470, loss: 0.07675700634717941
2023-01-22 19:59:55.145083: step: 858/470, loss: 0.0549500472843647
2023-01-22 19:59:55.862628: step: 860/470, loss: 0.07575095444917679
2023-01-22 19:59:56.571108: step: 862/470, loss: 0.01323747355490923
2023-01-22 19:59:57.369008: step: 864/470, loss: 0.19846421480178833
2023-01-22 19:59:58.156884: step: 866/470, loss: 0.0069488100707530975
2023-01-22 19:59:58.844205: step: 868/470, loss: 0.09136679023504257
2023-01-22 19:59:59.589516: step: 870/470, loss: 0.027809590101242065
2023-01-22 20:00:00.316936: step: 872/470, loss: 0.003995862323790789
2023-01-22 20:00:00.988186: step: 874/470, loss: 0.010341154411435127
2023-01-22 20:00:01.761407: step: 876/470, loss: 0.014673410914838314
2023-01-22 20:00:02.491782: step: 878/470, loss: 0.035946592688560486
2023-01-22 20:00:03.240151: step: 880/470, loss: 0.034462690353393555
2023-01-22 20:00:03.943592: step: 882/470, loss: 0.0298713780939579
2023-01-22 20:00:04.699758: step: 884/470, loss: 0.01902618259191513
2023-01-22 20:00:05.429454: step: 886/470, loss: 0.007162892259657383
2023-01-22 20:00:06.178598: step: 888/470, loss: 0.024051036685705185
2023-01-22 20:00:06.938687: step: 890/470, loss: 0.014205212704837322
2023-01-22 20:00:07.761297: step: 892/470, loss: 0.0005725105293095112
2023-01-22 20:00:08.547118: step: 894/470, loss: 0.04063863679766655
2023-01-22 20:00:09.302603: step: 896/470, loss: 0.11876030266284943
2023-01-22 20:00:10.104592: step: 898/470, loss: 0.012916138395667076
2023-01-22 20:00:10.901258: step: 900/470, loss: 0.013642225414514542
2023-01-22 20:00:11.703699: step: 902/470, loss: 0.022717280313372612
2023-01-22 20:00:12.437887: step: 904/470, loss: 0.4222767651081085
2023-01-22 20:00:13.133068: step: 906/470, loss: 0.013618819415569305
2023-01-22 20:00:13.886215: step: 908/470, loss: 0.061890263110399246
2023-01-22 20:00:14.644579: step: 910/470, loss: 0.04235636442899704
2023-01-22 20:00:15.403890: step: 912/470, loss: 0.0523671992123127
2023-01-22 20:00:16.237381: step: 914/470, loss: 0.0566101111471653
2023-01-22 20:00:16.952370: step: 916/470, loss: 0.07533188164234161
2023-01-22 20:00:17.711256: step: 918/470, loss: 0.019266333431005478
2023-01-22 20:00:18.449499: step: 920/470, loss: 0.008472178131341934
2023-01-22 20:00:19.143528: step: 922/470, loss: 0.03950265422463417
2023-01-22 20:00:19.829329: step: 924/470, loss: 0.02345268428325653
2023-01-22 20:00:20.625896: step: 926/470, loss: 0.015790196135640144
2023-01-22 20:00:21.321952: step: 928/470, loss: 0.027424369007349014
2023-01-22 20:00:22.126605: step: 930/470, loss: 0.1694997251033783
2023-01-22 20:00:22.854895: step: 932/470, loss: 0.04345071688294411
2023-01-22 20:00:23.623580: step: 934/470, loss: 0.029627729207277298
2023-01-22 20:00:24.328161: step: 936/470, loss: 1.4033803939819336
2023-01-22 20:00:25.043331: step: 938/470, loss: 0.07272469252347946
2023-01-22 20:00:25.781309: step: 940/470, loss: 0.07386843860149384
2023-01-22 20:00:26.432530: step: 942/470, loss: 0.00953019130975008
==================================================
Loss: 0.078
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2951851081530782, 'r': 0.3366342504743833, 'f1': 0.3145500886524823}, 'combined': 0.23177374953340799, 'epoch': 24}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33448411009531387, 'r': 0.36857575977810547, 'f1': 0.35070337618410763}, 'combined': 0.24427100828743817, 'epoch': 24}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29017783486930493, 'r': 0.3353288452284757, 'f1': 0.3111237701327583}, 'combined': 0.22924909378203243, 'epoch': 24}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3305422989570629, 'r': 0.36232521231831893, 'f1': 0.3457047897349098}, 'combined': 0.24078940578550934, 'epoch': 24}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2818378552971576, 'r': 0.3449438646426312, 'f1': 0.3102140216154721}, 'combined': 0.22857875276929523, 'epoch': 24}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3271542618069103, 'r': 0.3778002581058647, 'f1': 0.3506579816422127}, 'combined': 0.24423939019855612, 'epoch': 24}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20227272727272727, 'r': 0.31785714285714284, 'f1': 0.24722222222222223}, 'combined': 0.1648148148148148, 'epoch': 24}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.23333333333333334, 'r': 0.45652173913043476, 'f1': 0.3088235294117647}, 'combined': 0.15441176470588236, 'epoch': 24}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 24}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 25
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 20:03:02.208414: step: 2/470, loss: 0.02162099815905094
2023-01-22 20:03:02.960449: step: 4/470, loss: 0.012446287088096142
2023-01-22 20:03:03.682543: step: 6/470, loss: 0.034468457102775574
2023-01-22 20:03:04.446766: step: 8/470, loss: 0.016727212816476822
2023-01-22 20:03:05.214627: step: 10/470, loss: 0.03275219723582268
2023-01-22 20:03:05.910108: step: 12/470, loss: 0.012032398022711277
2023-01-22 20:03:06.729149: step: 14/470, loss: 0.04827987775206566
2023-01-22 20:03:07.463381: step: 16/470, loss: 0.039694756269454956
2023-01-22 20:03:08.197966: step: 18/470, loss: 0.018378468230366707
2023-01-22 20:03:08.786230: step: 20/470, loss: 0.010981571860611439
2023-01-22 20:03:09.634501: step: 22/470, loss: 1.3256505727767944
2023-01-22 20:03:10.352731: step: 24/470, loss: 0.007463351357728243
2023-01-22 20:03:11.127357: step: 26/470, loss: 0.008972594514489174
2023-01-22 20:03:11.819350: step: 28/470, loss: 0.005426797084510326
2023-01-22 20:03:12.582333: step: 30/470, loss: 0.005324822850525379
2023-01-22 20:03:13.277984: step: 32/470, loss: 0.07613864541053772
2023-01-22 20:03:13.987213: step: 34/470, loss: 0.03191568702459335
2023-01-22 20:03:14.709648: step: 36/470, loss: 0.05562712624669075
2023-01-22 20:03:15.453824: step: 38/470, loss: 0.01600096933543682
2023-01-22 20:03:16.188829: step: 40/470, loss: 0.044862739741802216
2023-01-22 20:03:16.947253: step: 42/470, loss: 0.3098965287208557
2023-01-22 20:03:17.682120: step: 44/470, loss: 0.027755551040172577
2023-01-22 20:03:18.407908: step: 46/470, loss: 0.09233322739601135
2023-01-22 20:03:19.113272: step: 48/470, loss: 0.39350318908691406
2023-01-22 20:03:19.804796: step: 50/470, loss: 0.04757951945066452
2023-01-22 20:03:20.543417: step: 52/470, loss: 0.004094702657312155
2023-01-22 20:03:21.291164: step: 54/470, loss: 0.037220463156700134
2023-01-22 20:03:22.005010: step: 56/470, loss: 0.0336788184940815
2023-01-22 20:03:22.814500: step: 58/470, loss: 0.010243861936032772
2023-01-22 20:03:23.516706: step: 60/470, loss: 0.08532825112342834
2023-01-22 20:03:24.199642: step: 62/470, loss: 0.031235769391059875
2023-01-22 20:03:24.811600: step: 64/470, loss: 0.012863215059041977
2023-01-22 20:03:25.606214: step: 66/470, loss: 1.0012062788009644
2023-01-22 20:03:26.336741: step: 68/470, loss: 0.02800358459353447
2023-01-22 20:03:27.107016: step: 70/470, loss: 0.021341489627957344
2023-01-22 20:03:27.816905: step: 72/470, loss: 0.013578714802861214
2023-01-22 20:03:28.606450: step: 74/470, loss: 0.01855326071381569
2023-01-22 20:03:29.357341: step: 76/470, loss: 0.04243265837430954
2023-01-22 20:03:30.041180: step: 78/470, loss: 0.03518841415643692
2023-01-22 20:03:30.723632: step: 80/470, loss: 0.08064284920692444
2023-01-22 20:03:31.437155: step: 82/470, loss: 0.017204048112034798
2023-01-22 20:03:32.205440: step: 84/470, loss: 0.014039833098649979
2023-01-22 20:03:32.916980: step: 86/470, loss: 0.023023655638098717
2023-01-22 20:03:33.615644: step: 88/470, loss: 0.021660305559635162
2023-01-22 20:03:34.346502: step: 90/470, loss: 0.10536940395832062
2023-01-22 20:03:35.078132: step: 92/470, loss: 0.024169238284230232
2023-01-22 20:03:35.736614: step: 94/470, loss: 0.029674746096134186
2023-01-22 20:03:36.510310: step: 96/470, loss: 0.028852693736553192
2023-01-22 20:03:37.218231: step: 98/470, loss: 0.00507341930642724
2023-01-22 20:03:37.994384: step: 100/470, loss: 0.017849357798695564
2023-01-22 20:03:38.779957: step: 102/470, loss: 0.0505632720887661
2023-01-22 20:03:39.608571: step: 104/470, loss: 0.009880991652607918
2023-01-22 20:03:40.392854: step: 106/470, loss: 0.02503761276602745
2023-01-22 20:03:41.075328: step: 108/470, loss: 0.0026527876034379005
2023-01-22 20:03:41.811982: step: 110/470, loss: 0.017480017617344856
2023-01-22 20:03:42.477181: step: 112/470, loss: 0.011955924332141876
2023-01-22 20:03:43.144897: step: 114/470, loss: 0.035263460129499435
2023-01-22 20:03:43.930379: step: 116/470, loss: 0.0948866754770279
2023-01-22 20:03:44.684859: step: 118/470, loss: 0.01817036233842373
2023-01-22 20:03:45.334197: step: 120/470, loss: 0.005630629137158394
2023-01-22 20:03:45.961903: step: 122/470, loss: 0.05774114280939102
2023-01-22 20:03:46.686546: step: 124/470, loss: 0.0010737971169874072
2023-01-22 20:03:47.601412: step: 126/470, loss: 0.01047587115317583
2023-01-22 20:03:48.290127: step: 128/470, loss: 0.0022798320278525352
2023-01-22 20:03:49.009082: step: 130/470, loss: 0.03199382126331329
2023-01-22 20:03:49.728867: step: 132/470, loss: 0.10577887296676636
2023-01-22 20:03:50.422620: step: 134/470, loss: 0.020609887316823006
2023-01-22 20:03:51.133612: step: 136/470, loss: 0.0020259118173271418
2023-01-22 20:03:51.908935: step: 138/470, loss: 0.020044716075062752
2023-01-22 20:03:52.630186: step: 140/470, loss: 0.004093657713383436
2023-01-22 20:03:53.371622: step: 142/470, loss: 0.062444720417261124
2023-01-22 20:03:54.060750: step: 144/470, loss: 0.03266696259379387
2023-01-22 20:03:54.847317: step: 146/470, loss: 0.05523476377129555
2023-01-22 20:03:55.590847: step: 148/470, loss: 0.0045193941332399845
2023-01-22 20:03:56.286072: step: 150/470, loss: 0.009763001464307308
2023-01-22 20:03:56.988296: step: 152/470, loss: 0.042540084570646286
2023-01-22 20:03:57.755469: step: 154/470, loss: 0.016827277839183807
2023-01-22 20:03:58.528118: step: 156/470, loss: 0.17072248458862305
2023-01-22 20:03:59.303968: step: 158/470, loss: 0.005717588122934103
2023-01-22 20:04:00.050285: step: 160/470, loss: 0.009820440784096718
2023-01-22 20:04:00.792957: step: 162/470, loss: 0.010699333623051643
2023-01-22 20:04:01.583265: step: 164/470, loss: 0.08145033568143845
2023-01-22 20:04:02.315582: step: 166/470, loss: 0.0005983722512610257
2023-01-22 20:04:03.125046: step: 168/470, loss: 0.028514329344034195
2023-01-22 20:04:03.849529: step: 170/470, loss: 0.006405293010175228
2023-01-22 20:04:04.558463: step: 172/470, loss: 0.00240780645981431
2023-01-22 20:04:05.288475: step: 174/470, loss: 0.026528997346758842
2023-01-22 20:04:06.104816: step: 176/470, loss: 0.02798590436577797
2023-01-22 20:04:06.839345: step: 178/470, loss: 0.014988838694989681
2023-01-22 20:04:07.568783: step: 180/470, loss: 0.13888667523860931
2023-01-22 20:04:08.286842: step: 182/470, loss: 0.020751958712935448
2023-01-22 20:04:08.922280: step: 184/470, loss: 0.0074022323824465275
2023-01-22 20:04:09.622459: step: 186/470, loss: 0.16846947371959686
2023-01-22 20:04:10.340121: step: 188/470, loss: 0.02288518100976944
2023-01-22 20:04:11.110314: step: 190/470, loss: 0.025580741465091705
2023-01-22 20:04:11.870415: step: 192/470, loss: 0.01590382121503353
2023-01-22 20:04:12.657068: step: 194/470, loss: 0.018982110545039177
2023-01-22 20:04:13.489373: step: 196/470, loss: 0.028010079637169838
2023-01-22 20:04:14.167193: step: 198/470, loss: 0.009743987582623959
2023-01-22 20:04:14.896654: step: 200/470, loss: 0.0009152348502539098
2023-01-22 20:04:15.732317: step: 202/470, loss: 0.0641738623380661
2023-01-22 20:04:16.543270: step: 204/470, loss: 0.006123876199126244
2023-01-22 20:04:17.291111: step: 206/470, loss: 0.03843360021710396
2023-01-22 20:04:18.087166: step: 208/470, loss: 0.0037462252657860518
2023-01-22 20:04:18.814117: step: 210/470, loss: 0.002261190675199032
2023-01-22 20:04:19.651658: step: 212/470, loss: 0.16585534811019897
2023-01-22 20:04:20.372141: step: 214/470, loss: 0.2700032889842987
2023-01-22 20:04:21.038341: step: 216/470, loss: 0.024171005934476852
2023-01-22 20:04:21.751961: step: 218/470, loss: 0.004075937904417515
2023-01-22 20:04:22.461687: step: 220/470, loss: 0.004899140447378159
2023-01-22 20:04:23.152966: step: 222/470, loss: 0.04851776361465454
2023-01-22 20:04:23.918240: step: 224/470, loss: 0.01797030307352543
2023-01-22 20:04:24.666156: step: 226/470, loss: 0.0035274296533316374
2023-01-22 20:04:25.422124: step: 228/470, loss: 0.024435440078377724
2023-01-22 20:04:26.198641: step: 230/470, loss: 0.14094187319278717
2023-01-22 20:04:27.024325: step: 232/470, loss: 0.009624892845749855
2023-01-22 20:04:27.788402: step: 234/470, loss: 0.03491733595728874
2023-01-22 20:04:28.540714: step: 236/470, loss: 0.028152016922831535
2023-01-22 20:04:29.268604: step: 238/470, loss: 0.02921573631465435
2023-01-22 20:04:30.074569: step: 240/470, loss: 0.018016021698713303
2023-01-22 20:04:30.830186: step: 242/470, loss: 0.21584904193878174
2023-01-22 20:04:31.498166: step: 244/470, loss: 0.0007679513073526323
2023-01-22 20:04:32.181116: step: 246/470, loss: 0.007389437407255173
2023-01-22 20:04:32.851499: step: 248/470, loss: 0.019924050197005272
2023-01-22 20:04:33.633529: step: 250/470, loss: 0.0013338790740817785
2023-01-22 20:04:34.366868: step: 252/470, loss: 0.09131523221731186
2023-01-22 20:04:35.092103: step: 254/470, loss: 0.04288085922598839
2023-01-22 20:04:35.878842: step: 256/470, loss: 0.008014186285436153
2023-01-22 20:04:36.596732: step: 258/470, loss: 0.002048267750069499
2023-01-22 20:04:37.347394: step: 260/470, loss: 0.007588651031255722
2023-01-22 20:04:38.047615: step: 262/470, loss: 0.010957635007798672
2023-01-22 20:04:38.796140: step: 264/470, loss: 0.011484313756227493
2023-01-22 20:04:39.516430: step: 266/470, loss: 0.04040658846497536
2023-01-22 20:04:40.252904: step: 268/470, loss: 0.015184608288109303
2023-01-22 20:04:40.989432: step: 270/470, loss: 0.010376902297139168
2023-01-22 20:04:41.637422: step: 272/470, loss: 0.04080960154533386
2023-01-22 20:04:42.332798: step: 274/470, loss: 1.0133119821548462
2023-01-22 20:04:43.070894: step: 276/470, loss: 0.005866447929292917
2023-01-22 20:04:43.827345: step: 278/470, loss: 0.11790863424539566
2023-01-22 20:04:44.546094: step: 280/470, loss: 0.00046028837095946074
2023-01-22 20:04:45.273684: step: 282/470, loss: 0.03480033576488495
2023-01-22 20:04:46.003497: step: 284/470, loss: 0.012186521664261818
2023-01-22 20:04:46.739427: step: 286/470, loss: 0.03706849738955498
2023-01-22 20:04:47.503067: step: 288/470, loss: 0.02106441929936409
2023-01-22 20:04:48.261632: step: 290/470, loss: 0.004235308617353439
2023-01-22 20:04:49.024119: step: 292/470, loss: 0.0014547484461218119
2023-01-22 20:04:49.791868: step: 294/470, loss: 0.029318470507860184
2023-01-22 20:04:50.500913: step: 296/470, loss: 0.05262761935591698
2023-01-22 20:04:51.207876: step: 298/470, loss: 0.004162387456744909
2023-01-22 20:04:51.944145: step: 300/470, loss: 0.08064429461956024
2023-01-22 20:04:52.582975: step: 302/470, loss: 0.011829620227217674
2023-01-22 20:04:53.336351: step: 304/470, loss: 0.020030930638313293
2023-01-22 20:04:54.010308: step: 306/470, loss: 0.006781530566513538
2023-01-22 20:04:54.699125: step: 308/470, loss: 0.10114534944295883
2023-01-22 20:04:55.415622: step: 310/470, loss: 0.03585520759224892
2023-01-22 20:04:56.179184: step: 312/470, loss: 0.02825266122817993
2023-01-22 20:04:56.872336: step: 314/470, loss: 0.043976690620183945
2023-01-22 20:04:57.653149: step: 316/470, loss: 0.045031096786260605
2023-01-22 20:04:58.415967: step: 318/470, loss: 0.04603327438235283
2023-01-22 20:04:59.198368: step: 320/470, loss: 0.04247571900486946
2023-01-22 20:04:59.859167: step: 322/470, loss: 0.0015748925507068634
2023-01-22 20:05:00.653775: step: 324/470, loss: 0.06393693387508392
2023-01-22 20:05:01.399144: step: 326/470, loss: 0.035000111907720566
2023-01-22 20:05:02.125877: step: 328/470, loss: 0.014710234478116035
2023-01-22 20:05:02.791851: step: 330/470, loss: 0.028020773082971573
2023-01-22 20:05:03.554905: step: 332/470, loss: 0.06262163072824478
2023-01-22 20:05:04.202511: step: 334/470, loss: 0.0007441341294907033
2023-01-22 20:05:04.865998: step: 336/470, loss: 0.08218454569578171
2023-01-22 20:05:05.726926: step: 338/470, loss: 0.4393693506717682
2023-01-22 20:05:06.478271: step: 340/470, loss: 0.014411939308047295
2023-01-22 20:05:07.188852: step: 342/470, loss: 0.060469575226306915
2023-01-22 20:05:07.944112: step: 344/470, loss: 0.036549992859363556
2023-01-22 20:05:08.743126: step: 346/470, loss: 0.031213141977787018
2023-01-22 20:05:09.477734: step: 348/470, loss: 0.0008316990570165217
2023-01-22 20:05:10.244727: step: 350/470, loss: 1.0978364944458008
2023-01-22 20:05:10.923325: step: 352/470, loss: 0.014219812117516994
2023-01-22 20:05:11.640805: step: 354/470, loss: 0.06110917776823044
2023-01-22 20:05:12.543865: step: 356/470, loss: 0.06231218948960304
2023-01-22 20:05:13.209120: step: 358/470, loss: 0.024384677410125732
2023-01-22 20:05:14.061173: step: 360/470, loss: 0.06801487505435944
2023-01-22 20:05:14.780066: step: 362/470, loss: 0.043319717049598694
2023-01-22 20:05:15.518784: step: 364/470, loss: 0.006488930433988571
2023-01-22 20:05:16.208030: step: 366/470, loss: 1.2596720457077026
2023-01-22 20:05:16.889468: step: 368/470, loss: 0.009231701493263245
2023-01-22 20:05:17.620880: step: 370/470, loss: 0.07412904500961304
2023-01-22 20:05:18.433078: step: 372/470, loss: 0.054003313183784485
2023-01-22 20:05:19.226956: step: 374/470, loss: 0.04891440272331238
2023-01-22 20:05:20.037881: step: 376/470, loss: 0.03218501806259155
2023-01-22 20:05:20.726489: step: 378/470, loss: 0.010670957155525684
2023-01-22 20:05:21.494683: step: 380/470, loss: 0.3814714848995209
2023-01-22 20:05:22.252737: step: 382/470, loss: 0.029765913262963295
2023-01-22 20:05:22.981506: step: 384/470, loss: 0.03948010876774788
2023-01-22 20:05:23.648254: step: 386/470, loss: 0.008174107410013676
2023-01-22 20:05:24.397001: step: 388/470, loss: 0.0791185200214386
2023-01-22 20:05:25.131254: step: 390/470, loss: 0.0023983244318515062
2023-01-22 20:05:25.880447: step: 392/470, loss: 0.0599571131169796
2023-01-22 20:05:26.551113: step: 394/470, loss: 0.05517046898603439
2023-01-22 20:05:27.299104: step: 396/470, loss: 0.044240474700927734
2023-01-22 20:05:28.021780: step: 398/470, loss: 0.017728475853800774
2023-01-22 20:05:28.783202: step: 400/470, loss: 0.06311778724193573
2023-01-22 20:05:29.516610: step: 402/470, loss: 0.00163270381744951
2023-01-22 20:05:30.319427: step: 404/470, loss: 0.014112650416791439
2023-01-22 20:05:31.004706: step: 406/470, loss: 0.0612499974668026
2023-01-22 20:05:31.782258: step: 408/470, loss: 0.01821378618478775
2023-01-22 20:05:32.485323: step: 410/470, loss: 0.20836558938026428
2023-01-22 20:05:33.280619: step: 412/470, loss: 0.03567926958203316
2023-01-22 20:05:34.006616: step: 414/470, loss: 0.07208713889122009
2023-01-22 20:05:34.761899: step: 416/470, loss: 0.13654865324497223
2023-01-22 20:05:35.482211: step: 418/470, loss: 0.03147239238023758
2023-01-22 20:05:36.184822: step: 420/470, loss: 0.017493341118097305
2023-01-22 20:05:36.934112: step: 422/470, loss: 0.09981317818164825
2023-01-22 20:05:37.646881: step: 424/470, loss: 0.032189272344112396
2023-01-22 20:05:38.390154: step: 426/470, loss: 0.014166963286697865
2023-01-22 20:05:39.278299: step: 428/470, loss: 0.09840293973684311
2023-01-22 20:05:40.047111: step: 430/470, loss: 0.08024189621210098
2023-01-22 20:05:40.785284: step: 432/470, loss: 0.04482298344373703
2023-01-22 20:05:41.544758: step: 434/470, loss: 0.038904860615730286
2023-01-22 20:05:42.335348: step: 436/470, loss: 0.2726028561592102
2023-01-22 20:05:43.044339: step: 438/470, loss: 0.02278323471546173
2023-01-22 20:05:43.807322: step: 440/470, loss: 0.01581525057554245
2023-01-22 20:05:44.538973: step: 442/470, loss: 0.04916553571820259
2023-01-22 20:05:45.336670: step: 444/470, loss: 0.018240492790937424
2023-01-22 20:05:46.041842: step: 446/470, loss: 0.05501729995012283
2023-01-22 20:05:46.826633: step: 448/470, loss: 0.014724891632795334
2023-01-22 20:05:47.689444: step: 450/470, loss: 0.09602244943380356
2023-01-22 20:05:48.376661: step: 452/470, loss: 0.004648915026336908
2023-01-22 20:05:49.152360: step: 454/470, loss: 0.01640310324728489
2023-01-22 20:05:49.896208: step: 456/470, loss: 0.03248788043856621
2023-01-22 20:05:50.624489: step: 458/470, loss: 1.1334494352340698
2023-01-22 20:05:51.384806: step: 460/470, loss: 0.14382703602313995
2023-01-22 20:05:52.124610: step: 462/470, loss: 0.06437462568283081
2023-01-22 20:05:52.962967: step: 464/470, loss: 0.020893843844532967
2023-01-22 20:05:53.615584: step: 466/470, loss: 0.020247068256139755
2023-01-22 20:05:54.379413: step: 468/470, loss: 0.06369510293006897
2023-01-22 20:05:55.130861: step: 470/470, loss: 0.002879982814192772
2023-01-22 20:05:55.822467: step: 472/470, loss: 0.01400853507220745
2023-01-22 20:05:56.569159: step: 474/470, loss: 0.03950931504368782
2023-01-22 20:05:57.288189: step: 476/470, loss: 0.02229795604944229
2023-01-22 20:05:58.112162: step: 478/470, loss: 0.017860140651464462
2023-01-22 20:05:58.867750: step: 480/470, loss: 0.00995658803731203
2023-01-22 20:05:59.589926: step: 482/470, loss: 0.0026193808298557997
2023-01-22 20:06:00.336822: step: 484/470, loss: 0.022055814042687416
2023-01-22 20:06:01.065376: step: 486/470, loss: 0.2256946861743927
2023-01-22 20:06:01.851662: step: 488/470, loss: 0.01226732973009348
2023-01-22 20:06:02.562505: step: 490/470, loss: 0.017396673560142517
2023-01-22 20:06:03.327255: step: 492/470, loss: 0.0489540733397007
2023-01-22 20:06:04.082725: step: 494/470, loss: 0.03391120210289955
2023-01-22 20:06:04.789239: step: 496/470, loss: 0.01827331632375717
2023-01-22 20:06:05.622999: step: 498/470, loss: 0.012197432108223438
2023-01-22 20:06:06.363409: step: 500/470, loss: 0.02815680392086506
2023-01-22 20:06:07.081598: step: 502/470, loss: 0.07767844945192337
2023-01-22 20:06:07.904240: step: 504/470, loss: 0.01819152943789959
2023-01-22 20:06:08.691957: step: 506/470, loss: 0.008796506561338902
2023-01-22 20:06:09.400582: step: 508/470, loss: 0.26540952920913696
2023-01-22 20:06:10.161307: step: 510/470, loss: 0.03128129988908768
2023-01-22 20:06:10.882884: step: 512/470, loss: 0.021161213517189026
2023-01-22 20:06:11.663917: step: 514/470, loss: 0.031146377325057983
2023-01-22 20:06:12.377298: step: 516/470, loss: 0.0022348014172166586
2023-01-22 20:06:13.206675: step: 518/470, loss: 0.0887453556060791
2023-01-22 20:06:13.874606: step: 520/470, loss: 0.023102333769202232
2023-01-22 20:06:14.705703: step: 522/470, loss: 0.035375066101551056
2023-01-22 20:06:15.417801: step: 524/470, loss: 0.006511027924716473
2023-01-22 20:06:16.157779: step: 526/470, loss: 0.0845172256231308
2023-01-22 20:06:16.884956: step: 528/470, loss: 0.03893345594406128
2023-01-22 20:06:17.646530: step: 530/470, loss: 0.22155825793743134
2023-01-22 20:06:18.376188: step: 532/470, loss: 0.06408680230379105
2023-01-22 20:06:19.126890: step: 534/470, loss: 0.08290005475282669
2023-01-22 20:06:19.839234: step: 536/470, loss: 0.018902825191617012
2023-01-22 20:06:20.564035: step: 538/470, loss: 0.05063078925013542
2023-01-22 20:06:21.286179: step: 540/470, loss: 0.06731826812028885
2023-01-22 20:06:21.986242: step: 542/470, loss: 0.04933793842792511
2023-01-22 20:06:22.687477: step: 544/470, loss: 0.12002909183502197
2023-01-22 20:06:23.392428: step: 546/470, loss: 0.042481400072574615
2023-01-22 20:06:24.073123: step: 548/470, loss: 0.11045798659324646
2023-01-22 20:06:24.741546: step: 550/470, loss: 0.003042022930458188
2023-01-22 20:06:25.524304: step: 552/470, loss: 0.03922036290168762
2023-01-22 20:06:26.245046: step: 554/470, loss: 0.03836175426840782
2023-01-22 20:06:27.002509: step: 556/470, loss: 0.03422430902719498
2023-01-22 20:06:27.740561: step: 558/470, loss: 0.01736604794859886
2023-01-22 20:06:28.484904: step: 560/470, loss: 0.029811743646860123
2023-01-22 20:06:29.195258: step: 562/470, loss: 0.010475804097950459
2023-01-22 20:06:29.915185: step: 564/470, loss: 0.0307230856269598
2023-01-22 20:06:30.647787: step: 566/470, loss: 0.020388364791870117
2023-01-22 20:06:31.423076: step: 568/470, loss: 0.18014267086982727
2023-01-22 20:06:32.083078: step: 570/470, loss: 0.03197851777076721
2023-01-22 20:06:32.843810: step: 572/470, loss: 0.6306474804878235
2023-01-22 20:06:33.472804: step: 574/470, loss: 0.21226122975349426
2023-01-22 20:06:34.175297: step: 576/470, loss: 0.012852661311626434
2023-01-22 20:06:34.902748: step: 578/470, loss: 0.07441854476928711
2023-01-22 20:06:35.577980: step: 580/470, loss: 0.016917813569307327
2023-01-22 20:06:36.280041: step: 582/470, loss: 0.08907926082611084
2023-01-22 20:06:36.965132: step: 584/470, loss: 0.003389795310795307
2023-01-22 20:06:37.730587: step: 586/470, loss: 0.040450599044561386
2023-01-22 20:06:38.527951: step: 588/470, loss: 0.054036617279052734
2023-01-22 20:06:39.240819: step: 590/470, loss: 0.05018281936645508
2023-01-22 20:06:39.948272: step: 592/470, loss: 0.01974686235189438
2023-01-22 20:06:40.642839: step: 594/470, loss: 0.10064013302326202
2023-01-22 20:06:41.373373: step: 596/470, loss: 0.008306887932121754
2023-01-22 20:06:42.195393: step: 598/470, loss: 0.04838766157627106
2023-01-22 20:06:42.990417: step: 600/470, loss: 0.001629787846468389
2023-01-22 20:06:43.772312: step: 602/470, loss: 0.028213849291205406
2023-01-22 20:06:44.473561: step: 604/470, loss: 0.024601630866527557
2023-01-22 20:06:45.196328: step: 606/470, loss: 0.028212811797857285
2023-01-22 20:06:45.970836: step: 608/470, loss: 0.030642293393611908
2023-01-22 20:06:46.718194: step: 610/470, loss: 0.011128339916467667
2023-01-22 20:06:47.408331: step: 612/470, loss: 0.000944534142035991
2023-01-22 20:06:48.126252: step: 614/470, loss: 0.029674546793103218
2023-01-22 20:06:48.807643: step: 616/470, loss: 0.007636074908077717
2023-01-22 20:06:49.621490: step: 618/470, loss: 0.014691839925944805
2023-01-22 20:06:50.491124: step: 620/470, loss: 0.05527832731604576
2023-01-22 20:06:51.230716: step: 622/470, loss: 0.015919934958219528
2023-01-22 20:06:51.945620: step: 624/470, loss: 0.02508891187608242
2023-01-22 20:06:52.757562: step: 626/470, loss: 0.01099168136715889
2023-01-22 20:06:53.446669: step: 628/470, loss: 0.035270821303129196
2023-01-22 20:06:54.075911: step: 630/470, loss: 0.03347640857100487
2023-01-22 20:06:54.726744: step: 632/470, loss: 0.05645357072353363
2023-01-22 20:06:55.408565: step: 634/470, loss: 0.011641307733952999
2023-01-22 20:06:56.230577: step: 636/470, loss: 0.06422200053930283
2023-01-22 20:06:56.929644: step: 638/470, loss: 0.01144405733793974
2023-01-22 20:06:57.714995: step: 640/470, loss: 0.029585037380456924
2023-01-22 20:06:58.413192: step: 642/470, loss: 0.04478341341018677
2023-01-22 20:06:59.144996: step: 644/470, loss: 0.14443320035934448
2023-01-22 20:06:59.848423: step: 646/470, loss: 0.000602882297243923
2023-01-22 20:07:00.579937: step: 648/470, loss: 0.01970474235713482
2023-01-22 20:07:01.326727: step: 650/470, loss: 0.05201108008623123
2023-01-22 20:07:02.050882: step: 652/470, loss: 0.022257506847381592
2023-01-22 20:07:02.739334: step: 654/470, loss: 0.08728256821632385
2023-01-22 20:07:03.454597: step: 656/470, loss: 0.015211334452033043
2023-01-22 20:07:04.197468: step: 658/470, loss: 0.2973870038986206
2023-01-22 20:07:04.926983: step: 660/470, loss: 0.035559751093387604
2023-01-22 20:07:05.602116: step: 662/470, loss: 0.026579704135656357
2023-01-22 20:07:06.355035: step: 664/470, loss: 0.02378200925886631
2023-01-22 20:07:07.123608: step: 666/470, loss: 0.08443901687860489
2023-01-22 20:07:07.834509: step: 668/470, loss: 0.006817949004471302
2023-01-22 20:07:08.560784: step: 670/470, loss: 0.08191236853599548
2023-01-22 20:07:09.364914: step: 672/470, loss: 0.00972555298358202
2023-01-22 20:07:10.051152: step: 674/470, loss: 0.002309043426066637
2023-01-22 20:07:10.763226: step: 676/470, loss: 0.03206325322389603
2023-01-22 20:07:11.496514: step: 678/470, loss: 0.023099826648831367
2023-01-22 20:07:12.184123: step: 680/470, loss: 0.03047085553407669
2023-01-22 20:07:12.939646: step: 682/470, loss: 0.26479578018188477
2023-01-22 20:07:13.665782: step: 684/470, loss: 0.04502062872052193
2023-01-22 20:07:14.404564: step: 686/470, loss: 0.017808128148317337
2023-01-22 20:07:15.082562: step: 688/470, loss: 0.14120163023471832
2023-01-22 20:07:15.888608: step: 690/470, loss: 0.006991311442106962
2023-01-22 20:07:16.600724: step: 692/470, loss: 0.04135780781507492
2023-01-22 20:07:17.307262: step: 694/470, loss: 0.024161092936992645
2023-01-22 20:07:18.019424: step: 696/470, loss: 0.02334967628121376
2023-01-22 20:07:18.733895: step: 698/470, loss: 0.04725329205393791
2023-01-22 20:07:19.495542: step: 700/470, loss: 0.13663579523563385
2023-01-22 20:07:20.179882: step: 702/470, loss: 0.029831871390342712
2023-01-22 20:07:20.899703: step: 704/470, loss: 0.06156457960605621
2023-01-22 20:07:21.641195: step: 706/470, loss: 0.08219487965106964
2023-01-22 20:07:22.448205: step: 708/470, loss: 0.23499932885169983
2023-01-22 20:07:23.316647: step: 710/470, loss: 0.05763453617691994
2023-01-22 20:07:24.079970: step: 712/470, loss: 0.6921198964118958
2023-01-22 20:07:24.882300: step: 714/470, loss: 0.025135423988103867
2023-01-22 20:07:25.670489: step: 716/470, loss: 0.06057261303067207
2023-01-22 20:07:26.378205: step: 718/470, loss: 0.0005019385716877878
2023-01-22 20:07:27.147194: step: 720/470, loss: 0.03366491198539734
2023-01-22 20:07:27.916347: step: 722/470, loss: 0.0844867005944252
2023-01-22 20:07:28.638354: step: 724/470, loss: 0.001989529235288501
2023-01-22 20:07:29.635989: step: 726/470, loss: 0.05526869744062424
2023-01-22 20:07:30.362134: step: 728/470, loss: 0.003986681811511517
2023-01-22 20:07:31.061652: step: 730/470, loss: 0.06542991101741791
2023-01-22 20:07:31.743068: step: 732/470, loss: 0.024848083034157753
2023-01-22 20:07:32.499075: step: 734/470, loss: 0.017168505117297173
2023-01-22 20:07:33.191421: step: 736/470, loss: 0.00605942215770483
2023-01-22 20:07:33.837874: step: 738/470, loss: 0.013854175806045532
2023-01-22 20:07:34.593511: step: 740/470, loss: 0.02051333710551262
2023-01-22 20:07:35.366645: step: 742/470, loss: 0.01970795914530754
2023-01-22 20:07:36.137488: step: 744/470, loss: 0.052142977714538574
2023-01-22 20:07:36.929266: step: 746/470, loss: 0.03665049001574516
2023-01-22 20:07:37.616879: step: 748/470, loss: 0.014172352850437164
2023-01-22 20:07:38.335738: step: 750/470, loss: 0.0662955716252327
2023-01-22 20:07:39.049223: step: 752/470, loss: 0.04770228639245033
2023-01-22 20:07:39.829147: step: 754/470, loss: 0.024025220423936844
2023-01-22 20:07:40.520290: step: 756/470, loss: 0.02347307652235031
2023-01-22 20:07:41.387784: step: 758/470, loss: 0.03415545076131821
2023-01-22 20:07:42.208756: step: 760/470, loss: 0.08358060568571091
2023-01-22 20:07:42.895872: step: 762/470, loss: 0.07076893001794815
2023-01-22 20:07:43.681029: step: 764/470, loss: 0.9924178719520569
2023-01-22 20:07:44.465123: step: 766/470, loss: 0.02128605917096138
2023-01-22 20:07:45.154329: step: 768/470, loss: 0.060910508036613464
2023-01-22 20:07:45.839663: step: 770/470, loss: 0.010893095284700394
2023-01-22 20:07:46.553425: step: 772/470, loss: 0.004468762315809727
2023-01-22 20:07:47.240100: step: 774/470, loss: 0.0033063499722629786
2023-01-22 20:07:48.005341: step: 776/470, loss: 0.16144682466983795
2023-01-22 20:07:48.727026: step: 778/470, loss: 0.01916014961898327
2023-01-22 20:07:49.420324: step: 780/470, loss: 0.007597747258841991
2023-01-22 20:07:50.101094: step: 782/470, loss: 0.013567719608545303
2023-01-22 20:07:50.774657: step: 784/470, loss: 0.0008880794048309326
2023-01-22 20:07:51.510464: step: 786/470, loss: 0.015842584893107414
2023-01-22 20:07:52.215616: step: 788/470, loss: 0.0290867630392313
2023-01-22 20:07:52.951042: step: 790/470, loss: 0.5169112682342529
2023-01-22 20:07:53.707023: step: 792/470, loss: 0.012393763288855553
2023-01-22 20:07:54.377940: step: 794/470, loss: 0.010337642394006252
2023-01-22 20:07:55.096951: step: 796/470, loss: 0.20648834109306335
2023-01-22 20:07:55.839438: step: 798/470, loss: 0.07127867639064789
2023-01-22 20:07:56.535634: step: 800/470, loss: 0.022180991247296333
2023-01-22 20:07:57.322235: step: 802/470, loss: 0.17413491010665894
2023-01-22 20:07:58.057933: step: 804/470, loss: 0.056421320885419846
2023-01-22 20:07:58.735426: step: 806/470, loss: 0.01221885159611702
2023-01-22 20:07:59.410025: step: 808/470, loss: 0.03740542382001877
2023-01-22 20:08:00.159555: step: 810/470, loss: 0.10675573348999023
2023-01-22 20:08:00.893580: step: 812/470, loss: 0.0472906269133091
2023-01-22 20:08:01.627389: step: 814/470, loss: 0.005474620033055544
2023-01-22 20:08:02.377557: step: 816/470, loss: 0.0021934225223958492
2023-01-22 20:08:03.130727: step: 818/470, loss: 0.028478167951107025
2023-01-22 20:08:03.872915: step: 820/470, loss: 0.07020837813615799
2023-01-22 20:08:04.550268: step: 822/470, loss: 0.004713045433163643
2023-01-22 20:08:05.325841: step: 824/470, loss: 0.034453753381967545
2023-01-22 20:08:06.125092: step: 826/470, loss: 0.08387379348278046
2023-01-22 20:08:06.776054: step: 828/470, loss: 0.008352800272405148
2023-01-22 20:08:07.541620: step: 830/470, loss: 0.06293504685163498
2023-01-22 20:08:08.212541: step: 832/470, loss: 0.05639214813709259
2023-01-22 20:08:08.951816: step: 834/470, loss: 0.016982192173600197
2023-01-22 20:08:09.682996: step: 836/470, loss: 0.08415093272924423
2023-01-22 20:08:10.369030: step: 838/470, loss: 0.0067184302024543285
2023-01-22 20:08:11.129995: step: 840/470, loss: 0.01616278663277626
2023-01-22 20:08:11.873966: step: 842/470, loss: 0.035632479935884476
2023-01-22 20:08:12.649505: step: 844/470, loss: 0.10122037678956985
2023-01-22 20:08:13.440321: step: 846/470, loss: 0.06999140232801437
2023-01-22 20:08:14.159473: step: 848/470, loss: 0.0007854777504689991
2023-01-22 20:08:14.905650: step: 850/470, loss: 0.0418260395526886
2023-01-22 20:08:15.676087: step: 852/470, loss: 0.15163059532642365
2023-01-22 20:08:16.476542: step: 854/470, loss: 0.05955205485224724
2023-01-22 20:08:17.300809: step: 856/470, loss: 0.005851359572261572
2023-01-22 20:08:18.054913: step: 858/470, loss: 0.025483133271336555
2023-01-22 20:08:18.765059: step: 860/470, loss: 0.03567005693912506
2023-01-22 20:08:19.477332: step: 862/470, loss: 0.007423198316246271
2023-01-22 20:08:20.179482: step: 864/470, loss: 0.00906333327293396
2023-01-22 20:08:20.981316: step: 866/470, loss: 0.02991068735718727
2023-01-22 20:08:21.697392: step: 868/470, loss: 0.03796318545937538
2023-01-22 20:08:22.320724: step: 870/470, loss: 0.03030499443411827
2023-01-22 20:08:23.109398: step: 872/470, loss: 0.003593269968405366
2023-01-22 20:08:23.798020: step: 874/470, loss: 0.0007432375568896532
2023-01-22 20:08:24.466293: step: 876/470, loss: 0.06043066084384918
2023-01-22 20:08:25.158005: step: 878/470, loss: 0.04188834875822067
2023-01-22 20:08:25.847848: step: 880/470, loss: 0.004259438719600439
2023-01-22 20:08:26.594654: step: 882/470, loss: 0.2212732881307602
2023-01-22 20:08:27.334323: step: 884/470, loss: 0.01849282905459404
2023-01-22 20:08:28.116385: step: 886/470, loss: 0.087897889316082
2023-01-22 20:08:28.925780: step: 888/470, loss: 0.028527600690722466
2023-01-22 20:08:29.683385: step: 890/470, loss: 0.009783981367945671
2023-01-22 20:08:30.331731: step: 892/470, loss: 0.010732408612966537
2023-01-22 20:08:31.007661: step: 894/470, loss: 0.005476772785186768
2023-01-22 20:08:31.723331: step: 896/470, loss: 0.11816710978746414
2023-01-22 20:08:32.434567: step: 898/470, loss: 0.03139311075210571
2023-01-22 20:08:33.115892: step: 900/470, loss: 0.05651181936264038
2023-01-22 20:08:33.756011: step: 902/470, loss: 0.011831426993012428
2023-01-22 20:08:34.455983: step: 904/470, loss: 0.05420336499810219
2023-01-22 20:08:35.133476: step: 906/470, loss: 0.06597546488046646
2023-01-22 20:08:35.899091: step: 908/470, loss: 0.6028205156326294
2023-01-22 20:08:36.627098: step: 910/470, loss: 0.036814119666814804
2023-01-22 20:08:37.572131: step: 912/470, loss: 0.022296173498034477
2023-01-22 20:08:38.351923: step: 914/470, loss: 0.02219575271010399
2023-01-22 20:08:39.114264: step: 916/470, loss: 0.041941218078136444
2023-01-22 20:08:39.855996: step: 918/470, loss: 0.010028064250946045
2023-01-22 20:08:40.509020: step: 920/470, loss: 0.04588298127055168
2023-01-22 20:08:41.235070: step: 922/470, loss: 0.054243478924036026
2023-01-22 20:08:42.079703: step: 924/470, loss: 0.1619579941034317
2023-01-22 20:08:42.859870: step: 926/470, loss: 0.04308824613690376
2023-01-22 20:08:43.546463: step: 928/470, loss: 0.0242212675511837
2023-01-22 20:08:44.239947: step: 930/470, loss: 0.0006321282708086073
2023-01-22 20:08:44.915914: step: 932/470, loss: 0.01612095721065998
2023-01-22 20:08:45.729711: step: 934/470, loss: 0.0768963098526001
2023-01-22 20:08:46.413995: step: 936/470, loss: 0.009668453596532345
2023-01-22 20:08:47.131582: step: 938/470, loss: 0.06522442400455475
2023-01-22 20:08:47.871374: step: 940/470, loss: 0.04865960404276848
2023-01-22 20:08:48.558020: step: 942/470, loss: 0.011983740143477917
==================================================
Loss: 0.066
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30469626823793494, 'r': 0.3434337444655282, 'f1': 0.3229073743681238}, 'combined': 0.237931749534407, 'epoch': 25}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3353308535299347, 'r': 0.34726089351128814, 'f1': 0.3411916195103823}, 'combined': 0.2376459041365847, 'epoch': 25}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3033368551760195, 'r': 0.34765742035354036, 'f1': 0.32398843594397125}, 'combined': 0.23872832122187354, 'epoch': 25}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33509607951121756, 'r': 0.33992919604262933, 'f1': 0.3374953354504387}, 'combined': 0.2350713779256787, 'epoch': 25}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28511661211129297, 'r': 0.35599000145964094, 'f1': 0.31663583252190847}, 'combined': 0.2333106134371957, 'epoch': 25}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3309281577809326, 'r': 0.35574776961450255, 'f1': 0.3428894164959061}, 'combined': 0.23882844930063113, 'epoch': 25}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2175925925925926, 'r': 0.3357142857142857, 'f1': 0.2640449438202247}, 'combined': 0.17602996254681647, 'epoch': 25}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.24285714285714285, 'r': 0.3695652173913043, 'f1': 0.29310344827586204}, 'combined': 0.14655172413793102, 'epoch': 25}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3977272727272727, 'r': 0.3017241379310345, 'f1': 0.34313725490196073}, 'combined': 0.2287581699346405, 'epoch': 25}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 26
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 20:11:24.004028: step: 2/470, loss: 0.019485026597976685
2023-01-22 20:11:24.755677: step: 4/470, loss: 0.04196685925126076
2023-01-22 20:11:25.490792: step: 6/470, loss: 0.048435427248477936
2023-01-22 20:11:26.241418: step: 8/470, loss: 0.08164027333259583
2023-01-22 20:11:27.033149: step: 10/470, loss: 0.031989555805921555
2023-01-22 20:11:27.837511: step: 12/470, loss: 0.03375351428985596
2023-01-22 20:11:28.592680: step: 14/470, loss: 0.04762651026248932
2023-01-22 20:11:29.367929: step: 16/470, loss: 0.030239004641771317
2023-01-22 20:11:30.044111: step: 18/470, loss: 0.00040057190926745534
2023-01-22 20:11:30.798831: step: 20/470, loss: 0.010928238742053509
2023-01-22 20:11:31.569931: step: 22/470, loss: 0.013470311649143696
2023-01-22 20:11:32.352222: step: 24/470, loss: 0.04967685043811798
2023-01-22 20:11:33.052818: step: 26/470, loss: 0.023781154304742813
2023-01-22 20:11:33.781586: step: 28/470, loss: 0.015070714987814426
2023-01-22 20:11:34.507461: step: 30/470, loss: 0.00012959256127942353
2023-01-22 20:11:35.248845: step: 32/470, loss: 0.020162206143140793
2023-01-22 20:11:35.988454: step: 34/470, loss: 0.05546073988080025
2023-01-22 20:11:36.638508: step: 36/470, loss: 0.06939268857240677
2023-01-22 20:11:37.431320: step: 38/470, loss: 0.0007489689160138369
2023-01-22 20:11:38.189226: step: 40/470, loss: 0.014805969782173634
2023-01-22 20:11:38.851738: step: 42/470, loss: 0.02614147588610649
2023-01-22 20:11:39.585667: step: 44/470, loss: 0.11476456373929977
2023-01-22 20:11:40.265499: step: 46/470, loss: 0.000534221762791276
2023-01-22 20:11:41.021175: step: 48/470, loss: 0.005874789785593748
2023-01-22 20:11:41.770813: step: 50/470, loss: 0.0771356076002121
2023-01-22 20:11:42.472777: step: 52/470, loss: 0.016250325366854668
2023-01-22 20:11:43.265032: step: 54/470, loss: 0.06606414169073105
2023-01-22 20:11:43.947072: step: 56/470, loss: 0.16989466547966003
2023-01-22 20:11:44.627855: step: 58/470, loss: 0.025766367092728615
2023-01-22 20:11:45.313408: step: 60/470, loss: 0.004818424582481384
2023-01-22 20:11:46.090717: step: 62/470, loss: 0.20682062208652496
2023-01-22 20:11:46.790240: step: 64/470, loss: 0.04396335780620575
2023-01-22 20:11:47.508884: step: 66/470, loss: 0.12180660665035248
2023-01-22 20:11:48.242307: step: 68/470, loss: 0.03703419491648674
2023-01-22 20:11:49.057080: step: 70/470, loss: 0.0014291710685938597
2023-01-22 20:11:49.772895: step: 72/470, loss: 0.046893779188394547
2023-01-22 20:11:50.447514: step: 74/470, loss: 0.012694248929619789
2023-01-22 20:11:51.229595: step: 76/470, loss: 0.019860833883285522
2023-01-22 20:11:51.953119: step: 78/470, loss: 1.4195009469985962
2023-01-22 20:11:52.676191: step: 80/470, loss: 0.23771710693836212
2023-01-22 20:11:53.519880: step: 82/470, loss: 0.24715445935726166
2023-01-22 20:11:54.273577: step: 84/470, loss: 0.01750795915722847
2023-01-22 20:11:55.018056: step: 86/470, loss: 0.20475627481937408
2023-01-22 20:11:55.842618: step: 88/470, loss: 0.0445147342979908
2023-01-22 20:11:56.555997: step: 90/470, loss: 0.0016261684941127896
2023-01-22 20:11:57.388470: step: 92/470, loss: 0.011423871852457523
2023-01-22 20:11:58.186268: step: 94/470, loss: 0.21087023615837097
2023-01-22 20:11:58.916430: step: 96/470, loss: 0.006003097631037235
2023-01-22 20:11:59.593164: step: 98/470, loss: 0.04363858327269554
2023-01-22 20:12:00.211709: step: 100/470, loss: 0.04111883044242859
2023-01-22 20:12:00.945506: step: 102/470, loss: 0.00875331461429596
2023-01-22 20:12:01.685933: step: 104/470, loss: 0.01105851773172617
2023-01-22 20:12:02.433442: step: 106/470, loss: 0.05842787027359009
2023-01-22 20:12:03.223867: step: 108/470, loss: 0.02871653437614441
2023-01-22 20:12:03.932461: step: 110/470, loss: 0.6604738235473633
2023-01-22 20:12:04.632441: step: 112/470, loss: 0.02996966242790222
2023-01-22 20:12:05.372264: step: 114/470, loss: 0.040596798062324524
2023-01-22 20:12:06.118800: step: 116/470, loss: 2.317312717437744
2023-01-22 20:12:06.875719: step: 118/470, loss: 0.00040206126868724823
2023-01-22 20:12:07.595697: step: 120/470, loss: 0.0035905339755117893
2023-01-22 20:12:08.355244: step: 122/470, loss: 0.006906208582222462
2023-01-22 20:12:09.093077: step: 124/470, loss: 0.08038660883903503
2023-01-22 20:12:09.799005: step: 126/470, loss: 0.003461079904809594
2023-01-22 20:12:10.575638: step: 128/470, loss: 0.012931152246892452
2023-01-22 20:12:11.301823: step: 130/470, loss: 0.04952579736709595
2023-01-22 20:12:12.052466: step: 132/470, loss: 0.5545482635498047
2023-01-22 20:12:12.776186: step: 134/470, loss: 0.009975926019251347
2023-01-22 20:12:13.523944: step: 136/470, loss: 0.0052613853476941586
2023-01-22 20:12:14.403931: step: 138/470, loss: 0.005113921128213406
2023-01-22 20:12:15.108115: step: 140/470, loss: 0.062149327248334885
2023-01-22 20:12:15.885529: step: 142/470, loss: 0.18093203008174896
2023-01-22 20:12:16.627866: step: 144/470, loss: 0.021489135921001434
2023-01-22 20:12:17.307432: step: 146/470, loss: 0.07839653640985489
2023-01-22 20:12:18.120315: step: 148/470, loss: 0.04690365120768547
2023-01-22 20:12:18.907421: step: 150/470, loss: 0.03063216619193554
2023-01-22 20:12:19.616536: step: 152/470, loss: 0.03267190232872963
2023-01-22 20:12:20.315744: step: 154/470, loss: 0.035660747438669205
2023-01-22 20:12:21.017820: step: 156/470, loss: 0.09285139292478561
2023-01-22 20:12:21.706403: step: 158/470, loss: 0.0034859278239309788
2023-01-22 20:12:22.391174: step: 160/470, loss: 0.018955281004309654
2023-01-22 20:12:23.229359: step: 162/470, loss: 0.0037439637817442417
2023-01-22 20:12:23.916778: step: 164/470, loss: 0.0017843381501734257
2023-01-22 20:12:24.687437: step: 166/470, loss: 0.04432709515094757
2023-01-22 20:12:25.480901: step: 168/470, loss: 0.04893715679645538
2023-01-22 20:12:26.163674: step: 170/470, loss: 0.0067788949236273766
2023-01-22 20:12:26.893920: step: 172/470, loss: 0.03473373129963875
2023-01-22 20:12:27.610369: step: 174/470, loss: 0.018431130796670914
2023-01-22 20:12:28.297758: step: 176/470, loss: 0.36892861127853394
2023-01-22 20:12:29.013164: step: 178/470, loss: 0.0027816283982247114
2023-01-22 20:12:29.810061: step: 180/470, loss: 0.15821048617362976
2023-01-22 20:12:30.567992: step: 182/470, loss: 0.6537167429924011
2023-01-22 20:12:31.268194: step: 184/470, loss: 0.0012202489888295531
2023-01-22 20:12:31.986104: step: 186/470, loss: 0.011547365225851536
2023-01-22 20:12:32.712064: step: 188/470, loss: 0.03449565917253494
2023-01-22 20:12:33.389835: step: 190/470, loss: 0.007175063248723745
2023-01-22 20:12:34.123944: step: 192/470, loss: 0.05448294058442116
2023-01-22 20:12:34.862353: step: 194/470, loss: 0.013299376703798771
2023-01-22 20:12:35.670317: step: 196/470, loss: 0.02153635025024414
2023-01-22 20:12:36.521238: step: 198/470, loss: 0.06576363742351532
2023-01-22 20:12:37.303987: step: 200/470, loss: 0.028407655656337738
2023-01-22 20:12:38.047769: step: 202/470, loss: 0.021715879440307617
2023-01-22 20:12:38.840583: step: 204/470, loss: 0.009564381092786789
2023-01-22 20:12:39.710777: step: 206/470, loss: 0.010834124870598316
2023-01-22 20:12:40.420121: step: 208/470, loss: 0.002131436485797167
2023-01-22 20:12:41.188964: step: 210/470, loss: 0.04402882605791092
2023-01-22 20:12:41.958534: step: 212/470, loss: 0.045613422989845276
2023-01-22 20:12:42.654138: step: 214/470, loss: 0.12864279747009277
2023-01-22 20:12:43.342507: step: 216/470, loss: 0.056581586599349976
2023-01-22 20:12:44.083947: step: 218/470, loss: 0.022101709619164467
2023-01-22 20:12:44.867628: step: 220/470, loss: 0.009549708105623722
2023-01-22 20:12:45.581456: step: 222/470, loss: 0.01309411134570837
2023-01-22 20:12:46.302634: step: 224/470, loss: 0.0033089620992541313
2023-01-22 20:12:46.991932: step: 226/470, loss: 0.023617535829544067
2023-01-22 20:12:47.704041: step: 228/470, loss: 0.00651435274630785
2023-01-22 20:12:48.449801: step: 230/470, loss: 0.004386777523905039
2023-01-22 20:12:49.129186: step: 232/470, loss: 0.7032762169837952
2023-01-22 20:12:49.981780: step: 234/470, loss: 0.04321502149105072
2023-01-22 20:12:50.797901: step: 236/470, loss: 0.008020198903977871
2023-01-22 20:12:51.482836: step: 238/470, loss: 0.016117895022034645
2023-01-22 20:12:52.160137: step: 240/470, loss: 0.0072062062099576
2023-01-22 20:12:52.901145: step: 242/470, loss: 0.040230728685855865
2023-01-22 20:12:53.632126: step: 244/470, loss: 0.021644841879606247
2023-01-22 20:12:54.388020: step: 246/470, loss: 0.013207136653363705
2023-01-22 20:12:55.149336: step: 248/470, loss: 0.0457160547375679
2023-01-22 20:12:55.855981: step: 250/470, loss: 0.03336277976632118
2023-01-22 20:12:56.558834: step: 252/470, loss: 0.0007846613880246878
2023-01-22 20:12:57.255352: step: 254/470, loss: 0.016548141837120056
2023-01-22 20:12:58.016252: step: 256/470, loss: 0.029072560369968414
2023-01-22 20:12:58.726588: step: 258/470, loss: 0.023857641965150833
2023-01-22 20:12:59.413085: step: 260/470, loss: 0.016008907929062843
2023-01-22 20:13:00.125067: step: 262/470, loss: 0.005333620123565197
2023-01-22 20:13:00.927453: step: 264/470, loss: 0.025424938648939133
2023-01-22 20:13:01.620612: step: 266/470, loss: 0.008555452339351177
2023-01-22 20:13:02.313859: step: 268/470, loss: 0.13639460504055023
2023-01-22 20:13:03.099654: step: 270/470, loss: 0.06864644587039948
2023-01-22 20:13:03.783477: step: 272/470, loss: 0.00018786423606798053
2023-01-22 20:13:04.547932: step: 274/470, loss: 0.13025711476802826
2023-01-22 20:13:05.252888: step: 276/470, loss: 0.1863914430141449
2023-01-22 20:13:05.973215: step: 278/470, loss: 0.15763676166534424
2023-01-22 20:13:06.673577: step: 280/470, loss: 0.017980456352233887
2023-01-22 20:13:07.426599: step: 282/470, loss: 0.04068325459957123
2023-01-22 20:13:08.178287: step: 284/470, loss: 0.008834258653223515
2023-01-22 20:13:08.925897: step: 286/470, loss: 0.09366513043642044
2023-01-22 20:13:09.608076: step: 288/470, loss: 0.0012397804530337453
2023-01-22 20:13:10.441078: step: 290/470, loss: 0.09330645203590393
2023-01-22 20:13:11.119268: step: 292/470, loss: 0.0060478076338768005
2023-01-22 20:13:11.850341: step: 294/470, loss: 0.01826561614871025
2023-01-22 20:13:12.671361: step: 296/470, loss: 0.016506120562553406
2023-01-22 20:13:13.329689: step: 298/470, loss: 0.018143299967050552
2023-01-22 20:13:14.051587: step: 300/470, loss: 0.002731665037572384
2023-01-22 20:13:14.803284: step: 302/470, loss: 0.042497992515563965
2023-01-22 20:13:15.495280: step: 304/470, loss: 0.0025194089394062757
2023-01-22 20:13:16.207206: step: 306/470, loss: 0.035188719630241394
2023-01-22 20:13:16.915723: step: 308/470, loss: 0.004296632017940283
2023-01-22 20:13:17.639036: step: 310/470, loss: 0.001335528795607388
2023-01-22 20:13:18.411102: step: 312/470, loss: 0.039289023727178574
2023-01-22 20:13:19.183761: step: 314/470, loss: 0.01676071807742119
2023-01-22 20:13:19.972111: step: 316/470, loss: 0.005507394205778837
2023-01-22 20:13:20.639123: step: 318/470, loss: 0.0006347045418806374
2023-01-22 20:13:21.272914: step: 320/470, loss: 0.0023768669925630093
2023-01-22 20:13:21.959300: step: 322/470, loss: 0.02550424449145794
2023-01-22 20:13:22.579730: step: 324/470, loss: 0.013288677670061588
2023-01-22 20:13:23.243931: step: 326/470, loss: 0.00595318665727973
2023-01-22 20:13:24.041973: step: 328/470, loss: 0.09272654354572296
2023-01-22 20:13:24.795486: step: 330/470, loss: 0.007605270016938448
2023-01-22 20:13:25.508165: step: 332/470, loss: 0.010236957110464573
2023-01-22 20:13:26.199949: step: 334/470, loss: 0.007872911170125008
2023-01-22 20:13:26.910476: step: 336/470, loss: 0.0018507775384932756
2023-01-22 20:13:27.666893: step: 338/470, loss: 0.028767062351107597
2023-01-22 20:13:28.391655: step: 340/470, loss: 0.01310647651553154
2023-01-22 20:13:29.165122: step: 342/470, loss: 0.03576286509633064
2023-01-22 20:13:29.894778: step: 344/470, loss: 0.01042783074080944
2023-01-22 20:13:30.605416: step: 346/470, loss: 0.4090971052646637
2023-01-22 20:13:31.552642: step: 348/470, loss: 0.006796136498451233
2023-01-22 20:13:32.282265: step: 350/470, loss: 0.039724674075841904
2023-01-22 20:13:33.042130: step: 352/470, loss: 0.010841785930097103
2023-01-22 20:13:33.816854: step: 354/470, loss: 0.03900299593806267
2023-01-22 20:13:34.634997: step: 356/470, loss: 0.048096682876348495
2023-01-22 20:13:35.343962: step: 358/470, loss: 0.0033374207559973
2023-01-22 20:13:36.068010: step: 360/470, loss: 0.08358647674322128
2023-01-22 20:13:36.831820: step: 362/470, loss: 0.2687551975250244
2023-01-22 20:13:37.563349: step: 364/470, loss: 0.01693040318787098
2023-01-22 20:13:38.270734: step: 366/470, loss: 0.005727311596274376
2023-01-22 20:13:38.969107: step: 368/470, loss: 0.0020413741003721952
2023-01-22 20:13:39.737131: step: 370/470, loss: 0.021475672721862793
2023-01-22 20:13:40.513297: step: 372/470, loss: 0.19835321605205536
2023-01-22 20:13:41.203799: step: 374/470, loss: 0.01151078287512064
2023-01-22 20:13:42.081792: step: 376/470, loss: 0.015609940513968468
2023-01-22 20:13:42.812461: step: 378/470, loss: 0.04101203382015228
2023-01-22 20:13:43.536886: step: 380/470, loss: 0.006876502186059952
2023-01-22 20:13:44.368200: step: 382/470, loss: 1.5188071727752686
2023-01-22 20:13:45.095524: step: 384/470, loss: 0.03681845963001251
2023-01-22 20:13:45.800482: step: 386/470, loss: 0.05127471312880516
2023-01-22 20:13:46.520747: step: 388/470, loss: 0.018120506778359413
2023-01-22 20:13:47.241003: step: 390/470, loss: 0.01568225957453251
2023-01-22 20:13:47.898515: step: 392/470, loss: 0.058441437780857086
2023-01-22 20:13:48.729918: step: 394/470, loss: 0.013389245606958866
2023-01-22 20:13:49.498531: step: 396/470, loss: 0.0006397226825356483
2023-01-22 20:13:50.259094: step: 398/470, loss: 0.026342155411839485
2023-01-22 20:13:51.072317: step: 400/470, loss: 0.044728025794029236
2023-01-22 20:13:51.779924: step: 402/470, loss: 0.008601291105151176
2023-01-22 20:13:52.511881: step: 404/470, loss: 0.04410114884376526
2023-01-22 20:13:53.315164: step: 406/470, loss: 0.006642171647399664
2023-01-22 20:13:54.129057: step: 408/470, loss: 0.0413130447268486
2023-01-22 20:13:54.894328: step: 410/470, loss: 0.04338083043694496
2023-01-22 20:13:55.559679: step: 412/470, loss: 0.006818010471761227
2023-01-22 20:13:56.386692: step: 414/470, loss: 0.03733073174953461
2023-01-22 20:13:57.153521: step: 416/470, loss: 0.1958683431148529
2023-01-22 20:13:57.935962: step: 418/470, loss: 0.0009550434770062566
2023-01-22 20:13:58.694433: step: 420/470, loss: 0.020624913275241852
2023-01-22 20:13:59.333018: step: 422/470, loss: 0.004369684495031834
2023-01-22 20:14:00.042846: step: 424/470, loss: 0.029023706912994385
2023-01-22 20:14:00.819095: step: 426/470, loss: 0.03372396156191826
2023-01-22 20:14:01.558559: step: 428/470, loss: 0.1394890546798706
2023-01-22 20:14:02.254985: step: 430/470, loss: 0.03233359009027481
2023-01-22 20:14:03.128324: step: 432/470, loss: 0.019605809822678566
2023-01-22 20:14:03.936758: step: 434/470, loss: 0.02610873058438301
2023-01-22 20:14:04.726614: step: 436/470, loss: 0.04683273285627365
2023-01-22 20:14:05.535354: step: 438/470, loss: 0.049369730055332184
2023-01-22 20:14:06.226760: step: 440/470, loss: 0.0025972574949264526
2023-01-22 20:14:06.954903: step: 442/470, loss: 0.011458461172878742
2023-01-22 20:14:07.721596: step: 444/470, loss: 0.008207599632441998
2023-01-22 20:14:08.556688: step: 446/470, loss: 0.0014893775805830956
2023-01-22 20:14:09.253716: step: 448/470, loss: 0.0214060191065073
2023-01-22 20:14:09.951760: step: 450/470, loss: 0.03423811122775078
2023-01-22 20:14:10.672622: step: 452/470, loss: 0.023825276643037796
2023-01-22 20:14:11.324349: step: 454/470, loss: 0.00232740119099617
2023-01-22 20:14:12.079832: step: 456/470, loss: 0.06115736439824104
2023-01-22 20:14:12.927536: step: 458/470, loss: 0.3774428963661194
2023-01-22 20:14:13.660164: step: 460/470, loss: 0.02544984221458435
2023-01-22 20:14:14.373126: step: 462/470, loss: 0.0458686426281929
2023-01-22 20:14:15.085319: step: 464/470, loss: 0.0019502779468894005
2023-01-22 20:14:15.681428: step: 466/470, loss: 0.0001484197418903932
2023-01-22 20:14:16.363737: step: 468/470, loss: 0.019259247928857803
2023-01-22 20:14:17.160072: step: 470/470, loss: 0.04199659079313278
2023-01-22 20:14:17.932992: step: 472/470, loss: 0.0764729380607605
2023-01-22 20:14:18.656725: step: 474/470, loss: 0.012650109827518463
2023-01-22 20:14:19.399165: step: 476/470, loss: 0.19659210741519928
2023-01-22 20:14:20.081828: step: 478/470, loss: 0.016243983060121536
2023-01-22 20:14:20.838756: step: 480/470, loss: 0.7099974751472473
2023-01-22 20:14:21.567497: step: 482/470, loss: 0.008293403312563896
2023-01-22 20:14:22.296865: step: 484/470, loss: 0.024716457352042198
2023-01-22 20:14:23.052426: step: 486/470, loss: 0.005962827242910862
2023-01-22 20:14:23.755885: step: 488/470, loss: 0.0011397538473829627
2023-01-22 20:14:24.560665: step: 490/470, loss: 0.007134813815355301
2023-01-22 20:14:25.320665: step: 492/470, loss: 0.1319524198770523
2023-01-22 20:14:26.037792: step: 494/470, loss: 0.5560120344161987
2023-01-22 20:14:26.714125: step: 496/470, loss: 0.058050792664289474
2023-01-22 20:14:27.413801: step: 498/470, loss: 0.025943944230675697
2023-01-22 20:14:28.149540: step: 500/470, loss: 0.031523432582616806
2023-01-22 20:14:28.886193: step: 502/470, loss: 0.008412609808146954
2023-01-22 20:14:29.577507: step: 504/470, loss: 0.009613175876438618
2023-01-22 20:14:30.336318: step: 506/470, loss: 0.01078837364912033
2023-01-22 20:14:31.108596: step: 508/470, loss: 0.0254935584962368
2023-01-22 20:14:31.785382: step: 510/470, loss: 0.009062767960131168
2023-01-22 20:14:32.482385: step: 512/470, loss: 0.048958227038383484
2023-01-22 20:14:33.201503: step: 514/470, loss: 0.015435706824064255
2023-01-22 20:14:33.956369: step: 516/470, loss: 0.017597481608390808
2023-01-22 20:14:34.644057: step: 518/470, loss: 0.01942635513842106
2023-01-22 20:14:35.324531: step: 520/470, loss: 0.007770019117742777
2023-01-22 20:14:36.026365: step: 522/470, loss: 0.0021495139226317406
2023-01-22 20:14:36.823628: step: 524/470, loss: 0.034324824810028076
2023-01-22 20:14:37.604251: step: 526/470, loss: 0.4315849840641022
2023-01-22 20:14:38.322166: step: 528/470, loss: 0.007081069517880678
2023-01-22 20:14:38.986919: step: 530/470, loss: 0.02178391069173813
2023-01-22 20:14:39.783625: step: 532/470, loss: 0.01920427940785885
2023-01-22 20:14:40.552837: step: 534/470, loss: 0.005591890309005976
2023-01-22 20:14:41.282500: step: 536/470, loss: 0.011183743365108967
2023-01-22 20:14:41.981000: step: 538/470, loss: 0.016883065924048424
2023-01-22 20:14:42.673167: step: 540/470, loss: 0.002876394661143422
2023-01-22 20:14:43.532837: step: 542/470, loss: 0.007916656322777271
2023-01-22 20:14:44.300588: step: 544/470, loss: 0.023198112845420837
2023-01-22 20:14:45.053076: step: 546/470, loss: 0.004471739754080772
2023-01-22 20:14:45.740020: step: 548/470, loss: 0.14783816039562225
2023-01-22 20:14:46.400180: step: 550/470, loss: 0.004815774969756603
2023-01-22 20:14:47.097185: step: 552/470, loss: 0.01722968928515911
2023-01-22 20:14:47.811776: step: 554/470, loss: 0.30158334970474243
2023-01-22 20:14:48.545659: step: 556/470, loss: 0.055766280740499496
2023-01-22 20:14:49.241031: step: 558/470, loss: 0.033450160175561905
2023-01-22 20:14:49.948533: step: 560/470, loss: 0.03725216165184975
2023-01-22 20:14:50.784170: step: 562/470, loss: 0.0021749266888946295
2023-01-22 20:14:51.574674: step: 564/470, loss: 0.006228404585272074
2023-01-22 20:14:52.366340: step: 566/470, loss: 0.003034188412129879
2023-01-22 20:14:53.084869: step: 568/470, loss: 0.0010111165465787053
2023-01-22 20:14:53.849018: step: 570/470, loss: 0.7480594515800476
2023-01-22 20:14:54.777294: step: 572/470, loss: 0.15064027905464172
2023-01-22 20:14:55.470627: step: 574/470, loss: 0.0038994362112134695
2023-01-22 20:14:56.150442: step: 576/470, loss: 0.00042104304884560406
2023-01-22 20:14:56.878089: step: 578/470, loss: 0.1475483477115631
2023-01-22 20:14:57.592221: step: 580/470, loss: 0.21218250691890717
2023-01-22 20:14:58.272323: step: 582/470, loss: 0.009204575791954994
2023-01-22 20:14:59.047607: step: 584/470, loss: 0.22064003348350525
2023-01-22 20:14:59.747675: step: 586/470, loss: 0.017769113183021545
2023-01-22 20:15:00.479247: step: 588/470, loss: 0.006627894006669521
2023-01-22 20:15:01.151779: step: 590/470, loss: 0.13599713146686554
2023-01-22 20:15:01.898786: step: 592/470, loss: 0.042819686233997345
2023-01-22 20:15:02.622052: step: 594/470, loss: 0.011788510717451572
2023-01-22 20:15:03.412077: step: 596/470, loss: 0.01742238737642765
2023-01-22 20:15:04.212176: step: 598/470, loss: 0.6136803030967712
2023-01-22 20:15:04.864413: step: 600/470, loss: 0.01876203715801239
2023-01-22 20:15:05.592829: step: 602/470, loss: 0.03775479272007942
2023-01-22 20:15:06.279870: step: 604/470, loss: 0.02878272905945778
2023-01-22 20:15:07.048067: step: 606/470, loss: 0.0009686170378699899
2023-01-22 20:15:07.852630: step: 608/470, loss: 0.065780408680439
2023-01-22 20:15:08.654897: step: 610/470, loss: 0.3254455327987671
2023-01-22 20:15:09.412413: step: 612/470, loss: 0.011034596711397171
2023-01-22 20:15:10.180439: step: 614/470, loss: 0.032889679074287415
2023-01-22 20:15:10.993911: step: 616/470, loss: 0.025389349088072777
2023-01-22 20:15:11.701803: step: 618/470, loss: 0.06543834507465363
2023-01-22 20:15:12.496173: step: 620/470, loss: 0.0328560434281826
2023-01-22 20:15:13.218572: step: 622/470, loss: 0.030454453080892563
2023-01-22 20:15:13.924729: step: 624/470, loss: 0.0002651447430253029
2023-01-22 20:15:14.704063: step: 626/470, loss: 0.008108319714665413
2023-01-22 20:15:15.403041: step: 628/470, loss: 0.028416186571121216
2023-01-22 20:15:16.122693: step: 630/470, loss: 0.014787995256483555
2023-01-22 20:15:16.880125: step: 632/470, loss: 0.4447817802429199
2023-01-22 20:15:17.616578: step: 634/470, loss: 0.00016679373220540583
2023-01-22 20:15:18.371698: step: 636/470, loss: 0.008493703790009022
2023-01-22 20:15:19.105052: step: 638/470, loss: 0.051174718886613846
2023-01-22 20:15:19.915268: step: 640/470, loss: 0.02636360004544258
2023-01-22 20:15:20.628207: step: 642/470, loss: 0.012426851317286491
2023-01-22 20:15:21.419908: step: 644/470, loss: 0.004039624240249395
2023-01-22 20:15:22.121450: step: 646/470, loss: 0.09385068714618683
2023-01-22 20:15:22.902583: step: 648/470, loss: 0.02949446067214012
2023-01-22 20:15:23.680142: step: 650/470, loss: 0.04192233458161354
2023-01-22 20:15:24.387453: step: 652/470, loss: 0.020343631505966187
2023-01-22 20:15:25.170259: step: 654/470, loss: 0.05575917288661003
2023-01-22 20:15:25.987800: step: 656/470, loss: 0.01872909814119339
2023-01-22 20:15:26.736796: step: 658/470, loss: 0.00723220594227314
2023-01-22 20:15:27.518398: step: 660/470, loss: 0.014894779771566391
2023-01-22 20:15:28.330707: step: 662/470, loss: 0.00329477246850729
2023-01-22 20:15:29.017556: step: 664/470, loss: 0.030976993963122368
2023-01-22 20:15:29.734725: step: 666/470, loss: 0.016939232125878334
2023-01-22 20:15:30.434963: step: 668/470, loss: 0.005721811670809984
2023-01-22 20:15:31.203490: step: 670/470, loss: 0.06608849763870239
2023-01-22 20:15:31.959762: step: 672/470, loss: 0.05654697120189667
2023-01-22 20:15:32.694195: step: 674/470, loss: 0.028054917231202126
2023-01-22 20:15:33.410060: step: 676/470, loss: 0.007750812452286482
2023-01-22 20:15:34.116938: step: 678/470, loss: 0.02219163253903389
2023-01-22 20:15:34.882378: step: 680/470, loss: 0.037425290793180466
2023-01-22 20:15:35.542982: step: 682/470, loss: 0.03459089994430542
2023-01-22 20:15:36.310711: step: 684/470, loss: 0.009903617203235626
2023-01-22 20:15:37.015772: step: 686/470, loss: 0.008926295675337315
2023-01-22 20:15:37.683209: step: 688/470, loss: 0.014270035549998283
2023-01-22 20:15:38.414326: step: 690/470, loss: 0.08540667593479156
2023-01-22 20:15:39.125673: step: 692/470, loss: 0.04163281247019768
2023-01-22 20:15:39.838315: step: 694/470, loss: 0.01574213244020939
2023-01-22 20:15:40.713724: step: 696/470, loss: 0.0054738158360123634
2023-01-22 20:15:41.469887: step: 698/470, loss: 0.20161749422550201
2023-01-22 20:15:42.181811: step: 700/470, loss: 0.4112975597381592
2023-01-22 20:15:42.884787: step: 702/470, loss: 0.00508745014667511
2023-01-22 20:15:43.549662: step: 704/470, loss: 0.00045277041499502957
2023-01-22 20:15:44.292047: step: 706/470, loss: 0.14759576320648193
2023-01-22 20:15:45.085034: step: 708/470, loss: 0.041470929980278015
2023-01-22 20:15:45.881819: step: 710/470, loss: 0.0423739068210125
2023-01-22 20:15:46.606698: step: 712/470, loss: 0.6495215892791748
2023-01-22 20:15:47.408944: step: 714/470, loss: 0.03245260939002037
2023-01-22 20:15:48.028062: step: 716/470, loss: 0.027776306495070457
2023-01-22 20:15:48.798719: step: 718/470, loss: 0.01630890928208828
2023-01-22 20:15:49.556484: step: 720/470, loss: 0.04993465170264244
2023-01-22 20:15:50.344309: step: 722/470, loss: 0.030327895656228065
2023-01-22 20:15:51.016708: step: 724/470, loss: 0.028972510248422623
2023-01-22 20:15:51.755366: step: 726/470, loss: 0.05604696646332741
2023-01-22 20:15:52.526652: step: 728/470, loss: 0.010281789116561413
2023-01-22 20:15:53.267410: step: 730/470, loss: 0.03586762771010399
2023-01-22 20:15:53.925200: step: 732/470, loss: 0.0005163901951164007
2023-01-22 20:15:54.630485: step: 734/470, loss: 0.01637759618461132
2023-01-22 20:15:55.277601: step: 736/470, loss: 0.022752603515982628
2023-01-22 20:15:56.057720: step: 738/470, loss: 0.015957066789269447
2023-01-22 20:15:56.724153: step: 740/470, loss: 0.013974886387586594
2023-01-22 20:15:57.408374: step: 742/470, loss: 0.007855596952140331
2023-01-22 20:15:58.140348: step: 744/470, loss: 0.01974407769739628
2023-01-22 20:15:58.888220: step: 746/470, loss: 0.019117096439003944
2023-01-22 20:15:59.628413: step: 748/470, loss: 0.03735620900988579
2023-01-22 20:16:00.342387: step: 750/470, loss: 0.08970566838979721
2023-01-22 20:16:01.034508: step: 752/470, loss: 0.018881360068917274
2023-01-22 20:16:01.746490: step: 754/470, loss: 0.001953059108927846
2023-01-22 20:16:02.562757: step: 756/470, loss: 0.691685140132904
2023-01-22 20:16:03.266392: step: 758/470, loss: 0.06533520668745041
2023-01-22 20:16:03.980813: step: 760/470, loss: 0.0035757829900830984
2023-01-22 20:16:04.668650: step: 762/470, loss: 0.00113035854883492
2023-01-22 20:16:05.384385: step: 764/470, loss: 0.02485186792910099
2023-01-22 20:16:06.098737: step: 766/470, loss: 0.004313065204769373
2023-01-22 20:16:06.789680: step: 768/470, loss: 0.016619572415947914
2023-01-22 20:16:07.598116: step: 770/470, loss: 0.004702294245362282
2023-01-22 20:16:08.391618: step: 772/470, loss: 0.054384443908929825
2023-01-22 20:16:09.124931: step: 774/470, loss: 0.00823363196104765
2023-01-22 20:16:09.905068: step: 776/470, loss: 0.0492500476539135
2023-01-22 20:16:10.637994: step: 778/470, loss: 0.0389709398150444
2023-01-22 20:16:11.384561: step: 780/470, loss: 0.03600706160068512
2023-01-22 20:16:12.044577: step: 782/470, loss: 0.007133893668651581
2023-01-22 20:16:12.747913: step: 784/470, loss: 0.045114368200302124
2023-01-22 20:16:13.583418: step: 786/470, loss: 0.016657711938023567
2023-01-22 20:16:14.363939: step: 788/470, loss: 0.025096865370869637
2023-01-22 20:16:15.103257: step: 790/470, loss: 1.0770021677017212
2023-01-22 20:16:15.875391: step: 792/470, loss: 0.9711056351661682
2023-01-22 20:16:16.547158: step: 794/470, loss: 0.014067924581468105
2023-01-22 20:16:17.251042: step: 796/470, loss: 0.04596575349569321
2023-01-22 20:16:18.093162: step: 798/470, loss: 0.0024457420222461224
2023-01-22 20:16:18.909971: step: 800/470, loss: 0.05553967505693436
2023-01-22 20:16:19.651065: step: 802/470, loss: 0.02744687721133232
2023-01-22 20:16:20.313267: step: 804/470, loss: 0.006461080629378557
2023-01-22 20:16:21.019403: step: 806/470, loss: 0.016188278794288635
2023-01-22 20:16:21.777056: step: 808/470, loss: 0.044517967849969864
2023-01-22 20:16:22.522383: step: 810/470, loss: 0.00267368508502841
2023-01-22 20:16:23.235287: step: 812/470, loss: 0.031701844185590744
2023-01-22 20:16:23.970538: step: 814/470, loss: 0.0011221464956179261
2023-01-22 20:16:24.712389: step: 816/470, loss: 0.013465669006109238
2023-01-22 20:16:25.444113: step: 818/470, loss: 0.2107423096895218
2023-01-22 20:16:26.204157: step: 820/470, loss: 0.028793897479772568
2023-01-22 20:16:27.028299: step: 822/470, loss: 0.01618114300072193
2023-01-22 20:16:27.750421: step: 824/470, loss: 0.09623509645462036
2023-01-22 20:16:28.484832: step: 826/470, loss: 0.041487544775009155
2023-01-22 20:16:29.192298: step: 828/470, loss: 0.011326837353408337
2023-01-22 20:16:29.879739: step: 830/470, loss: 0.045046452432870865
2023-01-22 20:16:30.686381: step: 832/470, loss: 0.10204900801181793
2023-01-22 20:16:31.511477: step: 834/470, loss: 0.07618521898984909
2023-01-22 20:16:32.313933: step: 836/470, loss: 0.08233476430177689
2023-01-22 20:16:33.039761: step: 838/470, loss: 0.06587542593479156
2023-01-22 20:16:33.714902: step: 840/470, loss: 0.01595766469836235
2023-01-22 20:16:34.410897: step: 842/470, loss: 0.0016488569090142846
2023-01-22 20:16:35.119151: step: 844/470, loss: 0.006250299047678709
2023-01-22 20:16:35.910476: step: 846/470, loss: 0.10261400043964386
2023-01-22 20:16:36.595836: step: 848/470, loss: 0.06171036139130592
2023-01-22 20:16:37.283913: step: 850/470, loss: 0.029668550938367844
2023-01-22 20:16:38.106672: step: 852/470, loss: 0.003090712008997798
2023-01-22 20:16:38.837773: step: 854/470, loss: 0.00039391950122080743
2023-01-22 20:16:39.540667: step: 856/470, loss: 0.0029829915147274733
2023-01-22 20:16:40.208784: step: 858/470, loss: 0.06782427430152893
2023-01-22 20:16:40.854344: step: 860/470, loss: 0.037175048142671585
2023-01-22 20:16:41.549364: step: 862/470, loss: 0.012290716171264648
2023-01-22 20:16:42.233396: step: 864/470, loss: 0.004582709167152643
2023-01-22 20:16:42.973445: step: 866/470, loss: 0.06253193318843842
2023-01-22 20:16:43.710263: step: 868/470, loss: 0.26506075263023376
2023-01-22 20:16:44.388441: step: 870/470, loss: 0.036856453865766525
2023-01-22 20:16:45.050600: step: 872/470, loss: 0.06115124374628067
2023-01-22 20:16:45.764528: step: 874/470, loss: 0.0035287141799926758
2023-01-22 20:16:46.417983: step: 876/470, loss: 0.010850594379007816
2023-01-22 20:16:47.177219: step: 878/470, loss: 0.022742489352822304
2023-01-22 20:16:47.923383: step: 880/470, loss: 0.1650201976299286
2023-01-22 20:16:48.652139: step: 882/470, loss: 0.021147647872567177
2023-01-22 20:16:49.373567: step: 884/470, loss: 0.02876165509223938
2023-01-22 20:16:50.073547: step: 886/470, loss: 0.031704407185316086
2023-01-22 20:16:50.747228: step: 888/470, loss: 0.020638834685087204
2023-01-22 20:16:51.425200: step: 890/470, loss: 0.020739523693919182
2023-01-22 20:16:52.101556: step: 892/470, loss: 0.02357344888150692
2023-01-22 20:16:52.803310: step: 894/470, loss: 0.009717467240989208
2023-01-22 20:16:53.468659: step: 896/470, loss: 0.033283960074186325
2023-01-22 20:16:54.259208: step: 898/470, loss: 0.04801145941019058
2023-01-22 20:16:55.002487: step: 900/470, loss: 0.0027546961791813374
2023-01-22 20:16:55.748151: step: 902/470, loss: 0.0054783690720796585
2023-01-22 20:16:56.548852: step: 904/470, loss: 0.14740252494812012
2023-01-22 20:16:57.263359: step: 906/470, loss: 0.047735873609781265
2023-01-22 20:16:57.977381: step: 908/470, loss: 0.01004134863615036
2023-01-22 20:16:58.689772: step: 910/470, loss: 0.048433274030685425
2023-01-22 20:16:59.458724: step: 912/470, loss: 0.018374241888523102
2023-01-22 20:17:00.184557: step: 914/470, loss: 0.015799539163708687
2023-01-22 20:17:00.891309: step: 916/470, loss: 0.01117359846830368
2023-01-22 20:17:01.651752: step: 918/470, loss: 0.012997347861528397
2023-01-22 20:17:02.342046: step: 920/470, loss: 0.02212097868323326
2023-01-22 20:17:03.011255: step: 922/470, loss: 0.08863328397274017
2023-01-22 20:17:03.730893: step: 924/470, loss: 0.008121066726744175
2023-01-22 20:17:04.448959: step: 926/470, loss: 0.2342129349708557
2023-01-22 20:17:05.183895: step: 928/470, loss: 0.011628974229097366
2023-01-22 20:17:05.902692: step: 930/470, loss: 0.019393447786569595
2023-01-22 20:17:06.702596: step: 932/470, loss: 0.013421921990811825
2023-01-22 20:17:07.455388: step: 934/470, loss: 0.3163841962814331
2023-01-22 20:17:08.166801: step: 936/470, loss: 0.003866309067234397
2023-01-22 20:17:08.898109: step: 938/470, loss: 0.04852140694856644
2023-01-22 20:17:09.613644: step: 940/470, loss: 0.008729308843612671
2023-01-22 20:17:10.268601: step: 942/470, loss: 0.04352358356118202
==================================================
Loss: 0.072
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29753125662216573, 'r': 0.34156814090400434, 'f1': 0.31803252695478845}, 'combined': 0.23433975670352833, 'epoch': 26}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364348350561144, 'r': 0.3597264774830762, 'f1': 0.3476910191286238}, 'combined': 0.2421728491443151, 'epoch': 26}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29081003289473684, 'r': 0.3443367372415859, 'f1': 0.31531791577118295}, 'combined': 0.23233951688402954, 'epoch': 26}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34448135984675676, 'r': 0.35640571461068293, 'f1': 0.35034210131862975}, 'combined': 0.24401937405277696, 'epoch': 26}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2828576864535769, 'r': 0.3526328273244782, 'f1': 0.31391469594594595}, 'combined': 0.2313055654338549, 'epoch': 26}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33027861948824616, 'r': 0.3683876909676592, 'f1': 0.34829381691487776}, 'combined': 0.24259270829891985, 'epoch': 26}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20601851851851852, 'r': 0.31785714285714284, 'f1': 0.25}, 'combined': 0.16666666666666666, 'epoch': 26}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3, 'r': 0.45652173913043476, 'f1': 0.3620689655172414}, 'combined': 0.1810344827586207, 'epoch': 26}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3977272727272727, 'r': 0.3017241379310345, 'f1': 0.34313725490196073}, 'combined': 0.2287581699346405, 'epoch': 26}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 27
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 20:19:45.793782: step: 2/470, loss: 0.01683763414621353
2023-01-22 20:19:46.472094: step: 4/470, loss: 0.00944485329091549
2023-01-22 20:19:47.110081: step: 6/470, loss: 0.06548219174146652
2023-01-22 20:19:47.903506: step: 8/470, loss: 0.07034937292337418
2023-01-22 20:19:48.651936: step: 10/470, loss: 0.00018511965754441917
2023-01-22 20:19:49.378070: step: 12/470, loss: 0.007175577338784933
2023-01-22 20:19:50.030903: step: 14/470, loss: 0.0017143557779490948
2023-01-22 20:19:50.752193: step: 16/470, loss: 0.038774389773607254
2023-01-22 20:19:51.491799: step: 18/470, loss: 0.067210853099823
2023-01-22 20:19:52.289697: step: 20/470, loss: 0.01777871884405613
2023-01-22 20:19:52.957358: step: 22/470, loss: 0.00815779808908701
2023-01-22 20:19:53.563720: step: 24/470, loss: 0.00567712401971221
2023-01-22 20:19:54.274201: step: 26/470, loss: 0.022142581641674042
2023-01-22 20:19:55.026510: step: 28/470, loss: 0.009569667279720306
2023-01-22 20:19:55.705205: step: 30/470, loss: 0.0004666670865844935
2023-01-22 20:19:56.445032: step: 32/470, loss: 0.011350602842867374
2023-01-22 20:19:57.125304: step: 34/470, loss: 0.029375847429037094
2023-01-22 20:19:57.823287: step: 36/470, loss: 0.006464695557951927
2023-01-22 20:19:58.543394: step: 38/470, loss: 0.0230893325060606
2023-01-22 20:19:59.207913: step: 40/470, loss: 0.015446262434124947
2023-01-22 20:19:59.896127: step: 42/470, loss: 0.026244178414344788
2023-01-22 20:20:00.570572: step: 44/470, loss: 0.019167501479387283
2023-01-22 20:20:01.398300: step: 46/470, loss: 0.025599118322134018
2023-01-22 20:20:02.200440: step: 48/470, loss: 0.06443053483963013
2023-01-22 20:20:02.941821: step: 50/470, loss: 0.016018331050872803
2023-01-22 20:20:03.771583: step: 52/470, loss: 0.003692210651934147
2023-01-22 20:20:04.496918: step: 54/470, loss: 0.02155778743326664
2023-01-22 20:20:05.208037: step: 56/470, loss: 0.1240386813879013
2023-01-22 20:20:05.880351: step: 58/470, loss: 0.013327186927199364
2023-01-22 20:20:06.605688: step: 60/470, loss: 0.009797775186598301
2023-01-22 20:20:07.303259: step: 62/470, loss: 0.02393781952559948
2023-01-22 20:20:08.056210: step: 64/470, loss: 0.00024999401648528874
2023-01-22 20:20:08.765714: step: 66/470, loss: 0.014125204645097256
2023-01-22 20:20:09.561594: step: 68/470, loss: 0.012959994375705719
2023-01-22 20:20:10.290107: step: 70/470, loss: 0.012555788271129131
2023-01-22 20:20:11.016609: step: 72/470, loss: 0.010418666526675224
2023-01-22 20:20:11.699796: step: 74/470, loss: 0.025468451902270317
2023-01-22 20:20:12.414934: step: 76/470, loss: 0.005443628877401352
2023-01-22 20:20:13.141691: step: 78/470, loss: 0.017685700207948685
2023-01-22 20:20:13.899768: step: 80/470, loss: 0.04424380883574486
2023-01-22 20:20:14.644920: step: 82/470, loss: 0.037951018661260605
2023-01-22 20:20:15.368285: step: 84/470, loss: 0.009052631445229053
2023-01-22 20:20:16.114115: step: 86/470, loss: 0.0344005785882473
2023-01-22 20:20:16.812965: step: 88/470, loss: 0.007054035551846027
2023-01-22 20:20:17.507092: step: 90/470, loss: 0.019252652302384377
2023-01-22 20:20:18.378508: step: 92/470, loss: 0.008761339820921421
2023-01-22 20:20:19.248464: step: 94/470, loss: 0.02975519932806492
2023-01-22 20:20:20.024989: step: 96/470, loss: 0.006972640287131071
2023-01-22 20:20:20.774499: step: 98/470, loss: 0.03771801292896271
2023-01-22 20:20:21.461673: step: 100/470, loss: 0.017774201929569244
2023-01-22 20:20:22.200159: step: 102/470, loss: 0.03576158732175827
2023-01-22 20:20:23.010008: step: 104/470, loss: 0.056759800761938095
2023-01-22 20:20:23.764882: step: 106/470, loss: 0.061209507286548615
2023-01-22 20:20:24.413198: step: 108/470, loss: 0.0349019393324852
2023-01-22 20:20:25.135701: step: 110/470, loss: 0.014727793633937836
2023-01-22 20:20:25.892081: step: 112/470, loss: 0.003246006788685918
2023-01-22 20:20:26.712387: step: 114/470, loss: 0.08207906782627106
2023-01-22 20:20:27.497146: step: 116/470, loss: 0.016705762594938278
2023-01-22 20:20:28.269486: step: 118/470, loss: 0.012947305105626583
2023-01-22 20:20:28.992294: step: 120/470, loss: 0.034973785281181335
2023-01-22 20:20:29.715819: step: 122/470, loss: 0.007712268736213446
2023-01-22 20:20:30.431937: step: 124/470, loss: 0.020008675754070282
2023-01-22 20:20:31.238967: step: 126/470, loss: 0.023369409143924713
2023-01-22 20:20:31.970216: step: 128/470, loss: 0.014888121746480465
2023-01-22 20:20:32.679323: step: 130/470, loss: 0.05595388263463974
2023-01-22 20:20:33.438012: step: 132/470, loss: 0.01942775398492813
2023-01-22 20:20:34.180108: step: 134/470, loss: 0.02803257293999195
2023-01-22 20:20:34.856595: step: 136/470, loss: 0.023012829944491386
2023-01-22 20:20:35.518792: step: 138/470, loss: 0.0042619104497134686
2023-01-22 20:20:36.404122: step: 140/470, loss: 0.007180250249803066
2023-01-22 20:20:37.091505: step: 142/470, loss: 0.019708437845110893
2023-01-22 20:20:37.805773: step: 144/470, loss: 0.0061777918599545956
2023-01-22 20:20:38.570502: step: 146/470, loss: 0.0012747780419886112
2023-01-22 20:20:39.338173: step: 148/470, loss: 0.022044524550437927
2023-01-22 20:20:40.024116: step: 150/470, loss: 0.020499933511018753
2023-01-22 20:20:40.758542: step: 152/470, loss: 0.0026768154930323362
2023-01-22 20:20:41.660782: step: 154/470, loss: 0.010907319374382496
2023-01-22 20:20:42.367482: step: 156/470, loss: 0.005641602911055088
2023-01-22 20:20:43.088107: step: 158/470, loss: 0.013856947422027588
2023-01-22 20:20:43.844930: step: 160/470, loss: 0.010804500430822372
2023-01-22 20:20:44.540340: step: 162/470, loss: 0.015558190643787384
2023-01-22 20:20:45.295181: step: 164/470, loss: 0.3554113507270813
2023-01-22 20:20:45.989897: step: 166/470, loss: 0.12705135345458984
2023-01-22 20:20:46.693091: step: 168/470, loss: 0.02279657870531082
2023-01-22 20:20:47.402898: step: 170/470, loss: 0.07756506651639938
2023-01-22 20:20:48.090264: step: 172/470, loss: 0.012663285247981548
2023-01-22 20:20:48.803341: step: 174/470, loss: 8.404543768847361e-05
2023-01-22 20:20:49.571814: step: 176/470, loss: 0.02814382128417492
2023-01-22 20:20:50.278029: step: 178/470, loss: 0.02191387489438057
2023-01-22 20:20:51.006249: step: 180/470, loss: 0.011857813224196434
2023-01-22 20:20:51.730531: step: 182/470, loss: 0.12916842103004456
2023-01-22 20:20:52.483375: step: 184/470, loss: 0.07631305605173111
2023-01-22 20:20:53.191584: step: 186/470, loss: 0.028871390968561172
2023-01-22 20:20:53.901025: step: 188/470, loss: 0.033751778304576874
2023-01-22 20:20:54.717882: step: 190/470, loss: 0.13906638324260712
2023-01-22 20:20:55.455264: step: 192/470, loss: 0.03259306401014328
2023-01-22 20:20:56.189474: step: 194/470, loss: 0.0015212270664051175
2023-01-22 20:20:56.915933: step: 196/470, loss: 0.02239634282886982
2023-01-22 20:20:57.667470: step: 198/470, loss: 0.06503739953041077
2023-01-22 20:20:58.358218: step: 200/470, loss: 0.4716545343399048
2023-01-22 20:20:59.067109: step: 202/470, loss: 0.02160857617855072
2023-01-22 20:20:59.769296: step: 204/470, loss: 0.004003697074949741
2023-01-22 20:21:00.515374: step: 206/470, loss: 0.007205252069979906
2023-01-22 20:21:01.209337: step: 208/470, loss: 0.01853962056338787
2023-01-22 20:21:01.893053: step: 210/470, loss: 0.004126167390495539
2023-01-22 20:21:02.633431: step: 212/470, loss: 0.026516355574131012
2023-01-22 20:21:03.389289: step: 214/470, loss: 0.013195443898439407
2023-01-22 20:21:04.051924: step: 216/470, loss: 0.02729533053934574
2023-01-22 20:21:04.750192: step: 218/470, loss: 0.016501324251294136
2023-01-22 20:21:05.507739: step: 220/470, loss: 0.011663485318422318
2023-01-22 20:21:06.269085: step: 222/470, loss: 0.16120895743370056
2023-01-22 20:21:06.969196: step: 224/470, loss: 0.00041892650187946856
2023-01-22 20:21:07.710016: step: 226/470, loss: 0.032136738300323486
2023-01-22 20:21:08.467759: step: 228/470, loss: 0.023074127733707428
2023-01-22 20:21:09.178989: step: 230/470, loss: 0.02281912975013256
2023-01-22 20:21:09.934619: step: 232/470, loss: 0.012881905771791935
2023-01-22 20:21:10.679106: step: 234/470, loss: 0.01737522892653942
2023-01-22 20:21:11.442028: step: 236/470, loss: 0.32629257440567017
2023-01-22 20:21:12.183680: step: 238/470, loss: 0.015904588624835014
2023-01-22 20:21:12.985014: step: 240/470, loss: 0.007637233939021826
2023-01-22 20:21:13.636121: step: 242/470, loss: 0.030431710183620453
2023-01-22 20:21:14.352915: step: 244/470, loss: 0.028963802382349968
2023-01-22 20:21:15.109114: step: 246/470, loss: 0.0031187073327600956
2023-01-22 20:21:15.881655: step: 248/470, loss: 0.15134938061237335
2023-01-22 20:21:16.628470: step: 250/470, loss: 0.026609888300299644
2023-01-22 20:21:17.438182: step: 252/470, loss: 0.018683232367038727
2023-01-22 20:21:18.158199: step: 254/470, loss: 0.01902608573436737
2023-01-22 20:21:18.899268: step: 256/470, loss: 0.23490701615810394
2023-01-22 20:21:19.530275: step: 258/470, loss: 0.005870967172086239
2023-01-22 20:21:20.205449: step: 260/470, loss: 0.037582509219646454
2023-01-22 20:21:20.924242: step: 262/470, loss: 0.056500356644392014
2023-01-22 20:21:21.675691: step: 264/470, loss: 0.023657605051994324
2023-01-22 20:21:22.361074: step: 266/470, loss: 0.0007725696195848286
2023-01-22 20:21:23.041911: step: 268/470, loss: 0.08393879979848862
2023-01-22 20:21:23.755712: step: 270/470, loss: 0.02035318873822689
2023-01-22 20:21:24.403421: step: 272/470, loss: 0.003998577129095793
2023-01-22 20:21:25.146908: step: 274/470, loss: 0.008322400040924549
2023-01-22 20:21:25.827268: step: 276/470, loss: 0.0008807040867395699
2023-01-22 20:21:26.592270: step: 278/470, loss: 0.0010697413235902786
2023-01-22 20:21:27.274791: step: 280/470, loss: 0.00225759856402874
2023-01-22 20:21:28.018924: step: 282/470, loss: 0.014795668423175812
2023-01-22 20:21:28.805352: step: 284/470, loss: 0.029663510620594025
2023-01-22 20:21:29.534406: step: 286/470, loss: 0.05489639937877655
2023-01-22 20:21:30.323180: step: 288/470, loss: 0.025471646338701248
2023-01-22 20:21:31.113576: step: 290/470, loss: 0.015530110336840153
2023-01-22 20:21:32.022783: step: 292/470, loss: 0.011148087680339813
2023-01-22 20:21:32.817816: step: 294/470, loss: 0.023910433053970337
2023-01-22 20:21:33.568962: step: 296/470, loss: 0.013895057141780853
2023-01-22 20:21:34.200192: step: 298/470, loss: 0.0005625097546726465
2023-01-22 20:21:34.909710: step: 300/470, loss: 0.05426546931266785
2023-01-22 20:21:35.565319: step: 302/470, loss: 0.00862344354391098
2023-01-22 20:21:36.313401: step: 304/470, loss: 0.060839202255010605
2023-01-22 20:21:37.043557: step: 306/470, loss: 0.003655111650004983
2023-01-22 20:21:37.790511: step: 308/470, loss: 0.039200231432914734
2023-01-22 20:21:38.644234: step: 310/470, loss: 0.04813004285097122
2023-01-22 20:21:39.283319: step: 312/470, loss: 0.0009427457116544247
2023-01-22 20:21:40.030847: step: 314/470, loss: 0.004311168100684881
2023-01-22 20:21:40.798672: step: 316/470, loss: 0.06394602358341217
2023-01-22 20:21:41.475685: step: 318/470, loss: 0.003433618927374482
2023-01-22 20:21:42.219217: step: 320/470, loss: 0.021177219226956367
2023-01-22 20:21:42.942659: step: 322/470, loss: 0.001753106014803052
2023-01-22 20:21:43.677134: step: 324/470, loss: 0.08285431563854218
2023-01-22 20:21:44.470281: step: 326/470, loss: 0.09834257513284683
2023-01-22 20:21:45.233622: step: 328/470, loss: 0.07702438533306122
2023-01-22 20:21:45.941729: step: 330/470, loss: 0.01453570369631052
2023-01-22 20:21:46.679533: step: 332/470, loss: 0.03407316654920578
2023-01-22 20:21:47.390387: step: 334/470, loss: 0.0027093144599348307
2023-01-22 20:21:48.061664: step: 336/470, loss: 0.017348872497677803
2023-01-22 20:21:48.888380: step: 338/470, loss: 0.10025624930858612
2023-01-22 20:21:49.642943: step: 340/470, loss: 0.023405015468597412
2023-01-22 20:21:50.404947: step: 342/470, loss: 0.1289200335741043
2023-01-22 20:21:51.165429: step: 344/470, loss: 0.001318649505265057
2023-01-22 20:21:51.868923: step: 346/470, loss: 0.3252336084842682
2023-01-22 20:21:52.580228: step: 348/470, loss: 0.00015436287503689528
2023-01-22 20:21:53.326750: step: 350/470, loss: 0.12891341745853424
2023-01-22 20:21:54.114109: step: 352/470, loss: 0.012002014555037022
2023-01-22 20:21:54.804668: step: 354/470, loss: 0.008551257662475109
2023-01-22 20:21:55.525278: step: 356/470, loss: 0.007327394559979439
2023-01-22 20:21:56.281738: step: 358/470, loss: 0.007789163384586573
2023-01-22 20:21:57.038944: step: 360/470, loss: 0.4248470962047577
2023-01-22 20:21:57.901642: step: 362/470, loss: 0.011140398681163788
2023-01-22 20:21:58.621477: step: 364/470, loss: 0.0026315178256481886
2023-01-22 20:21:59.409483: step: 366/470, loss: 0.016022127121686935
2023-01-22 20:22:00.150831: step: 368/470, loss: 0.05837252363562584
2023-01-22 20:22:00.844395: step: 370/470, loss: 0.0032597638200968504
2023-01-22 20:22:01.614953: step: 372/470, loss: 0.056031063199043274
2023-01-22 20:22:02.375338: step: 374/470, loss: 0.006611979100853205
2023-01-22 20:22:03.150687: step: 376/470, loss: 0.05569504201412201
2023-01-22 20:22:03.850783: step: 378/470, loss: 0.08907879143953323
2023-01-22 20:22:04.671258: step: 380/470, loss: 0.014300604350864887
2023-01-22 20:22:05.300317: step: 382/470, loss: 0.006313091143965721
2023-01-22 20:22:06.174053: step: 384/470, loss: 0.027734091505408287
2023-01-22 20:22:06.998699: step: 386/470, loss: 0.041512493044137955
2023-01-22 20:22:07.693622: step: 388/470, loss: 0.02768852189183235
2023-01-22 20:22:08.482845: step: 390/470, loss: 0.035742416977882385
2023-01-22 20:22:09.263099: step: 392/470, loss: 0.08417049050331116
2023-01-22 20:22:10.000447: step: 394/470, loss: 0.056899912655353546
2023-01-22 20:22:10.730684: step: 396/470, loss: 0.01473038736730814
2023-01-22 20:22:11.534893: step: 398/470, loss: 0.04913134500384331
2023-01-22 20:22:12.210215: step: 400/470, loss: 0.026948675513267517
2023-01-22 20:22:12.997543: step: 402/470, loss: 0.06986348330974579
2023-01-22 20:22:13.757930: step: 404/470, loss: 0.004675567615777254
2023-01-22 20:22:14.389756: step: 406/470, loss: 0.0008290672558359802
2023-01-22 20:22:15.092594: step: 408/470, loss: 0.008351105265319347
2023-01-22 20:22:15.864909: step: 410/470, loss: 0.03763250261545181
2023-01-22 20:22:16.574887: step: 412/470, loss: 0.020851025357842445
2023-01-22 20:22:17.316004: step: 414/470, loss: 0.06433157622814178
2023-01-22 20:22:18.017333: step: 416/470, loss: 0.005936459172517061
2023-01-22 20:22:18.765428: step: 418/470, loss: 0.046613890677690506
2023-01-22 20:22:19.456904: step: 420/470, loss: 0.019648538902401924
2023-01-22 20:22:20.185958: step: 422/470, loss: 0.010377058759331703
2023-01-22 20:22:20.871046: step: 424/470, loss: 0.03797370567917824
2023-01-22 20:22:21.703918: step: 426/470, loss: 0.10179644823074341
2023-01-22 20:22:22.437846: step: 428/470, loss: 0.042833250015974045
2023-01-22 20:22:23.224822: step: 430/470, loss: 0.13208261132240295
2023-01-22 20:22:23.967476: step: 432/470, loss: 0.09129922091960907
2023-01-22 20:22:24.666473: step: 434/470, loss: 0.0105623509734869
2023-01-22 20:22:25.370860: step: 436/470, loss: 0.006014485843479633
2023-01-22 20:22:26.103533: step: 438/470, loss: 0.014641005545854568
2023-01-22 20:22:26.814743: step: 440/470, loss: 0.012232620269060135
2023-01-22 20:22:27.490555: step: 442/470, loss: 2.0588850020430982e-05
2023-01-22 20:22:28.179555: step: 444/470, loss: 0.01798243820667267
2023-01-22 20:22:28.942174: step: 446/470, loss: 0.010261360555887222
2023-01-22 20:22:29.628988: step: 448/470, loss: 0.032064393162727356
2023-01-22 20:22:30.309434: step: 450/470, loss: 0.002512154169380665
2023-01-22 20:22:31.000536: step: 452/470, loss: 0.016261639073491096
2023-01-22 20:22:31.768223: step: 454/470, loss: 0.05349350348114967
2023-01-22 20:22:32.455633: step: 456/470, loss: 0.07273565232753754
2023-01-22 20:22:33.142893: step: 458/470, loss: 0.014662419445812702
2023-01-22 20:22:33.871383: step: 460/470, loss: 0.04515858367085457
2023-01-22 20:22:34.576517: step: 462/470, loss: 0.0028082530479878187
2023-01-22 20:22:35.253722: step: 464/470, loss: 0.06509249657392502
2023-01-22 20:22:35.979731: step: 466/470, loss: 0.015094724483788013
2023-01-22 20:22:36.690705: step: 468/470, loss: 0.0066069429740309715
2023-01-22 20:22:37.453523: step: 470/470, loss: 0.09069467335939407
2023-01-22 20:22:38.131829: step: 472/470, loss: 0.001958508975803852
2023-01-22 20:22:38.872689: step: 474/470, loss: 0.004850469995290041
2023-01-22 20:22:39.598288: step: 476/470, loss: 0.0013880267506465316
2023-01-22 20:22:40.338317: step: 478/470, loss: 0.07323987036943436
2023-01-22 20:22:40.999745: step: 480/470, loss: 0.18070386350154877
2023-01-22 20:22:41.799083: step: 482/470, loss: 0.0033805707935243845
2023-01-22 20:22:42.510832: step: 484/470, loss: 0.024858374148607254
2023-01-22 20:22:43.139991: step: 486/470, loss: 0.0003526340296957642
2023-01-22 20:22:43.870194: step: 488/470, loss: 0.007729541510343552
2023-01-22 20:22:44.628185: step: 490/470, loss: 0.039696142077445984
2023-01-22 20:22:45.335380: step: 492/470, loss: 0.011434253305196762
2023-01-22 20:22:46.076169: step: 494/470, loss: 0.0433819405734539
2023-01-22 20:22:46.803879: step: 496/470, loss: 0.030899059027433395
2023-01-22 20:22:47.511288: step: 498/470, loss: 0.04821249470114708
2023-01-22 20:22:48.256505: step: 500/470, loss: 0.02131025679409504
2023-01-22 20:22:49.115221: step: 502/470, loss: 0.05077216029167175
2023-01-22 20:22:49.851781: step: 504/470, loss: 0.0022677837405353785
2023-01-22 20:22:50.711386: step: 506/470, loss: 0.026514790952205658
2023-01-22 20:22:51.607817: step: 508/470, loss: 0.043541330844163895
2023-01-22 20:22:52.332603: step: 510/470, loss: 0.010781260207295418
2023-01-22 20:22:53.126135: step: 512/470, loss: 0.02016189508140087
2023-01-22 20:22:53.859178: step: 514/470, loss: 0.043015431612730026
2023-01-22 20:22:54.627493: step: 516/470, loss: 0.018223173916339874
2023-01-22 20:22:55.384138: step: 518/470, loss: 0.01400044560432434
2023-01-22 20:22:56.116430: step: 520/470, loss: 0.11256732046604156
2023-01-22 20:22:56.907549: step: 522/470, loss: 0.06279245764017105
2023-01-22 20:22:57.662934: step: 524/470, loss: 0.03156261146068573
2023-01-22 20:22:58.396060: step: 526/470, loss: 0.47835269570350647
2023-01-22 20:22:59.255845: step: 528/470, loss: 0.00015236996114253998
2023-01-22 20:23:00.008067: step: 530/470, loss: 0.12638600170612335
2023-01-22 20:23:00.792175: step: 532/470, loss: 0.012023607268929482
2023-01-22 20:23:01.530185: step: 534/470, loss: 0.015657739713788033
2023-01-22 20:23:02.189231: step: 536/470, loss: 0.007505686488002539
2023-01-22 20:23:02.895309: step: 538/470, loss: 0.0051700943149626255
2023-01-22 20:23:03.697958: step: 540/470, loss: 0.009726532734930515
2023-01-22 20:23:04.492448: step: 542/470, loss: 0.04598125070333481
2023-01-22 20:23:05.220958: step: 544/470, loss: 0.006266491021960974
2023-01-22 20:23:05.901756: step: 546/470, loss: 0.008492393419146538
2023-01-22 20:23:06.547088: step: 548/470, loss: 0.001625984674319625
2023-01-22 20:23:07.322391: step: 550/470, loss: 0.044714074581861496
2023-01-22 20:23:08.016629: step: 552/470, loss: 0.13521620631217957
2023-01-22 20:23:08.673345: step: 554/470, loss: 0.0015927805798128247
2023-01-22 20:23:09.497643: step: 556/470, loss: 0.04356268420815468
2023-01-22 20:23:10.302205: step: 558/470, loss: 0.051665596663951874
2023-01-22 20:23:11.038768: step: 560/470, loss: 0.028444265946745872
2023-01-22 20:23:11.779037: step: 562/470, loss: 0.041954174637794495
2023-01-22 20:23:12.507502: step: 564/470, loss: 0.022699544206261635
2023-01-22 20:23:13.157242: step: 566/470, loss: 0.02368500828742981
2023-01-22 20:23:13.923937: step: 568/470, loss: 0.04992617666721344
2023-01-22 20:23:14.659315: step: 570/470, loss: 0.0033017806708812714
2023-01-22 20:23:15.316756: step: 572/470, loss: 0.005991379264742136
2023-01-22 20:23:16.030577: step: 574/470, loss: 0.3665614724159241
2023-01-22 20:23:16.778143: step: 576/470, loss: 0.01564880833029747
2023-01-22 20:23:17.577365: step: 578/470, loss: 0.04914989322423935
2023-01-22 20:23:18.302123: step: 580/470, loss: 0.007808396127074957
2023-01-22 20:23:19.067298: step: 582/470, loss: 0.13653407990932465
2023-01-22 20:23:19.770380: step: 584/470, loss: 0.0009268509456887841
2023-01-22 20:23:20.523646: step: 586/470, loss: 0.033205803483724594
2023-01-22 20:23:21.216585: step: 588/470, loss: 0.05496671423316002
2023-01-22 20:23:21.951905: step: 590/470, loss: 0.04230504482984543
2023-01-22 20:23:22.708974: step: 592/470, loss: 0.03090505301952362
2023-01-22 20:23:23.378888: step: 594/470, loss: 0.007094330154359341
2023-01-22 20:23:24.114461: step: 596/470, loss: 0.013848799280822277
2023-01-22 20:23:24.868350: step: 598/470, loss: 0.003194592660292983
2023-01-22 20:23:25.662332: step: 600/470, loss: 0.01055984664708376
2023-01-22 20:23:26.491808: step: 602/470, loss: 0.014651630073785782
2023-01-22 20:23:27.262037: step: 604/470, loss: 0.0857321172952652
2023-01-22 20:23:27.994465: step: 606/470, loss: 0.001349782571196556
2023-01-22 20:23:28.710812: step: 608/470, loss: 0.14607299864292145
2023-01-22 20:23:29.472218: step: 610/470, loss: 0.007140479516237974
2023-01-22 20:23:30.198208: step: 612/470, loss: 0.0029003897216171026
2023-01-22 20:23:30.869030: step: 614/470, loss: 0.008922108449041843
2023-01-22 20:23:31.634931: step: 616/470, loss: 0.009059912525117397
2023-01-22 20:23:32.359430: step: 618/470, loss: 0.03438716009259224
2023-01-22 20:23:33.077052: step: 620/470, loss: 0.039528436958789825
2023-01-22 20:23:33.744219: step: 622/470, loss: 0.1352343112230301
2023-01-22 20:23:34.496861: step: 624/470, loss: 0.06945229321718216
2023-01-22 20:23:35.269628: step: 626/470, loss: 0.001418177504092455
2023-01-22 20:23:35.951060: step: 628/470, loss: 0.030531620606780052
2023-01-22 20:23:36.692831: step: 630/470, loss: 0.00512252002954483
2023-01-22 20:23:37.438598: step: 632/470, loss: 0.07616572082042694
2023-01-22 20:23:38.130586: step: 634/470, loss: 0.004690864589065313
2023-01-22 20:23:38.781575: step: 636/470, loss: 0.6737900376319885
2023-01-22 20:23:39.559935: step: 638/470, loss: 0.02247127704322338
2023-01-22 20:23:40.357695: step: 640/470, loss: 0.04330654442310333
2023-01-22 20:23:41.096675: step: 642/470, loss: 0.02554977498948574
2023-01-22 20:23:41.833870: step: 644/470, loss: 0.05359509587287903
2023-01-22 20:23:42.552090: step: 646/470, loss: 0.04412570595741272
2023-01-22 20:23:43.299236: step: 648/470, loss: 0.03207087889313698
2023-01-22 20:23:44.052034: step: 650/470, loss: 0.03689567372202873
2023-01-22 20:23:44.726386: step: 652/470, loss: 0.01859690062701702
2023-01-22 20:23:45.459079: step: 654/470, loss: 0.026259824633598328
2023-01-22 20:23:46.170012: step: 656/470, loss: 0.0039988174103200436
2023-01-22 20:23:46.961975: step: 658/470, loss: 0.02299419976770878
2023-01-22 20:23:47.666275: step: 660/470, loss: 0.020622316747903824
2023-01-22 20:23:48.380311: step: 662/470, loss: 0.029058068990707397
2023-01-22 20:23:49.187943: step: 664/470, loss: 0.002780361333861947
2023-01-22 20:23:49.945584: step: 666/470, loss: 0.0022796066477894783
2023-01-22 20:23:50.655886: step: 668/470, loss: 0.03231862932443619
2023-01-22 20:23:51.423956: step: 670/470, loss: 0.05333375930786133
2023-01-22 20:23:52.223185: step: 672/470, loss: 0.006049145944416523
2023-01-22 20:23:52.934929: step: 674/470, loss: 0.011256158351898193
2023-01-22 20:23:53.608676: step: 676/470, loss: 0.008002914488315582
2023-01-22 20:23:54.367333: step: 678/470, loss: 0.022282328456640244
2023-01-22 20:23:55.014009: step: 680/470, loss: 0.001529976725578308
2023-01-22 20:23:55.731971: step: 682/470, loss: 0.4798831641674042
2023-01-22 20:23:56.505640: step: 684/470, loss: 0.012694069184362888
2023-01-22 20:23:57.313120: step: 686/470, loss: 0.2012556791305542
2023-01-22 20:23:58.001963: step: 688/470, loss: 0.3873967230319977
2023-01-22 20:23:58.825925: step: 690/470, loss: 0.0851685032248497
2023-01-22 20:23:59.596629: step: 692/470, loss: 0.11975271999835968
2023-01-22 20:24:00.320695: step: 694/470, loss: 0.009530964307487011
2023-01-22 20:24:01.011447: step: 696/470, loss: 0.046175580471754074
2023-01-22 20:24:01.723050: step: 698/470, loss: 1.4199903011322021
2023-01-22 20:24:02.447381: step: 700/470, loss: 0.004222056828439236
2023-01-22 20:24:03.123148: step: 702/470, loss: 0.004082622472196817
2023-01-22 20:24:03.894587: step: 704/470, loss: 0.04654672369360924
2023-01-22 20:24:04.627701: step: 706/470, loss: 0.11172907054424286
2023-01-22 20:24:05.387892: step: 708/470, loss: 0.0367024689912796
2023-01-22 20:24:06.094472: step: 710/470, loss: 8.773482841206715e-05
2023-01-22 20:24:06.849623: step: 712/470, loss: 0.01656370982527733
2023-01-22 20:24:07.547223: step: 714/470, loss: 0.012438789010047913
2023-01-22 20:24:08.254781: step: 716/470, loss: 0.009644479490816593
2023-01-22 20:24:08.937497: step: 718/470, loss: 0.013749388046562672
2023-01-22 20:24:09.652873: step: 720/470, loss: 0.023235702887177467
2023-01-22 20:24:10.412560: step: 722/470, loss: 0.07161347568035126
2023-01-22 20:24:11.228557: step: 724/470, loss: 0.043580781668424606
2023-01-22 20:24:11.981081: step: 726/470, loss: 0.05737774074077606
2023-01-22 20:24:12.701955: step: 728/470, loss: 0.0016026493394747376
2023-01-22 20:24:13.467466: step: 730/470, loss: 0.057738371193408966
2023-01-22 20:24:14.216982: step: 732/470, loss: 0.00018781011749524623
2023-01-22 20:24:15.075104: step: 734/470, loss: 0.03806695714592934
2023-01-22 20:24:15.775750: step: 736/470, loss: 0.06477882713079453
2023-01-22 20:24:16.499548: step: 738/470, loss: 0.0006179798510856926
2023-01-22 20:24:17.266783: step: 740/470, loss: 0.047551143914461136
2023-01-22 20:24:18.002333: step: 742/470, loss: 0.47022610902786255
2023-01-22 20:24:18.769769: step: 744/470, loss: 0.02439289726316929
2023-01-22 20:24:19.493750: step: 746/470, loss: 0.023850999772548676
2023-01-22 20:24:20.258935: step: 748/470, loss: 0.13051940500736237
2023-01-22 20:24:20.928864: step: 750/470, loss: 0.011319885030388832
2023-01-22 20:24:21.685591: step: 752/470, loss: 0.05051903426647186
2023-01-22 20:24:22.338863: step: 754/470, loss: 0.05477369949221611
2023-01-22 20:24:22.959733: step: 756/470, loss: 0.02628343366086483
2023-01-22 20:24:23.694850: step: 758/470, loss: 0.006637097802013159
2023-01-22 20:24:24.421167: step: 760/470, loss: 0.07080532610416412
2023-01-22 20:24:25.094262: step: 762/470, loss: 0.03669466823339462
2023-01-22 20:24:25.750973: step: 764/470, loss: 0.0033256318420171738
2023-01-22 20:24:26.410403: step: 766/470, loss: 0.11121101677417755
2023-01-22 20:24:27.114197: step: 768/470, loss: 0.006534420885145664
2023-01-22 20:24:27.844377: step: 770/470, loss: 0.03840123862028122
2023-01-22 20:24:28.578205: step: 772/470, loss: 0.015428757295012474
2023-01-22 20:24:29.303220: step: 774/470, loss: 0.30759334564208984
2023-01-22 20:24:30.118279: step: 776/470, loss: 0.013859348371624947
2023-01-22 20:24:30.757945: step: 778/470, loss: 0.02122689038515091
2023-01-22 20:24:31.528477: step: 780/470, loss: 0.03834621235728264
2023-01-22 20:24:32.229594: step: 782/470, loss: 0.5577226281166077
2023-01-22 20:24:32.918548: step: 784/470, loss: 0.01965031400322914
2023-01-22 20:24:33.698501: step: 786/470, loss: 0.016025938093662262
2023-01-22 20:24:34.455501: step: 788/470, loss: 0.017744455486536026
2023-01-22 20:24:35.185420: step: 790/470, loss: 0.006757447961717844
2023-01-22 20:24:35.933431: step: 792/470, loss: 0.07866999506950378
2023-01-22 20:24:36.798531: step: 794/470, loss: 0.006022907793521881
2023-01-22 20:24:37.545277: step: 796/470, loss: 0.0842958465218544
2023-01-22 20:24:38.235893: step: 798/470, loss: 0.00013147601566743106
2023-01-22 20:24:38.940900: step: 800/470, loss: 0.002207849407568574
2023-01-22 20:24:39.724620: step: 802/470, loss: 0.011025402694940567
2023-01-22 20:24:40.449216: step: 804/470, loss: 0.07100294530391693
2023-01-22 20:24:41.166428: step: 806/470, loss: 0.12755174934864044
2023-01-22 20:24:41.881602: step: 808/470, loss: 0.0014298518653959036
2023-01-22 20:24:42.611424: step: 810/470, loss: 0.07408328354358673
2023-01-22 20:24:43.267805: step: 812/470, loss: 0.0061090909875929356
2023-01-22 20:24:44.025227: step: 814/470, loss: 0.018763698637485504
2023-01-22 20:24:44.701071: step: 816/470, loss: 0.004722012206912041
2023-01-22 20:24:45.505039: step: 818/470, loss: 0.10819140076637268
2023-01-22 20:24:46.249236: step: 820/470, loss: 0.013299317099153996
2023-01-22 20:24:46.978352: step: 822/470, loss: 0.23392438888549805
2023-01-22 20:24:47.642403: step: 824/470, loss: 0.018688471987843513
2023-01-22 20:24:48.367431: step: 826/470, loss: 0.05231665074825287
2023-01-22 20:24:49.131329: step: 828/470, loss: 0.05416341871023178
2023-01-22 20:24:49.888154: step: 830/470, loss: 0.0048498413525521755
2023-01-22 20:24:50.577622: step: 832/470, loss: 0.056482456624507904
2023-01-22 20:24:51.344805: step: 834/470, loss: 0.06690236181020737
2023-01-22 20:24:52.003745: step: 836/470, loss: 0.04062666743993759
2023-01-22 20:24:52.681896: step: 838/470, loss: 0.04290313646197319
2023-01-22 20:24:53.403916: step: 840/470, loss: 0.06305599957704544
2023-01-22 20:24:54.148990: step: 842/470, loss: 9.941688537597656
2023-01-22 20:24:54.867237: step: 844/470, loss: 0.060064323246479034
2023-01-22 20:24:55.641935: step: 846/470, loss: 0.054962724447250366
2023-01-22 20:24:56.387158: step: 848/470, loss: 0.0005881677498109639
2023-01-22 20:24:57.169950: step: 850/470, loss: 0.016850154846906662
2023-01-22 20:24:57.883374: step: 852/470, loss: 0.04970991238951683
2023-01-22 20:24:58.726330: step: 854/470, loss: 0.22735270857810974
2023-01-22 20:24:59.476148: step: 856/470, loss: 0.021856531500816345
2023-01-22 20:25:00.133857: step: 858/470, loss: 0.06958413124084473
2023-01-22 20:25:00.834664: step: 860/470, loss: 0.010652045719325542
2023-01-22 20:25:01.612727: step: 862/470, loss: 0.0281230416148901
2023-01-22 20:25:02.345075: step: 864/470, loss: 0.0192283783107996
2023-01-22 20:25:03.009424: step: 866/470, loss: 0.014173178002238274
2023-01-22 20:25:03.744940: step: 868/470, loss: 0.02912173420190811
2023-01-22 20:25:04.465802: step: 870/470, loss: 0.011722569353878498
2023-01-22 20:25:05.228256: step: 872/470, loss: 0.04161560535430908
2023-01-22 20:25:05.965764: step: 874/470, loss: 0.19505290687084198
2023-01-22 20:25:06.635887: step: 876/470, loss: 0.03534523397684097
2023-01-22 20:25:07.315073: step: 878/470, loss: 0.05336989462375641
2023-01-22 20:25:07.966688: step: 880/470, loss: 0.0025530781131237745
2023-01-22 20:25:08.693322: step: 882/470, loss: 0.016439758241176605
2023-01-22 20:25:09.475403: step: 884/470, loss: 0.006466133054345846
2023-01-22 20:25:10.229454: step: 886/470, loss: 0.01774168759584427
2023-01-22 20:25:10.905388: step: 888/470, loss: 0.04091699793934822
2023-01-22 20:25:11.599308: step: 890/470, loss: 0.1776171773672104
2023-01-22 20:25:12.419971: step: 892/470, loss: 0.11639781296253204
2023-01-22 20:25:13.088543: step: 894/470, loss: 0.01566343568265438
2023-01-22 20:25:13.837595: step: 896/470, loss: 0.024013573303818703
2023-01-22 20:25:14.602303: step: 898/470, loss: 0.004490656778216362
2023-01-22 20:25:15.448700: step: 900/470, loss: 0.0408441387116909
2023-01-22 20:25:16.103492: step: 902/470, loss: 0.08740266412496567
2023-01-22 20:25:16.811506: step: 904/470, loss: 0.026669248938560486
2023-01-22 20:25:17.642141: step: 906/470, loss: 0.037839457392692566
2023-01-22 20:25:18.375881: step: 908/470, loss: 0.19800342619419098
2023-01-22 20:25:19.069251: step: 910/470, loss: 0.007794266100972891
2023-01-22 20:25:19.758622: step: 912/470, loss: 0.36751270294189453
2023-01-22 20:25:20.466120: step: 914/470, loss: 0.5664834976196289
2023-01-22 20:25:21.200288: step: 916/470, loss: 0.021370526403188705
2023-01-22 20:25:21.945171: step: 918/470, loss: 0.010546115227043629
2023-01-22 20:25:22.717826: step: 920/470, loss: 0.019952479749917984
2023-01-22 20:25:23.465213: step: 922/470, loss: 0.03363412991166115
2023-01-22 20:25:24.237938: step: 924/470, loss: 0.018996473401784897
2023-01-22 20:25:25.070387: step: 926/470, loss: 0.052708521485328674
2023-01-22 20:25:25.699486: step: 928/470, loss: 0.3829970955848694
2023-01-22 20:25:26.456818: step: 930/470, loss: 0.05672343447804451
2023-01-22 20:25:27.233190: step: 932/470, loss: 0.19621804356575012
2023-01-22 20:25:27.966386: step: 934/470, loss: 0.040584880858659744
2023-01-22 20:25:28.653592: step: 936/470, loss: 0.04768889769911766
2023-01-22 20:25:29.367666: step: 938/470, loss: 0.30375567078590393
2023-01-22 20:25:30.137845: step: 940/470, loss: 0.2606930136680603
2023-01-22 20:25:30.776231: step: 942/470, loss: 0.0006679189973510802
==================================================
Loss: 0.073
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3085748792270532, 'r': 0.32321315623023406, 'f1': 0.3157244362063639}, 'combined': 0.23263905825732079, 'epoch': 27}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33988454281387587, 'r': 0.35099615286740643, 'f1': 0.3453509924144775}, 'combined': 0.24054297979117836, 'epoch': 27}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30335597567927036, 'r': 0.3188979326875062, 'f1': 0.31093285943814203}, 'combined': 0.22910842274389412, 'epoch': 27}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34509521403698895, 'r': 0.3567089952786184, 'f1': 0.3508060095411471}, 'combined': 0.24434249420776416, 'epoch': 27}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28896710610520926, 'r': 0.3295431323894322, 'f1': 0.30792416803055106}, 'combined': 0.22689149223303762, 'epoch': 27}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3362186543844472, 'r': 0.3594953304572166, 'f1': 0.3474676056463804}, 'combined': 0.24201723776364806, 'epoch': 27}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24744897959183673, 'r': 0.3464285714285714, 'f1': 0.28869047619047616}, 'combined': 0.19246031746031744, 'epoch': 27}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 27}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4642857142857143, 'r': 0.33620689655172414, 'f1': 0.39}, 'combined': 0.26, 'epoch': 27}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 28
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 20:28:06.611413: step: 2/470, loss: 0.0020869718864560127
2023-01-22 20:28:07.490109: step: 4/470, loss: 0.0639810636639595
2023-01-22 20:28:08.299660: step: 6/470, loss: 0.009995676577091217
2023-01-22 20:28:08.982630: step: 8/470, loss: 0.009512209333479404
2023-01-22 20:28:09.766167: step: 10/470, loss: 0.006158136297017336
2023-01-22 20:28:10.451989: step: 12/470, loss: 0.007754956372082233
2023-01-22 20:28:11.104249: step: 14/470, loss: 0.0035998544190078974
2023-01-22 20:28:11.815648: step: 16/470, loss: 0.015439898706972599
2023-01-22 20:28:12.552140: step: 18/470, loss: 0.014050621539354324
2023-01-22 20:28:13.240051: step: 20/470, loss: 0.04366869106888771
2023-01-22 20:28:14.059365: step: 22/470, loss: 0.014802333898842335
2023-01-22 20:28:14.817268: step: 24/470, loss: 0.03355008736252785
2023-01-22 20:28:15.531564: step: 26/470, loss: 0.0021390863694250584
2023-01-22 20:28:16.196050: step: 28/470, loss: 0.017872659489512444
2023-01-22 20:28:16.956656: step: 30/470, loss: 0.0009868554770946503
2023-01-22 20:28:17.715524: step: 32/470, loss: 0.007105813827365637
2023-01-22 20:28:18.457805: step: 34/470, loss: 0.020172271877527237
2023-01-22 20:28:19.224982: step: 36/470, loss: 0.058939579874277115
2023-01-22 20:28:19.959632: step: 38/470, loss: 0.08055589348077774
2023-01-22 20:28:20.684204: step: 40/470, loss: 0.053452666848897934
2023-01-22 20:28:21.417122: step: 42/470, loss: 0.018411824479699135
2023-01-22 20:28:22.188658: step: 44/470, loss: 0.018836546689271927
2023-01-22 20:28:22.885769: step: 46/470, loss: 0.001567376428283751
2023-01-22 20:28:23.590656: step: 48/470, loss: 0.002337083453312516
2023-01-22 20:28:24.307959: step: 50/470, loss: 0.2951555848121643
2023-01-22 20:28:24.960043: step: 52/470, loss: 0.01612759754061699
2023-01-22 20:28:25.808388: step: 54/470, loss: 0.011461992748081684
2023-01-22 20:28:26.540268: step: 56/470, loss: 0.0009162522037513554
2023-01-22 20:28:27.217405: step: 58/470, loss: 0.017956262454390526
2023-01-22 20:28:27.977413: step: 60/470, loss: 0.167605459690094
2023-01-22 20:28:28.714682: step: 62/470, loss: 0.0007975992048159242
2023-01-22 20:28:29.432970: step: 64/470, loss: 0.00465493556112051
2023-01-22 20:28:30.111796: step: 66/470, loss: 0.0031678981613367796
2023-01-22 20:28:30.809046: step: 68/470, loss: 0.011101577430963516
2023-01-22 20:28:31.572554: step: 70/470, loss: 0.04563984274864197
2023-01-22 20:28:32.286491: step: 72/470, loss: 0.014584038406610489
2023-01-22 20:28:33.031976: step: 74/470, loss: 0.000692845496814698
2023-01-22 20:28:33.859669: step: 76/470, loss: 0.003819751553237438
2023-01-22 20:28:34.539466: step: 78/470, loss: 0.007177893538028002
2023-01-22 20:28:35.332133: step: 80/470, loss: 0.013194219209253788
2023-01-22 20:28:36.067160: step: 82/470, loss: 0.005768152419477701
2023-01-22 20:28:36.825986: step: 84/470, loss: 0.008911560289561749
2023-01-22 20:28:37.632435: step: 86/470, loss: 0.029109152033925056
2023-01-22 20:28:38.347048: step: 88/470, loss: 0.0036423057317733765
2023-01-22 20:28:39.068296: step: 90/470, loss: 0.01244268286973238
2023-01-22 20:28:39.755155: step: 92/470, loss: 0.03755531460046768
2023-01-22 20:28:40.467910: step: 94/470, loss: 0.007035805378109217
2023-01-22 20:28:41.209438: step: 96/470, loss: 0.0064859106205403805
2023-01-22 20:28:41.889390: step: 98/470, loss: 0.000647165987174958
2023-01-22 20:28:42.570539: step: 100/470, loss: 0.014123012311756611
2023-01-22 20:28:43.299480: step: 102/470, loss: 0.0009315513307228684
2023-01-22 20:28:43.961593: step: 104/470, loss: 0.03605140745639801
2023-01-22 20:28:44.702482: step: 106/470, loss: 0.08731332421302795
2023-01-22 20:28:45.430112: step: 108/470, loss: 0.008800004608929157
2023-01-22 20:28:46.139365: step: 110/470, loss: 0.029222659766674042
2023-01-22 20:28:46.908584: step: 112/470, loss: 0.03977571055293083
2023-01-22 20:28:47.654206: step: 114/470, loss: 0.00808743480592966
2023-01-22 20:28:48.424263: step: 116/470, loss: 0.030444975942373276
2023-01-22 20:28:49.178460: step: 118/470, loss: 0.0036042286083102226
2023-01-22 20:28:49.834223: step: 120/470, loss: 0.001594691420905292
2023-01-22 20:28:50.565241: step: 122/470, loss: 0.034792497754096985
2023-01-22 20:28:51.311232: step: 124/470, loss: 0.003342484124004841
2023-01-22 20:28:52.000580: step: 126/470, loss: 0.003620708826929331
2023-01-22 20:28:52.705854: step: 128/470, loss: 0.058778248727321625
2023-01-22 20:28:53.371784: step: 130/470, loss: 0.09761997312307358
2023-01-22 20:28:54.100874: step: 132/470, loss: 0.042754001915454865
2023-01-22 20:28:54.763690: step: 134/470, loss: 0.018591521307826042
2023-01-22 20:28:55.507482: step: 136/470, loss: 0.02833203226327896
2023-01-22 20:28:56.267172: step: 138/470, loss: 0.06880441308021545
2023-01-22 20:28:56.979496: step: 140/470, loss: 0.03585517033934593
2023-01-22 20:28:57.773961: step: 142/470, loss: 0.004842748399823904
2023-01-22 20:28:58.460218: step: 144/470, loss: 0.012239599600434303
2023-01-22 20:28:59.256441: step: 146/470, loss: 0.0006771074840798974
2023-01-22 20:29:00.007971: step: 148/470, loss: 0.005776724312454462
2023-01-22 20:29:00.741874: step: 150/470, loss: 0.0004973204340785742
2023-01-22 20:29:01.405157: step: 152/470, loss: 0.06911028921604156
2023-01-22 20:29:02.211122: step: 154/470, loss: 0.010073547251522541
2023-01-22 20:29:02.936884: step: 156/470, loss: 0.0016500890487805009
2023-01-22 20:29:03.622606: step: 158/470, loss: 0.07199298590421677
2023-01-22 20:29:04.323324: step: 160/470, loss: 0.0059176781214773655
2023-01-22 20:29:05.029923: step: 162/470, loss: 0.006079540122300386
2023-01-22 20:29:05.752861: step: 164/470, loss: 0.16469572484493256
2023-01-22 20:29:06.519751: step: 166/470, loss: 0.08042943477630615
2023-01-22 20:29:07.199838: step: 168/470, loss: 0.07466889917850494
2023-01-22 20:29:07.928427: step: 170/470, loss: 0.02825554646551609
2023-01-22 20:29:08.633024: step: 172/470, loss: 0.07861734926700592
2023-01-22 20:29:09.379604: step: 174/470, loss: 0.012655568309128284
2023-01-22 20:29:10.099091: step: 176/470, loss: 0.4837439954280853
2023-01-22 20:29:10.851749: step: 178/470, loss: 0.015461144037544727
2023-01-22 20:29:11.596888: step: 180/470, loss: 0.04108460992574692
2023-01-22 20:29:12.343742: step: 182/470, loss: 0.0002883071720134467
2023-01-22 20:29:12.983275: step: 184/470, loss: 0.0014073270140215755
2023-01-22 20:29:13.753014: step: 186/470, loss: 0.0024875374510884285
2023-01-22 20:29:14.505310: step: 188/470, loss: 0.08386242389678955
2023-01-22 20:29:15.184995: step: 190/470, loss: 0.004048591013997793
2023-01-22 20:29:15.826217: step: 192/470, loss: 0.0006271903403103352
2023-01-22 20:29:16.627895: step: 194/470, loss: 0.003816502168774605
2023-01-22 20:29:17.395203: step: 196/470, loss: 0.04496389627456665
2023-01-22 20:29:18.148255: step: 198/470, loss: 0.06660241633653641
2023-01-22 20:29:18.899516: step: 200/470, loss: 0.011314080096781254
2023-01-22 20:29:19.712814: step: 202/470, loss: 0.010811764746904373
2023-01-22 20:29:20.408147: step: 204/470, loss: 0.001625021337531507
2023-01-22 20:29:21.107840: step: 206/470, loss: 0.07973671704530716
2023-01-22 20:29:21.902803: step: 208/470, loss: 0.016757629811763763
2023-01-22 20:29:22.609886: step: 210/470, loss: 0.014848452992737293
2023-01-22 20:29:23.368883: step: 212/470, loss: 0.02553386054933071
2023-01-22 20:29:24.051486: step: 214/470, loss: 0.06657985597848892
2023-01-22 20:29:24.839258: step: 216/470, loss: 0.00882027018815279
2023-01-22 20:29:25.592598: step: 218/470, loss: 0.015855491161346436
2023-01-22 20:29:26.330659: step: 220/470, loss: 0.023395488038659096
2023-01-22 20:29:27.020683: step: 222/470, loss: 0.08313391357660294
2023-01-22 20:29:27.729660: step: 224/470, loss: 0.002644822234287858
2023-01-22 20:29:28.416418: step: 226/470, loss: 0.4776703119277954
2023-01-22 20:29:29.162956: step: 228/470, loss: 0.033827830106019974
2023-01-22 20:29:29.907852: step: 230/470, loss: 0.002036722842603922
2023-01-22 20:29:30.658130: step: 232/470, loss: 0.07246463000774384
2023-01-22 20:29:31.478371: step: 234/470, loss: 2.729046583175659
2023-01-22 20:29:32.242267: step: 236/470, loss: 0.0005667444784194231
2023-01-22 20:29:32.980095: step: 238/470, loss: 0.010163289494812489
2023-01-22 20:29:33.703902: step: 240/470, loss: 0.040548261255025864
2023-01-22 20:29:34.453833: step: 242/470, loss: 0.07027406245470047
2023-01-22 20:29:35.260987: step: 244/470, loss: 0.045413631945848465
2023-01-22 20:29:35.971063: step: 246/470, loss: 0.018411103636026382
2023-01-22 20:29:36.621455: step: 248/470, loss: 0.0008637277642264962
2023-01-22 20:29:37.364229: step: 250/470, loss: 0.02072082832455635
2023-01-22 20:29:38.122295: step: 252/470, loss: 0.03055809810757637
2023-01-22 20:29:38.847659: step: 254/470, loss: 0.015467851422727108
2023-01-22 20:29:39.576497: step: 256/470, loss: 0.003622818971052766
2023-01-22 20:29:40.350225: step: 258/470, loss: 0.007900088094174862
2023-01-22 20:29:41.030811: step: 260/470, loss: 0.0008739789482206106
2023-01-22 20:29:41.704367: step: 262/470, loss: 0.07829133421182632
2023-01-22 20:29:42.440514: step: 264/470, loss: 0.013694636523723602
2023-01-22 20:29:43.120908: step: 266/470, loss: 0.15331532061100006
2023-01-22 20:29:43.824457: step: 268/470, loss: 0.008623996749520302
2023-01-22 20:29:44.502813: step: 270/470, loss: 0.014343681745231152
2023-01-22 20:29:45.273283: step: 272/470, loss: 0.00040280522080138326
2023-01-22 20:29:45.968448: step: 274/470, loss: 0.09008922427892685
2023-01-22 20:29:46.705414: step: 276/470, loss: 0.016768047586083412
2023-01-22 20:29:47.488602: step: 278/470, loss: 0.00032845677924342453
2023-01-22 20:29:48.293653: step: 280/470, loss: 0.02407873421907425
2023-01-22 20:29:49.068500: step: 282/470, loss: 0.07986540347337723
2023-01-22 20:29:49.783783: step: 284/470, loss: 0.03831029310822487
2023-01-22 20:29:50.465367: step: 286/470, loss: 0.00768911000341177
2023-01-22 20:29:51.164387: step: 288/470, loss: 0.14820675551891327
2023-01-22 20:29:51.866506: step: 290/470, loss: 0.06754887849092484
2023-01-22 20:29:52.640347: step: 292/470, loss: 0.03733934462070465
2023-01-22 20:29:53.357747: step: 294/470, loss: 0.03799036517739296
2023-01-22 20:29:54.057629: step: 296/470, loss: 0.002790941623970866
2023-01-22 20:29:54.871684: step: 298/470, loss: 0.010808521881699562
2023-01-22 20:29:55.617533: step: 300/470, loss: 0.010266797617077827
2023-01-22 20:29:56.299459: step: 302/470, loss: 0.0021426889579743147
2023-01-22 20:29:57.052496: step: 304/470, loss: 0.006693427916616201
2023-01-22 20:29:57.807743: step: 306/470, loss: 0.012375026941299438
2023-01-22 20:29:58.596520: step: 308/470, loss: 0.0827789232134819
2023-01-22 20:29:59.274591: step: 310/470, loss: 0.07285638898611069
2023-01-22 20:30:00.055574: step: 312/470, loss: 0.0009760952088981867
2023-01-22 20:30:00.770394: step: 314/470, loss: 0.006536416243761778
2023-01-22 20:30:01.625433: step: 316/470, loss: 0.2650093734264374
2023-01-22 20:30:02.339138: step: 318/470, loss: 0.02324749529361725
2023-01-22 20:30:03.124407: step: 320/470, loss: 0.007267648819833994
2023-01-22 20:30:03.836253: step: 322/470, loss: 0.02628829888999462
2023-01-22 20:30:04.539418: step: 324/470, loss: 0.023430757224559784
2023-01-22 20:30:05.261061: step: 326/470, loss: 0.019561942666769028
2023-01-22 20:30:05.968560: step: 328/470, loss: 0.0054289596155285835
2023-01-22 20:30:06.684758: step: 330/470, loss: 0.015765221789479256
2023-01-22 20:30:07.422953: step: 332/470, loss: 0.18133984506130219
2023-01-22 20:30:08.108457: step: 334/470, loss: 0.018263421952724457
2023-01-22 20:30:08.802624: step: 336/470, loss: 0.060671113431453705
2023-01-22 20:30:09.563208: step: 338/470, loss: 0.07180456817150116
2023-01-22 20:30:10.327997: step: 340/470, loss: 0.005747984629124403
2023-01-22 20:30:11.095582: step: 342/470, loss: 0.29718539118766785
2023-01-22 20:30:11.855430: step: 344/470, loss: 0.0482538603246212
2023-01-22 20:30:12.625670: step: 346/470, loss: 0.05792737379670143
2023-01-22 20:30:13.384709: step: 348/470, loss: 0.12915441393852234
2023-01-22 20:30:14.054213: step: 350/470, loss: 0.017134780064225197
2023-01-22 20:30:14.729021: step: 352/470, loss: 0.037275586277246475
2023-01-22 20:30:15.516826: step: 354/470, loss: 0.010397748090326786
2023-01-22 20:30:16.232237: step: 356/470, loss: 0.008629174903035164
2023-01-22 20:30:16.871026: step: 358/470, loss: 0.001150502823293209
2023-01-22 20:30:17.708573: step: 360/470, loss: 0.03983455151319504
2023-01-22 20:30:18.523051: step: 362/470, loss: 0.18434298038482666
2023-01-22 20:30:19.244700: step: 364/470, loss: 0.009704058058559895
2023-01-22 20:30:19.988502: step: 366/470, loss: 0.04657233878970146
2023-01-22 20:30:20.688436: step: 368/470, loss: 14.60478687286377
2023-01-22 20:30:21.424550: step: 370/470, loss: 0.02620551362633705
2023-01-22 20:30:22.125342: step: 372/470, loss: 0.0038664399180561304
2023-01-22 20:30:22.855705: step: 374/470, loss: 0.005592767149209976
2023-01-22 20:30:23.670546: step: 376/470, loss: 0.0027753994800150394
2023-01-22 20:30:24.364691: step: 378/470, loss: 0.017724450677633286
2023-01-22 20:30:25.154257: step: 380/470, loss: 0.015447490848600864
2023-01-22 20:30:26.014086: step: 382/470, loss: 0.03897276520729065
2023-01-22 20:30:26.722501: step: 384/470, loss: 0.0031961435452103615
2023-01-22 20:30:27.430884: step: 386/470, loss: 0.022479455918073654
2023-01-22 20:30:28.148698: step: 388/470, loss: 0.03246815502643585
2023-01-22 20:30:28.885669: step: 390/470, loss: 0.011416290886700153
2023-01-22 20:30:29.625894: step: 392/470, loss: 0.0019335534889250994
2023-01-22 20:30:30.282469: step: 394/470, loss: 0.016625449061393738
2023-01-22 20:30:30.924189: step: 396/470, loss: 0.0012744449777528644
2023-01-22 20:30:31.623736: step: 398/470, loss: 0.02477888949215412
2023-01-22 20:30:32.407282: step: 400/470, loss: 0.2593715786933899
2023-01-22 20:30:33.177355: step: 402/470, loss: 0.019976742565631866
2023-01-22 20:30:33.895755: step: 404/470, loss: 0.07440569996833801
2023-01-22 20:30:34.647382: step: 406/470, loss: 0.06923633068799973
2023-01-22 20:30:35.381981: step: 408/470, loss: 0.0011120573617517948
2023-01-22 20:30:36.077272: step: 410/470, loss: 0.003188740462064743
2023-01-22 20:30:36.808418: step: 412/470, loss: 0.4376097023487091
2023-01-22 20:30:37.506923: step: 414/470, loss: 0.0028341033030301332
2023-01-22 20:30:38.228757: step: 416/470, loss: 0.0008696450968272984
2023-01-22 20:30:38.932492: step: 418/470, loss: 0.008818319998681545
2023-01-22 20:30:39.706616: step: 420/470, loss: 0.0027629744727164507
2023-01-22 20:30:40.401020: step: 422/470, loss: 0.0039850943721830845
2023-01-22 20:30:41.190684: step: 424/470, loss: 0.035751424729824066
2023-01-22 20:30:41.916779: step: 426/470, loss: 0.020366976037621498
2023-01-22 20:30:42.720687: step: 428/470, loss: 0.2410111129283905
2023-01-22 20:30:43.466135: step: 430/470, loss: 0.005729255266487598
2023-01-22 20:30:44.207248: step: 432/470, loss: 0.010410521179437637
2023-01-22 20:30:44.939045: step: 434/470, loss: 0.06469309329986572
2023-01-22 20:30:45.789859: step: 436/470, loss: 0.04472040757536888
2023-01-22 20:30:46.492456: step: 438/470, loss: 0.023935789242386818
2023-01-22 20:30:47.480751: step: 440/470, loss: 0.041207972913980484
2023-01-22 20:30:48.166502: step: 442/470, loss: 0.018505996093153954
2023-01-22 20:30:48.955198: step: 444/470, loss: 0.025313975289463997
2023-01-22 20:30:49.639829: step: 446/470, loss: 0.013848811388015747
2023-01-22 20:30:50.361556: step: 448/470, loss: 0.00033676475868560374
2023-01-22 20:30:51.109923: step: 450/470, loss: 0.012692051008343697
2023-01-22 20:30:51.833971: step: 452/470, loss: 0.01313791237771511
2023-01-22 20:30:52.482806: step: 454/470, loss: 0.0016963921952992678
2023-01-22 20:30:53.196243: step: 456/470, loss: 0.5339106917381287
2023-01-22 20:30:53.955605: step: 458/470, loss: 0.055918145924806595
2023-01-22 20:30:54.603879: step: 460/470, loss: 0.00320792431011796
2023-01-22 20:30:55.394727: step: 462/470, loss: 0.0457182303071022
2023-01-22 20:30:56.208092: step: 464/470, loss: 0.01659577526152134
2023-01-22 20:30:57.038944: step: 466/470, loss: 0.03423323854804039
2023-01-22 20:30:57.879438: step: 468/470, loss: 0.009822395630180836
2023-01-22 20:30:58.556794: step: 470/470, loss: 0.0007459279731847346
2023-01-22 20:30:59.315115: step: 472/470, loss: 0.009417381137609482
2023-01-22 20:31:00.023923: step: 474/470, loss: 0.015447549521923065
2023-01-22 20:31:00.806056: step: 476/470, loss: 0.004266915377229452
2023-01-22 20:31:01.577226: step: 478/470, loss: 0.0016163645777851343
2023-01-22 20:31:02.320558: step: 480/470, loss: 0.007870226167142391
2023-01-22 20:31:03.015138: step: 482/470, loss: 0.04453890770673752
2023-01-22 20:31:03.782010: step: 484/470, loss: 0.08574463427066803
2023-01-22 20:31:04.511608: step: 486/470, loss: 0.0023265713825821877
2023-01-22 20:31:05.292270: step: 488/470, loss: 0.0027136588469147682
2023-01-22 20:31:06.006043: step: 490/470, loss: 0.056579723954200745
2023-01-22 20:31:06.764461: step: 492/470, loss: 0.049596644937992096
2023-01-22 20:31:07.372569: step: 494/470, loss: 0.009921560995280743
2023-01-22 20:31:08.060104: step: 496/470, loss: 0.011929440312087536
2023-01-22 20:31:08.895713: step: 498/470, loss: 0.05545575171709061
2023-01-22 20:31:09.700590: step: 500/470, loss: 0.041103947907686234
2023-01-22 20:31:10.593457: step: 502/470, loss: 0.05899772793054581
2023-01-22 20:31:11.330243: step: 504/470, loss: 0.02625754103064537
2023-01-22 20:31:12.044463: step: 506/470, loss: 1.3242918252944946
2023-01-22 20:31:12.738168: step: 508/470, loss: 0.011036560870707035
2023-01-22 20:31:13.471132: step: 510/470, loss: 0.002730847103521228
2023-01-22 20:31:14.125407: step: 512/470, loss: 0.04828563705086708
2023-01-22 20:31:14.886722: step: 514/470, loss: 0.011057223193347454
2023-01-22 20:31:15.631331: step: 516/470, loss: 0.024130506440997124
2023-01-22 20:31:16.319439: step: 518/470, loss: 0.009844631887972355
2023-01-22 20:31:17.073936: step: 520/470, loss: 0.09269572049379349
2023-01-22 20:31:17.804388: step: 522/470, loss: 0.010625121183693409
2023-01-22 20:31:18.626225: step: 524/470, loss: 0.09826123714447021
2023-01-22 20:31:19.376680: step: 526/470, loss: 0.07059445977210999
2023-01-22 20:31:20.197393: step: 528/470, loss: 0.21039122343063354
2023-01-22 20:31:20.900121: step: 530/470, loss: 0.004249433521181345
2023-01-22 20:31:21.703501: step: 532/470, loss: 0.6244630813598633
2023-01-22 20:31:22.412072: step: 534/470, loss: 0.10188359767198563
2023-01-22 20:31:23.160374: step: 536/470, loss: 0.0008839786169119179
2023-01-22 20:31:23.936310: step: 538/470, loss: 0.009506146423518658
2023-01-22 20:31:24.603041: step: 540/470, loss: 0.026201093569397926
2023-01-22 20:31:25.377239: step: 542/470, loss: 0.02899881824851036
2023-01-22 20:31:26.075370: step: 544/470, loss: 0.01946968585252762
2023-01-22 20:31:26.712686: step: 546/470, loss: 0.002837974112480879
2023-01-22 20:31:27.379952: step: 548/470, loss: 0.006309479475021362
2023-01-22 20:31:28.129345: step: 550/470, loss: 0.025487856939435005
2023-01-22 20:31:28.859813: step: 552/470, loss: 0.044974181801080704
2023-01-22 20:31:29.709151: step: 554/470, loss: 0.08220124244689941
2023-01-22 20:31:30.548525: step: 556/470, loss: 0.023944033309817314
2023-01-22 20:31:31.294903: step: 558/470, loss: 0.06157348304986954
2023-01-22 20:31:31.999834: step: 560/470, loss: 0.03174411877989769
2023-01-22 20:31:32.724684: step: 562/470, loss: 0.001561825512908399
2023-01-22 20:31:33.472454: step: 564/470, loss: 0.004232198931276798
2023-01-22 20:31:34.316716: step: 566/470, loss: 0.012148827314376831
2023-01-22 20:31:35.012571: step: 568/470, loss: 0.012420494109392166
2023-01-22 20:31:35.752079: step: 570/470, loss: 0.03385348618030548
2023-01-22 20:31:36.451521: step: 572/470, loss: 0.11622752249240875
2023-01-22 20:31:37.206000: step: 574/470, loss: 0.023387907072901726
2023-01-22 20:31:37.907022: step: 576/470, loss: 0.011087493039667606
2023-01-22 20:31:38.663929: step: 578/470, loss: 0.026949353516101837
2023-01-22 20:31:39.364447: step: 580/470, loss: 0.007216866593807936
2023-01-22 20:31:40.080812: step: 582/470, loss: 0.5527914762496948
2023-01-22 20:31:40.810015: step: 584/470, loss: 0.5917420387268066
2023-01-22 20:31:41.574495: step: 586/470, loss: 0.08542931079864502
2023-01-22 20:31:42.347220: step: 588/470, loss: 0.10411461442708969
2023-01-22 20:31:43.098509: step: 590/470, loss: 0.003107214579358697
2023-01-22 20:31:43.888564: step: 592/470, loss: 0.034524258226156235
2023-01-22 20:31:44.697236: step: 594/470, loss: 0.028853056952357292
2023-01-22 20:31:45.380471: step: 596/470, loss: 0.05348816141486168
2023-01-22 20:31:46.107274: step: 598/470, loss: 0.041593506932258606
2023-01-22 20:31:46.877218: step: 600/470, loss: 0.0063796937465667725
2023-01-22 20:31:47.630950: step: 602/470, loss: 0.016017813235521317
2023-01-22 20:31:48.360476: step: 604/470, loss: 0.062454525381326675
2023-01-22 20:31:49.093821: step: 606/470, loss: 0.19269520044326782
2023-01-22 20:31:49.773003: step: 608/470, loss: 0.014841437339782715
2023-01-22 20:31:50.606326: step: 610/470, loss: 2.196732759475708
2023-01-22 20:31:51.351487: step: 612/470, loss: 0.011269205249845982
2023-01-22 20:31:52.049976: step: 614/470, loss: 0.000654394447337836
2023-01-22 20:31:52.756797: step: 616/470, loss: 0.0068985833786427975
2023-01-22 20:31:53.500699: step: 618/470, loss: 0.009661390446126461
2023-01-22 20:31:54.168150: step: 620/470, loss: 0.009938615374267101
2023-01-22 20:31:54.941332: step: 622/470, loss: 0.28914228081703186
2023-01-22 20:31:55.727748: step: 624/470, loss: 0.057103097438812256
2023-01-22 20:31:56.614312: step: 626/470, loss: 0.0777493342757225
2023-01-22 20:31:57.331355: step: 628/470, loss: 0.0037567424587905407
2023-01-22 20:31:58.037797: step: 630/470, loss: 0.044795405119657516
2023-01-22 20:31:58.806894: step: 632/470, loss: 0.05516333505511284
2023-01-22 20:31:59.476479: step: 634/470, loss: 0.0026756152510643005
2023-01-22 20:32:00.195203: step: 636/470, loss: 0.049536339938640594
2023-01-22 20:32:00.940509: step: 638/470, loss: 0.020610058680176735
2023-01-22 20:32:01.708812: step: 640/470, loss: 0.0036903752479702234
2023-01-22 20:32:02.442931: step: 642/470, loss: 0.019514787942171097
2023-01-22 20:32:03.180453: step: 644/470, loss: 0.0012103342451155186
2023-01-22 20:32:03.933798: step: 646/470, loss: 0.043970245867967606
2023-01-22 20:32:04.647138: step: 648/470, loss: 0.3032195270061493
2023-01-22 20:32:05.362725: step: 650/470, loss: 0.05885202810168266
2023-01-22 20:32:06.129784: step: 652/470, loss: 0.06101761758327484
2023-01-22 20:32:06.814507: step: 654/470, loss: 0.017636749893426895
2023-01-22 20:32:07.501654: step: 656/470, loss: 0.09666401892900467
2023-01-22 20:32:08.247977: step: 658/470, loss: 0.006696424447000027
2023-01-22 20:32:08.992748: step: 660/470, loss: 0.012530512176454067
2023-01-22 20:32:09.758786: step: 662/470, loss: 0.03560841828584671
2023-01-22 20:32:10.517608: step: 664/470, loss: 0.12582863867282867
2023-01-22 20:32:11.150526: step: 666/470, loss: 0.039586570113897324
2023-01-22 20:32:11.734555: step: 668/470, loss: 0.0001087912532966584
2023-01-22 20:32:12.595062: step: 670/470, loss: 0.027073320001363754
2023-01-22 20:32:13.335930: step: 672/470, loss: 0.004335601814091206
2023-01-22 20:32:14.016334: step: 674/470, loss: 0.03368784487247467
2023-01-22 20:32:14.727874: step: 676/470, loss: 0.03928745165467262
2023-01-22 20:32:15.539850: step: 678/470, loss: 0.0066179316490888596
2023-01-22 20:32:16.295418: step: 680/470, loss: 0.03221479430794716
2023-01-22 20:32:17.099417: step: 682/470, loss: 0.08291277289390564
2023-01-22 20:32:17.829591: step: 684/470, loss: 0.023358231410384178
2023-01-22 20:32:18.586468: step: 686/470, loss: 0.052179984748363495
2023-01-22 20:32:19.326678: step: 688/470, loss: 0.012996486388146877
2023-01-22 20:32:20.079460: step: 690/470, loss: 0.2901443541049957
2023-01-22 20:32:20.836145: step: 692/470, loss: 0.15641692280769348
2023-01-22 20:32:21.595946: step: 694/470, loss: 0.03846118599176407
2023-01-22 20:32:22.386270: step: 696/470, loss: 0.008250097744166851
2023-01-22 20:32:23.143507: step: 698/470, loss: 0.1495591700077057
2023-01-22 20:32:23.932289: step: 700/470, loss: 0.05644164979457855
2023-01-22 20:32:24.594490: step: 702/470, loss: 0.0023439424112439156
2023-01-22 20:32:25.311625: step: 704/470, loss: 0.03498091921210289
2023-01-22 20:32:25.984413: step: 706/470, loss: 0.00011742630158551037
2023-01-22 20:32:26.685214: step: 708/470, loss: 0.011936147697269917
2023-01-22 20:32:27.389271: step: 710/470, loss: 0.013959010131657124
2023-01-22 20:32:28.078675: step: 712/470, loss: 0.003490228671580553
2023-01-22 20:32:28.818169: step: 714/470, loss: 0.03471314162015915
2023-01-22 20:32:29.616150: step: 716/470, loss: 0.04512022063136101
2023-01-22 20:32:30.291998: step: 718/470, loss: 0.013724502176046371
2023-01-22 20:32:30.960732: step: 720/470, loss: 0.04511544108390808
2023-01-22 20:32:31.670769: step: 722/470, loss: 0.04014601930975914
2023-01-22 20:32:32.466699: step: 724/470, loss: 0.0754375234246254
2023-01-22 20:32:33.364162: step: 726/470, loss: 0.06476394087076187
2023-01-22 20:32:34.029151: step: 728/470, loss: 0.027749724686145782
2023-01-22 20:32:34.759115: step: 730/470, loss: 0.259750634431839
2023-01-22 20:32:35.459832: step: 732/470, loss: 0.00022448692470788956
2023-01-22 20:32:36.193385: step: 734/470, loss: 0.057673707604408264
2023-01-22 20:32:36.899665: step: 736/470, loss: 0.012090279720723629
2023-01-22 20:32:37.652931: step: 738/470, loss: 0.0011684439377859235
2023-01-22 20:32:38.369212: step: 740/470, loss: 0.013645489700138569
2023-01-22 20:32:39.100652: step: 742/470, loss: 0.02157679945230484
2023-01-22 20:32:39.828362: step: 744/470, loss: 0.016018304973840714
2023-01-22 20:32:40.506136: step: 746/470, loss: 0.007724686060100794
2023-01-22 20:32:41.203610: step: 748/470, loss: 0.038802552968263626
2023-01-22 20:32:41.967443: step: 750/470, loss: 0.005301786120980978
2023-01-22 20:32:42.687506: step: 752/470, loss: 0.02522115781903267
2023-01-22 20:32:43.441698: step: 754/470, loss: 0.020645877346396446
2023-01-22 20:32:44.114569: step: 756/470, loss: 0.00777442567050457
2023-01-22 20:32:44.928098: step: 758/470, loss: 0.001848795684054494
2023-01-22 20:32:45.725216: step: 760/470, loss: 0.03325757756829262
2023-01-22 20:32:46.395827: step: 762/470, loss: 0.029930531978607178
2023-01-22 20:32:47.074295: step: 764/470, loss: 0.06273278594017029
2023-01-22 20:32:47.855196: step: 766/470, loss: 0.05899015814065933
2023-01-22 20:32:48.686105: step: 768/470, loss: 0.2313128113746643
2023-01-22 20:32:49.512763: step: 770/470, loss: 0.043592121452093124
2023-01-22 20:32:50.184990: step: 772/470, loss: 0.0039254468865692616
2023-01-22 20:32:50.968018: step: 774/470, loss: 1.0532337427139282
2023-01-22 20:32:51.727519: step: 776/470, loss: 0.0696612298488617
2023-01-22 20:32:52.446000: step: 778/470, loss: 0.05012049153447151
2023-01-22 20:32:53.212450: step: 780/470, loss: 0.029199251905083656
2023-01-22 20:32:53.946600: step: 782/470, loss: 0.6384598016738892
2023-01-22 20:32:54.637072: step: 784/470, loss: 0.05911829322576523
2023-01-22 20:32:55.365680: step: 786/470, loss: 0.010864563286304474
2023-01-22 20:32:56.017115: step: 788/470, loss: 0.005859819240868092
2023-01-22 20:32:56.811304: step: 790/470, loss: 0.020966263487935066
2023-01-22 20:32:57.585933: step: 792/470, loss: 0.33560967445373535
2023-01-22 20:32:58.325471: step: 794/470, loss: 0.040173858404159546
2023-01-22 20:32:59.146638: step: 796/470, loss: 0.025398118421435356
2023-01-22 20:32:59.880687: step: 798/470, loss: 0.06342984735965729
2023-01-22 20:33:00.596637: step: 800/470, loss: 0.06393054127693176
2023-01-22 20:33:01.349101: step: 802/470, loss: 0.04026153311133385
2023-01-22 20:33:02.068500: step: 804/470, loss: 0.0187918022274971
2023-01-22 20:33:02.740159: step: 806/470, loss: 0.3132553696632385
2023-01-22 20:33:03.507555: step: 808/470, loss: 0.007414802443236113
2023-01-22 20:33:04.215579: step: 810/470, loss: 0.005097710061818361
2023-01-22 20:33:04.969773: step: 812/470, loss: 0.011615417897701263
2023-01-22 20:33:05.705998: step: 814/470, loss: 0.12536713480949402
2023-01-22 20:33:06.508129: step: 816/470, loss: 0.029747048392891884
2023-01-22 20:33:07.243041: step: 818/470, loss: 0.050025250762701035
2023-01-22 20:33:07.989303: step: 820/470, loss: 0.01923954486846924
2023-01-22 20:33:08.723415: step: 822/470, loss: 0.039691563695669174
2023-01-22 20:33:09.464960: step: 824/470, loss: 0.03583470359444618
2023-01-22 20:33:10.153100: step: 826/470, loss: 0.06700265407562256
2023-01-22 20:33:10.899995: step: 828/470, loss: 0.02268780767917633
2023-01-22 20:33:11.570115: step: 830/470, loss: 0.05540559068322182
2023-01-22 20:33:12.304231: step: 832/470, loss: 0.03642084449529648
2023-01-22 20:33:12.967164: step: 834/470, loss: 0.007380470167845488
2023-01-22 20:33:13.692238: step: 836/470, loss: 0.04133666679263115
2023-01-22 20:33:14.368152: step: 838/470, loss: 0.09914152324199677
2023-01-22 20:33:15.123345: step: 840/470, loss: 0.0013483419315889478
2023-01-22 20:33:15.879759: step: 842/470, loss: 0.03963959217071533
2023-01-22 20:33:16.534495: step: 844/470, loss: 0.041381705552339554
2023-01-22 20:33:17.188246: step: 846/470, loss: 0.016487672924995422
2023-01-22 20:33:17.821573: step: 848/470, loss: 0.0062914639711380005
2023-01-22 20:33:18.496781: step: 850/470, loss: 0.011747756041586399
2023-01-22 20:33:19.258545: step: 852/470, loss: 0.0007929243729449809
2023-01-22 20:33:19.973108: step: 854/470, loss: 0.0006810800405219197
2023-01-22 20:33:20.669589: step: 856/470, loss: 0.002209881553426385
2023-01-22 20:33:21.411319: step: 858/470, loss: 0.028073936700820923
2023-01-22 20:33:22.081391: step: 860/470, loss: 0.16893041133880615
2023-01-22 20:33:22.853985: step: 862/470, loss: 0.0011155976681038737
2023-01-22 20:33:23.567337: step: 864/470, loss: 0.00859520398080349
2023-01-22 20:33:24.319532: step: 866/470, loss: 7.151709723984823e-05
2023-01-22 20:33:25.129313: step: 868/470, loss: 0.01832861453294754
2023-01-22 20:33:25.842383: step: 870/470, loss: 0.047499969601631165
2023-01-22 20:33:26.658046: step: 872/470, loss: 0.003909479361027479
2023-01-22 20:33:27.395148: step: 874/470, loss: 0.25040119886398315
2023-01-22 20:33:28.157148: step: 876/470, loss: 0.06178472191095352
2023-01-22 20:33:28.853453: step: 878/470, loss: 0.0017721912590786815
2023-01-22 20:33:29.590628: step: 880/470, loss: 0.007689218968153
2023-01-22 20:33:30.404651: step: 882/470, loss: 0.033220697194337845
2023-01-22 20:33:31.223558: step: 884/470, loss: 0.008743722923099995
2023-01-22 20:33:31.945733: step: 886/470, loss: 0.0026598607655614614
2023-01-22 20:33:32.701621: step: 888/470, loss: 0.006200912408530712
2023-01-22 20:33:33.375664: step: 890/470, loss: 0.033201370388269424
2023-01-22 20:33:34.083571: step: 892/470, loss: 0.005671496037393808
2023-01-22 20:33:34.823140: step: 894/470, loss: 0.0014364663511514664
2023-01-22 20:33:35.528960: step: 896/470, loss: 0.12019861489534378
2023-01-22 20:33:36.410148: step: 898/470, loss: 0.0630432739853859
2023-01-22 20:33:37.138592: step: 900/470, loss: 0.009634872898459435
2023-01-22 20:33:37.828054: step: 902/470, loss: 0.056970443576574326
2023-01-22 20:33:38.541210: step: 904/470, loss: 0.04602930322289467
2023-01-22 20:33:39.278641: step: 906/470, loss: 0.03439059853553772
2023-01-22 20:33:39.895159: step: 908/470, loss: 0.14804024994373322
2023-01-22 20:33:40.628991: step: 910/470, loss: 0.005356145091354847
2023-01-22 20:33:41.406445: step: 912/470, loss: 0.02320312149822712
2023-01-22 20:33:42.190689: step: 914/470, loss: 0.12080468982458115
2023-01-22 20:33:42.905353: step: 916/470, loss: 0.01958886720240116
2023-01-22 20:33:43.621773: step: 918/470, loss: 0.011003172025084496
2023-01-22 20:33:44.274991: step: 920/470, loss: 0.0002306982351001352
2023-01-22 20:33:45.065971: step: 922/470, loss: 0.06692475080490112
2023-01-22 20:33:45.830862: step: 924/470, loss: 0.030821437016129494
2023-01-22 20:33:46.515323: step: 926/470, loss: 0.03762578219175339
2023-01-22 20:33:47.160706: step: 928/470, loss: 0.0017827172996476293
2023-01-22 20:33:47.935888: step: 930/470, loss: 0.04079880192875862
2023-01-22 20:33:48.756535: step: 932/470, loss: 0.003436343977227807
2023-01-22 20:33:49.536146: step: 934/470, loss: 0.021370133385062218
2023-01-22 20:33:50.262158: step: 936/470, loss: 0.029703887179493904
2023-01-22 20:33:50.968299: step: 938/470, loss: 0.06702406704425812
2023-01-22 20:33:51.615929: step: 940/470, loss: 0.015583197586238384
2023-01-22 20:33:52.246601: step: 942/470, loss: 0.001184674329124391
==================================================
Loss: 0.093
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28582109842305603, 'r': 0.33246363061353573, 'f1': 0.3073830409356725}, 'combined': 0.22649276700523235, 'epoch': 28}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.324120752408383, 'r': 0.36681742844679505, 'f1': 0.34414986520944235}, 'combined': 0.23970637377772105, 'epoch': 28}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27722653286563065, 'r': 0.33509165357762183, 'f1': 0.30342491655568166}, 'combined': 0.22357625430418648, 'epoch': 28}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32527617462539155, 'r': 0.36124421316569927, 'f1': 0.34231797876294057}, 'combined': 0.23843043296921235, 'epoch': 28}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27060735512630013, 'r': 0.34557637571157496, 'f1': 0.30353125000000003}, 'combined': 0.22365460526315792, 'epoch': 28}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.31329216537409327, 'r': 0.3690220217146772, 'f1': 0.3388811501838978}, 'combined': 0.23603662201863532, 'epoch': 28}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.22629310344827586, 'r': 0.375, 'f1': 0.28225806451612906}, 'combined': 0.1881720430107527, 'epoch': 28}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.28378378378378377, 'r': 0.45652173913043476, 'f1': 0.3499999999999999}, 'combined': 0.17499999999999996, 'epoch': 28}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4431818181818182, 'r': 0.33620689655172414, 'f1': 0.38235294117647056}, 'combined': 0.2549019607843137, 'epoch': 28}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 29
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 20:36:27.608956: step: 2/470, loss: 0.2647108733654022
2023-01-22 20:36:28.445352: step: 4/470, loss: 0.02322511561214924
2023-01-22 20:36:29.111700: step: 6/470, loss: 0.02740596979856491
2023-01-22 20:36:29.823356: step: 8/470, loss: 0.013857753947377205
2023-01-22 20:36:30.618779: step: 10/470, loss: 0.005119292065501213
2023-01-22 20:36:31.361882: step: 12/470, loss: 0.00834457017481327
2023-01-22 20:36:31.999105: step: 14/470, loss: 0.0004951293813064694
2023-01-22 20:36:32.757013: step: 16/470, loss: 0.027414359152317047
2023-01-22 20:36:33.677129: step: 18/470, loss: 0.03084324114024639
2023-01-22 20:36:34.262209: step: 20/470, loss: 0.006820783019065857
2023-01-22 20:36:35.087880: step: 22/470, loss: 0.00931725837290287
2023-01-22 20:36:35.816353: step: 24/470, loss: 0.0211730245500803
2023-01-22 20:36:36.594875: step: 26/470, loss: 0.0012839719420298934
2023-01-22 20:36:37.280282: step: 28/470, loss: 0.04594583436846733
2023-01-22 20:36:37.989540: step: 30/470, loss: 0.012252802029252052
2023-01-22 20:36:38.696098: step: 32/470, loss: 0.004927062429487705
2023-01-22 20:36:39.493525: step: 34/470, loss: 0.006308556068688631
2023-01-22 20:36:40.301880: step: 36/470, loss: 0.015124126337468624
2023-01-22 20:36:41.067837: step: 38/470, loss: 0.007813768461346626
2023-01-22 20:36:41.747715: step: 40/470, loss: 0.0029113588389009237
2023-01-22 20:36:42.493345: step: 42/470, loss: 0.011285551823675632
2023-01-22 20:36:43.242984: step: 44/470, loss: 0.3646211326122284
2023-01-22 20:36:44.012230: step: 46/470, loss: 0.006847033277153969
2023-01-22 20:36:44.734114: step: 48/470, loss: 0.06652196496725082
2023-01-22 20:36:45.504990: step: 50/470, loss: 0.2817710041999817
2023-01-22 20:36:46.272210: step: 52/470, loss: 0.0034084455110132694
2023-01-22 20:36:47.024804: step: 54/470, loss: 0.04189238324761391
2023-01-22 20:36:47.679586: step: 56/470, loss: 0.002203726675361395
2023-01-22 20:36:48.499757: step: 58/470, loss: 0.011194828897714615
2023-01-22 20:36:49.284676: step: 60/470, loss: 0.19877992570400238
2023-01-22 20:36:50.013245: step: 62/470, loss: 0.007485152687877417
2023-01-22 20:36:50.705064: step: 64/470, loss: 0.020456980913877487
2023-01-22 20:36:51.411567: step: 66/470, loss: 0.005883743055164814
2023-01-22 20:36:52.141466: step: 68/470, loss: 0.012196771800518036
2023-01-22 20:36:52.824451: step: 70/470, loss: 0.00925607979297638
2023-01-22 20:36:53.461890: step: 72/470, loss: 0.014364490285515785
2023-01-22 20:36:54.192563: step: 74/470, loss: 0.37649011611938477
2023-01-22 20:36:54.946755: step: 76/470, loss: 0.010440860874950886
2023-01-22 20:36:55.754206: step: 78/470, loss: 0.02263338305056095
2023-01-22 20:36:56.503508: step: 80/470, loss: 0.2164899855852127
2023-01-22 20:36:57.240408: step: 82/470, loss: 0.0030306533444672823
2023-01-22 20:36:57.965748: step: 84/470, loss: 0.003299787174910307
2023-01-22 20:36:58.692931: step: 86/470, loss: 0.0003010545624420047
2023-01-22 20:36:59.408849: step: 88/470, loss: 0.3850425183773041
2023-01-22 20:37:00.218016: step: 90/470, loss: 0.01980891264975071
2023-01-22 20:37:00.902012: step: 92/470, loss: 0.021628176793456078
2023-01-22 20:37:01.707698: step: 94/470, loss: 0.0020503345876932144
2023-01-22 20:37:02.456240: step: 96/470, loss: 0.008198212832212448
2023-01-22 20:37:03.135512: step: 98/470, loss: 0.03375517949461937
2023-01-22 20:37:03.800281: step: 100/470, loss: 0.0032718630973249674
2023-01-22 20:37:04.442801: step: 102/470, loss: 0.0006153931026346982
2023-01-22 20:37:05.119721: step: 104/470, loss: 0.006163314450532198
2023-01-22 20:37:05.930701: step: 106/470, loss: 0.055401623249053955
2023-01-22 20:37:06.710487: step: 108/470, loss: 0.012150800786912441
2023-01-22 20:37:07.499916: step: 110/470, loss: 0.13651181757450104
2023-01-22 20:37:08.221142: step: 112/470, loss: 0.02135992981493473
2023-01-22 20:37:08.931225: step: 114/470, loss: 0.4167734980583191
2023-01-22 20:37:09.781497: step: 116/470, loss: 0.013348422944545746
2023-01-22 20:37:10.516349: step: 118/470, loss: 0.003862533252686262
2023-01-22 20:37:11.166664: step: 120/470, loss: 0.0047416831366717815
2023-01-22 20:37:11.847887: step: 122/470, loss: 0.0004611566837411374
2023-01-22 20:37:12.701271: step: 124/470, loss: 0.0077300965785980225
2023-01-22 20:37:13.468263: step: 126/470, loss: 0.005382179748266935
2023-01-22 20:37:14.122827: step: 128/470, loss: 0.004562853369861841
2023-01-22 20:37:14.811694: step: 130/470, loss: 0.04411611706018448
2023-01-22 20:37:15.556789: step: 132/470, loss: 0.013166757300496101
2023-01-22 20:37:16.246570: step: 134/470, loss: 0.005444676149636507
2023-01-22 20:37:17.017496: step: 136/470, loss: 9.606832463759929e-05
2023-01-22 20:37:17.810542: step: 138/470, loss: 0.003493986092507839
2023-01-22 20:37:18.553931: step: 140/470, loss: 0.0017787780379876494
2023-01-22 20:37:19.336022: step: 142/470, loss: 0.040565188974142075
2023-01-22 20:37:20.143512: step: 144/470, loss: 0.01262040063738823
2023-01-22 20:37:20.933983: step: 146/470, loss: 0.01510031707584858
2023-01-22 20:37:21.680699: step: 148/470, loss: 0.0011344999074935913
2023-01-22 20:37:22.477079: step: 150/470, loss: 0.049181923270225525
2023-01-22 20:37:23.203395: step: 152/470, loss: 0.04775718227028847
2023-01-22 20:37:23.907226: step: 154/470, loss: 4.9370075430488214e-05
2023-01-22 20:37:24.612455: step: 156/470, loss: 0.4461440443992615
2023-01-22 20:37:25.317419: step: 158/470, loss: 0.15681709349155426
2023-01-22 20:37:26.007896: step: 160/470, loss: 0.009236715734004974
2023-01-22 20:37:26.808454: step: 162/470, loss: 0.032232243567705154
2023-01-22 20:37:27.625958: step: 164/470, loss: 0.002545413561165333
2023-01-22 20:37:28.345679: step: 166/470, loss: 0.009975194931030273
2023-01-22 20:37:29.091825: step: 168/470, loss: 0.015161970630288124
2023-01-22 20:37:29.820329: step: 170/470, loss: 0.005908914841711521
2023-01-22 20:37:30.552056: step: 172/470, loss: 0.021803176030516624
2023-01-22 20:37:31.322435: step: 174/470, loss: 0.1319359987974167
2023-01-22 20:37:32.021720: step: 176/470, loss: 0.047474365681409836
2023-01-22 20:37:32.792494: step: 178/470, loss: 0.02708449400961399
2023-01-22 20:37:33.501844: step: 180/470, loss: 0.07310396432876587
2023-01-22 20:37:34.208855: step: 182/470, loss: 0.04242819547653198
2023-01-22 20:37:34.908128: step: 184/470, loss: 0.005080712027847767
2023-01-22 20:37:35.637878: step: 186/470, loss: 0.011022936552762985
2023-01-22 20:37:36.283488: step: 188/470, loss: 0.004775905515998602
2023-01-22 20:37:37.030015: step: 190/470, loss: 0.014512178488075733
2023-01-22 20:37:37.712899: step: 192/470, loss: 0.018934812396764755
2023-01-22 20:37:38.457649: step: 194/470, loss: 0.00309011316858232
2023-01-22 20:37:39.188679: step: 196/470, loss: 0.004391052294522524
2023-01-22 20:37:39.938842: step: 198/470, loss: 0.00033165913191623986
2023-01-22 20:37:40.599590: step: 200/470, loss: 0.00046572668361477554
2023-01-22 20:37:41.336227: step: 202/470, loss: 0.013232901692390442
2023-01-22 20:37:42.170243: step: 204/470, loss: 0.1024237647652626
2023-01-22 20:37:42.871632: step: 206/470, loss: 0.01619911752641201
2023-01-22 20:37:43.580043: step: 208/470, loss: 0.0010863811476156116
2023-01-22 20:37:44.297969: step: 210/470, loss: 0.0015397859970107675
2023-01-22 20:37:45.021975: step: 212/470, loss: 0.07132253795862198
2023-01-22 20:37:45.685557: step: 214/470, loss: 0.004997688811272383
2023-01-22 20:37:46.418503: step: 216/470, loss: 0.00376240280456841
2023-01-22 20:37:47.203504: step: 218/470, loss: 0.03204397112131119
2023-01-22 20:37:47.893685: step: 220/470, loss: 0.008753920905292034
2023-01-22 20:37:48.615242: step: 222/470, loss: 0.005575764458626509
2023-01-22 20:37:49.424684: step: 224/470, loss: 0.0023701766040176153
2023-01-22 20:37:50.123942: step: 226/470, loss: 0.005872036796063185
2023-01-22 20:37:50.889559: step: 228/470, loss: 0.023437704890966415
2023-01-22 20:37:51.642881: step: 230/470, loss: 0.010248042643070221
2023-01-22 20:37:52.399415: step: 232/470, loss: 0.02714042365550995
2023-01-22 20:37:53.196757: step: 234/470, loss: 0.01943190023303032
2023-01-22 20:37:53.886112: step: 236/470, loss: 0.00399386091157794
2023-01-22 20:37:54.566130: step: 238/470, loss: 0.0016181677347049117
2023-01-22 20:37:55.403372: step: 240/470, loss: 0.049513738602399826
2023-01-22 20:37:56.151090: step: 242/470, loss: 0.07210097461938858
2023-01-22 20:37:56.851427: step: 244/470, loss: 0.00037181295920163393
2023-01-22 20:37:57.591048: step: 246/470, loss: 0.19889435172080994
2023-01-22 20:37:58.284350: step: 248/470, loss: 0.006400907877832651
2023-01-22 20:37:59.167326: step: 250/470, loss: 0.028619172051548958
2023-01-22 20:37:59.887560: step: 252/470, loss: 0.021511005237698555
2023-01-22 20:38:00.600162: step: 254/470, loss: 0.04519416764378548
2023-01-22 20:38:01.324973: step: 256/470, loss: 0.13093401491641998
2023-01-22 20:38:02.078024: step: 258/470, loss: 0.09740595519542694
2023-01-22 20:38:02.831296: step: 260/470, loss: 0.13155671954154968
2023-01-22 20:38:03.628731: step: 262/470, loss: 0.07691262662410736
2023-01-22 20:38:04.388002: step: 264/470, loss: 0.004110024776309729
2023-01-22 20:38:05.065951: step: 266/470, loss: 0.1348675787448883
2023-01-22 20:38:05.759508: step: 268/470, loss: 0.10196854174137115
2023-01-22 20:38:06.513079: step: 270/470, loss: 0.009700944647192955
2023-01-22 20:38:07.232958: step: 272/470, loss: 0.0025991289876401424
2023-01-22 20:38:07.970858: step: 274/470, loss: 0.0007453685393556952
2023-01-22 20:38:08.620966: step: 276/470, loss: 0.0021520478185266256
2023-01-22 20:38:09.336916: step: 278/470, loss: 0.052726294845342636
2023-01-22 20:38:10.065618: step: 280/470, loss: 0.003794698743149638
2023-01-22 20:38:10.871767: step: 282/470, loss: 0.01943463459610939
2023-01-22 20:38:11.555695: step: 284/470, loss: 0.023348847404122353
2023-01-22 20:38:12.271012: step: 286/470, loss: 0.019955376163125038
2023-01-22 20:38:12.986152: step: 288/470, loss: 0.003484874265268445
2023-01-22 20:38:13.724351: step: 290/470, loss: 0.028693674132227898
2023-01-22 20:38:14.440891: step: 292/470, loss: 0.0033248071558773518
2023-01-22 20:38:15.161579: step: 294/470, loss: 0.03285335376858711
2023-01-22 20:38:15.934766: step: 296/470, loss: 0.01780891977250576
2023-01-22 20:38:16.718023: step: 298/470, loss: 0.05349568650126457
2023-01-22 20:38:17.438631: step: 300/470, loss: 0.5065484642982483
2023-01-22 20:38:18.270128: step: 302/470, loss: 0.03260203078389168
2023-01-22 20:38:19.024874: step: 304/470, loss: 0.03035620041191578
2023-01-22 20:38:19.726944: step: 306/470, loss: 0.006546898279339075
2023-01-22 20:38:20.519129: step: 308/470, loss: 0.002254707971587777
2023-01-22 20:38:21.260058: step: 310/470, loss: 0.00036036467645317316
2023-01-22 20:38:21.936594: step: 312/470, loss: 0.003247553249821067
2023-01-22 20:38:22.602780: step: 314/470, loss: 0.06962236016988754
2023-01-22 20:38:23.331690: step: 316/470, loss: 0.02976413629949093
2023-01-22 20:38:24.010010: step: 318/470, loss: 0.004767751786857843
2023-01-22 20:38:24.751625: step: 320/470, loss: 0.10309252142906189
2023-01-22 20:38:25.543014: step: 322/470, loss: 0.10256746411323547
2023-01-22 20:38:26.359726: step: 324/470, loss: 0.05060182884335518
2023-01-22 20:38:27.102103: step: 326/470, loss: 0.006237236317247152
2023-01-22 20:38:27.829615: step: 328/470, loss: 0.05871773138642311
2023-01-22 20:38:28.551366: step: 330/470, loss: 0.24029061198234558
2023-01-22 20:38:29.250486: step: 332/470, loss: 0.19288605451583862
2023-01-22 20:38:29.983125: step: 334/470, loss: 0.007970509119331837
2023-01-22 20:38:30.749054: step: 336/470, loss: 0.04301189258694649
2023-01-22 20:38:31.460288: step: 338/470, loss: 0.01984056457877159
2023-01-22 20:38:32.182914: step: 340/470, loss: 0.03184615448117256
2023-01-22 20:38:32.869369: step: 342/470, loss: 0.002288240008056164
2023-01-22 20:38:33.600433: step: 344/470, loss: 0.00532893929630518
2023-01-22 20:38:34.337318: step: 346/470, loss: 0.02240307815372944
2023-01-22 20:38:35.109616: step: 348/470, loss: 0.005755066871643066
2023-01-22 20:38:35.824437: step: 350/470, loss: 0.028193417936563492
2023-01-22 20:38:36.488497: step: 352/470, loss: 0.0016564959660172462
2023-01-22 20:38:37.215158: step: 354/470, loss: 0.1647537648677826
2023-01-22 20:38:37.990698: step: 356/470, loss: 0.02808982878923416
2023-01-22 20:38:38.722422: step: 358/470, loss: 0.02180049754679203
2023-01-22 20:38:39.469286: step: 360/470, loss: 0.009425032883882523
2023-01-22 20:38:40.192646: step: 362/470, loss: 0.002624044893309474
2023-01-22 20:38:40.977757: step: 364/470, loss: 0.03871319815516472
2023-01-22 20:38:41.743356: step: 366/470, loss: 0.0012272871099412441
2023-01-22 20:38:42.524056: step: 368/470, loss: 0.03193151205778122
2023-01-22 20:38:43.348946: step: 370/470, loss: 0.005393751431256533
2023-01-22 20:38:43.994136: step: 372/470, loss: 0.007179801352322102
2023-01-22 20:38:44.689456: step: 374/470, loss: 0.02233264036476612
2023-01-22 20:38:45.423147: step: 376/470, loss: 0.019881457090377808
2023-01-22 20:38:46.201537: step: 378/470, loss: 0.004716763272881508
2023-01-22 20:38:46.971590: step: 380/470, loss: 0.010665499605238438
2023-01-22 20:38:47.683262: step: 382/470, loss: 0.021654922515153885
2023-01-22 20:38:48.446742: step: 384/470, loss: 0.017089908942580223
2023-01-22 20:38:49.128842: step: 386/470, loss: 0.004330948460847139
2023-01-22 20:38:49.931210: step: 388/470, loss: 0.004959953483194113
2023-01-22 20:38:50.592840: step: 390/470, loss: 0.0001449349510949105
2023-01-22 20:38:51.268523: step: 392/470, loss: 0.020653393119573593
2023-01-22 20:38:52.041796: step: 394/470, loss: 0.029949171468615532
2023-01-22 20:38:52.732253: step: 396/470, loss: 0.002220702590420842
2023-01-22 20:38:53.495710: step: 398/470, loss: 0.004065732005983591
2023-01-22 20:38:54.209657: step: 400/470, loss: 0.06798814982175827
2023-01-22 20:38:55.010086: step: 402/470, loss: 0.011189811863005161
2023-01-22 20:38:55.689051: step: 404/470, loss: 0.00252006808295846
2023-01-22 20:38:56.443786: step: 406/470, loss: 0.008702918887138367
2023-01-22 20:38:57.138128: step: 408/470, loss: 0.17309211194515228
2023-01-22 20:38:57.876443: step: 410/470, loss: 0.05191047117114067
2023-01-22 20:38:58.635459: step: 412/470, loss: 0.09695277363061905
2023-01-22 20:38:59.318262: step: 414/470, loss: 0.006256232038140297
2023-01-22 20:39:00.042065: step: 416/470, loss: 0.05564850568771362
2023-01-22 20:39:00.816868: step: 418/470, loss: 0.0020740872714668512
2023-01-22 20:39:01.510571: step: 420/470, loss: 0.005247580353170633
2023-01-22 20:39:02.404755: step: 422/470, loss: 0.003924751654267311
2023-01-22 20:39:03.112116: step: 424/470, loss: 0.010796195827424526
2023-01-22 20:39:03.782979: step: 426/470, loss: 0.02733398787677288
2023-01-22 20:39:04.586107: step: 428/470, loss: 0.020288608968257904
2023-01-22 20:39:05.296051: step: 430/470, loss: 0.006797471083700657
2023-01-22 20:39:06.005939: step: 432/470, loss: 0.05538531392812729
2023-01-22 20:39:06.707845: step: 434/470, loss: 0.011707188561558723
2023-01-22 20:39:07.402682: step: 436/470, loss: 0.025928908959031105
2023-01-22 20:39:08.041183: step: 438/470, loss: 0.011687841266393661
2023-01-22 20:39:08.782729: step: 440/470, loss: 0.02929680421948433
2023-01-22 20:39:09.480466: step: 442/470, loss: 0.00014456742792390287
2023-01-22 20:39:10.231278: step: 444/470, loss: 0.018118448555469513
2023-01-22 20:39:10.947901: step: 446/470, loss: 1.0357182025909424
2023-01-22 20:39:11.767188: step: 448/470, loss: 0.035767797380685806
2023-01-22 20:39:12.570415: step: 450/470, loss: 0.012241028249263763
2023-01-22 20:39:13.289436: step: 452/470, loss: 0.02669922076165676
2023-01-22 20:39:13.992794: step: 454/470, loss: 0.0076654767617583275
2023-01-22 20:39:14.764071: step: 456/470, loss: 0.005637957714498043
2023-01-22 20:39:15.497378: step: 458/470, loss: 0.056888647377491
2023-01-22 20:39:16.229040: step: 460/470, loss: 0.020066574215888977
2023-01-22 20:39:16.996864: step: 462/470, loss: 0.36348721385002136
2023-01-22 20:39:17.671437: step: 464/470, loss: 0.029186828061938286
2023-01-22 20:39:18.430153: step: 466/470, loss: 0.013277608901262283
2023-01-22 20:39:19.115542: step: 468/470, loss: 0.19909025728702545
2023-01-22 20:39:19.842378: step: 470/470, loss: 0.004801159258931875
2023-01-22 20:39:20.679472: step: 472/470, loss: 0.012583213858306408
2023-01-22 20:39:21.439802: step: 474/470, loss: 0.07196840643882751
2023-01-22 20:39:22.161428: step: 476/470, loss: 0.024347444996237755
2023-01-22 20:39:22.915286: step: 478/470, loss: 0.020326513797044754
2023-01-22 20:39:23.636758: step: 480/470, loss: 0.011932437308132648
2023-01-22 20:39:24.416640: step: 482/470, loss: 0.02215908281505108
2023-01-22 20:39:25.160776: step: 484/470, loss: 0.0020135114900767803
2023-01-22 20:39:25.858639: step: 486/470, loss: 0.0020898778457194567
2023-01-22 20:39:26.592462: step: 488/470, loss: 0.014602022245526314
2023-01-22 20:39:27.399484: step: 490/470, loss: 0.017223408445715904
2023-01-22 20:39:28.069322: step: 492/470, loss: 0.0020636683329939842
2023-01-22 20:39:28.824353: step: 494/470, loss: 0.01937001757323742
2023-01-22 20:39:29.505213: step: 496/470, loss: 0.0012707647401839495
2023-01-22 20:39:30.207636: step: 498/470, loss: 0.17490433156490326
2023-01-22 20:39:30.946781: step: 500/470, loss: 0.013577910140156746
2023-01-22 20:39:31.658764: step: 502/470, loss: 0.007008845917880535
2023-01-22 20:39:32.369578: step: 504/470, loss: 0.002107697306200862
2023-01-22 20:39:33.121184: step: 506/470, loss: 0.005590823013335466
2023-01-22 20:39:33.872367: step: 508/470, loss: 0.019169259816408157
2023-01-22 20:39:34.541089: step: 510/470, loss: 0.0015802793204784393
2023-01-22 20:39:35.257909: step: 512/470, loss: 0.013873277232050896
2023-01-22 20:39:36.062000: step: 514/470, loss: 0.007271386217325926
2023-01-22 20:39:36.882358: step: 516/470, loss: 0.0057012708857655525
2023-01-22 20:39:37.643010: step: 518/470, loss: 0.0004432882706169039
2023-01-22 20:39:38.318401: step: 520/470, loss: 0.0004786129866261035
2023-01-22 20:39:39.005305: step: 522/470, loss: 0.1716701239347458
2023-01-22 20:39:39.645277: step: 524/470, loss: 0.018754906952381134
2023-01-22 20:39:40.421106: step: 526/470, loss: 0.0010185715509578586
2023-01-22 20:39:41.305310: step: 528/470, loss: 0.012098163366317749
2023-01-22 20:39:42.149555: step: 530/470, loss: 0.04463057965040207
2023-01-22 20:39:42.838368: step: 532/470, loss: 0.001784288208000362
2023-01-22 20:39:43.572295: step: 534/470, loss: 0.040405258536338806
2023-01-22 20:39:44.227217: step: 536/470, loss: 0.016458706930279732
2023-01-22 20:39:44.962359: step: 538/470, loss: 0.037848204374313354
2023-01-22 20:39:45.606643: step: 540/470, loss: 0.13946174085140228
2023-01-22 20:39:46.273679: step: 542/470, loss: 0.15389235317707062
2023-01-22 20:39:46.975309: step: 544/470, loss: 0.0027951474767178297
2023-01-22 20:39:47.667793: step: 546/470, loss: 0.0260777585208416
2023-01-22 20:39:48.347369: step: 548/470, loss: 0.0007106401026248932
2023-01-22 20:39:49.076574: step: 550/470, loss: 0.011294242925941944
2023-01-22 20:39:49.797035: step: 552/470, loss: 0.0024706493131816387
2023-01-22 20:39:50.500536: step: 554/470, loss: 0.0029934581834822893
2023-01-22 20:39:51.267926: step: 556/470, loss: 0.03564335033297539
2023-01-22 20:39:51.881114: step: 558/470, loss: 0.0014540080446749926
2023-01-22 20:39:52.584493: step: 560/470, loss: 0.0077100833877921104
2023-01-22 20:39:53.349845: step: 562/470, loss: 0.0005074184155091643
2023-01-22 20:39:54.161634: step: 564/470, loss: 0.13422176241874695
2023-01-22 20:39:54.938270: step: 566/470, loss: 0.011121930554509163
2023-01-22 20:39:55.681260: step: 568/470, loss: 0.0019553580787032843
2023-01-22 20:39:56.363308: step: 570/470, loss: 0.12414314597845078
2023-01-22 20:39:57.074694: step: 572/470, loss: 0.22418749332427979
2023-01-22 20:39:57.821691: step: 574/470, loss: 0.02621358633041382
2023-01-22 20:39:58.569023: step: 576/470, loss: 0.033430345356464386
2023-01-22 20:39:59.362701: step: 578/470, loss: 0.025795383378863335
2023-01-22 20:40:00.128966: step: 580/470, loss: 0.04664403572678566
2023-01-22 20:40:00.834723: step: 582/470, loss: 0.04867984354496002
2023-01-22 20:40:01.530724: step: 584/470, loss: 0.022736769169569016
2023-01-22 20:40:02.233929: step: 586/470, loss: 0.0002613358956295997
2023-01-22 20:40:03.017019: step: 588/470, loss: 0.016873285174369812
2023-01-22 20:40:03.720954: step: 590/470, loss: 0.013911283574998379
2023-01-22 20:40:04.467939: step: 592/470, loss: 0.0659724697470665
2023-01-22 20:40:05.163337: step: 594/470, loss: 0.008108820766210556
2023-01-22 20:40:05.953209: step: 596/470, loss: 0.02690688520669937
2023-01-22 20:40:06.711402: step: 598/470, loss: 0.05805189535021782
2023-01-22 20:40:07.502070: step: 600/470, loss: 0.08737591654062271
2023-01-22 20:40:08.249192: step: 602/470, loss: 0.02579532191157341
2023-01-22 20:40:08.987398: step: 604/470, loss: 0.009756003506481647
2023-01-22 20:40:09.597344: step: 606/470, loss: 0.0011332191061228514
2023-01-22 20:40:10.371036: step: 608/470, loss: 0.014959428459405899
2023-01-22 20:40:11.146442: step: 610/470, loss: 0.014169977977871895
2023-01-22 20:40:11.835466: step: 612/470, loss: 0.007126861251890659
2023-01-22 20:40:12.519788: step: 614/470, loss: 0.03526424989104271
2023-01-22 20:40:13.269550: step: 616/470, loss: 0.0036206073127686977
2023-01-22 20:40:14.037000: step: 618/470, loss: 0.005215490702539682
2023-01-22 20:40:14.825728: step: 620/470, loss: 0.011563556268811226
2023-01-22 20:40:15.580391: step: 622/470, loss: 0.03009108267724514
2023-01-22 20:40:16.327758: step: 624/470, loss: 0.47227317094802856
2023-01-22 20:40:17.063081: step: 626/470, loss: 0.000962880440056324
2023-01-22 20:40:17.771219: step: 628/470, loss: 0.004227377008646727
2023-01-22 20:40:18.444942: step: 630/470, loss: 0.05415330082178116
2023-01-22 20:40:19.146814: step: 632/470, loss: 0.02446996420621872
2023-01-22 20:40:19.901675: step: 634/470, loss: 0.10332430154085159
2023-01-22 20:40:20.580506: step: 636/470, loss: 0.0059739393182098866
2023-01-22 20:40:21.362738: step: 638/470, loss: 0.0033245279919356108
2023-01-22 20:40:22.088954: step: 640/470, loss: 0.044418323785066605
2023-01-22 20:40:22.754027: step: 642/470, loss: 0.00199850439094007
2023-01-22 20:40:23.530954: step: 644/470, loss: 0.05675657093524933
2023-01-22 20:40:24.288523: step: 646/470, loss: 0.0008988552144728601
2023-01-22 20:40:25.018221: step: 648/470, loss: 0.013591834343969822
2023-01-22 20:40:25.728084: step: 650/470, loss: 0.003277568379417062
2023-01-22 20:40:26.458930: step: 652/470, loss: 0.002477661008015275
2023-01-22 20:40:27.197950: step: 654/470, loss: 0.011621094308793545
2023-01-22 20:40:27.885970: step: 656/470, loss: 0.008883575908839703
2023-01-22 20:40:28.565125: step: 658/470, loss: 0.016700388863682747
2023-01-22 20:40:29.294374: step: 660/470, loss: 0.013254842720925808
2023-01-22 20:40:30.042209: step: 662/470, loss: 0.04380848631262779
2023-01-22 20:40:30.792919: step: 664/470, loss: 0.2254922240972519
2023-01-22 20:40:31.556278: step: 666/470, loss: 0.00549095356836915
2023-01-22 20:40:32.242722: step: 668/470, loss: 0.041242629289627075
2023-01-22 20:40:32.959565: step: 670/470, loss: 0.002172822365537286
2023-01-22 20:40:33.630380: step: 672/470, loss: 0.0004444690130185336
2023-01-22 20:40:34.503699: step: 674/470, loss: 0.21776027977466583
2023-01-22 20:40:35.341508: step: 676/470, loss: 0.04360530152916908
2023-01-22 20:40:36.126415: step: 678/470, loss: 0.01206052303314209
2023-01-22 20:40:36.927525: step: 680/470, loss: 0.1170274093747139
2023-01-22 20:40:37.684828: step: 682/470, loss: 0.05427645891904831
2023-01-22 20:40:38.400244: step: 684/470, loss: 0.025601759552955627
2023-01-22 20:40:39.188600: step: 686/470, loss: 0.027646034955978394
2023-01-22 20:40:39.875977: step: 688/470, loss: 0.18431520462036133
2023-01-22 20:40:40.632507: step: 690/470, loss: 0.0012170057743787766
2023-01-22 20:40:41.372432: step: 692/470, loss: 0.007006289437413216
2023-01-22 20:40:42.077569: step: 694/470, loss: 0.0009528612717986107
2023-01-22 20:40:42.801151: step: 696/470, loss: 0.11783985793590546
2023-01-22 20:40:43.478886: step: 698/470, loss: 0.038966577500104904
2023-01-22 20:40:44.193257: step: 700/470, loss: 0.008607025258243084
2023-01-22 20:40:44.918514: step: 702/470, loss: 0.024364376440644264
2023-01-22 20:40:45.713479: step: 704/470, loss: 0.030996840447187424
2023-01-22 20:40:46.464310: step: 706/470, loss: 0.03350379317998886
2023-01-22 20:40:47.080928: step: 708/470, loss: 0.0056647504679858685
2023-01-22 20:40:47.784382: step: 710/470, loss: 0.011958747170865536
2023-01-22 20:40:48.562623: step: 712/470, loss: 0.07865112274885178
2023-01-22 20:40:49.346462: step: 714/470, loss: 0.03213072568178177
2023-01-22 20:40:50.129443: step: 716/470, loss: 0.04514642804861069
2023-01-22 20:40:50.865107: step: 718/470, loss: 0.004229575861245394
2023-01-22 20:40:51.661209: step: 720/470, loss: 0.025142908096313477
2023-01-22 20:40:52.415424: step: 722/470, loss: 0.16131198406219482
2023-01-22 20:40:53.052102: step: 724/470, loss: 0.0029195209499448538
2023-01-22 20:40:53.794419: step: 726/470, loss: 0.06855201721191406
2023-01-22 20:40:54.479818: step: 728/470, loss: 0.006867049727588892
2023-01-22 20:40:55.235549: step: 730/470, loss: 0.004258542787283659
2023-01-22 20:40:55.903814: step: 732/470, loss: 0.0028415187261998653
2023-01-22 20:40:56.621502: step: 734/470, loss: 0.0037412350066006184
2023-01-22 20:40:57.399961: step: 736/470, loss: 0.0005636032437905669
2023-01-22 20:40:58.098729: step: 738/470, loss: 0.03270193934440613
2023-01-22 20:40:58.810039: step: 740/470, loss: 0.023219116032123566
2023-01-22 20:40:59.533219: step: 742/470, loss: 0.01399591937661171
2023-01-22 20:41:00.223308: step: 744/470, loss: 0.12446845322847366
2023-01-22 20:41:00.906887: step: 746/470, loss: 0.0018124807393178344
2023-01-22 20:41:01.708465: step: 748/470, loss: 0.025428785011172295
2023-01-22 20:41:02.384321: step: 750/470, loss: 0.005672887898981571
2023-01-22 20:41:03.090911: step: 752/470, loss: 0.002514556283131242
2023-01-22 20:41:03.922155: step: 754/470, loss: 0.016503768041729927
2023-01-22 20:41:04.809953: step: 756/470, loss: 0.001229889108799398
2023-01-22 20:41:05.433043: step: 758/470, loss: 0.008788308128714561
2023-01-22 20:41:06.225132: step: 760/470, loss: 0.030882153660058975
2023-01-22 20:41:06.926501: step: 762/470, loss: 0.027840539813041687
2023-01-22 20:41:07.703456: step: 764/470, loss: 0.0054314760491251945
2023-01-22 20:41:08.468642: step: 766/470, loss: 0.021803250536322594
2023-01-22 20:41:09.222582: step: 768/470, loss: 0.030251774936914444
2023-01-22 20:41:09.914955: step: 770/470, loss: 0.10658083856105804
2023-01-22 20:41:10.603435: step: 772/470, loss: 0.08436030149459839
2023-01-22 20:41:11.331992: step: 774/470, loss: 0.0032615482341498137
2023-01-22 20:41:11.991390: step: 776/470, loss: 0.01066649705171585
2023-01-22 20:41:12.743036: step: 778/470, loss: 0.009199859574437141
2023-01-22 20:41:13.495370: step: 780/470, loss: 0.018781311810016632
2023-01-22 20:41:14.204349: step: 782/470, loss: 0.020045407116413116
2023-01-22 20:41:14.953809: step: 784/470, loss: 0.02236953005194664
2023-01-22 20:41:15.717375: step: 786/470, loss: 0.01765470579266548
2023-01-22 20:41:16.459155: step: 788/470, loss: 0.18303386867046356
2023-01-22 20:41:17.286812: step: 790/470, loss: 0.004157851915806532
2023-01-22 20:41:17.971952: step: 792/470, loss: 0.017420660704374313
2023-01-22 20:41:18.744735: step: 794/470, loss: 0.026377053931355476
2023-01-22 20:41:19.453197: step: 796/470, loss: 0.057920631021261215
2023-01-22 20:41:20.210181: step: 798/470, loss: 0.015336936339735985
2023-01-22 20:41:20.945814: step: 800/470, loss: 0.19589649140834808
2023-01-22 20:41:21.586634: step: 802/470, loss: 0.08331488817930222
2023-01-22 20:41:22.358102: step: 804/470, loss: 0.1330551952123642
2023-01-22 20:41:23.079908: step: 806/470, loss: 0.007211843505501747
2023-01-22 20:41:23.810001: step: 808/470, loss: 0.024340027943253517
2023-01-22 20:41:24.605575: step: 810/470, loss: 0.04757057875394821
2023-01-22 20:41:25.310069: step: 812/470, loss: 0.01020081341266632
2023-01-22 20:41:26.027497: step: 814/470, loss: 0.041293397545814514
2023-01-22 20:41:26.758531: step: 816/470, loss: 0.02104293741285801
2023-01-22 20:41:27.570706: step: 818/470, loss: 0.08056701719760895
2023-01-22 20:41:28.397096: step: 820/470, loss: 0.013175521977245808
2023-01-22 20:41:29.119731: step: 822/470, loss: 0.04553241282701492
2023-01-22 20:41:29.872215: step: 824/470, loss: 0.07833508402109146
2023-01-22 20:41:30.640055: step: 826/470, loss: 0.027197131887078285
2023-01-22 20:41:31.361715: step: 828/470, loss: 0.007502416614443064
2023-01-22 20:41:32.101944: step: 830/470, loss: 0.04629238322377205
2023-01-22 20:41:32.792345: step: 832/470, loss: 0.0031321379356086254
2023-01-22 20:41:33.474807: step: 834/470, loss: 0.007129800971597433
2023-01-22 20:41:34.172901: step: 836/470, loss: 0.019213836640119553
2023-01-22 20:41:34.866521: step: 838/470, loss: 0.003881721990182996
2023-01-22 20:41:35.750475: step: 840/470, loss: 0.02087746188044548
2023-01-22 20:41:36.446506: step: 842/470, loss: 0.001440670806914568
2023-01-22 20:41:37.150504: step: 844/470, loss: 0.011802955530583858
2023-01-22 20:41:37.860192: step: 846/470, loss: 0.0013450667029246688
2023-01-22 20:41:38.559484: step: 848/470, loss: 0.03148926421999931
2023-01-22 20:41:39.316664: step: 850/470, loss: 0.08651398122310638
2023-01-22 20:41:40.173644: step: 852/470, loss: 0.03913048282265663
2023-01-22 20:41:40.872667: step: 854/470, loss: 0.04345300793647766
2023-01-22 20:41:41.586625: step: 856/470, loss: 0.0018893154338002205
2023-01-22 20:41:42.235740: step: 858/470, loss: 8.755026647122577e-05
2023-01-22 20:41:42.987367: step: 860/470, loss: 0.02182687819004059
2023-01-22 20:41:43.717046: step: 862/470, loss: 0.013897470198571682
2023-01-22 20:41:44.439308: step: 864/470, loss: 0.00483159814029932
2023-01-22 20:41:45.186610: step: 866/470, loss: 0.009607330895960331
2023-01-22 20:41:45.886974: step: 868/470, loss: 0.015445969067513943
2023-01-22 20:41:46.649619: step: 870/470, loss: 0.032280661165714264
2023-01-22 20:41:47.378711: step: 872/470, loss: 0.09819857031106949
2023-01-22 20:41:48.140486: step: 874/470, loss: 0.022332623600959778
2023-01-22 20:41:48.871953: step: 876/470, loss: 0.05316994711756706
2023-01-22 20:41:49.598705: step: 878/470, loss: 0.09301023185253143
2023-01-22 20:41:50.317124: step: 880/470, loss: 0.014414233155548573
2023-01-22 20:41:51.018804: step: 882/470, loss: 0.7137559056282043
2023-01-22 20:41:51.790709: step: 884/470, loss: 0.020797649398446083
2023-01-22 20:41:52.553567: step: 886/470, loss: 0.05245582386851311
2023-01-22 20:41:53.340186: step: 888/470, loss: 0.09029704332351685
2023-01-22 20:41:53.970646: step: 890/470, loss: 0.007554202806204557
2023-01-22 20:41:54.697488: step: 892/470, loss: 0.03437653183937073
2023-01-22 20:41:55.396609: step: 894/470, loss: 0.0020255944691598415
2023-01-22 20:41:56.150835: step: 896/470, loss: 0.11641070246696472
2023-01-22 20:41:56.905817: step: 898/470, loss: 0.11411511898040771
2023-01-22 20:41:57.614084: step: 900/470, loss: 0.028752509504556656
2023-01-22 20:41:58.320294: step: 902/470, loss: 0.020708488300442696
2023-01-22 20:41:59.069449: step: 904/470, loss: 0.06170295178890228
2023-01-22 20:42:00.055692: step: 906/470, loss: 0.030286438763141632
2023-01-22 20:42:00.848525: step: 908/470, loss: 0.011742115952074528
2023-01-22 20:42:01.557945: step: 910/470, loss: 0.008268856443464756
2023-01-22 20:42:02.280046: step: 912/470, loss: 0.07056379318237305
2023-01-22 20:42:02.922464: step: 914/470, loss: 0.0315357968211174
2023-01-22 20:42:03.685751: step: 916/470, loss: 0.032394226640462875
2023-01-22 20:42:04.450501: step: 918/470, loss: 0.012661329470574856
2023-01-22 20:42:05.141393: step: 920/470, loss: 0.06156188249588013
2023-01-22 20:42:05.909339: step: 922/470, loss: 0.0035831385757774115
2023-01-22 20:42:06.667105: step: 924/470, loss: 0.00764728058129549
2023-01-22 20:42:07.462860: step: 926/470, loss: 0.026822997257113457
2023-01-22 20:42:08.211212: step: 928/470, loss: 0.01422158908098936
2023-01-22 20:42:08.996720: step: 930/470, loss: 0.012633465230464935
2023-01-22 20:42:09.739066: step: 932/470, loss: 0.0021819123066961765
2023-01-22 20:42:10.446534: step: 934/470, loss: 0.09248220920562744
2023-01-22 20:42:11.134435: step: 936/470, loss: 0.019571691751480103
2023-01-22 20:42:11.847682: step: 938/470, loss: 0.37316635251045227
2023-01-22 20:42:12.674491: step: 940/470, loss: 0.016227828338742256
2023-01-22 20:42:13.349375: step: 942/470, loss: 0.004429019521921873
==================================================
Loss: 0.044
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2982536367953035, 'r': 0.3361720308470783, 'f1': 0.31607967931562936}, 'combined': 0.23290081633783213, 'epoch': 29}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.36339379413674205, 'r': 0.34242876755193, 'f1': 0.3525999190633735}, 'combined': 0.24559198342722535, 'epoch': 29}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29809959887155074, 'r': 0.337695371017677, 'f1': 0.31666452050945865}, 'combined': 0.23333175195433795, 'epoch': 29}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3720185925866563, 'r': 0.34483261851301605, 'f1': 0.35791010304744186}, 'combined': 0.24929061903801922, 'epoch': 29}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28678933021806857, 'r': 0.3493714421252372, 'f1': 0.3150021385799829}, 'combined': 0.2321068389536716, 'epoch': 29}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35292353630625145, 'r': 0.3444397974527358, 'f1': 0.34863006262855983}, 'combined': 0.24282690929352427, 'epoch': 29}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23863636363636365, 'r': 0.375, 'f1': 0.2916666666666667}, 'combined': 0.19444444444444445, 'epoch': 29}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.28125, 'r': 0.4891304347826087, 'f1': 0.3571428571428572}, 'combined': 0.1785714285714286, 'epoch': 29}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.40625, 'r': 0.33620689655172414, 'f1': 0.36792452830188677}, 'combined': 0.2452830188679245, 'epoch': 29}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 30
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 20:44:47.661825: step: 2/470, loss: 0.0015534983249381185
2023-01-22 20:44:48.355499: step: 4/470, loss: 0.0009303026017732918
2023-01-22 20:44:49.067052: step: 6/470, loss: 0.07198537886142731
2023-01-22 20:44:49.803204: step: 8/470, loss: 0.0074896845035254955
2023-01-22 20:44:50.581579: step: 10/470, loss: 0.0020844112150371075
2023-01-22 20:44:51.362441: step: 12/470, loss: 0.3400344252586365
2023-01-22 20:44:52.070892: step: 14/470, loss: 0.019580742344260216
2023-01-22 20:44:52.800474: step: 16/470, loss: 0.005592713598161936
2023-01-22 20:44:53.505049: step: 18/470, loss: 0.004001240245997906
2023-01-22 20:44:54.271968: step: 20/470, loss: 0.04294969141483307
2023-01-22 20:44:55.000824: step: 22/470, loss: 0.030762318521738052
2023-01-22 20:44:55.730100: step: 24/470, loss: 0.07296521216630936
2023-01-22 20:44:56.407008: step: 26/470, loss: 0.019644813612103462
2023-01-22 20:44:57.170784: step: 28/470, loss: 0.0019523368682712317
2023-01-22 20:44:57.871869: step: 30/470, loss: 0.004232059698551893
2023-01-22 20:44:58.605159: step: 32/470, loss: 0.00470116687938571
2023-01-22 20:44:59.342501: step: 34/470, loss: 3.0470375349977985e-05
2023-01-22 20:45:00.140991: step: 36/470, loss: 0.014174572192132473
2023-01-22 20:45:00.926519: step: 38/470, loss: 0.049307264387607574
2023-01-22 20:45:01.667213: step: 40/470, loss: 0.0007710535428486764
2023-01-22 20:45:02.387084: step: 42/470, loss: 0.004445178434252739
2023-01-22 20:45:03.128753: step: 44/470, loss: 0.006911000236868858
2023-01-22 20:45:03.793861: step: 46/470, loss: 0.007463586516678333
2023-01-22 20:45:04.572121: step: 48/470, loss: 0.00076903315493837
2023-01-22 20:45:05.394731: step: 50/470, loss: 0.03810786083340645
2023-01-22 20:45:06.135279: step: 52/470, loss: 0.029291216284036636
2023-01-22 20:45:06.805275: step: 54/470, loss: 0.00221418053843081
2023-01-22 20:45:07.591242: step: 56/470, loss: 0.0012072960380464792
2023-01-22 20:45:08.371498: step: 58/470, loss: 0.015327895060181618
2023-01-22 20:45:09.096380: step: 60/470, loss: 0.0036242054775357246
2023-01-22 20:45:09.851304: step: 62/470, loss: 0.039196036756038666
2023-01-22 20:45:10.542637: step: 64/470, loss: 0.004683348350226879
2023-01-22 20:45:11.251190: step: 66/470, loss: 0.005313752684742212
2023-01-22 20:45:12.002100: step: 68/470, loss: 0.003183474065735936
2023-01-22 20:45:12.679299: step: 70/470, loss: 0.042856525629758835
2023-01-22 20:45:13.304761: step: 72/470, loss: 0.015468944795429707
2023-01-22 20:45:13.955509: step: 74/470, loss: 0.003673919942229986
2023-01-22 20:45:14.621676: step: 76/470, loss: 0.0050133909098804
2023-01-22 20:45:15.310416: step: 78/470, loss: 0.0003503368643578142
2023-01-22 20:45:16.004789: step: 80/470, loss: 0.00029192844522185624
2023-01-22 20:45:16.756129: step: 82/470, loss: 0.002908646361902356
2023-01-22 20:45:17.534570: step: 84/470, loss: 0.041369758546352386
2023-01-22 20:45:18.312161: step: 86/470, loss: 0.011434613727033138
2023-01-22 20:45:19.049982: step: 88/470, loss: 0.014062466099858284
2023-01-22 20:45:19.798359: step: 90/470, loss: 0.012946287170052528
2023-01-22 20:45:20.533506: step: 92/470, loss: 0.0006630457355640829
2023-01-22 20:45:21.227837: step: 94/470, loss: 0.02848971076309681
2023-01-22 20:45:21.913872: step: 96/470, loss: 0.0033628770615905523
2023-01-22 20:45:22.655508: step: 98/470, loss: 0.02601010911166668
2023-01-22 20:45:23.376951: step: 100/470, loss: 0.13308343291282654
2023-01-22 20:45:24.142190: step: 102/470, loss: 0.02286795899271965
2023-01-22 20:45:24.976789: step: 104/470, loss: 0.006091211922466755
2023-01-22 20:45:25.669383: step: 106/470, loss: 0.0013653002679347992
2023-01-22 20:45:26.437125: step: 108/470, loss: 0.008479597978293896
2023-01-22 20:45:27.176479: step: 110/470, loss: 0.035104185342788696
2023-01-22 20:45:27.855116: step: 112/470, loss: 0.01217788178473711
2023-01-22 20:45:28.530420: step: 114/470, loss: 0.009542414918541908
2023-01-22 20:45:29.245998: step: 116/470, loss: 0.0510413832962513
2023-01-22 20:45:29.882435: step: 118/470, loss: 0.010977623052895069
2023-01-22 20:45:30.578323: step: 120/470, loss: 0.008249633945524693
2023-01-22 20:45:31.324208: step: 122/470, loss: 0.013754217885434628
2023-01-22 20:45:32.098874: step: 124/470, loss: 0.000642959144897759
2023-01-22 20:45:32.839060: step: 126/470, loss: 0.01749761775135994
2023-01-22 20:45:33.509737: step: 128/470, loss: 0.033281996846199036
2023-01-22 20:45:34.260971: step: 130/470, loss: 0.0049248565919697285
2023-01-22 20:45:34.956581: step: 132/470, loss: 0.080209881067276
2023-01-22 20:45:35.633898: step: 134/470, loss: 0.0143387196585536
2023-01-22 20:45:36.361031: step: 136/470, loss: 0.04557420313358307
2023-01-22 20:45:37.089683: step: 138/470, loss: 0.005927293561398983
2023-01-22 20:45:37.738272: step: 140/470, loss: 0.004758467432111502
2023-01-22 20:45:38.541297: step: 142/470, loss: 0.01647905260324478
2023-01-22 20:45:39.252114: step: 144/470, loss: 0.0004897841135971248
2023-01-22 20:45:39.988120: step: 146/470, loss: 0.2584097981452942
2023-01-22 20:45:40.715477: step: 148/470, loss: 0.01904984377324581
2023-01-22 20:45:41.408009: step: 150/470, loss: 0.000754874141421169
2023-01-22 20:45:42.088476: step: 152/470, loss: 0.0361163467168808
2023-01-22 20:45:42.911963: step: 154/470, loss: 0.046868957579135895
2023-01-22 20:45:43.585101: step: 156/470, loss: 0.006643644534051418
2023-01-22 20:45:44.355359: step: 158/470, loss: 0.03360613062977791
2023-01-22 20:45:45.052620: step: 160/470, loss: 0.0265851728618145
2023-01-22 20:45:45.743429: step: 162/470, loss: 0.002698094118386507
2023-01-22 20:45:46.436081: step: 164/470, loss: 0.0029194336384534836
2023-01-22 20:45:47.135798: step: 166/470, loss: 0.00015936991258058697
2023-01-22 20:45:47.876267: step: 168/470, loss: 0.011427337303757668
2023-01-22 20:45:48.591180: step: 170/470, loss: 0.0039392574690282345
2023-01-22 20:45:49.397781: step: 172/470, loss: 0.002686795312911272
2023-01-22 20:45:50.131010: step: 174/470, loss: 0.0013270019553601742
2023-01-22 20:45:50.869367: step: 176/470, loss: 0.0032820103224366903
2023-01-22 20:45:51.563144: step: 178/470, loss: 0.008707202039659023
2023-01-22 20:45:52.284792: step: 180/470, loss: 0.07832004129886627
2023-01-22 20:45:52.951226: step: 182/470, loss: 0.00024435168597847223
2023-01-22 20:45:53.618364: step: 184/470, loss: 0.019537262618541718
2023-01-22 20:45:54.414749: step: 186/470, loss: 0.024349162355065346
2023-01-22 20:45:55.133581: step: 188/470, loss: 0.026107704266905785
2023-01-22 20:45:55.832462: step: 190/470, loss: 0.2534019351005554
2023-01-22 20:45:56.526296: step: 192/470, loss: 0.022054988890886307
2023-01-22 20:45:57.165438: step: 194/470, loss: 0.00017441021918784827
2023-01-22 20:45:57.825309: step: 196/470, loss: 0.0004912808071821928
2023-01-22 20:45:58.533013: step: 198/470, loss: 0.006434681825339794
2023-01-22 20:45:59.293754: step: 200/470, loss: 0.041142772883176804
2023-01-22 20:46:00.032549: step: 202/470, loss: 0.010733246803283691
2023-01-22 20:46:00.702982: step: 204/470, loss: 0.00284022931009531
2023-01-22 20:46:01.450498: step: 206/470, loss: 0.04028492793440819
2023-01-22 20:46:02.295791: step: 208/470, loss: 0.04366816207766533
2023-01-22 20:46:02.944340: step: 210/470, loss: 0.002009680727496743
2023-01-22 20:46:03.637073: step: 212/470, loss: 0.04488565772771835
2023-01-22 20:46:04.353762: step: 214/470, loss: 0.004889700096100569
2023-01-22 20:46:05.064867: step: 216/470, loss: 0.029589461162686348
2023-01-22 20:46:05.823836: step: 218/470, loss: 0.08454018831253052
2023-01-22 20:46:06.564183: step: 220/470, loss: 0.015738148242235184
2023-01-22 20:46:07.296765: step: 222/470, loss: 3.354827404022217
2023-01-22 20:46:08.027491: step: 224/470, loss: 0.0028114912565797567
2023-01-22 20:46:08.722156: step: 226/470, loss: 0.03550800308585167
2023-01-22 20:46:09.435183: step: 228/470, loss: 0.044054701924324036
2023-01-22 20:46:10.150305: step: 230/470, loss: 0.09976823627948761
2023-01-22 20:46:10.914555: step: 232/470, loss: 0.008051842451095581
2023-01-22 20:46:11.689709: step: 234/470, loss: 0.08605451136827469
2023-01-22 20:46:12.455805: step: 236/470, loss: 0.0013634329661726952
2023-01-22 20:46:13.169370: step: 238/470, loss: 0.0263601616024971
2023-01-22 20:46:13.841178: step: 240/470, loss: 0.05547104775905609
2023-01-22 20:46:14.589103: step: 242/470, loss: 0.03622487559914589
2023-01-22 20:46:15.259899: step: 244/470, loss: 0.0007956080371513963
2023-01-22 20:46:15.991477: step: 246/470, loss: 0.0422469861805439
2023-01-22 20:46:16.783412: step: 248/470, loss: 0.019485946744680405
2023-01-22 20:46:17.474721: step: 250/470, loss: 4.62792013422586e-05
2023-01-22 20:46:18.311880: step: 252/470, loss: 0.011375891044735909
2023-01-22 20:46:19.024136: step: 254/470, loss: 0.027469327673316002
2023-01-22 20:46:19.738651: step: 256/470, loss: 0.0730309933423996
2023-01-22 20:46:20.575812: step: 258/470, loss: 0.1251501590013504
2023-01-22 20:46:21.615998: step: 260/470, loss: 0.0181076992303133
2023-01-22 20:46:22.369170: step: 262/470, loss: 0.7937953472137451
2023-01-22 20:46:23.115106: step: 264/470, loss: 0.004769394174218178
2023-01-22 20:46:23.868724: step: 266/470, loss: 0.03229885548353195
2023-01-22 20:46:24.549347: step: 268/470, loss: 0.007303445599973202
2023-01-22 20:46:25.335645: step: 270/470, loss: 0.058055225759744644
2023-01-22 20:46:26.090814: step: 272/470, loss: 0.34732547402381897
2023-01-22 20:46:26.721615: step: 274/470, loss: 0.015425494872033596
2023-01-22 20:46:27.406499: step: 276/470, loss: 0.012530090287327766
2023-01-22 20:46:28.212877: step: 278/470, loss: 0.015414786525070667
2023-01-22 20:46:29.045453: step: 280/470, loss: 0.031069021672010422
2023-01-22 20:46:29.712441: step: 282/470, loss: 0.026498055085539818
2023-01-22 20:46:30.497457: step: 284/470, loss: 0.004659529775381088
2023-01-22 20:46:31.322238: step: 286/470, loss: 0.02883639559149742
2023-01-22 20:46:32.103038: step: 288/470, loss: 0.0019614913035184145
2023-01-22 20:46:33.501559: step: 290/470, loss: 0.021054117009043694
2023-01-22 20:46:34.219821: step: 292/470, loss: 0.0282586757093668
2023-01-22 20:46:34.953145: step: 294/470, loss: 0.05488167703151703
2023-01-22 20:46:35.815543: step: 296/470, loss: 0.0710349828004837
2023-01-22 20:46:36.510015: step: 298/470, loss: 0.028987431898713112
2023-01-22 20:46:37.216404: step: 300/470, loss: 0.017589028924703598
2023-01-22 20:46:38.005538: step: 302/470, loss: 0.03203602880239487
2023-01-22 20:46:38.720889: step: 304/470, loss: 0.024194780737161636
2023-01-22 20:46:39.456805: step: 306/470, loss: 0.0027428928297013044
2023-01-22 20:46:40.099745: step: 308/470, loss: 0.08572112768888474
2023-01-22 20:46:40.969056: step: 310/470, loss: 0.06660182774066925
2023-01-22 20:46:41.722470: step: 312/470, loss: 0.09423809498548508
2023-01-22 20:46:42.515868: step: 314/470, loss: 0.03433975949883461
2023-01-22 20:46:43.370597: step: 316/470, loss: 0.04957527294754982
2023-01-22 20:46:44.081701: step: 318/470, loss: 0.0038216973189264536
2023-01-22 20:46:44.850976: step: 320/470, loss: 0.0018495884723961353
2023-01-22 20:46:45.607231: step: 322/470, loss: 0.14368680119514465
2023-01-22 20:46:46.302704: step: 324/470, loss: 0.002256029052659869
2023-01-22 20:46:47.038855: step: 326/470, loss: 0.017123982310295105
2023-01-22 20:46:47.704962: step: 328/470, loss: 0.18741732835769653
2023-01-22 20:46:48.424522: step: 330/470, loss: 0.014922713860869408
2023-01-22 20:46:49.147669: step: 332/470, loss: 0.03767160698771477
2023-01-22 20:46:49.871092: step: 334/470, loss: 0.05126776546239853
2023-01-22 20:46:50.520654: step: 336/470, loss: 0.01508275605738163
2023-01-22 20:46:51.224086: step: 338/470, loss: 0.00034520160988904536
2023-01-22 20:46:51.957508: step: 340/470, loss: 0.04148537665605545
2023-01-22 20:46:52.605053: step: 342/470, loss: 5.96605495957192e-05
2023-01-22 20:46:53.347545: step: 344/470, loss: 0.005885576829314232
2023-01-22 20:46:54.038121: step: 346/470, loss: 0.008368241600692272
2023-01-22 20:46:54.698149: step: 348/470, loss: 0.015697935596108437
2023-01-22 20:46:55.532463: step: 350/470, loss: 0.019847042858600616
2023-01-22 20:46:56.281820: step: 352/470, loss: 0.02182493358850479
2023-01-22 20:46:57.012362: step: 354/470, loss: 0.01692495495080948
2023-01-22 20:46:57.765699: step: 356/470, loss: 0.011305560357868671
2023-01-22 20:46:58.455365: step: 358/470, loss: 0.0026786348316818476
2023-01-22 20:46:59.177438: step: 360/470, loss: 0.0002164768666261807
2023-01-22 20:46:59.850537: step: 362/470, loss: 0.6910086870193481
2023-01-22 20:47:00.592094: step: 364/470, loss: 0.00040226319106295705
2023-01-22 20:47:01.295548: step: 366/470, loss: 0.016148222610354424
2023-01-22 20:47:01.981458: step: 368/470, loss: 0.027793431654572487
2023-01-22 20:47:02.716871: step: 370/470, loss: 0.006164975464344025
2023-01-22 20:47:03.404705: step: 372/470, loss: 0.01071165595203638
2023-01-22 20:47:04.093419: step: 374/470, loss: 0.0014239969896152616
2023-01-22 20:47:04.802829: step: 376/470, loss: 0.0013824844500049949
2023-01-22 20:47:05.560564: step: 378/470, loss: 0.004417424090206623
2023-01-22 20:47:06.300972: step: 380/470, loss: 0.02893391251564026
2023-01-22 20:47:06.999956: step: 382/470, loss: 0.030614320188760757
2023-01-22 20:47:07.687765: step: 384/470, loss: 0.001032169908285141
2023-01-22 20:47:08.393060: step: 386/470, loss: 0.007282666862010956
2023-01-22 20:47:09.090288: step: 388/470, loss: 0.01349354162812233
2023-01-22 20:47:09.815777: step: 390/470, loss: 0.015124008990824223
2023-01-22 20:47:10.511770: step: 392/470, loss: 0.013127674348652363
2023-01-22 20:47:11.160859: step: 394/470, loss: 0.032045748084783554
2023-01-22 20:47:11.900064: step: 396/470, loss: 0.2856377959251404
2023-01-22 20:47:12.628678: step: 398/470, loss: 0.020067989826202393
2023-01-22 20:47:13.398377: step: 400/470, loss: 0.008606786839663982
2023-01-22 20:47:14.150353: step: 402/470, loss: 0.018849369138479233
2023-01-22 20:47:14.847754: step: 404/470, loss: 0.002814099658280611
2023-01-22 20:47:15.507539: step: 406/470, loss: 0.0020936380606144667
2023-01-22 20:47:16.382521: step: 408/470, loss: 0.011628488078713417
2023-01-22 20:47:17.122558: step: 410/470, loss: 0.007815473712980747
2023-01-22 20:47:17.808244: step: 412/470, loss: 0.002352564362809062
2023-01-22 20:47:18.521671: step: 414/470, loss: 0.03523825854063034
2023-01-22 20:47:19.230383: step: 416/470, loss: 0.006999637931585312
2023-01-22 20:47:19.985245: step: 418/470, loss: 0.024556517601013184
2023-01-22 20:47:20.754710: step: 420/470, loss: 0.0016526913968846202
2023-01-22 20:47:21.486517: step: 422/470, loss: 0.013159074820578098
2023-01-22 20:47:22.144096: step: 424/470, loss: 0.023464815691113472
2023-01-22 20:47:22.912560: step: 426/470, loss: 0.0028531746938824654
2023-01-22 20:47:23.588840: step: 428/470, loss: 0.036497414112091064
2023-01-22 20:47:24.362934: step: 430/470, loss: 0.004592817276716232
2023-01-22 20:47:25.078784: step: 432/470, loss: 0.0013164383126422763
2023-01-22 20:47:25.754106: step: 434/470, loss: 0.00658793468028307
2023-01-22 20:47:26.529145: step: 436/470, loss: 0.514223575592041
2023-01-22 20:47:27.222954: step: 438/470, loss: 0.003137575928121805
2023-01-22 20:47:28.006668: step: 440/470, loss: 0.04794734716415405
2023-01-22 20:47:28.698045: step: 442/470, loss: 0.007328708656132221
2023-01-22 20:47:29.458615: step: 444/470, loss: 0.005198894999921322
2023-01-22 20:47:30.229576: step: 446/470, loss: 0.006771470420062542
2023-01-22 20:47:30.941573: step: 448/470, loss: 0.017400279641151428
2023-01-22 20:47:31.602541: step: 450/470, loss: 0.025920528918504715
2023-01-22 20:47:32.262941: step: 452/470, loss: 0.0040763262659311295
2023-01-22 20:47:32.981512: step: 454/470, loss: 0.02771720290184021
2023-01-22 20:47:33.774230: step: 456/470, loss: 0.007550915703177452
2023-01-22 20:47:34.508670: step: 458/470, loss: 0.021621685475111008
2023-01-22 20:47:35.229054: step: 460/470, loss: 0.022162331268191338
2023-01-22 20:47:35.968726: step: 462/470, loss: 0.0016908899415284395
2023-01-22 20:47:36.666130: step: 464/470, loss: 0.008422368206083775
2023-01-22 20:47:37.399586: step: 466/470, loss: 0.04641232267022133
2023-01-22 20:47:38.111515: step: 468/470, loss: 0.004679789766669273
2023-01-22 20:47:38.866675: step: 470/470, loss: 0.01792057789862156
2023-01-22 20:47:39.643019: step: 472/470, loss: 0.0020182339940220118
2023-01-22 20:47:40.437586: step: 474/470, loss: 0.011343245394527912
2023-01-22 20:47:41.215020: step: 476/470, loss: 0.08873055130243301
2023-01-22 20:47:41.997815: step: 478/470, loss: 0.007021929137408733
2023-01-22 20:47:42.682791: step: 480/470, loss: 0.0010284853633493185
2023-01-22 20:47:43.430322: step: 482/470, loss: 0.002863482804968953
2023-01-22 20:47:44.217794: step: 484/470, loss: 0.00471901660785079
2023-01-22 20:47:44.945322: step: 486/470, loss: 0.1730116307735443
2023-01-22 20:47:45.746614: step: 488/470, loss: 0.005156666971743107
2023-01-22 20:47:46.438969: step: 490/470, loss: 0.0037299960386008024
2023-01-22 20:47:47.090241: step: 492/470, loss: 0.003205210203304887
2023-01-22 20:47:47.899580: step: 494/470, loss: 0.008830721490085125
2023-01-22 20:47:48.623992: step: 496/470, loss: 0.06417898088693619
2023-01-22 20:47:49.401900: step: 498/470, loss: 0.04083579033613205
2023-01-22 20:47:50.188814: step: 500/470, loss: 3.602713108062744
2023-01-22 20:47:50.987243: step: 502/470, loss: 0.004617447033524513
2023-01-22 20:47:51.690368: step: 504/470, loss: 0.028277534991502762
2023-01-22 20:47:52.433486: step: 506/470, loss: 0.03145125135779381
2023-01-22 20:47:53.168478: step: 508/470, loss: 0.014155956916511059
2023-01-22 20:47:53.896219: step: 510/470, loss: 0.022612107917666435
2023-01-22 20:47:54.647610: step: 512/470, loss: 0.009106074459850788
2023-01-22 20:47:55.420447: step: 514/470, loss: 0.027399810031056404
2023-01-22 20:47:56.253327: step: 516/470, loss: 0.014880353584885597
2023-01-22 20:47:57.085202: step: 518/470, loss: 0.002752532484009862
2023-01-22 20:47:57.900658: step: 520/470, loss: 0.01837068982422352
2023-01-22 20:47:58.640258: step: 522/470, loss: 0.0025046353694051504
2023-01-22 20:47:59.386945: step: 524/470, loss: 0.02363811433315277
2023-01-22 20:48:00.180265: step: 526/470, loss: 0.02377389930188656
2023-01-22 20:48:00.918346: step: 528/470, loss: 0.0021252078004181385
2023-01-22 20:48:01.652068: step: 530/470, loss: 0.011902587488293648
2023-01-22 20:48:02.412345: step: 532/470, loss: 0.0007203198038041592
2023-01-22 20:48:03.117603: step: 534/470, loss: 0.015076599083840847
2023-01-22 20:48:03.912582: step: 536/470, loss: 0.021700425073504448
2023-01-22 20:48:04.621902: step: 538/470, loss: 0.08858056366443634
2023-01-22 20:48:05.366047: step: 540/470, loss: 0.02474750392138958
2023-01-22 20:48:06.041814: step: 542/470, loss: 0.009075379930436611
2023-01-22 20:48:06.737832: step: 544/470, loss: 0.014052581042051315
2023-01-22 20:48:07.507136: step: 546/470, loss: 0.005053224507719278
2023-01-22 20:48:08.264732: step: 548/470, loss: 0.00576430419459939
2023-01-22 20:48:09.040053: step: 550/470, loss: 0.005547594279050827
2023-01-22 20:48:09.826776: step: 552/470, loss: 0.007961531169712543
2023-01-22 20:48:10.575981: step: 554/470, loss: 0.0057564605958759785
2023-01-22 20:48:11.292133: step: 556/470, loss: 0.007082703057676554
2023-01-22 20:48:12.103148: step: 558/470, loss: 0.03066232055425644
2023-01-22 20:48:12.828302: step: 560/470, loss: 0.006466844584792852
2023-01-22 20:48:13.651335: step: 562/470, loss: 0.018887002021074295
2023-01-22 20:48:14.427002: step: 564/470, loss: 0.04409300163388252
2023-01-22 20:48:15.142284: step: 566/470, loss: 0.01083281822502613
2023-01-22 20:48:15.810049: step: 568/470, loss: 0.001143494970165193
2023-01-22 20:48:16.606694: step: 570/470, loss: 0.032482851296663284
2023-01-22 20:48:17.296090: step: 572/470, loss: 0.016237609088420868
2023-01-22 20:48:17.963689: step: 574/470, loss: 0.011964457109570503
2023-01-22 20:48:18.877575: step: 576/470, loss: 0.045262232422828674
2023-01-22 20:48:19.700138: step: 578/470, loss: 0.010416206903755665
2023-01-22 20:48:20.441689: step: 580/470, loss: 0.01974216289818287
2023-01-22 20:48:21.238453: step: 582/470, loss: 0.004339354112744331
2023-01-22 20:48:21.927111: step: 584/470, loss: 0.011843382380902767
2023-01-22 20:48:22.605583: step: 586/470, loss: 0.0004325766349211335
2023-01-22 20:48:23.388904: step: 588/470, loss: 0.011639975011348724
2023-01-22 20:48:24.100224: step: 590/470, loss: 0.01775071956217289
2023-01-22 20:48:24.806365: step: 592/470, loss: 0.028062820434570312
2023-01-22 20:48:25.554360: step: 594/470, loss: 0.01377648115158081
2023-01-22 20:48:26.251332: step: 596/470, loss: 0.0007976947817951441
2023-01-22 20:48:27.032937: step: 598/470, loss: 0.03537141531705856
2023-01-22 20:48:27.742453: step: 600/470, loss: 0.035397402942180634
2023-01-22 20:48:28.532735: step: 602/470, loss: 0.002034268341958523
2023-01-22 20:48:29.248047: step: 604/470, loss: 0.01001753006130457
2023-01-22 20:48:29.932991: step: 606/470, loss: 1.0455894470214844
2023-01-22 20:48:30.777162: step: 608/470, loss: 0.027688954025506973
2023-01-22 20:48:31.604946: step: 610/470, loss: 0.40734100341796875
2023-01-22 20:48:32.258715: step: 612/470, loss: 0.041962411254644394
2023-01-22 20:48:33.046766: step: 614/470, loss: 0.02194126509130001
2023-01-22 20:48:33.759808: step: 616/470, loss: 0.03260621055960655
2023-01-22 20:48:34.495211: step: 618/470, loss: 0.005211520008742809
2023-01-22 20:48:35.263223: step: 620/470, loss: 0.018071891739964485
2023-01-22 20:48:36.013872: step: 622/470, loss: 0.012008518911898136
2023-01-22 20:48:36.620583: step: 624/470, loss: 0.03403551131486893
2023-01-22 20:48:37.390797: step: 626/470, loss: 0.07104015350341797
2023-01-22 20:48:38.094768: step: 628/470, loss: 0.046591900289058685
2023-01-22 20:48:38.825462: step: 630/470, loss: 0.012893665581941605
2023-01-22 20:48:39.550544: step: 632/470, loss: 0.045894332230091095
2023-01-22 20:48:40.290057: step: 634/470, loss: 0.05242696404457092
2023-01-22 20:48:41.078386: step: 636/470, loss: 0.007960853166878223
2023-01-22 20:48:41.812541: step: 638/470, loss: 0.42619752883911133
2023-01-22 20:48:42.623191: step: 640/470, loss: 0.029724212363362312
2023-01-22 20:48:43.365544: step: 642/470, loss: 0.04799468442797661
2023-01-22 20:48:44.030601: step: 644/470, loss: 0.02126733399927616
2023-01-22 20:48:44.767188: step: 646/470, loss: 0.0056076874025166035
2023-01-22 20:48:45.501773: step: 648/470, loss: 9.23870102269575e-05
2023-01-22 20:48:46.245874: step: 650/470, loss: 0.009057758376002312
2023-01-22 20:48:46.923565: step: 652/470, loss: 0.02294195629656315
2023-01-22 20:48:47.712058: step: 654/470, loss: 0.06484882533550262
2023-01-22 20:48:48.443110: step: 656/470, loss: 0.03436193987727165
2023-01-22 20:48:49.194388: step: 658/470, loss: 0.051201097667217255
2023-01-22 20:48:49.907143: step: 660/470, loss: 0.03534897416830063
2023-01-22 20:48:50.631652: step: 662/470, loss: 0.0066528706811368465
2023-01-22 20:48:51.418600: step: 664/470, loss: 0.0037193207535892725
2023-01-22 20:48:52.173810: step: 666/470, loss: 0.0020945665892213583
2023-01-22 20:48:52.890289: step: 668/470, loss: 0.000837851723190397
2023-01-22 20:48:53.588212: step: 670/470, loss: 0.03179018944501877
2023-01-22 20:48:54.395580: step: 672/470, loss: 0.009496787562966347
2023-01-22 20:48:55.118464: step: 674/470, loss: 0.3629489243030548
2023-01-22 20:48:55.818305: step: 676/470, loss: 0.025496546179056168
2023-01-22 20:48:56.548997: step: 678/470, loss: 0.03851151093840599
2023-01-22 20:48:57.322097: step: 680/470, loss: 0.0084996921941638
2023-01-22 20:48:57.963700: step: 682/470, loss: 0.007409407291561365
2023-01-22 20:48:58.679789: step: 684/470, loss: 0.03160090744495392
2023-01-22 20:48:59.425774: step: 686/470, loss: 0.05882648006081581
2023-01-22 20:49:00.204932: step: 688/470, loss: 0.08515594899654388
2023-01-22 20:49:00.931224: step: 690/470, loss: 0.0018482680898159742
2023-01-22 20:49:01.635016: step: 692/470, loss: 0.04133886843919754
2023-01-22 20:49:02.381892: step: 694/470, loss: 0.0130581334233284
2023-01-22 20:49:03.106108: step: 696/470, loss: 0.9888176321983337
2023-01-22 20:49:03.948761: step: 698/470, loss: 0.06412041187286377
2023-01-22 20:49:04.661311: step: 700/470, loss: 0.03894779458642006
2023-01-22 20:49:05.291783: step: 702/470, loss: 0.020089661702513695
2023-01-22 20:49:05.951431: step: 704/470, loss: 0.017173096537590027
2023-01-22 20:49:06.694998: step: 706/470, loss: 0.005728584248572588
2023-01-22 20:49:07.423756: step: 708/470, loss: 0.04380139708518982
2023-01-22 20:49:08.137484: step: 710/470, loss: 0.0069374158047139645
2023-01-22 20:49:08.756823: step: 712/470, loss: 0.023490410298109055
2023-01-22 20:49:09.511372: step: 714/470, loss: 0.058307942003011703
2023-01-22 20:49:10.172438: step: 716/470, loss: 0.005838301964104176
2023-01-22 20:49:10.915286: step: 718/470, loss: 0.025616277009248734
2023-01-22 20:49:11.656754: step: 720/470, loss: 0.0021177027374505997
2023-01-22 20:49:12.366869: step: 722/470, loss: 0.07428384572267532
2023-01-22 20:49:13.123926: step: 724/470, loss: 0.14311569929122925
2023-01-22 20:49:13.901308: step: 726/470, loss: 0.007042250130325556
2023-01-22 20:49:14.635285: step: 728/470, loss: 0.0038853702135384083
2023-01-22 20:49:15.380285: step: 730/470, loss: 0.044650763273239136
2023-01-22 20:49:16.029284: step: 732/470, loss: 0.0028803348541259766
2023-01-22 20:49:16.730765: step: 734/470, loss: 0.002466881647706032
2023-01-22 20:49:17.436678: step: 736/470, loss: 0.02306767739355564
2023-01-22 20:49:18.178069: step: 738/470, loss: 0.1385963410139084
2023-01-22 20:49:18.885714: step: 740/470, loss: 0.024905715137720108
2023-01-22 20:49:19.668094: step: 742/470, loss: 0.010221011936664581
2023-01-22 20:49:20.351397: step: 744/470, loss: 0.002917324658483267
2023-01-22 20:49:21.042854: step: 746/470, loss: 0.010492140427231789
2023-01-22 20:49:21.738155: step: 748/470, loss: 0.036397598683834076
2023-01-22 20:49:22.499601: step: 750/470, loss: 0.020658204331994057
2023-01-22 20:49:23.304067: step: 752/470, loss: 0.004349207505583763
2023-01-22 20:49:24.000943: step: 754/470, loss: 0.04205322265625
2023-01-22 20:49:24.699219: step: 756/470, loss: 0.015505963005125523
2023-01-22 20:49:25.342653: step: 758/470, loss: 0.002480144612491131
2023-01-22 20:49:26.062493: step: 760/470, loss: 0.054736074060201645
2023-01-22 20:49:26.810274: step: 762/470, loss: 0.012036191299557686
2023-01-22 20:49:27.481973: step: 764/470, loss: 0.01874772645533085
2023-01-22 20:49:28.203744: step: 766/470, loss: 0.03384104743599892
2023-01-22 20:49:28.922447: step: 768/470, loss: 0.010049944743514061
2023-01-22 20:49:29.594926: step: 770/470, loss: 0.03430037200450897
2023-01-22 20:49:30.298239: step: 772/470, loss: 0.0023346322122961283
2023-01-22 20:49:30.970698: step: 774/470, loss: 0.29529932141304016
2023-01-22 20:49:31.726150: step: 776/470, loss: 0.019421333447098732
2023-01-22 20:49:32.450054: step: 778/470, loss: 0.003084076102823019
2023-01-22 20:49:33.167352: step: 780/470, loss: 0.10002864897251129
2023-01-22 20:49:33.955800: step: 782/470, loss: 0.002307226648554206
2023-01-22 20:49:34.643197: step: 784/470, loss: 0.017811257392168045
2023-01-22 20:49:35.345186: step: 786/470, loss: 0.015748564153909683
2023-01-22 20:49:36.118704: step: 788/470, loss: 0.03216710314154625
2023-01-22 20:49:36.867089: step: 790/470, loss: 0.0009349191677756608
2023-01-22 20:49:37.668398: step: 792/470, loss: 0.004412441980093718
2023-01-22 20:49:38.414846: step: 794/470, loss: 0.006835710722953081
2023-01-22 20:49:39.166142: step: 796/470, loss: 0.008032741025090218
2023-01-22 20:49:39.838418: step: 798/470, loss: 0.0019889273680746555
2023-01-22 20:49:40.562116: step: 800/470, loss: 0.008295338600873947
2023-01-22 20:49:41.336332: step: 802/470, loss: 0.01602669060230255
2023-01-22 20:49:42.123478: step: 804/470, loss: 0.03637155890464783
2023-01-22 20:49:42.819486: step: 806/470, loss: 0.040701597929000854
2023-01-22 20:49:43.644031: step: 808/470, loss: 0.005965395364910364
2023-01-22 20:49:44.355301: step: 810/470, loss: 0.010988143272697926
2023-01-22 20:49:45.165892: step: 812/470, loss: 0.09173979610204697
2023-01-22 20:49:45.827460: step: 814/470, loss: 0.004171342588961124
2023-01-22 20:49:46.539119: step: 816/470, loss: 0.00160531559959054
2023-01-22 20:49:47.319777: step: 818/470, loss: 0.11780795454978943
2023-01-22 20:49:48.061814: step: 820/470, loss: 0.005452371668070555
2023-01-22 20:49:48.742664: step: 822/470, loss: 0.005390825215727091
2023-01-22 20:49:49.462313: step: 824/470, loss: 0.0016363279428333044
2023-01-22 20:49:50.210042: step: 826/470, loss: 0.007646666374057531
2023-01-22 20:49:50.928539: step: 828/470, loss: 0.017727140337228775
2023-01-22 20:49:51.729535: step: 830/470, loss: 0.010663860477507114
2023-01-22 20:49:52.479079: step: 832/470, loss: 0.023380601778626442
2023-01-22 20:49:53.184159: step: 834/470, loss: 0.041295647621154785
2023-01-22 20:49:53.895427: step: 836/470, loss: 0.0017049266025424004
2023-01-22 20:49:54.688225: step: 838/470, loss: 0.006582122761756182
2023-01-22 20:49:55.390047: step: 840/470, loss: 0.021049687638878822
2023-01-22 20:49:56.103157: step: 842/470, loss: 0.01726703532040119
2023-01-22 20:49:56.820669: step: 844/470, loss: 0.012101834639906883
2023-01-22 20:49:57.643061: step: 846/470, loss: 0.030885327607393265
2023-01-22 20:49:58.362209: step: 848/470, loss: 0.030672363936901093
2023-01-22 20:49:59.041691: step: 850/470, loss: 0.6598572731018066
2023-01-22 20:49:59.711415: step: 852/470, loss: 0.0076820398680865765
2023-01-22 20:50:00.403200: step: 854/470, loss: 0.0031191399320960045
2023-01-22 20:50:01.188291: step: 856/470, loss: 0.004457424394786358
2023-01-22 20:50:01.880240: step: 858/470, loss: 0.15405337512493134
2023-01-22 20:50:02.565458: step: 860/470, loss: 0.010198515839874744
2023-01-22 20:50:03.289703: step: 862/470, loss: 0.12781405448913574
2023-01-22 20:50:04.009861: step: 864/470, loss: 0.006552521139383316
2023-01-22 20:50:04.710207: step: 866/470, loss: 0.005595530848950148
2023-01-22 20:50:05.404223: step: 868/470, loss: 0.008519892580807209
2023-01-22 20:50:06.037262: step: 870/470, loss: 0.0002687643573153764
2023-01-22 20:50:06.853592: step: 872/470, loss: 5.414352893829346
2023-01-22 20:50:07.575847: step: 874/470, loss: 0.03722013160586357
2023-01-22 20:50:08.205930: step: 876/470, loss: 0.05762125179171562
2023-01-22 20:50:08.878808: step: 878/470, loss: 0.006857017055153847
2023-01-22 20:50:09.670180: step: 880/470, loss: 0.009326043538749218
2023-01-22 20:50:10.373583: step: 882/470, loss: 0.033087752759456635
2023-01-22 20:50:11.106633: step: 884/470, loss: 0.052600014954805374
2023-01-22 20:50:11.762891: step: 886/470, loss: 0.024000994861125946
2023-01-22 20:50:12.473297: step: 888/470, loss: 0.031389061361551285
2023-01-22 20:50:13.113948: step: 890/470, loss: 0.018143486231565475
2023-01-22 20:50:13.919436: step: 892/470, loss: 0.0009539459133520722
2023-01-22 20:50:14.662302: step: 894/470, loss: 0.01012116763740778
2023-01-22 20:50:15.377669: step: 896/470, loss: 0.0203192550688982
2023-01-22 20:50:16.110849: step: 898/470, loss: 0.021785369142889977
2023-01-22 20:50:16.915937: step: 900/470, loss: 0.0018964793998748064
2023-01-22 20:50:17.691452: step: 902/470, loss: 0.012782180681824684
2023-01-22 20:50:18.404730: step: 904/470, loss: 0.01066429540514946
2023-01-22 20:50:19.230705: step: 906/470, loss: 0.017899200320243835
2023-01-22 20:50:19.944904: step: 908/470, loss: 0.0004175813519395888
2023-01-22 20:50:20.688888: step: 910/470, loss: 0.20423611998558044
2023-01-22 20:50:21.533029: step: 912/470, loss: 0.029853759333491325
2023-01-22 20:50:22.300961: step: 914/470, loss: 0.02101089619100094
2023-01-22 20:50:23.123038: step: 916/470, loss: 0.0083807073533535
2023-01-22 20:50:23.926690: step: 918/470, loss: 0.0004685977182816714
2023-01-22 20:50:24.642054: step: 920/470, loss: 0.006272825412452221
2023-01-22 20:50:25.422570: step: 922/470, loss: 0.007433359045535326
2023-01-22 20:50:26.180870: step: 924/470, loss: 0.02900080941617489
2023-01-22 20:50:26.851859: step: 926/470, loss: 0.0006584687507711351
2023-01-22 20:50:27.573901: step: 928/470, loss: 0.029323289170861244
2023-01-22 20:50:28.283774: step: 930/470, loss: 0.020921828225255013
2023-01-22 20:50:28.935609: step: 932/470, loss: 0.0083458935841918
2023-01-22 20:50:29.769539: step: 934/470, loss: 0.0011282124323770404
2023-01-22 20:50:30.481256: step: 936/470, loss: 0.017477432265877724
2023-01-22 20:50:31.163034: step: 938/470, loss: 0.001543686375953257
2023-01-22 20:50:31.834897: step: 940/470, loss: 0.00018178651225753129
2023-01-22 20:50:32.508465: step: 942/470, loss: 0.00588207645341754
==================================================
Loss: 0.064
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29721765350877194, 'r': 0.3429000632511069, 'f1': 0.3184287812041116}, 'combined': 0.23463173351881908, 'epoch': 30}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34420320254771597, 'r': 0.3600742435873801, 'f1': 0.35195989443611525}, 'combined': 0.24514619512963254, 'epoch': 30}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2908762926377528, 'r': 0.34220740310323855, 'f1': 0.31446085690567865}, 'combined': 0.23170799982523688, 'epoch': 30}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34478795454095695, 'r': 0.35803629093061906, 'f1': 0.3512872562288166}, 'combined': 0.24467769090564342, 'epoch': 30}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2811459909228442, 'r': 0.35196496212121214, 'f1': 0.3125946173254836}, 'combined': 0.23033287592404053, 'epoch': 30}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3303579410113354, 'r': 0.3598711864619158, 'f1': 0.3444835909028546}, 'combined': 0.23993881953432658, 'epoch': 30}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2125, 'r': 0.36428571428571427, 'f1': 0.26842105263157895}, 'combined': 0.17894736842105263, 'epoch': 30}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.21794871794871795, 'r': 0.3695652173913043, 'f1': 0.27419354838709675}, 'combined': 0.13709677419354838, 'epoch': 30}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42391304347826086, 'r': 0.33620689655172414, 'f1': 0.375}, 'combined': 0.25, 'epoch': 30}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 31
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 20:53:07.961338: step: 2/470, loss: 0.0004153551999479532
2023-01-22 20:53:08.758416: step: 4/470, loss: 1.0925959348678589
2023-01-22 20:53:09.442999: step: 6/470, loss: 0.0014063325943425298
2023-01-22 20:53:10.082681: step: 8/470, loss: 0.0018835861701518297
2023-01-22 20:53:10.901994: step: 10/470, loss: 0.010510102845728397
2023-01-22 20:53:11.585429: step: 12/470, loss: 0.004608213901519775
2023-01-22 20:53:12.312010: step: 14/470, loss: 0.000766645884141326
2023-01-22 20:53:13.002573: step: 16/470, loss: 0.02919374406337738
2023-01-22 20:53:13.636200: step: 18/470, loss: 0.004164369311183691
2023-01-22 20:53:14.260971: step: 20/470, loss: 0.022466279566287994
2023-01-22 20:53:14.989378: step: 22/470, loss: 0.032227374613285065
2023-01-22 20:53:15.711846: step: 24/470, loss: 0.00730488495901227
2023-01-22 20:53:16.395807: step: 26/470, loss: 0.0010027121752500534
2023-01-22 20:53:17.165694: step: 28/470, loss: 0.002904940862208605
2023-01-22 20:53:17.859281: step: 30/470, loss: 0.07680755108594894
2023-01-22 20:53:18.581304: step: 32/470, loss: 0.007039623335003853
2023-01-22 20:53:19.442856: step: 34/470, loss: 0.25433337688446045
2023-01-22 20:53:20.102832: step: 36/470, loss: 0.017493372783064842
2023-01-22 20:53:20.840157: step: 38/470, loss: 0.5216097235679626
2023-01-22 20:53:21.641684: step: 40/470, loss: 0.017964819446206093
2023-01-22 20:53:22.345765: step: 42/470, loss: 0.009211939759552479
2023-01-22 20:53:23.066714: step: 44/470, loss: 0.045933887362480164
2023-01-22 20:53:23.770932: step: 46/470, loss: 0.08470865339040756
2023-01-22 20:53:24.524781: step: 48/470, loss: 0.023487238213419914
2023-01-22 20:53:25.253317: step: 50/470, loss: 0.009432869963347912
2023-01-22 20:53:26.020519: step: 52/470, loss: 0.008719773031771183
2023-01-22 20:53:26.718604: step: 54/470, loss: 0.003286207327619195
2023-01-22 20:53:27.382052: step: 56/470, loss: 0.005947456229478121
2023-01-22 20:53:28.165070: step: 58/470, loss: 0.0014269596431404352
2023-01-22 20:53:28.985245: step: 60/470, loss: 0.0015790915349498391
2023-01-22 20:53:29.720131: step: 62/470, loss: 0.018821055069565773
2023-01-22 20:53:30.409639: step: 64/470, loss: 3.195769022568129e-05
2023-01-22 20:53:31.120128: step: 66/470, loss: 0.013032572343945503
2023-01-22 20:53:31.866804: step: 68/470, loss: 0.012471756897866726
2023-01-22 20:53:32.589321: step: 70/470, loss: 0.009083814918994904
2023-01-22 20:53:33.252875: step: 72/470, loss: 0.0110135143622756
2023-01-22 20:53:33.989402: step: 74/470, loss: 0.009082856588065624
2023-01-22 20:53:34.687238: step: 76/470, loss: 0.0004449693369679153
2023-01-22 20:53:35.436685: step: 78/470, loss: 0.05842125788331032
2023-01-22 20:53:36.162771: step: 80/470, loss: 0.008214079774916172
2023-01-22 20:53:36.948385: step: 82/470, loss: 0.06217104196548462
2023-01-22 20:53:37.791052: step: 84/470, loss: 0.006593683734536171
2023-01-22 20:53:38.464760: step: 86/470, loss: 0.019678259268403053
2023-01-22 20:53:39.191952: step: 88/470, loss: 0.005078400019556284
2023-01-22 20:53:39.935802: step: 90/470, loss: 0.03903871402144432
2023-01-22 20:53:40.637757: step: 92/470, loss: 0.4988504946231842
2023-01-22 20:53:41.415655: step: 94/470, loss: 0.018317870795726776
2023-01-22 20:53:42.177610: step: 96/470, loss: 0.0024577791336923838
2023-01-22 20:53:42.820143: step: 98/470, loss: 0.0027793124318122864
2023-01-22 20:53:43.474498: step: 100/470, loss: 0.00482197804376483
2023-01-22 20:53:44.142854: step: 102/470, loss: 0.019959578290581703
2023-01-22 20:53:44.871169: step: 104/470, loss: 0.0028080667834728956
2023-01-22 20:53:45.542013: step: 106/470, loss: 0.0010208826279267669
2023-01-22 20:53:46.238419: step: 108/470, loss: 0.030457837507128716
2023-01-22 20:53:46.908224: step: 110/470, loss: 0.0025482738856226206
2023-01-22 20:53:47.629155: step: 112/470, loss: 0.0258177500218153
2023-01-22 20:53:48.359629: step: 114/470, loss: 0.0043304734863340855
2023-01-22 20:53:49.117712: step: 116/470, loss: 0.002764065284281969
2023-01-22 20:53:49.913142: step: 118/470, loss: 0.03494582325220108
2023-01-22 20:53:50.747204: step: 120/470, loss: 0.04635448753833771
2023-01-22 20:53:51.532384: step: 122/470, loss: 0.04545215889811516
2023-01-22 20:53:52.279399: step: 124/470, loss: 0.019159091636538506
2023-01-22 20:53:52.959650: step: 126/470, loss: 0.0013390732929110527
2023-01-22 20:53:53.671133: step: 128/470, loss: 0.03846125304698944
2023-01-22 20:53:54.349015: step: 130/470, loss: 0.008521667681634426
2023-01-22 20:53:55.069372: step: 132/470, loss: 0.01758314110338688
2023-01-22 20:53:55.846186: step: 134/470, loss: 0.028450246900320053
2023-01-22 20:53:56.537855: step: 136/470, loss: 0.03396439552307129
2023-01-22 20:53:57.280586: step: 138/470, loss: 0.004837017506361008
2023-01-22 20:53:57.969763: step: 140/470, loss: 0.022973332554101944
2023-01-22 20:53:58.777289: step: 142/470, loss: 0.019509391859173775
2023-01-22 20:53:59.503563: step: 144/470, loss: 0.05560195818543434
2023-01-22 20:54:00.219411: step: 146/470, loss: 0.04433672875165939
2023-01-22 20:54:00.912979: step: 148/470, loss: 0.8889219164848328
2023-01-22 20:54:01.628700: step: 150/470, loss: 0.006953278090804815
2023-01-22 20:54:02.391751: step: 152/470, loss: 0.0006373568321578205
2023-01-22 20:54:03.078901: step: 154/470, loss: 0.005718933418393135
2023-01-22 20:54:03.857195: step: 156/470, loss: 0.007636924274265766
2023-01-22 20:54:04.570839: step: 158/470, loss: 0.04812711477279663
2023-01-22 20:54:05.325544: step: 160/470, loss: 0.0677870586514473
2023-01-22 20:54:06.039562: step: 162/470, loss: 0.009034083224833012
2023-01-22 20:54:06.938666: step: 164/470, loss: 0.010354172438383102
2023-01-22 20:54:07.619324: step: 166/470, loss: 0.004512510262429714
2023-01-22 20:54:08.378252: step: 168/470, loss: 0.01185314916074276
2023-01-22 20:54:09.148576: step: 170/470, loss: 0.00713575491681695
2023-01-22 20:54:09.791686: step: 172/470, loss: 0.000432536966400221
2023-01-22 20:54:10.484016: step: 174/470, loss: 0.0017447196878492832
2023-01-22 20:54:11.169438: step: 176/470, loss: 0.0017614453099668026
2023-01-22 20:54:11.896172: step: 178/470, loss: 0.12065732479095459
2023-01-22 20:54:12.650926: step: 180/470, loss: 0.00911496952176094
2023-01-22 20:54:13.407668: step: 182/470, loss: 0.050489142537117004
2023-01-22 20:54:14.141155: step: 184/470, loss: 0.0030859841499477625
2023-01-22 20:54:14.882901: step: 186/470, loss: 0.02064261958003044
2023-01-22 20:54:15.634556: step: 188/470, loss: 0.025169501081109047
2023-01-22 20:54:16.514036: step: 190/470, loss: 0.23960715532302856
2023-01-22 20:54:17.266477: step: 192/470, loss: 0.04839571937918663
2023-01-22 20:54:18.084429: step: 194/470, loss: 0.0479017049074173
2023-01-22 20:54:18.744626: step: 196/470, loss: 0.0008035176433622837
2023-01-22 20:54:19.445497: step: 198/470, loss: 0.0024430553894490004
2023-01-22 20:54:20.198217: step: 200/470, loss: 0.0055528427474200726
2023-01-22 20:54:20.953351: step: 202/470, loss: 0.014087006449699402
2023-01-22 20:54:21.656458: step: 204/470, loss: 0.007186644244939089
2023-01-22 20:54:22.400605: step: 206/470, loss: 0.017961587756872177
2023-01-22 20:54:23.081640: step: 208/470, loss: 0.027364250272512436
2023-01-22 20:54:23.737772: step: 210/470, loss: 0.004035270307213068
2023-01-22 20:54:24.424986: step: 212/470, loss: 0.00933856051415205
2023-01-22 20:54:25.217735: step: 214/470, loss: 0.006368427537381649
2023-01-22 20:54:25.926745: step: 216/470, loss: 0.04675932601094246
2023-01-22 20:54:26.657421: step: 218/470, loss: 0.008699115365743637
2023-01-22 20:54:27.424116: step: 220/470, loss: 0.005315710324794054
2023-01-22 20:54:28.080476: step: 222/470, loss: 0.0007220212719403207
2023-01-22 20:54:28.822868: step: 224/470, loss: 4.652983079722617e-06
2023-01-22 20:54:29.623330: step: 226/470, loss: 0.020241660997271538
2023-01-22 20:54:30.258963: step: 228/470, loss: 0.0002864209236577153
2023-01-22 20:54:30.936204: step: 230/470, loss: 0.0019567871931940317
2023-01-22 20:54:31.769629: step: 232/470, loss: 0.011841587722301483
2023-01-22 20:54:32.497691: step: 234/470, loss: 0.09722713381052017
2023-01-22 20:54:33.229602: step: 236/470, loss: 0.02826106734573841
2023-01-22 20:54:33.981016: step: 238/470, loss: 0.04371390491724014
2023-01-22 20:54:34.673866: step: 240/470, loss: 0.02666950784623623
2023-01-22 20:54:35.446510: step: 242/470, loss: 0.02603962831199169
2023-01-22 20:54:36.168446: step: 244/470, loss: 0.0011542732827365398
2023-01-22 20:54:36.916981: step: 246/470, loss: 0.04242149740457535
2023-01-22 20:54:37.702734: step: 248/470, loss: 0.005671241320669651
2023-01-22 20:54:38.466173: step: 250/470, loss: 0.06051589921116829
2023-01-22 20:54:39.095069: step: 252/470, loss: 0.022702636197209358
2023-01-22 20:54:39.809580: step: 254/470, loss: 0.00014661716704722494
2023-01-22 20:54:40.549806: step: 256/470, loss: 0.024693626910448074
2023-01-22 20:54:41.263406: step: 258/470, loss: 0.006267967633903027
2023-01-22 20:54:42.007329: step: 260/470, loss: 0.010373245924711227
2023-01-22 20:54:42.744396: step: 262/470, loss: 0.013863403350114822
2023-01-22 20:54:43.459010: step: 264/470, loss: 0.011223852634429932
2023-01-22 20:54:44.191633: step: 266/470, loss: 0.13165761530399323
2023-01-22 20:54:44.984075: step: 268/470, loss: 0.010476339608430862
2023-01-22 20:54:45.691066: step: 270/470, loss: 0.015369415283203125
2023-01-22 20:54:46.430469: step: 272/470, loss: 0.0017211531521752477
2023-01-22 20:54:47.141775: step: 274/470, loss: 5.57665407541208e-05
2023-01-22 20:54:47.828196: step: 276/470, loss: 0.0009223352535627782
2023-01-22 20:54:48.546803: step: 278/470, loss: 1.025863821269013e-05
2023-01-22 20:54:49.304528: step: 280/470, loss: 2.5038185119628906
2023-01-22 20:54:50.050017: step: 282/470, loss: 0.014256109483540058
2023-01-22 20:54:50.760130: step: 284/470, loss: 0.00037505527143366635
2023-01-22 20:54:51.440980: step: 286/470, loss: 0.002377528930082917
2023-01-22 20:54:52.120803: step: 288/470, loss: 0.025805901736021042
2023-01-22 20:54:52.864858: step: 290/470, loss: 0.1646108329296112
2023-01-22 20:54:53.600988: step: 292/470, loss: 0.004207650665193796
2023-01-22 20:54:54.433069: step: 294/470, loss: 0.006044092588126659
2023-01-22 20:54:55.186842: step: 296/470, loss: 0.0017826639814302325
2023-01-22 20:54:55.864716: step: 298/470, loss: 0.0007332692039199173
2023-01-22 20:54:56.618179: step: 300/470, loss: 0.01916944980621338
2023-01-22 20:54:57.281007: step: 302/470, loss: 0.015175165608525276
2023-01-22 20:54:57.927731: step: 304/470, loss: 0.0002173801331082359
2023-01-22 20:54:58.613958: step: 306/470, loss: 0.010625113733112812
2023-01-22 20:54:59.284561: step: 308/470, loss: 0.00954343844205141
2023-01-22 20:55:00.008297: step: 310/470, loss: 0.08960520476102829
2023-01-22 20:55:00.721730: step: 312/470, loss: 0.008206892758607864
2023-01-22 20:55:01.519649: step: 314/470, loss: 0.0023078385274857283
2023-01-22 20:55:02.207642: step: 316/470, loss: 0.02238607406616211
2023-01-22 20:55:02.952306: step: 318/470, loss: 0.0010710656642913818
2023-01-22 20:55:03.609014: step: 320/470, loss: 5.481565312948078e-05
2023-01-22 20:55:04.365999: step: 322/470, loss: 0.0008377675549127162
2023-01-22 20:55:05.108537: step: 324/470, loss: 0.016996121034026146
2023-01-22 20:55:05.836850: step: 326/470, loss: 0.03880900889635086
2023-01-22 20:55:06.550719: step: 328/470, loss: 0.019622113555669785
2023-01-22 20:55:07.283232: step: 330/470, loss: 0.017126567661762238
2023-01-22 20:55:08.023781: step: 332/470, loss: 0.004321925342082977
2023-01-22 20:55:08.686829: step: 334/470, loss: 0.00889088585972786
2023-01-22 20:55:09.427528: step: 336/470, loss: 0.014416373334825039
2023-01-22 20:55:10.233198: step: 338/470, loss: 0.05695127323269844
2023-01-22 20:55:10.974807: step: 340/470, loss: 0.017850443720817566
2023-01-22 20:55:11.674006: step: 342/470, loss: 0.028859199956059456
2023-01-22 20:55:12.306594: step: 344/470, loss: 0.03185954689979553
2023-01-22 20:55:12.978711: step: 346/470, loss: 0.004228611942380667
2023-01-22 20:55:13.818318: step: 348/470, loss: 0.052207764238119125
2023-01-22 20:55:14.490535: step: 350/470, loss: 0.2492973804473877
2023-01-22 20:55:15.313132: step: 352/470, loss: 0.002187067177146673
2023-01-22 20:55:16.004893: step: 354/470, loss: 0.004828231874853373
2023-01-22 20:55:16.753885: step: 356/470, loss: 0.030843263491988182
2023-01-22 20:55:17.465199: step: 358/470, loss: 0.004479340277612209
2023-01-22 20:55:18.258961: step: 360/470, loss: 0.010255182161927223
2023-01-22 20:55:18.913939: step: 362/470, loss: 0.0042448281310498714
2023-01-22 20:55:19.583120: step: 364/470, loss: 0.0041470276191830635
2023-01-22 20:55:20.243830: step: 366/470, loss: 0.004188673570752144
2023-01-22 20:55:21.019368: step: 368/470, loss: 0.004912644159048796
2023-01-22 20:55:21.689892: step: 370/470, loss: 0.010912226513028145
2023-01-22 20:55:22.542687: step: 372/470, loss: 0.017633339390158653
2023-01-22 20:55:23.305757: step: 374/470, loss: 0.07342100143432617
2023-01-22 20:55:24.056373: step: 376/470, loss: 0.003536728210747242
2023-01-22 20:55:24.749862: step: 378/470, loss: 0.0003867686027660966
2023-01-22 20:55:25.446965: step: 380/470, loss: 0.017503436654806137
2023-01-22 20:55:26.313661: step: 382/470, loss: 0.0033323050010949373
2023-01-22 20:55:27.011418: step: 384/470, loss: 0.0019946997053921223
2023-01-22 20:55:27.749144: step: 386/470, loss: 0.680500328540802
2023-01-22 20:55:28.481635: step: 388/470, loss: 0.01015088427811861
2023-01-22 20:55:29.185147: step: 390/470, loss: 0.0255475752055645
2023-01-22 20:55:29.876782: step: 392/470, loss: 0.011009021662175655
2023-01-22 20:55:30.579432: step: 394/470, loss: 0.0023041116073727608
2023-01-22 20:55:31.307782: step: 396/470, loss: 0.012929693795740604
2023-01-22 20:55:32.007834: step: 398/470, loss: 0.0013820825843140483
2023-01-22 20:55:32.794081: step: 400/470, loss: 0.03162797540426254
2023-01-22 20:55:33.528323: step: 402/470, loss: 0.23524107038974762
2023-01-22 20:55:34.279047: step: 404/470, loss: 0.008160697296261787
2023-01-22 20:55:34.983147: step: 406/470, loss: 0.024923594668507576
2023-01-22 20:55:35.739051: step: 408/470, loss: 0.0012302573304623365
2023-01-22 20:55:36.459846: step: 410/470, loss: 0.039357952773571014
2023-01-22 20:55:37.189064: step: 412/470, loss: 0.02063934877514839
2023-01-22 20:55:37.897760: step: 414/470, loss: 0.019131643697619438
2023-01-22 20:55:38.644040: step: 416/470, loss: 0.029757630079984665
2023-01-22 20:55:39.376316: step: 418/470, loss: 0.03168037533760071
2023-01-22 20:55:40.163625: step: 420/470, loss: 0.007195422891527414
2023-01-22 20:55:40.897805: step: 422/470, loss: 0.04357065260410309
2023-01-22 20:55:41.664902: step: 424/470, loss: 0.032375071197748184
2023-01-22 20:55:42.361445: step: 426/470, loss: 0.021866897121071815
2023-01-22 20:55:43.045650: step: 428/470, loss: 0.021189482882618904
2023-01-22 20:55:43.938110: step: 430/470, loss: 0.05813028663396835
2023-01-22 20:55:44.700457: step: 432/470, loss: 0.059212926775217056
2023-01-22 20:55:45.430482: step: 434/470, loss: 0.012862597592175007
2023-01-22 20:55:46.254968: step: 436/470, loss: 0.0023115493822842836
2023-01-22 20:55:46.933461: step: 438/470, loss: 0.08521554619073868
2023-01-22 20:55:47.618804: step: 440/470, loss: 0.6096815466880798
2023-01-22 20:55:48.355175: step: 442/470, loss: 0.012424707412719727
2023-01-22 20:55:49.078333: step: 444/470, loss: 0.00018685971735976636
2023-01-22 20:55:49.842317: step: 446/470, loss: 0.0018285795813426375
2023-01-22 20:55:50.593779: step: 448/470, loss: 0.15367041528224945
2023-01-22 20:55:51.280763: step: 450/470, loss: 0.15135274827480316
2023-01-22 20:55:51.956091: step: 452/470, loss: 0.0034649712033569813
2023-01-22 20:55:52.743103: step: 454/470, loss: 0.1291857212781906
2023-01-22 20:55:53.523387: step: 456/470, loss: 0.010504554957151413
2023-01-22 20:55:54.217210: step: 458/470, loss: 0.005182147957384586
2023-01-22 20:55:55.001384: step: 460/470, loss: 0.012676097452640533
2023-01-22 20:55:55.672494: step: 462/470, loss: 0.013613465242087841
2023-01-22 20:55:56.407093: step: 464/470, loss: 0.07927101105451584
2023-01-22 20:55:57.198299: step: 466/470, loss: 0.0009735323255881667
2023-01-22 20:55:57.949218: step: 468/470, loss: 0.02965150959789753
2023-01-22 20:55:58.736384: step: 470/470, loss: 0.000922163191717118
2023-01-22 20:55:59.480506: step: 472/470, loss: 0.04083675891160965
2023-01-22 20:56:00.176151: step: 474/470, loss: 0.0027813774067908525
2023-01-22 20:56:00.928254: step: 476/470, loss: 0.021299488842487335
2023-01-22 20:56:01.665862: step: 478/470, loss: 0.006957915611565113
2023-01-22 20:56:02.702110: step: 480/470, loss: 0.01972772739827633
2023-01-22 20:56:03.385524: step: 482/470, loss: 0.006241174414753914
2023-01-22 20:56:04.162127: step: 484/470, loss: 0.014599893242120743
2023-01-22 20:56:04.860122: step: 486/470, loss: 0.005494068842381239
2023-01-22 20:56:05.645444: step: 488/470, loss: 0.015743980184197426
2023-01-22 20:56:06.395587: step: 490/470, loss: 0.009499004110693932
2023-01-22 20:56:07.152186: step: 492/470, loss: 0.00025713659124448895
2023-01-22 20:56:07.995795: step: 494/470, loss: 0.024208668619394302
2023-01-22 20:56:08.800633: step: 496/470, loss: 0.008801139891147614
2023-01-22 20:56:09.547744: step: 498/470, loss: 0.007869623601436615
2023-01-22 20:56:10.233194: step: 500/470, loss: 0.0006736805662512779
2023-01-22 20:56:10.949295: step: 502/470, loss: 0.0008966495515778661
2023-01-22 20:56:11.718680: step: 504/470, loss: 0.03283290937542915
2023-01-22 20:56:12.438465: step: 506/470, loss: 0.013244382105767727
2023-01-22 20:56:13.159028: step: 508/470, loss: 0.09672006964683533
2023-01-22 20:56:13.875676: step: 510/470, loss: 0.03322713449597359
2023-01-22 20:56:14.620498: step: 512/470, loss: 0.004942721221596003
2023-01-22 20:56:15.377912: step: 514/470, loss: 0.02580172009766102
2023-01-22 20:56:16.119690: step: 516/470, loss: 0.042521312832832336
2023-01-22 20:56:16.817938: step: 518/470, loss: 0.050515204668045044
2023-01-22 20:56:17.637822: step: 520/470, loss: 0.15628911554813385
2023-01-22 20:56:18.407350: step: 522/470, loss: 0.0003710964519996196
2023-01-22 20:56:19.100302: step: 524/470, loss: 0.005137452390044928
2023-01-22 20:56:19.822841: step: 526/470, loss: 0.03880662843585014
2023-01-22 20:56:20.591837: step: 528/470, loss: 0.0028388279024511576
2023-01-22 20:56:21.300787: step: 530/470, loss: 0.00452554551884532
2023-01-22 20:56:22.066718: step: 532/470, loss: 0.07652177661657333
2023-01-22 20:56:22.806103: step: 534/470, loss: 0.017907770350575447
2023-01-22 20:56:23.532027: step: 536/470, loss: 0.017264176160097122
2023-01-22 20:56:24.281005: step: 538/470, loss: 0.017725540325045586
2023-01-22 20:56:24.989429: step: 540/470, loss: 0.0008670427487231791
2023-01-22 20:56:25.733288: step: 542/470, loss: 0.001019967021420598
2023-01-22 20:56:26.496873: step: 544/470, loss: 0.0039613074623048306
2023-01-22 20:56:27.282494: step: 546/470, loss: 0.01247483305633068
2023-01-22 20:56:27.956394: step: 548/470, loss: 0.002028008922934532
2023-01-22 20:56:28.685103: step: 550/470, loss: 0.004361606668680906
2023-01-22 20:56:29.378392: step: 552/470, loss: 0.011579647660255432
2023-01-22 20:56:30.082537: step: 554/470, loss: 0.049814943224191666
2023-01-22 20:56:30.763185: step: 556/470, loss: 0.0027671053539961576
2023-01-22 20:56:31.493117: step: 558/470, loss: 0.017059145495295525
2023-01-22 20:56:32.236919: step: 560/470, loss: 0.0030047514010220766
2023-01-22 20:56:32.959571: step: 562/470, loss: 0.011335933580994606
2023-01-22 20:56:33.733634: step: 564/470, loss: 0.03579147905111313
2023-01-22 20:56:34.472093: step: 566/470, loss: 0.021534211933612823
2023-01-22 20:56:35.253349: step: 568/470, loss: 0.03905900940299034
2023-01-22 20:56:35.950248: step: 570/470, loss: 0.0442798025906086
2023-01-22 20:56:36.715284: step: 572/470, loss: 0.001077734399586916
2023-01-22 20:56:37.439181: step: 574/470, loss: 0.030320877209305763
2023-01-22 20:56:38.068149: step: 576/470, loss: 0.00816918071359396
2023-01-22 20:56:38.793670: step: 578/470, loss: 0.013305963017046452
2023-01-22 20:56:39.499231: step: 580/470, loss: 0.009787117131054401
2023-01-22 20:56:40.124125: step: 582/470, loss: 0.007002311293035746
2023-01-22 20:56:40.913573: step: 584/470, loss: 0.035149309784173965
2023-01-22 20:56:41.614629: step: 586/470, loss: 0.00833014864474535
2023-01-22 20:56:42.406483: step: 588/470, loss: 0.020918749272823334
2023-01-22 20:56:43.114366: step: 590/470, loss: 0.14545173943042755
2023-01-22 20:56:43.805539: step: 592/470, loss: 0.03052116557955742
2023-01-22 20:56:44.580267: step: 594/470, loss: 0.012451532296836376
2023-01-22 20:56:45.314495: step: 596/470, loss: 0.15833701193332672
2023-01-22 20:56:46.091836: step: 598/470, loss: 0.0005307383253239095
2023-01-22 20:56:46.804146: step: 600/470, loss: 0.0017066209111362696
2023-01-22 20:56:47.541290: step: 602/470, loss: 0.03470804542303085
2023-01-22 20:56:48.273902: step: 604/470, loss: 0.0007092714658938348
2023-01-22 20:56:49.017257: step: 606/470, loss: 0.001324977376498282
2023-01-22 20:56:49.686820: step: 608/470, loss: 0.024211524054408073
2023-01-22 20:56:50.462651: step: 610/470, loss: 0.00011712490959325805
2023-01-22 20:56:51.211222: step: 612/470, loss: 7.496851139876526e-06
2023-01-22 20:56:51.984197: step: 614/470, loss: 0.07053697854280472
2023-01-22 20:56:52.696981: step: 616/470, loss: 0.05512640252709389
2023-01-22 20:56:53.444667: step: 618/470, loss: 0.03331885486841202
2023-01-22 20:56:54.215904: step: 620/470, loss: 0.0004636533558368683
2023-01-22 20:56:54.971564: step: 622/470, loss: 3.8023954402888194e-06
2023-01-22 20:56:55.663703: step: 624/470, loss: 0.01048552617430687
2023-01-22 20:56:56.330401: step: 626/470, loss: 0.017999017611145973
2023-01-22 20:56:56.988598: step: 628/470, loss: 0.044697657227516174
2023-01-22 20:56:57.851008: step: 630/470, loss: 0.017182713374495506
2023-01-22 20:56:58.540074: step: 632/470, loss: 0.03972567990422249
2023-01-22 20:56:59.271773: step: 634/470, loss: 0.018354123458266258
2023-01-22 20:56:59.998706: step: 636/470, loss: 0.0014592665247619152
2023-01-22 20:57:00.708992: step: 638/470, loss: 0.003360056085512042
2023-01-22 20:57:01.487233: step: 640/470, loss: 0.054131921380758286
2023-01-22 20:57:02.195241: step: 642/470, loss: 0.00018125410133507103
2023-01-22 20:57:02.837839: step: 644/470, loss: 0.00046586460666731
2023-01-22 20:57:03.492152: step: 646/470, loss: 0.003081733826547861
2023-01-22 20:57:04.241083: step: 648/470, loss: 0.0019446099177002907
2023-01-22 20:57:05.007660: step: 650/470, loss: 0.036725327372550964
2023-01-22 20:57:05.788370: step: 652/470, loss: 0.011674618348479271
2023-01-22 20:57:06.617747: step: 654/470, loss: 0.023591268807649612
2023-01-22 20:57:07.409514: step: 656/470, loss: 0.13545000553131104
2023-01-22 20:57:08.045716: step: 658/470, loss: 0.02520488202571869
2023-01-22 20:57:08.771208: step: 660/470, loss: 0.017133207991719246
2023-01-22 20:57:09.443660: step: 662/470, loss: 0.01911136694252491
2023-01-22 20:57:10.114923: step: 664/470, loss: 0.007725501898676157
2023-01-22 20:57:10.829511: step: 666/470, loss: 0.009709802456200123
2023-01-22 20:57:11.614122: step: 668/470, loss: 0.0017183064483106136
2023-01-22 20:57:12.377857: step: 670/470, loss: 0.026015179231762886
2023-01-22 20:57:13.154529: step: 672/470, loss: 0.008718994446098804
2023-01-22 20:57:13.844886: step: 674/470, loss: 0.0018770707538351417
2023-01-22 20:57:14.690792: step: 676/470, loss: 0.007993071340024471
2023-01-22 20:57:15.387538: step: 678/470, loss: 0.0003845719911623746
2023-01-22 20:57:16.206382: step: 680/470, loss: 0.0029241188894957304
2023-01-22 20:57:16.973933: step: 682/470, loss: 0.2095903605222702
2023-01-22 20:57:17.669128: step: 684/470, loss: 0.04601133614778519
2023-01-22 20:57:18.497280: step: 686/470, loss: 0.04851691052317619
2023-01-22 20:57:19.130384: step: 688/470, loss: 0.0033728540875017643
2023-01-22 20:57:19.829583: step: 690/470, loss: 0.0015807858435437083
2023-01-22 20:57:20.679338: step: 692/470, loss: 0.010904110968112946
2023-01-22 20:57:21.391599: step: 694/470, loss: 0.07372532784938812
2023-01-22 20:57:22.123715: step: 696/470, loss: 0.0032748605590313673
2023-01-22 20:57:22.829933: step: 698/470, loss: 0.0914636179804802
2023-01-22 20:57:23.516419: step: 700/470, loss: 0.0038345667999237776
2023-01-22 20:57:24.254322: step: 702/470, loss: 0.09439164400100708
2023-01-22 20:57:25.033291: step: 704/470, loss: 0.12708623707294464
2023-01-22 20:57:25.723303: step: 706/470, loss: 0.02249508537352085
2023-01-22 20:57:26.427117: step: 708/470, loss: 0.024676885455846786
2023-01-22 20:57:27.056492: step: 710/470, loss: 0.00023603100271429867
2023-01-22 20:57:27.781924: step: 712/470, loss: 0.07618135958909988
2023-01-22 20:57:28.506825: step: 714/470, loss: 0.0014070416800677776
2023-01-22 20:57:29.345699: step: 716/470, loss: 0.038883935660123825
2023-01-22 20:57:30.068577: step: 718/470, loss: 0.0010557807981967926
2023-01-22 20:57:30.843449: step: 720/470, loss: 0.00078931002644822
2023-01-22 20:57:31.525084: step: 722/470, loss: 0.0017666048370301723
2023-01-22 20:57:32.308135: step: 724/470, loss: 0.0047446005046367645
2023-01-22 20:57:33.027596: step: 726/470, loss: 0.03437475860118866
2023-01-22 20:57:33.801169: step: 728/470, loss: 0.008103154599666595
2023-01-22 20:57:34.552281: step: 730/470, loss: 0.15290933847427368
2023-01-22 20:57:35.272966: step: 732/470, loss: 0.005006398539990187
2023-01-22 20:57:36.002501: step: 734/470, loss: 0.03129494935274124
2023-01-22 20:57:36.813473: step: 736/470, loss: 0.1397247016429901
2023-01-22 20:57:37.547292: step: 738/470, loss: 0.018076607957482338
2023-01-22 20:57:38.263341: step: 740/470, loss: 0.012959785759449005
2023-01-22 20:57:38.974776: step: 742/470, loss: 0.0037444073241204023
2023-01-22 20:57:39.674237: step: 744/470, loss: 0.05442821606993675
2023-01-22 20:57:40.398857: step: 746/470, loss: 0.012656944803893566
2023-01-22 20:57:41.128975: step: 748/470, loss: 0.002542155794799328
2023-01-22 20:57:41.794912: step: 750/470, loss: 0.20244351029396057
2023-01-22 20:57:42.431937: step: 752/470, loss: 0.006245005410164595
2023-01-22 20:57:43.143857: step: 754/470, loss: 0.06883977353572845
2023-01-22 20:57:43.844710: step: 756/470, loss: 0.3660793900489807
2023-01-22 20:57:44.588713: step: 758/470, loss: 0.01697465591132641
2023-01-22 20:57:45.433049: step: 760/470, loss: 0.0022616013884544373
2023-01-22 20:57:46.143992: step: 762/470, loss: 0.013554520905017853
2023-01-22 20:57:46.901052: step: 764/470, loss: 0.0018667317926883698
2023-01-22 20:57:47.676077: step: 766/470, loss: 0.02620398811995983
2023-01-22 20:57:48.330694: step: 768/470, loss: 0.01824253797531128
2023-01-22 20:57:49.069874: step: 770/470, loss: 0.029288796707987785
2023-01-22 20:57:49.741411: step: 772/470, loss: 0.0019241668051108718
2023-01-22 20:57:50.432199: step: 774/470, loss: 0.009944219142198563
2023-01-22 20:57:51.170911: step: 776/470, loss: 0.02224019728600979
2023-01-22 20:57:51.799617: step: 778/470, loss: 0.0010763780446723104
2023-01-22 20:57:52.639181: step: 780/470, loss: 0.026158837601542473
2023-01-22 20:57:53.391886: step: 782/470, loss: 0.053973760455846786
2023-01-22 20:57:54.147387: step: 784/470, loss: 0.02082950621843338
2023-01-22 20:57:54.899895: step: 786/470, loss: 0.1821128875017166
2023-01-22 20:57:55.570428: step: 788/470, loss: 0.0018857375252991915
2023-01-22 20:57:56.291691: step: 790/470, loss: 0.01713024079799652
2023-01-22 20:57:56.935307: step: 792/470, loss: 0.012649615295231342
2023-01-22 20:57:57.656575: step: 794/470, loss: 0.15321439504623413
2023-01-22 20:57:58.541237: step: 796/470, loss: 0.03709512576460838
2023-01-22 20:57:59.348394: step: 798/470, loss: 0.00017801785725168884
2023-01-22 20:58:00.113205: step: 800/470, loss: 0.02271411009132862
2023-01-22 20:58:00.827191: step: 802/470, loss: 0.005088508129119873
2023-01-22 20:58:01.510160: step: 804/470, loss: 0.03457785025238991
2023-01-22 20:58:02.224602: step: 806/470, loss: 0.007744433358311653
2023-01-22 20:58:02.962082: step: 808/470, loss: 0.0011210455559194088
2023-01-22 20:58:03.773881: step: 810/470, loss: 0.004407666157931089
2023-01-22 20:58:04.583797: step: 812/470, loss: 0.024257738143205643
2023-01-22 20:58:05.361063: step: 814/470, loss: 0.008528418838977814
2023-01-22 20:58:06.062593: step: 816/470, loss: 0.002460848307237029
2023-01-22 20:58:06.841327: step: 818/470, loss: 0.0038715063128620386
2023-01-22 20:58:07.596426: step: 820/470, loss: 0.0031947391107678413
2023-01-22 20:58:08.361795: step: 822/470, loss: 0.021919481456279755
2023-01-22 20:58:09.140505: step: 824/470, loss: 0.00419453764334321
2023-01-22 20:58:09.864239: step: 826/470, loss: 0.18099209666252136
2023-01-22 20:58:10.513831: step: 828/470, loss: 0.0055846464820206165
2023-01-22 20:58:11.315456: step: 830/470, loss: 0.019906627014279366
2023-01-22 20:58:11.998600: step: 832/470, loss: 0.011373650282621384
2023-01-22 20:58:12.715467: step: 834/470, loss: 0.05863653123378754
2023-01-22 20:58:13.398875: step: 836/470, loss: 0.008630829863250256
2023-01-22 20:58:14.159600: step: 838/470, loss: 0.05342869088053703
2023-01-22 20:58:15.008798: step: 840/470, loss: 0.008590944111347198
2023-01-22 20:58:15.809508: step: 842/470, loss: 0.019462179392576218
2023-01-22 20:58:16.568288: step: 844/470, loss: 0.0030498160049319267
2023-01-22 20:58:17.342332: step: 846/470, loss: 0.02540343627333641
2023-01-22 20:58:18.161974: step: 848/470, loss: 0.015893662348389626
2023-01-22 20:58:18.811790: step: 850/470, loss: 0.01733972690999508
2023-01-22 20:58:19.676488: step: 852/470, loss: 0.006161740515381098
2023-01-22 20:58:20.439151: step: 854/470, loss: 0.0038143827114254236
2023-01-22 20:58:21.248644: step: 856/470, loss: 0.08798175305128098
2023-01-22 20:58:22.044295: step: 858/470, loss: 0.008321262896060944
2023-01-22 20:58:22.767264: step: 860/470, loss: 0.0049756853841245174
2023-01-22 20:58:23.547625: step: 862/470, loss: 0.03980034962296486
2023-01-22 20:58:24.270677: step: 864/470, loss: 0.008659124374389648
2023-01-22 20:58:25.045514: step: 866/470, loss: 0.06904779374599457
2023-01-22 20:58:25.717410: step: 868/470, loss: 0.0019073209259659052
2023-01-22 20:58:26.434445: step: 870/470, loss: 0.004029394127428532
2023-01-22 20:58:27.141531: step: 872/470, loss: 0.004503278061747551
2023-01-22 20:58:27.853515: step: 874/470, loss: 0.001992929959669709
2023-01-22 20:58:28.641338: step: 876/470, loss: 0.006583628244698048
2023-01-22 20:58:29.337511: step: 878/470, loss: 0.0009295732015743852
2023-01-22 20:58:30.147679: step: 880/470, loss: 0.0053373072296381
2023-01-22 20:58:30.881850: step: 882/470, loss: 0.009604030288755894
2023-01-22 20:58:31.620376: step: 884/470, loss: 0.002130313077941537
2023-01-22 20:58:32.309982: step: 886/470, loss: 0.04465380311012268
2023-01-22 20:58:33.145648: step: 888/470, loss: 0.10829721391201019
2023-01-22 20:58:33.899716: step: 890/470, loss: 0.03182058036327362
2023-01-22 20:58:34.611399: step: 892/470, loss: 0.013102928176522255
2023-01-22 20:58:35.395002: step: 894/470, loss: 0.02757185697555542
2023-01-22 20:58:36.155033: step: 896/470, loss: 0.013785184361040592
2023-01-22 20:58:36.962987: step: 898/470, loss: 0.013047303073108196
2023-01-22 20:58:37.688901: step: 900/470, loss: 3.3479478588560596e-05
2023-01-22 20:58:38.369881: step: 902/470, loss: 0.015448780730366707
2023-01-22 20:58:39.183878: step: 904/470, loss: 0.017426110804080963
2023-01-22 20:58:39.927174: step: 906/470, loss: 0.011090615764260292
2023-01-22 20:58:40.575543: step: 908/470, loss: 0.0027628943789750338
2023-01-22 20:58:41.345959: step: 910/470, loss: 0.07512981444597244
2023-01-22 20:58:42.030888: step: 912/470, loss: 0.003129625925794244
2023-01-22 20:58:42.629508: step: 914/470, loss: 0.0007694661035202444
2023-01-22 20:58:43.264289: step: 916/470, loss: 0.0655151829123497
2023-01-22 20:58:43.977982: step: 918/470, loss: 0.01531730592250824
2023-01-22 20:58:44.725017: step: 920/470, loss: 0.003190776566043496
2023-01-22 20:58:45.429017: step: 922/470, loss: 0.02201441302895546
2023-01-22 20:58:46.288643: step: 924/470, loss: 0.23225174844264984
2023-01-22 20:58:47.037398: step: 926/470, loss: 0.0298309326171875
2023-01-22 20:58:47.705623: step: 928/470, loss: 0.024859227240085602
2023-01-22 20:58:48.441315: step: 930/470, loss: 0.15923137962818146
2023-01-22 20:58:49.367901: step: 932/470, loss: 0.004126227926462889
2023-01-22 20:58:50.054548: step: 934/470, loss: 0.005694595165550709
2023-01-22 20:58:50.851982: step: 936/470, loss: 0.1984158605337143
2023-01-22 20:58:51.584600: step: 938/470, loss: 0.01643310859799385
2023-01-22 20:58:52.283469: step: 940/470, loss: 0.04566141590476036
2023-01-22 20:58:52.931412: step: 942/470, loss: 0.022141339257359505
==================================================
Loss: 0.041
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29751898604269295, 'r': 0.32744025029366586, 'f1': 0.3117633458080613}, 'combined': 0.2297203600690978, 'epoch': 31}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3371869177457899, 'r': 0.358585318295042, 'f1': 0.3475570652626689}, 'combined': 0.2420795479441475, 'epoch': 31}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2906982529854047, 'r': 0.3282077049835214, 'f1': 0.3083163289239141}, 'combined': 0.2271804528913051, 'epoch': 31}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33885016089940706, 'r': 0.36002829595562, 'f1': 0.34911834759332855}, 'combined': 0.2431670082739602, 'epoch': 31}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2830428685897436, 'r': 0.3351399430740038, 'f1': 0.3068961772371851}, 'combined': 0.2261340253326627, 'epoch': 31}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.32938994992287796, 'r': 0.3648627137607264, 'f1': 0.3462200933495943}, 'combined': 0.2411483237260856, 'epoch': 31}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21610169491525424, 'r': 0.36428571428571427, 'f1': 0.2712765957446808}, 'combined': 0.18085106382978722, 'epoch': 31}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2692307692307692, 'r': 0.45652173913043476, 'f1': 0.3387096774193548}, 'combined': 0.1693548387096774, 'epoch': 31}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4431818181818182, 'r': 0.33620689655172414, 'f1': 0.38235294117647056}, 'combined': 0.2549019607843137, 'epoch': 31}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 32
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 21:01:28.517667: step: 2/470, loss: 0.9720427393913269
2023-01-22 21:01:29.202543: step: 4/470, loss: 0.013476014137268066
2023-01-22 21:01:29.953635: step: 6/470, loss: 0.00015409085608553141
2023-01-22 21:01:30.704840: step: 8/470, loss: 0.005482874345034361
2023-01-22 21:01:31.405919: step: 10/470, loss: 0.02253660000860691
2023-01-22 21:01:32.096924: step: 12/470, loss: 0.0016350456280633807
2023-01-22 21:01:32.866442: step: 14/470, loss: 0.0006504120538011193
2023-01-22 21:01:33.588751: step: 16/470, loss: 0.0015973305562511086
2023-01-22 21:01:34.322070: step: 18/470, loss: 0.25637224316596985
2023-01-22 21:01:35.076035: step: 20/470, loss: 0.02262234315276146
2023-01-22 21:01:35.884305: step: 22/470, loss: 0.001908066333271563
2023-01-22 21:01:36.525308: step: 24/470, loss: 0.0029853819869458675
2023-01-22 21:01:37.297070: step: 26/470, loss: 0.009884890168905258
2023-01-22 21:01:38.068256: step: 28/470, loss: 0.0006165321101434529
2023-01-22 21:01:38.828769: step: 30/470, loss: 0.0001714162644930184
2023-01-22 21:01:39.569013: step: 32/470, loss: 0.0308544784784317
2023-01-22 21:01:40.334723: step: 34/470, loss: 0.027413802221417427
2023-01-22 21:01:41.119560: step: 36/470, loss: 0.1625737100839615
2023-01-22 21:01:41.805661: step: 38/470, loss: 0.006317344959825277
2023-01-22 21:01:42.646363: step: 40/470, loss: 0.003615674562752247
2023-01-22 21:01:43.367172: step: 42/470, loss: 0.08496110886335373
2023-01-22 21:01:44.143867: step: 44/470, loss: 0.0003270620945841074
2023-01-22 21:01:44.870686: step: 46/470, loss: 0.013454585336148739
2023-01-22 21:01:45.540468: step: 48/470, loss: 0.022000696510076523
2023-01-22 21:01:46.188850: step: 50/470, loss: 0.004566211719065905
2023-01-22 21:01:46.974330: step: 52/470, loss: 0.03704002499580383
2023-01-22 21:01:47.626727: step: 54/470, loss: 0.004721718840301037
2023-01-22 21:01:48.380932: step: 56/470, loss: 0.02784247137606144
2023-01-22 21:01:49.081561: step: 58/470, loss: 0.2554512321949005
2023-01-22 21:01:49.802899: step: 60/470, loss: 0.006956116762012243
2023-01-22 21:01:50.510837: step: 62/470, loss: 0.0004784489865414798
2023-01-22 21:01:51.181236: step: 64/470, loss: 0.0018533782567828894
2023-01-22 21:01:52.002686: step: 66/470, loss: 0.14442533254623413
2023-01-22 21:01:52.679691: step: 68/470, loss: 0.0010345384944230318
2023-01-22 21:01:53.436488: step: 70/470, loss: 0.02987985871732235
2023-01-22 21:01:54.201187: step: 72/470, loss: 0.010891645215451717
2023-01-22 21:01:54.979329: step: 74/470, loss: 0.03483196720480919
2023-01-22 21:01:55.800379: step: 76/470, loss: 0.09911884367465973
2023-01-22 21:01:56.595877: step: 78/470, loss: 0.007575498428195715
2023-01-22 21:01:57.407614: step: 80/470, loss: 0.007171786390244961
2023-01-22 21:01:58.163525: step: 82/470, loss: 0.002897205762565136
2023-01-22 21:01:58.867475: step: 84/470, loss: 0.0030799158848822117
2023-01-22 21:01:59.556058: step: 86/470, loss: 0.009569648653268814
2023-01-22 21:02:00.178583: step: 88/470, loss: 0.002280237153172493
2023-01-22 21:02:00.904020: step: 90/470, loss: 0.017339464277029037
2023-01-22 21:02:01.626475: step: 92/470, loss: 0.01658935844898224
2023-01-22 21:02:02.345535: step: 94/470, loss: 0.013809598982334137
2023-01-22 21:02:03.025060: step: 96/470, loss: 0.001008601044304669
2023-01-22 21:02:03.776830: step: 98/470, loss: 0.1749447137117386
2023-01-22 21:02:04.528544: step: 100/470, loss: 0.046566035598516464
2023-01-22 21:02:05.246776: step: 102/470, loss: 0.02105867676436901
2023-01-22 21:02:05.962397: step: 104/470, loss: 0.14165711402893066
2023-01-22 21:02:06.673179: step: 106/470, loss: 0.0024683044757694006
2023-01-22 21:02:07.392641: step: 108/470, loss: 0.00013477614265866578
2023-01-22 21:02:08.117447: step: 110/470, loss: 0.01837342046201229
2023-01-22 21:02:08.891187: step: 112/470, loss: 0.007353122346103191
2023-01-22 21:02:09.652107: step: 114/470, loss: 0.009461408481001854
2023-01-22 21:02:10.374704: step: 116/470, loss: 0.002974409842863679
2023-01-22 21:02:11.103286: step: 118/470, loss: 0.05226290225982666
2023-01-22 21:02:11.836615: step: 120/470, loss: 0.043346941471099854
2023-01-22 21:02:12.593558: step: 122/470, loss: 0.10949388891458511
2023-01-22 21:02:13.322013: step: 124/470, loss: 0.023482829332351685
2023-01-22 21:02:14.077418: step: 126/470, loss: 0.006389224901795387
2023-01-22 21:02:14.785120: step: 128/470, loss: 0.009503074921667576
2023-01-22 21:02:15.572275: step: 130/470, loss: 0.014946824871003628
2023-01-22 21:02:16.289265: step: 132/470, loss: 0.016744105145335197
2023-01-22 21:02:16.979356: step: 134/470, loss: 0.0011202177265658975
2023-01-22 21:02:17.726830: step: 136/470, loss: 0.0005344194360077381
2023-01-22 21:02:18.528377: step: 138/470, loss: 0.053323112428188324
2023-01-22 21:02:19.298794: step: 140/470, loss: 0.7324318289756775
2023-01-22 21:02:20.111225: step: 142/470, loss: 0.04300731047987938
2023-01-22 21:02:20.840794: step: 144/470, loss: 0.01699782721698284
2023-01-22 21:02:21.570923: step: 146/470, loss: 0.0031976874452084303
2023-01-22 21:02:22.215499: step: 148/470, loss: 0.010052609257400036
2023-01-22 21:02:22.937705: step: 150/470, loss: 0.0200212299823761
2023-01-22 21:02:23.661139: step: 152/470, loss: 0.012295265682041645
2023-01-22 21:02:24.439287: step: 154/470, loss: 0.00786919891834259
2023-01-22 21:02:25.207885: step: 156/470, loss: 0.019932325929403305
2023-01-22 21:02:26.121090: step: 158/470, loss: 0.0012513573747128248
2023-01-22 21:02:26.908776: step: 160/470, loss: 0.0011142558651044965
2023-01-22 21:02:27.673289: step: 162/470, loss: 0.021040918305516243
2023-01-22 21:02:28.436716: step: 164/470, loss: 0.002821336267516017
2023-01-22 21:02:29.205631: step: 166/470, loss: 0.006630197633057833
2023-01-22 21:02:29.876025: step: 168/470, loss: 0.004258208908140659
2023-01-22 21:02:30.559057: step: 170/470, loss: 0.03937026113271713
2023-01-22 21:02:31.313402: step: 172/470, loss: 0.0024332425091415644
2023-01-22 21:02:32.018014: step: 174/470, loss: 0.0002705961815081537
2023-01-22 21:02:32.679245: step: 176/470, loss: 0.0043231286108493805
2023-01-22 21:02:33.427348: step: 178/470, loss: 0.10010123252868652
2023-01-22 21:02:34.171855: step: 180/470, loss: 0.003182998625561595
2023-01-22 21:02:34.891428: step: 182/470, loss: 4.15868271375075e-05
2023-01-22 21:02:35.529308: step: 184/470, loss: 0.030571192502975464
2023-01-22 21:02:36.289490: step: 186/470, loss: 0.0007512365118600428
2023-01-22 21:02:37.034863: step: 188/470, loss: 0.0026000277139246464
2023-01-22 21:02:37.730735: step: 190/470, loss: 0.010836091823875904
2023-01-22 21:02:38.496542: step: 192/470, loss: 0.02573336847126484
2023-01-22 21:02:39.282833: step: 194/470, loss: 0.03251959756016731
2023-01-22 21:02:39.947253: step: 196/470, loss: 0.00026101371622644365
2023-01-22 21:02:40.617595: step: 198/470, loss: 0.09524267166852951
2023-01-22 21:02:41.392139: step: 200/470, loss: 0.11690568178892136
2023-01-22 21:02:42.053935: step: 202/470, loss: 0.007767211180180311
2023-01-22 21:02:42.806503: step: 204/470, loss: 0.18378157913684845
2023-01-22 21:02:43.584405: step: 206/470, loss: 0.13678520917892456
2023-01-22 21:02:44.447885: step: 208/470, loss: 0.0026962130796164274
2023-01-22 21:02:45.201489: step: 210/470, loss: 0.0014513169880956411
2023-01-22 21:02:45.871200: step: 212/470, loss: 0.010849079117178917
2023-01-22 21:02:46.621516: step: 214/470, loss: 0.008346461690962315
2023-01-22 21:02:47.390668: step: 216/470, loss: 0.07517098635435104
2023-01-22 21:02:48.119049: step: 218/470, loss: 0.27010560035705566
2023-01-22 21:02:48.891824: step: 220/470, loss: 0.02572491392493248
2023-01-22 21:02:49.596127: step: 222/470, loss: 0.0008853495819494128
2023-01-22 21:02:50.319710: step: 224/470, loss: 0.01680896058678627
2023-01-22 21:02:51.096013: step: 226/470, loss: 0.024884656071662903
2023-01-22 21:02:51.828613: step: 228/470, loss: 0.0003141724446322769
2023-01-22 21:02:52.478642: step: 230/470, loss: 0.06602133810520172
2023-01-22 21:02:53.107349: step: 232/470, loss: 0.014157207682728767
2023-01-22 21:02:53.815280: step: 234/470, loss: 0.00014316238230094314
2023-01-22 21:02:54.554567: step: 236/470, loss: 0.010098121128976345
2023-01-22 21:02:55.316775: step: 238/470, loss: 0.006802602671086788
2023-01-22 21:02:56.100455: step: 240/470, loss: 0.026168648153543472
2023-01-22 21:02:56.740772: step: 242/470, loss: 0.020882943645119667
2023-01-22 21:02:57.371233: step: 244/470, loss: 0.0026823831722140312
2023-01-22 21:02:58.053594: step: 246/470, loss: 0.002364139771088958
2023-01-22 21:02:58.846313: step: 248/470, loss: 0.04574478790163994
2023-01-22 21:02:59.607334: step: 250/470, loss: 0.0015829337062314153
2023-01-22 21:03:00.323527: step: 252/470, loss: 0.018606998026371002
2023-01-22 21:03:01.022322: step: 254/470, loss: 0.00044129794696345925
2023-01-22 21:03:01.739070: step: 256/470, loss: 0.03767343983054161
2023-01-22 21:03:02.484291: step: 258/470, loss: 0.00863537099212408
2023-01-22 21:03:03.200784: step: 260/470, loss: 0.01770273968577385
2023-01-22 21:03:03.913431: step: 262/470, loss: 0.015628566965460777
2023-01-22 21:03:04.608068: step: 264/470, loss: 0.0023462101817131042
2023-01-22 21:03:05.289985: step: 266/470, loss: 0.0092113446444273
2023-01-22 21:03:05.987830: step: 268/470, loss: 0.06474064290523529
2023-01-22 21:03:06.706889: step: 270/470, loss: 8.660142157168593e-06
2023-01-22 21:03:07.529607: step: 272/470, loss: 0.3112047612667084
2023-01-22 21:03:08.360688: step: 274/470, loss: 0.24923990666866302
2023-01-22 21:03:09.073546: step: 276/470, loss: 0.0041430373676121235
2023-01-22 21:03:09.821824: step: 278/470, loss: 0.008526407182216644
2023-01-22 21:03:10.430119: step: 280/470, loss: 0.004656743258237839
2023-01-22 21:03:11.183071: step: 282/470, loss: 0.016585668548941612
2023-01-22 21:03:11.867500: step: 284/470, loss: 3.0181516194716096e-05
2023-01-22 21:03:12.687741: step: 286/470, loss: 0.0011372804874554276
2023-01-22 21:03:13.485533: step: 288/470, loss: 0.022914016619324684
2023-01-22 21:03:14.251126: step: 290/470, loss: 0.06423134356737137
2023-01-22 21:03:15.030015: step: 292/470, loss: 0.002632809802889824
2023-01-22 21:03:15.823507: step: 294/470, loss: 0.04266877844929695
2023-01-22 21:03:16.603793: step: 296/470, loss: 0.03284723311662674
2023-01-22 21:03:17.354754: step: 298/470, loss: 0.007151145022362471
2023-01-22 21:03:18.172276: step: 300/470, loss: 0.1206933856010437
2023-01-22 21:03:18.981795: step: 302/470, loss: 0.010511813685297966
2023-01-22 21:03:19.664557: step: 304/470, loss: 0.011880377307534218
2023-01-22 21:03:20.381647: step: 306/470, loss: 0.28889280557632446
2023-01-22 21:03:21.064352: step: 308/470, loss: 0.008291719481348991
2023-01-22 21:03:21.694249: step: 310/470, loss: 0.0001515456533525139
2023-01-22 21:03:22.412029: step: 312/470, loss: 0.5845152139663696
2023-01-22 21:03:23.080961: step: 314/470, loss: 0.05446061119437218
2023-01-22 21:03:23.778026: step: 316/470, loss: 0.00031370227225124836
2023-01-22 21:03:24.548085: step: 318/470, loss: 0.0016886562807485461
2023-01-22 21:03:25.242720: step: 320/470, loss: 0.007711860351264477
2023-01-22 21:03:26.023219: step: 322/470, loss: 0.0003481293679215014
2023-01-22 21:03:26.712098: step: 324/470, loss: 0.00423666276037693
2023-01-22 21:03:27.482811: step: 326/470, loss: 0.21974371373653412
2023-01-22 21:03:28.222914: step: 328/470, loss: 0.02752552181482315
2023-01-22 21:03:28.964720: step: 330/470, loss: 0.001168736140243709
2023-01-22 21:03:29.717222: step: 332/470, loss: 0.18791626393795013
2023-01-22 21:03:30.483063: step: 334/470, loss: 0.016098229214549065
2023-01-22 21:03:31.099114: step: 336/470, loss: 0.005329936742782593
2023-01-22 21:03:31.848975: step: 338/470, loss: 0.05876723304390907
2023-01-22 21:03:32.526819: step: 340/470, loss: 0.06268248707056046
2023-01-22 21:03:33.234743: step: 342/470, loss: 0.006979916710406542
2023-01-22 21:03:33.939662: step: 344/470, loss: 0.0026592700742185116
2023-01-22 21:03:34.596908: step: 346/470, loss: 0.0027532707899808884
2023-01-22 21:03:35.386474: step: 348/470, loss: 0.05007663369178772
2023-01-22 21:03:36.098240: step: 350/470, loss: 0.04327116161584854
2023-01-22 21:03:36.896297: step: 352/470, loss: 0.0002385459520155564
2023-01-22 21:03:37.654473: step: 354/470, loss: 0.08725601434707642
2023-01-22 21:03:38.316489: step: 356/470, loss: 0.007848616689443588
2023-01-22 21:03:39.000989: step: 358/470, loss: 0.010468382388353348
2023-01-22 21:03:39.701676: step: 360/470, loss: 0.0008415202610194683
2023-01-22 21:03:40.506498: step: 362/470, loss: 0.005082852207124233
2023-01-22 21:03:41.289268: step: 364/470, loss: 0.04120028764009476
2023-01-22 21:03:41.979163: step: 366/470, loss: 0.052009016275405884
2023-01-22 21:03:42.699667: step: 368/470, loss: 8.392710878979415e-05
2023-01-22 21:03:43.433080: step: 370/470, loss: 0.005474635865539312
2023-01-22 21:03:44.111776: step: 372/470, loss: 0.015097817406058311
2023-01-22 21:03:44.896917: step: 374/470, loss: 0.016206717118620872
2023-01-22 21:03:45.649868: step: 376/470, loss: 0.0031522957142442465
2023-01-22 21:03:46.351846: step: 378/470, loss: 0.00015461869770660996
2023-01-22 21:03:47.095829: step: 380/470, loss: 0.0001224875304615125
2023-01-22 21:03:47.799884: step: 382/470, loss: 0.006665257271379232
2023-01-22 21:03:48.615017: step: 384/470, loss: 0.039671264588832855
2023-01-22 21:03:49.346630: step: 386/470, loss: 0.037569403648376465
2023-01-22 21:03:50.094833: step: 388/470, loss: 0.005145507864654064
2023-01-22 21:03:50.894507: step: 390/470, loss: 0.0063809738494455814
2023-01-22 21:03:51.676009: step: 392/470, loss: 0.01172274723649025
2023-01-22 21:03:52.409896: step: 394/470, loss: 0.0012702624080702662
2023-01-22 21:03:53.129595: step: 396/470, loss: 0.007107668090611696
2023-01-22 21:03:53.795088: step: 398/470, loss: 0.014695264399051666
2023-01-22 21:03:54.546648: step: 400/470, loss: 0.018078316003084183
2023-01-22 21:03:55.305037: step: 402/470, loss: 0.027752364054322243
2023-01-22 21:03:56.056362: step: 404/470, loss: 0.028842059895396233
2023-01-22 21:03:56.766268: step: 406/470, loss: 0.03767353668808937
2023-01-22 21:03:57.460085: step: 408/470, loss: 0.030763795599341393
2023-01-22 21:03:58.238000: step: 410/470, loss: 0.05021560564637184
2023-01-22 21:03:59.003708: step: 412/470, loss: 0.040465906262397766
2023-01-22 21:03:59.766924: step: 414/470, loss: 0.04318307340145111
2023-01-22 21:04:00.494021: step: 416/470, loss: 0.003911891486495733
2023-01-22 21:04:01.173215: step: 418/470, loss: 0.005350908264517784
2023-01-22 21:04:01.901941: step: 420/470, loss: 0.00030204097856767476
2023-01-22 21:04:02.560988: step: 422/470, loss: 0.015325166285037994
2023-01-22 21:04:03.300876: step: 424/470, loss: 0.41761523485183716
2023-01-22 21:04:03.997875: step: 426/470, loss: 0.011177667416632175
2023-01-22 21:04:04.784598: step: 428/470, loss: 0.0751306414604187
2023-01-22 21:04:05.564189: step: 430/470, loss: 0.05438210442662239
2023-01-22 21:04:06.340498: step: 432/470, loss: 0.05413680523633957
2023-01-22 21:04:07.016638: step: 434/470, loss: 0.04908444359898567
2023-01-22 21:04:07.806739: step: 436/470, loss: 0.0007037912728264928
2023-01-22 21:04:08.475191: step: 438/470, loss: 0.0084762591868639
2023-01-22 21:04:09.120115: step: 440/470, loss: 0.007872858084738255
2023-01-22 21:04:09.824146: step: 442/470, loss: 0.004519272595643997
2023-01-22 21:04:10.601376: step: 444/470, loss: 0.0006240661023184657
2023-01-22 21:04:11.311121: step: 446/470, loss: 0.25435835123062134
2023-01-22 21:04:12.017344: step: 448/470, loss: 0.009995101019740105
2023-01-22 21:04:12.722507: step: 450/470, loss: 0.0034806779585778713
2023-01-22 21:04:13.434428: step: 452/470, loss: 0.25618600845336914
2023-01-22 21:04:14.130173: step: 454/470, loss: 0.0810975506901741
2023-01-22 21:04:14.922008: step: 456/470, loss: 0.007433571387082338
2023-01-22 21:04:15.621140: step: 458/470, loss: 0.16480611264705658
2023-01-22 21:04:16.354855: step: 460/470, loss: 0.0011335683520883322
2023-01-22 21:04:17.158805: step: 462/470, loss: 0.005519744008779526
2023-01-22 21:04:17.827259: step: 464/470, loss: 0.006193581037223339
2023-01-22 21:04:18.498544: step: 466/470, loss: 0.08350327610969543
2023-01-22 21:04:19.211876: step: 468/470, loss: 0.035261370241642
2023-01-22 21:04:19.972331: step: 470/470, loss: 0.04092838987708092
2023-01-22 21:04:20.632728: step: 472/470, loss: 0.014473150484263897
2023-01-22 21:04:21.344112: step: 474/470, loss: 0.23851221799850464
2023-01-22 21:04:22.047896: step: 476/470, loss: 0.019818585366010666
2023-01-22 21:04:22.770632: step: 478/470, loss: 0.01893843151628971
2023-01-22 21:04:23.485030: step: 480/470, loss: 0.042298175394535065
2023-01-22 21:04:24.234763: step: 482/470, loss: 0.007379506714642048
2023-01-22 21:04:25.012831: step: 484/470, loss: 0.02085047774016857
2023-01-22 21:04:25.711410: step: 486/470, loss: 0.02521711029112339
2023-01-22 21:04:26.472780: step: 488/470, loss: 0.02616407722234726
2023-01-22 21:04:27.196194: step: 490/470, loss: 0.0031149170827120543
2023-01-22 21:04:27.885294: step: 492/470, loss: 0.0020052469335496426
2023-01-22 21:04:28.668399: step: 494/470, loss: 0.0112814512103796
2023-01-22 21:04:29.381895: step: 496/470, loss: 0.00834614410996437
2023-01-22 21:04:30.103113: step: 498/470, loss: 0.0071093300357460976
2023-01-22 21:04:30.840505: step: 500/470, loss: 0.008331052958965302
2023-01-22 21:04:31.557449: step: 502/470, loss: 0.02857259288430214
2023-01-22 21:04:32.205596: step: 504/470, loss: 0.014069000259041786
2023-01-22 21:04:32.882545: step: 506/470, loss: 0.13017906248569489
2023-01-22 21:04:33.759061: step: 508/470, loss: 0.0029538320377469063
2023-01-22 21:04:34.498040: step: 510/470, loss: 0.0012912432430312037
2023-01-22 21:04:35.302739: step: 512/470, loss: 0.0015609815018251538
2023-01-22 21:04:36.081929: step: 514/470, loss: 0.02052444778382778
2023-01-22 21:04:36.747567: step: 516/470, loss: 0.1478673666715622
2023-01-22 21:04:37.461991: step: 518/470, loss: 0.0018792763585224748
2023-01-22 21:04:38.170382: step: 520/470, loss: 0.006700445432215929
2023-01-22 21:04:38.874759: step: 522/470, loss: 0.016489727422595024
2023-01-22 21:04:39.614649: step: 524/470, loss: 0.09012142568826675
2023-01-22 21:04:40.408303: step: 526/470, loss: 0.019330738112330437
2023-01-22 21:04:41.112982: step: 528/470, loss: 0.013795935548841953
2023-01-22 21:04:41.972946: step: 530/470, loss: 0.014351630583405495
2023-01-22 21:04:42.678750: step: 532/470, loss: 0.08632518351078033
2023-01-22 21:04:43.431305: step: 534/470, loss: 0.023600619286298752
2023-01-22 21:04:44.147148: step: 536/470, loss: 0.009278071112930775
2023-01-22 21:04:44.847493: step: 538/470, loss: 0.007990618236362934
2023-01-22 21:04:45.506956: step: 540/470, loss: 8.854016778059304e-05
2023-01-22 21:04:46.174583: step: 542/470, loss: 0.11269865930080414
2023-01-22 21:04:46.864274: step: 544/470, loss: 0.01807483844459057
2023-01-22 21:04:47.709132: step: 546/470, loss: 0.02807825244963169
2023-01-22 21:04:48.380207: step: 548/470, loss: 0.02302536927163601
2023-01-22 21:04:49.117635: step: 550/470, loss: 0.03050990402698517
2023-01-22 21:04:49.880492: step: 552/470, loss: 0.03772333264350891
2023-01-22 21:04:50.681525: step: 554/470, loss: 0.00996860396116972
2023-01-22 21:04:51.399866: step: 556/470, loss: 0.006364746019244194
2023-01-22 21:04:52.133650: step: 558/470, loss: 0.011979727074503899
2023-01-22 21:04:52.877623: step: 560/470, loss: 0.05357194319367409
2023-01-22 21:04:53.660264: step: 562/470, loss: 0.0625770092010498
2023-01-22 21:04:54.346502: step: 564/470, loss: 0.00023006857372820377
2023-01-22 21:04:55.109483: step: 566/470, loss: 0.019672883674502373
2023-01-22 21:04:55.874040: step: 568/470, loss: 0.04599352553486824
2023-01-22 21:04:56.616786: step: 570/470, loss: 0.010658334009349346
2023-01-22 21:04:57.457454: step: 572/470, loss: 0.015365660190582275
2023-01-22 21:04:58.279090: step: 574/470, loss: 0.004618105012923479
2023-01-22 21:04:58.989111: step: 576/470, loss: 0.0076096258126199245
2023-01-22 21:04:59.694847: step: 578/470, loss: 0.020669929683208466
2023-01-22 21:05:00.364416: step: 580/470, loss: 0.001826974330469966
2023-01-22 21:05:01.020571: step: 582/470, loss: 0.1444631665945053
2023-01-22 21:05:01.752775: step: 584/470, loss: 0.0031216128263622522
2023-01-22 21:05:02.500632: step: 586/470, loss: 0.016765842214226723
2023-01-22 21:05:03.301131: step: 588/470, loss: 0.007116939872503281
2023-01-22 21:05:04.009672: step: 590/470, loss: 0.13170292973518372
2023-01-22 21:05:04.770570: step: 592/470, loss: 0.016895027831196785
2023-01-22 21:05:05.464406: step: 594/470, loss: 0.00024278272758238018
2023-01-22 21:05:06.183774: step: 596/470, loss: 0.0030464413575828075
2023-01-22 21:05:06.806014: step: 598/470, loss: 0.0016490904381498694
2023-01-22 21:05:07.605091: step: 600/470, loss: 0.03087281621992588
2023-01-22 21:05:08.365717: step: 602/470, loss: 0.003503436455503106
2023-01-22 21:05:09.033591: step: 604/470, loss: 0.18342113494873047
2023-01-22 21:05:09.743693: step: 606/470, loss: 0.018698526546359062
2023-01-22 21:05:10.491795: step: 608/470, loss: 0.05845620110630989
2023-01-22 21:05:11.231382: step: 610/470, loss: 0.001678596599958837
2023-01-22 21:05:11.945883: step: 612/470, loss: 0.014549157582223415
2023-01-22 21:05:12.647051: step: 614/470, loss: 0.0009063933975994587
2023-01-22 21:05:13.317693: step: 616/470, loss: 0.0022073141299188137
2023-01-22 21:05:14.001475: step: 618/470, loss: 0.012333320453763008
2023-01-22 21:05:14.746659: step: 620/470, loss: 0.09075351059436798
2023-01-22 21:05:15.481233: step: 622/470, loss: 0.029867831617593765
2023-01-22 21:05:16.224549: step: 624/470, loss: 0.09833616763353348
2023-01-22 21:05:16.902278: step: 626/470, loss: 0.0060694171115756035
2023-01-22 21:05:17.523665: step: 628/470, loss: 0.008746202103793621
2023-01-22 21:05:18.172417: step: 630/470, loss: 0.0012253581080585718
2023-01-22 21:05:18.888368: step: 632/470, loss: 0.01028769463300705
2023-01-22 21:05:19.685666: step: 634/470, loss: 0.011649365536868572
2023-01-22 21:05:20.488346: step: 636/470, loss: 0.02281986176967621
2023-01-22 21:05:21.224676: step: 638/470, loss: 0.21459834277629852
2023-01-22 21:05:21.875051: step: 640/470, loss: 0.004545276518911123
2023-01-22 21:05:22.521362: step: 642/470, loss: 3.121816189377569e-05
2023-01-22 21:05:23.171098: step: 644/470, loss: 0.005426404532045126
2023-01-22 21:05:24.030001: step: 646/470, loss: 0.040757469832897186
2023-01-22 21:05:24.701036: step: 648/470, loss: 0.011101129464805126
2023-01-22 21:05:25.487500: step: 650/470, loss: 2.5025525093078613
2023-01-22 21:05:26.166308: step: 652/470, loss: 0.012538554146885872
2023-01-22 21:05:26.894207: step: 654/470, loss: 0.03285971283912659
2023-01-22 21:05:27.739522: step: 656/470, loss: 0.0021789884194731712
2023-01-22 21:05:28.469785: step: 658/470, loss: 0.001402953639626503
2023-01-22 21:05:29.221058: step: 660/470, loss: 0.0017720997566357255
2023-01-22 21:05:29.968619: step: 662/470, loss: 0.039381928741931915
2023-01-22 21:05:30.735291: step: 664/470, loss: 0.01845177263021469
2023-01-22 21:05:31.362527: step: 666/470, loss: 0.029854735359549522
2023-01-22 21:05:32.048140: step: 668/470, loss: 0.003992500249296427
2023-01-22 21:05:32.745423: step: 670/470, loss: 0.004251103848218918
2023-01-22 21:05:33.457461: step: 672/470, loss: 0.010103264823555946
2023-01-22 21:05:34.200948: step: 674/470, loss: 0.0004654536605812609
2023-01-22 21:05:34.924255: step: 676/470, loss: 0.4272131025791168
2023-01-22 21:05:35.617207: step: 678/470, loss: 0.0190906822681427
2023-01-22 21:05:36.423153: step: 680/470, loss: 0.005119283217936754
2023-01-22 21:05:37.149651: step: 682/470, loss: 0.0027894098311662674
2023-01-22 21:05:37.959825: step: 684/470, loss: 0.01846400462090969
2023-01-22 21:05:38.716873: step: 686/470, loss: 0.1110844612121582
2023-01-22 21:05:39.405772: step: 688/470, loss: 0.0023693658877164125
2023-01-22 21:05:40.111756: step: 690/470, loss: 0.003205197863280773
2023-01-22 21:05:40.849908: step: 692/470, loss: 0.017842544242739677
2023-01-22 21:05:41.603347: step: 694/470, loss: 0.018687259405851364
2023-01-22 21:05:42.226747: step: 696/470, loss: 8.786357648205012e-05
2023-01-22 21:05:42.953031: step: 698/470, loss: 0.0007583802798762918
2023-01-22 21:05:43.754099: step: 700/470, loss: 0.20183929800987244
2023-01-22 21:05:44.491768: step: 702/470, loss: 0.00020361962378956378
2023-01-22 21:05:45.281655: step: 704/470, loss: 0.027718501165509224
2023-01-22 21:05:45.970578: step: 706/470, loss: 0.00023348911781795323
2023-01-22 21:05:46.601436: step: 708/470, loss: 0.032941270619630814
2023-01-22 21:05:47.360391: step: 710/470, loss: 0.04147607460618019
2023-01-22 21:05:48.074074: step: 712/470, loss: 6.337544618872926e-05
2023-01-22 21:05:48.801853: step: 714/470, loss: 0.014632035978138447
2023-01-22 21:05:49.501610: step: 716/470, loss: 0.020782971754670143
2023-01-22 21:05:50.175045: step: 718/470, loss: 0.006766524165868759
2023-01-22 21:05:50.948522: step: 720/470, loss: 0.014275794848799706
2023-01-22 21:05:51.718957: step: 722/470, loss: 0.017139313742518425
2023-01-22 21:05:52.440233: step: 724/470, loss: 0.014928764663636684
2023-01-22 21:05:53.124845: step: 726/470, loss: 0.028308287262916565
2023-01-22 21:05:53.862711: step: 728/470, loss: 0.05225411802530289
2023-01-22 21:05:54.558711: step: 730/470, loss: 0.045965153723955154
2023-01-22 21:05:55.333892: step: 732/470, loss: 0.001099904766306281
2023-01-22 21:05:56.131525: step: 734/470, loss: 0.018097948282957077
2023-01-22 21:05:56.856106: step: 736/470, loss: 0.06644519418478012
2023-01-22 21:05:57.531578: step: 738/470, loss: 0.017522266134619713
2023-01-22 21:05:58.308701: step: 740/470, loss: 0.006565961986780167
2023-01-22 21:05:59.006263: step: 742/470, loss: 0.0008447995060123503
2023-01-22 21:05:59.731060: step: 744/470, loss: 0.008136849850416183
2023-01-22 21:06:00.541649: step: 746/470, loss: 0.02021070197224617
2023-01-22 21:06:01.218427: step: 748/470, loss: 0.0010262180585414171
2023-01-22 21:06:01.924369: step: 750/470, loss: 0.028441239148378372
2023-01-22 21:06:02.633023: step: 752/470, loss: 1.7200602087541483e-05
2023-01-22 21:06:03.388466: step: 754/470, loss: 0.005179987754672766
2023-01-22 21:06:04.162967: step: 756/470, loss: 0.2640395760536194
2023-01-22 21:06:04.821157: step: 758/470, loss: 0.001883813296444714
2023-01-22 21:06:05.533913: step: 760/470, loss: 0.024232909083366394
2023-01-22 21:06:06.226500: step: 762/470, loss: 0.031181665137410164
2023-01-22 21:06:07.001275: step: 764/470, loss: 0.13508857786655426
2023-01-22 21:06:07.701147: step: 766/470, loss: 0.02267894335091114
2023-01-22 21:06:08.476651: step: 768/470, loss: 0.01819641701877117
2023-01-22 21:06:09.262476: step: 770/470, loss: 0.03003586456179619
2023-01-22 21:06:09.996596: step: 772/470, loss: 0.02495230734348297
2023-01-22 21:06:10.761504: step: 774/470, loss: 0.016687629744410515
2023-01-22 21:06:11.459788: step: 776/470, loss: 0.001529327011667192
2023-01-22 21:06:12.207697: step: 778/470, loss: 0.05840422213077545
2023-01-22 21:06:12.942796: step: 780/470, loss: 0.003544104751199484
2023-01-22 21:06:13.685458: step: 782/470, loss: 0.00039587877108715475
2023-01-22 21:06:14.560543: step: 784/470, loss: 0.6694744825363159
2023-01-22 21:06:15.329370: step: 786/470, loss: 0.03220684081315994
2023-01-22 21:06:16.061048: step: 788/470, loss: 0.014541038312017918
2023-01-22 21:06:16.731859: step: 790/470, loss: 0.004369522910565138
2023-01-22 21:06:17.419724: step: 792/470, loss: 0.013264582492411137
2023-01-22 21:06:18.156572: step: 794/470, loss: 0.0005037263035774231
2023-01-22 21:06:18.936269: step: 796/470, loss: 0.002712902380153537
2023-01-22 21:06:19.763920: step: 798/470, loss: 0.3494986593723297
2023-01-22 21:06:20.489126: step: 800/470, loss: 0.0015915961703285575
2023-01-22 21:06:21.228912: step: 802/470, loss: 0.013079517520964146
2023-01-22 21:06:22.017199: step: 804/470, loss: 0.004297505598515272
2023-01-22 21:06:22.758609: step: 806/470, loss: 0.40553227066993713
2023-01-22 21:06:23.615673: step: 808/470, loss: 0.034644801169633865
2023-01-22 21:06:24.294123: step: 810/470, loss: 0.008511470630764961
2023-01-22 21:06:25.044629: step: 812/470, loss: 0.09465232491493225
2023-01-22 21:06:25.732672: step: 814/470, loss: 0.001864009303972125
2023-01-22 21:06:26.418223: step: 816/470, loss: 0.03610503673553467
2023-01-22 21:06:27.171770: step: 818/470, loss: 0.03397827968001366
2023-01-22 21:06:27.893578: step: 820/470, loss: 0.003417443251237273
2023-01-22 21:06:28.573106: step: 822/470, loss: 0.020306063815951347
2023-01-22 21:06:29.317549: step: 824/470, loss: 0.06476482003927231
2023-01-22 21:06:30.025068: step: 826/470, loss: 0.002904894994571805
2023-01-22 21:06:30.793667: step: 828/470, loss: 0.004498578608036041
2023-01-22 21:06:31.503329: step: 830/470, loss: 0.03605084493756294
2023-01-22 21:06:32.224249: step: 832/470, loss: 0.011630040593445301
2023-01-22 21:06:32.901728: step: 834/470, loss: 0.01983511820435524
2023-01-22 21:06:33.622632: step: 836/470, loss: 0.002731953514739871
2023-01-22 21:06:34.422946: step: 838/470, loss: 0.009025120176374912
2023-01-22 21:06:35.151393: step: 840/470, loss: 0.19690948724746704
2023-01-22 21:06:35.938893: step: 842/470, loss: 0.0033933157101273537
2023-01-22 21:06:36.636213: step: 844/470, loss: 0.054548464715480804
2023-01-22 21:06:37.377290: step: 846/470, loss: 0.003134024329483509
2023-01-22 21:06:38.162098: step: 848/470, loss: 0.09228435903787613
2023-01-22 21:06:38.859081: step: 850/470, loss: 0.0018799483077600598
2023-01-22 21:06:39.722901: step: 852/470, loss: 0.13064418733119965
2023-01-22 21:06:40.434866: step: 854/470, loss: 0.0057640597224235535
2023-01-22 21:06:41.133815: step: 856/470, loss: 0.00749384006485343
2023-01-22 21:06:41.908274: step: 858/470, loss: 0.0018819028045982122
2023-01-22 21:06:42.644653: step: 860/470, loss: 0.012828037142753601
2023-01-22 21:06:43.335956: step: 862/470, loss: 0.00204385444521904
2023-01-22 21:06:44.109457: step: 864/470, loss: 0.03246442228555679
2023-01-22 21:06:44.825570: step: 866/470, loss: 0.042275648564100266
2023-01-22 21:06:45.437763: step: 868/470, loss: 0.020331397652626038
2023-01-22 21:06:46.099169: step: 870/470, loss: 0.019861869513988495
2023-01-22 21:06:46.752057: step: 872/470, loss: 0.0008119989070110023
2023-01-22 21:06:47.490000: step: 874/470, loss: 0.00033393464400433004
2023-01-22 21:06:48.201337: step: 876/470, loss: 0.001284466008655727
2023-01-22 21:06:48.875643: step: 878/470, loss: 0.0018008254701271653
2023-01-22 21:06:49.631096: step: 880/470, loss: 0.0011693740962073207
2023-01-22 21:06:50.339334: step: 882/470, loss: 0.002523294650018215
2023-01-22 21:06:51.058577: step: 884/470, loss: 0.022206205874681473
2023-01-22 21:06:51.753891: step: 886/470, loss: 0.0008540766430087388
2023-01-22 21:06:52.480672: step: 888/470, loss: 0.0023554093204438686
2023-01-22 21:06:53.191695: step: 890/470, loss: 0.013779774308204651
2023-01-22 21:06:53.970306: step: 892/470, loss: 0.010381845757365227
2023-01-22 21:06:54.708761: step: 894/470, loss: 0.02899681217968464
2023-01-22 21:06:55.492434: step: 896/470, loss: 0.04453825205564499
2023-01-22 21:06:56.191046: step: 898/470, loss: 0.05921311303973198
2023-01-22 21:06:57.074700: step: 900/470, loss: 0.006646065041422844
2023-01-22 21:06:57.785133: step: 902/470, loss: 0.023994415998458862
2023-01-22 21:06:58.545601: step: 904/470, loss: 0.002556569641456008
2023-01-22 21:06:59.278814: step: 906/470, loss: 0.0003309166640974581
2023-01-22 21:07:00.033984: step: 908/470, loss: 0.002325868234038353
2023-01-22 21:07:00.740369: step: 910/470, loss: 0.042233262211084366
2023-01-22 21:07:01.550037: step: 912/470, loss: 6.879373540868983e-05
2023-01-22 21:07:02.313036: step: 914/470, loss: 0.01983904279768467
2023-01-22 21:07:03.099098: step: 916/470, loss: 0.18573109805583954
2023-01-22 21:07:03.796951: step: 918/470, loss: 0.032089248299598694
2023-01-22 21:07:04.599283: step: 920/470, loss: 0.0024486505426466465
2023-01-22 21:07:05.339164: step: 922/470, loss: 0.013104692101478577
2023-01-22 21:07:06.042293: step: 924/470, loss: 0.9032142162322998
2023-01-22 21:07:06.865511: step: 926/470, loss: 0.13171081244945526
2023-01-22 21:07:07.584910: step: 928/470, loss: 0.026930810883641243
2023-01-22 21:07:08.338253: step: 930/470, loss: 0.5041398406028748
2023-01-22 21:07:09.086381: step: 932/470, loss: 0.002014985540881753
2023-01-22 21:07:09.712045: step: 934/470, loss: 0.0011477648513391614
2023-01-22 21:07:10.394230: step: 936/470, loss: 0.01803838089108467
2023-01-22 21:07:11.119225: step: 938/470, loss: 0.0009580638143233955
2023-01-22 21:07:11.882280: step: 940/470, loss: 0.0020920049864798784
2023-01-22 21:07:12.542414: step: 942/470, loss: 0.011814834550023079
==================================================
Loss: 0.048
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28490410052910053, 'r': 0.3405874446552815, 'f1': 0.3102672140593489}, 'combined': 0.22861794720162548, 'epoch': 32}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34558926877396756, 'r': 0.3721730586796574, 'f1': 0.3583888713211516}, 'combined': 0.24962408947741904, 'epoch': 32}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2784876766440414, 'r': 0.3408435511108287, 'f1': 0.306526538285677}, 'combined': 0.2258616597894462, 'epoch': 32}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35217647494606535, 'r': 0.3745261358561041, 'f1': 0.3630076246881158}, 'combined': 0.25284113162356325, 'epoch': 32}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2693469609261939, 'r': 0.3531665085388994, 'f1': 0.30561371100164203}, 'combined': 0.2251890502117362, 'epoch': 32}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33691353726061807, 'r': 0.3809714613639296, 'f1': 0.35759054135242496}, 'combined': 0.24906803875293282, 'epoch': 32}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23026315789473684, 'r': 0.375, 'f1': 0.28532608695652173}, 'combined': 0.1902173913043478, 'epoch': 32}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.20833333333333334, 'r': 0.32608695652173914, 'f1': 0.25423728813559326}, 'combined': 0.12711864406779663, 'epoch': 32}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4642857142857143, 'r': 0.33620689655172414, 'f1': 0.39}, 'combined': 0.26, 'epoch': 32}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 33
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 21:09:48.685151: step: 2/470, loss: 0.0353984571993351
2023-01-22 21:09:49.333277: step: 4/470, loss: 0.0006110117537900805
2023-01-22 21:09:50.013957: step: 6/470, loss: 0.003695101011544466
2023-01-22 21:09:50.786096: step: 8/470, loss: 0.01956905983388424
2023-01-22 21:09:51.518926: step: 10/470, loss: 0.010541500523686409
2023-01-22 21:09:52.198732: step: 12/470, loss: 0.025140857324004173
2023-01-22 21:09:52.977495: step: 14/470, loss: 0.00231540622189641
2023-01-22 21:09:53.736601: step: 16/470, loss: 0.0011222070315852761
2023-01-22 21:09:54.419989: step: 18/470, loss: 0.003358704037964344
2023-01-22 21:09:55.174065: step: 20/470, loss: 0.001413871650584042
2023-01-22 21:09:56.007546: step: 22/470, loss: 0.001081290072761476
2023-01-22 21:09:56.735280: step: 24/470, loss: 0.011456046253442764
2023-01-22 21:09:57.493733: step: 26/470, loss: 0.004079823382198811
2023-01-22 21:09:58.219395: step: 28/470, loss: 0.0013503070222213864
2023-01-22 21:09:58.877782: step: 30/470, loss: 0.005739379674196243
2023-01-22 21:09:59.597538: step: 32/470, loss: 0.016481278464198112
2023-01-22 21:10:00.335707: step: 34/470, loss: 0.0638788491487503
2023-01-22 21:10:01.052437: step: 36/470, loss: 0.003887937404215336
2023-01-22 21:10:01.871580: step: 38/470, loss: 2.0889205932617188
2023-01-22 21:10:02.595046: step: 40/470, loss: 0.005325763486325741
2023-01-22 21:10:03.273635: step: 42/470, loss: 0.004101912025362253
2023-01-22 21:10:03.997062: step: 44/470, loss: 0.0046531264670193195
2023-01-22 21:10:04.672208: step: 46/470, loss: 0.01230566669255495
2023-01-22 21:10:05.437872: step: 48/470, loss: 3.5447123082121834e-05
2023-01-22 21:10:06.291063: step: 50/470, loss: 0.012923387810587883
2023-01-22 21:10:06.989354: step: 52/470, loss: 0.016211075708270073
2023-01-22 21:10:07.768429: step: 54/470, loss: 0.09570623189210892
2023-01-22 21:10:08.563206: step: 56/470, loss: 0.01940716803073883
2023-01-22 21:10:09.280888: step: 58/470, loss: 0.010799039155244827
2023-01-22 21:10:10.030990: step: 60/470, loss: 0.0031259532552212477
2023-01-22 21:10:10.788733: step: 62/470, loss: 0.0015492573147639632
2023-01-22 21:10:11.551507: step: 64/470, loss: 0.03166002035140991
2023-01-22 21:10:12.247325: step: 66/470, loss: 0.0006916436832398176
2023-01-22 21:10:13.068667: step: 68/470, loss: 0.026572024449706078
2023-01-22 21:10:13.829819: step: 70/470, loss: 0.0100321089848876
2023-01-22 21:10:14.444011: step: 72/470, loss: 0.0022878365125507116
2023-01-22 21:10:15.154355: step: 74/470, loss: 0.0371539369225502
2023-01-22 21:10:15.917480: step: 76/470, loss: 0.05440312996506691
2023-01-22 21:10:16.686478: step: 78/470, loss: 0.007360953837633133
2023-01-22 21:10:17.379303: step: 80/470, loss: 0.012081542983651161
2023-01-22 21:10:18.086318: step: 82/470, loss: 0.0012202973011881113
2023-01-22 21:10:18.830743: step: 84/470, loss: 0.00959607120603323
2023-01-22 21:10:19.646254: step: 86/470, loss: 0.0013847972732037306
2023-01-22 21:10:20.343825: step: 88/470, loss: 0.0005331527790986001
2023-01-22 21:10:21.025982: step: 90/470, loss: 0.0019345465116202831
2023-01-22 21:10:21.753765: step: 92/470, loss: 0.005651640705764294
2023-01-22 21:10:22.594637: step: 94/470, loss: 0.47246649861335754
2023-01-22 21:10:23.303690: step: 96/470, loss: 0.008398247882723808
2023-01-22 21:10:23.987290: step: 98/470, loss: 0.002498921239748597
2023-01-22 21:10:24.695205: step: 100/470, loss: 0.0005510192713700235
2023-01-22 21:10:25.339054: step: 102/470, loss: 0.0007535783806815743
2023-01-22 21:10:26.091108: step: 104/470, loss: 0.00044582068221643567
2023-01-22 21:10:26.844026: step: 106/470, loss: 0.015184991993010044
2023-01-22 21:10:27.485513: step: 108/470, loss: 0.09019918739795685
2023-01-22 21:10:28.241831: step: 110/470, loss: 0.00018215616000816226
2023-01-22 21:10:29.006485: step: 112/470, loss: 0.0013423897325992584
2023-01-22 21:10:29.685031: step: 114/470, loss: 0.004689566791057587
2023-01-22 21:10:30.470560: step: 116/470, loss: 0.001340361312031746
2023-01-22 21:10:31.189234: step: 118/470, loss: 0.007616905961185694
2023-01-22 21:10:31.869953: step: 120/470, loss: 0.03174249827861786
2023-01-22 21:10:32.557077: step: 122/470, loss: 0.0005641809548251331
2023-01-22 21:10:33.265238: step: 124/470, loss: 0.0015309054870158434
2023-01-22 21:10:33.981755: step: 126/470, loss: 0.024390079081058502
2023-01-22 21:10:34.695989: step: 128/470, loss: 0.023455774411559105
2023-01-22 21:10:35.428077: step: 130/470, loss: 0.10771681368350983
2023-01-22 21:10:36.198567: step: 132/470, loss: 9.4806935521774e-05
2023-01-22 21:10:36.878105: step: 134/470, loss: 0.007546218577772379
2023-01-22 21:10:37.529777: step: 136/470, loss: 0.006308150477707386
2023-01-22 21:10:38.288967: step: 138/470, loss: 0.3277882933616638
2023-01-22 21:10:39.084755: step: 140/470, loss: 0.016741199418902397
2023-01-22 21:10:39.815680: step: 142/470, loss: 0.02945149876177311
2023-01-22 21:10:40.505588: step: 144/470, loss: 0.0745350643992424
2023-01-22 21:10:41.188546: step: 146/470, loss: 0.0008599523571319878
2023-01-22 21:10:41.978471: step: 148/470, loss: 0.01641632243990898
2023-01-22 21:10:42.734184: step: 150/470, loss: 0.007939077913761139
2023-01-22 21:10:43.423530: step: 152/470, loss: 0.0034217501524835825
2023-01-22 21:10:44.141100: step: 154/470, loss: 0.0031094097066670656
2023-01-22 21:10:44.800983: step: 156/470, loss: 0.020805522799491882
2023-01-22 21:10:45.556237: step: 158/470, loss: 0.0015209285775199533
2023-01-22 21:10:46.264081: step: 160/470, loss: 0.003026079386472702
2023-01-22 21:10:46.975900: step: 162/470, loss: 0.03428162634372711
2023-01-22 21:10:47.717037: step: 164/470, loss: 0.0027114320546388626
2023-01-22 21:10:48.500150: step: 166/470, loss: 0.027286209166049957
2023-01-22 21:10:49.218079: step: 168/470, loss: 0.00016404094640165567
2023-01-22 21:10:49.978430: step: 170/470, loss: 0.031211018562316895
2023-01-22 21:10:50.664629: step: 172/470, loss: 0.003412870690226555
2023-01-22 21:10:51.408606: step: 174/470, loss: 0.043129902333021164
2023-01-22 21:10:52.096448: step: 176/470, loss: 0.07710176706314087
2023-01-22 21:10:52.874204: step: 178/470, loss: 0.017537254840135574
2023-01-22 21:10:53.522939: step: 180/470, loss: 0.009631001390516758
2023-01-22 21:10:54.166077: step: 182/470, loss: 0.001838182215578854
2023-01-22 21:10:54.846012: step: 184/470, loss: 0.013489598408341408
2023-01-22 21:10:55.621618: step: 186/470, loss: 0.021947944536805153
2023-01-22 21:10:56.377416: step: 188/470, loss: 0.008992105722427368
2023-01-22 21:10:57.141286: step: 190/470, loss: 0.17299090325832367
2023-01-22 21:10:57.813693: step: 192/470, loss: 0.0001017658578348346
2023-01-22 21:10:58.516615: step: 194/470, loss: 0.00856022723019123
2023-01-22 21:10:59.206856: step: 196/470, loss: 0.0008848054567351937
2023-01-22 21:10:59.891447: step: 198/470, loss: 0.004278761800378561
2023-01-22 21:11:00.690103: step: 200/470, loss: 0.0017920746468007565
2023-01-22 21:11:01.399708: step: 202/470, loss: 0.00201309728436172
2023-01-22 21:11:02.111805: step: 204/470, loss: 0.01744202710688114
2023-01-22 21:11:02.836125: step: 206/470, loss: 0.0012796318624168634
2023-01-22 21:11:03.492859: step: 208/470, loss: 4.2182771721854806e-05
2023-01-22 21:11:04.209528: step: 210/470, loss: 0.0001089559227693826
2023-01-22 21:11:05.072714: step: 212/470, loss: 0.019380543380975723
2023-01-22 21:11:05.781763: step: 214/470, loss: 0.020527342334389687
2023-01-22 21:11:06.474254: step: 216/470, loss: 0.0021591780241578817
2023-01-22 21:11:07.192216: step: 218/470, loss: 0.00999562069773674
2023-01-22 21:11:08.026348: step: 220/470, loss: 0.02325505018234253
2023-01-22 21:11:08.723563: step: 222/470, loss: 0.022767867892980576
2023-01-22 21:11:09.449790: step: 224/470, loss: 0.0006900187581777573
2023-01-22 21:11:10.158599: step: 226/470, loss: 0.008171236142516136
2023-01-22 21:11:10.973381: step: 228/470, loss: 0.0029809472616761923
2023-01-22 21:11:11.676376: step: 230/470, loss: 0.002115656156092882
2023-01-22 21:11:12.473853: step: 232/470, loss: 0.003473465796560049
2023-01-22 21:11:13.323660: step: 234/470, loss: 0.040313441306352615
2023-01-22 21:11:14.260238: step: 236/470, loss: 0.027963347733020782
2023-01-22 21:11:15.047957: step: 238/470, loss: 0.011281131766736507
2023-01-22 21:11:15.771631: step: 240/470, loss: 0.00025161568191833794
2023-01-22 21:11:16.436014: step: 242/470, loss: 0.027061283588409424
2023-01-22 21:11:17.226731: step: 244/470, loss: 0.026121623814105988
2023-01-22 21:11:17.944831: step: 246/470, loss: 0.009257947094738483
2023-01-22 21:11:18.628075: step: 248/470, loss: 0.010101567022502422
2023-01-22 21:11:19.391864: step: 250/470, loss: 1.0979067087173462
2023-01-22 21:11:20.076933: step: 252/470, loss: 0.006160234101116657
2023-01-22 21:11:20.824960: step: 254/470, loss: 0.004955607000738382
2023-01-22 21:11:21.538396: step: 256/470, loss: 0.009282803162932396
2023-01-22 21:11:22.193846: step: 258/470, loss: 0.004642096348106861
2023-01-22 21:11:22.917178: step: 260/470, loss: 0.029528679326176643
2023-01-22 21:11:23.608543: step: 262/470, loss: 0.01058510597795248
2023-01-22 21:11:24.272874: step: 264/470, loss: 0.007069876883178949
2023-01-22 21:11:25.007748: step: 266/470, loss: 0.010932988487184048
2023-01-22 21:11:25.698237: step: 268/470, loss: 0.0012139062164351344
2023-01-22 21:11:26.478215: step: 270/470, loss: 0.0031020056921988726
2023-01-22 21:11:27.217213: step: 272/470, loss: 0.019556628540158272
2023-01-22 21:11:27.939623: step: 274/470, loss: 0.003774407086893916
2023-01-22 21:11:28.600096: step: 276/470, loss: 0.002119203330948949
2023-01-22 21:11:29.312166: step: 278/470, loss: 0.006396686192601919
2023-01-22 21:11:29.944286: step: 280/470, loss: 0.0008285631192848086
2023-01-22 21:11:30.628281: step: 282/470, loss: 0.030592042952775955
2023-01-22 21:11:31.300671: step: 284/470, loss: 0.02650538459420204
2023-01-22 21:11:32.029331: step: 286/470, loss: 0.0008941978449001908
2023-01-22 21:11:32.750074: step: 288/470, loss: 0.0010146403219550848
2023-01-22 21:11:33.511508: step: 290/470, loss: 0.002193046733736992
2023-01-22 21:11:34.249401: step: 292/470, loss: 0.013625368475914001
2023-01-22 21:11:34.957340: step: 294/470, loss: 0.00888641644269228
2023-01-22 21:11:35.682257: step: 296/470, loss: 0.0019641213584691286
2023-01-22 21:11:36.440328: step: 298/470, loss: 0.4439093768596649
2023-01-22 21:11:37.122693: step: 300/470, loss: 0.0006960076279938221
2023-01-22 21:11:37.887536: step: 302/470, loss: 0.0003841613361146301
2023-01-22 21:11:38.628530: step: 304/470, loss: 0.11751359701156616
2023-01-22 21:11:39.404988: step: 306/470, loss: 0.0003117234446108341
2023-01-22 21:11:40.121236: step: 308/470, loss: 0.012473184615373611
2023-01-22 21:11:40.924840: step: 310/470, loss: 0.003341148141771555
2023-01-22 21:11:41.716578: step: 312/470, loss: 0.016889702528715134
2023-01-22 21:11:42.505462: step: 314/470, loss: 0.03929717838764191
2023-01-22 21:11:43.247598: step: 316/470, loss: 4.825163341592997e-05
2023-01-22 21:11:43.969512: step: 318/470, loss: 0.48037540912628174
2023-01-22 21:11:44.691889: step: 320/470, loss: 0.010676422156393528
2023-01-22 21:11:45.436426: step: 322/470, loss: 0.00287465937435627
2023-01-22 21:11:46.141122: step: 324/470, loss: 0.0012692613527178764
2023-01-22 21:11:46.814975: step: 326/470, loss: 0.021290870383381844
2023-01-22 21:11:47.534679: step: 328/470, loss: 0.021226149052381516
2023-01-22 21:11:48.437373: step: 330/470, loss: 0.037113256752491
2023-01-22 21:11:49.170154: step: 332/470, loss: 0.0005753267323598266
2023-01-22 21:11:49.934621: step: 334/470, loss: 0.009010824374854565
2023-01-22 21:11:50.713252: step: 336/470, loss: 0.0034445514902472496
2023-01-22 21:11:51.408331: step: 338/470, loss: 0.0003466394846327603
2023-01-22 21:11:52.096255: step: 340/470, loss: 0.0053068287670612335
2023-01-22 21:11:52.742236: step: 342/470, loss: 0.017965000122785568
2023-01-22 21:11:53.526100: step: 344/470, loss: 0.027688566595315933
2023-01-22 21:11:54.253361: step: 346/470, loss: 0.0012403011787682772
2023-01-22 21:11:54.919201: step: 348/470, loss: 2.2492525577545166
2023-01-22 21:11:55.735845: step: 350/470, loss: 0.009851688519120216
2023-01-22 21:11:56.435432: step: 352/470, loss: 0.06665859371423721
2023-01-22 21:11:57.337968: step: 354/470, loss: 0.014958545565605164
2023-01-22 21:11:58.040575: step: 356/470, loss: 0.0006210833671502769
2023-01-22 21:11:58.759472: step: 358/470, loss: 0.001347895129583776
2023-01-22 21:11:59.492414: step: 360/470, loss: 0.0017309411196038127
2023-01-22 21:12:00.260239: step: 362/470, loss: 0.10375341773033142
2023-01-22 21:12:00.964722: step: 364/470, loss: 0.00011790274584200233
2023-01-22 21:12:01.733458: step: 366/470, loss: 0.024094436317682266
2023-01-22 21:12:02.417155: step: 368/470, loss: 0.007840093225240707
2023-01-22 21:12:03.192197: step: 370/470, loss: 0.005822331178933382
2023-01-22 21:12:04.047205: step: 372/470, loss: 0.015622143633663654
2023-01-22 21:12:04.687078: step: 374/470, loss: 0.0032653925009071827
2023-01-22 21:12:05.403710: step: 376/470, loss: 0.0022503521759063005
2023-01-22 21:12:06.166382: step: 378/470, loss: 0.01404476910829544
2023-01-22 21:12:06.933634: step: 380/470, loss: 0.007879259996116161
2023-01-22 21:12:07.638419: step: 382/470, loss: 0.5576677918434143
2023-01-22 21:12:08.331364: step: 384/470, loss: 0.00043255838681943715
2023-01-22 21:12:09.123970: step: 386/470, loss: 0.00029005203396081924
2023-01-22 21:12:09.895843: step: 388/470, loss: 0.0023896731436252594
2023-01-22 21:12:10.558769: step: 390/470, loss: 0.013917365111410618
2023-01-22 21:12:11.300417: step: 392/470, loss: 0.000244982453295961
2023-01-22 21:12:12.086907: step: 394/470, loss: 0.22541584074497223
2023-01-22 21:12:12.839240: step: 396/470, loss: 0.009782961569726467
2023-01-22 21:12:13.589913: step: 398/470, loss: 0.0009558402234688401
2023-01-22 21:12:14.403571: step: 400/470, loss: 0.04024609923362732
2023-01-22 21:12:15.085598: step: 402/470, loss: 0.030957777053117752
2023-01-22 21:12:15.869903: step: 404/470, loss: 0.0017546005547046661
2023-01-22 21:12:16.551577: step: 406/470, loss: 0.0013082153163850307
2023-01-22 21:12:17.332447: step: 408/470, loss: 0.11711828410625458
2023-01-22 21:12:18.043864: step: 410/470, loss: 0.020939351990818977
2023-01-22 21:12:18.726561: step: 412/470, loss: 0.04790695011615753
2023-01-22 21:12:19.423595: step: 414/470, loss: 0.0010895759332925081
2023-01-22 21:12:20.170545: step: 416/470, loss: 0.017710620537400246
2023-01-22 21:12:20.899962: step: 418/470, loss: 0.01992659457027912
2023-01-22 21:12:21.625187: step: 420/470, loss: 0.03188169375061989
2023-01-22 21:12:22.385843: step: 422/470, loss: 0.04130684584379196
2023-01-22 21:12:23.106283: step: 424/470, loss: 0.07215629518032074
2023-01-22 21:12:23.861926: step: 426/470, loss: 0.00011767345131374896
2023-01-22 21:12:24.682130: step: 428/470, loss: 0.000228075819904916
2023-01-22 21:12:25.453363: step: 430/470, loss: 0.0013060378842055798
2023-01-22 21:12:26.161632: step: 432/470, loss: 0.0043433355167508125
2023-01-22 21:12:26.878634: step: 434/470, loss: 0.259304016828537
2023-01-22 21:12:27.635415: step: 436/470, loss: 0.017298951745033264
2023-01-22 21:12:28.425996: step: 438/470, loss: 0.0009541614563204348
2023-01-22 21:12:29.176862: step: 440/470, loss: 0.0033586365170776844
2023-01-22 21:12:29.888750: step: 442/470, loss: 0.005000745877623558
2023-01-22 21:12:30.611271: step: 444/470, loss: 0.02338077686727047
2023-01-22 21:12:31.400230: step: 446/470, loss: 0.10848845541477203
2023-01-22 21:12:32.130285: step: 448/470, loss: 0.07149527221918106
2023-01-22 21:12:32.908513: step: 450/470, loss: 0.005873269401490688
2023-01-22 21:12:33.589637: step: 452/470, loss: 0.018467245623469353
2023-01-22 21:12:34.366153: step: 454/470, loss: 0.004103237763047218
2023-01-22 21:12:35.104760: step: 456/470, loss: 0.00016769995272625238
2023-01-22 21:12:35.894110: step: 458/470, loss: 0.05550146475434303
2023-01-22 21:12:36.570505: step: 460/470, loss: 0.002988182008266449
2023-01-22 21:12:37.299709: step: 462/470, loss: 0.019142037257552147
2023-01-22 21:12:38.013808: step: 464/470, loss: 0.0012444063322618604
2023-01-22 21:12:38.731067: step: 466/470, loss: 0.00499011529609561
2023-01-22 21:12:39.469305: step: 468/470, loss: 0.029499473050236702
2023-01-22 21:12:40.159649: step: 470/470, loss: 0.009594298899173737
2023-01-22 21:12:40.917968: step: 472/470, loss: 0.0007405190262943506
2023-01-22 21:12:41.631663: step: 474/470, loss: 0.006137060932815075
2023-01-22 21:12:42.355803: step: 476/470, loss: 4.0265680581796914e-05
2023-01-22 21:12:43.041513: step: 478/470, loss: 1.632533167139627e-05
2023-01-22 21:12:43.756811: step: 480/470, loss: 0.0258161760866642
2023-01-22 21:12:44.538232: step: 482/470, loss: 0.4235173165798187
2023-01-22 21:12:45.221503: step: 484/470, loss: 0.008250389248132706
2023-01-22 21:12:45.935102: step: 486/470, loss: 0.02013562060892582
2023-01-22 21:12:46.676805: step: 488/470, loss: 0.02626902237534523
2023-01-22 21:12:47.430393: step: 490/470, loss: 0.004141016863286495
2023-01-22 21:12:48.134939: step: 492/470, loss: 0.0033669506665319204
2023-01-22 21:12:48.849279: step: 494/470, loss: 0.7086845636367798
2023-01-22 21:12:49.532974: step: 496/470, loss: 0.0009194430313073099
2023-01-22 21:12:50.268944: step: 498/470, loss: 0.003966304939240217
2023-01-22 21:12:50.968562: step: 500/470, loss: 0.029114434495568275
2023-01-22 21:12:51.654857: step: 502/470, loss: 0.00011125182209070772
2023-01-22 21:12:52.399822: step: 504/470, loss: 0.014639819972217083
2023-01-22 21:12:53.099599: step: 506/470, loss: 0.008477681316435337
2023-01-22 21:12:53.842127: step: 508/470, loss: 0.011175676248967648
2023-01-22 21:12:54.609688: step: 510/470, loss: 0.0035168358590453863
2023-01-22 21:12:55.370024: step: 512/470, loss: 0.013511012308299541
2023-01-22 21:12:56.090966: step: 514/470, loss: 4.397913653519936e-05
2023-01-22 21:12:56.904727: step: 516/470, loss: 0.01750068925321102
2023-01-22 21:12:57.633829: step: 518/470, loss: 0.000392085436033085
2023-01-22 21:12:58.302866: step: 520/470, loss: 0.0018893035594373941
2023-01-22 21:12:58.986089: step: 522/470, loss: 0.006660451181232929
2023-01-22 21:12:59.750467: step: 524/470, loss: 0.02844826504588127
2023-01-22 21:13:00.573373: step: 526/470, loss: 0.009441560134291649
2023-01-22 21:13:01.319639: step: 528/470, loss: 0.006550501566380262
2023-01-22 21:13:02.163234: step: 530/470, loss: 0.06545102596282959
2023-01-22 21:13:02.895382: step: 532/470, loss: 0.017406875267624855
2023-01-22 21:13:03.658391: step: 534/470, loss: 0.016543585807085037
2023-01-22 21:13:04.419077: step: 536/470, loss: 0.01982169970870018
2023-01-22 21:13:05.185315: step: 538/470, loss: 0.004087928682565689
2023-01-22 21:13:06.042022: step: 540/470, loss: 0.017809614539146423
2023-01-22 21:13:06.740668: step: 542/470, loss: 0.016991348937153816
2023-01-22 21:13:07.563514: step: 544/470, loss: 0.002067740773782134
2023-01-22 21:13:08.254759: step: 546/470, loss: 0.07715543359518051
2023-01-22 21:13:08.889982: step: 548/470, loss: 3.090485552093014e-05
2023-01-22 21:13:09.616845: step: 550/470, loss: 0.015211367048323154
2023-01-22 21:13:10.279769: step: 552/470, loss: 0.11407588422298431
2023-01-22 21:13:11.081563: step: 554/470, loss: 0.04695338010787964
2023-01-22 21:13:11.854682: step: 556/470, loss: 0.007329762447625399
2023-01-22 21:13:12.625001: step: 558/470, loss: 0.007562029641121626
2023-01-22 21:13:13.481497: step: 560/470, loss: 0.028891831636428833
2023-01-22 21:13:14.215173: step: 562/470, loss: 0.004206001292914152
2023-01-22 21:13:14.854187: step: 564/470, loss: 0.0011216033017262816
2023-01-22 21:13:15.573807: step: 566/470, loss: 0.03309805318713188
2023-01-22 21:13:16.283519: step: 568/470, loss: 0.0024206622038036585
2023-01-22 21:13:17.037521: step: 570/470, loss: 0.03466884419322014
2023-01-22 21:13:17.713112: step: 572/470, loss: 0.028366921469569206
2023-01-22 21:13:18.413344: step: 574/470, loss: 0.014122523367404938
2023-01-22 21:13:19.105082: step: 576/470, loss: 0.03809332102537155
2023-01-22 21:13:19.874029: step: 578/470, loss: 0.032920315861701965
2023-01-22 21:13:20.600811: step: 580/470, loss: 0.45645061135292053
2023-01-22 21:13:21.339420: step: 582/470, loss: 0.007378171198070049
2023-01-22 21:13:22.124661: step: 584/470, loss: 0.016221599653363228
2023-01-22 21:13:22.782531: step: 586/470, loss: 0.0018637162866070867
2023-01-22 21:13:23.655809: step: 588/470, loss: 0.00019457412417978048
2023-01-22 21:13:24.435607: step: 590/470, loss: 0.0033394538331776857
2023-01-22 21:13:25.172386: step: 592/470, loss: 0.017871206626296043
2023-01-22 21:13:25.875652: step: 594/470, loss: 0.018105637282133102
2023-01-22 21:13:26.619910: step: 596/470, loss: 0.02217262051999569
2023-01-22 21:13:27.412624: step: 598/470, loss: 0.03489815443754196
2023-01-22 21:13:28.074572: step: 600/470, loss: 0.004941632971167564
2023-01-22 21:13:28.745300: step: 602/470, loss: 0.009684709832072258
2023-01-22 21:13:29.459640: step: 604/470, loss: 0.010802370496094227
2023-01-22 21:13:30.228081: step: 606/470, loss: 0.0353492833673954
2023-01-22 21:13:31.118922: step: 608/470, loss: 0.009187396615743637
2023-01-22 21:13:31.812580: step: 610/470, loss: 0.00303685013204813
2023-01-22 21:13:32.552944: step: 612/470, loss: 0.017729606479406357
2023-01-22 21:13:33.307941: step: 614/470, loss: 0.009220817126333714
2023-01-22 21:13:34.049734: step: 616/470, loss: 0.02744259312748909
2023-01-22 21:13:34.739890: step: 618/470, loss: 0.026758696883916855
2023-01-22 21:13:35.533918: step: 620/470, loss: 0.0033123791217803955
2023-01-22 21:13:36.301609: step: 622/470, loss: 0.00663144001737237
2023-01-22 21:13:37.051026: step: 624/470, loss: 0.0016671409830451012
2023-01-22 21:13:37.760889: step: 626/470, loss: 0.0074158660136163235
2023-01-22 21:13:38.442562: step: 628/470, loss: 0.0008439401281066239
2023-01-22 21:13:39.205794: step: 630/470, loss: 5.01374488521833e-05
2023-01-22 21:13:39.891100: step: 632/470, loss: 0.008946064859628677
2023-01-22 21:13:40.593576: step: 634/470, loss: 0.06714008748531342
2023-01-22 21:13:41.290502: step: 636/470, loss: 0.0008762570796534419
2023-01-22 21:13:42.128203: step: 638/470, loss: 0.001907090307213366
2023-01-22 21:13:42.854000: step: 640/470, loss: 0.03064919076859951
2023-01-22 21:13:43.692430: step: 642/470, loss: 0.00023972737835720181
2023-01-22 21:13:44.430603: step: 644/470, loss: 0.00011663758778013289
2023-01-22 21:13:45.147031: step: 646/470, loss: 0.010350205935537815
2023-01-22 21:13:45.919516: step: 648/470, loss: 0.015240548178553581
2023-01-22 21:13:46.652001: step: 650/470, loss: 0.017129601910710335
2023-01-22 21:13:47.389590: step: 652/470, loss: 0.03198548033833504
2023-01-22 21:13:48.028927: step: 654/470, loss: 0.0030342754907906055
2023-01-22 21:13:48.744293: step: 656/470, loss: 7.692570943618193e-05
2023-01-22 21:13:49.484518: step: 658/470, loss: 0.014984884299337864
2023-01-22 21:13:50.260951: step: 660/470, loss: 0.007573677692562342
2023-01-22 21:13:50.972623: step: 662/470, loss: 0.14432427287101746
2023-01-22 21:13:51.693915: step: 664/470, loss: 0.003277366515249014
2023-01-22 21:13:52.334957: step: 666/470, loss: 0.04675723984837532
2023-01-22 21:13:53.104475: step: 668/470, loss: 0.02985813282430172
2023-01-22 21:13:53.869878: step: 670/470, loss: 0.010331113822758198
2023-01-22 21:13:54.570086: step: 672/470, loss: 0.004046509508043528
2023-01-22 21:13:55.326306: step: 674/470, loss: 0.017745012417435646
2023-01-22 21:13:56.126293: step: 676/470, loss: 0.0010939788771793246
2023-01-22 21:13:56.827006: step: 678/470, loss: 0.0016873609274625778
2023-01-22 21:13:57.561908: step: 680/470, loss: 0.015853749588131905
2023-01-22 21:13:58.388891: step: 682/470, loss: 0.0017006437992677093
2023-01-22 21:13:59.069832: step: 684/470, loss: 0.002765461103990674
2023-01-22 21:13:59.789435: step: 686/470, loss: 0.7379614114761353
2023-01-22 21:14:00.512493: step: 688/470, loss: 0.005514780059456825
2023-01-22 21:14:01.171239: step: 690/470, loss: 0.002757574198767543
2023-01-22 21:14:01.914756: step: 692/470, loss: 0.46669384837150574
2023-01-22 21:14:02.581840: step: 694/470, loss: 0.005543508101254702
2023-01-22 21:14:03.267691: step: 696/470, loss: 0.0004790358943864703
2023-01-22 21:14:03.997850: step: 698/470, loss: 0.00039144910988397896
2023-01-22 21:14:04.726885: step: 700/470, loss: 0.01933109760284424
2023-01-22 21:14:05.483022: step: 702/470, loss: 0.0024042355362325907
2023-01-22 21:14:06.120015: step: 704/470, loss: 0.0020206007175147533
2023-01-22 21:14:06.853849: step: 706/470, loss: 0.00844528991729021
2023-01-22 21:14:07.554476: step: 708/470, loss: 0.0017009805887937546
2023-01-22 21:14:08.248146: step: 710/470, loss: 0.008159015327692032
2023-01-22 21:14:09.001680: step: 712/470, loss: 0.001408104319125414
2023-01-22 21:14:09.722287: step: 714/470, loss: 0.008478800766170025
2023-01-22 21:14:10.379780: step: 716/470, loss: 0.021621203050017357
2023-01-22 21:14:11.133973: step: 718/470, loss: 6.314300844678655e-05
2023-01-22 21:14:11.892746: step: 720/470, loss: 0.027302606031298637
2023-01-22 21:14:12.599924: step: 722/470, loss: 0.020021893084049225
2023-01-22 21:14:13.383827: step: 724/470, loss: 0.028122197836637497
2023-01-22 21:14:14.097335: step: 726/470, loss: 0.004987229593098164
2023-01-22 21:14:14.757747: step: 728/470, loss: 0.023552965372800827
2023-01-22 21:14:15.496074: step: 730/470, loss: 0.0023100976832211018
2023-01-22 21:14:16.233736: step: 732/470, loss: 0.014617957174777985
2023-01-22 21:14:16.960161: step: 734/470, loss: 0.012580832466483116
2023-01-22 21:14:17.703565: step: 736/470, loss: 0.0018753198673948646
2023-01-22 21:14:18.386665: step: 738/470, loss: 0.03843626379966736
2023-01-22 21:14:19.223689: step: 740/470, loss: 0.05392017588019371
2023-01-22 21:14:19.966150: step: 742/470, loss: 0.1939995437860489
2023-01-22 21:14:20.666344: step: 744/470, loss: 0.0006773190689273179
2023-01-22 21:14:21.461292: step: 746/470, loss: 0.04806168004870415
2023-01-22 21:14:22.197411: step: 748/470, loss: 0.03759084269404411
2023-01-22 21:14:22.970902: step: 750/470, loss: 0.002831129590049386
2023-01-22 21:14:23.711600: step: 752/470, loss: 0.006249632220715284
2023-01-22 21:14:24.438748: step: 754/470, loss: 0.004659464117139578
2023-01-22 21:14:25.122586: step: 756/470, loss: 0.000623860105406493
2023-01-22 21:14:25.785490: step: 758/470, loss: 0.0027934126555919647
2023-01-22 21:14:26.515618: step: 760/470, loss: 0.0031853329855948687
2023-01-22 21:14:27.212225: step: 762/470, loss: 0.02544858306646347
2023-01-22 21:14:27.938068: step: 764/470, loss: 0.010291761718690395
2023-01-22 21:14:28.680098: step: 766/470, loss: 0.011330293491482735
2023-01-22 21:14:29.529405: step: 768/470, loss: 0.006938802544027567
2023-01-22 21:14:30.236912: step: 770/470, loss: 0.029576266184449196
2023-01-22 21:14:30.970708: step: 772/470, loss: 0.02871057577431202
2023-01-22 21:14:31.712695: step: 774/470, loss: 0.006623897235840559
2023-01-22 21:14:32.344091: step: 776/470, loss: 0.01030951552093029
2023-01-22 21:14:33.040542: step: 778/470, loss: 0.0003881768207065761
2023-01-22 21:14:33.789250: step: 780/470, loss: 0.011595960706472397
2023-01-22 21:14:34.530848: step: 782/470, loss: 0.03303779661655426
2023-01-22 21:14:35.299051: step: 784/470, loss: 0.009521235711872578
2023-01-22 21:14:36.020714: step: 786/470, loss: 0.010765934363007545
2023-01-22 21:14:36.711034: step: 788/470, loss: 0.006151827983558178
2023-01-22 21:14:37.458127: step: 790/470, loss: 0.14049938321113586
2023-01-22 21:14:38.192798: step: 792/470, loss: 0.00779561884701252
2023-01-22 21:14:38.940721: step: 794/470, loss: 0.020738592371344566
2023-01-22 21:14:39.835214: step: 796/470, loss: 0.1423885077238083
2023-01-22 21:14:40.716330: step: 798/470, loss: 0.0193779356777668
2023-01-22 21:14:41.440727: step: 800/470, loss: 0.0032281007152050734
2023-01-22 21:14:42.072656: step: 802/470, loss: 0.00042432613554410636
2023-01-22 21:14:42.837544: step: 804/470, loss: 0.004177960567176342
2023-01-22 21:14:43.562400: step: 806/470, loss: 1.2552907466888428
2023-01-22 21:14:44.189144: step: 808/470, loss: 6.404746090993285e-05
2023-01-22 21:14:44.955668: step: 810/470, loss: 0.031237877905368805
2023-01-22 21:14:45.684426: step: 812/470, loss: 0.0003258582728449255
2023-01-22 21:14:46.325842: step: 814/470, loss: 0.007463258691132069
2023-01-22 21:14:47.066510: step: 816/470, loss: 0.01626862958073616
2023-01-22 21:14:47.857932: step: 818/470, loss: 0.02373459003865719
2023-01-22 21:14:48.585848: step: 820/470, loss: 0.0005793635500594974
2023-01-22 21:14:49.298317: step: 822/470, loss: 0.0021050209179520607
2023-01-22 21:14:50.039749: step: 824/470, loss: 0.17716780304908752
2023-01-22 21:14:50.840405: step: 826/470, loss: 0.036166831851005554
2023-01-22 21:14:51.657027: step: 828/470, loss: 0.024912940338253975
2023-01-22 21:14:52.382303: step: 830/470, loss: 0.007581733167171478
2023-01-22 21:14:53.095736: step: 832/470, loss: 0.007379438728094101
2023-01-22 21:14:53.788097: step: 834/470, loss: 0.08958467096090317
2023-01-22 21:14:54.605212: step: 836/470, loss: 0.0027318422216922045
2023-01-22 21:14:55.338015: step: 838/470, loss: 0.06193634122610092
2023-01-22 21:14:56.079860: step: 840/470, loss: 0.01766875572502613
2023-01-22 21:14:56.863044: step: 842/470, loss: 0.009170843288302422
2023-01-22 21:14:57.606824: step: 844/470, loss: 0.00840882770717144
2023-01-22 21:14:58.270057: step: 846/470, loss: 0.0007808993104845285
2023-01-22 21:14:58.971849: step: 848/470, loss: 0.06595759838819504
2023-01-22 21:14:59.730926: step: 850/470, loss: 0.017137767747044563
2023-01-22 21:15:00.420681: step: 852/470, loss: 0.0002639777958393097
2023-01-22 21:15:01.083929: step: 854/470, loss: 0.04219938814640045
2023-01-22 21:15:01.770308: step: 856/470, loss: 0.022198636084794998
2023-01-22 21:15:02.529426: step: 858/470, loss: 0.005382399074733257
2023-01-22 21:15:03.300994: step: 860/470, loss: 0.034826841205358505
2023-01-22 21:15:04.027187: step: 862/470, loss: 0.02772991545498371
2023-01-22 21:15:04.804443: step: 864/470, loss: 0.007337241433560848
2023-01-22 21:15:05.643818: step: 866/470, loss: 0.004963582381606102
2023-01-22 21:15:06.382679: step: 868/470, loss: 0.000665048137307167
2023-01-22 21:15:07.140861: step: 870/470, loss: 0.01284511387348175
2023-01-22 21:15:07.790054: step: 872/470, loss: 0.00016538244381081313
2023-01-22 21:15:08.483473: step: 874/470, loss: 0.023755772039294243
2023-01-22 21:15:09.129781: step: 876/470, loss: 0.0020838105119764805
2023-01-22 21:15:09.807474: step: 878/470, loss: 0.0033732212614268064
2023-01-22 21:15:10.612490: step: 880/470, loss: 0.08116719126701355
2023-01-22 21:15:11.240449: step: 882/470, loss: 0.0009367589373141527
2023-01-22 21:15:12.033461: step: 884/470, loss: 0.05737480893731117
2023-01-22 21:15:12.754057: step: 886/470, loss: 0.00760510703548789
2023-01-22 21:15:13.505955: step: 888/470, loss: 0.0016693559009581804
2023-01-22 21:15:14.232234: step: 890/470, loss: 0.010982673615217209
2023-01-22 21:15:15.021368: step: 892/470, loss: 0.01113244891166687
2023-01-22 21:15:15.752998: step: 894/470, loss: 0.0017129809129983187
2023-01-22 21:15:16.445834: step: 896/470, loss: 0.5727943181991577
2023-01-22 21:15:17.142854: step: 898/470, loss: 0.002152232686057687
2023-01-22 21:15:17.846914: step: 900/470, loss: 0.5070058107376099
2023-01-22 21:15:18.580916: step: 902/470, loss: 0.04603942856192589
2023-01-22 21:15:19.306546: step: 904/470, loss: 0.06946877390146255
2023-01-22 21:15:19.972829: step: 906/470, loss: 0.0038659495767205954
2023-01-22 21:15:20.691914: step: 908/470, loss: 0.0038466486148536205
2023-01-22 21:15:21.420453: step: 910/470, loss: 0.010113026015460491
2023-01-22 21:15:22.158460: step: 912/470, loss: 0.003725921269506216
2023-01-22 21:15:22.935606: step: 914/470, loss: 0.0018076320411637425
2023-01-22 21:15:23.743519: step: 916/470, loss: 0.043223872780799866
2023-01-22 21:15:24.424390: step: 918/470, loss: 0.0003173082077410072
2023-01-22 21:15:25.127745: step: 920/470, loss: 0.0005944594158791006
2023-01-22 21:15:25.899088: step: 922/470, loss: 0.05763893947005272
2023-01-22 21:15:26.651663: step: 924/470, loss: 0.0007061202195473015
2023-01-22 21:15:27.391042: step: 926/470, loss: 0.004733996000140905
2023-01-22 21:15:27.985455: step: 928/470, loss: 0.001815860508941114
2023-01-22 21:15:28.638636: step: 930/470, loss: 0.0008208305225707591
2023-01-22 21:15:29.306076: step: 932/470, loss: 0.01949726790189743
2023-01-22 21:15:30.015149: step: 934/470, loss: 0.010274535976350307
2023-01-22 21:15:30.703433: step: 936/470, loss: 0.013152135536074638
2023-01-22 21:15:31.470717: step: 938/470, loss: 0.023069579154253006
2023-01-22 21:15:32.105083: step: 940/470, loss: 0.006963435094803572
2023-01-22 21:15:32.831565: step: 942/470, loss: 1.931123188114725e-05
==================================================
Loss: 0.045
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29903591778591776, 'r': 0.3319468916598898, 'f1': 0.31463311493662216}, 'combined': 0.2318349267954058, 'epoch': 33}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3428089813247433, 'r': 0.362586422555017, 'f1': 0.3524204480908576}, 'combined': 0.24546697876975157, 'epoch': 33}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2891282818320387, 'r': 0.3220461127806579, 'f1': 0.3047007207098864}, 'combined': 0.2245163205230742, 'epoch': 33}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34980374117622254, 'r': 0.3699847262440815, 'f1': 0.3596113227045278}, 'combined': 0.2504755481524074, 'epoch': 33}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28349719101123594, 'r': 0.3351399430740038, 'f1': 0.3071630434782609}, 'combined': 0.22633066361556065, 'epoch': 33}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3373705612853303, 'r': 0.3818126448392632, 'f1': 0.3582184489245229}, 'combined': 0.249505387310613, 'epoch': 33}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.22453703703703703, 'r': 0.3464285714285714, 'f1': 0.2724719101123595}, 'combined': 0.1816479400749063, 'epoch': 33}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.26136363636363635, 'r': 0.5, 'f1': 0.34328358208955223}, 'combined': 0.17164179104477612, 'epoch': 33}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42391304347826086, 'r': 0.33620689655172414, 'f1': 0.375}, 'combined': 0.25, 'epoch': 33}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 34
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 21:18:07.769982: step: 2/470, loss: 0.0033803251571953297
2023-01-22 21:18:08.432480: step: 4/470, loss: 0.0006748238811269403
2023-01-22 21:18:09.186847: step: 6/470, loss: 0.005246671847999096
2023-01-22 21:18:09.941529: step: 8/470, loss: 0.051448754966259
2023-01-22 21:18:10.693072: step: 10/470, loss: 0.010346678085625172
2023-01-22 21:18:11.485189: step: 12/470, loss: 0.006094653159379959
2023-01-22 21:18:12.170946: step: 14/470, loss: 5.761585998698138e-05
2023-01-22 21:18:12.890768: step: 16/470, loss: 0.4367545545101166
2023-01-22 21:18:13.668284: step: 18/470, loss: 0.026379667222499847
2023-01-22 21:18:14.486168: step: 20/470, loss: 0.0011629628716036677
2023-01-22 21:18:15.348890: step: 22/470, loss: 0.009967586025595665
2023-01-22 21:18:16.093470: step: 24/470, loss: 0.5176779627799988
2023-01-22 21:18:16.815416: step: 26/470, loss: 0.06595677137374878
2023-01-22 21:18:17.579924: step: 28/470, loss: 0.010950235649943352
2023-01-22 21:18:18.280314: step: 30/470, loss: 0.0005241360631771386
2023-01-22 21:18:19.000884: step: 32/470, loss: 0.007944729179143906
2023-01-22 21:18:19.667307: step: 34/470, loss: 0.0030253706499934196
2023-01-22 21:18:20.351378: step: 36/470, loss: 0.0016459508333355188
2023-01-22 21:18:21.098273: step: 38/470, loss: 0.017528338357806206
2023-01-22 21:18:21.899893: step: 40/470, loss: 0.005726838018745184
2023-01-22 21:18:22.676547: step: 42/470, loss: 0.0029343708883970976
2023-01-22 21:18:23.430761: step: 44/470, loss: 0.0019074846059083939
2023-01-22 21:18:24.221001: step: 46/470, loss: 0.04953285679221153
2023-01-22 21:18:24.949358: step: 48/470, loss: 0.013332260772585869
2023-01-22 21:18:25.669379: step: 50/470, loss: 0.00047797494335100055
2023-01-22 21:18:26.394844: step: 52/470, loss: 0.004910385701805353
2023-01-22 21:18:27.106833: step: 54/470, loss: 0.001362175797112286
2023-01-22 21:18:27.859103: step: 56/470, loss: 0.00200113607570529
2023-01-22 21:18:28.561399: step: 58/470, loss: 0.009997074492275715
2023-01-22 21:18:29.194806: step: 60/470, loss: 9.74019494606182e-05
2023-01-22 21:18:29.909309: step: 62/470, loss: 0.02216336689889431
2023-01-22 21:18:30.674818: step: 64/470, loss: 0.003930054139345884
2023-01-22 21:18:31.455210: step: 66/470, loss: 0.00021434202790260315
2023-01-22 21:18:32.185891: step: 68/470, loss: 0.00011843130050692707
2023-01-22 21:18:32.926242: step: 70/470, loss: 0.044022075831890106
2023-01-22 21:18:33.688408: step: 72/470, loss: 0.060967884957790375
2023-01-22 21:18:34.455152: step: 74/470, loss: 0.0004368863010313362
2023-01-22 21:18:35.165435: step: 76/470, loss: 0.017974242568016052
2023-01-22 21:18:35.847166: step: 78/470, loss: 0.004248203709721565
2023-01-22 21:18:36.532812: step: 80/470, loss: 0.00158304488286376
2023-01-22 21:18:37.226076: step: 82/470, loss: 0.007524224929511547
2023-01-22 21:18:37.881636: step: 84/470, loss: 0.005340985022485256
2023-01-22 21:18:38.556606: step: 86/470, loss: 0.029072092846035957
2023-01-22 21:18:39.298469: step: 88/470, loss: 0.023193301633000374
2023-01-22 21:18:40.026201: step: 90/470, loss: 9.126600343734026e-05
2023-01-22 21:18:40.794824: step: 92/470, loss: 0.0002512194332666695
2023-01-22 21:18:41.495613: step: 94/470, loss: 0.4563930332660675
2023-01-22 21:18:42.246189: step: 96/470, loss: 0.16592247784137726
2023-01-22 21:18:43.042392: step: 98/470, loss: 0.013607371598482132
2023-01-22 21:18:43.715414: step: 100/470, loss: 0.006993814371526241
2023-01-22 21:18:44.393920: step: 102/470, loss: 0.005480475723743439
2023-01-22 21:18:45.132289: step: 104/470, loss: 0.0007254070951603353
2023-01-22 21:18:45.844538: step: 106/470, loss: 0.0031888075172901154
2023-01-22 21:18:46.567482: step: 108/470, loss: 0.0031884340569376945
2023-01-22 21:18:47.232072: step: 110/470, loss: 0.0006328716408461332
2023-01-22 21:18:48.020018: step: 112/470, loss: 0.012160047888755798
2023-01-22 21:18:48.749042: step: 114/470, loss: 0.004218654707074165
2023-01-22 21:18:49.468662: step: 116/470, loss: 0.001394663704559207
2023-01-22 21:18:50.244581: step: 118/470, loss: 0.002457190537825227
2023-01-22 21:18:50.960266: step: 120/470, loss: 0.14293168485164642
2023-01-22 21:18:51.655153: step: 122/470, loss: 0.047695934772491455
2023-01-22 21:18:52.402492: step: 124/470, loss: 0.003226999891921878
2023-01-22 21:18:53.076460: step: 126/470, loss: 0.001519688288681209
2023-01-22 21:18:53.808297: step: 128/470, loss: 0.004431163426488638
2023-01-22 21:18:54.556428: step: 130/470, loss: 0.004296420607715845
2023-01-22 21:18:55.206519: step: 132/470, loss: 0.0012974428245797753
2023-01-22 21:18:55.923069: step: 134/470, loss: 0.027212653309106827
2023-01-22 21:18:56.607689: step: 136/470, loss: 0.02067440375685692
2023-01-22 21:18:57.302789: step: 138/470, loss: 0.0018030147766694427
2023-01-22 21:18:58.074618: step: 140/470, loss: 0.5232383608818054
2023-01-22 21:18:58.825169: step: 142/470, loss: 0.002090280409902334
2023-01-22 21:18:59.660478: step: 144/470, loss: 0.03019622713327408
2023-01-22 21:19:00.441926: step: 146/470, loss: 0.06532511860132217
2023-01-22 21:19:01.169448: step: 148/470, loss: 0.0835709348320961
2023-01-22 21:19:01.881924: step: 150/470, loss: 0.002398706041276455
2023-01-22 21:19:02.554318: step: 152/470, loss: 0.0007716089021414518
2023-01-22 21:19:03.258119: step: 154/470, loss: 0.04274653270840645
2023-01-22 21:19:03.973362: step: 156/470, loss: 0.027724282816052437
2023-01-22 21:19:04.705297: step: 158/470, loss: 0.0108801806345582
2023-01-22 21:19:05.365645: step: 160/470, loss: 0.0027062701992690563
2023-01-22 21:19:06.083749: step: 162/470, loss: 0.001326837227679789
2023-01-22 21:19:06.881155: step: 164/470, loss: 0.000980255426838994
2023-01-22 21:19:07.556673: step: 166/470, loss: 0.004368356894701719
2023-01-22 21:19:08.308214: step: 168/470, loss: 0.0013895826414227486
2023-01-22 21:19:09.012185: step: 170/470, loss: 0.002898984821513295
2023-01-22 21:19:09.762928: step: 172/470, loss: 0.06322634965181351
2023-01-22 21:19:10.423620: step: 174/470, loss: 0.00011356957111274824
2023-01-22 21:19:11.165174: step: 176/470, loss: 0.018166067078709602
2023-01-22 21:19:11.875356: step: 178/470, loss: 0.011182754300534725
2023-01-22 21:19:12.550191: step: 180/470, loss: 0.01945425756275654
2023-01-22 21:19:13.317590: step: 182/470, loss: 0.004951994400471449
2023-01-22 21:19:14.082159: step: 184/470, loss: 0.27803167700767517
2023-01-22 21:19:14.799292: step: 186/470, loss: 0.014578554779291153
2023-01-22 21:19:15.557007: step: 188/470, loss: 0.026163099333643913
2023-01-22 21:19:16.300816: step: 190/470, loss: 0.016671251505613327
2023-01-22 21:19:17.001401: step: 192/470, loss: 0.0024631675332784653
2023-01-22 21:19:17.678741: step: 194/470, loss: 0.017945973202586174
2023-01-22 21:19:18.447391: step: 196/470, loss: 0.019402913749217987
2023-01-22 21:19:19.208996: step: 198/470, loss: 0.009785197675228119
2023-01-22 21:19:19.991583: step: 200/470, loss: 0.011927827261388302
2023-01-22 21:19:20.736165: step: 202/470, loss: 0.015688994899392128
2023-01-22 21:19:21.427724: step: 204/470, loss: 0.5554424524307251
2023-01-22 21:19:22.106990: step: 206/470, loss: 0.004341977182775736
2023-01-22 21:19:22.796720: step: 208/470, loss: 2.5874245693557896e-05
2023-01-22 21:19:23.586853: step: 210/470, loss: 0.03483826667070389
2023-01-22 21:19:24.298062: step: 212/470, loss: 0.004074705298990011
2023-01-22 21:19:25.012951: step: 214/470, loss: 0.003476059529930353
2023-01-22 21:19:25.755005: step: 216/470, loss: 0.00816492922604084
2023-01-22 21:19:26.443897: step: 218/470, loss: 0.022160356864333153
2023-01-22 21:19:27.186735: step: 220/470, loss: 0.008341852575540543
2023-01-22 21:19:28.011558: step: 222/470, loss: 0.0019108172273263335
2023-01-22 21:19:28.716456: step: 224/470, loss: 1.008707046508789
2023-01-22 21:19:29.417185: step: 226/470, loss: 0.00015085958875715733
2023-01-22 21:19:30.163668: step: 228/470, loss: 0.004038154147565365
2023-01-22 21:19:30.965638: step: 230/470, loss: 0.005438428372144699
2023-01-22 21:19:31.711688: step: 232/470, loss: 0.0011504045687615871
2023-01-22 21:19:32.424165: step: 234/470, loss: 0.02474108338356018
2023-01-22 21:19:33.189157: step: 236/470, loss: 0.04079394042491913
2023-01-22 21:19:33.944246: step: 238/470, loss: 0.008551133796572685
2023-01-22 21:19:34.620701: step: 240/470, loss: 0.00603491673246026
2023-01-22 21:19:35.335489: step: 242/470, loss: 0.004793131723999977
2023-01-22 21:19:36.163242: step: 244/470, loss: 0.0072413296438753605
2023-01-22 21:19:36.834667: step: 246/470, loss: 0.023858316242694855
2023-01-22 21:19:37.546370: step: 248/470, loss: 0.008859733119606972
2023-01-22 21:19:38.210597: step: 250/470, loss: 0.006357423961162567
2023-01-22 21:19:38.899801: step: 252/470, loss: 0.024346143007278442
2023-01-22 21:19:39.589196: step: 254/470, loss: 0.018336040899157524
2023-01-22 21:19:40.345709: step: 256/470, loss: 0.010750774294137955
2023-01-22 21:19:41.040766: step: 258/470, loss: 0.0013539177598431706
2023-01-22 21:19:41.848985: step: 260/470, loss: 0.06712424010038376
2023-01-22 21:19:42.564612: step: 262/470, loss: 0.015392746776342392
2023-01-22 21:19:43.389769: step: 264/470, loss: 0.011326344683766365
2023-01-22 21:19:44.111437: step: 266/470, loss: 0.03263202682137489
2023-01-22 21:19:44.848821: step: 268/470, loss: 0.019025059416890144
2023-01-22 21:19:45.585227: step: 270/470, loss: 0.004486290272325277
2023-01-22 21:19:46.352692: step: 272/470, loss: 0.028263265267014503
2023-01-22 21:19:47.040884: step: 274/470, loss: 0.06688546389341354
2023-01-22 21:19:47.815614: step: 276/470, loss: 0.0005725919036194682
2023-01-22 21:19:48.500408: step: 278/470, loss: 0.0008113943040370941
2023-01-22 21:19:49.196397: step: 280/470, loss: 0.00557939475402236
2023-01-22 21:19:50.009157: step: 282/470, loss: 0.026322869583964348
2023-01-22 21:19:50.732247: step: 284/470, loss: 0.0053300210274755955
2023-01-22 21:19:51.513653: step: 286/470, loss: 0.006512013729661703
2023-01-22 21:19:52.182113: step: 288/470, loss: 0.006800213363021612
2023-01-22 21:19:52.871972: step: 290/470, loss: 0.006016398314386606
2023-01-22 21:19:53.649297: step: 292/470, loss: 0.009520920924842358
2023-01-22 21:19:54.439457: step: 294/470, loss: 0.0036107206251472235
2023-01-22 21:19:55.198911: step: 296/470, loss: 0.020766550675034523
2023-01-22 21:19:55.943314: step: 298/470, loss: 0.005723374895751476
2023-01-22 21:19:56.696762: step: 300/470, loss: 0.03173263370990753
2023-01-22 21:19:57.462770: step: 302/470, loss: 0.029550369828939438
2023-01-22 21:19:58.169946: step: 304/470, loss: 0.0009951787069439888
2023-01-22 21:19:58.938869: step: 306/470, loss: 0.04182833433151245
2023-01-22 21:19:59.916306: step: 308/470, loss: 0.03832540661096573
2023-01-22 21:20:00.686850: step: 310/470, loss: 0.11555290967226028
2023-01-22 21:20:01.467941: step: 312/470, loss: 0.02390245907008648
2023-01-22 21:20:02.181818: step: 314/470, loss: 0.0017948574386537075
2023-01-22 21:20:02.949468: step: 316/470, loss: 0.0034852821845561266
2023-01-22 21:20:03.650260: step: 318/470, loss: 0.25961652398109436
2023-01-22 21:20:04.418048: step: 320/470, loss: 0.052189331501722336
2023-01-22 21:20:05.192621: step: 322/470, loss: 0.01036821585148573
2023-01-22 21:20:05.900040: step: 324/470, loss: 0.016944773495197296
2023-01-22 21:20:06.568004: step: 326/470, loss: 1.836652882047929e-05
2023-01-22 21:20:07.299357: step: 328/470, loss: 0.0037974936421960592
2023-01-22 21:20:07.947476: step: 330/470, loss: 0.00011987396283075213
2023-01-22 21:20:08.628225: step: 332/470, loss: 0.007104361429810524
2023-01-22 21:20:09.298692: step: 334/470, loss: 0.009579218924045563
2023-01-22 21:20:10.040739: step: 336/470, loss: 0.0007889914559200406
2023-01-22 21:20:10.724686: step: 338/470, loss: 0.003870560321956873
2023-01-22 21:20:11.481484: step: 340/470, loss: 0.0053961933590471745
2023-01-22 21:20:12.166935: step: 342/470, loss: 0.0044841766357421875
2023-01-22 21:20:12.840708: step: 344/470, loss: 4.063077722094022e-05
2023-01-22 21:20:13.553320: step: 346/470, loss: 0.001006243284791708
2023-01-22 21:20:14.216202: step: 348/470, loss: 0.007106869947165251
2023-01-22 21:20:14.861308: step: 350/470, loss: 0.0015916344709694386
2023-01-22 21:20:15.637486: step: 352/470, loss: 0.027905944734811783
2023-01-22 21:20:16.371644: step: 354/470, loss: 0.003524521365761757
2023-01-22 21:20:17.135687: step: 356/470, loss: 0.0009450623765587807
2023-01-22 21:20:17.832002: step: 358/470, loss: 0.00697721540927887
2023-01-22 21:20:18.540972: step: 360/470, loss: 0.0005012876354157925
2023-01-22 21:20:19.189892: step: 362/470, loss: 4.1443989175604656e-05
2023-01-22 21:20:19.884526: step: 364/470, loss: 0.04660176858305931
2023-01-22 21:20:20.556476: step: 366/470, loss: 2.2212430849322118e-05
2023-01-22 21:20:21.277871: step: 368/470, loss: 0.0106153329834342
2023-01-22 21:20:21.953436: step: 370/470, loss: 0.0111685274168849
2023-01-22 21:20:22.714226: step: 372/470, loss: 0.0011537930695340037
2023-01-22 21:20:23.386476: step: 374/470, loss: 0.06961429864168167
2023-01-22 21:20:24.165944: step: 376/470, loss: 0.0024143445771187544
2023-01-22 21:20:24.892268: step: 378/470, loss: 0.009551659226417542
2023-01-22 21:20:25.607956: step: 380/470, loss: 1.0005992650985718
2023-01-22 21:20:26.419729: step: 382/470, loss: 0.002678003627806902
2023-01-22 21:20:27.227643: step: 384/470, loss: 0.049086350947618484
2023-01-22 21:20:28.048425: step: 386/470, loss: 0.010009855031967163
2023-01-22 21:20:28.820716: step: 388/470, loss: 0.0012464200844988227
2023-01-22 21:20:29.532636: step: 390/470, loss: 4.9415495595894754e-05
2023-01-22 21:20:30.192415: step: 392/470, loss: 0.003669227007776499
2023-01-22 21:20:30.900034: step: 394/470, loss: 0.003987874835729599
2023-01-22 21:20:31.607919: step: 396/470, loss: 0.0017396406037732959
2023-01-22 21:20:32.305446: step: 398/470, loss: 0.025890368968248367
2023-01-22 21:20:33.018572: step: 400/470, loss: 0.01730758510529995
2023-01-22 21:20:33.802827: step: 402/470, loss: 0.004256324376910925
2023-01-22 21:20:34.529775: step: 404/470, loss: 0.24290981888771057
2023-01-22 21:20:35.184952: step: 406/470, loss: 3.430567085160874e-05
2023-01-22 21:20:35.910609: step: 408/470, loss: 0.01224263571202755
2023-01-22 21:20:36.657207: step: 410/470, loss: 0.0011447453871369362
2023-01-22 21:20:37.376969: step: 412/470, loss: 0.024092786014080048
2023-01-22 21:20:38.125141: step: 414/470, loss: 0.0011776899918913841
2023-01-22 21:20:38.868282: step: 416/470, loss: 0.006173381116241217
2023-01-22 21:20:39.589793: step: 418/470, loss: 0.007338505703955889
2023-01-22 21:20:40.291244: step: 420/470, loss: 0.002101232297718525
2023-01-22 21:20:40.998766: step: 422/470, loss: 0.0022618654184043407
2023-01-22 21:20:41.781010: step: 424/470, loss: 0.0012441343860700727
2023-01-22 21:20:42.676642: step: 426/470, loss: 0.0695013627409935
2023-01-22 21:20:43.403206: step: 428/470, loss: 0.23386645317077637
2023-01-22 21:20:44.172506: step: 430/470, loss: 0.0643640011548996
2023-01-22 21:20:44.874948: step: 432/470, loss: 0.00014748272951692343
2023-01-22 21:20:45.590945: step: 434/470, loss: 0.055859826505184174
2023-01-22 21:20:46.317776: step: 436/470, loss: 0.000146715174196288
2023-01-22 21:20:47.026767: step: 438/470, loss: 0.005512524861842394
2023-01-22 21:20:47.730535: step: 440/470, loss: 0.04210149496793747
2023-01-22 21:20:48.468662: step: 442/470, loss: 0.0007326016202569008
2023-01-22 21:20:49.302965: step: 444/470, loss: 0.017042549327015877
2023-01-22 21:20:50.048955: step: 446/470, loss: 0.0027442320715636015
2023-01-22 21:20:50.757887: step: 448/470, loss: 0.000428998377174139
2023-01-22 21:20:51.476427: step: 450/470, loss: 0.009314804337918758
2023-01-22 21:20:52.193746: step: 452/470, loss: 0.0005936333909630775
2023-01-22 21:20:52.954579: step: 454/470, loss: 0.018571410328149796
2023-01-22 21:20:53.648653: step: 456/470, loss: 0.0180160254240036
2023-01-22 21:20:54.344172: step: 458/470, loss: 0.02957836724817753
2023-01-22 21:20:55.027954: step: 460/470, loss: 0.002465310040861368
2023-01-22 21:20:55.742745: step: 462/470, loss: 0.0018986280774697661
2023-01-22 21:20:56.493541: step: 464/470, loss: 0.06108655408024788
2023-01-22 21:20:57.200637: step: 466/470, loss: 0.0003646984987426549
2023-01-22 21:20:57.924148: step: 468/470, loss: 0.017292622476816177
2023-01-22 21:20:58.628514: step: 470/470, loss: 0.01416701264679432
2023-01-22 21:20:59.352341: step: 472/470, loss: 0.00011536870442796499
2023-01-22 21:21:00.082677: step: 474/470, loss: 0.002867184579372406
2023-01-22 21:21:00.930160: step: 476/470, loss: 0.03824557363986969
2023-01-22 21:21:01.637441: step: 478/470, loss: 0.001631454681046307
2023-01-22 21:21:02.355617: step: 480/470, loss: 0.4666403532028198
2023-01-22 21:21:03.114169: step: 482/470, loss: 0.0006429323111660779
2023-01-22 21:21:03.822262: step: 484/470, loss: 0.07074841111898422
2023-01-22 21:21:04.492751: step: 486/470, loss: 0.00920712761580944
2023-01-22 21:21:05.210467: step: 488/470, loss: 0.027392836287617683
2023-01-22 21:21:05.926468: step: 490/470, loss: 0.0031878724694252014
2023-01-22 21:21:06.600298: step: 492/470, loss: 0.009520125575363636
2023-01-22 21:21:07.328202: step: 494/470, loss: 0.014723233878612518
2023-01-22 21:21:08.135638: step: 496/470, loss: 0.01308779139071703
2023-01-22 21:21:08.860579: step: 498/470, loss: 0.017647597938776016
2023-01-22 21:21:09.618887: step: 500/470, loss: 0.0010442689526826143
2023-01-22 21:21:10.354862: step: 502/470, loss: 0.0007168474257923663
2023-01-22 21:21:11.114013: step: 504/470, loss: 0.0017317109741270542
2023-01-22 21:21:11.828215: step: 506/470, loss: 0.0012164206709712744
2023-01-22 21:21:12.590934: step: 508/470, loss: 0.0004420246696099639
2023-01-22 21:21:13.276428: step: 510/470, loss: 0.0015642930520698428
2023-01-22 21:21:13.983043: step: 512/470, loss: 0.020066358149051666
2023-01-22 21:21:14.831371: step: 514/470, loss: 0.3007548451423645
2023-01-22 21:21:15.585120: step: 516/470, loss: 0.4788682460784912
2023-01-22 21:21:16.331543: step: 518/470, loss: 0.011519278399646282
2023-01-22 21:21:17.044322: step: 520/470, loss: 0.01719200238585472
2023-01-22 21:21:17.695323: step: 522/470, loss: 0.01048339158296585
2023-01-22 21:21:18.409790: step: 524/470, loss: 0.020729506388306618
2023-01-22 21:21:19.069724: step: 526/470, loss: 0.020677419379353523
2023-01-22 21:21:19.801489: step: 528/470, loss: 0.18149332702159882
2023-01-22 21:21:20.537940: step: 530/470, loss: 0.013467920944094658
2023-01-22 21:21:21.274826: step: 532/470, loss: 0.02106170728802681
2023-01-22 21:21:21.979909: step: 534/470, loss: 0.0007394176791422069
2023-01-22 21:21:22.713007: step: 536/470, loss: 0.04561655968427658
2023-01-22 21:21:23.526712: step: 538/470, loss: 0.01662643626332283
2023-01-22 21:21:24.255918: step: 540/470, loss: 0.001894438057206571
2023-01-22 21:21:24.921680: step: 542/470, loss: 0.00037416958366520703
2023-01-22 21:21:25.680114: step: 544/470, loss: 0.0077200643718242645
2023-01-22 21:21:26.409714: step: 546/470, loss: 0.010255703702569008
2023-01-22 21:21:27.148904: step: 548/470, loss: 0.053163353353738785
2023-01-22 21:21:27.894238: step: 550/470, loss: 0.039663802832365036
2023-01-22 21:21:28.699261: step: 552/470, loss: 0.00014281453331932425
2023-01-22 21:21:29.388737: step: 554/470, loss: 0.12468361854553223
2023-01-22 21:21:30.178234: step: 556/470, loss: 0.0031782027799636126
2023-01-22 21:21:30.960487: step: 558/470, loss: 0.25668269395828247
2023-01-22 21:21:31.776833: step: 560/470, loss: 0.005150767974555492
2023-01-22 21:21:32.449307: step: 562/470, loss: 0.0024627491366118193
2023-01-22 21:21:33.158205: step: 564/470, loss: 0.005648725666105747
2023-01-22 21:21:33.849248: step: 566/470, loss: 0.014787226915359497
2023-01-22 21:21:34.664150: step: 568/470, loss: 0.18614830076694489
2023-01-22 21:21:35.345199: step: 570/470, loss: 0.0038616762030869722
2023-01-22 21:21:36.054849: step: 572/470, loss: 0.003033594461157918
2023-01-22 21:21:36.744089: step: 574/470, loss: 0.03422601893544197
2023-01-22 21:21:37.559474: step: 576/470, loss: 0.008382627740502357
2023-01-22 21:21:38.292211: step: 578/470, loss: 0.00314133008942008
2023-01-22 21:21:38.979224: step: 580/470, loss: 0.0034324736334383488
2023-01-22 21:21:39.663727: step: 582/470, loss: 0.002011174103245139
2023-01-22 21:21:40.363571: step: 584/470, loss: 0.07423926889896393
2023-01-22 21:21:41.065365: step: 586/470, loss: 0.00035503433900885284
2023-01-22 21:21:41.792870: step: 588/470, loss: 0.015882398933172226
2023-01-22 21:21:42.548899: step: 590/470, loss: 0.03521262854337692
2023-01-22 21:21:43.245862: step: 592/470, loss: 0.06739047169685364
2023-01-22 21:21:43.932025: step: 594/470, loss: 0.001243374776095152
2023-01-22 21:21:44.702963: step: 596/470, loss: 0.0024422684218734503
2023-01-22 21:21:45.471381: step: 598/470, loss: 0.009328119456768036
2023-01-22 21:21:46.183542: step: 600/470, loss: 6.515645509352908e-05
2023-01-22 21:21:46.796080: step: 602/470, loss: 0.009061809629201889
2023-01-22 21:21:47.420267: step: 604/470, loss: 0.0029441039077937603
2023-01-22 21:21:48.164299: step: 606/470, loss: 0.030784372240304947
2023-01-22 21:21:48.880793: step: 608/470, loss: 0.009940296411514282
2023-01-22 21:21:49.599077: step: 610/470, loss: 0.010526066645979881
2023-01-22 21:21:50.421505: step: 612/470, loss: 0.0019004541682079434
2023-01-22 21:21:51.131995: step: 614/470, loss: 0.0026740499306470156
2023-01-22 21:21:51.893684: step: 616/470, loss: 0.0034406818449497223
2023-01-22 21:21:52.653367: step: 618/470, loss: 0.00043804876622743905
2023-01-22 21:21:53.373904: step: 620/470, loss: 0.017875712364912033
2023-01-22 21:21:54.055584: step: 622/470, loss: 0.0026596703100949526
2023-01-22 21:21:54.721445: step: 624/470, loss: 0.0004920915816910565
2023-01-22 21:21:55.437981: step: 626/470, loss: 0.016695676371455193
2023-01-22 21:21:56.209112: step: 628/470, loss: 0.0026145961601287127
2023-01-22 21:21:57.082331: step: 630/470, loss: 0.026421984657645226
2023-01-22 21:21:57.773458: step: 632/470, loss: 0.0005286968080326915
2023-01-22 21:21:58.581520: step: 634/470, loss: 0.06427496671676636
2023-01-22 21:21:59.276337: step: 636/470, loss: 0.0009096733992919326
2023-01-22 21:22:00.039335: step: 638/470, loss: 0.021214094012975693
2023-01-22 21:22:00.704935: step: 640/470, loss: 0.004757567774504423
2023-01-22 21:22:01.467324: step: 642/470, loss: 0.028353553265333176
2023-01-22 21:22:02.355597: step: 644/470, loss: 0.024054067209362984
2023-01-22 21:22:03.171990: step: 646/470, loss: 2.8277341698412783e-05
2023-01-22 21:22:03.906527: step: 648/470, loss: 0.01686178334057331
2023-01-22 21:22:04.576632: step: 650/470, loss: 3.088486846536398e-05
2023-01-22 21:22:05.382758: step: 652/470, loss: 0.0076260752975940704
2023-01-22 21:22:06.107669: step: 654/470, loss: 0.0021921610459685326
2023-01-22 21:22:06.878601: step: 656/470, loss: 0.015146718360483646
2023-01-22 21:22:07.649675: step: 658/470, loss: 1.6248441934585571
2023-01-22 21:22:08.321442: step: 660/470, loss: 0.0009182182257063687
2023-01-22 21:22:09.023505: step: 662/470, loss: 0.022168146446347237
2023-01-22 21:22:09.789750: step: 664/470, loss: 0.009737711399793625
2023-01-22 21:22:10.480248: step: 666/470, loss: 0.05892786756157875
2023-01-22 21:22:11.201558: step: 668/470, loss: 0.04346398264169693
2023-01-22 21:22:11.974401: step: 670/470, loss: 0.028981253504753113
2023-01-22 21:22:12.699239: step: 672/470, loss: 0.00941953994333744
2023-01-22 21:22:13.463826: step: 674/470, loss: 0.07243026047945023
2023-01-22 21:22:14.203749: step: 676/470, loss: 0.02073572389781475
2023-01-22 21:22:14.964439: step: 678/470, loss: 0.0022810224909335375
2023-01-22 21:22:15.659330: step: 680/470, loss: 0.09601109474897385
2023-01-22 21:22:16.354899: step: 682/470, loss: 0.003557687159627676
2023-01-22 21:22:17.051032: step: 684/470, loss: 0.0015952467219904065
2023-01-22 21:22:17.790405: step: 686/470, loss: 0.0002099236153298989
2023-01-22 21:22:18.515992: step: 688/470, loss: 0.376717746257782
2023-01-22 21:22:19.315004: step: 690/470, loss: 0.004120633937418461
2023-01-22 21:22:20.100340: step: 692/470, loss: 0.0018780836835503578
2023-01-22 21:22:20.968884: step: 694/470, loss: 0.5812046527862549
2023-01-22 21:22:21.692281: step: 696/470, loss: 0.002286061178892851
2023-01-22 21:22:22.450974: step: 698/470, loss: 0.013838349841535091
2023-01-22 21:22:23.188253: step: 700/470, loss: 0.0184122733771801
2023-01-22 21:22:23.861708: step: 702/470, loss: 0.0008420947706326842
2023-01-22 21:22:24.528513: step: 704/470, loss: 0.08517462015151978
2023-01-22 21:22:25.226723: step: 706/470, loss: 0.0022694526705890894
2023-01-22 21:22:26.081632: step: 708/470, loss: 0.029612381011247635
2023-01-22 21:22:26.752848: step: 710/470, loss: 0.0010812204563990235
2023-01-22 21:22:27.547808: step: 712/470, loss: 0.0535753071308136
2023-01-22 21:22:28.290003: step: 714/470, loss: 0.008847307413816452
2023-01-22 21:22:29.058505: step: 716/470, loss: 0.03432611748576164
2023-01-22 21:22:29.767667: step: 718/470, loss: 0.006384172476828098
2023-01-22 21:22:30.528659: step: 720/470, loss: 0.004302928224205971
2023-01-22 21:22:31.257054: step: 722/470, loss: 0.01254085823893547
2023-01-22 21:22:32.044353: step: 724/470, loss: 0.007098275702446699
2023-01-22 21:22:32.759634: step: 726/470, loss: 0.018687281757593155
2023-01-22 21:22:33.491143: step: 728/470, loss: 0.08355188369750977
2023-01-22 21:22:34.204068: step: 730/470, loss: 0.00029057872598059475
2023-01-22 21:22:34.962337: step: 732/470, loss: 0.06628356873989105
2023-01-22 21:22:35.644561: step: 734/470, loss: 0.04160122945904732
2023-01-22 21:22:36.440070: step: 736/470, loss: 0.005398217123001814
2023-01-22 21:22:37.229078: step: 738/470, loss: 0.00326385535299778
2023-01-22 21:22:38.032477: step: 740/470, loss: 0.10454016923904419
2023-01-22 21:22:38.768669: step: 742/470, loss: 0.00869603082537651
2023-01-22 21:22:39.533402: step: 744/470, loss: 0.01859329640865326
2023-01-22 21:22:40.273455: step: 746/470, loss: 0.0023927935399115086
2023-01-22 21:22:41.034758: step: 748/470, loss: 0.01185494102537632
2023-01-22 21:22:41.686041: step: 750/470, loss: 0.0039005994331091642
2023-01-22 21:22:42.327691: step: 752/470, loss: 0.001562373130582273
2023-01-22 21:22:43.023696: step: 754/470, loss: 0.14783407747745514
2023-01-22 21:22:43.832151: step: 756/470, loss: 0.0047768522053956985
2023-01-22 21:22:44.598747: step: 758/470, loss: 0.005835649557411671
2023-01-22 21:22:45.369592: step: 760/470, loss: 0.06568383425474167
2023-01-22 21:22:46.148650: step: 762/470, loss: 0.17401570081710815
2023-01-22 21:22:46.873203: step: 764/470, loss: 0.0028607286512851715
2023-01-22 21:22:47.547591: step: 766/470, loss: 0.03020673617720604
2023-01-22 21:22:48.296900: step: 768/470, loss: 0.2988532483577728
2023-01-22 21:22:49.103436: step: 770/470, loss: 0.2755778729915619
2023-01-22 21:22:49.839953: step: 772/470, loss: 0.07244252413511276
2023-01-22 21:22:50.614021: step: 774/470, loss: 0.030048388987779617
2023-01-22 21:22:51.313269: step: 776/470, loss: 0.18164348602294922
2023-01-22 21:22:52.064807: step: 778/470, loss: 0.001993674086406827
2023-01-22 21:22:52.847667: step: 780/470, loss: 0.003424519905820489
2023-01-22 21:22:53.759067: step: 782/470, loss: 0.01581845059990883
2023-01-22 21:22:54.527659: step: 784/470, loss: 0.03147071599960327
2023-01-22 21:22:55.242498: step: 786/470, loss: 0.016147736459970474
2023-01-22 21:22:55.963630: step: 788/470, loss: 0.0013450286351144314
2023-01-22 21:22:56.669536: step: 790/470, loss: 0.013478526845574379
2023-01-22 21:22:57.394300: step: 792/470, loss: 0.003012130269780755
2023-01-22 21:22:58.143786: step: 794/470, loss: 0.010243113152682781
2023-01-22 21:22:58.881587: step: 796/470, loss: 0.030851509422063828
2023-01-22 21:22:59.648733: step: 798/470, loss: 0.015330376103520393
2023-01-22 21:23:00.417336: step: 800/470, loss: 0.0013428201200440526
2023-01-22 21:23:01.149235: step: 802/470, loss: 0.0035743422340601683
2023-01-22 21:23:01.887886: step: 804/470, loss: 0.05729028955101967
2023-01-22 21:23:02.663988: step: 806/470, loss: 0.002276189159601927
2023-01-22 21:23:03.367668: step: 808/470, loss: 0.002368086948990822
2023-01-22 21:23:04.145591: step: 810/470, loss: 0.06536681950092316
2023-01-22 21:23:04.857761: step: 812/470, loss: 0.0029183574952185154
2023-01-22 21:23:05.606112: step: 814/470, loss: 0.0018473371164873242
2023-01-22 21:23:06.370508: step: 816/470, loss: 0.013988809660077095
2023-01-22 21:23:07.234461: step: 818/470, loss: 0.021747639402747154
2023-01-22 21:23:07.918409: step: 820/470, loss: 0.0005320486379787326
2023-01-22 21:23:08.644257: step: 822/470, loss: 0.026045726612210274
2023-01-22 21:23:09.313576: step: 824/470, loss: 0.009219018742442131
2023-01-22 21:23:10.070469: step: 826/470, loss: 0.0010474611772224307
2023-01-22 21:23:10.811986: step: 828/470, loss: 0.00877501629292965
2023-01-22 21:23:11.515825: step: 830/470, loss: 0.0060637411661446095
2023-01-22 21:23:12.280124: step: 832/470, loss: 0.02464357018470764
2023-01-22 21:23:13.067408: step: 834/470, loss: 0.00776535551995039
2023-01-22 21:23:13.751571: step: 836/470, loss: 0.053323835134506226
2023-01-22 21:23:14.461196: step: 838/470, loss: 0.0020373347215354443
2023-01-22 21:23:15.235365: step: 840/470, loss: 0.3750033974647522
2023-01-22 21:23:15.949634: step: 842/470, loss: 0.042009808123111725
2023-01-22 21:23:16.653868: step: 844/470, loss: 0.02685542218387127
2023-01-22 21:23:17.334301: step: 846/470, loss: 0.0003366958990227431
2023-01-22 21:23:18.033927: step: 848/470, loss: 0.036231983453035355
2023-01-22 21:23:18.737785: step: 850/470, loss: 0.01380055584013462
2023-01-22 21:23:19.549352: step: 852/470, loss: 0.04030189290642738
2023-01-22 21:23:20.272407: step: 854/470, loss: 0.007406915538012981
2023-01-22 21:23:20.941524: step: 856/470, loss: 0.0028321263380348682
2023-01-22 21:23:21.660736: step: 858/470, loss: 0.0024023745208978653
2023-01-22 21:23:22.350270: step: 860/470, loss: 0.045990705490112305
2023-01-22 21:23:23.081351: step: 862/470, loss: 0.0008657873258925974
2023-01-22 21:23:23.875306: step: 864/470, loss: 0.03380803018808365
2023-01-22 21:23:24.653011: step: 866/470, loss: 0.016098463907837868
2023-01-22 21:23:25.330324: step: 868/470, loss: 0.41227632761001587
2023-01-22 21:23:26.013170: step: 870/470, loss: 0.0017065646825358272
2023-01-22 21:23:26.795738: step: 872/470, loss: 0.002425319282338023
2023-01-22 21:23:27.548136: step: 874/470, loss: 0.003872190834954381
2023-01-22 21:23:28.266670: step: 876/470, loss: 0.0007468942785635591
2023-01-22 21:23:29.139183: step: 878/470, loss: 0.008748779073357582
2023-01-22 21:23:29.838311: step: 880/470, loss: 0.18740367889404297
2023-01-22 21:23:30.521827: step: 882/470, loss: 0.006937297526746988
2023-01-22 21:23:31.225819: step: 884/470, loss: 0.001644572359509766
2023-01-22 21:23:31.979059: step: 886/470, loss: 0.03953949362039566
2023-01-22 21:23:32.654734: step: 888/470, loss: 0.0010495680617168546
2023-01-22 21:23:33.384030: step: 890/470, loss: 0.004453408066183329
2023-01-22 21:23:34.057986: step: 892/470, loss: 0.03644545376300812
2023-01-22 21:23:34.733510: step: 894/470, loss: 0.0026314761489629745
2023-01-22 21:23:35.474802: step: 896/470, loss: 0.011988071724772453
2023-01-22 21:23:36.246974: step: 898/470, loss: 1.0937950611114502
2023-01-22 21:23:36.972698: step: 900/470, loss: 0.01913582533597946
2023-01-22 21:23:37.740320: step: 902/470, loss: 0.002004404319450259
2023-01-22 21:23:38.490347: step: 904/470, loss: 0.02826942503452301
2023-01-22 21:23:39.171406: step: 906/470, loss: 0.005874123424291611
2023-01-22 21:23:39.872984: step: 908/470, loss: 0.00016057485481724143
2023-01-22 21:23:40.623691: step: 910/470, loss: 0.02106778882443905
2023-01-22 21:23:41.348566: step: 912/470, loss: 0.011593667790293694
2023-01-22 21:23:42.056358: step: 914/470, loss: 0.006512309890240431
2023-01-22 21:23:42.883085: step: 916/470, loss: 0.022902552038431168
2023-01-22 21:23:43.676171: step: 918/470, loss: 0.00646227365359664
2023-01-22 21:23:44.361955: step: 920/470, loss: 0.022378139197826385
2023-01-22 21:23:45.055219: step: 922/470, loss: 0.027927104383707047
2023-01-22 21:23:45.814766: step: 924/470, loss: 0.0021522322203963995
2023-01-22 21:23:46.548094: step: 926/470, loss: 0.013384867459535599
2023-01-22 21:23:47.335812: step: 928/470, loss: 0.001673889346420765
2023-01-22 21:23:48.130248: step: 930/470, loss: 0.3148545026779175
2023-01-22 21:23:48.854052: step: 932/470, loss: 0.03243735432624817
2023-01-22 21:23:49.533152: step: 934/470, loss: 0.008292516693472862
2023-01-22 21:23:50.322369: step: 936/470, loss: 0.00035324000054970384
2023-01-22 21:23:51.067953: step: 938/470, loss: 0.003821393707767129
2023-01-22 21:23:51.816042: step: 940/470, loss: 0.008569333702325821
2023-01-22 21:23:52.525876: step: 942/470, loss: 0.003781524719670415
==================================================
Loss: 0.043
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30695768341998847, 'r': 0.3360808032890576, 'f1': 0.320859752415459}, 'combined': 0.2364229754640224, 'epoch': 34}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3418588143777791, 'r': 0.3763734062139972, 'f1': 0.3582868123227067}, 'combined': 0.24955300360785543, 'epoch': 34}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30097216824941914, 'r': 0.3375228679988742, 'f1': 0.3182013442493859}, 'combined': 0.23446414839428434, 'epoch': 34}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34812443322241643, 'r': 0.37590744087382083, 'f1': 0.36148288350325813}, 'combined': 0.2517791228380903, 'epoch': 34}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2869398730276134, 'r': 0.33975423295869217, 'f1': 0.31112159994653477}, 'combined': 0.22924749469744665, 'epoch': 34}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3366420050582426, 'r': 0.3877856942882449, 'f1': 0.3604085094367959}, 'combined': 0.2510308025927932, 'epoch': 34}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21875, 'r': 0.375, 'f1': 0.27631578947368424}, 'combined': 0.1842105263157895, 'epoch': 34}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.22093023255813954, 'r': 0.41304347826086957, 'f1': 0.2878787878787879}, 'combined': 0.14393939393939395, 'epoch': 34}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4166666666666667, 'r': 0.3017241379310345, 'f1': 0.35}, 'combined': 0.2333333333333333, 'epoch': 34}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 35
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 21:26:29.718226: step: 2/470, loss: 0.02259201370179653
2023-01-22 21:26:30.444294: step: 4/470, loss: 0.002634732285514474
2023-01-22 21:26:31.133801: step: 6/470, loss: 0.01444519218057394
2023-01-22 21:26:31.919350: step: 8/470, loss: 0.007645417936146259
2023-01-22 21:26:32.704717: step: 10/470, loss: 6.119604950072244e-05
2023-01-22 21:26:33.411599: step: 12/470, loss: 0.006398671306669712
2023-01-22 21:26:34.174903: step: 14/470, loss: 1.4735318422317505
2023-01-22 21:26:34.939664: step: 16/470, loss: 0.0003182763757649809
2023-01-22 21:26:35.861413: step: 18/470, loss: 0.014096281491219997
2023-01-22 21:26:36.560386: step: 20/470, loss: 0.14310337603092194
2023-01-22 21:26:37.425143: step: 22/470, loss: 0.00020834009046666324
2023-01-22 21:26:38.137287: step: 24/470, loss: 0.0019535699393600225
2023-01-22 21:26:38.909101: step: 26/470, loss: 0.020988579839468002
2023-01-22 21:26:39.663199: step: 28/470, loss: 0.02080502361059189
2023-01-22 21:26:40.364547: step: 30/470, loss: 0.006822787690907717
2023-01-22 21:26:41.133056: step: 32/470, loss: 0.006888087373226881
2023-01-22 21:26:41.821200: step: 34/470, loss: 0.0055128647945821285
2023-01-22 21:26:42.564954: step: 36/470, loss: 0.0021674029994755983
2023-01-22 21:26:43.265792: step: 38/470, loss: 0.03273850306868553
2023-01-22 21:26:44.032729: step: 40/470, loss: 0.03793059661984444
2023-01-22 21:26:45.011484: step: 42/470, loss: 0.0005464658606797457
2023-01-22 21:26:45.889052: step: 44/470, loss: 7.778897997923195e-05
2023-01-22 21:26:46.588751: step: 46/470, loss: 0.006451576016843319
2023-01-22 21:26:47.342873: step: 48/470, loss: 0.040247056633234024
2023-01-22 21:26:48.041077: step: 50/470, loss: 0.0015183590585365891
2023-01-22 21:26:48.736377: step: 52/470, loss: 0.005788735579699278
2023-01-22 21:26:49.463382: step: 54/470, loss: 0.0011430204613134265
2023-01-22 21:26:50.205012: step: 56/470, loss: 0.0012191730784252286
2023-01-22 21:26:50.932729: step: 58/470, loss: 5.7664259657030925e-05
2023-01-22 21:26:51.843392: step: 60/470, loss: 0.010701543651521206
2023-01-22 21:26:52.533025: step: 62/470, loss: 0.00015700850053690374
2023-01-22 21:26:53.266146: step: 64/470, loss: 0.00028906611260026693
2023-01-22 21:26:53.956406: step: 66/470, loss: 0.00823915097862482
2023-01-22 21:26:54.642041: step: 68/470, loss: 0.028155675157904625
2023-01-22 21:26:55.368348: step: 70/470, loss: 0.0030553205870091915
2023-01-22 21:26:56.006028: step: 72/470, loss: 0.003039710223674774
2023-01-22 21:26:56.721520: step: 74/470, loss: 0.001571728615090251
2023-01-22 21:26:57.387127: step: 76/470, loss: 0.5274283289909363
2023-01-22 21:26:58.110381: step: 78/470, loss: 0.04768010228872299
2023-01-22 21:26:58.836578: step: 80/470, loss: 0.00412197969853878
2023-01-22 21:26:59.561995: step: 82/470, loss: 0.1300504207611084
2023-01-22 21:27:00.250119: step: 84/470, loss: 0.0008046081056818366
2023-01-22 21:27:00.975485: step: 86/470, loss: 0.04525003209710121
2023-01-22 21:27:01.704618: step: 88/470, loss: 0.003112942911684513
2023-01-22 21:27:02.432985: step: 90/470, loss: 0.008025175891816616
2023-01-22 21:27:03.087804: step: 92/470, loss: 0.011606319807469845
2023-01-22 21:27:03.785846: step: 94/470, loss: 0.005697671324014664
2023-01-22 21:27:04.512712: step: 96/470, loss: 0.00157053186558187
2023-01-22 21:27:05.202158: step: 98/470, loss: 0.0029143900610506535
2023-01-22 21:27:05.929278: step: 100/470, loss: 0.0015309115406125784
2023-01-22 21:27:06.661835: step: 102/470, loss: 0.0018614137079566717
2023-01-22 21:27:07.399880: step: 104/470, loss: 0.007174816448241472
2023-01-22 21:27:08.136544: step: 106/470, loss: 0.037225011736154556
2023-01-22 21:27:08.885988: step: 108/470, loss: 0.013661464676260948
2023-01-22 21:27:09.586645: step: 110/470, loss: 0.015359270386397839
2023-01-22 21:27:10.301632: step: 112/470, loss: 0.05280671268701553
2023-01-22 21:27:11.141478: step: 114/470, loss: 0.0423421710729599
2023-01-22 21:27:11.880574: step: 116/470, loss: 0.6965582370758057
2023-01-22 21:27:12.560640: step: 118/470, loss: 0.016391227021813393
2023-01-22 21:27:13.317192: step: 120/470, loss: 0.002424615202471614
2023-01-22 21:27:14.038589: step: 122/470, loss: 0.0439317412674427
2023-01-22 21:27:14.774614: step: 124/470, loss: 0.041528187692165375
2023-01-22 21:27:15.511046: step: 126/470, loss: 0.022909237071871758
2023-01-22 21:27:16.199347: step: 128/470, loss: 0.005902472883462906
2023-01-22 21:27:17.006981: step: 130/470, loss: 0.012232090346515179
2023-01-22 21:27:17.683237: step: 132/470, loss: 0.006282647140324116
2023-01-22 21:27:18.362270: step: 134/470, loss: 0.009130376391112804
2023-01-22 21:27:19.059401: step: 136/470, loss: 0.0018813696224242449
2023-01-22 21:27:19.862245: step: 138/470, loss: 0.20341543853282928
2023-01-22 21:27:20.639797: step: 140/470, loss: 0.0039907037280499935
2023-01-22 21:27:21.395402: step: 142/470, loss: 0.00871391873806715
2023-01-22 21:27:22.191687: step: 144/470, loss: 0.004598352592438459
2023-01-22 21:27:22.820390: step: 146/470, loss: 0.02266603522002697
2023-01-22 21:27:23.565812: step: 148/470, loss: 0.014866764657199383
2023-01-22 21:27:24.264766: step: 150/470, loss: 0.023495275527238846
2023-01-22 21:27:24.961868: step: 152/470, loss: 0.015716491267085075
2023-01-22 21:27:25.721091: step: 154/470, loss: 0.021563276648521423
2023-01-22 21:27:26.399630: step: 156/470, loss: 0.08640297502279282
2023-01-22 21:27:27.074289: step: 158/470, loss: 0.01481255330145359
2023-01-22 21:27:27.770609: step: 160/470, loss: 0.005702580790966749
2023-01-22 21:27:28.574699: step: 162/470, loss: 0.0012152111157774925
2023-01-22 21:27:29.311536: step: 164/470, loss: 0.0035164314322173595
2023-01-22 21:27:29.956296: step: 166/470, loss: 4.3240583181614056e-05
2023-01-22 21:27:30.675178: step: 168/470, loss: 0.049790188670158386
2023-01-22 21:27:31.395321: step: 170/470, loss: 0.0005157435080036521
2023-01-22 21:27:32.140480: step: 172/470, loss: 0.0012744866544380784
2023-01-22 21:27:32.882032: step: 174/470, loss: 0.003838537260890007
2023-01-22 21:27:33.628809: step: 176/470, loss: 0.006663764826953411
2023-01-22 21:27:34.400822: step: 178/470, loss: 0.013853196054697037
2023-01-22 21:27:35.116582: step: 180/470, loss: 0.004837124142795801
2023-01-22 21:27:35.868021: step: 182/470, loss: 0.0024396313820034266
2023-01-22 21:27:36.625754: step: 184/470, loss: 0.009030799381434917
2023-01-22 21:27:37.331482: step: 186/470, loss: 0.010197999887168407
2023-01-22 21:27:38.100923: step: 188/470, loss: 0.1191810742020607
2023-01-22 21:27:38.780713: step: 190/470, loss: 7.335062400670722e-05
2023-01-22 21:27:39.505935: step: 192/470, loss: 0.022936223074793816
2023-01-22 21:27:40.274376: step: 194/470, loss: 0.002525016665458679
2023-01-22 21:27:40.991493: step: 196/470, loss: 0.15407709777355194
2023-01-22 21:27:41.689463: step: 198/470, loss: 0.02182081900537014
2023-01-22 21:27:42.402285: step: 200/470, loss: 0.02167477458715439
2023-01-22 21:27:43.148255: step: 202/470, loss: 0.017393987625837326
2023-01-22 21:27:43.925053: step: 204/470, loss: 0.04078075289726257
2023-01-22 21:27:44.732232: step: 206/470, loss: 0.0022740724962204695
2023-01-22 21:27:45.522756: step: 208/470, loss: 0.011434967629611492
2023-01-22 21:27:46.181674: step: 210/470, loss: 0.010663002729415894
2023-01-22 21:27:46.938214: step: 212/470, loss: 0.03014855459332466
2023-01-22 21:27:47.609671: step: 214/470, loss: 0.018498685210943222
2023-01-22 21:27:48.455305: step: 216/470, loss: 0.03520440682768822
2023-01-22 21:27:49.231736: step: 218/470, loss: 0.008998945355415344
2023-01-22 21:27:50.083419: step: 220/470, loss: 0.038609180599451065
2023-01-22 21:27:50.837210: step: 222/470, loss: 0.0071504549123346806
2023-01-22 21:27:51.502851: step: 224/470, loss: 0.0034373498056083918
2023-01-22 21:27:52.243446: step: 226/470, loss: 0.010733299888670444
2023-01-22 21:27:52.979464: step: 228/470, loss: 0.0056127398274838924
2023-01-22 21:27:53.705665: step: 230/470, loss: 0.006185805890709162
2023-01-22 21:27:54.419763: step: 232/470, loss: 0.007041038013994694
2023-01-22 21:27:55.132719: step: 234/470, loss: 0.12337449938058853
2023-01-22 21:27:55.862216: step: 236/470, loss: 0.005509430076926947
2023-01-22 21:27:56.617799: step: 238/470, loss: 0.46690887212753296
2023-01-22 21:27:57.377199: step: 240/470, loss: 0.004861161578446627
2023-01-22 21:27:58.102346: step: 242/470, loss: 0.025522425770759583
2023-01-22 21:27:58.836015: step: 244/470, loss: 0.00966788548976183
2023-01-22 21:27:59.570797: step: 246/470, loss: 0.003947984892874956
2023-01-22 21:28:00.297993: step: 248/470, loss: 0.00835223589092493
2023-01-22 21:28:01.060759: step: 250/470, loss: 0.0010288195917382836
2023-01-22 21:28:01.806178: step: 252/470, loss: 0.0008441155659966171
2023-01-22 21:28:02.506943: step: 254/470, loss: 0.0017779265763238072
2023-01-22 21:28:03.213311: step: 256/470, loss: 0.0010619647800922394
2023-01-22 21:28:03.915683: step: 258/470, loss: 0.0002834839397110045
2023-01-22 21:28:04.616977: step: 260/470, loss: 0.0008969651535153389
2023-01-22 21:28:05.386933: step: 262/470, loss: 0.0008425424457527697
2023-01-22 21:28:06.068349: step: 264/470, loss: 0.02052401751279831
2023-01-22 21:28:06.819617: step: 266/470, loss: 0.001179807586595416
2023-01-22 21:28:07.600572: step: 268/470, loss: 1.5121781826019287
2023-01-22 21:28:08.361061: step: 270/470, loss: 0.004608070477843285
2023-01-22 21:28:09.124229: step: 272/470, loss: 0.0143381766974926
2023-01-22 21:28:09.834762: step: 274/470, loss: 0.0026956668589264154
2023-01-22 21:28:10.558579: step: 276/470, loss: 0.009074504487216473
2023-01-22 21:28:11.227607: step: 278/470, loss: 0.012543557211756706
2023-01-22 21:28:11.877359: step: 280/470, loss: 0.020108414813876152
2023-01-22 21:28:12.570763: step: 282/470, loss: 0.004175996873527765
2023-01-22 21:28:13.207042: step: 284/470, loss: 0.0059522595256567
2023-01-22 21:28:13.872855: step: 286/470, loss: 0.00022827064094599336
2023-01-22 21:28:14.656546: step: 288/470, loss: 0.007600300945341587
2023-01-22 21:28:15.413413: step: 290/470, loss: 0.00705496221780777
2023-01-22 21:28:16.181058: step: 292/470, loss: 0.06734557449817657
2023-01-22 21:28:16.935085: step: 294/470, loss: 8.682074258103967e-05
2023-01-22 21:28:17.816492: step: 296/470, loss: 0.004848700948059559
2023-01-22 21:28:18.558093: step: 298/470, loss: 0.0014980545965954661
2023-01-22 21:28:19.248074: step: 300/470, loss: 0.0006909299991093576
2023-01-22 21:28:20.006865: step: 302/470, loss: 0.0281376875936985
2023-01-22 21:28:20.706789: step: 304/470, loss: 0.010767661035060883
2023-01-22 21:28:21.446126: step: 306/470, loss: 0.18951472640037537
2023-01-22 21:28:22.163275: step: 308/470, loss: 0.0026056517381221056
2023-01-22 21:28:22.834558: step: 310/470, loss: 0.0158822201192379
2023-01-22 21:28:23.540290: step: 312/470, loss: 0.03624594956636429
2023-01-22 21:28:24.287243: step: 314/470, loss: 0.026492631062865257
2023-01-22 21:28:24.942749: step: 316/470, loss: 0.0021404740400612354
2023-01-22 21:28:25.718670: step: 318/470, loss: 0.0041463132947683334
2023-01-22 21:28:26.493460: step: 320/470, loss: 0.02275344356894493
2023-01-22 21:28:27.283716: step: 322/470, loss: 0.03233027830719948
2023-01-22 21:28:27.987026: step: 324/470, loss: 0.0033383751288056374
2023-01-22 21:28:28.761656: step: 326/470, loss: 0.010370167903602123
2023-01-22 21:28:29.421220: step: 328/470, loss: 0.20740625262260437
2023-01-22 21:28:30.170470: step: 330/470, loss: 0.031531982123851776
2023-01-22 21:28:30.918103: step: 332/470, loss: 0.0020223986357450485
2023-01-22 21:28:31.657142: step: 334/470, loss: 0.0020372618455439806
2023-01-22 21:28:32.343383: step: 336/470, loss: 0.0007067452534101903
2023-01-22 21:28:32.978338: step: 338/470, loss: 0.0010336972773075104
2023-01-22 21:28:33.750807: step: 340/470, loss: 0.00013325613690540195
2023-01-22 21:28:34.502504: step: 342/470, loss: 0.009005560539662838
2023-01-22 21:28:35.233921: step: 344/470, loss: 0.0064828358590602875
2023-01-22 21:28:35.895708: step: 346/470, loss: 0.0001396966545144096
2023-01-22 21:28:36.769511: step: 348/470, loss: 0.16062486171722412
2023-01-22 21:28:37.492191: step: 350/470, loss: 0.2716470956802368
2023-01-22 21:28:38.237142: step: 352/470, loss: 0.05235571414232254
2023-01-22 21:28:38.977609: step: 354/470, loss: 0.029102042317390442
2023-01-22 21:28:39.705914: step: 356/470, loss: 0.01925988309085369
2023-01-22 21:28:40.375289: step: 358/470, loss: 0.0007001806516200304
2023-01-22 21:28:41.093656: step: 360/470, loss: 0.0038126695435494184
2023-01-22 21:28:41.802302: step: 362/470, loss: 0.009832276962697506
2023-01-22 21:28:42.497262: step: 364/470, loss: 0.010709324851632118
2023-01-22 21:28:43.351614: step: 366/470, loss: 0.0702999159693718
2023-01-22 21:28:44.004625: step: 368/470, loss: 0.006159055978059769
2023-01-22 21:28:44.731424: step: 370/470, loss: 6.533000123454258e-05
2023-01-22 21:28:45.496904: step: 372/470, loss: 0.022670604288578033
2023-01-22 21:28:46.315334: step: 374/470, loss: 0.005668703466653824
2023-01-22 21:28:47.011750: step: 376/470, loss: 0.020378923043608665
2023-01-22 21:28:47.745751: step: 378/470, loss: 0.00037373710074461997
2023-01-22 21:28:48.540016: step: 380/470, loss: 0.03276490792632103
2023-01-22 21:28:49.314720: step: 382/470, loss: 0.04409230127930641
2023-01-22 21:28:50.100527: step: 384/470, loss: 0.003761183237656951
2023-01-22 21:28:50.829424: step: 386/470, loss: 0.03813392296433449
2023-01-22 21:28:51.566270: step: 388/470, loss: 0.0055965944193303585
2023-01-22 21:28:52.313937: step: 390/470, loss: 0.003348251339048147
2023-01-22 21:28:53.037354: step: 392/470, loss: 0.015311792492866516
2023-01-22 21:28:53.752759: step: 394/470, loss: 0.00032469138386659324
2023-01-22 21:28:54.574267: step: 396/470, loss: 0.006082088686525822
2023-01-22 21:28:55.415402: step: 398/470, loss: 0.02094237320125103
2023-01-22 21:28:56.153772: step: 400/470, loss: 0.01110068242996931
2023-01-22 21:28:56.836459: step: 402/470, loss: 0.20870746672153473
2023-01-22 21:28:57.584051: step: 404/470, loss: 0.0033058554399758577
2023-01-22 21:28:58.279317: step: 406/470, loss: 0.00017056135402526706
2023-01-22 21:28:59.042228: step: 408/470, loss: 0.0010944005334749818
2023-01-22 21:28:59.776608: step: 410/470, loss: 0.03575807437300682
2023-01-22 21:29:00.483650: step: 412/470, loss: 0.007012884132564068
2023-01-22 21:29:01.289483: step: 414/470, loss: 4.490640276344493e-05
2023-01-22 21:29:02.024569: step: 416/470, loss: 0.05343223735690117
2023-01-22 21:29:02.748103: step: 418/470, loss: 0.007675068452954292
2023-01-22 21:29:03.426560: step: 420/470, loss: 0.0003359982802066952
2023-01-22 21:29:04.265911: step: 422/470, loss: 0.00039737403858453035
2023-01-22 21:29:04.946866: step: 424/470, loss: 0.002490453887730837
2023-01-22 21:29:05.702800: step: 426/470, loss: 0.0012507832143455744
2023-01-22 21:29:06.440581: step: 428/470, loss: 0.003989855293184519
2023-01-22 21:29:07.184819: step: 430/470, loss: 0.0036130514927208424
2023-01-22 21:29:07.890554: step: 432/470, loss: 0.0005295684677548707
2023-01-22 21:29:08.681480: step: 434/470, loss: 0.019468065351247787
2023-01-22 21:29:09.374797: step: 436/470, loss: 0.01111428253352642
2023-01-22 21:29:10.096041: step: 438/470, loss: 0.08234895020723343
2023-01-22 21:29:10.814434: step: 440/470, loss: 0.016692696139216423
2023-01-22 21:29:11.552108: step: 442/470, loss: 0.03166506811976433
2023-01-22 21:29:12.304626: step: 444/470, loss: 0.03169902786612511
2023-01-22 21:29:13.046584: step: 446/470, loss: 0.010146571323275566
2023-01-22 21:29:13.771990: step: 448/470, loss: 0.0064794747158885
2023-01-22 21:29:14.421262: step: 450/470, loss: 0.009995583444833755
2023-01-22 21:29:15.102695: step: 452/470, loss: 0.004090282134711742
2023-01-22 21:29:15.836775: step: 454/470, loss: 0.011358017101883888
2023-01-22 21:29:16.501594: step: 456/470, loss: 0.023835793137550354
2023-01-22 21:29:17.223966: step: 458/470, loss: 0.040863286703825
2023-01-22 21:29:18.033874: step: 460/470, loss: 0.025173354893922806
2023-01-22 21:29:18.731225: step: 462/470, loss: 0.0024334678892046213
2023-01-22 21:29:19.487607: step: 464/470, loss: 0.011209073476493359
2023-01-22 21:29:20.262140: step: 466/470, loss: 0.015448382124304771
2023-01-22 21:29:20.884036: step: 468/470, loss: 0.027771124616265297
2023-01-22 21:29:21.701079: step: 470/470, loss: 0.006685018073767424
2023-01-22 21:29:22.433020: step: 472/470, loss: 0.005859097465872765
2023-01-22 21:29:23.164675: step: 474/470, loss: 0.009597435593605042
2023-01-22 21:29:23.908720: step: 476/470, loss: 0.006935752462595701
2023-01-22 21:29:24.620711: step: 478/470, loss: 0.0011011871974915266
2023-01-22 21:29:25.366982: step: 480/470, loss: 0.008520321920514107
2023-01-22 21:29:26.103536: step: 482/470, loss: 0.031099451705813408
2023-01-22 21:29:26.805732: step: 484/470, loss: 0.001046741963364184
2023-01-22 21:29:27.456669: step: 486/470, loss: 0.001939225709065795
2023-01-22 21:29:28.250491: step: 488/470, loss: 0.027191482484340668
2023-01-22 21:29:29.033582: step: 490/470, loss: 0.004440982360392809
2023-01-22 21:29:29.729558: step: 492/470, loss: 0.00052472302922979
2023-01-22 21:29:30.501629: step: 494/470, loss: 0.005477104801684618
2023-01-22 21:29:31.329158: step: 496/470, loss: 0.006036494392901659
2023-01-22 21:29:32.042014: step: 498/470, loss: 0.006640726700425148
2023-01-22 21:29:32.796030: step: 500/470, loss: 0.024400828406214714
2023-01-22 21:29:33.611887: step: 502/470, loss: 0.002363094361498952
2023-01-22 21:29:34.346976: step: 504/470, loss: 0.007462051697075367
2023-01-22 21:29:35.100648: step: 506/470, loss: 0.005165347829461098
2023-01-22 21:29:35.844080: step: 508/470, loss: 0.0008528852486051619
2023-01-22 21:29:36.581188: step: 510/470, loss: 0.002549446653574705
2023-01-22 21:29:37.372406: step: 512/470, loss: 0.003729384858161211
2023-01-22 21:29:38.159066: step: 514/470, loss: 0.008527263067662716
2023-01-22 21:29:38.884560: step: 516/470, loss: 0.0031432053074240685
2023-01-22 21:29:39.637637: step: 518/470, loss: 0.018408743664622307
2023-01-22 21:29:40.334049: step: 520/470, loss: 0.008144121617078781
2023-01-22 21:29:41.132093: step: 522/470, loss: 0.020345963537693024
2023-01-22 21:29:41.818126: step: 524/470, loss: 0.0073492685332894325
2023-01-22 21:29:42.525081: step: 526/470, loss: 0.009888478554785252
2023-01-22 21:29:43.249031: step: 528/470, loss: 0.002217804081737995
2023-01-22 21:29:44.008535: step: 530/470, loss: 0.6544013619422913
2023-01-22 21:29:44.751894: step: 532/470, loss: 0.007728029508143663
2023-01-22 21:29:45.526689: step: 534/470, loss: 0.0011883730767294765
2023-01-22 21:29:46.228499: step: 536/470, loss: 0.0005980039713904262
2023-01-22 21:29:46.919303: step: 538/470, loss: 0.0516948327422142
2023-01-22 21:29:47.702856: step: 540/470, loss: 0.029013799503445625
2023-01-22 21:29:48.435956: step: 542/470, loss: 0.0037074440624564886
2023-01-22 21:29:49.219163: step: 544/470, loss: 0.00036978485877625644
2023-01-22 21:29:49.965776: step: 546/470, loss: 0.0021586138755083084
2023-01-22 21:29:50.761011: step: 548/470, loss: 0.014409597963094711
2023-01-22 21:29:51.454027: step: 550/470, loss: 0.0010483302175998688
2023-01-22 21:29:52.203770: step: 552/470, loss: 0.026682112365961075
2023-01-22 21:29:52.877863: step: 554/470, loss: 0.00963746290653944
2023-01-22 21:29:53.579114: step: 556/470, loss: 0.03591204062104225
2023-01-22 21:29:54.380016: step: 558/470, loss: 0.013330896385014057
2023-01-22 21:29:55.075116: step: 560/470, loss: 0.008176986128091812
2023-01-22 21:29:55.846914: step: 562/470, loss: 0.00987264420837164
2023-01-22 21:29:56.670916: step: 564/470, loss: 0.018903588876128197
2023-01-22 21:29:57.362733: step: 566/470, loss: 0.00032135986839421093
2023-01-22 21:29:58.102706: step: 568/470, loss: 0.00034836053964681923
2023-01-22 21:29:58.757715: step: 570/470, loss: 0.006845478434115648
2023-01-22 21:29:59.473161: step: 572/470, loss: 0.01886317878961563
2023-01-22 21:30:00.118377: step: 574/470, loss: 0.0015140185132622719
2023-01-22 21:30:00.893745: step: 576/470, loss: 0.0014535411028191447
2023-01-22 21:30:01.645669: step: 578/470, loss: 0.00014838328934274614
2023-01-22 21:30:02.282771: step: 580/470, loss: 0.005177702754735947
2023-01-22 21:30:02.971807: step: 582/470, loss: 0.0012136365985497832
2023-01-22 21:30:03.749254: step: 584/470, loss: 0.001734656747430563
2023-01-22 21:30:04.497356: step: 586/470, loss: 0.0007220085244625807
2023-01-22 21:30:05.111678: step: 588/470, loss: 0.0014062359696254134
2023-01-22 21:30:05.793735: step: 590/470, loss: 5.9928792325081304e-05
2023-01-22 21:30:06.498661: step: 592/470, loss: 0.03473540395498276
2023-01-22 21:30:07.183376: step: 594/470, loss: 0.01883302815258503
2023-01-22 21:30:07.878068: step: 596/470, loss: 0.008976499550044537
2023-01-22 21:30:08.632535: step: 598/470, loss: 8.038515079533681e-05
2023-01-22 21:30:09.489899: step: 600/470, loss: 0.008133098483085632
2023-01-22 21:30:10.284395: step: 602/470, loss: 0.009850953705608845
2023-01-22 21:30:11.084531: step: 604/470, loss: 0.016613174229860306
2023-01-22 21:30:11.757269: step: 606/470, loss: 0.008490724489092827
2023-01-22 21:30:12.444402: step: 608/470, loss: 0.00034214864717796445
2023-01-22 21:30:13.178505: step: 610/470, loss: 0.010509525425732136
2023-01-22 21:30:13.842852: step: 612/470, loss: 0.0069589437916874886
2023-01-22 21:30:14.698513: step: 614/470, loss: 0.11274606734514236
2023-01-22 21:30:15.415756: step: 616/470, loss: 0.009286433458328247
2023-01-22 21:30:16.255428: step: 618/470, loss: 0.11397167295217514
2023-01-22 21:30:16.976746: step: 620/470, loss: 0.04145457595586777
2023-01-22 21:30:17.671651: step: 622/470, loss: 0.03650517016649246
2023-01-22 21:30:18.399357: step: 624/470, loss: 0.004478362388908863
2023-01-22 21:30:19.180358: step: 626/470, loss: 0.06043071672320366
2023-01-22 21:30:19.872215: step: 628/470, loss: 0.055728744715452194
2023-01-22 21:30:20.641532: step: 630/470, loss: 0.09390320628881454
2023-01-22 21:30:21.266408: step: 632/470, loss: 0.0012103930348530412
2023-01-22 21:30:21.965711: step: 634/470, loss: 0.00010801952157635242
2023-01-22 21:30:22.725057: step: 636/470, loss: 0.0020870454609394073
2023-01-22 21:30:23.420183: step: 638/470, loss: 0.0008572909864597023
2023-01-22 21:30:24.198309: step: 640/470, loss: 0.00878854189068079
2023-01-22 21:30:24.885799: step: 642/470, loss: 0.006001758389174938
2023-01-22 21:30:25.594138: step: 644/470, loss: 0.003095379564911127
2023-01-22 21:30:26.391438: step: 646/470, loss: 0.005022485740482807
2023-01-22 21:30:27.153678: step: 648/470, loss: 0.01622042804956436
2023-01-22 21:30:27.879181: step: 650/470, loss: 0.03620656952261925
2023-01-22 21:30:28.623273: step: 652/470, loss: 0.0006067268550395966
2023-01-22 21:30:29.344829: step: 654/470, loss: 0.0015004700981080532
2023-01-22 21:30:30.169467: step: 656/470, loss: 0.003583112731575966
2023-01-22 21:30:30.831023: step: 658/470, loss: 0.0014826322440057993
2023-01-22 21:30:31.556733: step: 660/470, loss: 0.004717591218650341
2023-01-22 21:30:32.304366: step: 662/470, loss: 0.00042355526238679886
2023-01-22 21:30:33.049445: step: 664/470, loss: 0.005252582021057606
2023-01-22 21:30:33.819086: step: 666/470, loss: 0.011925187893211842
2023-01-22 21:30:34.599959: step: 668/470, loss: 0.005225887056440115
2023-01-22 21:30:35.382793: step: 670/470, loss: 0.04948273301124573
2023-01-22 21:30:36.119248: step: 672/470, loss: 0.0006488541257567704
2023-01-22 21:30:36.802167: step: 674/470, loss: 0.004141774959862232
2023-01-22 21:30:37.546974: step: 676/470, loss: 0.10701893270015717
2023-01-22 21:30:38.266631: step: 678/470, loss: 0.0004678604891523719
2023-01-22 21:30:38.922091: step: 680/470, loss: 0.0048322975635528564
2023-01-22 21:30:39.664067: step: 682/470, loss: 0.023693975061178207
2023-01-22 21:30:40.382125: step: 684/470, loss: 0.00018593238200992346
2023-01-22 21:30:41.156838: step: 686/470, loss: 8.329687989316881e-05
2023-01-22 21:30:41.854694: step: 688/470, loss: 0.0013428764650598168
2023-01-22 21:30:42.538118: step: 690/470, loss: 0.01941107213497162
2023-01-22 21:30:43.339676: step: 692/470, loss: 0.007984393276274204
2023-01-22 21:30:44.101034: step: 694/470, loss: 0.4107176661491394
2023-01-22 21:30:44.868080: step: 696/470, loss: 0.16444319486618042
2023-01-22 21:30:45.615023: step: 698/470, loss: 0.010815066285431385
2023-01-22 21:30:46.445741: step: 700/470, loss: 0.04077745974063873
2023-01-22 21:30:47.216108: step: 702/470, loss: 0.01998460479080677
2023-01-22 21:30:48.055410: step: 704/470, loss: 0.0018847326282411814
2023-01-22 21:30:48.801108: step: 706/470, loss: 0.12863512337207794
2023-01-22 21:30:49.533245: step: 708/470, loss: 0.00011070125765400007
2023-01-22 21:30:50.200478: step: 710/470, loss: 0.0005842326791025698
2023-01-22 21:30:50.922569: step: 712/470, loss: 0.000646944681648165
2023-01-22 21:30:51.709504: step: 714/470, loss: 0.005940971430391073
2023-01-22 21:30:52.499410: step: 716/470, loss: 0.00032181438291445374
2023-01-22 21:30:53.193107: step: 718/470, loss: 0.001542411744594574
2023-01-22 21:30:53.948542: step: 720/470, loss: 0.005175524391233921
2023-01-22 21:30:54.663964: step: 722/470, loss: 0.009312089532613754
2023-01-22 21:30:55.422502: step: 724/470, loss: 0.0014529626350849867
2023-01-22 21:30:56.166132: step: 726/470, loss: 0.012921427376568317
2023-01-22 21:30:56.901515: step: 728/470, loss: 0.010379222221672535
2023-01-22 21:30:57.598110: step: 730/470, loss: 0.02943400666117668
2023-01-22 21:30:58.399582: step: 732/470, loss: 0.004278372973203659
2023-01-22 21:30:59.128557: step: 734/470, loss: 0.002038972917944193
2023-01-22 21:30:59.837605: step: 736/470, loss: 0.008259556256234646
2023-01-22 21:31:00.598535: step: 738/470, loss: 0.005812020972371101
2023-01-22 21:31:01.434016: step: 740/470, loss: 0.0011574298841878772
2023-01-22 21:31:02.203170: step: 742/470, loss: 0.038374532014131546
2023-01-22 21:31:02.967598: step: 744/470, loss: 0.002495008986443281
2023-01-22 21:31:03.720963: step: 746/470, loss: 0.009755531325936317
2023-01-22 21:31:04.457810: step: 748/470, loss: 0.12439113855361938
2023-01-22 21:31:05.105683: step: 750/470, loss: 0.0035697193816304207
2023-01-22 21:31:05.805293: step: 752/470, loss: 0.0054044960997998714
2023-01-22 21:31:06.543615: step: 754/470, loss: 0.012278404086828232
2023-01-22 21:31:07.183633: step: 756/470, loss: 0.009794940240681171
2023-01-22 21:31:07.924535: step: 758/470, loss: 0.002220005262643099
2023-01-22 21:31:08.658484: step: 760/470, loss: 0.012325046584010124
2023-01-22 21:31:09.418624: step: 762/470, loss: 0.018408851698040962
2023-01-22 21:31:10.147926: step: 764/470, loss: 0.01817646436393261
2023-01-22 21:31:10.859792: step: 766/470, loss: 0.02506135031580925
2023-01-22 21:31:11.638607: step: 768/470, loss: 0.014540938660502434
2023-01-22 21:31:12.406673: step: 770/470, loss: 0.004760831594467163
2023-01-22 21:31:13.136703: step: 772/470, loss: 0.07413551956415176
2023-01-22 21:31:13.895880: step: 774/470, loss: 0.03643839806318283
2023-01-22 21:31:14.630847: step: 776/470, loss: 0.0018023299053311348
2023-01-22 21:31:15.412585: step: 778/470, loss: 0.020913278684020042
2023-01-22 21:31:16.181255: step: 780/470, loss: 0.02016664668917656
2023-01-22 21:31:16.879952: step: 782/470, loss: 0.01156390830874443
2023-01-22 21:31:17.709328: step: 784/470, loss: 0.013799360953271389
2023-01-22 21:31:18.410069: step: 786/470, loss: 0.0006355499499477446
2023-01-22 21:31:19.128948: step: 788/470, loss: 0.00016411063552368432
2023-01-22 21:31:19.849583: step: 790/470, loss: 0.0022397139109671116
2023-01-22 21:31:20.569813: step: 792/470, loss: 0.028047997504472733
2023-01-22 21:31:21.382185: step: 794/470, loss: 0.0009197811014018953
2023-01-22 21:31:22.150761: step: 796/470, loss: 0.5110117793083191
2023-01-22 21:31:22.885470: step: 798/470, loss: 0.0024509942159056664
2023-01-22 21:31:23.570298: step: 800/470, loss: 0.3866247832775116
2023-01-22 21:31:24.295848: step: 802/470, loss: 0.027848878875374794
2023-01-22 21:31:25.056698: step: 804/470, loss: 0.004700549878180027
2023-01-22 21:31:25.931630: step: 806/470, loss: 0.0064826603047549725
2023-01-22 21:31:26.610222: step: 808/470, loss: 0.000695836846716702
2023-01-22 21:31:27.375093: step: 810/470, loss: 0.0028286667075008154
2023-01-22 21:31:28.130537: step: 812/470, loss: 0.00968991406261921
2023-01-22 21:31:28.863255: step: 814/470, loss: 0.001139800762757659
2023-01-22 21:31:29.553319: step: 816/470, loss: 0.004776866175234318
2023-01-22 21:31:30.293446: step: 818/470, loss: 0.015945924445986748
2023-01-22 21:31:30.949936: step: 820/470, loss: 0.0016348791541531682
2023-01-22 21:31:31.723930: step: 822/470, loss: 0.02290150709450245
2023-01-22 21:31:32.476683: step: 824/470, loss: 0.046208322048187256
2023-01-22 21:31:33.200657: step: 826/470, loss: 0.0024622592609375715
2023-01-22 21:31:33.979807: step: 828/470, loss: 0.011288406327366829
2023-01-22 21:31:34.735627: step: 830/470, loss: 0.042418159544467926
2023-01-22 21:31:35.434415: step: 832/470, loss: 0.0909082442522049
2023-01-22 21:31:36.059896: step: 834/470, loss: 0.000317727419314906
2023-01-22 21:31:36.668780: step: 836/470, loss: 0.0007268586196005344
2023-01-22 21:31:37.457580: step: 838/470, loss: 0.012510606087744236
2023-01-22 21:31:38.204806: step: 840/470, loss: 0.007081144023686647
2023-01-22 21:31:38.871169: step: 842/470, loss: 0.0002773547312244773
2023-01-22 21:31:39.632816: step: 844/470, loss: 0.002572752069681883
2023-01-22 21:31:40.298600: step: 846/470, loss: 0.024069497361779213
2023-01-22 21:31:41.129645: step: 848/470, loss: 0.0006529639358632267
2023-01-22 21:31:41.789672: step: 850/470, loss: 0.008918379433453083
2023-01-22 21:31:42.493434: step: 852/470, loss: 0.005846343468874693
2023-01-22 21:31:43.167136: step: 854/470, loss: 0.011811641044914722
2023-01-22 21:31:43.853743: step: 856/470, loss: 0.002782166237011552
2023-01-22 21:31:44.625286: step: 858/470, loss: 0.0026911317836493254
2023-01-22 21:31:45.379858: step: 860/470, loss: 0.07831226289272308
2023-01-22 21:31:46.125991: step: 862/470, loss: 0.009529894217848778
2023-01-22 21:31:46.801586: step: 864/470, loss: 0.0002590777294244617
2023-01-22 21:31:47.525590: step: 866/470, loss: 0.14221465587615967
2023-01-22 21:31:48.248324: step: 868/470, loss: 0.03858411684632301
2023-01-22 21:31:49.019343: step: 870/470, loss: 0.020872116088867188
2023-01-22 21:31:49.808387: step: 872/470, loss: 0.0001517470518592745
2023-01-22 21:31:50.497568: step: 874/470, loss: 0.0035211762879043818
2023-01-22 21:31:51.239419: step: 876/470, loss: 0.04481646046042442
2023-01-22 21:31:51.953513: step: 878/470, loss: 0.013270605355501175
2023-01-22 21:31:52.672286: step: 880/470, loss: 0.020657042041420937
2023-01-22 21:31:53.425422: step: 882/470, loss: 0.036236584186553955
2023-01-22 21:31:54.128081: step: 884/470, loss: 0.012062986381351948
2023-01-22 21:31:54.836237: step: 886/470, loss: 0.0015210265992209315
2023-01-22 21:31:55.568998: step: 888/470, loss: 0.004456940107047558
2023-01-22 21:31:56.309916: step: 890/470, loss: 0.01179597806185484
2023-01-22 21:31:57.065781: step: 892/470, loss: 0.0002963356382679194
2023-01-22 21:31:57.931241: step: 894/470, loss: 0.001176392543129623
2023-01-22 21:31:58.729603: step: 896/470, loss: 0.0065690902993083
2023-01-22 21:31:59.497027: step: 898/470, loss: 0.008019453845918179
2023-01-22 21:32:00.254207: step: 900/470, loss: 0.002323372755199671
2023-01-22 21:32:00.967914: step: 902/470, loss: 0.036690160632133484
2023-01-22 21:32:01.661252: step: 904/470, loss: 0.01081377174705267
2023-01-22 21:32:02.368799: step: 906/470, loss: 0.014264862053096294
2023-01-22 21:32:03.102129: step: 908/470, loss: 0.014920435845851898
2023-01-22 21:32:03.805798: step: 910/470, loss: 0.030699947848916054
2023-01-22 21:32:04.507764: step: 912/470, loss: 0.0012479553697630763
2023-01-22 21:32:05.309712: step: 914/470, loss: 0.3528791069984436
2023-01-22 21:32:06.029645: step: 916/470, loss: 0.02547892928123474
2023-01-22 21:32:06.788982: step: 918/470, loss: 0.0035649023484438658
2023-01-22 21:32:07.478521: step: 920/470, loss: 0.0018619990441948175
2023-01-22 21:32:08.139447: step: 922/470, loss: 0.0008721183985471725
2023-01-22 21:32:08.848160: step: 924/470, loss: 0.04525361210107803
2023-01-22 21:32:09.519458: step: 926/470, loss: 0.17319992184638977
2023-01-22 21:32:10.192594: step: 928/470, loss: 0.00043553844443522394
2023-01-22 21:32:11.093941: step: 930/470, loss: 0.007656523957848549
2023-01-22 21:32:11.799631: step: 932/470, loss: 0.003974429797381163
2023-01-22 21:32:12.528003: step: 934/470, loss: 0.028335638344287872
2023-01-22 21:32:13.184297: step: 936/470, loss: 0.016558095812797546
2023-01-22 21:32:13.923021: step: 938/470, loss: 0.008354702033102512
2023-01-22 21:32:14.666121: step: 940/470, loss: 0.023873982951045036
2023-01-22 21:32:15.309271: step: 942/470, loss: 0.25000032782554626
==================================================
Loss: 0.034
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3006525683975433, 'r': 0.3405874446552815, 'f1': 0.31937648279952546}, 'combined': 0.23533003995754506, 'epoch': 35}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3540031340467799, 'r': 0.3625046502342626, 'f1': 0.35820345599797565}, 'combined': 0.24949494447620196, 'epoch': 35}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2930894524617996, 'r': 0.3448111205432937, 'f1': 0.3168534621208645}, 'combined': 0.23347097208905804, 'epoch': 35}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3545024543162406, 'r': 0.3609727200530404, 'f1': 0.3577083308664589}, 'combined': 0.24915008120051868, 'epoch': 35}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2789093365094121, 'r': 0.35035669975186107, 'f1': 0.3105769230769231}, 'combined': 0.22884615384615384, 'epoch': 35}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34280056080802684, 'r': 0.3681566061319635, 'f1': 0.35502642610780366}, 'combined': 0.24728208783628117, 'epoch': 35}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21929824561403508, 'r': 0.35714285714285715, 'f1': 0.2717391304347826}, 'combined': 0.18115942028985504, 'epoch': 35}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2361111111111111, 'r': 0.3695652173913043, 'f1': 0.28813559322033905}, 'combined': 0.14406779661016952, 'epoch': 35}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 35}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 36
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 21:34:52.407274: step: 2/470, loss: 0.00923900119960308
2023-01-22 21:34:53.145347: step: 4/470, loss: 0.012077202089130878
2023-01-22 21:34:53.969023: step: 6/470, loss: 0.017157871276140213
2023-01-22 21:34:54.702844: step: 8/470, loss: 0.0011838817736133933
2023-01-22 21:34:55.407262: step: 10/470, loss: 0.031294677406549454
2023-01-22 21:34:56.106004: step: 12/470, loss: 0.0029603552538901567
2023-01-22 21:34:56.851295: step: 14/470, loss: 0.0066464850679039955
2023-01-22 21:34:57.583973: step: 16/470, loss: 0.00202410900965333
2023-01-22 21:34:58.344602: step: 18/470, loss: 0.007574394345283508
2023-01-22 21:34:59.088818: step: 20/470, loss: 0.39814719557762146
2023-01-22 21:34:59.829593: step: 22/470, loss: 0.0019493503496050835
2023-01-22 21:35:00.646073: step: 24/470, loss: 0.035010937601327896
2023-01-22 21:35:01.424190: step: 26/470, loss: 0.000734560308046639
2023-01-22 21:35:02.195919: step: 28/470, loss: 0.008018039166927338
2023-01-22 21:35:02.921603: step: 30/470, loss: 0.0227291788905859
2023-01-22 21:35:03.615690: step: 32/470, loss: 0.003483888227492571
2023-01-22 21:35:04.271956: step: 34/470, loss: 0.0005610057269223034
2023-01-22 21:35:04.982633: step: 36/470, loss: 0.0045489352196455
2023-01-22 21:35:05.883248: step: 38/470, loss: 0.04132385924458504
2023-01-22 21:35:06.652101: step: 40/470, loss: 0.002870872151106596
2023-01-22 21:35:07.416605: step: 42/470, loss: 0.005469549912959337
2023-01-22 21:35:08.073040: step: 44/470, loss: 0.004644967149943113
2023-01-22 21:35:08.770894: step: 46/470, loss: 0.0010548782302066684
2023-01-22 21:35:09.480780: step: 48/470, loss: 0.008158699609339237
2023-01-22 21:35:10.194572: step: 50/470, loss: 0.0006612870492972434
2023-01-22 21:35:10.877243: step: 52/470, loss: 0.008797750808298588
2023-01-22 21:35:11.613820: step: 54/470, loss: 0.04867735132575035
2023-01-22 21:35:12.379480: step: 56/470, loss: 0.005971251055598259
2023-01-22 21:35:13.107308: step: 58/470, loss: 0.003688129596412182
2023-01-22 21:35:13.795040: step: 60/470, loss: 0.0009264365653507411
2023-01-22 21:35:14.598648: step: 62/470, loss: 0.010077004320919514
2023-01-22 21:35:15.218058: step: 64/470, loss: 0.0002823990071192384
2023-01-22 21:35:15.921226: step: 66/470, loss: 0.007472657132893801
2023-01-22 21:35:16.658136: step: 68/470, loss: 0.12757711112499237
2023-01-22 21:35:17.403295: step: 70/470, loss: 0.0001368361699860543
2023-01-22 21:35:18.098037: step: 72/470, loss: 0.021803027018904686
2023-01-22 21:35:18.822636: step: 74/470, loss: 0.00901093054562807
2023-01-22 21:35:19.611239: step: 76/470, loss: 0.013547614216804504
2023-01-22 21:35:20.363289: step: 78/470, loss: 0.0005593632231466472
2023-01-22 21:35:21.056485: step: 80/470, loss: 0.0004783176409546286
2023-01-22 21:35:21.797640: step: 82/470, loss: 7.210922194644809e-05
2023-01-22 21:35:22.560480: step: 84/470, loss: 0.0192702803760767
2023-01-22 21:35:23.347114: step: 86/470, loss: 0.005496703088283539
2023-01-22 21:35:24.135710: step: 88/470, loss: 0.023109078407287598
2023-01-22 21:35:24.864630: step: 90/470, loss: 0.005734420381486416
2023-01-22 21:35:25.633644: step: 92/470, loss: 0.24637438356876373
2023-01-22 21:35:26.381247: step: 94/470, loss: 0.02152753807604313
2023-01-22 21:35:27.106827: step: 96/470, loss: 0.005265772808343172
2023-01-22 21:35:27.847194: step: 98/470, loss: 0.012245593592524529
2023-01-22 21:35:28.637680: step: 100/470, loss: 0.0001247525360668078
2023-01-22 21:35:29.465113: step: 102/470, loss: 0.0013826676877215505
2023-01-22 21:35:30.201177: step: 104/470, loss: 0.0027163000777363777
2023-01-22 21:35:30.928880: step: 106/470, loss: 0.005290861241519451
2023-01-22 21:35:31.686665: step: 108/470, loss: 0.009316950105130672
2023-01-22 21:35:32.497480: step: 110/470, loss: 0.1678803563117981
2023-01-22 21:35:33.180211: step: 112/470, loss: 0.09275523573160172
2023-01-22 21:35:33.850795: step: 114/470, loss: 0.0027781319804489613
2023-01-22 21:35:34.481356: step: 116/470, loss: 4.896317113889381e-05
2023-01-22 21:35:35.228583: step: 118/470, loss: 2.4704264433239587e-05
2023-01-22 21:35:35.958128: step: 120/470, loss: 0.004806291311979294
2023-01-22 21:35:36.746947: step: 122/470, loss: 0.09023859351873398
2023-01-22 21:35:37.429445: step: 124/470, loss: 0.0018310233717784286
2023-01-22 21:35:38.140758: step: 126/470, loss: 0.0012032542144879699
2023-01-22 21:35:38.866513: step: 128/470, loss: 0.0027267164550721645
2023-01-22 21:35:39.556385: step: 130/470, loss: 0.0002811734448187053
2023-01-22 21:35:40.327600: step: 132/470, loss: 0.00040184182580560446
2023-01-22 21:35:41.060509: step: 134/470, loss: 0.0015739360824227333
2023-01-22 21:35:41.787025: step: 136/470, loss: 0.00714887585490942
2023-01-22 21:35:42.496421: step: 138/470, loss: 0.022787457332015038
2023-01-22 21:35:43.251826: step: 140/470, loss: 0.00430362019687891
2023-01-22 21:35:43.895393: step: 142/470, loss: 3.319919778732583e-05
2023-01-22 21:35:44.563249: step: 144/470, loss: 0.015644496306777
2023-01-22 21:35:45.285452: step: 146/470, loss: 0.019434552639722824
2023-01-22 21:35:46.047011: step: 148/470, loss: 0.001240216544829309
2023-01-22 21:35:46.819133: step: 150/470, loss: 0.001468593254685402
2023-01-22 21:35:47.537689: step: 152/470, loss: 0.005688677076250315
2023-01-22 21:35:48.280666: step: 154/470, loss: 0.03621711581945419
2023-01-22 21:35:49.080209: step: 156/470, loss: 0.002134978072717786
2023-01-22 21:35:49.879732: step: 158/470, loss: 0.0038371176924556494
2023-01-22 21:35:50.630401: step: 160/470, loss: 0.025045614689588547
2023-01-22 21:35:51.383835: step: 162/470, loss: 0.002029221039265394
2023-01-22 21:35:52.359317: step: 164/470, loss: 0.0003728036826942116
2023-01-22 21:35:53.068573: step: 166/470, loss: 0.00826074555516243
2023-01-22 21:35:53.890066: step: 168/470, loss: 0.003485210472717881
2023-01-22 21:35:54.668353: step: 170/470, loss: 0.002386857522651553
2023-01-22 21:35:55.406979: step: 172/470, loss: 0.010757505893707275
2023-01-22 21:35:56.170478: step: 174/470, loss: 0.00275437138043344
2023-01-22 21:35:56.806632: step: 176/470, loss: 0.007767565548419952
2023-01-22 21:35:57.593749: step: 178/470, loss: 0.9939495921134949
2023-01-22 21:35:58.300733: step: 180/470, loss: 0.0013092899462208152
2023-01-22 21:35:59.056306: step: 182/470, loss: 0.003127588424831629
2023-01-22 21:35:59.796065: step: 184/470, loss: 0.0006091459654271603
2023-01-22 21:36:00.502591: step: 186/470, loss: 0.03590903431177139
2023-01-22 21:36:01.243587: step: 188/470, loss: 0.024302396923303604
2023-01-22 21:36:02.033392: step: 190/470, loss: 0.0021148929372429848
2023-01-22 21:36:02.719261: step: 192/470, loss: 0.011187209747731686
2023-01-22 21:36:03.379576: step: 194/470, loss: 0.004178525879979134
2023-01-22 21:36:04.129929: step: 196/470, loss: 0.033812280744314194
2023-01-22 21:36:04.798338: step: 198/470, loss: 0.009949339553713799
2023-01-22 21:36:05.493657: step: 200/470, loss: 0.016883907839655876
2023-01-22 21:36:06.225984: step: 202/470, loss: 0.000815562263596803
2023-01-22 21:36:06.983489: step: 204/470, loss: 0.010811416432261467
2023-01-22 21:36:07.702258: step: 206/470, loss: 0.029568077996373177
2023-01-22 21:36:08.472335: step: 208/470, loss: 0.07659181952476501
2023-01-22 21:36:09.170607: step: 210/470, loss: 0.0033108582720160484
2023-01-22 21:36:09.926240: step: 212/470, loss: 0.011148279532790184
2023-01-22 21:36:10.702838: step: 214/470, loss: 0.07719606906175613
2023-01-22 21:36:11.393919: step: 216/470, loss: 0.00038251784280873835
2023-01-22 21:36:12.059617: step: 218/470, loss: 0.002361322520300746
2023-01-22 21:36:12.789483: step: 220/470, loss: 0.005027166102081537
2023-01-22 21:36:13.617548: step: 222/470, loss: 0.005157764069736004
2023-01-22 21:36:14.283454: step: 224/470, loss: 0.001214994816109538
2023-01-22 21:36:15.158360: step: 226/470, loss: 0.016031332314014435
2023-01-22 21:36:15.813564: step: 228/470, loss: 0.0022524199448525906
2023-01-22 21:36:16.604482: step: 230/470, loss: 0.011084591038525105
2023-01-22 21:36:17.235331: step: 232/470, loss: 0.0007433760329149663
2023-01-22 21:36:17.922813: step: 234/470, loss: 0.000476872461149469
2023-01-22 21:36:18.608116: step: 236/470, loss: 0.007138427346944809
2023-01-22 21:36:19.310086: step: 238/470, loss: 0.010517815127968788
2023-01-22 21:36:20.054837: step: 240/470, loss: 0.007859362289309502
2023-01-22 21:36:20.766511: step: 242/470, loss: 0.002640694146975875
2023-01-22 21:36:21.537969: step: 244/470, loss: 0.0009882624726742506
2023-01-22 21:36:22.298975: step: 246/470, loss: 0.41087213158607483
2023-01-22 21:36:22.988886: step: 248/470, loss: 0.003996912389993668
2023-01-22 21:36:23.737309: step: 250/470, loss: 0.0006755517679266632
2023-01-22 21:36:24.465656: step: 252/470, loss: 0.7485092878341675
2023-01-22 21:36:25.195760: step: 254/470, loss: 0.014115111902356148
2023-01-22 21:36:25.972731: step: 256/470, loss: 0.0011114904191344976
2023-01-22 21:36:26.718221: step: 258/470, loss: 0.003493404248729348
2023-01-22 21:36:27.410575: step: 260/470, loss: 0.005939795169979334
2023-01-22 21:36:28.131244: step: 262/470, loss: 0.002627335721626878
2023-01-22 21:36:28.886177: step: 264/470, loss: 0.005035010632127523
2023-01-22 21:36:29.584177: step: 266/470, loss: 0.0006927988724783063
2023-01-22 21:36:30.351266: step: 268/470, loss: 0.0007211231859400868
2023-01-22 21:36:31.088378: step: 270/470, loss: 0.011166412383317947
2023-01-22 21:36:31.713975: step: 272/470, loss: 0.001943384064361453
2023-01-22 21:36:32.553033: step: 274/470, loss: 0.0034223003312945366
2023-01-22 21:36:33.244052: step: 276/470, loss: 0.0008902418776415288
2023-01-22 21:36:33.913650: step: 278/470, loss: 1.600859104655683e-05
2023-01-22 21:36:34.660793: step: 280/470, loss: 0.009566079825162888
2023-01-22 21:36:35.366563: step: 282/470, loss: 0.014527286402881145
2023-01-22 21:36:36.046657: step: 284/470, loss: 0.0004398828314151615
2023-01-22 21:36:36.798262: step: 286/470, loss: 0.0003213112649973482
2023-01-22 21:36:37.498835: step: 288/470, loss: 0.015395899303257465
2023-01-22 21:36:38.238179: step: 290/470, loss: 0.0060600400902330875
2023-01-22 21:36:38.878747: step: 292/470, loss: 0.043014369904994965
2023-01-22 21:36:39.668189: step: 294/470, loss: 0.0011471402831375599
2023-01-22 21:36:40.393582: step: 296/470, loss: 0.005423126742243767
2023-01-22 21:36:41.067475: step: 298/470, loss: 0.002312835305929184
2023-01-22 21:36:41.880536: step: 300/470, loss: 3.738845043699257e-05
2023-01-22 21:36:42.635567: step: 302/470, loss: 0.0018065288895741105
2023-01-22 21:36:43.381123: step: 304/470, loss: 0.0027574519626796246
2023-01-22 21:36:44.112015: step: 306/470, loss: 0.01440048310905695
2023-01-22 21:36:44.756498: step: 308/470, loss: 0.0008997022523544729
2023-01-22 21:36:45.403225: step: 310/470, loss: 6.702099199173972e-05
2023-01-22 21:36:46.202360: step: 312/470, loss: 0.0026232399977743626
2023-01-22 21:36:46.973763: step: 314/470, loss: 0.024350032210350037
2023-01-22 21:36:47.722797: step: 316/470, loss: 0.001658335910178721
2023-01-22 21:36:48.593389: step: 318/470, loss: 0.17800642549991608
2023-01-22 21:36:49.447000: step: 320/470, loss: 0.007545904256403446
2023-01-22 21:36:50.152143: step: 322/470, loss: 0.005511886440217495
2023-01-22 21:36:50.914434: step: 324/470, loss: 0.00106968788895756
2023-01-22 21:36:51.685494: step: 326/470, loss: 0.009400931186974049
2023-01-22 21:36:52.477661: step: 328/470, loss: 0.09563762694597244
2023-01-22 21:36:53.313132: step: 330/470, loss: 0.032428767532110214
2023-01-22 21:36:54.009232: step: 332/470, loss: 0.0007735613035038114
2023-01-22 21:36:54.735077: step: 334/470, loss: 0.0012304666452109814
2023-01-22 21:36:55.461185: step: 336/470, loss: 0.009064443409442902
2023-01-22 21:36:56.179994: step: 338/470, loss: 0.013549595139920712
2023-01-22 21:36:56.822340: step: 340/470, loss: 0.005491095595061779
2023-01-22 21:36:57.567850: step: 342/470, loss: 0.05642802268266678
2023-01-22 21:36:58.332883: step: 344/470, loss: 0.0018173677381128073
2023-01-22 21:36:59.109543: step: 346/470, loss: 5.139792442321777
2023-01-22 21:36:59.834588: step: 348/470, loss: 0.02769005112349987
2023-01-22 21:37:00.534792: step: 350/470, loss: 0.000412216002587229
2023-01-22 21:37:01.245872: step: 352/470, loss: 0.003857748582959175
2023-01-22 21:37:01.942296: step: 354/470, loss: 2.7695212338585407e-05
2023-01-22 21:37:02.654367: step: 356/470, loss: 0.018569406121969223
2023-01-22 21:37:03.305438: step: 358/470, loss: 0.012955770827829838
2023-01-22 21:37:04.086923: step: 360/470, loss: 0.010661961510777473
2023-01-22 21:37:04.785937: step: 362/470, loss: 0.00027638301253318787
2023-01-22 21:37:05.529080: step: 364/470, loss: 0.007698203437030315
2023-01-22 21:37:06.313176: step: 366/470, loss: 0.04173200950026512
2023-01-22 21:37:07.051787: step: 368/470, loss: 0.024436986073851585
2023-01-22 21:37:07.812409: step: 370/470, loss: 0.01597761921584606
2023-01-22 21:37:08.541433: step: 372/470, loss: 0.0023119584657251835
2023-01-22 21:37:09.277278: step: 374/470, loss: 0.014497130177915096
2023-01-22 21:37:10.018964: step: 376/470, loss: 0.050365082919597626
2023-01-22 21:37:10.793394: step: 378/470, loss: 0.0003797081299126148
2023-01-22 21:37:11.463686: step: 380/470, loss: 0.008779437281191349
2023-01-22 21:37:12.248435: step: 382/470, loss: 0.0028053114656358957
2023-01-22 21:37:12.937074: step: 384/470, loss: 0.03160949423909187
2023-01-22 21:37:13.611209: step: 386/470, loss: 0.0006880006403662264
2023-01-22 21:37:14.373507: step: 388/470, loss: 0.04208315163850784
2023-01-22 21:37:15.069635: step: 390/470, loss: 0.048570651561021805
2023-01-22 21:37:15.747189: step: 392/470, loss: 0.00653655594214797
2023-01-22 21:37:16.532827: step: 394/470, loss: 0.007898114621639252
2023-01-22 21:37:17.185844: step: 396/470, loss: 0.004265481140464544
2023-01-22 21:37:17.892069: step: 398/470, loss: 0.01859181746840477
2023-01-22 21:37:18.628850: step: 400/470, loss: 0.08174117654561996
2023-01-22 21:37:19.387180: step: 402/470, loss: 0.0019423263147473335
2023-01-22 21:37:20.196874: step: 404/470, loss: 0.8433279991149902
2023-01-22 21:37:20.908798: step: 406/470, loss: 0.01536853052675724
2023-01-22 21:37:21.665645: step: 408/470, loss: 0.0003358535177540034
2023-01-22 21:37:22.520146: step: 410/470, loss: 0.0031478151213377714
2023-01-22 21:37:23.246231: step: 412/470, loss: 0.013405255042016506
2023-01-22 21:37:24.043347: step: 414/470, loss: 0.016643131151795387
2023-01-22 21:37:24.900540: step: 416/470, loss: 0.02678093872964382
2023-01-22 21:37:25.589453: step: 418/470, loss: 0.020490285009145737
2023-01-22 21:37:26.325602: step: 420/470, loss: 0.0006113100098446012
2023-01-22 21:37:27.055857: step: 422/470, loss: 0.002850792370736599
2023-01-22 21:37:27.724469: step: 424/470, loss: 0.006809963844716549
2023-01-22 21:37:28.417447: step: 426/470, loss: 0.004680205602198839
2023-01-22 21:37:29.181016: step: 428/470, loss: 0.05235651135444641
2023-01-22 21:37:29.799218: step: 430/470, loss: 0.0019032071577385068
2023-01-22 21:37:30.557514: step: 432/470, loss: 0.002714117057621479
2023-01-22 21:37:31.241940: step: 434/470, loss: 4.397636803332716e-05
2023-01-22 21:37:31.977426: step: 436/470, loss: 0.004602306988090277
2023-01-22 21:37:32.686255: step: 438/470, loss: 0.002536438638344407
2023-01-22 21:37:33.313804: step: 440/470, loss: 0.0079796202480793
2023-01-22 21:37:34.014420: step: 442/470, loss: 0.0008243197808042169
2023-01-22 21:37:34.764074: step: 444/470, loss: 0.5589166283607483
2023-01-22 21:37:35.488149: step: 446/470, loss: 0.0018179480684921145
2023-01-22 21:37:36.139569: step: 448/470, loss: 0.0001185851579066366
2023-01-22 21:37:36.893761: step: 450/470, loss: 0.0011897934600710869
2023-01-22 21:37:37.655699: step: 452/470, loss: 0.00027267372934147716
2023-01-22 21:37:38.407612: step: 454/470, loss: 0.0025439695455133915
2023-01-22 21:37:39.081655: step: 456/470, loss: 0.002703068545088172
2023-01-22 21:37:39.829190: step: 458/470, loss: 0.005375206470489502
2023-01-22 21:37:40.501233: step: 460/470, loss: 0.19524531066417694
2023-01-22 21:37:41.183204: step: 462/470, loss: 0.010033880360424519
2023-01-22 21:37:41.946892: step: 464/470, loss: 0.012586308643221855
2023-01-22 21:37:42.686517: step: 466/470, loss: 0.0472489595413208
2023-01-22 21:37:43.364502: step: 468/470, loss: 0.0008478930103592575
2023-01-22 21:37:44.103913: step: 470/470, loss: 0.11491312831640244
2023-01-22 21:37:44.862418: step: 472/470, loss: 0.009833801537752151
2023-01-22 21:37:45.604464: step: 474/470, loss: 0.0006098474841564894
2023-01-22 21:37:46.301147: step: 476/470, loss: 0.008477217517793179
2023-01-22 21:37:47.086850: step: 478/470, loss: 0.01668260060250759
2023-01-22 21:37:47.769513: step: 480/470, loss: 0.0023414173629134893
2023-01-22 21:37:48.497214: step: 482/470, loss: 0.00018246278341393918
2023-01-22 21:37:49.183044: step: 484/470, loss: 0.12619908154010773
2023-01-22 21:37:49.929833: step: 486/470, loss: 0.2414586991071701
2023-01-22 21:37:50.549266: step: 488/470, loss: 0.010544035583734512
2023-01-22 21:37:51.225960: step: 490/470, loss: 0.005296720191836357
2023-01-22 21:37:51.915997: step: 492/470, loss: 0.00037122564390301704
2023-01-22 21:37:52.658963: step: 494/470, loss: 0.03093797340989113
2023-01-22 21:37:53.418611: step: 496/470, loss: 0.008792520500719547
2023-01-22 21:37:54.166240: step: 498/470, loss: 0.00578495254740119
2023-01-22 21:37:54.881097: step: 500/470, loss: 0.001827099360525608
2023-01-22 21:37:55.642261: step: 502/470, loss: 0.0032651459332555532
2023-01-22 21:37:56.329963: step: 504/470, loss: 0.006231415551155806
2023-01-22 21:37:57.070819: step: 506/470, loss: 0.007668264210224152
2023-01-22 21:37:57.809932: step: 508/470, loss: 0.008598407730460167
2023-01-22 21:37:58.525919: step: 510/470, loss: 0.00026979786343872547
2023-01-22 21:37:59.235392: step: 512/470, loss: 0.0024315055925399065
2023-01-22 21:37:59.921697: step: 514/470, loss: 0.004124908242374659
2023-01-22 21:38:00.629427: step: 516/470, loss: 0.016314754262566566
2023-01-22 21:38:01.331220: step: 518/470, loss: 0.0018118376610800624
2023-01-22 21:38:02.154690: step: 520/470, loss: 0.015621883794665337
2023-01-22 21:38:02.910984: step: 522/470, loss: 0.9467869400978088
2023-01-22 21:38:03.721201: step: 524/470, loss: 0.0005159341963008046
2023-01-22 21:38:04.393742: step: 526/470, loss: 0.0463469959795475
2023-01-22 21:38:05.085688: step: 528/470, loss: 0.006032614037394524
2023-01-22 21:38:05.839826: step: 530/470, loss: 0.0176707673817873
2023-01-22 21:38:06.559420: step: 532/470, loss: 0.0011732151033356786
2023-01-22 21:38:07.280076: step: 534/470, loss: 0.00020226027118042111
2023-01-22 21:38:08.024870: step: 536/470, loss: 0.021612750366330147
2023-01-22 21:38:08.741545: step: 538/470, loss: 0.00013169506564736366
2023-01-22 21:38:09.475228: step: 540/470, loss: 0.003677097614854574
2023-01-22 21:38:10.170761: step: 542/470, loss: 0.0020855306647717953
2023-01-22 21:38:10.874184: step: 544/470, loss: 0.0180249884724617
2023-01-22 21:38:11.570442: step: 546/470, loss: 0.40944904088974
2023-01-22 21:38:12.290017: step: 548/470, loss: 0.03017675317823887
2023-01-22 21:38:13.013487: step: 550/470, loss: 0.0034764918964356184
2023-01-22 21:38:13.760350: step: 552/470, loss: 0.034397684037685394
2023-01-22 21:38:14.533602: step: 554/470, loss: 0.03786651790142059
2023-01-22 21:38:15.235283: step: 556/470, loss: 5.748906914959662e-05
2023-01-22 21:38:15.955653: step: 558/470, loss: 0.010671430267393589
2023-01-22 21:38:16.564128: step: 560/470, loss: 0.004713733680546284
2023-01-22 21:38:17.362470: step: 562/470, loss: 0.009778480976819992
2023-01-22 21:38:18.134484: step: 564/470, loss: 0.030256683006882668
2023-01-22 21:38:18.904941: step: 566/470, loss: 0.16448631882667542
2023-01-22 21:38:19.654026: step: 568/470, loss: 0.031042061746120453
2023-01-22 21:38:20.305437: step: 570/470, loss: 0.0012754781637340784
2023-01-22 21:38:21.026835: step: 572/470, loss: 4.709012864623219e-05
2023-01-22 21:38:21.786075: step: 574/470, loss: 0.0009633488371036947
2023-01-22 21:38:22.486477: step: 576/470, loss: 0.004429661203175783
2023-01-22 21:38:23.241292: step: 578/470, loss: 0.002976109506562352
2023-01-22 21:38:23.947234: step: 580/470, loss: 7.336642738664523e-05
2023-01-22 21:38:24.707855: step: 582/470, loss: 0.002431001979857683
2023-01-22 21:38:25.466462: step: 584/470, loss: 0.0037843480240553617
2023-01-22 21:38:26.137712: step: 586/470, loss: 0.010521448217332363
2023-01-22 21:38:26.899637: step: 588/470, loss: 0.025577588006854057
2023-01-22 21:38:27.692211: step: 590/470, loss: 1.7032889445545152e-05
2023-01-22 21:38:28.371751: step: 592/470, loss: 0.009300955571234226
2023-01-22 21:38:29.039809: step: 594/470, loss: 0.0038660001009702682
2023-01-22 21:38:29.752869: step: 596/470, loss: 0.015712929889559746
2023-01-22 21:38:30.475972: step: 598/470, loss: 0.0012648508418351412
2023-01-22 21:38:31.107607: step: 600/470, loss: 1.5697081835241988e-05
2023-01-22 21:38:31.900882: step: 602/470, loss: 0.004670980852097273
2023-01-22 21:38:32.646653: step: 604/470, loss: 0.0012620283523574471
2023-01-22 21:38:33.526027: step: 606/470, loss: 0.03995297849178314
2023-01-22 21:38:34.263423: step: 608/470, loss: 0.0038986399304121733
2023-01-22 21:38:34.923594: step: 610/470, loss: 0.00033180887112393975
2023-01-22 21:38:35.676374: step: 612/470, loss: 0.2208339273929596
2023-01-22 21:38:36.377909: step: 614/470, loss: 0.005182696972042322
2023-01-22 21:38:37.063298: step: 616/470, loss: 0.05351833254098892
2023-01-22 21:38:37.741871: step: 618/470, loss: 0.002840483095496893
2023-01-22 21:38:38.496703: step: 620/470, loss: 0.02025892585515976
2023-01-22 21:38:39.206000: step: 622/470, loss: 0.0013204108690842986
2023-01-22 21:38:39.969579: step: 624/470, loss: 0.013018092140555382
2023-01-22 21:38:40.687683: step: 626/470, loss: 0.012406433932483196
2023-01-22 21:38:41.445304: step: 628/470, loss: 0.05976390466094017
2023-01-22 21:38:42.179946: step: 630/470, loss: 0.026684027165174484
2023-01-22 21:38:42.884024: step: 632/470, loss: 0.02948051132261753
2023-01-22 21:38:43.609558: step: 634/470, loss: 0.007042787969112396
2023-01-22 21:38:44.290845: step: 636/470, loss: 0.0019455266883596778
2023-01-22 21:38:45.063134: step: 638/470, loss: 0.0003431853256188333
2023-01-22 21:38:45.805781: step: 640/470, loss: 7.0864763983991e-05
2023-01-22 21:38:46.559425: step: 642/470, loss: 0.0003391270583961159
2023-01-22 21:38:47.297566: step: 644/470, loss: 4.537831409834325e-05
2023-01-22 21:38:47.970027: step: 646/470, loss: 0.0003427540068514645
2023-01-22 21:38:48.771884: step: 648/470, loss: 0.0021758859511464834
2023-01-22 21:38:49.500035: step: 650/470, loss: 0.005326189566403627
2023-01-22 21:38:50.285044: step: 652/470, loss: 0.0031783096492290497
2023-01-22 21:38:51.011565: step: 654/470, loss: 0.008024906739592552
2023-01-22 21:38:51.676481: step: 656/470, loss: 0.02158765122294426
2023-01-22 21:38:52.376203: step: 658/470, loss: 0.002388355555012822
2023-01-22 21:38:53.069087: step: 660/470, loss: 0.06495095044374466
2023-01-22 21:38:53.796373: step: 662/470, loss: 8.486651495331898e-05
2023-01-22 21:38:54.542975: step: 664/470, loss: 0.0028081880882382393
2023-01-22 21:38:55.262139: step: 666/470, loss: 0.0018558679148554802
2023-01-22 21:38:56.094423: step: 668/470, loss: 0.06942654401063919
2023-01-22 21:38:56.844508: step: 670/470, loss: 0.07627329230308533
2023-01-22 21:38:57.548750: step: 672/470, loss: 0.001862462260760367
2023-01-22 21:38:58.272865: step: 674/470, loss: 0.05258966609835625
2023-01-22 21:38:59.001582: step: 676/470, loss: 0.0007247717585414648
2023-01-22 21:38:59.672326: step: 678/470, loss: 0.018573222681879997
2023-01-22 21:39:00.453808: step: 680/470, loss: 0.0053161317482590675
2023-01-22 21:39:01.162935: step: 682/470, loss: 0.00019386372878216207
2023-01-22 21:39:01.835433: step: 684/470, loss: 0.13742390275001526
2023-01-22 21:39:02.610175: step: 686/470, loss: 0.0006456512492150068
2023-01-22 21:39:03.389367: step: 688/470, loss: 0.18807780742645264
2023-01-22 21:39:04.169085: step: 690/470, loss: 0.028313491493463516
2023-01-22 21:39:04.880983: step: 692/470, loss: 0.0024669389240443707
2023-01-22 21:39:05.648651: step: 694/470, loss: 0.03522627428174019
2023-01-22 21:39:06.384840: step: 696/470, loss: 0.010675939731299877
2023-01-22 21:39:07.050084: step: 698/470, loss: 0.0003027912462130189
2023-01-22 21:39:07.754183: step: 700/470, loss: 0.002517101587727666
2023-01-22 21:39:08.377939: step: 702/470, loss: 0.014464635401964188
2023-01-22 21:39:09.027735: step: 704/470, loss: 0.0031239360105246305
2023-01-22 21:39:09.734586: step: 706/470, loss: 0.00918420311063528
2023-01-22 21:39:10.445865: step: 708/470, loss: 0.001296902191825211
2023-01-22 21:39:11.176380: step: 710/470, loss: 0.022592980414628983
2023-01-22 21:39:11.932844: step: 712/470, loss: 0.00858447514474392
2023-01-22 21:39:12.642065: step: 714/470, loss: 0.0009968002559617162
2023-01-22 21:39:13.483077: step: 716/470, loss: 0.01551523432135582
2023-01-22 21:39:14.191809: step: 718/470, loss: 0.0007260640268214047
2023-01-22 21:39:14.937381: step: 720/470, loss: 0.35326698422431946
2023-01-22 21:39:15.677421: step: 722/470, loss: 0.01254792045801878
2023-01-22 21:39:16.352819: step: 724/470, loss: 0.0011204167967662215
2023-01-22 21:39:17.141440: step: 726/470, loss: 0.009652595967054367
2023-01-22 21:39:17.920284: step: 728/470, loss: 0.0007612319895997643
2023-01-22 21:39:18.659462: step: 730/470, loss: 0.08440537005662918
2023-01-22 21:39:19.367760: step: 732/470, loss: 0.0013828004011884332
2023-01-22 21:39:20.075188: step: 734/470, loss: 0.03739370405673981
2023-01-22 21:39:20.878620: step: 736/470, loss: 0.009630827233195305
2023-01-22 21:39:21.584969: step: 738/470, loss: 0.002095034345984459
2023-01-22 21:39:22.409020: step: 740/470, loss: 0.010538318194448948
2023-01-22 21:39:23.154147: step: 742/470, loss: 0.014126413501799107
2023-01-22 21:39:23.776620: step: 744/470, loss: 4.5405220589600503e-05
2023-01-22 21:39:24.562200: step: 746/470, loss: 0.9865442514419556
2023-01-22 21:39:25.338171: step: 748/470, loss: 0.7587553262710571
2023-01-22 21:39:26.009955: step: 750/470, loss: 0.004690216854214668
2023-01-22 21:39:26.751303: step: 752/470, loss: 0.016793884336948395
2023-01-22 21:39:27.468679: step: 754/470, loss: 0.003269862150773406
2023-01-22 21:39:28.190603: step: 756/470, loss: 0.018169786781072617
2023-01-22 21:39:28.913530: step: 758/470, loss: 0.02258247695863247
2023-01-22 21:39:29.595044: step: 760/470, loss: 5.565112587646581e-05
2023-01-22 21:39:30.264545: step: 762/470, loss: 0.009303715080022812
2023-01-22 21:39:31.049821: step: 764/470, loss: 0.017047366127371788
2023-01-22 21:39:31.795574: step: 766/470, loss: 0.015494248829782009
2023-01-22 21:39:32.526141: step: 768/470, loss: 0.026896020397543907
2023-01-22 21:39:33.241673: step: 770/470, loss: 0.005921604577451944
2023-01-22 21:39:34.013723: step: 772/470, loss: 0.001984368311241269
2023-01-22 21:39:34.698529: step: 774/470, loss: 0.002783828182145953
2023-01-22 21:39:35.439049: step: 776/470, loss: 0.019098268821835518
2023-01-22 21:39:36.273645: step: 778/470, loss: 0.005505918525159359
2023-01-22 21:39:37.018975: step: 780/470, loss: 0.24571584165096283
2023-01-22 21:39:37.700013: step: 782/470, loss: 0.0006462166784331203
2023-01-22 21:39:38.380858: step: 784/470, loss: 0.0012267071288079023
2023-01-22 21:39:39.062019: step: 786/470, loss: 0.004911855328828096
2023-01-22 21:39:39.781193: step: 788/470, loss: 0.011736730113625526
2023-01-22 21:39:40.497709: step: 790/470, loss: 0.00543177267536521
2023-01-22 21:39:41.417266: step: 792/470, loss: 0.024822987616062164
2023-01-22 21:39:42.194972: step: 794/470, loss: 0.011290385387837887
2023-01-22 21:39:42.947727: step: 796/470, loss: 0.0001863948127720505
2023-01-22 21:39:43.762423: step: 798/470, loss: 0.0004333317338023335
2023-01-22 21:39:44.442948: step: 800/470, loss: 0.0003069574595429003
2023-01-22 21:39:45.177864: step: 802/470, loss: 0.001023111748509109
2023-01-22 21:39:45.944885: step: 804/470, loss: 0.002765122102573514
2023-01-22 21:39:46.642760: step: 806/470, loss: 0.0706728845834732
2023-01-22 21:39:47.474559: step: 808/470, loss: 0.001774181961081922
2023-01-22 21:39:48.223958: step: 810/470, loss: 0.0005504356813617051
2023-01-22 21:39:49.109592: step: 812/470, loss: 0.024189863353967667
2023-01-22 21:39:49.861157: step: 814/470, loss: 0.019002093002200127
2023-01-22 21:39:50.608611: step: 816/470, loss: 0.0006984842475503683
2023-01-22 21:39:51.299432: step: 818/470, loss: 0.0062248483300209045
2023-01-22 21:39:52.059018: step: 820/470, loss: 0.0006082578329369426
2023-01-22 21:39:52.859233: step: 822/470, loss: 0.0046651409938931465
2023-01-22 21:39:53.555248: step: 824/470, loss: 0.0008501000702381134
2023-01-22 21:39:54.215366: step: 826/470, loss: 0.008006863296031952
2023-01-22 21:39:54.943918: step: 828/470, loss: 0.0064245061948895454
2023-01-22 21:39:55.588693: step: 830/470, loss: 0.0001547907741041854
2023-01-22 21:39:56.252875: step: 832/470, loss: 0.0005969268968328834
2023-01-22 21:39:56.995557: step: 834/470, loss: 0.04945269599556923
2023-01-22 21:39:57.811674: step: 836/470, loss: 0.0009366283193230629
2023-01-22 21:39:58.581419: step: 838/470, loss: 0.0020159182604402304
2023-01-22 21:39:59.299594: step: 840/470, loss: 0.14137539267539978
2023-01-22 21:40:00.073648: step: 842/470, loss: 0.012791264802217484
2023-01-22 21:40:00.740371: step: 844/470, loss: 0.0020705685019493103
2023-01-22 21:40:01.529517: step: 846/470, loss: 0.006297953426837921
2023-01-22 21:40:02.317339: step: 848/470, loss: 0.01519366167485714
2023-01-22 21:40:03.117949: step: 850/470, loss: 0.001254754257388413
2023-01-22 21:40:03.945346: step: 852/470, loss: 0.00023478205548599362
2023-01-22 21:40:04.672736: step: 854/470, loss: 0.004564228001981974
2023-01-22 21:40:05.359614: step: 856/470, loss: 0.0048842052929103374
2023-01-22 21:40:06.045064: step: 858/470, loss: 0.020877385511994362
2023-01-22 21:40:06.801618: step: 860/470, loss: 0.18510141968727112
2023-01-22 21:40:07.573213: step: 862/470, loss: 0.011671909131109715
2023-01-22 21:40:08.318217: step: 864/470, loss: 0.02993558533489704
2023-01-22 21:40:08.985802: step: 866/470, loss: 0.0056413402780890465
2023-01-22 21:40:09.707602: step: 868/470, loss: 0.009789801202714443
2023-01-22 21:40:10.483198: step: 870/470, loss: 0.029731469228863716
2023-01-22 21:40:11.227259: step: 872/470, loss: 0.01826680265367031
2023-01-22 21:40:11.934067: step: 874/470, loss: 0.0003056666173506528
2023-01-22 21:40:12.714999: step: 876/470, loss: 0.007411897648125887
2023-01-22 21:40:13.586675: step: 878/470, loss: 0.00305022019892931
2023-01-22 21:40:14.272579: step: 880/470, loss: 5.6819328165147454e-05
2023-01-22 21:40:15.022273: step: 882/470, loss: 0.0015559961320832372
2023-01-22 21:40:15.796239: step: 884/470, loss: 0.03191646188497543
2023-01-22 21:40:16.631008: step: 886/470, loss: 0.00044945150148123503
2023-01-22 21:40:17.328045: step: 888/470, loss: 0.00564240338280797
2023-01-22 21:40:18.056013: step: 890/470, loss: 0.0024683803785592318
2023-01-22 21:40:18.794839: step: 892/470, loss: 0.025083282962441444
2023-01-22 21:40:19.524205: step: 894/470, loss: 0.007105534430593252
2023-01-22 21:40:20.200725: step: 896/470, loss: 0.0048616016283631325
2023-01-22 21:40:20.968086: step: 898/470, loss: 0.03480706736445427
2023-01-22 21:40:21.755136: step: 900/470, loss: 0.0010672089410945773
2023-01-22 21:40:22.553712: step: 902/470, loss: 0.006357176695019007
2023-01-22 21:40:23.296674: step: 904/470, loss: 0.002066312823444605
2023-01-22 21:40:23.997007: step: 906/470, loss: 9.631262946641073e-05
2023-01-22 21:40:24.712498: step: 908/470, loss: 0.001976320054382086
2023-01-22 21:40:25.641564: step: 910/470, loss: 0.00038530846359208226
2023-01-22 21:40:26.395724: step: 912/470, loss: 0.0007559002260677516
2023-01-22 21:40:27.128768: step: 914/470, loss: 0.004526065196841955
2023-01-22 21:40:27.898717: step: 916/470, loss: 0.0027980429586023092
2023-01-22 21:40:28.663583: step: 918/470, loss: 0.001787687069736421
2023-01-22 21:40:29.389382: step: 920/470, loss: 0.0017783924704417586
2023-01-22 21:40:30.119951: step: 922/470, loss: 0.010765299201011658
2023-01-22 21:40:30.996712: step: 924/470, loss: 0.005860594101250172
2023-01-22 21:40:31.753640: step: 926/470, loss: 0.009120491333305836
2023-01-22 21:40:32.576263: step: 928/470, loss: 0.051197804510593414
2023-01-22 21:40:33.486117: step: 930/470, loss: 0.1064954325556755
2023-01-22 21:40:34.208495: step: 932/470, loss: 0.008499711751937866
2023-01-22 21:40:34.922346: step: 934/470, loss: 0.03420386090874672
2023-01-22 21:40:35.697536: step: 936/470, loss: 0.001930433209054172
2023-01-22 21:40:36.434320: step: 938/470, loss: 0.06531298905611038
2023-01-22 21:40:37.106314: step: 940/470, loss: 0.048529766499996185
2023-01-22 21:40:37.696701: step: 942/470, loss: 0.0032194419763982296
==================================================
Loss: 0.043
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28993341570565623, 'r': 0.3339460784313726, 'f1': 0.31038727219282775}, 'combined': 0.228706411089452, 'epoch': 36}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3398487305486143, 'r': 0.36958549447161804, 'f1': 0.35409388691891547}, 'combined': 0.24663255805297596, 'epoch': 36}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2865501638698008, 'r': 0.3365741013954587, 'f1': 0.30955419098674813}, 'combined': 0.22809256177970913, 'epoch': 36}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3422391101402614, 'r': 0.3705396519403215, 'f1': 0.35582755126309723}, 'combined': 0.24784008545688366, 'epoch': 36}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26583015267175575, 'r': 0.330396110056926, 'f1': 0.2946171742808799}, 'combined': 0.21708633894380625, 'epoch': 36}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33340920520038964, 'r': 0.3850235148516038, 'f1': 0.35736229847895395}, 'combined': 0.24890906361718187, 'epoch': 36}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20550351288056204, 'r': 0.3581632653061224, 'f1': 0.2611607142857143}, 'combined': 0.17410714285714285, 'epoch': 36}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.23469387755102042, 'r': 0.5, 'f1': 0.3194444444444444}, 'combined': 0.1597222222222222, 'epoch': 36}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.40625, 'r': 0.33620689655172414, 'f1': 0.36792452830188677}, 'combined': 0.2452830188679245, 'epoch': 36}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 37
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 21:43:15.133072: step: 2/470, loss: 0.0016411297256127
2023-01-22 21:43:15.978913: step: 4/470, loss: 0.016578450798988342
2023-01-22 21:43:16.725884: step: 6/470, loss: 0.00037532756687141955
2023-01-22 21:43:17.430641: step: 8/470, loss: 0.0027909998316317797
2023-01-22 21:43:18.137218: step: 10/470, loss: 0.08526574820280075
2023-01-22 21:43:18.849801: step: 12/470, loss: 0.00015779869863763452
2023-01-22 21:43:19.565718: step: 14/470, loss: 0.0017313596326857805
2023-01-22 21:43:20.309257: step: 16/470, loss: 0.00044223369332030416
2023-01-22 21:43:21.060148: step: 18/470, loss: 0.06428509205579758
2023-01-22 21:43:21.849069: step: 20/470, loss: 0.00421540392562747
2023-01-22 21:43:22.568219: step: 22/470, loss: 2.9487378924386576e-05
2023-01-22 21:43:23.389818: step: 24/470, loss: 0.0027779489755630493
2023-01-22 21:43:24.063962: step: 26/470, loss: 0.00016546357073821127
2023-01-22 21:43:24.724674: step: 28/470, loss: 0.006498188711702824
2023-01-22 21:43:25.440365: step: 30/470, loss: 0.0014709843089804053
2023-01-22 21:43:26.213039: step: 32/470, loss: 0.0002651438699103892
2023-01-22 21:43:26.913838: step: 34/470, loss: 0.7554433941841125
2023-01-22 21:43:27.588387: step: 36/470, loss: 0.00971017125993967
2023-01-22 21:43:28.320670: step: 38/470, loss: 0.002934138523414731
2023-01-22 21:43:28.992011: step: 40/470, loss: 0.00081524538109079
2023-01-22 21:43:29.636114: step: 42/470, loss: 0.003965584561228752
2023-01-22 21:43:30.378601: step: 44/470, loss: 0.26607316732406616
2023-01-22 21:43:31.110733: step: 46/470, loss: 0.37619858980178833
2023-01-22 21:43:31.923375: step: 48/470, loss: 0.20665885508060455
2023-01-22 21:43:32.688608: step: 50/470, loss: 0.0007290860521607101
2023-01-22 21:43:33.440657: step: 52/470, loss: 0.032187577337026596
2023-01-22 21:43:34.141051: step: 54/470, loss: 0.006359893828630447
2023-01-22 21:43:34.889511: step: 56/470, loss: 0.000407334475312382
2023-01-22 21:43:35.658860: step: 58/470, loss: 0.004570923279970884
2023-01-22 21:43:36.364690: step: 60/470, loss: 0.02728239819407463
2023-01-22 21:43:37.204456: step: 62/470, loss: 0.17052745819091797
2023-01-22 21:43:37.935717: step: 64/470, loss: 0.007626243866980076
2023-01-22 21:43:38.646567: step: 66/470, loss: 0.0001989319862332195
2023-01-22 21:43:39.397143: step: 68/470, loss: 0.011886470019817352
2023-01-22 21:43:40.065409: step: 70/470, loss: 0.0021775467321276665
2023-01-22 21:43:40.814799: step: 72/470, loss: 0.0016382178291678429
2023-01-22 21:43:41.601456: step: 74/470, loss: 0.005465012509375811
2023-01-22 21:43:42.395121: step: 76/470, loss: 0.004183304961770773
2023-01-22 21:43:43.114759: step: 78/470, loss: 0.029515385627746582
2023-01-22 21:43:43.873895: step: 80/470, loss: 0.0003540659963618964
2023-01-22 21:43:44.579268: step: 82/470, loss: 0.00043878774158656597
2023-01-22 21:43:45.348493: step: 84/470, loss: 0.0017511650221422315
2023-01-22 21:43:46.068595: step: 86/470, loss: 0.0043872627429664135
2023-01-22 21:43:46.838712: step: 88/470, loss: 0.4596310257911682
2023-01-22 21:43:47.542455: step: 90/470, loss: 0.006851941347122192
2023-01-22 21:43:48.258141: step: 92/470, loss: 0.015803921967744827
2023-01-22 21:43:49.015410: step: 94/470, loss: 0.014629622921347618
2023-01-22 21:43:49.861854: step: 96/470, loss: 0.01233682967722416
2023-01-22 21:43:50.654022: step: 98/470, loss: 0.0026958484668284655
2023-01-22 21:43:51.366803: step: 100/470, loss: 0.005636794026941061
2023-01-22 21:43:52.081117: step: 102/470, loss: 0.00012584813521243632
2023-01-22 21:43:52.858836: step: 104/470, loss: 0.006042279303073883
2023-01-22 21:43:53.514666: step: 106/470, loss: 5.00088935950771e-05
2023-01-22 21:43:54.221418: step: 108/470, loss: 0.0024630522821098566
2023-01-22 21:43:54.982515: step: 110/470, loss: 0.045400720089673996
2023-01-22 21:43:55.701905: step: 112/470, loss: 0.006315591745078564
2023-01-22 21:43:56.459744: step: 114/470, loss: 3.898659269907512e-05
2023-01-22 21:43:57.170533: step: 116/470, loss: 0.0008913876954466105
2023-01-22 21:43:57.919173: step: 118/470, loss: 0.007831503637135029
2023-01-22 21:43:58.713220: step: 120/470, loss: 0.0005501203122548759
2023-01-22 21:43:59.392128: step: 122/470, loss: 0.06952209770679474
2023-01-22 21:44:00.168535: step: 124/470, loss: 0.002455966779962182
2023-01-22 21:44:00.907309: step: 126/470, loss: 0.018089069053530693
2023-01-22 21:44:01.649207: step: 128/470, loss: 0.0002797857450786978
2023-01-22 21:44:02.376294: step: 130/470, loss: 0.0014697941951453686
2023-01-22 21:44:03.150900: step: 132/470, loss: 0.027464300394058228
2023-01-22 21:44:03.908207: step: 134/470, loss: 0.0019714029040187597
2023-01-22 21:44:04.644689: step: 136/470, loss: 0.00593600096181035
2023-01-22 21:44:05.361757: step: 138/470, loss: 0.008636260405182838
2023-01-22 21:44:06.104468: step: 140/470, loss: 0.021064892411231995
2023-01-22 21:44:06.834812: step: 142/470, loss: 2.5779121642699465e-05
2023-01-22 21:44:07.592381: step: 144/470, loss: 1.2797374438378029e-05
2023-01-22 21:44:08.370005: step: 146/470, loss: 0.05897778272628784
2023-01-22 21:44:09.208449: step: 148/470, loss: 0.016995619982481003
2023-01-22 21:44:09.927718: step: 150/470, loss: 0.0013439225731417537
2023-01-22 21:44:10.630963: step: 152/470, loss: 0.056216444820165634
2023-01-22 21:44:11.310297: step: 154/470, loss: 0.0074424357153475285
2023-01-22 21:44:12.053721: step: 156/470, loss: 0.2076435685157776
2023-01-22 21:44:12.772789: step: 158/470, loss: 0.0012701174709945917
2023-01-22 21:44:13.504585: step: 160/470, loss: 0.00368306296877563
2023-01-22 21:44:14.343809: step: 162/470, loss: 0.05626552179455757
2023-01-22 21:44:15.068624: step: 164/470, loss: 0.01470974925905466
2023-01-22 21:44:15.739367: step: 166/470, loss: 0.1756785660982132
2023-01-22 21:44:16.424957: step: 168/470, loss: 0.0030123700853437185
2023-01-22 21:44:17.141012: step: 170/470, loss: 0.002067750785499811
2023-01-22 21:44:17.897785: step: 172/470, loss: 3.085620846832171e-05
2023-01-22 21:44:18.707095: step: 174/470, loss: 0.014414145611226559
2023-01-22 21:44:19.468182: step: 176/470, loss: 0.03165549039840698
2023-01-22 21:44:20.227190: step: 178/470, loss: 0.014181282371282578
2023-01-22 21:44:20.928340: step: 180/470, loss: 1.0798722505569458
2023-01-22 21:44:21.585433: step: 182/470, loss: 0.0001561841054353863
2023-01-22 21:44:22.256834: step: 184/470, loss: 0.015310071408748627
2023-01-22 21:44:23.245332: step: 186/470, loss: 0.022418607026338577
2023-01-22 21:44:23.987651: step: 188/470, loss: 0.07125722616910934
2023-01-22 21:44:24.758757: step: 190/470, loss: 0.013494039885699749
2023-01-22 21:44:25.493599: step: 192/470, loss: 0.015244124457240105
2023-01-22 21:44:26.190996: step: 194/470, loss: 0.01948845013976097
2023-01-22 21:44:26.888865: step: 196/470, loss: 0.00848582573235035
2023-01-22 21:44:27.617819: step: 198/470, loss: 0.049408018589019775
2023-01-22 21:44:28.347977: step: 200/470, loss: 0.003815028350800276
2023-01-22 21:44:29.089449: step: 202/470, loss: 0.05077585205435753
2023-01-22 21:44:29.911654: step: 204/470, loss: 0.0009153272258117795
2023-01-22 21:44:30.683667: step: 206/470, loss: 0.00020322480122558773
2023-01-22 21:44:31.463363: step: 208/470, loss: 0.00020252318063285202
2023-01-22 21:44:32.235365: step: 210/470, loss: 0.0242539644241333
2023-01-22 21:44:33.008172: step: 212/470, loss: 0.029064660891890526
2023-01-22 21:44:33.683146: step: 214/470, loss: 0.0016236408846452832
2023-01-22 21:44:34.404324: step: 216/470, loss: 0.12475449591875076
2023-01-22 21:44:35.040527: step: 218/470, loss: 0.0002371451264480129
2023-01-22 21:44:35.762168: step: 220/470, loss: 0.011168582364916801
2023-01-22 21:44:36.477697: step: 222/470, loss: 0.005518828984349966
2023-01-22 21:44:37.157890: step: 224/470, loss: 0.010224402882158756
2023-01-22 21:44:37.950632: step: 226/470, loss: 0.020215503871440887
2023-01-22 21:44:38.726418: step: 228/470, loss: 0.0007321978337131441
2023-01-22 21:44:39.434707: step: 230/470, loss: 2.0057850633747876e-05
2023-01-22 21:44:40.226801: step: 232/470, loss: 0.04708104953169823
2023-01-22 21:44:40.881253: step: 234/470, loss: 0.0007134419283829629
2023-01-22 21:44:41.593250: step: 236/470, loss: 0.7298058271408081
2023-01-22 21:44:42.254081: step: 238/470, loss: 0.007942304015159607
2023-01-22 21:44:42.979588: step: 240/470, loss: 0.00015898249694146216
2023-01-22 21:44:43.721521: step: 242/470, loss: 0.023740533739328384
2023-01-22 21:44:44.581737: step: 244/470, loss: 0.004855903331190348
2023-01-22 21:44:45.260756: step: 246/470, loss: 0.0001292641827603802
2023-01-22 21:44:46.033303: step: 248/470, loss: 0.0025803775060921907
2023-01-22 21:44:46.751403: step: 250/470, loss: 0.5248620510101318
2023-01-22 21:44:47.497437: step: 252/470, loss: 0.010610873810946941
2023-01-22 21:44:48.167270: step: 254/470, loss: 0.02230040729045868
2023-01-22 21:44:48.883634: step: 256/470, loss: 0.023776421323418617
2023-01-22 21:44:49.599887: step: 258/470, loss: 0.0019985968247056007
2023-01-22 21:44:50.385514: step: 260/470, loss: 0.07004007697105408
2023-01-22 21:44:51.182517: step: 262/470, loss: 0.0001779235026333481
2023-01-22 21:44:51.921352: step: 264/470, loss: 0.00566717516630888
2023-01-22 21:44:52.575603: step: 266/470, loss: 0.00029370139236561954
2023-01-22 21:44:53.314186: step: 268/470, loss: 0.0012920513981953263
2023-01-22 21:44:54.058712: step: 270/470, loss: 0.001267312210984528
2023-01-22 21:44:54.740756: step: 272/470, loss: 0.011984679847955704
2023-01-22 21:44:55.395434: step: 274/470, loss: 0.018051162362098694
2023-01-22 21:44:56.110867: step: 276/470, loss: 0.00023922794207464904
2023-01-22 21:44:56.859749: step: 278/470, loss: 0.016359608620405197
2023-01-22 21:44:57.547787: step: 280/470, loss: 0.011056328192353249
2023-01-22 21:44:58.268195: step: 282/470, loss: 0.01704174093902111
2023-01-22 21:44:58.975345: step: 284/470, loss: 0.0023452085442841053
2023-01-22 21:44:59.636022: step: 286/470, loss: 0.0006594705628231168
2023-01-22 21:45:00.411807: step: 288/470, loss: 0.00027242524083703756
2023-01-22 21:45:01.181366: step: 290/470, loss: 0.006094738841056824
2023-01-22 21:45:01.888713: step: 292/470, loss: 0.0011509230826050043
2023-01-22 21:45:02.665263: step: 294/470, loss: 0.008679484948515892
2023-01-22 21:45:03.434155: step: 296/470, loss: 0.027196824550628662
2023-01-22 21:45:04.091101: step: 298/470, loss: 3.1080591725185513e-05
2023-01-22 21:45:04.853779: step: 300/470, loss: 0.001202079583890736
2023-01-22 21:45:05.571462: step: 302/470, loss: 0.013225025497376919
2023-01-22 21:45:06.353997: step: 304/470, loss: 0.015826869755983353
2023-01-22 21:45:07.015597: step: 306/470, loss: 0.0002728473045863211
2023-01-22 21:45:07.811844: step: 308/470, loss: 0.0064653316512703896
2023-01-22 21:45:08.585512: step: 310/470, loss: 0.005568230524659157
2023-01-22 21:45:09.373621: step: 312/470, loss: 8.150991925504059e-05
2023-01-22 21:45:10.143556: step: 314/470, loss: 0.005682247690856457
2023-01-22 21:45:10.830759: step: 316/470, loss: 0.0011145909084007144
2023-01-22 21:45:11.537127: step: 318/470, loss: 0.0007300268625840545
2023-01-22 21:45:12.253318: step: 320/470, loss: 0.00024394701176788658
2023-01-22 21:45:12.977197: step: 322/470, loss: 0.0013543710811063647
2023-01-22 21:45:13.746465: step: 324/470, loss: 0.015326937660574913
2023-01-22 21:45:14.444294: step: 326/470, loss: 0.004613461904227734
2023-01-22 21:45:15.132980: step: 328/470, loss: 1.1873652510985266e-05
2023-01-22 21:45:15.866951: step: 330/470, loss: 0.0037322877906262875
2023-01-22 21:45:16.549502: step: 332/470, loss: 0.001422520843334496
2023-01-22 21:45:17.249302: step: 334/470, loss: 0.003986767493188381
2023-01-22 21:45:17.966943: step: 336/470, loss: 0.0021966679487377405
2023-01-22 21:45:18.735268: step: 338/470, loss: 0.03222150355577469
2023-01-22 21:45:19.414365: step: 340/470, loss: 0.0010147334542125463
2023-01-22 21:45:20.166319: step: 342/470, loss: 0.010336131788790226
2023-01-22 21:45:20.870212: step: 344/470, loss: 0.006794884335249662
2023-01-22 21:45:21.617983: step: 346/470, loss: 0.009388666599988937
2023-01-22 21:45:22.324582: step: 348/470, loss: 0.004102275241166353
2023-01-22 21:45:23.103302: step: 350/470, loss: 0.00270704529248178
2023-01-22 21:45:23.787184: step: 352/470, loss: 2.3283802875084803e-05
2023-01-22 21:45:24.464303: step: 354/470, loss: 0.000149372877785936
2023-01-22 21:45:25.232191: step: 356/470, loss: 0.015503468923270702
2023-01-22 21:45:25.894437: step: 358/470, loss: 0.013661712408065796
2023-01-22 21:45:26.639607: step: 360/470, loss: 0.029292738065123558
2023-01-22 21:45:27.384801: step: 362/470, loss: 0.07505685836076736
2023-01-22 21:45:28.157527: step: 364/470, loss: 0.005268405191600323
2023-01-22 21:45:28.873845: step: 366/470, loss: 4.039578925585374e-05
2023-01-22 21:45:29.795023: step: 368/470, loss: 0.040998730808496475
2023-01-22 21:45:30.556791: step: 370/470, loss: 0.010451802052557468
2023-01-22 21:45:31.392099: step: 372/470, loss: 0.2076258659362793
2023-01-22 21:45:32.129352: step: 374/470, loss: 0.010212671011686325
2023-01-22 21:45:32.778406: step: 376/470, loss: 0.00308050075545907
2023-01-22 21:45:33.481534: step: 378/470, loss: 2.2757983207702637
2023-01-22 21:45:34.218004: step: 380/470, loss: 0.08818937093019485
2023-01-22 21:45:34.973949: step: 382/470, loss: 0.2878647744655609
2023-01-22 21:45:35.676691: step: 384/470, loss: 0.0031312655191868544
2023-01-22 21:45:36.386748: step: 386/470, loss: 0.002897688653320074
2023-01-22 21:45:37.143840: step: 388/470, loss: 0.02370820753276348
2023-01-22 21:45:37.910404: step: 390/470, loss: 0.005385119933634996
2023-01-22 21:45:38.662461: step: 392/470, loss: 0.002497171750292182
2023-01-22 21:45:39.342901: step: 394/470, loss: 0.006736780051141977
2023-01-22 21:45:40.021334: step: 396/470, loss: 0.0072611235082149506
2023-01-22 21:45:40.730582: step: 398/470, loss: 0.0004087547422386706
2023-01-22 21:45:41.443792: step: 400/470, loss: 0.00022048353275749832
2023-01-22 21:45:42.142307: step: 402/470, loss: 0.0018256985349580646
2023-01-22 21:45:42.809599: step: 404/470, loss: 0.0001288076746277511
2023-01-22 21:45:43.496006: step: 406/470, loss: 0.004111488815397024
2023-01-22 21:45:44.235341: step: 408/470, loss: 0.0005288118845783174
2023-01-22 21:45:44.988722: step: 410/470, loss: 0.0015056623378768563
2023-01-22 21:45:45.855560: step: 412/470, loss: 0.10391915589570999
2023-01-22 21:45:46.567906: step: 414/470, loss: 0.00016978340863715857
2023-01-22 21:45:47.373526: step: 416/470, loss: 0.006940767168998718
2023-01-22 21:45:48.023716: step: 418/470, loss: 0.4740176498889923
2023-01-22 21:45:48.713490: step: 420/470, loss: 0.00903422199189663
2023-01-22 21:45:49.456394: step: 422/470, loss: 1.154094934463501
2023-01-22 21:45:50.237894: step: 424/470, loss: 0.0007773156394250691
2023-01-22 21:45:51.008407: step: 426/470, loss: 0.00015792468911968172
2023-01-22 21:45:51.758305: step: 428/470, loss: 0.0006084730848670006
2023-01-22 21:45:52.487639: step: 430/470, loss: 0.003304409794509411
2023-01-22 21:45:53.283023: step: 432/470, loss: 0.0006498509901575744
2023-01-22 21:45:53.941010: step: 434/470, loss: 0.014365673996508121
2023-01-22 21:45:54.707361: step: 436/470, loss: 0.0002987508487422019
2023-01-22 21:45:55.557117: step: 438/470, loss: 0.03105132095515728
2023-01-22 21:45:56.199843: step: 440/470, loss: 5.6159387895604596e-05
2023-01-22 21:45:57.044607: step: 442/470, loss: 0.0020124197471886873
2023-01-22 21:45:57.711751: step: 444/470, loss: 0.002125130034983158
2023-01-22 21:45:58.420214: step: 446/470, loss: 0.0010889448458328843
2023-01-22 21:45:59.124344: step: 448/470, loss: 3.070883030886762e-05
2023-01-22 21:45:59.795978: step: 450/470, loss: 0.005335522815585136
2023-01-22 21:46:00.583975: step: 452/470, loss: 0.01190522313117981
2023-01-22 21:46:01.289756: step: 454/470, loss: 0.00037295298534445465
2023-01-22 21:46:01.988671: step: 456/470, loss: 0.005229064263403416
2023-01-22 21:46:02.737699: step: 458/470, loss: 0.0013408676022663713
2023-01-22 21:46:03.527667: step: 460/470, loss: 0.0023357283789664507
2023-01-22 21:46:04.252630: step: 462/470, loss: 0.0028918476309627295
2023-01-22 21:46:05.027216: step: 464/470, loss: 0.0005529711488634348
2023-01-22 21:46:05.738825: step: 466/470, loss: 0.00048034434439614415
2023-01-22 21:46:06.515284: step: 468/470, loss: 1.2877992048743181e-05
2023-01-22 21:46:07.286651: step: 470/470, loss: 0.09141544997692108
2023-01-22 21:46:08.048819: step: 472/470, loss: 0.15473003685474396
2023-01-22 21:46:08.850272: step: 474/470, loss: 0.0005995671381242573
2023-01-22 21:46:09.538000: step: 476/470, loss: 0.00010133895557373762
2023-01-22 21:46:10.297674: step: 478/470, loss: 0.006271105259656906
2023-01-22 21:46:11.054285: step: 480/470, loss: 0.02504108101129532
2023-01-22 21:46:11.831177: step: 482/470, loss: 0.0013932195724919438
2023-01-22 21:46:12.625355: step: 484/470, loss: 0.0003886119229719043
2023-01-22 21:46:13.342950: step: 486/470, loss: 0.00025422993348911405
2023-01-22 21:46:14.097226: step: 488/470, loss: 0.0017747258534654975
2023-01-22 21:46:14.774768: step: 490/470, loss: 0.016103271394968033
2023-01-22 21:46:15.439728: step: 492/470, loss: 0.003346665995195508
2023-01-22 21:46:16.202954: step: 494/470, loss: 0.00019028606766369194
2023-01-22 21:46:16.868772: step: 496/470, loss: 6.881119043100625e-05
2023-01-22 21:46:17.645314: step: 498/470, loss: 0.000268188159679994
2023-01-22 21:46:18.407201: step: 500/470, loss: 0.0006737832445651293
2023-01-22 21:46:19.271940: step: 502/470, loss: 0.007682368624955416
2023-01-22 21:46:19.953089: step: 504/470, loss: 1.9424080164753832e-05
2023-01-22 21:46:20.694469: step: 506/470, loss: 7.247896428452805e-05
2023-01-22 21:46:21.379479: step: 508/470, loss: 0.006508438847959042
2023-01-22 21:46:22.132220: step: 510/470, loss: 0.008590683341026306
2023-01-22 21:46:22.863760: step: 512/470, loss: 0.019543835893273354
2023-01-22 21:46:23.631355: step: 514/470, loss: 0.30058515071868896
2023-01-22 21:46:24.338730: step: 516/470, loss: 2.5567267584847286e-05
2023-01-22 21:46:25.052767: step: 518/470, loss: 0.022811856120824814
2023-01-22 21:46:25.851333: step: 520/470, loss: 0.00019056579913012683
2023-01-22 21:46:26.566002: step: 522/470, loss: 0.006042586639523506
2023-01-22 21:46:27.217778: step: 524/470, loss: 0.009766626171767712
2023-01-22 21:46:27.952087: step: 526/470, loss: 0.0004236418753862381
2023-01-22 21:46:28.628271: step: 528/470, loss: 0.0460224524140358
2023-01-22 21:46:29.374620: step: 530/470, loss: 0.03648354113101959
2023-01-22 21:46:30.172882: step: 532/470, loss: 0.026953857392072678
2023-01-22 21:46:31.002017: step: 534/470, loss: 0.001078708446584642
2023-01-22 21:46:31.696901: step: 536/470, loss: 0.0006425505271181464
2023-01-22 21:46:32.371660: step: 538/470, loss: 0.013254445046186447
2023-01-22 21:46:33.113448: step: 540/470, loss: 0.005868022330105305
2023-01-22 21:46:33.845451: step: 542/470, loss: 0.000866345944814384
2023-01-22 21:46:34.533639: step: 544/470, loss: 0.019351843744516373
2023-01-22 21:46:35.271111: step: 546/470, loss: 0.0006408991175703704
2023-01-22 21:46:35.973525: step: 548/470, loss: 0.007142396178096533
2023-01-22 21:46:36.653191: step: 550/470, loss: 0.0009534017299301922
2023-01-22 21:46:37.400377: step: 552/470, loss: 0.0083243353292346
2023-01-22 21:46:38.084361: step: 554/470, loss: 0.007734335493296385
2023-01-22 21:46:38.837044: step: 556/470, loss: 0.0021097231656312943
2023-01-22 21:46:39.632593: step: 558/470, loss: 0.10651249438524246
2023-01-22 21:46:40.428787: step: 560/470, loss: 0.06708988547325134
2023-01-22 21:46:41.133602: step: 562/470, loss: 0.012138977646827698
2023-01-22 21:46:41.837721: step: 564/470, loss: 0.0041181351989507675
2023-01-22 21:46:42.568257: step: 566/470, loss: 0.004253920167684555
2023-01-22 21:46:43.296467: step: 568/470, loss: 0.009514007717370987
2023-01-22 21:46:44.090934: step: 570/470, loss: 1.9646420696517453e-05
2023-01-22 21:46:44.837812: step: 572/470, loss: 0.0004975633346475661
2023-01-22 21:46:45.508686: step: 574/470, loss: 1.6465276075905422e-06
2023-01-22 21:46:46.172475: step: 576/470, loss: 0.03554369881749153
2023-01-22 21:46:46.818098: step: 578/470, loss: 0.0003723879635799676
2023-01-22 21:46:47.613720: step: 580/470, loss: 0.0021262504160404205
2023-01-22 21:46:48.391360: step: 582/470, loss: 0.006091665010899305
2023-01-22 21:46:49.161718: step: 584/470, loss: 0.07040276378393173
2023-01-22 21:46:49.912857: step: 586/470, loss: 0.007872075773775578
2023-01-22 21:46:50.601480: step: 588/470, loss: 0.010333622805774212
2023-01-22 21:46:51.314466: step: 590/470, loss: 0.003944714087992907
2023-01-22 21:46:52.087786: step: 592/470, loss: 0.08302487432956696
2023-01-22 21:46:52.870942: step: 594/470, loss: 0.002667823573574424
2023-01-22 21:46:53.659394: step: 596/470, loss: 0.0011115572415292263
2023-01-22 21:46:54.438685: step: 598/470, loss: 0.0013725311728194356
2023-01-22 21:46:55.128935: step: 600/470, loss: 0.01085622701793909
2023-01-22 21:46:55.852858: step: 602/470, loss: 0.011929565109312534
2023-01-22 21:46:56.617030: step: 604/470, loss: 0.5936955809593201
2023-01-22 21:46:57.347255: step: 606/470, loss: 0.0015288189752027392
2023-01-22 21:46:58.064052: step: 608/470, loss: 0.004490552004426718
2023-01-22 21:46:58.830010: step: 610/470, loss: 0.01219299528747797
2023-01-22 21:46:59.565925: step: 612/470, loss: 0.004125348757952452
2023-01-22 21:47:00.297154: step: 614/470, loss: 0.0011770040728151798
2023-01-22 21:47:01.038175: step: 616/470, loss: 0.0035097640939056873
2023-01-22 21:47:01.825543: step: 618/470, loss: 0.04082076996564865
2023-01-22 21:47:02.486919: step: 620/470, loss: 0.04343542456626892
2023-01-22 21:47:03.250312: step: 622/470, loss: 0.0005687833181582391
2023-01-22 21:47:04.044103: step: 624/470, loss: 0.02319457195699215
2023-01-22 21:47:04.819449: step: 626/470, loss: 0.020851243287324905
2023-01-22 21:47:05.609389: step: 628/470, loss: 0.0018202860374003649
2023-01-22 21:47:06.321043: step: 630/470, loss: 0.006153845693916082
2023-01-22 21:47:07.031215: step: 632/470, loss: 0.004557922948151827
2023-01-22 21:47:07.816636: step: 634/470, loss: 0.018611159175634384
2023-01-22 21:47:08.539384: step: 636/470, loss: 0.0369689054787159
2023-01-22 21:47:09.307985: step: 638/470, loss: 0.002355735981836915
2023-01-22 21:47:10.109840: step: 640/470, loss: 0.0005931655177846551
2023-01-22 21:47:10.815626: step: 642/470, loss: 0.03275495022535324
2023-01-22 21:47:11.503882: step: 644/470, loss: 0.0019692745991051197
2023-01-22 21:47:12.244616: step: 646/470, loss: 0.0005796861951239407
2023-01-22 21:47:13.042056: step: 648/470, loss: 0.0003035140107385814
2023-01-22 21:47:13.894533: step: 650/470, loss: 0.00021470840147230774
2023-01-22 21:47:14.600897: step: 652/470, loss: 0.010880122892558575
2023-01-22 21:47:15.337569: step: 654/470, loss: 2.0693125406978652e-05
2023-01-22 21:47:16.042264: step: 656/470, loss: 0.0021833537612110376
2023-01-22 21:47:16.777862: step: 658/470, loss: 0.010350065305829048
2023-01-22 21:47:17.514943: step: 660/470, loss: 0.00021858404215890914
2023-01-22 21:47:18.197408: step: 662/470, loss: 0.000333769858116284
2023-01-22 21:47:18.943228: step: 664/470, loss: 0.004476209171116352
2023-01-22 21:47:19.737498: step: 666/470, loss: 0.01990194246172905
2023-01-22 21:47:20.492384: step: 668/470, loss: 0.09436644613742828
2023-01-22 21:47:21.199508: step: 670/470, loss: 0.00025006639771163464
2023-01-22 21:47:21.953326: step: 672/470, loss: 0.050850946456193924
2023-01-22 21:47:22.625561: step: 674/470, loss: 0.0038154199719429016
2023-01-22 21:47:23.371283: step: 676/470, loss: 0.0026396666653454304
2023-01-22 21:47:24.136011: step: 678/470, loss: 0.02135513350367546
2023-01-22 21:47:24.854973: step: 680/470, loss: 0.001105017145164311
2023-01-22 21:47:25.693899: step: 682/470, loss: 0.009239214472472668
2023-01-22 21:47:26.468820: step: 684/470, loss: 0.11062158644199371
2023-01-22 21:47:27.198944: step: 686/470, loss: 7.758984429528937e-05
2023-01-22 21:47:28.007110: step: 688/470, loss: 0.007189847994595766
2023-01-22 21:47:28.781117: step: 690/470, loss: 0.004308292642235756
2023-01-22 21:47:29.430512: step: 692/470, loss: 0.0004358371370472014
2023-01-22 21:47:30.112113: step: 694/470, loss: 0.2612048089504242
2023-01-22 21:47:30.855325: step: 696/470, loss: 9.558172314427793e-05
2023-01-22 21:47:31.533498: step: 698/470, loss: 0.00466720899567008
2023-01-22 21:47:32.313664: step: 700/470, loss: 0.0009645888931117952
2023-01-22 21:47:33.127251: step: 702/470, loss: 0.009687711484730244
2023-01-22 21:47:33.902002: step: 704/470, loss: 0.03733493387699127
2023-01-22 21:47:34.629776: step: 706/470, loss: 0.0338343009352684
2023-01-22 21:47:35.439833: step: 708/470, loss: 0.0013095543254166842
2023-01-22 21:47:36.173390: step: 710/470, loss: 0.0019843606278300285
2023-01-22 21:47:36.930762: step: 712/470, loss: 0.0003942087641917169
2023-01-22 21:47:37.693289: step: 714/470, loss: 0.004477455280721188
2023-01-22 21:47:38.466381: step: 716/470, loss: 0.00019188599253538996
2023-01-22 21:47:39.177800: step: 718/470, loss: 0.012036411091685295
2023-01-22 21:47:39.824335: step: 720/470, loss: 0.0012441710568964481
2023-01-22 21:47:40.518102: step: 722/470, loss: 0.02268451265990734
2023-01-22 21:47:41.271422: step: 724/470, loss: 0.04499243572354317
2023-01-22 21:47:42.012016: step: 726/470, loss: 0.000995938084088266
2023-01-22 21:47:42.815959: step: 728/470, loss: 0.002610167022794485
2023-01-22 21:47:43.548117: step: 730/470, loss: 0.001554196118377149
2023-01-22 21:47:44.260087: step: 732/470, loss: 0.0007086883997544646
2023-01-22 21:47:44.961438: step: 734/470, loss: 0.00042572562233544886
2023-01-22 21:47:45.683877: step: 736/470, loss: 0.004255416337400675
2023-01-22 21:47:46.402620: step: 738/470, loss: 0.006742789875715971
2023-01-22 21:47:47.058222: step: 740/470, loss: 0.0009496554266661406
2023-01-22 21:47:47.753251: step: 742/470, loss: 0.001538438955321908
2023-01-22 21:47:48.456568: step: 744/470, loss: 0.002146479906514287
2023-01-22 21:47:49.161877: step: 746/470, loss: 0.00030127508216537535
2023-01-22 21:47:49.809818: step: 748/470, loss: 4.851120593230007e-06
2023-01-22 21:47:50.531558: step: 750/470, loss: 0.22810763120651245
2023-01-22 21:47:51.276623: step: 752/470, loss: 0.0003023869649041444
2023-01-22 21:47:52.045323: step: 754/470, loss: 0.0018333548214286566
2023-01-22 21:47:52.896914: step: 756/470, loss: 0.012261569499969482
2023-01-22 21:47:53.592570: step: 758/470, loss: 3.2106316211866215e-05
2023-01-22 21:47:54.281508: step: 760/470, loss: 0.0017151250503957272
2023-01-22 21:47:55.002851: step: 762/470, loss: 0.08843082189559937
2023-01-22 21:47:55.758560: step: 764/470, loss: 0.0009025583858601749
2023-01-22 21:47:56.508742: step: 766/470, loss: 0.03692952170968056
2023-01-22 21:47:57.259696: step: 768/470, loss: 0.0004031884600408375
2023-01-22 21:47:58.011212: step: 770/470, loss: 0.06433983892202377
2023-01-22 21:47:58.837521: step: 772/470, loss: 0.013428415171802044
2023-01-22 21:47:59.665466: step: 774/470, loss: 0.00031575208413414657
2023-01-22 21:48:00.389616: step: 776/470, loss: 0.00019189363229088485
2023-01-22 21:48:01.086369: step: 778/470, loss: 0.0002521543647162616
2023-01-22 21:48:01.880927: step: 780/470, loss: 0.012361546978354454
2023-01-22 21:48:02.537410: step: 782/470, loss: 0.0014749522088095546
2023-01-22 21:48:03.387625: step: 784/470, loss: 0.004103075712919235
2023-01-22 21:48:04.161790: step: 786/470, loss: 0.015317887999117374
2023-01-22 21:48:04.891712: step: 788/470, loss: 0.007157180458307266
2023-01-22 21:48:05.608599: step: 790/470, loss: 0.03482293710112572
2023-01-22 21:48:06.328824: step: 792/470, loss: 0.0006050001247785985
2023-01-22 21:48:07.065260: step: 794/470, loss: 0.006788891274482012
2023-01-22 21:48:07.876976: step: 796/470, loss: 0.12752631306648254
2023-01-22 21:48:08.589658: step: 798/470, loss: 0.5755633115768433
2023-01-22 21:48:09.309571: step: 800/470, loss: 0.004557878710329533
2023-01-22 21:48:10.126688: step: 802/470, loss: 0.0018064269097521901
2023-01-22 21:48:10.860993: step: 804/470, loss: 0.09993268549442291
2023-01-22 21:48:11.547066: step: 806/470, loss: 0.0003193170123267919
2023-01-22 21:48:12.322005: step: 808/470, loss: 0.031694598495960236
2023-01-22 21:48:13.035133: step: 810/470, loss: 0.0002737323520705104
2023-01-22 21:48:13.752851: step: 812/470, loss: 0.00031162946834228933
2023-01-22 21:48:14.446141: step: 814/470, loss: 0.055558472871780396
2023-01-22 21:48:15.174423: step: 816/470, loss: 0.0006891106604598463
2023-01-22 21:48:15.886598: step: 818/470, loss: 0.012265880592167377
2023-01-22 21:48:16.585059: step: 820/470, loss: 0.005278497468680143
2023-01-22 21:48:17.339882: step: 822/470, loss: 0.0007367177749983966
2023-01-22 21:48:18.120867: step: 824/470, loss: 0.00032776681473478675
2023-01-22 21:48:18.777509: step: 826/470, loss: 0.004107217770069838
2023-01-22 21:48:19.600293: step: 828/470, loss: 0.008525116369128227
2023-01-22 21:48:20.343640: step: 830/470, loss: 0.00033007533056661487
2023-01-22 21:48:21.071789: step: 832/470, loss: 0.0008853072067722678
2023-01-22 21:48:21.774521: step: 834/470, loss: 0.0006735201459378004
2023-01-22 21:48:22.445029: step: 836/470, loss: 0.0024453336372971535
2023-01-22 21:48:23.154129: step: 838/470, loss: 1.662024988036137e-05
2023-01-22 21:48:23.886238: step: 840/470, loss: 0.007163457106798887
2023-01-22 21:48:24.520586: step: 842/470, loss: 8.924589928938076e-05
2023-01-22 21:48:25.252975: step: 844/470, loss: 0.012785697355866432
2023-01-22 21:48:25.992342: step: 846/470, loss: 0.004503779578953981
2023-01-22 21:48:26.681159: step: 848/470, loss: 0.04323597252368927
2023-01-22 21:48:27.493459: step: 850/470, loss: 0.09764706343412399
2023-01-22 21:48:28.301135: step: 852/470, loss: 0.11818161606788635
2023-01-22 21:48:29.022166: step: 854/470, loss: 0.00011157716653542593
2023-01-22 21:48:29.805975: step: 856/470, loss: 0.003554239170625806
2023-01-22 21:48:30.527302: step: 858/470, loss: 0.009540732949972153
2023-01-22 21:48:31.237004: step: 860/470, loss: 0.0023567378520965576
2023-01-22 21:48:31.993569: step: 862/470, loss: 0.0008384129614569247
2023-01-22 21:48:32.721474: step: 864/470, loss: 0.0015519903972744942
2023-01-22 21:48:33.439876: step: 866/470, loss: 0.0001553489564685151
2023-01-22 21:48:34.366486: step: 868/470, loss: 0.018373709172010422
2023-01-22 21:48:35.149576: step: 870/470, loss: 0.0008085042354650795
2023-01-22 21:48:35.849385: step: 872/470, loss: 0.0006269579171203077
2023-01-22 21:48:36.538175: step: 874/470, loss: 0.00702142296358943
2023-01-22 21:48:37.321055: step: 876/470, loss: 0.0382898710668087
2023-01-22 21:48:37.962142: step: 878/470, loss: 0.004564675502479076
2023-01-22 21:48:38.776766: step: 880/470, loss: 0.0015754105988889933
2023-01-22 21:48:39.519359: step: 882/470, loss: 0.00046436249976977706
2023-01-22 21:48:40.277578: step: 884/470, loss: 0.0009858196135610342
2023-01-22 21:48:40.981060: step: 886/470, loss: 1.2100362255296204e-05
2023-01-22 21:48:41.778294: step: 888/470, loss: 0.001151207135990262
2023-01-22 21:48:42.537269: step: 890/470, loss: 0.002776085864752531
2023-01-22 21:48:43.270610: step: 892/470, loss: 0.0019681635312736034
2023-01-22 21:48:44.141893: step: 894/470, loss: 0.0007172105833888054
2023-01-22 21:48:44.773439: step: 896/470, loss: 0.010990173555910587
2023-01-22 21:48:45.515151: step: 898/470, loss: 0.01894933171570301
2023-01-22 21:48:46.227500: step: 900/470, loss: 0.003088920610025525
2023-01-22 21:48:46.915695: step: 902/470, loss: 0.026566803455352783
2023-01-22 21:48:47.608890: step: 904/470, loss: 0.0029794382862746716
2023-01-22 21:48:48.318237: step: 906/470, loss: 0.0001242105645360425
2023-01-22 21:48:49.121886: step: 908/470, loss: 0.10085117816925049
2023-01-22 21:48:49.789711: step: 910/470, loss: 0.00012268772115930915
2023-01-22 21:48:50.497669: step: 912/470, loss: 0.004678426310420036
2023-01-22 21:48:51.265128: step: 914/470, loss: 0.0005872580222785473
2023-01-22 21:48:51.948668: step: 916/470, loss: 0.00040301651461049914
2023-01-22 21:48:52.746124: step: 918/470, loss: 0.0017456887289881706
2023-01-22 21:48:53.456588: step: 920/470, loss: 0.07405664026737213
2023-01-22 21:48:54.138328: step: 922/470, loss: 0.0002474442298989743
2023-01-22 21:48:54.886827: step: 924/470, loss: 0.019610069692134857
2023-01-22 21:48:55.597795: step: 926/470, loss: 0.00045439210953190923
2023-01-22 21:48:56.376193: step: 928/470, loss: 0.004804328549653292
2023-01-22 21:48:57.080220: step: 930/470, loss: 0.02111213654279709
2023-01-22 21:48:57.846527: step: 932/470, loss: 0.04191237688064575
2023-01-22 21:48:58.565039: step: 934/470, loss: 0.007126152515411377
2023-01-22 21:48:59.289881: step: 936/470, loss: 0.0033556444104760885
2023-01-22 21:48:59.971131: step: 938/470, loss: 0.0007148180739022791
2023-01-22 21:49:00.737728: step: 940/470, loss: 0.12642525136470795
2023-01-22 21:49:01.319190: step: 942/470, loss: 0.00044497830094769597
==================================================
Loss: 0.036
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30282611771363893, 'r': 0.3384527197975965, 'f1': 0.3196497909199522}, 'combined': 0.23553142488838583, 'epoch': 37}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3440310092967713, 'r': 0.3638789521408158, 'f1': 0.353676738529391}, 'combined': 0.24634200693589425, 'epoch': 37}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2931962461359044, 'r': 0.3332534182835042, 'f1': 0.31194414109308477}, 'combined': 0.22985357764753614, 'epoch': 37}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3486073107962775, 'r': 0.3667080750106996, 'f1': 0.3574286766739715}, 'combined': 0.2489552971858508, 'epoch': 37}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2836884955703637, 'r': 0.34290241305184377, 'f1': 0.31049754583904066}, 'combined': 0.22878766535508258, 'epoch': 37}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33661146480964615, 'r': 0.37674590869079627, 'f1': 0.35554967789331055}, 'combined': 0.24764654181623622, 'epoch': 37}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23317307692307693, 'r': 0.3464285714285714, 'f1': 0.278735632183908}, 'combined': 0.185823754789272, 'epoch': 37}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2875, 'r': 0.5, 'f1': 0.36507936507936506}, 'combined': 0.18253968253968253, 'epoch': 37}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3645833333333333, 'r': 0.3017241379310345, 'f1': 0.33018867924528306}, 'combined': 0.22012578616352202, 'epoch': 37}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 38
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 21:51:38.911228: step: 2/470, loss: 0.003493683412671089
2023-01-22 21:51:39.669376: step: 4/470, loss: 3.1483668863074854e-05
2023-01-22 21:51:40.395561: step: 6/470, loss: 0.0010329708456993103
2023-01-22 21:51:41.109174: step: 8/470, loss: 0.015900876373052597
2023-01-22 21:51:41.846558: step: 10/470, loss: 0.0006670716102235019
2023-01-22 21:51:42.630157: step: 12/470, loss: 0.03588513284921646
2023-01-22 21:51:43.273655: step: 14/470, loss: 0.018479470163583755
2023-01-22 21:51:43.956531: step: 16/470, loss: 0.0064428700134158134
2023-01-22 21:51:44.677381: step: 18/470, loss: 0.008134379982948303
2023-01-22 21:51:45.427582: step: 20/470, loss: 0.04875548183917999
2023-01-22 21:51:46.255746: step: 22/470, loss: 0.007432709448039532
2023-01-22 21:51:47.007184: step: 24/470, loss: 0.015830012038350105
2023-01-22 21:51:47.691597: step: 26/470, loss: 0.0009923202451318502
2023-01-22 21:51:48.449194: step: 28/470, loss: 0.02561793476343155
2023-01-22 21:51:49.195634: step: 30/470, loss: 0.06104350462555885
2023-01-22 21:51:49.909565: step: 32/470, loss: 0.00034792270162142813
2023-01-22 21:51:50.746576: step: 34/470, loss: 0.0635775625705719
2023-01-22 21:51:51.460686: step: 36/470, loss: 0.0034135098103433847
2023-01-22 21:51:52.113252: step: 38/470, loss: 0.0001381459878757596
2023-01-22 21:51:52.854242: step: 40/470, loss: 0.005255894735455513
2023-01-22 21:51:53.642791: step: 42/470, loss: 0.006958745885640383
2023-01-22 21:51:54.295582: step: 44/470, loss: 2.5377163183293305e-05
2023-01-22 21:51:54.996765: step: 46/470, loss: 0.0034183606039732695
2023-01-22 21:51:55.799573: step: 48/470, loss: 0.011098065413534641
2023-01-22 21:51:56.567315: step: 50/470, loss: 0.03030436858534813
2023-01-22 21:51:57.262336: step: 52/470, loss: 0.001068002893589437
2023-01-22 21:51:58.003353: step: 54/470, loss: 0.0028049203101545572
2023-01-22 21:51:58.834759: step: 56/470, loss: 0.0009381828713230789
2023-01-22 21:51:59.554924: step: 58/470, loss: 0.00014905152784194797
2023-01-22 21:52:00.391549: step: 60/470, loss: 0.013133973814547062
2023-01-22 21:52:01.104716: step: 62/470, loss: 0.0014203452738001943
2023-01-22 21:52:01.948960: step: 64/470, loss: 0.0008770119166001678
2023-01-22 21:52:02.767286: step: 66/470, loss: 0.018221968784928322
2023-01-22 21:52:03.476940: step: 68/470, loss: 0.00032925268169492483
2023-01-22 21:52:04.104157: step: 70/470, loss: 8.492947381455451e-05
2023-01-22 21:52:05.042783: step: 72/470, loss: 0.01569739170372486
2023-01-22 21:52:05.796014: step: 74/470, loss: 0.011922664940357208
2023-01-22 21:52:06.501639: step: 76/470, loss: 0.00024971627863124013
2023-01-22 21:52:07.229578: step: 78/470, loss: 0.012681872583925724
2023-01-22 21:52:07.913282: step: 80/470, loss: 0.03299639746546745
2023-01-22 21:52:08.712842: step: 82/470, loss: 0.3435828983783722
2023-01-22 21:52:09.403367: step: 84/470, loss: 0.0480882003903389
2023-01-22 21:52:10.092071: step: 86/470, loss: 0.006340092979371548
2023-01-22 21:52:10.835928: step: 88/470, loss: 0.018705761060118675
2023-01-22 21:52:11.563746: step: 90/470, loss: 0.0008621179731562734
2023-01-22 21:52:12.243179: step: 92/470, loss: 0.022489935159683228
2023-01-22 21:52:12.952815: step: 94/470, loss: 0.008963331580162048
2023-01-22 21:52:13.725223: step: 96/470, loss: 0.04265124723315239
2023-01-22 21:52:14.456095: step: 98/470, loss: 0.022511204704642296
2023-01-22 21:52:15.199279: step: 100/470, loss: 0.002531637204810977
2023-01-22 21:52:15.910372: step: 102/470, loss: 0.0007971610175445676
2023-01-22 21:52:16.562900: step: 104/470, loss: 0.01751614920794964
2023-01-22 21:52:17.325584: step: 106/470, loss: 0.022801943123340607
2023-01-22 21:52:18.084046: step: 108/470, loss: 7.938418275443837e-05
2023-01-22 21:52:18.766490: step: 110/470, loss: 0.0036345114931464195
2023-01-22 21:52:19.546076: step: 112/470, loss: 0.0004885205999016762
2023-01-22 21:52:20.274182: step: 114/470, loss: 0.02976686879992485
2023-01-22 21:52:20.975836: step: 116/470, loss: 0.0012918829452246428
2023-01-22 21:52:21.686956: step: 118/470, loss: 0.030225861817598343
2023-01-22 21:52:22.430386: step: 120/470, loss: 0.0013654425274580717
2023-01-22 21:52:23.165766: step: 122/470, loss: 0.049725260585546494
2023-01-22 21:52:23.906816: step: 124/470, loss: 0.0041059935465455055
2023-01-22 21:52:24.588233: step: 126/470, loss: 0.0016458419850096107
2023-01-22 21:52:25.288079: step: 128/470, loss: 0.0037780962884426117
2023-01-22 21:52:25.985918: step: 130/470, loss: 0.00395290507003665
2023-01-22 21:52:26.736356: step: 132/470, loss: 0.01029009185731411
2023-01-22 21:52:27.441248: step: 134/470, loss: 0.0011309736873954535
2023-01-22 21:52:28.203113: step: 136/470, loss: 0.00018435719539411366
2023-01-22 21:52:28.902905: step: 138/470, loss: 0.0008806980913504958
2023-01-22 21:52:29.614940: step: 140/470, loss: 0.0079522505402565
2023-01-22 21:52:30.424112: step: 142/470, loss: 3.3286640245933086e-05
2023-01-22 21:52:31.181286: step: 144/470, loss: 0.0006921407766640186
2023-01-22 21:52:31.918468: step: 146/470, loss: 0.2176320105791092
2023-01-22 21:52:32.722679: step: 148/470, loss: 0.011884159408509731
2023-01-22 21:52:33.443237: step: 150/470, loss: 0.0032580445986241102
2023-01-22 21:52:34.222709: step: 152/470, loss: 0.0007281180587597191
2023-01-22 21:52:35.102463: step: 154/470, loss: 0.019526991993188858
2023-01-22 21:52:35.812879: step: 156/470, loss: 0.005697279702872038
2023-01-22 21:52:36.586883: step: 158/470, loss: 0.004067837260663509
2023-01-22 21:52:37.299795: step: 160/470, loss: 5.4411604651249945e-05
2023-01-22 21:52:37.972608: step: 162/470, loss: 0.019002696499228477
2023-01-22 21:52:38.712387: step: 164/470, loss: 0.0015450211940333247
2023-01-22 21:52:39.512908: step: 166/470, loss: 0.0039725713431835175
2023-01-22 21:52:40.287326: step: 168/470, loss: 0.011467957869172096
2023-01-22 21:52:40.992245: step: 170/470, loss: 0.027040036395192146
2023-01-22 21:52:41.654898: step: 172/470, loss: 0.00044272729428485036
2023-01-22 21:52:42.443213: step: 174/470, loss: 0.0003731549368239939
2023-01-22 21:52:43.165826: step: 176/470, loss: 0.016215885058045387
2023-01-22 21:52:43.891494: step: 178/470, loss: 0.03532567247748375
2023-01-22 21:52:44.557680: step: 180/470, loss: 0.002269421936944127
2023-01-22 21:52:45.258117: step: 182/470, loss: 0.004340062849223614
2023-01-22 21:52:45.955777: step: 184/470, loss: 0.021665049716830254
2023-01-22 21:52:46.690637: step: 186/470, loss: 0.0015216005267575383
2023-01-22 21:52:47.447621: step: 188/470, loss: 0.03777991607785225
2023-01-22 21:52:48.187326: step: 190/470, loss: 0.0024247351102530956
2023-01-22 21:52:48.968012: step: 192/470, loss: 0.026008278131484985
2023-01-22 21:52:49.752325: step: 194/470, loss: 0.011309238150715828
2023-01-22 21:52:50.483052: step: 196/470, loss: 0.0033743376843631268
2023-01-22 21:52:51.237117: step: 198/470, loss: 0.022116800770163536
2023-01-22 21:52:51.970905: step: 200/470, loss: 6.394281808752567e-05
2023-01-22 21:52:52.642358: step: 202/470, loss: 0.010615077801048756
2023-01-22 21:52:53.368587: step: 204/470, loss: 0.0010532918386161327
2023-01-22 21:52:54.046509: step: 206/470, loss: 0.001243436592631042
2023-01-22 21:52:54.734415: step: 208/470, loss: 0.3090232312679291
2023-01-22 21:52:55.428556: step: 210/470, loss: 0.00770140066742897
2023-01-22 21:52:56.176874: step: 212/470, loss: 0.0004572441102936864
2023-01-22 21:52:56.865802: step: 214/470, loss: 0.0049099307507276535
2023-01-22 21:52:57.520755: step: 216/470, loss: 0.00032190539059229195
2023-01-22 21:52:58.208794: step: 218/470, loss: 0.002639106009155512
2023-01-22 21:52:58.986907: step: 220/470, loss: 0.0019580356311053038
2023-01-22 21:52:59.669234: step: 222/470, loss: 0.0008421125821769238
2023-01-22 21:53:00.417776: step: 224/470, loss: 0.0025131748989224434
2023-01-22 21:53:01.157720: step: 226/470, loss: 0.006898400839418173
2023-01-22 21:53:01.829809: step: 228/470, loss: 0.003961809910833836
2023-01-22 21:53:02.584346: step: 230/470, loss: 0.012256169691681862
2023-01-22 21:53:03.278140: step: 232/470, loss: 0.011719431728124619
2023-01-22 21:53:04.012529: step: 234/470, loss: 0.07077656686306
2023-01-22 21:53:04.779135: step: 236/470, loss: 0.0006426791660487652
2023-01-22 21:53:05.504184: step: 238/470, loss: 1.4502748854283709e-05
2023-01-22 21:53:06.128120: step: 240/470, loss: 0.00010448225657455623
2023-01-22 21:53:06.892825: step: 242/470, loss: 0.008650097995996475
2023-01-22 21:53:07.623811: step: 244/470, loss: 0.00271412986330688
2023-01-22 21:53:08.389471: step: 246/470, loss: 0.008904355578124523
2023-01-22 21:53:09.120882: step: 248/470, loss: 0.01523964386433363
2023-01-22 21:53:09.861894: step: 250/470, loss: 0.0009835069067776203
2023-01-22 21:53:10.556934: step: 252/470, loss: 0.001248181564733386
2023-01-22 21:53:11.350186: step: 254/470, loss: 0.12711653113365173
2023-01-22 21:53:12.118060: step: 256/470, loss: 0.014596930705010891
2023-01-22 21:53:12.920869: step: 258/470, loss: 0.03263501450419426
2023-01-22 21:53:13.605701: step: 260/470, loss: 0.12978902459144592
2023-01-22 21:53:14.331115: step: 262/470, loss: 0.011506453156471252
2023-01-22 21:53:15.109618: step: 264/470, loss: 0.07690394669771194
2023-01-22 21:53:15.815651: step: 266/470, loss: 0.0022593012545257807
2023-01-22 21:53:16.577633: step: 268/470, loss: 0.008098762482404709
2023-01-22 21:53:17.371762: step: 270/470, loss: 0.0018563955090939999
2023-01-22 21:53:18.157806: step: 272/470, loss: 0.0008043406414799392
2023-01-22 21:53:18.891581: step: 274/470, loss: 0.006701835431158543
2023-01-22 21:53:19.615599: step: 276/470, loss: 0.0002937865210697055
2023-01-22 21:53:20.286730: step: 278/470, loss: 0.029652804136276245
2023-01-22 21:53:21.053771: step: 280/470, loss: 0.22939205169677734
2023-01-22 21:53:21.757145: step: 282/470, loss: 0.0002202181494794786
2023-01-22 21:53:22.446454: step: 284/470, loss: 1.331815747107612e-05
2023-01-22 21:53:23.180828: step: 286/470, loss: 0.02264559268951416
2023-01-22 21:53:23.955759: step: 288/470, loss: 0.0002129612839780748
2023-01-22 21:53:24.712225: step: 290/470, loss: 0.005394687410444021
2023-01-22 21:53:25.441089: step: 292/470, loss: 0.025830525904893875
2023-01-22 21:53:26.198327: step: 294/470, loss: 0.0006529740057885647
2023-01-22 21:53:26.909532: step: 296/470, loss: 0.011604727245867252
2023-01-22 21:53:27.625941: step: 298/470, loss: 0.002371342619881034
2023-01-22 21:53:28.407296: step: 300/470, loss: 0.005713804624974728
2023-01-22 21:53:29.119935: step: 302/470, loss: 0.041894592344760895
2023-01-22 21:53:29.866930: step: 304/470, loss: 0.04704660177230835
2023-01-22 21:53:30.615025: step: 306/470, loss: 0.0020737978629767895
2023-01-22 21:53:31.382692: step: 308/470, loss: 0.006861019879579544
2023-01-22 21:53:32.031413: step: 310/470, loss: 0.25099924206733704
2023-01-22 21:53:32.691917: step: 312/470, loss: 0.00043172220466658473
2023-01-22 21:53:33.370520: step: 314/470, loss: 0.015380592085421085
2023-01-22 21:53:34.052922: step: 316/470, loss: 0.0004332458192948252
2023-01-22 21:53:34.830895: step: 318/470, loss: 0.005911845248192549
2023-01-22 21:53:35.582859: step: 320/470, loss: 0.00782099924981594
2023-01-22 21:53:36.293411: step: 322/470, loss: 0.006352236494421959
2023-01-22 21:53:37.046978: step: 324/470, loss: 0.006406526081264019
2023-01-22 21:53:37.731728: step: 326/470, loss: 0.006970448885113001
2023-01-22 21:53:38.447532: step: 328/470, loss: 0.004823725204914808
2023-01-22 21:53:39.206406: step: 330/470, loss: 0.021097727119922638
2023-01-22 21:53:39.953053: step: 332/470, loss: 0.014263940043747425
2023-01-22 21:53:40.664947: step: 334/470, loss: 0.005755257327109575
2023-01-22 21:53:41.369206: step: 336/470, loss: 0.0009758573723956943
2023-01-22 21:53:42.153162: step: 338/470, loss: 5.3987059800419956e-05
2023-01-22 21:53:42.859045: step: 340/470, loss: 0.001099450164474547
2023-01-22 21:53:43.574824: step: 342/470, loss: 0.0010999426012858748
2023-01-22 21:53:44.335088: step: 344/470, loss: 0.02734139934182167
2023-01-22 21:53:45.089363: step: 346/470, loss: 0.005323213990777731
2023-01-22 21:53:45.835941: step: 348/470, loss: 0.0010934954043477774
2023-01-22 21:53:46.559500: step: 350/470, loss: 0.02636098861694336
2023-01-22 21:53:47.326731: step: 352/470, loss: 0.29431140422821045
2023-01-22 21:53:48.115419: step: 354/470, loss: 1.4190295587468427e-06
2023-01-22 21:53:48.803375: step: 356/470, loss: 0.00703160697594285
2023-01-22 21:53:49.502960: step: 358/470, loss: 4.769103725266177e-06
2023-01-22 21:53:50.279965: step: 360/470, loss: 0.008066543377935886
2023-01-22 21:53:51.053292: step: 362/470, loss: 0.008893858641386032
2023-01-22 21:53:51.793760: step: 364/470, loss: 0.0012347385054454207
2023-01-22 21:53:52.617724: step: 366/470, loss: 0.03243786841630936
2023-01-22 21:53:53.428367: step: 368/470, loss: 0.05025627464056015
2023-01-22 21:53:54.202681: step: 370/470, loss: 0.0002960547572001815
2023-01-22 21:53:54.956561: step: 372/470, loss: 0.01112099178135395
2023-01-22 21:53:55.726530: step: 374/470, loss: 5.0827387894969434e-05
2023-01-22 21:53:56.494212: step: 376/470, loss: 0.0254096370190382
2023-01-22 21:53:57.197010: step: 378/470, loss: 1.0762357711791992
2023-01-22 21:53:58.025888: step: 380/470, loss: 0.09362594038248062
2023-01-22 21:53:58.710672: step: 382/470, loss: 0.08472180366516113
2023-01-22 21:53:59.413402: step: 384/470, loss: 5.627515201922506e-05
2023-01-22 21:54:00.201270: step: 386/470, loss: 0.04056701436638832
2023-01-22 21:54:00.983100: step: 388/470, loss: 0.0017334421863779426
2023-01-22 21:54:01.735708: step: 390/470, loss: 0.013753866776823997
2023-01-22 21:54:02.508259: step: 392/470, loss: 0.029546622186899185
2023-01-22 21:54:03.289213: step: 394/470, loss: 0.008471227250993252
2023-01-22 21:54:04.047150: step: 396/470, loss: 0.05549805611371994
2023-01-22 21:54:04.780808: step: 398/470, loss: 4.936423465551343e-06
2023-01-22 21:54:05.603211: step: 400/470, loss: 0.022593067958950996
2023-01-22 21:54:06.394891: step: 402/470, loss: 0.011362415738403797
2023-01-22 21:54:07.088336: step: 404/470, loss: 0.007395919878035784
2023-01-22 21:54:07.731265: step: 406/470, loss: 0.0004373751871753484
2023-01-22 21:54:08.458117: step: 408/470, loss: 0.0032540217507630587
2023-01-22 21:54:09.209324: step: 410/470, loss: 6.207002297742292e-05
2023-01-22 21:54:09.995482: step: 412/470, loss: 0.012555564753711224
2023-01-22 21:54:10.761751: step: 414/470, loss: 0.005541603546589613
2023-01-22 21:54:11.526065: step: 416/470, loss: 1.1564688682556152
2023-01-22 21:54:12.254200: step: 418/470, loss: 0.011560517363250256
2023-01-22 21:54:12.999474: step: 420/470, loss: 0.13285844027996063
2023-01-22 21:54:13.746058: step: 422/470, loss: 0.02132769674062729
2023-01-22 21:54:14.539545: step: 424/470, loss: 3.81058816856239e-05
2023-01-22 21:54:15.291716: step: 426/470, loss: 0.005625903606414795
2023-01-22 21:54:15.996742: step: 428/470, loss: 3.352219209773466e-05
2023-01-22 21:54:16.766084: step: 430/470, loss: 0.0006965019856579602
2023-01-22 21:54:17.476442: step: 432/470, loss: 0.00841616839170456
2023-01-22 21:54:18.161106: step: 434/470, loss: 0.0019366976339370012
2023-01-22 21:54:19.059505: step: 436/470, loss: 0.0008078304235823452
2023-01-22 21:54:19.818974: step: 438/470, loss: 0.008926390670239925
2023-01-22 21:54:20.602385: step: 440/470, loss: 0.012859417125582695
2023-01-22 21:54:21.371353: step: 442/470, loss: 0.00021163160272408277
2023-01-22 21:54:22.063757: step: 444/470, loss: 0.0004545637348201126
2023-01-22 21:54:22.728085: step: 446/470, loss: 4.504845492192544e-06
2023-01-22 21:54:23.540747: step: 448/470, loss: 0.04429243505001068
2023-01-22 21:54:24.220200: step: 450/470, loss: 0.013035489246249199
2023-01-22 21:54:25.002014: step: 452/470, loss: 0.01099762599915266
2023-01-22 21:54:25.772472: step: 454/470, loss: 0.0008165753679350019
2023-01-22 21:54:26.457675: step: 456/470, loss: 0.00030910957138985395
2023-01-22 21:54:27.258430: step: 458/470, loss: 0.004646346438676119
2023-01-22 21:54:28.044526: step: 460/470, loss: 1.028315782546997
2023-01-22 21:54:28.753832: step: 462/470, loss: 0.0014696192229166627
2023-01-22 21:54:29.518330: step: 464/470, loss: 0.05205130949616432
2023-01-22 21:54:30.267090: step: 466/470, loss: 2.820938971126452e-05
2023-01-22 21:54:31.069398: step: 468/470, loss: 0.00012028154014842585
2023-01-22 21:54:31.688785: step: 470/470, loss: 6.529298116220161e-05
2023-01-22 21:54:32.419617: step: 472/470, loss: 0.0006013525417074561
2023-01-22 21:54:33.144668: step: 474/470, loss: 3.899422154063359e-05
2023-01-22 21:54:33.999942: step: 476/470, loss: 0.0051171015948057175
2023-01-22 21:54:34.739519: step: 478/470, loss: 0.0003485481138341129
2023-01-22 21:54:35.434264: step: 480/470, loss: 0.0009719117661006749
2023-01-22 21:54:36.185367: step: 482/470, loss: 0.0005722529022023082
2023-01-22 21:54:36.905351: step: 484/470, loss: 0.0002770486462395638
2023-01-22 21:54:37.603681: step: 486/470, loss: 0.004022694192826748
2023-01-22 21:54:38.331056: step: 488/470, loss: 0.007053688168525696
2023-01-22 21:54:39.038390: step: 490/470, loss: 0.05090930685400963
2023-01-22 21:54:39.716232: step: 492/470, loss: 0.0005236592842265964
2023-01-22 21:54:40.503786: step: 494/470, loss: 0.03422538563609123
2023-01-22 21:54:41.237913: step: 496/470, loss: 0.011507346294820309
2023-01-22 21:54:41.943485: step: 498/470, loss: 0.14850161969661713
2023-01-22 21:54:42.592756: step: 500/470, loss: 0.02185884863138199
2023-01-22 21:54:43.295185: step: 502/470, loss: 0.39024344086647034
2023-01-22 21:54:44.050115: step: 504/470, loss: 5.338906339602545e-05
2023-01-22 21:54:44.742747: step: 506/470, loss: 0.008324535563588142
2023-01-22 21:54:45.463471: step: 508/470, loss: 0.9969122409820557
2023-01-22 21:54:46.202456: step: 510/470, loss: 0.005451219622045755
2023-01-22 21:54:46.840652: step: 512/470, loss: 0.00021868124895263463
2023-01-22 21:54:47.559079: step: 514/470, loss: 0.009522140957415104
2023-01-22 21:54:48.324216: step: 516/470, loss: 0.053997401148080826
2023-01-22 21:54:49.071428: step: 518/470, loss: 0.07220856100320816
2023-01-22 21:54:49.827899: step: 520/470, loss: 0.19266104698181152
2023-01-22 21:54:50.508431: step: 522/470, loss: 0.0018507946515455842
2023-01-22 21:54:51.153663: step: 524/470, loss: 0.01633111573755741
2023-01-22 21:54:52.030913: step: 526/470, loss: 0.5133503079414368
2023-01-22 21:54:52.736961: step: 528/470, loss: 0.2512091100215912
2023-01-22 21:54:53.490495: step: 530/470, loss: 0.00509637501090765
2023-01-22 21:54:54.454425: step: 532/470, loss: 0.05830131098628044
2023-01-22 21:54:55.109508: step: 534/470, loss: 0.002167430240660906
2023-01-22 21:54:55.797053: step: 536/470, loss: 0.00017176716937683523
2023-01-22 21:54:56.566911: step: 538/470, loss: 0.018888715654611588
2023-01-22 21:54:57.282852: step: 540/470, loss: 0.0069089666940271854
2023-01-22 21:54:58.104290: step: 542/470, loss: 0.002944743959233165
2023-01-22 21:54:58.817362: step: 544/470, loss: 0.012334275059401989
2023-01-22 21:54:59.530372: step: 546/470, loss: 0.03784177079796791
2023-01-22 21:55:00.313799: step: 548/470, loss: 0.005058033857494593
2023-01-22 21:55:01.138733: step: 550/470, loss: 0.007854700088500977
2023-01-22 21:55:01.779858: step: 552/470, loss: 3.625124918471556e-06
2023-01-22 21:55:02.549760: step: 554/470, loss: 0.011495105922222137
2023-01-22 21:55:03.222838: step: 556/470, loss: 0.0006342419073916972
2023-01-22 21:55:03.966600: step: 558/470, loss: 0.0004920351784676313
2023-01-22 21:55:04.747717: step: 560/470, loss: 0.0354156494140625
2023-01-22 21:55:05.604375: step: 562/470, loss: 0.03654221445322037
2023-01-22 21:55:06.309130: step: 564/470, loss: 0.005547667853534222
2023-01-22 21:55:06.955488: step: 566/470, loss: 0.005937586072832346
2023-01-22 21:55:07.654566: step: 568/470, loss: 0.0038067607674747705
2023-01-22 21:55:08.360381: step: 570/470, loss: 0.0002508886100258678
2023-01-22 21:55:09.106097: step: 572/470, loss: 0.021944653242826462
2023-01-22 21:55:09.811119: step: 574/470, loss: 3.4421158488839865e-05
2023-01-22 21:55:10.461561: step: 576/470, loss: 0.005076797213405371
2023-01-22 21:55:11.216405: step: 578/470, loss: 0.026614626869559288
2023-01-22 21:55:11.928419: step: 580/470, loss: 0.0064454590901732445
2023-01-22 21:55:12.684791: step: 582/470, loss: 0.009054692462086678
2023-01-22 21:55:13.454068: step: 584/470, loss: 0.0006180154159665108
2023-01-22 21:55:14.141639: step: 586/470, loss: 0.03550654277205467
2023-01-22 21:55:14.945516: step: 588/470, loss: 0.006163349840790033
2023-01-22 21:55:15.664957: step: 590/470, loss: 0.019109375774860382
2023-01-22 21:55:16.353126: step: 592/470, loss: 0.03721586987376213
2023-01-22 21:55:17.012063: step: 594/470, loss: 3.0975337722338736e-05
2023-01-22 21:55:17.812317: step: 596/470, loss: 0.0007861484191380441
2023-01-22 21:55:18.523482: step: 598/470, loss: 0.009015318937599659
2023-01-22 21:55:19.282542: step: 600/470, loss: 0.0021047855261713266
2023-01-22 21:55:19.980263: step: 602/470, loss: 4.80856433568988e-05
2023-01-22 21:55:20.716811: step: 604/470, loss: 0.00718892365694046
2023-01-22 21:55:21.420594: step: 606/470, loss: 0.05739133059978485
2023-01-22 21:55:22.170555: step: 608/470, loss: 0.00620870478451252
2023-01-22 21:55:22.907029: step: 610/470, loss: 0.01584588550031185
2023-01-22 21:55:23.681742: step: 612/470, loss: 0.028577158227562904
2023-01-22 21:55:24.401039: step: 614/470, loss: 0.00660181138664484
2023-01-22 21:55:25.105451: step: 616/470, loss: 0.01830855756998062
2023-01-22 21:55:25.780244: step: 618/470, loss: 0.010931288823485374
2023-01-22 21:55:26.555305: step: 620/470, loss: 0.20352265238761902
2023-01-22 21:55:27.308996: step: 622/470, loss: 0.01606188900768757
2023-01-22 21:55:28.058813: step: 624/470, loss: 0.0026829990092664957
2023-01-22 21:55:28.824321: step: 626/470, loss: 0.0006494335830211639
2023-01-22 21:55:29.526157: step: 628/470, loss: 0.019799262285232544
2023-01-22 21:55:30.331505: step: 630/470, loss: 0.06131910905241966
2023-01-22 21:55:30.949101: step: 632/470, loss: 6.267506978474557e-05
2023-01-22 21:55:31.686216: step: 634/470, loss: 0.012804257683455944
2023-01-22 21:55:32.380100: step: 636/470, loss: 0.0005007492727600038
2023-01-22 21:55:33.125093: step: 638/470, loss: 0.001479864353314042
2023-01-22 21:55:33.760337: step: 640/470, loss: 0.0061265756376087666
2023-01-22 21:55:34.408883: step: 642/470, loss: 0.0012702817330136895
2023-01-22 21:55:35.191491: step: 644/470, loss: 0.00014075188664719462
2023-01-22 21:55:35.882214: step: 646/470, loss: 0.0016734458040446043
2023-01-22 21:55:36.622496: step: 648/470, loss: 0.010227406397461891
2023-01-22 21:55:37.273872: step: 650/470, loss: 0.029626229777932167
2023-01-22 21:55:38.082511: step: 652/470, loss: 0.022710563614964485
2023-01-22 21:55:38.889076: step: 654/470, loss: 0.009011475369334221
2023-01-22 21:55:39.633883: step: 656/470, loss: 0.004524306394159794
2023-01-22 21:55:40.365690: step: 658/470, loss: 0.007571091875433922
2023-01-22 21:55:41.094814: step: 660/470, loss: 0.032529208809137344
2023-01-22 21:55:41.817429: step: 662/470, loss: 0.01610148325562477
2023-01-22 21:55:42.519043: step: 664/470, loss: 0.02389807626605034
2023-01-22 21:55:43.303783: step: 666/470, loss: 0.02644765004515648
2023-01-22 21:55:43.998485: step: 668/470, loss: 0.008968241512775421
2023-01-22 21:55:44.743704: step: 670/470, loss: 0.005838526878505945
2023-01-22 21:55:45.546739: step: 672/470, loss: 0.000868885894306004
2023-01-22 21:55:46.318169: step: 674/470, loss: 0.015672659501433372
2023-01-22 21:55:47.128093: step: 676/470, loss: 0.005507215391844511
2023-01-22 21:55:47.837176: step: 678/470, loss: 0.04494674503803253
2023-01-22 21:55:48.585540: step: 680/470, loss: 0.027755441144108772
2023-01-22 21:55:49.339918: step: 682/470, loss: 0.003982035908848047
2023-01-22 21:55:50.030465: step: 684/470, loss: 0.0009073261171579361
2023-01-22 21:55:50.779454: step: 686/470, loss: 0.004845160525292158
2023-01-22 21:55:51.482292: step: 688/470, loss: 0.0002821074740495533
2023-01-22 21:55:52.342447: step: 690/470, loss: 0.007127921562641859
2023-01-22 21:55:53.063089: step: 692/470, loss: 0.0001395836443407461
2023-01-22 21:55:53.775931: step: 694/470, loss: 0.0343923382461071
2023-01-22 21:55:54.522906: step: 696/470, loss: 0.06720244139432907
2023-01-22 21:55:55.257177: step: 698/470, loss: 0.02562553994357586
2023-01-22 21:55:55.993767: step: 700/470, loss: 0.07589274644851685
2023-01-22 21:55:56.770266: step: 702/470, loss: 0.03103337623178959
2023-01-22 21:55:57.432278: step: 704/470, loss: 0.1309605836868286
2023-01-22 21:55:58.154422: step: 706/470, loss: 0.04467151314020157
2023-01-22 21:55:58.886667: step: 708/470, loss: 0.0040990193374454975
2023-01-22 21:55:59.577541: step: 710/470, loss: 0.004827653989195824
2023-01-22 21:56:00.314242: step: 712/470, loss: 0.18793350458145142
2023-01-22 21:56:01.062004: step: 714/470, loss: 0.0711977481842041
2023-01-22 21:56:01.745037: step: 716/470, loss: 0.0011849101865664124
2023-01-22 21:56:02.424575: step: 718/470, loss: 0.038444213569164276
2023-01-22 21:56:03.149732: step: 720/470, loss: 0.01529417559504509
2023-01-22 21:56:03.894281: step: 722/470, loss: 0.02028188854455948
2023-01-22 21:56:04.647683: step: 724/470, loss: 0.0011991052888333797
2023-01-22 21:56:05.456064: step: 726/470, loss: 0.007202590350061655
2023-01-22 21:56:06.217545: step: 728/470, loss: 0.03086160123348236
2023-01-22 21:56:06.932005: step: 730/470, loss: 0.005256262607872486
2023-01-22 21:56:07.703934: step: 732/470, loss: 0.07266030460596085
2023-01-22 21:56:08.484986: step: 734/470, loss: 0.003284410573542118
2023-01-22 21:56:09.224297: step: 736/470, loss: 0.018563855439424515
2023-01-22 21:56:09.915822: step: 738/470, loss: 2.060541373793967e-05
2023-01-22 21:56:10.743512: step: 740/470, loss: 0.004683589097112417
2023-01-22 21:56:11.371584: step: 742/470, loss: 0.00043677486246451735
2023-01-22 21:56:12.018726: step: 744/470, loss: 0.0007822015904821455
2023-01-22 21:56:12.787662: step: 746/470, loss: 0.0006057433784008026
2023-01-22 21:56:13.550581: step: 748/470, loss: 0.053732726722955704
2023-01-22 21:56:14.222392: step: 750/470, loss: 0.009779625572264194
2023-01-22 21:56:14.954040: step: 752/470, loss: 0.0024724539835006
2023-01-22 21:56:15.655540: step: 754/470, loss: 0.8649208545684814
2023-01-22 21:56:16.397858: step: 756/470, loss: 0.005285963881760836
2023-01-22 21:56:17.144216: step: 758/470, loss: 0.01545005477964878
2023-01-22 21:56:17.818967: step: 760/470, loss: 0.011997690424323082
2023-01-22 21:56:18.574939: step: 762/470, loss: 0.0027697875630110502
2023-01-22 21:56:19.297277: step: 764/470, loss: 0.000867619295604527
2023-01-22 21:56:19.995699: step: 766/470, loss: 0.0008559745037928224
2023-01-22 21:56:20.682399: step: 768/470, loss: 0.002753552980720997
2023-01-22 21:56:21.449774: step: 770/470, loss: 0.08743966370820999
2023-01-22 21:56:22.148159: step: 772/470, loss: 0.8679112792015076
2023-01-22 21:56:22.913752: step: 774/470, loss: 0.0008498340612277389
2023-01-22 21:56:23.646245: step: 776/470, loss: 0.012493046931922436
2023-01-22 21:56:24.338053: step: 778/470, loss: 0.0022574099712073803
2023-01-22 21:56:25.104638: step: 780/470, loss: 0.09348601847887039
2023-01-22 21:56:25.866844: step: 782/470, loss: 0.09230636805295944
2023-01-22 21:56:26.545692: step: 784/470, loss: 0.0021880273707211018
2023-01-22 21:56:27.319535: step: 786/470, loss: 0.003932863939553499
2023-01-22 21:56:28.081280: step: 788/470, loss: 0.009727765806019306
2023-01-22 21:56:28.871406: step: 790/470, loss: 0.002854890888556838
2023-01-22 21:56:29.744796: step: 792/470, loss: 0.028947800397872925
2023-01-22 21:56:30.523999: step: 794/470, loss: 0.004353455267846584
2023-01-22 21:56:31.232557: step: 796/470, loss: 0.016604196280241013
2023-01-22 21:56:31.959312: step: 798/470, loss: 0.0022141074296087027
2023-01-22 21:56:32.689443: step: 800/470, loss: 0.0014762524515390396
2023-01-22 21:56:33.437953: step: 802/470, loss: 0.008055765181779861
2023-01-22 21:56:34.137605: step: 804/470, loss: 0.0005244429339654744
2023-01-22 21:56:34.848745: step: 806/470, loss: 0.01423501968383789
2023-01-22 21:56:35.486158: step: 808/470, loss: 0.0004736521514132619
2023-01-22 21:56:36.198846: step: 810/470, loss: 0.0029225496109575033
2023-01-22 21:56:36.927151: step: 812/470, loss: 0.006569644436240196
2023-01-22 21:56:37.683044: step: 814/470, loss: 0.003673528553918004
2023-01-22 21:56:38.441243: step: 816/470, loss: 0.0015710997395217419
2023-01-22 21:56:39.250658: step: 818/470, loss: 0.006185244768857956
2023-01-22 21:56:40.030961: step: 820/470, loss: 0.014171771705150604
2023-01-22 21:56:40.719322: step: 822/470, loss: 0.006676795426756144
2023-01-22 21:56:41.435347: step: 824/470, loss: 0.000639638863503933
2023-01-22 21:56:42.113966: step: 826/470, loss: 0.036543309688568115
2023-01-22 21:56:42.800240: step: 828/470, loss: 0.00471093412488699
2023-01-22 21:56:43.466357: step: 830/470, loss: 0.0005620458978228271
2023-01-22 21:56:44.154734: step: 832/470, loss: 0.04118078574538231
2023-01-22 21:56:44.911684: step: 834/470, loss: 0.0009206313407048583
2023-01-22 21:56:45.707428: step: 836/470, loss: 0.006762698758393526
2023-01-22 21:56:46.433841: step: 838/470, loss: 0.01615045592188835
2023-01-22 21:56:47.208025: step: 840/470, loss: 0.00715272594243288
2023-01-22 21:56:47.945025: step: 842/470, loss: 0.028812158852815628
2023-01-22 21:56:48.706745: step: 844/470, loss: 0.0012455545365810394
2023-01-22 21:56:49.433331: step: 846/470, loss: 0.027298571541905403
2023-01-22 21:56:50.113051: step: 848/470, loss: 0.017294684424996376
2023-01-22 21:56:50.772617: step: 850/470, loss: 0.0035474118776619434
2023-01-22 21:56:51.503519: step: 852/470, loss: 0.005111002828925848
2023-01-22 21:56:52.239443: step: 854/470, loss: 0.0006961169419810176
2023-01-22 21:56:52.991284: step: 856/470, loss: 0.036905642598867416
2023-01-22 21:56:53.762747: step: 858/470, loss: 0.0012904554605484009
2023-01-22 21:56:54.508587: step: 860/470, loss: 0.058939360082149506
2023-01-22 21:56:55.250069: step: 862/470, loss: 0.056269776076078415
2023-01-22 21:56:55.940649: step: 864/470, loss: 0.0005217547295615077
2023-01-22 21:56:56.619654: step: 866/470, loss: 0.0017588756745681167
2023-01-22 21:56:57.363998: step: 868/470, loss: 0.0008544818265363574
2023-01-22 21:56:58.046323: step: 870/470, loss: 0.0433480478823185
2023-01-22 21:56:58.800504: step: 872/470, loss: 0.030004724860191345
2023-01-22 21:56:59.527329: step: 874/470, loss: 0.002005601767450571
2023-01-22 21:57:00.165938: step: 876/470, loss: 0.00046739837853237987
2023-01-22 21:57:00.867227: step: 878/470, loss: 0.00015845979214645922
2023-01-22 21:57:01.584776: step: 880/470, loss: 0.0015988233499228954
2023-01-22 21:57:02.281306: step: 882/470, loss: 0.0655452087521553
2023-01-22 21:57:03.073258: step: 884/470, loss: 0.08574583381414413
2023-01-22 21:57:03.854589: step: 886/470, loss: 1.4678356647491455
2023-01-22 21:57:04.576451: step: 888/470, loss: 0.00045837866491638124
2023-01-22 21:57:05.322901: step: 890/470, loss: 0.18071959912776947
2023-01-22 21:57:06.039960: step: 892/470, loss: 0.016763942316174507
2023-01-22 21:57:06.797639: step: 894/470, loss: 0.01770934835076332
2023-01-22 21:57:07.517882: step: 896/470, loss: 0.01703697070479393
2023-01-22 21:57:08.247689: step: 898/470, loss: 0.003155779093503952
2023-01-22 21:57:08.946570: step: 900/470, loss: 0.01867401972413063
2023-01-22 21:57:09.742347: step: 902/470, loss: 0.08417651057243347
2023-01-22 21:57:10.518454: step: 904/470, loss: 0.00018019463459495455
2023-01-22 21:57:11.257166: step: 906/470, loss: 0.016756407916545868
2023-01-22 21:57:12.014022: step: 908/470, loss: 0.02904907800257206
2023-01-22 21:57:12.687323: step: 910/470, loss: 0.0007967533310875297
2023-01-22 21:57:13.392739: step: 912/470, loss: 5.6903561926446855e-05
2023-01-22 21:57:14.124651: step: 914/470, loss: 0.0034690299071371555
2023-01-22 21:57:14.853765: step: 916/470, loss: 0.005849133711308241
2023-01-22 21:57:15.693255: step: 918/470, loss: 0.004884378984570503
2023-01-22 21:57:16.345965: step: 920/470, loss: 0.00029265874763950706
2023-01-22 21:57:17.007985: step: 922/470, loss: 0.0014200083678588271
2023-01-22 21:57:17.730703: step: 924/470, loss: 0.004363223910331726
2023-01-22 21:57:18.519965: step: 926/470, loss: 0.04603644460439682
2023-01-22 21:57:19.264110: step: 928/470, loss: 0.012013577856123447
2023-01-22 21:57:19.979505: step: 930/470, loss: 0.011867745779454708
2023-01-22 21:57:20.666978: step: 932/470, loss: 0.014655977487564087
2023-01-22 21:57:21.369598: step: 934/470, loss: 0.0016832905821502209
2023-01-22 21:57:22.091188: step: 936/470, loss: 0.003247485961765051
2023-01-22 21:57:22.813387: step: 938/470, loss: 0.015403217636048794
2023-01-22 21:57:23.539242: step: 940/470, loss: 0.00028605852276086807
2023-01-22 21:57:24.210924: step: 942/470, loss: 0.0061555225402116776
==================================================
Loss: 0.037
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2909310605087793, 'r': 0.3516567088123196, 'f1': 0.3184245456084063}, 'combined': 0.23462861255356252, 'epoch': 38}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33380113463939504, 'r': 0.3588362197373497, 'f1': 0.34586623589142135}, 'combined': 0.2409018558447711, 'epoch': 38}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28547473267732565, 'r': 0.3472282801635023, 'f1': 0.3133378487091879}, 'combined': 0.23088052010150686, 'epoch': 38}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.33948870723145785, 'r': 0.3639710659260342, 'f1': 0.3513038594552905}, 'combined': 0.24468925534199343, 'epoch': 38}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27717695074709464, 'r': 0.36553696540651004, 'f1': 0.31528311091527134}, 'combined': 0.23231387120072625, 'epoch': 38}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3286611580684856, 'r': 0.3744841079914956, 'f1': 0.3500795256729487}, 'combined': 0.24383648554334736, 'epoch': 38}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20491803278688525, 'r': 0.35714285714285715, 'f1': 0.2604166666666667}, 'combined': 0.1736111111111111, 'epoch': 38}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2875, 'r': 0.5, 'f1': 0.36507936507936506}, 'combined': 0.18253968253968253, 'epoch': 38}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4605263157894737, 'r': 0.3017241379310345, 'f1': 0.3645833333333333}, 'combined': 0.24305555555555552, 'epoch': 38}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}
******************************
Epoch: 39
command: python train.py --model_name slot --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --event_hidden_num 450 --role_hidden_num 350 --p1_data_weight 0.1 --learning_rate 9e-4
2023-01-22 22:00:02.170564: step: 2/470, loss: 0.0007795958081260324
2023-01-22 22:00:02.924691: step: 4/470, loss: 0.008938697166740894
2023-01-22 22:00:03.716948: step: 6/470, loss: 0.004093769006431103
2023-01-22 22:00:04.448214: step: 8/470, loss: 0.012828747741878033
2023-01-22 22:00:05.152375: step: 10/470, loss: 0.00028150121215730906
2023-01-22 22:00:05.844181: step: 12/470, loss: 4.195710062049329e-05
2023-01-22 22:00:06.613932: step: 14/470, loss: 0.3589991629123688
2023-01-22 22:00:07.297588: step: 16/470, loss: 0.00017055154603440315
2023-01-22 22:00:08.062835: step: 18/470, loss: 0.0029144282452762127
2023-01-22 22:00:08.771215: step: 20/470, loss: 0.007652122061699629
2023-01-22 22:00:09.490520: step: 22/470, loss: 0.03987063094973564
2023-01-22 22:00:10.226542: step: 24/470, loss: 0.032152093946933746
2023-01-22 22:00:10.938125: step: 26/470, loss: 0.20022591948509216
2023-01-22 22:00:11.728484: step: 28/470, loss: 0.17966990172863007
2023-01-22 22:00:12.474296: step: 30/470, loss: 0.001606591627933085
2023-01-22 22:00:13.235828: step: 32/470, loss: 0.012557115405797958
2023-01-22 22:00:13.885164: step: 34/470, loss: 0.003112519159913063
2023-01-22 22:00:14.686980: step: 36/470, loss: 0.08968937397003174
2023-01-22 22:00:15.447113: step: 38/470, loss: 5.763117587775923e-05
2023-01-22 22:00:16.231122: step: 40/470, loss: 0.02070966176688671
2023-01-22 22:00:16.937822: step: 42/470, loss: 0.000932761759031564
2023-01-22 22:00:17.635029: step: 44/470, loss: 0.020521540194749832
2023-01-22 22:00:18.324156: step: 46/470, loss: 0.004408894572407007
2023-01-22 22:00:19.089662: step: 48/470, loss: 0.6617658734321594
2023-01-22 22:00:19.783013: step: 50/470, loss: 0.00338426954112947
2023-01-22 22:00:20.555596: step: 52/470, loss: 0.09528716653585434
2023-01-22 22:00:21.279509: step: 54/470, loss: 0.002500073052942753
2023-01-22 22:00:22.031483: step: 56/470, loss: 0.023632550612092018
2023-01-22 22:00:22.751460: step: 58/470, loss: 0.02701537311077118
2023-01-22 22:00:23.447770: step: 60/470, loss: 0.0013945092214271426
2023-01-22 22:00:24.216676: step: 62/470, loss: 0.0031489867251366377
2023-01-22 22:00:24.890074: step: 64/470, loss: 0.0029364058282226324
2023-01-22 22:00:25.588302: step: 66/470, loss: 9.198818588629365e-05
2023-01-22 22:00:26.273905: step: 68/470, loss: 0.011578256264328957
2023-01-22 22:00:26.982105: step: 70/470, loss: 1.6287378912238637e-06
2023-01-22 22:00:27.675176: step: 72/470, loss: 0.013432585634291172
2023-01-22 22:00:28.382671: step: 74/470, loss: 4.559730768960435e-06
2023-01-22 22:00:29.187089: step: 76/470, loss: 0.01460875291377306
2023-01-22 22:00:29.883840: step: 78/470, loss: 0.007790104486048222
2023-01-22 22:00:30.694968: step: 80/470, loss: 0.001107382820919156
2023-01-22 22:00:31.540504: step: 82/470, loss: 0.15270131826400757
2023-01-22 22:00:32.263290: step: 84/470, loss: 0.0016121534863486886
2023-01-22 22:00:32.966763: step: 86/470, loss: 0.013319252990186214
2023-01-22 22:00:33.715288: step: 88/470, loss: 0.001663623726926744
2023-01-22 22:00:34.591531: step: 90/470, loss: 5.101099668536335e-05
2023-01-22 22:00:35.354372: step: 92/470, loss: 0.3214491605758667
2023-01-22 22:00:36.028841: step: 94/470, loss: 0.0008662448963150382
2023-01-22 22:00:36.790747: step: 96/470, loss: 0.002882634988054633
2023-01-22 22:00:37.561905: step: 98/470, loss: 0.041424382477998734
2023-01-22 22:00:38.310408: step: 100/470, loss: 0.00402632774785161
2023-01-22 22:00:39.078962: step: 102/470, loss: 0.018145432695746422
2023-01-22 22:00:39.780840: step: 104/470, loss: 0.0006512062391266227
2023-01-22 22:00:40.482965: step: 106/470, loss: 0.0001297965063713491
2023-01-22 22:00:41.268774: step: 108/470, loss: 0.13866417109966278
2023-01-22 22:00:41.979447: step: 110/470, loss: 0.0011843107640743256
2023-01-22 22:00:42.833997: step: 112/470, loss: 0.0004619006940629333
2023-01-22 22:00:43.594514: step: 114/470, loss: 0.03009113296866417
2023-01-22 22:00:44.294888: step: 116/470, loss: 0.0007518218480981886
2023-01-22 22:00:44.988660: step: 118/470, loss: 0.00045790887088514864
2023-01-22 22:00:45.683622: step: 120/470, loss: 0.005708106327801943
2023-01-22 22:00:46.443968: step: 122/470, loss: 0.00396349374204874
2023-01-22 22:00:47.121502: step: 124/470, loss: 0.0009232903830707073
2023-01-22 22:00:47.937584: step: 126/470, loss: 0.012349043041467667
2023-01-22 22:00:48.710187: step: 128/470, loss: 0.01509046833962202
2023-01-22 22:00:49.455803: step: 130/470, loss: 0.0012966676149517298
2023-01-22 22:00:50.157470: step: 132/470, loss: 0.0010874420404434204
2023-01-22 22:00:50.895428: step: 134/470, loss: 0.001199746155180037
2023-01-22 22:00:51.519119: step: 136/470, loss: 0.04231145977973938
2023-01-22 22:00:52.243225: step: 138/470, loss: 0.0131779033690691
2023-01-22 22:00:52.945915: step: 140/470, loss: 0.7903496623039246
2023-01-22 22:00:53.770506: step: 142/470, loss: 0.00014183785242494196
2023-01-22 22:00:54.525435: step: 144/470, loss: 0.00482182577252388
2023-01-22 22:00:55.246605: step: 146/470, loss: 0.026487575843930244
2023-01-22 22:00:56.044798: step: 148/470, loss: 0.0030447212047874928
2023-01-22 22:00:56.788713: step: 150/470, loss: 6.557068263646215e-05
2023-01-22 22:00:57.506523: step: 152/470, loss: 0.0004728731291834265
2023-01-22 22:00:58.309975: step: 154/470, loss: 0.0145382359623909
2023-01-22 22:00:58.987801: step: 156/470, loss: 0.0035765781067311764
2023-01-22 22:00:59.720960: step: 158/470, loss: 0.0564517006278038
2023-01-22 22:01:00.426918: step: 160/470, loss: 0.0001131351527874358
2023-01-22 22:01:01.137432: step: 162/470, loss: 0.005984265822917223
2023-01-22 22:01:01.811937: step: 164/470, loss: 0.012996729463338852
2023-01-22 22:01:02.480242: step: 166/470, loss: 0.03707212582230568
2023-01-22 22:01:03.313460: step: 168/470, loss: 0.08814679831266403
2023-01-22 22:01:04.105662: step: 170/470, loss: 0.01129702664911747
2023-01-22 22:01:04.788412: step: 172/470, loss: 4.848052776651457e-05
2023-01-22 22:01:05.597758: step: 174/470, loss: 0.08441205322742462
2023-01-22 22:01:06.339949: step: 176/470, loss: 0.005867713131010532
2023-01-22 22:01:07.046306: step: 178/470, loss: 0.00030190395773388445
2023-01-22 22:01:07.780889: step: 180/470, loss: 0.009309839457273483
2023-01-22 22:01:08.512500: step: 182/470, loss: 0.005093792919069529
2023-01-22 22:01:09.271950: step: 184/470, loss: 0.0002611110976431519
2023-01-22 22:01:10.003478: step: 186/470, loss: 0.0002226200158474967
2023-01-22 22:01:10.773650: step: 188/470, loss: 0.015231126919388771
2023-01-22 22:01:11.439522: step: 190/470, loss: 0.045069869607686996
2023-01-22 22:01:12.111897: step: 192/470, loss: 0.15897539258003235
2023-01-22 22:01:12.823671: step: 194/470, loss: 0.003946701996028423
2023-01-22 22:01:13.509233: step: 196/470, loss: 0.0025108088739216328
2023-01-22 22:01:14.250436: step: 198/470, loss: 0.0012698525097221136
2023-01-22 22:01:15.043645: step: 200/470, loss: 0.6876391172409058
2023-01-22 22:01:15.782238: step: 202/470, loss: 0.004398363176733255
2023-01-22 22:01:16.623269: step: 204/470, loss: 0.01833234541118145
2023-01-22 22:01:17.283386: step: 206/470, loss: 0.0011467249132692814
2023-01-22 22:01:17.984406: step: 208/470, loss: 0.00026933234767057
2023-01-22 22:01:18.740055: step: 210/470, loss: 0.00012024387979181483
2023-01-22 22:01:19.447819: step: 212/470, loss: 0.024397404864430428
2023-01-22 22:01:20.188744: step: 214/470, loss: 0.0003621695504989475
2023-01-22 22:01:20.885656: step: 216/470, loss: 0.0002858054649550468
2023-01-22 22:01:21.657124: step: 218/470, loss: 1.0421897172927856
2023-01-22 22:01:22.426520: step: 220/470, loss: 0.007457996252924204
2023-01-22 22:01:23.132436: step: 222/470, loss: 0.004006984643638134
2023-01-22 22:01:23.782790: step: 224/470, loss: 0.0020408506970852613
2023-01-22 22:01:24.448469: step: 226/470, loss: 0.007179014850407839
2023-01-22 22:01:25.189041: step: 228/470, loss: 0.0010738419368863106
2023-01-22 22:01:25.914782: step: 230/470, loss: 0.0004274783132132143
2023-01-22 22:01:26.621736: step: 232/470, loss: 0.0001489683927502483
2023-01-22 22:01:27.390587: step: 234/470, loss: 0.00039236308657564223
2023-01-22 22:01:28.093013: step: 236/470, loss: 0.0004236626555211842
2023-01-22 22:01:28.887699: step: 238/470, loss: 0.003484722226858139
2023-01-22 22:01:29.605803: step: 240/470, loss: 0.3052813410758972
2023-01-22 22:01:30.297787: step: 242/470, loss: 0.0012881134171038866
2023-01-22 22:01:30.961675: step: 244/470, loss: 0.0002472828491590917
2023-01-22 22:01:31.625399: step: 246/470, loss: 0.002726994687691331
2023-01-22 22:01:32.384814: step: 248/470, loss: 0.06096314638853073
2023-01-22 22:01:33.095343: step: 250/470, loss: 0.006045083049684763
2023-01-22 22:01:33.739465: step: 252/470, loss: 0.003386293537914753
2023-01-22 22:01:34.481238: step: 254/470, loss: 0.0014597978442907333
2023-01-22 22:01:35.205672: step: 256/470, loss: 0.022637123242020607
2023-01-22 22:01:36.070340: step: 258/470, loss: 0.0008558848057873547
2023-01-22 22:01:36.839482: step: 260/470, loss: 0.0035284487530589104
2023-01-22 22:01:37.608818: step: 262/470, loss: 4.839608664042316e-06
2023-01-22 22:01:38.367438: step: 264/470, loss: 0.0002396140480414033
2023-01-22 22:01:39.094061: step: 266/470, loss: 0.0001242422586074099
2023-01-22 22:01:39.840889: step: 268/470, loss: 0.006238142028450966
2023-01-22 22:01:40.542807: step: 270/470, loss: 0.001572537119500339
2023-01-22 22:01:41.202440: step: 272/470, loss: 0.0011656886199489236
2023-01-22 22:01:42.021767: step: 274/470, loss: 0.047970063984394073
2023-01-22 22:01:42.813731: step: 276/470, loss: 0.017633995041251183
2023-01-22 22:01:43.560590: step: 278/470, loss: 0.00019742750737350434
2023-01-22 22:01:44.274600: step: 280/470, loss: 0.12787386775016785
2023-01-22 22:01:45.040104: step: 282/470, loss: 0.009434567764401436
2023-01-22 22:01:45.762479: step: 284/470, loss: 0.013597944751381874
2023-01-22 22:01:46.504270: step: 286/470, loss: 0.00370029010809958
2023-01-22 22:01:47.211741: step: 288/470, loss: 0.04034204035997391
2023-01-22 22:01:47.966986: step: 290/470, loss: 0.0010682768188416958
2023-01-22 22:01:48.698679: step: 292/470, loss: 0.003589589847251773
2023-01-22 22:01:49.450876: step: 294/470, loss: 0.0023420064244419336
2023-01-22 22:01:50.211573: step: 296/470, loss: 0.2466408759355545
2023-01-22 22:01:50.990834: step: 298/470, loss: 0.028866639360785484
2023-01-22 22:01:51.703947: step: 300/470, loss: 0.002564261667430401
2023-01-22 22:01:52.434061: step: 302/470, loss: 0.02908160910010338
2023-01-22 22:01:53.230780: step: 304/470, loss: 0.01281247939914465
2023-01-22 22:01:53.933148: step: 306/470, loss: 0.0089055011048913
2023-01-22 22:01:54.669295: step: 308/470, loss: 0.0027301160153001547
2023-01-22 22:01:55.387698: step: 310/470, loss: 0.0009317622752860188
2023-01-22 22:01:56.065523: step: 312/470, loss: 0.0025892360135912895
2023-01-22 22:01:56.840575: step: 314/470, loss: 0.00038833668804727495
2023-01-22 22:01:57.580348: step: 316/470, loss: 0.011556989513337612
2023-01-22 22:01:58.282204: step: 318/470, loss: 0.0006725000566802919
2023-01-22 22:01:59.008002: step: 320/470, loss: 0.005721176974475384
2023-01-22 22:01:59.721268: step: 322/470, loss: 0.000432559143519029
2023-01-22 22:02:00.506663: step: 324/470, loss: 0.026360701769590378
2023-01-22 22:02:01.314776: step: 326/470, loss: 0.002206456381827593
2023-01-22 22:02:02.019973: step: 328/470, loss: 0.0021658348850905895
2023-01-22 22:02:02.737916: step: 330/470, loss: 0.0009932523826137185
2023-01-22 22:02:03.470752: step: 332/470, loss: 0.01891978457570076
2023-01-22 22:02:04.229211: step: 334/470, loss: 0.0009264256223104894
2023-01-22 22:02:05.021984: step: 336/470, loss: 0.03548232465982437
2023-01-22 22:02:05.737688: step: 338/470, loss: 0.0002263460773974657
2023-01-22 22:02:06.374875: step: 340/470, loss: 0.0013739075511693954
2023-01-22 22:02:07.110865: step: 342/470, loss: 0.29935917258262634
2023-01-22 22:02:07.899470: step: 344/470, loss: 0.007482586428523064
2023-01-22 22:02:08.548093: step: 346/470, loss: 0.012100168503820896
2023-01-22 22:02:09.258593: step: 348/470, loss: 0.00046900202869437635
2023-01-22 22:02:10.028544: step: 350/470, loss: 0.0212935209274292
2023-01-22 22:02:10.771977: step: 352/470, loss: 0.000681842677295208
2023-01-22 22:02:11.541005: step: 354/470, loss: 0.006671892944723368
2023-01-22 22:02:12.332705: step: 356/470, loss: 0.024509701877832413
2023-01-22 22:02:13.038769: step: 358/470, loss: 0.0007479641353711486
2023-01-22 22:02:13.783258: step: 360/470, loss: 0.06951668113470078
2023-01-22 22:02:14.578008: step: 362/470, loss: 0.02821964956820011
2023-01-22 22:02:15.281928: step: 364/470, loss: 0.005078599322587252
2023-01-22 22:02:16.057398: step: 366/470, loss: 0.021827857941389084
2023-01-22 22:02:16.818154: step: 368/470, loss: 0.0009424221352674067
2023-01-22 22:02:17.536744: step: 370/470, loss: 0.38306307792663574
2023-01-22 22:02:18.285474: step: 372/470, loss: 0.0023595362436026335
2023-01-22 22:02:19.031388: step: 374/470, loss: 0.01760093681514263
2023-01-22 22:02:19.715810: step: 376/470, loss: 0.0019117107149213552
2023-01-22 22:02:20.418627: step: 378/470, loss: 0.010603736154735088
2023-01-22 22:02:21.131628: step: 380/470, loss: 0.0070642814971506596
2023-01-22 22:02:21.900623: step: 382/470, loss: 0.0003894304682034999
2023-01-22 22:02:22.635137: step: 384/470, loss: 0.003691543824970722
2023-01-22 22:02:23.370036: step: 386/470, loss: 0.07347030937671661
2023-01-22 22:02:24.155481: step: 388/470, loss: 0.0005422882386483252
2023-01-22 22:02:24.864133: step: 390/470, loss: 0.10034418106079102
2023-01-22 22:02:25.490777: step: 392/470, loss: 0.0036059198901057243
2023-01-22 22:02:26.288284: step: 394/470, loss: 0.000504388939589262
2023-01-22 22:02:26.952919: step: 396/470, loss: 0.01450659055262804
2023-01-22 22:02:27.649306: step: 398/470, loss: 0.0029942444525659084
2023-01-22 22:02:28.330824: step: 400/470, loss: 0.0008541368297301233
2023-01-22 22:02:29.042456: step: 402/470, loss: 0.017634334042668343
2023-01-22 22:02:29.727727: step: 404/470, loss: 0.0022887280210852623
2023-01-22 22:02:30.462524: step: 406/470, loss: 0.03916192799806595
2023-01-22 22:02:31.183468: step: 408/470, loss: 0.16810278594493866
2023-01-22 22:02:31.910639: step: 410/470, loss: 0.0020672930404543877
2023-01-22 22:02:32.665183: step: 412/470, loss: 0.01781904324889183
2023-01-22 22:02:33.330443: step: 414/470, loss: 0.001842794707044959
2023-01-22 22:02:34.071183: step: 416/470, loss: 0.021762700751423836
2023-01-22 22:02:34.792531: step: 418/470, loss: 0.013885277323424816
2023-01-22 22:02:35.437098: step: 420/470, loss: 0.0006842563161626458
2023-01-22 22:02:36.144736: step: 422/470, loss: 0.0057321698404848576
2023-01-22 22:02:36.814809: step: 424/470, loss: 0.009932457469403744
2023-01-22 22:02:37.612663: step: 426/470, loss: 0.008049868047237396
2023-01-22 22:02:38.316979: step: 428/470, loss: 0.005516226403415203
2023-01-22 22:02:39.080591: step: 430/470, loss: 0.0049128164537250996
2023-01-22 22:02:39.878891: step: 432/470, loss: 0.1927299201488495
2023-01-22 22:02:40.561079: step: 434/470, loss: 0.007491968106478453
2023-01-22 22:02:41.251625: step: 436/470, loss: 0.009216003119945526
2023-01-22 22:02:41.906167: step: 438/470, loss: 0.00041842067730613053
2023-01-22 22:02:42.599334: step: 440/470, loss: 0.0009216439793817699
2023-01-22 22:02:43.306067: step: 442/470, loss: 0.14297710359096527
2023-01-22 22:02:44.043940: step: 444/470, loss: 0.04162221401929855
2023-01-22 22:02:44.778024: step: 446/470, loss: 0.01259060762822628
2023-01-22 22:02:45.523003: step: 448/470, loss: 0.02452508918941021
2023-01-22 22:02:46.220244: step: 450/470, loss: 0.008215454407036304
2023-01-22 22:02:46.963830: step: 452/470, loss: 9.857612894847989e-05
2023-01-22 22:02:47.686421: step: 454/470, loss: 0.004926904104650021
2023-01-22 22:02:48.381583: step: 456/470, loss: 0.00019339239224791527
2023-01-22 22:02:49.037490: step: 458/470, loss: 0.0010940470965579152
2023-01-22 22:02:49.795433: step: 460/470, loss: 0.0007743262685835361
2023-01-22 22:02:50.610041: step: 462/470, loss: 0.00038364637293852866
2023-01-22 22:02:51.380370: step: 464/470, loss: 0.001179278246127069
2023-01-22 22:02:52.120934: step: 466/470, loss: 0.007702074479311705
2023-01-22 22:02:52.873219: step: 468/470, loss: 0.00043093261774629354
2023-01-22 22:02:53.606244: step: 470/470, loss: 0.05112699419260025
2023-01-22 22:02:54.405744: step: 472/470, loss: 0.015505004674196243
2023-01-22 22:02:55.116260: step: 474/470, loss: 0.0007698743138462305
2023-01-22 22:02:55.867858: step: 476/470, loss: 0.15226824581623077
2023-01-22 22:02:56.566376: step: 478/470, loss: 0.00011416709457989782
2023-01-22 22:02:57.251945: step: 480/470, loss: 0.009174869395792484
2023-01-22 22:02:58.020254: step: 482/470, loss: 0.06859564036130905
2023-01-22 22:02:58.821885: step: 484/470, loss: 0.0012576787266880274
2023-01-22 22:02:59.507872: step: 486/470, loss: 0.0073244026862084866
2023-01-22 22:03:00.245641: step: 488/470, loss: 0.0008550825295969844
2023-01-22 22:03:00.959699: step: 490/470, loss: 0.05312467738986015
2023-01-22 22:03:01.672035: step: 492/470, loss: 0.022805843502283096
2023-01-22 22:03:02.431854: step: 494/470, loss: 0.005543670151382685
2023-01-22 22:03:03.137982: step: 496/470, loss: 0.0007484982488676906
2023-01-22 22:03:03.835700: step: 498/470, loss: 0.06718970835208893
2023-01-22 22:03:04.565433: step: 500/470, loss: 0.013428159058094025
2023-01-22 22:03:05.283364: step: 502/470, loss: 0.027854073792696
2023-01-22 22:03:05.992032: step: 504/470, loss: 0.010355038568377495
2023-01-22 22:03:06.750007: step: 506/470, loss: 0.02420848049223423
2023-01-22 22:03:07.440858: step: 508/470, loss: 2.1866453607799485e-05
2023-01-22 22:03:08.149294: step: 510/470, loss: 0.010722950100898743
2023-01-22 22:03:08.842212: step: 512/470, loss: 0.0001193592615891248
2023-01-22 22:03:09.589088: step: 514/470, loss: 0.4225482940673828
2023-01-22 22:03:10.339435: step: 516/470, loss: 0.015295075252652168
2023-01-22 22:03:11.091770: step: 518/470, loss: 0.32571691274642944
2023-01-22 22:03:11.805280: step: 520/470, loss: 0.0004058307677041739
2023-01-22 22:03:12.560079: step: 522/470, loss: 0.019950976595282555
2023-01-22 22:03:13.302175: step: 524/470, loss: 0.014127479866147041
2023-01-22 22:03:14.074235: step: 526/470, loss: 0.000844079302623868
2023-01-22 22:03:14.730573: step: 528/470, loss: 0.0007464765221811831
2023-01-22 22:03:15.477265: step: 530/470, loss: 0.0009180636261589825
2023-01-22 22:03:16.178540: step: 532/470, loss: 0.0004960569203831255
2023-01-22 22:03:16.866535: step: 534/470, loss: 0.0015324270352721214
2023-01-22 22:03:17.687335: step: 536/470, loss: 0.74675053358078
2023-01-22 22:03:18.328575: step: 538/470, loss: 0.0016997962957248092
2023-01-22 22:03:19.061102: step: 540/470, loss: 0.03810073807835579
2023-01-22 22:03:19.768842: step: 542/470, loss: 0.02312638983130455
2023-01-22 22:03:20.557793: step: 544/470, loss: 0.20076841115951538
2023-01-22 22:03:21.272500: step: 546/470, loss: 0.044742703437805176
2023-01-22 22:03:21.977044: step: 548/470, loss: 0.033179204910993576
2023-01-22 22:03:22.723439: step: 550/470, loss: 0.048377711325883865
2023-01-22 22:03:23.503274: step: 552/470, loss: 0.006665708031505346
2023-01-22 22:03:24.287346: step: 554/470, loss: 0.011248448863625526
2023-01-22 22:03:24.985515: step: 556/470, loss: 0.010977053083479404
2023-01-22 22:03:25.761243: step: 558/470, loss: 0.007646726910024881
2023-01-22 22:03:26.502475: step: 560/470, loss: 0.0020836268085986376
2023-01-22 22:03:27.201371: step: 562/470, loss: 0.00017479869711678475
2023-01-22 22:03:27.963155: step: 564/470, loss: 0.002762383548542857
2023-01-22 22:03:28.684164: step: 566/470, loss: 0.0010429834946990013
2023-01-22 22:03:29.395264: step: 568/470, loss: 0.02210627682507038
2023-01-22 22:03:30.120481: step: 570/470, loss: 3.689844015752897e-05
2023-01-22 22:03:30.812333: step: 572/470, loss: 0.06625575572252274
2023-01-22 22:03:31.468021: step: 574/470, loss: 0.006409522611647844
2023-01-22 22:03:32.294933: step: 576/470, loss: 0.0005805494729429483
2023-01-22 22:03:33.065958: step: 578/470, loss: 0.012947368435561657
2023-01-22 22:03:33.815609: step: 580/470, loss: 0.00042535990360192955
2023-01-22 22:03:34.476409: step: 582/470, loss: 0.00019787903875112534
2023-01-22 22:03:35.147179: step: 584/470, loss: 0.14290878176689148
2023-01-22 22:03:35.948090: step: 586/470, loss: 0.013853715732693672
2023-01-22 22:03:36.673709: step: 588/470, loss: 0.030745120719075203
2023-01-22 22:03:37.333900: step: 590/470, loss: 0.0006633042357861996
2023-01-22 22:03:38.051024: step: 592/470, loss: 0.022054284811019897
2023-01-22 22:03:38.856596: step: 594/470, loss: 0.0035873970482498407
2023-01-22 22:03:39.629520: step: 596/470, loss: 0.001877595204859972
2023-01-22 22:03:40.377224: step: 598/470, loss: 0.021728595718741417
2023-01-22 22:03:41.131033: step: 600/470, loss: 0.0009449566714465618
2023-01-22 22:03:41.880589: step: 602/470, loss: 0.012191184796392918
2023-01-22 22:03:42.592592: step: 604/470, loss: 0.21409592032432556
2023-01-22 22:03:43.254506: step: 606/470, loss: 0.0021795283537358046
2023-01-22 22:03:44.012869: step: 608/470, loss: 0.08947306126356125
2023-01-22 22:03:44.731618: step: 610/470, loss: 0.027726903557777405
2023-01-22 22:03:45.466367: step: 612/470, loss: 0.004544347990304232
2023-01-22 22:03:46.168244: step: 614/470, loss: 0.006356291007250547
2023-01-22 22:03:46.958246: step: 616/470, loss: 0.0020529376342892647
2023-01-22 22:03:47.714919: step: 618/470, loss: 0.0441039502620697
2023-01-22 22:03:48.389219: step: 620/470, loss: 0.05852342024445534
2023-01-22 22:03:49.107819: step: 622/470, loss: 0.0003269554581493139
2023-01-22 22:03:49.821607: step: 624/470, loss: 0.015510090626776218
2023-01-22 22:03:50.497408: step: 626/470, loss: 0.00037635324406437576
2023-01-22 22:03:51.226941: step: 628/470, loss: 0.002281700260937214
2023-01-22 22:03:51.911950: step: 630/470, loss: 0.010925859212875366
2023-01-22 22:03:52.647400: step: 632/470, loss: 0.003865706268697977
2023-01-22 22:03:53.367895: step: 634/470, loss: 0.0007639245595782995
2023-01-22 22:03:54.140384: step: 636/470, loss: 0.04122069478034973
2023-01-22 22:03:54.844898: step: 638/470, loss: 0.013298324309289455
2023-01-22 22:03:55.551052: step: 640/470, loss: 0.007208535913378
2023-01-22 22:03:56.355144: step: 642/470, loss: 0.5793889760971069
2023-01-22 22:03:57.156238: step: 644/470, loss: 0.010782578960061073
2023-01-22 22:03:57.881404: step: 646/470, loss: 0.003287682542577386
2023-01-22 22:03:58.588397: step: 648/470, loss: 0.005844367202371359
2023-01-22 22:03:59.281404: step: 650/470, loss: 0.00159078452270478
2023-01-22 22:03:59.977561: step: 652/470, loss: 0.007373278960585594
2023-01-22 22:04:00.630071: step: 654/470, loss: 0.0001302184391533956
2023-01-22 22:04:01.328028: step: 656/470, loss: 0.002802535193040967
2023-01-22 22:04:02.063225: step: 658/470, loss: 0.028815504163503647
2023-01-22 22:04:02.835474: step: 660/470, loss: 0.0023840556386858225
2023-01-22 22:04:03.567024: step: 662/470, loss: 0.00024311590823344886
2023-01-22 22:04:04.243621: step: 664/470, loss: 1.6967294868663885e-05
2023-01-22 22:04:04.904737: step: 666/470, loss: 0.00038249947829172015
2023-01-22 22:04:05.665276: step: 668/470, loss: 0.0011958489194512367
2023-01-22 22:04:06.471863: step: 670/470, loss: 0.0026525375433266163
2023-01-22 22:04:07.134482: step: 672/470, loss: 0.0011103339493274689
2023-01-22 22:04:07.845628: step: 674/470, loss: 7.855349394958466e-05
2023-01-22 22:04:08.622023: step: 676/470, loss: 0.036018408834934235
2023-01-22 22:04:09.404404: step: 678/470, loss: 0.03961295261979103
2023-01-22 22:04:10.083143: step: 680/470, loss: 0.009320229291915894
2023-01-22 22:04:10.761108: step: 682/470, loss: 0.0022059644106775522
2023-01-22 22:04:11.537967: step: 684/470, loss: 0.07972223311662674
2023-01-22 22:04:12.279666: step: 686/470, loss: 0.003704060334712267
2023-01-22 22:04:13.057668: step: 688/470, loss: 0.5761838555335999
2023-01-22 22:04:13.773090: step: 690/470, loss: 0.002108166925609112
2023-01-22 22:04:14.523749: step: 692/470, loss: 0.001077714143320918
2023-01-22 22:04:15.265369: step: 694/470, loss: 0.03051694482564926
2023-01-22 22:04:15.974596: step: 696/470, loss: 2.4262013539555483e-05
2023-01-22 22:04:16.688050: step: 698/470, loss: 0.009325804188847542
2023-01-22 22:04:17.459623: step: 700/470, loss: 0.0015849667834118009
2023-01-22 22:04:18.168599: step: 702/470, loss: 0.005560775753110647
2023-01-22 22:04:18.969699: step: 704/470, loss: 0.05311994254589081
2023-01-22 22:04:19.738299: step: 706/470, loss: 0.00885532982647419
2023-01-22 22:04:20.468018: step: 708/470, loss: 0.025782722979784012
2023-01-22 22:04:21.142568: step: 710/470, loss: 0.00032764862407930195
2023-01-22 22:04:21.833043: step: 712/470, loss: 0.0006452351808547974
2023-01-22 22:04:22.579535: step: 714/470, loss: 0.018562477082014084
2023-01-22 22:04:23.332219: step: 716/470, loss: 0.004105889238417149
2023-01-22 22:04:24.079485: step: 718/470, loss: 0.004994503688067198
2023-01-22 22:04:24.808029: step: 720/470, loss: 0.015740545466542244
2023-01-22 22:04:25.555337: step: 722/470, loss: 0.002721569035202265
2023-01-22 22:04:26.329005: step: 724/470, loss: 0.0018496755510568619
2023-01-22 22:04:27.030764: step: 726/470, loss: 0.029428904876112938
2023-01-22 22:04:27.833401: step: 728/470, loss: 0.0025027492083609104
2023-01-22 22:04:28.540286: step: 730/470, loss: 0.0005519500700756907
2023-01-22 22:04:29.253840: step: 732/470, loss: 0.00124834175221622
2023-01-22 22:04:29.992308: step: 734/470, loss: 0.025663498789072037
2023-01-22 22:04:30.716290: step: 736/470, loss: 0.00022738105326425284
2023-01-22 22:04:31.580799: step: 738/470, loss: 0.04520634189248085
2023-01-22 22:04:32.300666: step: 740/470, loss: 0.00048320789937861264
2023-01-22 22:04:33.099205: step: 742/470, loss: 0.001786353881470859
2023-01-22 22:04:33.796373: step: 744/470, loss: 0.011439421214163303
2023-01-22 22:04:34.546646: step: 746/470, loss: 0.035814620554447174
2023-01-22 22:04:35.233769: step: 748/470, loss: 0.46565985679626465
2023-01-22 22:04:36.166932: step: 750/470, loss: 0.0016404861817136407
2023-01-22 22:04:36.946146: step: 752/470, loss: 0.006969146430492401
2023-01-22 22:04:37.721366: step: 754/470, loss: 0.011821585707366467
2023-01-22 22:04:38.515851: step: 756/470, loss: 0.0448044054210186
2023-01-22 22:04:39.284567: step: 758/470, loss: 0.0014806183753535151
2023-01-22 22:04:40.010232: step: 760/470, loss: 0.25201913714408875
2023-01-22 22:04:40.686280: step: 762/470, loss: 0.026176057755947113
2023-01-22 22:04:41.392248: step: 764/470, loss: 0.0018919870490208268
2023-01-22 22:04:42.120249: step: 766/470, loss: 6.11542709521018e-05
2023-01-22 22:04:42.952254: step: 768/470, loss: 0.06037821248173714
2023-01-22 22:04:43.680161: step: 770/470, loss: 0.005792189389467239
2023-01-22 22:04:44.402600: step: 772/470, loss: 0.00010853780258912593
2023-01-22 22:04:45.086936: step: 774/470, loss: 3.3160622479044832e-06
2023-01-22 22:04:45.872517: step: 776/470, loss: 0.048592712730169296
2023-01-22 22:04:46.610963: step: 778/470, loss: 0.0152989961206913
2023-01-22 22:04:47.327292: step: 780/470, loss: 0.027926130220294
2023-01-22 22:04:48.020189: step: 782/470, loss: 0.0008958295802585781
2023-01-22 22:04:48.636177: step: 784/470, loss: 0.00017820145876612514
2023-01-22 22:04:49.365395: step: 786/470, loss: 0.028859004378318787
2023-01-22 22:04:50.043968: step: 788/470, loss: 0.009325975552201271
2023-01-22 22:04:50.687819: step: 790/470, loss: 0.018157802522182465
2023-01-22 22:04:51.390814: step: 792/470, loss: 5.18089764227625e-05
2023-01-22 22:04:52.152726: step: 794/470, loss: 0.0016927659744396806
2023-01-22 22:04:52.863655: step: 796/470, loss: 0.004147370811551809
2023-01-22 22:04:53.550834: step: 798/470, loss: 0.002366115804761648
2023-01-22 22:04:54.295721: step: 800/470, loss: 0.08526662737131119
2023-01-22 22:04:54.971690: step: 802/470, loss: 0.02207419089972973
2023-01-22 22:04:55.805657: step: 804/470, loss: 0.00026135783991776407
2023-01-22 22:04:56.483226: step: 806/470, loss: 0.017718037590384483
2023-01-22 22:04:57.256671: step: 808/470, loss: 0.009163436479866505
2023-01-22 22:04:57.966641: step: 810/470, loss: 0.049685999751091
2023-01-22 22:04:58.744821: step: 812/470, loss: 0.004708106629550457
2023-01-22 22:04:59.426470: step: 814/470, loss: 0.01260793674737215
2023-01-22 22:05:00.115675: step: 816/470, loss: 0.7914705276489258
2023-01-22 22:05:00.868279: step: 818/470, loss: 0.007497282233089209
2023-01-22 22:05:01.644645: step: 820/470, loss: 0.0009469312499277294
2023-01-22 22:05:02.400587: step: 822/470, loss: 0.001793618779629469
2023-01-22 22:05:03.101639: step: 824/470, loss: 0.025681249797344208
2023-01-22 22:05:03.837690: step: 826/470, loss: 0.037340566515922546
2023-01-22 22:05:04.576750: step: 828/470, loss: 0.00744800828397274
2023-01-22 22:05:05.341530: step: 830/470, loss: 1.3749153367825784e-05
2023-01-22 22:05:06.027300: step: 832/470, loss: 0.014599119313061237
2023-01-22 22:05:06.810867: step: 834/470, loss: 0.0006064804038032889
2023-01-22 22:05:07.531485: step: 836/470, loss: 0.0008935255464166403
2023-01-22 22:05:08.265002: step: 838/470, loss: 0.003527364693582058
2023-01-22 22:05:09.065349: step: 840/470, loss: 0.0005473060882650316
2023-01-22 22:05:09.887098: step: 842/470, loss: 0.10252714157104492
2023-01-22 22:05:10.614277: step: 844/470, loss: 0.004621810279786587
2023-01-22 22:05:11.473738: step: 846/470, loss: 0.0056939744390547276
2023-01-22 22:05:12.162384: step: 848/470, loss: 0.021790560334920883
2023-01-22 22:05:12.887249: step: 850/470, loss: 0.011583208106458187
2023-01-22 22:05:13.578872: step: 852/470, loss: 0.002285032533109188
2023-01-22 22:05:14.300107: step: 854/470, loss: 0.0009343082783743739
2023-01-22 22:05:15.061367: step: 856/470, loss: 0.006179484073072672
2023-01-22 22:05:15.754981: step: 858/470, loss: 0.007022823207080364
2023-01-22 22:05:16.516628: step: 860/470, loss: 0.01619824767112732
2023-01-22 22:05:17.236056: step: 862/470, loss: 0.0002929774345830083
2023-01-22 22:05:17.963895: step: 864/470, loss: 0.01771281473338604
2023-01-22 22:05:18.658431: step: 866/470, loss: 1.254774360859301e-05
2023-01-22 22:05:19.451764: step: 868/470, loss: 0.001473193638958037
2023-01-22 22:05:20.194322: step: 870/470, loss: 0.001364637166261673
2023-01-22 22:05:20.872058: step: 872/470, loss: 0.0011659307638183236
2023-01-22 22:05:21.560118: step: 874/470, loss: 0.0024868298787623644
2023-01-22 22:05:22.179440: step: 876/470, loss: 0.0011807549744844437
2023-01-22 22:05:22.821182: step: 878/470, loss: 0.00360662373714149
2023-01-22 22:05:23.578028: step: 880/470, loss: 0.0015713890315964818
2023-01-22 22:05:24.255559: step: 882/470, loss: 6.543661584146321e-05
2023-01-22 22:05:24.965016: step: 884/470, loss: 0.004186991136521101
2023-01-22 22:05:25.692151: step: 886/470, loss: 0.0009998814202845097
2023-01-22 22:05:26.419809: step: 888/470, loss: 0.0374150276184082
2023-01-22 22:05:27.271773: step: 890/470, loss: 0.01954301819205284
2023-01-22 22:05:28.001337: step: 892/470, loss: 0.0002561210421845317
2023-01-22 22:05:28.758930: step: 894/470, loss: 0.0005132320802658796
2023-01-22 22:05:29.495350: step: 896/470, loss: 0.07816541939973831
2023-01-22 22:05:30.267169: step: 898/470, loss: 0.014139272272586823
2023-01-22 22:05:30.991710: step: 900/470, loss: 0.00017748454411048442
2023-01-22 22:05:31.792533: step: 902/470, loss: 0.0016783780883997679
2023-01-22 22:05:32.565434: step: 904/470, loss: 0.022887928411364555
2023-01-22 22:05:33.277998: step: 906/470, loss: 0.0025164291728287935
2023-01-22 22:05:33.979530: step: 908/470, loss: 0.0015736209461465478
2023-01-22 22:05:34.672663: step: 910/470, loss: 5.445835540740518e-06
2023-01-22 22:05:35.432646: step: 912/470, loss: 0.003006444312632084
2023-01-22 22:05:36.200308: step: 914/470, loss: 0.05807241424918175
2023-01-22 22:05:37.036823: step: 916/470, loss: 0.008495689369738102
2023-01-22 22:05:37.708568: step: 918/470, loss: 0.0016545577673241496
2023-01-22 22:05:38.431325: step: 920/470, loss: 0.0005608369829133153
2023-01-22 22:05:39.178700: step: 922/470, loss: 0.1146390438079834
2023-01-22 22:05:39.928345: step: 924/470, loss: 0.00022846035426482558
2023-01-22 22:05:40.592273: step: 926/470, loss: 0.14736011624336243
2023-01-22 22:05:41.249122: step: 928/470, loss: 0.00010952012962661684
2023-01-22 22:05:42.043777: step: 930/470, loss: 0.3251962661743164
2023-01-22 22:05:42.858949: step: 932/470, loss: 0.005167566705495119
2023-01-22 22:05:43.590108: step: 934/470, loss: 0.03677722439169884
2023-01-22 22:05:44.456533: step: 936/470, loss: 0.00461982935667038
2023-01-22 22:05:45.236959: step: 938/470, loss: 7.254021329572424e-05
2023-01-22 22:05:45.991813: step: 940/470, loss: 0.014099986292421818
2023-01-22 22:05:46.637525: step: 942/470, loss: 0.00016049730766098946
==================================================
Loss: 0.037
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.290494644497469, 'r': 0.3428608517598211, 'f1': 0.3145129136247619}, 'combined': 0.2317463574077193, 'epoch': 39}
Test Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35179975638777394, 'r': 0.3676983992245291, 'f1': 0.359573422842981}, 'combined': 0.25044915023889225, 'epoch': 39}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2817969659652227, 'r': 0.34596325802561495, 'f1': 0.31060074442844815}, 'combined': 0.2288637064209618, 'epoch': 39}
Test Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35111378537428956, 'r': 0.36293011468977043, 'f1': 0.35692417898568446}, 'combined': 0.24860390576117328, 'epoch': 39}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2717336703062838, 'r': 0.36042094031137073, 'f1': 0.3098561754389762}, 'combined': 0.2283150766392456, 'epoch': 39}
Test Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.34380852167795695, 'r': 0.3795117143137448, 'f1': 0.3607789605907629}, 'combined': 0.2512888282721732, 'epoch': 39}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.20161290322580644, 'r': 0.35714285714285715, 'f1': 0.25773195876288657}, 'combined': 0.17182130584192437, 'epoch': 39}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.26973684210526316, 'r': 0.44565217391304346, 'f1': 0.3360655737704918}, 'combined': 0.1680327868852459, 'epoch': 39}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4166666666666667, 'r': 0.3017241379310345, 'f1': 0.35}, 'combined': 0.2333333333333333, 'epoch': 39}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923636226642556, 'r': 0.3067876344086022, 'f1': 0.2994020061728395}, 'combined': 0.22061200454840804, 'epoch': 14}
Test for Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3454664828223071, 'r': 0.36074673110098604, 'f1': 0.352941298537183}, 'combined': 0.24582976017515235, 'epoch': 14}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2734375, 'r': 0.375, 'f1': 0.31626506024096385}, 'combined': 0.2108433734939759, 'epoch': 14}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30551046597601705, 'r': 0.32638025112807895, 'f1': 0.3156007198981608}, 'combined': 0.232547898872329, 'epoch': 18}
Test for Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.35064055717249865, 'r': 0.36344011641606727, 'f1': 0.3569256237633264}, 'combined': 0.2486049120739587, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3026315789473684, 'r': 0.5, 'f1': 0.3770491803278689}, 'combined': 0.18852459016393444, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2827471864951769, 'r': 0.3337167931688805, 'f1': 0.3061248912097476}, 'combined': 0.2255657093124456, 'epoch': 17}
Test for Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5511811023622047, 'f1': 0.6965174129353234}, 'slot': {'p': 0.3364419482005735, 'r': 0.34355898941250873, 'f1': 0.33996322453759187}, 'combined': 0.23679030564807396, 'epoch': 17}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4673913043478261, 'r': 0.3706896551724138, 'f1': 0.4134615384615385}, 'combined': 0.27564102564102566, 'epoch': 17}