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.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.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.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.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.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.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.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.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.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.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.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.hospitalized-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.hospitalized-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.hospitalized-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.hospitalized-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-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.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.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.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-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.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.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.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.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.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.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.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.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.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.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-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.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.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.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 09:29:03.303233: step: 2/466, loss: 13.076241493225098
2023-01-22 09:29:03.857142: step: 4/466, loss: 12.855111122131348
2023-01-22 09:29:04.465850: step: 6/466, loss: 8.903879165649414
2023-01-22 09:29:05.150111: step: 8/466, loss: 14.036937713623047
2023-01-22 09:29:05.754611: step: 10/466, loss: 10.639755249023438
2023-01-22 09:29:06.374131: step: 12/466, loss: 12.28707218170166
2023-01-22 09:29:07.055499: step: 14/466, loss: 22.052391052246094
2023-01-22 09:29:07.596187: step: 16/466, loss: 14.403186798095703
2023-01-22 09:29:08.215679: step: 18/466, loss: 14.720062255859375
2023-01-22 09:29:08.835975: step: 20/466, loss: 14.548443794250488
2023-01-22 09:29:09.444903: step: 22/466, loss: 12.669960021972656
2023-01-22 09:29:10.114099: step: 24/466, loss: 26.453371047973633
2023-01-22 09:29:10.757913: step: 26/466, loss: 16.097545623779297
2023-01-22 09:29:11.378453: step: 28/466, loss: 10.801416397094727
2023-01-22 09:29:12.078625: step: 30/466, loss: 5.212574005126953
2023-01-22 09:29:12.730541: step: 32/466, loss: 22.528642654418945
2023-01-22 09:29:13.359026: step: 34/466, loss: 4.774672031402588
2023-01-22 09:29:13.932917: step: 36/466, loss: 17.159042358398438
2023-01-22 09:29:14.530985: step: 38/466, loss: 18.028188705444336
2023-01-22 09:29:15.145412: step: 40/466, loss: 5.712503910064697
2023-01-22 09:29:15.705278: step: 42/466, loss: 12.436981201171875
2023-01-22 09:29:16.287040: step: 44/466, loss: 7.921031475067139
2023-01-22 09:29:16.934486: step: 46/466, loss: 13.548808097839355
2023-01-22 09:29:17.525518: step: 48/466, loss: 5.939296722412109
2023-01-22 09:29:18.192310: step: 50/466, loss: 6.09789514541626
2023-01-22 09:29:18.796069: step: 52/466, loss: 5.971683502197266
2023-01-22 09:29:19.408450: step: 54/466, loss: 19.42380714416504
2023-01-22 09:29:19.972152: step: 56/466, loss: 19.322917938232422
2023-01-22 09:29:20.639318: step: 58/466, loss: 16.892105102539062
2023-01-22 09:29:21.283462: step: 60/466, loss: 13.79200267791748
2023-01-22 09:29:21.908798: step: 62/466, loss: 10.073508262634277
2023-01-22 09:29:22.517666: step: 64/466, loss: 9.672430992126465
2023-01-22 09:29:23.128601: step: 66/466, loss: 16.316783905029297
2023-01-22 09:29:23.747768: step: 68/466, loss: 15.566567420959473
2023-01-22 09:29:24.329199: step: 70/466, loss: 13.069356918334961
2023-01-22 09:29:25.031913: step: 72/466, loss: 6.8840131759643555
2023-01-22 09:29:25.605530: step: 74/466, loss: 12.612266540527344
2023-01-22 09:29:26.245162: step: 76/466, loss: 5.053008079528809
2023-01-22 09:29:26.852191: step: 78/466, loss: 25.458084106445312
2023-01-22 09:29:27.457024: step: 80/466, loss: 12.025644302368164
2023-01-22 09:29:28.095413: step: 82/466, loss: 18.070756912231445
2023-01-22 09:29:28.759971: step: 84/466, loss: 12.265995979309082
2023-01-22 09:29:29.421440: step: 86/466, loss: 5.9723334312438965
2023-01-22 09:29:30.082171: step: 88/466, loss: 23.769235610961914
2023-01-22 09:29:30.771441: step: 90/466, loss: 11.45355224609375
2023-01-22 09:29:31.398462: step: 92/466, loss: 19.209590911865234
2023-01-22 09:29:32.001401: step: 94/466, loss: 5.9348039627075195
2023-01-22 09:29:32.674448: step: 96/466, loss: 20.47209930419922
2023-01-22 09:29:33.356562: step: 98/466, loss: 15.648857116699219
2023-01-22 09:29:33.935369: step: 100/466, loss: 26.48772430419922
2023-01-22 09:29:34.590738: step: 102/466, loss: 23.994529724121094
2023-01-22 09:29:35.200852: step: 104/466, loss: 4.9366841316223145
2023-01-22 09:29:35.842058: step: 106/466, loss: 6.385857105255127
2023-01-22 09:29:36.445008: step: 108/466, loss: 16.829540252685547
2023-01-22 09:29:37.113959: step: 110/466, loss: 14.721445083618164
2023-01-22 09:29:37.707767: step: 112/466, loss: 15.021709442138672
2023-01-22 09:29:38.406875: step: 114/466, loss: 16.95585060119629
2023-01-22 09:29:39.115405: step: 116/466, loss: 5.885819435119629
2023-01-22 09:29:39.692462: step: 118/466, loss: 22.682077407836914
2023-01-22 09:29:40.271056: step: 120/466, loss: 8.589439392089844
2023-01-22 09:29:40.850924: step: 122/466, loss: 7.018434524536133
2023-01-22 09:29:41.405062: step: 124/466, loss: 15.75301742553711
2023-01-22 09:29:42.005691: step: 126/466, loss: 10.034443855285645
2023-01-22 09:29:42.638634: step: 128/466, loss: 7.172554969787598
2023-01-22 09:29:43.278663: step: 130/466, loss: 16.368778228759766
2023-01-22 09:29:43.929516: step: 132/466, loss: 7.45112419128418
2023-01-22 09:29:44.543442: step: 134/466, loss: 9.522209167480469
2023-01-22 09:29:45.203350: step: 136/466, loss: 17.63762664794922
2023-01-22 09:29:45.849094: step: 138/466, loss: 8.851346015930176
2023-01-22 09:29:46.499908: step: 140/466, loss: 14.376631736755371
2023-01-22 09:29:47.133960: step: 142/466, loss: 7.4392409324646
2023-01-22 09:29:47.769348: step: 144/466, loss: 4.238392353057861
2023-01-22 09:29:48.422797: step: 146/466, loss: 5.5457048416137695
2023-01-22 09:29:49.081865: step: 148/466, loss: 12.26491928100586
2023-01-22 09:29:49.734821: step: 150/466, loss: 15.939020156860352
2023-01-22 09:29:50.386068: step: 152/466, loss: 4.8080153465271
2023-01-22 09:29:50.992108: step: 154/466, loss: 17.984691619873047
2023-01-22 09:29:51.594210: step: 156/466, loss: 3.5370397567749023
2023-01-22 09:29:52.199495: step: 158/466, loss: 8.747307777404785
2023-01-22 09:29:52.850301: step: 160/466, loss: 6.944577217102051
2023-01-22 09:29:53.458129: step: 162/466, loss: 15.041013717651367
2023-01-22 09:29:54.092680: step: 164/466, loss: 17.815420150756836
2023-01-22 09:29:54.909044: step: 166/466, loss: 12.960419654846191
2023-01-22 09:29:55.552200: step: 168/466, loss: 16.44618797302246
2023-01-22 09:29:56.220740: step: 170/466, loss: 5.99251651763916
2023-01-22 09:29:56.829731: step: 172/466, loss: 3.8540897369384766
2023-01-22 09:29:57.430843: step: 174/466, loss: 11.568319320678711
2023-01-22 09:29:58.049338: step: 176/466, loss: 13.330349922180176
2023-01-22 09:29:58.656403: step: 178/466, loss: 15.725419998168945
2023-01-22 09:29:59.292014: step: 180/466, loss: 4.868077278137207
2023-01-22 09:29:59.923380: step: 182/466, loss: 4.35472297668457
2023-01-22 09:30:00.573472: step: 184/466, loss: 6.567266941070557
2023-01-22 09:30:01.190697: step: 186/466, loss: 3.5111114978790283
2023-01-22 09:30:01.838362: step: 188/466, loss: 11.336760520935059
2023-01-22 09:30:02.469498: step: 190/466, loss: 3.495755672454834
2023-01-22 09:30:03.058824: step: 192/466, loss: 3.3268911838531494
2023-01-22 09:30:03.706023: step: 194/466, loss: 12.559239387512207
2023-01-22 09:30:04.370769: step: 196/466, loss: 13.295437812805176
2023-01-22 09:30:04.996090: step: 198/466, loss: 12.328798294067383
2023-01-22 09:30:05.599172: step: 200/466, loss: 4.826976299285889
2023-01-22 09:30:06.219160: step: 202/466, loss: 8.107643127441406
2023-01-22 09:30:06.802551: step: 204/466, loss: 12.581511497497559
2023-01-22 09:30:07.415217: step: 206/466, loss: 10.175179481506348
2023-01-22 09:30:08.004845: step: 208/466, loss: 3.33925724029541
2023-01-22 09:30:08.619849: step: 210/466, loss: 12.030865669250488
2023-01-22 09:30:09.181925: step: 212/466, loss: 6.707439422607422
2023-01-22 09:30:09.769630: step: 214/466, loss: 6.418980121612549
2023-01-22 09:30:10.431146: step: 216/466, loss: 5.509450435638428
2023-01-22 09:30:11.072631: step: 218/466, loss: 7.686718940734863
2023-01-22 09:30:11.652767: step: 220/466, loss: 9.260184288024902
2023-01-22 09:30:12.353461: step: 222/466, loss: 7.044439792633057
2023-01-22 09:30:13.014912: step: 224/466, loss: 10.225696563720703
2023-01-22 09:30:13.675326: step: 226/466, loss: 3.3414080142974854
2023-01-22 09:30:14.387955: step: 228/466, loss: 4.594356060028076
2023-01-22 09:30:15.033374: step: 230/466, loss: 9.147964477539062
2023-01-22 09:30:15.649215: step: 232/466, loss: 10.93932819366455
2023-01-22 09:30:16.341834: step: 234/466, loss: 3.6889586448669434
2023-01-22 09:30:16.973882: step: 236/466, loss: 6.666989326477051
2023-01-22 09:30:17.593820: step: 238/466, loss: 8.69485092163086
2023-01-22 09:30:18.252526: step: 240/466, loss: 6.226055145263672
2023-01-22 09:30:18.848305: step: 242/466, loss: 5.682862281799316
2023-01-22 09:30:19.445537: step: 244/466, loss: 8.642372131347656
2023-01-22 09:30:20.076448: step: 246/466, loss: 4.897340297698975
2023-01-22 09:30:20.704509: step: 248/466, loss: 9.65620231628418
2023-01-22 09:30:21.280130: step: 250/466, loss: 9.824047088623047
2023-01-22 09:30:21.902859: step: 252/466, loss: 12.255440711975098
2023-01-22 09:30:22.482299: step: 254/466, loss: 8.427801132202148
2023-01-22 09:30:23.113477: step: 256/466, loss: 2.771171808242798
2023-01-22 09:30:23.704913: step: 258/466, loss: 2.793335437774658
2023-01-22 09:30:24.316530: step: 260/466, loss: 4.4932026863098145
2023-01-22 09:30:24.837976: step: 262/466, loss: 14.632492065429688
2023-01-22 09:30:25.476539: step: 264/466, loss: 6.25474739074707
2023-01-22 09:30:26.088733: step: 266/466, loss: 4.915351867675781
2023-01-22 09:30:26.689750: step: 268/466, loss: 2.20871901512146
2023-01-22 09:30:27.316347: step: 270/466, loss: 3.317594528198242
2023-01-22 09:30:27.978317: step: 272/466, loss: 2.623382329940796
2023-01-22 09:30:28.639983: step: 274/466, loss: 5.40425968170166
2023-01-22 09:30:29.244424: step: 276/466, loss: 5.922799110412598
2023-01-22 09:30:29.810100: step: 278/466, loss: 10.036717414855957
2023-01-22 09:30:30.505042: step: 280/466, loss: 7.337660789489746
2023-01-22 09:30:31.076325: step: 282/466, loss: 4.743040561676025
2023-01-22 09:30:31.772019: step: 284/466, loss: 11.601187705993652
2023-01-22 09:30:32.381937: step: 286/466, loss: 7.599787712097168
2023-01-22 09:30:32.981815: step: 288/466, loss: 4.125901222229004
2023-01-22 09:30:33.608268: step: 290/466, loss: 8.427830696105957
2023-01-22 09:30:34.231537: step: 292/466, loss: 4.56728458404541
2023-01-22 09:30:34.825496: step: 294/466, loss: 8.052621841430664
2023-01-22 09:30:35.493395: step: 296/466, loss: 12.73134708404541
2023-01-22 09:30:36.163080: step: 298/466, loss: 3.4680447578430176
2023-01-22 09:30:36.819542: step: 300/466, loss: 13.000292778015137
2023-01-22 09:30:37.469967: step: 302/466, loss: 1.799185872077942
2023-01-22 09:30:38.080982: step: 304/466, loss: 4.542043685913086
2023-01-22 09:30:38.690460: step: 306/466, loss: 1.7015113830566406
2023-01-22 09:30:39.318038: step: 308/466, loss: 8.83305549621582
2023-01-22 09:30:39.964744: step: 310/466, loss: 2.995100498199463
2023-01-22 09:30:40.516025: step: 312/466, loss: 3.73531436920166
2023-01-22 09:30:41.110572: step: 314/466, loss: 3.0925674438476562
2023-01-22 09:30:41.746503: step: 316/466, loss: 8.24208927154541
2023-01-22 09:30:42.387653: step: 318/466, loss: 5.052097797393799
2023-01-22 09:30:43.051258: step: 320/466, loss: 10.515788078308105
2023-01-22 09:30:43.717295: step: 322/466, loss: 2.801037073135376
2023-01-22 09:30:44.318523: step: 324/466, loss: 3.955794334411621
2023-01-22 09:30:44.916250: step: 326/466, loss: 8.783456802368164
2023-01-22 09:30:45.509310: step: 328/466, loss: 7.397550106048584
2023-01-22 09:30:46.142959: step: 330/466, loss: 2.2124977111816406
2023-01-22 09:30:46.742247: step: 332/466, loss: 2.6953563690185547
2023-01-22 09:30:47.346356: step: 334/466, loss: 3.194175958633423
2023-01-22 09:30:48.000675: step: 336/466, loss: 8.288835525512695
2023-01-22 09:30:48.684659: step: 338/466, loss: 5.7289719581604
2023-01-22 09:30:49.309936: step: 340/466, loss: 1.7479150295257568
2023-01-22 09:30:49.945121: step: 342/466, loss: 3.9976894855499268
2023-01-22 09:30:50.594141: step: 344/466, loss: 5.309848785400391
2023-01-22 09:30:51.222104: step: 346/466, loss: 9.174612998962402
2023-01-22 09:30:51.805314: step: 348/466, loss: 10.968244552612305
2023-01-22 09:30:52.403708: step: 350/466, loss: 7.314735412597656
2023-01-22 09:30:53.022380: step: 352/466, loss: 5.568917274475098
2023-01-22 09:30:53.673413: step: 354/466, loss: 5.966447830200195
2023-01-22 09:30:54.346154: step: 356/466, loss: 2.349154472351074
2023-01-22 09:30:54.947094: step: 358/466, loss: 1.817748785018921
2023-01-22 09:30:55.553548: step: 360/466, loss: 4.91948127746582
2023-01-22 09:30:56.207657: step: 362/466, loss: 5.156692981719971
2023-01-22 09:30:56.778075: step: 364/466, loss: 2.1112470626831055
2023-01-22 09:30:57.465867: step: 366/466, loss: 3.301403284072876
2023-01-22 09:30:58.056214: step: 368/466, loss: 2.6327786445617676
2023-01-22 09:30:58.742485: step: 370/466, loss: 11.900964736938477
2023-01-22 09:30:59.363069: step: 372/466, loss: 1.7852437496185303
2023-01-22 09:30:59.962853: step: 374/466, loss: 11.14040470123291
2023-01-22 09:31:00.543436: step: 376/466, loss: 6.314337253570557
2023-01-22 09:31:01.251014: step: 378/466, loss: 5.979366302490234
2023-01-22 09:31:01.875541: step: 380/466, loss: 2.11566162109375
2023-01-22 09:31:02.538306: step: 382/466, loss: 2.9155261516571045
2023-01-22 09:31:03.164167: step: 384/466, loss: 1.8489387035369873
2023-01-22 09:31:03.792696: step: 386/466, loss: 2.673495054244995
2023-01-22 09:31:04.387514: step: 388/466, loss: 2.064558744430542
2023-01-22 09:31:05.041829: step: 390/466, loss: 4.720061302185059
2023-01-22 09:31:05.652789: step: 392/466, loss: 0.9562152624130249
2023-01-22 09:31:06.257814: step: 394/466, loss: 3.733920097351074
2023-01-22 09:31:06.853705: step: 396/466, loss: 1.6869310140609741
2023-01-22 09:31:07.557142: step: 398/466, loss: 3.41373872756958
2023-01-22 09:31:08.152622: step: 400/466, loss: 8.510161399841309
2023-01-22 09:31:08.724308: step: 402/466, loss: 2.9869790077209473
2023-01-22 09:31:09.421207: step: 404/466, loss: 2.9523603916168213
2023-01-22 09:31:10.066780: step: 406/466, loss: 4.403825759887695
2023-01-22 09:31:10.743404: step: 408/466, loss: 6.967065811157227
2023-01-22 09:31:11.334450: step: 410/466, loss: 1.8065185546875
2023-01-22 09:31:11.973837: step: 412/466, loss: 2.615292549133301
2023-01-22 09:31:12.595075: step: 414/466, loss: 3.42132568359375
2023-01-22 09:31:13.194815: step: 416/466, loss: 1.5297431945800781
2023-01-22 09:31:13.859547: step: 418/466, loss: 2.7468690872192383
2023-01-22 09:31:14.516654: step: 420/466, loss: 1.3169325590133667
2023-01-22 09:31:15.105646: step: 422/466, loss: 1.277280330657959
2023-01-22 09:31:15.748686: step: 424/466, loss: 6.031007766723633
2023-01-22 09:31:16.393091: step: 426/466, loss: 0.8889445066452026
2023-01-22 09:31:17.062669: step: 428/466, loss: 3.3562746047973633
2023-01-22 09:31:17.703090: step: 430/466, loss: 1.2084641456604004
2023-01-22 09:31:18.269016: step: 432/466, loss: 6.203814506530762
2023-01-22 09:31:18.918646: step: 434/466, loss: 4.7271857261657715
2023-01-22 09:31:19.527888: step: 436/466, loss: 1.5970778465270996
2023-01-22 09:31:20.164166: step: 438/466, loss: 1.6236553192138672
2023-01-22 09:31:20.719334: step: 440/466, loss: 2.298182487487793
2023-01-22 09:31:21.330908: step: 442/466, loss: 2.216686248779297
2023-01-22 09:31:21.958121: step: 444/466, loss: 1.738180160522461
2023-01-22 09:31:22.546394: step: 446/466, loss: 0.6070207357406616
2023-01-22 09:31:23.217564: step: 448/466, loss: 6.839568138122559
2023-01-22 09:31:23.857429: step: 450/466, loss: 1.0888025760650635
2023-01-22 09:31:24.464645: step: 452/466, loss: 2.980574369430542
2023-01-22 09:31:25.142879: step: 454/466, loss: 3.1009440422058105
2023-01-22 09:31:25.726997: step: 456/466, loss: 3.6753101348876953
2023-01-22 09:31:26.299476: step: 458/466, loss: 0.9100843667984009
2023-01-22 09:31:26.943247: step: 460/466, loss: 1.9703644514083862
2023-01-22 09:31:27.620480: step: 462/466, loss: 1.3446106910705566
2023-01-22 09:31:28.255644: step: 464/466, loss: 1.59548020362854
2023-01-22 09:31:28.931608: step: 466/466, loss: 2.3122241497039795
2023-01-22 09:31:29.560819: step: 468/466, loss: 1.7087005376815796
2023-01-22 09:31:30.233376: step: 470/466, loss: 0.7805963754653931
2023-01-22 09:31:30.896600: step: 472/466, loss: 1.2716556787490845
2023-01-22 09:31:31.500222: step: 474/466, loss: 7.557900428771973
2023-01-22 09:31:32.204438: step: 476/466, loss: 7.787192344665527
2023-01-22 09:31:32.786831: step: 478/466, loss: 1.5486183166503906
2023-01-22 09:31:33.431191: step: 480/466, loss: 0.793107807636261
2023-01-22 09:31:34.025350: step: 482/466, loss: 4.602435111999512
2023-01-22 09:31:34.648111: step: 484/466, loss: 14.594005584716797
2023-01-22 09:31:35.325250: step: 486/466, loss: 0.6587408185005188
2023-01-22 09:31:35.960963: step: 488/466, loss: 1.9012621641159058
2023-01-22 09:31:36.587526: step: 490/466, loss: 1.7635666131973267
2023-01-22 09:31:37.185023: step: 492/466, loss: 5.529452800750732
2023-01-22 09:31:37.801910: step: 494/466, loss: 3.497648239135742
2023-01-22 09:31:38.432537: step: 496/466, loss: 1.3656432628631592
2023-01-22 09:31:39.032430: step: 498/466, loss: 1.1757444143295288
2023-01-22 09:31:39.641268: step: 500/466, loss: 11.79849624633789
2023-01-22 09:31:40.245638: step: 502/466, loss: 2.29689621925354
2023-01-22 09:31:40.860744: step: 504/466, loss: 3.479254722595215
2023-01-22 09:31:41.422024: step: 506/466, loss: 0.8649065494537354
2023-01-22 09:31:41.984932: step: 508/466, loss: 1.3104722499847412
2023-01-22 09:31:42.584439: step: 510/466, loss: 2.9688644409179688
2023-01-22 09:31:43.247195: step: 512/466, loss: 1.84807550907135
2023-01-22 09:31:43.891276: step: 514/466, loss: 2.0440447330474854
2023-01-22 09:31:44.555640: step: 516/466, loss: 1.0096993446350098
2023-01-22 09:31:45.273491: step: 518/466, loss: 1.8664580583572388
2023-01-22 09:31:45.887849: step: 520/466, loss: 2.7214341163635254
2023-01-22 09:31:46.487974: step: 522/466, loss: 1.2181735038757324
2023-01-22 09:31:47.143115: step: 524/466, loss: 2.78680419921875
2023-01-22 09:31:47.866957: step: 526/466, loss: 1.1728681325912476
2023-01-22 09:31:48.519591: step: 528/466, loss: 7.325881004333496
2023-01-22 09:31:49.118490: step: 530/466, loss: 0.7084908485412598
2023-01-22 09:31:49.708174: step: 532/466, loss: 4.042177677154541
2023-01-22 09:31:50.292929: step: 534/466, loss: 0.99375319480896
2023-01-22 09:31:50.933665: step: 536/466, loss: 8.10824203491211
2023-01-22 09:31:51.500272: step: 538/466, loss: 2.4628915786743164
2023-01-22 09:31:52.086266: step: 540/466, loss: 3.5445218086242676
2023-01-22 09:31:52.663104: step: 542/466, loss: 5.805854320526123
2023-01-22 09:31:53.297725: step: 544/466, loss: 2.3361477851867676
2023-01-22 09:31:53.883401: step: 546/466, loss: 1.2651429176330566
2023-01-22 09:31:54.556687: step: 548/466, loss: 6.927567958831787
2023-01-22 09:31:55.118648: step: 550/466, loss: 2.0593607425689697
2023-01-22 09:31:55.772902: step: 552/466, loss: 3.235837459564209
2023-01-22 09:31:56.409096: step: 554/466, loss: 1.5556988716125488
2023-01-22 09:31:57.007219: step: 556/466, loss: 1.3860385417938232
2023-01-22 09:31:57.650862: step: 558/466, loss: 3.06978178024292
2023-01-22 09:31:58.209615: step: 560/466, loss: 1.8661152124404907
2023-01-22 09:31:58.791611: step: 562/466, loss: 1.7554469108581543
2023-01-22 09:31:59.343103: step: 564/466, loss: 0.7988944053649902
2023-01-22 09:31:59.955934: step: 566/466, loss: 1.3624035120010376
2023-01-22 09:32:00.576693: step: 568/466, loss: 3.3787741661071777
2023-01-22 09:32:01.263319: step: 570/466, loss: 8.649011611938477
2023-01-22 09:32:01.922640: step: 572/466, loss: 0.8634949326515198
2023-01-22 09:32:02.525392: step: 574/466, loss: 8.739198684692383
2023-01-22 09:32:03.160027: step: 576/466, loss: 8.703192710876465
2023-01-22 09:32:03.800847: step: 578/466, loss: 1.8177729845046997
2023-01-22 09:32:04.397271: step: 580/466, loss: 1.5112245082855225
2023-01-22 09:32:05.054935: step: 582/466, loss: 3.063086986541748
2023-01-22 09:32:05.685891: step: 584/466, loss: 5.767726898193359
2023-01-22 09:32:06.297360: step: 586/466, loss: 2.0085208415985107
2023-01-22 09:32:06.932840: step: 588/466, loss: 6.870216369628906
2023-01-22 09:32:07.566816: step: 590/466, loss: 0.4155629873275757
2023-01-22 09:32:08.203023: step: 592/466, loss: 3.4884564876556396
2023-01-22 09:32:08.795992: step: 594/466, loss: 5.3875322341918945
2023-01-22 09:32:09.459534: step: 596/466, loss: 3.704777240753174
2023-01-22 09:32:10.101840: step: 598/466, loss: 3.0357890129089355
2023-01-22 09:32:10.701538: step: 600/466, loss: 2.5868122577667236
2023-01-22 09:32:11.325254: step: 602/466, loss: 2.622529983520508
2023-01-22 09:32:11.978862: step: 604/466, loss: 2.5356907844543457
2023-01-22 09:32:12.653175: step: 606/466, loss: 1.3839924335479736
2023-01-22 09:32:13.286890: step: 608/466, loss: 10.012450218200684
2023-01-22 09:32:13.940479: step: 610/466, loss: 4.111511707305908
2023-01-22 09:32:14.591625: step: 612/466, loss: 2.201719284057617
2023-01-22 09:32:15.187417: step: 614/466, loss: 4.48403263092041
2023-01-22 09:32:15.817405: step: 616/466, loss: 3.024829149246216
2023-01-22 09:32:16.471136: step: 618/466, loss: 3.7050843238830566
2023-01-22 09:32:17.076435: step: 620/466, loss: 1.3436836004257202
2023-01-22 09:32:17.686492: step: 622/466, loss: 1.4644038677215576
2023-01-22 09:32:18.278614: step: 624/466, loss: 1.202675700187683
2023-01-22 09:32:18.976105: step: 626/466, loss: 5.483269691467285
2023-01-22 09:32:19.638615: step: 628/466, loss: 1.0728418827056885
2023-01-22 09:32:20.239334: step: 630/466, loss: 6.990755558013916
2023-01-22 09:32:20.847306: step: 632/466, loss: 2.7628517150878906
2023-01-22 09:32:21.582149: step: 634/466, loss: 1.0182297229766846
2023-01-22 09:32:22.210693: step: 636/466, loss: 2.5928008556365967
2023-01-22 09:32:22.869594: step: 638/466, loss: 8.490153312683105
2023-01-22 09:32:23.597371: step: 640/466, loss: 0.6833595037460327
2023-01-22 09:32:24.246375: step: 642/466, loss: 0.8581178188323975
2023-01-22 09:32:24.899377: step: 644/466, loss: 2.870028495788574
2023-01-22 09:32:25.498627: step: 646/466, loss: 1.4932246208190918
2023-01-22 09:32:26.106632: step: 648/466, loss: 4.9424920082092285
2023-01-22 09:32:26.747489: step: 650/466, loss: 11.312755584716797
2023-01-22 09:32:27.356697: step: 652/466, loss: 3.2909493446350098
2023-01-22 09:32:28.002115: step: 654/466, loss: 2.3444089889526367
2023-01-22 09:32:28.630573: step: 656/466, loss: 1.102722406387329
2023-01-22 09:32:29.334299: step: 658/466, loss: 1.4511377811431885
2023-01-22 09:32:30.047967: step: 660/466, loss: 4.209312438964844
2023-01-22 09:32:30.683613: step: 662/466, loss: 1.1369702816009521
2023-01-22 09:32:31.374724: step: 664/466, loss: 3.2985424995422363
2023-01-22 09:32:31.964424: step: 666/466, loss: 0.7985827922821045
2023-01-22 09:32:32.589782: step: 668/466, loss: 0.6459063291549683
2023-01-22 09:32:33.202526: step: 670/466, loss: 2.3331503868103027
2023-01-22 09:32:33.835716: step: 672/466, loss: 5.232911109924316
2023-01-22 09:32:34.474959: step: 674/466, loss: 0.4341469705104828
2023-01-22 09:32:35.123781: step: 676/466, loss: 14.222973823547363
2023-01-22 09:32:35.753482: step: 678/466, loss: 0.7190119624137878
2023-01-22 09:32:36.392578: step: 680/466, loss: 2.441484212875366
2023-01-22 09:32:37.058230: step: 682/466, loss: 1.3511295318603516
2023-01-22 09:32:37.694715: step: 684/466, loss: 2.3318142890930176
2023-01-22 09:32:38.303527: step: 686/466, loss: 7.932394027709961
2023-01-22 09:32:38.969931: step: 688/466, loss: 3.3909051418304443
2023-01-22 09:32:39.627276: step: 690/466, loss: 5.007787704467773
2023-01-22 09:32:40.216767: step: 692/466, loss: 8.316167831420898
2023-01-22 09:32:40.812032: step: 694/466, loss: 2.1374423503875732
2023-01-22 09:32:41.379264: step: 696/466, loss: 2.0556044578552246
2023-01-22 09:32:42.029501: step: 698/466, loss: 3.3444528579711914
2023-01-22 09:32:42.759929: step: 700/466, loss: 3.3472328186035156
2023-01-22 09:32:43.333007: step: 702/466, loss: 5.110820770263672
2023-01-22 09:32:43.999079: step: 704/466, loss: 1.0950136184692383
2023-01-22 09:32:44.607439: step: 706/466, loss: 1.4175435304641724
2023-01-22 09:32:45.265845: step: 708/466, loss: 0.6698507070541382
2023-01-22 09:32:45.843376: step: 710/466, loss: 2.666046619415283
2023-01-22 09:32:46.443195: step: 712/466, loss: 0.7699897289276123
2023-01-22 09:32:47.022829: step: 714/466, loss: 4.566158294677734
2023-01-22 09:32:47.612884: step: 716/466, loss: 0.4597007632255554
2023-01-22 09:32:48.241838: step: 718/466, loss: 3.247370719909668
2023-01-22 09:32:48.881902: step: 720/466, loss: 1.869280219078064
2023-01-22 09:32:49.522494: step: 722/466, loss: 1.0909264087677002
2023-01-22 09:32:50.100071: step: 724/466, loss: 1.2511248588562012
2023-01-22 09:32:50.700323: step: 726/466, loss: 0.8433552980422974
2023-01-22 09:32:51.365056: step: 728/466, loss: 0.5003337264060974
2023-01-22 09:32:51.946077: step: 730/466, loss: 10.544416427612305
2023-01-22 09:32:52.547535: step: 732/466, loss: 1.9595627784729004
2023-01-22 09:32:53.099304: step: 734/466, loss: 0.4986826181411743
2023-01-22 09:32:53.683679: step: 736/466, loss: 2.4393367767333984
2023-01-22 09:32:54.499307: step: 738/466, loss: 0.43393364548683167
2023-01-22 09:32:55.089545: step: 740/466, loss: 4.039564609527588
2023-01-22 09:32:55.654436: step: 742/466, loss: 3.1970245838165283
2023-01-22 09:32:56.271838: step: 744/466, loss: 0.92037433385849
2023-01-22 09:32:56.976308: step: 746/466, loss: 1.3021045923233032
2023-01-22 09:32:57.624209: step: 748/466, loss: 1.1154721975326538
2023-01-22 09:32:58.222765: step: 750/466, loss: 3.194521188735962
2023-01-22 09:32:58.796310: step: 752/466, loss: 1.9175065755844116
2023-01-22 09:32:59.466928: step: 754/466, loss: 2.066864490509033
2023-01-22 09:33:00.138895: step: 756/466, loss: 2.003392219543457
2023-01-22 09:33:00.739779: step: 758/466, loss: 2.3764588832855225
2023-01-22 09:33:01.354705: step: 760/466, loss: 1.6392319202423096
2023-01-22 09:33:02.100753: step: 762/466, loss: 2.3279452323913574
2023-01-22 09:33:02.853587: step: 764/466, loss: 1.0867607593536377
2023-01-22 09:33:03.490197: step: 766/466, loss: 2.5018019676208496
2023-01-22 09:33:04.111007: step: 768/466, loss: 0.972590446472168
2023-01-22 09:33:04.711032: step: 770/466, loss: 2.3740994930267334
2023-01-22 09:33:05.319136: step: 772/466, loss: 1.1381977796554565
2023-01-22 09:33:05.972667: step: 774/466, loss: 1.6053963899612427
2023-01-22 09:33:06.553780: step: 776/466, loss: 2.5549421310424805
2023-01-22 09:33:07.180990: step: 778/466, loss: 6.050621509552002
2023-01-22 09:33:07.802310: step: 780/466, loss: 9.900514602661133
2023-01-22 09:33:08.399546: step: 782/466, loss: 2.7175397872924805
2023-01-22 09:33:09.020650: step: 784/466, loss: 6.7735700607299805
2023-01-22 09:33:09.670002: step: 786/466, loss: 4.265678405761719
2023-01-22 09:33:10.239009: step: 788/466, loss: 1.092139482498169
2023-01-22 09:33:10.877612: step: 790/466, loss: 3.1744885444641113
2023-01-22 09:33:11.455711: step: 792/466, loss: 1.2144368886947632
2023-01-22 09:33:12.108943: step: 794/466, loss: 1.2058383226394653
2023-01-22 09:33:12.742269: step: 796/466, loss: 3.056980609893799
2023-01-22 09:33:13.371083: step: 798/466, loss: 2.6981399059295654
2023-01-22 09:33:13.989924: step: 800/466, loss: 3.3247382640838623
2023-01-22 09:33:14.649889: step: 802/466, loss: 2.5999903678894043
2023-01-22 09:33:15.271170: step: 804/466, loss: 1.947007179260254
2023-01-22 09:33:15.942161: step: 806/466, loss: 3.425672769546509
2023-01-22 09:33:16.540553: step: 808/466, loss: 1.6140003204345703
2023-01-22 09:33:17.108490: step: 810/466, loss: 2.9465503692626953
2023-01-22 09:33:17.738737: step: 812/466, loss: 0.9249109625816345
2023-01-22 09:33:18.322102: step: 814/466, loss: 0.5993981957435608
2023-01-22 09:33:18.897405: step: 816/466, loss: 1.445728063583374
2023-01-22 09:33:19.521153: step: 818/466, loss: 2.0373096466064453
2023-01-22 09:33:20.120371: step: 820/466, loss: 0.901696503162384
2023-01-22 09:33:20.740547: step: 822/466, loss: 1.959995150566101
2023-01-22 09:33:21.349839: step: 824/466, loss: 0.6444437503814697
2023-01-22 09:33:21.977212: step: 826/466, loss: 1.7989659309387207
2023-01-22 09:33:22.617837: step: 828/466, loss: 1.0831447839736938
2023-01-22 09:33:23.302390: step: 830/466, loss: 0.9967033863067627
2023-01-22 09:33:23.898542: step: 832/466, loss: 3.739194631576538
2023-01-22 09:33:24.511630: step: 834/466, loss: 1.3975876569747925
2023-01-22 09:33:25.230915: step: 836/466, loss: 2.5847549438476562
2023-01-22 09:33:25.858042: step: 838/466, loss: 1.2046366930007935
2023-01-22 09:33:26.462302: step: 840/466, loss: 0.6176460981369019
2023-01-22 09:33:27.227264: step: 842/466, loss: 1.2880494594573975
2023-01-22 09:33:27.781850: step: 844/466, loss: 1.0232499837875366
2023-01-22 09:33:28.445621: step: 846/466, loss: 7.343748569488525
2023-01-22 09:33:29.138373: step: 848/466, loss: 2.252338171005249
2023-01-22 09:33:29.797042: step: 850/466, loss: 0.7068266272544861
2023-01-22 09:33:30.442426: step: 852/466, loss: 0.9141572713851929
2023-01-22 09:33:31.085048: step: 854/466, loss: 8.108214378356934
2023-01-22 09:33:31.690163: step: 856/466, loss: 6.887636184692383
2023-01-22 09:33:32.316328: step: 858/466, loss: 0.5420605540275574
2023-01-22 09:33:33.022661: step: 860/466, loss: 0.5500837564468384
2023-01-22 09:33:33.673296: step: 862/466, loss: 1.6031155586242676
2023-01-22 09:33:34.302587: step: 864/466, loss: 3.2517027854919434
2023-01-22 09:33:34.994478: step: 866/466, loss: 1.4873687028884888
2023-01-22 09:33:35.641671: step: 868/466, loss: 1.351752758026123
2023-01-22 09:33:36.296491: step: 870/466, loss: 1.4392306804656982
2023-01-22 09:33:36.952137: step: 872/466, loss: 3.2745513916015625
2023-01-22 09:33:37.559979: step: 874/466, loss: 1.054884672164917
2023-01-22 09:33:38.211301: step: 876/466, loss: 3.826343059539795
2023-01-22 09:33:38.887670: step: 878/466, loss: 1.9085838794708252
2023-01-22 09:33:39.526709: step: 880/466, loss: 0.7896057367324829
2023-01-22 09:33:40.119303: step: 882/466, loss: 1.2758047580718994
2023-01-22 09:33:40.748254: step: 884/466, loss: 8.894779205322266
2023-01-22 09:33:41.417495: step: 886/466, loss: 12.874110221862793
2023-01-22 09:33:42.138502: step: 888/466, loss: 4.848669052124023
2023-01-22 09:33:42.795368: step: 890/466, loss: 3.7010364532470703
2023-01-22 09:33:43.400257: step: 892/466, loss: 1.2354850769042969
2023-01-22 09:33:44.046148: step: 894/466, loss: 0.6324902176856995
2023-01-22 09:33:44.616017: step: 896/466, loss: 1.2102067470550537
2023-01-22 09:33:45.186671: step: 898/466, loss: 0.9676986336708069
2023-01-22 09:33:45.757060: step: 900/466, loss: 1.7856495380401611
2023-01-22 09:33:46.373341: step: 902/466, loss: 1.2424051761627197
2023-01-22 09:33:46.986540: step: 904/466, loss: 0.7720033526420593
2023-01-22 09:33:47.562110: step: 906/466, loss: 0.6424551010131836
2023-01-22 09:33:48.100104: step: 908/466, loss: 0.5964785218238831
2023-01-22 09:33:48.793139: step: 910/466, loss: 0.453046053647995
2023-01-22 09:33:49.431740: step: 912/466, loss: 2.552675724029541
2023-01-22 09:33:50.090852: step: 914/466, loss: 1.0938541889190674
2023-01-22 09:33:50.693972: step: 916/466, loss: 4.85699462890625
2023-01-22 09:33:51.286552: step: 918/466, loss: 13.960785865783691
2023-01-22 09:33:51.891794: step: 920/466, loss: 0.9788107872009277
2023-01-22 09:33:52.503587: step: 922/466, loss: 3.9030308723449707
2023-01-22 09:33:53.088348: step: 924/466, loss: 0.75482577085495
2023-01-22 09:33:53.696808: step: 926/466, loss: 0.974812388420105
2023-01-22 09:33:54.303973: step: 928/466, loss: 2.224337577819824
2023-01-22 09:33:54.929105: step: 930/466, loss: 4.5829362869262695
2023-01-22 09:33:55.628195: step: 932/466, loss: 2.171318292617798
==================================================
Loss: 5.563
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.47619047619047616, 'r': 0.03780718336483932, 'f1': 0.07005253940455342}, 'combined': 0.05161766061388146, 'epoch': 0}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3229166666666667, 'r': 0.027852650494159928, 'f1': 0.05128205128205129}, 'combined': 0.03211119098969567, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 0}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3082682291666667, 'r': 0.02658917340521114, 'f1': 0.048955748552522736}, 'combined': 0.03033877375085916, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 0}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.28833333333333333, 'r': 0.019429469901168013, 'f1': 0.03640572390572391}, 'combined': 0.02415033169983665, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, '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': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 0.47619047619047616, 'r': 0.03780718336483932, 'f1': 0.07005253940455342}, 'combined': 0.05161766061388146, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3229166666666667, 'r': 0.027852650494159928, 'f1': 0.05128205128205129}, 'combined': 0.03211119098969567, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 0}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3082682291666667, 'r': 0.02658917340521114, 'f1': 0.048955748552522736}, 'combined': 0.03033877375085916, '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': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.28833333333333333, 'r': 0.019429469901168013, 'f1': 0.03640572390572391}, 'combined': 0.02415033169983665, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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 09:36:40.306343: step: 2/466, loss: 4.929131507873535
2023-01-22 09:36:40.919523: step: 4/466, loss: 2.8415467739105225
2023-01-22 09:36:41.555220: step: 6/466, loss: 2.0225117206573486
2023-01-22 09:36:42.192165: step: 8/466, loss: 0.7062174081802368
2023-01-22 09:36:42.801696: step: 10/466, loss: 1.4165326356887817
2023-01-22 09:36:43.397671: step: 12/466, loss: 2.3219292163848877
2023-01-22 09:36:43.977936: step: 14/466, loss: 1.5617159605026245
2023-01-22 09:36:44.657281: step: 16/466, loss: 1.4706218242645264
2023-01-22 09:36:45.214610: step: 18/466, loss: 6.345338821411133
2023-01-22 09:36:45.860834: step: 20/466, loss: 6.110724925994873
2023-01-22 09:36:46.467690: step: 22/466, loss: 1.883397102355957
2023-01-22 09:36:47.133574: step: 24/466, loss: 12.628595352172852
2023-01-22 09:36:47.788369: step: 26/466, loss: 1.3402032852172852
2023-01-22 09:36:48.394620: step: 28/466, loss: 1.3088589906692505
2023-01-22 09:36:49.013812: step: 30/466, loss: 1.4807056188583374
2023-01-22 09:36:49.670330: step: 32/466, loss: 4.869627952575684
2023-01-22 09:36:50.330571: step: 34/466, loss: 1.9308644533157349
2023-01-22 09:36:50.954009: step: 36/466, loss: 2.5034115314483643
2023-01-22 09:36:51.553327: step: 38/466, loss: 1.6823831796646118
2023-01-22 09:36:52.120702: step: 40/466, loss: 0.5867857933044434
2023-01-22 09:36:52.742804: step: 42/466, loss: 2.1307899951934814
2023-01-22 09:36:53.307649: step: 44/466, loss: 0.2725277841091156
2023-01-22 09:36:53.858632: step: 46/466, loss: 2.647444009780884
2023-01-22 09:36:54.519394: step: 48/466, loss: 3.0356178283691406
2023-01-22 09:36:55.184510: step: 50/466, loss: 4.61689567565918
2023-01-22 09:36:55.737484: step: 52/466, loss: 1.5133917331695557
2023-01-22 09:36:56.386953: step: 54/466, loss: 0.7836480140686035
2023-01-22 09:36:57.011025: step: 56/466, loss: 1.1973618268966675
2023-01-22 09:36:57.654125: step: 58/466, loss: 1.8865139484405518
2023-01-22 09:36:58.244371: step: 60/466, loss: 0.727965235710144
2023-01-22 09:36:59.018965: step: 62/466, loss: 7.887497901916504
2023-01-22 09:36:59.669427: step: 64/466, loss: 2.089545726776123
2023-01-22 09:37:00.289114: step: 66/466, loss: 2.698453187942505
2023-01-22 09:37:00.927145: step: 68/466, loss: 3.0904152393341064
2023-01-22 09:37:01.578007: step: 70/466, loss: 2.1787655353546143
2023-01-22 09:37:02.205610: step: 72/466, loss: 0.7506197690963745
2023-01-22 09:37:02.817006: step: 74/466, loss: 1.150722622871399
2023-01-22 09:37:03.420150: step: 76/466, loss: 0.5888922810554504
2023-01-22 09:37:04.036365: step: 78/466, loss: 1.4027190208435059
2023-01-22 09:37:04.656977: step: 80/466, loss: 4.744175434112549
2023-01-22 09:37:05.265690: step: 82/466, loss: 0.45425620675086975
2023-01-22 09:37:05.865791: step: 84/466, loss: 1.6839087009429932
2023-01-22 09:37:06.518334: step: 86/466, loss: 0.9715327620506287
2023-01-22 09:37:07.104417: step: 88/466, loss: 1.4811819791793823
2023-01-22 09:37:07.658747: step: 90/466, loss: 0.8654317259788513
2023-01-22 09:37:08.347131: step: 92/466, loss: 0.7142919898033142
2023-01-22 09:37:08.972953: step: 94/466, loss: 1.9248844385147095
2023-01-22 09:37:09.603191: step: 96/466, loss: 8.593791007995605
2023-01-22 09:37:10.153313: step: 98/466, loss: 12.591300964355469
2023-01-22 09:37:10.793327: step: 100/466, loss: 0.34657251834869385
2023-01-22 09:37:11.409720: step: 102/466, loss: 4.688027858734131
2023-01-22 09:37:11.998138: step: 104/466, loss: 2.3076515197753906
2023-01-22 09:37:12.645040: step: 106/466, loss: 8.795105934143066
2023-01-22 09:37:13.283503: step: 108/466, loss: 10.504772186279297
2023-01-22 09:37:13.843973: step: 110/466, loss: 2.015002965927124
2023-01-22 09:37:14.433148: step: 112/466, loss: 0.8676893711090088
2023-01-22 09:37:15.044889: step: 114/466, loss: 2.728665828704834
2023-01-22 09:37:15.669291: step: 116/466, loss: 3.5228874683380127
2023-01-22 09:37:16.358628: step: 118/466, loss: 1.037108302116394
2023-01-22 09:37:16.956585: step: 120/466, loss: 4.725841045379639
2023-01-22 09:37:17.577314: step: 122/466, loss: 1.8643794059753418
2023-01-22 09:37:18.207552: step: 124/466, loss: 1.6684551239013672
2023-01-22 09:37:18.831879: step: 126/466, loss: 0.8428720235824585
2023-01-22 09:37:19.411793: step: 128/466, loss: 4.136777400970459
2023-01-22 09:37:20.111563: step: 130/466, loss: 1.1405422687530518
2023-01-22 09:37:20.774752: step: 132/466, loss: 1.033148169517517
2023-01-22 09:37:21.402111: step: 134/466, loss: 1.2923126220703125
2023-01-22 09:37:22.016659: step: 136/466, loss: 1.0092655420303345
2023-01-22 09:37:22.622788: step: 138/466, loss: 0.3972666263580322
2023-01-22 09:37:23.218127: step: 140/466, loss: 5.283818244934082
2023-01-22 09:37:23.852163: step: 142/466, loss: 0.5786647200584412
2023-01-22 09:37:24.560666: step: 144/466, loss: 1.15341055393219
2023-01-22 09:37:25.261872: step: 146/466, loss: 6.17548942565918
2023-01-22 09:37:25.856121: step: 148/466, loss: 2.5550308227539062
2023-01-22 09:37:26.535403: step: 150/466, loss: 1.2243494987487793
2023-01-22 09:37:27.213360: step: 152/466, loss: 0.4730167090892792
2023-01-22 09:37:27.908774: step: 154/466, loss: 5.324580192565918
2023-01-22 09:37:28.562653: step: 156/466, loss: 2.6694695949554443
2023-01-22 09:37:29.182168: step: 158/466, loss: 1.080947756767273
2023-01-22 09:37:29.815382: step: 160/466, loss: 1.998123288154602
2023-01-22 09:37:30.570574: step: 162/466, loss: 3.806281089782715
2023-01-22 09:37:31.190718: step: 164/466, loss: 1.2770198583602905
2023-01-22 09:37:31.799806: step: 166/466, loss: 1.6960055828094482
2023-01-22 09:37:32.500031: step: 168/466, loss: 1.8077749013900757
2023-01-22 09:37:33.131893: step: 170/466, loss: 2.616239309310913
2023-01-22 09:37:33.767099: step: 172/466, loss: 1.490473747253418
2023-01-22 09:37:34.448319: step: 174/466, loss: 6.659701824188232
2023-01-22 09:37:35.074273: step: 176/466, loss: 0.7965739369392395
2023-01-22 09:37:35.706639: step: 178/466, loss: 1.3609330654144287
2023-01-22 09:37:36.311807: step: 180/466, loss: 3.4460201263427734
2023-01-22 09:37:36.981192: step: 182/466, loss: 1.4271316528320312
2023-01-22 09:37:37.612369: step: 184/466, loss: 15.995522499084473
2023-01-22 09:37:38.269814: step: 186/466, loss: 1.9016940593719482
2023-01-22 09:37:38.877216: step: 188/466, loss: 1.519442081451416
2023-01-22 09:37:39.564565: step: 190/466, loss: 2.3379290103912354
2023-01-22 09:37:40.191030: step: 192/466, loss: 4.037121295928955
2023-01-22 09:37:40.831438: step: 194/466, loss: 1.0202337503433228
2023-01-22 09:37:41.426129: step: 196/466, loss: 1.505065679550171
2023-01-22 09:37:42.092428: step: 198/466, loss: 4.231905937194824
2023-01-22 09:37:42.685810: step: 200/466, loss: 0.5224823951721191
2023-01-22 09:37:43.327183: step: 202/466, loss: 1.1126139163970947
2023-01-22 09:37:43.973579: step: 204/466, loss: 2.1017184257507324
2023-01-22 09:37:44.590053: step: 206/466, loss: 1.1046385765075684
2023-01-22 09:37:45.187960: step: 208/466, loss: 0.5189461708068848
2023-01-22 09:37:45.763970: step: 210/466, loss: 1.4643187522888184
2023-01-22 09:37:46.537557: step: 212/466, loss: 2.6156485080718994
2023-01-22 09:37:47.224732: step: 214/466, loss: 1.7121052742004395
2023-01-22 09:37:47.818851: step: 216/466, loss: 1.8391915559768677
2023-01-22 09:37:48.436991: step: 218/466, loss: 0.9342567920684814
2023-01-22 09:37:49.086028: step: 220/466, loss: 3.362318754196167
2023-01-22 09:37:49.762496: step: 222/466, loss: 1.9302512407302856
2023-01-22 09:37:50.437810: step: 224/466, loss: 2.4147017002105713
2023-01-22 09:37:51.194269: step: 226/466, loss: 3.9908182621002197
2023-01-22 09:37:51.800609: step: 228/466, loss: 4.233687400817871
2023-01-22 09:37:52.501107: step: 230/466, loss: 2.4430644512176514
2023-01-22 09:37:53.112660: step: 232/466, loss: 2.7673659324645996
2023-01-22 09:37:53.707221: step: 234/466, loss: 1.1658360958099365
2023-01-22 09:37:54.366561: step: 236/466, loss: 0.8770806193351746
2023-01-22 09:37:54.981521: step: 238/466, loss: 2.096273899078369
2023-01-22 09:37:55.589587: step: 240/466, loss: 7.8668599128723145
2023-01-22 09:37:56.248846: step: 242/466, loss: 1.9725823402404785
2023-01-22 09:37:56.904354: step: 244/466, loss: 3.454176664352417
2023-01-22 09:37:57.553463: step: 246/466, loss: 4.818187713623047
2023-01-22 09:37:58.151627: step: 248/466, loss: 2.0286688804626465
2023-01-22 09:37:58.729125: step: 250/466, loss: 2.0410051345825195
2023-01-22 09:37:59.387454: step: 252/466, loss: 0.6237905025482178
2023-01-22 09:38:00.016069: step: 254/466, loss: 2.2543628215789795
2023-01-22 09:38:00.611057: step: 256/466, loss: 1.4204860925674438
2023-01-22 09:38:01.226217: step: 258/466, loss: 8.815642356872559
2023-01-22 09:38:01.843553: step: 260/466, loss: 2.6833858489990234
2023-01-22 09:38:02.545323: step: 262/466, loss: 0.5628165602684021
2023-01-22 09:38:03.126350: step: 264/466, loss: 2.933077096939087
2023-01-22 09:38:03.731900: step: 266/466, loss: 1.7693064212799072
2023-01-22 09:38:04.261873: step: 268/466, loss: 0.9090259075164795
2023-01-22 09:38:04.913438: step: 270/466, loss: 0.7030649781227112
2023-01-22 09:38:05.561017: step: 272/466, loss: 0.9038471579551697
2023-01-22 09:38:06.239735: step: 274/466, loss: 2.7512764930725098
2023-01-22 09:38:06.944375: step: 276/466, loss: 5.882218360900879
2023-01-22 09:38:07.526307: step: 278/466, loss: 2.691417694091797
2023-01-22 09:38:08.147251: step: 280/466, loss: 1.095444917678833
2023-01-22 09:38:08.778522: step: 282/466, loss: 5.419581890106201
2023-01-22 09:38:09.410361: step: 284/466, loss: 3.2140955924987793
2023-01-22 09:38:09.995493: step: 286/466, loss: 0.7479810118675232
2023-01-22 09:38:10.595150: step: 288/466, loss: 1.4674075841903687
2023-01-22 09:38:11.207646: step: 290/466, loss: 1.0882282257080078
2023-01-22 09:38:11.825237: step: 292/466, loss: 0.6354427337646484
2023-01-22 09:38:12.417743: step: 294/466, loss: 0.7517061233520508
2023-01-22 09:38:13.051942: step: 296/466, loss: 1.2195165157318115
2023-01-22 09:38:13.683794: step: 298/466, loss: 1.6127018928527832
2023-01-22 09:38:14.322310: step: 300/466, loss: 0.7257331609725952
2023-01-22 09:38:14.952471: step: 302/466, loss: 4.134901523590088
2023-01-22 09:38:15.726004: step: 304/466, loss: 5.65886116027832
2023-01-22 09:38:16.391324: step: 306/466, loss: 3.192089080810547
2023-01-22 09:38:16.982386: step: 308/466, loss: 0.6151542067527771
2023-01-22 09:38:17.769803: step: 310/466, loss: 0.7849242091178894
2023-01-22 09:38:18.415024: step: 312/466, loss: 3.01977276802063
2023-01-22 09:38:19.031561: step: 314/466, loss: 3.3342926502227783
2023-01-22 09:38:19.693972: step: 316/466, loss: 0.28638797998428345
2023-01-22 09:38:20.318692: step: 318/466, loss: 4.61793327331543
2023-01-22 09:38:20.921276: step: 320/466, loss: 1.9822195768356323
2023-01-22 09:38:21.515001: step: 322/466, loss: 1.9863197803497314
2023-01-22 09:38:22.058437: step: 324/466, loss: 2.362244129180908
2023-01-22 09:38:22.713212: step: 326/466, loss: 1.6751642227172852
2023-01-22 09:38:23.370017: step: 328/466, loss: 0.8643975257873535
2023-01-22 09:38:24.059748: step: 330/466, loss: 1.003990650177002
2023-01-22 09:38:24.706418: step: 332/466, loss: 2.7076058387756348
2023-01-22 09:38:25.378617: step: 334/466, loss: 1.2687891721725464
2023-01-22 09:38:25.981508: step: 336/466, loss: 0.9781487584114075
2023-01-22 09:38:26.633293: step: 338/466, loss: 1.5812121629714966
2023-01-22 09:38:27.295354: step: 340/466, loss: 0.7526068091392517
2023-01-22 09:38:27.936625: step: 342/466, loss: 0.7111249566078186
2023-01-22 09:38:28.567941: step: 344/466, loss: 1.1937557458877563
2023-01-22 09:38:29.206582: step: 346/466, loss: 1.871544599533081
2023-01-22 09:38:29.800159: step: 348/466, loss: 3.4902377128601074
2023-01-22 09:38:30.424154: step: 350/466, loss: 1.8830691576004028
2023-01-22 09:38:31.026711: step: 352/466, loss: 1.7916781902313232
2023-01-22 09:38:31.724826: step: 354/466, loss: 21.213960647583008
2023-01-22 09:38:32.399675: step: 356/466, loss: 3.97394061088562
2023-01-22 09:38:33.019225: step: 358/466, loss: 1.4885226488113403
2023-01-22 09:38:33.672840: step: 360/466, loss: 2.4368529319763184
2023-01-22 09:38:34.246309: step: 362/466, loss: 8.993447303771973
2023-01-22 09:38:34.856947: step: 364/466, loss: 1.512786865234375
2023-01-22 09:38:35.486943: step: 366/466, loss: 0.8020037412643433
2023-01-22 09:38:36.094282: step: 368/466, loss: 3.514601707458496
2023-01-22 09:38:36.692378: step: 370/466, loss: 1.5181677341461182
2023-01-22 09:38:37.361509: step: 372/466, loss: 1.298141598701477
2023-01-22 09:38:37.965191: step: 374/466, loss: 0.8693670034408569
2023-01-22 09:38:38.581613: step: 376/466, loss: 1.5451771020889282
2023-01-22 09:38:39.173118: step: 378/466, loss: 1.384331464767456
2023-01-22 09:38:39.789261: step: 380/466, loss: 1.4840786457061768
2023-01-22 09:38:40.469061: step: 382/466, loss: 0.9185431003570557
2023-01-22 09:38:41.047786: step: 384/466, loss: 1.204012393951416
2023-01-22 09:38:41.742203: step: 386/466, loss: 1.0616750717163086
2023-01-22 09:38:42.386309: step: 388/466, loss: 0.9257512092590332
2023-01-22 09:38:43.053256: step: 390/466, loss: 5.8560791015625
2023-01-22 09:38:43.729860: step: 392/466, loss: 0.400015652179718
2023-01-22 09:38:44.323033: step: 394/466, loss: 1.7335723638534546
2023-01-22 09:38:44.984397: step: 396/466, loss: 0.47278809547424316
2023-01-22 09:38:45.624596: step: 398/466, loss: 1.4631285667419434
2023-01-22 09:38:46.279598: step: 400/466, loss: 0.72065669298172
2023-01-22 09:38:46.892354: step: 402/466, loss: 2.369809865951538
2023-01-22 09:38:47.478913: step: 404/466, loss: 3.312589168548584
2023-01-22 09:38:48.109043: step: 406/466, loss: 4.5040974617004395
2023-01-22 09:38:48.681222: step: 408/466, loss: 1.723700761795044
2023-01-22 09:38:49.283438: step: 410/466, loss: 1.7383880615234375
2023-01-22 09:38:49.955201: step: 412/466, loss: 0.31944039463996887
2023-01-22 09:38:50.613094: step: 414/466, loss: 0.3767268657684326
2023-01-22 09:38:51.275406: step: 416/466, loss: 1.6418299674987793
2023-01-22 09:38:51.851648: step: 418/466, loss: 1.1182104349136353
2023-01-22 09:38:52.504548: step: 420/466, loss: 1.0689901113510132
2023-01-22 09:38:53.241974: step: 422/466, loss: 4.924126148223877
2023-01-22 09:38:53.873341: step: 424/466, loss: 1.012005090713501
2023-01-22 09:38:54.444059: step: 426/466, loss: 2.006622076034546
2023-01-22 09:38:54.984586: step: 428/466, loss: 2.862314224243164
2023-01-22 09:38:55.594393: step: 430/466, loss: 1.9691691398620605
2023-01-22 09:38:56.196929: step: 432/466, loss: 2.445025682449341
2023-01-22 09:38:56.871866: step: 434/466, loss: 1.6351045370101929
2023-01-22 09:38:57.530633: step: 436/466, loss: 3.27296781539917
2023-01-22 09:38:58.125097: step: 438/466, loss: 5.215020179748535
2023-01-22 09:38:58.802363: step: 440/466, loss: 1.332781195640564
2023-01-22 09:38:59.424574: step: 442/466, loss: 0.8536605834960938
2023-01-22 09:39:00.050571: step: 444/466, loss: 1.8220601081848145
2023-01-22 09:39:00.642635: step: 446/466, loss: 1.024617075920105
2023-01-22 09:39:01.253810: step: 448/466, loss: 1.2876169681549072
2023-01-22 09:39:01.866348: step: 450/466, loss: 3.4061126708984375
2023-01-22 09:39:02.460821: step: 452/466, loss: 0.49869418144226074
2023-01-22 09:39:03.064275: step: 454/466, loss: 0.6542998552322388
2023-01-22 09:39:03.638640: step: 456/466, loss: 4.0117998123168945
2023-01-22 09:39:04.304654: step: 458/466, loss: 2.689338207244873
2023-01-22 09:39:04.888969: step: 460/466, loss: 4.6095428466796875
2023-01-22 09:39:05.582683: step: 462/466, loss: 1.7618801593780518
2023-01-22 09:39:06.214144: step: 464/466, loss: 1.122097134590149
2023-01-22 09:39:06.838868: step: 466/466, loss: 0.6446213722229004
2023-01-22 09:39:07.436280: step: 468/466, loss: 1.0039113759994507
2023-01-22 09:39:08.037871: step: 470/466, loss: 9.731908798217773
2023-01-22 09:39:08.686003: step: 472/466, loss: 0.5952492952346802
2023-01-22 09:39:09.284830: step: 474/466, loss: 1.4649676084518433
2023-01-22 09:39:09.882225: step: 476/466, loss: 4.67943000793457
2023-01-22 09:39:10.568072: step: 478/466, loss: 0.49548181891441345
2023-01-22 09:39:11.179575: step: 480/466, loss: 0.4967639446258545
2023-01-22 09:39:11.789343: step: 482/466, loss: 0.6325618028640747
2023-01-22 09:39:12.568660: step: 484/466, loss: 1.9765273332595825
2023-01-22 09:39:13.211650: step: 486/466, loss: 0.9099281430244446
2023-01-22 09:39:13.852143: step: 488/466, loss: 3.319847583770752
2023-01-22 09:39:14.417746: step: 490/466, loss: 1.457308053970337
2023-01-22 09:39:15.074209: step: 492/466, loss: 2.3949124813079834
2023-01-22 09:39:15.693065: step: 494/466, loss: 1.507026195526123
2023-01-22 09:39:16.324747: step: 496/466, loss: 1.5553545951843262
2023-01-22 09:39:16.918743: step: 498/466, loss: 0.35252252221107483
2023-01-22 09:39:17.472802: step: 500/466, loss: 2.2092807292938232
2023-01-22 09:39:18.154292: step: 502/466, loss: 3.489619493484497
2023-01-22 09:39:18.774316: step: 504/466, loss: 0.6942618489265442
2023-01-22 09:39:19.486699: step: 506/466, loss: 4.0520758628845215
2023-01-22 09:39:20.098603: step: 508/466, loss: 2.635681629180908
2023-01-22 09:39:20.790149: step: 510/466, loss: 2.1636979579925537
2023-01-22 09:39:21.423850: step: 512/466, loss: 1.7167152166366577
2023-01-22 09:39:22.057025: step: 514/466, loss: 1.7931861877441406
2023-01-22 09:39:22.616327: step: 516/466, loss: 2.4630913734436035
2023-01-22 09:39:23.260790: step: 518/466, loss: 0.3835010528564453
2023-01-22 09:39:23.917982: step: 520/466, loss: 3.4767537117004395
2023-01-22 09:39:24.573900: step: 522/466, loss: 1.347123384475708
2023-01-22 09:39:25.195684: step: 524/466, loss: 5.978583335876465
2023-01-22 09:39:25.732412: step: 526/466, loss: 0.522865891456604
2023-01-22 09:39:26.384124: step: 528/466, loss: 0.9223169684410095
2023-01-22 09:39:26.991877: step: 530/466, loss: 0.24813520908355713
2023-01-22 09:39:27.580031: step: 532/466, loss: 4.144888401031494
2023-01-22 09:39:28.144243: step: 534/466, loss: 2.292142868041992
2023-01-22 09:39:28.712489: step: 536/466, loss: 2.742295980453491
2023-01-22 09:39:29.332986: step: 538/466, loss: 2.1504781246185303
2023-01-22 09:39:29.912304: step: 540/466, loss: 0.5144567489624023
2023-01-22 09:39:30.567363: step: 542/466, loss: 1.7471604347229004
2023-01-22 09:39:31.220599: step: 544/466, loss: 1.7209891080856323
2023-01-22 09:39:31.878605: step: 546/466, loss: 0.3878607749938965
2023-01-22 09:39:32.547566: step: 548/466, loss: 1.5918083190917969
2023-01-22 09:39:33.209531: step: 550/466, loss: 4.83439302444458
2023-01-22 09:39:33.803076: step: 552/466, loss: 0.20302298665046692
2023-01-22 09:39:34.506060: step: 554/466, loss: 2.577263832092285
2023-01-22 09:39:35.162990: step: 556/466, loss: 3.62603759765625
2023-01-22 09:39:35.829904: step: 558/466, loss: 1.6257869005203247
2023-01-22 09:39:36.433871: step: 560/466, loss: 0.7063632011413574
2023-01-22 09:39:37.143263: step: 562/466, loss: 3.2233450412750244
2023-01-22 09:39:37.701911: step: 564/466, loss: 1.3194761276245117
2023-01-22 09:39:38.300004: step: 566/466, loss: 0.6329874992370605
2023-01-22 09:39:39.012325: step: 568/466, loss: 1.4945679903030396
2023-01-22 09:39:39.630962: step: 570/466, loss: 0.9494670629501343
2023-01-22 09:39:40.250639: step: 572/466, loss: 5.421570301055908
2023-01-22 09:39:40.833689: step: 574/466, loss: 5.772930145263672
2023-01-22 09:39:41.457824: step: 576/466, loss: 5.787838459014893
2023-01-22 09:39:42.131751: step: 578/466, loss: 0.34725356101989746
2023-01-22 09:39:42.715670: step: 580/466, loss: 1.0084733963012695
2023-01-22 09:39:43.302648: step: 582/466, loss: 1.314733862876892
2023-01-22 09:39:43.979240: step: 584/466, loss: 1.7601927518844604
2023-01-22 09:39:44.523191: step: 586/466, loss: 1.2080614566802979
2023-01-22 09:39:45.167161: step: 588/466, loss: 0.6289536952972412
2023-01-22 09:39:45.842338: step: 590/466, loss: 11.007817268371582
2023-01-22 09:39:46.520166: step: 592/466, loss: 2.669806957244873
2023-01-22 09:39:47.085172: step: 594/466, loss: 0.7001340985298157
2023-01-22 09:39:47.692394: step: 596/466, loss: 3.2594616413116455
2023-01-22 09:39:48.287581: step: 598/466, loss: 0.4124808609485626
2023-01-22 09:39:48.942422: step: 600/466, loss: 4.088919639587402
2023-01-22 09:39:49.594615: step: 602/466, loss: 2.3946118354797363
2023-01-22 09:39:50.224916: step: 604/466, loss: 5.389073848724365
2023-01-22 09:39:50.880325: step: 606/466, loss: 5.529489994049072
2023-01-22 09:39:51.422687: step: 608/466, loss: 2.3979246616363525
2023-01-22 09:39:52.022198: step: 610/466, loss: 1.1010305881500244
2023-01-22 09:39:52.645376: step: 612/466, loss: 2.4431354999542236
2023-01-22 09:39:53.268039: step: 614/466, loss: 2.6164841651916504
2023-01-22 09:39:53.930557: step: 616/466, loss: 6.679588317871094
2023-01-22 09:39:54.510165: step: 618/466, loss: 1.1283159255981445
2023-01-22 09:39:55.165273: step: 620/466, loss: 0.9353471398353577
2023-01-22 09:39:55.818116: step: 622/466, loss: 1.9671612977981567
2023-01-22 09:39:56.413464: step: 624/466, loss: 0.5379169583320618
2023-01-22 09:39:57.058682: step: 626/466, loss: 0.6202490329742432
2023-01-22 09:39:57.648211: step: 628/466, loss: 0.6703006029129028
2023-01-22 09:39:58.295826: step: 630/466, loss: 3.3022804260253906
2023-01-22 09:39:58.844995: step: 632/466, loss: 1.3915318250656128
2023-01-22 09:39:59.462312: step: 634/466, loss: 8.410735130310059
2023-01-22 09:40:00.058685: step: 636/466, loss: 2.620047092437744
2023-01-22 09:40:00.626819: step: 638/466, loss: 0.33021292090415955
2023-01-22 09:40:01.287306: step: 640/466, loss: 0.47434836626052856
2023-01-22 09:40:01.906929: step: 642/466, loss: 0.6993430256843567
2023-01-22 09:40:02.666458: step: 644/466, loss: 6.348758697509766
2023-01-22 09:40:03.273846: step: 646/466, loss: 0.26549726724624634
2023-01-22 09:40:03.879138: step: 648/466, loss: 4.406766891479492
2023-01-22 09:40:04.485300: step: 650/466, loss: 0.6784960031509399
2023-01-22 09:40:05.122194: step: 652/466, loss: 0.45862019062042236
2023-01-22 09:40:05.672894: step: 654/466, loss: 2.127203941345215
2023-01-22 09:40:06.269806: step: 656/466, loss: 1.7913119792938232
2023-01-22 09:40:06.892867: step: 658/466, loss: 2.031116247177124
2023-01-22 09:40:07.548511: step: 660/466, loss: 2.6137585639953613
2023-01-22 09:40:08.209817: step: 662/466, loss: 2.5916874408721924
2023-01-22 09:40:08.806977: step: 664/466, loss: 0.9867198467254639
2023-01-22 09:40:09.442863: step: 666/466, loss: 4.332546710968018
2023-01-22 09:40:10.055498: step: 668/466, loss: 0.40057533979415894
2023-01-22 09:40:10.711877: step: 670/466, loss: 0.5043292045593262
2023-01-22 09:40:11.312952: step: 672/466, loss: 0.16987332701683044
2023-01-22 09:40:11.930638: step: 674/466, loss: 0.329906165599823
2023-01-22 09:40:12.592851: step: 676/466, loss: 1.4557455778121948
2023-01-22 09:40:13.235574: step: 678/466, loss: 1.384361743927002
2023-01-22 09:40:13.877445: step: 680/466, loss: 0.8367301225662231
2023-01-22 09:40:14.480367: step: 682/466, loss: 1.65016770362854
2023-01-22 09:40:15.135023: step: 684/466, loss: 0.9726030826568604
2023-01-22 09:40:15.820548: step: 686/466, loss: 9.812848091125488
2023-01-22 09:40:16.486892: step: 688/466, loss: 3.3158957958221436
2023-01-22 09:40:17.085611: step: 690/466, loss: 0.994577169418335
2023-01-22 09:40:17.740403: step: 692/466, loss: 6.210993766784668
2023-01-22 09:40:18.400191: step: 694/466, loss: 0.6562169790267944
2023-01-22 09:40:18.985138: step: 696/466, loss: 0.40056052803993225
2023-01-22 09:40:19.628464: step: 698/466, loss: 0.6570945382118225
2023-01-22 09:40:20.315881: step: 700/466, loss: 4.279087066650391
2023-01-22 09:40:20.934306: step: 702/466, loss: 0.7729417085647583
2023-01-22 09:40:21.607373: step: 704/466, loss: 0.7772341966629028
2023-01-22 09:40:22.248031: step: 706/466, loss: 2.9096169471740723
2023-01-22 09:40:22.933601: step: 708/466, loss: 1.0564897060394287
2023-01-22 09:40:23.624285: step: 710/466, loss: 0.5298444032669067
2023-01-22 09:40:24.276405: step: 712/466, loss: 0.607456624507904
2023-01-22 09:40:24.926460: step: 714/466, loss: 0.9207783937454224
2023-01-22 09:40:25.554228: step: 716/466, loss: 20.0753116607666
2023-01-22 09:40:26.129236: step: 718/466, loss: 1.4352962970733643
2023-01-22 09:40:26.737319: step: 720/466, loss: 1.1125893592834473
2023-01-22 09:40:27.306003: step: 722/466, loss: 2.0145692825317383
2023-01-22 09:40:27.924270: step: 724/466, loss: 1.474932312965393
2023-01-22 09:40:28.535711: step: 726/466, loss: 1.502770185470581
2023-01-22 09:40:29.162502: step: 728/466, loss: 0.8884294033050537
2023-01-22 09:40:29.772753: step: 730/466, loss: 0.4197545051574707
2023-01-22 09:40:30.388908: step: 732/466, loss: 2.686546802520752
2023-01-22 09:40:30.970445: step: 734/466, loss: 1.3755604028701782
2023-01-22 09:40:31.588196: step: 736/466, loss: 1.4181619882583618
2023-01-22 09:40:32.198969: step: 738/466, loss: 1.007577896118164
2023-01-22 09:40:32.828138: step: 740/466, loss: 1.4114456176757812
2023-01-22 09:40:33.400654: step: 742/466, loss: 1.0807565450668335
2023-01-22 09:40:33.999668: step: 744/466, loss: 0.7102230191230774
2023-01-22 09:40:34.614909: step: 746/466, loss: 1.7669364213943481
2023-01-22 09:40:35.200060: step: 748/466, loss: 0.5153622031211853
2023-01-22 09:40:35.838452: step: 750/466, loss: 6.274852752685547
2023-01-22 09:40:36.453030: step: 752/466, loss: 2.974384069442749
2023-01-22 09:40:37.075939: step: 754/466, loss: 1.164354920387268
2023-01-22 09:40:37.742329: step: 756/466, loss: 1.9302465915679932
2023-01-22 09:40:38.335518: step: 758/466, loss: 2.3095157146453857
2023-01-22 09:40:38.968498: step: 760/466, loss: 1.5579822063446045
2023-01-22 09:40:39.553331: step: 762/466, loss: 1.3251173496246338
2023-01-22 09:40:40.215101: step: 764/466, loss: 1.529748797416687
2023-01-22 09:40:40.798797: step: 766/466, loss: 0.7907923460006714
2023-01-22 09:40:41.402083: step: 768/466, loss: 0.675163984298706
2023-01-22 09:40:42.027404: step: 770/466, loss: 0.3156393766403198
2023-01-22 09:40:42.720978: step: 772/466, loss: 1.0035383701324463
2023-01-22 09:40:43.372246: step: 774/466, loss: 0.6493601202964783
2023-01-22 09:40:43.968220: step: 776/466, loss: 1.1197794675827026
2023-01-22 09:40:44.594908: step: 778/466, loss: 1.0847022533416748
2023-01-22 09:40:45.234554: step: 780/466, loss: 2.637948513031006
2023-01-22 09:40:45.954163: step: 782/466, loss: 0.8970670700073242
2023-01-22 09:40:46.546662: step: 784/466, loss: 2.524245023727417
2023-01-22 09:40:47.213252: step: 786/466, loss: 0.7719473242759705
2023-01-22 09:40:47.870911: step: 788/466, loss: 2.2784554958343506
2023-01-22 09:40:48.454152: step: 790/466, loss: 0.5189509987831116
2023-01-22 09:40:49.116324: step: 792/466, loss: 4.731783390045166
2023-01-22 09:40:49.695811: step: 794/466, loss: 1.8328797817230225
2023-01-22 09:40:50.299202: step: 796/466, loss: 0.6995648741722107
2023-01-22 09:40:50.953760: step: 798/466, loss: 0.4558100700378418
2023-01-22 09:40:51.627761: step: 800/466, loss: 0.5942729115486145
2023-01-22 09:40:52.303094: step: 802/466, loss: 3.3813037872314453
2023-01-22 09:40:52.892637: step: 804/466, loss: 0.9906265139579773
2023-01-22 09:40:53.464183: step: 806/466, loss: 0.8813824653625488
2023-01-22 09:40:54.079346: step: 808/466, loss: 1.026023268699646
2023-01-22 09:40:54.737922: step: 810/466, loss: 1.2499135732650757
2023-01-22 09:40:55.412584: step: 812/466, loss: 0.6142721772193909
2023-01-22 09:40:55.943383: step: 814/466, loss: 4.311723709106445
2023-01-22 09:40:56.580513: step: 816/466, loss: 1.9721442461013794
2023-01-22 09:40:57.186749: step: 818/466, loss: 0.46852439641952515
2023-01-22 09:40:57.811458: step: 820/466, loss: 0.37276071310043335
2023-01-22 09:40:58.431417: step: 822/466, loss: 0.5146880149841309
2023-01-22 09:40:59.093643: step: 824/466, loss: 0.17100459337234497
2023-01-22 09:40:59.717506: step: 826/466, loss: 0.8161599040031433
2023-01-22 09:41:00.321665: step: 828/466, loss: 3.149770736694336
2023-01-22 09:41:00.926985: step: 830/466, loss: 2.1626739501953125
2023-01-22 09:41:01.518059: step: 832/466, loss: 0.6332207918167114
2023-01-22 09:41:02.150597: step: 834/466, loss: 0.6228510141372681
2023-01-22 09:41:02.736160: step: 836/466, loss: 1.3058120012283325
2023-01-22 09:41:03.332650: step: 838/466, loss: 1.0543804168701172
2023-01-22 09:41:03.953965: step: 840/466, loss: 1.508296012878418
2023-01-22 09:41:04.626376: step: 842/466, loss: 0.8300260305404663
2023-01-22 09:41:05.347876: step: 844/466, loss: 2.9184799194335938
2023-01-22 09:41:05.997312: step: 846/466, loss: 0.8929555416107178
2023-01-22 09:41:06.698701: step: 848/466, loss: 0.19070546329021454
2023-01-22 09:41:07.287741: step: 850/466, loss: 2.262145519256592
2023-01-22 09:41:07.917637: step: 852/466, loss: 0.9234271049499512
2023-01-22 09:41:08.527935: step: 854/466, loss: 1.4189567565917969
2023-01-22 09:41:09.147741: step: 856/466, loss: 1.4584400653839111
2023-01-22 09:41:09.789359: step: 858/466, loss: 0.23545756936073303
2023-01-22 09:41:10.414851: step: 860/466, loss: 1.1982975006103516
2023-01-22 09:41:11.066343: step: 862/466, loss: 2.1789932250976562
2023-01-22 09:41:11.623688: step: 864/466, loss: 1.9957928657531738
2023-01-22 09:41:12.224099: step: 866/466, loss: 1.0068098306655884
2023-01-22 09:41:12.888992: step: 868/466, loss: 0.5375741720199585
2023-01-22 09:41:13.505838: step: 870/466, loss: 0.4122433662414551
2023-01-22 09:41:14.140882: step: 872/466, loss: 1.5965980291366577
2023-01-22 09:41:14.797598: step: 874/466, loss: 1.0646878480911255
2023-01-22 09:41:15.509292: step: 876/466, loss: 0.7865087389945984
2023-01-22 09:41:16.097073: step: 878/466, loss: 0.2480173259973526
2023-01-22 09:41:16.770470: step: 880/466, loss: 1.5218760967254639
2023-01-22 09:41:17.406585: step: 882/466, loss: 0.9669118523597717
2023-01-22 09:41:17.970023: step: 884/466, loss: 1.3069440126419067
2023-01-22 09:41:18.578649: step: 886/466, loss: 2.0562679767608643
2023-01-22 09:41:19.244679: step: 888/466, loss: 0.3450886905193329
2023-01-22 09:41:19.839045: step: 890/466, loss: 0.26835256814956665
2023-01-22 09:41:20.458910: step: 892/466, loss: 1.6029860973358154
2023-01-22 09:41:21.075591: step: 894/466, loss: 8.579366683959961
2023-01-22 09:41:21.626296: step: 896/466, loss: 3.9586119651794434
2023-01-22 09:41:22.221092: step: 898/466, loss: 7.937643527984619
2023-01-22 09:41:22.807256: step: 900/466, loss: 8.824544906616211
2023-01-22 09:41:23.394128: step: 902/466, loss: 0.5659041404724121
2023-01-22 09:41:24.035183: step: 904/466, loss: 0.9789327383041382
2023-01-22 09:41:24.636264: step: 906/466, loss: 2.2036490440368652
2023-01-22 09:41:25.233337: step: 908/466, loss: 1.389280915260315
2023-01-22 09:41:25.821187: step: 910/466, loss: 0.3952607810497284
2023-01-22 09:41:26.410436: step: 912/466, loss: 1.1622967720031738
2023-01-22 09:41:27.058719: step: 914/466, loss: 1.0768131017684937
2023-01-22 09:41:27.699817: step: 916/466, loss: 1.861532211303711
2023-01-22 09:41:28.333321: step: 918/466, loss: 1.5120859146118164
2023-01-22 09:41:28.979679: step: 920/466, loss: 0.650384247303009
2023-01-22 09:41:29.566467: step: 922/466, loss: 1.4881584644317627
2023-01-22 09:41:30.199721: step: 924/466, loss: 5.14249849319458
2023-01-22 09:41:30.816681: step: 926/466, loss: 6.586747646331787
2023-01-22 09:41:31.411384: step: 928/466, loss: 2.0965332984924316
2023-01-22 09:41:32.098787: step: 930/466, loss: 0.7308897376060486
2023-01-22 09:41:32.753236: step: 932/466, loss: 0.4634906053543091
==================================================
Loss: 2.258
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3320471810797898, 'r': 0.2039987407390013, 'f1': 0.252729119088833}, 'combined': 0.18622145617071903, 'epoch': 1}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.29574588662703416, 'r': 0.1626735715441757, 'f1': 0.20989527730365423}, 'combined': 0.13142975307798913, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30663862023429567, 'r': 0.21041553713619912, 'f1': 0.24957358552701644}, 'combined': 0.18389632617780158, 'epoch': 1}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.2979608449851448, 'r': 0.16308587277365455, 'f1': 0.2107951432470663}, 'combined': 0.13063360989959039, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30841750503018106, 'r': 0.2073640422077922, 'f1': 0.24799142533570623}, 'combined': 0.182730523931573, 'epoch': 1}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3463263399393878, 'r': 0.1569095872288562, 'f1': 0.2159699660243139}, 'combined': 0.14326720518444586, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35294117647058826, 'r': 0.17142857142857143, 'f1': 0.23076923076923078}, 'combined': 0.15384615384615385, 'epoch': 1}
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': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.375, 'r': 0.12931034482758622, 'f1': 0.19230769230769235}, 'combined': 0.12820512820512822, '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': 0.3320471810797898, 'r': 0.2039987407390013, 'f1': 0.252729119088833}, 'combined': 0.18622145617071903, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.29574588662703416, 'r': 0.1626735715441757, 'f1': 0.20989527730365423}, 'combined': 0.13142975307798913, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35294117647058826, 'r': 0.17142857142857143, 'f1': 0.23076923076923078}, 'combined': 0.15384615384615385, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30663862023429567, 'r': 0.21041553713619912, 'f1': 0.24957358552701644}, 'combined': 0.18389632617780158, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.2979608449851448, 'r': 0.16308587277365455, 'f1': 0.2107951432470663}, 'combined': 0.13063360989959039, 'epoch': 1}
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': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30841750503018106, 'r': 0.2073640422077922, 'f1': 0.24799142533570623}, 'combined': 0.182730523931573, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3463263399393878, 'r': 0.1569095872288562, 'f1': 0.2159699660243139}, 'combined': 0.14326720518444586, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.375, 'r': 0.12931034482758622, 'f1': 0.19230769230769235}, 'combined': 0.12820512820512822, '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 09:44:23.276157: step: 2/466, loss: 1.0007905960083008
2023-01-22 09:44:23.895051: step: 4/466, loss: 1.2795113325119019
2023-01-22 09:44:24.574944: step: 6/466, loss: 1.0669078826904297
2023-01-22 09:44:25.185056: step: 8/466, loss: 1.4870511293411255
2023-01-22 09:44:25.761011: step: 10/466, loss: 0.9705473184585571
2023-01-22 09:44:26.494018: step: 12/466, loss: 1.5953006744384766
2023-01-22 09:44:27.149863: step: 14/466, loss: 0.5289072394371033
2023-01-22 09:44:27.760592: step: 16/466, loss: 3.811513900756836
2023-01-22 09:44:28.361284: step: 18/466, loss: 1.093912124633789
2023-01-22 09:44:28.995860: step: 20/466, loss: 1.7505240440368652
2023-01-22 09:44:29.636589: step: 22/466, loss: 0.5484552979469299
2023-01-22 09:44:30.293350: step: 24/466, loss: 0.9728226661682129
2023-01-22 09:44:30.907274: step: 26/466, loss: 2.6790177822113037
2023-01-22 09:44:31.567768: step: 28/466, loss: 0.8624144792556763
2023-01-22 09:44:32.223512: step: 30/466, loss: 1.5027284622192383
2023-01-22 09:44:32.804145: step: 32/466, loss: 1.7417893409729004
2023-01-22 09:44:33.441761: step: 34/466, loss: 2.7208542823791504
2023-01-22 09:44:34.027815: step: 36/466, loss: 0.5122177004814148
2023-01-22 09:44:34.604733: step: 38/466, loss: 2.3946847915649414
2023-01-22 09:44:35.247094: step: 40/466, loss: 0.323329895734787
2023-01-22 09:44:35.880578: step: 42/466, loss: 0.25720643997192383
2023-01-22 09:44:36.524960: step: 44/466, loss: 2.548123359680176
2023-01-22 09:44:37.187207: step: 46/466, loss: 1.8145484924316406
2023-01-22 09:44:37.860492: step: 48/466, loss: 0.6130473613739014
2023-01-22 09:44:38.553971: step: 50/466, loss: 1.706362247467041
2023-01-22 09:44:39.189217: step: 52/466, loss: 0.9382619261741638
2023-01-22 09:44:39.806414: step: 54/466, loss: 0.4019174575805664
2023-01-22 09:44:40.377370: step: 56/466, loss: 0.6776026487350464
2023-01-22 09:44:40.984005: step: 58/466, loss: 0.9875388741493225
2023-01-22 09:44:41.631919: step: 60/466, loss: 6.833479881286621
2023-01-22 09:44:42.217809: step: 62/466, loss: 1.4245370626449585
2023-01-22 09:44:42.794534: step: 64/466, loss: 2.217290163040161
2023-01-22 09:44:43.487137: step: 66/466, loss: 4.7894487380981445
2023-01-22 09:44:44.109567: step: 68/466, loss: 1.358396291732788
2023-01-22 09:44:44.726045: step: 70/466, loss: 0.8565866947174072
2023-01-22 09:44:45.357845: step: 72/466, loss: 4.278141498565674
2023-01-22 09:44:46.038197: step: 74/466, loss: 0.4032544791698456
2023-01-22 09:44:46.693444: step: 76/466, loss: 2.2673137187957764
2023-01-22 09:44:47.316876: step: 78/466, loss: 3.062309741973877
2023-01-22 09:44:47.917327: step: 80/466, loss: 5.96394681930542
2023-01-22 09:44:48.544493: step: 82/466, loss: 0.931776225566864
2023-01-22 09:44:49.197010: step: 84/466, loss: 1.801688551902771
2023-01-22 09:44:49.771184: step: 86/466, loss: 3.738779067993164
2023-01-22 09:44:50.411191: step: 88/466, loss: 0.6716089844703674
2023-01-22 09:44:50.988320: step: 90/466, loss: 1.2108234167099
2023-01-22 09:44:51.592602: step: 92/466, loss: 2.0988945960998535
2023-01-22 09:44:52.279619: step: 94/466, loss: 0.8946915864944458
2023-01-22 09:44:52.910534: step: 96/466, loss: 2.214448928833008
2023-01-22 09:44:53.526112: step: 98/466, loss: 1.5128629207611084
2023-01-22 09:44:54.117096: step: 100/466, loss: 0.4282916188240051
2023-01-22 09:44:54.751398: step: 102/466, loss: 2.5158019065856934
2023-01-22 09:44:55.422971: step: 104/466, loss: 0.8134267926216125
2023-01-22 09:44:56.023511: step: 106/466, loss: 1.235172986984253
2023-01-22 09:44:56.693450: step: 108/466, loss: 2.3581175804138184
2023-01-22 09:44:57.317936: step: 110/466, loss: 0.6340959668159485
2023-01-22 09:44:57.885376: step: 112/466, loss: 0.33954349160194397
2023-01-22 09:44:58.511236: step: 114/466, loss: 3.7588131427764893
2023-01-22 09:44:59.134638: step: 116/466, loss: 1.792893648147583
2023-01-22 09:44:59.828526: step: 118/466, loss: 1.8706941604614258
2023-01-22 09:45:00.442948: step: 120/466, loss: 0.8998050093650818
2023-01-22 09:45:01.076370: step: 122/466, loss: 2.079965829849243
2023-01-22 09:45:01.719361: step: 124/466, loss: 1.328823208808899
2023-01-22 09:45:02.361150: step: 126/466, loss: 0.9241964817047119
2023-01-22 09:45:02.876365: step: 128/466, loss: 2.9763731956481934
2023-01-22 09:45:03.448722: step: 130/466, loss: 0.8257662653923035
2023-01-22 09:45:04.116704: step: 132/466, loss: 4.552613258361816
2023-01-22 09:45:04.767698: step: 134/466, loss: 0.3572910726070404
2023-01-22 09:45:05.339348: step: 136/466, loss: 0.5996128916740417
2023-01-22 09:45:06.003132: step: 138/466, loss: 4.204519271850586
2023-01-22 09:45:06.642374: step: 140/466, loss: 0.29403766989707947
2023-01-22 09:45:07.331976: step: 142/466, loss: 5.7278218269348145
2023-01-22 09:45:07.970132: step: 144/466, loss: 3.6073617935180664
2023-01-22 09:45:08.574078: step: 146/466, loss: 0.6985445022583008
2023-01-22 09:45:09.223147: step: 148/466, loss: 5.286581993103027
2023-01-22 09:45:09.840351: step: 150/466, loss: 0.6464492678642273
2023-01-22 09:45:10.485284: step: 152/466, loss: 0.5447022914886475
2023-01-22 09:45:11.160288: step: 154/466, loss: 0.7505475878715515
2023-01-22 09:45:11.774057: step: 156/466, loss: 1.7825226783752441
2023-01-22 09:45:12.497674: step: 158/466, loss: 6.1614603996276855
2023-01-22 09:45:13.132042: step: 160/466, loss: 2.721989154815674
2023-01-22 09:45:13.798967: step: 162/466, loss: 0.7275187373161316
2023-01-22 09:45:14.348616: step: 164/466, loss: 2.613816499710083
2023-01-22 09:45:14.945643: step: 166/466, loss: 2.0387091636657715
2023-01-22 09:45:15.587087: step: 168/466, loss: 0.9608566761016846
2023-01-22 09:45:16.274236: step: 170/466, loss: 0.5621725916862488
2023-01-22 09:45:16.933667: step: 172/466, loss: 0.38025912642478943
2023-01-22 09:45:17.578194: step: 174/466, loss: 2.2258999347686768
2023-01-22 09:45:18.217686: step: 176/466, loss: 1.0006108283996582
2023-01-22 09:45:18.833946: step: 178/466, loss: 1.6930632591247559
2023-01-22 09:45:19.408739: step: 180/466, loss: 0.9917345643043518
2023-01-22 09:45:20.035849: step: 182/466, loss: 1.0644450187683105
2023-01-22 09:45:20.678777: step: 184/466, loss: 5.928044319152832
2023-01-22 09:45:21.326903: step: 186/466, loss: 1.5287227630615234
2023-01-22 09:45:21.978422: step: 188/466, loss: 0.4561346173286438
2023-01-22 09:45:22.589078: step: 190/466, loss: 1.8703564405441284
2023-01-22 09:45:23.180938: step: 192/466, loss: 0.7041752338409424
2023-01-22 09:45:23.786873: step: 194/466, loss: 0.954352855682373
2023-01-22 09:45:24.428516: step: 196/466, loss: 4.054781436920166
2023-01-22 09:45:25.048354: step: 198/466, loss: 2.8203413486480713
2023-01-22 09:45:25.704498: step: 200/466, loss: 1.3781147003173828
2023-01-22 09:45:26.336921: step: 202/466, loss: 0.9691088199615479
2023-01-22 09:45:26.952413: step: 204/466, loss: 0.4873339533805847
2023-01-22 09:45:27.537365: step: 206/466, loss: 0.4727945923805237
2023-01-22 09:45:28.127156: step: 208/466, loss: 1.238034963607788
2023-01-22 09:45:28.758548: step: 210/466, loss: 0.9873964786529541
2023-01-22 09:45:29.390365: step: 212/466, loss: 1.174421787261963
2023-01-22 09:45:30.010241: step: 214/466, loss: 0.6589047908782959
2023-01-22 09:45:30.580859: step: 216/466, loss: 0.8934488892555237
2023-01-22 09:45:31.205573: step: 218/466, loss: 0.25499317049980164
2023-01-22 09:45:31.865154: step: 220/466, loss: 2.4782047271728516
2023-01-22 09:45:32.500892: step: 222/466, loss: 2.103694438934326
2023-01-22 09:45:33.087573: step: 224/466, loss: 1.934326410293579
2023-01-22 09:45:33.736506: step: 226/466, loss: 1.7219918966293335
2023-01-22 09:45:34.402417: step: 228/466, loss: 6.521765232086182
2023-01-22 09:45:35.030893: step: 230/466, loss: 0.5097403526306152
2023-01-22 09:45:35.765001: step: 232/466, loss: 1.2184298038482666
2023-01-22 09:45:36.380193: step: 234/466, loss: 1.6723867654800415
2023-01-22 09:45:36.975587: step: 236/466, loss: 0.8256341814994812
2023-01-22 09:45:37.608233: step: 238/466, loss: 1.6084046363830566
2023-01-22 09:45:38.201998: step: 240/466, loss: 1.970080852508545
2023-01-22 09:45:38.770873: step: 242/466, loss: 7.471807479858398
2023-01-22 09:45:39.347854: step: 244/466, loss: 3.635483741760254
2023-01-22 09:45:40.016402: step: 246/466, loss: 6.248327732086182
2023-01-22 09:45:40.653863: step: 248/466, loss: 0.9783942699432373
2023-01-22 09:45:41.258025: step: 250/466, loss: 0.5623174905776978
2023-01-22 09:45:41.922901: step: 252/466, loss: 1.348527431488037
2023-01-22 09:45:42.561630: step: 254/466, loss: 5.015925407409668
2023-01-22 09:45:43.204601: step: 256/466, loss: 0.29038581252098083
2023-01-22 09:45:43.838331: step: 258/466, loss: 1.9894683361053467
2023-01-22 09:45:44.443363: step: 260/466, loss: 1.0170519351959229
2023-01-22 09:45:45.064577: step: 262/466, loss: 1.5105358362197876
2023-01-22 09:45:45.604132: step: 264/466, loss: 1.338410496711731
2023-01-22 09:45:46.444589: step: 266/466, loss: 1.3438609838485718
2023-01-22 09:45:47.115041: step: 268/466, loss: 1.1082217693328857
2023-01-22 09:45:47.751106: step: 270/466, loss: 0.8171354532241821
2023-01-22 09:45:48.315609: step: 272/466, loss: 1.6580418348312378
2023-01-22 09:45:48.958943: step: 274/466, loss: 0.27594417333602905
2023-01-22 09:45:49.598378: step: 276/466, loss: 1.3367584943771362
2023-01-22 09:45:50.198582: step: 278/466, loss: 7.378208160400391
2023-01-22 09:45:50.848390: step: 280/466, loss: 1.6158980131149292
2023-01-22 09:45:51.513129: step: 282/466, loss: 0.30594396591186523
2023-01-22 09:45:52.153850: step: 284/466, loss: 0.8640335202217102
2023-01-22 09:45:52.761960: step: 286/466, loss: 2.3039379119873047
2023-01-22 09:45:53.344110: step: 288/466, loss: 0.6274563074111938
2023-01-22 09:45:53.934196: step: 290/466, loss: 4.776246070861816
2023-01-22 09:45:54.565926: step: 292/466, loss: 2.09666109085083
2023-01-22 09:45:55.151605: step: 294/466, loss: 0.856423020362854
2023-01-22 09:45:55.797079: step: 296/466, loss: 0.7674209475517273
2023-01-22 09:45:56.404000: step: 298/466, loss: 1.4367313385009766
2023-01-22 09:45:57.064254: step: 300/466, loss: 7.290987014770508
2023-01-22 09:45:57.723103: step: 302/466, loss: 1.410239338874817
2023-01-22 09:45:58.354678: step: 304/466, loss: 2.5137248039245605
2023-01-22 09:45:58.937008: step: 306/466, loss: 3.087893009185791
2023-01-22 09:45:59.585166: step: 308/466, loss: 2.1465885639190674
2023-01-22 09:46:00.219148: step: 310/466, loss: 0.7133780121803284
2023-01-22 09:46:00.851435: step: 312/466, loss: 1.4325982332229614
2023-01-22 09:46:01.468434: step: 314/466, loss: 1.3673746585845947
2023-01-22 09:46:02.084159: step: 316/466, loss: 2.9142794609069824
2023-01-22 09:46:02.734373: step: 318/466, loss: 0.836786150932312
2023-01-22 09:46:03.266956: step: 320/466, loss: 3.114619731903076
2023-01-22 09:46:03.843155: step: 322/466, loss: 0.8955129384994507
2023-01-22 09:46:04.459794: step: 324/466, loss: 0.37643033266067505
2023-01-22 09:46:05.044509: step: 326/466, loss: 3.5487020015716553
2023-01-22 09:46:05.602821: step: 328/466, loss: 0.6180459856987
2023-01-22 09:46:06.276933: step: 330/466, loss: 1.730918526649475
2023-01-22 09:46:06.904812: step: 332/466, loss: 0.4487214982509613
2023-01-22 09:46:07.466461: step: 334/466, loss: 1.153430461883545
2023-01-22 09:46:08.108264: step: 336/466, loss: 4.707362174987793
2023-01-22 09:46:08.849613: step: 338/466, loss: 0.5890976190567017
2023-01-22 09:46:09.397300: step: 340/466, loss: 0.44397884607315063
2023-01-22 09:46:09.967532: step: 342/466, loss: 1.1188628673553467
2023-01-22 09:46:10.611041: step: 344/466, loss: 1.7424533367156982
2023-01-22 09:46:11.250698: step: 346/466, loss: 0.40749967098236084
2023-01-22 09:46:11.931914: step: 348/466, loss: 0.6263022422790527
2023-01-22 09:46:12.577287: step: 350/466, loss: 7.1182403564453125
2023-01-22 09:46:13.242380: step: 352/466, loss: 1.014331579208374
2023-01-22 09:46:13.812384: step: 354/466, loss: 0.2972826063632965
2023-01-22 09:46:14.474781: step: 356/466, loss: 2.3395979404449463
2023-01-22 09:46:15.134060: step: 358/466, loss: 0.20275095105171204
2023-01-22 09:46:15.709617: step: 360/466, loss: 1.164963960647583
2023-01-22 09:46:16.334484: step: 362/466, loss: 1.2121949195861816
2023-01-22 09:46:16.977362: step: 364/466, loss: 1.8604505062103271
2023-01-22 09:46:17.646822: step: 366/466, loss: 1.8596770763397217
2023-01-22 09:46:18.227147: step: 368/466, loss: 0.3896671533584595
2023-01-22 09:46:18.857029: step: 370/466, loss: 0.41178327798843384
2023-01-22 09:46:19.459971: step: 372/466, loss: 1.0141046047210693
2023-01-22 09:46:20.149052: step: 374/466, loss: 4.194189071655273
2023-01-22 09:46:20.799792: step: 376/466, loss: 0.7731515169143677
2023-01-22 09:46:21.411920: step: 378/466, loss: 1.2757165431976318
2023-01-22 09:46:22.083660: step: 380/466, loss: 0.7043675780296326
2023-01-22 09:46:22.750376: step: 382/466, loss: 0.7703564763069153
2023-01-22 09:46:23.451291: step: 384/466, loss: 4.547868728637695
2023-01-22 09:46:24.100978: step: 386/466, loss: 1.9865307807922363
2023-01-22 09:46:24.680244: step: 388/466, loss: 1.0352140665054321
2023-01-22 09:46:25.251330: step: 390/466, loss: 0.7538135647773743
2023-01-22 09:46:25.865043: step: 392/466, loss: 0.7600349187850952
2023-01-22 09:46:26.558424: step: 394/466, loss: 3.319429397583008
2023-01-22 09:46:27.168303: step: 396/466, loss: 1.6095876693725586
2023-01-22 09:46:27.864660: step: 398/466, loss: 0.44667908549308777
2023-01-22 09:46:28.457318: step: 400/466, loss: 2.0603199005126953
2023-01-22 09:46:29.048709: step: 402/466, loss: 0.6938265562057495
2023-01-22 09:46:29.629608: step: 404/466, loss: 1.0607950687408447
2023-01-22 09:46:30.283969: step: 406/466, loss: 2.9250197410583496
2023-01-22 09:46:30.956685: step: 408/466, loss: 0.7286068797111511
2023-01-22 09:46:31.588927: step: 410/466, loss: 0.30672362446784973
2023-01-22 09:46:32.219684: step: 412/466, loss: 4.567588806152344
2023-01-22 09:46:32.899746: step: 414/466, loss: 0.5163266658782959
2023-01-22 09:46:33.561457: step: 416/466, loss: 0.4423064589500427
2023-01-22 09:46:34.174785: step: 418/466, loss: 3.9670162200927734
2023-01-22 09:46:34.861249: step: 420/466, loss: 2.407794713973999
2023-01-22 09:46:35.551144: step: 422/466, loss: 1.1102468967437744
2023-01-22 09:46:36.210524: step: 424/466, loss: 0.608360230922699
2023-01-22 09:46:36.770301: step: 426/466, loss: 1.0862195491790771
2023-01-22 09:46:37.390760: step: 428/466, loss: 1.6679542064666748
2023-01-22 09:46:37.985275: step: 430/466, loss: 1.446641206741333
2023-01-22 09:46:38.622796: step: 432/466, loss: 0.6515058279037476
2023-01-22 09:46:39.213417: step: 434/466, loss: 1.2712185382843018
2023-01-22 09:46:39.793586: step: 436/466, loss: 0.557579517364502
2023-01-22 09:46:40.407266: step: 438/466, loss: 2.2417097091674805
2023-01-22 09:46:40.987990: step: 440/466, loss: 1.2886192798614502
2023-01-22 09:46:41.638600: step: 442/466, loss: 2.7027368545532227
2023-01-22 09:46:42.256962: step: 444/466, loss: 1.0164638757705688
2023-01-22 09:46:42.877374: step: 446/466, loss: 1.0663093328475952
2023-01-22 09:46:43.505060: step: 448/466, loss: 0.3144289553165436
2023-01-22 09:46:44.148956: step: 450/466, loss: 1.0528595447540283
2023-01-22 09:46:44.822370: step: 452/466, loss: 0.9924498200416565
2023-01-22 09:46:45.491422: step: 454/466, loss: 0.743733823299408
2023-01-22 09:46:46.072003: step: 456/466, loss: 1.4638175964355469
2023-01-22 09:46:46.675398: step: 458/466, loss: 2.861349105834961
2023-01-22 09:46:47.262124: step: 460/466, loss: 1.7835991382598877
2023-01-22 09:46:47.886131: step: 462/466, loss: 0.4124907851219177
2023-01-22 09:46:48.561720: step: 464/466, loss: 1.207486629486084
2023-01-22 09:46:49.212090: step: 466/466, loss: 0.31861570477485657
2023-01-22 09:46:49.885756: step: 468/466, loss: 1.9745697975158691
2023-01-22 09:46:50.459906: step: 470/466, loss: 2.2617297172546387
2023-01-22 09:46:51.058689: step: 472/466, loss: 2.919684410095215
2023-01-22 09:46:51.743047: step: 474/466, loss: 3.470987558364868
2023-01-22 09:46:52.356242: step: 476/466, loss: 0.8952714204788208
2023-01-22 09:46:53.032665: step: 478/466, loss: 2.6644530296325684
2023-01-22 09:46:53.668032: step: 480/466, loss: 2.006141185760498
2023-01-22 09:46:54.272688: step: 482/466, loss: 4.732282638549805
2023-01-22 09:46:54.906673: step: 484/466, loss: 1.192002773284912
2023-01-22 09:46:55.542030: step: 486/466, loss: 2.153209686279297
2023-01-22 09:46:56.114146: step: 488/466, loss: 1.0872876644134521
2023-01-22 09:46:56.755720: step: 490/466, loss: 2.7692017555236816
2023-01-22 09:46:57.354665: step: 492/466, loss: 0.38183367252349854
2023-01-22 09:46:57.949625: step: 494/466, loss: 1.6027545928955078
2023-01-22 09:46:58.553714: step: 496/466, loss: 0.4790688157081604
2023-01-22 09:46:59.169680: step: 498/466, loss: 0.7380142211914062
2023-01-22 09:46:59.857979: step: 500/466, loss: 3.60632586479187
2023-01-22 09:47:00.561159: step: 502/466, loss: 1.2529616355895996
2023-01-22 09:47:01.164176: step: 504/466, loss: 2.807490348815918
2023-01-22 09:47:01.735263: step: 506/466, loss: 1.3200613260269165
2023-01-22 09:47:02.352608: step: 508/466, loss: 5.073716163635254
2023-01-22 09:47:02.972314: step: 510/466, loss: 0.47445380687713623
2023-01-22 09:47:03.599506: step: 512/466, loss: 0.7447572350502014
2023-01-22 09:47:04.212591: step: 514/466, loss: 2.9716830253601074
2023-01-22 09:47:04.773224: step: 516/466, loss: 1.3143442869186401
2023-01-22 09:47:05.406487: step: 518/466, loss: 3.1109838485717773
2023-01-22 09:47:06.140778: step: 520/466, loss: 0.7308715581893921
2023-01-22 09:47:06.743991: step: 522/466, loss: 2.5015788078308105
2023-01-22 09:47:07.438416: step: 524/466, loss: 1.1616835594177246
2023-01-22 09:47:08.025124: step: 526/466, loss: 1.4940903186798096
2023-01-22 09:47:08.647419: step: 528/466, loss: 1.7208335399627686
2023-01-22 09:47:09.223619: step: 530/466, loss: 2.474591016769409
2023-01-22 09:47:09.817691: step: 532/466, loss: 2.384066581726074
2023-01-22 09:47:10.483142: step: 534/466, loss: 0.5469551086425781
2023-01-22 09:47:11.110539: step: 536/466, loss: 0.5962178707122803
2023-01-22 09:47:11.751680: step: 538/466, loss: 1.3938179016113281
2023-01-22 09:47:12.433988: step: 540/466, loss: 1.20782470703125
2023-01-22 09:47:13.059783: step: 542/466, loss: 0.7852320075035095
2023-01-22 09:47:13.679522: step: 544/466, loss: 0.7039216160774231
2023-01-22 09:47:14.310872: step: 546/466, loss: 0.3611880838871002
2023-01-22 09:47:14.906988: step: 548/466, loss: 0.287416934967041
2023-01-22 09:47:15.566141: step: 550/466, loss: 0.48172226548194885
2023-01-22 09:47:16.136779: step: 552/466, loss: 1.6074293851852417
2023-01-22 09:47:16.735227: step: 554/466, loss: 0.7348114848136902
2023-01-22 09:47:17.371854: step: 556/466, loss: 1.5510615110397339
2023-01-22 09:47:18.015879: step: 558/466, loss: 1.1155942678451538
2023-01-22 09:47:18.646257: step: 560/466, loss: 0.3913913667201996
2023-01-22 09:47:19.297990: step: 562/466, loss: 0.7518240809440613
2023-01-22 09:47:19.905941: step: 564/466, loss: 0.8426482677459717
2023-01-22 09:47:20.525629: step: 566/466, loss: 0.9242572784423828
2023-01-22 09:47:21.099699: step: 568/466, loss: 1.272059440612793
2023-01-22 09:47:21.679090: step: 570/466, loss: 0.3866838216781616
2023-01-22 09:47:22.312595: step: 572/466, loss: 1.8356395959854126
2023-01-22 09:47:22.902291: step: 574/466, loss: 1.0556504726409912
2023-01-22 09:47:23.491047: step: 576/466, loss: 0.3894895613193512
2023-01-22 09:47:24.108485: step: 578/466, loss: 1.6263072490692139
2023-01-22 09:47:24.767125: step: 580/466, loss: 0.590576708316803
2023-01-22 09:47:25.412783: step: 582/466, loss: 0.2043585479259491
2023-01-22 09:47:26.045188: step: 584/466, loss: 0.3871784806251526
2023-01-22 09:47:26.664683: step: 586/466, loss: 0.532533586025238
2023-01-22 09:47:27.236603: step: 588/466, loss: 0.3990240693092346
2023-01-22 09:47:27.834149: step: 590/466, loss: 1.0591825246810913
2023-01-22 09:47:28.484646: step: 592/466, loss: 0.41628965735435486
2023-01-22 09:47:29.111858: step: 594/466, loss: 0.5125265121459961
2023-01-22 09:47:29.686595: step: 596/466, loss: 0.779667317867279
2023-01-22 09:47:30.245650: step: 598/466, loss: 0.9149830341339111
2023-01-22 09:47:30.831753: step: 600/466, loss: 0.9261771440505981
2023-01-22 09:47:31.507239: step: 602/466, loss: 0.8956090211868286
2023-01-22 09:47:32.120168: step: 604/466, loss: 1.623434066772461
2023-01-22 09:47:32.728216: step: 606/466, loss: 0.27385449409484863
2023-01-22 09:47:33.306828: step: 608/466, loss: 0.6099010109901428
2023-01-22 09:47:33.906860: step: 610/466, loss: 13.654857635498047
2023-01-22 09:47:34.511768: step: 612/466, loss: 0.9391835331916809
2023-01-22 09:47:35.154535: step: 614/466, loss: 1.1547439098358154
2023-01-22 09:47:35.761976: step: 616/466, loss: 0.310383677482605
2023-01-22 09:47:36.353432: step: 618/466, loss: 1.902803897857666
2023-01-22 09:47:36.928647: step: 620/466, loss: 1.2837306261062622
2023-01-22 09:47:37.594916: step: 622/466, loss: 0.4341290593147278
2023-01-22 09:47:38.215527: step: 624/466, loss: 0.219343900680542
2023-01-22 09:47:38.851779: step: 626/466, loss: 0.5104776620864868
2023-01-22 09:47:39.481256: step: 628/466, loss: 1.1290161609649658
2023-01-22 09:47:40.149906: step: 630/466, loss: 0.6613913178443909
2023-01-22 09:47:40.705856: step: 632/466, loss: 0.8362389802932739
2023-01-22 09:47:41.278619: step: 634/466, loss: 0.9189055562019348
2023-01-22 09:47:41.926860: step: 636/466, loss: 1.5628864765167236
2023-01-22 09:47:42.565378: step: 638/466, loss: 0.7641006708145142
2023-01-22 09:47:43.159835: step: 640/466, loss: 0.5106600522994995
2023-01-22 09:47:43.778439: step: 642/466, loss: 0.38074567914009094
2023-01-22 09:47:44.566717: step: 644/466, loss: 1.1373883485794067
2023-01-22 09:47:45.187649: step: 646/466, loss: 1.6016144752502441
2023-01-22 09:47:45.801414: step: 648/466, loss: 0.6494314670562744
2023-01-22 09:47:46.401513: step: 650/466, loss: 1.4632269144058228
2023-01-22 09:47:47.035029: step: 652/466, loss: 0.897118866443634
2023-01-22 09:47:47.635825: step: 654/466, loss: 4.597709655761719
2023-01-22 09:47:48.226977: step: 656/466, loss: 1.9993581771850586
2023-01-22 09:47:48.947656: step: 658/466, loss: 0.49946463108062744
2023-01-22 09:47:49.532449: step: 660/466, loss: 1.2993544340133667
2023-01-22 09:47:50.190560: step: 662/466, loss: 0.7454898357391357
2023-01-22 09:47:50.785568: step: 664/466, loss: 1.7169160842895508
2023-01-22 09:47:51.397866: step: 666/466, loss: 1.1759848594665527
2023-01-22 09:47:52.052442: step: 668/466, loss: 8.05697250366211
2023-01-22 09:47:52.648563: step: 670/466, loss: 0.5740476250648499
2023-01-22 09:47:53.329467: step: 672/466, loss: 2.474055290222168
2023-01-22 09:47:53.929022: step: 674/466, loss: 0.395702600479126
2023-01-22 09:47:54.483249: step: 676/466, loss: 1.6007153987884521
2023-01-22 09:47:55.077991: step: 678/466, loss: 0.2818623185157776
2023-01-22 09:47:55.662070: step: 680/466, loss: 4.446594715118408
2023-01-22 09:47:56.347125: step: 682/466, loss: 1.9578866958618164
2023-01-22 09:47:56.979694: step: 684/466, loss: 1.037970781326294
2023-01-22 09:47:57.557574: step: 686/466, loss: 0.7141876220703125
2023-01-22 09:47:58.168912: step: 688/466, loss: 2.255034923553467
2023-01-22 09:47:58.834107: step: 690/466, loss: 10.886655807495117
2023-01-22 09:47:59.469001: step: 692/466, loss: 1.1650443077087402
2023-01-22 09:48:00.103820: step: 694/466, loss: 5.413592338562012
2023-01-22 09:48:00.801703: step: 696/466, loss: 0.4792379140853882
2023-01-22 09:48:01.595943: step: 698/466, loss: 2.427898645401001
2023-01-22 09:48:02.215733: step: 700/466, loss: 3.009459972381592
2023-01-22 09:48:02.832029: step: 702/466, loss: 1.1028814315795898
2023-01-22 09:48:03.418356: step: 704/466, loss: 1.290452241897583
2023-01-22 09:48:04.025036: step: 706/466, loss: 1.0856568813323975
2023-01-22 09:48:04.672933: step: 708/466, loss: 5.001242160797119
2023-01-22 09:48:05.260511: step: 710/466, loss: 0.9065005779266357
2023-01-22 09:48:05.903132: step: 712/466, loss: 3.011390209197998
2023-01-22 09:48:06.550287: step: 714/466, loss: 1.2671661376953125
2023-01-22 09:48:07.279373: step: 716/466, loss: 1.3516714572906494
2023-01-22 09:48:07.905554: step: 718/466, loss: 0.7642638087272644
2023-01-22 09:48:08.493486: step: 720/466, loss: 2.3630306720733643
2023-01-22 09:48:09.089861: step: 722/466, loss: 4.939443588256836
2023-01-22 09:48:09.739879: step: 724/466, loss: 3.4752659797668457
2023-01-22 09:48:10.382938: step: 726/466, loss: 0.9839559197425842
2023-01-22 09:48:10.980675: step: 728/466, loss: 0.7253423929214478
2023-01-22 09:48:11.524775: step: 730/466, loss: 0.8835292458534241
2023-01-22 09:48:12.131520: step: 732/466, loss: 12.320352554321289
2023-01-22 09:48:12.702451: step: 734/466, loss: 0.40207937359809875
2023-01-22 09:48:13.358468: step: 736/466, loss: 1.4247490167617798
2023-01-22 09:48:14.012243: step: 738/466, loss: 1.3991518020629883
2023-01-22 09:48:14.630057: step: 740/466, loss: 0.4203867018222809
2023-01-22 09:48:15.279295: step: 742/466, loss: 1.7171530723571777
2023-01-22 09:48:15.957494: step: 744/466, loss: 0.23868979513645172
2023-01-22 09:48:16.612630: step: 746/466, loss: 0.8822340965270996
2023-01-22 09:48:17.204884: step: 748/466, loss: 1.2991575002670288
2023-01-22 09:48:17.783373: step: 750/466, loss: 0.4201277196407318
2023-01-22 09:48:18.490660: step: 752/466, loss: 0.22441129386425018
2023-01-22 09:48:19.102231: step: 754/466, loss: 0.4418560266494751
2023-01-22 09:48:19.776079: step: 756/466, loss: 1.5701426267623901
2023-01-22 09:48:20.383958: step: 758/466, loss: 1.8360600471496582
2023-01-22 09:48:20.991092: step: 760/466, loss: 1.4463838338851929
2023-01-22 09:48:21.610166: step: 762/466, loss: 0.6107949018478394
2023-01-22 09:48:22.209497: step: 764/466, loss: 0.6653521060943604
2023-01-22 09:48:22.817553: step: 766/466, loss: 0.731359601020813
2023-01-22 09:48:23.436177: step: 768/466, loss: 1.046613097190857
2023-01-22 09:48:24.039059: step: 770/466, loss: 0.967674970626831
2023-01-22 09:48:24.681073: step: 772/466, loss: 0.46457409858703613
2023-01-22 09:48:25.317606: step: 774/466, loss: 0.9775880575180054
2023-01-22 09:48:25.918494: step: 776/466, loss: 1.8870127201080322
2023-01-22 09:48:26.508055: step: 778/466, loss: 0.9271981716156006
2023-01-22 09:48:27.155356: step: 780/466, loss: 0.6026844382286072
2023-01-22 09:48:27.811527: step: 782/466, loss: 0.5312908887863159
2023-01-22 09:48:28.410684: step: 784/466, loss: 1.074860692024231
2023-01-22 09:48:28.994030: step: 786/466, loss: 0.8712797164916992
2023-01-22 09:48:29.575219: step: 788/466, loss: 0.5918893814086914
2023-01-22 09:48:30.250941: step: 790/466, loss: 4.984042644500732
2023-01-22 09:48:30.846797: step: 792/466, loss: 1.0119539499282837
2023-01-22 09:48:31.449177: step: 794/466, loss: 0.4847181439399719
2023-01-22 09:48:32.100139: step: 796/466, loss: 1.4674978256225586
2023-01-22 09:48:32.755960: step: 798/466, loss: 1.7132019996643066
2023-01-22 09:48:33.361795: step: 800/466, loss: 1.2459526062011719
2023-01-22 09:48:33.966961: step: 802/466, loss: 1.554520606994629
2023-01-22 09:48:34.625835: step: 804/466, loss: 0.8004475831985474
2023-01-22 09:48:35.190384: step: 806/466, loss: 1.0957187414169312
2023-01-22 09:48:35.834201: step: 808/466, loss: 1.0078699588775635
2023-01-22 09:48:36.470115: step: 810/466, loss: 0.3722212314605713
2023-01-22 09:48:37.023996: step: 812/466, loss: 1.91087806224823
2023-01-22 09:48:37.642025: step: 814/466, loss: 0.80485600233078
2023-01-22 09:48:38.234265: step: 816/466, loss: 0.5591756701469421
2023-01-22 09:48:38.862346: step: 818/466, loss: 1.6538398265838623
2023-01-22 09:48:39.479603: step: 820/466, loss: 3.7490296363830566
2023-01-22 09:48:40.153134: step: 822/466, loss: 2.7190322875976562
2023-01-22 09:48:40.785631: step: 824/466, loss: 0.6726736426353455
2023-01-22 09:48:41.353710: step: 826/466, loss: 2.7653231620788574
2023-01-22 09:48:41.990998: step: 828/466, loss: 1.475852131843567
2023-01-22 09:48:42.692148: step: 830/466, loss: 2.943328857421875
2023-01-22 09:48:43.352975: step: 832/466, loss: 1.0336472988128662
2023-01-22 09:48:43.965883: step: 834/466, loss: 0.3038322627544403
2023-01-22 09:48:44.555718: step: 836/466, loss: 1.8001176118850708
2023-01-22 09:48:45.123421: step: 838/466, loss: 0.42354637384414673
2023-01-22 09:48:45.734923: step: 840/466, loss: 0.46030494570732117
2023-01-22 09:48:46.354979: step: 842/466, loss: 0.9527333378791809
2023-01-22 09:48:46.969719: step: 844/466, loss: 0.7411099076271057
2023-01-22 09:48:47.646423: step: 846/466, loss: 1.9437055587768555
2023-01-22 09:48:48.463130: step: 848/466, loss: 2.4826438426971436
2023-01-22 09:48:48.996767: step: 850/466, loss: 1.0268150568008423
2023-01-22 09:48:49.620552: step: 852/466, loss: 0.6188070178031921
2023-01-22 09:48:50.266648: step: 854/466, loss: 5.253035068511963
2023-01-22 09:48:50.894105: step: 856/466, loss: 0.48597168922424316
2023-01-22 09:48:51.507639: step: 858/466, loss: 0.34880343079566956
2023-01-22 09:48:52.117138: step: 860/466, loss: 2.08416485786438
2023-01-22 09:48:52.743458: step: 862/466, loss: 0.24188533425331116
2023-01-22 09:48:53.372574: step: 864/466, loss: 0.2954680323600769
2023-01-22 09:48:54.028441: step: 866/466, loss: 0.2146918773651123
2023-01-22 09:48:54.584588: step: 868/466, loss: 3.6382498741149902
2023-01-22 09:48:55.262142: step: 870/466, loss: 0.46276894211769104
2023-01-22 09:48:55.934730: step: 872/466, loss: 2.3691139221191406
2023-01-22 09:48:56.591770: step: 874/466, loss: 1.9170887470245361
2023-01-22 09:48:57.154275: step: 876/466, loss: 0.5025712251663208
2023-01-22 09:48:57.765331: step: 878/466, loss: 1.055784821510315
2023-01-22 09:48:58.359113: step: 880/466, loss: 1.6783256530761719
2023-01-22 09:48:58.952440: step: 882/466, loss: 0.9137502312660217
2023-01-22 09:48:59.659312: step: 884/466, loss: 0.7934946417808533
2023-01-22 09:49:00.312164: step: 886/466, loss: 1.179140567779541
2023-01-22 09:49:01.021051: step: 888/466, loss: 0.5907734036445618
2023-01-22 09:49:01.611347: step: 890/466, loss: 0.8271014094352722
2023-01-22 09:49:02.215232: step: 892/466, loss: 1.8222496509552002
2023-01-22 09:49:02.825420: step: 894/466, loss: 0.6691303253173828
2023-01-22 09:49:03.409354: step: 896/466, loss: 1.140409231185913
2023-01-22 09:49:04.040210: step: 898/466, loss: 0.9140684604644775
2023-01-22 09:49:04.597882: step: 900/466, loss: 0.8692017197608948
2023-01-22 09:49:05.194446: step: 902/466, loss: 0.9234033226966858
2023-01-22 09:49:05.819909: step: 904/466, loss: 3.5146474838256836
2023-01-22 09:49:06.449502: step: 906/466, loss: 0.4510563313961029
2023-01-22 09:49:07.139129: step: 908/466, loss: 1.0838690996170044
2023-01-22 09:49:07.782745: step: 910/466, loss: 1.114465355873108
2023-01-22 09:49:08.391961: step: 912/466, loss: 0.6830224394798279
2023-01-22 09:49:08.979809: step: 914/466, loss: 0.6976163983345032
2023-01-22 09:49:09.564674: step: 916/466, loss: 2.7160091400146484
2023-01-22 09:49:10.227212: step: 918/466, loss: 0.525048017501831
2023-01-22 09:49:10.853604: step: 920/466, loss: 1.2110346555709839
2023-01-22 09:49:11.462106: step: 922/466, loss: 0.9209542870521545
2023-01-22 09:49:12.101283: step: 924/466, loss: 1.5772969722747803
2023-01-22 09:49:12.749606: step: 926/466, loss: 1.398496389389038
2023-01-22 09:49:13.480808: step: 928/466, loss: 1.5231181383132935
2023-01-22 09:49:14.138188: step: 930/466, loss: 0.5613966584205627
2023-01-22 09:49:14.769699: step: 932/466, loss: 1.8047528266906738
==================================================
Loss: 1.637
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.25636211011211013, 'r': 0.20829421446608948, 'f1': 0.22984189182465048}, 'combined': 0.16935718344974246, 'epoch': 2}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.2695231859963899, 'r': 0.21989978352052028, 'f1': 0.24219578542816744}, 'combined': 0.1516553048942731, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.23587630849753696, 'r': 0.20767857142857143, 'f1': 0.22088114458699726}, 'combined': 0.16275452759041903, 'epoch': 2}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.283777480995869, 'r': 0.22441194845209841, 'f1': 0.2506272415240455}, 'combined': 0.15531829052194365, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2112110620110113, 'r': 0.20439780194614, 'f1': 0.20774858558460127}, 'combined': 0.15307790516760092, 'epoch': 2}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3124898450851608, 'r': 0.22328768515118536, 'f1': 0.26046308478647234}, 'combined': 0.17278244238310542, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2608695652173913, 'r': 0.17142857142857143, 'f1': 0.20689655172413796}, 'combined': 0.13793103448275862, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2857142857142857, 'r': 0.13793103448275862, 'f1': 0.18604651162790697}, 'combined': 0.12403100775193798, 'epoch': 2}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3320471810797898, 'r': 0.2039987407390013, 'f1': 0.252729119088833}, 'combined': 0.18622145617071903, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.29574588662703416, 'r': 0.1626735715441757, 'f1': 0.20989527730365423}, 'combined': 0.13142975307798913, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35294117647058826, 'r': 0.17142857142857143, 'f1': 0.23076923076923078}, 'combined': 0.15384615384615385, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.23587630849753696, 'r': 0.20767857142857143, 'f1': 0.22088114458699726}, 'combined': 0.16275452759041903, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.283777480995869, 'r': 0.22441194845209841, 'f1': 0.2506272415240455}, 'combined': 0.15531829052194365, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30841750503018106, 'r': 0.2073640422077922, 'f1': 0.24799142533570623}, 'combined': 0.182730523931573, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3463263399393878, 'r': 0.1569095872288562, 'f1': 0.2159699660243139}, 'combined': 0.14326720518444586, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.375, 'r': 0.12931034482758622, 'f1': 0.19230769230769235}, 'combined': 0.12820512820512822, '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 09:51:55.394785: step: 2/466, loss: 3.664102077484131
2023-01-22 09:51:55.953989: step: 4/466, loss: 0.40151816606521606
2023-01-22 09:51:56.526330: step: 6/466, loss: 2.1475913524627686
2023-01-22 09:51:57.096139: step: 8/466, loss: 0.7339213490486145
2023-01-22 09:51:57.731076: step: 10/466, loss: 4.051681041717529
2023-01-22 09:51:58.327023: step: 12/466, loss: 1.5498143434524536
2023-01-22 09:51:59.020984: step: 14/466, loss: 2.397935390472412
2023-01-22 09:51:59.608008: step: 16/466, loss: 1.6067132949829102
2023-01-22 09:52:00.222005: step: 18/466, loss: 3.1149888038635254
2023-01-22 09:52:00.818000: step: 20/466, loss: 1.5309289693832397
2023-01-22 09:52:01.386582: step: 22/466, loss: 0.772601842880249
2023-01-22 09:52:01.992099: step: 24/466, loss: 0.8743709921836853
2023-01-22 09:52:02.601832: step: 26/466, loss: 0.5453883409500122
2023-01-22 09:52:03.242792: step: 28/466, loss: 0.5393946766853333
2023-01-22 09:52:03.895940: step: 30/466, loss: 0.6002148389816284
2023-01-22 09:52:04.480744: step: 32/466, loss: 0.5188323259353638
2023-01-22 09:52:05.122760: step: 34/466, loss: 0.7406638264656067
2023-01-22 09:52:05.744357: step: 36/466, loss: 1.0719877481460571
2023-01-22 09:52:06.429874: step: 38/466, loss: 0.2701267898082733
2023-01-22 09:52:07.091064: step: 40/466, loss: 1.4338196516036987
2023-01-22 09:52:07.617218: step: 42/466, loss: 0.8116973638534546
2023-01-22 09:52:08.199135: step: 44/466, loss: 1.9013493061065674
2023-01-22 09:52:08.795468: step: 46/466, loss: 0.285178005695343
2023-01-22 09:52:09.388045: step: 48/466, loss: 1.4673213958740234
2023-01-22 09:52:09.988970: step: 50/466, loss: 0.21668323874473572
2023-01-22 09:52:10.618057: step: 52/466, loss: 0.46653103828430176
2023-01-22 09:52:11.268338: step: 54/466, loss: 0.36020365357398987
2023-01-22 09:52:11.917969: step: 56/466, loss: 1.5513995885849
2023-01-22 09:52:12.533792: step: 58/466, loss: 2.431891441345215
2023-01-22 09:52:13.166899: step: 60/466, loss: 1.670435905456543
2023-01-22 09:52:13.772536: step: 62/466, loss: 0.7893364429473877
2023-01-22 09:52:14.357854: step: 64/466, loss: 16.907676696777344
2023-01-22 09:52:15.062563: step: 66/466, loss: 2.427928924560547
2023-01-22 09:52:15.684681: step: 68/466, loss: 0.8623694777488708
2023-01-22 09:52:16.283225: step: 70/466, loss: 0.2605237066745758
2023-01-22 09:52:16.888656: step: 72/466, loss: 2.150390625
2023-01-22 09:52:17.520600: step: 74/466, loss: 1.1520700454711914
2023-01-22 09:52:18.224335: step: 76/466, loss: 0.7585049867630005
2023-01-22 09:52:18.910166: step: 78/466, loss: 14.417007446289062
2023-01-22 09:52:19.510032: step: 80/466, loss: 1.6159945726394653
2023-01-22 09:52:20.070633: step: 82/466, loss: 0.515458345413208
2023-01-22 09:52:20.718917: step: 84/466, loss: 1.3202629089355469
2023-01-22 09:52:21.346718: step: 86/466, loss: 1.8619874715805054
2023-01-22 09:52:21.946886: step: 88/466, loss: 0.9497697949409485
2023-01-22 09:52:22.583384: step: 90/466, loss: 2.008118152618408
2023-01-22 09:52:23.274004: step: 92/466, loss: 2.1800649166107178
2023-01-22 09:52:23.917877: step: 94/466, loss: 0.2916567325592041
2023-01-22 09:52:24.561710: step: 96/466, loss: 0.7603704929351807
2023-01-22 09:52:25.244507: step: 98/466, loss: 1.2155827283859253
2023-01-22 09:52:25.832244: step: 100/466, loss: 0.31005045771598816
2023-01-22 09:52:26.462553: step: 102/466, loss: 0.2987905442714691
2023-01-22 09:52:27.110916: step: 104/466, loss: 0.3084142208099365
2023-01-22 09:52:27.731184: step: 106/466, loss: 0.5264069437980652
2023-01-22 09:52:28.381796: step: 108/466, loss: 2.4641854763031006
2023-01-22 09:52:28.995710: step: 110/466, loss: 2.1395678520202637
2023-01-22 09:52:29.622936: step: 112/466, loss: 1.2254267930984497
2023-01-22 09:52:30.362038: step: 114/466, loss: 0.19523349404335022
2023-01-22 09:52:30.977099: step: 116/466, loss: 0.5350965857505798
2023-01-22 09:52:31.607068: step: 118/466, loss: 0.7030841112136841
2023-01-22 09:52:32.274884: step: 120/466, loss: 3.22244930267334
2023-01-22 09:52:33.006276: step: 122/466, loss: 2.011723518371582
2023-01-22 09:52:33.601879: step: 124/466, loss: 0.3849104344844818
2023-01-22 09:52:34.178321: step: 126/466, loss: 1.2131569385528564
2023-01-22 09:52:34.811722: step: 128/466, loss: 3.6725645065307617
2023-01-22 09:52:35.427638: step: 130/466, loss: 0.6502686142921448
2023-01-22 09:52:36.031787: step: 132/466, loss: 0.8727032542228699
2023-01-22 09:52:36.577148: step: 134/466, loss: 0.8338615894317627
2023-01-22 09:52:37.340464: step: 136/466, loss: 0.6537538170814514
2023-01-22 09:52:37.926779: step: 138/466, loss: 0.39510753750801086
2023-01-22 09:52:38.538400: step: 140/466, loss: 0.3558765947818756
2023-01-22 09:52:39.165859: step: 142/466, loss: 1.0830470323562622
2023-01-22 09:52:39.795658: step: 144/466, loss: 2.405442953109741
2023-01-22 09:52:40.482519: step: 146/466, loss: 1.432064175605774
2023-01-22 09:52:41.133898: step: 148/466, loss: 1.0634498596191406
2023-01-22 09:52:41.756568: step: 150/466, loss: 0.53861403465271
2023-01-22 09:52:42.406663: step: 152/466, loss: 0.768478274345398
2023-01-22 09:52:43.033978: step: 154/466, loss: 2.361758232116699
2023-01-22 09:52:43.712299: step: 156/466, loss: 1.7955210208892822
2023-01-22 09:52:44.387145: step: 158/466, loss: 0.30507999658584595
2023-01-22 09:52:45.047073: step: 160/466, loss: 0.5709603428840637
2023-01-22 09:52:45.659108: step: 162/466, loss: 0.5453020334243774
2023-01-22 09:52:46.282584: step: 164/466, loss: 0.49675092101097107
2023-01-22 09:52:46.897462: step: 166/466, loss: 3.5595688819885254
2023-01-22 09:52:47.534732: step: 168/466, loss: 0.6276785135269165
2023-01-22 09:52:48.155786: step: 170/466, loss: 0.7200762629508972
2023-01-22 09:52:48.830845: step: 172/466, loss: 0.27785107493400574
2023-01-22 09:52:49.425455: step: 174/466, loss: 4.538939952850342
2023-01-22 09:52:50.067556: step: 176/466, loss: 0.8747923374176025
2023-01-22 09:52:50.698939: step: 178/466, loss: 1.369985580444336
2023-01-22 09:52:51.336196: step: 180/466, loss: 0.858673632144928
2023-01-22 09:52:51.983983: step: 182/466, loss: 0.38743600249290466
2023-01-22 09:52:52.614316: step: 184/466, loss: 1.7733240127563477
2023-01-22 09:52:53.261694: step: 186/466, loss: 1.5448582172393799
2023-01-22 09:52:53.872520: step: 188/466, loss: 2.079050064086914
2023-01-22 09:52:54.546047: step: 190/466, loss: 0.4500921964645386
2023-01-22 09:52:55.147592: step: 192/466, loss: 0.7650596499443054
2023-01-22 09:52:55.796411: step: 194/466, loss: 0.4266965389251709
2023-01-22 09:52:56.463617: step: 196/466, loss: 0.25606733560562134
2023-01-22 09:52:57.079747: step: 198/466, loss: 1.3332277536392212
2023-01-22 09:52:57.642347: step: 200/466, loss: 2.5043814182281494
2023-01-22 09:52:58.269145: step: 202/466, loss: 0.5503528714179993
2023-01-22 09:52:58.865599: step: 204/466, loss: 0.5619066953659058
2023-01-22 09:52:59.510217: step: 206/466, loss: 4.957601070404053
2023-01-22 09:53:00.173909: step: 208/466, loss: 2.668531894683838
2023-01-22 09:53:00.759034: step: 210/466, loss: 2.5844016075134277
2023-01-22 09:53:01.391315: step: 212/466, loss: 0.9975607395172119
2023-01-22 09:53:02.019661: step: 214/466, loss: 2.120330333709717
2023-01-22 09:53:02.624326: step: 216/466, loss: 0.9294872879981995
2023-01-22 09:53:03.236236: step: 218/466, loss: 2.3738186359405518
2023-01-22 09:53:03.815720: step: 220/466, loss: 0.3995184302330017
2023-01-22 09:53:04.488774: step: 222/466, loss: 0.6052391529083252
2023-01-22 09:53:05.139864: step: 224/466, loss: 0.3948894739151001
2023-01-22 09:53:05.767306: step: 226/466, loss: 0.21116848289966583
2023-01-22 09:53:06.444287: step: 228/466, loss: 3.6097004413604736
2023-01-22 09:53:07.006408: step: 230/466, loss: 0.32661372423171997
2023-01-22 09:53:07.623185: step: 232/466, loss: 0.31234103441238403
2023-01-22 09:53:08.260230: step: 234/466, loss: 1.1091272830963135
2023-01-22 09:53:08.940335: step: 236/466, loss: 0.518258810043335
2023-01-22 09:53:09.549866: step: 238/466, loss: 1.1867866516113281
2023-01-22 09:53:10.225718: step: 240/466, loss: 0.2828126847743988
2023-01-22 09:53:10.899465: step: 242/466, loss: 2.3363542556762695
2023-01-22 09:53:11.543497: step: 244/466, loss: 0.9250749349594116
2023-01-22 09:53:12.209133: step: 246/466, loss: 5.13469123840332
2023-01-22 09:53:12.809506: step: 248/466, loss: 2.2560393810272217
2023-01-22 09:53:13.436587: step: 250/466, loss: 1.9248523712158203
2023-01-22 09:53:14.132691: step: 252/466, loss: 2.239680528640747
2023-01-22 09:53:14.757342: step: 254/466, loss: 1.234459400177002
2023-01-22 09:53:15.373020: step: 256/466, loss: 2.088820219039917
2023-01-22 09:53:15.971580: step: 258/466, loss: 0.6357910633087158
2023-01-22 09:53:16.613332: step: 260/466, loss: 0.7092756032943726
2023-01-22 09:53:17.269836: step: 262/466, loss: 0.9330479502677917
2023-01-22 09:53:17.913891: step: 264/466, loss: 1.0234520435333252
2023-01-22 09:53:18.634652: step: 266/466, loss: 1.4933377504348755
2023-01-22 09:53:19.228222: step: 268/466, loss: 0.2533833980560303
2023-01-22 09:53:19.933810: step: 270/466, loss: 1.2477463483810425
2023-01-22 09:53:20.498194: step: 272/466, loss: 1.2700772285461426
2023-01-22 09:53:21.179221: step: 274/466, loss: 0.3964977562427521
2023-01-22 09:53:21.758623: step: 276/466, loss: 0.6327396035194397
2023-01-22 09:53:22.394042: step: 278/466, loss: 1.403305172920227
2023-01-22 09:53:22.963621: step: 280/466, loss: 0.45391255617141724
2023-01-22 09:53:23.549361: step: 282/466, loss: 3.441476345062256
2023-01-22 09:53:24.245352: step: 284/466, loss: 0.4469655454158783
2023-01-22 09:53:24.930485: step: 286/466, loss: 0.7628692984580994
2023-01-22 09:53:25.562664: step: 288/466, loss: 0.2860978841781616
2023-01-22 09:53:26.219808: step: 290/466, loss: 1.103793740272522
2023-01-22 09:53:26.811769: step: 292/466, loss: 1.050951361656189
2023-01-22 09:53:27.389688: step: 294/466, loss: 0.6237990260124207
2023-01-22 09:53:28.014317: step: 296/466, loss: 2.5325663089752197
2023-01-22 09:53:28.627073: step: 298/466, loss: 3.6511988639831543
2023-01-22 09:53:29.226691: step: 300/466, loss: 0.3682664632797241
2023-01-22 09:53:29.900603: step: 302/466, loss: 0.960863471031189
2023-01-22 09:53:30.482119: step: 304/466, loss: 1.7748119831085205
2023-01-22 09:53:31.146189: step: 306/466, loss: 1.5512523651123047
2023-01-22 09:53:31.783787: step: 308/466, loss: 0.5298848152160645
2023-01-22 09:53:32.328195: step: 310/466, loss: 0.7937417030334473
2023-01-22 09:53:32.970322: step: 312/466, loss: 3.202949047088623
2023-01-22 09:53:33.559935: step: 314/466, loss: 1.4959990978240967
2023-01-22 09:53:34.152427: step: 316/466, loss: 0.8022971153259277
2023-01-22 09:53:34.782957: step: 318/466, loss: 0.6434112191200256
2023-01-22 09:53:35.387463: step: 320/466, loss: 1.8489172458648682
2023-01-22 09:53:35.999991: step: 322/466, loss: 3.028909921646118
2023-01-22 09:53:36.598001: step: 324/466, loss: 6.65090274810791
2023-01-22 09:53:37.176691: step: 326/466, loss: 0.27499574422836304
2023-01-22 09:53:37.813809: step: 328/466, loss: 0.5359196066856384
2023-01-22 09:53:38.474572: step: 330/466, loss: 0.7141134738922119
2023-01-22 09:53:39.100706: step: 332/466, loss: 1.1901698112487793
2023-01-22 09:53:39.743113: step: 334/466, loss: 0.29804643988609314
2023-01-22 09:53:40.394692: step: 336/466, loss: 1.2590359449386597
2023-01-22 09:53:41.056937: step: 338/466, loss: 0.5071896910667419
2023-01-22 09:53:41.633268: step: 340/466, loss: 0.5313383340835571
2023-01-22 09:53:42.241578: step: 342/466, loss: 0.27631691098213196
2023-01-22 09:53:42.893926: step: 344/466, loss: 5.005047798156738
2023-01-22 09:53:43.537586: step: 346/466, loss: 1.0587619543075562
2023-01-22 09:53:44.192704: step: 348/466, loss: 1.04067063331604
2023-01-22 09:53:44.846370: step: 350/466, loss: 0.7760108709335327
2023-01-22 09:53:45.528694: step: 352/466, loss: 0.7545616626739502
2023-01-22 09:53:46.163481: step: 354/466, loss: 0.33428868651390076
2023-01-22 09:53:46.763623: step: 356/466, loss: 1.632312297821045
2023-01-22 09:53:47.326558: step: 358/466, loss: 0.4681653678417206
2023-01-22 09:53:47.954007: step: 360/466, loss: 1.2167729139328003
2023-01-22 09:53:48.585971: step: 362/466, loss: 1.0824363231658936
2023-01-22 09:53:49.210544: step: 364/466, loss: 0.20817844569683075
2023-01-22 09:53:49.785534: step: 366/466, loss: 0.18479155004024506
2023-01-22 09:53:50.446853: step: 368/466, loss: 1.523261547088623
2023-01-22 09:53:51.077040: step: 370/466, loss: 1.6464836597442627
2023-01-22 09:53:51.648990: step: 372/466, loss: 0.3085121810436249
2023-01-22 09:53:52.284227: step: 374/466, loss: 1.1452617645263672
2023-01-22 09:53:52.980059: step: 376/466, loss: 2.8488006591796875
2023-01-22 09:53:53.560424: step: 378/466, loss: 1.1419049501419067
2023-01-22 09:53:54.156240: step: 380/466, loss: 1.8636515140533447
2023-01-22 09:53:54.732659: step: 382/466, loss: 0.4585052728652954
2023-01-22 09:53:55.374256: step: 384/466, loss: 0.5190721154212952
2023-01-22 09:53:56.014371: step: 386/466, loss: 2.541865348815918
2023-01-22 09:53:56.607192: step: 388/466, loss: 2.4935693740844727
2023-01-22 09:53:57.259071: step: 390/466, loss: 1.0227413177490234
2023-01-22 09:53:57.827111: step: 392/466, loss: 0.1942005157470703
2023-01-22 09:53:58.544750: step: 394/466, loss: 1.268861174583435
2023-01-22 09:53:59.115934: step: 396/466, loss: 1.6738542318344116
2023-01-22 09:53:59.935010: step: 398/466, loss: 0.8321402668952942
2023-01-22 09:54:00.580020: step: 400/466, loss: 0.4387907087802887
2023-01-22 09:54:01.155655: step: 402/466, loss: 0.31822243332862854
2023-01-22 09:54:01.751447: step: 404/466, loss: 0.49491021037101746
2023-01-22 09:54:02.400440: step: 406/466, loss: 1.4946244955062866
2023-01-22 09:54:03.052403: step: 408/466, loss: 1.4691944122314453
2023-01-22 09:54:03.657270: step: 410/466, loss: 0.5321866273880005
2023-01-22 09:54:04.290280: step: 412/466, loss: 0.9545515775680542
2023-01-22 09:54:04.911414: step: 414/466, loss: 1.2634650468826294
2023-01-22 09:54:05.583131: step: 416/466, loss: 0.5948762893676758
2023-01-22 09:54:06.263769: step: 418/466, loss: 1.9317556619644165
2023-01-22 09:54:06.914437: step: 420/466, loss: 1.3317902088165283
2023-01-22 09:54:07.632658: step: 422/466, loss: 3.525007724761963
2023-01-22 09:54:08.205644: step: 424/466, loss: 1.9378377199172974
2023-01-22 09:54:08.823540: step: 426/466, loss: 0.842423677444458
2023-01-22 09:54:09.487894: step: 428/466, loss: 0.8884983658790588
2023-01-22 09:54:10.148453: step: 430/466, loss: 1.428268551826477
2023-01-22 09:54:10.800821: step: 432/466, loss: 1.537893295288086
2023-01-22 09:54:11.452327: step: 434/466, loss: 1.5906682014465332
2023-01-22 09:54:12.187940: step: 436/466, loss: 0.4472990334033966
2023-01-22 09:54:12.816723: step: 438/466, loss: 5.959825038909912
2023-01-22 09:54:13.495371: step: 440/466, loss: 0.9203157424926758
2023-01-22 09:54:14.107941: step: 442/466, loss: 0.6418544054031372
2023-01-22 09:54:14.767321: step: 444/466, loss: 1.447567343711853
2023-01-22 09:54:15.349871: step: 446/466, loss: 1.3381247520446777
2023-01-22 09:54:16.013629: step: 448/466, loss: 0.4526243507862091
2023-01-22 09:54:16.626688: step: 450/466, loss: 0.39733874797821045
2023-01-22 09:54:17.288454: step: 452/466, loss: 0.9563053250312805
2023-01-22 09:54:17.889626: step: 454/466, loss: 0.2351032793521881
2023-01-22 09:54:18.511388: step: 456/466, loss: 1.4261122941970825
2023-01-22 09:54:19.053219: step: 458/466, loss: 0.7196982502937317
2023-01-22 09:54:19.670401: step: 460/466, loss: 2.4283785820007324
2023-01-22 09:54:20.268746: step: 462/466, loss: 1.0949922800064087
2023-01-22 09:54:20.925657: step: 464/466, loss: 0.6088125705718994
2023-01-22 09:54:21.622829: step: 466/466, loss: 0.16389231383800507
2023-01-22 09:54:22.235884: step: 468/466, loss: 1.042517066001892
2023-01-22 09:54:22.908315: step: 470/466, loss: 0.8288591504096985
2023-01-22 09:54:23.494794: step: 472/466, loss: 1.2409992218017578
2023-01-22 09:54:24.150544: step: 474/466, loss: 1.3684990406036377
2023-01-22 09:54:24.833772: step: 476/466, loss: 0.4185815155506134
2023-01-22 09:54:25.356552: step: 478/466, loss: 1.293931245803833
2023-01-22 09:54:26.000234: step: 480/466, loss: 1.0922472476959229
2023-01-22 09:54:26.633216: step: 482/466, loss: 1.0459352731704712
2023-01-22 09:54:27.254667: step: 484/466, loss: 0.6630339622497559
2023-01-22 09:54:27.906943: step: 486/466, loss: 2.040816307067871
2023-01-22 09:54:28.594801: step: 488/466, loss: 0.9988837838172913
2023-01-22 09:54:29.274536: step: 490/466, loss: 0.9036743640899658
2023-01-22 09:54:29.973414: step: 492/466, loss: 3.2113442420959473
2023-01-22 09:54:30.592476: step: 494/466, loss: 1.0254572629928589
2023-01-22 09:54:31.274847: step: 496/466, loss: 0.71244215965271
2023-01-22 09:54:31.871531: step: 498/466, loss: 0.4137183427810669
2023-01-22 09:54:32.526442: step: 500/466, loss: 0.9377108812332153
2023-01-22 09:54:33.151097: step: 502/466, loss: 0.9592562317848206
2023-01-22 09:54:33.753663: step: 504/466, loss: 0.9918196797370911
2023-01-22 09:54:34.396777: step: 506/466, loss: 3.5560927391052246
2023-01-22 09:54:34.984975: step: 508/466, loss: 2.3743810653686523
2023-01-22 09:54:35.587681: step: 510/466, loss: 1.9230139255523682
2023-01-22 09:54:36.163575: step: 512/466, loss: 1.1159083843231201
2023-01-22 09:54:36.768846: step: 514/466, loss: 1.7958159446716309
2023-01-22 09:54:37.382815: step: 516/466, loss: 0.5810664296150208
2023-01-22 09:54:38.019173: step: 518/466, loss: 0.9423800706863403
2023-01-22 09:54:38.589842: step: 520/466, loss: 0.35207512974739075
2023-01-22 09:54:39.190397: step: 522/466, loss: 2.6577353477478027
2023-01-22 09:54:39.825440: step: 524/466, loss: 1.07778799533844
2023-01-22 09:54:40.470977: step: 526/466, loss: 2.047811985015869
2023-01-22 09:54:41.039883: step: 528/466, loss: 0.7667275071144104
2023-01-22 09:54:41.663979: step: 530/466, loss: 2.874121904373169
2023-01-22 09:54:42.311694: step: 532/466, loss: 0.4974350035190582
2023-01-22 09:54:42.933233: step: 534/466, loss: 0.31851255893707275
2023-01-22 09:54:43.567214: step: 536/466, loss: 1.2831884622573853
2023-01-22 09:54:44.190142: step: 538/466, loss: 0.3160209655761719
2023-01-22 09:54:44.749496: step: 540/466, loss: 0.5134939551353455
2023-01-22 09:54:45.362693: step: 542/466, loss: 0.2660251259803772
2023-01-22 09:54:45.996387: step: 544/466, loss: 1.1474089622497559
2023-01-22 09:54:46.617171: step: 546/466, loss: 0.7397912740707397
2023-01-22 09:54:47.209409: step: 548/466, loss: 1.9008302688598633
2023-01-22 09:54:47.852351: step: 550/466, loss: 0.5208633542060852
2023-01-22 09:54:48.501908: step: 552/466, loss: 0.4891583323478699
2023-01-22 09:54:49.091095: step: 554/466, loss: 1.0825510025024414
2023-01-22 09:54:49.702735: step: 556/466, loss: 0.7252593040466309
2023-01-22 09:54:50.283281: step: 558/466, loss: 0.3966256380081177
2023-01-22 09:54:51.012735: step: 560/466, loss: 0.15954799950122833
2023-01-22 09:54:51.652209: step: 562/466, loss: 1.3751274347305298
2023-01-22 09:54:52.271131: step: 564/466, loss: 0.7945005297660828
2023-01-22 09:54:52.858485: step: 566/466, loss: 11.734745025634766
2023-01-22 09:54:53.501275: step: 568/466, loss: 0.872058629989624
2023-01-22 09:54:54.132758: step: 570/466, loss: 2.14370059967041
2023-01-22 09:54:54.857865: step: 572/466, loss: 1.0840165615081787
2023-01-22 09:54:55.476538: step: 574/466, loss: 0.42503124475479126
2023-01-22 09:54:56.078628: step: 576/466, loss: 1.4932385683059692
2023-01-22 09:54:56.763541: step: 578/466, loss: 1.268698811531067
2023-01-22 09:54:57.367300: step: 580/466, loss: 0.6315069198608398
2023-01-22 09:54:57.930142: step: 582/466, loss: 1.204034686088562
2023-01-22 09:54:58.634795: step: 584/466, loss: 4.475171089172363
2023-01-22 09:54:59.265738: step: 586/466, loss: 0.7657732367515564
2023-01-22 09:54:59.856602: step: 588/466, loss: 0.6819864511489868
2023-01-22 09:55:00.494163: step: 590/466, loss: 0.8920553922653198
2023-01-22 09:55:01.081691: step: 592/466, loss: 1.0124226808547974
2023-01-22 09:55:01.636876: step: 594/466, loss: 0.6939584016799927
2023-01-22 09:55:02.296167: step: 596/466, loss: 0.49833014607429504
2023-01-22 09:55:02.907979: step: 598/466, loss: 1.2310301065444946
2023-01-22 09:55:03.549777: step: 600/466, loss: 0.3144940435886383
2023-01-22 09:55:04.154445: step: 602/466, loss: 2.4529874324798584
2023-01-22 09:55:04.748178: step: 604/466, loss: 1.0824910402297974
2023-01-22 09:55:05.349192: step: 606/466, loss: 0.5533326864242554
2023-01-22 09:55:05.930427: step: 608/466, loss: 0.390047162771225
2023-01-22 09:55:06.523694: step: 610/466, loss: 1.4454784393310547
2023-01-22 09:55:07.120943: step: 612/466, loss: 2.1368541717529297
2023-01-22 09:55:07.697994: step: 614/466, loss: 1.6841633319854736
2023-01-22 09:55:08.318015: step: 616/466, loss: 0.9814568161964417
2023-01-22 09:55:08.944084: step: 618/466, loss: 0.7741979360580444
2023-01-22 09:55:09.625712: step: 620/466, loss: 0.892448902130127
2023-01-22 09:55:10.291899: step: 622/466, loss: 0.2893030643463135
2023-01-22 09:55:10.885947: step: 624/466, loss: 1.7950413227081299
2023-01-22 09:55:11.516700: step: 626/466, loss: 0.40497180819511414
2023-01-22 09:55:12.202953: step: 628/466, loss: 1.072169303894043
2023-01-22 09:55:12.829388: step: 630/466, loss: 0.420509397983551
2023-01-22 09:55:13.495069: step: 632/466, loss: 0.37140047550201416
2023-01-22 09:55:14.200470: step: 634/466, loss: 0.42654693126678467
2023-01-22 09:55:14.722652: step: 636/466, loss: 0.6957866549491882
2023-01-22 09:55:15.341379: step: 638/466, loss: 0.48537787795066833
2023-01-22 09:55:15.985192: step: 640/466, loss: 2.398995876312256
2023-01-22 09:55:16.629391: step: 642/466, loss: 1.7987191677093506
2023-01-22 09:55:17.228241: step: 644/466, loss: 0.6381231546401978
2023-01-22 09:55:17.874951: step: 646/466, loss: 2.920368194580078
2023-01-22 09:55:18.521161: step: 648/466, loss: 0.937603235244751
2023-01-22 09:55:19.163471: step: 650/466, loss: 0.8973060846328735
2023-01-22 09:55:19.847900: step: 652/466, loss: 0.3030257225036621
2023-01-22 09:55:20.437682: step: 654/466, loss: 0.23769119381904602
2023-01-22 09:55:21.025989: step: 656/466, loss: 7.699764251708984
2023-01-22 09:55:21.680119: step: 658/466, loss: 0.7156766057014465
2023-01-22 09:55:22.313278: step: 660/466, loss: 0.5250595211982727
2023-01-22 09:55:22.930481: step: 662/466, loss: 0.7946426868438721
2023-01-22 09:55:23.560647: step: 664/466, loss: 0.6435459852218628
2023-01-22 09:55:24.206004: step: 666/466, loss: 1.4385056495666504
2023-01-22 09:55:24.829757: step: 668/466, loss: 0.6356618404388428
2023-01-22 09:55:25.484290: step: 670/466, loss: 0.76902174949646
2023-01-22 09:55:26.097710: step: 672/466, loss: 0.5062452554702759
2023-01-22 09:55:26.706566: step: 674/466, loss: 1.047088861465454
2023-01-22 09:55:27.326233: step: 676/466, loss: 0.5389862656593323
2023-01-22 09:55:27.995321: step: 678/466, loss: 0.564977765083313
2023-01-22 09:55:28.667311: step: 680/466, loss: 1.376876950263977
2023-01-22 09:55:29.320524: step: 682/466, loss: 0.615401029586792
2023-01-22 09:55:29.929665: step: 684/466, loss: 1.184968113899231
2023-01-22 09:55:30.536900: step: 686/466, loss: 0.5089195370674133
2023-01-22 09:55:31.193402: step: 688/466, loss: 1.1755729913711548
2023-01-22 09:55:31.833069: step: 690/466, loss: 0.7577053308486938
2023-01-22 09:55:32.479691: step: 692/466, loss: 0.29133859276771545
2023-01-22 09:55:33.097356: step: 694/466, loss: 0.8675771951675415
2023-01-22 09:55:33.700151: step: 696/466, loss: 0.32761046290397644
2023-01-22 09:55:34.295653: step: 698/466, loss: 1.0314862728118896
2023-01-22 09:55:34.877357: step: 700/466, loss: 1.219602346420288
2023-01-22 09:55:35.543480: step: 702/466, loss: 0.7685061097145081
2023-01-22 09:55:36.201810: step: 704/466, loss: 2.6815826892852783
2023-01-22 09:55:36.825282: step: 706/466, loss: 0.17379489541053772
2023-01-22 09:55:37.466775: step: 708/466, loss: 1.164201259613037
2023-01-22 09:55:38.047828: step: 710/466, loss: 0.624973475933075
2023-01-22 09:55:38.656445: step: 712/466, loss: 1.5552754402160645
2023-01-22 09:55:39.323852: step: 714/466, loss: 0.37641841173171997
2023-01-22 09:55:39.863461: step: 716/466, loss: 0.8614609837532043
2023-01-22 09:55:40.527645: step: 718/466, loss: 0.3931480944156647
2023-01-22 09:55:41.114650: step: 720/466, loss: 0.5416122078895569
2023-01-22 09:55:41.693704: step: 722/466, loss: 0.3402988314628601
2023-01-22 09:55:42.340844: step: 724/466, loss: 5.0532941818237305
2023-01-22 09:55:43.033078: step: 726/466, loss: 2.229910373687744
2023-01-22 09:55:43.707126: step: 728/466, loss: 1.0713385343551636
2023-01-22 09:55:44.306174: step: 730/466, loss: 2.3561525344848633
2023-01-22 09:55:44.943557: step: 732/466, loss: 0.47308316826820374
2023-01-22 09:55:45.558659: step: 734/466, loss: 0.5159525275230408
2023-01-22 09:55:46.164825: step: 736/466, loss: 0.6816383600234985
2023-01-22 09:55:46.802810: step: 738/466, loss: 3.2255191802978516
2023-01-22 09:55:47.439512: step: 740/466, loss: 0.5438644886016846
2023-01-22 09:55:48.129122: step: 742/466, loss: 1.8124189376831055
2023-01-22 09:55:48.780621: step: 744/466, loss: 0.43985387682914734
2023-01-22 09:55:49.569094: step: 746/466, loss: 2.1252360343933105
2023-01-22 09:55:50.186194: step: 748/466, loss: 1.001505732536316
2023-01-22 09:55:50.811374: step: 750/466, loss: 0.34168243408203125
2023-01-22 09:55:51.421265: step: 752/466, loss: 0.82155442237854
2023-01-22 09:55:52.038386: step: 754/466, loss: 0.3661108911037445
2023-01-22 09:55:52.780935: step: 756/466, loss: 0.38035377860069275
2023-01-22 09:55:53.333141: step: 758/466, loss: 0.4773160517215729
2023-01-22 09:55:53.949601: step: 760/466, loss: 0.8049483895301819
2023-01-22 09:55:54.546052: step: 762/466, loss: 1.2205617427825928
2023-01-22 09:55:55.179316: step: 764/466, loss: 0.9722318053245544
2023-01-22 09:55:55.778557: step: 766/466, loss: 3.272855043411255
2023-01-22 09:55:56.369896: step: 768/466, loss: 1.0239043235778809
2023-01-22 09:55:57.032978: step: 770/466, loss: 0.6385643482208252
2023-01-22 09:55:57.658586: step: 772/466, loss: 2.9943175315856934
2023-01-22 09:55:58.358938: step: 774/466, loss: 2.038254976272583
2023-01-22 09:55:58.938067: step: 776/466, loss: 0.8814162015914917
2023-01-22 09:55:59.539983: step: 778/466, loss: 3.2607007026672363
2023-01-22 09:56:00.131530: step: 780/466, loss: 3.3752236366271973
2023-01-22 09:56:00.858462: step: 782/466, loss: 7.300093650817871
2023-01-22 09:56:01.447819: step: 784/466, loss: 0.7274892330169678
2023-01-22 09:56:02.065779: step: 786/466, loss: 0.9277554750442505
2023-01-22 09:56:02.723730: step: 788/466, loss: 1.0070232152938843
2023-01-22 09:56:03.390551: step: 790/466, loss: 0.9627074003219604
2023-01-22 09:56:04.069701: step: 792/466, loss: 3.5604138374328613
2023-01-22 09:56:04.686239: step: 794/466, loss: 0.5762374401092529
2023-01-22 09:56:05.300403: step: 796/466, loss: 1.2100515365600586
2023-01-22 09:56:06.053704: step: 798/466, loss: 0.7598632574081421
2023-01-22 09:56:06.684889: step: 800/466, loss: 0.3530119061470032
2023-01-22 09:56:07.319303: step: 802/466, loss: 0.5504021048545837
2023-01-22 09:56:07.959425: step: 804/466, loss: 1.1767265796661377
2023-01-22 09:56:08.566368: step: 806/466, loss: 1.640741229057312
2023-01-22 09:56:09.116881: step: 808/466, loss: 0.6865524649620056
2023-01-22 09:56:09.659003: step: 810/466, loss: 3.889336109161377
2023-01-22 09:56:10.303162: step: 812/466, loss: 0.7453906536102295
2023-01-22 09:56:10.946212: step: 814/466, loss: 0.771681010723114
2023-01-22 09:56:11.568732: step: 816/466, loss: 1.5986517667770386
2023-01-22 09:56:12.219359: step: 818/466, loss: 1.1174575090408325
2023-01-22 09:56:12.886767: step: 820/466, loss: 0.34714770317077637
2023-01-22 09:56:13.465413: step: 822/466, loss: 2.073472499847412
2023-01-22 09:56:14.205057: step: 824/466, loss: 0.419218510389328
2023-01-22 09:56:14.840887: step: 826/466, loss: 0.43204182386398315
2023-01-22 09:56:15.421885: step: 828/466, loss: 0.655705451965332
2023-01-22 09:56:16.033138: step: 830/466, loss: 0.9431020617485046
2023-01-22 09:56:16.621852: step: 832/466, loss: 2.661907196044922
2023-01-22 09:56:17.243322: step: 834/466, loss: 0.28297674655914307
2023-01-22 09:56:17.883383: step: 836/466, loss: 0.3602883815765381
2023-01-22 09:56:18.486946: step: 838/466, loss: 0.5022509694099426
2023-01-22 09:56:19.124037: step: 840/466, loss: 0.3109540641307831
2023-01-22 09:56:19.704022: step: 842/466, loss: 9.10473918914795
2023-01-22 09:56:20.289035: step: 844/466, loss: 0.667523980140686
2023-01-22 09:56:20.923791: step: 846/466, loss: 2.73602032661438
2023-01-22 09:56:21.545226: step: 848/466, loss: 0.6200502514839172
2023-01-22 09:56:22.096151: step: 850/466, loss: 1.79677152633667
2023-01-22 09:56:22.621802: step: 852/466, loss: 0.5190490484237671
2023-01-22 09:56:23.311597: step: 854/466, loss: 0.5402984619140625
2023-01-22 09:56:23.901349: step: 856/466, loss: 1.1196444034576416
2023-01-22 09:56:24.532980: step: 858/466, loss: 0.24323970079421997
2023-01-22 09:56:25.187503: step: 860/466, loss: 1.542398452758789
2023-01-22 09:56:25.833619: step: 862/466, loss: 1.082638144493103
2023-01-22 09:56:26.459645: step: 864/466, loss: 1.3859745264053345
2023-01-22 09:56:27.034847: step: 866/466, loss: 0.6537830829620361
2023-01-22 09:56:27.624398: step: 868/466, loss: 8.41200065612793
2023-01-22 09:56:28.291912: step: 870/466, loss: 1.0243313312530518
2023-01-22 09:56:28.931454: step: 872/466, loss: 1.7913784980773926
2023-01-22 09:56:29.545063: step: 874/466, loss: 0.897002100944519
2023-01-22 09:56:30.069536: step: 876/466, loss: 0.3358590602874756
2023-01-22 09:56:30.668678: step: 878/466, loss: 0.19971369206905365
2023-01-22 09:56:31.314760: step: 880/466, loss: 1.4521043300628662
2023-01-22 09:56:31.948089: step: 882/466, loss: 0.7002207040786743
2023-01-22 09:56:32.592949: step: 884/466, loss: 0.8930506110191345
2023-01-22 09:56:33.261100: step: 886/466, loss: 1.1874725818634033
2023-01-22 09:56:33.859470: step: 888/466, loss: 1.0502787828445435
2023-01-22 09:56:34.509287: step: 890/466, loss: 0.3964206576347351
2023-01-22 09:56:35.136319: step: 892/466, loss: 1.472832441329956
2023-01-22 09:56:35.763826: step: 894/466, loss: 0.9696194529533386
2023-01-22 09:56:36.392723: step: 896/466, loss: 0.9544723629951477
2023-01-22 09:56:37.042220: step: 898/466, loss: 0.18317130208015442
2023-01-22 09:56:37.667153: step: 900/466, loss: 2.1016006469726562
2023-01-22 09:56:38.331923: step: 902/466, loss: 1.6702429056167603
2023-01-22 09:56:38.949423: step: 904/466, loss: 0.48005521297454834
2023-01-22 09:56:39.645337: step: 906/466, loss: 1.803809642791748
2023-01-22 09:56:40.254920: step: 908/466, loss: 1.603433609008789
2023-01-22 09:56:40.852731: step: 910/466, loss: 3.0145821571350098
2023-01-22 09:56:41.569087: step: 912/466, loss: 1.1885614395141602
2023-01-22 09:56:42.201313: step: 914/466, loss: 0.4076838791370392
2023-01-22 09:56:42.905238: step: 916/466, loss: 0.33982279896736145
2023-01-22 09:56:43.569535: step: 918/466, loss: 0.5260677337646484
2023-01-22 09:56:44.253086: step: 920/466, loss: 1.7159318923950195
2023-01-22 09:56:44.953086: step: 922/466, loss: 3.7175893783569336
2023-01-22 09:56:45.509787: step: 924/466, loss: 0.6074461936950684
2023-01-22 09:56:46.130815: step: 926/466, loss: 1.825785756111145
2023-01-22 09:56:46.751482: step: 928/466, loss: 0.3798740804195404
2023-01-22 09:56:47.462953: step: 930/466, loss: 0.7044768333435059
2023-01-22 09:56:48.082041: step: 932/466, loss: 1.870772361755371
==================================================
Loss: 1.351
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2945562611952451, 'r': 0.24825290953008347, 'f1': 0.26942967365238246}, 'combined': 0.19852712795438707, 'epoch': 3}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.30204819227052765, 'r': 0.24975490740493586, 'f1': 0.273423684414683}, 'combined': 0.17120922295125013, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2813930976430976, 'r': 0.263806029040404, 'f1': 0.27231590094493313}, 'combined': 0.2006538217488981, 'epoch': 3}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.31168620497308175, 'r': 0.25631904322403115, 'f1': 0.2813041256164775}, 'combined': 0.17432931728345083, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26979583333333335, 'r': 0.25548847853535356, 'f1': 0.2624473086900129}, 'combined': 0.193382227455799, 'epoch': 3}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.34059245483151923, 'r': 0.2532137220653481, 'f1': 0.2904741868666739}, 'combined': 0.19269079722838767, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29545454545454547, 'r': 0.2785714285714286, 'f1': 0.2867647058823529}, 'combined': 0.19117647058823528, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.19736842105263158, 'r': 0.16304347826086957, 'f1': 0.17857142857142858}, 'combined': 0.08928571428571429, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2727272727272727, 'r': 0.10344827586206896, 'f1': 0.15}, 'combined': 0.09999999999999999, 'epoch': 3}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2945562611952451, 'r': 0.24825290953008347, 'f1': 0.26942967365238246}, 'combined': 0.19852712795438707, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.30204819227052765, 'r': 0.24975490740493586, 'f1': 0.273423684414683}, 'combined': 0.17120922295125013, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29545454545454547, 'r': 0.2785714285714286, 'f1': 0.2867647058823529}, 'combined': 0.19117647058823528, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.23587630849753696, 'r': 0.20767857142857143, 'f1': 0.22088114458699726}, 'combined': 0.16275452759041903, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.283777480995869, 'r': 0.22441194845209841, 'f1': 0.2506272415240455}, 'combined': 0.15531829052194365, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36, 'r': 0.391304347826087, 'f1': 0.37499999999999994}, 'combined': 0.18749999999999997, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30841750503018106, 'r': 0.2073640422077922, 'f1': 0.24799142533570623}, 'combined': 0.182730523931573, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3463263399393878, 'r': 0.1569095872288562, 'f1': 0.2159699660243139}, 'combined': 0.14326720518444586, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.375, 'r': 0.12931034482758622, 'f1': 0.19230769230769235}, 'combined': 0.12820512820512822, '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 09:59:33.660975: step: 2/466, loss: 0.8234193325042725
2023-01-22 09:59:34.282415: step: 4/466, loss: 0.5527621507644653
2023-01-22 09:59:34.900707: step: 6/466, loss: 0.5562136173248291
2023-01-22 09:59:35.499353: step: 8/466, loss: 0.6088646054267883
2023-01-22 09:59:36.079745: step: 10/466, loss: 3.758753776550293
2023-01-22 09:59:36.608935: step: 12/466, loss: 0.39627838134765625
2023-01-22 09:59:37.234415: step: 14/466, loss: 0.7602285146713257
2023-01-22 09:59:37.875513: step: 16/466, loss: 0.8169283866882324
2023-01-22 09:59:38.481938: step: 18/466, loss: 1.195311188697815
2023-01-22 09:59:39.066203: step: 20/466, loss: 0.9847410917282104
2023-01-22 09:59:39.713385: step: 22/466, loss: 0.3099139928817749
2023-01-22 09:59:40.341314: step: 24/466, loss: 0.53386390209198
2023-01-22 09:59:40.943905: step: 26/466, loss: 2.3639395236968994
2023-01-22 09:59:41.563987: step: 28/466, loss: 1.3981447219848633
2023-01-22 09:59:42.267349: step: 30/466, loss: 0.45659926533699036
2023-01-22 09:59:42.892487: step: 32/466, loss: 0.33734163641929626
2023-01-22 09:59:43.517074: step: 34/466, loss: 1.5848418474197388
2023-01-22 09:59:44.189268: step: 36/466, loss: 0.6364235281944275
2023-01-22 09:59:44.810866: step: 38/466, loss: 0.6908300518989563
2023-01-22 09:59:45.483749: step: 40/466, loss: 0.4133012294769287
2023-01-22 09:59:46.163263: step: 42/466, loss: 0.43771636486053467
2023-01-22 09:59:46.764630: step: 44/466, loss: 1.4768908023834229
2023-01-22 09:59:47.417151: step: 46/466, loss: 1.4073878526687622
2023-01-22 09:59:48.012388: step: 48/466, loss: 1.0671855211257935
2023-01-22 09:59:48.632430: step: 50/466, loss: 0.3492785692214966
2023-01-22 09:59:49.248106: step: 52/466, loss: 0.7020103335380554
2023-01-22 09:59:49.786327: step: 54/466, loss: 0.5150268077850342
2023-01-22 09:59:50.379624: step: 56/466, loss: 0.7967656254768372
2023-01-22 09:59:50.985854: step: 58/466, loss: 0.5937609672546387
2023-01-22 09:59:51.625121: step: 60/466, loss: 1.9360209703445435
2023-01-22 09:59:52.289014: step: 62/466, loss: 0.5878614187240601
2023-01-22 09:59:52.960077: step: 64/466, loss: 0.24815517663955688
2023-01-22 09:59:53.612218: step: 66/466, loss: 0.32944440841674805
2023-01-22 09:59:54.192804: step: 68/466, loss: 0.6284695863723755
2023-01-22 09:59:54.834726: step: 70/466, loss: 1.988524317741394
2023-01-22 09:59:55.424207: step: 72/466, loss: 1.0196870565414429
2023-01-22 09:59:56.061201: step: 74/466, loss: 0.7447625398635864
2023-01-22 09:59:56.643512: step: 76/466, loss: 0.29737746715545654
2023-01-22 09:59:57.272390: step: 78/466, loss: 2.552250385284424
2023-01-22 09:59:57.923541: step: 80/466, loss: 1.034410834312439
2023-01-22 09:59:58.590361: step: 82/466, loss: 1.1705375909805298
2023-01-22 09:59:59.245942: step: 84/466, loss: 2.288651704788208
2023-01-22 09:59:59.864473: step: 86/466, loss: 4.031686305999756
2023-01-22 10:00:00.490780: step: 88/466, loss: 9.568753242492676
2023-01-22 10:00:01.063870: step: 90/466, loss: 1.692314863204956
2023-01-22 10:00:01.640426: step: 92/466, loss: 1.6322171688079834
2023-01-22 10:00:02.276080: step: 94/466, loss: 0.867580771446228
2023-01-22 10:00:02.912724: step: 96/466, loss: 0.3122093379497528
2023-01-22 10:00:03.497534: step: 98/466, loss: 1.1003360748291016
2023-01-22 10:00:04.155436: step: 100/466, loss: 0.5618632435798645
2023-01-22 10:00:04.756382: step: 102/466, loss: 0.3283842206001282
2023-01-22 10:00:05.316536: step: 104/466, loss: 0.6832338571548462
2023-01-22 10:00:06.006175: step: 106/466, loss: 0.2865106165409088
2023-01-22 10:00:06.625654: step: 108/466, loss: 3.1510965824127197
2023-01-22 10:00:07.262765: step: 110/466, loss: 0.6936209201812744
2023-01-22 10:00:07.836137: step: 112/466, loss: 1.8776599168777466
2023-01-22 10:00:08.489833: step: 114/466, loss: 2.3227715492248535
2023-01-22 10:00:09.143166: step: 116/466, loss: 0.4241205155849457
2023-01-22 10:00:09.759468: step: 118/466, loss: 0.759576678276062
2023-01-22 10:00:10.397582: step: 120/466, loss: 0.23246560990810394
2023-01-22 10:00:10.989682: step: 122/466, loss: 0.2546248137950897
2023-01-22 10:00:11.603773: step: 124/466, loss: 0.7287163734436035
2023-01-22 10:00:12.306722: step: 126/466, loss: 8.166577339172363
2023-01-22 10:00:12.923900: step: 128/466, loss: 1.5923850536346436
2023-01-22 10:00:13.627015: step: 130/466, loss: 0.37262099981307983
2023-01-22 10:00:14.288453: step: 132/466, loss: 1.4601284265518188
2023-01-22 10:00:14.870018: step: 134/466, loss: 0.18822559714317322
2023-01-22 10:00:15.426308: step: 136/466, loss: 1.4293346405029297
2023-01-22 10:00:15.996014: step: 138/466, loss: 0.3131538927555084
2023-01-22 10:00:16.607289: step: 140/466, loss: 0.611158013343811
2023-01-22 10:00:17.204051: step: 142/466, loss: 0.7587867379188538
2023-01-22 10:00:17.881634: step: 144/466, loss: 1.0173994302749634
2023-01-22 10:00:18.527177: step: 146/466, loss: 1.2000371217727661
2023-01-22 10:00:19.158772: step: 148/466, loss: 0.832184374332428
2023-01-22 10:00:19.781503: step: 150/466, loss: 0.9794172048568726
2023-01-22 10:00:20.400966: step: 152/466, loss: 0.5464068651199341
2023-01-22 10:00:21.026130: step: 154/466, loss: 1.0173841714859009
2023-01-22 10:00:21.630180: step: 156/466, loss: 3.6597390174865723
2023-01-22 10:00:22.217391: step: 158/466, loss: 5.955989837646484
2023-01-22 10:00:22.837582: step: 160/466, loss: 0.3543793559074402
2023-01-22 10:00:23.467079: step: 162/466, loss: 2.2218308448791504
2023-01-22 10:00:24.107105: step: 164/466, loss: 1.0682404041290283
2023-01-22 10:00:24.737250: step: 166/466, loss: 1.0099315643310547
2023-01-22 10:00:25.465618: step: 168/466, loss: 1.0879361629486084
2023-01-22 10:00:26.050160: step: 170/466, loss: 0.2668413519859314
2023-01-22 10:00:26.692074: step: 172/466, loss: 0.5412415862083435
2023-01-22 10:00:27.384761: step: 174/466, loss: 1.0546385049819946
2023-01-22 10:00:28.007582: step: 176/466, loss: 0.1540793776512146
2023-01-22 10:00:28.623718: step: 178/466, loss: 0.30003786087036133
2023-01-22 10:00:29.218363: step: 180/466, loss: 0.7003176808357239
2023-01-22 10:00:29.831237: step: 182/466, loss: 0.372450053691864
2023-01-22 10:00:30.520817: step: 184/466, loss: 6.132852554321289
2023-01-22 10:00:31.126320: step: 186/466, loss: 0.26928791403770447
2023-01-22 10:00:31.753340: step: 188/466, loss: 0.7455117106437683
2023-01-22 10:00:32.399417: step: 190/466, loss: 2.13204288482666
2023-01-22 10:00:33.128027: step: 192/466, loss: 1.1307880878448486
2023-01-22 10:00:33.774886: step: 194/466, loss: 1.6704050302505493
2023-01-22 10:00:34.475910: step: 196/466, loss: 0.37431788444519043
2023-01-22 10:00:35.068438: step: 198/466, loss: 1.84345281124115
2023-01-22 10:00:35.732131: step: 200/466, loss: 0.3616538941860199
2023-01-22 10:00:36.290235: step: 202/466, loss: 0.933368444442749
2023-01-22 10:00:36.945047: step: 204/466, loss: 5.045001029968262
2023-01-22 10:00:37.550875: step: 206/466, loss: 0.23763899505138397
2023-01-22 10:00:38.182906: step: 208/466, loss: 2.020751476287842
2023-01-22 10:00:38.786032: step: 210/466, loss: 0.3125147819519043
2023-01-22 10:00:39.397784: step: 212/466, loss: 1.8077600002288818
2023-01-22 10:00:40.057770: step: 214/466, loss: 2.1511735916137695
2023-01-22 10:00:40.703949: step: 216/466, loss: 15.920232772827148
2023-01-22 10:00:41.338312: step: 218/466, loss: 4.202001094818115
2023-01-22 10:00:41.995139: step: 220/466, loss: 1.3560482263565063
2023-01-22 10:00:42.653324: step: 222/466, loss: 1.4759902954101562
2023-01-22 10:00:43.306431: step: 224/466, loss: 0.2740112245082855
2023-01-22 10:00:43.904653: step: 226/466, loss: 1.1533056497573853
2023-01-22 10:00:44.596696: step: 228/466, loss: 1.33697509765625
2023-01-22 10:00:45.388899: step: 230/466, loss: 2.2029709815979004
2023-01-22 10:00:45.973455: step: 232/466, loss: 0.7078940868377686
2023-01-22 10:00:46.662468: step: 234/466, loss: 0.8712655305862427
2023-01-22 10:00:47.242811: step: 236/466, loss: 0.7303901314735413
2023-01-22 10:00:47.915880: step: 238/466, loss: 2.421600341796875
2023-01-22 10:00:48.543003: step: 240/466, loss: 0.9266837239265442
2023-01-22 10:00:49.218011: step: 242/466, loss: 1.455971121788025
2023-01-22 10:00:49.816903: step: 244/466, loss: 0.9863547086715698
2023-01-22 10:00:50.454225: step: 246/466, loss: 0.3293907642364502
2023-01-22 10:00:51.137856: step: 248/466, loss: 0.6340574026107788
2023-01-22 10:00:51.681820: step: 250/466, loss: 0.7300431728363037
2023-01-22 10:00:52.259535: step: 252/466, loss: 7.62088680267334
2023-01-22 10:00:52.896292: step: 254/466, loss: 1.5418038368225098
2023-01-22 10:00:53.534736: step: 256/466, loss: 1.0736063718795776
2023-01-22 10:00:54.178326: step: 258/466, loss: 0.27653467655181885
2023-01-22 10:00:54.770638: step: 260/466, loss: 1.1074532270431519
2023-01-22 10:00:55.414332: step: 262/466, loss: 1.368119239807129
2023-01-22 10:00:56.042293: step: 264/466, loss: 1.368348479270935
2023-01-22 10:00:56.713970: step: 266/466, loss: 0.3171231150627136
2023-01-22 10:00:57.490830: step: 268/466, loss: 0.7048443555831909
2023-01-22 10:00:58.123081: step: 270/466, loss: 1.8752702474594116
2023-01-22 10:00:58.767582: step: 272/466, loss: 0.34659889340400696
2023-01-22 10:00:59.373751: step: 274/466, loss: 0.3979450464248657
2023-01-22 10:00:59.987209: step: 276/466, loss: 0.4131494164466858
2023-01-22 10:01:00.571482: step: 278/466, loss: 1.8385015726089478
2023-01-22 10:01:01.200347: step: 280/466, loss: 0.54398512840271
2023-01-22 10:01:01.857901: step: 282/466, loss: 0.26953792572021484
2023-01-22 10:01:02.480401: step: 284/466, loss: 0.14041590690612793
2023-01-22 10:01:03.056579: step: 286/466, loss: 0.2797807455062866
2023-01-22 10:01:03.671182: step: 288/466, loss: 1.2565838098526
2023-01-22 10:01:04.261331: step: 290/466, loss: 0.25621214509010315
2023-01-22 10:01:04.860351: step: 292/466, loss: 0.23986800014972687
2023-01-22 10:01:05.496669: step: 294/466, loss: 1.2190638780593872
2023-01-22 10:01:06.181391: step: 296/466, loss: 0.9308200478553772
2023-01-22 10:01:06.864764: step: 298/466, loss: 0.9362515211105347
2023-01-22 10:01:07.513482: step: 300/466, loss: 0.7603223323822021
2023-01-22 10:01:08.141056: step: 302/466, loss: 0.5132754445075989
2023-01-22 10:01:08.754958: step: 304/466, loss: 0.25197291374206543
2023-01-22 10:01:09.378160: step: 306/466, loss: 1.2909669876098633
2023-01-22 10:01:10.035638: step: 308/466, loss: 1.3695316314697266
2023-01-22 10:01:10.621245: step: 310/466, loss: 0.8792002201080322
2023-01-22 10:01:11.225517: step: 312/466, loss: 0.6641198992729187
2023-01-22 10:01:11.883722: step: 314/466, loss: 1.4005305767059326
2023-01-22 10:01:12.488229: step: 316/466, loss: 0.47896987199783325
2023-01-22 10:01:13.147151: step: 318/466, loss: 0.6251979470252991
2023-01-22 10:01:13.750810: step: 320/466, loss: 0.3861716687679291
2023-01-22 10:01:14.346598: step: 322/466, loss: 0.2425888180732727
2023-01-22 10:01:14.959428: step: 324/466, loss: 0.9359714984893799
2023-01-22 10:01:15.674302: step: 326/466, loss: 0.6627274751663208
2023-01-22 10:01:16.311523: step: 328/466, loss: 1.0809791088104248
2023-01-22 10:01:16.923717: step: 330/466, loss: 0.7750211358070374
2023-01-22 10:01:17.557065: step: 332/466, loss: 0.6194950938224792
2023-01-22 10:01:18.263496: step: 334/466, loss: 0.20308737456798553
2023-01-22 10:01:18.876012: step: 336/466, loss: 2.0507476329803467
2023-01-22 10:01:19.508831: step: 338/466, loss: 1.2626909017562866
2023-01-22 10:01:20.078975: step: 340/466, loss: 0.49783921241760254
2023-01-22 10:01:20.746112: step: 342/466, loss: 2.4868323802948
2023-01-22 10:01:21.381044: step: 344/466, loss: 0.5746316909790039
2023-01-22 10:01:21.984291: step: 346/466, loss: 0.9443038105964661
2023-01-22 10:01:22.588155: step: 348/466, loss: 0.4447798430919647
2023-01-22 10:01:23.269685: step: 350/466, loss: 0.6863400936126709
2023-01-22 10:01:23.916780: step: 352/466, loss: 0.35676565766334534
2023-01-22 10:01:24.529250: step: 354/466, loss: 0.5012394189834595
2023-01-22 10:01:25.111420: step: 356/466, loss: 1.7943192720413208
2023-01-22 10:01:25.748778: step: 358/466, loss: 0.8492233157157898
2023-01-22 10:01:26.382462: step: 360/466, loss: 0.7463604211807251
2023-01-22 10:01:26.979561: step: 362/466, loss: 0.9617664813995361
2023-01-22 10:01:27.562257: step: 364/466, loss: 0.5592828989028931
2023-01-22 10:01:28.231148: step: 366/466, loss: 1.3846055269241333
2023-01-22 10:01:28.850580: step: 368/466, loss: 0.6915057301521301
2023-01-22 10:01:29.461067: step: 370/466, loss: 0.8128398656845093
2023-01-22 10:01:30.147762: step: 372/466, loss: 1.2673065662384033
2023-01-22 10:01:30.802970: step: 374/466, loss: 0.8283820748329163
2023-01-22 10:01:31.446223: step: 376/466, loss: 1.3461519479751587
2023-01-22 10:01:32.037214: step: 378/466, loss: 0.9876441359519958
2023-01-22 10:01:32.635397: step: 380/466, loss: 1.5725579261779785
2023-01-22 10:01:33.249865: step: 382/466, loss: 0.7976436614990234
2023-01-22 10:01:33.829742: step: 384/466, loss: 1.8078581094741821
2023-01-22 10:01:34.506113: step: 386/466, loss: 1.8934369087219238
2023-01-22 10:01:35.218106: step: 388/466, loss: 0.28402432799339294
2023-01-22 10:01:35.915894: step: 390/466, loss: 1.4807446002960205
2023-01-22 10:01:36.572872: step: 392/466, loss: 0.7380787134170532
2023-01-22 10:01:37.231468: step: 394/466, loss: 0.47656989097595215
2023-01-22 10:01:37.836588: step: 396/466, loss: 0.4588451385498047
2023-01-22 10:01:38.437080: step: 398/466, loss: 0.6063854694366455
2023-01-22 10:01:39.087374: step: 400/466, loss: 0.9722875952720642
2023-01-22 10:01:39.717025: step: 402/466, loss: 0.24728664755821228
2023-01-22 10:01:40.358617: step: 404/466, loss: 0.202083557844162
2023-01-22 10:01:40.948317: step: 406/466, loss: 1.6964472532272339
2023-01-22 10:01:41.562425: step: 408/466, loss: 1.0508222579956055
2023-01-22 10:01:42.173580: step: 410/466, loss: 0.32941722869873047
2023-01-22 10:01:42.805356: step: 412/466, loss: 1.6181867122650146
2023-01-22 10:01:43.435674: step: 414/466, loss: 0.5365049242973328
2023-01-22 10:01:44.043369: step: 416/466, loss: 0.25431028008461
2023-01-22 10:01:44.610815: step: 418/466, loss: 0.9074522852897644
2023-01-22 10:01:45.170128: step: 420/466, loss: 4.191633224487305
2023-01-22 10:01:45.793499: step: 422/466, loss: 1.4547134637832642
2023-01-22 10:01:46.494899: step: 424/466, loss: 2.038376569747925
2023-01-22 10:01:47.227301: step: 426/466, loss: 2.3599841594696045
2023-01-22 10:01:47.844808: step: 428/466, loss: 0.7275699973106384
2023-01-22 10:01:48.469089: step: 430/466, loss: 0.6593179702758789
2023-01-22 10:01:49.091368: step: 432/466, loss: 0.6755656003952026
2023-01-22 10:01:49.772320: step: 434/466, loss: 3.1001334190368652
2023-01-22 10:01:50.449687: step: 436/466, loss: 0.731447696685791
2023-01-22 10:01:51.018059: step: 438/466, loss: 0.3785054385662079
2023-01-22 10:01:51.608982: step: 440/466, loss: 0.9702725410461426
2023-01-22 10:01:52.189578: step: 442/466, loss: 0.6594955921173096
2023-01-22 10:01:52.784502: step: 444/466, loss: 0.7122897505760193
2023-01-22 10:01:53.420344: step: 446/466, loss: 0.36549654603004456
2023-01-22 10:01:54.042348: step: 448/466, loss: 0.6760743856430054
2023-01-22 10:01:54.651282: step: 450/466, loss: 1.709719181060791
2023-01-22 10:01:55.187884: step: 452/466, loss: 1.601709246635437
2023-01-22 10:01:55.818929: step: 454/466, loss: 1.7167366743087769
2023-01-22 10:01:56.488564: step: 456/466, loss: 0.5454731583595276
2023-01-22 10:01:57.144328: step: 458/466, loss: 0.9240479469299316
2023-01-22 10:01:57.835074: step: 460/466, loss: 2.346407890319824
2023-01-22 10:01:58.497891: step: 462/466, loss: 3.4541802406311035
2023-01-22 10:01:59.077872: step: 464/466, loss: 0.7184671759605408
2023-01-22 10:01:59.723135: step: 466/466, loss: 1.4777228832244873
2023-01-22 10:02:00.341800: step: 468/466, loss: 0.3892070949077606
2023-01-22 10:02:00.955145: step: 470/466, loss: 0.7117869853973389
2023-01-22 10:02:01.584787: step: 472/466, loss: 0.46897411346435547
2023-01-22 10:02:02.232482: step: 474/466, loss: 0.5022502541542053
2023-01-22 10:02:02.884640: step: 476/466, loss: 9.41117000579834
2023-01-22 10:02:03.449529: step: 478/466, loss: 0.522497296333313
2023-01-22 10:02:04.055625: step: 480/466, loss: 0.438643217086792
2023-01-22 10:02:04.725323: step: 482/466, loss: 0.21643486618995667
2023-01-22 10:02:05.358187: step: 484/466, loss: 0.9862494468688965
2023-01-22 10:02:05.963297: step: 486/466, loss: 1.7793397903442383
2023-01-22 10:02:06.650358: step: 488/466, loss: 0.77402263879776
2023-01-22 10:02:07.262445: step: 490/466, loss: 1.1911898851394653
2023-01-22 10:02:07.907846: step: 492/466, loss: 3.382206678390503
2023-01-22 10:02:08.534468: step: 494/466, loss: 1.221908688545227
2023-01-22 10:02:09.109164: step: 496/466, loss: 1.3005276918411255
2023-01-22 10:02:09.769016: step: 498/466, loss: 0.49820587038993835
2023-01-22 10:02:10.326586: step: 500/466, loss: 0.5385996103286743
2023-01-22 10:02:11.003891: step: 502/466, loss: 0.3212437033653259
2023-01-22 10:02:11.636491: step: 504/466, loss: 1.192125678062439
2023-01-22 10:02:12.284480: step: 506/466, loss: 4.746476173400879
2023-01-22 10:02:12.960547: step: 508/466, loss: 0.5380405783653259
2023-01-22 10:02:13.546588: step: 510/466, loss: 2.430771589279175
2023-01-22 10:02:14.106331: step: 512/466, loss: 0.5627239942550659
2023-01-22 10:02:14.737245: step: 514/466, loss: 1.427639365196228
2023-01-22 10:02:15.359488: step: 516/466, loss: 1.5477802753448486
2023-01-22 10:02:15.915708: step: 518/466, loss: 1.1179890632629395
2023-01-22 10:02:16.606032: step: 520/466, loss: 0.30601030588150024
2023-01-22 10:02:17.191846: step: 522/466, loss: 0.421135812997818
2023-01-22 10:02:17.788359: step: 524/466, loss: 2.8707714080810547
2023-01-22 10:02:18.415934: step: 526/466, loss: 2.263228416442871
2023-01-22 10:02:19.059947: step: 528/466, loss: 0.7130519151687622
2023-01-22 10:02:19.700944: step: 530/466, loss: 1.3197085857391357
2023-01-22 10:02:20.246016: step: 532/466, loss: 0.6716258525848389
2023-01-22 10:02:20.883989: step: 534/466, loss: 0.5461893677711487
2023-01-22 10:02:21.529646: step: 536/466, loss: 0.38266992568969727
2023-01-22 10:02:22.108062: step: 538/466, loss: 0.4114155173301697
2023-01-22 10:02:22.723109: step: 540/466, loss: 1.5288643836975098
2023-01-22 10:02:23.300910: step: 542/466, loss: 2.4292304515838623
2023-01-22 10:02:23.950920: step: 544/466, loss: 0.3957027196884155
2023-01-22 10:02:24.523355: step: 546/466, loss: 0.5813397169113159
2023-01-22 10:02:25.118338: step: 548/466, loss: 1.0507454872131348
2023-01-22 10:02:25.819202: step: 550/466, loss: 1.3837651014328003
2023-01-22 10:02:26.481747: step: 552/466, loss: 1.1009317636489868
2023-01-22 10:02:27.176232: step: 554/466, loss: 0.4339676797389984
2023-01-22 10:02:27.831941: step: 556/466, loss: 1.4487650394439697
2023-01-22 10:02:28.428161: step: 558/466, loss: 0.7837366461753845
2023-01-22 10:02:29.109264: step: 560/466, loss: 0.9487995505332947
2023-01-22 10:02:29.800362: step: 562/466, loss: 2.581289768218994
2023-01-22 10:02:30.452127: step: 564/466, loss: 2.4496123790740967
2023-01-22 10:02:31.041936: step: 566/466, loss: 1.0049906969070435
2023-01-22 10:02:31.583145: step: 568/466, loss: 1.7165555953979492
2023-01-22 10:02:32.188361: step: 570/466, loss: 1.0403224229812622
2023-01-22 10:02:32.826401: step: 572/466, loss: 0.5541769862174988
2023-01-22 10:02:33.425664: step: 574/466, loss: 0.27094000577926636
2023-01-22 10:02:34.042794: step: 576/466, loss: 0.6843553185462952
2023-01-22 10:02:34.661086: step: 578/466, loss: 0.1781836748123169
2023-01-22 10:02:35.270295: step: 580/466, loss: 2.5594866275787354
2023-01-22 10:02:35.990034: step: 582/466, loss: 1.2028337717056274
2023-01-22 10:02:36.616946: step: 584/466, loss: 0.4208811819553375
2023-01-22 10:02:37.214594: step: 586/466, loss: 0.6839389204978943
2023-01-22 10:02:37.876894: step: 588/466, loss: 0.609345555305481
2023-01-22 10:02:38.452280: step: 590/466, loss: 0.9183725714683533
2023-01-22 10:02:39.069533: step: 592/466, loss: 0.50873863697052
2023-01-22 10:02:39.721366: step: 594/466, loss: 1.2759383916854858
2023-01-22 10:02:40.372495: step: 596/466, loss: 0.9638827443122864
2023-01-22 10:02:41.023955: step: 598/466, loss: 0.3420892059803009
2023-01-22 10:02:41.620761: step: 600/466, loss: 0.9437588453292847
2023-01-22 10:02:42.357779: step: 602/466, loss: 0.6606385707855225
2023-01-22 10:02:42.965111: step: 604/466, loss: 0.629491925239563
2023-01-22 10:02:43.582487: step: 606/466, loss: 1.1778596639633179
2023-01-22 10:02:44.206448: step: 608/466, loss: 0.7342720627784729
2023-01-22 10:02:44.771440: step: 610/466, loss: 0.17956723272800446
2023-01-22 10:02:45.436414: step: 612/466, loss: 0.9784295558929443
2023-01-22 10:02:46.084321: step: 614/466, loss: 3.4845693111419678
2023-01-22 10:02:46.721567: step: 616/466, loss: 0.5351054668426514
2023-01-22 10:02:47.319115: step: 618/466, loss: 1.9158273935317993
2023-01-22 10:02:47.961199: step: 620/466, loss: 0.2676509916782379
2023-01-22 10:02:48.625512: step: 622/466, loss: 0.2582094967365265
2023-01-22 10:02:49.247803: step: 624/466, loss: 0.6532222628593445
2023-01-22 10:02:49.824123: step: 626/466, loss: 0.21216334402561188
2023-01-22 10:02:50.481020: step: 628/466, loss: 2.3480544090270996
2023-01-22 10:02:51.096525: step: 630/466, loss: 1.132393717765808
2023-01-22 10:02:51.752618: step: 632/466, loss: 5.891961097717285
2023-01-22 10:02:52.352298: step: 634/466, loss: 0.527739405632019
2023-01-22 10:02:52.997209: step: 636/466, loss: 1.0703450441360474
2023-01-22 10:02:53.687968: step: 638/466, loss: 0.42220592498779297
2023-01-22 10:02:54.365950: step: 640/466, loss: 1.296844720840454
2023-01-22 10:02:55.110497: step: 642/466, loss: 0.9484662413597107
2023-01-22 10:02:55.685780: step: 644/466, loss: 1.2204694747924805
2023-01-22 10:02:56.308002: step: 646/466, loss: 1.5694851875305176
2023-01-22 10:02:56.948008: step: 648/466, loss: 0.7809709310531616
2023-01-22 10:02:57.590771: step: 650/466, loss: 0.31678450107574463
2023-01-22 10:02:58.191193: step: 652/466, loss: 0.7704044580459595
2023-01-22 10:02:58.833531: step: 654/466, loss: 0.8784146308898926
2023-01-22 10:02:59.469054: step: 656/466, loss: 1.0362260341644287
2023-01-22 10:03:00.125013: step: 658/466, loss: 0.5954376459121704
2023-01-22 10:03:00.820669: step: 660/466, loss: 0.31657710671424866
2023-01-22 10:03:01.465221: step: 662/466, loss: 0.3830662965774536
2023-01-22 10:03:02.044647: step: 664/466, loss: 1.6849455833435059
2023-01-22 10:03:02.634983: step: 666/466, loss: 1.2949471473693848
2023-01-22 10:03:03.310680: step: 668/466, loss: 2.7972347736358643
2023-01-22 10:03:03.961670: step: 670/466, loss: 0.7938665151596069
2023-01-22 10:03:04.506221: step: 672/466, loss: 0.7428727149963379
2023-01-22 10:03:05.091206: step: 674/466, loss: 0.5348787903785706
2023-01-22 10:03:05.890692: step: 676/466, loss: 1.3804330825805664
2023-01-22 10:03:06.488237: step: 678/466, loss: 2.004319190979004
2023-01-22 10:03:07.083484: step: 680/466, loss: 0.28002798557281494
2023-01-22 10:03:07.700829: step: 682/466, loss: 1.3072905540466309
2023-01-22 10:03:08.297979: step: 684/466, loss: 0.21807393431663513
2023-01-22 10:03:08.922536: step: 686/466, loss: 0.422049343585968
2023-01-22 10:03:09.515855: step: 688/466, loss: 0.12766236066818237
2023-01-22 10:03:10.094233: step: 690/466, loss: 0.21372602880001068
2023-01-22 10:03:10.724654: step: 692/466, loss: 0.6505768895149231
2023-01-22 10:03:11.326768: step: 694/466, loss: 1.8058565855026245
2023-01-22 10:03:11.986001: step: 696/466, loss: 1.6718077659606934
2023-01-22 10:03:12.661913: step: 698/466, loss: 0.3383273482322693
2023-01-22 10:03:13.371055: step: 700/466, loss: 0.31181371212005615
2023-01-22 10:03:13.966577: step: 702/466, loss: 0.33269938826560974
2023-01-22 10:03:14.621922: step: 704/466, loss: 1.0136563777923584
2023-01-22 10:03:15.135603: step: 706/466, loss: 0.47253674268722534
2023-01-22 10:03:15.742463: step: 708/466, loss: 0.7834235429763794
2023-01-22 10:03:16.361690: step: 710/466, loss: 0.43739745020866394
2023-01-22 10:03:16.959235: step: 712/466, loss: 0.7709540724754333
2023-01-22 10:03:17.587715: step: 714/466, loss: 1.3063597679138184
2023-01-22 10:03:18.209081: step: 716/466, loss: 0.9646741151809692
2023-01-22 10:03:18.781653: step: 718/466, loss: 0.3246005177497864
2023-01-22 10:03:19.433258: step: 720/466, loss: 0.23996220529079437
2023-01-22 10:03:19.997431: step: 722/466, loss: 0.6034432053565979
2023-01-22 10:03:20.605644: step: 724/466, loss: 0.6511892676353455
2023-01-22 10:03:21.232859: step: 726/466, loss: 0.30328404903411865
2023-01-22 10:03:21.805420: step: 728/466, loss: 0.8836084008216858
2023-01-22 10:03:22.423544: step: 730/466, loss: 0.3370964229106903
2023-01-22 10:03:23.106860: step: 732/466, loss: 0.6672161817550659
2023-01-22 10:03:23.791375: step: 734/466, loss: 0.6693808436393738
2023-01-22 10:03:24.433224: step: 736/466, loss: 0.3571440577507019
2023-01-22 10:03:25.056292: step: 738/466, loss: 0.9070135951042175
2023-01-22 10:03:25.688422: step: 740/466, loss: 1.1195652484893799
2023-01-22 10:03:26.321502: step: 742/466, loss: 0.1802312284708023
2023-01-22 10:03:26.968805: step: 744/466, loss: 0.5180309414863586
2023-01-22 10:03:27.538762: step: 746/466, loss: 0.132245272397995
2023-01-22 10:03:28.170663: step: 748/466, loss: 0.9627670049667358
2023-01-22 10:03:28.776732: step: 750/466, loss: 0.22905667126178741
2023-01-22 10:03:29.402512: step: 752/466, loss: 0.6364123821258545
2023-01-22 10:03:30.085117: step: 754/466, loss: 7.123708724975586
2023-01-22 10:03:30.728741: step: 756/466, loss: 0.43862396478652954
2023-01-22 10:03:31.342005: step: 758/466, loss: 0.3531898558139801
2023-01-22 10:03:31.918154: step: 760/466, loss: 0.9491121768951416
2023-01-22 10:03:32.571893: step: 762/466, loss: 0.4505407214164734
2023-01-22 10:03:33.207456: step: 764/466, loss: 0.48531121015548706
2023-01-22 10:03:33.864917: step: 766/466, loss: 1.101506233215332
2023-01-22 10:03:34.475623: step: 768/466, loss: 0.8574106693267822
2023-01-22 10:03:35.100995: step: 770/466, loss: 0.5556524395942688
2023-01-22 10:03:35.810632: step: 772/466, loss: 0.4280818700790405
2023-01-22 10:03:36.417837: step: 774/466, loss: 0.9926246404647827
2023-01-22 10:03:37.000644: step: 776/466, loss: 0.30997520685195923
2023-01-22 10:03:37.768685: step: 778/466, loss: 0.3498050272464752
2023-01-22 10:03:38.388732: step: 780/466, loss: 0.736324667930603
2023-01-22 10:03:39.073864: step: 782/466, loss: 0.3913474380970001
2023-01-22 10:03:39.688552: step: 784/466, loss: 0.7822198271751404
2023-01-22 10:03:40.395170: step: 786/466, loss: 1.2186057567596436
2023-01-22 10:03:40.976263: step: 788/466, loss: 1.2209784984588623
2023-01-22 10:03:41.600547: step: 790/466, loss: 0.35334426164627075
2023-01-22 10:03:42.209814: step: 792/466, loss: 1.4263582229614258
2023-01-22 10:03:42.882196: step: 794/466, loss: 0.28296440839767456
2023-01-22 10:03:43.430267: step: 796/466, loss: 1.9911689758300781
2023-01-22 10:03:44.064705: step: 798/466, loss: 1.1145910024642944
2023-01-22 10:03:44.703027: step: 800/466, loss: 0.26959559321403503
2023-01-22 10:03:45.319119: step: 802/466, loss: 0.5132648348808289
2023-01-22 10:03:45.931327: step: 804/466, loss: 9.53636646270752
2023-01-22 10:03:46.525778: step: 806/466, loss: 0.8781405091285706
2023-01-22 10:03:47.154367: step: 808/466, loss: 0.5908510088920593
2023-01-22 10:03:47.827855: step: 810/466, loss: 1.6838551759719849
2023-01-22 10:03:48.425936: step: 812/466, loss: 0.2623120844364166
2023-01-22 10:03:49.016384: step: 814/466, loss: 2.2486305236816406
2023-01-22 10:03:49.641217: step: 816/466, loss: 1.1749213933944702
2023-01-22 10:03:50.237651: step: 818/466, loss: 3.2100768089294434
2023-01-22 10:03:50.884810: step: 820/466, loss: 0.8678385019302368
2023-01-22 10:03:51.535250: step: 822/466, loss: 1.8635488748550415
2023-01-22 10:03:52.172100: step: 824/466, loss: 1.5381243228912354
2023-01-22 10:03:52.792032: step: 826/466, loss: 1.2123987674713135
2023-01-22 10:03:53.473753: step: 828/466, loss: 1.2208527326583862
2023-01-22 10:03:54.126089: step: 830/466, loss: 4.604278564453125
2023-01-22 10:03:54.695721: step: 832/466, loss: 0.23117735981941223
2023-01-22 10:03:55.324922: step: 834/466, loss: 1.1699235439300537
2023-01-22 10:03:55.991056: step: 836/466, loss: 2.572183132171631
2023-01-22 10:03:56.609014: step: 838/466, loss: 0.9678937792778015
2023-01-22 10:03:57.256419: step: 840/466, loss: 4.89470100402832
2023-01-22 10:03:57.885647: step: 842/466, loss: 0.48709937930107117
2023-01-22 10:03:58.558227: step: 844/466, loss: 0.44832372665405273
2023-01-22 10:03:59.127672: step: 846/466, loss: 0.7639361619949341
2023-01-22 10:03:59.753734: step: 848/466, loss: 2.037889003753662
2023-01-22 10:04:00.309817: step: 850/466, loss: 1.6136598587036133
2023-01-22 10:04:00.940506: step: 852/466, loss: 0.6163361072540283
2023-01-22 10:04:01.501102: step: 854/466, loss: 0.6797692775726318
2023-01-22 10:04:02.092124: step: 856/466, loss: 1.4036130905151367
2023-01-22 10:04:02.710873: step: 858/466, loss: 0.15858228504657745
2023-01-22 10:04:03.352274: step: 860/466, loss: 0.4420839846134186
2023-01-22 10:04:04.002733: step: 862/466, loss: 1.3558509349822998
2023-01-22 10:04:04.691155: step: 864/466, loss: 0.7650389671325684
2023-01-22 10:04:05.395391: step: 866/466, loss: 1.6276443004608154
2023-01-22 10:04:05.973047: step: 868/466, loss: 0.6392664909362793
2023-01-22 10:04:06.630035: step: 870/466, loss: 0.6262152194976807
2023-01-22 10:04:07.253193: step: 872/466, loss: 1.5029776096343994
2023-01-22 10:04:07.877085: step: 874/466, loss: 0.5986423492431641
2023-01-22 10:04:08.507166: step: 876/466, loss: 1.5892155170440674
2023-01-22 10:04:09.118201: step: 878/466, loss: 0.380433589220047
2023-01-22 10:04:09.749559: step: 880/466, loss: 1.5511170625686646
2023-01-22 10:04:10.307472: step: 882/466, loss: 0.8453248143196106
2023-01-22 10:04:10.963087: step: 884/466, loss: 1.493863821029663
2023-01-22 10:04:11.584984: step: 886/466, loss: 0.7681907415390015
2023-01-22 10:04:12.239147: step: 888/466, loss: 0.3795468509197235
2023-01-22 10:04:12.810336: step: 890/466, loss: 0.41383445262908936
2023-01-22 10:04:13.418091: step: 892/466, loss: 0.41684284806251526
2023-01-22 10:04:14.041113: step: 894/466, loss: 0.5345543026924133
2023-01-22 10:04:14.747116: step: 896/466, loss: 6.320236682891846
2023-01-22 10:04:15.366840: step: 898/466, loss: 1.5392639636993408
2023-01-22 10:04:16.031159: step: 900/466, loss: 0.6952849626541138
2023-01-22 10:04:16.690770: step: 902/466, loss: 0.41941577196121216
2023-01-22 10:04:17.302682: step: 904/466, loss: 5.019166946411133
2023-01-22 10:04:17.885847: step: 906/466, loss: 0.20151279866695404
2023-01-22 10:04:18.510043: step: 908/466, loss: 1.0805621147155762
2023-01-22 10:04:19.222921: step: 910/466, loss: 0.6773832440376282
2023-01-22 10:04:19.877692: step: 912/466, loss: 0.6606972217559814
2023-01-22 10:04:20.484773: step: 914/466, loss: 0.5137636065483093
2023-01-22 10:04:21.019788: step: 916/466, loss: 0.9369035363197327
2023-01-22 10:04:21.610168: step: 918/466, loss: 0.3441203832626343
2023-01-22 10:04:22.247171: step: 920/466, loss: 0.8426586389541626
2023-01-22 10:04:22.872703: step: 922/466, loss: 2.424509286880493
2023-01-22 10:04:23.503705: step: 924/466, loss: 1.6193931102752686
2023-01-22 10:04:24.093719: step: 926/466, loss: 2.54475998878479
2023-01-22 10:04:24.704253: step: 928/466, loss: 1.66229248046875
2023-01-22 10:04:25.277224: step: 930/466, loss: 0.48374447226524353
2023-01-22 10:04:25.979575: step: 932/466, loss: 0.8983269929885864
==================================================
Loss: 1.197
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3125951086956522, 'r': 0.2728534155597723, 'f1': 0.2913753799392097}, 'combined': 0.21469764837625976, 'epoch': 4}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32426953156573873, 'r': 0.23676358396812514, 'f1': 0.27369228068511486}, 'combined': 0.1713774094009598, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3029132443531828, 'r': 0.27992172675521826, 'f1': 0.2909640039447732}, 'combined': 0.21439452922246444, 'epoch': 4}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3324774795250554, 'r': 0.24343707247461224, 'f1': 0.28107414198266006}, 'combined': 0.17418679221460623, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28125, 'r': 0.2759131878557875, 'f1': 0.2785560344827587}, 'combined': 0.2052518148820327, 'epoch': 4}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3549316211602677, 'r': 0.24377523799906475, 'f1': 0.28903473911499594}, 'combined': 0.19173591604658147, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3157894736842105, 'r': 0.34285714285714286, 'f1': 0.3287671232876712}, 'combined': 0.2191780821917808, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4027777777777778, 'r': 0.31521739130434784, 'f1': 0.3536585365853659}, 'combined': 0.17682926829268295, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34210526315789475, 'r': 0.22413793103448276, 'f1': 0.2708333333333333}, 'combined': 0.18055555555555552, 'epoch': 4}
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': 0.3125951086956522, 'r': 0.2728534155597723, 'f1': 0.2913753799392097}, 'combined': 0.21469764837625976, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32426953156573873, 'r': 0.23676358396812514, 'f1': 0.27369228068511486}, 'combined': 0.1713774094009598, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3157894736842105, 'r': 0.34285714285714286, 'f1': 0.3287671232876712}, 'combined': 0.2191780821917808, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3029132443531828, 'r': 0.27992172675521826, 'f1': 0.2909640039447732}, 'combined': 0.21439452922246444, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3324774795250554, 'r': 0.24343707247461224, 'f1': 0.28107414198266006}, 'combined': 0.17418679221460623, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4027777777777778, 'r': 0.31521739130434784, 'f1': 0.3536585365853659}, 'combined': 0.17682926829268295, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28125, 'r': 0.2759131878557875, 'f1': 0.2785560344827587}, 'combined': 0.2052518148820327, 'epoch': 4}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3549316211602677, 'r': 0.24377523799906475, 'f1': 0.28903473911499594}, 'combined': 0.19173591604658147, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34210526315789475, 'r': 0.22413793103448276, 'f1': 0.2708333333333333}, 'combined': 0.18055555555555552, 'epoch': 4}
******************************
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 10:07:32.544315: step: 2/466, loss: 0.5471147298812866
2023-01-22 10:07:33.196297: step: 4/466, loss: 0.4550301134586334
2023-01-22 10:07:33.823633: step: 6/466, loss: 1.0673224925994873
2023-01-22 10:07:34.500450: step: 8/466, loss: 1.0695760250091553
2023-01-22 10:07:35.241320: step: 10/466, loss: 4.457903861999512
2023-01-22 10:07:35.827369: step: 12/466, loss: 0.25589051842689514
2023-01-22 10:07:36.531370: step: 14/466, loss: 0.45844224095344543
2023-01-22 10:07:37.126812: step: 16/466, loss: 0.7497357130050659
2023-01-22 10:07:37.768530: step: 18/466, loss: 0.3468421697616577
2023-01-22 10:07:38.366975: step: 20/466, loss: 0.6334825754165649
2023-01-22 10:07:39.021639: step: 22/466, loss: 0.2468576431274414
2023-01-22 10:07:39.696963: step: 24/466, loss: 1.0535274744033813
2023-01-22 10:07:40.368108: step: 26/466, loss: 0.5754486918449402
2023-01-22 10:07:40.962234: step: 28/466, loss: 0.5943377614021301
2023-01-22 10:07:41.604044: step: 30/466, loss: 0.04559643566608429
2023-01-22 10:07:42.240091: step: 32/466, loss: 0.26631873846054077
2023-01-22 10:07:42.821116: step: 34/466, loss: 0.13600394129753113
2023-01-22 10:07:43.411243: step: 36/466, loss: 0.40314531326293945
2023-01-22 10:07:44.064131: step: 38/466, loss: 0.6339420080184937
2023-01-22 10:07:44.680111: step: 40/466, loss: 0.7132548093795776
2023-01-22 10:07:45.384521: step: 42/466, loss: 1.5578649044036865
2023-01-22 10:07:46.036473: step: 44/466, loss: 0.669644832611084
2023-01-22 10:07:46.669772: step: 46/466, loss: 0.5667735934257507
2023-01-22 10:07:47.277637: step: 48/466, loss: 0.3961609899997711
2023-01-22 10:07:47.991027: step: 50/466, loss: 0.4249700605869293
2023-01-22 10:07:48.620658: step: 52/466, loss: 0.7943816781044006
2023-01-22 10:07:49.243909: step: 54/466, loss: 0.4422169327735901
2023-01-22 10:07:49.922167: step: 56/466, loss: 2.761477470397949
2023-01-22 10:07:50.574087: step: 58/466, loss: 0.96144700050354
2023-01-22 10:07:51.185040: step: 60/466, loss: 0.18480552732944489
2023-01-22 10:07:51.781732: step: 62/466, loss: 0.50814288854599
2023-01-22 10:07:52.375665: step: 64/466, loss: 1.698656439781189
2023-01-22 10:07:52.959260: step: 66/466, loss: 0.9207381010055542
2023-01-22 10:07:53.577144: step: 68/466, loss: 1.8269872665405273
2023-01-22 10:07:54.199905: step: 70/466, loss: 0.7651251554489136
2023-01-22 10:07:54.872732: step: 72/466, loss: 0.3633600175380707
2023-01-22 10:07:55.482934: step: 74/466, loss: 2.6156022548675537
2023-01-22 10:07:56.086467: step: 76/466, loss: 0.8331165313720703
2023-01-22 10:07:56.738399: step: 78/466, loss: 0.9168491363525391
2023-01-22 10:07:57.357734: step: 80/466, loss: 9.40099048614502
2023-01-22 10:07:57.991462: step: 82/466, loss: 0.814190149307251
2023-01-22 10:07:58.590423: step: 84/466, loss: 0.9722875952720642
2023-01-22 10:07:59.277268: step: 86/466, loss: 0.3626081049442291
2023-01-22 10:07:59.870638: step: 88/466, loss: 0.2767053544521332
2023-01-22 10:08:00.581513: step: 90/466, loss: 0.5099116563796997
2023-01-22 10:08:01.124932: step: 92/466, loss: 2.0675015449523926
2023-01-22 10:08:01.727535: step: 94/466, loss: 0.41941386461257935
2023-01-22 10:08:02.340546: step: 96/466, loss: 0.9571064114570618
2023-01-22 10:08:02.923919: step: 98/466, loss: 0.5113182663917542
2023-01-22 10:08:03.565093: step: 100/466, loss: 0.6901702880859375
2023-01-22 10:08:04.275700: step: 102/466, loss: 0.28122299909591675
2023-01-22 10:08:04.878679: step: 104/466, loss: 0.46844592690467834
2023-01-22 10:08:05.436529: step: 106/466, loss: 0.5279050469398499
2023-01-22 10:08:06.047227: step: 108/466, loss: 1.4865195751190186
2023-01-22 10:08:06.655117: step: 110/466, loss: 1.2874722480773926
2023-01-22 10:08:07.285159: step: 112/466, loss: 0.5957018136978149
2023-01-22 10:08:07.884647: step: 114/466, loss: 0.7692592740058899
2023-01-22 10:08:08.467005: step: 116/466, loss: 0.8668258786201477
2023-01-22 10:08:09.133848: step: 118/466, loss: 0.5483438372612
2023-01-22 10:08:09.796059: step: 120/466, loss: 0.26125210523605347
2023-01-22 10:08:10.452981: step: 122/466, loss: 0.9838550090789795
2023-01-22 10:08:10.998258: step: 124/466, loss: 0.8422924876213074
2023-01-22 10:08:11.590295: step: 126/466, loss: 0.402086079120636
2023-01-22 10:08:12.229528: step: 128/466, loss: 0.9473074674606323
2023-01-22 10:08:12.908222: step: 130/466, loss: 0.4960426688194275
2023-01-22 10:08:13.538018: step: 132/466, loss: 0.31938955187797546
2023-01-22 10:08:14.205067: step: 134/466, loss: 0.5474739670753479
2023-01-22 10:08:14.935979: step: 136/466, loss: 0.9406565427780151
2023-01-22 10:08:15.593165: step: 138/466, loss: 0.9508500695228577
2023-01-22 10:08:16.251970: step: 140/466, loss: 0.6886086463928223
2023-01-22 10:08:16.865680: step: 142/466, loss: 0.4171375036239624
2023-01-22 10:08:17.450358: step: 144/466, loss: 1.6779673099517822
2023-01-22 10:08:18.102206: step: 146/466, loss: 1.1907424926757812
2023-01-22 10:08:18.714965: step: 148/466, loss: 0.4422885775566101
2023-01-22 10:08:19.307012: step: 150/466, loss: 0.3932275176048279
2023-01-22 10:08:19.975524: step: 152/466, loss: 1.4827567338943481
2023-01-22 10:08:20.601011: step: 154/466, loss: 1.9700175523757935
2023-01-22 10:08:21.251661: step: 156/466, loss: 0.7869168519973755
2023-01-22 10:08:21.936363: step: 158/466, loss: 1.7329630851745605
2023-01-22 10:08:22.573170: step: 160/466, loss: 0.7041877508163452
2023-01-22 10:08:23.156263: step: 162/466, loss: 0.39406371116638184
2023-01-22 10:08:23.718432: step: 164/466, loss: 0.28115153312683105
2023-01-22 10:08:24.331287: step: 166/466, loss: 1.389836311340332
2023-01-22 10:08:25.007721: step: 168/466, loss: 1.2109633684158325
2023-01-22 10:08:25.532796: step: 170/466, loss: 0.3636434078216553
2023-01-22 10:08:26.185861: step: 172/466, loss: 0.9906993508338928
2023-01-22 10:08:26.688533: step: 174/466, loss: 0.27599167823791504
2023-01-22 10:08:27.303967: step: 176/466, loss: 0.22614003717899323
2023-01-22 10:08:27.959871: step: 178/466, loss: 0.966813325881958
2023-01-22 10:08:28.577633: step: 180/466, loss: 0.6766749024391174
2023-01-22 10:08:29.263516: step: 182/466, loss: 1.502366304397583
2023-01-22 10:08:29.876565: step: 184/466, loss: 0.789996325969696
2023-01-22 10:08:30.455449: step: 186/466, loss: 1.4622113704681396
2023-01-22 10:08:31.090911: step: 188/466, loss: 0.2746245265007019
2023-01-22 10:08:31.740510: step: 190/466, loss: 0.450369656085968
2023-01-22 10:08:32.321288: step: 192/466, loss: 0.6498920917510986
2023-01-22 10:08:32.976065: step: 194/466, loss: 0.5333251953125
2023-01-22 10:08:33.672933: step: 196/466, loss: 0.5039653182029724
2023-01-22 10:08:34.319726: step: 198/466, loss: 0.7706683874130249
2023-01-22 10:08:34.930490: step: 200/466, loss: 1.9963417053222656
2023-01-22 10:08:35.569745: step: 202/466, loss: 0.7868274450302124
2023-01-22 10:08:36.142019: step: 204/466, loss: 2.225334882736206
2023-01-22 10:08:36.847321: step: 206/466, loss: 1.7012133598327637
2023-01-22 10:08:37.460355: step: 208/466, loss: 1.375243902206421
2023-01-22 10:08:38.028516: step: 210/466, loss: 0.24912454187870026
2023-01-22 10:08:38.616259: step: 212/466, loss: 0.4540861248970032
2023-01-22 10:08:39.291324: step: 214/466, loss: 0.18188805878162384
2023-01-22 10:08:39.830503: step: 216/466, loss: 1.0026720762252808
2023-01-22 10:08:40.470814: step: 218/466, loss: 0.1911715269088745
2023-01-22 10:08:41.102920: step: 220/466, loss: 1.7427427768707275
2023-01-22 10:08:41.735777: step: 222/466, loss: 0.2735958397388458
2023-01-22 10:08:42.469999: step: 224/466, loss: 1.141740322113037
2023-01-22 10:08:43.069984: step: 226/466, loss: 0.9161017537117004
2023-01-22 10:08:43.670161: step: 228/466, loss: 0.6430374383926392
2023-01-22 10:08:44.345987: step: 230/466, loss: 0.2332015037536621
2023-01-22 10:08:44.916795: step: 232/466, loss: 0.7723779678344727
2023-01-22 10:08:45.529403: step: 234/466, loss: 1.0226749181747437
2023-01-22 10:08:46.144137: step: 236/466, loss: 1.4921715259552002
2023-01-22 10:08:46.829549: step: 238/466, loss: 0.9061295390129089
2023-01-22 10:08:47.433466: step: 240/466, loss: 0.632529616355896
2023-01-22 10:08:48.068869: step: 242/466, loss: 0.4292992651462555
2023-01-22 10:08:48.726800: step: 244/466, loss: 5.121511459350586
2023-01-22 10:08:49.319832: step: 246/466, loss: 0.35150039196014404
2023-01-22 10:08:49.846108: step: 248/466, loss: 0.8618891835212708
2023-01-22 10:08:50.389548: step: 250/466, loss: 0.5347373485565186
2023-01-22 10:08:50.986266: step: 252/466, loss: 1.1457524299621582
2023-01-22 10:08:51.618671: step: 254/466, loss: 0.5770044922828674
2023-01-22 10:08:52.225369: step: 256/466, loss: 0.24066293239593506
2023-01-22 10:08:52.851993: step: 258/466, loss: 1.601750135421753
2023-01-22 10:08:53.515357: step: 260/466, loss: 1.0965805053710938
2023-01-22 10:08:54.166218: step: 262/466, loss: 0.6310383677482605
2023-01-22 10:08:54.796787: step: 264/466, loss: 0.7483865022659302
2023-01-22 10:08:55.387754: step: 266/466, loss: 0.2918630540370941
2023-01-22 10:08:55.972461: step: 268/466, loss: 0.26249969005584717
2023-01-22 10:08:56.623867: step: 270/466, loss: 0.6872038245201111
2023-01-22 10:08:57.252303: step: 272/466, loss: 0.8737920522689819
2023-01-22 10:08:57.858018: step: 274/466, loss: 0.9862958192825317
2023-01-22 10:08:58.476662: step: 276/466, loss: 0.27447277307510376
2023-01-22 10:08:59.086123: step: 278/466, loss: 0.42368435859680176
2023-01-22 10:08:59.767864: step: 280/466, loss: 2.0328128337860107
2023-01-22 10:09:00.358997: step: 282/466, loss: 0.27252835035324097
2023-01-22 10:09:01.008125: step: 284/466, loss: 1.5242037773132324
2023-01-22 10:09:01.679273: step: 286/466, loss: 0.49943602085113525
2023-01-22 10:09:02.249132: step: 288/466, loss: 0.5066887140274048
2023-01-22 10:09:02.876607: step: 290/466, loss: 0.6561540365219116
2023-01-22 10:09:03.482372: step: 292/466, loss: 1.1317684650421143
2023-01-22 10:09:04.035354: step: 294/466, loss: 0.6730414032936096
2023-01-22 10:09:04.662119: step: 296/466, loss: 0.3380054533481598
2023-01-22 10:09:05.282203: step: 298/466, loss: 6.33916711807251
2023-01-22 10:09:05.955642: step: 300/466, loss: 1.1168296337127686
2023-01-22 10:09:06.574102: step: 302/466, loss: 0.9960553646087646
2023-01-22 10:09:07.204484: step: 304/466, loss: 2.274310827255249
2023-01-22 10:09:07.768914: step: 306/466, loss: 0.43179214000701904
2023-01-22 10:09:08.362724: step: 308/466, loss: 0.5681861042976379
2023-01-22 10:09:08.966483: step: 310/466, loss: 0.48849573731422424
2023-01-22 10:09:09.547424: step: 312/466, loss: 0.5110349059104919
2023-01-22 10:09:10.173429: step: 314/466, loss: 0.3079199194908142
2023-01-22 10:09:10.837441: step: 316/466, loss: 0.26568320393562317
2023-01-22 10:09:11.527296: step: 318/466, loss: 0.6109682321548462
2023-01-22 10:09:12.171707: step: 320/466, loss: 0.4193262755870819
2023-01-22 10:09:12.781183: step: 322/466, loss: 1.9041683673858643
2023-01-22 10:09:13.389460: step: 324/466, loss: 0.544060230255127
2023-01-22 10:09:13.926467: step: 326/466, loss: 0.18650314211845398
2023-01-22 10:09:14.526448: step: 328/466, loss: 0.8428384065628052
2023-01-22 10:09:15.133522: step: 330/466, loss: 0.7781572341918945
2023-01-22 10:09:15.753742: step: 332/466, loss: 0.1482735127210617
2023-01-22 10:09:16.314191: step: 334/466, loss: 0.6369302272796631
2023-01-22 10:09:16.974526: step: 336/466, loss: 3.364443302154541
2023-01-22 10:09:17.603233: step: 338/466, loss: 0.43260252475738525
2023-01-22 10:09:18.314072: step: 340/466, loss: 3.7939000129699707
2023-01-22 10:09:18.922222: step: 342/466, loss: 0.2519223392009735
2023-01-22 10:09:19.547699: step: 344/466, loss: 1.088708758354187
2023-01-22 10:09:20.220901: step: 346/466, loss: 0.42403557896614075
2023-01-22 10:09:20.864658: step: 348/466, loss: 0.7898201942443848
2023-01-22 10:09:21.477673: step: 350/466, loss: 0.32544323801994324
2023-01-22 10:09:22.111460: step: 352/466, loss: 1.1407803297042847
2023-01-22 10:09:22.725125: step: 354/466, loss: 0.7153778076171875
2023-01-22 10:09:23.338605: step: 356/466, loss: 0.13664700090885162
2023-01-22 10:09:23.952220: step: 358/466, loss: 0.6526727676391602
2023-01-22 10:09:24.610711: step: 360/466, loss: 2.440610885620117
2023-01-22 10:09:25.267991: step: 362/466, loss: 0.9656744003295898
2023-01-22 10:09:25.838042: step: 364/466, loss: 0.3585507869720459
2023-01-22 10:09:26.442324: step: 366/466, loss: 0.5643820762634277
2023-01-22 10:09:27.062965: step: 368/466, loss: 0.9318143725395203
2023-01-22 10:09:27.654364: step: 370/466, loss: 0.39900118112564087
2023-01-22 10:09:28.249267: step: 372/466, loss: 0.21007654070854187
2023-01-22 10:09:28.880030: step: 374/466, loss: 0.2853618264198303
2023-01-22 10:09:29.572800: step: 376/466, loss: 1.3852022886276245
2023-01-22 10:09:30.201118: step: 378/466, loss: 2.298675298690796
2023-01-22 10:09:30.823951: step: 380/466, loss: 0.691215991973877
2023-01-22 10:09:31.396404: step: 382/466, loss: 0.32657772302627563
2023-01-22 10:09:31.993358: step: 384/466, loss: 0.35438624024391174
2023-01-22 10:09:32.642216: step: 386/466, loss: 0.28829479217529297
2023-01-22 10:09:33.253501: step: 388/466, loss: 2.6161675453186035
2023-01-22 10:09:33.898438: step: 390/466, loss: 1.0138685703277588
2023-01-22 10:09:34.476162: step: 392/466, loss: 0.47145283222198486
2023-01-22 10:09:35.134266: step: 394/466, loss: 0.6214955449104309
2023-01-22 10:09:35.784618: step: 396/466, loss: 0.31575721502304077
2023-01-22 10:09:36.333376: step: 398/466, loss: 0.6875791549682617
2023-01-22 10:09:36.941061: step: 400/466, loss: 1.193183422088623
2023-01-22 10:09:37.624455: step: 402/466, loss: 0.32001224160194397
2023-01-22 10:09:38.218018: step: 404/466, loss: 0.4855941832065582
2023-01-22 10:09:38.841407: step: 406/466, loss: 0.5931132435798645
2023-01-22 10:09:39.447450: step: 408/466, loss: 0.324947327375412
2023-01-22 10:09:40.131894: step: 410/466, loss: 0.7642245292663574
2023-01-22 10:09:40.716296: step: 412/466, loss: 0.48168429732322693
2023-01-22 10:09:41.373174: step: 414/466, loss: 0.5540041923522949
2023-01-22 10:09:42.120180: step: 416/466, loss: 1.211597204208374
2023-01-22 10:09:42.700941: step: 418/466, loss: 3.63765549659729
2023-01-22 10:09:43.289688: step: 420/466, loss: 0.7998482584953308
2023-01-22 10:09:43.918178: step: 422/466, loss: 2.532569408416748
2023-01-22 10:09:44.637002: step: 424/466, loss: 1.9449009895324707
2023-01-22 10:09:45.294047: step: 426/466, loss: 0.1245807558298111
2023-01-22 10:09:45.925869: step: 428/466, loss: 1.633721947669983
2023-01-22 10:09:46.537982: step: 430/466, loss: 0.49564772844314575
2023-01-22 10:09:47.251540: step: 432/466, loss: 0.3808407783508301
2023-01-22 10:09:47.874473: step: 434/466, loss: 0.6128196716308594
2023-01-22 10:09:48.512103: step: 436/466, loss: 0.6539456844329834
2023-01-22 10:09:49.085804: step: 438/466, loss: 1.2176947593688965
2023-01-22 10:09:49.678676: step: 440/466, loss: 0.6139934062957764
2023-01-22 10:09:50.330666: step: 442/466, loss: 0.3103480041027069
2023-01-22 10:09:51.029530: step: 444/466, loss: 1.0488853454589844
2023-01-22 10:09:51.698589: step: 446/466, loss: 0.5255616903305054
2023-01-22 10:09:52.297327: step: 448/466, loss: 0.39966022968292236
2023-01-22 10:09:52.932128: step: 450/466, loss: 0.35611096024513245
2023-01-22 10:09:53.560481: step: 452/466, loss: 0.34888365864753723
2023-01-22 10:09:54.176991: step: 454/466, loss: 0.19215558469295502
2023-01-22 10:09:54.775904: step: 456/466, loss: 4.303584575653076
2023-01-22 10:09:55.394489: step: 458/466, loss: 1.0213844776153564
2023-01-22 10:09:56.003094: step: 460/466, loss: 0.5794013142585754
2023-01-22 10:09:56.610459: step: 462/466, loss: 0.6341109275817871
2023-01-22 10:09:57.251845: step: 464/466, loss: 0.953895628452301
2023-01-22 10:09:57.881268: step: 466/466, loss: 0.20153357088565826
2023-01-22 10:09:58.551660: step: 468/466, loss: 0.1921996772289276
2023-01-22 10:09:59.171436: step: 470/466, loss: 0.45410609245300293
2023-01-22 10:09:59.760790: step: 472/466, loss: 0.4120723009109497
2023-01-22 10:10:00.379249: step: 474/466, loss: 0.7399694323539734
2023-01-22 10:10:01.009105: step: 476/466, loss: 0.752868115901947
2023-01-22 10:10:01.667624: step: 478/466, loss: 0.5677819848060608
2023-01-22 10:10:02.310931: step: 480/466, loss: 0.5402620434761047
2023-01-22 10:10:02.947712: step: 482/466, loss: 0.481319785118103
2023-01-22 10:10:03.571312: step: 484/466, loss: 1.7091079950332642
2023-01-22 10:10:04.189061: step: 486/466, loss: 1.1242730617523193
2023-01-22 10:10:04.843042: step: 488/466, loss: 0.3815958499908447
2023-01-22 10:10:05.482840: step: 490/466, loss: 0.56468266248703
2023-01-22 10:10:06.091832: step: 492/466, loss: 0.29745882749557495
2023-01-22 10:10:06.671688: step: 494/466, loss: 0.17169640958309174
2023-01-22 10:10:07.253941: step: 496/466, loss: 0.3405081629753113
2023-01-22 10:10:07.856655: step: 498/466, loss: 0.503221869468689
2023-01-22 10:10:08.454340: step: 500/466, loss: 0.9509025812149048
2023-01-22 10:10:09.018450: step: 502/466, loss: 0.1658211201429367
2023-01-22 10:10:09.729239: step: 504/466, loss: 0.47876477241516113
2023-01-22 10:10:10.329567: step: 506/466, loss: 1.4690961837768555
2023-01-22 10:10:10.908254: step: 508/466, loss: 0.7093818187713623
2023-01-22 10:10:11.488734: step: 510/466, loss: 0.7716629505157471
2023-01-22 10:10:12.077631: step: 512/466, loss: 0.9928057193756104
2023-01-22 10:10:12.727844: step: 514/466, loss: 0.41204598546028137
2023-01-22 10:10:13.363693: step: 516/466, loss: 0.43097513914108276
2023-01-22 10:10:13.991387: step: 518/466, loss: 0.4565886855125427
2023-01-22 10:10:14.606016: step: 520/466, loss: 0.6934749484062195
2023-01-22 10:10:15.349441: step: 522/466, loss: 1.2867885828018188
2023-01-22 10:10:15.959511: step: 524/466, loss: 0.7034398317337036
2023-01-22 10:10:16.565277: step: 526/466, loss: 0.894005537033081
2023-01-22 10:10:17.156907: step: 528/466, loss: 0.2675049602985382
2023-01-22 10:10:17.795010: step: 530/466, loss: 0.5433415770530701
2023-01-22 10:10:18.439623: step: 532/466, loss: 0.2747874855995178
2023-01-22 10:10:19.067506: step: 534/466, loss: 0.5573550462722778
2023-01-22 10:10:19.647153: step: 536/466, loss: 3.402272939682007
2023-01-22 10:10:20.285657: step: 538/466, loss: 1.3509525060653687
2023-01-22 10:10:20.868265: step: 540/466, loss: 1.3163940906524658
2023-01-22 10:10:21.481157: step: 542/466, loss: 0.9249829053878784
2023-01-22 10:10:22.127913: step: 544/466, loss: 0.9020353555679321
2023-01-22 10:10:22.732927: step: 546/466, loss: 0.6468010544776917
2023-01-22 10:10:23.338070: step: 548/466, loss: 0.1497478038072586
2023-01-22 10:10:23.992021: step: 550/466, loss: 2.2226760387420654
2023-01-22 10:10:24.658064: step: 552/466, loss: 1.034489393234253
2023-01-22 10:10:25.313502: step: 554/466, loss: 1.2668101787567139
2023-01-22 10:10:25.885850: step: 556/466, loss: 0.41327354311943054
2023-01-22 10:10:26.568173: step: 558/466, loss: 0.5404168367385864
2023-01-22 10:10:27.179156: step: 560/466, loss: 0.5784534811973572
2023-01-22 10:10:27.781246: step: 562/466, loss: 1.1106534004211426
2023-01-22 10:10:28.462914: step: 564/466, loss: 0.853075385093689
2023-01-22 10:10:29.064040: step: 566/466, loss: 1.339813470840454
2023-01-22 10:10:29.661381: step: 568/466, loss: 0.4004724621772766
2023-01-22 10:10:30.236340: step: 570/466, loss: 0.26823610067367554
2023-01-22 10:10:30.877989: step: 572/466, loss: 2.8942439556121826
2023-01-22 10:10:31.532750: step: 574/466, loss: 0.3049118220806122
2023-01-22 10:10:32.223491: step: 576/466, loss: 1.6497358083724976
2023-01-22 10:10:32.902668: step: 578/466, loss: 0.47421208024024963
2023-01-22 10:10:33.538269: step: 580/466, loss: 1.4139649868011475
2023-01-22 10:10:34.184429: step: 582/466, loss: 0.91805100440979
2023-01-22 10:10:34.801637: step: 584/466, loss: 0.918079137802124
2023-01-22 10:10:35.450770: step: 586/466, loss: 1.3088068962097168
2023-01-22 10:10:36.023040: step: 588/466, loss: 1.1106313467025757
2023-01-22 10:10:36.628508: step: 590/466, loss: 0.6188311576843262
2023-01-22 10:10:37.238625: step: 592/466, loss: 0.36715516448020935
2023-01-22 10:10:37.821231: step: 594/466, loss: 0.8313745260238647
2023-01-22 10:10:38.440794: step: 596/466, loss: 0.2605927884578705
2023-01-22 10:10:39.024669: step: 598/466, loss: 1.2984670400619507
2023-01-22 10:10:39.631452: step: 600/466, loss: 0.2875438630580902
2023-01-22 10:10:40.260854: step: 602/466, loss: 0.7626654505729675
2023-01-22 10:10:40.916190: step: 604/466, loss: 0.46695560216903687
2023-01-22 10:10:41.560846: step: 606/466, loss: 0.5650315880775452
2023-01-22 10:10:42.171143: step: 608/466, loss: 0.2230704426765442
2023-01-22 10:10:42.759857: step: 610/466, loss: 0.7090718150138855
2023-01-22 10:10:43.361698: step: 612/466, loss: 1.0561984777450562
2023-01-22 10:10:44.017014: step: 614/466, loss: 0.34719061851501465
2023-01-22 10:10:44.625328: step: 616/466, loss: 2.2053418159484863
2023-01-22 10:10:45.231587: step: 618/466, loss: 2.624155044555664
2023-01-22 10:10:45.886001: step: 620/466, loss: 1.5863568782806396
2023-01-22 10:10:46.559657: step: 622/466, loss: 0.5461592674255371
2023-01-22 10:10:47.245343: step: 624/466, loss: 0.5462601184844971
2023-01-22 10:10:47.865824: step: 626/466, loss: 1.3564051389694214
2023-01-22 10:10:48.480987: step: 628/466, loss: 0.18615445494651794
2023-01-22 10:10:49.120973: step: 630/466, loss: 0.8325631022453308
2023-01-22 10:10:49.778550: step: 632/466, loss: 0.6906343102455139
2023-01-22 10:10:50.401542: step: 634/466, loss: 0.4399493336677551
2023-01-22 10:10:51.104171: step: 636/466, loss: 0.5468199253082275
2023-01-22 10:10:51.747634: step: 638/466, loss: 0.7452964186668396
2023-01-22 10:10:52.417995: step: 640/466, loss: 1.1611220836639404
2023-01-22 10:10:52.972526: step: 642/466, loss: 0.549014687538147
2023-01-22 10:10:53.599327: step: 644/466, loss: 0.3178991973400116
2023-01-22 10:10:54.237869: step: 646/466, loss: 1.5364816188812256
2023-01-22 10:10:54.844887: step: 648/466, loss: 1.1733858585357666
2023-01-22 10:10:55.482770: step: 650/466, loss: 0.8622576594352722
2023-01-22 10:10:56.131660: step: 652/466, loss: 0.8693770170211792
2023-01-22 10:10:56.750778: step: 654/466, loss: 0.4081299304962158
2023-01-22 10:10:57.400679: step: 656/466, loss: 0.7796466946601868
2023-01-22 10:10:58.049531: step: 658/466, loss: 0.8079643845558167
2023-01-22 10:10:58.634315: step: 660/466, loss: 1.3321342468261719
2023-01-22 10:10:59.211179: step: 662/466, loss: 0.5625272989273071
2023-01-22 10:10:59.856719: step: 664/466, loss: 0.6250572204589844
2023-01-22 10:11:00.438812: step: 666/466, loss: 0.3744121193885803
2023-01-22 10:11:01.013386: step: 668/466, loss: 0.9476857781410217
2023-01-22 10:11:01.621533: step: 670/466, loss: 0.280961275100708
2023-01-22 10:11:02.210022: step: 672/466, loss: 0.34791773557662964
2023-01-22 10:11:02.856863: step: 674/466, loss: 1.0845293998718262
2023-01-22 10:11:03.462520: step: 676/466, loss: 0.43291908502578735
2023-01-22 10:11:04.100717: step: 678/466, loss: 1.20071280002594
2023-01-22 10:11:04.694061: step: 680/466, loss: 0.8086950778961182
2023-01-22 10:11:05.277605: step: 682/466, loss: 0.5120579600334167
2023-01-22 10:11:05.910146: step: 684/466, loss: 0.47946423292160034
2023-01-22 10:11:06.495896: step: 686/466, loss: 0.5221784114837646
2023-01-22 10:11:07.085502: step: 688/466, loss: 7.150136947631836
2023-01-22 10:11:07.685653: step: 690/466, loss: 0.1715814769268036
2023-01-22 10:11:08.316720: step: 692/466, loss: 2.3639845848083496
2023-01-22 10:11:08.919221: step: 694/466, loss: 0.6342852115631104
2023-01-22 10:11:09.479153: step: 696/466, loss: 0.5407548546791077
2023-01-22 10:11:10.186322: step: 698/466, loss: 0.4505281448364258
2023-01-22 10:11:10.904781: step: 700/466, loss: 0.5976901054382324
2023-01-22 10:11:11.502192: step: 702/466, loss: 3.942974328994751
2023-01-22 10:11:12.205127: step: 704/466, loss: 0.6684309244155884
2023-01-22 10:11:12.797911: step: 706/466, loss: 0.8447902798652649
2023-01-22 10:11:13.416998: step: 708/466, loss: 1.9354099035263062
2023-01-22 10:11:14.048452: step: 710/466, loss: 0.29163914918899536
2023-01-22 10:11:14.720767: step: 712/466, loss: 0.6639055013656616
2023-01-22 10:11:15.441733: step: 714/466, loss: 0.558269739151001
2023-01-22 10:11:16.130407: step: 716/466, loss: 6.34437370300293
2023-01-22 10:11:16.744121: step: 718/466, loss: 0.8044198751449585
2023-01-22 10:11:17.416423: step: 720/466, loss: 0.1624743640422821
2023-01-22 10:11:17.994259: step: 722/466, loss: 1.1905999183654785
2023-01-22 10:11:18.653471: step: 724/466, loss: 0.8427300453186035
2023-01-22 10:11:19.274248: step: 726/466, loss: 0.21977035701274872
2023-01-22 10:11:19.919442: step: 728/466, loss: 0.23939011991024017
2023-01-22 10:11:20.576233: step: 730/466, loss: 1.2132254838943481
2023-01-22 10:11:21.280503: step: 732/466, loss: 1.0316905975341797
2023-01-22 10:11:22.110280: step: 734/466, loss: 1.0953068733215332
2023-01-22 10:11:22.720169: step: 736/466, loss: 0.48757675290107727
2023-01-22 10:11:23.323023: step: 738/466, loss: 0.36855441331863403
2023-01-22 10:11:23.960567: step: 740/466, loss: 0.9813733100891113
2023-01-22 10:11:24.624538: step: 742/466, loss: 0.45953619480133057
2023-01-22 10:11:25.228312: step: 744/466, loss: 1.2267102003097534
2023-01-22 10:11:25.821616: step: 746/466, loss: 0.2407502830028534
2023-01-22 10:11:26.470374: step: 748/466, loss: 0.585015058517456
2023-01-22 10:11:27.097732: step: 750/466, loss: 0.6010576486587524
2023-01-22 10:11:27.714151: step: 752/466, loss: 0.994664192199707
2023-01-22 10:11:28.293438: step: 754/466, loss: 0.9954037666320801
2023-01-22 10:11:28.910303: step: 756/466, loss: 0.8531153202056885
2023-01-22 10:11:29.578949: step: 758/466, loss: 0.7809121608734131
2023-01-22 10:11:30.262430: step: 760/466, loss: 1.1692357063293457
2023-01-22 10:11:30.849894: step: 762/466, loss: 0.8527080416679382
2023-01-22 10:11:31.461231: step: 764/466, loss: 1.1707797050476074
2023-01-22 10:11:32.082696: step: 766/466, loss: 5.228311061859131
2023-01-22 10:11:32.725060: step: 768/466, loss: 0.7698712944984436
2023-01-22 10:11:33.358608: step: 770/466, loss: 2.095247268676758
2023-01-22 10:11:33.989579: step: 772/466, loss: 0.5572216510772705
2023-01-22 10:11:34.624832: step: 774/466, loss: 1.3784372806549072
2023-01-22 10:11:35.226641: step: 776/466, loss: 0.3510480523109436
2023-01-22 10:11:35.936290: step: 778/466, loss: 1.1574081182479858
2023-01-22 10:11:36.725838: step: 780/466, loss: 0.28958892822265625
2023-01-22 10:11:37.363535: step: 782/466, loss: 0.5354122519493103
2023-01-22 10:11:37.964304: step: 784/466, loss: 0.5628578066825867
2023-01-22 10:11:38.602151: step: 786/466, loss: 0.34347057342529297
2023-01-22 10:11:39.235149: step: 788/466, loss: 0.30458784103393555
2023-01-22 10:11:39.923382: step: 790/466, loss: 0.7543378472328186
2023-01-22 10:11:40.623997: step: 792/466, loss: 0.5978944301605225
2023-01-22 10:11:41.237587: step: 794/466, loss: 0.8760815262794495
2023-01-22 10:11:41.879655: step: 796/466, loss: 2.8389697074890137
2023-01-22 10:11:42.452593: step: 798/466, loss: 1.1012701988220215
2023-01-22 10:11:43.098233: step: 800/466, loss: 0.6880276203155518
2023-01-22 10:11:43.707915: step: 802/466, loss: 0.4630478024482727
2023-01-22 10:11:44.390517: step: 804/466, loss: 0.2929562032222748
2023-01-22 10:11:45.015107: step: 806/466, loss: 0.42517170310020447
2023-01-22 10:11:45.628512: step: 808/466, loss: 0.29620039463043213
2023-01-22 10:11:46.279885: step: 810/466, loss: 1.1095701456069946
2023-01-22 10:11:46.837790: step: 812/466, loss: 0.15149930119514465
2023-01-22 10:11:47.401461: step: 814/466, loss: 0.45719343423843384
2023-01-22 10:11:48.009129: step: 816/466, loss: 0.2268422544002533
2023-01-22 10:11:48.693400: step: 818/466, loss: 0.35965633392333984
2023-01-22 10:11:49.400108: step: 820/466, loss: 0.3629857897758484
2023-01-22 10:11:50.056582: step: 822/466, loss: 0.45110806822776794
2023-01-22 10:11:50.657079: step: 824/466, loss: 4.482956409454346
2023-01-22 10:11:51.271953: step: 826/466, loss: 0.6074123382568359
2023-01-22 10:11:51.916591: step: 828/466, loss: 0.16443508863449097
2023-01-22 10:11:52.562037: step: 830/466, loss: 0.6019780039787292
2023-01-22 10:11:53.254312: step: 832/466, loss: 0.2932056486606598
2023-01-22 10:11:53.807906: step: 834/466, loss: 0.7100816965103149
2023-01-22 10:11:54.367393: step: 836/466, loss: 2.600250482559204
2023-01-22 10:11:54.983966: step: 838/466, loss: 2.4224514961242676
2023-01-22 10:11:55.591350: step: 840/466, loss: 0.4868653118610382
2023-01-22 10:11:56.205123: step: 842/466, loss: 2.266256332397461
2023-01-22 10:11:56.837783: step: 844/466, loss: 0.674579918384552
2023-01-22 10:11:57.417606: step: 846/466, loss: 0.46162062883377075
2023-01-22 10:11:58.052492: step: 848/466, loss: 0.2178461253643036
2023-01-22 10:11:58.733528: step: 850/466, loss: 0.7983039021492004
2023-01-22 10:11:59.385858: step: 852/466, loss: 1.6612443923950195
2023-01-22 10:11:59.945945: step: 854/466, loss: 4.634618759155273
2023-01-22 10:12:00.567838: step: 856/466, loss: 1.1053825616836548
2023-01-22 10:12:01.225950: step: 858/466, loss: 0.2669443190097809
2023-01-22 10:12:01.811146: step: 860/466, loss: 0.5047089457511902
2023-01-22 10:12:02.456778: step: 862/466, loss: 0.6695466637611389
2023-01-22 10:12:03.065117: step: 864/466, loss: 3.249666213989258
2023-01-22 10:12:03.700463: step: 866/466, loss: 0.6248589754104614
2023-01-22 10:12:04.325262: step: 868/466, loss: 2.089353084564209
2023-01-22 10:12:04.920552: step: 870/466, loss: 1.4833861589431763
2023-01-22 10:12:05.599151: step: 872/466, loss: 0.49304646253585815
2023-01-22 10:12:06.213936: step: 874/466, loss: 0.20364585518836975
2023-01-22 10:12:06.816299: step: 876/466, loss: 0.41799670457839966
2023-01-22 10:12:07.457850: step: 878/466, loss: 1.991162896156311
2023-01-22 10:12:08.077504: step: 880/466, loss: 0.585088849067688
2023-01-22 10:12:08.613556: step: 882/466, loss: 1.423997402191162
2023-01-22 10:12:09.323560: step: 884/466, loss: 0.5289191007614136
2023-01-22 10:12:09.889008: step: 886/466, loss: 0.7948544025421143
2023-01-22 10:12:10.511649: step: 888/466, loss: 0.3936300277709961
2023-01-22 10:12:11.093810: step: 890/466, loss: 4.33754301071167
2023-01-22 10:12:11.740362: step: 892/466, loss: 1.7852764129638672
2023-01-22 10:12:12.375866: step: 894/466, loss: 0.3783182203769684
2023-01-22 10:12:12.963636: step: 896/466, loss: 0.40759915113449097
2023-01-22 10:12:13.533611: step: 898/466, loss: 0.35211068391799927
2023-01-22 10:12:14.092879: step: 900/466, loss: 1.551925539970398
2023-01-22 10:12:14.785678: step: 902/466, loss: 0.40734782814979553
2023-01-22 10:12:15.443763: step: 904/466, loss: 1.77029287815094
2023-01-22 10:12:16.019205: step: 906/466, loss: 3.029491901397705
2023-01-22 10:12:16.649369: step: 908/466, loss: 0.45158347487449646
2023-01-22 10:12:17.267421: step: 910/466, loss: 2.3562979698181152
2023-01-22 10:12:17.894315: step: 912/466, loss: 1.232257604598999
2023-01-22 10:12:18.524393: step: 914/466, loss: 1.3863972425460815
2023-01-22 10:12:19.131681: step: 916/466, loss: 0.934714138507843
2023-01-22 10:12:19.755078: step: 918/466, loss: 0.5982561111450195
2023-01-22 10:12:20.372676: step: 920/466, loss: 0.21740776300430298
2023-01-22 10:12:21.033724: step: 922/466, loss: 0.20542573928833008
2023-01-22 10:12:21.645293: step: 924/466, loss: 0.2219095677137375
2023-01-22 10:12:22.239584: step: 926/466, loss: 1.0753498077392578
2023-01-22 10:12:22.884136: step: 928/466, loss: 0.4892817437648773
2023-01-22 10:12:23.509161: step: 930/466, loss: 1.2177451848983765
2023-01-22 10:12:24.141603: step: 932/466, loss: 0.2971642017364502
==================================================
Loss: 0.944
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32179632189901575, 'r': 0.27355740457449534, 'f1': 0.29572256863745444}, 'combined': 0.21790084004865062, 'epoch': 5}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32150230293281284, 'r': 0.23234132099932273, 'f1': 0.26974498410723674}, 'combined': 0.16890573771200806, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32129421518054535, 'r': 0.28959156017221827, 'f1': 0.30462026389373054}, 'combined': 0.22445703655327512, 'epoch': 5}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3240670324587135, 'r': 0.23983300236114177, 'f1': 0.2756586790623911}, 'combined': 0.17083073068655222, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2870113455833512, 'r': 0.27611907440371736, 'f1': 0.2814598688796113}, 'combined': 0.20739148233234514, 'epoch': 5}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3582228395089435, 'r': 0.2388152263392957, 'f1': 0.28657827160715477}, 'combined': 0.19010637819484524, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25609756097560976, 'r': 0.3, 'f1': 0.2763157894736842}, 'combined': 0.18421052631578944, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.29545454545454547, 'r': 0.2826086956521739, 'f1': 0.2888888888888889}, 'combined': 0.14444444444444446, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4117647058823529, 'r': 0.2413793103448276, 'f1': 0.3043478260869565}, 'combined': 0.20289855072463764, 'epoch': 5}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3125951086956522, 'r': 0.2728534155597723, 'f1': 0.2913753799392097}, 'combined': 0.21469764837625976, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32426953156573873, 'r': 0.23676358396812514, 'f1': 0.27369228068511486}, 'combined': 0.1713774094009598, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3157894736842105, 'r': 0.34285714285714286, 'f1': 0.3287671232876712}, 'combined': 0.2191780821917808, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3029132443531828, 'r': 0.27992172675521826, 'f1': 0.2909640039447732}, 'combined': 0.21439452922246444, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3324774795250554, 'r': 0.24343707247461224, 'f1': 0.28107414198266006}, 'combined': 0.17418679221460623, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4027777777777778, 'r': 0.31521739130434784, 'f1': 0.3536585365853659}, 'combined': 0.17682926829268295, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2870113455833512, 'r': 0.27611907440371736, 'f1': 0.2814598688796113}, 'combined': 0.20739148233234514, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3582228395089435, 'r': 0.2388152263392957, 'f1': 0.28657827160715477}, 'combined': 0.19010637819484524, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4117647058823529, 'r': 0.2413793103448276, 'f1': 0.3043478260869565}, 'combined': 0.20289855072463764, 'epoch': 5}
******************************
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 10:15:07.378441: step: 2/466, loss: 0.786810040473938
2023-01-22 10:15:07.999224: step: 4/466, loss: 1.206434726715088
2023-01-22 10:15:08.582912: step: 6/466, loss: 1.0188630819320679
2023-01-22 10:15:09.254944: step: 8/466, loss: 0.14964409172534943
2023-01-22 10:15:10.590299: step: 10/466, loss: 0.21679998934268951
2023-01-22 10:15:11.217460: step: 12/466, loss: 1.7508819103240967
2023-01-22 10:15:11.870424: step: 14/466, loss: 2.308197498321533
2023-01-22 10:15:12.443606: step: 16/466, loss: 0.463043212890625
2023-01-22 10:15:13.067250: step: 18/466, loss: 0.18147246539592743
2023-01-22 10:15:13.689088: step: 20/466, loss: 0.17629674077033997
2023-01-22 10:15:14.319798: step: 22/466, loss: 0.5790026783943176
2023-01-22 10:15:14.993009: step: 24/466, loss: 1.3718117475509644
2023-01-22 10:15:15.586276: step: 26/466, loss: 0.25628361105918884
2023-01-22 10:15:16.229625: step: 28/466, loss: 0.8798097372055054
2023-01-22 10:15:16.850202: step: 30/466, loss: 0.3664752244949341
2023-01-22 10:15:17.427195: step: 32/466, loss: 1.7821688652038574
2023-01-22 10:15:18.037230: step: 34/466, loss: 0.6296994090080261
2023-01-22 10:15:18.727651: step: 36/466, loss: 5.59828519821167
2023-01-22 10:15:19.320243: step: 38/466, loss: 0.8631159663200378
2023-01-22 10:15:19.888086: step: 40/466, loss: 0.21120579540729523
2023-01-22 10:15:20.528805: step: 42/466, loss: 2.49690580368042
2023-01-22 10:15:21.169831: step: 44/466, loss: 0.40758389234542847
2023-01-22 10:15:21.815967: step: 46/466, loss: 0.4912774860858917
2023-01-22 10:15:22.431380: step: 48/466, loss: 0.09327677637338638
2023-01-22 10:15:23.042284: step: 50/466, loss: 0.6095417737960815
2023-01-22 10:15:23.697159: step: 52/466, loss: 0.43752914667129517
2023-01-22 10:15:24.316796: step: 54/466, loss: 0.5212745070457458
2023-01-22 10:15:24.937614: step: 56/466, loss: 0.7521660327911377
2023-01-22 10:15:25.594793: step: 58/466, loss: 0.48838797211647034
2023-01-22 10:15:26.225730: step: 60/466, loss: 0.6393229961395264
2023-01-22 10:15:26.820314: step: 62/466, loss: 0.7894414663314819
2023-01-22 10:15:27.567201: step: 64/466, loss: 1.2035799026489258
2023-01-22 10:15:28.239339: step: 66/466, loss: 1.823659896850586
2023-01-22 10:15:28.848624: step: 68/466, loss: 1.1329340934753418
2023-01-22 10:15:29.572056: step: 70/466, loss: 0.5138535499572754
2023-01-22 10:15:30.146950: step: 72/466, loss: 0.24458928406238556
2023-01-22 10:15:30.783515: step: 74/466, loss: 0.41312578320503235
2023-01-22 10:15:31.437163: step: 76/466, loss: 0.9526811242103577
2023-01-22 10:15:32.040841: step: 78/466, loss: 0.23132620751857758
2023-01-22 10:15:32.686841: step: 80/466, loss: 2.6661341190338135
2023-01-22 10:15:33.376091: step: 82/466, loss: 0.8018032312393188
2023-01-22 10:15:34.046346: step: 84/466, loss: 0.6294028162956238
2023-01-22 10:15:34.690042: step: 86/466, loss: 0.5024424195289612
2023-01-22 10:15:35.299887: step: 88/466, loss: 1.4013025760650635
2023-01-22 10:15:35.838368: step: 90/466, loss: 5.564722061157227
2023-01-22 10:15:36.437174: step: 92/466, loss: 1.7727617025375366
2023-01-22 10:15:37.092226: step: 94/466, loss: 0.2613389790058136
2023-01-22 10:15:37.701810: step: 96/466, loss: 0.3380162715911865
2023-01-22 10:15:38.389658: step: 98/466, loss: 0.1322072297334671
2023-01-22 10:15:39.061257: step: 100/466, loss: 1.1087273359298706
2023-01-22 10:15:39.665924: step: 102/466, loss: 0.4166465103626251
2023-01-22 10:15:40.222008: step: 104/466, loss: 0.5383948683738708
2023-01-22 10:15:40.947441: step: 106/466, loss: 0.6129652857780457
2023-01-22 10:15:41.564879: step: 108/466, loss: 0.20186620950698853
2023-01-22 10:15:42.175546: step: 110/466, loss: 0.6196213960647583
2023-01-22 10:15:42.775000: step: 112/466, loss: 0.6186575889587402
2023-01-22 10:15:43.361280: step: 114/466, loss: 0.531226634979248
2023-01-22 10:15:43.952846: step: 116/466, loss: 0.40110477805137634
2023-01-22 10:15:44.592606: step: 118/466, loss: 0.6995194554328918
2023-01-22 10:15:45.164732: step: 120/466, loss: 0.1502196490764618
2023-01-22 10:15:45.906191: step: 122/466, loss: 0.43456703424453735
2023-01-22 10:15:46.549726: step: 124/466, loss: 0.8035438656806946
2023-01-22 10:15:47.161260: step: 126/466, loss: 2.1317715644836426
2023-01-22 10:15:47.812807: step: 128/466, loss: 0.7160360813140869
2023-01-22 10:15:48.383242: step: 130/466, loss: 0.1807565689086914
2023-01-22 10:15:49.011599: step: 132/466, loss: 0.5092267394065857
2023-01-22 10:15:49.665959: step: 134/466, loss: 0.30304017663002014
2023-01-22 10:15:50.311525: step: 136/466, loss: 0.3935609459877014
2023-01-22 10:15:50.930934: step: 138/466, loss: 0.5923236012458801
2023-01-22 10:15:51.478449: step: 140/466, loss: 0.5156057476997375
2023-01-22 10:15:52.129862: step: 142/466, loss: 0.33324167132377625
2023-01-22 10:15:52.774281: step: 144/466, loss: 0.276790589094162
2023-01-22 10:15:53.428585: step: 146/466, loss: 0.7008892893791199
2023-01-22 10:15:54.045967: step: 148/466, loss: 4.521030902862549
2023-01-22 10:15:54.671801: step: 150/466, loss: 0.36508435010910034
2023-01-22 10:15:55.294463: step: 152/466, loss: 0.21985134482383728
2023-01-22 10:15:55.915510: step: 154/466, loss: 3.0521111488342285
2023-01-22 10:15:56.561215: step: 156/466, loss: 0.5557551980018616
2023-01-22 10:15:57.155173: step: 158/466, loss: 0.9050538539886475
2023-01-22 10:15:57.750574: step: 160/466, loss: 0.48003241419792175
2023-01-22 10:15:58.418240: step: 162/466, loss: 9.193645477294922
2023-01-22 10:15:59.088095: step: 164/466, loss: 1.3696081638336182
2023-01-22 10:15:59.714701: step: 166/466, loss: 0.286681592464447
2023-01-22 10:16:00.402572: step: 168/466, loss: 0.6474204659461975
2023-01-22 10:16:01.075170: step: 170/466, loss: 1.1203362941741943
2023-01-22 10:16:01.690791: step: 172/466, loss: 0.9201343059539795
2023-01-22 10:16:02.295169: step: 174/466, loss: 0.40289899706840515
2023-01-22 10:16:02.906559: step: 176/466, loss: 0.31696873903274536
2023-01-22 10:16:03.522432: step: 178/466, loss: 0.8729555010795593
2023-01-22 10:16:04.159845: step: 180/466, loss: 0.2728038430213928
2023-01-22 10:16:04.791353: step: 182/466, loss: 0.4005033075809479
2023-01-22 10:16:05.370487: step: 184/466, loss: 0.15636737644672394
2023-01-22 10:16:05.928493: step: 186/466, loss: 0.2103724181652069
2023-01-22 10:16:06.567298: step: 188/466, loss: 0.8750123381614685
2023-01-22 10:16:07.206548: step: 190/466, loss: 0.23224452137947083
2023-01-22 10:16:07.851235: step: 192/466, loss: 0.7866896986961365
2023-01-22 10:16:08.489923: step: 194/466, loss: 0.43896278738975525
2023-01-22 10:16:09.102115: step: 196/466, loss: 0.2491196095943451
2023-01-22 10:16:09.725432: step: 198/466, loss: 0.5458095073699951
2023-01-22 10:16:10.442023: step: 200/466, loss: 0.5856198072433472
2023-01-22 10:16:11.082075: step: 202/466, loss: 1.415247917175293
2023-01-22 10:16:11.716756: step: 204/466, loss: 0.8848930597305298
2023-01-22 10:16:12.384928: step: 206/466, loss: 0.5740233659744263
2023-01-22 10:16:13.045270: step: 208/466, loss: 0.3295213282108307
2023-01-22 10:16:13.687537: step: 210/466, loss: 0.3278895318508148
2023-01-22 10:16:14.393522: step: 212/466, loss: 0.34687161445617676
2023-01-22 10:16:15.043983: step: 214/466, loss: 1.2130358219146729
2023-01-22 10:16:15.584482: step: 216/466, loss: 0.4145267605781555
2023-01-22 10:16:16.224235: step: 218/466, loss: 0.9429118037223816
2023-01-22 10:16:16.859287: step: 220/466, loss: 0.8307474255561829
2023-01-22 10:16:17.460595: step: 222/466, loss: 0.8328704237937927
2023-01-22 10:16:18.057413: step: 224/466, loss: 0.21130898594856262
2023-01-22 10:16:18.745530: step: 226/466, loss: 0.9046894907951355
2023-01-22 10:16:19.404003: step: 228/466, loss: 1.3835208415985107
2023-01-22 10:16:20.043904: step: 230/466, loss: 0.21962091326713562
2023-01-22 10:16:20.672722: step: 232/466, loss: 0.5466563105583191
2023-01-22 10:16:21.302268: step: 234/466, loss: 0.4586387574672699
2023-01-22 10:16:21.929993: step: 236/466, loss: 0.6743621826171875
2023-01-22 10:16:22.510592: step: 238/466, loss: 0.5060661435127258
2023-01-22 10:16:23.135007: step: 240/466, loss: 0.19885101914405823
2023-01-22 10:16:23.766473: step: 242/466, loss: 0.12861591577529907
2023-01-22 10:16:24.344191: step: 244/466, loss: 0.12938374280929565
2023-01-22 10:16:24.948867: step: 246/466, loss: 0.8911042213439941
2023-01-22 10:16:25.569962: step: 248/466, loss: 1.198577642440796
2023-01-22 10:16:26.191053: step: 250/466, loss: 1.077630877494812
2023-01-22 10:16:26.805129: step: 252/466, loss: 0.5633366107940674
2023-01-22 10:16:27.420630: step: 254/466, loss: 0.3750508427619934
2023-01-22 10:16:28.035852: step: 256/466, loss: 0.6132140755653381
2023-01-22 10:16:28.625446: step: 258/466, loss: 0.8923450708389282
2023-01-22 10:16:29.229564: step: 260/466, loss: 0.3184509575366974
2023-01-22 10:16:29.914901: step: 262/466, loss: 0.4965699315071106
2023-01-22 10:16:30.505995: step: 264/466, loss: 0.3206332325935364
2023-01-22 10:16:31.124092: step: 266/466, loss: 1.2157940864562988
2023-01-22 10:16:31.774048: step: 268/466, loss: 0.6410622596740723
2023-01-22 10:16:32.307867: step: 270/466, loss: 1.0094743967056274
2023-01-22 10:16:32.881572: step: 272/466, loss: 0.7588210105895996
2023-01-22 10:16:33.493210: step: 274/466, loss: 0.666674792766571
2023-01-22 10:16:34.133214: step: 276/466, loss: 0.6273010969161987
2023-01-22 10:16:34.765176: step: 278/466, loss: 0.34044626355171204
2023-01-22 10:16:35.364637: step: 280/466, loss: 0.17507882416248322
2023-01-22 10:16:36.016996: step: 282/466, loss: 0.2489982396364212
2023-01-22 10:16:36.633604: step: 284/466, loss: 0.7076356410980225
2023-01-22 10:16:37.242081: step: 286/466, loss: 0.5299989581108093
2023-01-22 10:16:37.828536: step: 288/466, loss: 0.1635860949754715
2023-01-22 10:16:38.447340: step: 290/466, loss: 0.4878239333629608
2023-01-22 10:16:39.089518: step: 292/466, loss: 0.6388272047042847
2023-01-22 10:16:39.683031: step: 294/466, loss: 0.09273450821638107
2023-01-22 10:16:40.377943: step: 296/466, loss: 0.43097102642059326
2023-01-22 10:16:41.161672: step: 298/466, loss: 1.4195430278778076
2023-01-22 10:16:41.769935: step: 300/466, loss: 0.3426002860069275
2023-01-22 10:16:42.502116: step: 302/466, loss: 0.6514154672622681
2023-01-22 10:16:43.197499: step: 304/466, loss: 0.2610836327075958
2023-01-22 10:16:43.979952: step: 306/466, loss: 0.43020790815353394
2023-01-22 10:16:44.582239: step: 308/466, loss: 0.16784794628620148
2023-01-22 10:16:45.224079: step: 310/466, loss: 0.5591654777526855
2023-01-22 10:16:45.844282: step: 312/466, loss: 0.4326792359352112
2023-01-22 10:16:46.461654: step: 314/466, loss: 0.2679749131202698
2023-01-22 10:16:47.081117: step: 316/466, loss: 0.8848189115524292
2023-01-22 10:16:47.665125: step: 318/466, loss: 1.574328899383545
2023-01-22 10:16:48.286117: step: 320/466, loss: 0.28649765253067017
2023-01-22 10:16:48.899616: step: 322/466, loss: 0.7625613808631897
2023-01-22 10:16:49.468621: step: 324/466, loss: 0.26245927810668945
2023-01-22 10:16:50.104193: step: 326/466, loss: 0.6206868886947632
2023-01-22 10:16:50.738879: step: 328/466, loss: 0.3276185691356659
2023-01-22 10:16:51.281972: step: 330/466, loss: 0.5720335245132446
2023-01-22 10:16:51.884073: step: 332/466, loss: 0.5923988819122314
2023-01-22 10:16:52.532637: step: 334/466, loss: 0.7126914858818054
2023-01-22 10:16:53.143568: step: 336/466, loss: 0.10740337520837784
2023-01-22 10:16:53.719648: step: 338/466, loss: 1.55208158493042
2023-01-22 10:16:54.437704: step: 340/466, loss: 0.47114670276641846
2023-01-22 10:16:55.048281: step: 342/466, loss: 0.34138184785842896
2023-01-22 10:16:55.626233: step: 344/466, loss: 0.8074330687522888
2023-01-22 10:16:56.251517: step: 346/466, loss: 0.24854327738285065
2023-01-22 10:16:56.881365: step: 348/466, loss: 0.2922949492931366
2023-01-22 10:16:57.524766: step: 350/466, loss: 0.2991713881492615
2023-01-22 10:16:58.160198: step: 352/466, loss: 0.21093149483203888
2023-01-22 10:16:58.881572: step: 354/466, loss: 0.19404518604278564
2023-01-22 10:16:59.502651: step: 356/466, loss: 0.6495528817176819
2023-01-22 10:17:00.228137: step: 358/466, loss: 0.9190727472305298
2023-01-22 10:17:00.832932: step: 360/466, loss: 0.4907245337963104
2023-01-22 10:17:01.508399: step: 362/466, loss: 1.6439244747161865
2023-01-22 10:17:02.151261: step: 364/466, loss: 0.8146404027938843
2023-01-22 10:17:02.760608: step: 366/466, loss: 0.2428710162639618
2023-01-22 10:17:03.334779: step: 368/466, loss: 0.2377680093050003
2023-01-22 10:17:03.976056: step: 370/466, loss: 0.24059906601905823
2023-01-22 10:17:04.663666: step: 372/466, loss: 0.218387633562088
2023-01-22 10:17:05.339991: step: 374/466, loss: 0.36093229055404663
2023-01-22 10:17:05.966725: step: 376/466, loss: 0.7442221641540527
2023-01-22 10:17:06.592392: step: 378/466, loss: 0.22716902196407318
2023-01-22 10:17:07.252382: step: 380/466, loss: 0.7637770175933838
2023-01-22 10:17:07.863758: step: 382/466, loss: 0.2453354448080063
2023-01-22 10:17:08.513231: step: 384/466, loss: 0.43727368116378784
2023-01-22 10:17:09.162753: step: 386/466, loss: 1.6836223602294922
2023-01-22 10:17:09.788429: step: 388/466, loss: 0.28373491764068604
2023-01-22 10:17:10.398845: step: 390/466, loss: 2.0264334678649902
2023-01-22 10:17:11.070927: step: 392/466, loss: 0.448641836643219
2023-01-22 10:17:11.705600: step: 394/466, loss: 1.5419176816940308
2023-01-22 10:17:12.367075: step: 396/466, loss: 0.6299686431884766
2023-01-22 10:17:12.963208: step: 398/466, loss: 1.0106375217437744
2023-01-22 10:17:13.568683: step: 400/466, loss: 0.420911967754364
2023-01-22 10:17:14.217787: step: 402/466, loss: 0.6072839498519897
2023-01-22 10:17:14.792829: step: 404/466, loss: 0.8522168397903442
2023-01-22 10:17:15.455228: step: 406/466, loss: 0.09603744745254517
2023-01-22 10:17:16.062048: step: 408/466, loss: 0.19519944489002228
2023-01-22 10:17:16.642356: step: 410/466, loss: 0.3113097846508026
2023-01-22 10:17:17.220722: step: 412/466, loss: 0.4202454090118408
2023-01-22 10:17:17.822921: step: 414/466, loss: 0.6679733395576477
2023-01-22 10:17:18.413574: step: 416/466, loss: 0.25027406215667725
2023-01-22 10:17:19.003866: step: 418/466, loss: 0.5896903276443481
2023-01-22 10:17:19.598293: step: 420/466, loss: 0.16288059949874878
2023-01-22 10:17:20.195191: step: 422/466, loss: 0.2254132181406021
2023-01-22 10:17:20.895507: step: 424/466, loss: 0.8087993264198303
2023-01-22 10:17:21.496614: step: 426/466, loss: 0.38509637117385864
2023-01-22 10:17:22.199355: step: 428/466, loss: 0.8836284875869751
2023-01-22 10:17:22.800597: step: 430/466, loss: 0.32001492381095886
2023-01-22 10:17:23.406701: step: 432/466, loss: 0.6224542260169983
2023-01-22 10:17:23.983692: step: 434/466, loss: 0.3766172528266907
2023-01-22 10:17:24.658985: step: 436/466, loss: 0.5045154094696045
2023-01-22 10:17:25.278560: step: 438/466, loss: 5.073431968688965
2023-01-22 10:17:25.919493: step: 440/466, loss: 0.3151794970035553
2023-01-22 10:17:26.518485: step: 442/466, loss: 0.426649272441864
2023-01-22 10:17:27.092141: step: 444/466, loss: 0.24568483233451843
2023-01-22 10:17:27.730440: step: 446/466, loss: 0.09146913141012192
2023-01-22 10:17:28.350329: step: 448/466, loss: 1.8122892379760742
2023-01-22 10:17:28.979809: step: 450/466, loss: 0.5065184831619263
2023-01-22 10:17:29.652219: step: 452/466, loss: 0.8282049894332886
2023-01-22 10:17:30.324524: step: 454/466, loss: 0.7290765643119812
2023-01-22 10:17:30.963469: step: 456/466, loss: 0.3378812074661255
2023-01-22 10:17:31.609068: step: 458/466, loss: 0.40172505378723145
2023-01-22 10:17:32.232516: step: 460/466, loss: 0.2633054554462433
2023-01-22 10:17:32.870574: step: 462/466, loss: 0.16881847381591797
2023-01-22 10:17:33.498122: step: 464/466, loss: 0.3000826835632324
2023-01-22 10:17:34.073348: step: 466/466, loss: 1.2336972951889038
2023-01-22 10:17:34.665585: step: 468/466, loss: 0.27715569734573364
2023-01-22 10:17:35.283545: step: 470/466, loss: 0.16088084876537323
2023-01-22 10:17:35.941324: step: 472/466, loss: 0.6458614468574524
2023-01-22 10:17:36.526519: step: 474/466, loss: 0.5212080478668213
2023-01-22 10:17:37.138918: step: 476/466, loss: 0.894993007183075
2023-01-22 10:17:37.782599: step: 478/466, loss: 1.0347660779953003
2023-01-22 10:17:38.614656: step: 480/466, loss: 1.368758201599121
2023-01-22 10:17:39.202876: step: 482/466, loss: 0.9775394201278687
2023-01-22 10:17:39.866697: step: 484/466, loss: 0.9914467930793762
2023-01-22 10:17:40.526802: step: 486/466, loss: 0.5039624571800232
2023-01-22 10:17:41.181041: step: 488/466, loss: 0.43688344955444336
2023-01-22 10:17:41.834551: step: 490/466, loss: 0.3364666998386383
2023-01-22 10:17:42.534784: step: 492/466, loss: 1.1753532886505127
2023-01-22 10:17:43.144665: step: 494/466, loss: 0.9748474955558777
2023-01-22 10:17:43.723820: step: 496/466, loss: 1.6335086822509766
2023-01-22 10:17:44.336122: step: 498/466, loss: 0.22400739789009094
2023-01-22 10:17:44.981053: step: 500/466, loss: 0.31947603821754456
2023-01-22 10:17:45.602534: step: 502/466, loss: 0.6949931979179382
2023-01-22 10:17:46.175513: step: 504/466, loss: 0.3621494472026825
2023-01-22 10:17:46.813971: step: 506/466, loss: 0.24993956089019775
2023-01-22 10:17:47.408704: step: 508/466, loss: 0.35971206426620483
2023-01-22 10:17:48.089950: step: 510/466, loss: 1.8766340017318726
2023-01-22 10:17:48.690686: step: 512/466, loss: 0.4962426424026489
2023-01-22 10:17:49.340630: step: 514/466, loss: 0.6077012419700623
2023-01-22 10:17:49.934045: step: 516/466, loss: 0.6568211317062378
2023-01-22 10:17:50.496558: step: 518/466, loss: 0.7788378000259399
2023-01-22 10:17:51.162850: step: 520/466, loss: 1.1048991680145264
2023-01-22 10:17:51.769382: step: 522/466, loss: 0.23610150814056396
2023-01-22 10:17:52.384065: step: 524/466, loss: 3.0489180088043213
2023-01-22 10:17:53.029818: step: 526/466, loss: 0.9111219048500061
2023-01-22 10:17:53.787174: step: 528/466, loss: 0.3445698618888855
2023-01-22 10:17:54.413021: step: 530/466, loss: 0.6594105362892151
2023-01-22 10:17:55.006531: step: 532/466, loss: 0.28699102997779846
2023-01-22 10:17:55.620682: step: 534/466, loss: 1.6701980829238892
2023-01-22 10:17:56.189334: step: 536/466, loss: 0.227378711104393
2023-01-22 10:17:56.802837: step: 538/466, loss: 0.6038797497749329
2023-01-22 10:17:57.402870: step: 540/466, loss: 1.1404021978378296
2023-01-22 10:17:58.010937: step: 542/466, loss: 1.1455515623092651
2023-01-22 10:17:58.624506: step: 544/466, loss: 1.6472821235656738
2023-01-22 10:17:59.282709: step: 546/466, loss: 0.8400754332542419
2023-01-22 10:17:59.900135: step: 548/466, loss: 0.5330002307891846
2023-01-22 10:18:00.465840: step: 550/466, loss: 1.4000282287597656
2023-01-22 10:18:01.064228: step: 552/466, loss: 0.5982736945152283
2023-01-22 10:18:01.760869: step: 554/466, loss: 0.345943808555603
2023-01-22 10:18:02.412798: step: 556/466, loss: 0.5705140233039856
2023-01-22 10:18:03.016870: step: 558/466, loss: 0.2651577591896057
2023-01-22 10:18:03.669759: step: 560/466, loss: 0.22759249806404114
2023-01-22 10:18:04.314121: step: 562/466, loss: 0.59922194480896
2023-01-22 10:18:04.937455: step: 564/466, loss: 1.2552974224090576
2023-01-22 10:18:05.598992: step: 566/466, loss: 0.19052596390247345
2023-01-22 10:18:06.231776: step: 568/466, loss: 1.6358355283737183
2023-01-22 10:18:06.845144: step: 570/466, loss: 0.7840304970741272
2023-01-22 10:18:07.509822: step: 572/466, loss: 0.6998308897018433
2023-01-22 10:18:08.065246: step: 574/466, loss: 0.5584572553634644
2023-01-22 10:18:08.709733: step: 576/466, loss: 0.4735950231552124
2023-01-22 10:18:09.295466: step: 578/466, loss: 4.024959564208984
2023-01-22 10:18:09.958686: step: 580/466, loss: 3.8568780422210693
2023-01-22 10:18:10.573425: step: 582/466, loss: 0.5000805854797363
2023-01-22 10:18:11.146948: step: 584/466, loss: 0.7963584065437317
2023-01-22 10:18:11.755020: step: 586/466, loss: 0.4287252426147461
2023-01-22 10:18:12.437936: step: 588/466, loss: 0.19504182040691376
2023-01-22 10:18:13.125597: step: 590/466, loss: 0.6054005026817322
2023-01-22 10:18:13.736123: step: 592/466, loss: 1.4158061742782593
2023-01-22 10:18:14.336861: step: 594/466, loss: 0.7032748460769653
2023-01-22 10:18:15.026564: step: 596/466, loss: 0.3883163332939148
2023-01-22 10:18:15.678207: step: 598/466, loss: 0.25828832387924194
2023-01-22 10:18:16.298270: step: 600/466, loss: 1.2799416780471802
2023-01-22 10:18:16.895080: step: 602/466, loss: 1.442213535308838
2023-01-22 10:18:17.558517: step: 604/466, loss: 0.40329328179359436
2023-01-22 10:18:18.166916: step: 606/466, loss: 0.14056351780891418
2023-01-22 10:18:18.811240: step: 608/466, loss: 0.1742161363363266
2023-01-22 10:18:19.357127: step: 610/466, loss: 0.31428566575050354
2023-01-22 10:18:19.970740: step: 612/466, loss: 5.002796173095703
2023-01-22 10:18:20.570196: step: 614/466, loss: 0.3916827440261841
2023-01-22 10:18:21.175580: step: 616/466, loss: 0.27184417843818665
2023-01-22 10:18:21.806228: step: 618/466, loss: 0.2802789807319641
2023-01-22 10:18:22.441775: step: 620/466, loss: 0.2814117670059204
2023-01-22 10:18:23.003933: step: 622/466, loss: 0.8114979267120361
2023-01-22 10:18:23.610524: step: 624/466, loss: 3.3512256145477295
2023-01-22 10:18:24.261165: step: 626/466, loss: 0.41930854320526123
2023-01-22 10:18:24.866565: step: 628/466, loss: 0.41478148102760315
2023-01-22 10:18:25.471487: step: 630/466, loss: 0.8603408336639404
2023-01-22 10:18:26.182189: step: 632/466, loss: 0.34210678935050964
2023-01-22 10:18:26.853011: step: 634/466, loss: 0.8705849051475525
2023-01-22 10:18:27.411843: step: 636/466, loss: 0.7041741013526917
2023-01-22 10:18:28.029583: step: 638/466, loss: 1.4362998008728027
2023-01-22 10:18:28.627085: step: 640/466, loss: 0.1915927529335022
2023-01-22 10:18:29.197594: step: 642/466, loss: 0.20950928330421448
2023-01-22 10:18:29.811411: step: 644/466, loss: 0.3953920602798462
2023-01-22 10:18:30.382717: step: 646/466, loss: 0.4086073637008667
2023-01-22 10:18:30.979180: step: 648/466, loss: 0.9524459838867188
2023-01-22 10:18:31.619986: step: 650/466, loss: 0.17150622606277466
2023-01-22 10:18:32.269049: step: 652/466, loss: 0.5794564485549927
2023-01-22 10:18:32.869568: step: 654/466, loss: 0.6404372453689575
2023-01-22 10:18:33.507205: step: 656/466, loss: 0.9542464017868042
2023-01-22 10:18:34.128128: step: 658/466, loss: 0.5697581171989441
2023-01-22 10:18:34.700054: step: 660/466, loss: 0.5123308300971985
2023-01-22 10:18:35.315412: step: 662/466, loss: 0.3932381868362427
2023-01-22 10:18:35.939672: step: 664/466, loss: 0.37858468294143677
2023-01-22 10:18:36.574752: step: 666/466, loss: 0.9859458208084106
2023-01-22 10:18:37.288347: step: 668/466, loss: 0.22349879145622253
2023-01-22 10:18:37.970539: step: 670/466, loss: 0.5277111530303955
2023-01-22 10:18:38.655538: step: 672/466, loss: 1.1844608783721924
2023-01-22 10:18:39.289154: step: 674/466, loss: 0.284910649061203
2023-01-22 10:18:39.998628: step: 676/466, loss: 0.6260483860969543
2023-01-22 10:18:40.616293: step: 678/466, loss: 0.1024300828576088
2023-01-22 10:18:41.325074: step: 680/466, loss: 0.19412025809288025
2023-01-22 10:18:41.932739: step: 682/466, loss: 0.19316069781780243
2023-01-22 10:18:42.534029: step: 684/466, loss: 0.3085916340351105
2023-01-22 10:18:43.191416: step: 686/466, loss: 0.31294581294059753
2023-01-22 10:18:43.894377: step: 688/466, loss: 5.219769477844238
2023-01-22 10:18:44.512269: step: 690/466, loss: 0.398385226726532
2023-01-22 10:18:45.150488: step: 692/466, loss: 0.7441683411598206
2023-01-22 10:18:45.770824: step: 694/466, loss: 0.45424970984458923
2023-01-22 10:18:46.449031: step: 696/466, loss: 0.5073054432868958
2023-01-22 10:18:47.050586: step: 698/466, loss: 1.23970365524292
2023-01-22 10:18:47.674712: step: 700/466, loss: 0.26997852325439453
2023-01-22 10:18:48.290384: step: 702/466, loss: 0.30107223987579346
2023-01-22 10:18:48.908527: step: 704/466, loss: 1.047650933265686
2023-01-22 10:18:49.507893: step: 706/466, loss: 1.2337769269943237
2023-01-22 10:18:50.114488: step: 708/466, loss: 0.1382889598608017
2023-01-22 10:18:50.796007: step: 710/466, loss: 0.5219071507453918
2023-01-22 10:18:51.420931: step: 712/466, loss: 0.8577562570571899
2023-01-22 10:18:51.974691: step: 714/466, loss: 2.7157881259918213
2023-01-22 10:18:52.616792: step: 716/466, loss: 1.589961290359497
2023-01-22 10:18:53.179161: step: 718/466, loss: 0.7895178198814392
2023-01-22 10:18:53.852223: step: 720/466, loss: 0.4477238655090332
2023-01-22 10:18:54.442634: step: 722/466, loss: 0.2571891248226166
2023-01-22 10:18:55.084073: step: 724/466, loss: 1.1215697526931763
2023-01-22 10:18:55.710476: step: 726/466, loss: 0.6022098660469055
2023-01-22 10:18:56.375631: step: 728/466, loss: 0.8486770391464233
2023-01-22 10:18:57.013885: step: 730/466, loss: 1.3985038995742798
2023-01-22 10:18:57.643470: step: 732/466, loss: 0.5383131504058838
2023-01-22 10:18:58.354709: step: 734/466, loss: 1.4918358325958252
2023-01-22 10:18:59.056853: step: 736/466, loss: 2.111380100250244
2023-01-22 10:18:59.644347: step: 738/466, loss: 0.23163145780563354
2023-01-22 10:19:00.314030: step: 740/466, loss: 1.5169225931167603
2023-01-22 10:19:01.017508: step: 742/466, loss: 0.9196684956550598
2023-01-22 10:19:01.637760: step: 744/466, loss: 1.2737724781036377
2023-01-22 10:19:02.271895: step: 746/466, loss: 0.5097503662109375
2023-01-22 10:19:02.817745: step: 748/466, loss: 0.37727874517440796
2023-01-22 10:19:03.424986: step: 750/466, loss: 0.6758705973625183
2023-01-22 10:19:04.026073: step: 752/466, loss: 0.6611981987953186
2023-01-22 10:19:04.695479: step: 754/466, loss: 0.43644487857818604
2023-01-22 10:19:05.273321: step: 756/466, loss: 1.3894761800765991
2023-01-22 10:19:05.884106: step: 758/466, loss: 0.591181218624115
2023-01-22 10:19:06.624073: step: 760/466, loss: 0.5741158127784729
2023-01-22 10:19:07.245592: step: 762/466, loss: 0.40604686737060547
2023-01-22 10:19:07.870595: step: 764/466, loss: 0.26860132813453674
2023-01-22 10:19:08.485311: step: 766/466, loss: 0.797225832939148
2023-01-22 10:19:09.097769: step: 768/466, loss: 1.1374201774597168
2023-01-22 10:19:09.761036: step: 770/466, loss: 0.7190713882446289
2023-01-22 10:19:10.412765: step: 772/466, loss: 0.26857054233551025
2023-01-22 10:19:11.023484: step: 774/466, loss: 0.5708498358726501
2023-01-22 10:19:11.612183: step: 776/466, loss: 0.14177720248699188
2023-01-22 10:19:12.215208: step: 778/466, loss: 0.42916902899742126
2023-01-22 10:19:12.832091: step: 780/466, loss: 0.49903401732444763
2023-01-22 10:19:13.440529: step: 782/466, loss: 0.45851343870162964
2023-01-22 10:19:14.066947: step: 784/466, loss: 0.22907648980617523
2023-01-22 10:19:14.711818: step: 786/466, loss: 1.1436830759048462
2023-01-22 10:19:15.330772: step: 788/466, loss: 0.5820797681808472
2023-01-22 10:19:16.059655: step: 790/466, loss: 2.55900502204895
2023-01-22 10:19:16.702501: step: 792/466, loss: 0.19003260135650635
2023-01-22 10:19:17.272118: step: 794/466, loss: 1.064763069152832
2023-01-22 10:19:17.940553: step: 796/466, loss: 1.7375653982162476
2023-01-22 10:19:18.495422: step: 798/466, loss: 0.31202900409698486
2023-01-22 10:19:19.122828: step: 800/466, loss: 0.576053261756897
2023-01-22 10:19:19.780975: step: 802/466, loss: 0.4688360095024109
2023-01-22 10:19:20.393895: step: 804/466, loss: 0.24730272591114044
2023-01-22 10:19:20.983986: step: 806/466, loss: 0.44804060459136963
2023-01-22 10:19:21.583815: step: 808/466, loss: 1.33967125415802
2023-01-22 10:19:22.284969: step: 810/466, loss: 8.95032024383545
2023-01-22 10:19:22.882539: step: 812/466, loss: 0.2827244699001312
2023-01-22 10:19:23.516748: step: 814/466, loss: 0.24904581904411316
2023-01-22 10:19:24.154020: step: 816/466, loss: 0.947492778301239
2023-01-22 10:19:24.748461: step: 818/466, loss: 0.24781152606010437
2023-01-22 10:19:25.329281: step: 820/466, loss: 0.4108606278896332
2023-01-22 10:19:26.026302: step: 822/466, loss: 0.0980253517627716
2023-01-22 10:19:26.627881: step: 824/466, loss: 0.6137410402297974
2023-01-22 10:19:27.221138: step: 826/466, loss: 2.0315511226654053
2023-01-22 10:19:27.828908: step: 828/466, loss: 0.8632413148880005
2023-01-22 10:19:28.524795: step: 830/466, loss: 0.3644121289253235
2023-01-22 10:19:29.210653: step: 832/466, loss: 0.39598798751831055
2023-01-22 10:19:29.806374: step: 834/466, loss: 0.6666589975357056
2023-01-22 10:19:30.404930: step: 836/466, loss: 4.266134262084961
2023-01-22 10:19:31.040802: step: 838/466, loss: 1.6588128805160522
2023-01-22 10:19:31.660119: step: 840/466, loss: 0.3272869884967804
2023-01-22 10:19:32.249288: step: 842/466, loss: 0.38514748215675354
2023-01-22 10:19:32.812785: step: 844/466, loss: 0.38480067253112793
2023-01-22 10:19:33.436361: step: 846/466, loss: 0.490105003118515
2023-01-22 10:19:34.050809: step: 848/466, loss: 2.017117500305176
2023-01-22 10:19:34.724564: step: 850/466, loss: 0.6285754442214966
2023-01-22 10:19:35.346808: step: 852/466, loss: 0.516296923160553
2023-01-22 10:19:35.938753: step: 854/466, loss: 0.4578474760055542
2023-01-22 10:19:36.510839: step: 856/466, loss: 0.76552814245224
2023-01-22 10:19:37.145408: step: 858/466, loss: 0.884811520576477
2023-01-22 10:19:37.735393: step: 860/466, loss: 0.34015825390815735
2023-01-22 10:19:38.393130: step: 862/466, loss: 0.2531778812408447
2023-01-22 10:19:39.031078: step: 864/466, loss: 0.1724013090133667
2023-01-22 10:19:39.653131: step: 866/466, loss: 0.5326557755470276
2023-01-22 10:19:40.282682: step: 868/466, loss: 1.0472228527069092
2023-01-22 10:19:40.904429: step: 870/466, loss: 1.7959599494934082
2023-01-22 10:19:41.547827: step: 872/466, loss: 0.6444715857505798
2023-01-22 10:19:42.271360: step: 874/466, loss: 0.26546746492385864
2023-01-22 10:19:42.856360: step: 876/466, loss: 0.48505330085754395
2023-01-22 10:19:43.469839: step: 878/466, loss: 1.3470640182495117
2023-01-22 10:19:44.099249: step: 880/466, loss: 1.7580037117004395
2023-01-22 10:19:44.700268: step: 882/466, loss: 0.28422167897224426
2023-01-22 10:19:45.289039: step: 884/466, loss: 0.5739858746528625
2023-01-22 10:19:45.961795: step: 886/466, loss: 1.6449081897735596
2023-01-22 10:19:46.621652: step: 888/466, loss: 0.3343558609485626
2023-01-22 10:19:47.245366: step: 890/466, loss: 0.4418397545814514
2023-01-22 10:19:47.895850: step: 892/466, loss: 0.8011448979377747
2023-01-22 10:19:48.479042: step: 894/466, loss: 0.329490065574646
2023-01-22 10:19:49.165505: step: 896/466, loss: 0.8715149164199829
2023-01-22 10:19:49.765911: step: 898/466, loss: 3.0846753120422363
2023-01-22 10:19:50.366904: step: 900/466, loss: 0.9813827276229858
2023-01-22 10:19:50.956872: step: 902/466, loss: 0.4854777753353119
2023-01-22 10:19:51.619655: step: 904/466, loss: 0.42504075169563293
2023-01-22 10:19:52.210602: step: 906/466, loss: 1.4318958520889282
2023-01-22 10:19:52.838202: step: 908/466, loss: 0.6176507472991943
2023-01-22 10:19:53.472074: step: 910/466, loss: 0.8056727647781372
2023-01-22 10:19:54.065451: step: 912/466, loss: 0.29409268498420715
2023-01-22 10:19:54.635557: step: 914/466, loss: 0.285684198141098
2023-01-22 10:19:55.317992: step: 916/466, loss: 0.5347999930381775
2023-01-22 10:19:55.921425: step: 918/466, loss: 0.6455689072608948
2023-01-22 10:19:56.617992: step: 920/466, loss: 0.2150963693857193
2023-01-22 10:19:57.278657: step: 922/466, loss: 0.9827973246574402
2023-01-22 10:19:57.849607: step: 924/466, loss: 0.4846271574497223
2023-01-22 10:19:58.465532: step: 926/466, loss: 1.0096116065979004
2023-01-22 10:19:59.055174: step: 928/466, loss: 0.7601162195205688
2023-01-22 10:19:59.690489: step: 930/466, loss: 0.5822792649269104
2023-01-22 10:20:00.425409: step: 932/466, loss: 0.4887627959251404
==================================================
Loss: 0.795
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2974311495835157, 'r': 0.2754201157433694, 'f1': 0.28600276058474017}, 'combined': 0.21073887622033485, 'epoch': 6}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.29478717326167986, 'r': 0.25495106876685825, 'f1': 0.2734257838948914}, 'combined': 0.17121053757904417, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29598244032745535, 'r': 0.29317425778165407, 'f1': 0.29457165653180495}, 'combined': 0.217052799549751, 'epoch': 6}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3040888340368659, 'r': 0.2610392876493204, 'f1': 0.2809243765192589}, 'combined': 0.17409397981475197, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27662005991315347, 'r': 0.2965660983888647, 'f1': 0.28624603269401416}, 'combined': 0.2109181293534841, 'epoch': 6}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.32947175762669556, 'r': 0.2646478919564612, 'f1': 0.29352338767543446}, 'combined': 0.19471353439855554, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2611111111111111, 'r': 0.3357142857142857, 'f1': 0.29375}, 'combined': 0.19583333333333333, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27586206896551724, 'r': 0.34782608695652173, 'f1': 0.3076923076923077}, 'combined': 0.15384615384615385, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.359375, 'r': 0.19827586206896552, 'f1': 0.2555555555555556}, 'combined': 0.1703703703703704, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3125951086956522, 'r': 0.2728534155597723, 'f1': 0.2913753799392097}, 'combined': 0.21469764837625976, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32426953156573873, 'r': 0.23676358396812514, 'f1': 0.27369228068511486}, 'combined': 0.1713774094009598, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3157894736842105, 'r': 0.34285714285714286, 'f1': 0.3287671232876712}, 'combined': 0.2191780821917808, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3029132443531828, 'r': 0.27992172675521826, 'f1': 0.2909640039447732}, 'combined': 0.21439452922246444, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3324774795250554, 'r': 0.24343707247461224, 'f1': 0.28107414198266006}, 'combined': 0.17418679221460623, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4027777777777778, 'r': 0.31521739130434784, 'f1': 0.3536585365853659}, 'combined': 0.17682926829268295, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2870113455833512, 'r': 0.27611907440371736, 'f1': 0.2814598688796113}, 'combined': 0.20739148233234514, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3582228395089435, 'r': 0.2388152263392957, 'f1': 0.28657827160715477}, 'combined': 0.19010637819484524, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4117647058823529, 'r': 0.2413793103448276, 'f1': 0.3043478260869565}, 'combined': 0.20289855072463764, 'epoch': 5}
******************************
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 10:22:37.225731: step: 2/466, loss: 0.9606571793556213
2023-01-22 10:22:37.769646: step: 4/466, loss: 0.3612016439437866
2023-01-22 10:22:38.441545: step: 6/466, loss: 0.9253258109092712
2023-01-22 10:22:39.092199: step: 8/466, loss: 0.4830124080181122
2023-01-22 10:22:39.740661: step: 10/466, loss: 0.38346290588378906
2023-01-22 10:22:40.344736: step: 12/466, loss: 0.8057071566581726
2023-01-22 10:22:40.998052: step: 14/466, loss: 0.3059096038341522
2023-01-22 10:22:41.737950: step: 16/466, loss: 0.22083964943885803
2023-01-22 10:22:42.354531: step: 18/466, loss: 0.30529630184173584
2023-01-22 10:22:43.035087: step: 20/466, loss: 0.5498822927474976
2023-01-22 10:22:43.642001: step: 22/466, loss: 1.5517122745513916
2023-01-22 10:22:44.302915: step: 24/466, loss: 0.7829954624176025
2023-01-22 10:22:44.866666: step: 26/466, loss: 0.20105233788490295
2023-01-22 10:22:45.506209: step: 28/466, loss: 0.6444220542907715
2023-01-22 10:22:46.127778: step: 30/466, loss: 1.7132608890533447
2023-01-22 10:22:46.729791: step: 32/466, loss: 0.9501598477363586
2023-01-22 10:22:47.339910: step: 34/466, loss: 0.34672775864601135
2023-01-22 10:22:47.950710: step: 36/466, loss: 0.5987630486488342
2023-01-22 10:22:48.582431: step: 38/466, loss: 0.2633925676345825
2023-01-22 10:22:49.165792: step: 40/466, loss: 1.5883678197860718
2023-01-22 10:22:49.801365: step: 42/466, loss: 0.2523646950721741
2023-01-22 10:22:50.448540: step: 44/466, loss: 0.32839834690093994
2023-01-22 10:22:51.018856: step: 46/466, loss: 0.4045436978340149
2023-01-22 10:22:51.623257: step: 48/466, loss: 0.4517868757247925
2023-01-22 10:22:52.295627: step: 50/466, loss: 0.22546136379241943
2023-01-22 10:22:52.962893: step: 52/466, loss: 0.23036596179008484
2023-01-22 10:22:53.548411: step: 54/466, loss: 0.28984159231185913
2023-01-22 10:22:54.155489: step: 56/466, loss: 0.4410346746444702
2023-01-22 10:22:54.835942: step: 58/466, loss: 0.21367600560188293
2023-01-22 10:22:55.460666: step: 60/466, loss: 0.35458019375801086
2023-01-22 10:22:56.085417: step: 62/466, loss: 0.17024670541286469
2023-01-22 10:22:56.730135: step: 64/466, loss: 0.14700041711330414
2023-01-22 10:22:57.396161: step: 66/466, loss: 0.5288400650024414
2023-01-22 10:22:58.054228: step: 68/466, loss: 0.13167166709899902
2023-01-22 10:22:58.704143: step: 70/466, loss: 0.6722766757011414
2023-01-22 10:22:59.321532: step: 72/466, loss: 0.1936565488576889
2023-01-22 10:22:59.971888: step: 74/466, loss: 0.46509358286857605
2023-01-22 10:23:00.552131: step: 76/466, loss: 0.4784170687198639
2023-01-22 10:23:01.196276: step: 78/466, loss: 0.36129406094551086
2023-01-22 10:23:01.834469: step: 80/466, loss: 3.51059889793396
2023-01-22 10:23:02.447553: step: 82/466, loss: 0.17317715287208557
2023-01-22 10:23:03.092519: step: 84/466, loss: 0.9708307385444641
2023-01-22 10:23:03.740056: step: 86/466, loss: 0.8890564441680908
2023-01-22 10:23:04.347139: step: 88/466, loss: 0.5933763384819031
2023-01-22 10:23:04.955837: step: 90/466, loss: 0.30360448360443115
2023-01-22 10:23:05.529198: step: 92/466, loss: 0.5512064099311829
2023-01-22 10:23:06.157454: step: 94/466, loss: 0.4373668432235718
2023-01-22 10:23:06.737255: step: 96/466, loss: 0.35091495513916016
2023-01-22 10:23:07.416918: step: 98/466, loss: 0.7135890126228333
2023-01-22 10:23:08.119252: step: 100/466, loss: 0.702728807926178
2023-01-22 10:23:08.802875: step: 102/466, loss: 0.22279851138591766
2023-01-22 10:23:09.444491: step: 104/466, loss: 0.3196096420288086
2023-01-22 10:23:10.095700: step: 106/466, loss: 0.3496376574039459
2023-01-22 10:23:10.773552: step: 108/466, loss: 0.23381787538528442
2023-01-22 10:23:11.438097: step: 110/466, loss: 2.360985279083252
2023-01-22 10:23:12.087950: step: 112/466, loss: 0.6244679689407349
2023-01-22 10:23:12.741979: step: 114/466, loss: 0.6387752294540405
2023-01-22 10:23:13.348086: step: 116/466, loss: 0.29985910654067993
2023-01-22 10:23:13.961125: step: 118/466, loss: 0.37929147481918335
2023-01-22 10:23:14.651491: step: 120/466, loss: 0.7739306092262268
2023-01-22 10:23:15.305538: step: 122/466, loss: 0.7082308530807495
2023-01-22 10:23:15.870158: step: 124/466, loss: 0.3670591115951538
2023-01-22 10:23:16.533808: step: 126/466, loss: 0.5902093648910522
2023-01-22 10:23:17.181279: step: 128/466, loss: 0.7791361808776855
2023-01-22 10:23:17.892960: step: 130/466, loss: 0.19285088777542114
2023-01-22 10:23:18.506397: step: 132/466, loss: 0.35721462965011597
2023-01-22 10:23:19.105354: step: 134/466, loss: 0.3081234395503998
2023-01-22 10:23:19.789793: step: 136/466, loss: 0.3913836181163788
2023-01-22 10:23:20.394441: step: 138/466, loss: 0.31764063239097595
2023-01-22 10:23:21.024463: step: 140/466, loss: 0.17015546560287476
2023-01-22 10:23:21.701898: step: 142/466, loss: 0.49441781640052795
2023-01-22 10:23:22.328822: step: 144/466, loss: 0.2210272252559662
2023-01-22 10:23:23.035206: step: 146/466, loss: 0.4163098633289337
2023-01-22 10:23:23.609354: step: 148/466, loss: 0.9439469575881958
2023-01-22 10:23:24.250320: step: 150/466, loss: 0.7482032179832458
2023-01-22 10:23:24.823388: step: 152/466, loss: 0.2315014749765396
2023-01-22 10:23:25.453549: step: 154/466, loss: 0.477324903011322
2023-01-22 10:23:26.059434: step: 156/466, loss: 0.31996142864227295
2023-01-22 10:23:26.703672: step: 158/466, loss: 0.3227391839027405
2023-01-22 10:23:27.390872: step: 160/466, loss: 1.9098715782165527
2023-01-22 10:23:28.055053: step: 162/466, loss: 0.15192030370235443
2023-01-22 10:23:28.629909: step: 164/466, loss: 2.4227092266082764
2023-01-22 10:23:29.249658: step: 166/466, loss: 0.9149259924888611
2023-01-22 10:23:29.920409: step: 168/466, loss: 0.28424474596977234
2023-01-22 10:23:30.497678: step: 170/466, loss: 0.2596474289894104
2023-01-22 10:23:31.176653: step: 172/466, loss: 0.6030668020248413
2023-01-22 10:23:31.790884: step: 174/466, loss: 0.4024707078933716
2023-01-22 10:23:32.361913: step: 176/466, loss: 0.11528413742780685
2023-01-22 10:23:33.010966: step: 178/466, loss: 0.1654813587665558
2023-01-22 10:23:33.655511: step: 180/466, loss: 0.16900886595249176
2023-01-22 10:23:34.314699: step: 182/466, loss: 0.5156384110450745
2023-01-22 10:23:34.936321: step: 184/466, loss: 0.42618176341056824
2023-01-22 10:23:35.579617: step: 186/466, loss: 0.6345421671867371
2023-01-22 10:23:36.233989: step: 188/466, loss: 0.24912512302398682
2023-01-22 10:23:36.826382: step: 190/466, loss: 0.7710665464401245
2023-01-22 10:23:37.394719: step: 192/466, loss: 0.3259478509426117
2023-01-22 10:23:38.037791: step: 194/466, loss: 0.216398224234581
2023-01-22 10:23:38.647278: step: 196/466, loss: 0.8208011984825134
2023-01-22 10:23:39.267904: step: 198/466, loss: 0.5244461894035339
2023-01-22 10:23:39.923370: step: 200/466, loss: 0.6144452691078186
2023-01-22 10:23:40.600105: step: 202/466, loss: 0.22315502166748047
2023-01-22 10:23:41.227693: step: 204/466, loss: 0.42204487323760986
2023-01-22 10:23:41.872556: step: 206/466, loss: 0.7389995455741882
2023-01-22 10:23:42.483520: step: 208/466, loss: 0.18414448201656342
2023-01-22 10:23:43.088801: step: 210/466, loss: 0.8658441305160522
2023-01-22 10:23:43.715511: step: 212/466, loss: 0.41797181963920593
2023-01-22 10:23:44.414734: step: 214/466, loss: 0.9090080261230469
2023-01-22 10:23:45.029543: step: 216/466, loss: 0.5187643766403198
2023-01-22 10:23:45.634614: step: 218/466, loss: 0.7451024651527405
2023-01-22 10:23:46.242042: step: 220/466, loss: 0.49195000529289246
2023-01-22 10:23:46.894707: step: 222/466, loss: 0.18547570705413818
2023-01-22 10:23:47.564624: step: 224/466, loss: 0.1988060474395752
2023-01-22 10:23:48.173836: step: 226/466, loss: 0.508165180683136
2023-01-22 10:23:48.760351: step: 228/466, loss: 0.11084049940109253
2023-01-22 10:23:49.404583: step: 230/466, loss: 0.9763489961624146
2023-01-22 10:23:50.032702: step: 232/466, loss: 0.5351693630218506
2023-01-22 10:23:50.544051: step: 234/466, loss: 0.5538202524185181
2023-01-22 10:23:51.176344: step: 236/466, loss: 0.3254033327102661
2023-01-22 10:23:51.778898: step: 238/466, loss: 0.32077309489250183
2023-01-22 10:23:52.432946: step: 240/466, loss: 0.9185691475868225
2023-01-22 10:23:53.063546: step: 242/466, loss: 0.11787169426679611
2023-01-22 10:23:53.646658: step: 244/466, loss: 0.5049479007720947
2023-01-22 10:23:54.254510: step: 246/466, loss: 0.09478340297937393
2023-01-22 10:23:54.885389: step: 248/466, loss: 0.15972957015037537
2023-01-22 10:23:55.461941: step: 250/466, loss: 3.33953595161438
2023-01-22 10:23:56.107543: step: 252/466, loss: 0.14158812165260315
2023-01-22 10:23:56.754607: step: 254/466, loss: 0.4418643116950989
2023-01-22 10:23:57.420646: step: 256/466, loss: 0.5265594124794006
2023-01-22 10:23:58.110520: step: 258/466, loss: 0.2596603035926819
2023-01-22 10:23:58.729730: step: 260/466, loss: 0.5344682931900024
2023-01-22 10:23:59.332011: step: 262/466, loss: 0.20869165658950806
2023-01-22 10:24:00.006731: step: 264/466, loss: 0.4390193819999695
2023-01-22 10:24:00.651100: step: 266/466, loss: 0.8909998536109924
2023-01-22 10:24:01.268578: step: 268/466, loss: 0.7148413062095642
2023-01-22 10:24:01.888176: step: 270/466, loss: 0.8363057374954224
2023-01-22 10:24:02.499017: step: 272/466, loss: 0.5471477508544922
2023-01-22 10:24:03.100502: step: 274/466, loss: 0.2999334931373596
2023-01-22 10:24:03.715848: step: 276/466, loss: 0.45258891582489014
2023-01-22 10:24:04.327849: step: 278/466, loss: 0.33410534262657166
2023-01-22 10:24:04.984643: step: 280/466, loss: 0.46963629126548767
2023-01-22 10:24:05.592014: step: 282/466, loss: 1.2168225049972534
2023-01-22 10:24:06.151152: step: 284/466, loss: 0.06262262910604477
2023-01-22 10:24:06.862281: step: 286/466, loss: 0.4550589919090271
2023-01-22 10:24:07.498962: step: 288/466, loss: 0.15784329175949097
2023-01-22 10:24:08.103561: step: 290/466, loss: 0.9966462254524231
2023-01-22 10:24:08.761502: step: 292/466, loss: 0.4710371494293213
2023-01-22 10:24:09.405906: step: 294/466, loss: 1.3634792566299438
2023-01-22 10:24:10.035297: step: 296/466, loss: 0.45720961689949036
2023-01-22 10:24:10.638126: step: 298/466, loss: 0.48143327236175537
2023-01-22 10:24:11.320746: step: 300/466, loss: 1.4690943956375122
2023-01-22 10:24:11.937423: step: 302/466, loss: 0.18070606887340546
2023-01-22 10:24:12.631231: step: 304/466, loss: 1.0625159740447998
2023-01-22 10:24:13.271931: step: 306/466, loss: 0.3338050842285156
2023-01-22 10:24:13.897811: step: 308/466, loss: 0.21788737177848816
2023-01-22 10:24:14.558647: step: 310/466, loss: 0.28946834802627563
2023-01-22 10:24:15.211613: step: 312/466, loss: 1.5697287321090698
2023-01-22 10:24:15.787565: step: 314/466, loss: 0.3977658748626709
2023-01-22 10:24:16.402404: step: 316/466, loss: 0.4918626844882965
2023-01-22 10:24:17.079905: step: 318/466, loss: 0.24856841564178467
2023-01-22 10:24:17.701434: step: 320/466, loss: 2.086498737335205
2023-01-22 10:24:18.287897: step: 322/466, loss: 1.2578928470611572
2023-01-22 10:24:18.962821: step: 324/466, loss: 0.12625814974308014
2023-01-22 10:24:19.591425: step: 326/466, loss: 0.34538987278938293
2023-01-22 10:24:20.205841: step: 328/466, loss: 1.0326175689697266
2023-01-22 10:24:20.805700: step: 330/466, loss: 0.5270153880119324
2023-01-22 10:24:21.429858: step: 332/466, loss: 0.5706387758255005
2023-01-22 10:24:22.057291: step: 334/466, loss: 0.5501885414123535
2023-01-22 10:24:22.768899: step: 336/466, loss: 0.5912823677062988
2023-01-22 10:24:23.370253: step: 338/466, loss: 0.9064117670059204
2023-01-22 10:24:23.995609: step: 340/466, loss: 0.10313384234905243
2023-01-22 10:24:24.557788: step: 342/466, loss: 0.20501954853534698
2023-01-22 10:24:25.240878: step: 344/466, loss: 0.305141806602478
2023-01-22 10:24:25.840450: step: 346/466, loss: 0.3541070818901062
2023-01-22 10:24:26.446329: step: 348/466, loss: 0.17641820013523102
2023-01-22 10:24:27.100839: step: 350/466, loss: 0.8985726237297058
2023-01-22 10:24:27.735779: step: 352/466, loss: 0.6228352189064026
2023-01-22 10:24:28.393379: step: 354/466, loss: 1.645764946937561
2023-01-22 10:24:28.984228: step: 356/466, loss: 0.4667787253856659
2023-01-22 10:24:29.682906: step: 358/466, loss: 1.009447455406189
2023-01-22 10:24:30.394367: step: 360/466, loss: 0.27950695157051086
2023-01-22 10:24:31.049519: step: 362/466, loss: 3.32397198677063
2023-01-22 10:24:31.662104: step: 364/466, loss: 0.46399447321891785
2023-01-22 10:24:32.285792: step: 366/466, loss: 0.3752869665622711
2023-01-22 10:24:32.958481: step: 368/466, loss: 0.6119229793548584
2023-01-22 10:24:33.597452: step: 370/466, loss: 0.27729475498199463
2023-01-22 10:24:34.225939: step: 372/466, loss: 1.4170265197753906
2023-01-22 10:24:34.902563: step: 374/466, loss: 0.18623074889183044
2023-01-22 10:24:35.521820: step: 376/466, loss: 0.678354024887085
2023-01-22 10:24:36.169629: step: 378/466, loss: 0.7824224829673767
2023-01-22 10:24:36.794041: step: 380/466, loss: 0.24425385892391205
2023-01-22 10:24:37.585086: step: 382/466, loss: 0.6537637114524841
2023-01-22 10:24:38.220363: step: 384/466, loss: 0.6355273127555847
2023-01-22 10:24:38.941070: step: 386/466, loss: 2.3607473373413086
2023-01-22 10:24:39.574874: step: 388/466, loss: 0.7117860317230225
2023-01-22 10:24:40.117488: step: 390/466, loss: 1.5877604484558105
2023-01-22 10:24:40.769859: step: 392/466, loss: 0.25026875734329224
2023-01-22 10:24:41.361708: step: 394/466, loss: 0.9659414291381836
2023-01-22 10:24:41.977348: step: 396/466, loss: 0.8510382175445557
2023-01-22 10:24:42.630669: step: 398/466, loss: 0.23068997263908386
2023-01-22 10:24:43.285158: step: 400/466, loss: 0.14895950257778168
2023-01-22 10:24:43.860176: step: 402/466, loss: 0.511879563331604
2023-01-22 10:24:44.442826: step: 404/466, loss: 0.562067985534668
2023-01-22 10:24:45.082028: step: 406/466, loss: 0.6167904734611511
2023-01-22 10:24:45.740437: step: 408/466, loss: 0.29697105288505554
2023-01-22 10:24:46.310026: step: 410/466, loss: 0.7155808210372925
2023-01-22 10:24:46.937742: step: 412/466, loss: 0.27304062247276306
2023-01-22 10:24:47.551566: step: 414/466, loss: 0.17526191473007202
2023-01-22 10:24:48.202558: step: 416/466, loss: 0.31682494282722473
2023-01-22 10:24:48.794256: step: 418/466, loss: 0.45163649320602417
2023-01-22 10:24:49.464073: step: 420/466, loss: 1.0491752624511719
2023-01-22 10:24:50.150701: step: 422/466, loss: 1.2448574304580688
2023-01-22 10:24:50.773637: step: 424/466, loss: 0.12224073708057404
2023-01-22 10:24:51.427143: step: 426/466, loss: 0.35593071579933167
2023-01-22 10:24:52.066177: step: 428/466, loss: 0.5212833285331726
2023-01-22 10:24:52.618039: step: 430/466, loss: 0.19980010390281677
2023-01-22 10:24:53.193680: step: 432/466, loss: 0.3044664263725281
2023-01-22 10:24:53.848686: step: 434/466, loss: 0.39862319827079773
2023-01-22 10:24:54.433104: step: 436/466, loss: 0.41108438372612
2023-01-22 10:24:55.041795: step: 438/466, loss: 0.9988893866539001
2023-01-22 10:24:55.662886: step: 440/466, loss: 0.6291717886924744
2023-01-22 10:24:56.342798: step: 442/466, loss: 2.1317265033721924
2023-01-22 10:24:56.938102: step: 444/466, loss: 0.6207007169723511
2023-01-22 10:24:57.564419: step: 446/466, loss: 0.38326412439346313
2023-01-22 10:24:58.189940: step: 448/466, loss: 1.4615135192871094
2023-01-22 10:24:58.771982: step: 450/466, loss: 0.1804785281419754
2023-01-22 10:24:59.406555: step: 452/466, loss: 0.6153715252876282
2023-01-22 10:25:00.013370: step: 454/466, loss: 0.3203708529472351
2023-01-22 10:25:00.620418: step: 456/466, loss: 0.32922083139419556
2023-01-22 10:25:01.269595: step: 458/466, loss: 0.3243230879306793
2023-01-22 10:25:01.942855: step: 460/466, loss: 0.3458571434020996
2023-01-22 10:25:02.549679: step: 462/466, loss: 0.3195928931236267
2023-01-22 10:25:03.222918: step: 464/466, loss: 0.8329210877418518
2023-01-22 10:25:03.781245: step: 466/466, loss: 0.23395095765590668
2023-01-22 10:25:04.403701: step: 468/466, loss: 0.47280454635620117
2023-01-22 10:25:05.028234: step: 470/466, loss: 0.4958782494068146
2023-01-22 10:25:05.683351: step: 472/466, loss: 0.2251265048980713
2023-01-22 10:25:06.342519: step: 474/466, loss: 0.2383415699005127
2023-01-22 10:25:06.923376: step: 476/466, loss: 0.2788371741771698
2023-01-22 10:25:07.505563: step: 478/466, loss: 0.35121840238571167
2023-01-22 10:25:08.095697: step: 480/466, loss: 0.35221993923187256
2023-01-22 10:25:08.673690: step: 482/466, loss: 0.4240202009677887
2023-01-22 10:25:09.292375: step: 484/466, loss: 0.23571814596652985
2023-01-22 10:25:09.936644: step: 486/466, loss: 0.5392071008682251
2023-01-22 10:25:10.638190: step: 488/466, loss: 0.16577844321727753
2023-01-22 10:25:11.265945: step: 490/466, loss: 0.4230649769306183
2023-01-22 10:25:11.889835: step: 492/466, loss: 0.36499860882759094
2023-01-22 10:25:12.490424: step: 494/466, loss: 1.428270936012268
2023-01-22 10:25:13.127534: step: 496/466, loss: 0.21719515323638916
2023-01-22 10:25:13.764744: step: 498/466, loss: 0.9568606615066528
2023-01-22 10:25:14.328555: step: 500/466, loss: 3.720993995666504
2023-01-22 10:25:14.962738: step: 502/466, loss: 0.5529990792274475
2023-01-22 10:25:15.573722: step: 504/466, loss: 0.5724399089813232
2023-01-22 10:25:16.188925: step: 506/466, loss: 1.9884328842163086
2023-01-22 10:25:16.830501: step: 508/466, loss: 0.5034530162811279
2023-01-22 10:25:17.485501: step: 510/466, loss: 0.8145545721054077
2023-01-22 10:25:18.098395: step: 512/466, loss: 0.5394100546836853
2023-01-22 10:25:18.686145: step: 514/466, loss: 0.15192024409770966
2023-01-22 10:25:19.376661: step: 516/466, loss: 0.5822650194168091
2023-01-22 10:25:20.039892: step: 518/466, loss: 0.8212950825691223
2023-01-22 10:25:20.747170: step: 520/466, loss: 0.11858353763818741
2023-01-22 10:25:21.378278: step: 522/466, loss: 0.2861880362033844
2023-01-22 10:25:21.987552: step: 524/466, loss: 0.18946318328380585
2023-01-22 10:25:22.633072: step: 526/466, loss: 0.36098793148994446
2023-01-22 10:25:23.279264: step: 528/466, loss: 0.6966142654418945
2023-01-22 10:25:24.012132: step: 530/466, loss: 1.6891040802001953
2023-01-22 10:25:24.618347: step: 532/466, loss: 0.21906842291355133
2023-01-22 10:25:25.247024: step: 534/466, loss: 0.3703289330005646
2023-01-22 10:25:25.798716: step: 536/466, loss: 0.22129729390144348
2023-01-22 10:25:26.404858: step: 538/466, loss: 0.41192248463630676
2023-01-22 10:25:27.010432: step: 540/466, loss: 0.44342806935310364
2023-01-22 10:25:27.611190: step: 542/466, loss: 1.316843032836914
2023-01-22 10:25:28.186122: step: 544/466, loss: 0.2924029231071472
2023-01-22 10:25:28.821530: step: 546/466, loss: 0.31457072496414185
2023-01-22 10:25:29.406251: step: 548/466, loss: 0.209502175450325
2023-01-22 10:25:30.009682: step: 550/466, loss: 0.3837663531303406
2023-01-22 10:25:30.642792: step: 552/466, loss: 0.2353142350912094
2023-01-22 10:25:31.259264: step: 554/466, loss: 0.4405522644519806
2023-01-22 10:25:31.962777: step: 556/466, loss: 0.3007507622241974
2023-01-22 10:25:32.640420: step: 558/466, loss: 0.7260340452194214
2023-01-22 10:25:33.220901: step: 560/466, loss: 0.26162004470825195
2023-01-22 10:25:33.865981: step: 562/466, loss: 0.3456798493862152
2023-01-22 10:25:34.506655: step: 564/466, loss: 0.5380363464355469
2023-01-22 10:25:35.086208: step: 566/466, loss: 2.494497299194336
2023-01-22 10:25:35.709917: step: 568/466, loss: 0.23229075968265533
2023-01-22 10:25:36.358652: step: 570/466, loss: 0.23848365247249603
2023-01-22 10:25:36.975651: step: 572/466, loss: 0.5783706307411194
2023-01-22 10:25:37.598717: step: 574/466, loss: 1.4762802124023438
2023-01-22 10:25:38.166192: step: 576/466, loss: 0.5708321332931519
2023-01-22 10:25:38.809862: step: 578/466, loss: 0.26208239793777466
2023-01-22 10:25:39.402391: step: 580/466, loss: 1.4005645513534546
2023-01-22 10:25:39.992516: step: 582/466, loss: 0.2656085193157196
2023-01-22 10:25:40.586906: step: 584/466, loss: 0.3431568741798401
2023-01-22 10:25:41.306090: step: 586/466, loss: 0.2746313810348511
2023-01-22 10:25:41.987411: step: 588/466, loss: 0.8503986597061157
2023-01-22 10:25:42.611315: step: 590/466, loss: 0.412700355052948
2023-01-22 10:25:43.230114: step: 592/466, loss: 0.24228881299495697
2023-01-22 10:25:43.832110: step: 594/466, loss: 0.06156359612941742
2023-01-22 10:25:44.448813: step: 596/466, loss: 1.6006569862365723
2023-01-22 10:25:45.034278: step: 598/466, loss: 0.21712467074394226
2023-01-22 10:25:45.637441: step: 600/466, loss: 0.21318912506103516
2023-01-22 10:25:46.249551: step: 602/466, loss: 0.50748211145401
2023-01-22 10:25:46.930110: step: 604/466, loss: 0.3261891007423401
2023-01-22 10:25:47.483020: step: 606/466, loss: 0.12974101305007935
2023-01-22 10:25:48.100656: step: 608/466, loss: 0.4472119212150574
2023-01-22 10:25:48.677528: step: 610/466, loss: 1.4981715679168701
2023-01-22 10:25:49.286408: step: 612/466, loss: 0.7696586847305298
2023-01-22 10:25:49.898642: step: 614/466, loss: 0.4564979374408722
2023-01-22 10:25:50.507750: step: 616/466, loss: 0.29963427782058716
2023-01-22 10:25:51.094122: step: 618/466, loss: 1.1432433128356934
2023-01-22 10:25:51.743319: step: 620/466, loss: 0.8962889313697815
2023-01-22 10:25:52.342024: step: 622/466, loss: 0.5036012530326843
2023-01-22 10:25:53.086132: step: 624/466, loss: 0.28956055641174316
2023-01-22 10:25:53.782494: step: 626/466, loss: 0.8795130848884583
2023-01-22 10:25:54.423030: step: 628/466, loss: 0.6439096927642822
2023-01-22 10:25:54.987887: step: 630/466, loss: 2.8661391735076904
2023-01-22 10:25:55.594153: step: 632/466, loss: 0.1871575117111206
2023-01-22 10:25:56.227269: step: 634/466, loss: 0.41019201278686523
2023-01-22 10:25:56.849635: step: 636/466, loss: 0.5545302033424377
2023-01-22 10:25:57.459369: step: 638/466, loss: 0.25796765089035034
2023-01-22 10:25:58.062669: step: 640/466, loss: 0.6741047501564026
2023-01-22 10:25:58.675209: step: 642/466, loss: 0.7461636066436768
2023-01-22 10:25:59.244659: step: 644/466, loss: 0.10852614790201187
2023-01-22 10:25:59.933284: step: 646/466, loss: 0.44105851650238037
2023-01-22 10:26:00.538549: step: 648/466, loss: 0.3716807961463928
2023-01-22 10:26:01.144221: step: 650/466, loss: 0.6248000264167786
2023-01-22 10:26:01.746994: step: 652/466, loss: 0.5479502081871033
2023-01-22 10:26:02.372016: step: 654/466, loss: 0.22235040366649628
2023-01-22 10:26:02.999973: step: 656/466, loss: 0.24069158732891083
2023-01-22 10:26:03.692126: step: 658/466, loss: 0.6740921139717102
2023-01-22 10:26:04.285917: step: 660/466, loss: 0.7209137082099915
2023-01-22 10:26:04.873740: step: 662/466, loss: 0.18780159950256348
2023-01-22 10:26:05.503243: step: 664/466, loss: 1.1777057647705078
2023-01-22 10:26:06.131163: step: 666/466, loss: 0.40443477034568787
2023-01-22 10:26:06.806964: step: 668/466, loss: 0.31447118520736694
2023-01-22 10:26:07.419115: step: 670/466, loss: 0.18810229003429413
2023-01-22 10:26:08.047248: step: 672/466, loss: 0.37618061900138855
2023-01-22 10:26:08.671284: step: 674/466, loss: 0.3444058895111084
2023-01-22 10:26:09.319748: step: 676/466, loss: 0.34029021859169006
2023-01-22 10:26:10.004540: step: 678/466, loss: 0.35844942927360535
2023-01-22 10:26:10.690539: step: 680/466, loss: 0.5731791257858276
2023-01-22 10:26:11.312294: step: 682/466, loss: 0.3525617718696594
2023-01-22 10:26:11.929955: step: 684/466, loss: 0.49626442790031433
2023-01-22 10:26:12.574255: step: 686/466, loss: 1.9497008323669434
2023-01-22 10:26:13.162458: step: 688/466, loss: 0.54268479347229
2023-01-22 10:26:13.733539: step: 690/466, loss: 2.6503868103027344
2023-01-22 10:26:14.347016: step: 692/466, loss: 0.7313562631607056
2023-01-22 10:26:15.091604: step: 694/466, loss: 2.6455135345458984
2023-01-22 10:26:15.752596: step: 696/466, loss: 0.7552454471588135
2023-01-22 10:26:16.395023: step: 698/466, loss: 0.5448524355888367
2023-01-22 10:26:17.023485: step: 700/466, loss: 0.2509639263153076
2023-01-22 10:26:17.631127: step: 702/466, loss: 0.7717275619506836
2023-01-22 10:26:18.274970: step: 704/466, loss: 0.6373904943466187
2023-01-22 10:26:18.961460: step: 706/466, loss: 0.2916221618652344
2023-01-22 10:26:19.590401: step: 708/466, loss: 0.09957034140825272
2023-01-22 10:26:20.266925: step: 710/466, loss: 0.16980797052383423
2023-01-22 10:26:20.924252: step: 712/466, loss: 0.1834866851568222
2023-01-22 10:26:21.522407: step: 714/466, loss: 0.1340818852186203
2023-01-22 10:26:22.123025: step: 716/466, loss: 0.20902466773986816
2023-01-22 10:26:22.786856: step: 718/466, loss: 1.2532103061676025
2023-01-22 10:26:23.578778: step: 720/466, loss: 0.7625625133514404
2023-01-22 10:26:24.244118: step: 722/466, loss: 0.23378467559814453
2023-01-22 10:26:24.908724: step: 724/466, loss: 0.763206422328949
2023-01-22 10:26:25.574853: step: 726/466, loss: 0.4498950242996216
2023-01-22 10:26:26.243238: step: 728/466, loss: 0.19985279440879822
2023-01-22 10:26:26.854997: step: 730/466, loss: 1.2688860893249512
2023-01-22 10:26:27.475503: step: 732/466, loss: 0.16228799521923065
2023-01-22 10:26:28.104630: step: 734/466, loss: 0.5916755795478821
2023-01-22 10:26:28.674994: step: 736/466, loss: 0.8936856389045715
2023-01-22 10:26:29.393563: step: 738/466, loss: 0.6819954514503479
2023-01-22 10:26:30.040504: step: 740/466, loss: 0.5362803339958191
2023-01-22 10:26:30.661321: step: 742/466, loss: 0.342614084482193
2023-01-22 10:26:31.283651: step: 744/466, loss: 0.5168187618255615
2023-01-22 10:26:31.908758: step: 746/466, loss: 0.5107553601264954
2023-01-22 10:26:32.544018: step: 748/466, loss: 0.3864627182483673
2023-01-22 10:26:33.132267: step: 750/466, loss: 1.1903786659240723
2023-01-22 10:26:33.741507: step: 752/466, loss: 1.3825924396514893
2023-01-22 10:26:34.389843: step: 754/466, loss: 0.36727002263069153
2023-01-22 10:26:34.954846: step: 756/466, loss: 0.13973617553710938
2023-01-22 10:26:35.597701: step: 758/466, loss: 0.3887569308280945
2023-01-22 10:26:36.240505: step: 760/466, loss: 0.6890345215797424
2023-01-22 10:26:36.899453: step: 762/466, loss: 0.4852111339569092
2023-01-22 10:26:37.569117: step: 764/466, loss: 1.3857756853103638
2023-01-22 10:26:38.170079: step: 766/466, loss: 0.3762704133987427
2023-01-22 10:26:38.778338: step: 768/466, loss: 0.28308290243148804
2023-01-22 10:26:39.428896: step: 770/466, loss: 0.5062119960784912
2023-01-22 10:26:40.031670: step: 772/466, loss: 1.144497036933899
2023-01-22 10:26:40.600338: step: 774/466, loss: 0.2258695363998413
2023-01-22 10:26:41.223857: step: 776/466, loss: 0.3459767699241638
2023-01-22 10:26:41.889913: step: 778/466, loss: 0.8844873309135437
2023-01-22 10:26:42.513922: step: 780/466, loss: 0.14429156482219696
2023-01-22 10:26:43.173320: step: 782/466, loss: 0.18639802932739258
2023-01-22 10:26:43.781098: step: 784/466, loss: 0.5045554041862488
2023-01-22 10:26:44.422970: step: 786/466, loss: 0.26245996356010437
2023-01-22 10:26:44.990684: step: 788/466, loss: 0.9515361189842224
2023-01-22 10:26:45.699862: step: 790/466, loss: 0.7297141551971436
2023-01-22 10:26:46.296238: step: 792/466, loss: 0.07746868580579758
2023-01-22 10:26:46.943806: step: 794/466, loss: 0.25915664434432983
2023-01-22 10:26:47.571234: step: 796/466, loss: 0.2650740444660187
2023-01-22 10:26:48.171572: step: 798/466, loss: 0.45773547887802124
2023-01-22 10:26:48.788111: step: 800/466, loss: 1.342380166053772
2023-01-22 10:26:49.404904: step: 802/466, loss: 1.4285269975662231
2023-01-22 10:26:50.066353: step: 804/466, loss: 0.2560678720474243
2023-01-22 10:26:50.728357: step: 806/466, loss: 0.4064926505088806
2023-01-22 10:26:51.328581: step: 808/466, loss: 0.2849564254283905
2023-01-22 10:26:51.899589: step: 810/466, loss: 1.2182557582855225
2023-01-22 10:26:52.495591: step: 812/466, loss: 0.44663289189338684
2023-01-22 10:26:53.119905: step: 814/466, loss: 0.3266800045967102
2023-01-22 10:26:53.718981: step: 816/466, loss: 0.5361456871032715
2023-01-22 10:26:54.321971: step: 818/466, loss: 0.3417607545852661
2023-01-22 10:26:54.912956: step: 820/466, loss: 0.2348371148109436
2023-01-22 10:26:55.566885: step: 822/466, loss: 0.6924700140953064
2023-01-22 10:26:56.284481: step: 824/466, loss: 0.39939966797828674
2023-01-22 10:26:56.955457: step: 826/466, loss: 0.2644041180610657
2023-01-22 10:26:57.560051: step: 828/466, loss: 0.8015566468238831
2023-01-22 10:26:58.154022: step: 830/466, loss: 0.14491812884807587
2023-01-22 10:26:58.747514: step: 832/466, loss: 0.19254310429096222
2023-01-22 10:26:59.444922: step: 834/466, loss: 0.7438780069351196
2023-01-22 10:27:00.078627: step: 836/466, loss: 0.6236226558685303
2023-01-22 10:27:00.806774: step: 838/466, loss: 0.3768724203109741
2023-01-22 10:27:01.390670: step: 840/466, loss: 0.4085683822631836
2023-01-22 10:27:02.020239: step: 842/466, loss: 0.6542133688926697
2023-01-22 10:27:02.653532: step: 844/466, loss: 0.1571868658065796
2023-01-22 10:27:03.273826: step: 846/466, loss: 0.2461111694574356
2023-01-22 10:27:03.872601: step: 848/466, loss: 0.9098088145256042
2023-01-22 10:27:04.533899: step: 850/466, loss: 0.5644944310188293
2023-01-22 10:27:05.107356: step: 852/466, loss: 1.5331993103027344
2023-01-22 10:27:05.732433: step: 854/466, loss: 0.19291947782039642
2023-01-22 10:27:06.314718: step: 856/466, loss: 0.2534935772418976
2023-01-22 10:27:06.860854: step: 858/466, loss: 0.2990705072879791
2023-01-22 10:27:07.532706: step: 860/466, loss: 0.18518830835819244
2023-01-22 10:27:08.139504: step: 862/466, loss: 0.6862562894821167
2023-01-22 10:27:08.733580: step: 864/466, loss: 0.5459586381912231
2023-01-22 10:27:09.301173: step: 866/466, loss: 0.7927795648574829
2023-01-22 10:27:09.914235: step: 868/466, loss: 0.7867419123649597
2023-01-22 10:27:10.493528: step: 870/466, loss: 0.20071671903133392
2023-01-22 10:27:11.165458: step: 872/466, loss: 0.23669061064720154
2023-01-22 10:27:11.830170: step: 874/466, loss: 1.3111863136291504
2023-01-22 10:27:12.458967: step: 876/466, loss: 3.68401837348938
2023-01-22 10:27:13.146397: step: 878/466, loss: 0.4205979108810425
2023-01-22 10:27:13.761624: step: 880/466, loss: 0.5019314885139465
2023-01-22 10:27:14.334349: step: 882/466, loss: 0.253624826669693
2023-01-22 10:27:14.960054: step: 884/466, loss: 3.2044146060943604
2023-01-22 10:27:15.587208: step: 886/466, loss: 0.7262096405029297
2023-01-22 10:27:16.216864: step: 888/466, loss: 0.42531633377075195
2023-01-22 10:27:16.810357: step: 890/466, loss: 0.5560821294784546
2023-01-22 10:27:17.381371: step: 892/466, loss: 0.6997929811477661
2023-01-22 10:27:17.991028: step: 894/466, loss: 0.34848010540008545
2023-01-22 10:27:18.660269: step: 896/466, loss: 1.874853253364563
2023-01-22 10:27:19.309072: step: 898/466, loss: 0.22323575615882874
2023-01-22 10:27:19.884133: step: 900/466, loss: 0.30327314138412476
2023-01-22 10:27:20.496989: step: 902/466, loss: 0.1081712618470192
2023-01-22 10:27:21.162577: step: 904/466, loss: 0.5367346405982971
2023-01-22 10:27:21.788129: step: 906/466, loss: 0.18195709586143494
2023-01-22 10:27:22.407106: step: 908/466, loss: 2.1218409538269043
2023-01-22 10:27:23.110700: step: 910/466, loss: 0.5148961544036865
2023-01-22 10:27:23.688627: step: 912/466, loss: 0.1135493814945221
2023-01-22 10:27:24.446383: step: 914/466, loss: 0.31819668412208557
2023-01-22 10:27:25.093308: step: 916/466, loss: 0.255973756313324
2023-01-22 10:27:25.646796: step: 918/466, loss: 0.6888198852539062
2023-01-22 10:27:26.373520: step: 920/466, loss: 0.6373869180679321
2023-01-22 10:27:26.991697: step: 922/466, loss: 0.15597975254058838
2023-01-22 10:27:27.622702: step: 924/466, loss: 0.43550437688827515
2023-01-22 10:27:28.248803: step: 926/466, loss: 0.2740226686000824
2023-01-22 10:27:28.847452: step: 928/466, loss: 0.3159542679786682
2023-01-22 10:27:29.503188: step: 930/466, loss: 0.24795958399772644
2023-01-22 10:27:30.122195: step: 932/466, loss: 0.5158659219741821
==================================================
Loss: 0.600
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30466885011453176, 'r': 0.3474496753678057, 'f1': 0.32465599099083975}, 'combined': 0.23922020388798718, 'epoch': 7}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.30854926403548943, 'r': 0.26733510241342046, 'f1': 0.2864674018124466}, 'combined': 0.1793767843124666, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27365358270908674, 'r': 0.3447931288782421, 'f1': 0.3051317865975375}, 'combined': 0.22483394801923812, 'epoch': 7}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.31705946042321687, 'r': 0.2795393255402526, 'f1': 0.29711957116952437}, 'combined': 0.18413043847125452, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.251406256990498, 'r': 0.3539723770150845, 'f1': 0.2940006976941679}, 'combined': 0.21663209303780792, 'epoch': 7}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.34096603886854954, 'r': 0.28152028864124146, 'f1': 0.30840471007011805}, 'combined': 0.2045853027197813, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.19230769230769232, 'r': 0.35714285714285715, 'f1': 0.25}, 'combined': 0.16666666666666666, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3092105263157895, 'r': 0.5108695652173914, 'f1': 0.3852459016393443}, 'combined': 0.19262295081967215, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.19852941176470587, 'r': 0.23275862068965517, 'f1': 0.21428571428571427}, 'combined': 0.14285714285714285, 'epoch': 7}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3125951086956522, 'r': 0.2728534155597723, 'f1': 0.2913753799392097}, 'combined': 0.21469764837625976, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32426953156573873, 'r': 0.23676358396812514, 'f1': 0.27369228068511486}, 'combined': 0.1713774094009598, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3157894736842105, 'r': 0.34285714285714286, 'f1': 0.3287671232876712}, 'combined': 0.2191780821917808, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27365358270908674, 'r': 0.3447931288782421, 'f1': 0.3051317865975375}, 'combined': 0.22483394801923812, 'epoch': 7}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.31705946042321687, 'r': 0.2795393255402526, 'f1': 0.29711957116952437}, 'combined': 0.18413043847125452, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3092105263157895, 'r': 0.5108695652173914, 'f1': 0.3852459016393443}, 'combined': 0.19262295081967215, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2870113455833512, 'r': 0.27611907440371736, 'f1': 0.2814598688796113}, 'combined': 0.20739148233234514, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3582228395089435, 'r': 0.2388152263392957, 'f1': 0.28657827160715477}, 'combined': 0.19010637819484524, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4117647058823529, 'r': 0.2413793103448276, 'f1': 0.3043478260869565}, 'combined': 0.20289855072463764, 'epoch': 5}
******************************
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 10:30:14.656530: step: 2/466, loss: 0.4891449809074402
2023-01-22 10:30:15.289075: step: 4/466, loss: 0.16528034210205078
2023-01-22 10:30:15.919964: step: 6/466, loss: 0.5206984877586365
2023-01-22 10:30:16.619319: step: 8/466, loss: 0.8224088549613953
2023-01-22 10:30:17.242572: step: 10/466, loss: 0.1467466652393341
2023-01-22 10:30:17.831166: step: 12/466, loss: 0.389367938041687
2023-01-22 10:30:18.493938: step: 14/466, loss: 0.41784942150115967
2023-01-22 10:30:19.061252: step: 16/466, loss: 0.5343703031539917
2023-01-22 10:30:19.626297: step: 18/466, loss: 0.2499110996723175
2023-01-22 10:30:20.287379: step: 20/466, loss: 0.11215971410274506
2023-01-22 10:30:20.946288: step: 22/466, loss: 0.4292660057544708
2023-01-22 10:30:21.573677: step: 24/466, loss: 0.306545615196228
2023-01-22 10:30:22.187788: step: 26/466, loss: 0.336021363735199
2023-01-22 10:30:22.829367: step: 28/466, loss: 0.4028060734272003
2023-01-22 10:30:23.430911: step: 30/466, loss: 0.11552461236715317
2023-01-22 10:30:23.996710: step: 32/466, loss: 0.43966126441955566
2023-01-22 10:30:24.602327: step: 34/466, loss: 0.15228354930877686
2023-01-22 10:30:25.221057: step: 36/466, loss: 0.3842215836048126
2023-01-22 10:30:25.815440: step: 38/466, loss: 0.11852533370256424
2023-01-22 10:30:26.605171: step: 40/466, loss: 0.32897087931632996
2023-01-22 10:30:27.190494: step: 42/466, loss: 0.25963473320007324
2023-01-22 10:30:27.770839: step: 44/466, loss: 0.4247356355190277
2023-01-22 10:30:28.351205: step: 46/466, loss: 0.2964792549610138
2023-01-22 10:30:28.992640: step: 48/466, loss: 0.2749635577201843
2023-01-22 10:30:29.657061: step: 50/466, loss: 0.33326396346092224
2023-01-22 10:30:30.366860: step: 52/466, loss: 0.3246749937534332
2023-01-22 10:30:30.942328: step: 54/466, loss: 0.36350858211517334
2023-01-22 10:30:31.585044: step: 56/466, loss: 0.423279345035553
2023-01-22 10:30:32.214101: step: 58/466, loss: 0.45801088213920593
2023-01-22 10:30:32.774049: step: 60/466, loss: 0.46881794929504395
2023-01-22 10:30:33.401895: step: 62/466, loss: 0.30722299218177795
2023-01-22 10:30:34.090824: step: 64/466, loss: 0.9380748271942139
2023-01-22 10:30:34.699494: step: 66/466, loss: 0.3640623390674591
2023-01-22 10:30:35.282641: step: 68/466, loss: 0.10745082050561905
2023-01-22 10:30:35.857694: step: 70/466, loss: 0.0724589079618454
2023-01-22 10:30:36.509305: step: 72/466, loss: 1.0328303575515747
2023-01-22 10:30:37.128236: step: 74/466, loss: 0.1602552980184555
2023-01-22 10:30:37.759560: step: 76/466, loss: 0.2987484037876129
2023-01-22 10:30:38.356238: step: 78/466, loss: 0.3314462900161743
2023-01-22 10:30:38.979525: step: 80/466, loss: 0.5131017565727234
2023-01-22 10:30:39.626119: step: 82/466, loss: 1.0332460403442383
2023-01-22 10:30:40.173929: step: 84/466, loss: 0.21270959079265594
2023-01-22 10:30:40.841580: step: 86/466, loss: 0.21382087469100952
2023-01-22 10:30:41.455715: step: 88/466, loss: 0.17594799399375916
2023-01-22 10:30:42.103934: step: 90/466, loss: 0.7188621163368225
2023-01-22 10:30:42.732607: step: 92/466, loss: 0.21991394460201263
2023-01-22 10:30:43.380611: step: 94/466, loss: 0.08778136968612671
2023-01-22 10:30:44.065363: step: 96/466, loss: 0.2640227675437927
2023-01-22 10:30:44.661921: step: 98/466, loss: 0.36777612566947937
2023-01-22 10:30:45.238425: step: 100/466, loss: 0.8869547247886658
2023-01-22 10:30:45.868496: step: 102/466, loss: 1.0804152488708496
2023-01-22 10:30:46.428373: step: 104/466, loss: 0.14686386287212372
2023-01-22 10:30:47.090057: step: 106/466, loss: 0.17105038464069366
2023-01-22 10:30:47.712775: step: 108/466, loss: 0.11347710341215134
2023-01-22 10:30:48.335329: step: 110/466, loss: 1.2311139106750488
2023-01-22 10:30:49.013792: step: 112/466, loss: 0.12046322226524353
2023-01-22 10:30:49.620411: step: 114/466, loss: 0.08653685450553894
2023-01-22 10:30:50.275329: step: 116/466, loss: 0.7125675678253174
2023-01-22 10:30:50.872410: step: 118/466, loss: 1.1520308256149292
2023-01-22 10:30:51.476852: step: 120/466, loss: 3.4308528900146484
2023-01-22 10:30:52.047836: step: 122/466, loss: 0.5015811920166016
2023-01-22 10:30:52.647062: step: 124/466, loss: 0.19502291083335876
2023-01-22 10:30:53.320840: step: 126/466, loss: 0.44669079780578613
2023-01-22 10:30:53.990788: step: 128/466, loss: 0.21128225326538086
2023-01-22 10:30:54.575543: step: 130/466, loss: 0.143118754029274
2023-01-22 10:30:55.186677: step: 132/466, loss: 0.44315147399902344
2023-01-22 10:30:55.808235: step: 134/466, loss: 0.24999311566352844
2023-01-22 10:30:56.383023: step: 136/466, loss: 0.30038580298423767
2023-01-22 10:30:56.995663: step: 138/466, loss: 0.33321985602378845
2023-01-22 10:30:57.608872: step: 140/466, loss: 0.6168915629386902
2023-01-22 10:30:58.304378: step: 142/466, loss: 0.30142584443092346
2023-01-22 10:30:58.961508: step: 144/466, loss: 0.1558297872543335
2023-01-22 10:30:59.532145: step: 146/466, loss: 0.9224661588668823
2023-01-22 10:31:00.043787: step: 148/466, loss: 0.5734288692474365
2023-01-22 10:31:00.668579: step: 150/466, loss: 0.3471072316169739
2023-01-22 10:31:01.302676: step: 152/466, loss: 0.4813990890979767
2023-01-22 10:31:01.955167: step: 154/466, loss: 0.6883899569511414
2023-01-22 10:31:02.601192: step: 156/466, loss: 0.761605441570282
2023-01-22 10:31:03.378063: step: 158/466, loss: 0.3350845277309418
2023-01-22 10:31:04.038021: step: 160/466, loss: 0.49126744270324707
2023-01-22 10:31:04.615416: step: 162/466, loss: 0.2792118191719055
2023-01-22 10:31:05.284825: step: 164/466, loss: 0.30940383672714233
2023-01-22 10:31:05.873762: step: 166/466, loss: 0.39825183153152466
2023-01-22 10:31:06.494091: step: 168/466, loss: 0.2737186849117279
2023-01-22 10:31:07.150946: step: 170/466, loss: 0.4189709424972534
2023-01-22 10:31:07.775464: step: 172/466, loss: 0.22759076952934265
2023-01-22 10:31:08.417280: step: 174/466, loss: 0.3200244903564453
2023-01-22 10:31:09.085325: step: 176/466, loss: 0.408761203289032
2023-01-22 10:31:09.785878: step: 178/466, loss: 0.7359369397163391
2023-01-22 10:31:10.359854: step: 180/466, loss: 1.7133041620254517
2023-01-22 10:31:11.008952: step: 182/466, loss: 1.0704987049102783
2023-01-22 10:31:11.632919: step: 184/466, loss: 1.2679871320724487
2023-01-22 10:31:12.371945: step: 186/466, loss: 0.19554297626018524
2023-01-22 10:31:12.989233: step: 188/466, loss: 1.5121451616287231
2023-01-22 10:31:13.658898: step: 190/466, loss: 0.14149893820285797
2023-01-22 10:31:14.303667: step: 192/466, loss: 0.5469195246696472
2023-01-22 10:31:14.964128: step: 194/466, loss: 0.19274388253688812
2023-01-22 10:31:15.609566: step: 196/466, loss: 0.10487526655197144
2023-01-22 10:31:16.193183: step: 198/466, loss: 0.20737946033477783
2023-01-22 10:31:16.781604: step: 200/466, loss: 0.22559292614459991
2023-01-22 10:31:17.373914: step: 202/466, loss: 0.28806859254837036
2023-01-22 10:31:17.980319: step: 204/466, loss: 0.23927956819534302
2023-01-22 10:31:18.635671: step: 206/466, loss: 0.6100448966026306
2023-01-22 10:31:19.308631: step: 208/466, loss: 0.7341493368148804
2023-01-22 10:31:19.930855: step: 210/466, loss: 0.15287290513515472
2023-01-22 10:31:20.583516: step: 212/466, loss: 0.45582741498947144
2023-01-22 10:31:21.242494: step: 214/466, loss: 0.19518420100212097
2023-01-22 10:31:21.983088: step: 216/466, loss: 0.3610004186630249
2023-01-22 10:31:22.624082: step: 218/466, loss: 0.5222340822219849
2023-01-22 10:31:23.235361: step: 220/466, loss: 0.4963740110397339
2023-01-22 10:31:23.933323: step: 222/466, loss: 0.4004770517349243
2023-01-22 10:31:24.472447: step: 224/466, loss: 0.27218079566955566
2023-01-22 10:31:25.128337: step: 226/466, loss: 1.1614692211151123
2023-01-22 10:31:25.820770: step: 228/466, loss: 0.4531356394290924
2023-01-22 10:31:26.384526: step: 230/466, loss: 0.4567834734916687
2023-01-22 10:31:27.041343: step: 232/466, loss: 0.3453659415245056
2023-01-22 10:31:27.702214: step: 234/466, loss: 0.18262067437171936
2023-01-22 10:31:28.364393: step: 236/466, loss: 0.3032654821872711
2023-01-22 10:31:28.900055: step: 238/466, loss: 0.21114803850650787
2023-01-22 10:31:29.526905: step: 240/466, loss: 0.28366371989250183
2023-01-22 10:31:30.091082: step: 242/466, loss: 0.20999203622341156
2023-01-22 10:31:30.701332: step: 244/466, loss: 0.10796754062175751
2023-01-22 10:31:31.294211: step: 246/466, loss: 1.5038633346557617
2023-01-22 10:31:31.868275: step: 248/466, loss: 1.139866590499878
2023-01-22 10:31:32.427722: step: 250/466, loss: 0.08542253077030182
2023-01-22 10:31:32.994317: step: 252/466, loss: 0.8522475361824036
2023-01-22 10:31:33.603931: step: 254/466, loss: 0.3592441976070404
2023-01-22 10:31:34.228401: step: 256/466, loss: 0.32976898550987244
2023-01-22 10:31:34.818807: step: 258/466, loss: 0.8676184415817261
2023-01-22 10:31:35.416606: step: 260/466, loss: 0.30186426639556885
2023-01-22 10:31:36.011981: step: 262/466, loss: 0.7166699767112732
2023-01-22 10:31:36.564269: step: 264/466, loss: 0.38969892263412476
2023-01-22 10:31:37.127895: step: 266/466, loss: 1.7875447273254395
2023-01-22 10:31:37.828507: step: 268/466, loss: 1.1755938529968262
2023-01-22 10:31:38.389669: step: 270/466, loss: 0.20601579546928406
2023-01-22 10:31:39.050685: step: 272/466, loss: 0.18585112690925598
2023-01-22 10:31:39.675552: step: 274/466, loss: 0.25609394907951355
2023-01-22 10:31:40.291670: step: 276/466, loss: 0.27535563707351685
2023-01-22 10:31:40.952797: step: 278/466, loss: 0.21241937577724457
2023-01-22 10:31:41.661011: step: 280/466, loss: 0.6060916781425476
2023-01-22 10:31:42.253140: step: 282/466, loss: 0.9486252665519714
2023-01-22 10:31:43.008415: step: 284/466, loss: 0.41912248730659485
2023-01-22 10:31:43.641228: step: 286/466, loss: 1.7066893577575684
2023-01-22 10:31:44.302411: step: 288/466, loss: 0.5481307506561279
2023-01-22 10:31:44.942355: step: 290/466, loss: 0.4919094741344452
2023-01-22 10:31:45.648134: step: 292/466, loss: 0.6574281454086304
2023-01-22 10:31:46.278499: step: 294/466, loss: 0.22694242000579834
2023-01-22 10:31:46.908184: step: 296/466, loss: 2.1146581172943115
2023-01-22 10:31:47.494384: step: 298/466, loss: 0.5112307667732239
2023-01-22 10:31:48.147138: step: 300/466, loss: 0.895716667175293
2023-01-22 10:31:48.753904: step: 302/466, loss: 0.2852054834365845
2023-01-22 10:31:49.373871: step: 304/466, loss: 0.29013773798942566
2023-01-22 10:31:50.009605: step: 306/466, loss: 0.31209948658943176
2023-01-22 10:31:50.671423: step: 308/466, loss: 0.0986483246088028
2023-01-22 10:31:51.297151: step: 310/466, loss: 0.22533275187015533
2023-01-22 10:31:51.902226: step: 312/466, loss: 0.20643262565135956
2023-01-22 10:31:52.521251: step: 314/466, loss: 0.7615416646003723
2023-01-22 10:31:53.091762: step: 316/466, loss: 0.15414905548095703
2023-01-22 10:31:53.811134: step: 318/466, loss: 1.1039615869522095
2023-01-22 10:31:54.463607: step: 320/466, loss: 0.265773206949234
2023-01-22 10:31:55.121108: step: 322/466, loss: 0.40013816952705383
2023-01-22 10:31:55.795121: step: 324/466, loss: 0.667767345905304
2023-01-22 10:31:56.406875: step: 326/466, loss: 0.4804272949695587
2023-01-22 10:31:57.100289: step: 328/466, loss: 0.6763488054275513
2023-01-22 10:31:57.796693: step: 330/466, loss: 2.750519037246704
2023-01-22 10:31:58.397335: step: 332/466, loss: 1.282062292098999
2023-01-22 10:31:58.981801: step: 334/466, loss: 1.68393075466156
2023-01-22 10:31:59.613766: step: 336/466, loss: 0.23293834924697876
2023-01-22 10:32:00.246661: step: 338/466, loss: 0.7747480869293213
2023-01-22 10:32:00.882276: step: 340/466, loss: 0.11038610339164734
2023-01-22 10:32:01.488423: step: 342/466, loss: 0.08814762532711029
2023-01-22 10:32:02.156756: step: 344/466, loss: 0.4685029983520508
2023-01-22 10:32:02.733519: step: 346/466, loss: 0.25662773847579956
2023-01-22 10:32:03.306579: step: 348/466, loss: 0.3834894895553589
2023-01-22 10:32:03.927059: step: 350/466, loss: 0.3033915162086487
2023-01-22 10:32:04.577512: step: 352/466, loss: 0.6060888171195984
2023-01-22 10:32:05.211183: step: 354/466, loss: 0.3031148612499237
2023-01-22 10:32:05.830697: step: 356/466, loss: 0.26334863901138306
2023-01-22 10:32:06.423002: step: 358/466, loss: 0.4853774905204773
2023-01-22 10:32:07.085331: step: 360/466, loss: 0.6246654391288757
2023-01-22 10:32:07.765521: step: 362/466, loss: 0.10203198343515396
2023-01-22 10:32:08.372945: step: 364/466, loss: 0.6044864058494568
2023-01-22 10:32:09.042718: step: 366/466, loss: 0.3602357506752014
2023-01-22 10:32:09.646746: step: 368/466, loss: 0.25677040219306946
2023-01-22 10:32:10.271204: step: 370/466, loss: 0.10781390219926834
2023-01-22 10:32:10.835710: step: 372/466, loss: 0.35638684034347534
2023-01-22 10:32:11.447471: step: 374/466, loss: 1.1047513484954834
2023-01-22 10:32:12.002632: step: 376/466, loss: 0.28093698620796204
2023-01-22 10:32:12.596054: step: 378/466, loss: 0.7687437534332275
2023-01-22 10:32:13.222614: step: 380/466, loss: 1.9897117614746094
2023-01-22 10:32:13.829774: step: 382/466, loss: 0.5927366018295288
2023-01-22 10:32:14.427496: step: 384/466, loss: 0.3256917893886566
2023-01-22 10:32:15.022620: step: 386/466, loss: 0.09695328027009964
2023-01-22 10:32:15.693816: step: 388/466, loss: 0.2785665988922119
2023-01-22 10:32:16.299671: step: 390/466, loss: 0.2793259620666504
2023-01-22 10:32:16.928750: step: 392/466, loss: 0.3837505578994751
2023-01-22 10:32:17.609880: step: 394/466, loss: 1.2248982191085815
2023-01-22 10:32:18.269549: step: 396/466, loss: 0.18187536299228668
2023-01-22 10:32:18.858327: step: 398/466, loss: 1.0493046045303345
2023-01-22 10:32:19.498153: step: 400/466, loss: 0.19331248104572296
2023-01-22 10:32:20.179144: step: 402/466, loss: 3.6122488975524902
2023-01-22 10:32:20.847250: step: 404/466, loss: 2.8651459217071533
2023-01-22 10:32:21.423953: step: 406/466, loss: 0.35814833641052246
2023-01-22 10:32:22.024556: step: 408/466, loss: 0.13510677218437195
2023-01-22 10:32:22.734217: step: 410/466, loss: 0.4739450216293335
2023-01-22 10:32:23.328719: step: 412/466, loss: 0.8541678190231323
2023-01-22 10:32:23.927492: step: 414/466, loss: 0.8350094556808472
2023-01-22 10:32:24.548076: step: 416/466, loss: 0.2985285818576813
2023-01-22 10:32:25.113234: step: 418/466, loss: 1.1642861366271973
2023-01-22 10:32:25.755873: step: 420/466, loss: 0.674666702747345
2023-01-22 10:32:26.405250: step: 422/466, loss: 0.48510220646858215
2023-01-22 10:32:27.002370: step: 424/466, loss: 0.5639714002609253
2023-01-22 10:32:27.569842: step: 426/466, loss: 0.37887322902679443
2023-01-22 10:32:28.123055: step: 428/466, loss: 0.43298012018203735
2023-01-22 10:32:28.742465: step: 430/466, loss: 0.07726405560970306
2023-01-22 10:32:29.308459: step: 432/466, loss: 1.3216429948806763
2023-01-22 10:32:29.909177: step: 434/466, loss: 0.33925119042396545
2023-01-22 10:32:30.543509: step: 436/466, loss: 0.29555174708366394
2023-01-22 10:32:31.180733: step: 438/466, loss: 0.15159834921360016
2023-01-22 10:32:31.782303: step: 440/466, loss: 0.3884194791316986
2023-01-22 10:32:32.474943: step: 442/466, loss: 0.19900605082511902
2023-01-22 10:32:33.182350: step: 444/466, loss: 0.2201690375804901
2023-01-22 10:32:33.799952: step: 446/466, loss: 0.46234437823295593
2023-01-22 10:32:34.435170: step: 448/466, loss: 0.26391351222991943
2023-01-22 10:32:35.047732: step: 450/466, loss: 0.16837245225906372
2023-01-22 10:32:35.701481: step: 452/466, loss: 0.11911796033382416
2023-01-22 10:32:36.382828: step: 454/466, loss: 0.7436661720275879
2023-01-22 10:32:36.968607: step: 456/466, loss: 0.8642342686653137
2023-01-22 10:32:37.557677: step: 458/466, loss: 0.12915383279323578
2023-01-22 10:32:38.207246: step: 460/466, loss: 0.8493901491165161
2023-01-22 10:32:38.841700: step: 462/466, loss: 0.13043589890003204
2023-01-22 10:32:39.441861: step: 464/466, loss: 0.17544306814670563
2023-01-22 10:32:40.094982: step: 466/466, loss: 0.20262432098388672
2023-01-22 10:32:40.766408: step: 468/466, loss: 0.3896419107913971
2023-01-22 10:32:41.386136: step: 470/466, loss: 0.28438907861709595
2023-01-22 10:32:42.079016: step: 472/466, loss: 0.5023604035377502
2023-01-22 10:32:42.768380: step: 474/466, loss: 0.57744961977005
2023-01-22 10:32:43.383419: step: 476/466, loss: 0.9624512195587158
2023-01-22 10:32:43.957641: step: 478/466, loss: 0.7388322949409485
2023-01-22 10:32:44.595275: step: 480/466, loss: 0.4975886046886444
2023-01-22 10:32:45.207522: step: 482/466, loss: 0.05164724215865135
2023-01-22 10:32:45.852082: step: 484/466, loss: 0.4877254366874695
2023-01-22 10:32:46.514177: step: 486/466, loss: 0.28059661388397217
2023-01-22 10:32:47.155378: step: 488/466, loss: 0.8249738216400146
2023-01-22 10:32:47.784441: step: 490/466, loss: 0.5365325212478638
2023-01-22 10:32:48.389898: step: 492/466, loss: 1.1868059635162354
2023-01-22 10:32:49.043261: step: 494/466, loss: 0.7013980150222778
2023-01-22 10:32:49.668828: step: 496/466, loss: 0.29911187291145325
2023-01-22 10:32:50.320190: step: 498/466, loss: 0.34993094205856323
2023-01-22 10:32:50.863990: step: 500/466, loss: 0.37614795565605164
2023-01-22 10:32:51.451277: step: 502/466, loss: 0.3541680872440338
2023-01-22 10:32:52.078098: step: 504/466, loss: 0.12377132475376129
2023-01-22 10:32:52.677459: step: 506/466, loss: 0.2723594009876251
2023-01-22 10:32:53.325845: step: 508/466, loss: 1.4284451007843018
2023-01-22 10:32:53.964753: step: 510/466, loss: 0.11622864753007889
2023-01-22 10:32:54.653616: step: 512/466, loss: 0.22645901143550873
2023-01-22 10:32:55.271237: step: 514/466, loss: 0.37532246112823486
2023-01-22 10:32:55.955179: step: 516/466, loss: 2.2145767211914062
2023-01-22 10:32:56.526507: step: 518/466, loss: 0.613787055015564
2023-01-22 10:32:57.109713: step: 520/466, loss: 0.2860957980155945
2023-01-22 10:32:57.689584: step: 522/466, loss: 1.8711495399475098
2023-01-22 10:32:58.292254: step: 524/466, loss: 0.2798992395401001
2023-01-22 10:32:58.898518: step: 526/466, loss: 0.7050901651382446
2023-01-22 10:32:59.538382: step: 528/466, loss: 0.17970451712608337
2023-01-22 10:33:00.213581: step: 530/466, loss: 0.7807099223136902
2023-01-22 10:33:00.823600: step: 532/466, loss: 0.24164973199367523
2023-01-22 10:33:01.527657: step: 534/466, loss: 0.15025509893894196
2023-01-22 10:33:02.151697: step: 536/466, loss: 1.8316205739974976
2023-01-22 10:33:02.751553: step: 538/466, loss: 0.12155395746231079
2023-01-22 10:33:03.397202: step: 540/466, loss: 1.446241855621338
2023-01-22 10:33:04.063775: step: 542/466, loss: 0.3058852553367615
2023-01-22 10:33:04.790736: step: 544/466, loss: 0.6193525791168213
2023-01-22 10:33:05.466700: step: 546/466, loss: 0.21508213877677917
2023-01-22 10:33:06.053226: step: 548/466, loss: 0.21789303421974182
2023-01-22 10:33:06.658882: step: 550/466, loss: 0.4308699071407318
2023-01-22 10:33:07.340390: step: 552/466, loss: 0.3660205900669098
2023-01-22 10:33:08.012068: step: 554/466, loss: 1.035229206085205
2023-01-22 10:33:08.580426: step: 556/466, loss: 0.6700537204742432
2023-01-22 10:33:09.204650: step: 558/466, loss: 0.7066946625709534
2023-01-22 10:33:09.755184: step: 560/466, loss: 0.3775577247142792
2023-01-22 10:33:10.377082: step: 562/466, loss: 0.6352196931838989
2023-01-22 10:33:11.019130: step: 564/466, loss: 0.2720373868942261
2023-01-22 10:33:11.673235: step: 566/466, loss: 0.21507731080055237
2023-01-22 10:33:12.392920: step: 568/466, loss: 0.6397743821144104
2023-01-22 10:33:13.158512: step: 570/466, loss: 0.33709046244621277
2023-01-22 10:33:13.801620: step: 572/466, loss: 0.662662923336029
2023-01-22 10:33:14.405909: step: 574/466, loss: 0.5373324751853943
2023-01-22 10:33:14.988437: step: 576/466, loss: 0.4190295934677124
2023-01-22 10:33:15.669616: step: 578/466, loss: 0.27939939498901367
2023-01-22 10:33:16.245877: step: 580/466, loss: 0.3925917148590088
2023-01-22 10:33:16.861566: step: 582/466, loss: 0.7767550945281982
2023-01-22 10:33:17.510807: step: 584/466, loss: 0.29361432790756226
2023-01-22 10:33:18.096286: step: 586/466, loss: 0.5022650957107544
2023-01-22 10:33:18.706191: step: 588/466, loss: 0.2584410011768341
2023-01-22 10:33:19.305798: step: 590/466, loss: 0.16977599263191223
2023-01-22 10:33:19.945664: step: 592/466, loss: 0.7773684859275818
2023-01-22 10:33:20.513733: step: 594/466, loss: 1.2744741439819336
2023-01-22 10:33:21.120861: step: 596/466, loss: 0.3293832838535309
2023-01-22 10:33:21.740200: step: 598/466, loss: 0.4391189515590668
2023-01-22 10:33:22.335387: step: 600/466, loss: 0.33168160915374756
2023-01-22 10:33:22.924402: step: 602/466, loss: 0.5100934505462646
2023-01-22 10:33:23.521581: step: 604/466, loss: 1.8785651922225952
2023-01-22 10:33:24.073015: step: 606/466, loss: 0.6358599662780762
2023-01-22 10:33:24.668071: step: 608/466, loss: 0.1605401188135147
2023-01-22 10:33:25.353061: step: 610/466, loss: 0.21751931309700012
2023-01-22 10:33:25.956976: step: 612/466, loss: 0.5162280797958374
2023-01-22 10:33:26.544853: step: 614/466, loss: 0.2392381727695465
2023-01-22 10:33:27.166183: step: 616/466, loss: 0.5406078100204468
2023-01-22 10:33:27.778042: step: 618/466, loss: 0.4269423484802246
2023-01-22 10:33:28.375611: step: 620/466, loss: 0.4323086142539978
2023-01-22 10:33:29.025707: step: 622/466, loss: 0.7112070918083191
2023-01-22 10:33:29.639125: step: 624/466, loss: 0.7384576797485352
2023-01-22 10:33:30.293817: step: 626/466, loss: 0.19302891194820404
2023-01-22 10:33:30.925108: step: 628/466, loss: 0.8037995100021362
2023-01-22 10:33:31.508038: step: 630/466, loss: 0.28480249643325806
2023-01-22 10:33:32.167230: step: 632/466, loss: 0.14106625318527222
2023-01-22 10:33:32.864930: step: 634/466, loss: 0.43928807973861694
2023-01-22 10:33:33.473831: step: 636/466, loss: 0.2419721484184265
2023-01-22 10:33:34.086954: step: 638/466, loss: 0.3035977780818939
2023-01-22 10:33:34.736394: step: 640/466, loss: 0.22203347086906433
2023-01-22 10:33:35.356157: step: 642/466, loss: 0.22260044515132904
2023-01-22 10:33:36.031204: step: 644/466, loss: 0.46736451983451843
2023-01-22 10:33:36.627691: step: 646/466, loss: 0.40349987149238586
2023-01-22 10:33:37.185824: step: 648/466, loss: 0.5523925423622131
2023-01-22 10:33:37.860567: step: 650/466, loss: 2.0567588806152344
2023-01-22 10:33:38.491294: step: 652/466, loss: 0.1411169320344925
2023-01-22 10:33:39.100741: step: 654/466, loss: 0.30137670040130615
2023-01-22 10:33:39.811984: step: 656/466, loss: 0.1508619785308838
2023-01-22 10:33:40.479925: step: 658/466, loss: 0.3482684791088104
2023-01-22 10:33:41.151264: step: 660/466, loss: 0.12911884486675262
2023-01-22 10:33:41.792828: step: 662/466, loss: 0.17649178206920624
2023-01-22 10:33:42.467323: step: 664/466, loss: 0.1580641120672226
2023-01-22 10:33:43.099586: step: 666/466, loss: 0.6881174445152283
2023-01-22 10:33:43.667579: step: 668/466, loss: 0.5445083379745483
2023-01-22 10:33:44.264761: step: 670/466, loss: 0.18814463913440704
2023-01-22 10:33:44.903005: step: 672/466, loss: 0.4814763069152832
2023-01-22 10:33:45.514842: step: 674/466, loss: 0.6384454965591431
2023-01-22 10:33:46.130401: step: 676/466, loss: 0.5807408094406128
2023-01-22 10:33:46.766829: step: 678/466, loss: 0.7347681522369385
2023-01-22 10:33:47.334705: step: 680/466, loss: 0.3069644570350647
2023-01-22 10:33:47.962003: step: 682/466, loss: 9.15442180633545
2023-01-22 10:33:48.668832: step: 684/466, loss: 1.127607822418213
2023-01-22 10:33:49.272645: step: 686/466, loss: 0.92728191614151
2023-01-22 10:33:49.887019: step: 688/466, loss: 0.3164721429347992
2023-01-22 10:33:50.450892: step: 690/466, loss: 0.5347660183906555
2023-01-22 10:33:51.066409: step: 692/466, loss: 0.9528379440307617
2023-01-22 10:33:51.699140: step: 694/466, loss: 0.12908470630645752
2023-01-22 10:33:52.362144: step: 696/466, loss: 0.49494537711143494
2023-01-22 10:33:53.055057: step: 698/466, loss: 0.49588873982429504
2023-01-22 10:33:53.655736: step: 700/466, loss: 0.44561535120010376
2023-01-22 10:33:54.249204: step: 702/466, loss: 0.27392247319221497
2023-01-22 10:33:54.852228: step: 704/466, loss: 0.1783570647239685
2023-01-22 10:33:55.470165: step: 706/466, loss: 0.1547602117061615
2023-01-22 10:33:56.046160: step: 708/466, loss: 0.5803582668304443
2023-01-22 10:33:56.667317: step: 710/466, loss: 0.11984024196863174
2023-01-22 10:33:57.311018: step: 712/466, loss: 0.6738526225090027
2023-01-22 10:33:57.960178: step: 714/466, loss: 0.1570020318031311
2023-01-22 10:33:58.579621: step: 716/466, loss: 0.5142013430595398
2023-01-22 10:33:59.125726: step: 718/466, loss: 0.1734398752450943
2023-01-22 10:33:59.777188: step: 720/466, loss: 0.5289613008499146
2023-01-22 10:34:00.411890: step: 722/466, loss: 0.14029181003570557
2023-01-22 10:34:01.141856: step: 724/466, loss: 0.38573265075683594
2023-01-22 10:34:01.806298: step: 726/466, loss: 0.5696289539337158
2023-01-22 10:34:02.467449: step: 728/466, loss: 0.4644445776939392
2023-01-22 10:34:03.059473: step: 730/466, loss: 0.34148305654525757
2023-01-22 10:34:03.643820: step: 732/466, loss: 1.0923960208892822
2023-01-22 10:34:04.202647: step: 734/466, loss: 0.1537511795759201
2023-01-22 10:34:04.828673: step: 736/466, loss: 0.16307362914085388
2023-01-22 10:34:05.472040: step: 738/466, loss: 0.20459650456905365
2023-01-22 10:34:06.128968: step: 740/466, loss: 0.2831628620624542
2023-01-22 10:34:06.781317: step: 742/466, loss: 0.6424025297164917
2023-01-22 10:34:07.351561: step: 744/466, loss: 0.25834977626800537
2023-01-22 10:34:08.000643: step: 746/466, loss: 0.5080797672271729
2023-01-22 10:34:08.610653: step: 748/466, loss: 0.9643440842628479
2023-01-22 10:34:09.275510: step: 750/466, loss: 0.1867329627275467
2023-01-22 10:34:09.912938: step: 752/466, loss: 1.104346513748169
2023-01-22 10:34:10.554519: step: 754/466, loss: 0.20777837932109833
2023-01-22 10:34:11.197472: step: 756/466, loss: 0.40053248405456543
2023-01-22 10:34:11.892064: step: 758/466, loss: 0.7012250423431396
2023-01-22 10:34:12.436638: step: 760/466, loss: 0.24934914708137512
2023-01-22 10:34:12.986869: step: 762/466, loss: 0.08132177591323853
2023-01-22 10:34:13.553925: step: 764/466, loss: 0.7300129532814026
2023-01-22 10:34:14.199348: step: 766/466, loss: 0.2983568012714386
2023-01-22 10:34:14.790540: step: 768/466, loss: 0.4181157052516937
2023-01-22 10:34:15.462280: step: 770/466, loss: 0.1665697544813156
2023-01-22 10:34:16.104764: step: 772/466, loss: 0.3983364403247833
2023-01-22 10:34:16.749550: step: 774/466, loss: 0.9016590714454651
2023-01-22 10:34:17.395999: step: 776/466, loss: 0.2623269557952881
2023-01-22 10:34:18.020525: step: 778/466, loss: 0.30989834666252136
2023-01-22 10:34:18.663421: step: 780/466, loss: 0.30029258131980896
2023-01-22 10:34:19.351822: step: 782/466, loss: 0.8610550165176392
2023-01-22 10:34:19.950706: step: 784/466, loss: 0.18214188516139984
2023-01-22 10:34:20.600811: step: 786/466, loss: 1.3146240711212158
2023-01-22 10:34:21.207221: step: 788/466, loss: 0.17744801938533783
2023-01-22 10:34:21.846402: step: 790/466, loss: 0.3240196108818054
2023-01-22 10:34:22.543835: step: 792/466, loss: 0.15075667202472687
2023-01-22 10:34:23.209870: step: 794/466, loss: 0.1881697028875351
2023-01-22 10:34:23.888239: step: 796/466, loss: 1.692413568496704
2023-01-22 10:34:24.485585: step: 798/466, loss: 0.1842980831861496
2023-01-22 10:34:25.062349: step: 800/466, loss: 0.9132423400878906
2023-01-22 10:34:25.770142: step: 802/466, loss: 0.25958237051963806
2023-01-22 10:34:26.367685: step: 804/466, loss: 0.46160873770713806
2023-01-22 10:34:26.950919: step: 806/466, loss: 0.5344682931900024
2023-01-22 10:34:27.544698: step: 808/466, loss: 0.3357923924922943
2023-01-22 10:34:28.135498: step: 810/466, loss: 0.16021166741847992
2023-01-22 10:34:28.730787: step: 812/466, loss: 0.15776556730270386
2023-01-22 10:34:29.324053: step: 814/466, loss: 3.033827304840088
2023-01-22 10:34:29.945279: step: 816/466, loss: 0.7120888233184814
2023-01-22 10:34:30.595181: step: 818/466, loss: 0.3273853361606598
2023-01-22 10:34:31.182620: step: 820/466, loss: 0.7432978749275208
2023-01-22 10:34:31.831415: step: 822/466, loss: 0.1920372098684311
2023-01-22 10:34:32.478418: step: 824/466, loss: 1.0010572671890259
2023-01-22 10:34:33.107931: step: 826/466, loss: 1.0172005891799927
2023-01-22 10:34:33.791014: step: 828/466, loss: 0.19087344408035278
2023-01-22 10:34:34.427225: step: 830/466, loss: 0.5420885682106018
2023-01-22 10:34:35.043983: step: 832/466, loss: 0.22804272174835205
2023-01-22 10:34:35.764529: step: 834/466, loss: 0.2788725793361664
2023-01-22 10:34:36.447835: step: 836/466, loss: 0.16794948279857635
2023-01-22 10:34:37.063401: step: 838/466, loss: 0.5333663821220398
2023-01-22 10:34:37.633664: step: 840/466, loss: 0.1299857646226883
2023-01-22 10:34:38.241042: step: 842/466, loss: 0.3256866931915283
2023-01-22 10:34:38.853094: step: 844/466, loss: 0.5658522248268127
2023-01-22 10:34:39.515011: step: 846/466, loss: 0.2746819853782654
2023-01-22 10:34:40.123109: step: 848/466, loss: 0.2980114221572876
2023-01-22 10:34:40.755023: step: 850/466, loss: 0.2512083947658539
2023-01-22 10:34:41.360656: step: 852/466, loss: 0.42742490768432617
2023-01-22 10:34:41.997083: step: 854/466, loss: 0.7600464820861816
2023-01-22 10:34:42.615243: step: 856/466, loss: 0.14330822229385376
2023-01-22 10:34:43.192385: step: 858/466, loss: 1.0403125286102295
2023-01-22 10:34:43.860316: step: 860/466, loss: 0.2647596001625061
2023-01-22 10:34:44.447590: step: 862/466, loss: 0.11951369047164917
2023-01-22 10:34:45.132836: step: 864/466, loss: 0.4448555111885071
2023-01-22 10:34:45.800405: step: 866/466, loss: 0.2565997540950775
2023-01-22 10:34:46.465803: step: 868/466, loss: 0.21580347418785095
2023-01-22 10:34:47.143424: step: 870/466, loss: 1.1926987171173096
2023-01-22 10:34:47.709365: step: 872/466, loss: 0.2284402698278427
2023-01-22 10:34:48.287899: step: 874/466, loss: 0.2942436933517456
2023-01-22 10:34:48.964563: step: 876/466, loss: 0.2567604184150696
2023-01-22 10:34:49.618665: step: 878/466, loss: 0.26719653606414795
2023-01-22 10:34:50.244185: step: 880/466, loss: 0.16044160723686218
2023-01-22 10:34:50.852416: step: 882/466, loss: 0.19051779806613922
2023-01-22 10:34:51.525354: step: 884/466, loss: 5.118203163146973
2023-01-22 10:34:52.191275: step: 886/466, loss: 0.16387850046157837
2023-01-22 10:34:52.868121: step: 888/466, loss: 0.46310433745384216
2023-01-22 10:34:53.481312: step: 890/466, loss: 0.07903813570737839
2023-01-22 10:34:54.060602: step: 892/466, loss: 0.2074670046567917
2023-01-22 10:34:54.657585: step: 894/466, loss: 0.49393320083618164
2023-01-22 10:34:55.295433: step: 896/466, loss: 1.1565308570861816
2023-01-22 10:34:55.924803: step: 898/466, loss: 0.5069413185119629
2023-01-22 10:34:56.559151: step: 900/466, loss: 0.47783806920051575
2023-01-22 10:34:57.181569: step: 902/466, loss: 1.0002384185791016
2023-01-22 10:34:57.746911: step: 904/466, loss: 0.6225457787513733
2023-01-22 10:34:58.320231: step: 906/466, loss: 0.29943346977233887
2023-01-22 10:34:58.930850: step: 908/466, loss: 0.1338597536087036
2023-01-22 10:34:59.521450: step: 910/466, loss: 0.36804789304733276
2023-01-22 10:35:00.106892: step: 912/466, loss: 0.7149313688278198
2023-01-22 10:35:00.859760: step: 914/466, loss: 0.3055904805660248
2023-01-22 10:35:01.520522: step: 916/466, loss: 0.17568480968475342
2023-01-22 10:35:02.134284: step: 918/466, loss: 0.7913815975189209
2023-01-22 10:35:02.773040: step: 920/466, loss: 0.25138628482818604
2023-01-22 10:35:03.382138: step: 922/466, loss: 0.40639394521713257
2023-01-22 10:35:03.995807: step: 924/466, loss: 0.3113460838794708
2023-01-22 10:35:04.560541: step: 926/466, loss: 1.047174334526062
2023-01-22 10:35:05.262884: step: 928/466, loss: 1.0717891454696655
2023-01-22 10:35:05.909351: step: 930/466, loss: 0.12569622695446014
2023-01-22 10:35:06.555335: step: 932/466, loss: 0.19045127928256989
==================================================
Loss: 0.536
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31689272703616966, 'r': 0.3294964150432901, 'f1': 0.32307169385860196}, 'combined': 0.2380528270537067, 'epoch': 8}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.30242231340921544, 'r': 0.2994199258212178, 'f1': 0.30091363066658444}, 'combined': 0.18842255378188, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3052956890947505, 'r': 0.3388319579725829, 'f1': 0.32119079678550055}, 'combined': 0.23666690289457934, 'epoch': 8}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.30736114481862375, 'r': 0.30902555535013254, 'f1': 0.3081911029054427}, 'combined': 0.19099166940618983, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28223545997346305, 'r': 0.34531080898268396, 'f1': 0.31060324896568503}, 'combined': 0.22886555186945212, 'epoch': 8}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.327356138502792, 'r': 0.30044610363038543, 'f1': 0.31332438692306797}, 'combined': 0.20784885073114412, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24479166666666666, 'r': 0.3357142857142857, 'f1': 0.2831325301204819}, 'combined': 0.18875502008032125, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25806451612903225, 'r': 0.34782608695652173, 'f1': 0.2962962962962963}, 'combined': 0.14814814814814814, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.23275862068965517, 'f1': 0.2755102040816327}, 'combined': 0.1836734693877551, 'epoch': 8}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3125951086956522, 'r': 0.2728534155597723, 'f1': 0.2913753799392097}, 'combined': 0.21469764837625976, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32426953156573873, 'r': 0.23676358396812514, 'f1': 0.27369228068511486}, 'combined': 0.1713774094009598, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3157894736842105, 'r': 0.34285714285714286, 'f1': 0.3287671232876712}, 'combined': 0.2191780821917808, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27365358270908674, 'r': 0.3447931288782421, 'f1': 0.3051317865975375}, 'combined': 0.22483394801923812, 'epoch': 7}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.31705946042321687, 'r': 0.2795393255402526, 'f1': 0.29711957116952437}, 'combined': 0.18413043847125452, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3092105263157895, 'r': 0.5108695652173914, 'f1': 0.3852459016393443}, 'combined': 0.19262295081967215, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28223545997346305, 'r': 0.34531080898268396, 'f1': 0.31060324896568503}, 'combined': 0.22886555186945212, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.327356138502792, 'r': 0.30044610363038543, 'f1': 0.31332438692306797}, 'combined': 0.20784885073114412, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3375, 'r': 0.23275862068965517, 'f1': 0.2755102040816327}, 'combined': 0.1836734693877551, '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 10:37:50.446644: step: 2/466, loss: 0.14333821833133698
2023-01-22 10:37:51.082232: step: 4/466, loss: 0.3721154034137726
2023-01-22 10:37:51.691742: step: 6/466, loss: 0.1154833510518074
2023-01-22 10:37:52.315200: step: 8/466, loss: 0.31080323457717896
2023-01-22 10:37:52.914880: step: 10/466, loss: 0.22003662586212158
2023-01-22 10:37:53.523104: step: 12/466, loss: 0.13437055051326752
2023-01-22 10:37:54.131607: step: 14/466, loss: 0.17498359084129333
2023-01-22 10:37:54.702131: step: 16/466, loss: 0.28144538402557373
2023-01-22 10:37:55.333769: step: 18/466, loss: 0.0995631068944931
2023-01-22 10:37:55.952638: step: 20/466, loss: 0.49647435545921326
2023-01-22 10:37:56.485026: step: 22/466, loss: 0.2559816539287567
2023-01-22 10:37:57.055860: step: 24/466, loss: 0.2428935170173645
2023-01-22 10:37:57.738248: step: 26/466, loss: 0.15105891227722168
2023-01-22 10:37:58.359144: step: 28/466, loss: 0.18047349154949188
2023-01-22 10:37:59.027141: step: 30/466, loss: 1.209218144416809
2023-01-22 10:37:59.716200: step: 32/466, loss: 0.3093844950199127
2023-01-22 10:38:00.358916: step: 34/466, loss: 0.25497299432754517
2023-01-22 10:38:00.921491: step: 36/466, loss: 0.2641991376876831
2023-01-22 10:38:01.547957: step: 38/466, loss: 0.11457935720682144
2023-01-22 10:38:02.187030: step: 40/466, loss: 0.4195786714553833
2023-01-22 10:38:02.747842: step: 42/466, loss: 0.1561284363269806
2023-01-22 10:38:03.373265: step: 44/466, loss: 0.3661919832229614
2023-01-22 10:38:04.030673: step: 46/466, loss: 0.24955451488494873
2023-01-22 10:38:04.600694: step: 48/466, loss: 0.11433481425046921
2023-01-22 10:38:05.306896: step: 50/466, loss: 0.07350247353315353
2023-01-22 10:38:05.900286: step: 52/466, loss: 0.12642313539981842
2023-01-22 10:38:06.517585: step: 54/466, loss: 0.6436976790428162
2023-01-22 10:38:07.093384: step: 56/466, loss: 1.2792249917984009
2023-01-22 10:38:07.743310: step: 58/466, loss: 0.11254329234361649
2023-01-22 10:38:08.333794: step: 60/466, loss: 0.17455169558525085
2023-01-22 10:38:08.870065: step: 62/466, loss: 0.2526421546936035
2023-01-22 10:38:09.492260: step: 64/466, loss: 0.7558532953262329
2023-01-22 10:38:10.088569: step: 66/466, loss: 0.4842546582221985
2023-01-22 10:38:10.748684: step: 68/466, loss: 0.15906848013401031
2023-01-22 10:38:11.355159: step: 70/466, loss: 0.2760641276836395
2023-01-22 10:38:11.939447: step: 72/466, loss: 0.6627677083015442
2023-01-22 10:38:12.579976: step: 74/466, loss: 0.7741183638572693
2023-01-22 10:38:13.235464: step: 76/466, loss: 0.1407208889722824
2023-01-22 10:38:13.826501: step: 78/466, loss: 0.49924731254577637
2023-01-22 10:38:14.455957: step: 80/466, loss: 0.9123730659484863
2023-01-22 10:38:15.141602: step: 82/466, loss: 0.11611166596412659
2023-01-22 10:38:15.724399: step: 84/466, loss: 0.6890730261802673
2023-01-22 10:38:16.350806: step: 86/466, loss: 0.3308718502521515
2023-01-22 10:38:16.958744: step: 88/466, loss: 0.10638472437858582
2023-01-22 10:38:17.640477: step: 90/466, loss: 0.14739586412906647
2023-01-22 10:38:18.493171: step: 92/466, loss: 0.3096799850463867
2023-01-22 10:38:19.180178: step: 94/466, loss: 0.25767630338668823
2023-01-22 10:38:19.801467: step: 96/466, loss: 0.7320065498352051
2023-01-22 10:38:20.508275: step: 98/466, loss: 0.524272084236145
2023-01-22 10:38:21.129502: step: 100/466, loss: 0.12355181574821472
2023-01-22 10:38:21.819628: step: 102/466, loss: 0.35262879729270935
2023-01-22 10:38:22.465191: step: 104/466, loss: 0.43407341837882996
2023-01-22 10:38:23.094291: step: 106/466, loss: 0.24438145756721497
2023-01-22 10:38:23.700358: step: 108/466, loss: 0.19344185292720795
2023-01-22 10:38:24.379639: step: 110/466, loss: 0.22223243117332458
2023-01-22 10:38:24.990254: step: 112/466, loss: 0.22712765634059906
2023-01-22 10:38:25.631913: step: 114/466, loss: 0.5355889201164246
2023-01-22 10:38:26.262320: step: 116/466, loss: 0.20177462697029114
2023-01-22 10:38:26.869182: step: 118/466, loss: 3.8853647708892822
2023-01-22 10:38:27.560604: step: 120/466, loss: 0.6942616701126099
2023-01-22 10:38:28.124729: step: 122/466, loss: 0.1367759108543396
2023-01-22 10:38:28.716072: step: 124/466, loss: 0.28530353307724
2023-01-22 10:38:29.315042: step: 126/466, loss: 0.40220534801483154
2023-01-22 10:38:29.957707: step: 128/466, loss: 0.25116458535194397
2023-01-22 10:38:30.557008: step: 130/466, loss: 0.33628004789352417
2023-01-22 10:38:31.205389: step: 132/466, loss: 0.16188682615756989
2023-01-22 10:38:31.811036: step: 134/466, loss: 0.11521150171756744
2023-01-22 10:38:32.421160: step: 136/466, loss: 0.21888132393360138
2023-01-22 10:38:33.022378: step: 138/466, loss: 0.16899710893630981
2023-01-22 10:38:33.686064: step: 140/466, loss: 0.2219388335943222
2023-01-22 10:38:34.347881: step: 142/466, loss: 0.1316850483417511
2023-01-22 10:38:35.012517: step: 144/466, loss: 0.44268444180488586
2023-01-22 10:38:35.637330: step: 146/466, loss: 0.17376552522182465
2023-01-22 10:38:36.258105: step: 148/466, loss: 0.2718490660190582
2023-01-22 10:38:36.815067: step: 150/466, loss: 0.18473376333713531
2023-01-22 10:38:37.423628: step: 152/466, loss: 0.3350732624530792
2023-01-22 10:38:38.032078: step: 154/466, loss: 0.18617266416549683
2023-01-22 10:38:38.617389: step: 156/466, loss: 0.5854041576385498
2023-01-22 10:38:39.325653: step: 158/466, loss: 0.20790636539459229
2023-01-22 10:38:39.933138: step: 160/466, loss: 0.1810241937637329
2023-01-22 10:38:40.609669: step: 162/466, loss: 0.5088878273963928
2023-01-22 10:38:41.314973: step: 164/466, loss: 1.458961009979248
2023-01-22 10:38:41.990023: step: 166/466, loss: 3.8906965255737305
2023-01-22 10:38:42.581783: step: 168/466, loss: 0.3065788745880127
2023-01-22 10:38:43.137044: step: 170/466, loss: 0.30616405606269836
2023-01-22 10:38:43.707350: step: 172/466, loss: 0.3278638422489166
2023-01-22 10:38:44.337201: step: 174/466, loss: 0.458742618560791
2023-01-22 10:38:44.972511: step: 176/466, loss: 0.507235586643219
2023-01-22 10:38:45.566032: step: 178/466, loss: 0.16787923872470856
2023-01-22 10:38:46.269342: step: 180/466, loss: 0.89646315574646
2023-01-22 10:38:46.963554: step: 182/466, loss: 0.11676928400993347
2023-01-22 10:38:47.530829: step: 184/466, loss: 0.517906665802002
2023-01-22 10:38:48.133281: step: 186/466, loss: 1.5923292636871338
2023-01-22 10:38:48.760668: step: 188/466, loss: 0.17046838998794556
2023-01-22 10:38:49.342038: step: 190/466, loss: 0.20602427423000336
2023-01-22 10:38:49.978793: step: 192/466, loss: 0.5573226809501648
2023-01-22 10:38:50.584497: step: 194/466, loss: 0.4264920949935913
2023-01-22 10:38:51.244748: step: 196/466, loss: 0.18450847268104553
2023-01-22 10:38:51.835023: step: 198/466, loss: 0.07594388723373413
2023-01-22 10:38:52.508892: step: 200/466, loss: 0.7025171518325806
2023-01-22 10:38:53.020863: step: 202/466, loss: 0.48026180267333984
2023-01-22 10:38:53.638201: step: 204/466, loss: 0.13154345750808716
2023-01-22 10:38:54.298305: step: 206/466, loss: 0.6287126541137695
2023-01-22 10:38:54.901053: step: 208/466, loss: 0.960460364818573
2023-01-22 10:38:55.560366: step: 210/466, loss: 1.5425586700439453
2023-01-22 10:38:56.228875: step: 212/466, loss: 0.3823030889034271
2023-01-22 10:38:56.805973: step: 214/466, loss: 0.25595736503601074
2023-01-22 10:38:57.477031: step: 216/466, loss: 0.20159533619880676
2023-01-22 10:38:58.109736: step: 218/466, loss: 0.23626333475112915
2023-01-22 10:38:58.792150: step: 220/466, loss: 0.4423496425151825
2023-01-22 10:38:59.354146: step: 222/466, loss: 0.0924079641699791
2023-01-22 10:39:00.032979: step: 224/466, loss: 0.3597632944583893
2023-01-22 10:39:00.641638: step: 226/466, loss: 0.15774992108345032
2023-01-22 10:39:01.252125: step: 228/466, loss: 0.21371318399906158
2023-01-22 10:39:01.933225: step: 230/466, loss: 0.5776114463806152
2023-01-22 10:39:02.620203: step: 232/466, loss: 0.13860873878002167
2023-01-22 10:39:03.212108: step: 234/466, loss: 0.6534222364425659
2023-01-22 10:39:03.833354: step: 236/466, loss: 0.31477588415145874
2023-01-22 10:39:04.395614: step: 238/466, loss: 1.035041332244873
2023-01-22 10:39:04.964628: step: 240/466, loss: 0.7310987114906311
2023-01-22 10:39:05.566999: step: 242/466, loss: 0.48828408122062683
2023-01-22 10:39:06.218845: step: 244/466, loss: 0.4517148435115814
2023-01-22 10:39:06.812579: step: 246/466, loss: 0.07291319221258163
2023-01-22 10:39:07.365447: step: 248/466, loss: 0.2562633454799652
2023-01-22 10:39:07.974231: step: 250/466, loss: 0.23484401404857635
2023-01-22 10:39:08.649261: step: 252/466, loss: 0.19312064349651337
2023-01-22 10:39:09.317440: step: 254/466, loss: 0.17013314366340637
2023-01-22 10:39:09.978041: step: 256/466, loss: 0.17698858678340912
2023-01-22 10:39:10.605757: step: 258/466, loss: 0.2043430656194687
2023-01-22 10:39:11.260165: step: 260/466, loss: 0.24182303249835968
2023-01-22 10:39:11.830697: step: 262/466, loss: 0.4848344624042511
2023-01-22 10:39:12.511171: step: 264/466, loss: 0.7192230224609375
2023-01-22 10:39:13.201644: step: 266/466, loss: 0.4204176366329193
2023-01-22 10:39:13.831244: step: 268/466, loss: 0.2875136435031891
2023-01-22 10:39:14.447591: step: 270/466, loss: 0.0769433081150055
2023-01-22 10:39:15.031685: step: 272/466, loss: 0.15030288696289062
2023-01-22 10:39:15.655395: step: 274/466, loss: 0.8517444133758545
2023-01-22 10:39:16.360331: step: 276/466, loss: 0.4224884510040283
2023-01-22 10:39:16.959798: step: 278/466, loss: 0.8873869180679321
2023-01-22 10:39:17.603071: step: 280/466, loss: 2.515134572982788
2023-01-22 10:39:18.187613: step: 282/466, loss: 0.2280302494764328
2023-01-22 10:39:18.746442: step: 284/466, loss: 0.08815629780292511
2023-01-22 10:39:19.457128: step: 286/466, loss: 0.4746396541595459
2023-01-22 10:39:20.109499: step: 288/466, loss: 0.2827693819999695
2023-01-22 10:39:20.760173: step: 290/466, loss: 0.16482758522033691
2023-01-22 10:39:21.370313: step: 292/466, loss: 0.7850125432014465
2023-01-22 10:39:21.998599: step: 294/466, loss: 0.20151492953300476
2023-01-22 10:39:22.672258: step: 296/466, loss: 0.6452239155769348
2023-01-22 10:39:23.266478: step: 298/466, loss: 1.8399653434753418
2023-01-22 10:39:24.042487: step: 300/466, loss: 1.0284277200698853
2023-01-22 10:39:24.666741: step: 302/466, loss: 0.14042891561985016
2023-01-22 10:39:25.236403: step: 304/466, loss: 0.17981228232383728
2023-01-22 10:39:25.910852: step: 306/466, loss: 0.8614758849143982
2023-01-22 10:39:26.496224: step: 308/466, loss: 0.17790968716144562
2023-01-22 10:39:27.148068: step: 310/466, loss: 0.22819513082504272
2023-01-22 10:39:27.737987: step: 312/466, loss: 0.18512138724327087
2023-01-22 10:39:28.376527: step: 314/466, loss: 0.46361806988716125
2023-01-22 10:39:29.018701: step: 316/466, loss: 0.5142015218734741
2023-01-22 10:39:29.625683: step: 318/466, loss: 0.20874568819999695
2023-01-22 10:39:30.225324: step: 320/466, loss: 0.4852907061576843
2023-01-22 10:39:30.805570: step: 322/466, loss: 0.39413660764694214
2023-01-22 10:39:31.396352: step: 324/466, loss: 0.29739612340927124
2023-01-22 10:39:31.998211: step: 326/466, loss: 0.7066906690597534
2023-01-22 10:39:32.565496: step: 328/466, loss: 0.2640800476074219
2023-01-22 10:39:33.195263: step: 330/466, loss: 0.39870014786720276
2023-01-22 10:39:33.807321: step: 332/466, loss: 0.991432249546051
2023-01-22 10:39:34.467519: step: 334/466, loss: 0.14665810763835907
2023-01-22 10:39:35.063483: step: 336/466, loss: 0.09133289754390717
2023-01-22 10:39:35.688418: step: 338/466, loss: 0.11483022570610046
2023-01-22 10:39:36.392514: step: 340/466, loss: 1.3138666152954102
2023-01-22 10:39:37.034499: step: 342/466, loss: 0.320402055978775
2023-01-22 10:39:37.706808: step: 344/466, loss: 0.7380730509757996
2023-01-22 10:39:38.331213: step: 346/466, loss: 1.4596487283706665
2023-01-22 10:39:38.935282: step: 348/466, loss: 0.773550271987915
2023-01-22 10:39:39.600359: step: 350/466, loss: 0.1945510059595108
2023-01-22 10:39:40.284074: step: 352/466, loss: 0.33311906456947327
2023-01-22 10:39:40.885540: step: 354/466, loss: 0.08922120928764343
2023-01-22 10:39:41.501781: step: 356/466, loss: 0.35805872082710266
2023-01-22 10:39:42.181936: step: 358/466, loss: 0.42160797119140625
2023-01-22 10:39:42.827989: step: 360/466, loss: 0.2711777985095978
2023-01-22 10:39:43.443203: step: 362/466, loss: 0.5504414439201355
2023-01-22 10:39:44.070359: step: 364/466, loss: 0.11443190276622772
2023-01-22 10:39:44.719770: step: 366/466, loss: 0.10705424100160599
2023-01-22 10:39:45.330697: step: 368/466, loss: 0.422481894493103
2023-01-22 10:39:45.942179: step: 370/466, loss: 0.257695734500885
2023-01-22 10:39:46.581271: step: 372/466, loss: 1.4501545429229736
2023-01-22 10:39:47.156692: step: 374/466, loss: 0.10965612530708313
2023-01-22 10:39:47.766489: step: 376/466, loss: 0.2261856198310852
2023-01-22 10:39:48.432632: step: 378/466, loss: 0.14318789541721344
2023-01-22 10:39:49.036599: step: 380/466, loss: 0.2959175407886505
2023-01-22 10:39:49.620785: step: 382/466, loss: 0.16589011251926422
2023-01-22 10:39:50.218227: step: 384/466, loss: 0.2049659788608551
2023-01-22 10:39:50.846091: step: 386/466, loss: 0.4398001730442047
2023-01-22 10:39:51.515100: step: 388/466, loss: 0.8791870474815369
2023-01-22 10:39:52.124785: step: 390/466, loss: 0.38660451769828796
2023-01-22 10:39:52.817892: step: 392/466, loss: 0.8298895359039307
2023-01-22 10:39:53.387898: step: 394/466, loss: 0.27300766110420227
2023-01-22 10:39:54.021537: step: 396/466, loss: 0.30740171670913696
2023-01-22 10:39:54.712587: step: 398/466, loss: 0.5869360566139221
2023-01-22 10:39:55.321597: step: 400/466, loss: 0.1795710325241089
2023-01-22 10:39:55.979418: step: 402/466, loss: 0.34334051609039307
2023-01-22 10:39:56.581500: step: 404/466, loss: 0.7431521415710449
2023-01-22 10:39:57.216423: step: 406/466, loss: 0.3503372073173523
2023-01-22 10:39:57.801002: step: 408/466, loss: 0.47325900197029114
2023-01-22 10:39:58.394609: step: 410/466, loss: 0.2354981154203415
2023-01-22 10:39:59.008030: step: 412/466, loss: 0.8883786797523499
2023-01-22 10:39:59.644113: step: 414/466, loss: 0.3884502053260803
2023-01-22 10:40:00.335102: step: 416/466, loss: 0.42652392387390137
2023-01-22 10:40:00.992015: step: 418/466, loss: 0.4728102385997772
2023-01-22 10:40:01.628282: step: 420/466, loss: 0.16548635065555573
2023-01-22 10:40:02.304528: step: 422/466, loss: 0.23618537187576294
2023-01-22 10:40:02.988574: step: 424/466, loss: 0.7445458173751831
2023-01-22 10:40:03.635655: step: 426/466, loss: 0.24472343921661377
2023-01-22 10:40:04.280119: step: 428/466, loss: 0.12914451956748962
2023-01-22 10:40:04.921247: step: 430/466, loss: 0.28074443340301514
2023-01-22 10:40:05.467579: step: 432/466, loss: 0.4233020544052124
2023-01-22 10:40:06.115988: step: 434/466, loss: 0.1644560694694519
2023-01-22 10:40:06.759919: step: 436/466, loss: 0.23518234491348267
2023-01-22 10:40:07.358973: step: 438/466, loss: 0.40295037627220154
2023-01-22 10:40:08.009266: step: 440/466, loss: 0.5894485712051392
2023-01-22 10:40:08.625919: step: 442/466, loss: 0.17456242442131042
2023-01-22 10:40:09.277362: step: 444/466, loss: 0.1628921926021576
2023-01-22 10:40:09.910497: step: 446/466, loss: 0.28210774064064026
2023-01-22 10:40:10.516591: step: 448/466, loss: 0.4841403365135193
2023-01-22 10:40:11.140742: step: 450/466, loss: 0.23069562017917633
2023-01-22 10:40:11.774671: step: 452/466, loss: 0.14583279192447662
2023-01-22 10:40:12.426641: step: 454/466, loss: 0.1791859269142151
2023-01-22 10:40:13.033084: step: 456/466, loss: 1.2605204582214355
2023-01-22 10:40:13.723360: step: 458/466, loss: 0.3231509327888489
2023-01-22 10:40:14.324141: step: 460/466, loss: 0.14519108831882477
2023-01-22 10:40:14.924084: step: 462/466, loss: 0.4772692918777466
2023-01-22 10:40:15.568632: step: 464/466, loss: 0.20196957886219025
2023-01-22 10:40:16.161706: step: 466/466, loss: 0.42681217193603516
2023-01-22 10:40:16.784776: step: 468/466, loss: 0.2679383158683777
2023-01-22 10:40:17.413540: step: 470/466, loss: 0.17321833968162537
2023-01-22 10:40:18.047938: step: 472/466, loss: 0.7088302969932556
2023-01-22 10:40:18.772523: step: 474/466, loss: 0.5940250754356384
2023-01-22 10:40:19.383913: step: 476/466, loss: 0.24723488092422485
2023-01-22 10:40:20.089237: step: 478/466, loss: 0.5523827075958252
2023-01-22 10:40:20.695647: step: 480/466, loss: 0.1399628221988678
2023-01-22 10:40:21.318378: step: 482/466, loss: 0.20225651562213898
2023-01-22 10:40:21.892149: step: 484/466, loss: 0.41005074977874756
2023-01-22 10:40:22.555751: step: 486/466, loss: 0.4968833923339844
2023-01-22 10:40:23.127975: step: 488/466, loss: 0.172898069024086
2023-01-22 10:40:23.788840: step: 490/466, loss: 0.44241058826446533
2023-01-22 10:40:24.376694: step: 492/466, loss: 0.24638186395168304
2023-01-22 10:40:24.983772: step: 494/466, loss: 0.1952744871377945
2023-01-22 10:40:25.666086: step: 496/466, loss: 0.3134210407733917
2023-01-22 10:40:26.306740: step: 498/466, loss: 0.2878206968307495
2023-01-22 10:40:26.904480: step: 500/466, loss: 0.16420000791549683
2023-01-22 10:40:27.520408: step: 502/466, loss: 0.05525343492627144
2023-01-22 10:40:28.091804: step: 504/466, loss: 0.4072072505950928
2023-01-22 10:40:28.649063: step: 506/466, loss: 0.26593515276908875
2023-01-22 10:40:29.321211: step: 508/466, loss: 0.1372692883014679
2023-01-22 10:40:29.894678: step: 510/466, loss: 0.10550988465547562
2023-01-22 10:40:30.479389: step: 512/466, loss: 0.43171632289886475
2023-01-22 10:40:31.105776: step: 514/466, loss: 0.3661409914493561
2023-01-22 10:40:31.748944: step: 516/466, loss: 0.26294615864753723
2023-01-22 10:40:32.419755: step: 518/466, loss: 0.25712138414382935
2023-01-22 10:40:33.024838: step: 520/466, loss: 0.27735304832458496
2023-01-22 10:40:33.591773: step: 522/466, loss: 1.425169825553894
2023-01-22 10:40:34.144231: step: 524/466, loss: 0.34775903820991516
2023-01-22 10:40:34.862791: step: 526/466, loss: 0.06502726674079895
2023-01-22 10:40:35.548669: step: 528/466, loss: 0.29903191328048706
2023-01-22 10:40:36.196408: step: 530/466, loss: 0.2911469638347626
2023-01-22 10:40:36.825123: step: 532/466, loss: 0.19249558448791504
2023-01-22 10:40:37.412178: step: 534/466, loss: 0.5120958685874939
2023-01-22 10:40:37.949073: step: 536/466, loss: 0.25753968954086304
2023-01-22 10:40:38.662039: step: 538/466, loss: 0.3769363462924957
2023-01-22 10:40:39.255447: step: 540/466, loss: 0.2791467308998108
2023-01-22 10:40:39.818477: step: 542/466, loss: 0.5322665572166443
2023-01-22 10:40:40.441903: step: 544/466, loss: 0.5498647689819336
2023-01-22 10:40:41.048192: step: 546/466, loss: 0.1426161825656891
2023-01-22 10:40:41.651410: step: 548/466, loss: 0.4128901958465576
2023-01-22 10:40:42.282054: step: 550/466, loss: 0.17598459124565125
2023-01-22 10:40:42.906304: step: 552/466, loss: 0.21260590851306915
2023-01-22 10:40:43.494999: step: 554/466, loss: 0.5410464406013489
2023-01-22 10:40:44.112919: step: 556/466, loss: 0.2087046205997467
2023-01-22 10:40:44.714876: step: 558/466, loss: 0.29485809803009033
2023-01-22 10:40:45.351106: step: 560/466, loss: 0.3445322513580322
2023-01-22 10:40:45.920070: step: 562/466, loss: 0.1379055231809616
2023-01-22 10:40:46.595253: step: 564/466, loss: 0.19649401307106018
2023-01-22 10:40:47.179649: step: 566/466, loss: 0.24501477181911469
2023-01-22 10:40:47.810853: step: 568/466, loss: 0.3747404217720032
2023-01-22 10:40:48.520383: step: 570/466, loss: 0.1150267943739891
2023-01-22 10:40:49.171769: step: 572/466, loss: 0.2907281816005707
2023-01-22 10:40:49.802960: step: 574/466, loss: 0.2371668964624405
2023-01-22 10:40:50.375956: step: 576/466, loss: 0.37155136466026306
2023-01-22 10:40:50.972413: step: 578/466, loss: 0.51060551404953
2023-01-22 10:40:51.595642: step: 580/466, loss: 0.35388556122779846
2023-01-22 10:40:52.176670: step: 582/466, loss: 0.386762797832489
2023-01-22 10:40:52.845338: step: 584/466, loss: 0.43013936281204224
2023-01-22 10:40:53.529110: step: 586/466, loss: 0.10582101345062256
2023-01-22 10:40:54.114462: step: 588/466, loss: 0.09551119059324265
2023-01-22 10:40:54.757203: step: 590/466, loss: 1.1651842594146729
2023-01-22 10:40:55.419097: step: 592/466, loss: 0.4927811026573181
2023-01-22 10:40:55.992140: step: 594/466, loss: 0.3293505609035492
2023-01-22 10:40:56.616377: step: 596/466, loss: 0.11302569508552551
2023-01-22 10:40:57.286649: step: 598/466, loss: 0.1843276470899582
2023-01-22 10:40:57.927632: step: 600/466, loss: 0.2377513200044632
2023-01-22 10:40:58.589429: step: 602/466, loss: 0.1325540989637375
2023-01-22 10:40:59.169423: step: 604/466, loss: 2.2765705585479736
2023-01-22 10:40:59.804327: step: 606/466, loss: 0.35985463857650757
2023-01-22 10:41:00.472448: step: 608/466, loss: 0.4295981228351593
2023-01-22 10:41:01.053472: step: 610/466, loss: 0.19231435656547546
2023-01-22 10:41:01.778669: step: 612/466, loss: 0.13297294080257416
2023-01-22 10:41:02.319326: step: 614/466, loss: 0.21880677342414856
2023-01-22 10:41:02.940888: step: 616/466, loss: 0.09613621234893799
2023-01-22 10:41:03.663818: step: 618/466, loss: 0.16539478302001953
2023-01-22 10:41:04.288338: step: 620/466, loss: 0.3807227313518524
2023-01-22 10:41:04.872896: step: 622/466, loss: 0.2249719202518463
2023-01-22 10:41:05.407106: step: 624/466, loss: 0.09430894255638123
2023-01-22 10:41:05.998423: step: 626/466, loss: 0.3039550483226776
2023-01-22 10:41:06.655101: step: 628/466, loss: 0.17318031191825867
2023-01-22 10:41:07.236831: step: 630/466, loss: 0.3045390844345093
2023-01-22 10:41:07.860654: step: 632/466, loss: 0.08908650279045105
2023-01-22 10:41:08.475822: step: 634/466, loss: 0.045281678438186646
2023-01-22 10:41:09.098001: step: 636/466, loss: 0.28397464752197266
2023-01-22 10:41:09.701737: step: 638/466, loss: 0.2249760925769806
2023-01-22 10:41:10.341678: step: 640/466, loss: 0.16043658554553986
2023-01-22 10:41:10.952419: step: 642/466, loss: 0.12697969377040863
2023-01-22 10:41:11.571528: step: 644/466, loss: 0.5979228615760803
2023-01-22 10:41:12.220929: step: 646/466, loss: 1.1969491243362427
2023-01-22 10:41:12.889226: step: 648/466, loss: 0.30741339921951294
2023-01-22 10:41:13.502239: step: 650/466, loss: 0.17364108562469482
2023-01-22 10:41:14.131047: step: 652/466, loss: 0.9397881627082825
2023-01-22 10:41:14.689251: step: 654/466, loss: 0.26951509714126587
2023-01-22 10:41:15.343339: step: 656/466, loss: 0.13325363397598267
2023-01-22 10:41:15.938823: step: 658/466, loss: 0.868958592414856
2023-01-22 10:41:16.643805: step: 660/466, loss: 0.4372906982898712
2023-01-22 10:41:17.270032: step: 662/466, loss: 0.24490392208099365
2023-01-22 10:41:17.856234: step: 664/466, loss: 0.07556468993425369
2023-01-22 10:41:18.451580: step: 666/466, loss: 0.3491494655609131
2023-01-22 10:41:19.091198: step: 668/466, loss: 0.34895455837249756
2023-01-22 10:41:19.733819: step: 670/466, loss: 0.12369483709335327
2023-01-22 10:41:20.351383: step: 672/466, loss: 0.36864712834358215
2023-01-22 10:41:21.034130: step: 674/466, loss: 0.2754892110824585
2023-01-22 10:41:21.675912: step: 676/466, loss: 0.5482978224754333
2023-01-22 10:41:22.304518: step: 678/466, loss: 0.31320154666900635
2023-01-22 10:41:22.938247: step: 680/466, loss: 1.316051721572876
2023-01-22 10:41:23.546891: step: 682/466, loss: 0.3966720402240753
2023-01-22 10:41:24.250010: step: 684/466, loss: 0.277188777923584
2023-01-22 10:41:24.889133: step: 686/466, loss: 0.23997512459754944
2023-01-22 10:41:25.627648: step: 688/466, loss: 0.5385978817939758
2023-01-22 10:41:26.232122: step: 690/466, loss: 0.19652266800403595
2023-01-22 10:41:26.858270: step: 692/466, loss: 0.25740042328834534
2023-01-22 10:41:27.508796: step: 694/466, loss: 0.2064402997493744
2023-01-22 10:41:28.134117: step: 696/466, loss: 0.18065351247787476
2023-01-22 10:41:28.750957: step: 698/466, loss: 0.12909433245658875
2023-01-22 10:41:29.357060: step: 700/466, loss: 1.1202539205551147
2023-01-22 10:41:30.060827: step: 702/466, loss: 0.17530035972595215
2023-01-22 10:41:30.663130: step: 704/466, loss: 0.21027502417564392
2023-01-22 10:41:31.264606: step: 706/466, loss: 0.17757992446422577
2023-01-22 10:41:31.892866: step: 708/466, loss: 0.17123140394687653
2023-01-22 10:41:32.507951: step: 710/466, loss: 0.2377919703722
2023-01-22 10:41:33.090767: step: 712/466, loss: 0.37611502408981323
2023-01-22 10:41:33.630960: step: 714/466, loss: 0.3173653483390808
2023-01-22 10:41:34.276754: step: 716/466, loss: 0.3790663182735443
2023-01-22 10:41:34.903323: step: 718/466, loss: 2.566300392150879
2023-01-22 10:41:35.530506: step: 720/466, loss: 0.17286144196987152
2023-01-22 10:41:36.103772: step: 722/466, loss: 0.24581412971019745
2023-01-22 10:41:36.772634: step: 724/466, loss: 0.4705178439617157
2023-01-22 10:41:37.427008: step: 726/466, loss: 0.15359728038311005
2023-01-22 10:41:38.091331: step: 728/466, loss: 0.463126003742218
2023-01-22 10:41:38.735312: step: 730/466, loss: 0.29831749200820923
2023-01-22 10:41:39.331419: step: 732/466, loss: 0.3101665675640106
2023-01-22 10:41:39.966653: step: 734/466, loss: 0.31220731139183044
2023-01-22 10:41:40.580019: step: 736/466, loss: 0.20585808157920837
2023-01-22 10:41:41.206565: step: 738/466, loss: 0.1852637231349945
2023-01-22 10:41:41.894189: step: 740/466, loss: 0.3673744797706604
2023-01-22 10:41:42.567041: step: 742/466, loss: 0.5200921893119812
2023-01-22 10:41:43.197715: step: 744/466, loss: 0.3681810200214386
2023-01-22 10:41:43.771081: step: 746/466, loss: 0.446247935295105
2023-01-22 10:41:44.457872: step: 748/466, loss: 0.3060239553451538
2023-01-22 10:41:45.076487: step: 750/466, loss: 0.2827172875404358
2023-01-22 10:41:45.757290: step: 752/466, loss: 0.5558502674102783
2023-01-22 10:41:46.397258: step: 754/466, loss: 0.13139766454696655
2023-01-22 10:41:47.081097: step: 756/466, loss: 0.3317015767097473
2023-01-22 10:41:47.729195: step: 758/466, loss: 0.2862865924835205
2023-01-22 10:41:48.363315: step: 760/466, loss: 0.15090171992778778
2023-01-22 10:41:49.033669: step: 762/466, loss: 0.2872665822505951
2023-01-22 10:41:49.638674: step: 764/466, loss: 1.0078598260879517
2023-01-22 10:41:50.249920: step: 766/466, loss: 0.3062320053577423
2023-01-22 10:41:50.855494: step: 768/466, loss: 0.22913332283496857
2023-01-22 10:41:51.462146: step: 770/466, loss: 0.9309630990028381
2023-01-22 10:41:51.997798: step: 772/466, loss: 0.2182549238204956
2023-01-22 10:41:52.610915: step: 774/466, loss: 0.5010969042778015
2023-01-22 10:41:53.255658: step: 776/466, loss: 0.23311811685562134
2023-01-22 10:41:53.926955: step: 778/466, loss: 0.24458865821361542
2023-01-22 10:41:54.490385: step: 780/466, loss: 0.5709508061408997
2023-01-22 10:41:55.199898: step: 782/466, loss: 0.4269219636917114
2023-01-22 10:41:55.809479: step: 784/466, loss: 0.1943705976009369
2023-01-22 10:41:56.420587: step: 786/466, loss: 0.20909816026687622
2023-01-22 10:41:57.074882: step: 788/466, loss: 0.15215927362442017
2023-01-22 10:41:57.666937: step: 790/466, loss: 0.3103340268135071
2023-01-22 10:41:58.258861: step: 792/466, loss: 0.28564512729644775
2023-01-22 10:41:58.920587: step: 794/466, loss: 0.9070299863815308
2023-01-22 10:41:59.577424: step: 796/466, loss: 0.29510730504989624
2023-01-22 10:42:00.135768: step: 798/466, loss: 0.22085902094841003
2023-01-22 10:42:00.726447: step: 800/466, loss: 2.387493371963501
2023-01-22 10:42:01.368353: step: 802/466, loss: 0.11658139526844025
2023-01-22 10:42:01.943411: step: 804/466, loss: 0.1715186983346939
2023-01-22 10:42:02.552475: step: 806/466, loss: 0.35206925868988037
2023-01-22 10:42:03.089116: step: 808/466, loss: 0.0895785465836525
2023-01-22 10:42:03.678843: step: 810/466, loss: 0.4298768937587738
2023-01-22 10:42:04.366088: step: 812/466, loss: 0.5055814385414124
2023-01-22 10:42:04.975925: step: 814/466, loss: 0.4311542510986328
2023-01-22 10:42:05.609463: step: 816/466, loss: 0.20049983263015747
2023-01-22 10:42:06.218448: step: 818/466, loss: 0.15987136960029602
2023-01-22 10:42:06.953689: step: 820/466, loss: 0.15413245558738708
2023-01-22 10:42:07.574182: step: 822/466, loss: 0.18975743651390076
2023-01-22 10:42:08.230251: step: 824/466, loss: 0.2768426239490509
2023-01-22 10:42:08.851230: step: 826/466, loss: 0.14185315370559692
2023-01-22 10:42:09.528286: step: 828/466, loss: 0.9774134159088135
2023-01-22 10:42:10.131639: step: 830/466, loss: 0.09398987889289856
2023-01-22 10:42:10.789277: step: 832/466, loss: 0.20575417578220367
2023-01-22 10:42:11.420506: step: 834/466, loss: 1.6657462120056152
2023-01-22 10:42:12.078633: step: 836/466, loss: 0.1069575697183609
2023-01-22 10:42:12.820693: step: 838/466, loss: 0.7195698618888855
2023-01-22 10:42:13.403697: step: 840/466, loss: 0.6453332304954529
2023-01-22 10:42:14.042317: step: 842/466, loss: 0.12283100187778473
2023-01-22 10:42:14.711809: step: 844/466, loss: 0.2211642861366272
2023-01-22 10:42:15.303344: step: 846/466, loss: 0.5271596908569336
2023-01-22 10:42:15.973701: step: 848/466, loss: 0.6781986951828003
2023-01-22 10:42:16.663346: step: 850/466, loss: 0.09970416128635406
2023-01-22 10:42:17.266022: step: 852/466, loss: 0.434560626745224
2023-01-22 10:42:17.861770: step: 854/466, loss: 0.2963170111179352
2023-01-22 10:42:18.476306: step: 856/466, loss: 0.5884841680526733
2023-01-22 10:42:19.112504: step: 858/466, loss: 0.8253400325775146
2023-01-22 10:42:19.703605: step: 860/466, loss: 0.5129435062408447
2023-01-22 10:42:20.279796: step: 862/466, loss: 0.2506413161754608
2023-01-22 10:42:20.925044: step: 864/466, loss: 0.31779375672340393
2023-01-22 10:42:21.569107: step: 866/466, loss: 0.44427239894866943
2023-01-22 10:42:22.139403: step: 868/466, loss: 0.14660854637622833
2023-01-22 10:42:22.710577: step: 870/466, loss: 0.13683336973190308
2023-01-22 10:42:23.393234: step: 872/466, loss: 0.607457160949707
2023-01-22 10:42:24.012004: step: 874/466, loss: 0.12032435834407806
2023-01-22 10:42:24.627314: step: 876/466, loss: 0.1489037722349167
2023-01-22 10:42:25.253639: step: 878/466, loss: 0.539090096950531
2023-01-22 10:42:25.838107: step: 880/466, loss: 0.3116208612918854
2023-01-22 10:42:26.485853: step: 882/466, loss: 0.2158992737531662
2023-01-22 10:42:27.121900: step: 884/466, loss: 0.2425546646118164
2023-01-22 10:42:27.798086: step: 886/466, loss: 0.5707557797431946
2023-01-22 10:42:28.403982: step: 888/466, loss: 0.7293208837509155
2023-01-22 10:42:29.024812: step: 890/466, loss: 0.7477041482925415
2023-01-22 10:42:29.685507: step: 892/466, loss: 0.6065076589584351
2023-01-22 10:42:30.440504: step: 894/466, loss: 0.17689277231693268
2023-01-22 10:42:31.185491: step: 896/466, loss: 1.6025630235671997
2023-01-22 10:42:31.870402: step: 898/466, loss: 0.08351809531450272
2023-01-22 10:42:32.460081: step: 900/466, loss: 0.541731059551239
2023-01-22 10:42:33.072290: step: 902/466, loss: 0.6780999302864075
2023-01-22 10:42:33.654641: step: 904/466, loss: 0.20099695026874542
2023-01-22 10:42:34.341903: step: 906/466, loss: 2.1794590950012207
2023-01-22 10:42:34.878016: step: 908/466, loss: 0.11681900918483734
2023-01-22 10:42:35.507568: step: 910/466, loss: 2.078395366668701
2023-01-22 10:42:36.127006: step: 912/466, loss: 0.3107766807079315
2023-01-22 10:42:36.747857: step: 914/466, loss: 0.09672574698925018
2023-01-22 10:42:37.373875: step: 916/466, loss: 0.1826476752758026
2023-01-22 10:42:37.995039: step: 918/466, loss: 0.2181442677974701
2023-01-22 10:42:38.586645: step: 920/466, loss: 0.14747542142868042
2023-01-22 10:42:39.205353: step: 922/466, loss: 0.3388816714286804
2023-01-22 10:42:39.847855: step: 924/466, loss: 0.15716803073883057
2023-01-22 10:42:40.460694: step: 926/466, loss: 0.2093413770198822
2023-01-22 10:42:41.059924: step: 928/466, loss: 0.19133101403713226
2023-01-22 10:42:41.732924: step: 930/466, loss: 0.1611374169588089
2023-01-22 10:42:42.336882: step: 932/466, loss: 0.272554874420166
==================================================
Loss: 0.409
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31577048417132214, 'r': 0.3211529356060606, 'f1': 0.3184389671361502}, 'combined': 0.23463923894242647, 'epoch': 9}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3284561871627026, 'r': 0.29466195851960864, 'f1': 0.3106426736819471}, 'combined': 0.1925109527043052, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.34615384615384615, 'r': 0.391304347826087, 'f1': 0.36734693877551017}, 'combined': 0.18367346938775508, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
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': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27365358270908674, 'r': 0.3447931288782421, 'f1': 0.3051317865975375}, 'combined': 0.22483394801923812, 'epoch': 7}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.31705946042321687, 'r': 0.2795393255402526, 'f1': 0.29711957116952437}, 'combined': 0.18413043847125452, 'epoch': 7}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3092105263157895, 'r': 0.5108695652173914, 'f1': 0.3852459016393443}, 'combined': 0.19262295081967215, 'epoch': 7}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 10:45:30.017928: step: 2/466, loss: 0.06481149047613144
2023-01-22 10:45:30.614466: step: 4/466, loss: 0.1914258748292923
2023-01-22 10:45:31.220398: step: 6/466, loss: 0.3393650949001312
2023-01-22 10:45:31.856041: step: 8/466, loss: 0.13467082381248474
2023-01-22 10:45:32.509250: step: 10/466, loss: 0.3454969823360443
2023-01-22 10:45:33.137284: step: 12/466, loss: 0.8786474466323853
2023-01-22 10:45:33.737189: step: 14/466, loss: 0.5851201415061951
2023-01-22 10:45:34.394208: step: 16/466, loss: 0.07797753065824509
2023-01-22 10:45:34.990179: step: 18/466, loss: 0.08148655295372009
2023-01-22 10:45:35.569982: step: 20/466, loss: 0.23666100203990936
2023-01-22 10:45:36.162713: step: 22/466, loss: 0.0680367574095726
2023-01-22 10:45:36.908879: step: 24/466, loss: 0.521649956703186
2023-01-22 10:45:37.568258: step: 26/466, loss: 0.5934398174285889
2023-01-22 10:45:38.178102: step: 28/466, loss: 0.5916581153869629
2023-01-22 10:45:38.810799: step: 30/466, loss: 0.2847846746444702
2023-01-22 10:45:39.366939: step: 32/466, loss: 0.1682792603969574
2023-01-22 10:45:40.072354: step: 34/466, loss: 0.5811177492141724
2023-01-22 10:45:40.709658: step: 36/466, loss: 0.37301358580589294
2023-01-22 10:45:41.366474: step: 38/466, loss: 0.6371402740478516
2023-01-22 10:45:41.993381: step: 40/466, loss: 0.29740265011787415
2023-01-22 10:45:42.636197: step: 42/466, loss: 0.23849110305309296
2023-01-22 10:45:43.243054: step: 44/466, loss: 0.20933814346790314
2023-01-22 10:45:43.894621: step: 46/466, loss: 1.008119821548462
2023-01-22 10:45:44.500198: step: 48/466, loss: 0.12082512676715851
2023-01-22 10:45:45.144602: step: 50/466, loss: 0.17111796140670776
2023-01-22 10:45:45.826966: step: 52/466, loss: 0.5508844256401062
2023-01-22 10:45:46.464949: step: 54/466, loss: 0.07896469533443451
2023-01-22 10:45:47.048913: step: 56/466, loss: 0.16774111986160278
2023-01-22 10:45:47.682030: step: 58/466, loss: 0.13596868515014648
2023-01-22 10:45:48.273188: step: 60/466, loss: 0.29006361961364746
2023-01-22 10:45:48.828914: step: 62/466, loss: 0.13309992849826813
2023-01-22 10:45:49.393493: step: 64/466, loss: 0.14383406937122345
2023-01-22 10:45:50.168533: step: 66/466, loss: 0.29724830389022827
2023-01-22 10:45:50.806905: step: 68/466, loss: 0.1715736985206604
2023-01-22 10:45:51.482970: step: 70/466, loss: 0.3546826243400574
2023-01-22 10:45:52.078157: step: 72/466, loss: 0.10893898457288742
2023-01-22 10:45:52.739005: step: 74/466, loss: 0.8169422149658203
2023-01-22 10:45:53.343413: step: 76/466, loss: 0.36334866285324097
2023-01-22 10:45:53.893511: step: 78/466, loss: 0.10342225432395935
2023-01-22 10:45:54.480243: step: 80/466, loss: 0.37415358424186707
2023-01-22 10:45:55.081623: step: 82/466, loss: 0.1697869598865509
2023-01-22 10:45:55.684076: step: 84/466, loss: 0.17617714405059814
2023-01-22 10:45:56.369916: step: 86/466, loss: 0.385753870010376
2023-01-22 10:45:56.985375: step: 88/466, loss: 0.11032872647047043
2023-01-22 10:45:57.637800: step: 90/466, loss: 0.3091268241405487
2023-01-22 10:45:58.308838: step: 92/466, loss: 0.21702732145786285
2023-01-22 10:45:58.931583: step: 94/466, loss: 0.16088707745075226
2023-01-22 10:45:59.610545: step: 96/466, loss: 0.09631867706775665
2023-01-22 10:46:00.287518: step: 98/466, loss: 0.23908157646656036
2023-01-22 10:46:00.875769: step: 100/466, loss: 0.35277605056762695
2023-01-22 10:46:01.527151: step: 102/466, loss: 0.5009201765060425
2023-01-22 10:46:02.213081: step: 104/466, loss: 0.16452857851982117
2023-01-22 10:46:02.788064: step: 106/466, loss: 0.5607878565788269
2023-01-22 10:46:03.530801: step: 108/466, loss: 0.25911426544189453
2023-01-22 10:46:04.127205: step: 110/466, loss: 0.11729790270328522
2023-01-22 10:46:04.780357: step: 112/466, loss: 0.2607351839542389
2023-01-22 10:46:05.398287: step: 114/466, loss: 0.21392768621444702
2023-01-22 10:46:06.022352: step: 116/466, loss: 0.04871556907892227
2023-01-22 10:46:06.646174: step: 118/466, loss: 0.1251087337732315
2023-01-22 10:46:07.286048: step: 120/466, loss: 2.139417886734009
2023-01-22 10:46:07.947290: step: 122/466, loss: 0.9409970641136169
2023-01-22 10:46:08.546007: step: 124/466, loss: 0.5758810043334961
2023-01-22 10:46:09.168794: step: 126/466, loss: 0.20359812676906586
2023-01-22 10:46:09.829184: step: 128/466, loss: 0.1587243527173996
2023-01-22 10:46:10.472424: step: 130/466, loss: 0.17990712821483612
2023-01-22 10:46:11.085167: step: 132/466, loss: 0.17337213456630707
2023-01-22 10:46:11.675414: step: 134/466, loss: 0.0818430483341217
2023-01-22 10:46:12.323622: step: 136/466, loss: 0.1378822922706604
2023-01-22 10:46:12.964295: step: 138/466, loss: 0.5450152158737183
2023-01-22 10:46:13.541661: step: 140/466, loss: 0.07567490637302399
2023-01-22 10:46:14.129813: step: 142/466, loss: 1.2197580337524414
2023-01-22 10:46:14.783886: step: 144/466, loss: 0.38101068139076233
2023-01-22 10:46:15.400825: step: 146/466, loss: 0.1391480714082718
2023-01-22 10:46:16.125544: step: 148/466, loss: 0.19454778730869293
2023-01-22 10:46:16.806259: step: 150/466, loss: 0.3941478729248047
2023-01-22 10:46:17.330814: step: 152/466, loss: 0.15801694989204407
2023-01-22 10:46:18.032625: step: 154/466, loss: 0.41450387239456177
2023-01-22 10:46:18.645902: step: 156/466, loss: 0.2930014431476593
2023-01-22 10:46:19.280596: step: 158/466, loss: 0.19108444452285767
2023-01-22 10:46:19.908737: step: 160/466, loss: 0.22323651611804962
2023-01-22 10:46:20.556986: step: 162/466, loss: 0.2740851044654846
2023-01-22 10:46:21.154409: step: 164/466, loss: 0.07235020399093628
2023-01-22 10:46:21.787057: step: 166/466, loss: 0.18892675638198853
2023-01-22 10:46:22.437331: step: 168/466, loss: 0.37091153860092163
2023-01-22 10:46:23.074959: step: 170/466, loss: 0.944072961807251
2023-01-22 10:46:23.692757: step: 172/466, loss: 0.16395629942417145
2023-01-22 10:46:24.287713: step: 174/466, loss: 0.05845191329717636
2023-01-22 10:46:24.956987: step: 176/466, loss: 0.05888865143060684
2023-01-22 10:46:25.616277: step: 178/466, loss: 0.31981462240219116
2023-01-22 10:46:26.235412: step: 180/466, loss: 0.23472468554973602
2023-01-22 10:46:26.833467: step: 182/466, loss: 0.14848054945468903
2023-01-22 10:46:27.415533: step: 184/466, loss: 0.6054875254631042
2023-01-22 10:46:28.158273: step: 186/466, loss: 0.9153898358345032
2023-01-22 10:46:28.765834: step: 188/466, loss: 0.2103879302740097
2023-01-22 10:46:29.302497: step: 190/466, loss: 0.26340317726135254
2023-01-22 10:46:29.953084: step: 192/466, loss: 0.18384523689746857
2023-01-22 10:46:30.562054: step: 194/466, loss: 0.38214704394340515
2023-01-22 10:46:31.268043: step: 196/466, loss: 0.21841195225715637
2023-01-22 10:46:31.935118: step: 198/466, loss: 0.42027539014816284
2023-01-22 10:46:32.525271: step: 200/466, loss: 0.5119179487228394
2023-01-22 10:46:33.157199: step: 202/466, loss: 0.11029555648565292
2023-01-22 10:46:33.796019: step: 204/466, loss: 0.13725778460502625
2023-01-22 10:46:34.386535: step: 206/466, loss: 0.23730728030204773
2023-01-22 10:46:34.988037: step: 208/466, loss: 0.10681381076574326
2023-01-22 10:46:35.576880: step: 210/466, loss: 0.4054355025291443
2023-01-22 10:46:36.232532: step: 212/466, loss: 0.17219959199428558
2023-01-22 10:46:36.870257: step: 214/466, loss: 0.15734705328941345
2023-01-22 10:46:37.463319: step: 216/466, loss: 0.11057482659816742
2023-01-22 10:46:38.065691: step: 218/466, loss: 0.10751251131296158
2023-01-22 10:46:38.673682: step: 220/466, loss: 0.29336410760879517
2023-01-22 10:46:39.282562: step: 222/466, loss: 0.3931858539581299
2023-01-22 10:46:39.882802: step: 224/466, loss: 0.32212305068969727
2023-01-22 10:46:40.508272: step: 226/466, loss: 0.2841503918170929
2023-01-22 10:46:41.203122: step: 228/466, loss: 0.4519486427307129
2023-01-22 10:46:41.862094: step: 230/466, loss: 0.7676974534988403
2023-01-22 10:46:42.542860: step: 232/466, loss: 0.3085453510284424
2023-01-22 10:46:43.213820: step: 234/466, loss: 0.20741544663906097
2023-01-22 10:46:43.831716: step: 236/466, loss: 0.4583464562892914
2023-01-22 10:46:44.444458: step: 238/466, loss: 0.1378641277551651
2023-01-22 10:46:45.069892: step: 240/466, loss: 0.7796522378921509
2023-01-22 10:46:45.715430: step: 242/466, loss: 0.3027142286300659
2023-01-22 10:46:46.385647: step: 244/466, loss: 0.08265858143568039
2023-01-22 10:46:47.065971: step: 246/466, loss: 0.3559706509113312
2023-01-22 10:46:47.712934: step: 248/466, loss: 0.6588718295097351
2023-01-22 10:46:48.285514: step: 250/466, loss: 0.3847041726112366
2023-01-22 10:46:48.919868: step: 252/466, loss: 0.35952022671699524
2023-01-22 10:46:49.562057: step: 254/466, loss: 0.10576501488685608
2023-01-22 10:46:50.235138: step: 256/466, loss: 0.4464896321296692
2023-01-22 10:46:50.892051: step: 258/466, loss: 0.2264501303434372
2023-01-22 10:46:51.578772: step: 260/466, loss: 0.24269479513168335
2023-01-22 10:46:52.238005: step: 262/466, loss: 0.17529931664466858
2023-01-22 10:46:52.858672: step: 264/466, loss: 0.14880551397800446
2023-01-22 10:46:53.434600: step: 266/466, loss: 0.12219415605068207
2023-01-22 10:46:54.072650: step: 268/466, loss: 0.8103137612342834
2023-01-22 10:46:54.700649: step: 270/466, loss: 0.18102988600730896
2023-01-22 10:46:55.340372: step: 272/466, loss: 0.4099413752555847
2023-01-22 10:46:55.910699: step: 274/466, loss: 0.4709075391292572
2023-01-22 10:46:56.517702: step: 276/466, loss: 0.1665007621049881
2023-01-22 10:46:57.164461: step: 278/466, loss: 0.21260009706020355
2023-01-22 10:46:57.798738: step: 280/466, loss: 0.2750088572502136
2023-01-22 10:46:58.461648: step: 282/466, loss: 0.18898963928222656
2023-01-22 10:46:59.082472: step: 284/466, loss: 0.11391142010688782
2023-01-22 10:46:59.694336: step: 286/466, loss: 0.25304052233695984
2023-01-22 10:47:00.317525: step: 288/466, loss: 0.6753566265106201
2023-01-22 10:47:00.951992: step: 290/466, loss: 0.255403995513916
2023-01-22 10:47:01.628793: step: 292/466, loss: 0.06397488713264465
2023-01-22 10:47:02.250516: step: 294/466, loss: 0.17752189934253693
2023-01-22 10:47:02.870046: step: 296/466, loss: 0.46928924322128296
2023-01-22 10:47:03.461075: step: 298/466, loss: 2.6196093559265137
2023-01-22 10:47:04.070372: step: 300/466, loss: 0.46346068382263184
2023-01-22 10:47:04.654408: step: 302/466, loss: 0.3404328227043152
2023-01-22 10:47:05.316936: step: 304/466, loss: 0.21604882180690765
2023-01-22 10:47:05.968034: step: 306/466, loss: 0.218265101313591
2023-01-22 10:47:06.613738: step: 308/466, loss: 0.46633002161979675
2023-01-22 10:47:07.312457: step: 310/466, loss: 0.17038500308990479
2023-01-22 10:47:07.957636: step: 312/466, loss: 0.26837801933288574
2023-01-22 10:47:08.585025: step: 314/466, loss: 0.29201966524124146
2023-01-22 10:47:09.265132: step: 316/466, loss: 0.6387988924980164
2023-01-22 10:47:09.959237: step: 318/466, loss: 0.18127477169036865
2023-01-22 10:47:10.572302: step: 320/466, loss: 0.5306467413902283
2023-01-22 10:47:11.196689: step: 322/466, loss: 0.12120350450277328
2023-01-22 10:47:11.796235: step: 324/466, loss: 0.18139812350273132
2023-01-22 10:47:12.440623: step: 326/466, loss: 0.11129505932331085
2023-01-22 10:47:13.044658: step: 328/466, loss: 0.18971511721611023
2023-01-22 10:47:13.777750: step: 330/466, loss: 0.17079608142375946
2023-01-22 10:47:14.417876: step: 332/466, loss: 0.3552361726760864
2023-01-22 10:47:15.109980: step: 334/466, loss: 0.18197661638259888
2023-01-22 10:47:15.724131: step: 336/466, loss: 0.36013326048851013
2023-01-22 10:47:16.338487: step: 338/466, loss: 0.478237509727478
2023-01-22 10:47:16.949643: step: 340/466, loss: 0.18918289244174957
2023-01-22 10:47:17.552201: step: 342/466, loss: 0.13420641422271729
2023-01-22 10:47:18.184257: step: 344/466, loss: 0.14395514130592346
2023-01-22 10:47:18.843885: step: 346/466, loss: 0.361555278301239
2023-01-22 10:47:19.442759: step: 348/466, loss: 0.14946097135543823
2023-01-22 10:47:20.023866: step: 350/466, loss: 0.2907811403274536
2023-01-22 10:47:20.648267: step: 352/466, loss: 0.14296364784240723
2023-01-22 10:47:21.195708: step: 354/466, loss: 0.3844510614871979
2023-01-22 10:47:21.812068: step: 356/466, loss: 0.1620994210243225
2023-01-22 10:47:22.494558: step: 358/466, loss: 0.31386253237724304
2023-01-22 10:47:23.127202: step: 360/466, loss: 0.33979666233062744
2023-01-22 10:47:23.799854: step: 362/466, loss: 0.22030147910118103
2023-01-22 10:47:24.427196: step: 364/466, loss: 0.3009497821331024
2023-01-22 10:47:25.067554: step: 366/466, loss: 0.2967192530632019
2023-01-22 10:47:25.735212: step: 368/466, loss: 0.14870119094848633
2023-01-22 10:47:26.347111: step: 370/466, loss: 0.21280643343925476
2023-01-22 10:47:26.901745: step: 372/466, loss: 0.1196550503373146
2023-01-22 10:47:27.497782: step: 374/466, loss: 0.19388926029205322
2023-01-22 10:47:28.133847: step: 376/466, loss: 0.17999613285064697
2023-01-22 10:47:28.749734: step: 378/466, loss: 0.13130156695842743
2023-01-22 10:47:29.318680: step: 380/466, loss: 0.22691947221755981
2023-01-22 10:47:29.898766: step: 382/466, loss: 0.14949214458465576
2023-01-22 10:47:30.531460: step: 384/466, loss: 0.2136528193950653
2023-01-22 10:47:31.128738: step: 386/466, loss: 0.5096291899681091
2023-01-22 10:47:31.770814: step: 388/466, loss: 0.14101539552211761
2023-01-22 10:47:32.397428: step: 390/466, loss: 0.18433600664138794
2023-01-22 10:47:32.963320: step: 392/466, loss: 0.17363117635250092
2023-01-22 10:47:33.635449: step: 394/466, loss: 0.32679206132888794
2023-01-22 10:47:34.305443: step: 396/466, loss: 0.9661167860031128
2023-01-22 10:47:34.937150: step: 398/466, loss: 0.46869587898254395
2023-01-22 10:47:35.558708: step: 400/466, loss: 0.14851966500282288
2023-01-22 10:47:36.170133: step: 402/466, loss: 0.19928830862045288
2023-01-22 10:47:36.779443: step: 404/466, loss: 0.3361433148384094
2023-01-22 10:47:37.394053: step: 406/466, loss: 0.10857192426919937
2023-01-22 10:47:38.110306: step: 408/466, loss: 0.18808101117610931
2023-01-22 10:47:38.747339: step: 410/466, loss: 0.2283339947462082
2023-01-22 10:47:39.454284: step: 412/466, loss: 0.44825655221939087
2023-01-22 10:47:40.115462: step: 414/466, loss: 0.7821473479270935
2023-01-22 10:47:40.841648: step: 416/466, loss: 0.4337299168109894
2023-01-22 10:47:41.496487: step: 418/466, loss: 0.3108523190021515
2023-01-22 10:47:42.216203: step: 420/466, loss: 0.14360187947750092
2023-01-22 10:47:42.831173: step: 422/466, loss: 0.2493402510881424
2023-01-22 10:47:43.433489: step: 424/466, loss: 0.1904027760028839
2023-01-22 10:47:44.050372: step: 426/466, loss: 0.4023641347885132
2023-01-22 10:47:44.684918: step: 428/466, loss: 0.09789680689573288
2023-01-22 10:47:45.276357: step: 430/466, loss: 0.3129696846008301
2023-01-22 10:47:45.947471: step: 432/466, loss: 0.2356068640947342
2023-01-22 10:47:46.577605: step: 434/466, loss: 0.1248709037899971
2023-01-22 10:47:47.190336: step: 436/466, loss: 0.5273644328117371
2023-01-22 10:47:47.785013: step: 438/466, loss: 0.2423192709684372
2023-01-22 10:47:48.425144: step: 440/466, loss: 0.1080382913351059
2023-01-22 10:47:49.048879: step: 442/466, loss: 0.18122127652168274
2023-01-22 10:47:49.685089: step: 444/466, loss: 0.5400142073631287
2023-01-22 10:47:50.321430: step: 446/466, loss: 0.263302743434906
2023-01-22 10:47:50.912998: step: 448/466, loss: 0.2619061768054962
2023-01-22 10:47:51.578766: step: 450/466, loss: 0.42697620391845703
2023-01-22 10:47:52.178162: step: 452/466, loss: 0.5079036951065063
2023-01-22 10:47:52.805401: step: 454/466, loss: 0.8966825008392334
2023-01-22 10:47:53.439046: step: 456/466, loss: 1.4609519243240356
2023-01-22 10:47:54.102233: step: 458/466, loss: 1.9890491962432861
2023-01-22 10:47:54.708535: step: 460/466, loss: 0.3308573067188263
2023-01-22 10:47:55.379794: step: 462/466, loss: 0.20168599486351013
2023-01-22 10:47:55.968781: step: 464/466, loss: 0.15842114388942719
2023-01-22 10:47:56.552619: step: 466/466, loss: 0.12318496406078339
2023-01-22 10:47:57.169231: step: 468/466, loss: 0.10131128877401352
2023-01-22 10:47:57.806137: step: 470/466, loss: 0.316278338432312
2023-01-22 10:47:58.395242: step: 472/466, loss: 0.15732251107692719
2023-01-22 10:47:59.023413: step: 474/466, loss: 0.22823511064052582
2023-01-22 10:47:59.694529: step: 476/466, loss: 0.14556622505187988
2023-01-22 10:48:00.350186: step: 478/466, loss: 0.49621596932411194
2023-01-22 10:48:01.006592: step: 480/466, loss: 0.5935064554214478
2023-01-22 10:48:01.576433: step: 482/466, loss: 0.1994830071926117
2023-01-22 10:48:02.388100: step: 484/466, loss: 0.23406997323036194
2023-01-22 10:48:02.919699: step: 486/466, loss: 0.14036954939365387
2023-01-22 10:48:03.493240: step: 488/466, loss: 0.16422095894813538
2023-01-22 10:48:04.240580: step: 490/466, loss: 0.10193836688995361
2023-01-22 10:48:04.856549: step: 492/466, loss: 0.3593794107437134
2023-01-22 10:48:05.495060: step: 494/466, loss: 0.12931369245052338
2023-01-22 10:48:06.097518: step: 496/466, loss: 0.24577723443508148
2023-01-22 10:48:06.736755: step: 498/466, loss: 0.42191627621650696
2023-01-22 10:48:07.352127: step: 500/466, loss: 0.08254116773605347
2023-01-22 10:48:07.998984: step: 502/466, loss: 1.0767302513122559
2023-01-22 10:48:08.670827: step: 504/466, loss: 0.18729932606220245
2023-01-22 10:48:09.266183: step: 506/466, loss: 0.34757569432258606
2023-01-22 10:48:09.912163: step: 508/466, loss: 0.19753587245941162
2023-01-22 10:48:10.508205: step: 510/466, loss: 0.6562075018882751
2023-01-22 10:48:11.173946: step: 512/466, loss: 0.45441025495529175
2023-01-22 10:48:11.753220: step: 514/466, loss: 0.11676815897226334
2023-01-22 10:48:12.399928: step: 516/466, loss: 0.5185372829437256
2023-01-22 10:48:13.002520: step: 518/466, loss: 0.3092823028564453
2023-01-22 10:48:13.654426: step: 520/466, loss: 0.11145910620689392
2023-01-22 10:48:14.234704: step: 522/466, loss: 0.3906674087047577
2023-01-22 10:48:14.851895: step: 524/466, loss: 0.28080275654792786
2023-01-22 10:48:15.471453: step: 526/466, loss: 0.1907173991203308
2023-01-22 10:48:16.065444: step: 528/466, loss: 0.28857186436653137
2023-01-22 10:48:16.638338: step: 530/466, loss: 0.33306193351745605
2023-01-22 10:48:17.278182: step: 532/466, loss: 0.24578644335269928
2023-01-22 10:48:17.887350: step: 534/466, loss: 0.23515483736991882
2023-01-22 10:48:18.518535: step: 536/466, loss: 1.1538259983062744
2023-01-22 10:48:19.146782: step: 538/466, loss: 0.6076947450637817
2023-01-22 10:48:19.774481: step: 540/466, loss: 1.0239328145980835
2023-01-22 10:48:20.416000: step: 542/466, loss: 0.25282955169677734
2023-01-22 10:48:21.072274: step: 544/466, loss: 0.40280333161354065
2023-01-22 10:48:21.679832: step: 546/466, loss: 0.4870428144931793
2023-01-22 10:48:22.316708: step: 548/466, loss: 0.0939960926771164
2023-01-22 10:48:22.919276: step: 550/466, loss: 0.12107057124376297
2023-01-22 10:48:23.609653: step: 552/466, loss: 0.41152551770210266
2023-01-22 10:48:24.233930: step: 554/466, loss: 0.29801052808761597
2023-01-22 10:48:24.859892: step: 556/466, loss: 0.2560926079750061
2023-01-22 10:48:25.479850: step: 558/466, loss: 0.1539243757724762
2023-01-22 10:48:26.084273: step: 560/466, loss: 1.2889466285705566
2023-01-22 10:48:26.668417: step: 562/466, loss: 0.348409503698349
2023-01-22 10:48:27.247286: step: 564/466, loss: 0.2598280906677246
2023-01-22 10:48:27.849125: step: 566/466, loss: 0.20993900299072266
2023-01-22 10:48:28.480942: step: 568/466, loss: 0.22750478982925415
2023-01-22 10:48:29.036315: step: 570/466, loss: 0.4462200701236725
2023-01-22 10:48:29.729092: step: 572/466, loss: 0.9216004610061646
2023-01-22 10:48:30.334677: step: 574/466, loss: 0.5238385796546936
2023-01-22 10:48:30.971264: step: 576/466, loss: 0.13033205270767212
2023-01-22 10:48:31.651193: step: 578/466, loss: 0.24837486445903778
2023-01-22 10:48:32.244956: step: 580/466, loss: 0.045542627573013306
2023-01-22 10:48:32.893563: step: 582/466, loss: 0.18392203748226166
2023-01-22 10:48:33.536587: step: 584/466, loss: 0.1877361536026001
2023-01-22 10:48:34.201815: step: 586/466, loss: 0.2505837082862854
2023-01-22 10:48:34.823371: step: 588/466, loss: 0.2759116291999817
2023-01-22 10:48:35.408256: step: 590/466, loss: 0.3421742022037506
2023-01-22 10:48:36.084951: step: 592/466, loss: 0.7619215846061707
2023-01-22 10:48:36.665275: step: 594/466, loss: 0.11908534914255142
2023-01-22 10:48:37.285291: step: 596/466, loss: 0.34376809000968933
2023-01-22 10:48:37.903048: step: 598/466, loss: 0.164188414812088
2023-01-22 10:48:38.507334: step: 600/466, loss: 0.4696170687675476
2023-01-22 10:48:39.153045: step: 602/466, loss: 0.33465299010276794
2023-01-22 10:48:39.729790: step: 604/466, loss: 0.16777755320072174
2023-01-22 10:48:40.344724: step: 606/466, loss: 0.2437925487756729
2023-01-22 10:48:40.993300: step: 608/466, loss: 0.2520957291126251
2023-01-22 10:48:41.540523: step: 610/466, loss: 0.0658729299902916
2023-01-22 10:48:42.175418: step: 612/466, loss: 0.13700823485851288
2023-01-22 10:48:42.742500: step: 614/466, loss: 0.7343111038208008
2023-01-22 10:48:43.348977: step: 616/466, loss: 0.21706841886043549
2023-01-22 10:48:44.073457: step: 618/466, loss: 0.11549585312604904
2023-01-22 10:48:44.669604: step: 620/466, loss: 0.4640030860900879
2023-01-22 10:48:45.231082: step: 622/466, loss: 0.12104494124650955
2023-01-22 10:48:45.887595: step: 624/466, loss: 0.6957822442054749
2023-01-22 10:48:46.492670: step: 626/466, loss: 0.12641991674900055
2023-01-22 10:48:47.116463: step: 628/466, loss: 0.18275563418865204
2023-01-22 10:48:47.880800: step: 630/466, loss: 0.1254248172044754
2023-01-22 10:48:48.558732: step: 632/466, loss: 0.2987591028213501
2023-01-22 10:48:49.169937: step: 634/466, loss: 0.17989489436149597
2023-01-22 10:48:49.789267: step: 636/466, loss: 0.26884424686431885
2023-01-22 10:48:50.541069: step: 638/466, loss: 0.447631299495697
2023-01-22 10:48:51.157891: step: 640/466, loss: 0.22676263749599457
2023-01-22 10:48:51.752459: step: 642/466, loss: 0.16808676719665527
2023-01-22 10:48:52.381736: step: 644/466, loss: 0.11691843718290329
2023-01-22 10:48:53.100394: step: 646/466, loss: 0.3022649586200714
2023-01-22 10:48:53.760556: step: 648/466, loss: 0.13623934984207153
2023-01-22 10:48:54.427230: step: 650/466, loss: 1.3627370595932007
2023-01-22 10:48:55.029029: step: 652/466, loss: 0.09851698577404022
2023-01-22 10:48:55.642257: step: 654/466, loss: 0.46624961495399475
2023-01-22 10:48:56.246495: step: 656/466, loss: 0.08882220834493637
2023-01-22 10:48:56.829353: step: 658/466, loss: 1.265326738357544
2023-01-22 10:48:57.393466: step: 660/466, loss: 0.22405727207660675
2023-01-22 10:48:57.992096: step: 662/466, loss: 0.6508872509002686
2023-01-22 10:48:58.603198: step: 664/466, loss: 0.15667793154716492
2023-01-22 10:48:59.177721: step: 666/466, loss: 0.22925753891468048
2023-01-22 10:48:59.834364: step: 668/466, loss: 0.23180414736270905
2023-01-22 10:49:00.414317: step: 670/466, loss: 0.051641300320625305
2023-01-22 10:49:01.013795: step: 672/466, loss: 0.9895915985107422
2023-01-22 10:49:01.665789: step: 674/466, loss: 0.0929332822561264
2023-01-22 10:49:02.270029: step: 676/466, loss: 0.13406313955783844
2023-01-22 10:49:02.813691: step: 678/466, loss: 0.06268256902694702
2023-01-22 10:49:03.432801: step: 680/466, loss: 0.17089411616325378
2023-01-22 10:49:04.064328: step: 682/466, loss: 0.14011450111865997
2023-01-22 10:49:04.776137: step: 684/466, loss: 0.22866925597190857
2023-01-22 10:49:05.362286: step: 686/466, loss: 0.5124398469924927
2023-01-22 10:49:05.965923: step: 688/466, loss: 0.1384267508983612
2023-01-22 10:49:06.603144: step: 690/466, loss: 9.537487983703613
2023-01-22 10:49:07.172264: step: 692/466, loss: 0.15773287415504456
2023-01-22 10:49:07.796154: step: 694/466, loss: 0.21435973048210144
2023-01-22 10:49:08.435653: step: 696/466, loss: 0.2601606249809265
2023-01-22 10:49:09.051347: step: 698/466, loss: 0.2897873520851135
2023-01-22 10:49:09.690955: step: 700/466, loss: 0.12837408483028412
2023-01-22 10:49:10.335001: step: 702/466, loss: 0.094563327729702
2023-01-22 10:49:10.997272: step: 704/466, loss: 0.17177322506904602
2023-01-22 10:49:11.606698: step: 706/466, loss: 0.1358441412448883
2023-01-22 10:49:12.204200: step: 708/466, loss: 0.10824206471443176
2023-01-22 10:49:12.794355: step: 710/466, loss: 2.6558961868286133
2023-01-22 10:49:13.350165: step: 712/466, loss: 0.20807532966136932
2023-01-22 10:49:14.009584: step: 714/466, loss: 0.2447029948234558
2023-01-22 10:49:14.665787: step: 716/466, loss: 0.1848250776529312
2023-01-22 10:49:15.261172: step: 718/466, loss: 0.08883415907621384
2023-01-22 10:49:15.882060: step: 720/466, loss: 1.2126619815826416
2023-01-22 10:49:16.506654: step: 722/466, loss: 0.9208321571350098
2023-01-22 10:49:17.169959: step: 724/466, loss: 0.43263712525367737
2023-01-22 10:49:17.764184: step: 726/466, loss: 0.4163546562194824
2023-01-22 10:49:18.459976: step: 728/466, loss: 0.24820135533809662
2023-01-22 10:49:19.089596: step: 730/466, loss: 0.5538040399551392
2023-01-22 10:49:19.696864: step: 732/466, loss: 0.08325211703777313
2023-01-22 10:49:20.377713: step: 734/466, loss: 0.5551610589027405
2023-01-22 10:49:21.024204: step: 736/466, loss: 0.14608952403068542
2023-01-22 10:49:21.627662: step: 738/466, loss: 0.1840585619211197
2023-01-22 10:49:22.210196: step: 740/466, loss: 0.29782766103744507
2023-01-22 10:49:22.745972: step: 742/466, loss: 0.14386539161205292
2023-01-22 10:49:23.371177: step: 744/466, loss: 1.7157152891159058
2023-01-22 10:49:24.067322: step: 746/466, loss: 0.10851907730102539
2023-01-22 10:49:24.699499: step: 748/466, loss: 0.19914494454860687
2023-01-22 10:49:25.336348: step: 750/466, loss: 0.22274081408977509
2023-01-22 10:49:25.979946: step: 752/466, loss: 0.08526704460382462
2023-01-22 10:49:26.573958: step: 754/466, loss: 0.23813314735889435
2023-01-22 10:49:27.188170: step: 756/466, loss: 0.1329123079776764
2023-01-22 10:49:27.797570: step: 758/466, loss: 0.2598244845867157
2023-01-22 10:49:28.452458: step: 760/466, loss: 0.3998894691467285
2023-01-22 10:49:29.119627: step: 762/466, loss: 0.2382477968931198
2023-01-22 10:49:29.707826: step: 764/466, loss: 0.1373913437128067
2023-01-22 10:49:30.366896: step: 766/466, loss: 0.47792330384254456
2023-01-22 10:49:30.948507: step: 768/466, loss: 0.3679344654083252
2023-01-22 10:49:31.638465: step: 770/466, loss: 0.15216253697872162
2023-01-22 10:49:32.276021: step: 772/466, loss: 0.15031273663043976
2023-01-22 10:49:32.991795: step: 774/466, loss: 2.023613929748535
2023-01-22 10:49:33.665866: step: 776/466, loss: 0.7451434135437012
2023-01-22 10:49:34.291946: step: 778/466, loss: 0.09389051049947739
2023-01-22 10:49:34.892284: step: 780/466, loss: 0.14813999831676483
2023-01-22 10:49:35.432847: step: 782/466, loss: 0.7446677684783936
2023-01-22 10:49:36.056035: step: 784/466, loss: 0.28307709097862244
2023-01-22 10:49:36.695359: step: 786/466, loss: 0.2559066414833069
2023-01-22 10:49:37.324754: step: 788/466, loss: 0.9395307302474976
2023-01-22 10:49:37.997841: step: 790/466, loss: 0.12403196096420288
2023-01-22 10:49:38.643336: step: 792/466, loss: 0.11562259495258331
2023-01-22 10:49:39.339997: step: 794/466, loss: 0.1862974762916565
2023-01-22 10:49:40.009331: step: 796/466, loss: 0.34427696466445923
2023-01-22 10:49:40.696889: step: 798/466, loss: 0.09961500763893127
2023-01-22 10:49:41.343537: step: 800/466, loss: 0.8094140291213989
2023-01-22 10:49:41.969936: step: 802/466, loss: 0.2891375422477722
2023-01-22 10:49:42.607656: step: 804/466, loss: 0.6342332363128662
2023-01-22 10:49:43.269628: step: 806/466, loss: 0.2321213334798813
2023-01-22 10:49:43.953688: step: 808/466, loss: 0.19736243784427643
2023-01-22 10:49:44.607082: step: 810/466, loss: 0.19904033839702606
2023-01-22 10:49:45.231709: step: 812/466, loss: 0.11806154251098633
2023-01-22 10:49:45.849980: step: 814/466, loss: 0.40048617124557495
2023-01-22 10:49:46.469383: step: 816/466, loss: 0.5157013535499573
2023-01-22 10:49:47.090426: step: 818/466, loss: 0.16514591872692108
2023-01-22 10:49:47.735882: step: 820/466, loss: 0.45448026061058044
2023-01-22 10:49:48.345937: step: 822/466, loss: 0.15857598185539246
2023-01-22 10:49:48.979493: step: 824/466, loss: 0.3477775454521179
2023-01-22 10:49:49.625587: step: 826/466, loss: 0.20452511310577393
2023-01-22 10:49:50.239555: step: 828/466, loss: 0.46907299757003784
2023-01-22 10:49:50.922627: step: 830/466, loss: 0.13698351383209229
2023-01-22 10:49:51.577708: step: 832/466, loss: 0.17828044295310974
2023-01-22 10:49:52.203971: step: 834/466, loss: 0.11355534940958023
2023-01-22 10:49:52.805532: step: 836/466, loss: 0.48741504549980164
2023-01-22 10:49:53.395207: step: 838/466, loss: 0.19051556289196014
2023-01-22 10:49:54.008953: step: 840/466, loss: 0.13757193088531494
2023-01-22 10:49:54.593479: step: 842/466, loss: 0.17317397892475128
2023-01-22 10:49:55.226252: step: 844/466, loss: 0.9766011834144592
2023-01-22 10:49:55.845696: step: 846/466, loss: 0.27026239037513733
2023-01-22 10:49:56.522748: step: 848/466, loss: 0.4328172504901886
2023-01-22 10:49:57.227655: step: 850/466, loss: 0.06835843622684479
2023-01-22 10:49:57.861021: step: 852/466, loss: 0.4180905222892761
2023-01-22 10:49:58.477706: step: 854/466, loss: 0.27884113788604736
2023-01-22 10:49:59.136834: step: 856/466, loss: 0.37110257148742676
2023-01-22 10:49:59.733791: step: 858/466, loss: 0.11132179200649261
2023-01-22 10:50:00.377665: step: 860/466, loss: 0.17947500944137573
2023-01-22 10:50:01.080621: step: 862/466, loss: 0.14948973059654236
2023-01-22 10:50:01.762380: step: 864/466, loss: 0.7457356452941895
2023-01-22 10:50:02.407629: step: 866/466, loss: 0.20709970593452454
2023-01-22 10:50:03.000753: step: 868/466, loss: 0.1610090434551239
2023-01-22 10:50:03.660998: step: 870/466, loss: 0.1790013164281845
2023-01-22 10:50:04.292378: step: 872/466, loss: 0.8546355366706848
2023-01-22 10:50:04.859745: step: 874/466, loss: 0.09819687902927399
2023-01-22 10:50:05.423382: step: 876/466, loss: 0.2067101001739502
2023-01-22 10:50:06.089119: step: 878/466, loss: 0.27337244153022766
2023-01-22 10:50:06.709768: step: 880/466, loss: 0.6295063495635986
2023-01-22 10:50:07.356678: step: 882/466, loss: 0.3326685428619385
2023-01-22 10:50:07.990432: step: 884/466, loss: 0.2988430857658386
2023-01-22 10:50:08.586288: step: 886/466, loss: 0.5852946639060974
2023-01-22 10:50:09.225620: step: 888/466, loss: 0.18134286999702454
2023-01-22 10:50:09.856079: step: 890/466, loss: 0.22485585510730743
2023-01-22 10:50:10.526562: step: 892/466, loss: 0.3484098017215729
2023-01-22 10:50:11.196327: step: 894/466, loss: 0.48258063197135925
2023-01-22 10:50:11.916443: step: 896/466, loss: 0.37149667739868164
2023-01-22 10:50:12.629951: step: 898/466, loss: 0.1821063756942749
2023-01-22 10:50:13.299770: step: 900/466, loss: 0.16822296380996704
2023-01-22 10:50:13.921610: step: 902/466, loss: 0.43086278438568115
2023-01-22 10:50:14.570610: step: 904/466, loss: 0.13566407561302185
2023-01-22 10:50:15.208511: step: 906/466, loss: 0.32909202575683594
2023-01-22 10:50:15.845357: step: 908/466, loss: 0.21370433270931244
2023-01-22 10:50:16.430814: step: 910/466, loss: 0.41602638363838196
2023-01-22 10:50:17.088424: step: 912/466, loss: 0.36425134539604187
2023-01-22 10:50:17.746453: step: 914/466, loss: 0.06356432288885117
2023-01-22 10:50:18.448338: step: 916/466, loss: 0.17971070110797882
2023-01-22 10:50:19.083543: step: 918/466, loss: 0.2898575961589813
2023-01-22 10:50:19.710949: step: 920/466, loss: 0.8324838876724243
2023-01-22 10:50:20.403977: step: 922/466, loss: 0.26693013310432434
2023-01-22 10:50:21.029933: step: 924/466, loss: 2.2129180431365967
2023-01-22 10:50:21.658445: step: 926/466, loss: 0.1820612996816635
2023-01-22 10:50:22.306225: step: 928/466, loss: 0.14786766469478607
2023-01-22 10:50:22.991800: step: 930/466, loss: 0.26998090744018555
2023-01-22 10:50:23.715373: step: 932/466, loss: 0.18968722224235535
==================================================
Loss: 0.357
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3058406624384642, 'r': 0.3551698015414423, 'f1': 0.3286645924711854}, 'combined': 0.24217391024192608, 'epoch': 10}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.2906178595465435, 'r': 0.3066175792508207, 'f1': 0.29840340606931}, 'combined': 0.1868507309032128, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2892599128382881, 'r': 0.36665203373050564, 'f1': 0.3233901619681615}, 'combined': 0.23828748776601372, 'epoch': 10}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.2997370676177068, 'r': 0.31813248331987654, 'f1': 0.30866093828233204}, 'combined': 0.19128283499186774, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2612496596301635, 'r': 0.3608913704188976, 'f1': 0.3030912385828829}, 'combined': 0.2233303863242295, 'epoch': 10}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3122351791363572, 'r': 0.3229436058576402, 'f1': 0.31749912625578114}, 'combined': 0.2106182322686865, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.22058823529411764, 'r': 0.32142857142857145, 'f1': 0.26162790697674415}, 'combined': 0.17441860465116277, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3055555555555556, 'r': 0.4782608695652174, 'f1': 0.3728813559322034}, 'combined': 0.1864406779661017, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.21875, 'r': 0.2413793103448276, 'f1': 0.22950819672131145}, 'combined': 0.1530054644808743, 'epoch': 10}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2892599128382881, 'r': 0.36665203373050564, 'f1': 0.3233901619681615}, 'combined': 0.23828748776601372, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.2997370676177068, 'r': 0.31813248331987654, 'f1': 0.30866093828233204}, 'combined': 0.19128283499186774, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3055555555555556, 'r': 0.4782608695652174, 'f1': 0.3728813559322034}, 'combined': 0.1864406779661017, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 10:53:20.981185: step: 2/466, loss: 0.056166116148233414
2023-01-22 10:53:21.601365: step: 4/466, loss: 0.2557902932167053
2023-01-22 10:53:22.359369: step: 6/466, loss: 0.1701134741306305
2023-01-22 10:53:23.008733: step: 8/466, loss: 0.14746788144111633
2023-01-22 10:53:23.732065: step: 10/466, loss: 0.10391730070114136
2023-01-22 10:53:24.368249: step: 12/466, loss: 0.13643328845500946
2023-01-22 10:53:25.032289: step: 14/466, loss: 0.14409023523330688
2023-01-22 10:53:25.732844: step: 16/466, loss: 0.4911487400531769
2023-01-22 10:53:26.353796: step: 18/466, loss: 0.3150400221347809
2023-01-22 10:53:27.013277: step: 20/466, loss: 0.15729796886444092
2023-01-22 10:53:27.698579: step: 22/466, loss: 0.6850324273109436
2023-01-22 10:53:28.360375: step: 24/466, loss: 1.054762840270996
2023-01-22 10:53:29.042965: step: 26/466, loss: 0.21192385256290436
2023-01-22 10:53:29.644838: step: 28/466, loss: 0.40402689576148987
2023-01-22 10:53:30.322601: step: 30/466, loss: 0.14002251625061035
2023-01-22 10:53:30.968445: step: 32/466, loss: 0.3916529715061188
2023-01-22 10:53:31.613472: step: 34/466, loss: 0.8134997487068176
2023-01-22 10:53:32.218934: step: 36/466, loss: 0.11228177696466446
2023-01-22 10:53:32.850257: step: 38/466, loss: 0.10730807483196259
2023-01-22 10:53:33.523936: step: 40/466, loss: 0.23734834790229797
2023-01-22 10:53:34.119253: step: 42/466, loss: 0.18028199672698975
2023-01-22 10:53:34.734113: step: 44/466, loss: 0.09118640422821045
2023-01-22 10:53:35.356494: step: 46/466, loss: 0.1470775306224823
2023-01-22 10:53:35.968842: step: 48/466, loss: 0.09362707287073135
2023-01-22 10:53:36.707746: step: 50/466, loss: 0.03722560405731201
2023-01-22 10:53:37.376928: step: 52/466, loss: 0.28206494450569153
2023-01-22 10:53:38.027593: step: 54/466, loss: 0.322757750749588
2023-01-22 10:53:38.692169: step: 56/466, loss: 0.20481041073799133
2023-01-22 10:53:39.329469: step: 58/466, loss: 0.16629400849342346
2023-01-22 10:53:39.983430: step: 60/466, loss: 0.16229598224163055
2023-01-22 10:53:40.660795: step: 62/466, loss: 0.1146460473537445
2023-01-22 10:53:41.407418: step: 64/466, loss: 0.11553932726383209
2023-01-22 10:53:42.124813: step: 66/466, loss: 0.3799624443054199
2023-01-22 10:53:42.781443: step: 68/466, loss: 0.04066538065671921
2023-01-22 10:53:43.411749: step: 70/466, loss: 0.14782850444316864
2023-01-22 10:53:44.046321: step: 72/466, loss: 0.12409090250730515
2023-01-22 10:53:44.710440: step: 74/466, loss: 0.5242952108383179
2023-01-22 10:53:45.361360: step: 76/466, loss: 0.014922366477549076
2023-01-22 10:53:46.051932: step: 78/466, loss: 0.4112562835216522
2023-01-22 10:53:46.736677: step: 80/466, loss: 0.26756608486175537
2023-01-22 10:53:47.438498: step: 82/466, loss: 0.3237709105014801
2023-01-22 10:53:48.160715: step: 84/466, loss: 0.27106547355651855
2023-01-22 10:53:48.785523: step: 86/466, loss: 0.11905548721551895
2023-01-22 10:53:49.439575: step: 88/466, loss: 1.0723085403442383
2023-01-22 10:53:50.096313: step: 90/466, loss: 0.1311020404100418
2023-01-22 10:53:50.765861: step: 92/466, loss: 0.07831726968288422
2023-01-22 10:53:51.387721: step: 94/466, loss: 0.20921853184700012
2023-01-22 10:53:52.026223: step: 96/466, loss: 0.098052978515625
2023-01-22 10:53:52.688912: step: 98/466, loss: 0.23252728581428528
2023-01-22 10:53:53.422172: step: 100/466, loss: 0.09003081172704697
2023-01-22 10:53:54.109326: step: 102/466, loss: 0.5116091966629028
2023-01-22 10:53:54.703492: step: 104/466, loss: 0.6654913425445557
2023-01-22 10:53:55.344297: step: 106/466, loss: 0.267116904258728
2023-01-22 10:53:55.992250: step: 108/466, loss: 0.3134758472442627
2023-01-22 10:53:56.736111: step: 110/466, loss: 0.46777868270874023
2023-01-22 10:53:57.325952: step: 112/466, loss: 4.004735946655273
2023-01-22 10:53:57.961094: step: 114/466, loss: 0.17657536268234253
2023-01-22 10:53:58.602113: step: 116/466, loss: 0.03620237484574318
2023-01-22 10:53:59.229268: step: 118/466, loss: 0.0979924350976944
2023-01-22 10:53:59.894167: step: 120/466, loss: 0.15746234357357025
2023-01-22 10:54:00.546938: step: 122/466, loss: 0.3161891996860504
2023-01-22 10:54:01.202091: step: 124/466, loss: 0.17940855026245117
2023-01-22 10:54:01.896584: step: 126/466, loss: 0.6414418816566467
2023-01-22 10:54:02.577796: step: 128/466, loss: 0.09979026764631271
2023-01-22 10:54:03.171096: step: 130/466, loss: 0.15462499856948853
2023-01-22 10:54:03.799558: step: 132/466, loss: 0.04857669025659561
2023-01-22 10:54:04.462063: step: 134/466, loss: 0.10343555361032486
2023-01-22 10:54:05.169160: step: 136/466, loss: 0.19048278033733368
2023-01-22 10:54:05.736182: step: 138/466, loss: 0.20670101046562195
2023-01-22 10:54:06.337041: step: 140/466, loss: 0.6163320541381836
2023-01-22 10:54:07.016115: step: 142/466, loss: 0.44770777225494385
2023-01-22 10:54:07.599227: step: 144/466, loss: 0.20391231775283813
2023-01-22 10:54:08.251743: step: 146/466, loss: 0.08158297091722488
2023-01-22 10:54:08.889588: step: 148/466, loss: 0.22164416313171387
2023-01-22 10:54:09.494093: step: 150/466, loss: 0.16902580857276917
2023-01-22 10:54:10.154921: step: 152/466, loss: 0.19119475781917572
2023-01-22 10:54:10.822540: step: 154/466, loss: 0.1406470388174057
2023-01-22 10:54:11.501623: step: 156/466, loss: 0.2205415517091751
2023-01-22 10:54:12.130377: step: 158/466, loss: 0.12865635752677917
2023-01-22 10:54:12.796488: step: 160/466, loss: 0.35933148860931396
2023-01-22 10:54:13.488466: step: 162/466, loss: 0.45000115036964417
2023-01-22 10:54:14.098987: step: 164/466, loss: 0.17844568192958832
2023-01-22 10:54:14.811846: step: 166/466, loss: 0.6599502563476562
2023-01-22 10:54:15.449385: step: 168/466, loss: 0.18270272016525269
2023-01-22 10:54:16.099664: step: 170/466, loss: 0.12775404751300812
2023-01-22 10:54:16.839669: step: 172/466, loss: 0.6985673308372498
2023-01-22 10:54:17.493544: step: 174/466, loss: 0.3083813190460205
2023-01-22 10:54:18.117718: step: 176/466, loss: 0.05631847307085991
2023-01-22 10:54:18.790249: step: 178/466, loss: 0.20867310464382172
2023-01-22 10:54:19.415842: step: 180/466, loss: 0.1922890990972519
2023-01-22 10:54:20.070473: step: 182/466, loss: 0.1106002926826477
2023-01-22 10:54:20.722576: step: 184/466, loss: 0.0857967808842659
2023-01-22 10:54:21.347285: step: 186/466, loss: 0.2109062820672989
2023-01-22 10:54:21.895226: step: 188/466, loss: 0.17689363658428192
2023-01-22 10:54:22.548795: step: 190/466, loss: 0.4798988401889801
2023-01-22 10:54:23.263025: step: 192/466, loss: 0.2285255342721939
2023-01-22 10:54:23.937523: step: 194/466, loss: 0.202779620885849
2023-01-22 10:54:24.663194: step: 196/466, loss: 0.0576382577419281
2023-01-22 10:54:25.363127: step: 198/466, loss: 0.1753125935792923
2023-01-22 10:54:25.989142: step: 200/466, loss: 0.10562325268983841
2023-01-22 10:54:26.653877: step: 202/466, loss: 0.22770178318023682
2023-01-22 10:54:27.353600: step: 204/466, loss: 0.09853328764438629
2023-01-22 10:54:28.058272: step: 206/466, loss: 0.12197496742010117
2023-01-22 10:54:28.745788: step: 208/466, loss: 0.3578759729862213
2023-01-22 10:54:29.368120: step: 210/466, loss: 0.09613992273807526
2023-01-22 10:54:29.977402: step: 212/466, loss: 0.1323639452457428
2023-01-22 10:54:30.638573: step: 214/466, loss: 0.15989448130130768
2023-01-22 10:54:31.326260: step: 216/466, loss: 0.622464656829834
2023-01-22 10:54:31.958532: step: 218/466, loss: 0.09623079746961594
2023-01-22 10:54:32.554091: step: 220/466, loss: 0.22858555614948273
2023-01-22 10:54:33.195905: step: 222/466, loss: 0.10492166876792908
2023-01-22 10:54:33.869678: step: 224/466, loss: 1.284364938735962
2023-01-22 10:54:34.517427: step: 226/466, loss: 0.17451579868793488
2023-01-22 10:54:35.159517: step: 228/466, loss: 0.11049184203147888
2023-01-22 10:54:35.840474: step: 230/466, loss: 0.07170509546995163
2023-01-22 10:54:36.481991: step: 232/466, loss: 0.21166926622390747
2023-01-22 10:54:37.156986: step: 234/466, loss: 0.14977402985095978
2023-01-22 10:54:37.854559: step: 236/466, loss: 0.19428275525569916
2023-01-22 10:54:38.504422: step: 238/466, loss: 0.2535887360572815
2023-01-22 10:54:39.177959: step: 240/466, loss: 0.2047453373670578
2023-01-22 10:54:39.812242: step: 242/466, loss: 0.3012225031852722
2023-01-22 10:54:40.379828: step: 244/466, loss: 0.19248755276203156
2023-01-22 10:54:40.989491: step: 246/466, loss: 0.05941566452383995
2023-01-22 10:54:41.629614: step: 248/466, loss: 0.07200485467910767
2023-01-22 10:54:42.227921: step: 250/466, loss: 0.22358103096485138
2023-01-22 10:54:42.876024: step: 252/466, loss: 0.2905464470386505
2023-01-22 10:54:43.525620: step: 254/466, loss: 0.20560117065906525
2023-01-22 10:54:44.166485: step: 256/466, loss: 0.10541833192110062
2023-01-22 10:54:44.790798: step: 258/466, loss: 0.11137007176876068
2023-01-22 10:54:45.437592: step: 260/466, loss: 0.04343457892537117
2023-01-22 10:54:46.070060: step: 262/466, loss: 0.13195733726024628
2023-01-22 10:54:46.713601: step: 264/466, loss: 0.16842803359031677
2023-01-22 10:54:47.415988: step: 266/466, loss: 0.1032499447464943
2023-01-22 10:54:48.022432: step: 268/466, loss: 0.18273863196372986
2023-01-22 10:54:48.677045: step: 270/466, loss: 0.1662614494562149
2023-01-22 10:54:49.322182: step: 272/466, loss: 0.1534671187400818
2023-01-22 10:54:50.001823: step: 274/466, loss: 0.20650523900985718
2023-01-22 10:54:50.619733: step: 276/466, loss: 0.372755229473114
2023-01-22 10:54:51.235085: step: 278/466, loss: 0.06759672611951828
2023-01-22 10:54:51.853790: step: 280/466, loss: 0.11779394000768661
2023-01-22 10:54:52.479653: step: 282/466, loss: 0.7636472582817078
2023-01-22 10:54:53.123615: step: 284/466, loss: 0.11199310421943665
2023-01-22 10:54:53.784466: step: 286/466, loss: 0.12100084125995636
2023-01-22 10:54:54.378350: step: 288/466, loss: 0.12693998217582703
2023-01-22 10:54:55.055393: step: 290/466, loss: 0.1179727166891098
2023-01-22 10:54:55.733527: step: 292/466, loss: 0.14116007089614868
2023-01-22 10:54:56.447072: step: 294/466, loss: 0.22696992754936218
2023-01-22 10:54:57.100926: step: 296/466, loss: 0.30198702216148376
2023-01-22 10:54:57.831931: step: 298/466, loss: 0.6689245700836182
2023-01-22 10:54:58.523526: step: 300/466, loss: 0.9285719394683838
2023-01-22 10:54:59.123919: step: 302/466, loss: 0.13377000391483307
2023-01-22 10:54:59.766394: step: 304/466, loss: 0.2543970048427582
2023-01-22 10:55:00.485702: step: 306/466, loss: 0.10936364531517029
2023-01-22 10:55:01.155765: step: 308/466, loss: 1.0188202857971191
2023-01-22 10:55:01.870780: step: 310/466, loss: 0.12935645878314972
2023-01-22 10:55:02.515828: step: 312/466, loss: 0.19918908178806305
2023-01-22 10:55:03.160627: step: 314/466, loss: 0.16760675609111786
2023-01-22 10:55:03.784088: step: 316/466, loss: 0.1381971687078476
2023-01-22 10:55:04.435304: step: 318/466, loss: 0.09110873937606812
2023-01-22 10:55:05.022383: step: 320/466, loss: 0.5863840579986572
2023-01-22 10:55:05.704116: step: 322/466, loss: 0.0976371094584465
2023-01-22 10:55:06.411978: step: 324/466, loss: 0.13793091475963593
2023-01-22 10:55:07.035833: step: 326/466, loss: 1.1786155700683594
2023-01-22 10:55:07.675964: step: 328/466, loss: 0.40811020135879517
2023-01-22 10:55:08.272130: step: 330/466, loss: 0.10378309339284897
2023-01-22 10:55:08.891251: step: 332/466, loss: 0.8036404848098755
2023-01-22 10:55:09.592002: step: 334/466, loss: 0.08031360059976578
2023-01-22 10:55:10.282898: step: 336/466, loss: 0.2537367343902588
2023-01-22 10:55:10.900176: step: 338/466, loss: 0.5860034823417664
2023-01-22 10:55:11.610726: step: 340/466, loss: 0.22907838225364685
2023-01-22 10:55:12.352309: step: 342/466, loss: 0.0988997146487236
2023-01-22 10:55:13.067204: step: 344/466, loss: 0.2374100387096405
2023-01-22 10:55:13.675580: step: 346/466, loss: 0.35751140117645264
2023-01-22 10:55:14.293596: step: 348/466, loss: 0.1537267416715622
2023-01-22 10:55:14.883773: step: 350/466, loss: 0.3873507082462311
2023-01-22 10:55:15.489123: step: 352/466, loss: 0.13627862930297852
2023-01-22 10:55:16.144076: step: 354/466, loss: 0.2671084403991699
2023-01-22 10:55:16.790244: step: 356/466, loss: 0.21971730887889862
2023-01-22 10:55:17.519979: step: 358/466, loss: 0.13752120733261108
2023-01-22 10:55:18.232980: step: 360/466, loss: 0.47819826006889343
2023-01-22 10:55:18.908741: step: 362/466, loss: 0.11981973797082901
2023-01-22 10:55:19.504446: step: 364/466, loss: 0.8910827040672302
2023-01-22 10:55:20.133554: step: 366/466, loss: 0.124082051217556
2023-01-22 10:55:20.717170: step: 368/466, loss: 0.09532630443572998
2023-01-22 10:55:21.369561: step: 370/466, loss: 0.7827644944190979
2023-01-22 10:55:22.026213: step: 372/466, loss: 0.15190982818603516
2023-01-22 10:55:22.682618: step: 374/466, loss: 0.4592849612236023
2023-01-22 10:55:23.282339: step: 376/466, loss: 0.1304216831922531
2023-01-22 10:55:23.925015: step: 378/466, loss: 1.2518675327301025
2023-01-22 10:55:24.575877: step: 380/466, loss: 0.5958972573280334
2023-01-22 10:55:25.263909: step: 382/466, loss: 0.8851840496063232
2023-01-22 10:55:25.955165: step: 384/466, loss: 0.16735360026359558
2023-01-22 10:55:26.601146: step: 386/466, loss: 0.10196258127689362
2023-01-22 10:55:27.183669: step: 388/466, loss: 0.042919568717479706
2023-01-22 10:55:27.846328: step: 390/466, loss: 0.07912568002939224
2023-01-22 10:55:28.491757: step: 392/466, loss: 0.25435715913772583
2023-01-22 10:55:29.094459: step: 394/466, loss: 0.20457041263580322
2023-01-22 10:55:29.832306: step: 396/466, loss: 1.0136419534683228
2023-01-22 10:55:30.479190: step: 398/466, loss: 0.32960301637649536
2023-01-22 10:55:31.110848: step: 400/466, loss: 0.1917905956506729
2023-01-22 10:55:31.772624: step: 402/466, loss: 0.3560708165168762
2023-01-22 10:55:32.425574: step: 404/466, loss: 0.4032041132450104
2023-01-22 10:55:33.018231: step: 406/466, loss: 0.17448638379573822
2023-01-22 10:55:33.724547: step: 408/466, loss: 1.0081785917282104
2023-01-22 10:55:34.324949: step: 410/466, loss: 0.1689838171005249
2023-01-22 10:55:34.867430: step: 412/466, loss: 0.8321733474731445
2023-01-22 10:55:35.534324: step: 414/466, loss: 0.4371199309825897
2023-01-22 10:55:36.153058: step: 416/466, loss: 0.20262926816940308
2023-01-22 10:55:36.726020: step: 418/466, loss: 0.053672414273023605
2023-01-22 10:55:37.357125: step: 420/466, loss: 0.14170688390731812
2023-01-22 10:55:37.987808: step: 422/466, loss: 0.2766505479812622
2023-01-22 10:55:38.653768: step: 424/466, loss: 0.2543244957923889
2023-01-22 10:55:39.281896: step: 426/466, loss: 0.08526773750782013
2023-01-22 10:55:39.920287: step: 428/466, loss: 0.1939818561077118
2023-01-22 10:55:40.547599: step: 430/466, loss: 0.38968127965927124
2023-01-22 10:55:41.197204: step: 432/466, loss: 0.08138088881969452
2023-01-22 10:55:41.831308: step: 434/466, loss: 0.17517045140266418
2023-01-22 10:55:42.497691: step: 436/466, loss: 0.148594930768013
2023-01-22 10:55:43.124023: step: 438/466, loss: 0.22264939546585083
2023-01-22 10:55:43.791132: step: 440/466, loss: 0.1607075184583664
2023-01-22 10:55:44.409762: step: 442/466, loss: 1.6625304222106934
2023-01-22 10:55:44.988698: step: 444/466, loss: 0.46067410707473755
2023-01-22 10:55:45.604597: step: 446/466, loss: 0.27573996782302856
2023-01-22 10:55:46.200232: step: 448/466, loss: 0.08637235313653946
2023-01-22 10:55:46.915856: step: 450/466, loss: 0.40373581647872925
2023-01-22 10:55:47.580454: step: 452/466, loss: 0.12875215709209442
2023-01-22 10:55:48.169075: step: 454/466, loss: 0.16318896412849426
2023-01-22 10:55:48.786159: step: 456/466, loss: 0.3789152204990387
2023-01-22 10:55:49.507357: step: 458/466, loss: 0.41057494282722473
2023-01-22 10:55:50.209240: step: 460/466, loss: 0.09855090826749802
2023-01-22 10:55:50.857506: step: 462/466, loss: 0.11188815534114838
2023-01-22 10:55:51.543481: step: 464/466, loss: 0.09850119054317474
2023-01-22 10:55:52.193094: step: 466/466, loss: 0.5544841289520264
2023-01-22 10:55:52.811463: step: 468/466, loss: 0.10233950614929199
2023-01-22 10:55:53.529224: step: 470/466, loss: 0.12407094240188599
2023-01-22 10:55:54.206444: step: 472/466, loss: 0.06933730840682983
2023-01-22 10:55:54.827503: step: 474/466, loss: 1.7711869478225708
2023-01-22 10:55:55.551606: step: 476/466, loss: 0.26224398612976074
2023-01-22 10:55:56.207347: step: 478/466, loss: 0.17908237874507904
2023-01-22 10:55:56.845814: step: 480/466, loss: 0.236375093460083
2023-01-22 10:55:57.556516: step: 482/466, loss: 0.19716686010360718
2023-01-22 10:55:58.238356: step: 484/466, loss: 0.12723639607429504
2023-01-22 10:55:58.859285: step: 486/466, loss: 0.17864809930324554
2023-01-22 10:55:59.464590: step: 488/466, loss: 0.5733076333999634
2023-01-22 10:56:00.083476: step: 490/466, loss: 0.5182340741157532
2023-01-22 10:56:00.742003: step: 492/466, loss: 0.06551437079906464
2023-01-22 10:56:01.379245: step: 494/466, loss: 0.046929892152547836
2023-01-22 10:56:02.027198: step: 496/466, loss: 0.1886240541934967
2023-01-22 10:56:02.611800: step: 498/466, loss: 0.2766363322734833
2023-01-22 10:56:03.298233: step: 500/466, loss: 0.34598588943481445
2023-01-22 10:56:03.953457: step: 502/466, loss: 0.5055862665176392
2023-01-22 10:56:04.572683: step: 504/466, loss: 0.1396089792251587
2023-01-22 10:56:05.221865: step: 506/466, loss: 0.4359109401702881
2023-01-22 10:56:05.835023: step: 508/466, loss: 0.2639307677745819
2023-01-22 10:56:06.548867: step: 510/466, loss: 0.28115010261535645
2023-01-22 10:56:07.186987: step: 512/466, loss: 0.2753887474536896
2023-01-22 10:56:07.971652: step: 514/466, loss: 0.16874361038208008
2023-01-22 10:56:08.630904: step: 516/466, loss: 0.21374468505382538
2023-01-22 10:56:09.336354: step: 518/466, loss: 1.2864924669265747
2023-01-22 10:56:09.998782: step: 520/466, loss: 0.13360130786895752
2023-01-22 10:56:10.659484: step: 522/466, loss: 0.6753610372543335
2023-01-22 10:56:11.232648: step: 524/466, loss: 0.2466708868741989
2023-01-22 10:56:11.900313: step: 526/466, loss: 0.15917545557022095
2023-01-22 10:56:12.531908: step: 528/466, loss: 0.21142955124378204
2023-01-22 10:56:13.182963: step: 530/466, loss: 0.30307796597480774
2023-01-22 10:56:13.916329: step: 532/466, loss: 0.2757112383842468
2023-01-22 10:56:14.590518: step: 534/466, loss: 0.21693839132785797
2023-01-22 10:56:15.306405: step: 536/466, loss: 0.07317715138196945
2023-01-22 10:56:15.975461: step: 538/466, loss: 0.06557666510343552
2023-01-22 10:56:16.633683: step: 540/466, loss: 0.11224383115768433
2023-01-22 10:56:17.285415: step: 542/466, loss: 0.10584692656993866
2023-01-22 10:56:17.969244: step: 544/466, loss: 0.13893507421016693
2023-01-22 10:56:18.598827: step: 546/466, loss: 0.14835600554943085
2023-01-22 10:56:19.239602: step: 548/466, loss: 0.1030556708574295
2023-01-22 10:56:19.882108: step: 550/466, loss: 0.23301927745342255
2023-01-22 10:56:20.515366: step: 552/466, loss: 0.1005689799785614
2023-01-22 10:56:21.158395: step: 554/466, loss: 0.7783551216125488
2023-01-22 10:56:21.792801: step: 556/466, loss: 0.1749415099620819
2023-01-22 10:56:22.502772: step: 558/466, loss: 0.12470461428165436
2023-01-22 10:56:23.141659: step: 560/466, loss: 0.10696142911911011
2023-01-22 10:56:23.844297: step: 562/466, loss: 0.1840374767780304
2023-01-22 10:56:24.495517: step: 564/466, loss: 0.1637786328792572
2023-01-22 10:56:25.115629: step: 566/466, loss: 0.2765638530254364
2023-01-22 10:56:25.741996: step: 568/466, loss: 0.1757660061120987
2023-01-22 10:56:26.390257: step: 570/466, loss: 0.3000456988811493
2023-01-22 10:56:27.081354: step: 572/466, loss: 0.253776490688324
2023-01-22 10:56:27.729458: step: 574/466, loss: 0.17246007919311523
2023-01-22 10:56:28.414584: step: 576/466, loss: 0.2563311755657196
2023-01-22 10:56:29.105274: step: 578/466, loss: 0.3139677047729492
2023-01-22 10:56:29.794953: step: 580/466, loss: 0.5516467690467834
2023-01-22 10:56:30.447130: step: 582/466, loss: 0.12537474930286407
2023-01-22 10:56:31.221523: step: 584/466, loss: 0.25660762190818787
2023-01-22 10:56:31.935829: step: 586/466, loss: 0.10562071949243546
2023-01-22 10:56:32.577905: step: 588/466, loss: 0.29111579060554504
2023-01-22 10:56:33.253694: step: 590/466, loss: 0.186752051115036
2023-01-22 10:56:33.920998: step: 592/466, loss: 0.22669342160224915
2023-01-22 10:56:34.606346: step: 594/466, loss: 0.17457406222820282
2023-01-22 10:56:35.369514: step: 596/466, loss: 0.13138017058372498
2023-01-22 10:56:35.957956: step: 598/466, loss: 0.18545128405094147
2023-01-22 10:56:36.613390: step: 600/466, loss: 1.5592176914215088
2023-01-22 10:56:37.208886: step: 602/466, loss: 0.1451473832130432
2023-01-22 10:56:37.861508: step: 604/466, loss: 0.19037167727947235
2023-01-22 10:56:38.520229: step: 606/466, loss: 0.6539323329925537
2023-01-22 10:56:39.143351: step: 608/466, loss: 0.37702956795692444
2023-01-22 10:56:39.770711: step: 610/466, loss: 0.261125385761261
2023-01-22 10:56:40.355993: step: 612/466, loss: 0.5847034454345703
2023-01-22 10:56:41.012970: step: 614/466, loss: 1.1425877809524536
2023-01-22 10:56:41.608283: step: 616/466, loss: 0.5076453685760498
2023-01-22 10:56:42.270342: step: 618/466, loss: 0.2025333195924759
2023-01-22 10:56:42.916816: step: 620/466, loss: 0.2334977239370346
2023-01-22 10:56:43.635612: step: 622/466, loss: 0.21920332312583923
2023-01-22 10:56:44.320765: step: 624/466, loss: 0.1656721979379654
2023-01-22 10:56:44.943001: step: 626/466, loss: 0.28424978256225586
2023-01-22 10:56:45.605619: step: 628/466, loss: 0.1002599224448204
2023-01-22 10:56:46.226031: step: 630/466, loss: 0.27894553542137146
2023-01-22 10:56:46.819536: step: 632/466, loss: 0.6983669400215149
2023-01-22 10:56:47.478350: step: 634/466, loss: 0.08150078356266022
2023-01-22 10:56:48.110897: step: 636/466, loss: 1.2374701499938965
2023-01-22 10:56:48.792344: step: 638/466, loss: 0.12696145474910736
2023-01-22 10:56:49.419290: step: 640/466, loss: 0.18900883197784424
2023-01-22 10:56:50.073414: step: 642/466, loss: 0.12979234755039215
2023-01-22 10:56:50.682626: step: 644/466, loss: 0.09342486411333084
2023-01-22 10:56:51.301048: step: 646/466, loss: 0.2928432822227478
2023-01-22 10:56:52.004420: step: 648/466, loss: 0.3717673122882843
2023-01-22 10:56:52.650749: step: 650/466, loss: 0.2137729972600937
2023-01-22 10:56:53.295698: step: 652/466, loss: 0.11146210134029388
2023-01-22 10:56:53.952991: step: 654/466, loss: 0.1910243183374405
2023-01-22 10:56:54.687636: step: 656/466, loss: 0.6716959476470947
2023-01-22 10:56:55.375767: step: 658/466, loss: 0.3120448887348175
2023-01-22 10:56:56.062768: step: 660/466, loss: 0.1816355288028717
2023-01-22 10:56:56.722784: step: 662/466, loss: 0.14433424174785614
2023-01-22 10:56:57.344652: step: 664/466, loss: 0.2028488665819168
2023-01-22 10:56:58.095410: step: 666/466, loss: 0.6138753890991211
2023-01-22 10:56:58.738022: step: 668/466, loss: 0.8248133659362793
2023-01-22 10:56:59.347904: step: 670/466, loss: 0.30739057064056396
2023-01-22 10:56:59.961011: step: 672/466, loss: 0.1564578264951706
2023-01-22 10:57:00.611092: step: 674/466, loss: 0.2032361924648285
2023-01-22 10:57:01.266469: step: 676/466, loss: 0.1419278085231781
2023-01-22 10:57:01.922670: step: 678/466, loss: 0.16310647130012512
2023-01-22 10:57:02.634490: step: 680/466, loss: 0.2876623272895813
2023-01-22 10:57:03.436393: step: 682/466, loss: 0.08155625313520432
2023-01-22 10:57:04.083253: step: 684/466, loss: 0.5003127455711365
2023-01-22 10:57:04.701033: step: 686/466, loss: 0.10688678920269012
2023-01-22 10:57:05.324875: step: 688/466, loss: 0.11806152760982513
2023-01-22 10:57:05.956974: step: 690/466, loss: 0.19526918232440948
2023-01-22 10:57:06.622676: step: 692/466, loss: 0.15610742568969727
2023-01-22 10:57:07.331976: step: 694/466, loss: 0.2325829118490219
2023-01-22 10:57:08.000056: step: 696/466, loss: 0.067191481590271
2023-01-22 10:57:08.627517: step: 698/466, loss: 0.2806580662727356
2023-01-22 10:57:09.241514: step: 700/466, loss: 0.33890679478645325
2023-01-22 10:57:09.919161: step: 702/466, loss: 0.2745884656906128
2023-01-22 10:57:10.643343: step: 704/466, loss: 0.08699221163988113
2023-01-22 10:57:11.252234: step: 706/466, loss: 0.2990705072879791
2023-01-22 10:57:11.912723: step: 708/466, loss: 0.22613131999969482
2023-01-22 10:57:12.559446: step: 710/466, loss: 0.17546585202217102
2023-01-22 10:57:13.170641: step: 712/466, loss: 0.2502884566783905
2023-01-22 10:57:13.817860: step: 714/466, loss: 0.18384194374084473
2023-01-22 10:57:14.441974: step: 716/466, loss: 0.3344501852989197
2023-01-22 10:57:15.088695: step: 718/466, loss: 0.2311343103647232
2023-01-22 10:57:15.749945: step: 720/466, loss: 0.4437202215194702
2023-01-22 10:57:16.425618: step: 722/466, loss: 0.23476120829582214
2023-01-22 10:57:17.131823: step: 724/466, loss: 0.10877900570631027
2023-01-22 10:57:17.835096: step: 726/466, loss: 0.1343332678079605
2023-01-22 10:57:18.445487: step: 728/466, loss: 0.13292235136032104
2023-01-22 10:57:19.077096: step: 730/466, loss: 0.08492002636194229
2023-01-22 10:57:19.762677: step: 732/466, loss: 0.32326027750968933
2023-01-22 10:57:20.333761: step: 734/466, loss: 0.2701374590396881
2023-01-22 10:57:21.010222: step: 736/466, loss: 0.32011130452156067
2023-01-22 10:57:21.651852: step: 738/466, loss: 0.15664590895175934
2023-01-22 10:57:22.371875: step: 740/466, loss: 0.8938038349151611
2023-01-22 10:57:23.034634: step: 742/466, loss: 0.11967580020427704
2023-01-22 10:57:23.700004: step: 744/466, loss: 0.3725675046443939
2023-01-22 10:57:24.409604: step: 746/466, loss: 0.3549603521823883
2023-01-22 10:57:25.166474: step: 748/466, loss: 0.22611792385578156
2023-01-22 10:57:25.855225: step: 750/466, loss: 0.13594792783260345
2023-01-22 10:57:26.543335: step: 752/466, loss: 0.13058385252952576
2023-01-22 10:57:27.154185: step: 754/466, loss: 0.12555429339408875
2023-01-22 10:57:27.719913: step: 756/466, loss: 0.08366088569164276
2023-01-22 10:57:28.393931: step: 758/466, loss: 0.15027771890163422
2023-01-22 10:57:29.013621: step: 760/466, loss: 0.5595515966415405
2023-01-22 10:57:29.601584: step: 762/466, loss: 0.09424523264169693
2023-01-22 10:57:30.293081: step: 764/466, loss: 0.15257276594638824
2023-01-22 10:57:30.898851: step: 766/466, loss: 0.08885790407657623
2023-01-22 10:57:31.526205: step: 768/466, loss: 0.378495454788208
2023-01-22 10:57:32.155481: step: 770/466, loss: 0.07986627519130707
2023-01-22 10:57:32.802137: step: 772/466, loss: 0.1039273589849472
2023-01-22 10:57:33.498922: step: 774/466, loss: 0.09044419974088669
2023-01-22 10:57:34.142965: step: 776/466, loss: 0.2003486156463623
2023-01-22 10:57:34.775150: step: 778/466, loss: 0.17398804426193237
2023-01-22 10:57:35.432073: step: 780/466, loss: 0.30610060691833496
2023-01-22 10:57:36.070591: step: 782/466, loss: 0.14237099885940552
2023-01-22 10:57:36.736702: step: 784/466, loss: 0.2621976435184479
2023-01-22 10:57:37.330433: step: 786/466, loss: 0.35762977600097656
2023-01-22 10:57:37.966873: step: 788/466, loss: 0.38972553610801697
2023-01-22 10:57:38.633559: step: 790/466, loss: 0.13141439855098724
2023-01-22 10:57:39.268183: step: 792/466, loss: 0.11431451886892319
2023-01-22 10:57:39.830943: step: 794/466, loss: 0.25144729018211365
2023-01-22 10:57:40.462268: step: 796/466, loss: 0.35012686252593994
2023-01-22 10:57:41.128473: step: 798/466, loss: 0.11493077129125595
2023-01-22 10:57:41.891722: step: 800/466, loss: 0.5581721067428589
2023-01-22 10:57:42.551942: step: 802/466, loss: 0.1472097933292389
2023-01-22 10:57:43.143605: step: 804/466, loss: 0.3674423098564148
2023-01-22 10:57:43.857793: step: 806/466, loss: 0.2731553614139557
2023-01-22 10:57:44.559978: step: 808/466, loss: 0.20992299914360046
2023-01-22 10:57:45.333054: step: 810/466, loss: 0.5103529095649719
2023-01-22 10:57:46.077789: step: 812/466, loss: 0.06470693647861481
2023-01-22 10:57:46.757586: step: 814/466, loss: 0.08526197820901871
2023-01-22 10:57:47.452254: step: 816/466, loss: 0.5159960985183716
2023-01-22 10:57:48.108654: step: 818/466, loss: 0.7602057456970215
2023-01-22 10:57:48.754152: step: 820/466, loss: 0.44809937477111816
2023-01-22 10:57:49.346185: step: 822/466, loss: 0.0920209214091301
2023-01-22 10:57:49.948715: step: 824/466, loss: 0.10172657668590546
2023-01-22 10:57:50.602456: step: 826/466, loss: 0.1861218512058258
2023-01-22 10:57:51.237982: step: 828/466, loss: 0.11565698683261871
2023-01-22 10:57:51.832572: step: 830/466, loss: 0.11650048196315765
2023-01-22 10:57:52.480799: step: 832/466, loss: 0.22282303869724274
2023-01-22 10:57:53.152643: step: 834/466, loss: 0.45914947986602783
2023-01-22 10:57:53.808779: step: 836/466, loss: 0.20269319415092468
2023-01-22 10:57:54.464304: step: 838/466, loss: 0.4981473684310913
2023-01-22 10:57:55.100316: step: 840/466, loss: 0.12210121005773544
2023-01-22 10:57:55.720602: step: 842/466, loss: 0.27366921305656433
2023-01-22 10:57:56.376014: step: 844/466, loss: 0.24226875603199005
2023-01-22 10:57:57.074828: step: 846/466, loss: 0.32749420404434204
2023-01-22 10:57:57.757209: step: 848/466, loss: 0.2046627700328827
2023-01-22 10:57:58.412581: step: 850/466, loss: 11.532801628112793
2023-01-22 10:57:59.062227: step: 852/466, loss: 1.3917676210403442
2023-01-22 10:57:59.691465: step: 854/466, loss: 0.41023728251457214
2023-01-22 10:58:00.481685: step: 856/466, loss: 0.4746791124343872
2023-01-22 10:58:01.116198: step: 858/466, loss: 0.2983412742614746
2023-01-22 10:58:01.745526: step: 860/466, loss: 0.5580613613128662
2023-01-22 10:58:02.355072: step: 862/466, loss: 0.6077788472175598
2023-01-22 10:58:03.033716: step: 864/466, loss: 0.1894834190607071
2023-01-22 10:58:03.633996: step: 866/466, loss: 0.14195139706134796
2023-01-22 10:58:04.242031: step: 868/466, loss: 1.7875826358795166
2023-01-22 10:58:04.833003: step: 870/466, loss: 0.4175891578197479
2023-01-22 10:58:05.400376: step: 872/466, loss: 0.1943206787109375
2023-01-22 10:58:05.997818: step: 874/466, loss: 0.20352262258529663
2023-01-22 10:58:06.714581: step: 876/466, loss: 1.3924146890640259
2023-01-22 10:58:07.324883: step: 878/466, loss: 0.7312995791435242
2023-01-22 10:58:07.966414: step: 880/466, loss: 0.1208275556564331
2023-01-22 10:58:08.637160: step: 882/466, loss: 0.44542407989501953
2023-01-22 10:58:09.314260: step: 884/466, loss: 0.20071272552013397
2023-01-22 10:58:09.956583: step: 886/466, loss: 0.2863750755786896
2023-01-22 10:58:10.623992: step: 888/466, loss: 0.3443882465362549
2023-01-22 10:58:11.239256: step: 890/466, loss: 0.2728160321712494
2023-01-22 10:58:11.934327: step: 892/466, loss: 0.2089729905128479
2023-01-22 10:58:12.598523: step: 894/466, loss: 0.4772091209888458
2023-01-22 10:58:13.271541: step: 896/466, loss: 0.5877247452735901
2023-01-22 10:58:13.960730: step: 898/466, loss: 0.12831562757492065
2023-01-22 10:58:14.600941: step: 900/466, loss: 0.08909977227449417
2023-01-22 10:58:15.265174: step: 902/466, loss: 0.12847910821437836
2023-01-22 10:58:16.013876: step: 904/466, loss: 0.16102434694766998
2023-01-22 10:58:16.623038: step: 906/466, loss: 0.11746357381343842
2023-01-22 10:58:17.251401: step: 908/466, loss: 0.13781356811523438
2023-01-22 10:58:17.879586: step: 910/466, loss: 0.2222241312265396
2023-01-22 10:58:18.586891: step: 912/466, loss: 0.5814196467399597
2023-01-22 10:58:19.269981: step: 914/466, loss: 0.6439260840415955
2023-01-22 10:58:19.864690: step: 916/466, loss: 0.13478106260299683
2023-01-22 10:58:20.540300: step: 918/466, loss: 0.18502192199230194
2023-01-22 10:58:21.258908: step: 920/466, loss: 0.27424484491348267
2023-01-22 10:58:22.068181: step: 922/466, loss: 0.20019055902957916
2023-01-22 10:58:22.743975: step: 924/466, loss: 0.11570438742637634
2023-01-22 10:58:23.418254: step: 926/466, loss: 0.2209179401397705
2023-01-22 10:58:24.076896: step: 928/466, loss: 0.4133010804653168
2023-01-22 10:58:24.699830: step: 930/466, loss: 0.3311747908592224
2023-01-22 10:58:25.338429: step: 932/466, loss: 0.052754368633031845
==================================================
Loss: 0.319
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33515203916636727, 'r': 0.321796834569605, 'f1': 0.3283386869664701}, 'combined': 0.2419337693437148, 'epoch': 11}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.34513260930550244, 'r': 0.29840888060890913, 'f1': 0.32007457862020455}, 'combined': 0.2004205305378851, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3152404991413218, 'r': 0.3272040854464953, 'f1': 0.321110899497771}, 'combined': 0.23660803120888388, 'epoch': 11}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.35594899623239706, 'r': 0.30904596965303793, 'f1': 0.3308434148556193}, 'combined': 0.2050297218823556, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28212771699092254, 'r': 0.3303089210311181, 'f1': 0.304323079341607}, 'combined': 0.22423805846223674, 'epoch': 11}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3483506685998897, 'r': 0.30331075394366525, 'f1': 0.3242742328290902}, 'combined': 0.21511260989652517, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29375, 'r': 0.3357142857142857, 'f1': 0.31333333333333335}, 'combined': 0.2088888888888889, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2857142857142857, 'r': 0.20689655172413793, 'f1': 0.24000000000000002}, 'combined': 0.16, 'epoch': 11}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3152404991413218, 'r': 0.3272040854464953, 'f1': 0.321110899497771}, 'combined': 0.23660803120888388, 'epoch': 11}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.35594899623239706, 'r': 0.30904596965303793, 'f1': 0.3308434148556193}, 'combined': 0.2050297218823556, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:01:17.699531: step: 2/466, loss: 0.06511319428682327
2023-01-22 11:01:18.300331: step: 4/466, loss: 0.13714738190174103
2023-01-22 11:01:18.953307: step: 6/466, loss: 0.12040044367313385
2023-01-22 11:01:19.579310: step: 8/466, loss: 0.1934211552143097
2023-01-22 11:01:20.196944: step: 10/466, loss: 0.14183814823627472
2023-01-22 11:01:20.826181: step: 12/466, loss: 0.2772085964679718
2023-01-22 11:01:21.459292: step: 14/466, loss: 1.1655776500701904
2023-01-22 11:01:22.058101: step: 16/466, loss: 0.13058745861053467
2023-01-22 11:01:22.645695: step: 18/466, loss: 0.18193387985229492
2023-01-22 11:01:23.269002: step: 20/466, loss: 0.4208381772041321
2023-01-22 11:01:23.840713: step: 22/466, loss: 0.15971587598323822
2023-01-22 11:01:24.442994: step: 24/466, loss: 0.04996322840452194
2023-01-22 11:01:25.089770: step: 26/466, loss: 0.6347571611404419
2023-01-22 11:01:25.729345: step: 28/466, loss: 0.06279143691062927
2023-01-22 11:01:26.314740: step: 30/466, loss: 0.09358839690685272
2023-01-22 11:01:26.956888: step: 32/466, loss: 4.3400750160217285
2023-01-22 11:01:27.628152: step: 34/466, loss: 0.21792274713516235
2023-01-22 11:01:28.243248: step: 36/466, loss: 0.15213552117347717
2023-01-22 11:01:28.909534: step: 38/466, loss: 0.13988621532917023
2023-01-22 11:01:29.550337: step: 40/466, loss: 0.19849446415901184
2023-01-22 11:01:30.114714: step: 42/466, loss: 0.03976305201649666
2023-01-22 11:01:30.726520: step: 44/466, loss: 0.258556991815567
2023-01-22 11:01:31.294640: step: 46/466, loss: 0.5114126205444336
2023-01-22 11:01:31.857036: step: 48/466, loss: 0.074154332280159
2023-01-22 11:01:32.434625: step: 50/466, loss: 0.061618831008672714
2023-01-22 11:01:33.115777: step: 52/466, loss: 0.1468667984008789
2023-01-22 11:01:33.708377: step: 54/466, loss: 0.30897611379623413
2023-01-22 11:01:34.318585: step: 56/466, loss: 0.10922352969646454
2023-01-22 11:01:35.000109: step: 58/466, loss: 0.15912429988384247
2023-01-22 11:01:35.615657: step: 60/466, loss: 0.1769641935825348
2023-01-22 11:01:36.238683: step: 62/466, loss: 0.3742664158344269
2023-01-22 11:01:36.835493: step: 64/466, loss: 0.07299426943063736
2023-01-22 11:01:37.477523: step: 66/466, loss: 0.17261630296707153
2023-01-22 11:01:38.103895: step: 68/466, loss: 0.14107061922550201
2023-01-22 11:01:38.795202: step: 70/466, loss: 0.054710984230041504
2023-01-22 11:01:39.418000: step: 72/466, loss: 0.06515087932348251
2023-01-22 11:01:39.998454: step: 74/466, loss: 0.12145428359508514
2023-01-22 11:01:40.593621: step: 76/466, loss: 0.19312424957752228
2023-01-22 11:01:41.303627: step: 78/466, loss: 0.27080410718917847
2023-01-22 11:01:41.971295: step: 80/466, loss: 0.20949777960777283
2023-01-22 11:01:42.609346: step: 82/466, loss: 0.18421269953250885
2023-01-22 11:01:43.208788: step: 84/466, loss: 0.21335816383361816
2023-01-22 11:01:43.846525: step: 86/466, loss: 0.1356712132692337
2023-01-22 11:01:44.514671: step: 88/466, loss: 0.18476635217666626
2023-01-22 11:01:45.164444: step: 90/466, loss: 0.7203394174575806
2023-01-22 11:01:45.775121: step: 92/466, loss: 0.32669126987457275
2023-01-22 11:01:46.404855: step: 94/466, loss: 0.834490954875946
2023-01-22 11:01:47.049626: step: 96/466, loss: 0.12480907887220383
2023-01-22 11:01:47.679589: step: 98/466, loss: 0.21006691455841064
2023-01-22 11:01:48.290235: step: 100/466, loss: 0.10662776231765747
2023-01-22 11:01:48.936327: step: 102/466, loss: 0.3675839900970459
2023-01-22 11:01:49.537943: step: 104/466, loss: 0.12077916413545609
2023-01-22 11:01:50.203982: step: 106/466, loss: 0.2399625927209854
2023-01-22 11:01:50.814889: step: 108/466, loss: 0.10004761070013046
2023-01-22 11:01:51.536794: step: 110/466, loss: 0.12662649154663086
2023-01-22 11:01:52.204224: step: 112/466, loss: 0.3942157030105591
2023-01-22 11:01:52.866049: step: 114/466, loss: 0.4537506103515625
2023-01-22 11:01:53.569919: step: 116/466, loss: 0.18500998616218567
2023-01-22 11:01:54.166310: step: 118/466, loss: 0.1711919903755188
2023-01-22 11:01:54.785623: step: 120/466, loss: 0.33424004912376404
2023-01-22 11:01:55.404380: step: 122/466, loss: 0.22498555481433868
2023-01-22 11:01:56.054308: step: 124/466, loss: 0.19132056832313538
2023-01-22 11:01:56.717839: step: 126/466, loss: 0.6551756858825684
2023-01-22 11:01:57.368818: step: 128/466, loss: 0.37431344389915466
2023-01-22 11:01:57.970877: step: 130/466, loss: 0.2734319269657135
2023-01-22 11:01:58.586777: step: 132/466, loss: 0.10243318974971771
2023-01-22 11:01:59.202156: step: 134/466, loss: 0.17675721645355225
2023-01-22 11:01:59.838228: step: 136/466, loss: 0.09176446497440338
2023-01-22 11:02:00.509635: step: 138/466, loss: 0.1962217390537262
2023-01-22 11:02:01.126836: step: 140/466, loss: 0.3212512135505676
2023-01-22 11:02:01.739307: step: 142/466, loss: 0.11028824746608734
2023-01-22 11:02:02.393916: step: 144/466, loss: 0.45328283309936523
2023-01-22 11:02:03.102954: step: 146/466, loss: 0.07855706661939621
2023-01-22 11:02:03.762620: step: 148/466, loss: 0.07228368520736694
2023-01-22 11:02:04.354911: step: 150/466, loss: 0.1302642971277237
2023-01-22 11:02:04.955836: step: 152/466, loss: 0.06668470799922943
2023-01-22 11:02:05.580555: step: 154/466, loss: 0.23040235042572021
2023-01-22 11:02:06.256310: step: 156/466, loss: 0.28832942247390747
2023-01-22 11:02:06.889794: step: 158/466, loss: 0.09825500845909119
2023-01-22 11:02:07.475201: step: 160/466, loss: 0.8808926939964294
2023-01-22 11:02:08.066254: step: 162/466, loss: 0.10054733604192734
2023-01-22 11:02:08.733191: step: 164/466, loss: 0.13233955204486847
2023-01-22 11:02:09.416623: step: 166/466, loss: 0.13742248713970184
2023-01-22 11:02:10.019833: step: 168/466, loss: 0.1636868417263031
2023-01-22 11:02:10.661561: step: 170/466, loss: 0.09520162642002106
2023-01-22 11:02:11.339099: step: 172/466, loss: 0.1735386997461319
2023-01-22 11:02:11.983790: step: 174/466, loss: 0.07352687418460846
2023-01-22 11:02:12.663379: step: 176/466, loss: 0.11939296871423721
2023-01-22 11:02:13.323775: step: 178/466, loss: 0.06646954268217087
2023-01-22 11:02:13.962960: step: 180/466, loss: 0.2287725806236267
2023-01-22 11:02:14.621409: step: 182/466, loss: 0.13557642698287964
2023-01-22 11:02:15.288477: step: 184/466, loss: 0.12363395094871521
2023-01-22 11:02:15.888152: step: 186/466, loss: 0.04114263132214546
2023-01-22 11:02:16.522673: step: 188/466, loss: 0.6626765727996826
2023-01-22 11:02:17.104487: step: 190/466, loss: 0.021727893501520157
2023-01-22 11:02:17.692409: step: 192/466, loss: 0.528025209903717
2023-01-22 11:02:18.324677: step: 194/466, loss: 0.04923209920525551
2023-01-22 11:02:19.053480: step: 196/466, loss: 0.15736114978790283
2023-01-22 11:02:19.674341: step: 198/466, loss: 0.1750304102897644
2023-01-22 11:02:20.285073: step: 200/466, loss: 0.06680495291948318
2023-01-22 11:02:20.891352: step: 202/466, loss: 0.09692071378231049
2023-01-22 11:02:21.550885: step: 204/466, loss: 0.07838789373636246
2023-01-22 11:02:22.226213: step: 206/466, loss: 0.3004598021507263
2023-01-22 11:02:22.864580: step: 208/466, loss: 0.1860407292842865
2023-01-22 11:02:23.488998: step: 210/466, loss: 0.35397303104400635
2023-01-22 11:02:24.118358: step: 212/466, loss: 0.18014740943908691
2023-01-22 11:02:24.782957: step: 214/466, loss: 0.24358399212360382
2023-01-22 11:02:25.485954: step: 216/466, loss: 0.21685518324375153
2023-01-22 11:02:26.104588: step: 218/466, loss: 0.08633943647146225
2023-01-22 11:02:26.715886: step: 220/466, loss: 0.08359657973051071
2023-01-22 11:02:27.461753: step: 222/466, loss: 0.1390642523765564
2023-01-22 11:02:28.068842: step: 224/466, loss: 0.5406646728515625
2023-01-22 11:02:28.738151: step: 226/466, loss: 0.20375865697860718
2023-01-22 11:02:29.328865: step: 228/466, loss: 0.2889938950538635
2023-01-22 11:02:30.024643: step: 230/466, loss: 0.37442490458488464
2023-01-22 11:02:30.639781: step: 232/466, loss: 0.06598281115293503
2023-01-22 11:02:31.292670: step: 234/466, loss: 0.24299190938472748
2023-01-22 11:02:31.912956: step: 236/466, loss: 0.12016425281763077
2023-01-22 11:02:32.531946: step: 238/466, loss: 0.09447656571865082
2023-01-22 11:02:33.179193: step: 240/466, loss: 0.23242297768592834
2023-01-22 11:02:33.806028: step: 242/466, loss: 0.14975641667842865
2023-01-22 11:02:34.494592: step: 244/466, loss: 0.26126527786254883
2023-01-22 11:02:35.063930: step: 246/466, loss: 0.26530560851097107
2023-01-22 11:02:35.724941: step: 248/466, loss: 0.3171543478965759
2023-01-22 11:02:36.470490: step: 250/466, loss: 0.19703979790210724
2023-01-22 11:02:37.093820: step: 252/466, loss: 0.04827583208680153
2023-01-22 11:02:37.759108: step: 254/466, loss: 0.299142450094223
2023-01-22 11:02:38.442998: step: 256/466, loss: 0.20214809477329254
2023-01-22 11:02:39.097052: step: 258/466, loss: 0.7955482006072998
2023-01-22 11:02:39.755463: step: 260/466, loss: 0.40130114555358887
2023-01-22 11:02:40.436757: step: 262/466, loss: 0.16113027930259705
2023-01-22 11:02:41.168868: step: 264/466, loss: 0.07945267111063004
2023-01-22 11:02:41.774570: step: 266/466, loss: 0.11397974193096161
2023-01-22 11:02:42.405006: step: 268/466, loss: 0.1477915346622467
2023-01-22 11:02:43.051542: step: 270/466, loss: 0.42245355248451233
2023-01-22 11:02:43.701786: step: 272/466, loss: 0.06648483872413635
2023-01-22 11:02:44.440584: step: 274/466, loss: 0.30151882767677307
2023-01-22 11:02:45.102006: step: 276/466, loss: 0.18119044601917267
2023-01-22 11:02:45.803073: step: 278/466, loss: 0.7626487016677856
2023-01-22 11:02:46.470164: step: 280/466, loss: 0.4290889799594879
2023-01-22 11:02:47.083829: step: 282/466, loss: 0.07369454205036163
2023-01-22 11:02:47.796784: step: 284/466, loss: 0.32976651191711426
2023-01-22 11:02:48.495783: step: 286/466, loss: 0.0721362978219986
2023-01-22 11:02:49.200492: step: 288/466, loss: 0.2435348480939865
2023-01-22 11:02:49.886851: step: 290/466, loss: 0.26690465211868286
2023-01-22 11:02:50.545284: step: 292/466, loss: 0.04773420840501785
2023-01-22 11:02:51.264440: step: 294/466, loss: 0.15354648232460022
2023-01-22 11:02:51.921889: step: 296/466, loss: 0.07595565915107727
2023-01-22 11:02:52.557960: step: 298/466, loss: 0.12475527822971344
2023-01-22 11:02:53.145299: step: 300/466, loss: 0.18679562211036682
2023-01-22 11:02:53.793517: step: 302/466, loss: 0.09634778648614883
2023-01-22 11:02:54.435832: step: 304/466, loss: 0.17946763336658478
2023-01-22 11:02:55.038294: step: 306/466, loss: 0.08628623932600021
2023-01-22 11:02:55.690896: step: 308/466, loss: 0.09216740727424622
2023-01-22 11:02:56.288093: step: 310/466, loss: 0.12150314450263977
2023-01-22 11:02:56.951098: step: 312/466, loss: 0.23423610627651215
2023-01-22 11:02:57.565508: step: 314/466, loss: 0.1008576825261116
2023-01-22 11:02:58.214856: step: 316/466, loss: 0.15783874690532684
2023-01-22 11:02:58.862337: step: 318/466, loss: 0.06963887065649033
2023-01-22 11:02:59.485934: step: 320/466, loss: 0.06577898561954498
2023-01-22 11:03:00.167929: step: 322/466, loss: 1.1378934383392334
2023-01-22 11:03:00.806527: step: 324/466, loss: 0.364601194858551
2023-01-22 11:03:01.473307: step: 326/466, loss: 0.28841596841812134
2023-01-22 11:03:02.141700: step: 328/466, loss: 0.11138347536325455
2023-01-22 11:03:02.743121: step: 330/466, loss: 0.4491463601589203
2023-01-22 11:03:03.396073: step: 332/466, loss: 0.10850333422422409
2023-01-22 11:03:04.022734: step: 334/466, loss: 0.11454664170742035
2023-01-22 11:03:04.650701: step: 336/466, loss: 0.46762022376060486
2023-01-22 11:03:05.339998: step: 338/466, loss: 0.1430659145116806
2023-01-22 11:03:05.981574: step: 340/466, loss: 1.066911220550537
2023-01-22 11:03:06.652449: step: 342/466, loss: 0.25913503766059875
2023-01-22 11:03:07.328531: step: 344/466, loss: 0.16815349459648132
2023-01-22 11:03:08.050211: step: 346/466, loss: 0.13444244861602783
2023-01-22 11:03:08.743698: step: 348/466, loss: 0.13549885153770447
2023-01-22 11:03:09.437770: step: 350/466, loss: 0.23235894739627838
2023-01-22 11:03:10.077540: step: 352/466, loss: 0.39627596735954285
2023-01-22 11:03:10.646733: step: 354/466, loss: 0.12371134012937546
2023-01-22 11:03:11.299615: step: 356/466, loss: 0.11389538645744324
2023-01-22 11:03:11.910378: step: 358/466, loss: 0.09537847340106964
2023-01-22 11:03:12.591901: step: 360/466, loss: 0.4542959928512573
2023-01-22 11:03:13.197989: step: 362/466, loss: 0.057292964309453964
2023-01-22 11:03:14.002836: step: 364/466, loss: 0.21706074476242065
2023-01-22 11:03:14.680716: step: 366/466, loss: 0.802412211894989
2023-01-22 11:03:15.390369: step: 368/466, loss: 0.2602801024913788
2023-01-22 11:03:16.022187: step: 370/466, loss: 0.0633874163031578
2023-01-22 11:03:16.662231: step: 372/466, loss: 0.16423580050468445
2023-01-22 11:03:17.315632: step: 374/466, loss: 0.23285065591335297
2023-01-22 11:03:17.998162: step: 376/466, loss: 0.10875140875577927
2023-01-22 11:03:18.633194: step: 378/466, loss: 0.25117120146751404
2023-01-22 11:03:19.308008: step: 380/466, loss: 0.133839413523674
2023-01-22 11:03:20.009568: step: 382/466, loss: 0.13380390405654907
2023-01-22 11:03:20.575388: step: 384/466, loss: 0.14601582288742065
2023-01-22 11:03:21.330224: step: 386/466, loss: 0.1574646681547165
2023-01-22 11:03:21.938224: step: 388/466, loss: 0.07392328977584839
2023-01-22 11:03:22.582150: step: 390/466, loss: 0.6617650389671326
2023-01-22 11:03:23.196381: step: 392/466, loss: 0.09536303579807281
2023-01-22 11:03:23.820276: step: 394/466, loss: 0.31436464190483093
2023-01-22 11:03:24.467311: step: 396/466, loss: 0.4017498791217804
2023-01-22 11:03:25.070418: step: 398/466, loss: 0.08853510767221451
2023-01-22 11:03:25.780652: step: 400/466, loss: 0.11967477202415466
2023-01-22 11:03:26.385561: step: 402/466, loss: 4.735015869140625
2023-01-22 11:03:27.053124: step: 404/466, loss: 0.6043958067893982
2023-01-22 11:03:27.637735: step: 406/466, loss: 0.3705092966556549
2023-01-22 11:03:28.361665: step: 408/466, loss: 0.10290555655956268
2023-01-22 11:03:29.000169: step: 410/466, loss: 0.06083455681800842
2023-01-22 11:03:29.614715: step: 412/466, loss: 0.05793687701225281
2023-01-22 11:03:30.271141: step: 414/466, loss: 0.29581812024116516
2023-01-22 11:03:30.983747: step: 416/466, loss: 0.09313644468784332
2023-01-22 11:03:31.608601: step: 418/466, loss: 0.08619770407676697
2023-01-22 11:03:32.191824: step: 420/466, loss: 0.05409029871225357
2023-01-22 11:03:32.827789: step: 422/466, loss: 0.19690914452075958
2023-01-22 11:03:33.479160: step: 424/466, loss: 0.14666756987571716
2023-01-22 11:03:34.122654: step: 426/466, loss: 0.060391172766685486
2023-01-22 11:03:34.725176: step: 428/466, loss: 0.1270732432603836
2023-01-22 11:03:35.403234: step: 430/466, loss: 0.304675430059433
2023-01-22 11:03:36.031749: step: 432/466, loss: 0.37709683179855347
2023-01-22 11:03:36.714816: step: 434/466, loss: 0.06947958469390869
2023-01-22 11:03:37.420806: step: 436/466, loss: 0.12346003204584122
2023-01-22 11:03:38.055574: step: 438/466, loss: 0.1719336062669754
2023-01-22 11:03:38.646511: step: 440/466, loss: 0.27502453327178955
2023-01-22 11:03:39.331637: step: 442/466, loss: 0.49445199966430664
2023-01-22 11:03:39.971357: step: 444/466, loss: 0.07066982239484787
2023-01-22 11:03:40.642767: step: 446/466, loss: 0.7173477411270142
2023-01-22 11:03:41.256743: step: 448/466, loss: 0.28133848309516907
2023-01-22 11:03:41.935023: step: 450/466, loss: 0.17305824160575867
2023-01-22 11:03:42.636032: step: 452/466, loss: 0.1007755696773529
2023-01-22 11:03:43.335895: step: 454/466, loss: 0.07673931121826172
2023-01-22 11:03:43.997444: step: 456/466, loss: 0.26113641262054443
2023-01-22 11:03:44.638115: step: 458/466, loss: 0.09634999930858612
2023-01-22 11:03:45.362710: step: 460/466, loss: 0.3144139349460602
2023-01-22 11:03:46.020335: step: 462/466, loss: 0.1348186433315277
2023-01-22 11:03:46.752767: step: 464/466, loss: 0.6207475662231445
2023-01-22 11:03:47.443299: step: 466/466, loss: 0.6087349057197571
2023-01-22 11:03:48.103153: step: 468/466, loss: 1.3309130668640137
2023-01-22 11:03:48.766647: step: 470/466, loss: 0.11831938475370407
2023-01-22 11:03:49.404846: step: 472/466, loss: 0.35188978910446167
2023-01-22 11:03:50.155215: step: 474/466, loss: 0.07000864297151566
2023-01-22 11:03:50.851104: step: 476/466, loss: 0.15208332240581512
2023-01-22 11:03:51.449387: step: 478/466, loss: 0.2524581849575043
2023-01-22 11:03:52.116006: step: 480/466, loss: 0.1295643150806427
2023-01-22 11:03:52.757985: step: 482/466, loss: 0.13918237388134003
2023-01-22 11:03:53.389309: step: 484/466, loss: 0.06539881229400635
2023-01-22 11:03:54.091209: step: 486/466, loss: 0.7312734127044678
2023-01-22 11:03:54.768829: step: 488/466, loss: 0.3051009178161621
2023-01-22 11:03:55.423569: step: 490/466, loss: 0.29282113909721375
2023-01-22 11:03:56.085387: step: 492/466, loss: 0.06706909090280533
2023-01-22 11:03:56.796297: step: 494/466, loss: 0.19537198543548584
2023-01-22 11:03:57.410134: step: 496/466, loss: 1.2063255310058594
2023-01-22 11:03:58.053342: step: 498/466, loss: 0.24088512361049652
2023-01-22 11:03:58.727748: step: 500/466, loss: 0.08956007659435272
2023-01-22 11:03:59.434224: step: 502/466, loss: 1.016743779182434
2023-01-22 11:04:00.091512: step: 504/466, loss: 0.32006266713142395
2023-01-22 11:04:00.796363: step: 506/466, loss: 0.4554866552352905
2023-01-22 11:04:01.433706: step: 508/466, loss: 0.6734225749969482
2023-01-22 11:04:02.095528: step: 510/466, loss: 0.294268399477005
2023-01-22 11:04:02.777039: step: 512/466, loss: 0.22506310045719147
2023-01-22 11:04:03.474804: step: 514/466, loss: 0.3229205012321472
2023-01-22 11:04:04.115112: step: 516/466, loss: 0.6201850771903992
2023-01-22 11:04:04.728438: step: 518/466, loss: 0.07383572310209274
2023-01-22 11:04:05.405677: step: 520/466, loss: 0.6262032985687256
2023-01-22 11:04:06.090960: step: 522/466, loss: 0.24702614545822144
2023-01-22 11:04:06.755618: step: 524/466, loss: 0.9728817343711853
2023-01-22 11:04:07.487719: step: 526/466, loss: 2.29763126373291
2023-01-22 11:04:08.160706: step: 528/466, loss: 0.4962475001811981
2023-01-22 11:04:08.761950: step: 530/466, loss: 0.143583282828331
2023-01-22 11:04:09.423093: step: 532/466, loss: 0.3662044107913971
2023-01-22 11:04:10.033353: step: 534/466, loss: 3.1325182914733887
2023-01-22 11:04:10.670614: step: 536/466, loss: 0.18455298244953156
2023-01-22 11:04:11.294073: step: 538/466, loss: 0.17454926669597626
2023-01-22 11:04:11.992085: step: 540/466, loss: 0.12500549852848053
2023-01-22 11:04:12.684581: step: 542/466, loss: 0.22460201382637024
2023-01-22 11:04:13.450215: step: 544/466, loss: 0.33004269003868103
2023-01-22 11:04:14.084772: step: 546/466, loss: 0.20828965306282043
2023-01-22 11:04:14.739108: step: 548/466, loss: 0.17520847916603088
2023-01-22 11:04:15.353012: step: 550/466, loss: 0.10480187088251114
2023-01-22 11:04:16.052234: step: 552/466, loss: 0.13264250755310059
2023-01-22 11:04:16.723112: step: 554/466, loss: 0.21460601687431335
2023-01-22 11:04:17.378536: step: 556/466, loss: 0.08982677757740021
2023-01-22 11:04:18.102311: step: 558/466, loss: 0.10906903445720673
2023-01-22 11:04:18.796717: step: 560/466, loss: 0.21557100117206573
2023-01-22 11:04:19.462775: step: 562/466, loss: 0.13042625784873962
2023-01-22 11:04:20.106869: step: 564/466, loss: 0.15146774053573608
2023-01-22 11:04:20.696231: step: 566/466, loss: 0.03116701729595661
2023-01-22 11:04:21.328356: step: 568/466, loss: 0.02243943326175213
2023-01-22 11:04:22.051616: step: 570/466, loss: 0.08668933063745499
2023-01-22 11:04:22.743643: step: 572/466, loss: 0.04543516784906387
2023-01-22 11:04:23.383105: step: 574/466, loss: 0.38458898663520813
2023-01-22 11:04:24.065347: step: 576/466, loss: 0.2776734530925751
2023-01-22 11:04:24.705332: step: 578/466, loss: 0.13305240869522095
2023-01-22 11:04:25.383837: step: 580/466, loss: 0.3373351991176605
2023-01-22 11:04:26.069424: step: 582/466, loss: 0.40106603503227234
2023-01-22 11:04:26.770778: step: 584/466, loss: 0.37612906098365784
2023-01-22 11:04:27.413303: step: 586/466, loss: 0.5300690531730652
2023-01-22 11:04:28.076586: step: 588/466, loss: 0.4692898392677307
2023-01-22 11:04:28.688431: step: 590/466, loss: 0.18448734283447266
2023-01-22 11:04:29.360385: step: 592/466, loss: 0.15303319692611694
2023-01-22 11:04:29.991071: step: 594/466, loss: 0.07411587238311768
2023-01-22 11:04:30.626453: step: 596/466, loss: 0.08063060790300369
2023-01-22 11:04:31.274544: step: 598/466, loss: 0.19190742075443268
2023-01-22 11:04:31.907353: step: 600/466, loss: 0.17303743958473206
2023-01-22 11:04:32.546355: step: 602/466, loss: 0.7020127773284912
2023-01-22 11:04:33.200068: step: 604/466, loss: 0.21286289393901825
2023-01-22 11:04:33.871630: step: 606/466, loss: 0.12226472795009613
2023-01-22 11:04:34.516005: step: 608/466, loss: 0.17794010043144226
2023-01-22 11:04:35.143200: step: 610/466, loss: 0.05442595109343529
2023-01-22 11:04:35.789684: step: 612/466, loss: 0.7128135561943054
2023-01-22 11:04:36.434442: step: 614/466, loss: 0.13611501455307007
2023-01-22 11:04:37.110351: step: 616/466, loss: 0.41149094700813293
2023-01-22 11:04:37.691804: step: 618/466, loss: 0.3342394530773163
2023-01-22 11:04:38.335650: step: 620/466, loss: 0.2459389865398407
2023-01-22 11:04:38.960757: step: 622/466, loss: 0.10671906918287277
2023-01-22 11:04:39.603287: step: 624/466, loss: 0.08950351923704147
2023-01-22 11:04:40.234275: step: 626/466, loss: 0.11727484315633774
2023-01-22 11:04:40.913933: step: 628/466, loss: 0.06244143843650818
2023-01-22 11:04:41.536286: step: 630/466, loss: 0.12855567038059235
2023-01-22 11:04:42.193701: step: 632/466, loss: 0.0703582912683487
2023-01-22 11:04:42.826442: step: 634/466, loss: 0.05989354848861694
2023-01-22 11:04:43.437771: step: 636/466, loss: 0.19541144371032715
2023-01-22 11:04:44.088615: step: 638/466, loss: 0.077695332467556
2023-01-22 11:04:44.699380: step: 640/466, loss: 0.3223434388637543
2023-01-22 11:04:45.317967: step: 642/466, loss: 0.08753734081983566
2023-01-22 11:04:45.901843: step: 644/466, loss: 0.1359861195087433
2023-01-22 11:04:46.541466: step: 646/466, loss: 0.44570258259773254
2023-01-22 11:04:47.187130: step: 648/466, loss: 0.23596426844596863
2023-01-22 11:04:47.889679: step: 650/466, loss: 0.3924348056316376
2023-01-22 11:04:48.534133: step: 652/466, loss: 0.4193865656852722
2023-01-22 11:04:49.201578: step: 654/466, loss: 0.10640563070774078
2023-01-22 11:04:49.821607: step: 656/466, loss: 0.06833884119987488
2023-01-22 11:04:50.513825: step: 658/466, loss: 0.17900003492832184
2023-01-22 11:04:51.166609: step: 660/466, loss: 0.17604024708271027
2023-01-22 11:04:51.839511: step: 662/466, loss: 0.327255517244339
2023-01-22 11:04:52.471366: step: 664/466, loss: 0.18427890539169312
2023-01-22 11:04:53.074669: step: 666/466, loss: 0.2898465394973755
2023-01-22 11:04:53.776390: step: 668/466, loss: 0.1335490345954895
2023-01-22 11:04:54.476699: step: 670/466, loss: 0.12968330085277557
2023-01-22 11:04:55.122148: step: 672/466, loss: 0.39474010467529297
2023-01-22 11:04:55.837656: step: 674/466, loss: 0.1463014930486679
2023-01-22 11:04:56.455462: step: 676/466, loss: 1.5141112804412842
2023-01-22 11:04:57.142118: step: 678/466, loss: 0.5454038977622986
2023-01-22 11:04:57.776823: step: 680/466, loss: 0.2692568004131317
2023-01-22 11:04:58.395488: step: 682/466, loss: 0.5969122648239136
2023-01-22 11:04:59.016835: step: 684/466, loss: 0.05869481712579727
2023-01-22 11:04:59.612768: step: 686/466, loss: 0.9477701187133789
2023-01-22 11:05:00.229823: step: 688/466, loss: 0.4314132034778595
2023-01-22 11:05:00.931561: step: 690/466, loss: 0.13118954002857208
2023-01-22 11:05:01.608618: step: 692/466, loss: 0.12757283449172974
2023-01-22 11:05:02.248244: step: 694/466, loss: 0.16748552024364471
2023-01-22 11:05:02.909543: step: 696/466, loss: 0.4196185767650604
2023-01-22 11:05:03.510553: step: 698/466, loss: 0.1329767256975174
2023-01-22 11:05:04.192980: step: 700/466, loss: 0.32858502864837646
2023-01-22 11:05:04.901140: step: 702/466, loss: 0.08262277394533157
2023-01-22 11:05:05.558395: step: 704/466, loss: 0.1173609271645546
2023-01-22 11:05:06.212923: step: 706/466, loss: 0.2870000898838043
2023-01-22 11:05:06.896423: step: 708/466, loss: 0.5597653388977051
2023-01-22 11:05:07.594327: step: 710/466, loss: 0.14444905519485474
2023-01-22 11:05:08.493454: step: 712/466, loss: 0.35095858573913574
2023-01-22 11:05:09.137122: step: 714/466, loss: 0.1954328566789627
2023-01-22 11:05:09.748976: step: 716/466, loss: 0.19545452296733856
2023-01-22 11:05:10.368327: step: 718/466, loss: 0.7782852649688721
2023-01-22 11:05:11.053520: step: 720/466, loss: 0.5309181213378906
2023-01-22 11:05:11.766218: step: 722/466, loss: 0.36571553349494934
2023-01-22 11:05:12.400106: step: 724/466, loss: 0.7747761011123657
2023-01-22 11:05:13.025640: step: 726/466, loss: 0.20885266363620758
2023-01-22 11:05:13.729175: step: 728/466, loss: 0.17795908451080322
2023-01-22 11:05:14.393570: step: 730/466, loss: 0.09812970459461212
2023-01-22 11:05:15.117199: step: 732/466, loss: 0.6455363631248474
2023-01-22 11:05:15.745494: step: 734/466, loss: 0.4045051336288452
2023-01-22 11:05:16.366710: step: 736/466, loss: 0.10788479447364807
2023-01-22 11:05:17.101404: step: 738/466, loss: 0.14161811769008636
2023-01-22 11:05:17.706293: step: 740/466, loss: 0.11607873439788818
2023-01-22 11:05:18.391038: step: 742/466, loss: 0.055919233709573746
2023-01-22 11:05:18.997359: step: 744/466, loss: 0.1498071700334549
2023-01-22 11:05:19.618830: step: 746/466, loss: 0.03807078301906586
2023-01-22 11:05:20.262352: step: 748/466, loss: 1.082453966140747
2023-01-22 11:05:20.932557: step: 750/466, loss: 0.1055598184466362
2023-01-22 11:05:21.535189: step: 752/466, loss: 0.19270923733711243
2023-01-22 11:05:22.180640: step: 754/466, loss: 0.08269581198692322
2023-01-22 11:05:22.833820: step: 756/466, loss: 0.12768109142780304
2023-01-22 11:05:23.469979: step: 758/466, loss: 0.20174935460090637
2023-01-22 11:05:24.102441: step: 760/466, loss: 0.026714444160461426
2023-01-22 11:05:24.733593: step: 762/466, loss: 0.25208786129951477
2023-01-22 11:05:25.395352: step: 764/466, loss: 0.20811015367507935
2023-01-22 11:05:26.089826: step: 766/466, loss: 0.18629762530326843
2023-01-22 11:05:26.792257: step: 768/466, loss: 0.07611539959907532
2023-01-22 11:05:27.438545: step: 770/466, loss: 0.16778625547885895
2023-01-22 11:05:28.071465: step: 772/466, loss: 0.8209713101387024
2023-01-22 11:05:28.766198: step: 774/466, loss: 0.06022028997540474
2023-01-22 11:05:29.408459: step: 776/466, loss: 0.05615582689642906
2023-01-22 11:05:30.112224: step: 778/466, loss: 0.08323463052511215
2023-01-22 11:05:30.813597: step: 780/466, loss: 0.28745153546333313
2023-01-22 11:05:31.555858: step: 782/466, loss: 0.15258856117725372
2023-01-22 11:05:32.216669: step: 784/466, loss: 0.11546079814434052
2023-01-22 11:05:32.877449: step: 786/466, loss: 0.15049335360527039
2023-01-22 11:05:33.568275: step: 788/466, loss: 0.1887330263853073
2023-01-22 11:05:34.214725: step: 790/466, loss: 0.0862591415643692
2023-01-22 11:05:34.973040: step: 792/466, loss: 0.8746164441108704
2023-01-22 11:05:35.596016: step: 794/466, loss: 0.20723503828048706
2023-01-22 11:05:36.261718: step: 796/466, loss: 0.4907574951648712
2023-01-22 11:05:36.929749: step: 798/466, loss: 1.3156168460845947
2023-01-22 11:05:37.568840: step: 800/466, loss: 0.21074840426445007
2023-01-22 11:05:38.340528: step: 802/466, loss: 0.3152695596218109
2023-01-22 11:05:38.949083: step: 804/466, loss: 0.06980019062757492
2023-01-22 11:05:39.577953: step: 806/466, loss: 1.8368053436279297
2023-01-22 11:05:40.270036: step: 808/466, loss: 1.4271897077560425
2023-01-22 11:05:40.936488: step: 810/466, loss: 0.19687141478061676
2023-01-22 11:05:41.580483: step: 812/466, loss: 0.3990250825881958
2023-01-22 11:05:42.237979: step: 814/466, loss: 0.15776890516281128
2023-01-22 11:05:42.978106: step: 816/466, loss: 0.11926817893981934
2023-01-22 11:05:43.657766: step: 818/466, loss: 0.07674985378980637
2023-01-22 11:05:44.305186: step: 820/466, loss: 0.1839275360107422
2023-01-22 11:05:44.939815: step: 822/466, loss: 0.035189174115657806
2023-01-22 11:05:45.663078: step: 824/466, loss: 0.2586238384246826
2023-01-22 11:05:46.271811: step: 826/466, loss: 0.11197404563426971
2023-01-22 11:05:46.931159: step: 828/466, loss: 0.41328197717666626
2023-01-22 11:05:47.579047: step: 830/466, loss: 0.6752942204475403
2023-01-22 11:05:48.262028: step: 832/466, loss: 0.23095834255218506
2023-01-22 11:05:48.911408: step: 834/466, loss: 0.19791486859321594
2023-01-22 11:05:49.674970: step: 836/466, loss: 0.4155274033546448
2023-01-22 11:05:50.318603: step: 838/466, loss: 0.11686521023511887
2023-01-22 11:05:50.985442: step: 840/466, loss: 0.10920114070177078
2023-01-22 11:05:51.704024: step: 842/466, loss: 0.1957877278327942
2023-01-22 11:05:52.347580: step: 844/466, loss: 0.19180512428283691
2023-01-22 11:05:52.983901: step: 846/466, loss: 0.8602334260940552
2023-01-22 11:05:53.841111: step: 848/466, loss: 1.637770175933838
2023-01-22 11:05:54.507656: step: 850/466, loss: 0.08310823887586594
2023-01-22 11:05:55.265371: step: 852/466, loss: 0.3732314109802246
2023-01-22 11:05:55.915815: step: 854/466, loss: 0.2023201435804367
2023-01-22 11:05:56.595123: step: 856/466, loss: 0.3385159969329834
2023-01-22 11:05:57.247603: step: 858/466, loss: 0.10411600768566132
2023-01-22 11:05:57.866428: step: 860/466, loss: 0.18611595034599304
2023-01-22 11:05:58.488529: step: 862/466, loss: 0.24844716489315033
2023-01-22 11:05:59.082049: step: 864/466, loss: 0.12318140268325806
2023-01-22 11:05:59.718353: step: 866/466, loss: 0.20975176990032196
2023-01-22 11:06:00.358575: step: 868/466, loss: 0.1696348488330841
2023-01-22 11:06:01.028453: step: 870/466, loss: 0.23161551356315613
2023-01-22 11:06:01.597771: step: 872/466, loss: 0.19035020470619202
2023-01-22 11:06:02.240172: step: 874/466, loss: 0.3820752203464508
2023-01-22 11:06:02.933489: step: 876/466, loss: 0.1305333822965622
2023-01-22 11:06:03.622665: step: 878/466, loss: 0.1538640856742859
2023-01-22 11:06:04.253339: step: 880/466, loss: 0.3288590908050537
2023-01-22 11:06:04.833949: step: 882/466, loss: 0.18580347299575806
2023-01-22 11:06:05.470993: step: 884/466, loss: 0.1356642097234726
2023-01-22 11:06:06.139159: step: 886/466, loss: 0.49856212735176086
2023-01-22 11:06:06.871372: step: 888/466, loss: 0.23073936998844147
2023-01-22 11:06:07.494660: step: 890/466, loss: 0.2459000051021576
2023-01-22 11:06:08.187842: step: 892/466, loss: 0.18568305671215057
2023-01-22 11:06:08.845010: step: 894/466, loss: 0.15195661783218384
2023-01-22 11:06:09.524461: step: 896/466, loss: 0.11524511873722076
2023-01-22 11:06:10.152845: step: 898/466, loss: 0.11277007311582565
2023-01-22 11:06:10.805950: step: 900/466, loss: 0.04688365012407303
2023-01-22 11:06:11.427161: step: 902/466, loss: 0.08872295916080475
2023-01-22 11:06:12.083098: step: 904/466, loss: 0.14066576957702637
2023-01-22 11:06:12.688225: step: 906/466, loss: 0.2034319043159485
2023-01-22 11:06:13.358323: step: 908/466, loss: 0.09343183040618896
2023-01-22 11:06:13.992363: step: 910/466, loss: 0.36260998249053955
2023-01-22 11:06:14.596437: step: 912/466, loss: 0.15928703546524048
2023-01-22 11:06:15.205309: step: 914/466, loss: 1.7589353322982788
2023-01-22 11:06:15.802342: step: 916/466, loss: 0.3109453618526459
2023-01-22 11:06:16.466587: step: 918/466, loss: 0.08942896127700806
2023-01-22 11:06:17.119705: step: 920/466, loss: 0.12767262756824493
2023-01-22 11:06:17.816342: step: 922/466, loss: 0.1355731040239334
2023-01-22 11:06:18.524629: step: 924/466, loss: 0.20094452798366547
2023-01-22 11:06:19.170028: step: 926/466, loss: 0.2024645060300827
2023-01-22 11:06:19.814083: step: 928/466, loss: 0.08893533796072006
2023-01-22 11:06:20.466765: step: 930/466, loss: 0.24943366646766663
2023-01-22 11:06:21.045519: step: 932/466, loss: 0.11482098698616028
==================================================
Loss: 0.289
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3014169839758845, 'r': 0.32772662584095225, 'f1': 0.314021694214876}, 'combined': 0.23138440626359286, 'epoch': 12}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159914027183931, 'r': 0.28034255313373685, 'f1': 0.29710143364149255}, 'combined': 0.18603547714000002, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2870144294316346, 'r': 0.33711941521476624, 'f1': 0.3100557274313818}, 'combined': 0.22846211494943922, 'epoch': 12}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.32264329628451566, 'r': 0.29410625383335814, 'f1': 0.30771456963867877}, 'combined': 0.1906963530155192, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2640739385065886, 'r': 0.34224383301707784, 'f1': 0.2981198347107438}, 'combined': 0.2196672466289691, 'epoch': 12}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.32411618527466063, 'r': 0.29190951826453176, 'f1': 0.30717094745136564}, 'combined': 0.20376686613110395, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23979591836734693, 'r': 0.3357142857142857, 'f1': 0.2797619047619047}, 'combined': 0.18650793650793646, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2727272727272727, 'r': 0.391304347826087, 'f1': 0.32142857142857145}, 'combined': 0.16071428571428573, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25961538461538464, 'r': 0.23275862068965517, 'f1': 0.24545454545454543}, 'combined': 0.1636363636363636, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3152404991413218, 'r': 0.3272040854464953, 'f1': 0.321110899497771}, 'combined': 0.23660803120888388, 'epoch': 11}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.35594899623239706, 'r': 0.30904596965303793, 'f1': 0.3308434148556193}, 'combined': 0.2050297218823556, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:09:09.653249: step: 2/466, loss: 0.1640540212392807
2023-01-22 11:09:10.310863: step: 4/466, loss: 0.3309607207775116
2023-01-22 11:09:11.002307: step: 6/466, loss: 0.2043866664171219
2023-01-22 11:09:11.567385: step: 8/466, loss: 0.08511985093355179
2023-01-22 11:09:12.234739: step: 10/466, loss: 0.03777071461081505
2023-01-22 11:09:12.907501: step: 12/466, loss: 0.4136914014816284
2023-01-22 11:09:13.571625: step: 14/466, loss: 0.03706258535385132
2023-01-22 11:09:14.273067: step: 16/466, loss: 0.2376665621995926
2023-01-22 11:09:14.991723: step: 18/466, loss: 0.5675952434539795
2023-01-22 11:09:15.610979: step: 20/466, loss: 0.20553147792816162
2023-01-22 11:09:16.255149: step: 22/466, loss: 0.25619378685951233
2023-01-22 11:09:16.922085: step: 24/466, loss: 0.07210592180490494
2023-01-22 11:09:17.542881: step: 26/466, loss: 0.11914689838886261
2023-01-22 11:09:18.155950: step: 28/466, loss: 0.5526707768440247
2023-01-22 11:09:18.836799: step: 30/466, loss: 0.22043925523757935
2023-01-22 11:09:19.455369: step: 32/466, loss: 0.07043454796075821
2023-01-22 11:09:20.167907: step: 34/466, loss: 0.17447586357593536
2023-01-22 11:09:20.857184: step: 36/466, loss: 0.14629477262496948
2023-01-22 11:09:21.485080: step: 38/466, loss: 0.04400822892785072
2023-01-22 11:09:22.111079: step: 40/466, loss: 0.27579110860824585
2023-01-22 11:09:22.715948: step: 42/466, loss: 0.11529107391834259
2023-01-22 11:09:23.296484: step: 44/466, loss: 0.060026880353689194
2023-01-22 11:09:24.005533: step: 46/466, loss: 0.08529799431562424
2023-01-22 11:09:24.670465: step: 48/466, loss: 0.13222745060920715
2023-01-22 11:09:25.400498: step: 50/466, loss: 0.0990067720413208
2023-01-22 11:09:26.048540: step: 52/466, loss: 0.13855914771556854
2023-01-22 11:09:26.741098: step: 54/466, loss: 0.13198557496070862
2023-01-22 11:09:27.461097: step: 56/466, loss: 0.11340803653001785
2023-01-22 11:09:28.093060: step: 58/466, loss: 0.5908045768737793
2023-01-22 11:09:28.757088: step: 60/466, loss: 0.14172838628292084
2023-01-22 11:09:29.365315: step: 62/466, loss: 0.14429081976413727
2023-01-22 11:09:30.058746: step: 64/466, loss: 0.36701783537864685
2023-01-22 11:09:30.774121: step: 66/466, loss: 0.197360098361969
2023-01-22 11:09:31.351093: step: 68/466, loss: 0.08826547116041183
2023-01-22 11:09:31.965572: step: 70/466, loss: 0.3188633918762207
2023-01-22 11:09:32.575831: step: 72/466, loss: 0.061413321644067764
2023-01-22 11:09:33.193141: step: 74/466, loss: 0.10852718353271484
2023-01-22 11:09:33.852084: step: 76/466, loss: 0.09878215193748474
2023-01-22 11:09:34.517309: step: 78/466, loss: 0.069364532828331
2023-01-22 11:09:35.156583: step: 80/466, loss: 0.1032869890332222
2023-01-22 11:09:35.740615: step: 82/466, loss: 0.08465754985809326
2023-01-22 11:09:36.326557: step: 84/466, loss: 0.22014209628105164
2023-01-22 11:09:36.997364: step: 86/466, loss: 0.12644293904304504
2023-01-22 11:09:37.581709: step: 88/466, loss: 0.14519761502742767
2023-01-22 11:09:38.207225: step: 90/466, loss: 0.706619143486023
2023-01-22 11:09:38.841107: step: 92/466, loss: 0.20220623910427094
2023-01-22 11:09:39.484208: step: 94/466, loss: 0.08715146034955978
2023-01-22 11:09:40.202700: step: 96/466, loss: 0.25675857067108154
2023-01-22 11:09:40.839021: step: 98/466, loss: 0.17394381761550903
2023-01-22 11:09:41.460630: step: 100/466, loss: 0.18044376373291016
2023-01-22 11:09:42.131108: step: 102/466, loss: 0.10915549844503403
2023-01-22 11:09:42.686113: step: 104/466, loss: 0.06167028471827507
2023-01-22 11:09:43.348673: step: 106/466, loss: 0.06519010663032532
2023-01-22 11:09:43.979553: step: 108/466, loss: 0.12466680258512497
2023-01-22 11:09:44.600475: step: 110/466, loss: 0.13578496873378754
2023-01-22 11:09:45.335267: step: 112/466, loss: 0.5819948315620422
2023-01-22 11:09:45.995465: step: 114/466, loss: 0.1312570869922638
2023-01-22 11:09:46.590750: step: 116/466, loss: 0.1735519915819168
2023-01-22 11:09:47.294702: step: 118/466, loss: 1.240576982498169
2023-01-22 11:09:47.946571: step: 120/466, loss: 0.1172071099281311
2023-01-22 11:09:48.627574: step: 122/466, loss: 0.10495390743017197
2023-01-22 11:09:49.228753: step: 124/466, loss: 0.11870117485523224
2023-01-22 11:09:49.851250: step: 126/466, loss: 0.13622358441352844
2023-01-22 11:09:50.467932: step: 128/466, loss: 0.11489726603031158
2023-01-22 11:09:51.090078: step: 130/466, loss: 0.22453820705413818
2023-01-22 11:09:51.779371: step: 132/466, loss: 0.14519764482975006
2023-01-22 11:09:52.462441: step: 134/466, loss: 0.1792580485343933
2023-01-22 11:09:53.133905: step: 136/466, loss: 1.21463143825531
2023-01-22 11:09:53.744003: step: 138/466, loss: 0.06776592135429382
2023-01-22 11:09:54.373075: step: 140/466, loss: 0.36141058802604675
2023-01-22 11:09:55.040387: step: 142/466, loss: 0.41635945439338684
2023-01-22 11:09:55.645050: step: 144/466, loss: 0.42210379242897034
2023-01-22 11:09:56.237803: step: 146/466, loss: 0.1286270171403885
2023-01-22 11:09:56.874408: step: 148/466, loss: 0.152645543217659
2023-01-22 11:09:57.588844: step: 150/466, loss: 0.129474475979805
2023-01-22 11:09:58.214168: step: 152/466, loss: 0.31282925605773926
2023-01-22 11:09:58.879099: step: 154/466, loss: 0.27455687522888184
2023-01-22 11:09:59.512706: step: 156/466, loss: 0.08866291493177414
2023-01-22 11:10:00.136984: step: 158/466, loss: 0.16239285469055176
2023-01-22 11:10:00.726607: step: 160/466, loss: 0.048395611345767975
2023-01-22 11:10:01.350423: step: 162/466, loss: 0.19695651531219482
2023-01-22 11:10:01.996560: step: 164/466, loss: 0.24603235721588135
2023-01-22 11:10:02.714692: step: 166/466, loss: 0.09938321262598038
2023-01-22 11:10:03.411910: step: 168/466, loss: 0.1550007462501526
2023-01-22 11:10:04.178653: step: 170/466, loss: 0.29955270886421204
2023-01-22 11:10:04.861773: step: 172/466, loss: 0.09472016245126724
2023-01-22 11:10:05.531566: step: 174/466, loss: 0.4685268998146057
2023-01-22 11:10:06.181731: step: 176/466, loss: 0.19812646508216858
2023-01-22 11:10:06.806194: step: 178/466, loss: 0.15283237397670746
2023-01-22 11:10:07.531739: step: 180/466, loss: 0.04112152382731438
2023-01-22 11:10:08.192553: step: 182/466, loss: 0.3206070363521576
2023-01-22 11:10:08.984184: step: 184/466, loss: 0.08839256316423416
2023-01-22 11:10:09.628349: step: 186/466, loss: 0.02866632677614689
2023-01-22 11:10:10.306691: step: 188/466, loss: 0.4633135497570038
2023-01-22 11:10:10.895101: step: 190/466, loss: 0.0650775283575058
2023-01-22 11:10:11.510006: step: 192/466, loss: 0.04255685210227966
2023-01-22 11:10:12.212458: step: 194/466, loss: 0.15480415523052216
2023-01-22 11:10:12.895310: step: 196/466, loss: 0.09784644097089767
2023-01-22 11:10:13.519586: step: 198/466, loss: 0.4938371479511261
2023-01-22 11:10:14.151771: step: 200/466, loss: 0.21996623277664185
2023-01-22 11:10:14.762839: step: 202/466, loss: 0.5384853482246399
2023-01-22 11:10:15.427716: step: 204/466, loss: 0.7514946460723877
2023-01-22 11:10:16.138406: step: 206/466, loss: 0.4952646791934967
2023-01-22 11:10:16.798921: step: 208/466, loss: 0.05475543439388275
2023-01-22 11:10:17.501196: step: 210/466, loss: 0.0820336639881134
2023-01-22 11:10:18.179775: step: 212/466, loss: 0.17772632837295532
2023-01-22 11:10:18.883879: step: 214/466, loss: 0.07154051959514618
2023-01-22 11:10:19.604946: step: 216/466, loss: 0.39577537775039673
2023-01-22 11:10:20.240529: step: 218/466, loss: 0.10776152461767197
2023-01-22 11:10:20.851782: step: 220/466, loss: 0.23313681781291962
2023-01-22 11:10:21.507133: step: 222/466, loss: 0.2835061252117157
2023-01-22 11:10:22.115666: step: 224/466, loss: 0.15277494490146637
2023-01-22 11:10:22.776422: step: 226/466, loss: 0.08761324733495712
2023-01-22 11:10:23.462753: step: 228/466, loss: 0.1521938443183899
2023-01-22 11:10:24.056315: step: 230/466, loss: 1.1920808553695679
2023-01-22 11:10:24.712568: step: 232/466, loss: 0.2710120677947998
2023-01-22 11:10:25.360481: step: 234/466, loss: 0.1194315254688263
2023-01-22 11:10:25.997805: step: 236/466, loss: 0.5656651258468628
2023-01-22 11:10:26.684914: step: 238/466, loss: 0.4444570541381836
2023-01-22 11:10:27.341954: step: 240/466, loss: 0.15339183807373047
2023-01-22 11:10:28.000595: step: 242/466, loss: 0.22125717997550964
2023-01-22 11:10:28.786994: step: 244/466, loss: 0.252727210521698
2023-01-22 11:10:29.422563: step: 246/466, loss: 0.04293074458837509
2023-01-22 11:10:30.079838: step: 248/466, loss: 0.39329782128334045
2023-01-22 11:10:30.739681: step: 250/466, loss: 0.11064071953296661
2023-01-22 11:10:31.357690: step: 252/466, loss: 0.03417646139860153
2023-01-22 11:10:32.010841: step: 254/466, loss: 0.7463078498840332
2023-01-22 11:10:32.640640: step: 256/466, loss: 0.09719155728816986
2023-01-22 11:10:33.251501: step: 258/466, loss: 0.4411686956882477
2023-01-22 11:10:33.913824: step: 260/466, loss: 0.22540371119976044
2023-01-22 11:10:34.544864: step: 262/466, loss: 0.07298116385936737
2023-01-22 11:10:35.232572: step: 264/466, loss: 0.3341713547706604
2023-01-22 11:10:35.912078: step: 266/466, loss: 0.19830569624900818
2023-01-22 11:10:36.577557: step: 268/466, loss: 0.06072846055030823
2023-01-22 11:10:37.305031: step: 270/466, loss: 0.20249119400978088
2023-01-22 11:10:37.901736: step: 272/466, loss: 0.38819921016693115
2023-01-22 11:10:38.612617: step: 274/466, loss: 0.09318225085735321
2023-01-22 11:10:39.258620: step: 276/466, loss: 0.12391915917396545
2023-01-22 11:10:39.928771: step: 278/466, loss: 0.11748528480529785
2023-01-22 11:10:40.646843: step: 280/466, loss: 0.0606972798705101
2023-01-22 11:10:41.293716: step: 282/466, loss: 0.07778766751289368
2023-01-22 11:10:41.989360: step: 284/466, loss: 0.08217433840036392
2023-01-22 11:10:42.771704: step: 286/466, loss: 0.22422903776168823
2023-01-22 11:10:43.389565: step: 288/466, loss: 0.1362757831811905
2023-01-22 11:10:43.990780: step: 290/466, loss: 0.4838602542877197
2023-01-22 11:10:44.600633: step: 292/466, loss: 0.48333677649497986
2023-01-22 11:10:45.204950: step: 294/466, loss: 0.08443082123994827
2023-01-22 11:10:45.873564: step: 296/466, loss: 0.07937867194414139
2023-01-22 11:10:46.543827: step: 298/466, loss: 0.19950351119041443
2023-01-22 11:10:47.206635: step: 300/466, loss: 0.07143021374940872
2023-01-22 11:10:47.846021: step: 302/466, loss: 0.1029263511300087
2023-01-22 11:10:48.490339: step: 304/466, loss: 0.08823765814304352
2023-01-22 11:10:49.128764: step: 306/466, loss: 0.07364961504936218
2023-01-22 11:10:49.757291: step: 308/466, loss: 0.16864685714244843
2023-01-22 11:10:50.412810: step: 310/466, loss: 0.45850521326065063
2023-01-22 11:10:51.113183: step: 312/466, loss: 0.10307233780622482
2023-01-22 11:10:51.759996: step: 314/466, loss: 0.18089449405670166
2023-01-22 11:10:52.362839: step: 316/466, loss: 0.0594630092382431
2023-01-22 11:10:53.025872: step: 318/466, loss: 0.3256591558456421
2023-01-22 11:10:53.707072: step: 320/466, loss: 0.16105329990386963
2023-01-22 11:10:54.416761: step: 322/466, loss: 0.10364712029695511
2023-01-22 11:10:55.047761: step: 324/466, loss: 0.04758321866393089
2023-01-22 11:10:55.700163: step: 326/466, loss: 0.22980478405952454
2023-01-22 11:10:56.347124: step: 328/466, loss: 0.08890247344970703
2023-01-22 11:10:56.956922: step: 330/466, loss: 0.23473994433879852
2023-01-22 11:10:57.585905: step: 332/466, loss: 0.21703583002090454
2023-01-22 11:10:58.217757: step: 334/466, loss: 0.02021816000342369
2023-01-22 11:10:58.889610: step: 336/466, loss: 0.04711470007896423
2023-01-22 11:10:59.537351: step: 338/466, loss: 0.1616368442773819
2023-01-22 11:11:00.227652: step: 340/466, loss: 0.2109578549861908
2023-01-22 11:11:00.878485: step: 342/466, loss: 0.1256185621023178
2023-01-22 11:11:01.496625: step: 344/466, loss: 0.17266616225242615
2023-01-22 11:11:02.094150: step: 346/466, loss: 0.09382988512516022
2023-01-22 11:11:02.776048: step: 348/466, loss: 0.1868274211883545
2023-01-22 11:11:03.447657: step: 350/466, loss: 0.09630129486322403
2023-01-22 11:11:04.123463: step: 352/466, loss: 0.1375264823436737
2023-01-22 11:11:04.798849: step: 354/466, loss: 0.18844608962535858
2023-01-22 11:11:05.425859: step: 356/466, loss: 0.08993268013000488
2023-01-22 11:11:06.055350: step: 358/466, loss: 0.07612888514995575
2023-01-22 11:11:06.684702: step: 360/466, loss: 0.5700476169586182
2023-01-22 11:11:07.330421: step: 362/466, loss: 0.5032669305801392
2023-01-22 11:11:07.928866: step: 364/466, loss: 0.2480846643447876
2023-01-22 11:11:08.586077: step: 366/466, loss: 0.12014836817979813
2023-01-22 11:11:09.222839: step: 368/466, loss: 0.14348430931568146
2023-01-22 11:11:09.937424: step: 370/466, loss: 0.06538870930671692
2023-01-22 11:11:10.620972: step: 372/466, loss: 0.6643422842025757
2023-01-22 11:11:11.337493: step: 374/466, loss: 0.05286271125078201
2023-01-22 11:11:12.018517: step: 376/466, loss: 0.105209119617939
2023-01-22 11:11:12.661000: step: 378/466, loss: 0.26690319180488586
2023-01-22 11:11:13.237270: step: 380/466, loss: 0.15930518507957458
2023-01-22 11:11:13.880077: step: 382/466, loss: 0.15475893020629883
2023-01-22 11:11:14.481270: step: 384/466, loss: 0.2482644021511078
2023-01-22 11:11:15.150578: step: 386/466, loss: 0.07550220936536789
2023-01-22 11:11:15.792373: step: 388/466, loss: 0.18894460797309875
2023-01-22 11:11:16.427145: step: 390/466, loss: 0.091074638068676
2023-01-22 11:11:17.129280: step: 392/466, loss: 0.04081743583083153
2023-01-22 11:11:17.826656: step: 394/466, loss: 0.1577485054731369
2023-01-22 11:11:18.496174: step: 396/466, loss: 0.18509070575237274
2023-01-22 11:11:19.127618: step: 398/466, loss: 0.15012842416763306
2023-01-22 11:11:19.697777: step: 400/466, loss: 0.16608832776546478
2023-01-22 11:11:20.299571: step: 402/466, loss: 0.22238484025001526
2023-01-22 11:11:20.966163: step: 404/466, loss: 0.2626784145832062
2023-01-22 11:11:21.651924: step: 406/466, loss: 0.12193439155817032
2023-01-22 11:11:22.368227: step: 408/466, loss: 0.12389352172613144
2023-01-22 11:11:23.022547: step: 410/466, loss: 0.3696343004703522
2023-01-22 11:11:23.685587: step: 412/466, loss: 0.1802680492401123
2023-01-22 11:11:24.332907: step: 414/466, loss: 0.1357947587966919
2023-01-22 11:11:25.002217: step: 416/466, loss: 0.16391897201538086
2023-01-22 11:11:25.664166: step: 418/466, loss: 0.7947637438774109
2023-01-22 11:11:26.327168: step: 420/466, loss: 0.19358088076114655
2023-01-22 11:11:27.012254: step: 422/466, loss: 0.028136981651186943
2023-01-22 11:11:27.689502: step: 424/466, loss: 0.129495769739151
2023-01-22 11:11:28.282277: step: 426/466, loss: 0.06203593313694
2023-01-22 11:11:28.918921: step: 428/466, loss: 0.27690795063972473
2023-01-22 11:11:29.613000: step: 430/466, loss: 0.08294371515512466
2023-01-22 11:11:30.312130: step: 432/466, loss: 0.0887903943657875
2023-01-22 11:11:30.991433: step: 434/466, loss: 0.40193527936935425
2023-01-22 11:11:31.625451: step: 436/466, loss: 0.18932312726974487
2023-01-22 11:11:32.238787: step: 438/466, loss: 0.20605716109275818
2023-01-22 11:11:32.917418: step: 440/466, loss: 0.19271188974380493
2023-01-22 11:11:33.559101: step: 442/466, loss: 0.22124242782592773
2023-01-22 11:11:34.187667: step: 444/466, loss: 0.08189988136291504
2023-01-22 11:11:34.837023: step: 446/466, loss: 0.3875589072704315
2023-01-22 11:11:35.463807: step: 448/466, loss: 0.7076061964035034
2023-01-22 11:11:36.052299: step: 450/466, loss: 0.08960109204053879
2023-01-22 11:11:36.754702: step: 452/466, loss: 0.4185073971748352
2023-01-22 11:11:37.434173: step: 454/466, loss: 0.11291522532701492
2023-01-22 11:11:38.129892: step: 456/466, loss: 0.4014487564563751
2023-01-22 11:11:38.816760: step: 458/466, loss: 0.14478829503059387
2023-01-22 11:11:39.518297: step: 460/466, loss: 0.2312946915626526
2023-01-22 11:11:40.231969: step: 462/466, loss: 0.11276478320360184
2023-01-22 11:11:40.978774: step: 464/466, loss: 0.1325899064540863
2023-01-22 11:11:41.637238: step: 466/466, loss: 0.08391700685024261
2023-01-22 11:11:42.339164: step: 468/466, loss: 0.2524271607398987
2023-01-22 11:11:43.023180: step: 470/466, loss: 0.14266198873519897
2023-01-22 11:11:43.634088: step: 472/466, loss: 0.19147278368473053
2023-01-22 11:11:44.343703: step: 474/466, loss: 0.16023756563663483
2023-01-22 11:11:45.093598: step: 476/466, loss: 0.34925153851509094
2023-01-22 11:11:45.717653: step: 478/466, loss: 0.1936853975057602
2023-01-22 11:11:46.354312: step: 480/466, loss: 0.06167168170213699
2023-01-22 11:11:46.982740: step: 482/466, loss: 0.06931286305189133
2023-01-22 11:11:47.566058: step: 484/466, loss: 0.24022479355335236
2023-01-22 11:11:48.277778: step: 486/466, loss: 0.12189552187919617
2023-01-22 11:11:48.864561: step: 488/466, loss: 0.277190238237381
2023-01-22 11:11:49.543307: step: 490/466, loss: 0.10748836398124695
2023-01-22 11:11:50.164793: step: 492/466, loss: 0.03430560231208801
2023-01-22 11:11:50.811447: step: 494/466, loss: 0.2065049707889557
2023-01-22 11:11:51.479827: step: 496/466, loss: 0.06921470910310745
2023-01-22 11:11:52.213139: step: 498/466, loss: 0.12291540205478668
2023-01-22 11:11:52.950931: step: 500/466, loss: 0.040339380502700806
2023-01-22 11:11:53.587570: step: 502/466, loss: 0.26626771688461304
2023-01-22 11:11:54.317625: step: 504/466, loss: 0.2785085439682007
2023-01-22 11:11:55.105424: step: 506/466, loss: 0.12924779951572418
2023-01-22 11:11:55.806168: step: 508/466, loss: 0.13007335364818573
2023-01-22 11:11:56.421987: step: 510/466, loss: 0.08024508506059647
2023-01-22 11:11:57.155925: step: 512/466, loss: 0.6170725226402283
2023-01-22 11:11:57.791519: step: 514/466, loss: 0.5800790190696716
2023-01-22 11:11:58.372835: step: 516/466, loss: 0.11268080025911331
2023-01-22 11:11:59.053640: step: 518/466, loss: 0.22556880116462708
2023-01-22 11:11:59.693415: step: 520/466, loss: 0.14080668985843658
2023-01-22 11:12:00.308656: step: 522/466, loss: 0.2947949767112732
2023-01-22 11:12:00.911686: step: 524/466, loss: 0.15909208357334137
2023-01-22 11:12:01.592986: step: 526/466, loss: 0.10946908593177795
2023-01-22 11:12:02.258999: step: 528/466, loss: 0.15271134674549103
2023-01-22 11:12:02.865790: step: 530/466, loss: 0.42776089906692505
2023-01-22 11:12:03.565669: step: 532/466, loss: 0.02391742914915085
2023-01-22 11:12:04.202542: step: 534/466, loss: 0.36857134103775024
2023-01-22 11:12:04.847994: step: 536/466, loss: 0.25262266397476196
2023-01-22 11:12:05.537611: step: 538/466, loss: 0.10111632943153381
2023-01-22 11:12:06.232958: step: 540/466, loss: 0.20518727600574493
2023-01-22 11:12:06.829220: step: 542/466, loss: 0.08978749811649323
2023-01-22 11:12:07.528108: step: 544/466, loss: 0.196076899766922
2023-01-22 11:12:08.150351: step: 546/466, loss: 0.16637547314167023
2023-01-22 11:12:08.850981: step: 548/466, loss: 0.1056482344865799
2023-01-22 11:12:09.482448: step: 550/466, loss: 0.20052708685398102
2023-01-22 11:12:10.103324: step: 552/466, loss: 0.18453501164913177
2023-01-22 11:12:10.715665: step: 554/466, loss: 0.21498796343803406
2023-01-22 11:12:11.390731: step: 556/466, loss: 0.08253206312656403
2023-01-22 11:12:12.010507: step: 558/466, loss: 0.5168558955192566
2023-01-22 11:12:12.617018: step: 560/466, loss: 0.14647255837917328
2023-01-22 11:12:13.243001: step: 562/466, loss: 0.0941804051399231
2023-01-22 11:12:13.908296: step: 564/466, loss: 0.07615640014410019
2023-01-22 11:12:14.552588: step: 566/466, loss: 0.11760447174310684
2023-01-22 11:12:15.210190: step: 568/466, loss: 0.14441268146038055
2023-01-22 11:12:15.818502: step: 570/466, loss: 0.14566536247730255
2023-01-22 11:12:16.499864: step: 572/466, loss: 0.015807218849658966
2023-01-22 11:12:17.114011: step: 574/466, loss: 0.19025352597236633
2023-01-22 11:12:17.732096: step: 576/466, loss: 0.2444162666797638
2023-01-22 11:12:18.284829: step: 578/466, loss: 0.10195492208003998
2023-01-22 11:12:18.931941: step: 580/466, loss: 0.2547774016857147
2023-01-22 11:12:19.582603: step: 582/466, loss: 0.11530125141143799
2023-01-22 11:12:20.245626: step: 584/466, loss: 0.14400054514408112
2023-01-22 11:12:20.946816: step: 586/466, loss: 0.17188303172588348
2023-01-22 11:12:21.592153: step: 588/466, loss: 0.2476584017276764
2023-01-22 11:12:22.309913: step: 590/466, loss: 0.617317259311676
2023-01-22 11:12:23.021127: step: 592/466, loss: 0.15053248405456543
2023-01-22 11:12:23.694138: step: 594/466, loss: 0.1030726283788681
2023-01-22 11:12:24.387237: step: 596/466, loss: 0.16715604066848755
2023-01-22 11:12:25.013027: step: 598/466, loss: 0.039887625724077225
2023-01-22 11:12:25.668694: step: 600/466, loss: 0.08842974901199341
2023-01-22 11:12:26.313582: step: 602/466, loss: 2.2897515296936035
2023-01-22 11:12:26.933446: step: 604/466, loss: 0.10700254887342453
2023-01-22 11:12:27.571738: step: 606/466, loss: 0.09269782900810242
2023-01-22 11:12:28.244073: step: 608/466, loss: 0.15501828491687775
2023-01-22 11:12:28.876006: step: 610/466, loss: 0.2086525410413742
2023-01-22 11:12:29.478030: step: 612/466, loss: 0.20226308703422546
2023-01-22 11:12:30.095182: step: 614/466, loss: 0.20458634197711945
2023-01-22 11:12:30.697262: step: 616/466, loss: 0.570742130279541
2023-01-22 11:12:31.344318: step: 618/466, loss: 0.5643695592880249
2023-01-22 11:12:31.966128: step: 620/466, loss: 0.04040331020951271
2023-01-22 11:12:32.639930: step: 622/466, loss: 0.17890098690986633
2023-01-22 11:12:33.269857: step: 624/466, loss: 0.08190061151981354
2023-01-22 11:12:33.886658: step: 626/466, loss: 1.0058467388153076
2023-01-22 11:12:34.512153: step: 628/466, loss: 0.11896853893995285
2023-01-22 11:12:35.152894: step: 630/466, loss: 0.12671291828155518
2023-01-22 11:12:35.714944: step: 632/466, loss: 0.15029926598072052
2023-01-22 11:12:36.273346: step: 634/466, loss: 0.16588181257247925
2023-01-22 11:12:36.929047: step: 636/466, loss: 0.631856381893158
2023-01-22 11:12:37.589756: step: 638/466, loss: 0.18267585337162018
2023-01-22 11:12:38.242016: step: 640/466, loss: 0.21784941852092743
2023-01-22 11:12:38.874823: step: 642/466, loss: 0.06392834335565567
2023-01-22 11:12:39.501396: step: 644/466, loss: 0.13560988008975983
2023-01-22 11:12:40.253374: step: 646/466, loss: 0.41749024391174316
2023-01-22 11:12:40.877961: step: 648/466, loss: 0.12861019372940063
2023-01-22 11:12:41.489961: step: 650/466, loss: 0.0982961505651474
2023-01-22 11:12:42.202914: step: 652/466, loss: 0.18329547345638275
2023-01-22 11:12:42.896344: step: 654/466, loss: 0.11583784222602844
2023-01-22 11:12:43.642254: step: 656/466, loss: 0.20851461589336395
2023-01-22 11:12:44.310146: step: 658/466, loss: 0.10331014543771744
2023-01-22 11:12:45.044685: step: 660/466, loss: 0.0695447102189064
2023-01-22 11:12:45.727267: step: 662/466, loss: 0.22022593021392822
2023-01-22 11:12:46.398818: step: 664/466, loss: 0.2137749046087265
2023-01-22 11:12:47.097223: step: 666/466, loss: 0.09532894194126129
2023-01-22 11:12:47.757564: step: 668/466, loss: 0.11481019109487534
2023-01-22 11:12:48.387263: step: 670/466, loss: 0.034565288573503494
2023-01-22 11:12:48.982764: step: 672/466, loss: 0.14431558549404144
2023-01-22 11:12:49.661855: step: 674/466, loss: 0.2387639433145523
2023-01-22 11:12:50.290958: step: 676/466, loss: 0.13092225790023804
2023-01-22 11:12:50.958942: step: 678/466, loss: 0.3727954030036926
2023-01-22 11:12:51.617674: step: 680/466, loss: 0.22211085259914398
2023-01-22 11:12:52.299301: step: 682/466, loss: 0.12298870831727982
2023-01-22 11:12:52.906032: step: 684/466, loss: 0.15994293987751007
2023-01-22 11:12:53.514168: step: 686/466, loss: 0.32660427689552307
2023-01-22 11:12:54.194973: step: 688/466, loss: 0.12016677856445312
2023-01-22 11:12:54.894613: step: 690/466, loss: 0.12251818180084229
2023-01-22 11:12:55.567617: step: 692/466, loss: 0.28071627020835876
2023-01-22 11:12:56.216186: step: 694/466, loss: 0.1375160813331604
2023-01-22 11:12:56.802855: step: 696/466, loss: 0.11511513590812683
2023-01-22 11:12:57.401216: step: 698/466, loss: 0.9334464073181152
2023-01-22 11:12:58.034952: step: 700/466, loss: 0.11350943893194199
2023-01-22 11:12:58.674908: step: 702/466, loss: 0.08908645063638687
2023-01-22 11:12:59.495488: step: 704/466, loss: 0.07174257189035416
2023-01-22 11:13:00.105071: step: 706/466, loss: 0.07029732316732407
2023-01-22 11:13:00.828594: step: 708/466, loss: 0.14587418735027313
2023-01-22 11:13:01.522652: step: 710/466, loss: 0.17657369375228882
2023-01-22 11:13:02.195344: step: 712/466, loss: 0.12829914689064026
2023-01-22 11:13:02.809541: step: 714/466, loss: 0.3506952226161957
2023-01-22 11:13:03.457371: step: 716/466, loss: 0.09446898102760315
2023-01-22 11:13:04.098435: step: 718/466, loss: 0.17156566679477692
2023-01-22 11:13:04.743714: step: 720/466, loss: 0.1899915337562561
2023-01-22 11:13:05.395481: step: 722/466, loss: 0.2282724231481552
2023-01-22 11:13:05.989326: step: 724/466, loss: 0.07543264329433441
2023-01-22 11:13:06.624602: step: 726/466, loss: 0.24867254495620728
2023-01-22 11:13:07.278119: step: 728/466, loss: 0.4091861844062805
2023-01-22 11:13:07.982865: step: 730/466, loss: 0.08514761179685593
2023-01-22 11:13:08.625925: step: 732/466, loss: 0.2007623314857483
2023-01-22 11:13:09.250647: step: 734/466, loss: 0.045061640441417694
2023-01-22 11:13:09.888954: step: 736/466, loss: 0.08761599659919739
2023-01-22 11:13:10.644063: step: 738/466, loss: 0.21438206732273102
2023-01-22 11:13:11.333103: step: 740/466, loss: 0.14008253812789917
2023-01-22 11:13:12.152010: step: 742/466, loss: 0.14892008900642395
2023-01-22 11:13:12.816878: step: 744/466, loss: 0.1852099746465683
2023-01-22 11:13:13.514085: step: 746/466, loss: 0.12888222932815552
2023-01-22 11:13:14.160490: step: 748/466, loss: 0.20296093821525574
2023-01-22 11:13:14.811273: step: 750/466, loss: 0.04399174451828003
2023-01-22 11:13:15.452673: step: 752/466, loss: 0.10388326644897461
2023-01-22 11:13:16.131174: step: 754/466, loss: 0.09159988164901733
2023-01-22 11:13:16.771701: step: 756/466, loss: 0.05983365327119827
2023-01-22 11:13:17.446523: step: 758/466, loss: 0.42964819073677063
2023-01-22 11:13:18.093287: step: 760/466, loss: 0.10957743227481842
2023-01-22 11:13:18.711034: step: 762/466, loss: 0.06509745121002197
2023-01-22 11:13:19.384760: step: 764/466, loss: 0.06311726570129395
2023-01-22 11:13:20.183276: step: 766/466, loss: 0.3187008798122406
2023-01-22 11:13:20.838931: step: 768/466, loss: 0.07424849271774292
2023-01-22 11:13:21.423439: step: 770/466, loss: 0.06358221173286438
2023-01-22 11:13:22.097915: step: 772/466, loss: 0.22837388515472412
2023-01-22 11:13:22.753045: step: 774/466, loss: 0.06742311269044876
2023-01-22 11:13:23.414937: step: 776/466, loss: 0.5217674970626831
2023-01-22 11:13:24.140535: step: 778/466, loss: 0.4974120855331421
2023-01-22 11:13:24.826888: step: 780/466, loss: 0.1293429136276245
2023-01-22 11:13:25.482675: step: 782/466, loss: 0.13213907182216644
2023-01-22 11:13:26.162398: step: 784/466, loss: 0.06015023961663246
2023-01-22 11:13:26.831484: step: 786/466, loss: 0.14418943226337433
2023-01-22 11:13:27.461594: step: 788/466, loss: 0.20209401845932007
2023-01-22 11:13:28.056366: step: 790/466, loss: 0.08692203462123871
2023-01-22 11:13:28.801792: step: 792/466, loss: 0.11871273815631866
2023-01-22 11:13:29.423060: step: 794/466, loss: 0.13457347452640533
2023-01-22 11:13:30.045174: step: 796/466, loss: 0.5627838373184204
2023-01-22 11:13:30.691749: step: 798/466, loss: 0.06300508230924606
2023-01-22 11:13:31.361614: step: 800/466, loss: 0.12110118567943573
2023-01-22 11:13:32.088466: step: 802/466, loss: 1.1750342845916748
2023-01-22 11:13:32.737918: step: 804/466, loss: 0.08435027301311493
2023-01-22 11:13:33.447869: step: 806/466, loss: 0.17642229795455933
2023-01-22 11:13:34.044900: step: 808/466, loss: 0.08418819308280945
2023-01-22 11:13:34.716641: step: 810/466, loss: 0.06966585665941238
2023-01-22 11:13:35.374234: step: 812/466, loss: 0.25622549653053284
2023-01-22 11:13:36.018666: step: 814/466, loss: 0.18494339287281036
2023-01-22 11:13:36.700927: step: 816/466, loss: 0.22128863632678986
2023-01-22 11:13:37.394817: step: 818/466, loss: 0.19796879589557648
2023-01-22 11:13:38.026338: step: 820/466, loss: 0.17516906559467316
2023-01-22 11:13:38.637491: step: 822/466, loss: 0.028141312301158905
2023-01-22 11:13:39.296981: step: 824/466, loss: 0.25652971863746643
2023-01-22 11:13:39.909275: step: 826/466, loss: 0.1690840721130371
2023-01-22 11:13:40.590357: step: 828/466, loss: 0.04922156035900116
2023-01-22 11:13:41.214683: step: 830/466, loss: 0.1817835122346878
2023-01-22 11:13:41.823709: step: 832/466, loss: 0.1686851680278778
2023-01-22 11:13:42.471651: step: 834/466, loss: 0.16623874008655548
2023-01-22 11:13:43.171672: step: 836/466, loss: 0.18103083968162537
2023-01-22 11:13:43.792233: step: 838/466, loss: 0.15125532448291779
2023-01-22 11:13:44.466611: step: 840/466, loss: 0.1299140602350235
2023-01-22 11:13:45.128554: step: 842/466, loss: 0.08949729055166245
2023-01-22 11:13:45.685256: step: 844/466, loss: 0.09528897702693939
2023-01-22 11:13:46.304306: step: 846/466, loss: 0.26403525471687317
2023-01-22 11:13:46.961008: step: 848/466, loss: 0.11076653003692627
2023-01-22 11:13:47.612209: step: 850/466, loss: 0.11650221049785614
2023-01-22 11:13:48.310047: step: 852/466, loss: 0.02086993306875229
2023-01-22 11:13:48.884911: step: 854/466, loss: 0.03652055189013481
2023-01-22 11:13:49.522721: step: 856/466, loss: 0.22360306978225708
2023-01-22 11:13:50.156674: step: 858/466, loss: 0.05483764782547951
2023-01-22 11:13:50.749858: step: 860/466, loss: 0.11446105688810349
2023-01-22 11:13:51.405591: step: 862/466, loss: 0.11421798169612885
2023-01-22 11:13:52.076660: step: 864/466, loss: 0.2829704284667969
2023-01-22 11:13:52.750403: step: 866/466, loss: 0.13539977371692657
2023-01-22 11:13:53.385498: step: 868/466, loss: 0.1167941689491272
2023-01-22 11:13:54.089455: step: 870/466, loss: 0.1312185376882553
2023-01-22 11:13:54.765825: step: 872/466, loss: 0.7470857501029968
2023-01-22 11:13:55.410371: step: 874/466, loss: 0.4336667060852051
2023-01-22 11:13:56.062638: step: 876/466, loss: 1.348360300064087
2023-01-22 11:13:56.798283: step: 878/466, loss: 0.13151061534881592
2023-01-22 11:13:57.493287: step: 880/466, loss: 0.6406599283218384
2023-01-22 11:13:58.180000: step: 882/466, loss: 0.2077856957912445
2023-01-22 11:13:58.813109: step: 884/466, loss: 0.14853604137897491
2023-01-22 11:13:59.434379: step: 886/466, loss: 0.2359350323677063
2023-01-22 11:14:00.019218: step: 888/466, loss: 0.0797957330942154
2023-01-22 11:14:00.698817: step: 890/466, loss: 0.15271800756454468
2023-01-22 11:14:01.403337: step: 892/466, loss: 0.0849347859621048
2023-01-22 11:14:02.041682: step: 894/466, loss: 0.29333633184432983
2023-01-22 11:14:02.727031: step: 896/466, loss: 1.1319775581359863
2023-01-22 11:14:03.369068: step: 898/466, loss: 0.08828303962945938
2023-01-22 11:14:04.027464: step: 900/466, loss: 0.13764886558055878
2023-01-22 11:14:04.690177: step: 902/466, loss: 0.3116423189640045
2023-01-22 11:14:05.445392: step: 904/466, loss: 0.1575583517551422
2023-01-22 11:14:06.141648: step: 906/466, loss: 0.15604592859745026
2023-01-22 11:14:06.861260: step: 908/466, loss: 0.19787052273750305
2023-01-22 11:14:07.570217: step: 910/466, loss: 0.14253224432468414
2023-01-22 11:14:08.309934: step: 912/466, loss: 0.18719810247421265
2023-01-22 11:14:08.963005: step: 914/466, loss: 1.0880357027053833
2023-01-22 11:14:09.637140: step: 916/466, loss: 0.22350358963012695
2023-01-22 11:14:10.231367: step: 918/466, loss: 0.14658449590206146
2023-01-22 11:14:10.839782: step: 920/466, loss: 0.14227831363677979
2023-01-22 11:14:11.419702: step: 922/466, loss: 0.18480584025382996
2023-01-22 11:14:12.117010: step: 924/466, loss: 0.25192248821258545
2023-01-22 11:14:12.708452: step: 926/466, loss: 0.25395455956459045
2023-01-22 11:14:13.393775: step: 928/466, loss: 0.4100404977798462
2023-01-22 11:14:14.087973: step: 930/466, loss: 0.04821727052330971
2023-01-22 11:14:14.759254: step: 932/466, loss: 0.20392407476902008
==================================================
Loss: 0.213
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3064593377315402, 'r': 0.3273939414475468, 'f1': 0.3165809305373526}, 'combined': 0.2332701593433124, 'epoch': 13}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.30333580107561425, 'r': 0.3055259512638859, 'f1': 0.3044269370507064}, 'combined': 0.1906224746018442, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2959081095000396, 'r': 0.3374587738321135, 'f1': 0.315320520938872}, 'combined': 0.23234143648127406, 'epoch': 13}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3089549549660353, 'r': 0.317877841752058, 'f1': 0.3133528902680429}, 'combined': 0.19419052354639277, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2729497851772288, 'r': 0.34442430197885604, 'f1': 0.3045496764141898}, 'combined': 0.2244050247262451, 'epoch': 13}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3135813290006257, 'r': 0.3141478716004461, 'f1': 0.31386434464051793}, 'combined': 0.20820704050410596, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.27717391304347827, 'r': 0.36428571428571427, 'f1': 0.3148148148148148}, 'combined': 0.20987654320987653, 'epoch': 13}
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': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25806451612903225, 'r': 0.27586206896551724, 'f1': 0.26666666666666666}, 'combined': 0.17777777777777776, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3152404991413218, 'r': 0.3272040854464953, 'f1': 0.321110899497771}, 'combined': 0.23660803120888388, 'epoch': 11}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.35594899623239706, 'r': 0.30904596965303793, 'f1': 0.3308434148556193}, 'combined': 0.2050297218823556, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:17:02.428425: step: 2/466, loss: 0.21664494276046753
2023-01-22 11:17:03.139002: step: 4/466, loss: 0.2588813006877899
2023-01-22 11:17:03.753584: step: 6/466, loss: 0.23247914016246796
2023-01-22 11:17:04.393824: step: 8/466, loss: 0.10080494731664658
2023-01-22 11:17:05.021808: step: 10/466, loss: 0.07782622426748276
2023-01-22 11:17:05.642886: step: 12/466, loss: 0.27462607622146606
2023-01-22 11:17:06.191831: step: 14/466, loss: 0.2357061505317688
2023-01-22 11:17:06.812036: step: 16/466, loss: 0.06383047252893448
2023-01-22 11:17:07.494610: step: 18/466, loss: 0.09361665695905685
2023-01-22 11:17:08.114879: step: 20/466, loss: 0.7580082416534424
2023-01-22 11:17:08.774051: step: 22/466, loss: 0.06528540700674057
2023-01-22 11:17:09.361966: step: 24/466, loss: 0.05765198543667793
2023-01-22 11:17:10.034967: step: 26/466, loss: 0.0284025426954031
2023-01-22 11:17:10.676053: step: 28/466, loss: 0.12420958280563354
2023-01-22 11:17:11.328596: step: 30/466, loss: 0.07885674387216568
2023-01-22 11:17:12.019424: step: 32/466, loss: 0.04992187023162842
2023-01-22 11:17:12.687127: step: 34/466, loss: 0.0710175409913063
2023-01-22 11:17:13.257028: step: 36/466, loss: 0.0854632556438446
2023-01-22 11:17:13.951640: step: 38/466, loss: 0.24539466202259064
2023-01-22 11:17:14.549206: step: 40/466, loss: 0.08943222463130951
2023-01-22 11:17:15.314714: step: 42/466, loss: 0.417314738035202
2023-01-22 11:17:15.904965: step: 44/466, loss: 0.0895300880074501
2023-01-22 11:17:16.518267: step: 46/466, loss: 0.09953930974006653
2023-01-22 11:17:17.135978: step: 48/466, loss: 0.008541363291442394
2023-01-22 11:17:17.849109: step: 50/466, loss: 0.1880522072315216
2023-01-22 11:17:18.490042: step: 52/466, loss: 0.6083518862724304
2023-01-22 11:17:19.210064: step: 54/466, loss: 0.22280308604240417
2023-01-22 11:17:19.862850: step: 56/466, loss: 0.1025019958615303
2023-01-22 11:17:20.610641: step: 58/466, loss: 0.5052645802497864
2023-01-22 11:17:21.328515: step: 60/466, loss: 0.13890738785266876
2023-01-22 11:17:21.947693: step: 62/466, loss: 0.024933665990829468
2023-01-22 11:17:22.647440: step: 64/466, loss: 0.0999549999833107
2023-01-22 11:17:23.354098: step: 66/466, loss: 0.09658706188201904
2023-01-22 11:17:23.946388: step: 68/466, loss: 0.39057597517967224
2023-01-22 11:17:24.624383: step: 70/466, loss: 0.07361017912626266
2023-01-22 11:17:25.256130: step: 72/466, loss: 0.16718822717666626
2023-01-22 11:17:25.909370: step: 74/466, loss: 0.03773102909326553
2023-01-22 11:17:26.567068: step: 76/466, loss: 0.31345033645629883
2023-01-22 11:17:27.246346: step: 78/466, loss: 0.07871197164058685
2023-01-22 11:17:27.858684: step: 80/466, loss: 0.10839194804430008
2023-01-22 11:17:28.539478: step: 82/466, loss: 0.05946098640561104
2023-01-22 11:17:29.233944: step: 84/466, loss: 0.10564349591732025
2023-01-22 11:17:29.924169: step: 86/466, loss: 0.06663645058870316
2023-01-22 11:17:30.572101: step: 88/466, loss: 0.23888219892978668
2023-01-22 11:17:31.244453: step: 90/466, loss: 0.1846161186695099
2023-01-22 11:17:31.941953: step: 92/466, loss: 0.10354091972112656
2023-01-22 11:17:32.581759: step: 94/466, loss: 0.11738651990890503
2023-01-22 11:17:33.222848: step: 96/466, loss: 0.39901578426361084
2023-01-22 11:17:33.880841: step: 98/466, loss: 0.16923528909683228
2023-01-22 11:17:34.470166: step: 100/466, loss: 0.03673376888036728
2023-01-22 11:17:35.105581: step: 102/466, loss: 0.05416484177112579
2023-01-22 11:17:35.778714: step: 104/466, loss: 0.5004127025604248
2023-01-22 11:17:36.425540: step: 106/466, loss: 0.07831823825836182
2023-01-22 11:17:37.097379: step: 108/466, loss: 0.21493087708950043
2023-01-22 11:17:37.784834: step: 110/466, loss: 0.11279312521219254
2023-01-22 11:17:38.428551: step: 112/466, loss: 0.1883641928434372
2023-01-22 11:17:39.021677: step: 114/466, loss: 0.13482354581356049
2023-01-22 11:17:39.668705: step: 116/466, loss: 0.41808295249938965
2023-01-22 11:17:40.199458: step: 118/466, loss: 0.17674140632152557
2023-01-22 11:17:40.835053: step: 120/466, loss: 0.7946280837059021
2023-01-22 11:17:41.466761: step: 122/466, loss: 0.06088021770119667
2023-01-22 11:17:42.195357: step: 124/466, loss: 0.0929827019572258
2023-01-22 11:17:42.877721: step: 126/466, loss: 0.09999638050794601
2023-01-22 11:17:43.570045: step: 128/466, loss: 0.3582874536514282
2023-01-22 11:17:44.219910: step: 130/466, loss: 0.2149185836315155
2023-01-22 11:17:44.889471: step: 132/466, loss: 0.046425435692071915
2023-01-22 11:17:45.552547: step: 134/466, loss: 0.14573967456817627
2023-01-22 11:17:46.155033: step: 136/466, loss: 0.06734217703342438
2023-01-22 11:17:46.822436: step: 138/466, loss: 0.8096088171005249
2023-01-22 11:17:47.515225: step: 140/466, loss: 1.5389599800109863
2023-01-22 11:17:48.171664: step: 142/466, loss: 0.17086271941661835
2023-01-22 11:17:48.765869: step: 144/466, loss: 1.1946203708648682
2023-01-22 11:17:49.482889: step: 146/466, loss: 0.1435568928718567
2023-01-22 11:17:50.098081: step: 148/466, loss: 0.3198951780796051
2023-01-22 11:17:50.662918: step: 150/466, loss: 0.056569430977106094
2023-01-22 11:17:51.208466: step: 152/466, loss: 0.06694243848323822
2023-01-22 11:17:51.857397: step: 154/466, loss: 0.08120336383581161
2023-01-22 11:17:52.517007: step: 156/466, loss: 0.04717717319726944
2023-01-22 11:17:53.133001: step: 158/466, loss: 0.10398121923208237
2023-01-22 11:17:53.795806: step: 160/466, loss: 0.07995104044675827
2023-01-22 11:17:54.414703: step: 162/466, loss: 0.09553412348031998
2023-01-22 11:17:55.151734: step: 164/466, loss: 0.04434293508529663
2023-01-22 11:17:55.772507: step: 166/466, loss: 0.36308401823043823
2023-01-22 11:17:56.368883: step: 168/466, loss: 0.007103645242750645
2023-01-22 11:17:57.011616: step: 170/466, loss: 0.19649642705917358
2023-01-22 11:17:57.692648: step: 172/466, loss: 0.17209577560424805
2023-01-22 11:17:58.418768: step: 174/466, loss: 0.09232991188764572
2023-01-22 11:17:59.086169: step: 176/466, loss: 1.4124647378921509
2023-01-22 11:17:59.670992: step: 178/466, loss: 0.20708917081356049
2023-01-22 11:18:00.328800: step: 180/466, loss: 0.05523412674665451
2023-01-22 11:18:00.977682: step: 182/466, loss: 0.0384976901113987
2023-01-22 11:18:01.571689: step: 184/466, loss: 0.19864994287490845
2023-01-22 11:18:02.249630: step: 186/466, loss: 0.09787686169147491
2023-01-22 11:18:02.868785: step: 188/466, loss: 0.2546052038669586
2023-01-22 11:18:03.571575: step: 190/466, loss: 0.3419496417045593
2023-01-22 11:18:04.241306: step: 192/466, loss: 0.07933840900659561
2023-01-22 11:18:04.969904: step: 194/466, loss: 0.2112976312637329
2023-01-22 11:18:05.615093: step: 196/466, loss: 0.054273150861263275
2023-01-22 11:18:06.297718: step: 198/466, loss: 0.07770832628011703
2023-01-22 11:18:06.938914: step: 200/466, loss: 0.1153278797864914
2023-01-22 11:18:07.611419: step: 202/466, loss: 0.1545044481754303
2023-01-22 11:18:08.256873: step: 204/466, loss: 0.06076398864388466
2023-01-22 11:18:08.883447: step: 206/466, loss: 0.10364454984664917
2023-01-22 11:18:09.581869: step: 208/466, loss: 0.11774459481239319
2023-01-22 11:18:10.252669: step: 210/466, loss: 0.32848066091537476
2023-01-22 11:18:10.912111: step: 212/466, loss: 0.23459117114543915
2023-01-22 11:18:11.549633: step: 214/466, loss: 0.042070191353559494
2023-01-22 11:18:12.180469: step: 216/466, loss: 0.08094526082277298
2023-01-22 11:18:12.877465: step: 218/466, loss: 0.1356755793094635
2023-01-22 11:18:13.572425: step: 220/466, loss: 0.6302579641342163
2023-01-22 11:18:14.191292: step: 222/466, loss: 0.6548448204994202
2023-01-22 11:18:14.871053: step: 224/466, loss: 0.10057955980300903
2023-01-22 11:18:15.554445: step: 226/466, loss: 0.4888569712638855
2023-01-22 11:18:16.155045: step: 228/466, loss: 0.3553338050842285
2023-01-22 11:18:16.830660: step: 230/466, loss: 0.10962367802858353
2023-01-22 11:18:17.582004: step: 232/466, loss: 0.15608611702919006
2023-01-22 11:18:18.268848: step: 234/466, loss: 0.18678003549575806
2023-01-22 11:18:18.902376: step: 236/466, loss: 0.21261128783226013
2023-01-22 11:18:19.573271: step: 238/466, loss: 0.07746458053588867
2023-01-22 11:18:20.218970: step: 240/466, loss: 0.4363856911659241
2023-01-22 11:18:20.880704: step: 242/466, loss: 0.1325339823961258
2023-01-22 11:18:21.523428: step: 244/466, loss: 0.15851140022277832
2023-01-22 11:18:22.234178: step: 246/466, loss: 0.14201043546199799
2023-01-22 11:18:22.898981: step: 248/466, loss: 0.3462273180484772
2023-01-22 11:18:23.611443: step: 250/466, loss: 0.09096142649650574
2023-01-22 11:18:24.284525: step: 252/466, loss: 0.8484412431716919
2023-01-22 11:18:24.923708: step: 254/466, loss: 0.15960969030857086
2023-01-22 11:18:25.614833: step: 256/466, loss: 0.42807015776634216
2023-01-22 11:18:26.289653: step: 258/466, loss: 0.31719139218330383
2023-01-22 11:18:26.937876: step: 260/466, loss: 0.08133837580680847
2023-01-22 11:18:27.593807: step: 262/466, loss: 0.09300018101930618
2023-01-22 11:18:28.260799: step: 264/466, loss: 0.18810880184173584
2023-01-22 11:18:28.935542: step: 266/466, loss: 0.18063776195049286
2023-01-22 11:18:29.573828: step: 268/466, loss: 0.1170445904135704
2023-01-22 11:18:30.230051: step: 270/466, loss: 0.046691134572029114
2023-01-22 11:18:30.906251: step: 272/466, loss: 0.15165668725967407
2023-01-22 11:18:31.623485: step: 274/466, loss: 0.2840859591960907
2023-01-22 11:18:32.220253: step: 276/466, loss: 0.08033007383346558
2023-01-22 11:18:32.901026: step: 278/466, loss: 0.30552706122398376
2023-01-22 11:18:33.576418: step: 280/466, loss: 0.03319627046585083
2023-01-22 11:18:34.144787: step: 282/466, loss: 0.060096003115177155
2023-01-22 11:18:34.833329: step: 284/466, loss: 0.0664438009262085
2023-01-22 11:18:35.476390: step: 286/466, loss: 0.18188567459583282
2023-01-22 11:18:36.162465: step: 288/466, loss: 0.29840531945228577
2023-01-22 11:18:36.812601: step: 290/466, loss: 0.08392433077096939
2023-01-22 11:18:37.468912: step: 292/466, loss: 0.1635517030954361
2023-01-22 11:18:38.097740: step: 294/466, loss: 0.10469960421323776
2023-01-22 11:18:38.781001: step: 296/466, loss: 1.0305179357528687
2023-01-22 11:18:39.480738: step: 298/466, loss: 0.12768679857254028
2023-01-22 11:18:40.180657: step: 300/466, loss: 0.17497457563877106
2023-01-22 11:18:40.873665: step: 302/466, loss: 0.14417117834091187
2023-01-22 11:18:41.551227: step: 304/466, loss: 0.1257448047399521
2023-01-22 11:18:42.267286: step: 306/466, loss: 0.32153579592704773
2023-01-22 11:18:42.918068: step: 308/466, loss: 0.18655270338058472
2023-01-22 11:18:43.541766: step: 310/466, loss: 0.2795713245868683
2023-01-22 11:18:44.190751: step: 312/466, loss: 0.14642831683158875
2023-01-22 11:18:44.873925: step: 314/466, loss: 0.023899976164102554
2023-01-22 11:18:45.505188: step: 316/466, loss: 0.191590815782547
2023-01-22 11:18:46.113159: step: 318/466, loss: 0.23445306718349457
2023-01-22 11:18:46.766872: step: 320/466, loss: 0.0523383729159832
2023-01-22 11:18:47.411491: step: 322/466, loss: 0.12506917119026184
2023-01-22 11:18:48.064803: step: 324/466, loss: 0.4583035707473755
2023-01-22 11:18:48.658461: step: 326/466, loss: 0.08694583177566528
2023-01-22 11:18:49.286654: step: 328/466, loss: 0.5271000862121582
2023-01-22 11:18:49.899181: step: 330/466, loss: 0.14745131134986877
2023-01-22 11:18:50.544176: step: 332/466, loss: 0.07641014456748962
2023-01-22 11:18:51.159082: step: 334/466, loss: 0.08735503256320953
2023-01-22 11:18:51.836022: step: 336/466, loss: 0.06401679664850235
2023-01-22 11:18:52.515252: step: 338/466, loss: 0.07610401511192322
2023-01-22 11:18:53.103108: step: 340/466, loss: 0.32962048053741455
2023-01-22 11:18:53.836046: step: 342/466, loss: 0.13128696382045746
2023-01-22 11:18:54.450890: step: 344/466, loss: 0.021335458382964134
2023-01-22 11:18:55.113909: step: 346/466, loss: 0.14687997102737427
2023-01-22 11:18:55.773585: step: 348/466, loss: 0.19566234946250916
2023-01-22 11:18:56.509798: step: 350/466, loss: 0.5493302345275879
2023-01-22 11:18:57.184720: step: 352/466, loss: 0.08697886765003204
2023-01-22 11:18:57.857625: step: 354/466, loss: 0.22227326035499573
2023-01-22 11:18:58.479195: step: 356/466, loss: 0.04099361598491669
2023-01-22 11:18:59.118934: step: 358/466, loss: 0.10837606340646744
2023-01-22 11:18:59.778894: step: 360/466, loss: 0.09568150341510773
2023-01-22 11:19:00.414888: step: 362/466, loss: 0.14171753823757172
2023-01-22 11:19:01.028315: step: 364/466, loss: 0.08027523756027222
2023-01-22 11:19:01.627878: step: 366/466, loss: 0.15333522856235504
2023-01-22 11:19:02.269334: step: 368/466, loss: 0.052050329744815826
2023-01-22 11:19:02.949204: step: 370/466, loss: 0.08375398069620132
2023-01-22 11:19:03.607139: step: 372/466, loss: 0.03649580478668213
2023-01-22 11:19:04.250968: step: 374/466, loss: 0.16528141498565674
2023-01-22 11:19:04.915904: step: 376/466, loss: 0.05533326044678688
2023-01-22 11:19:05.589926: step: 378/466, loss: 0.05703647434711456
2023-01-22 11:19:06.311457: step: 380/466, loss: 0.12570974230766296
2023-01-22 11:19:06.918175: step: 382/466, loss: 0.8404884934425354
2023-01-22 11:19:07.535595: step: 384/466, loss: 0.11699473857879639
2023-01-22 11:19:08.176351: step: 386/466, loss: 0.030063355341553688
2023-01-22 11:19:08.808484: step: 388/466, loss: 0.1502676010131836
2023-01-22 11:19:09.521513: step: 390/466, loss: 0.1679421216249466
2023-01-22 11:19:10.150880: step: 392/466, loss: 0.09521698206663132
2023-01-22 11:19:10.811529: step: 394/466, loss: 0.10098012536764145
2023-01-22 11:19:11.500870: step: 396/466, loss: 0.1282902956008911
2023-01-22 11:19:12.188229: step: 398/466, loss: 0.09492602944374084
2023-01-22 11:19:12.921018: step: 400/466, loss: 0.12190713733434677
2023-01-22 11:19:13.558243: step: 402/466, loss: 0.15735898911952972
2023-01-22 11:19:14.194755: step: 404/466, loss: 0.08567700535058975
2023-01-22 11:19:14.843957: step: 406/466, loss: 0.09509891271591187
2023-01-22 11:19:15.469395: step: 408/466, loss: 0.009957714006304741
2023-01-22 11:19:16.123193: step: 410/466, loss: 0.09173969179391861
2023-01-22 11:19:16.743935: step: 412/466, loss: 0.10093410313129425
2023-01-22 11:19:17.416863: step: 414/466, loss: 1.867976188659668
2023-01-22 11:19:18.074362: step: 416/466, loss: 0.1114923283457756
2023-01-22 11:19:18.778462: step: 418/466, loss: 0.6304705142974854
2023-01-22 11:19:19.368646: step: 420/466, loss: 0.04427172616124153
2023-01-22 11:19:20.094165: step: 422/466, loss: 0.06850725412368774
2023-01-22 11:19:20.760087: step: 424/466, loss: 0.20498473942279816
2023-01-22 11:19:21.445443: step: 426/466, loss: 0.10735539346933365
2023-01-22 11:19:22.038667: step: 428/466, loss: 0.07468348741531372
2023-01-22 11:19:22.676796: step: 430/466, loss: 0.20282858610153198
2023-01-22 11:19:23.374247: step: 432/466, loss: 0.1597706526517868
2023-01-22 11:19:24.044670: step: 434/466, loss: 0.34720179438591003
2023-01-22 11:19:24.657810: step: 436/466, loss: 0.2628512382507324
2023-01-22 11:19:25.281880: step: 438/466, loss: 0.06142502278089523
2023-01-22 11:19:25.912566: step: 440/466, loss: 0.10227291285991669
2023-01-22 11:19:26.569618: step: 442/466, loss: 0.0427645742893219
2023-01-22 11:19:27.200737: step: 444/466, loss: 0.22859515249729156
2023-01-22 11:19:27.860205: step: 446/466, loss: 0.095253124833107
2023-01-22 11:19:28.503353: step: 448/466, loss: 0.12162463366985321
2023-01-22 11:19:29.137117: step: 450/466, loss: 0.07784131914377213
2023-01-22 11:19:29.853908: step: 452/466, loss: 0.507390022277832
2023-01-22 11:19:30.538893: step: 454/466, loss: 0.10997535288333893
2023-01-22 11:19:31.197652: step: 456/466, loss: 1.8567255735397339
2023-01-22 11:19:31.974228: step: 458/466, loss: 0.2736664414405823
2023-01-22 11:19:32.602526: step: 460/466, loss: 0.08910427242517471
2023-01-22 11:19:33.289598: step: 462/466, loss: 0.37200602889060974
2023-01-22 11:19:33.937055: step: 464/466, loss: 0.368376761674881
2023-01-22 11:19:34.612391: step: 466/466, loss: 0.06825045496225357
2023-01-22 11:19:35.225962: step: 468/466, loss: 0.08737295120954514
2023-01-22 11:19:35.915300: step: 470/466, loss: 0.7475695013999939
2023-01-22 11:19:36.647641: step: 472/466, loss: 0.17576569318771362
2023-01-22 11:19:37.312617: step: 474/466, loss: 0.09032467007637024
2023-01-22 11:19:37.981839: step: 476/466, loss: 0.23489834368228912
2023-01-22 11:19:38.692137: step: 478/466, loss: 0.12705419957637787
2023-01-22 11:19:39.329156: step: 480/466, loss: 0.26893118023872375
2023-01-22 11:19:40.007332: step: 482/466, loss: 0.13266262412071228
2023-01-22 11:19:40.654582: step: 484/466, loss: 0.11018592119216919
2023-01-22 11:19:41.292119: step: 486/466, loss: 0.13621945679187775
2023-01-22 11:19:41.981001: step: 488/466, loss: 0.14668114483356476
2023-01-22 11:19:42.614140: step: 490/466, loss: 0.1817501336336136
2023-01-22 11:19:43.218101: step: 492/466, loss: 0.06757530570030212
2023-01-22 11:19:43.962469: step: 494/466, loss: 0.13275770843029022
2023-01-22 11:19:44.579446: step: 496/466, loss: 0.1039777398109436
2023-01-22 11:19:45.249857: step: 498/466, loss: 0.07613973319530487
2023-01-22 11:19:45.999254: step: 500/466, loss: 0.06720180064439774
2023-01-22 11:19:46.624622: step: 502/466, loss: 0.14942774176597595
2023-01-22 11:19:47.195877: step: 504/466, loss: 0.15461429953575134
2023-01-22 11:19:47.844075: step: 506/466, loss: 0.14893974363803864
2023-01-22 11:19:48.519142: step: 508/466, loss: 0.07165000587701797
2023-01-22 11:19:49.169554: step: 510/466, loss: 0.23073656857013702
2023-01-22 11:19:49.798114: step: 512/466, loss: 0.14023169875144958
2023-01-22 11:19:50.457334: step: 514/466, loss: 0.5554453730583191
2023-01-22 11:19:51.081979: step: 516/466, loss: 0.39692938327789307
2023-01-22 11:19:51.781862: step: 518/466, loss: 0.20564937591552734
2023-01-22 11:19:52.384020: step: 520/466, loss: 0.09200834482908249
2023-01-22 11:19:52.981664: step: 522/466, loss: 0.1810818910598755
2023-01-22 11:19:53.644489: step: 524/466, loss: 0.08566950261592865
2023-01-22 11:19:54.330588: step: 526/466, loss: 0.07795694470405579
2023-01-22 11:19:55.032638: step: 528/466, loss: 0.04060513526201248
2023-01-22 11:19:55.735050: step: 530/466, loss: 0.1456119865179062
2023-01-22 11:19:56.373151: step: 532/466, loss: 0.46540188789367676
2023-01-22 11:19:57.095009: step: 534/466, loss: 0.04797811806201935
2023-01-22 11:19:57.798333: step: 536/466, loss: 0.1219116598367691
2023-01-22 11:19:58.460749: step: 538/466, loss: 0.13186098635196686
2023-01-22 11:19:59.133450: step: 540/466, loss: 0.1312079131603241
2023-01-22 11:19:59.798606: step: 542/466, loss: 0.13683204352855682
2023-01-22 11:20:00.451810: step: 544/466, loss: 0.20569588243961334
2023-01-22 11:20:01.078278: step: 546/466, loss: 3.6133134365081787
2023-01-22 11:20:01.737363: step: 548/466, loss: 0.1964557021856308
2023-01-22 11:20:02.455120: step: 550/466, loss: 0.032030846923589706
2023-01-22 11:20:03.164045: step: 552/466, loss: 0.23671674728393555
2023-01-22 11:20:03.781949: step: 554/466, loss: 0.06673205643892288
2023-01-22 11:20:04.442868: step: 556/466, loss: 0.205203115940094
2023-01-22 11:20:05.089382: step: 558/466, loss: 0.08683093637228012
2023-01-22 11:20:05.818680: step: 560/466, loss: 0.13626570999622345
2023-01-22 11:20:06.462407: step: 562/466, loss: 0.1898723691701889
2023-01-22 11:20:07.176280: step: 564/466, loss: 0.021120157092809677
2023-01-22 11:20:07.794365: step: 566/466, loss: 0.15750077366828918
2023-01-22 11:20:08.419610: step: 568/466, loss: 0.06532016396522522
2023-01-22 11:20:09.057383: step: 570/466, loss: 0.033128079026937485
2023-01-22 11:20:09.638248: step: 572/466, loss: 0.22112499177455902
2023-01-22 11:20:10.248438: step: 574/466, loss: 0.050089944154024124
2023-01-22 11:20:10.889703: step: 576/466, loss: 0.12589536607265472
2023-01-22 11:20:11.492314: step: 578/466, loss: 0.06084910407662392
2023-01-22 11:20:12.142980: step: 580/466, loss: 0.09911134093999863
2023-01-22 11:20:12.773206: step: 582/466, loss: 0.07547442615032196
2023-01-22 11:20:13.419929: step: 584/466, loss: 0.13044041395187378
2023-01-22 11:20:14.004531: step: 586/466, loss: 0.12678459286689758
2023-01-22 11:20:14.598636: step: 588/466, loss: 0.11398551613092422
2023-01-22 11:20:15.204914: step: 590/466, loss: 0.06138450652360916
2023-01-22 11:20:15.770627: step: 592/466, loss: 0.07820218056440353
2023-01-22 11:20:16.403102: step: 594/466, loss: 0.14266575872898102
2023-01-22 11:20:17.068063: step: 596/466, loss: 0.038015060126781464
2023-01-22 11:20:17.735596: step: 598/466, loss: 0.25807908177375793
2023-01-22 11:20:18.442407: step: 600/466, loss: 0.12017034739255905
2023-01-22 11:20:19.150397: step: 602/466, loss: 0.6884686350822449
2023-01-22 11:20:19.794810: step: 604/466, loss: 0.18772900104522705
2023-01-22 11:20:20.409970: step: 606/466, loss: 0.13137471675872803
2023-01-22 11:20:21.048582: step: 608/466, loss: 0.15554356575012207
2023-01-22 11:20:21.678440: step: 610/466, loss: 0.06444638967514038
2023-01-22 11:20:22.296401: step: 612/466, loss: 0.3176107108592987
2023-01-22 11:20:22.917844: step: 614/466, loss: 0.38138628005981445
2023-01-22 11:20:23.594016: step: 616/466, loss: 0.06246405467391014
2023-01-22 11:20:24.318332: step: 618/466, loss: 0.13891153037548065
2023-01-22 11:20:24.976119: step: 620/466, loss: 0.0745665654540062
2023-01-22 11:20:25.616846: step: 622/466, loss: 0.07133463025093079
2023-01-22 11:20:26.220295: step: 624/466, loss: 1.2177377939224243
2023-01-22 11:20:26.840836: step: 626/466, loss: 0.08016962558031082
2023-01-22 11:20:27.511305: step: 628/466, loss: 0.1497739851474762
2023-01-22 11:20:28.151614: step: 630/466, loss: 0.22510574758052826
2023-01-22 11:20:28.772557: step: 632/466, loss: 0.15465585887432098
2023-01-22 11:20:29.359645: step: 634/466, loss: 0.11404050141572952
2023-01-22 11:20:29.979057: step: 636/466, loss: 0.13050960004329681
2023-01-22 11:20:30.618527: step: 638/466, loss: 0.21021117269992828
2023-01-22 11:20:31.223480: step: 640/466, loss: 0.30213674902915955
2023-01-22 11:20:31.917296: step: 642/466, loss: 0.1877560168504715
2023-01-22 11:20:32.524386: step: 644/466, loss: 0.4449322521686554
2023-01-22 11:20:33.217052: step: 646/466, loss: 0.03945323824882507
2023-01-22 11:20:33.809662: step: 648/466, loss: 0.1734963208436966
2023-01-22 11:20:34.594758: step: 650/466, loss: 0.0660005435347557
2023-01-22 11:20:35.243532: step: 652/466, loss: 0.08190672099590302
2023-01-22 11:20:35.916443: step: 654/466, loss: 0.21880212426185608
2023-01-22 11:20:36.602191: step: 656/466, loss: 0.047313012182712555
2023-01-22 11:20:37.231175: step: 658/466, loss: 0.06312886625528336
2023-01-22 11:20:37.948723: step: 660/466, loss: 0.1220080703496933
2023-01-22 11:20:38.668059: step: 662/466, loss: 0.47863081097602844
2023-01-22 11:20:39.381261: step: 664/466, loss: 0.1615520715713501
2023-01-22 11:20:40.049908: step: 666/466, loss: 0.1046697348356247
2023-01-22 11:20:40.730473: step: 668/466, loss: 0.2509707808494568
2023-01-22 11:20:41.365751: step: 670/466, loss: 0.1696101576089859
2023-01-22 11:20:42.006896: step: 672/466, loss: 0.05695287883281708
2023-01-22 11:20:42.662535: step: 674/466, loss: 0.08349854499101639
2023-01-22 11:20:43.347843: step: 676/466, loss: 0.1294446587562561
2023-01-22 11:20:44.084079: step: 678/466, loss: 0.1571851223707199
2023-01-22 11:20:44.724302: step: 680/466, loss: 0.19614636898040771
2023-01-22 11:20:45.373369: step: 682/466, loss: 0.1105930507183075
2023-01-22 11:20:46.034575: step: 684/466, loss: 0.523503303527832
2023-01-22 11:20:46.723917: step: 686/466, loss: 0.05425763875246048
2023-01-22 11:20:47.369052: step: 688/466, loss: 0.07267965376377106
2023-01-22 11:20:48.035225: step: 690/466, loss: 0.40452754497528076
2023-01-22 11:20:48.678675: step: 692/466, loss: 0.11994507163763046
2023-01-22 11:20:49.246458: step: 694/466, loss: 0.3443394899368286
2023-01-22 11:20:49.907997: step: 696/466, loss: 0.2467920035123825
2023-01-22 11:20:50.502163: step: 698/466, loss: 0.13529010117053986
2023-01-22 11:20:51.125072: step: 700/466, loss: 0.10970811545848846
2023-01-22 11:20:51.788213: step: 702/466, loss: 0.5327137112617493
2023-01-22 11:20:52.458980: step: 704/466, loss: 0.5181942582130432
2023-01-22 11:20:53.143690: step: 706/466, loss: 0.2738834619522095
2023-01-22 11:20:53.761889: step: 708/466, loss: 0.08478600531816483
2023-01-22 11:20:54.382126: step: 710/466, loss: 0.05863865092396736
2023-01-22 11:20:55.033145: step: 712/466, loss: 0.05520498380064964
2023-01-22 11:20:55.706335: step: 714/466, loss: 0.19641073048114777
2023-01-22 11:20:56.336521: step: 716/466, loss: 0.8427484035491943
2023-01-22 11:20:57.009089: step: 718/466, loss: 0.09054213762283325
2023-01-22 11:20:57.688169: step: 720/466, loss: 0.11003617942333221
2023-01-22 11:20:58.387031: step: 722/466, loss: 0.09100736677646637
2023-01-22 11:20:59.023061: step: 724/466, loss: 0.10934733599424362
2023-01-22 11:20:59.744067: step: 726/466, loss: 0.22367994487285614
2023-01-22 11:21:00.394829: step: 728/466, loss: 0.08802761882543564
2023-01-22 11:21:01.090077: step: 730/466, loss: 0.7977679967880249
2023-01-22 11:21:01.719918: step: 732/466, loss: 0.13046298921108246
2023-01-22 11:21:02.357636: step: 734/466, loss: 0.10032875835895538
2023-01-22 11:21:03.000723: step: 736/466, loss: 0.06097870692610741
2023-01-22 11:21:03.638566: step: 738/466, loss: 0.08550991863012314
2023-01-22 11:21:04.307512: step: 740/466, loss: 0.10648110508918762
2023-01-22 11:21:04.956096: step: 742/466, loss: 0.046441011130809784
2023-01-22 11:21:05.631543: step: 744/466, loss: 0.20584163069725037
2023-01-22 11:21:06.309444: step: 746/466, loss: 0.42919909954071045
2023-01-22 11:21:06.947917: step: 748/466, loss: 0.09509290009737015
2023-01-22 11:21:07.512069: step: 750/466, loss: 0.0858200341463089
2023-01-22 11:21:08.183698: step: 752/466, loss: 0.29318660497665405
2023-01-22 11:21:08.866316: step: 754/466, loss: 0.18614895641803741
2023-01-22 11:21:09.529530: step: 756/466, loss: 1.4461302757263184
2023-01-22 11:21:10.165982: step: 758/466, loss: 0.11748125404119492
2023-01-22 11:21:10.831824: step: 760/466, loss: 0.19098018109798431
2023-01-22 11:21:11.483586: step: 762/466, loss: 0.15145912766456604
2023-01-22 11:21:12.151098: step: 764/466, loss: 0.05735521391034126
2023-01-22 11:21:12.788326: step: 766/466, loss: 0.186171293258667
2023-01-22 11:21:13.455862: step: 768/466, loss: 0.19050681591033936
2023-01-22 11:21:14.109215: step: 770/466, loss: 0.19891580939292908
2023-01-22 11:21:14.731286: step: 772/466, loss: 8.71715259552002
2023-01-22 11:21:15.438826: step: 774/466, loss: 0.09013688564300537
2023-01-22 11:21:16.058112: step: 776/466, loss: 0.44694456458091736
2023-01-22 11:21:16.779704: step: 778/466, loss: 0.1340249925851822
2023-01-22 11:21:17.429275: step: 780/466, loss: 0.5292209386825562
2023-01-22 11:21:18.095986: step: 782/466, loss: 0.32261040806770325
2023-01-22 11:21:18.787274: step: 784/466, loss: 0.09790646284818649
2023-01-22 11:21:19.398520: step: 786/466, loss: 0.038367241621017456
2023-01-22 11:21:20.085291: step: 788/466, loss: 0.4195810854434967
2023-01-22 11:21:20.734707: step: 790/466, loss: 0.2766675651073456
2023-01-22 11:21:21.434542: step: 792/466, loss: 0.21886131167411804
2023-01-22 11:21:22.040440: step: 794/466, loss: 0.08811365813016891
2023-01-22 11:21:22.681184: step: 796/466, loss: 0.05479082837700844
2023-01-22 11:21:23.325152: step: 798/466, loss: 0.10200653225183487
2023-01-22 11:21:23.970022: step: 800/466, loss: 0.22190265357494354
2023-01-22 11:21:24.619959: step: 802/466, loss: 0.15918050706386566
2023-01-22 11:21:25.247020: step: 804/466, loss: 0.3613383173942566
2023-01-22 11:21:25.907545: step: 806/466, loss: 0.1719532608985901
2023-01-22 11:21:26.587026: step: 808/466, loss: 0.09152864664793015
2023-01-22 11:21:27.219574: step: 810/466, loss: 0.38782280683517456
2023-01-22 11:21:27.862934: step: 812/466, loss: 0.13327616453170776
2023-01-22 11:21:28.469893: step: 814/466, loss: 0.10806596279144287
2023-01-22 11:21:29.126275: step: 816/466, loss: 0.01866796426475048
2023-01-22 11:21:29.848160: step: 818/466, loss: 0.007938460446894169
2023-01-22 11:21:30.519660: step: 820/466, loss: 0.08328758180141449
2023-01-22 11:21:31.118159: step: 822/466, loss: 0.09915492683649063
2023-01-22 11:21:31.788153: step: 824/466, loss: 0.19329403340816498
2023-01-22 11:21:32.431553: step: 826/466, loss: 0.21803811192512512
2023-01-22 11:21:33.100691: step: 828/466, loss: 0.08334982395172119
2023-01-22 11:21:33.737915: step: 830/466, loss: 1.3822726011276245
2023-01-22 11:21:34.366209: step: 832/466, loss: 0.08953722566366196
2023-01-22 11:21:35.002593: step: 834/466, loss: 0.048605214804410934
2023-01-22 11:21:35.709802: step: 836/466, loss: 0.4795377254486084
2023-01-22 11:21:36.339202: step: 838/466, loss: 0.07054489105939865
2023-01-22 11:21:36.999335: step: 840/466, loss: 0.20257791876792908
2023-01-22 11:21:37.581604: step: 842/466, loss: 0.1157168447971344
2023-01-22 11:21:38.221035: step: 844/466, loss: 0.0845470279455185
2023-01-22 11:21:38.928224: step: 846/466, loss: 0.10139591246843338
2023-01-22 11:21:39.653588: step: 848/466, loss: 0.2176181674003601
2023-01-22 11:21:40.314748: step: 850/466, loss: 0.067507803440094
2023-01-22 11:21:40.965919: step: 852/466, loss: 0.12499594688415527
2023-01-22 11:21:41.661724: step: 854/466, loss: 0.060795966535806656
2023-01-22 11:21:42.304627: step: 856/466, loss: 0.1424483060836792
2023-01-22 11:21:42.959716: step: 858/466, loss: 0.21677431464195251
2023-01-22 11:21:43.681277: step: 860/466, loss: 1.9143980741500854
2023-01-22 11:21:44.283244: step: 862/466, loss: 0.16681039333343506
2023-01-22 11:21:44.993964: step: 864/466, loss: 0.1073463186621666
2023-01-22 11:21:45.592053: step: 866/466, loss: 0.04946222901344299
2023-01-22 11:21:46.274331: step: 868/466, loss: 0.4168989956378937
2023-01-22 11:21:46.967976: step: 870/466, loss: 0.21804341673851013
2023-01-22 11:21:47.691936: step: 872/466, loss: 0.27743685245513916
2023-01-22 11:21:48.313539: step: 874/466, loss: 0.10394605249166489
2023-01-22 11:21:49.011459: step: 876/466, loss: 0.0699191465973854
2023-01-22 11:21:49.618110: step: 878/466, loss: 0.16605454683303833
2023-01-22 11:21:50.238579: step: 880/466, loss: 0.3739076554775238
2023-01-22 11:21:50.870318: step: 882/466, loss: 0.31669163703918457
2023-01-22 11:21:51.509437: step: 884/466, loss: 0.12097109854221344
2023-01-22 11:21:52.128339: step: 886/466, loss: 0.5599779486656189
2023-01-22 11:21:52.831612: step: 888/466, loss: 0.1497298777103424
2023-01-22 11:21:53.519946: step: 890/466, loss: 0.07432295382022858
2023-01-22 11:21:54.268323: step: 892/466, loss: 0.10274899750947952
2023-01-22 11:21:54.977326: step: 894/466, loss: 0.384609192609787
2023-01-22 11:21:55.671956: step: 896/466, loss: 0.4249957203865051
2023-01-22 11:21:56.363029: step: 898/466, loss: 0.04452158883213997
2023-01-22 11:21:57.082992: step: 900/466, loss: 0.015567224472761154
2023-01-22 11:21:57.821212: step: 902/466, loss: 0.19822470843791962
2023-01-22 11:21:58.516512: step: 904/466, loss: 0.4278334379196167
2023-01-22 11:21:59.194936: step: 906/466, loss: 0.11612143367528915
2023-01-22 11:21:59.848226: step: 908/466, loss: 0.2971527874469757
2023-01-22 11:22:00.493368: step: 910/466, loss: 0.16825099289417267
2023-01-22 11:22:01.095088: step: 912/466, loss: 0.05000316724181175
2023-01-22 11:22:01.851757: step: 914/466, loss: 0.18294182419776917
2023-01-22 11:22:02.552768: step: 916/466, loss: 0.3873891234397888
2023-01-22 11:22:03.166521: step: 918/466, loss: 0.11834461241960526
2023-01-22 11:22:03.846267: step: 920/466, loss: 0.18775823712348938
2023-01-22 11:22:04.579022: step: 922/466, loss: 0.19691264629364014
2023-01-22 11:22:05.182287: step: 924/466, loss: 0.1103270873427391
2023-01-22 11:22:05.995547: step: 926/466, loss: 0.1784142553806305
2023-01-22 11:22:06.648785: step: 928/466, loss: 0.3308243155479431
2023-01-22 11:22:07.317280: step: 930/466, loss: 0.38338178396224976
2023-01-22 11:22:07.966814: step: 932/466, loss: 0.12993201613426208
==================================================
Loss: 0.232
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3209746975147155, 'r': 0.33863744178023114, 'f1': 0.3295695878452111}, 'combined': 0.2428407489385766, 'epoch': 14}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3135694424674537, 'r': 0.3096037945952366, 'f1': 0.31157400056084267}, 'combined': 0.1950977386689389, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2725284090909091, 'r': 0.34130692599620494, 'f1': 0.3030644481887111}, 'combined': 0.2233106460337871, 'epoch': 14}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.31790209865384017, 'r': 0.31272828511336176, 'f1': 0.315293968400527}, 'combined': 0.20915540478054762, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2865853658536585, 'r': 0.3357142857142857, 'f1': 0.30921052631578944}, 'combined': 0.20614035087719296, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.26666666666666666, 'r': 0.27586206896551724, 'f1': 0.2711864406779661}, 'combined': 0.1807909604519774, 'epoch': 14}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:25:06.714677: step: 2/466, loss: 0.07601815462112427
2023-01-22 11:25:07.388090: step: 4/466, loss: 0.060319118201732635
2023-01-22 11:25:08.034265: step: 6/466, loss: 0.14708635210990906
2023-01-22 11:25:08.624679: step: 8/466, loss: 0.0160928163677454
2023-01-22 11:25:09.326362: step: 10/466, loss: 0.11274747550487518
2023-01-22 11:25:10.011262: step: 12/466, loss: 0.03984593600034714
2023-01-22 11:25:10.656323: step: 14/466, loss: 2.9654884338378906
2023-01-22 11:25:11.261362: step: 16/466, loss: 0.0605609156191349
2023-01-22 11:25:11.908281: step: 18/466, loss: 0.12641334533691406
2023-01-22 11:25:12.536538: step: 20/466, loss: 0.06787180155515671
2023-01-22 11:25:13.158849: step: 22/466, loss: 0.1013396605849266
2023-01-22 11:25:13.850443: step: 24/466, loss: 0.06734860688447952
2023-01-22 11:25:14.500649: step: 26/466, loss: 0.043701812624931335
2023-01-22 11:25:15.162817: step: 28/466, loss: 0.0785311907529831
2023-01-22 11:25:15.805017: step: 30/466, loss: 0.12360072135925293
2023-01-22 11:25:16.476723: step: 32/466, loss: 0.21179643273353577
2023-01-22 11:25:17.117816: step: 34/466, loss: 0.46735018491744995
2023-01-22 11:25:17.738211: step: 36/466, loss: 0.0781048834323883
2023-01-22 11:25:18.338501: step: 38/466, loss: 0.3329731523990631
2023-01-22 11:25:19.010091: step: 40/466, loss: 0.23325176537036896
2023-01-22 11:25:19.663055: step: 42/466, loss: 0.055112116038799286
2023-01-22 11:25:20.302036: step: 44/466, loss: 0.09325244277715683
2023-01-22 11:25:20.941697: step: 46/466, loss: 6.907464981079102
2023-01-22 11:25:21.660570: step: 48/466, loss: 0.1494046449661255
2023-01-22 11:25:22.281872: step: 50/466, loss: 0.1370428204536438
2023-01-22 11:25:22.949879: step: 52/466, loss: 0.09927735477685928
2023-01-22 11:25:23.718655: step: 54/466, loss: 0.5274226069450378
2023-01-22 11:25:24.385718: step: 56/466, loss: 0.11505471915006638
2023-01-22 11:25:25.032753: step: 58/466, loss: 0.13182595372200012
2023-01-22 11:25:25.704060: step: 60/466, loss: 0.18545888364315033
2023-01-22 11:25:26.383460: step: 62/466, loss: 0.36592501401901245
2023-01-22 11:25:27.026816: step: 64/466, loss: 0.122297003865242
2023-01-22 11:25:27.756997: step: 66/466, loss: 0.06750189512968063
2023-01-22 11:25:28.486542: step: 68/466, loss: 0.2126324325799942
2023-01-22 11:25:29.177746: step: 70/466, loss: 0.03938804194331169
2023-01-22 11:25:29.816424: step: 72/466, loss: 0.12230225652456284
2023-01-22 11:25:30.532239: step: 74/466, loss: 0.0553334578871727
2023-01-22 11:25:31.219324: step: 76/466, loss: 0.5174123048782349
2023-01-22 11:25:31.865879: step: 78/466, loss: 0.10611777007579803
2023-01-22 11:25:32.708511: step: 80/466, loss: 0.03924800083041191
2023-01-22 11:25:33.387745: step: 82/466, loss: 0.10162966698408127
2023-01-22 11:25:34.013525: step: 84/466, loss: 0.060497235506772995
2023-01-22 11:25:34.658628: step: 86/466, loss: 0.20899879932403564
2023-01-22 11:25:35.324418: step: 88/466, loss: 0.08463367074728012
2023-01-22 11:25:35.953184: step: 90/466, loss: 0.05687631666660309
2023-01-22 11:25:36.593264: step: 92/466, loss: 0.06662612408399582
2023-01-22 11:25:37.325594: step: 94/466, loss: 0.02623327076435089
2023-01-22 11:25:38.023696: step: 96/466, loss: 0.1103297770023346
2023-01-22 11:25:38.826832: step: 98/466, loss: 0.17696203291416168
2023-01-22 11:25:39.505840: step: 100/466, loss: 0.1444133222103119
2023-01-22 11:25:40.215255: step: 102/466, loss: 0.28258079290390015
2023-01-22 11:25:40.914213: step: 104/466, loss: 0.16617068648338318
2023-01-22 11:25:41.529355: step: 106/466, loss: 0.03628968447446823
2023-01-22 11:25:42.203014: step: 108/466, loss: 0.030992701649665833
2023-01-22 11:25:42.884837: step: 110/466, loss: 0.15708261728286743
2023-01-22 11:25:43.527374: step: 112/466, loss: 0.4777582585811615
2023-01-22 11:25:44.148711: step: 114/466, loss: 0.05228717252612114
2023-01-22 11:25:45.001921: step: 116/466, loss: 0.09536279737949371
2023-01-22 11:25:45.671347: step: 118/466, loss: 0.13929015398025513
2023-01-22 11:25:46.289131: step: 120/466, loss: 0.08980412036180496
2023-01-22 11:25:47.014077: step: 122/466, loss: 0.09776115417480469
2023-01-22 11:25:47.645886: step: 124/466, loss: 0.27029654383659363
2023-01-22 11:25:48.330349: step: 126/466, loss: 0.10421734303236008
2023-01-22 11:25:49.004219: step: 128/466, loss: 0.06566141545772552
2023-01-22 11:25:49.702465: step: 130/466, loss: 0.1898757666349411
2023-01-22 11:25:50.331859: step: 132/466, loss: 0.052807580679655075
2023-01-22 11:25:50.934126: step: 134/466, loss: 0.07725521177053452
2023-01-22 11:25:51.530959: step: 136/466, loss: 0.04953015223145485
2023-01-22 11:25:52.235089: step: 138/466, loss: 0.12636981904506683
2023-01-22 11:25:52.897201: step: 140/466, loss: 0.3295181095600128
2023-01-22 11:25:53.595759: step: 142/466, loss: 0.07382170855998993
2023-01-22 11:25:54.250361: step: 144/466, loss: 0.11951906234025955
2023-01-22 11:25:54.871661: step: 146/466, loss: 0.06142144650220871
2023-01-22 11:25:55.492602: step: 148/466, loss: 0.02745065465569496
2023-01-22 11:25:56.130328: step: 150/466, loss: 0.4685656428337097
2023-01-22 11:25:56.773351: step: 152/466, loss: 0.06786028295755386
2023-01-22 11:25:57.472921: step: 154/466, loss: 0.18896110355854034
2023-01-22 11:25:58.174805: step: 156/466, loss: 0.06052001938223839
2023-01-22 11:25:58.814759: step: 158/466, loss: 0.08299747109413147
2023-01-22 11:25:59.451553: step: 160/466, loss: 0.029955944046378136
2023-01-22 11:26:00.074743: step: 162/466, loss: 0.11253871768712997
2023-01-22 11:26:00.758156: step: 164/466, loss: 0.0854821652173996
2023-01-22 11:26:01.390008: step: 166/466, loss: 0.04195922985672951
2023-01-22 11:26:02.039226: step: 168/466, loss: 0.1804516315460205
2023-01-22 11:26:02.679300: step: 170/466, loss: 0.04488290473818779
2023-01-22 11:26:03.282106: step: 172/466, loss: 0.11197320371866226
2023-01-22 11:26:03.953076: step: 174/466, loss: 0.16332344710826874
2023-01-22 11:26:04.570848: step: 176/466, loss: 0.061043087393045425
2023-01-22 11:26:05.161620: step: 178/466, loss: 0.09745758026838303
2023-01-22 11:26:05.797711: step: 180/466, loss: 0.08789185434579849
2023-01-22 11:26:06.466166: step: 182/466, loss: 0.03371937945485115
2023-01-22 11:26:07.115792: step: 184/466, loss: 0.03100101836025715
2023-01-22 11:26:07.744770: step: 186/466, loss: 0.06895512342453003
2023-01-22 11:26:08.353556: step: 188/466, loss: 0.0844266265630722
2023-01-22 11:26:08.957868: step: 190/466, loss: 0.10798672586679459
2023-01-22 11:26:09.661111: step: 192/466, loss: 0.10067951679229736
2023-01-22 11:26:10.226325: step: 194/466, loss: 0.1494479924440384
2023-01-22 11:26:10.871321: step: 196/466, loss: 0.0792386457324028
2023-01-22 11:26:11.512385: step: 198/466, loss: 0.04849759489297867
2023-01-22 11:26:12.133582: step: 200/466, loss: 0.42589089274406433
2023-01-22 11:26:12.771101: step: 202/466, loss: 0.16432368755340576
2023-01-22 11:26:13.437929: step: 204/466, loss: 0.3137759566307068
2023-01-22 11:26:14.052246: step: 206/466, loss: 0.8784408569335938
2023-01-22 11:26:14.726144: step: 208/466, loss: 0.07093644142150879
2023-01-22 11:26:15.462495: step: 210/466, loss: 0.20242880284786224
2023-01-22 11:26:16.136481: step: 212/466, loss: 0.27905434370040894
2023-01-22 11:26:16.772586: step: 214/466, loss: 0.0937686562538147
2023-01-22 11:26:17.448007: step: 216/466, loss: 0.2798430323600769
2023-01-22 11:26:18.061924: step: 218/466, loss: 0.18162015080451965
2023-01-22 11:26:18.696881: step: 220/466, loss: 0.07361326366662979
2023-01-22 11:26:19.390311: step: 222/466, loss: 0.09918847680091858
2023-01-22 11:26:20.025392: step: 224/466, loss: 0.07619430869817734
2023-01-22 11:26:20.687587: step: 226/466, loss: 0.07150990515947342
2023-01-22 11:26:21.253332: step: 228/466, loss: 0.04885377362370491
2023-01-22 11:26:21.914346: step: 230/466, loss: 0.053341105580329895
2023-01-22 11:26:22.556050: step: 232/466, loss: 0.08202479779720306
2023-01-22 11:26:23.290489: step: 234/466, loss: 0.11043872684240341
2023-01-22 11:26:23.935798: step: 236/466, loss: 0.36070725321769714
2023-01-22 11:26:24.590544: step: 238/466, loss: 0.20646990835666656
2023-01-22 11:26:25.253565: step: 240/466, loss: 0.08996447920799255
2023-01-22 11:26:25.974965: step: 242/466, loss: 0.17766429483890533
2023-01-22 11:26:26.701265: step: 244/466, loss: 0.05220003053545952
2023-01-22 11:26:27.361026: step: 246/466, loss: 0.15690936148166656
2023-01-22 11:26:28.004939: step: 248/466, loss: 0.11198737472295761
2023-01-22 11:26:28.669754: step: 250/466, loss: 0.03883950784802437
2023-01-22 11:26:29.326747: step: 252/466, loss: 0.05150290206074715
2023-01-22 11:26:29.944463: step: 254/466, loss: 0.056819669902324677
2023-01-22 11:26:30.552210: step: 256/466, loss: 0.11226635426282883
2023-01-22 11:26:31.203027: step: 258/466, loss: 0.18033404648303986
2023-01-22 11:26:31.854661: step: 260/466, loss: 0.2898689806461334
2023-01-22 11:26:32.520210: step: 262/466, loss: 0.03009466640651226
2023-01-22 11:26:33.140530: step: 264/466, loss: 0.1417255401611328
2023-01-22 11:26:33.734351: step: 266/466, loss: 0.22924448549747467
2023-01-22 11:26:34.340392: step: 268/466, loss: 0.09219784289598465
2023-01-22 11:26:34.935404: step: 270/466, loss: 0.2014540135860443
2023-01-22 11:26:35.655283: step: 272/466, loss: 0.08747085928916931
2023-01-22 11:26:36.266554: step: 274/466, loss: 0.03199044615030289
2023-01-22 11:26:36.909813: step: 276/466, loss: 0.1765107810497284
2023-01-22 11:26:37.546881: step: 278/466, loss: 0.04221271350979805
2023-01-22 11:26:38.197979: step: 280/466, loss: 0.04762676730751991
2023-01-22 11:26:38.814756: step: 282/466, loss: 0.18033361434936523
2023-01-22 11:26:39.392546: step: 284/466, loss: 0.2735659182071686
2023-01-22 11:26:40.031277: step: 286/466, loss: 0.041960328817367554
2023-01-22 11:26:40.755461: step: 288/466, loss: 0.7181612849235535
2023-01-22 11:26:41.389874: step: 290/466, loss: 0.07804315537214279
2023-01-22 11:26:42.094061: step: 292/466, loss: 0.022585544735193253
2023-01-22 11:26:42.739922: step: 294/466, loss: 0.04021203890442848
2023-01-22 11:26:43.395219: step: 296/466, loss: 0.13588309288024902
2023-01-22 11:26:44.089637: step: 298/466, loss: 0.08786024898290634
2023-01-22 11:26:44.673198: step: 300/466, loss: 0.10801000148057938
2023-01-22 11:26:45.294361: step: 302/466, loss: 0.558252215385437
2023-01-22 11:26:45.936058: step: 304/466, loss: 0.05378791317343712
2023-01-22 11:26:46.565470: step: 306/466, loss: 0.08215916901826859
2023-01-22 11:26:47.181484: step: 308/466, loss: 0.10823218524456024
2023-01-22 11:26:47.879431: step: 310/466, loss: 0.1119224950671196
2023-01-22 11:26:48.538911: step: 312/466, loss: 0.0791698768734932
2023-01-22 11:26:49.146030: step: 314/466, loss: 0.09614011645317078
2023-01-22 11:26:49.862585: step: 316/466, loss: 0.18332503736019135
2023-01-22 11:26:50.574358: step: 318/466, loss: 0.9485373497009277
2023-01-22 11:26:51.181644: step: 320/466, loss: 0.08354584872722626
2023-01-22 11:26:51.794719: step: 322/466, loss: 0.1311836689710617
2023-01-22 11:26:52.390111: step: 324/466, loss: 0.061109501868486404
2023-01-22 11:26:53.010796: step: 326/466, loss: 0.09852179139852524
2023-01-22 11:26:53.649970: step: 328/466, loss: 0.05198030546307564
2023-01-22 11:26:54.317195: step: 330/466, loss: 0.34303319454193115
2023-01-22 11:26:54.899891: step: 332/466, loss: 0.03909998759627342
2023-01-22 11:26:55.511132: step: 334/466, loss: 0.1568313091993332
2023-01-22 11:26:56.164901: step: 336/466, loss: 0.2192315310239792
2023-01-22 11:26:56.844621: step: 338/466, loss: 0.05793094262480736
2023-01-22 11:26:57.576031: step: 340/466, loss: 0.08549658209085464
2023-01-22 11:26:58.229532: step: 342/466, loss: 0.22737926244735718
2023-01-22 11:26:58.862099: step: 344/466, loss: 0.04497341439127922
2023-01-22 11:26:59.490758: step: 346/466, loss: 0.08036022633314133
2023-01-22 11:27:00.104956: step: 348/466, loss: 0.10172585397958755
2023-01-22 11:27:00.685224: step: 350/466, loss: 0.20139440894126892
2023-01-22 11:27:01.348610: step: 352/466, loss: 0.004828613717108965
2023-01-22 11:27:01.973819: step: 354/466, loss: 0.02619241178035736
2023-01-22 11:27:02.559952: step: 356/466, loss: 0.10344935208559036
2023-01-22 11:27:03.184106: step: 358/466, loss: 0.004835547413676977
2023-01-22 11:27:03.814915: step: 360/466, loss: 0.019727077335119247
2023-01-22 11:27:04.474512: step: 362/466, loss: 0.030233588069677353
2023-01-22 11:27:05.134861: step: 364/466, loss: 0.1266247034072876
2023-01-22 11:27:05.805007: step: 366/466, loss: 0.10013896226882935
2023-01-22 11:27:06.435799: step: 368/466, loss: 0.04225357621908188
2023-01-22 11:27:07.056073: step: 370/466, loss: 0.07900624722242355
2023-01-22 11:27:07.675948: step: 372/466, loss: 0.046091485768556595
2023-01-22 11:27:08.401902: step: 374/466, loss: 0.0288006030023098
2023-01-22 11:27:08.992557: step: 376/466, loss: 0.039047833532094955
2023-01-22 11:27:09.582189: step: 378/466, loss: 0.029453450813889503
2023-01-22 11:27:10.191482: step: 380/466, loss: 0.07940339297056198
2023-01-22 11:27:10.916152: step: 382/466, loss: 0.07525602728128433
2023-01-22 11:27:11.545946: step: 384/466, loss: 0.07274336367845535
2023-01-22 11:27:12.188061: step: 386/466, loss: 0.04453727975487709
2023-01-22 11:27:12.793309: step: 388/466, loss: 0.1365232914686203
2023-01-22 11:27:13.476010: step: 390/466, loss: 0.2327868491411209
2023-01-22 11:27:14.085329: step: 392/466, loss: 0.02457980439066887
2023-01-22 11:27:14.704133: step: 394/466, loss: 0.04232895001769066
2023-01-22 11:27:15.345328: step: 396/466, loss: 0.08623890578746796
2023-01-22 11:27:16.016465: step: 398/466, loss: 0.09994079917669296
2023-01-22 11:27:16.725109: step: 400/466, loss: 1.7402442693710327
2023-01-22 11:27:17.427258: step: 402/466, loss: 0.7849536538124084
2023-01-22 11:27:18.072208: step: 404/466, loss: 0.07542157918214798
2023-01-22 11:27:18.698686: step: 406/466, loss: 0.5290749669075012
2023-01-22 11:27:19.297612: step: 408/466, loss: 0.06260983645915985
2023-01-22 11:27:19.987378: step: 410/466, loss: 0.11872803419828415
2023-01-22 11:27:20.575766: step: 412/466, loss: 0.09024270623922348
2023-01-22 11:27:21.244690: step: 414/466, loss: 0.07944059371948242
2023-01-22 11:27:21.867894: step: 416/466, loss: 0.08568576723337173
2023-01-22 11:27:22.560369: step: 418/466, loss: 0.11215931922197342
2023-01-22 11:27:23.154340: step: 420/466, loss: 0.08207669854164124
2023-01-22 11:27:23.713771: step: 422/466, loss: 0.5597177743911743
2023-01-22 11:27:24.358144: step: 424/466, loss: 0.1940152645111084
2023-01-22 11:27:25.024525: step: 426/466, loss: 0.13238102197647095
2023-01-22 11:27:25.626276: step: 428/466, loss: 0.05639738216996193
2023-01-22 11:27:26.386650: step: 430/466, loss: 0.12276247888803482
2023-01-22 11:27:27.069309: step: 432/466, loss: 0.3074175715446472
2023-01-22 11:27:27.655250: step: 434/466, loss: 0.7562771439552307
2023-01-22 11:27:28.331198: step: 436/466, loss: 0.04212067648768425
2023-01-22 11:27:28.965132: step: 438/466, loss: 0.3160960376262665
2023-01-22 11:27:29.647778: step: 440/466, loss: 0.04419974610209465
2023-01-22 11:27:30.356272: step: 442/466, loss: 0.09615902602672577
2023-01-22 11:27:30.978551: step: 444/466, loss: 0.11447758972644806
2023-01-22 11:27:31.632133: step: 446/466, loss: 0.03149205818772316
2023-01-22 11:27:32.226753: step: 448/466, loss: 0.1052766740322113
2023-01-22 11:27:32.851474: step: 450/466, loss: 4.804030895233154
2023-01-22 11:27:33.475324: step: 452/466, loss: 0.13028061389923096
2023-01-22 11:27:34.206940: step: 454/466, loss: 0.1731548011302948
2023-01-22 11:27:34.859257: step: 456/466, loss: 0.10007569938898087
2023-01-22 11:27:35.601690: step: 458/466, loss: 0.0489235520362854
2023-01-22 11:27:36.290907: step: 460/466, loss: 0.0729367583990097
2023-01-22 11:27:36.970754: step: 462/466, loss: 0.06604597717523575
2023-01-22 11:27:37.537176: step: 464/466, loss: 0.09258797019720078
2023-01-22 11:27:38.155804: step: 466/466, loss: 0.1299390345811844
2023-01-22 11:27:38.820843: step: 468/466, loss: 0.44548994302749634
2023-01-22 11:27:39.476168: step: 470/466, loss: 0.047990284860134125
2023-01-22 11:27:40.142338: step: 472/466, loss: 0.07879111170768738
2023-01-22 11:27:40.883925: step: 474/466, loss: 0.8586330413818359
2023-01-22 11:27:41.559568: step: 476/466, loss: 0.09463603794574738
2023-01-22 11:27:42.219008: step: 478/466, loss: 0.07230973988771439
2023-01-22 11:27:42.841245: step: 480/466, loss: 0.07197661697864532
2023-01-22 11:27:43.611563: step: 482/466, loss: 0.21483659744262695
2023-01-22 11:27:44.277864: step: 484/466, loss: 0.194536954164505
2023-01-22 11:27:44.968876: step: 486/466, loss: 0.5943006277084351
2023-01-22 11:27:45.634165: step: 488/466, loss: 0.14670486748218536
2023-01-22 11:27:46.324852: step: 490/466, loss: 0.0978560596704483
2023-01-22 11:27:46.974317: step: 492/466, loss: 0.046716898679733276
2023-01-22 11:27:47.569572: step: 494/466, loss: 0.07400691509246826
2023-01-22 11:27:48.251276: step: 496/466, loss: 0.37783244252204895
2023-01-22 11:27:48.996905: step: 498/466, loss: 0.09189492464065552
2023-01-22 11:27:49.591368: step: 500/466, loss: 0.07810716331005096
2023-01-22 11:27:50.172960: step: 502/466, loss: 1.526832938194275
2023-01-22 11:27:50.878922: step: 504/466, loss: 0.07685349136590958
2023-01-22 11:27:51.561898: step: 506/466, loss: 0.16347895562648773
2023-01-22 11:27:52.181203: step: 508/466, loss: 0.08108357340097427
2023-01-22 11:27:52.820241: step: 510/466, loss: 0.23870421946048737
2023-01-22 11:27:53.530936: step: 512/466, loss: 0.7059723138809204
2023-01-22 11:27:54.227059: step: 514/466, loss: 0.11288327723741531
2023-01-22 11:27:54.916987: step: 516/466, loss: 0.10943610966205597
2023-01-22 11:27:55.569655: step: 518/466, loss: 0.11879923939704895
2023-01-22 11:27:56.259936: step: 520/466, loss: 0.7888107895851135
2023-01-22 11:27:56.902930: step: 522/466, loss: 0.12313000112771988
2023-01-22 11:27:57.518405: step: 524/466, loss: 0.13041269779205322
2023-01-22 11:27:58.192221: step: 526/466, loss: 0.25587916374206543
2023-01-22 11:27:58.837044: step: 528/466, loss: 0.15828891098499298
2023-01-22 11:27:59.474304: step: 530/466, loss: 0.048195432871580124
2023-01-22 11:28:00.161956: step: 532/466, loss: 0.07142874598503113
2023-01-22 11:28:00.788569: step: 534/466, loss: 0.38426005840301514
2023-01-22 11:28:01.459932: step: 536/466, loss: 1.4751911163330078
2023-01-22 11:28:02.073720: step: 538/466, loss: 0.1260657161474228
2023-01-22 11:28:02.743790: step: 540/466, loss: 0.058579664677381516
2023-01-22 11:28:03.349335: step: 542/466, loss: 0.09295614063739777
2023-01-22 11:28:04.009077: step: 544/466, loss: 0.08101192861795425
2023-01-22 11:28:04.614199: step: 546/466, loss: 0.07070556282997131
2023-01-22 11:28:05.214429: step: 548/466, loss: 0.13065387308597565
2023-01-22 11:28:05.830977: step: 550/466, loss: 0.04952845722436905
2023-01-22 11:28:06.591138: step: 552/466, loss: 0.40858757495880127
2023-01-22 11:28:07.205701: step: 554/466, loss: 0.1270357072353363
2023-01-22 11:28:07.939990: step: 556/466, loss: 0.09554903954267502
2023-01-22 11:28:08.539483: step: 558/466, loss: 0.14123162627220154
2023-01-22 11:28:09.255038: step: 560/466, loss: 0.16500283777713776
2023-01-22 11:28:09.961155: step: 562/466, loss: 0.1087973341345787
2023-01-22 11:28:10.583568: step: 564/466, loss: 2.558933734893799
2023-01-22 11:28:11.269246: step: 566/466, loss: 0.06741175800561905
2023-01-22 11:28:11.935099: step: 568/466, loss: 0.31716012954711914
2023-01-22 11:28:12.567870: step: 570/466, loss: 0.21854546666145325
2023-01-22 11:28:13.200349: step: 572/466, loss: 0.07974494993686676
2023-01-22 11:28:14.562976: step: 574/466, loss: 0.20376497507095337
2023-01-22 11:28:15.197340: step: 576/466, loss: 0.1335975080728531
2023-01-22 11:28:15.857573: step: 578/466, loss: 0.6455204486846924
2023-01-22 11:28:16.482292: step: 580/466, loss: 0.1294020712375641
2023-01-22 11:28:17.143529: step: 582/466, loss: 0.059759803116321564
2023-01-22 11:28:17.794802: step: 584/466, loss: 0.09268747270107269
2023-01-22 11:28:18.504885: step: 586/466, loss: 0.0681382343173027
2023-01-22 11:28:19.169402: step: 588/466, loss: 0.37580254673957825
2023-01-22 11:28:19.850086: step: 590/466, loss: 0.04175303503870964
2023-01-22 11:28:20.509056: step: 592/466, loss: 0.06763419508934021
2023-01-22 11:28:21.135328: step: 594/466, loss: 0.9200158715248108
2023-01-22 11:28:21.763254: step: 596/466, loss: 0.5125054717063904
2023-01-22 11:28:22.376907: step: 598/466, loss: 0.05300223082304001
2023-01-22 11:28:23.061572: step: 600/466, loss: 0.15013554692268372
2023-01-22 11:28:23.745905: step: 602/466, loss: 0.0917985662817955
2023-01-22 11:28:24.418055: step: 604/466, loss: 0.05620555952191353
2023-01-22 11:28:25.142437: step: 606/466, loss: 0.0702977180480957
2023-01-22 11:28:25.798764: step: 608/466, loss: 0.10241170972585678
2023-01-22 11:28:26.436087: step: 610/466, loss: 0.1015259325504303
2023-01-22 11:28:27.107224: step: 612/466, loss: 0.2273823469877243
2023-01-22 11:28:27.733511: step: 614/466, loss: 0.07430493086576462
2023-01-22 11:28:28.429075: step: 616/466, loss: 0.05069427192211151
2023-01-22 11:28:29.107274: step: 618/466, loss: 0.48775190114974976
2023-01-22 11:28:29.761828: step: 620/466, loss: 0.11173519492149353
2023-01-22 11:28:30.503801: step: 622/466, loss: 0.09555468708276749
2023-01-22 11:28:31.125264: step: 624/466, loss: 0.07484864443540573
2023-01-22 11:28:31.785598: step: 626/466, loss: 0.31091174483299255
2023-01-22 11:28:32.500970: step: 628/466, loss: 0.10514596104621887
2023-01-22 11:28:33.112382: step: 630/466, loss: 0.08873254805803299
2023-01-22 11:28:33.734926: step: 632/466, loss: 0.10823825001716614
2023-01-22 11:28:34.385607: step: 634/466, loss: 0.128699392080307
2023-01-22 11:28:35.020255: step: 636/466, loss: 0.18408691883087158
2023-01-22 11:28:35.613875: step: 638/466, loss: 0.38384726643562317
2023-01-22 11:28:36.323326: step: 640/466, loss: 0.13084720075130463
2023-01-22 11:28:36.986976: step: 642/466, loss: 0.2408980429172516
2023-01-22 11:28:37.608917: step: 644/466, loss: 0.12450685352087021
2023-01-22 11:28:38.256120: step: 646/466, loss: 0.053344011306762695
2023-01-22 11:28:38.891608: step: 648/466, loss: 0.15100985765457153
2023-01-22 11:28:39.612912: step: 650/466, loss: 0.5366571545600891
2023-01-22 11:28:40.364924: step: 652/466, loss: 0.23490466177463531
2023-01-22 11:28:41.047665: step: 654/466, loss: 0.15787655115127563
2023-01-22 11:28:41.664964: step: 656/466, loss: 0.10110142827033997
2023-01-22 11:28:42.396677: step: 658/466, loss: 0.11273965984582901
2023-01-22 11:28:43.077904: step: 660/466, loss: 0.09545809775590897
2023-01-22 11:28:43.738860: step: 662/466, loss: 0.06254058331251144
2023-01-22 11:28:44.418965: step: 664/466, loss: 0.13021764159202576
2023-01-22 11:28:45.049926: step: 666/466, loss: 0.06415732204914093
2023-01-22 11:28:45.663271: step: 668/466, loss: 0.04331839457154274
2023-01-22 11:28:46.316214: step: 670/466, loss: 0.03789485618472099
2023-01-22 11:28:47.008717: step: 672/466, loss: 0.3357715308666229
2023-01-22 11:28:47.633920: step: 674/466, loss: 0.10420241206884384
2023-01-22 11:28:48.304973: step: 676/466, loss: 0.9282556772232056
2023-01-22 11:28:48.880898: step: 678/466, loss: 0.3590840697288513
2023-01-22 11:28:49.484983: step: 680/466, loss: 0.11960817128419876
2023-01-22 11:28:50.103660: step: 682/466, loss: 0.06062834709882736
2023-01-22 11:28:50.759924: step: 684/466, loss: 0.1513691395521164
2023-01-22 11:28:51.373667: step: 686/466, loss: 0.07220091670751572
2023-01-22 11:28:52.002734: step: 688/466, loss: 0.31088271737098694
2023-01-22 11:28:52.669237: step: 690/466, loss: 0.1168995201587677
2023-01-22 11:28:53.235210: step: 692/466, loss: 0.1224537119269371
2023-01-22 11:28:53.888669: step: 694/466, loss: 0.12207366526126862
2023-01-22 11:28:54.570657: step: 696/466, loss: 0.09792041778564453
2023-01-22 11:28:55.250081: step: 698/466, loss: 0.056785568594932556
2023-01-22 11:28:55.881317: step: 700/466, loss: 0.09063652902841568
2023-01-22 11:28:56.494546: step: 702/466, loss: 0.1667562574148178
2023-01-22 11:28:57.141286: step: 704/466, loss: 0.1611327975988388
2023-01-22 11:28:57.786484: step: 706/466, loss: 0.06084573268890381
2023-01-22 11:28:58.442848: step: 708/466, loss: 0.13086815178394318
2023-01-22 11:28:59.033312: step: 710/466, loss: 0.0684676244854927
2023-01-22 11:28:59.634422: step: 712/466, loss: 0.06935244798660278
2023-01-22 11:29:00.303209: step: 714/466, loss: 0.1311349719762802
2023-01-22 11:29:00.962046: step: 716/466, loss: 0.09169892221689224
2023-01-22 11:29:01.659664: step: 718/466, loss: 0.33384251594543457
2023-01-22 11:29:02.298941: step: 720/466, loss: 0.029739664867520332
2023-01-22 11:29:02.897557: step: 722/466, loss: 0.9668821692466736
2023-01-22 11:29:03.535298: step: 724/466, loss: 0.0668252483010292
2023-01-22 11:29:04.155743: step: 726/466, loss: 0.047192059457302094
2023-01-22 11:29:04.811634: step: 728/466, loss: 0.03709348663687706
2023-01-22 11:29:05.413055: step: 730/466, loss: 0.02418670989573002
2023-01-22 11:29:06.001345: step: 732/466, loss: 0.09607279300689697
2023-01-22 11:29:06.675418: step: 734/466, loss: 0.09355024248361588
2023-01-22 11:29:07.338012: step: 736/466, loss: 0.1411276012659073
2023-01-22 11:29:08.028015: step: 738/466, loss: 0.1141132116317749
2023-01-22 11:29:08.671081: step: 740/466, loss: 0.09725882858037949
2023-01-22 11:29:09.319780: step: 742/466, loss: 0.57298743724823
2023-01-22 11:29:09.934238: step: 744/466, loss: 0.22138182818889618
2023-01-22 11:29:10.583581: step: 746/466, loss: 0.18136608600616455
2023-01-22 11:29:11.178370: step: 748/466, loss: 0.05033509433269501
2023-01-22 11:29:11.881210: step: 750/466, loss: 0.1305447220802307
2023-01-22 11:29:12.542938: step: 752/466, loss: 0.15778738260269165
2023-01-22 11:29:13.209096: step: 754/466, loss: 0.07518231868743896
2023-01-22 11:29:13.779709: step: 756/466, loss: 0.4249395430088043
2023-01-22 11:29:14.473283: step: 758/466, loss: 0.059822119772434235
2023-01-22 11:29:15.103169: step: 760/466, loss: 0.0772186666727066
2023-01-22 11:29:15.782995: step: 762/466, loss: 0.03227313980460167
2023-01-22 11:29:16.501668: step: 764/466, loss: 0.37721946835517883
2023-01-22 11:29:17.107545: step: 766/466, loss: 0.36189213395118713
2023-01-22 11:29:17.745489: step: 768/466, loss: 0.27587422728538513
2023-01-22 11:29:18.486812: step: 770/466, loss: 0.34329304099082947
2023-01-22 11:29:19.215910: step: 772/466, loss: 0.15921442210674286
2023-01-22 11:29:19.799811: step: 774/466, loss: 0.020679069682955742
2023-01-22 11:29:20.445325: step: 776/466, loss: 4.652289867401123
2023-01-22 11:29:21.054054: step: 778/466, loss: 0.18183699250221252
2023-01-22 11:29:21.748622: step: 780/466, loss: 0.126389279961586
2023-01-22 11:29:22.368799: step: 782/466, loss: 0.12384083867073059
2023-01-22 11:29:23.017722: step: 784/466, loss: 0.13537752628326416
2023-01-22 11:29:23.596129: step: 786/466, loss: 0.16725100576877594
2023-01-22 11:29:24.249171: step: 788/466, loss: 0.04753489792346954
2023-01-22 11:29:24.933099: step: 790/466, loss: 0.30294153094291687
2023-01-22 11:29:25.565166: step: 792/466, loss: 0.03696773201227188
2023-01-22 11:29:26.232072: step: 794/466, loss: 0.020780369639396667
2023-01-22 11:29:26.874307: step: 796/466, loss: 0.08103333413600922
2023-01-22 11:29:27.632609: step: 798/466, loss: 0.0900353491306305
2023-01-22 11:29:28.307964: step: 800/466, loss: 0.20286378264427185
2023-01-22 11:29:28.913228: step: 802/466, loss: 0.3709118366241455
2023-01-22 11:29:29.582086: step: 804/466, loss: 0.029136160388588905
2023-01-22 11:29:30.222352: step: 806/466, loss: 0.059885792434215546
2023-01-22 11:29:30.905215: step: 808/466, loss: 0.1759241819381714
2023-01-22 11:29:31.485469: step: 810/466, loss: 0.056672364473342896
2023-01-22 11:29:32.077628: step: 812/466, loss: 0.046470172703266144
2023-01-22 11:29:32.752497: step: 814/466, loss: 0.08381474018096924
2023-01-22 11:29:33.316453: step: 816/466, loss: 0.08822699636220932
2023-01-22 11:29:33.990623: step: 818/466, loss: 0.09209505468606949
2023-01-22 11:29:34.783925: step: 820/466, loss: 4.051313877105713
2023-01-22 11:29:35.441359: step: 822/466, loss: 0.6569058895111084
2023-01-22 11:29:36.073201: step: 824/466, loss: 0.09321137517690659
2023-01-22 11:29:36.758300: step: 826/466, loss: 0.19895921647548676
2023-01-22 11:29:37.352168: step: 828/466, loss: 0.3110239505767822
2023-01-22 11:29:38.016712: step: 830/466, loss: 0.06787966936826706
2023-01-22 11:29:38.678658: step: 832/466, loss: 0.17457108199596405
2023-01-22 11:29:39.383982: step: 834/466, loss: 0.320141077041626
2023-01-22 11:29:39.996658: step: 836/466, loss: 0.11265549063682556
2023-01-22 11:29:40.753128: step: 838/466, loss: 0.08899205178022385
2023-01-22 11:29:41.468311: step: 840/466, loss: 0.33463096618652344
2023-01-22 11:29:42.170088: step: 842/466, loss: 0.027461307123303413
2023-01-22 11:29:42.809661: step: 844/466, loss: 0.20710547268390656
2023-01-22 11:29:43.449578: step: 846/466, loss: 0.10874569416046143
2023-01-22 11:29:44.100850: step: 848/466, loss: 0.09417065978050232
2023-01-22 11:29:44.721196: step: 850/466, loss: 0.09330161660909653
2023-01-22 11:29:45.363347: step: 852/466, loss: 0.03307119756937027
2023-01-22 11:29:46.001899: step: 854/466, loss: 0.42967110872268677
2023-01-22 11:29:46.636057: step: 856/466, loss: 0.17626191675662994
2023-01-22 11:29:47.235062: step: 858/466, loss: 0.07999088615179062
2023-01-22 11:29:47.837389: step: 860/466, loss: 0.40590253472328186
2023-01-22 11:29:48.479287: step: 862/466, loss: 0.1420111209154129
2023-01-22 11:29:49.098360: step: 864/466, loss: 0.06737148016691208
2023-01-22 11:29:49.714409: step: 866/466, loss: 0.086174875497818
2023-01-22 11:29:50.313094: step: 868/466, loss: 0.1882144808769226
2023-01-22 11:29:50.961924: step: 870/466, loss: 0.0016450968105345964
2023-01-22 11:29:51.559484: step: 872/466, loss: 2.2953505516052246
2023-01-22 11:29:52.191833: step: 874/466, loss: 0.33501380681991577
2023-01-22 11:29:52.877434: step: 876/466, loss: 0.06336680799722672
2023-01-22 11:29:53.516115: step: 878/466, loss: 0.14617972075939178
2023-01-22 11:29:54.154926: step: 880/466, loss: 0.10545101761817932
2023-01-22 11:29:54.865002: step: 882/466, loss: 0.5115710496902466
2023-01-22 11:29:55.486153: step: 884/466, loss: 0.044568244367837906
2023-01-22 11:29:56.246418: step: 886/466, loss: 0.09607965499162674
2023-01-22 11:29:56.872873: step: 888/466, loss: 0.30455282330513
2023-01-22 11:29:57.483353: step: 890/466, loss: 0.09439221024513245
2023-01-22 11:29:58.100129: step: 892/466, loss: 0.160738006234169
2023-01-22 11:29:58.758778: step: 894/466, loss: 0.055197641253471375
2023-01-22 11:29:59.404614: step: 896/466, loss: 0.10426119714975357
2023-01-22 11:30:00.066412: step: 898/466, loss: 0.07737888395786285
2023-01-22 11:30:00.662286: step: 900/466, loss: 0.08653061091899872
2023-01-22 11:30:01.364526: step: 902/466, loss: 0.20931552350521088
2023-01-22 11:30:02.068142: step: 904/466, loss: 0.05122126266360283
2023-01-22 11:30:02.786184: step: 906/466, loss: 0.13378262519836426
2023-01-22 11:30:03.357191: step: 908/466, loss: 0.11195065826177597
2023-01-22 11:30:04.038457: step: 910/466, loss: 0.1351906657218933
2023-01-22 11:30:04.658549: step: 912/466, loss: 0.03451892361044884
2023-01-22 11:30:05.345803: step: 914/466, loss: 0.1293785274028778
2023-01-22 11:30:06.002213: step: 916/466, loss: 0.08654919266700745
2023-01-22 11:30:06.640913: step: 918/466, loss: 0.059098485857248306
2023-01-22 11:30:07.259682: step: 920/466, loss: 0.46760809421539307
2023-01-22 11:30:07.922866: step: 922/466, loss: 0.13194270431995392
2023-01-22 11:30:08.557598: step: 924/466, loss: 0.14335869252681732
2023-01-22 11:30:09.228628: step: 926/466, loss: 0.017652394250035286
2023-01-22 11:30:09.880521: step: 928/466, loss: 0.13621695339679718
2023-01-22 11:30:10.585875: step: 930/466, loss: 0.07794871181249619
2023-01-22 11:30:11.211469: step: 932/466, loss: 0.12003447115421295
==================================================
Loss: 0.223
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30819346207618514, 'r': 0.3128719207035276, 'f1': 0.310515070076759}, 'combined': 0.22880057795129607, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3055201420442433, 'r': 0.28206105254671787, 'f1': 0.2933222970119461}, 'combined': 0.18366910186729338, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28863171091180334, 'r': 0.3368282774397705, 'f1': 0.3108730336440613}, 'combined': 0.22906434057983466, 'epoch': 15}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.30905935608968366, 'r': 0.2909286176909206, 'f1': 0.29972004500375643}, 'combined': 0.18574199972063776, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26910228194177016, 'r': 0.33242046592806906, 'f1': 0.2974288379356407}, 'combined': 0.21915809111047208, 'epoch': 15}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3116520334728427, 'r': 0.2924907872918722, 'f1': 0.3017675473365771}, 'combined': 0.20018243239159078, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24489795918367346, 'r': 0.34285714285714286, 'f1': 0.28571428571428575}, 'combined': 0.1904761904761905, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.29605263157894735, 'r': 0.4891304347826087, 'f1': 0.3688524590163934}, 'combined': 0.1844262295081967, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23809523809523808, 'r': 0.1724137931034483, 'f1': 0.19999999999999998}, 'combined': 0.1333333333333333, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:32:58.214468: step: 2/466, loss: 0.0364297553896904
2023-01-22 11:32:58.862870: step: 4/466, loss: 0.041913751512765884
2023-01-22 11:32:59.582587: step: 6/466, loss: 0.044302765280008316
2023-01-22 11:33:00.243619: step: 8/466, loss: 0.09393715113401413
2023-01-22 11:33:00.949093: step: 10/466, loss: 0.10036303848028183
2023-01-22 11:33:01.565753: step: 12/466, loss: 0.03882470354437828
2023-01-22 11:33:02.192361: step: 14/466, loss: 0.05609731003642082
2023-01-22 11:33:02.868239: step: 16/466, loss: 0.010594441555440426
2023-01-22 11:33:03.532235: step: 18/466, loss: 0.03913673385977745
2023-01-22 11:33:04.162264: step: 20/466, loss: 0.07897093147039413
2023-01-22 11:33:04.805117: step: 22/466, loss: 0.09117831289768219
2023-01-22 11:33:05.443860: step: 24/466, loss: 0.0415981151163578
2023-01-22 11:33:06.071156: step: 26/466, loss: 0.23397918045520782
2023-01-22 11:33:06.807685: step: 28/466, loss: 0.7837872505187988
2023-01-22 11:33:07.461957: step: 30/466, loss: 0.2118677943944931
2023-01-22 11:33:08.093877: step: 32/466, loss: 0.12464660406112671
2023-01-22 11:33:08.804745: step: 34/466, loss: 0.01113061048090458
2023-01-22 11:33:09.453477: step: 36/466, loss: 0.2734963893890381
2023-01-22 11:33:10.126501: step: 38/466, loss: 0.09920921921730042
2023-01-22 11:33:10.788789: step: 40/466, loss: 0.14077113568782806
2023-01-22 11:33:11.415312: step: 42/466, loss: 0.09466637670993805
2023-01-22 11:33:12.066264: step: 44/466, loss: 0.07245796173810959
2023-01-22 11:33:12.788021: step: 46/466, loss: 0.16933250427246094
2023-01-22 11:33:13.371629: step: 48/466, loss: 0.07951069623231888
2023-01-22 11:33:14.042820: step: 50/466, loss: 0.14674483239650726
2023-01-22 11:33:14.716222: step: 52/466, loss: 0.059572115540504456
2023-01-22 11:33:15.328091: step: 54/466, loss: 0.056674208492040634
2023-01-22 11:33:15.981679: step: 56/466, loss: 0.06632649153470993
2023-01-22 11:33:16.643206: step: 58/466, loss: 0.05860430747270584
2023-01-22 11:33:17.330928: step: 60/466, loss: 0.09247143566608429
2023-01-22 11:33:17.979856: step: 62/466, loss: 0.07196611911058426
2023-01-22 11:33:18.658965: step: 64/466, loss: 0.06352918595075607
2023-01-22 11:33:19.374151: step: 66/466, loss: 0.1437981277704239
2023-01-22 11:33:20.010862: step: 68/466, loss: 0.04908664897084236
2023-01-22 11:33:20.663364: step: 70/466, loss: 0.2820562720298767
2023-01-22 11:33:21.345598: step: 72/466, loss: 0.030099721625447273
2023-01-22 11:33:22.011492: step: 74/466, loss: 0.03254220262169838
2023-01-22 11:33:22.697036: step: 76/466, loss: 0.05652083083987236
2023-01-22 11:33:23.363055: step: 78/466, loss: 0.03945573419332504
2023-01-22 11:33:24.098398: step: 80/466, loss: 0.06642769277095795
2023-01-22 11:33:24.745903: step: 82/466, loss: 0.04746884107589722
2023-01-22 11:33:25.452096: step: 84/466, loss: 0.07368164509534836
2023-01-22 11:33:26.099849: step: 86/466, loss: 0.17138804495334625
2023-01-22 11:33:26.745691: step: 88/466, loss: 0.10994307696819305
2023-01-22 11:33:27.431770: step: 90/466, loss: 0.07358071208000183
2023-01-22 11:33:28.127383: step: 92/466, loss: 0.2667846977710724
2023-01-22 11:33:28.778514: step: 94/466, loss: 0.1575712114572525
2023-01-22 11:33:29.398365: step: 96/466, loss: 0.06615050882101059
2023-01-22 11:33:29.996663: step: 98/466, loss: 0.04318195581436157
2023-01-22 11:33:30.632042: step: 100/466, loss: 2.450364112854004
2023-01-22 11:33:31.322211: step: 102/466, loss: 0.16622458398342133
2023-01-22 11:33:31.989208: step: 104/466, loss: 0.1172252893447876
2023-01-22 11:33:32.628968: step: 106/466, loss: 0.15681900084018707
2023-01-22 11:33:33.282586: step: 108/466, loss: 0.11366615444421768
2023-01-22 11:33:33.994622: step: 110/466, loss: 0.13074658811092377
2023-01-22 11:33:34.649840: step: 112/466, loss: 0.9056664705276489
2023-01-22 11:33:35.336897: step: 114/466, loss: 0.07722001522779465
2023-01-22 11:33:35.999401: step: 116/466, loss: 0.07057715952396393
2023-01-22 11:33:36.645655: step: 118/466, loss: 0.06568702310323715
2023-01-22 11:33:37.265369: step: 120/466, loss: 0.06861089169979095
2023-01-22 11:33:37.911413: step: 122/466, loss: 0.27800774574279785
2023-01-22 11:33:38.590873: step: 124/466, loss: 0.08259350806474686
2023-01-22 11:33:39.264103: step: 126/466, loss: 0.16336436569690704
2023-01-22 11:33:39.928389: step: 128/466, loss: 0.07314635068178177
2023-01-22 11:33:40.647041: step: 130/466, loss: 0.13182193040847778
2023-01-22 11:33:41.260136: step: 132/466, loss: 0.09079380333423615
2023-01-22 11:33:41.934232: step: 134/466, loss: 0.06319943070411682
2023-01-22 11:33:42.593889: step: 136/466, loss: 0.08041159063577652
2023-01-22 11:33:43.256346: step: 138/466, loss: 0.09127406030893326
2023-01-22 11:33:43.851538: step: 140/466, loss: 0.07198181003332138
2023-01-22 11:33:44.568891: step: 142/466, loss: 0.4676929712295532
2023-01-22 11:33:45.231803: step: 144/466, loss: 0.0892963632941246
2023-01-22 11:33:45.991618: step: 146/466, loss: 0.07624605298042297
2023-01-22 11:33:46.651846: step: 148/466, loss: 0.21611839532852173
2023-01-22 11:33:47.337232: step: 150/466, loss: 0.06725850701332092
2023-01-22 11:33:48.036107: step: 152/466, loss: 0.13193872570991516
2023-01-22 11:33:48.664292: step: 154/466, loss: 0.13217201828956604
2023-01-22 11:33:49.389896: step: 156/466, loss: 2.136812210083008
2023-01-22 11:33:50.033178: step: 158/466, loss: 0.016867976635694504
2023-01-22 11:33:50.732158: step: 160/466, loss: 0.058701291680336
2023-01-22 11:33:51.422453: step: 162/466, loss: 0.09831482172012329
2023-01-22 11:33:52.107058: step: 164/466, loss: 0.054717060178518295
2023-01-22 11:33:52.753619: step: 166/466, loss: 0.16726908087730408
2023-01-22 11:33:53.363035: step: 168/466, loss: 0.04749428108334541
2023-01-22 11:33:53.951472: step: 170/466, loss: 0.39669886231422424
2023-01-22 11:33:54.573998: step: 172/466, loss: 0.024730466306209564
2023-01-22 11:33:55.264515: step: 174/466, loss: 0.22909945249557495
2023-01-22 11:33:55.861419: step: 176/466, loss: 0.03844194486737251
2023-01-22 11:33:56.470585: step: 178/466, loss: 0.16384950280189514
2023-01-22 11:33:57.181024: step: 180/466, loss: 0.7103508710861206
2023-01-22 11:33:57.790216: step: 182/466, loss: 0.039173197001218796
2023-01-22 11:33:58.480965: step: 184/466, loss: 0.04706037417054176
2023-01-22 11:33:59.155722: step: 186/466, loss: 0.09144410490989685
2023-01-22 11:33:59.802249: step: 188/466, loss: 0.1519036740064621
2023-01-22 11:34:00.425318: step: 190/466, loss: 0.03659029304981232
2023-01-22 11:34:01.068077: step: 192/466, loss: 0.054771166294813156
2023-01-22 11:34:01.759851: step: 194/466, loss: 0.438940167427063
2023-01-22 11:34:02.397814: step: 196/466, loss: 0.25274887681007385
2023-01-22 11:34:03.009809: step: 198/466, loss: 0.012997581623494625
2023-01-22 11:34:03.715446: step: 200/466, loss: 0.13784900307655334
2023-01-22 11:34:04.462992: step: 202/466, loss: 0.17327864468097687
2023-01-22 11:34:05.052730: step: 204/466, loss: 0.06874261796474457
2023-01-22 11:34:05.736949: step: 206/466, loss: 0.1746750921010971
2023-01-22 11:34:06.415743: step: 208/466, loss: 0.0177956260740757
2023-01-22 11:34:07.065201: step: 210/466, loss: 0.05754571035504341
2023-01-22 11:34:07.731293: step: 212/466, loss: 0.10158266127109528
2023-01-22 11:34:08.413344: step: 214/466, loss: 0.031053008511662483
2023-01-22 11:34:09.073053: step: 216/466, loss: 0.029317565262317657
2023-01-22 11:34:09.758518: step: 218/466, loss: 0.15037000179290771
2023-01-22 11:34:10.417740: step: 220/466, loss: 0.1555047184228897
2023-01-22 11:34:11.129670: step: 222/466, loss: 0.9966866970062256
2023-01-22 11:34:11.766750: step: 224/466, loss: 0.05561330169439316
2023-01-22 11:34:12.473839: step: 226/466, loss: 0.27670490741729736
2023-01-22 11:34:13.187503: step: 228/466, loss: 0.07437361031770706
2023-01-22 11:34:13.830039: step: 230/466, loss: 0.059094492346048355
2023-01-22 11:34:14.532345: step: 232/466, loss: 0.08575653284788132
2023-01-22 11:34:15.188774: step: 234/466, loss: 0.14250144362449646
2023-01-22 11:34:15.824443: step: 236/466, loss: 0.12382957339286804
2023-01-22 11:34:16.453401: step: 238/466, loss: 0.11464880406856537
2023-01-22 11:34:17.085502: step: 240/466, loss: 0.07331466674804688
2023-01-22 11:34:17.763210: step: 242/466, loss: 0.0688156932592392
2023-01-22 11:34:18.363846: step: 244/466, loss: 0.03604768216609955
2023-01-22 11:34:19.029866: step: 246/466, loss: 0.07054924219846725
2023-01-22 11:34:19.727896: step: 248/466, loss: 0.1382962018251419
2023-01-22 11:34:20.437530: step: 250/466, loss: 0.1107596680521965
2023-01-22 11:34:21.023354: step: 252/466, loss: 0.02213207073509693
2023-01-22 11:34:21.722382: step: 254/466, loss: 0.08174173533916473
2023-01-22 11:34:22.389598: step: 256/466, loss: 0.2501335144042969
2023-01-22 11:34:23.119809: step: 258/466, loss: 0.053914088755846024
2023-01-22 11:34:23.785118: step: 260/466, loss: 0.04311135411262512
2023-01-22 11:34:24.369910: step: 262/466, loss: 0.25014761090278625
2023-01-22 11:34:25.014610: step: 264/466, loss: 0.1010250523686409
2023-01-22 11:34:25.678306: step: 266/466, loss: 0.09395529329776764
2023-01-22 11:34:26.288043: step: 268/466, loss: 0.02777744270861149
2023-01-22 11:34:26.972021: step: 270/466, loss: 0.053821831941604614
2023-01-22 11:34:27.558650: step: 272/466, loss: 0.12027788907289505
2023-01-22 11:34:28.190506: step: 274/466, loss: 0.07144496589899063
2023-01-22 11:34:28.833180: step: 276/466, loss: 0.07142110913991928
2023-01-22 11:34:29.475307: step: 278/466, loss: 0.03224104270339012
2023-01-22 11:34:30.063185: step: 280/466, loss: 0.1393880844116211
2023-01-22 11:34:30.609770: step: 282/466, loss: 0.09324046969413757
2023-01-22 11:34:31.248496: step: 284/466, loss: 0.09826359152793884
2023-01-22 11:34:31.878484: step: 286/466, loss: 0.06192191690206528
2023-01-22 11:34:32.523852: step: 288/466, loss: 0.059555042535066605
2023-01-22 11:34:33.138611: step: 290/466, loss: 0.32981789112091064
2023-01-22 11:34:33.787344: step: 292/466, loss: 0.14390693604946136
2023-01-22 11:34:34.441442: step: 294/466, loss: 0.1129252165555954
2023-01-22 11:34:35.088303: step: 296/466, loss: 0.08461034297943115
2023-01-22 11:34:35.756440: step: 298/466, loss: 0.09603862464427948
2023-01-22 11:34:36.333693: step: 300/466, loss: 0.0672009214758873
2023-01-22 11:34:37.109363: step: 302/466, loss: 0.09006774425506592
2023-01-22 11:34:37.738811: step: 304/466, loss: 0.0714765414595604
2023-01-22 11:34:38.382073: step: 306/466, loss: 0.3602089583873749
2023-01-22 11:34:39.028227: step: 308/466, loss: 0.045358337461948395
2023-01-22 11:34:39.654825: step: 310/466, loss: 0.17103302478790283
2023-01-22 11:34:40.264292: step: 312/466, loss: 1.0719202756881714
2023-01-22 11:34:40.914855: step: 314/466, loss: 0.14032472670078278
2023-01-22 11:34:41.517480: step: 316/466, loss: 0.13565972447395325
2023-01-22 11:34:42.212538: step: 318/466, loss: 0.6626256108283997
2023-01-22 11:34:42.836946: step: 320/466, loss: 0.9905956387519836
2023-01-22 11:34:43.469722: step: 322/466, loss: 0.09602364897727966
2023-01-22 11:34:44.103468: step: 324/466, loss: 0.07717530429363251
2023-01-22 11:34:44.796057: step: 326/466, loss: 0.30983152985572815
2023-01-22 11:34:45.438595: step: 328/466, loss: 0.1082986518740654
2023-01-22 11:34:46.028457: step: 330/466, loss: 0.11601077020168304
2023-01-22 11:34:46.694533: step: 332/466, loss: 0.11921878904104233
2023-01-22 11:34:47.283979: step: 334/466, loss: 0.0804547518491745
2023-01-22 11:34:47.917734: step: 336/466, loss: 0.09161564707756042
2023-01-22 11:34:48.656499: step: 338/466, loss: 0.40797990560531616
2023-01-22 11:34:49.228893: step: 340/466, loss: 0.13910165429115295
2023-01-22 11:34:49.836630: step: 342/466, loss: 0.07941452413797379
2023-01-22 11:34:50.495791: step: 344/466, loss: 0.055207520723342896
2023-01-22 11:34:51.169776: step: 346/466, loss: 0.0494774654507637
2023-01-22 11:34:51.830795: step: 348/466, loss: 0.19999352097511292
2023-01-22 11:34:52.528674: step: 350/466, loss: 0.12860815227031708
2023-01-22 11:34:53.178506: step: 352/466, loss: 0.20784658193588257
2023-01-22 11:34:53.847695: step: 354/466, loss: 0.04734490066766739
2023-01-22 11:34:54.539569: step: 356/466, loss: 0.048202116042375565
2023-01-22 11:34:55.143993: step: 358/466, loss: 0.37989869713783264
2023-01-22 11:34:55.757755: step: 360/466, loss: 0.040857430547475815
2023-01-22 11:34:56.383964: step: 362/466, loss: 0.19746412336826324
2023-01-22 11:34:57.084257: step: 364/466, loss: 0.15635210275650024
2023-01-22 11:34:57.719252: step: 366/466, loss: 0.1906730830669403
2023-01-22 11:34:58.464554: step: 368/466, loss: 0.13276511430740356
2023-01-22 11:34:59.100482: step: 370/466, loss: 0.07794889807701111
2023-01-22 11:34:59.691912: step: 372/466, loss: 0.056645467877388
2023-01-22 11:35:00.298762: step: 374/466, loss: 0.08633853495121002
2023-01-22 11:35:00.988178: step: 376/466, loss: 0.10069998353719711
2023-01-22 11:35:01.621741: step: 378/466, loss: 0.17765261232852936
2023-01-22 11:35:02.299159: step: 380/466, loss: 0.151209756731987
2023-01-22 11:35:02.957967: step: 382/466, loss: 0.22974668443202972
2023-01-22 11:35:03.617302: step: 384/466, loss: 0.0981052815914154
2023-01-22 11:35:04.261418: step: 386/466, loss: 0.2308218628168106
2023-01-22 11:35:04.909346: step: 388/466, loss: 0.12051533907651901
2023-01-22 11:35:05.577157: step: 390/466, loss: 0.08414598554372787
2023-01-22 11:35:06.184906: step: 392/466, loss: 0.10993286222219467
2023-01-22 11:35:06.779240: step: 394/466, loss: 0.01752668432891369
2023-01-22 11:35:07.404510: step: 396/466, loss: 0.098649762570858
2023-01-22 11:35:08.021608: step: 398/466, loss: 0.16422350704669952
2023-01-22 11:35:08.638071: step: 400/466, loss: 0.0024283877573907375
2023-01-22 11:35:09.236568: step: 402/466, loss: 0.05185849219560623
2023-01-22 11:35:09.833911: step: 404/466, loss: 0.16710449755191803
2023-01-22 11:35:10.460843: step: 406/466, loss: 0.17796562612056732
2023-01-22 11:35:11.155209: step: 408/466, loss: 0.2567916810512543
2023-01-22 11:35:11.818638: step: 410/466, loss: 0.10605175793170929
2023-01-22 11:35:12.478036: step: 412/466, loss: 0.24402956664562225
2023-01-22 11:35:13.076446: step: 414/466, loss: 0.0167254451662302
2023-01-22 11:35:13.672905: step: 416/466, loss: 0.4071357250213623
2023-01-22 11:35:14.294359: step: 418/466, loss: 0.4210357367992401
2023-01-22 11:35:14.915712: step: 420/466, loss: 0.20658299326896667
2023-01-22 11:35:15.541973: step: 422/466, loss: 0.36707136034965515
2023-01-22 11:35:16.172229: step: 424/466, loss: 0.026186460629105568
2023-01-22 11:35:16.819629: step: 426/466, loss: 0.04088641703128815
2023-01-22 11:35:17.470500: step: 428/466, loss: 0.08710642158985138
2023-01-22 11:35:18.071149: step: 430/466, loss: 0.1455727219581604
2023-01-22 11:35:18.732961: step: 432/466, loss: 0.038881801068782806
2023-01-22 11:35:19.364856: step: 434/466, loss: 0.1724172830581665
2023-01-22 11:35:20.007754: step: 436/466, loss: 0.181453675031662
2023-01-22 11:35:20.722523: step: 438/466, loss: 0.2943277955055237
2023-01-22 11:35:21.344731: step: 440/466, loss: 0.1346326470375061
2023-01-22 11:35:21.985433: step: 442/466, loss: 0.09035190939903259
2023-01-22 11:35:22.607891: step: 444/466, loss: 0.044517651200294495
2023-01-22 11:35:23.296328: step: 446/466, loss: 0.1681986153125763
2023-01-22 11:35:23.952871: step: 448/466, loss: 0.37380313873291016
2023-01-22 11:35:24.617587: step: 450/466, loss: 0.3123873174190521
2023-01-22 11:35:25.261403: step: 452/466, loss: 0.056177251040935516
2023-01-22 11:35:25.843102: step: 454/466, loss: 0.1289960741996765
2023-01-22 11:35:26.455371: step: 456/466, loss: 0.047767218202352524
2023-01-22 11:35:27.083396: step: 458/466, loss: 0.22923243045806885
2023-01-22 11:35:27.642909: step: 460/466, loss: 0.06283791363239288
2023-01-22 11:35:28.271528: step: 462/466, loss: 0.24462512135505676
2023-01-22 11:35:29.002663: step: 464/466, loss: 6.311313152313232
2023-01-22 11:35:29.605430: step: 466/466, loss: 1.465904712677002
2023-01-22 11:35:30.253052: step: 468/466, loss: 0.19708696007728577
2023-01-22 11:35:30.944442: step: 470/466, loss: 0.09209314733743668
2023-01-22 11:35:31.573488: step: 472/466, loss: 0.07932702451944351
2023-01-22 11:35:32.261128: step: 474/466, loss: 0.18532010912895203
2023-01-22 11:35:32.943352: step: 476/466, loss: 0.12062534689903259
2023-01-22 11:35:33.598794: step: 478/466, loss: 0.5024365782737732
2023-01-22 11:35:34.233642: step: 480/466, loss: 0.04506577178835869
2023-01-22 11:35:34.844445: step: 482/466, loss: 0.07182347029447556
2023-01-22 11:35:35.548812: step: 484/466, loss: 0.18841418623924255
2023-01-22 11:35:36.137074: step: 486/466, loss: 0.12853263318538666
2023-01-22 11:35:36.893181: step: 488/466, loss: 0.06982048600912094
2023-01-22 11:35:37.505606: step: 490/466, loss: 0.08866838365793228
2023-01-22 11:35:38.143048: step: 492/466, loss: 0.1469661295413971
2023-01-22 11:35:38.762344: step: 494/466, loss: 0.04782625660300255
2023-01-22 11:35:39.405035: step: 496/466, loss: 0.0394095852971077
2023-01-22 11:35:40.058512: step: 498/466, loss: 0.06809506565332413
2023-01-22 11:35:40.703654: step: 500/466, loss: 0.06742847710847855
2023-01-22 11:35:41.382778: step: 502/466, loss: 0.6899810433387756
2023-01-22 11:35:42.006936: step: 504/466, loss: 0.04344059154391289
2023-01-22 11:35:42.670847: step: 506/466, loss: 0.02709837257862091
2023-01-22 11:35:43.299299: step: 508/466, loss: 0.17914627492427826
2023-01-22 11:35:43.988682: step: 510/466, loss: 0.17754724621772766
2023-01-22 11:35:44.605905: step: 512/466, loss: 0.0071636890061199665
2023-01-22 11:35:45.234800: step: 514/466, loss: 0.02729751169681549
2023-01-22 11:35:45.891157: step: 516/466, loss: 0.33817991614341736
2023-01-22 11:35:46.519670: step: 518/466, loss: 0.17708256840705872
2023-01-22 11:35:47.136723: step: 520/466, loss: 0.019362229853868484
2023-01-22 11:35:47.749687: step: 522/466, loss: 0.06572502851486206
2023-01-22 11:35:48.434901: step: 524/466, loss: 0.08744283765554428
2023-01-22 11:35:49.070481: step: 526/466, loss: 0.2761349678039551
2023-01-22 11:35:49.782698: step: 528/466, loss: 0.5027775764465332
2023-01-22 11:35:50.413551: step: 530/466, loss: 0.025422899052500725
2023-01-22 11:35:51.127605: step: 532/466, loss: 0.05502090975642204
2023-01-22 11:35:51.736434: step: 534/466, loss: 0.20646455883979797
2023-01-22 11:35:52.424755: step: 536/466, loss: 0.07636255770921707
2023-01-22 11:35:53.050187: step: 538/466, loss: 0.08909200876951218
2023-01-22 11:35:53.682967: step: 540/466, loss: 0.07184493541717529
2023-01-22 11:35:54.398029: step: 542/466, loss: 0.4698965847492218
2023-01-22 11:35:55.020781: step: 544/466, loss: 0.16242723166942596
2023-01-22 11:35:55.618364: step: 546/466, loss: 0.14060641825199127
2023-01-22 11:35:56.237771: step: 548/466, loss: 0.25153452157974243
2023-01-22 11:35:56.888670: step: 550/466, loss: 0.06144038960337639
2023-01-22 11:35:57.557518: step: 552/466, loss: 0.28175848722457886
2023-01-22 11:35:58.215285: step: 554/466, loss: 0.0455288402736187
2023-01-22 11:35:58.884048: step: 556/466, loss: 0.26265767216682434
2023-01-22 11:35:59.563340: step: 558/466, loss: 0.4596168100833893
2023-01-22 11:36:00.169413: step: 560/466, loss: 0.04697806388139725
2023-01-22 11:36:00.778092: step: 562/466, loss: 0.22388292849063873
2023-01-22 11:36:01.446668: step: 564/466, loss: 0.08523406833410263
2023-01-22 11:36:02.122748: step: 566/466, loss: 0.0574776865541935
2023-01-22 11:36:02.782251: step: 568/466, loss: 0.19718588888645172
2023-01-22 11:36:03.509595: step: 570/466, loss: 0.13567817211151123
2023-01-22 11:36:04.121667: step: 572/466, loss: 0.06724944710731506
2023-01-22 11:36:04.781238: step: 574/466, loss: 0.104249507188797
2023-01-22 11:36:05.443801: step: 576/466, loss: 0.23395521938800812
2023-01-22 11:36:06.102856: step: 578/466, loss: 0.1479276567697525
2023-01-22 11:36:06.767520: step: 580/466, loss: 0.07878604531288147
2023-01-22 11:36:07.372414: step: 582/466, loss: 0.3168390691280365
2023-01-22 11:36:08.098068: step: 584/466, loss: 0.1844732016324997
2023-01-22 11:36:08.748695: step: 586/466, loss: 0.052865419536828995
2023-01-22 11:36:09.570323: step: 588/466, loss: 0.16163483262062073
2023-01-22 11:36:10.136689: step: 590/466, loss: 0.10157793760299683
2023-01-22 11:36:10.851631: step: 592/466, loss: 0.5824289321899414
2023-01-22 11:36:11.490613: step: 594/466, loss: 0.04869154840707779
2023-01-22 11:36:12.127481: step: 596/466, loss: 0.04857758805155754
2023-01-22 11:36:12.775723: step: 598/466, loss: 0.09195052087306976
2023-01-22 11:36:13.404946: step: 600/466, loss: 0.3458186686038971
2023-01-22 11:36:14.020775: step: 602/466, loss: 0.08263885974884033
2023-01-22 11:36:14.721317: step: 604/466, loss: 0.11075650900602341
2023-01-22 11:36:15.388238: step: 606/466, loss: 0.07145028561353683
2023-01-22 11:36:16.035895: step: 608/466, loss: 0.06847894936800003
2023-01-22 11:36:16.682232: step: 610/466, loss: 0.07767244428396225
2023-01-22 11:36:17.317765: step: 612/466, loss: 0.09935230761766434
2023-01-22 11:36:17.880667: step: 614/466, loss: 0.12344237416982651
2023-01-22 11:36:18.518212: step: 616/466, loss: 0.11530716717243195
2023-01-22 11:36:19.348933: step: 618/466, loss: 0.3105453550815582
2023-01-22 11:36:19.942933: step: 620/466, loss: 0.03813612833619118
2023-01-22 11:36:20.567580: step: 622/466, loss: 0.1672123670578003
2023-01-22 11:36:21.187092: step: 624/466, loss: 0.09853332489728928
2023-01-22 11:36:21.794423: step: 626/466, loss: 0.05499133840203285
2023-01-22 11:36:22.499800: step: 628/466, loss: 0.06897318363189697
2023-01-22 11:36:23.122686: step: 630/466, loss: 0.08766872435808182
2023-01-22 11:36:23.748605: step: 632/466, loss: 0.10207361727952957
2023-01-22 11:36:24.422531: step: 634/466, loss: 0.05842089653015137
2023-01-22 11:36:25.029567: step: 636/466, loss: 0.030612140893936157
2023-01-22 11:36:25.740551: step: 638/466, loss: 0.039262767881155014
2023-01-22 11:36:26.378507: step: 640/466, loss: 0.015716716647148132
2023-01-22 11:36:27.012765: step: 642/466, loss: 0.1715877503156662
2023-01-22 11:36:27.716714: step: 644/466, loss: 0.1346689909696579
2023-01-22 11:36:28.413346: step: 646/466, loss: 0.14579948782920837
2023-01-22 11:36:29.000169: step: 648/466, loss: 0.08950228244066238
2023-01-22 11:36:29.613592: step: 650/466, loss: 0.13232272863388062
2023-01-22 11:36:30.216461: step: 652/466, loss: 0.17211388051509857
2023-01-22 11:36:30.862159: step: 654/466, loss: 0.028392614796757698
2023-01-22 11:36:31.458424: step: 656/466, loss: 0.12627607583999634
2023-01-22 11:36:32.079758: step: 658/466, loss: 0.12688058614730835
2023-01-22 11:36:32.735824: step: 660/466, loss: 0.10577981919050217
2023-01-22 11:36:33.430928: step: 662/466, loss: 0.15648826956748962
2023-01-22 11:36:34.037144: step: 664/466, loss: 0.033302515745162964
2023-01-22 11:36:34.723176: step: 666/466, loss: 0.05960897356271744
2023-01-22 11:36:35.336568: step: 668/466, loss: 0.09449905157089233
2023-01-22 11:36:35.992187: step: 670/466, loss: 0.16037170588970184
2023-01-22 11:36:36.642051: step: 672/466, loss: 0.117377370595932
2023-01-22 11:36:37.324811: step: 674/466, loss: 0.13370610773563385
2023-01-22 11:36:37.951814: step: 676/466, loss: 0.0766676589846611
2023-01-22 11:36:38.715711: step: 678/466, loss: 0.059579480439424515
2023-01-22 11:36:39.335464: step: 680/466, loss: 0.054846640676259995
2023-01-22 11:36:39.987296: step: 682/466, loss: 0.009645046666264534
2023-01-22 11:36:40.677407: step: 684/466, loss: 0.23150868713855743
2023-01-22 11:36:41.335267: step: 686/466, loss: 0.21831421554088593
2023-01-22 11:36:41.972836: step: 688/466, loss: 0.0784607082605362
2023-01-22 11:36:42.517708: step: 690/466, loss: 0.061767883598804474
2023-01-22 11:36:43.230817: step: 692/466, loss: 0.05261386185884476
2023-01-22 11:36:43.909622: step: 694/466, loss: 0.2991788387298584
2023-01-22 11:36:44.545364: step: 696/466, loss: 0.03715163469314575
2023-01-22 11:36:45.192944: step: 698/466, loss: 0.1540336012840271
2023-01-22 11:36:45.811227: step: 700/466, loss: 0.027739468961954117
2023-01-22 11:36:46.461887: step: 702/466, loss: 0.06844502687454224
2023-01-22 11:36:47.157773: step: 704/466, loss: 0.1026684120297432
2023-01-22 11:36:47.809259: step: 706/466, loss: 0.18602652847766876
2023-01-22 11:36:48.525577: step: 708/466, loss: 0.08809852600097656
2023-01-22 11:36:49.160867: step: 710/466, loss: 0.2600739896297455
2023-01-22 11:36:49.877510: step: 712/466, loss: 0.6950864195823669
2023-01-22 11:36:50.533143: step: 714/466, loss: 0.06049566715955734
2023-01-22 11:36:51.245031: step: 716/466, loss: 0.07595871388912201
2023-01-22 11:36:51.910776: step: 718/466, loss: 0.15007273852825165
2023-01-22 11:36:52.538959: step: 720/466, loss: 0.019157638773322105
2023-01-22 11:36:53.192110: step: 722/466, loss: 0.03895778954029083
2023-01-22 11:36:53.806519: step: 724/466, loss: 0.048599064350128174
2023-01-22 11:36:54.467871: step: 726/466, loss: 0.0881853774189949
2023-01-22 11:36:55.148985: step: 728/466, loss: 0.05115104094147682
2023-01-22 11:36:55.794308: step: 730/466, loss: 0.12414344400167465
2023-01-22 11:36:56.475136: step: 732/466, loss: 0.0771954357624054
2023-01-22 11:36:57.131952: step: 734/466, loss: 0.07813917845487595
2023-01-22 11:36:57.834540: step: 736/466, loss: 0.09652063250541687
2023-01-22 11:36:58.472190: step: 738/466, loss: 0.041155245155096054
2023-01-22 11:36:59.100462: step: 740/466, loss: 0.10691135376691818
2023-01-22 11:36:59.732962: step: 742/466, loss: 0.10555917769670486
2023-01-22 11:37:00.407071: step: 744/466, loss: 0.04085260257124901
2023-01-22 11:37:01.009195: step: 746/466, loss: 0.04388800263404846
2023-01-22 11:37:01.708228: step: 748/466, loss: 0.068348228931427
2023-01-22 11:37:02.355956: step: 750/466, loss: 0.09691111743450165
2023-01-22 11:37:03.018112: step: 752/466, loss: 0.040126457810401917
2023-01-22 11:37:03.609790: step: 754/466, loss: 0.07099471241235733
2023-01-22 11:37:04.252982: step: 756/466, loss: 0.13388031721115112
2023-01-22 11:37:04.996449: step: 758/466, loss: 0.1699666678905487
2023-01-22 11:37:05.629826: step: 760/466, loss: 0.051609255373477936
2023-01-22 11:37:06.257928: step: 762/466, loss: 0.01984989456832409
2023-01-22 11:37:06.869811: step: 764/466, loss: 0.35947635769844055
2023-01-22 11:37:07.527490: step: 766/466, loss: 0.112865149974823
2023-01-22 11:37:08.162943: step: 768/466, loss: 0.04542209953069687
2023-01-22 11:37:08.837303: step: 770/466, loss: 0.07269290834665298
2023-01-22 11:37:09.458939: step: 772/466, loss: 0.11141180992126465
2023-01-22 11:37:10.116389: step: 774/466, loss: 0.04350070655345917
2023-01-22 11:37:10.731537: step: 776/466, loss: 0.09883411973714828
2023-01-22 11:37:11.359478: step: 778/466, loss: 0.0780629888176918
2023-01-22 11:37:12.071578: step: 780/466, loss: 0.05787418782711029
2023-01-22 11:37:12.790365: step: 782/466, loss: 0.5285390019416809
2023-01-22 11:37:13.413795: step: 784/466, loss: 0.04558119550347328
2023-01-22 11:37:14.100703: step: 786/466, loss: 0.20061707496643066
2023-01-22 11:37:14.770739: step: 788/466, loss: 0.11438582092523575
2023-01-22 11:37:15.502025: step: 790/466, loss: 0.01749095879495144
2023-01-22 11:37:16.159108: step: 792/466, loss: 0.11763517558574677
2023-01-22 11:37:16.859706: step: 794/466, loss: 0.09132517874240875
2023-01-22 11:37:17.458527: step: 796/466, loss: 0.08119666576385498
2023-01-22 11:37:18.163221: step: 798/466, loss: 0.07370875775814056
2023-01-22 11:37:18.744889: step: 800/466, loss: 0.14316020905971527
2023-01-22 11:37:19.446733: step: 802/466, loss: 0.34998998045921326
2023-01-22 11:37:20.130539: step: 804/466, loss: 0.1565779745578766
2023-01-22 11:37:20.755178: step: 806/466, loss: 0.045447055250406265
2023-01-22 11:37:21.427476: step: 808/466, loss: 0.03068552538752556
2023-01-22 11:37:22.026723: step: 810/466, loss: 0.06253843754529953
2023-01-22 11:37:22.685012: step: 812/466, loss: 0.354098379611969
2023-01-22 11:37:23.395522: step: 814/466, loss: 0.046952590346336365
2023-01-22 11:37:24.051718: step: 816/466, loss: 0.12536762654781342
2023-01-22 11:37:24.731417: step: 818/466, loss: 0.24964533746242523
2023-01-22 11:37:25.441695: step: 820/466, loss: 0.14116087555885315
2023-01-22 11:37:26.070554: step: 822/466, loss: 0.10435947775840759
2023-01-22 11:37:26.681007: step: 824/466, loss: 0.03001273237168789
2023-01-22 11:37:27.251982: step: 826/466, loss: 0.04351481422781944
2023-01-22 11:37:27.952293: step: 828/466, loss: 0.1352987289428711
2023-01-22 11:37:28.614365: step: 830/466, loss: 0.07766462117433548
2023-01-22 11:37:29.273715: step: 832/466, loss: 0.06786693632602692
2023-01-22 11:37:29.952055: step: 834/466, loss: 0.2304045706987381
2023-01-22 11:37:30.529918: step: 836/466, loss: 0.07369163632392883
2023-01-22 11:37:31.164245: step: 838/466, loss: 0.1992221474647522
2023-01-22 11:37:31.756695: step: 840/466, loss: 0.04259900376200676
2023-01-22 11:37:32.388853: step: 842/466, loss: 0.14957328140735626
2023-01-22 11:37:33.148493: step: 844/466, loss: 0.19445879757404327
2023-01-22 11:37:33.706382: step: 846/466, loss: 0.02491155080497265
2023-01-22 11:37:34.314378: step: 848/466, loss: 0.09199264645576477
2023-01-22 11:37:34.995994: step: 850/466, loss: 0.058149468153715134
2023-01-22 11:37:35.678337: step: 852/466, loss: 0.4377081096172333
2023-01-22 11:37:36.353045: step: 854/466, loss: 0.2140495330095291
2023-01-22 11:37:37.004497: step: 856/466, loss: 0.1769515573978424
2023-01-22 11:37:37.619667: step: 858/466, loss: 0.576966404914856
2023-01-22 11:37:38.254880: step: 860/466, loss: 0.14778044819831848
2023-01-22 11:37:38.873833: step: 862/466, loss: 0.10003938525915146
2023-01-22 11:37:39.474510: step: 864/466, loss: 0.2692798674106598
2023-01-22 11:37:40.056052: step: 866/466, loss: 0.0770498588681221
2023-01-22 11:37:40.694627: step: 868/466, loss: 0.4713871479034424
2023-01-22 11:37:41.330040: step: 870/466, loss: 2.7093138694763184
2023-01-22 11:37:41.933286: step: 872/466, loss: 0.07809975743293762
2023-01-22 11:37:42.530265: step: 874/466, loss: 0.08426910638809204
2023-01-22 11:37:43.167312: step: 876/466, loss: 0.08476223796606064
2023-01-22 11:37:43.786004: step: 878/466, loss: 0.05442659556865692
2023-01-22 11:37:44.413888: step: 880/466, loss: 0.02732786163687706
2023-01-22 11:37:45.052879: step: 882/466, loss: 0.07974054664373398
2023-01-22 11:37:45.739784: step: 884/466, loss: 0.2001144289970398
2023-01-22 11:37:46.354893: step: 886/466, loss: 0.015165749937295914
2023-01-22 11:37:46.996208: step: 888/466, loss: 0.05666099488735199
2023-01-22 11:37:47.614245: step: 890/466, loss: 0.13954006135463715
2023-01-22 11:37:48.222484: step: 892/466, loss: 0.21236880123615265
2023-01-22 11:37:48.917842: step: 894/466, loss: 0.06382488459348679
2023-01-22 11:37:49.559012: step: 896/466, loss: 0.12354041635990143
2023-01-22 11:37:50.176433: step: 898/466, loss: 0.09248878061771393
2023-01-22 11:37:50.827667: step: 900/466, loss: 0.08557818830013275
2023-01-22 11:37:51.461386: step: 902/466, loss: 0.06944967806339264
2023-01-22 11:37:52.206014: step: 904/466, loss: 0.25239336490631104
2023-01-22 11:37:52.828792: step: 906/466, loss: 0.046425044536590576
2023-01-22 11:37:53.457699: step: 908/466, loss: 0.2908068001270294
2023-01-22 11:37:54.090847: step: 910/466, loss: 0.2102268934249878
2023-01-22 11:37:54.705803: step: 912/466, loss: 0.1882074475288391
2023-01-22 11:37:55.343906: step: 914/466, loss: 0.14248530566692352
2023-01-22 11:37:56.036272: step: 916/466, loss: 0.5766107439994812
2023-01-22 11:37:56.744502: step: 918/466, loss: 0.07786186784505844
2023-01-22 11:37:57.387740: step: 920/466, loss: 0.08814342319965363
2023-01-22 11:37:58.032275: step: 922/466, loss: 0.11284119635820389
2023-01-22 11:37:58.710467: step: 924/466, loss: 0.3373393416404724
2023-01-22 11:37:59.286443: step: 926/466, loss: 0.012794055975973606
2023-01-22 11:37:59.929489: step: 928/466, loss: 0.019589319825172424
2023-01-22 11:38:00.645642: step: 930/466, loss: 0.017791852355003357
2023-01-22 11:38:01.259775: step: 932/466, loss: 0.037928689271211624
==================================================
Loss: 0.170
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3390854105571848, 'r': 0.3191392099361739, 'f1': 0.328810095085755}, 'combined': 0.24228112269476682, 'epoch': 16}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3146385015347374, 'r': 0.269203338858241, 'f1': 0.2901530150339796}, 'combined': 0.18168459819884705, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3183141394753679, 'r': 0.3146900695762176, 'f1': 0.31649173027989824}, 'combined': 0.23320443283781975, 'epoch': 16}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3288802784439474, 'r': 0.2873250086044594, 'f1': 0.3067014542714268}, 'combined': 0.1900685068724335, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28534991568296797, 'r': 0.32108633776091083, 'f1': 0.3021651785714286}, 'combined': 0.22264802631578948, 'epoch': 16}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3305276542697926, 'r': 0.2851025155274703, 'f1': 0.3061392059935749}, 'combined': 0.20308244357989624, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.28343023255813954, 'r': 0.3482142857142857, 'f1': 0.3125}, 'combined': 0.20833333333333331, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3055555555555556, 'r': 0.4782608695652174, 'f1': 0.3728813559322034}, 'combined': 0.1864406779661017, 'epoch': 16}
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': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:40:46.489232: step: 2/466, loss: 0.0552273727953434
2023-01-22 11:40:47.113825: step: 4/466, loss: 0.03032900206744671
2023-01-22 11:40:47.706879: step: 6/466, loss: 0.0997084379196167
2023-01-22 11:40:48.431029: step: 8/466, loss: 0.0820755660533905
2023-01-22 11:40:49.101623: step: 10/466, loss: 0.24237942695617676
2023-01-22 11:40:49.807698: step: 12/466, loss: 0.6239765882492065
2023-01-22 11:40:50.476011: step: 14/466, loss: 0.10396306961774826
2023-01-22 11:40:51.076558: step: 16/466, loss: 0.05649964511394501
2023-01-22 11:40:51.672944: step: 18/466, loss: 0.037888143211603165
2023-01-22 11:40:52.339230: step: 20/466, loss: 0.0896913930773735
2023-01-22 11:40:52.991078: step: 22/466, loss: 0.13036413490772247
2023-01-22 11:40:53.625512: step: 24/466, loss: 0.08791163563728333
2023-01-22 11:40:54.341837: step: 26/466, loss: 0.03862424194812775
2023-01-22 11:40:54.983751: step: 28/466, loss: 0.024081386625766754
2023-01-22 11:40:55.652359: step: 30/466, loss: 0.050525031983852386
2023-01-22 11:40:56.202214: step: 32/466, loss: 0.4528115689754486
2023-01-22 11:40:56.935314: step: 34/466, loss: 0.14363859593868256
2023-01-22 11:40:57.686150: step: 36/466, loss: 0.3207593858242035
2023-01-22 11:40:58.359296: step: 38/466, loss: 0.08752243220806122
2023-01-22 11:40:58.992439: step: 40/466, loss: 0.03985515609383583
2023-01-22 11:40:59.669030: step: 42/466, loss: 0.011252796277403831
2023-01-22 11:41:00.357632: step: 44/466, loss: 0.06112007051706314
2023-01-22 11:41:01.020750: step: 46/466, loss: 0.13862279057502747
2023-01-22 11:41:01.714867: step: 48/466, loss: 0.053066641092300415
2023-01-22 11:41:02.334371: step: 50/466, loss: 0.43007010221481323
2023-01-22 11:41:02.963547: step: 52/466, loss: 0.13144581019878387
2023-01-22 11:41:03.610905: step: 54/466, loss: 0.07558626681566238
2023-01-22 11:41:04.273756: step: 56/466, loss: 0.23427191376686096
2023-01-22 11:41:04.924560: step: 58/466, loss: 0.08729560673236847
2023-01-22 11:41:05.650288: step: 60/466, loss: 0.05417446047067642
2023-01-22 11:41:06.267662: step: 62/466, loss: 0.13129599392414093
2023-01-22 11:41:06.870422: step: 64/466, loss: 0.07614006847143173
2023-01-22 11:41:07.531377: step: 66/466, loss: 0.16889949142932892
2023-01-22 11:41:08.264258: step: 68/466, loss: 0.24261288344860077
2023-01-22 11:41:08.862118: step: 70/466, loss: 0.038321852684020996
2023-01-22 11:41:09.465171: step: 72/466, loss: 0.044602423906326294
2023-01-22 11:41:10.139772: step: 74/466, loss: 0.01967819780111313
2023-01-22 11:41:10.800253: step: 76/466, loss: 0.02813856489956379
2023-01-22 11:41:11.424682: step: 78/466, loss: 0.04209369421005249
2023-01-22 11:41:12.075549: step: 80/466, loss: 0.024040287360548973
2023-01-22 11:41:12.737631: step: 82/466, loss: 0.09991413354873657
2023-01-22 11:41:13.353335: step: 84/466, loss: 0.07372264564037323
2023-01-22 11:41:14.033487: step: 86/466, loss: 0.029386376962065697
2023-01-22 11:41:14.675515: step: 88/466, loss: 0.4689430594444275
2023-01-22 11:41:15.276951: step: 90/466, loss: 0.053494032472372055
2023-01-22 11:41:15.916961: step: 92/466, loss: 0.013472192920744419
2023-01-22 11:41:16.505723: step: 94/466, loss: 0.0707637220621109
2023-01-22 11:41:17.344884: step: 96/466, loss: 0.061210937798023224
2023-01-22 11:41:17.963642: step: 98/466, loss: 0.04127485305070877
2023-01-22 11:41:18.605579: step: 100/466, loss: 0.07582556456327438
2023-01-22 11:41:19.263128: step: 102/466, loss: 0.029441645368933678
2023-01-22 11:41:19.873782: step: 104/466, loss: 0.06904749572277069
2023-01-22 11:41:20.557042: step: 106/466, loss: 0.20207440853118896
2023-01-22 11:41:21.188424: step: 108/466, loss: 0.09177403151988983
2023-01-22 11:41:21.863132: step: 110/466, loss: 0.06599751859903336
2023-01-22 11:41:22.552437: step: 112/466, loss: 0.05812675133347511
2023-01-22 11:41:23.211735: step: 114/466, loss: 0.024880943819880486
2023-01-22 11:41:23.861140: step: 116/466, loss: 0.06967656314373016
2023-01-22 11:41:24.509601: step: 118/466, loss: 0.090497687458992
2023-01-22 11:41:25.216948: step: 120/466, loss: 0.12288883328437805
2023-01-22 11:41:25.856202: step: 122/466, loss: 0.12109700590372086
2023-01-22 11:41:26.467107: step: 124/466, loss: 0.07176961749792099
2023-01-22 11:41:27.115978: step: 126/466, loss: 0.12157073616981506
2023-01-22 11:41:27.756818: step: 128/466, loss: 0.015516109764575958
2023-01-22 11:41:28.367712: step: 130/466, loss: 0.02540462650358677
2023-01-22 11:41:28.984544: step: 132/466, loss: 0.007711430545896292
2023-01-22 11:41:29.603656: step: 134/466, loss: 0.07219022512435913
2023-01-22 11:41:30.264600: step: 136/466, loss: 0.106453076004982
2023-01-22 11:41:30.932903: step: 138/466, loss: 0.08396579325199127
2023-01-22 11:41:31.598759: step: 140/466, loss: 0.09653432667255402
2023-01-22 11:41:32.265553: step: 142/466, loss: 0.01763550192117691
2023-01-22 11:41:32.859663: step: 144/466, loss: 0.05190001428127289
2023-01-22 11:41:33.533412: step: 146/466, loss: 0.18059158325195312
2023-01-22 11:41:34.077108: step: 148/466, loss: 0.1982903927564621
2023-01-22 11:41:34.736339: step: 150/466, loss: 0.02685152180492878
2023-01-22 11:41:35.398353: step: 152/466, loss: 0.6735672354698181
2023-01-22 11:41:36.088921: step: 154/466, loss: 0.37587738037109375
2023-01-22 11:41:36.705640: step: 156/466, loss: 0.03102908469736576
2023-01-22 11:41:37.304580: step: 158/466, loss: 0.05640149489045143
2023-01-22 11:41:37.958997: step: 160/466, loss: 0.1766110360622406
2023-01-22 11:41:38.588329: step: 162/466, loss: 0.08404644578695297
2023-01-22 11:41:39.339641: step: 164/466, loss: 0.07357435673475266
2023-01-22 11:41:40.037480: step: 166/466, loss: 0.047804638743400574
2023-01-22 11:41:40.767502: step: 168/466, loss: 0.022309113293886185
2023-01-22 11:41:41.407215: step: 170/466, loss: 0.016016261652112007
2023-01-22 11:41:42.144374: step: 172/466, loss: 0.29546135663986206
2023-01-22 11:41:42.832448: step: 174/466, loss: 0.03904377669095993
2023-01-22 11:41:43.448688: step: 176/466, loss: 0.014926779083907604
2023-01-22 11:41:44.112011: step: 178/466, loss: 0.07515985518693924
2023-01-22 11:41:44.850567: step: 180/466, loss: 0.024379044771194458
2023-01-22 11:41:45.561863: step: 182/466, loss: 0.05204268544912338
2023-01-22 11:41:46.187869: step: 184/466, loss: 0.009238921105861664
2023-01-22 11:41:46.845753: step: 186/466, loss: 0.04101286828517914
2023-01-22 11:41:47.474983: step: 188/466, loss: 0.020316865295171738
2023-01-22 11:41:48.077400: step: 190/466, loss: 0.3560216724872589
2023-01-22 11:41:48.705270: step: 192/466, loss: 0.07066544890403748
2023-01-22 11:41:49.346755: step: 194/466, loss: 0.07007250934839249
2023-01-22 11:41:49.932527: step: 196/466, loss: 0.017157820984721184
2023-01-22 11:41:50.572404: step: 198/466, loss: 0.13828325271606445
2023-01-22 11:41:51.207269: step: 200/466, loss: 0.12338992208242416
2023-01-22 11:41:51.877603: step: 202/466, loss: 0.09103899449110031
2023-01-22 11:41:52.533269: step: 204/466, loss: 0.16109821200370789
2023-01-22 11:41:53.146006: step: 206/466, loss: 0.07542702555656433
2023-01-22 11:41:53.772786: step: 208/466, loss: 0.06226639449596405
2023-01-22 11:41:54.428623: step: 210/466, loss: 0.03805557265877724
2023-01-22 11:41:55.034513: step: 212/466, loss: 0.1261565387248993
2023-01-22 11:41:55.655058: step: 214/466, loss: 0.07257590442895889
2023-01-22 11:41:56.330288: step: 216/466, loss: 0.16820329427719116
2023-01-22 11:41:56.929201: step: 218/466, loss: 0.024088187143206596
2023-01-22 11:41:57.641749: step: 220/466, loss: 0.2577759325504303
2023-01-22 11:41:58.239221: step: 222/466, loss: 0.26061850786209106
2023-01-22 11:41:58.907417: step: 224/466, loss: 0.026563717052340508
2023-01-22 11:41:59.601568: step: 226/466, loss: 0.06560484319925308
2023-01-22 11:42:00.305339: step: 228/466, loss: 0.9863904714584351
2023-01-22 11:42:00.914575: step: 230/466, loss: 0.029565483331680298
2023-01-22 11:42:01.590272: step: 232/466, loss: 0.10892686992883682
2023-01-22 11:42:02.241022: step: 234/466, loss: 0.06505019962787628
2023-01-22 11:42:02.882486: step: 236/466, loss: 0.019741952419281006
2023-01-22 11:42:03.498791: step: 238/466, loss: 0.029368475079536438
2023-01-22 11:42:04.216100: step: 240/466, loss: 0.03153730928897858
2023-01-22 11:42:04.863374: step: 242/466, loss: 0.3902517855167389
2023-01-22 11:42:05.491395: step: 244/466, loss: 0.03810492530465126
2023-01-22 11:42:06.129435: step: 246/466, loss: 0.06299792230129242
2023-01-22 11:42:06.812684: step: 248/466, loss: 0.10881893336772919
2023-01-22 11:42:07.403143: step: 250/466, loss: 0.20353665947914124
2023-01-22 11:42:08.048024: step: 252/466, loss: 0.04542895406484604
2023-01-22 11:42:08.795801: step: 254/466, loss: 0.04115154221653938
2023-01-22 11:42:09.438223: step: 256/466, loss: 0.034337591379880905
2023-01-22 11:42:10.070529: step: 258/466, loss: 0.20907801389694214
2023-01-22 11:42:10.697681: step: 260/466, loss: 0.049190454185009
2023-01-22 11:42:11.383096: step: 262/466, loss: 0.091862253844738
2023-01-22 11:42:12.120873: step: 264/466, loss: 5.106974124908447
2023-01-22 11:42:12.792370: step: 266/466, loss: 0.07528732717037201
2023-01-22 11:42:13.419253: step: 268/466, loss: 0.06413239240646362
2023-01-22 11:42:14.088316: step: 270/466, loss: 1.6005995273590088
2023-01-22 11:42:14.696722: step: 272/466, loss: 0.06114184856414795
2023-01-22 11:42:15.260042: step: 274/466, loss: 0.10123945027589798
2023-01-22 11:42:15.903709: step: 276/466, loss: 0.25699582695961
2023-01-22 11:42:16.528059: step: 278/466, loss: 0.08306179195642471
2023-01-22 11:42:17.163355: step: 280/466, loss: 0.03990897908806801
2023-01-22 11:42:17.790115: step: 282/466, loss: 0.03646804392337799
2023-01-22 11:42:18.442142: step: 284/466, loss: 0.10514121502637863
2023-01-22 11:42:19.081427: step: 286/466, loss: 0.005694656167179346
2023-01-22 11:42:19.847457: step: 288/466, loss: 0.026155471801757812
2023-01-22 11:42:20.448649: step: 290/466, loss: 0.13834121823310852
2023-01-22 11:42:21.093455: step: 292/466, loss: 0.02711542136967182
2023-01-22 11:42:21.732787: step: 294/466, loss: 0.05465665087103844
2023-01-22 11:42:22.360309: step: 296/466, loss: 0.049648333340883255
2023-01-22 11:42:22.979667: step: 298/466, loss: 0.0783451497554779
2023-01-22 11:42:23.580209: step: 300/466, loss: 0.049439627677202225
2023-01-22 11:42:24.279496: step: 302/466, loss: 0.15175487101078033
2023-01-22 11:42:24.903680: step: 304/466, loss: 0.06957145035266876
2023-01-22 11:42:25.552407: step: 306/466, loss: 0.06854043900966644
2023-01-22 11:42:26.191782: step: 308/466, loss: 0.12385958433151245
2023-01-22 11:42:26.876055: step: 310/466, loss: 0.020379463210701942
2023-01-22 11:42:27.532575: step: 312/466, loss: 0.028115959838032722
2023-01-22 11:42:28.249907: step: 314/466, loss: 0.057811226695775986
2023-01-22 11:42:28.851461: step: 316/466, loss: 0.02322530187666416
2023-01-22 11:42:29.491092: step: 318/466, loss: 0.0995943695306778
2023-01-22 11:42:30.100712: step: 320/466, loss: 0.08957862854003906
2023-01-22 11:42:30.763392: step: 322/466, loss: 0.2572743594646454
2023-01-22 11:42:31.412987: step: 324/466, loss: 0.3369157314300537
2023-01-22 11:42:32.056750: step: 326/466, loss: 0.013277021236717701
2023-01-22 11:42:32.732072: step: 328/466, loss: 0.06267574429512024
2023-01-22 11:42:33.418874: step: 330/466, loss: 0.07259294390678406
2023-01-22 11:42:34.141668: step: 332/466, loss: 0.04938018321990967
2023-01-22 11:42:34.815083: step: 334/466, loss: 0.050406381487846375
2023-01-22 11:42:35.446587: step: 336/466, loss: 0.08300729840993881
2023-01-22 11:42:36.173566: step: 338/466, loss: 0.03568604961037636
2023-01-22 11:42:36.754316: step: 340/466, loss: 0.03801991045475006
2023-01-22 11:42:37.357919: step: 342/466, loss: 0.09266859292984009
2023-01-22 11:42:38.049745: step: 344/466, loss: 0.1025686264038086
2023-01-22 11:42:38.686174: step: 346/466, loss: 0.03731289505958557
2023-01-22 11:42:39.410409: step: 348/466, loss: 0.1353796124458313
2023-01-22 11:42:40.040318: step: 350/466, loss: 0.04047910496592522
2023-01-22 11:42:40.662733: step: 352/466, loss: 0.10990084707736969
2023-01-22 11:42:41.341562: step: 354/466, loss: 0.15826545655727386
2023-01-22 11:42:41.977455: step: 356/466, loss: 0.10664297640323639
2023-01-22 11:42:42.702023: step: 358/466, loss: 0.17812858521938324
2023-01-22 11:42:43.312730: step: 360/466, loss: 0.06930878013372421
2023-01-22 11:42:43.946347: step: 362/466, loss: 0.06571146845817566
2023-01-22 11:42:44.492263: step: 364/466, loss: 0.03256172314286232
2023-01-22 11:42:45.129810: step: 366/466, loss: 0.12351781129837036
2023-01-22 11:42:45.763717: step: 368/466, loss: 0.2548113167285919
2023-01-22 11:42:46.401506: step: 370/466, loss: 0.1263582408428192
2023-01-22 11:42:46.993963: step: 372/466, loss: 0.07582645118236542
2023-01-22 11:42:47.738292: step: 374/466, loss: 0.05496755614876747
2023-01-22 11:42:48.358911: step: 376/466, loss: 0.08954503387212753
2023-01-22 11:42:48.996243: step: 378/466, loss: 0.12195761501789093
2023-01-22 11:42:49.646048: step: 380/466, loss: 0.39381787180900574
2023-01-22 11:42:50.324609: step: 382/466, loss: 0.16818027198314667
2023-01-22 11:42:50.946932: step: 384/466, loss: 0.04547747224569321
2023-01-22 11:42:51.540580: step: 386/466, loss: 0.12755371630191803
2023-01-22 11:42:52.207152: step: 388/466, loss: 0.11845839768648148
2023-01-22 11:42:52.802092: step: 390/466, loss: 0.47920721769332886
2023-01-22 11:42:53.452713: step: 392/466, loss: 0.08540887385606766
2023-01-22 11:42:54.082241: step: 394/466, loss: 0.19534656405448914
2023-01-22 11:42:54.742867: step: 396/466, loss: 0.1510317176580429
2023-01-22 11:42:55.400828: step: 398/466, loss: 0.09187552332878113
2023-01-22 11:42:56.022816: step: 400/466, loss: 0.06261609494686127
2023-01-22 11:42:56.693592: step: 402/466, loss: 0.03584316000342369
2023-01-22 11:42:57.348504: step: 404/466, loss: 0.14746913313865662
2023-01-22 11:42:58.012111: step: 406/466, loss: 0.14273861050605774
2023-01-22 11:42:58.620288: step: 408/466, loss: 0.06443028897047043
2023-01-22 11:42:59.319930: step: 410/466, loss: 0.044804513454437256
2023-01-22 11:42:59.998218: step: 412/466, loss: 0.2150534689426422
2023-01-22 11:43:00.592921: step: 414/466, loss: 0.01897166483104229
2023-01-22 11:43:01.206601: step: 416/466, loss: 0.028580371290445328
2023-01-22 11:43:01.922455: step: 418/466, loss: 0.18393245339393616
2023-01-22 11:43:02.589191: step: 420/466, loss: 0.19016799330711365
2023-01-22 11:43:03.183497: step: 422/466, loss: 0.07028649002313614
2023-01-22 11:43:03.776842: step: 424/466, loss: 0.2922304570674896
2023-01-22 11:43:04.509009: step: 426/466, loss: 0.042799223214387894
2023-01-22 11:43:05.146806: step: 428/466, loss: 0.04283499717712402
2023-01-22 11:43:05.817005: step: 430/466, loss: 0.02132521942257881
2023-01-22 11:43:06.555707: step: 432/466, loss: 0.0802520364522934
2023-01-22 11:43:07.213097: step: 434/466, loss: 0.15386797487735748
2023-01-22 11:43:07.900558: step: 436/466, loss: 0.043837256729602814
2023-01-22 11:43:08.548138: step: 438/466, loss: 0.06992541253566742
2023-01-22 11:43:09.176588: step: 440/466, loss: 0.05010535567998886
2023-01-22 11:43:09.770720: step: 442/466, loss: 0.09200336784124374
2023-01-22 11:43:10.390064: step: 444/466, loss: 0.03776991367340088
2023-01-22 11:43:11.055717: step: 446/466, loss: 0.006169892381876707
2023-01-22 11:43:11.734651: step: 448/466, loss: 0.060634829103946686
2023-01-22 11:43:12.481083: step: 450/466, loss: 0.031265951693058014
2023-01-22 11:43:13.146914: step: 452/466, loss: 0.021036386489868164
2023-01-22 11:43:13.780469: step: 454/466, loss: 0.023153940215706825
2023-01-22 11:43:14.442904: step: 456/466, loss: 0.10088212043046951
2023-01-22 11:43:15.113946: step: 458/466, loss: 0.036887239664793015
2023-01-22 11:43:15.785505: step: 460/466, loss: 0.05326121300458908
2023-01-22 11:43:16.368620: step: 462/466, loss: 0.02424703910946846
2023-01-22 11:43:16.988323: step: 464/466, loss: 0.4780868589878082
2023-01-22 11:43:17.737903: step: 466/466, loss: 0.052299145609140396
2023-01-22 11:43:18.396017: step: 468/466, loss: 2.543187141418457
2023-01-22 11:43:18.972342: step: 470/466, loss: 0.15826913714408875
2023-01-22 11:43:19.572816: step: 472/466, loss: 0.027156120166182518
2023-01-22 11:43:20.213818: step: 474/466, loss: 0.018557526171207428
2023-01-22 11:43:20.836957: step: 476/466, loss: 0.19445599615573883
2023-01-22 11:43:21.548762: step: 478/466, loss: 0.09860493242740631
2023-01-22 11:43:22.231431: step: 480/466, loss: 0.04384823516011238
2023-01-22 11:43:22.893298: step: 482/466, loss: 0.04084863141179085
2023-01-22 11:43:23.562884: step: 484/466, loss: 0.34274789690971375
2023-01-22 11:43:24.175974: step: 486/466, loss: 0.0950087234377861
2023-01-22 11:43:24.842124: step: 488/466, loss: 0.10143581032752991
2023-01-22 11:43:25.501598: step: 490/466, loss: 0.07003463804721832
2023-01-22 11:43:26.147384: step: 492/466, loss: 0.08866386115550995
2023-01-22 11:43:26.817733: step: 494/466, loss: 0.06682950258255005
2023-01-22 11:43:27.502294: step: 496/466, loss: 0.11515610665082932
2023-01-22 11:43:28.155932: step: 498/466, loss: 0.758357048034668
2023-01-22 11:43:28.796418: step: 500/466, loss: 0.1596226990222931
2023-01-22 11:43:29.511945: step: 502/466, loss: 0.17213603854179382
2023-01-22 11:43:30.139977: step: 504/466, loss: 0.029680604115128517
2023-01-22 11:43:30.826568: step: 506/466, loss: 0.4964957535266876
2023-01-22 11:43:31.499600: step: 508/466, loss: 0.027684777975082397
2023-01-22 11:43:32.139548: step: 510/466, loss: 0.09656545519828796
2023-01-22 11:43:32.812201: step: 512/466, loss: 0.058670736849308014
2023-01-22 11:43:33.475974: step: 514/466, loss: 0.046255968511104584
2023-01-22 11:43:34.063898: step: 516/466, loss: 0.0634763315320015
2023-01-22 11:43:34.754801: step: 518/466, loss: 0.06766517460346222
2023-01-22 11:43:35.404658: step: 520/466, loss: 0.11908484250307083
2023-01-22 11:43:36.022508: step: 522/466, loss: 0.046817272901535034
2023-01-22 11:43:36.579633: step: 524/466, loss: 0.05099989473819733
2023-01-22 11:43:37.240850: step: 526/466, loss: 0.093465656042099
2023-01-22 11:43:37.846275: step: 528/466, loss: 0.07280781865119934
2023-01-22 11:43:38.452377: step: 530/466, loss: 0.1566302329301834
2023-01-22 11:43:39.124247: step: 532/466, loss: 0.027845079079270363
2023-01-22 11:43:39.790662: step: 534/466, loss: 0.16751457750797272
2023-01-22 11:43:40.413899: step: 536/466, loss: 0.105364590883255
2023-01-22 11:43:41.094676: step: 538/466, loss: 0.022764407098293304
2023-01-22 11:43:41.743452: step: 540/466, loss: 0.016718149185180664
2023-01-22 11:43:42.415530: step: 542/466, loss: 0.01735505647957325
2023-01-22 11:43:43.087554: step: 544/466, loss: 0.0612952895462513
2023-01-22 11:43:43.852612: step: 546/466, loss: 0.022740516811609268
2023-01-22 11:43:44.509210: step: 548/466, loss: 0.07891835272312164
2023-01-22 11:43:45.158644: step: 550/466, loss: 0.03998878598213196
2023-01-22 11:43:45.797670: step: 552/466, loss: 0.07046996057033539
2023-01-22 11:43:46.396857: step: 554/466, loss: 0.09587815403938293
2023-01-22 11:43:47.038497: step: 556/466, loss: 0.10038372874259949
2023-01-22 11:43:47.620883: step: 558/466, loss: 0.08871347457170486
2023-01-22 11:43:48.307701: step: 560/466, loss: 0.5055253505706787
2023-01-22 11:43:48.938209: step: 562/466, loss: 0.512459933757782
2023-01-22 11:43:49.507833: step: 564/466, loss: 0.16453763842582703
2023-01-22 11:43:50.188638: step: 566/466, loss: 0.18959884345531464
2023-01-22 11:43:50.886674: step: 568/466, loss: 0.025106430053710938
2023-01-22 11:43:51.547924: step: 570/466, loss: 0.03585100546479225
2023-01-22 11:43:52.220560: step: 572/466, loss: 1.0049701929092407
2023-01-22 11:43:52.889286: step: 574/466, loss: 0.09710993617773056
2023-01-22 11:43:53.563939: step: 576/466, loss: 0.09198971837759018
2023-01-22 11:43:54.244053: step: 578/466, loss: 0.22630296647548676
2023-01-22 11:43:54.975147: step: 580/466, loss: 0.09247155487537384
2023-01-22 11:43:55.596278: step: 582/466, loss: 0.33415427803993225
2023-01-22 11:43:56.233619: step: 584/466, loss: 0.22004912793636322
2023-01-22 11:43:56.931653: step: 586/466, loss: 0.04450481757521629
2023-01-22 11:43:57.603418: step: 588/466, loss: 0.06292744725942612
2023-01-22 11:43:58.236061: step: 590/466, loss: 0.1736353039741516
2023-01-22 11:43:58.827280: step: 592/466, loss: 0.025799855589866638
2023-01-22 11:43:59.488312: step: 594/466, loss: 0.1439337283372879
2023-01-22 11:44:00.116087: step: 596/466, loss: 0.012740693055093288
2023-01-22 11:44:00.759303: step: 598/466, loss: 0.02078421227633953
2023-01-22 11:44:01.400819: step: 600/466, loss: 0.07006371021270752
2023-01-22 11:44:02.168359: step: 602/466, loss: 0.146609827876091
2023-01-22 11:44:02.823257: step: 604/466, loss: 0.09524525701999664
2023-01-22 11:44:03.513100: step: 606/466, loss: 0.09198599308729172
2023-01-22 11:44:04.153029: step: 608/466, loss: 1.013004183769226
2023-01-22 11:44:04.799781: step: 610/466, loss: 0.02928597293794155
2023-01-22 11:44:05.451169: step: 612/466, loss: 0.06546822190284729
2023-01-22 11:44:06.092386: step: 614/466, loss: 0.16060662269592285
2023-01-22 11:44:06.763945: step: 616/466, loss: 0.13668808341026306
2023-01-22 11:44:07.453965: step: 618/466, loss: 0.04572014883160591
2023-01-22 11:44:08.174227: step: 620/466, loss: 0.09879611432552338
2023-01-22 11:44:08.841309: step: 622/466, loss: 0.0328047052025795
2023-01-22 11:44:09.569756: step: 624/466, loss: 0.14962564408779144
2023-01-22 11:44:10.247287: step: 626/466, loss: 0.5662903189659119
2023-01-22 11:44:10.925202: step: 628/466, loss: 0.0919908806681633
2023-01-22 11:44:11.620906: step: 630/466, loss: 0.051337748765945435
2023-01-22 11:44:12.247269: step: 632/466, loss: 0.0314980186522007
2023-01-22 11:44:12.882676: step: 634/466, loss: 0.40809789299964905
2023-01-22 11:44:13.506740: step: 636/466, loss: 0.04629041627049446
2023-01-22 11:44:14.161700: step: 638/466, loss: 0.12016425281763077
2023-01-22 11:44:14.894775: step: 640/466, loss: 0.025917401537299156
2023-01-22 11:44:15.597885: step: 642/466, loss: 0.24926666915416718
2023-01-22 11:44:16.304594: step: 644/466, loss: 0.11441686749458313
2023-01-22 11:44:16.889377: step: 646/466, loss: 0.09986777603626251
2023-01-22 11:44:17.493152: step: 648/466, loss: 0.01881973072886467
2023-01-22 11:44:18.114989: step: 650/466, loss: 0.029893090948462486
2023-01-22 11:44:18.783194: step: 652/466, loss: 0.041874662041664124
2023-01-22 11:44:19.489442: step: 654/466, loss: 0.05112221837043762
2023-01-22 11:44:20.162773: step: 656/466, loss: 0.06019367277622223
2023-01-22 11:44:20.745866: step: 658/466, loss: 0.06566891819238663
2023-01-22 11:44:21.369764: step: 660/466, loss: 0.3472343683242798
2023-01-22 11:44:21.995516: step: 662/466, loss: 0.08255734294652939
2023-01-22 11:44:22.670029: step: 664/466, loss: 0.03303737938404083
2023-01-22 11:44:23.353751: step: 666/466, loss: 0.33435532450675964
2023-01-22 11:44:23.960518: step: 668/466, loss: 0.04343652352690697
2023-01-22 11:44:24.614781: step: 670/466, loss: 0.5589689612388611
2023-01-22 11:44:25.272759: step: 672/466, loss: 0.1640758216381073
2023-01-22 11:44:26.015131: step: 674/466, loss: 0.09021838754415512
2023-01-22 11:44:26.672205: step: 676/466, loss: 0.06118958070874214
2023-01-22 11:44:27.356293: step: 678/466, loss: 0.3956887125968933
2023-01-22 11:44:28.016220: step: 680/466, loss: 0.026741499081254005
2023-01-22 11:44:28.646981: step: 682/466, loss: 0.17171710729599
2023-01-22 11:44:29.281098: step: 684/466, loss: 0.3079081177711487
2023-01-22 11:44:29.901498: step: 686/466, loss: 0.10954593867063522
2023-01-22 11:44:30.535082: step: 688/466, loss: 0.6995450258255005
2023-01-22 11:44:31.203269: step: 690/466, loss: 0.043250422924757004
2023-01-22 11:44:31.845129: step: 692/466, loss: 0.09776352345943451
2023-01-22 11:44:32.493279: step: 694/466, loss: 0.3069460690021515
2023-01-22 11:44:33.153635: step: 696/466, loss: 0.013332807458937168
2023-01-22 11:44:33.807390: step: 698/466, loss: 0.23258814215660095
2023-01-22 11:44:34.458883: step: 700/466, loss: 0.05831009894609451
2023-01-22 11:44:35.059410: step: 702/466, loss: 0.06570618599653244
2023-01-22 11:44:35.701396: step: 704/466, loss: 0.04204113036394119
2023-01-22 11:44:36.371513: step: 706/466, loss: 0.03426389768719673
2023-01-22 11:44:36.984870: step: 708/466, loss: 0.0980169028043747
2023-01-22 11:44:37.625817: step: 710/466, loss: 0.15948888659477234
2023-01-22 11:44:38.337102: step: 712/466, loss: 0.056519124656915665
2023-01-22 11:44:39.020244: step: 714/466, loss: 0.06070170924067497
2023-01-22 11:44:39.657805: step: 716/466, loss: 0.11161601543426514
2023-01-22 11:44:40.327960: step: 718/466, loss: 0.23625513911247253
2023-01-22 11:44:40.965182: step: 720/466, loss: 0.012628679163753986
2023-01-22 11:44:41.555139: step: 722/466, loss: 0.12756291031837463
2023-01-22 11:44:42.265641: step: 724/466, loss: 0.1475050300359726
2023-01-22 11:44:42.905164: step: 726/466, loss: 0.04249989986419678
2023-01-22 11:44:43.613074: step: 728/466, loss: 0.49722063541412354
2023-01-22 11:44:44.345853: step: 730/466, loss: 0.04375768452882767
2023-01-22 11:44:45.025993: step: 732/466, loss: 0.07949644327163696
2023-01-22 11:44:45.623226: step: 734/466, loss: 0.05384787917137146
2023-01-22 11:44:46.303824: step: 736/466, loss: 0.15113519132137299
2023-01-22 11:44:46.984270: step: 738/466, loss: 0.10131586343050003
2023-01-22 11:44:47.570521: step: 740/466, loss: 0.05296603962779045
2023-01-22 11:44:48.283042: step: 742/466, loss: 0.039442624896764755
2023-01-22 11:44:48.888328: step: 744/466, loss: 0.1297570765018463
2023-01-22 11:44:49.620856: step: 746/466, loss: 0.17817160487174988
2023-01-22 11:44:50.234373: step: 748/466, loss: 0.025621848180890083
2023-01-22 11:44:50.900838: step: 750/466, loss: 1.840409517288208
2023-01-22 11:44:51.514263: step: 752/466, loss: 3.542585849761963
2023-01-22 11:44:52.160101: step: 754/466, loss: 0.08421312272548676
2023-01-22 11:44:52.884909: step: 756/466, loss: 0.14330342411994934
2023-01-22 11:44:53.518305: step: 758/466, loss: 0.09391725063323975
2023-01-22 11:44:54.115958: step: 760/466, loss: 0.1429196298122406
2023-01-22 11:44:54.808040: step: 762/466, loss: 0.20400117337703705
2023-01-22 11:44:55.593629: step: 764/466, loss: 0.06184087693691254
2023-01-22 11:44:56.244004: step: 766/466, loss: 0.19144916534423828
2023-01-22 11:44:56.885280: step: 768/466, loss: 0.7109355330467224
2023-01-22 11:44:57.507381: step: 770/466, loss: 0.03441312536597252
2023-01-22 11:44:58.164889: step: 772/466, loss: 0.06554859131574631
2023-01-22 11:44:58.768030: step: 774/466, loss: 0.12567520141601562
2023-01-22 11:44:59.423404: step: 776/466, loss: 0.14205007255077362
2023-01-22 11:44:59.955712: step: 778/466, loss: 0.009420069865882397
2023-01-22 11:45:00.562134: step: 780/466, loss: 0.10395492613315582
2023-01-22 11:45:01.195949: step: 782/466, loss: 1.3356351852416992
2023-01-22 11:45:01.791488: step: 784/466, loss: 0.06981461495161057
2023-01-22 11:45:02.405320: step: 786/466, loss: 0.04637700691819191
2023-01-22 11:45:03.031741: step: 788/466, loss: 0.0754745677113533
2023-01-22 11:45:03.631934: step: 790/466, loss: 0.03780405595898628
2023-01-22 11:45:04.318773: step: 792/466, loss: 0.04822218418121338
2023-01-22 11:45:05.004452: step: 794/466, loss: 0.022367283701896667
2023-01-22 11:45:05.646957: step: 796/466, loss: 0.2079140990972519
2023-01-22 11:45:06.321610: step: 798/466, loss: 1.3244308233261108
2023-01-22 11:45:07.043268: step: 800/466, loss: 0.34323838353157043
2023-01-22 11:45:07.700553: step: 802/466, loss: 0.14083780348300934
2023-01-22 11:45:08.373402: step: 804/466, loss: 0.22988341748714447
2023-01-22 11:45:09.027615: step: 806/466, loss: 0.04329225793480873
2023-01-22 11:45:09.687636: step: 808/466, loss: 0.032999325543642044
2023-01-22 11:45:10.320986: step: 810/466, loss: 5.826337814331055
2023-01-22 11:45:10.938981: step: 812/466, loss: 0.09369110316038132
2023-01-22 11:45:11.576787: step: 814/466, loss: 0.025686241686344147
2023-01-22 11:45:12.206253: step: 816/466, loss: 0.03150394186377525
2023-01-22 11:45:12.850178: step: 818/466, loss: 0.01394703146070242
2023-01-22 11:45:13.436640: step: 820/466, loss: 0.10388254374265671
2023-01-22 11:45:14.130138: step: 822/466, loss: 0.05112575739622116
2023-01-22 11:45:14.715878: step: 824/466, loss: 0.1600683033466339
2023-01-22 11:45:15.408529: step: 826/466, loss: 0.17425380647182465
2023-01-22 11:45:16.025115: step: 828/466, loss: 0.021439744159579277
2023-01-22 11:45:16.675118: step: 830/466, loss: 0.0466870479285717
2023-01-22 11:45:17.339550: step: 832/466, loss: 0.10297922044992447
2023-01-22 11:45:18.078121: step: 834/466, loss: 0.1491861492395401
2023-01-22 11:45:18.694875: step: 836/466, loss: 0.0686078816652298
2023-01-22 11:45:19.298356: step: 838/466, loss: 0.08716202527284622
2023-01-22 11:45:19.944442: step: 840/466, loss: 0.20605508983135223
2023-01-22 11:45:20.632756: step: 842/466, loss: 0.0744304209947586
2023-01-22 11:45:21.345024: step: 844/466, loss: 0.049539387226104736
2023-01-22 11:45:21.965406: step: 846/466, loss: 0.12177298218011856
2023-01-22 11:45:22.545446: step: 848/466, loss: 0.07692743092775345
2023-01-22 11:45:23.210661: step: 850/466, loss: 0.1394100934267044
2023-01-22 11:45:23.849626: step: 852/466, loss: 0.1861666738986969
2023-01-22 11:45:24.446192: step: 854/466, loss: 0.1190071627497673
2023-01-22 11:45:25.036764: step: 856/466, loss: 0.13761764764785767
2023-01-22 11:45:25.663947: step: 858/466, loss: 0.09148634970188141
2023-01-22 11:45:26.345360: step: 860/466, loss: 0.05858558416366577
2023-01-22 11:45:26.991901: step: 862/466, loss: 0.19387279450893402
2023-01-22 11:45:27.546551: step: 864/466, loss: 0.06237471103668213
2023-01-22 11:45:28.168241: step: 866/466, loss: 0.06779488176107407
2023-01-22 11:45:28.760271: step: 868/466, loss: 0.0751604288816452
2023-01-22 11:45:29.423477: step: 870/466, loss: 0.07606161385774612
2023-01-22 11:45:30.015458: step: 872/466, loss: 0.029564842581748962
2023-01-22 11:45:30.653994: step: 874/466, loss: 0.03874971345067024
2023-01-22 11:45:31.353311: step: 876/466, loss: 0.10743102431297302
2023-01-22 11:45:32.047271: step: 878/466, loss: 0.1099063903093338
2023-01-22 11:45:32.720319: step: 880/466, loss: 0.04139665514230728
2023-01-22 11:45:33.335022: step: 882/466, loss: 0.14583469927310944
2023-01-22 11:45:33.973772: step: 884/466, loss: 0.08397570252418518
2023-01-22 11:45:34.560504: step: 886/466, loss: 0.07745757699012756
2023-01-22 11:45:35.239473: step: 888/466, loss: 0.1580204963684082
2023-01-22 11:45:35.982502: step: 890/466, loss: 0.1032017320394516
2023-01-22 11:45:36.648829: step: 892/466, loss: 0.06455115973949432
2023-01-22 11:45:37.320335: step: 894/466, loss: 0.08590283989906311
2023-01-22 11:45:37.954799: step: 896/466, loss: 0.19114746153354645
2023-01-22 11:45:38.575042: step: 898/466, loss: 0.3613285720348358
2023-01-22 11:45:39.267150: step: 900/466, loss: 0.2982882857322693
2023-01-22 11:45:39.870076: step: 902/466, loss: 0.014200277626514435
2023-01-22 11:45:40.507384: step: 904/466, loss: 0.058966249227523804
2023-01-22 11:45:41.145716: step: 906/466, loss: 0.09376897662878036
2023-01-22 11:45:41.706767: step: 908/466, loss: 0.29971009492874146
2023-01-22 11:45:42.425300: step: 910/466, loss: 0.07468503713607788
2023-01-22 11:45:43.110154: step: 912/466, loss: 0.08336369693279266
2023-01-22 11:45:43.782430: step: 914/466, loss: 0.04851008951663971
2023-01-22 11:45:44.433419: step: 916/466, loss: 0.19046419858932495
2023-01-22 11:45:45.029917: step: 918/466, loss: 0.022284705191850662
2023-01-22 11:45:45.705525: step: 920/466, loss: 0.05849120393395424
2023-01-22 11:45:46.405652: step: 922/466, loss: 0.0836711972951889
2023-01-22 11:45:47.078918: step: 924/466, loss: 0.13933195173740387
2023-01-22 11:45:47.654012: step: 926/466, loss: 0.11811508238315582
2023-01-22 11:45:48.345115: step: 928/466, loss: 0.09238840639591217
2023-01-22 11:45:49.013534: step: 930/466, loss: 0.49136781692504883
2023-01-22 11:45:49.599366: step: 932/466, loss: 0.04988570883870125
==================================================
Loss: 0.167
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3343271072796935, 'r': 0.33115512333965846, 'f1': 0.33273355576739755}, 'combined': 0.24517209372334556, 'epoch': 17}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3384184213131582, 'r': 0.2820153510942985, 'f1': 0.3076531102846893}, 'combined': 0.19264260176704845, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3126403281519862, 'r': 0.34348908918406074, 'f1': 0.3273395117540687}, 'combined': 0.2411975349766822, 'epoch': 17}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34221196818024896, 'r': 0.2953082538760129, 'f1': 0.3170347081786043}, 'combined': 0.19647221351913505, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2806988188976378, 'r': 0.3382234345351044, 'f1': 0.30678786574870914}, 'combined': 0.22605421686746988, 'epoch': 17}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.34675791352260693, 'r': 0.2923031509297066, 'f1': 0.3172104713321399}, 'combined': 0.21042674830943936, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2611111111111111, 'r': 0.3357142857142857, 'f1': 0.29375}, 'combined': 0.19583333333333333, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3142857142857143, 'r': 0.4782608695652174, 'f1': 0.3793103448275862}, 'combined': 0.1896551724137931, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25, 'r': 0.23275862068965517, 'f1': 0.24107142857142858}, 'combined': 0.1607142857142857, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:48:36.835510: step: 2/466, loss: 0.030299948528409004
2023-01-22 11:48:37.482549: step: 4/466, loss: 0.18529173731803894
2023-01-22 11:48:38.142410: step: 6/466, loss: 0.23373645544052124
2023-01-22 11:48:38.790452: step: 8/466, loss: 0.3838213384151459
2023-01-22 11:48:39.421616: step: 10/466, loss: 0.020283006131649017
2023-01-22 11:48:40.122048: step: 12/466, loss: 0.03348774090409279
2023-01-22 11:48:40.747661: step: 14/466, loss: 0.05698230862617493
2023-01-22 11:48:41.364939: step: 16/466, loss: 0.08389558643102646
2023-01-22 11:48:42.081439: step: 18/466, loss: 0.0727858766913414
2023-01-22 11:48:42.682048: step: 20/466, loss: 0.03135587275028229
2023-01-22 11:48:43.314875: step: 22/466, loss: 0.07733876258134842
2023-01-22 11:48:43.941581: step: 24/466, loss: 0.0626508891582489
2023-01-22 11:48:44.596602: step: 26/466, loss: 0.11715943366289139
2023-01-22 11:48:45.216588: step: 28/466, loss: 0.06282183527946472
2023-01-22 11:48:45.951952: step: 30/466, loss: 0.06618069112300873
2023-01-22 11:48:46.599270: step: 32/466, loss: 0.36386919021606445
2023-01-22 11:48:47.267790: step: 34/466, loss: 0.023268923163414
2023-01-22 11:48:47.889725: step: 36/466, loss: 0.026226868852972984
2023-01-22 11:48:48.601513: step: 38/466, loss: 0.1648685336112976
2023-01-22 11:48:49.222107: step: 40/466, loss: 0.09379521757364273
2023-01-22 11:48:49.839353: step: 42/466, loss: 0.009535979479551315
2023-01-22 11:48:50.478444: step: 44/466, loss: 0.022059675306081772
2023-01-22 11:48:51.092212: step: 46/466, loss: 0.04059113934636116
2023-01-22 11:48:51.702748: step: 48/466, loss: 0.017242122441530228
2023-01-22 11:48:52.330119: step: 50/466, loss: 0.053310081362724304
2023-01-22 11:48:52.957756: step: 52/466, loss: 0.029806554317474365
2023-01-22 11:48:53.609320: step: 54/466, loss: 0.3543507158756256
2023-01-22 11:48:54.254466: step: 56/466, loss: 0.014609129168093204
2023-01-22 11:48:54.853053: step: 58/466, loss: 0.03231660649180412
2023-01-22 11:48:55.499781: step: 60/466, loss: 0.04060859978199005
2023-01-22 11:48:56.116524: step: 62/466, loss: 0.3378612995147705
2023-01-22 11:48:56.733084: step: 64/466, loss: 0.114456906914711
2023-01-22 11:48:57.540993: step: 66/466, loss: 0.004361505154520273
2023-01-22 11:48:58.169575: step: 68/466, loss: 0.14874155819416046
2023-01-22 11:48:58.823066: step: 70/466, loss: 0.24420452117919922
2023-01-22 11:48:59.437085: step: 72/466, loss: 0.04582386463880539
2023-01-22 11:49:00.112224: step: 74/466, loss: 0.17232546210289001
2023-01-22 11:49:00.768867: step: 76/466, loss: 0.11485756933689117
2023-01-22 11:49:01.410828: step: 78/466, loss: 0.0269269198179245
2023-01-22 11:49:01.995956: step: 80/466, loss: 0.058198269456624985
2023-01-22 11:49:02.689157: step: 82/466, loss: 0.11508843302726746
2023-01-22 11:49:03.284100: step: 84/466, loss: 0.023328503593802452
2023-01-22 11:49:03.887027: step: 86/466, loss: 0.03980041295289993
2023-01-22 11:49:04.573066: step: 88/466, loss: 0.08690007030963898
2023-01-22 11:49:05.264229: step: 90/466, loss: 0.04720456153154373
2023-01-22 11:49:05.982619: step: 92/466, loss: 0.062441691756248474
2023-01-22 11:49:06.674297: step: 94/466, loss: 0.04656941071152687
2023-01-22 11:49:07.370939: step: 96/466, loss: 0.08133785426616669
2023-01-22 11:49:08.033959: step: 98/466, loss: 0.08496791124343872
2023-01-22 11:49:08.790336: step: 100/466, loss: 0.08659321069717407
2023-01-22 11:49:09.481756: step: 102/466, loss: 0.057392898947000504
2023-01-22 11:49:10.063192: step: 104/466, loss: 0.03435138985514641
2023-01-22 11:49:10.726399: step: 106/466, loss: 0.02512931078672409
2023-01-22 11:49:11.447853: step: 108/466, loss: 0.06552870571613312
2023-01-22 11:49:12.084397: step: 110/466, loss: 0.08875542134046555
2023-01-22 11:49:12.842992: step: 112/466, loss: 3.140612840652466
2023-01-22 11:49:13.555703: step: 114/466, loss: 0.018068477511405945
2023-01-22 11:49:14.217348: step: 116/466, loss: 0.2105257362127304
2023-01-22 11:49:14.889189: step: 118/466, loss: 0.1643773317337036
2023-01-22 11:49:15.516784: step: 120/466, loss: 0.026753926649689674
2023-01-22 11:49:16.280231: step: 122/466, loss: 0.18800696730613708
2023-01-22 11:49:16.953668: step: 124/466, loss: 0.047364406287670135
2023-01-22 11:49:17.606560: step: 126/466, loss: 0.03672315552830696
2023-01-22 11:49:18.272962: step: 128/466, loss: 0.12688279151916504
2023-01-22 11:49:19.057252: step: 130/466, loss: 0.08330725878477097
2023-01-22 11:49:19.652732: step: 132/466, loss: 0.07648205012083054
2023-01-22 11:49:20.266516: step: 134/466, loss: 0.04698558151721954
2023-01-22 11:49:20.962874: step: 136/466, loss: 0.03224561735987663
2023-01-22 11:49:21.597576: step: 138/466, loss: 8.10254192352295
2023-01-22 11:49:22.233816: step: 140/466, loss: 0.041842713952064514
2023-01-22 11:49:22.837249: step: 142/466, loss: 0.2807225286960602
2023-01-22 11:49:23.476690: step: 144/466, loss: 0.04971598833799362
2023-01-22 11:49:24.149853: step: 146/466, loss: 0.11303872615098953
2023-01-22 11:49:24.764060: step: 148/466, loss: 0.0421968437731266
2023-01-22 11:49:25.404347: step: 150/466, loss: 0.03591064363718033
2023-01-22 11:49:26.056245: step: 152/466, loss: 0.07601898908615112
2023-01-22 11:49:26.712693: step: 154/466, loss: 0.14888262748718262
2023-01-22 11:49:27.381347: step: 156/466, loss: 0.05524364858865738
2023-01-22 11:49:28.028556: step: 158/466, loss: 0.04960860311985016
2023-01-22 11:49:28.664207: step: 160/466, loss: 0.10067957639694214
2023-01-22 11:49:29.310117: step: 162/466, loss: 0.44527915120124817
2023-01-22 11:49:29.938111: step: 164/466, loss: 0.05498115345835686
2023-01-22 11:49:30.624421: step: 166/466, loss: 0.14127767086029053
2023-01-22 11:49:31.267859: step: 168/466, loss: 0.057458266615867615
2023-01-22 11:49:31.842368: step: 170/466, loss: 0.06778069585561752
2023-01-22 11:49:32.486120: step: 172/466, loss: 0.03087298944592476
2023-01-22 11:49:33.187693: step: 174/466, loss: 0.05096074193716049
2023-01-22 11:49:33.830870: step: 176/466, loss: 0.010274292901158333
2023-01-22 11:49:34.506171: step: 178/466, loss: 0.046914875507354736
2023-01-22 11:49:35.165200: step: 180/466, loss: 0.06641078740358353
2023-01-22 11:49:35.814544: step: 182/466, loss: 0.060954492539167404
2023-01-22 11:49:36.485313: step: 184/466, loss: 0.14127805829048157
2023-01-22 11:49:37.119816: step: 186/466, loss: 0.07113578915596008
2023-01-22 11:49:37.821501: step: 188/466, loss: 0.5118537545204163
2023-01-22 11:49:38.493015: step: 190/466, loss: 0.18475711345672607
2023-01-22 11:49:39.238758: step: 192/466, loss: 0.009850537404417992
2023-01-22 11:49:39.797338: step: 194/466, loss: 0.06644842028617859
2023-01-22 11:49:40.445094: step: 196/466, loss: 0.3611626625061035
2023-01-22 11:49:41.126282: step: 198/466, loss: 0.03637146204710007
2023-01-22 11:49:41.827334: step: 200/466, loss: 0.02886369824409485
2023-01-22 11:49:42.412457: step: 202/466, loss: 0.08305783569812775
2023-01-22 11:49:43.060542: step: 204/466, loss: 0.06811418384313583
2023-01-22 11:49:43.762360: step: 206/466, loss: 0.04947146400809288
2023-01-22 11:49:44.406444: step: 208/466, loss: 0.03452489525079727
2023-01-22 11:49:45.049581: step: 210/466, loss: 0.01952638477087021
2023-01-22 11:49:45.653603: step: 212/466, loss: 0.03577161207795143
2023-01-22 11:49:46.294014: step: 214/466, loss: 0.8099901676177979
2023-01-22 11:49:46.935163: step: 216/466, loss: 0.1089983657002449
2023-01-22 11:49:47.582634: step: 218/466, loss: 0.05485111102461815
2023-01-22 11:49:48.216111: step: 220/466, loss: 0.2529895603656769
2023-01-22 11:49:48.831016: step: 222/466, loss: 0.08142302185297012
2023-01-22 11:49:49.474277: step: 224/466, loss: 0.05828835442662239
2023-01-22 11:49:50.125623: step: 226/466, loss: 0.08212900906801224
2023-01-22 11:49:50.751259: step: 228/466, loss: 0.03911758214235306
2023-01-22 11:49:51.410122: step: 230/466, loss: 0.11328721046447754
2023-01-22 11:49:51.978950: step: 232/466, loss: 0.09146860986948013
2023-01-22 11:49:52.605667: step: 234/466, loss: 0.042395103722810745
2023-01-22 11:49:53.283463: step: 236/466, loss: 0.04986429214477539
2023-01-22 11:49:53.929800: step: 238/466, loss: 0.09979227930307388
2023-01-22 11:49:54.592679: step: 240/466, loss: 0.08626820892095566
2023-01-22 11:49:55.189767: step: 242/466, loss: 0.03569401800632477
2023-01-22 11:49:55.803151: step: 244/466, loss: 0.7742249965667725
2023-01-22 11:49:56.419750: step: 246/466, loss: 0.2065431922674179
2023-01-22 11:49:56.964149: step: 248/466, loss: 0.02376331388950348
2023-01-22 11:49:57.561012: step: 250/466, loss: 0.2195350080728531
2023-01-22 11:49:58.171139: step: 252/466, loss: 0.032758988440036774
2023-01-22 11:49:58.817886: step: 254/466, loss: 0.8895750045776367
2023-01-22 11:49:59.510689: step: 256/466, loss: 0.032414816319942474
2023-01-22 11:50:00.131661: step: 258/466, loss: 0.06055746227502823
2023-01-22 11:50:00.713327: step: 260/466, loss: 0.028709404170513153
2023-01-22 11:50:01.351046: step: 262/466, loss: 0.05509772151708603
2023-01-22 11:50:01.979903: step: 264/466, loss: 0.05865830183029175
2023-01-22 11:50:02.616519: step: 266/466, loss: 0.1421409249305725
2023-01-22 11:50:03.161030: step: 268/466, loss: 0.05160105600953102
2023-01-22 11:50:03.781513: step: 270/466, loss: 0.017292175441980362
2023-01-22 11:50:04.527317: step: 272/466, loss: 0.4796491861343384
2023-01-22 11:50:05.129911: step: 274/466, loss: 0.3645254075527191
2023-01-22 11:50:05.777744: step: 276/466, loss: 0.01594046875834465
2023-01-22 11:50:06.441436: step: 278/466, loss: 0.12046370655298233
2023-01-22 11:50:07.205638: step: 280/466, loss: 0.0017643040046095848
2023-01-22 11:50:07.855506: step: 282/466, loss: 0.06266909837722778
2023-01-22 11:50:08.489563: step: 284/466, loss: 0.11617766320705414
2023-01-22 11:50:09.149354: step: 286/466, loss: 0.1816425919532776
2023-01-22 11:50:09.793033: step: 288/466, loss: 0.05535324662923813
2023-01-22 11:50:10.441025: step: 290/466, loss: 0.09581460803747177
2023-01-22 11:50:11.087239: step: 292/466, loss: 0.0881056934595108
2023-01-22 11:50:11.684291: step: 294/466, loss: 0.1429542750120163
2023-01-22 11:50:12.328617: step: 296/466, loss: 0.07996713370084763
2023-01-22 11:50:12.950536: step: 298/466, loss: 0.11317909508943558
2023-01-22 11:50:13.631000: step: 300/466, loss: 0.09892372041940689
2023-01-22 11:50:14.307075: step: 302/466, loss: 0.016523847356438637
2023-01-22 11:50:14.898828: step: 304/466, loss: 0.12549863755702972
2023-01-22 11:50:15.556318: step: 306/466, loss: 0.024841489270329475
2023-01-22 11:50:16.245515: step: 308/466, loss: 0.0675235316157341
2023-01-22 11:50:16.876854: step: 310/466, loss: 0.054056644439697266
2023-01-22 11:50:17.512305: step: 312/466, loss: 0.03715312108397484
2023-01-22 11:50:18.131497: step: 314/466, loss: 0.020889652892947197
2023-01-22 11:50:18.852028: step: 316/466, loss: 0.08342738449573517
2023-01-22 11:50:19.456062: step: 318/466, loss: 0.0254612285643816
2023-01-22 11:50:20.154757: step: 320/466, loss: 0.12345464527606964
2023-01-22 11:50:20.773332: step: 322/466, loss: 0.012913811951875687
2023-01-22 11:50:21.481520: step: 324/466, loss: 0.05068105459213257
2023-01-22 11:50:22.066779: step: 326/466, loss: 0.03996245190501213
2023-01-22 11:50:22.650007: step: 328/466, loss: 0.057917702943086624
2023-01-22 11:50:23.360843: step: 330/466, loss: 0.078567273914814
2023-01-22 11:50:23.942636: step: 332/466, loss: 0.032266248017549515
2023-01-22 11:50:24.574448: step: 334/466, loss: 0.015446437522768974
2023-01-22 11:50:25.270716: step: 336/466, loss: 0.01915135607123375
2023-01-22 11:50:25.963091: step: 338/466, loss: 0.07407674938440323
2023-01-22 11:50:26.561795: step: 340/466, loss: 0.055599890649318695
2023-01-22 11:50:27.165917: step: 342/466, loss: 0.06590849161148071
2023-01-22 11:50:27.816159: step: 344/466, loss: 0.030756264925003052
2023-01-22 11:50:28.470694: step: 346/466, loss: 0.09312482923269272
2023-01-22 11:50:29.150996: step: 348/466, loss: 0.04294842481613159
2023-01-22 11:50:29.801290: step: 350/466, loss: 0.023063605651259422
2023-01-22 11:50:30.396404: step: 352/466, loss: 0.050428006798028946
2023-01-22 11:50:31.036803: step: 354/466, loss: 0.035761695355176926
2023-01-22 11:50:31.686699: step: 356/466, loss: 0.4424636960029602
2023-01-22 11:50:32.350371: step: 358/466, loss: 0.061999861150979996
2023-01-22 11:50:32.979729: step: 360/466, loss: 0.06003555655479431
2023-01-22 11:50:33.682941: step: 362/466, loss: 0.09660322964191437
2023-01-22 11:50:34.331769: step: 364/466, loss: 0.32913368940353394
2023-01-22 11:50:34.960284: step: 366/466, loss: 0.06287943571805954
2023-01-22 11:50:35.544721: step: 368/466, loss: 0.04135376960039139
2023-01-22 11:50:36.145251: step: 370/466, loss: 0.12273543328046799
2023-01-22 11:50:36.777152: step: 372/466, loss: 0.09697325527667999
2023-01-22 11:50:37.553041: step: 374/466, loss: 0.20717570185661316
2023-01-22 11:50:38.313399: step: 376/466, loss: 0.17564678192138672
2023-01-22 11:50:38.941238: step: 378/466, loss: 0.02127458155155182
2023-01-22 11:50:39.555527: step: 380/466, loss: 0.03983462601900101
2023-01-22 11:50:40.228684: step: 382/466, loss: 0.0415821298956871
2023-01-22 11:50:40.863323: step: 384/466, loss: 0.03752491623163223
2023-01-22 11:50:41.463688: step: 386/466, loss: 0.20886972546577454
2023-01-22 11:50:42.150539: step: 388/466, loss: 0.06603700667619705
2023-01-22 11:50:42.797883: step: 390/466, loss: 0.659958004951477
2023-01-22 11:50:43.469151: step: 392/466, loss: 0.02154848352074623
2023-01-22 11:50:44.190633: step: 394/466, loss: 0.122312992811203
2023-01-22 11:50:44.772712: step: 396/466, loss: 0.11460147053003311
2023-01-22 11:50:45.383451: step: 398/466, loss: 0.02296714298427105
2023-01-22 11:50:46.073539: step: 400/466, loss: 0.12299858033657074
2023-01-22 11:50:46.636804: step: 402/466, loss: 0.04612415283918381
2023-01-22 11:50:47.299547: step: 404/466, loss: 0.036721426993608475
2023-01-22 11:50:47.922681: step: 406/466, loss: 0.049663905054330826
2023-01-22 11:50:48.617359: step: 408/466, loss: 2.824491024017334
2023-01-22 11:50:49.293763: step: 410/466, loss: 0.06330715864896774
2023-01-22 11:50:49.954124: step: 412/466, loss: 0.08676332980394363
2023-01-22 11:50:50.693340: step: 414/466, loss: 0.0636594295501709
2023-01-22 11:50:51.369844: step: 416/466, loss: 0.082150399684906
2023-01-22 11:50:52.013085: step: 418/466, loss: 0.0154802855104208
2023-01-22 11:50:52.581010: step: 420/466, loss: 0.10068855434656143
2023-01-22 11:50:53.278105: step: 422/466, loss: 0.06975843757390976
2023-01-22 11:50:53.898530: step: 424/466, loss: 0.0383467897772789
2023-01-22 11:50:54.521418: step: 426/466, loss: 0.4652051031589508
2023-01-22 11:50:55.104693: step: 428/466, loss: 0.16508370637893677
2023-01-22 11:50:55.900896: step: 430/466, loss: 0.07636451721191406
2023-01-22 11:50:56.583552: step: 432/466, loss: 0.15149201452732086
2023-01-22 11:50:57.264426: step: 434/466, loss: 0.057252347469329834
2023-01-22 11:50:57.965046: step: 436/466, loss: 0.04258215054869652
2023-01-22 11:50:58.622293: step: 438/466, loss: 0.014870988205075264
2023-01-22 11:50:59.368569: step: 440/466, loss: 0.040493033826351166
2023-01-22 11:51:00.089182: step: 442/466, loss: 0.21843920648097992
2023-01-22 11:51:00.712299: step: 444/466, loss: 0.07427722215652466
2023-01-22 11:51:01.325687: step: 446/466, loss: 0.022667555138468742
2023-01-22 11:51:02.049319: step: 448/466, loss: 0.08415772020816803
2023-01-22 11:51:02.722555: step: 450/466, loss: 0.21720390021800995
2023-01-22 11:51:03.361384: step: 452/466, loss: 0.18814308941364288
2023-01-22 11:51:04.011945: step: 454/466, loss: 0.0605594739317894
2023-01-22 11:51:04.643103: step: 456/466, loss: 1.33790123462677
2023-01-22 11:51:05.326123: step: 458/466, loss: 0.3248315751552582
2023-01-22 11:51:05.990054: step: 460/466, loss: 0.025710759684443474
2023-01-22 11:51:06.592305: step: 462/466, loss: 0.06335184723138809
2023-01-22 11:51:07.237316: step: 464/466, loss: 0.021018141880631447
2023-01-22 11:51:07.893325: step: 466/466, loss: 0.15620258450508118
2023-01-22 11:51:08.581130: step: 468/466, loss: 0.09127360582351685
2023-01-22 11:51:09.240400: step: 470/466, loss: 0.09151540696620941
2023-01-22 11:51:09.971835: step: 472/466, loss: 0.19718727469444275
2023-01-22 11:51:10.637206: step: 474/466, loss: 0.1726331263780594
2023-01-22 11:51:11.329056: step: 476/466, loss: 0.4496327340602875
2023-01-22 11:51:11.968499: step: 478/466, loss: 0.04377531632781029
2023-01-22 11:51:12.586993: step: 480/466, loss: 0.07953672856092453
2023-01-22 11:51:13.250618: step: 482/466, loss: 0.08268735557794571
2023-01-22 11:51:13.966603: step: 484/466, loss: 0.05951434746384621
2023-01-22 11:51:14.604634: step: 486/466, loss: 0.16865141689777374
2023-01-22 11:51:15.190690: step: 488/466, loss: 0.013609996996819973
2023-01-22 11:51:15.895451: step: 490/466, loss: 0.07433077692985535
2023-01-22 11:51:16.491781: step: 492/466, loss: 0.5957027077674866
2023-01-22 11:51:17.088920: step: 494/466, loss: 0.07487273216247559
2023-01-22 11:51:17.774158: step: 496/466, loss: 1.4150335788726807
2023-01-22 11:51:18.335045: step: 498/466, loss: 0.021949447691440582
2023-01-22 11:51:19.006404: step: 500/466, loss: 0.20540384948253632
2023-01-22 11:51:19.666649: step: 502/466, loss: 0.022929711267352104
2023-01-22 11:51:20.274275: step: 504/466, loss: 0.04285015910863876
2023-01-22 11:51:20.983589: step: 506/466, loss: 0.053249284625053406
2023-01-22 11:51:21.613206: step: 508/466, loss: 0.061508845537900925
2023-01-22 11:51:22.216806: step: 510/466, loss: 0.11744923144578934
2023-01-22 11:51:22.874667: step: 512/466, loss: 0.043242596089839935
2023-01-22 11:51:23.483423: step: 514/466, loss: 0.082844078540802
2023-01-22 11:51:24.091759: step: 516/466, loss: 0.5550380349159241
2023-01-22 11:51:24.792304: step: 518/466, loss: 0.09134536981582642
2023-01-22 11:51:25.454198: step: 520/466, loss: 0.050895120948553085
2023-01-22 11:51:26.098396: step: 522/466, loss: 0.08660466969013214
2023-01-22 11:51:26.764261: step: 524/466, loss: 0.1148732453584671
2023-01-22 11:51:27.434403: step: 526/466, loss: 0.06860499083995819
2023-01-22 11:51:28.013104: step: 528/466, loss: 0.04227155074477196
2023-01-22 11:51:28.679072: step: 530/466, loss: 0.02154962532222271
2023-01-22 11:51:29.305063: step: 532/466, loss: 0.016374345868825912
2023-01-22 11:51:30.029252: step: 534/466, loss: 0.00850632879883051
2023-01-22 11:51:30.633934: step: 536/466, loss: 0.07412139326334
2023-01-22 11:51:31.238465: step: 538/466, loss: 0.016608145087957382
2023-01-22 11:51:31.874673: step: 540/466, loss: 0.2312714159488678
2023-01-22 11:51:32.534613: step: 542/466, loss: 0.07605907320976257
2023-01-22 11:51:33.198326: step: 544/466, loss: 0.195210799574852
2023-01-22 11:51:33.825382: step: 546/466, loss: 0.08772149682044983
2023-01-22 11:51:34.444622: step: 548/466, loss: 0.03903600573539734
2023-01-22 11:51:35.075148: step: 550/466, loss: 0.23316924273967743
2023-01-22 11:51:35.730152: step: 552/466, loss: 0.15976104140281677
2023-01-22 11:51:36.357636: step: 554/466, loss: 0.17922474443912506
2023-01-22 11:51:37.140749: step: 556/466, loss: 0.06768238544464111
2023-01-22 11:51:37.793905: step: 558/466, loss: 0.06729494780302048
2023-01-22 11:51:38.441951: step: 560/466, loss: 0.15633723139762878
2023-01-22 11:51:39.151742: step: 562/466, loss: 0.4016426205635071
2023-01-22 11:51:39.786966: step: 564/466, loss: 0.03239607810974121
2023-01-22 11:51:40.483173: step: 566/466, loss: 0.1015559509396553
2023-01-22 11:51:41.107614: step: 568/466, loss: 0.06320659071207047
2023-01-22 11:51:41.795833: step: 570/466, loss: 0.11583807319402695
2023-01-22 11:51:42.499025: step: 572/466, loss: 0.03362603485584259
2023-01-22 11:51:43.207222: step: 574/466, loss: 0.13453516364097595
2023-01-22 11:51:43.799197: step: 576/466, loss: 0.12629076838493347
2023-01-22 11:51:44.462261: step: 578/466, loss: 0.07032449543476105
2023-01-22 11:51:45.081572: step: 580/466, loss: 0.09611865133047104
2023-01-22 11:51:45.716639: step: 582/466, loss: 0.05391501635313034
2023-01-22 11:51:46.445402: step: 584/466, loss: 0.36836880445480347
2023-01-22 11:51:47.213309: step: 586/466, loss: 0.08569643646478653
2023-01-22 11:51:47.913529: step: 588/466, loss: 0.20361623167991638
2023-01-22 11:51:48.620570: step: 590/466, loss: 0.013120735064148903
2023-01-22 11:51:49.312183: step: 592/466, loss: 0.09215152263641357
2023-01-22 11:51:49.931074: step: 594/466, loss: 0.05402675271034241
2023-01-22 11:51:50.639254: step: 596/466, loss: 0.10387832671403885
2023-01-22 11:51:51.264482: step: 598/466, loss: 0.02782166376709938
2023-01-22 11:51:51.894338: step: 600/466, loss: 0.0770563930273056
2023-01-22 11:51:52.542385: step: 602/466, loss: 0.12681631743907928
2023-01-22 11:51:53.193386: step: 604/466, loss: 0.14232604205608368
2023-01-22 11:51:53.787352: step: 606/466, loss: 2.2815752029418945
2023-01-22 11:51:54.404142: step: 608/466, loss: 0.4033258855342865
2023-01-22 11:51:55.061963: step: 610/466, loss: 0.0938134416937828
2023-01-22 11:51:55.706061: step: 612/466, loss: 0.08770494163036346
2023-01-22 11:51:56.382522: step: 614/466, loss: 0.026598917320370674
2023-01-22 11:51:57.075403: step: 616/466, loss: 0.060589879751205444
2023-01-22 11:51:57.718938: step: 618/466, loss: 0.2691894769668579
2023-01-22 11:51:58.290759: step: 620/466, loss: 0.08119969069957733
2023-01-22 11:51:58.926731: step: 622/466, loss: 0.1171530932188034
2023-01-22 11:51:59.612394: step: 624/466, loss: 0.06047392264008522
2023-01-22 11:52:00.260270: step: 626/466, loss: 0.06534136086702347
2023-01-22 11:52:00.931181: step: 628/466, loss: 0.03197570890188217
2023-01-22 11:52:01.583584: step: 630/466, loss: 0.3263348639011383
2023-01-22 11:52:02.304777: step: 632/466, loss: 0.05140954628586769
2023-01-22 11:52:02.939437: step: 634/466, loss: 0.06105520948767662
2023-01-22 11:52:03.495923: step: 636/466, loss: 0.005694460589438677
2023-01-22 11:52:04.165440: step: 638/466, loss: 0.5783259868621826
2023-01-22 11:52:04.868072: step: 640/466, loss: 0.2999393343925476
2023-01-22 11:52:05.498442: step: 642/466, loss: 0.04860677570104599
2023-01-22 11:52:06.121241: step: 644/466, loss: 0.062296394258737564
2023-01-22 11:52:06.731237: step: 646/466, loss: 0.09006703644990921
2023-01-22 11:52:07.410551: step: 648/466, loss: 0.0551469512283802
2023-01-22 11:52:08.009506: step: 650/466, loss: 0.09826161712408066
2023-01-22 11:52:08.680227: step: 652/466, loss: 0.059834785759449005
2023-01-22 11:52:09.322665: step: 654/466, loss: 0.09664934873580933
2023-01-22 11:52:10.014757: step: 656/466, loss: 0.3826269209384918
2023-01-22 11:52:10.650628: step: 658/466, loss: 0.10701795667409897
2023-01-22 11:52:11.361142: step: 660/466, loss: 0.030481388792395592
2023-01-22 11:52:12.082554: step: 662/466, loss: 0.04147927090525627
2023-01-22 11:52:12.744066: step: 664/466, loss: 0.04073699563741684
2023-01-22 11:52:13.364927: step: 666/466, loss: 0.0898548811674118
2023-01-22 11:52:14.027720: step: 668/466, loss: 0.04935910552740097
2023-01-22 11:52:14.731177: step: 670/466, loss: 0.09589585661888123
2023-01-22 11:52:15.353491: step: 672/466, loss: 0.10625513643026352
2023-01-22 11:52:15.990424: step: 674/466, loss: 0.003971959929913282
2023-01-22 11:52:16.642497: step: 676/466, loss: 0.03810294717550278
2023-01-22 11:52:17.361759: step: 678/466, loss: 0.5456706881523132
2023-01-22 11:52:18.036957: step: 680/466, loss: 0.06984337419271469
2023-01-22 11:52:18.723524: step: 682/466, loss: 0.05832561105489731
2023-01-22 11:52:19.395713: step: 684/466, loss: 0.11955627799034119
2023-01-22 11:52:20.065326: step: 686/466, loss: 0.076075479388237
2023-01-22 11:52:20.677678: step: 688/466, loss: 0.04003051295876503
2023-01-22 11:52:21.286459: step: 690/466, loss: 0.02638140693306923
2023-01-22 11:52:21.884739: step: 692/466, loss: 0.034705035388469696
2023-01-22 11:52:22.480967: step: 694/466, loss: 0.07898691296577454
2023-01-22 11:52:23.120630: step: 696/466, loss: 0.3519253730773926
2023-01-22 11:52:23.760824: step: 698/466, loss: 0.043164726346731186
2023-01-22 11:52:24.416144: step: 700/466, loss: 0.13846589624881744
2023-01-22 11:52:25.055080: step: 702/466, loss: 0.04918210208415985
2023-01-22 11:52:25.686916: step: 704/466, loss: 0.2499314844608307
2023-01-22 11:52:26.366087: step: 706/466, loss: 0.031565580517053604
2023-01-22 11:52:26.967302: step: 708/466, loss: 0.03719315677881241
2023-01-22 11:52:27.641211: step: 710/466, loss: 0.0273834727704525
2023-01-22 11:52:28.336309: step: 712/466, loss: 0.9689732789993286
2023-01-22 11:52:28.982657: step: 714/466, loss: 0.046712346374988556
2023-01-22 11:52:29.610338: step: 716/466, loss: 0.11686748266220093
2023-01-22 11:52:30.343379: step: 718/466, loss: 0.0049114711582660675
2023-01-22 11:52:30.943830: step: 720/466, loss: 0.23147809505462646
2023-01-22 11:52:31.627601: step: 722/466, loss: 0.1909041404724121
2023-01-22 11:52:32.202077: step: 724/466, loss: 0.03427097946405411
2023-01-22 11:52:32.862642: step: 726/466, loss: 0.060599882155656815
2023-01-22 11:52:33.581363: step: 728/466, loss: 0.1319151222705841
2023-01-22 11:52:34.231696: step: 730/466, loss: 0.20778167247772217
2023-01-22 11:52:34.913205: step: 732/466, loss: 0.061015255749225616
2023-01-22 11:52:35.551621: step: 734/466, loss: 0.08025775849819183
2023-01-22 11:52:36.261664: step: 736/466, loss: 0.05546239763498306
2023-01-22 11:52:36.953476: step: 738/466, loss: 0.158542200922966
2023-01-22 11:52:37.617443: step: 740/466, loss: 0.06881777942180634
2023-01-22 11:52:38.320557: step: 742/466, loss: 0.15654173493385315
2023-01-22 11:52:38.971817: step: 744/466, loss: 0.9193609952926636
2023-01-22 11:52:39.586107: step: 746/466, loss: 0.007909778505563736
2023-01-22 11:52:40.261482: step: 748/466, loss: 0.022688794881105423
2023-01-22 11:52:40.916471: step: 750/466, loss: 0.071705661714077
2023-01-22 11:52:41.539883: step: 752/466, loss: 0.1914301961660385
2023-01-22 11:52:42.240063: step: 754/466, loss: 0.005395537707954645
2023-01-22 11:52:42.916202: step: 756/466, loss: 0.08468862622976303
2023-01-22 11:52:43.491719: step: 758/466, loss: 0.17027100920677185
2023-01-22 11:52:44.097714: step: 760/466, loss: 0.05055655539035797
2023-01-22 11:52:44.741532: step: 762/466, loss: 0.055712856352329254
2023-01-22 11:52:45.410538: step: 764/466, loss: 0.0562840960919857
2023-01-22 11:52:46.042795: step: 766/466, loss: 0.230503112077713
2023-01-22 11:52:46.669741: step: 768/466, loss: 0.013948547653853893
2023-01-22 11:52:47.305129: step: 770/466, loss: 0.980506420135498
2023-01-22 11:52:47.996904: step: 772/466, loss: 0.04344959929585457
2023-01-22 11:52:48.672356: step: 774/466, loss: 0.4502314031124115
2023-01-22 11:52:49.336459: step: 776/466, loss: 0.09271130710840225
2023-01-22 11:52:50.021111: step: 778/466, loss: 0.09359487891197205
2023-01-22 11:52:50.676377: step: 780/466, loss: 0.0551677905023098
2023-01-22 11:52:51.278793: step: 782/466, loss: 0.06417146325111389
2023-01-22 11:52:51.947576: step: 784/466, loss: 0.1077897772192955
2023-01-22 11:52:52.584481: step: 786/466, loss: 0.048716768622398376
2023-01-22 11:52:53.214554: step: 788/466, loss: 0.004000423010438681
2023-01-22 11:52:53.913613: step: 790/466, loss: 0.18237416446208954
2023-01-22 11:52:54.562166: step: 792/466, loss: 0.040526874363422394
2023-01-22 11:52:55.219720: step: 794/466, loss: 0.0530264787375927
2023-01-22 11:52:55.888792: step: 796/466, loss: 0.06333018839359283
2023-01-22 11:52:56.539816: step: 798/466, loss: 0.07818601280450821
2023-01-22 11:52:57.212007: step: 800/466, loss: 0.06600316613912582
2023-01-22 11:52:57.844139: step: 802/466, loss: 1.0129446983337402
2023-01-22 11:52:58.489438: step: 804/466, loss: 0.09120383113622665
2023-01-22 11:52:59.253379: step: 806/466, loss: 0.09274714440107346
2023-01-22 11:52:59.886680: step: 808/466, loss: 0.049328066408634186
2023-01-22 11:53:00.509984: step: 810/466, loss: 0.07375475764274597
2023-01-22 11:53:01.195124: step: 812/466, loss: 0.5586576461791992
2023-01-22 11:53:01.870993: step: 814/466, loss: 0.384542852640152
2023-01-22 11:53:02.509323: step: 816/466, loss: 0.09888996183872223
2023-01-22 11:53:03.176738: step: 818/466, loss: 0.06262814998626709
2023-01-22 11:53:03.781269: step: 820/466, loss: 0.01604458875954151
2023-01-22 11:53:04.349474: step: 822/466, loss: 0.04279208555817604
2023-01-22 11:53:04.989269: step: 824/466, loss: 0.010919441469013691
2023-01-22 11:53:05.608854: step: 826/466, loss: 0.02665875479578972
2023-01-22 11:53:06.275300: step: 828/466, loss: 0.11534024775028229
2023-01-22 11:53:06.885816: step: 830/466, loss: 0.04270065203309059
2023-01-22 11:53:07.475472: step: 832/466, loss: 0.11828695237636566
2023-01-22 11:53:08.138769: step: 834/466, loss: 0.026358330622315407
2023-01-22 11:53:08.822653: step: 836/466, loss: 0.005910153966397047
2023-01-22 11:53:09.426415: step: 838/466, loss: 0.34486469626426697
2023-01-22 11:53:10.067281: step: 840/466, loss: 0.029074277728796005
2023-01-22 11:53:10.720578: step: 842/466, loss: 0.10085507482290268
2023-01-22 11:53:11.314068: step: 844/466, loss: 0.06384452432394028
2023-01-22 11:53:11.937694: step: 846/466, loss: 0.8601533770561218
2023-01-22 11:53:12.525312: step: 848/466, loss: 0.05942033231258392
2023-01-22 11:53:13.154878: step: 850/466, loss: 0.019594671204686165
2023-01-22 11:53:13.780283: step: 852/466, loss: 0.07780236750841141
2023-01-22 11:53:14.408254: step: 854/466, loss: 0.03243729844689369
2023-01-22 11:53:14.996892: step: 856/466, loss: 0.05148492380976677
2023-01-22 11:53:15.670652: step: 858/466, loss: 0.11528807878494263
2023-01-22 11:53:16.311031: step: 860/466, loss: 0.0014300361508503556
2023-01-22 11:53:17.015969: step: 862/466, loss: 0.09031727910041809
2023-01-22 11:53:17.633835: step: 864/466, loss: 0.19160300493240356
2023-01-22 11:53:18.282125: step: 866/466, loss: 0.12051482498645782
2023-01-22 11:53:18.971387: step: 868/466, loss: 0.07214026898145676
2023-01-22 11:53:19.590386: step: 870/466, loss: 0.08420170843601227
2023-01-22 11:53:20.239454: step: 872/466, loss: 0.3128611743450165
2023-01-22 11:53:20.811353: step: 874/466, loss: 0.0372660830616951
2023-01-22 11:53:21.495956: step: 876/466, loss: 0.08981478214263916
2023-01-22 11:53:22.137446: step: 878/466, loss: 0.05171480029821396
2023-01-22 11:53:22.821832: step: 880/466, loss: 0.16538923978805542
2023-01-22 11:53:23.571781: step: 882/466, loss: 0.09176956862211227
2023-01-22 11:53:24.148540: step: 884/466, loss: 0.028760412707924843
2023-01-22 11:53:24.746198: step: 886/466, loss: 0.052656181156635284
2023-01-22 11:53:25.354260: step: 888/466, loss: 0.24712523818016052
2023-01-22 11:53:26.022760: step: 890/466, loss: 0.07343322783708572
2023-01-22 11:53:26.732267: step: 892/466, loss: 0.038961004465818405
2023-01-22 11:53:27.369138: step: 894/466, loss: 0.0370122492313385
2023-01-22 11:53:28.026973: step: 896/466, loss: 0.11388856917619705
2023-01-22 11:53:28.699588: step: 898/466, loss: 0.30981096625328064
2023-01-22 11:53:29.371518: step: 900/466, loss: 0.03733278065919876
2023-01-22 11:53:30.033294: step: 902/466, loss: 0.1259738802909851
2023-01-22 11:53:30.631035: step: 904/466, loss: 0.025919705629348755
2023-01-22 11:53:31.263068: step: 906/466, loss: 0.04043346643447876
2023-01-22 11:53:31.964142: step: 908/466, loss: 0.48000040650367737
2023-01-22 11:53:32.599949: step: 910/466, loss: 0.028711294755339622
2023-01-22 11:53:33.292308: step: 912/466, loss: 0.05317974463105202
2023-01-22 11:53:33.950945: step: 914/466, loss: 0.15121129155158997
2023-01-22 11:53:34.529192: step: 916/466, loss: 0.02880292758345604
2023-01-22 11:53:35.211111: step: 918/466, loss: 0.23636382818222046
2023-01-22 11:53:35.821776: step: 920/466, loss: 0.06250850856304169
2023-01-22 11:53:36.497213: step: 922/466, loss: 0.10944357514381409
2023-01-22 11:53:37.117477: step: 924/466, loss: 0.06018063798546791
2023-01-22 11:53:37.758979: step: 926/466, loss: 0.07557946443557739
2023-01-22 11:53:38.488704: step: 928/466, loss: 0.11695948988199234
2023-01-22 11:53:39.124305: step: 930/466, loss: 0.8124833703041077
2023-01-22 11:53:39.751443: step: 932/466, loss: 0.12831737101078033
==================================================
Loss: 0.158
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3043943533697632, 'r': 0.3171015180265655, 'f1': 0.3106180297397769}, 'combined': 0.2288764429661514, 'epoch': 18}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3082954280733886, 'r': 0.29409211566892357, 'f1': 0.3010263264405903}, 'combined': 0.18849312029457527, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2923994974874372, 'r': 0.3312381404174573, 'f1': 0.31060943060498225}, 'combined': 0.22887010676156586, 'epoch': 18}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.31674725145254334, 'r': 0.3147461406581681, 'f1': 0.3157435254406974}, 'combined': 0.19567204393508006, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26993400621118013, 'r': 0.3298624288425048, 'f1': 0.2969043552519215}, 'combined': 0.21877163018562634, 'epoch': 18}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.31838241537768386, 'r': 0.310609969432659, 'f1': 0.31444817042793666}, 'combined': 0.2085943308779382, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25, 'r': 0.30714285714285716, 'f1': 0.27564102564102566}, 'combined': 0.18376068376068377, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27586206896551724, 'r': 0.34782608695652173, 'f1': 0.3076923076923077}, 'combined': 0.15384615384615385, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3181818181818182, 'r': 0.2413793103448276, 'f1': 0.27450980392156865}, 'combined': 0.18300653594771243, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 11:56:26.870960: step: 2/466, loss: 0.13111266493797302
2023-01-22 11:56:27.525817: step: 4/466, loss: 0.030377304181456566
2023-01-22 11:56:28.214707: step: 6/466, loss: 0.062473639845848083
2023-01-22 11:56:28.949858: step: 8/466, loss: 0.2828475534915924
2023-01-22 11:56:29.634799: step: 10/466, loss: 0.09224869310855865
2023-01-22 11:56:30.238865: step: 12/466, loss: 0.10512147098779678
2023-01-22 11:56:30.844636: step: 14/466, loss: 0.0439586415886879
2023-01-22 11:56:31.484552: step: 16/466, loss: 0.04128061607480049
2023-01-22 11:56:32.073967: step: 18/466, loss: 0.08516164124011993
2023-01-22 11:56:32.653026: step: 20/466, loss: 0.0048162443563342094
2023-01-22 11:56:33.319880: step: 22/466, loss: 0.09766031056642532
2023-01-22 11:56:33.951517: step: 24/466, loss: 0.09914689511060715
2023-01-22 11:56:34.617389: step: 26/466, loss: 0.04481856897473335
2023-01-22 11:56:35.217566: step: 28/466, loss: 0.05663405358791351
2023-01-22 11:56:35.906756: step: 30/466, loss: 0.054416682571172714
2023-01-22 11:56:36.500790: step: 32/466, loss: 0.25426021218299866
2023-01-22 11:56:37.134647: step: 34/466, loss: 0.05254456400871277
2023-01-22 11:56:37.808386: step: 36/466, loss: 0.01980424113571644
2023-01-22 11:56:38.428456: step: 38/466, loss: 0.010959596373140812
2023-01-22 11:56:39.087024: step: 40/466, loss: 0.051106374710798264
2023-01-22 11:56:39.742253: step: 42/466, loss: 0.1551026999950409
2023-01-22 11:56:40.408923: step: 44/466, loss: 0.0789317935705185
2023-01-22 11:56:41.010437: step: 46/466, loss: 0.05944628641009331
2023-01-22 11:56:41.701445: step: 48/466, loss: 0.03127778694033623
2023-01-22 11:56:42.339032: step: 50/466, loss: 0.08062749356031418
2023-01-22 11:56:43.020805: step: 52/466, loss: 5.5594801902771
2023-01-22 11:56:43.719060: step: 54/466, loss: 0.07140307873487473
2023-01-22 11:56:44.391750: step: 56/466, loss: 0.04742332920432091
2023-01-22 11:56:44.971323: step: 58/466, loss: 0.016738969832658768
2023-01-22 11:56:45.610656: step: 60/466, loss: 0.028866413980722427
2023-01-22 11:56:46.259172: step: 62/466, loss: 0.07691535353660583
2023-01-22 11:56:46.875415: step: 64/466, loss: 0.10655559599399567
2023-01-22 11:56:47.520857: step: 66/466, loss: 0.040917158126831055
2023-01-22 11:56:48.137037: step: 68/466, loss: 0.1279160976409912
2023-01-22 11:56:48.766185: step: 70/466, loss: 0.2998110055923462
2023-01-22 11:56:49.385713: step: 72/466, loss: 0.070008784532547
2023-01-22 11:56:50.006670: step: 74/466, loss: 0.09292187541723251
2023-01-22 11:56:50.673497: step: 76/466, loss: 0.10964535176753998
2023-01-22 11:56:51.241542: step: 78/466, loss: 0.049997728317976
2023-01-22 11:56:51.849930: step: 80/466, loss: 0.9389095902442932
2023-01-22 11:56:52.478378: step: 82/466, loss: 0.04234647378325462
2023-01-22 11:56:53.172841: step: 84/466, loss: 0.09408138692378998
2023-01-22 11:56:53.779751: step: 86/466, loss: 0.03672255575656891
2023-01-22 11:56:54.383609: step: 88/466, loss: 0.017950015142560005
2023-01-22 11:56:54.997327: step: 90/466, loss: 0.04448329284787178
2023-01-22 11:56:55.624684: step: 92/466, loss: 0.0492829866707325
2023-01-22 11:56:56.274493: step: 94/466, loss: 0.6904706954956055
2023-01-22 11:56:56.892032: step: 96/466, loss: 0.07388099282979965
2023-01-22 11:56:57.527817: step: 98/466, loss: 0.07274051010608673
2023-01-22 11:56:58.174408: step: 100/466, loss: 0.017620012164115906
2023-01-22 11:56:58.804800: step: 102/466, loss: 0.04263727739453316
2023-01-22 11:56:59.464672: step: 104/466, loss: 0.05030503869056702
2023-01-22 11:57:00.028463: step: 106/466, loss: 0.018043609336018562
2023-01-22 11:57:00.696932: step: 108/466, loss: 0.09793735295534134
2023-01-22 11:57:01.359614: step: 110/466, loss: 0.01932547613978386
2023-01-22 11:57:02.053019: step: 112/466, loss: 0.04864615947008133
2023-01-22 11:57:02.676545: step: 114/466, loss: 0.038060806691646576
2023-01-22 11:57:03.318089: step: 116/466, loss: 0.0922747403383255
2023-01-22 11:57:03.957748: step: 118/466, loss: 0.07914816588163376
2023-01-22 11:57:04.647757: step: 120/466, loss: 0.06315623968839645
2023-01-22 11:57:05.371773: step: 122/466, loss: 0.08343784511089325
2023-01-22 11:57:06.084536: step: 124/466, loss: 0.017767300829291344
2023-01-22 11:57:06.695106: step: 126/466, loss: 0.08279591798782349
2023-01-22 11:57:07.309694: step: 128/466, loss: 0.036457426846027374
2023-01-22 11:57:07.929348: step: 130/466, loss: 0.03488573431968689
2023-01-22 11:57:08.583946: step: 132/466, loss: 0.11147907376289368
2023-01-22 11:57:09.242480: step: 134/466, loss: 0.0624677874147892
2023-01-22 11:57:09.902363: step: 136/466, loss: 0.3967929184436798
2023-01-22 11:57:10.565223: step: 138/466, loss: 0.061561837792396545
2023-01-22 11:57:11.213399: step: 140/466, loss: 0.04596086964011192
2023-01-22 11:57:11.813004: step: 142/466, loss: 0.07178357988595963
2023-01-22 11:57:12.523153: step: 144/466, loss: 0.04006802290678024
2023-01-22 11:57:13.256842: step: 146/466, loss: 0.2670358419418335
2023-01-22 11:57:13.836675: step: 148/466, loss: 0.0967395082116127
2023-01-22 11:57:14.528249: step: 150/466, loss: 0.059438809752464294
2023-01-22 11:57:15.181375: step: 152/466, loss: 0.07806328684091568
2023-01-22 11:57:15.822763: step: 154/466, loss: 0.12640124559402466
2023-01-22 11:57:16.411879: step: 156/466, loss: 0.056182656437158585
2023-01-22 11:57:17.047309: step: 158/466, loss: 0.0118029173463583
2023-01-22 11:57:17.672722: step: 160/466, loss: 0.05292297899723053
2023-01-22 11:57:18.235179: step: 162/466, loss: 0.04758679121732712
2023-01-22 11:57:18.916907: step: 164/466, loss: 0.1466142237186432
2023-01-22 11:57:19.697611: step: 166/466, loss: 0.014361128211021423
2023-01-22 11:57:20.328470: step: 168/466, loss: 0.07442910969257355
2023-01-22 11:57:20.971179: step: 170/466, loss: 0.12469945847988129
2023-01-22 11:57:21.615311: step: 172/466, loss: 0.03124932013452053
2023-01-22 11:57:22.186163: step: 174/466, loss: 0.12064909189939499
2023-01-22 11:57:22.896979: step: 176/466, loss: 0.010970078408718109
2023-01-22 11:57:23.539965: step: 178/466, loss: 0.044288016855716705
2023-01-22 11:57:24.182943: step: 180/466, loss: 0.08396290987730026
2023-01-22 11:57:24.821318: step: 182/466, loss: 0.041987329721450806
2023-01-22 11:57:25.456716: step: 184/466, loss: 0.048830945044755936
2023-01-22 11:57:26.188349: step: 186/466, loss: 0.0017868517898023129
2023-01-22 11:57:26.794303: step: 188/466, loss: 0.03212421387434006
2023-01-22 11:57:27.497820: step: 190/466, loss: 0.12949633598327637
2023-01-22 11:57:28.233756: step: 192/466, loss: 0.04548605531454086
2023-01-22 11:57:28.820638: step: 194/466, loss: 0.059311699122190475
2023-01-22 11:57:29.479051: step: 196/466, loss: 0.019009608775377274
2023-01-22 11:57:30.138016: step: 198/466, loss: 0.004964243154972792
2023-01-22 11:57:30.867736: step: 200/466, loss: 0.09717816114425659
2023-01-22 11:57:31.497814: step: 202/466, loss: 0.08246175199747086
2023-01-22 11:57:32.176762: step: 204/466, loss: 2.0336592197418213
2023-01-22 11:57:32.795162: step: 206/466, loss: 0.027664698660373688
2023-01-22 11:57:33.483902: step: 208/466, loss: 0.036029212176799774
2023-01-22 11:57:34.084376: step: 210/466, loss: 0.0020111678168177605
2023-01-22 11:57:34.676297: step: 212/466, loss: 0.07115798443555832
2023-01-22 11:57:35.329169: step: 214/466, loss: 0.029138866811990738
2023-01-22 11:57:36.040955: step: 216/466, loss: 0.06382667273283005
2023-01-22 11:57:36.664263: step: 218/466, loss: 0.029953237622976303
2023-01-22 11:57:37.265430: step: 220/466, loss: 0.5576077699661255
2023-01-22 11:57:37.940215: step: 222/466, loss: 0.055012043565511703
2023-01-22 11:57:38.621188: step: 224/466, loss: 0.05663612112402916
2023-01-22 11:57:39.341551: step: 226/466, loss: 0.040842924267053604
2023-01-22 11:57:39.969872: step: 228/466, loss: 0.07554465532302856
2023-01-22 11:57:40.644372: step: 230/466, loss: 0.08036981523036957
2023-01-22 11:57:41.377459: step: 232/466, loss: 0.02852747216820717
2023-01-22 11:57:42.084050: step: 234/466, loss: 0.0490492507815361
2023-01-22 11:57:42.739889: step: 236/466, loss: 0.08456084877252579
2023-01-22 11:57:43.463570: step: 238/466, loss: 0.02745949849486351
2023-01-22 11:57:44.065734: step: 240/466, loss: 0.005800113547593355
2023-01-22 11:57:44.779949: step: 242/466, loss: 0.15487007796764374
2023-01-22 11:57:45.407412: step: 244/466, loss: 0.16259633004665375
2023-01-22 11:57:46.202743: step: 246/466, loss: 0.2039099931716919
2023-01-22 11:57:46.772858: step: 248/466, loss: 0.017041269689798355
2023-01-22 11:57:47.369543: step: 250/466, loss: 0.06916677206754684
2023-01-22 11:57:48.157120: step: 252/466, loss: 0.1294555813074112
2023-01-22 11:57:48.866702: step: 254/466, loss: 0.05329286679625511
2023-01-22 11:57:49.599570: step: 256/466, loss: 0.06700216233730316
2023-01-22 11:57:50.230296: step: 258/466, loss: 0.05133777856826782
2023-01-22 11:57:50.866199: step: 260/466, loss: 0.21220001578330994
2023-01-22 11:57:51.586713: step: 262/466, loss: 0.20323196053504944
2023-01-22 11:57:52.224393: step: 264/466, loss: 1.021466612815857
2023-01-22 11:57:52.849933: step: 266/466, loss: 0.29994967579841614
2023-01-22 11:57:53.494763: step: 268/466, loss: 0.04251955449581146
2023-01-22 11:57:54.177159: step: 270/466, loss: 0.03821241855621338
2023-01-22 11:57:54.824630: step: 272/466, loss: 0.27829816937446594
2023-01-22 11:57:55.571711: step: 274/466, loss: 0.017957674339413643
2023-01-22 11:57:56.262160: step: 276/466, loss: 0.032462190836668015
2023-01-22 11:57:56.968666: step: 278/466, loss: 0.05432771518826485
2023-01-22 11:57:57.688995: step: 280/466, loss: 0.06187226250767708
2023-01-22 11:57:58.351114: step: 282/466, loss: 0.10310728847980499
2023-01-22 11:57:58.976958: step: 284/466, loss: 0.00489452388137579
2023-01-22 11:57:59.603082: step: 286/466, loss: 0.1849922090768814
2023-01-22 11:58:00.234468: step: 288/466, loss: 0.06912319362163544
2023-01-22 11:58:00.898299: step: 290/466, loss: 0.06165488809347153
2023-01-22 11:58:01.586636: step: 292/466, loss: 0.03635357692837715
2023-01-22 11:58:02.138619: step: 294/466, loss: 0.025050140917301178
2023-01-22 11:58:02.774388: step: 296/466, loss: 0.05851269140839577
2023-01-22 11:58:03.463597: step: 298/466, loss: 0.013517416082322598
2023-01-22 11:58:04.186951: step: 300/466, loss: 0.03553743287920952
2023-01-22 11:58:04.741351: step: 302/466, loss: 0.0637500062584877
2023-01-22 11:58:05.360474: step: 304/466, loss: 0.20800507068634033
2023-01-22 11:58:05.989837: step: 306/466, loss: 0.04209780693054199
2023-01-22 11:58:06.631763: step: 308/466, loss: 0.09888007491827011
2023-01-22 11:58:07.273180: step: 310/466, loss: 0.07714834809303284
2023-01-22 11:58:07.974878: step: 312/466, loss: 0.3459691107273102
2023-01-22 11:58:08.638628: step: 314/466, loss: 0.10351727902889252
2023-01-22 11:58:09.237295: step: 316/466, loss: 0.021968403831124306
2023-01-22 11:58:09.925920: step: 318/466, loss: 0.025281671434640884
2023-01-22 11:58:10.582575: step: 320/466, loss: 0.22677254676818848
2023-01-22 11:58:11.212170: step: 322/466, loss: 0.038426004350185394
2023-01-22 11:58:11.907621: step: 324/466, loss: 0.13164333999156952
2023-01-22 11:58:12.504113: step: 326/466, loss: 0.014954368583858013
2023-01-22 11:58:13.140015: step: 328/466, loss: 0.09496348351240158
2023-01-22 11:58:13.858936: step: 330/466, loss: 0.038174692541360855
2023-01-22 11:58:14.430549: step: 332/466, loss: 0.009528448805212975
2023-01-22 11:58:15.056045: step: 334/466, loss: 0.046064235270023346
2023-01-22 11:58:15.722461: step: 336/466, loss: 0.07075343281030655
2023-01-22 11:58:16.444523: step: 338/466, loss: 0.021331191062927246
2023-01-22 11:58:17.107142: step: 340/466, loss: 0.05234293267130852
2023-01-22 11:58:17.728808: step: 342/466, loss: 0.006639528088271618
2023-01-22 11:58:18.367673: step: 344/466, loss: 0.02011287584900856
2023-01-22 11:58:18.951811: step: 346/466, loss: 0.06851448863744736
2023-01-22 11:58:19.551529: step: 348/466, loss: 0.05958017334342003
2023-01-22 11:58:20.182654: step: 350/466, loss: 0.026816874742507935
2023-01-22 11:58:20.784510: step: 352/466, loss: 0.022725136950612068
2023-01-22 11:58:21.426909: step: 354/466, loss: 0.040746208280324936
2023-01-22 11:58:22.080651: step: 356/466, loss: 0.06710579246282578
2023-01-22 11:58:22.727942: step: 358/466, loss: 0.03984346240758896
2023-01-22 11:58:23.450008: step: 360/466, loss: 0.44433659315109253
2023-01-22 11:58:24.076158: step: 362/466, loss: 0.06242652237415314
2023-01-22 11:58:24.727816: step: 364/466, loss: 0.16920684278011322
2023-01-22 11:58:25.289845: step: 366/466, loss: 0.05334998667240143
2023-01-22 11:58:25.911743: step: 368/466, loss: 0.1814628690481186
2023-01-22 11:58:26.459769: step: 370/466, loss: 0.029765360057353973
2023-01-22 11:58:27.067670: step: 372/466, loss: 0.07934707403182983
2023-01-22 11:58:27.741569: step: 374/466, loss: 0.11064215749502182
2023-01-22 11:58:28.339285: step: 376/466, loss: 0.04964088648557663
2023-01-22 11:58:28.968070: step: 378/466, loss: 0.030018683522939682
2023-01-22 11:58:29.651278: step: 380/466, loss: 0.014424442313611507
2023-01-22 11:58:30.303047: step: 382/466, loss: 0.0486597903072834
2023-01-22 11:58:30.943338: step: 384/466, loss: 0.17942792177200317
2023-01-22 11:58:31.581312: step: 386/466, loss: 0.16916340589523315
2023-01-22 11:58:32.201371: step: 388/466, loss: 0.029808206483721733
2023-01-22 11:58:32.800179: step: 390/466, loss: 0.020174860954284668
2023-01-22 11:58:33.421677: step: 392/466, loss: 0.02940339222550392
2023-01-22 11:58:34.096669: step: 394/466, loss: 0.1403074562549591
2023-01-22 11:58:34.751086: step: 396/466, loss: 0.04364815354347229
2023-01-22 11:58:35.439372: step: 398/466, loss: 0.08063490688800812
2023-01-22 11:58:36.088921: step: 400/466, loss: 0.05557699501514435
2023-01-22 11:58:36.777432: step: 402/466, loss: 0.03992890194058418
2023-01-22 11:58:37.560677: step: 404/466, loss: 0.010678840801119804
2023-01-22 11:58:38.227317: step: 406/466, loss: 0.05775224417448044
2023-01-22 11:58:38.898750: step: 408/466, loss: 0.15753324329853058
2023-01-22 11:58:39.554545: step: 410/466, loss: 0.026866205036640167
2023-01-22 11:58:40.215406: step: 412/466, loss: 0.0920744314789772
2023-01-22 11:58:40.838353: step: 414/466, loss: 0.009046662598848343
2023-01-22 11:58:41.459814: step: 416/466, loss: 0.5653553009033203
2023-01-22 11:58:42.075052: step: 418/466, loss: 0.02821408212184906
2023-01-22 11:58:42.772112: step: 420/466, loss: 0.01933966390788555
2023-01-22 11:58:43.358094: step: 422/466, loss: 0.08733387291431427
2023-01-22 11:58:44.056421: step: 424/466, loss: 0.06458159536123276
2023-01-22 11:58:44.681984: step: 426/466, loss: 0.020542047917842865
2023-01-22 11:58:45.347657: step: 428/466, loss: 0.01162881962954998
2023-01-22 11:58:45.942584: step: 430/466, loss: 0.08747508376836777
2023-01-22 11:58:46.659174: step: 432/466, loss: 0.01085928175598383
2023-01-22 11:58:47.261953: step: 434/466, loss: 0.045907966792583466
2023-01-22 11:58:47.952674: step: 436/466, loss: 0.03741806745529175
2023-01-22 11:58:48.548315: step: 438/466, loss: 0.14698748290538788
2023-01-22 11:58:49.204951: step: 440/466, loss: 0.010019396431744099
2023-01-22 11:58:49.871298: step: 442/466, loss: 0.06800957024097443
2023-01-22 11:58:50.518070: step: 444/466, loss: 0.027711616829037666
2023-01-22 11:58:51.099437: step: 446/466, loss: 0.03754089027643204
2023-01-22 11:58:51.744931: step: 448/466, loss: 0.1358477920293808
2023-01-22 11:58:52.419137: step: 450/466, loss: 0.04760868102312088
2023-01-22 11:58:53.063552: step: 452/466, loss: 0.009993338957428932
2023-01-22 11:58:53.824773: step: 454/466, loss: 0.03732457756996155
2023-01-22 11:58:54.482359: step: 456/466, loss: 0.025478068739175797
2023-01-22 11:58:55.103115: step: 458/466, loss: 0.10090377926826477
2023-01-22 11:58:55.727941: step: 460/466, loss: 0.02373766154050827
2023-01-22 11:58:56.362965: step: 462/466, loss: 0.049498915672302246
2023-01-22 11:58:57.026939: step: 464/466, loss: 0.19183450937271118
2023-01-22 11:58:57.695446: step: 466/466, loss: 0.050915125757455826
2023-01-22 11:58:58.321823: step: 468/466, loss: 0.2524608373641968
2023-01-22 11:58:58.952016: step: 470/466, loss: 0.09752923250198364
2023-01-22 11:58:59.605345: step: 472/466, loss: 0.01077574584633112
2023-01-22 11:59:00.238641: step: 474/466, loss: 0.02293819561600685
2023-01-22 11:59:00.864341: step: 476/466, loss: 0.11887908726930618
2023-01-22 11:59:01.560431: step: 478/466, loss: 0.03859763592481613
2023-01-22 11:59:02.193429: step: 480/466, loss: 0.024055566638708115
2023-01-22 11:59:02.864849: step: 482/466, loss: 0.08013734221458435
2023-01-22 11:59:03.576138: step: 484/466, loss: 0.11558590829372406
2023-01-22 11:59:04.277404: step: 486/466, loss: 0.02335383929312229
2023-01-22 11:59:04.910178: step: 488/466, loss: 1.0002586841583252
2023-01-22 11:59:05.565286: step: 490/466, loss: 0.14254963397979736
2023-01-22 11:59:06.267640: step: 492/466, loss: 0.07002247869968414
2023-01-22 11:59:06.857442: step: 494/466, loss: 0.014882318675518036
2023-01-22 11:59:07.465590: step: 496/466, loss: 0.016202298924326897
2023-01-22 11:59:08.144011: step: 498/466, loss: 0.10031528770923615
2023-01-22 11:59:08.819409: step: 500/466, loss: 0.10986057668924332
2023-01-22 11:59:09.411133: step: 502/466, loss: 0.052671339362859726
2023-01-22 11:59:10.091102: step: 504/466, loss: 0.02062651887536049
2023-01-22 11:59:10.762826: step: 506/466, loss: 0.04933162406086922
2023-01-22 11:59:11.415046: step: 508/466, loss: 0.4361085593700409
2023-01-22 11:59:12.113733: step: 510/466, loss: 0.2579571008682251
2023-01-22 11:59:12.761063: step: 512/466, loss: 0.07255497574806213
2023-01-22 11:59:13.425009: step: 514/466, loss: 0.08569323271512985
2023-01-22 11:59:14.031031: step: 516/466, loss: 0.03176683187484741
2023-01-22 11:59:14.668473: step: 518/466, loss: 0.06901123374700546
2023-01-22 11:59:15.337016: step: 520/466, loss: 0.2679722011089325
2023-01-22 11:59:16.056025: step: 522/466, loss: 0.15320459008216858
2023-01-22 11:59:16.760895: step: 524/466, loss: 0.02791094221174717
2023-01-22 11:59:17.405561: step: 526/466, loss: 0.17762930691242218
2023-01-22 11:59:18.083580: step: 528/466, loss: 0.04258953034877777
2023-01-22 11:59:18.787910: step: 530/466, loss: 0.01920774206519127
2023-01-22 11:59:19.365865: step: 532/466, loss: 0.18327747285366058
2023-01-22 11:59:19.984484: step: 534/466, loss: 0.02820243313908577
2023-01-22 11:59:20.614477: step: 536/466, loss: 0.267128586769104
2023-01-22 11:59:21.194964: step: 538/466, loss: 0.044478755444288254
2023-01-22 11:59:21.863032: step: 540/466, loss: 0.05204843729734421
2023-01-22 11:59:22.505991: step: 542/466, loss: 0.11069519072771072
2023-01-22 11:59:23.242683: step: 544/466, loss: 0.30489975214004517
2023-01-22 11:59:23.848040: step: 546/466, loss: 0.13504533469676971
2023-01-22 11:59:24.492514: step: 548/466, loss: 0.05704271420836449
2023-01-22 11:59:25.167408: step: 550/466, loss: 0.024533575400710106
2023-01-22 11:59:25.860316: step: 552/466, loss: 0.058383066207170486
2023-01-22 11:59:26.499616: step: 554/466, loss: 0.3767291009426117
2023-01-22 11:59:27.170152: step: 556/466, loss: 0.06400660425424576
2023-01-22 11:59:27.799047: step: 558/466, loss: 3.120527982711792
2023-01-22 11:59:28.457666: step: 560/466, loss: 0.1019875556230545
2023-01-22 11:59:29.191284: step: 562/466, loss: 0.14001332223415375
2023-01-22 11:59:29.799713: step: 564/466, loss: 0.040228210389614105
2023-01-22 11:59:30.448682: step: 566/466, loss: 0.042286038398742676
2023-01-22 11:59:31.088319: step: 568/466, loss: 0.14664529263973236
2023-01-22 11:59:31.648458: step: 570/466, loss: 0.3690696656703949
2023-01-22 11:59:32.370613: step: 572/466, loss: 0.047218356281518936
2023-01-22 11:59:33.036324: step: 574/466, loss: 0.0679393857717514
2023-01-22 11:59:33.693961: step: 576/466, loss: 0.0728268176317215
2023-01-22 11:59:34.330702: step: 578/466, loss: 0.11438603699207306
2023-01-22 11:59:34.925924: step: 580/466, loss: 0.3222803771495819
2023-01-22 11:59:35.663778: step: 582/466, loss: 0.5018194913864136
2023-01-22 11:59:36.330974: step: 584/466, loss: 0.10466251522302628
2023-01-22 11:59:36.984835: step: 586/466, loss: 0.0772814080119133
2023-01-22 11:59:37.699522: step: 588/466, loss: 0.07693363726139069
2023-01-22 11:59:38.381963: step: 590/466, loss: 0.11500084400177002
2023-01-22 11:59:39.064992: step: 592/466, loss: 0.18170012533664703
2023-01-22 11:59:39.711274: step: 594/466, loss: 0.08627156913280487
2023-01-22 11:59:40.328978: step: 596/466, loss: 0.0973271057009697
2023-01-22 11:59:40.989425: step: 598/466, loss: 0.3498533070087433
2023-01-22 11:59:41.628452: step: 600/466, loss: 0.15622715651988983
2023-01-22 11:59:42.233482: step: 602/466, loss: 0.06789826601743698
2023-01-22 11:59:42.882325: step: 604/466, loss: 0.07342401891946793
2023-01-22 11:59:43.579111: step: 606/466, loss: 0.052906207740306854
2023-01-22 11:59:44.230276: step: 608/466, loss: 0.44701021909713745
2023-01-22 11:59:44.914336: step: 610/466, loss: 0.030610734596848488
2023-01-22 11:59:45.584372: step: 612/466, loss: 0.22132834792137146
2023-01-22 11:59:46.231996: step: 614/466, loss: 0.05592351034283638
2023-01-22 11:59:46.853663: step: 616/466, loss: 0.09313730895519257
2023-01-22 11:59:47.469917: step: 618/466, loss: 0.06869268417358398
2023-01-22 11:59:48.104920: step: 620/466, loss: 0.6655417084693909
2023-01-22 11:59:48.786138: step: 622/466, loss: 0.14721828699111938
2023-01-22 11:59:49.510518: step: 624/466, loss: 0.03533070161938667
2023-01-22 11:59:50.159150: step: 626/466, loss: 0.0813283696770668
2023-01-22 11:59:50.801125: step: 628/466, loss: 0.009937165305018425
2023-01-22 11:59:51.434763: step: 630/466, loss: 0.010268451645970345
2023-01-22 11:59:52.087586: step: 632/466, loss: 0.0864536464214325
2023-01-22 11:59:52.693890: step: 634/466, loss: 0.03386939689517021
2023-01-22 11:59:53.354236: step: 636/466, loss: 0.23723642528057098
2023-01-22 11:59:54.057359: step: 638/466, loss: 0.09166768193244934
2023-01-22 11:59:54.771249: step: 640/466, loss: 0.06017732992768288
2023-01-22 11:59:55.386476: step: 642/466, loss: 0.038364145904779434
2023-01-22 11:59:56.033947: step: 644/466, loss: 0.13770458102226257
2023-01-22 11:59:56.808730: step: 646/466, loss: 0.08427499979734421
2023-01-22 11:59:57.446310: step: 648/466, loss: 0.41027942299842834
2023-01-22 11:59:58.121839: step: 650/466, loss: 0.06100025773048401
2023-01-22 11:59:58.715214: step: 652/466, loss: 0.11708735674619675
2023-01-22 11:59:59.286550: step: 654/466, loss: 0.04891982674598694
2023-01-22 11:59:59.927501: step: 656/466, loss: 0.22542575001716614
2023-01-22 12:00:00.624174: step: 658/466, loss: 0.028449928387999535
2023-01-22 12:00:01.261152: step: 660/466, loss: 0.013650071807205677
2023-01-22 12:00:01.944927: step: 662/466, loss: 0.3902254104614258
2023-01-22 12:00:02.640521: step: 664/466, loss: 1.6393153667449951
2023-01-22 12:00:03.312938: step: 666/466, loss: 0.02685406059026718
2023-01-22 12:00:04.032633: step: 668/466, loss: 0.039072226732969284
2023-01-22 12:00:04.757838: step: 670/466, loss: 0.05245056375861168
2023-01-22 12:00:05.404257: step: 672/466, loss: 0.03552987053990364
2023-01-22 12:00:06.052809: step: 674/466, loss: 0.8868280053138733
2023-01-22 12:00:06.661723: step: 676/466, loss: 0.10024195909500122
2023-01-22 12:00:07.278561: step: 678/466, loss: 0.1645973175764084
2023-01-22 12:00:07.867783: step: 680/466, loss: 0.07723838090896606
2023-01-22 12:00:08.503079: step: 682/466, loss: 0.07511638849973679
2023-01-22 12:00:09.209242: step: 684/466, loss: 0.13545194268226624
2023-01-22 12:00:09.807840: step: 686/466, loss: 0.17986997961997986
2023-01-22 12:00:10.455712: step: 688/466, loss: 0.03680276498198509
2023-01-22 12:00:11.087219: step: 690/466, loss: 0.10135433822870255
2023-01-22 12:00:11.731282: step: 692/466, loss: 0.22157587110996246
2023-01-22 12:00:12.382896: step: 694/466, loss: 0.018694933503866196
2023-01-22 12:00:13.037186: step: 696/466, loss: 0.04209217429161072
2023-01-22 12:00:13.665725: step: 698/466, loss: 0.04767581820487976
2023-01-22 12:00:14.341432: step: 700/466, loss: 0.05723273381590843
2023-01-22 12:00:15.041905: step: 702/466, loss: 0.04313664138317108
2023-01-22 12:00:15.786210: step: 704/466, loss: 0.128017857670784
2023-01-22 12:00:16.376793: step: 706/466, loss: 0.06857144832611084
2023-01-22 12:00:16.934144: step: 708/466, loss: 0.0038373505230993032
2023-01-22 12:00:17.583279: step: 710/466, loss: 0.031138163059949875
2023-01-22 12:00:18.228925: step: 712/466, loss: 0.03506476804614067
2023-01-22 12:00:18.902858: step: 714/466, loss: 0.32810282707214355
2023-01-22 12:00:19.585133: step: 716/466, loss: 0.06982269883155823
2023-01-22 12:00:20.316686: step: 718/466, loss: 0.06388357281684875
2023-01-22 12:00:21.010442: step: 720/466, loss: 0.07002855837345123
2023-01-22 12:00:21.618361: step: 722/466, loss: 0.043687477707862854
2023-01-22 12:00:22.220837: step: 724/466, loss: 0.0316498838365078
2023-01-22 12:00:22.882562: step: 726/466, loss: 0.05471200495958328
2023-01-22 12:00:23.535906: step: 728/466, loss: 0.03243080899119377
2023-01-22 12:00:24.190710: step: 730/466, loss: 0.044905055314302444
2023-01-22 12:00:24.866013: step: 732/466, loss: 2.867321729660034
2023-01-22 12:00:25.583140: step: 734/466, loss: 0.2733849883079529
2023-01-22 12:00:26.307083: step: 736/466, loss: 0.06968646496534348
2023-01-22 12:00:26.941264: step: 738/466, loss: 0.03289669007062912
2023-01-22 12:00:27.545368: step: 740/466, loss: 0.05700673535466194
2023-01-22 12:00:28.230352: step: 742/466, loss: 0.05384642258286476
2023-01-22 12:00:28.872698: step: 744/466, loss: 0.09741157293319702
2023-01-22 12:00:29.520251: step: 746/466, loss: 0.14611674845218658
2023-01-22 12:00:30.186870: step: 748/466, loss: 0.33620062470436096
2023-01-22 12:00:30.812656: step: 750/466, loss: 0.03367577865719795
2023-01-22 12:00:31.377923: step: 752/466, loss: 0.45889565348625183
2023-01-22 12:00:31.977742: step: 754/466, loss: 0.9962413311004639
2023-01-22 12:00:32.664683: step: 756/466, loss: 0.07204210758209229
2023-01-22 12:00:33.330290: step: 758/466, loss: 0.03932822868227959
2023-01-22 12:00:33.968188: step: 760/466, loss: 0.040566276758909225
2023-01-22 12:00:34.592865: step: 762/466, loss: 0.06714367866516113
2023-01-22 12:00:35.204791: step: 764/466, loss: 0.04591933637857437
2023-01-22 12:00:35.878712: step: 766/466, loss: 0.055630650371313095
2023-01-22 12:00:36.484283: step: 768/466, loss: 0.06030455604195595
2023-01-22 12:00:37.123512: step: 770/466, loss: 0.03375536948442459
2023-01-22 12:00:37.804805: step: 772/466, loss: 0.17689305543899536
2023-01-22 12:00:38.480153: step: 774/466, loss: 0.2330557405948639
2023-01-22 12:00:39.098045: step: 776/466, loss: 0.5213000774383545
2023-01-22 12:00:39.768796: step: 778/466, loss: 0.4058179557323456
2023-01-22 12:00:40.352537: step: 780/466, loss: 0.11434870958328247
2023-01-22 12:00:40.997301: step: 782/466, loss: 0.037684813141822815
2023-01-22 12:00:41.694634: step: 784/466, loss: 0.08802974224090576
2023-01-22 12:00:42.351252: step: 786/466, loss: 0.03473489359021187
2023-01-22 12:00:42.969172: step: 788/466, loss: 0.027913058176636696
2023-01-22 12:00:43.557182: step: 790/466, loss: 0.05223953723907471
2023-01-22 12:00:44.134327: step: 792/466, loss: 0.04339861124753952
2023-01-22 12:00:44.783669: step: 794/466, loss: 0.08510332554578781
2023-01-22 12:00:45.393362: step: 796/466, loss: 0.11441497504711151
2023-01-22 12:00:46.008120: step: 798/466, loss: 0.04340003430843353
2023-01-22 12:00:46.620090: step: 800/466, loss: 0.07298655062913895
2023-01-22 12:00:47.259430: step: 802/466, loss: 0.06131652370095253
2023-01-22 12:00:47.976504: step: 804/466, loss: 0.1494426429271698
2023-01-22 12:00:48.576519: step: 806/466, loss: 0.07292305678129196
2023-01-22 12:00:49.253269: step: 808/466, loss: 0.43063512444496155
2023-01-22 12:00:49.852554: step: 810/466, loss: 0.09854334592819214
2023-01-22 12:00:50.459063: step: 812/466, loss: 0.027418632060289383
2023-01-22 12:00:51.080064: step: 814/466, loss: 0.0341159962117672
2023-01-22 12:00:51.761081: step: 816/466, loss: 0.08582870662212372
2023-01-22 12:00:52.463747: step: 818/466, loss: 0.08624772727489471
2023-01-22 12:00:53.112443: step: 820/466, loss: 0.07493390142917633
2023-01-22 12:00:53.738633: step: 822/466, loss: 0.035955145955085754
2023-01-22 12:00:54.306057: step: 824/466, loss: 0.01353217102587223
2023-01-22 12:00:55.012382: step: 826/466, loss: 0.14625613391399384
2023-01-22 12:00:55.699541: step: 828/466, loss: 0.0401049479842186
2023-01-22 12:00:56.314808: step: 830/466, loss: 0.02966419607400894
2023-01-22 12:00:56.963322: step: 832/466, loss: 0.02818690799176693
2023-01-22 12:00:57.570748: step: 834/466, loss: 0.15146100521087646
2023-01-22 12:00:58.163010: step: 836/466, loss: 0.045433297753334045
2023-01-22 12:00:58.814759: step: 838/466, loss: 0.0740746334195137
2023-01-22 12:00:59.433492: step: 840/466, loss: 0.09819278866052628
2023-01-22 12:01:00.088598: step: 842/466, loss: 0.1914547085762024
2023-01-22 12:01:00.705464: step: 844/466, loss: 0.008679748512804508
2023-01-22 12:01:01.314711: step: 846/466, loss: 0.017056753858923912
2023-01-22 12:01:02.006592: step: 848/466, loss: 0.04419960081577301
2023-01-22 12:01:02.611900: step: 850/466, loss: 0.05022304132580757
2023-01-22 12:01:03.263628: step: 852/466, loss: 0.08829095959663391
2023-01-22 12:01:03.913601: step: 854/466, loss: 0.05575420334935188
2023-01-22 12:01:04.592110: step: 856/466, loss: 0.013077719137072563
2023-01-22 12:01:05.202672: step: 858/466, loss: 0.0013224079739302397
2023-01-22 12:01:05.853164: step: 860/466, loss: 0.07103028893470764
2023-01-22 12:01:06.498324: step: 862/466, loss: 0.06670407205820084
2023-01-22 12:01:07.232546: step: 864/466, loss: 0.00398715166375041
2023-01-22 12:01:07.826307: step: 866/466, loss: 0.20541343092918396
2023-01-22 12:01:08.454777: step: 868/466, loss: 0.0585695244371891
2023-01-22 12:01:09.119987: step: 870/466, loss: 0.04970893636345863
2023-01-22 12:01:09.776757: step: 872/466, loss: 0.0989101380109787
2023-01-22 12:01:10.507606: step: 874/466, loss: 0.03108326904475689
2023-01-22 12:01:11.135481: step: 876/466, loss: 0.1255584955215454
2023-01-22 12:01:11.930878: step: 878/466, loss: 0.10420676320791245
2023-01-22 12:01:12.599487: step: 880/466, loss: 0.08131679892539978
2023-01-22 12:01:13.281189: step: 882/466, loss: 0.15888020396232605
2023-01-22 12:01:13.910111: step: 884/466, loss: 0.1120786964893341
2023-01-22 12:01:14.527425: step: 886/466, loss: 0.06874912232160568
2023-01-22 12:01:15.135271: step: 888/466, loss: 0.14452779293060303
2023-01-22 12:01:15.802509: step: 890/466, loss: 0.026590008288621902
2023-01-22 12:01:16.407752: step: 892/466, loss: 0.05112864449620247
2023-01-22 12:01:17.131191: step: 894/466, loss: 0.1316065490245819
2023-01-22 12:01:17.720501: step: 896/466, loss: 0.10517143458127975
2023-01-22 12:01:18.351074: step: 898/466, loss: 0.03901936486363411
2023-01-22 12:01:19.055806: step: 900/466, loss: 0.0990578681230545
2023-01-22 12:01:19.692682: step: 902/466, loss: 0.059160854667425156
2023-01-22 12:01:20.383215: step: 904/466, loss: 0.04121256619691849
2023-01-22 12:01:20.946336: step: 906/466, loss: 0.06555764377117157
2023-01-22 12:01:21.611532: step: 908/466, loss: 0.025577547028660774
2023-01-22 12:01:22.250885: step: 910/466, loss: 0.07716955244541168
2023-01-22 12:01:22.868154: step: 912/466, loss: 0.3638467788696289
2023-01-22 12:01:23.455644: step: 914/466, loss: 3.7387709617614746
2023-01-22 12:01:24.085517: step: 916/466, loss: 0.050838202238082886
2023-01-22 12:01:24.680482: step: 918/466, loss: 0.04963570088148117
2023-01-22 12:01:25.321160: step: 920/466, loss: 0.044707197695970535
2023-01-22 12:01:25.885110: step: 922/466, loss: 0.08209022879600525
2023-01-22 12:01:26.542825: step: 924/466, loss: 0.09267618507146835
2023-01-22 12:01:27.198813: step: 926/466, loss: 0.08240016549825668
2023-01-22 12:01:27.860798: step: 928/466, loss: 0.030464094132184982
2023-01-22 12:01:28.504193: step: 930/466, loss: 0.058836594223976135
2023-01-22 12:01:29.207294: step: 932/466, loss: 0.18826398253440857
==================================================
Loss: 0.142
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34200965447154474, 'r': 0.319295540796964, 'f1': 0.3302625122669284}, 'combined': 0.243351324828263, 'epoch': 19}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.33642771152585144, 'r': 0.2936151597883559, 'f1': 0.31356684052578154}, 'combined': 0.19634559173109686, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3196859335839599, 'r': 0.3227190069576218, 'f1': 0.3211953100409191}, 'combined': 0.23667022845120356, 'epoch': 19}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3427951959932954, 'r': 0.3090725638964821, 'f1': 0.32506160493336694}, 'combined': 0.2014466284094105, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30095562390158176, 'r': 0.32494070208728654, 'f1': 0.31248859489051095}, 'combined': 0.23025475412985016, 'epoch': 19}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.33884655328704255, 'r': 0.2977928117495528, 'f1': 0.31699600557748353}, 'combined': 0.21028447894743957, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.30405405405405406, 'r': 0.32142857142857145, 'f1': 0.3125}, 'combined': 0.20833333333333331, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36607142857142855, 'r': 0.44565217391304346, 'f1': 0.4019607843137254}, 'combined': 0.2009803921568627, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.2413793103448276, 'f1': 0.28}, 'combined': 0.18666666666666668, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:04:16.738349: step: 2/466, loss: 0.04473452270030975
2023-01-22 12:04:17.319316: step: 4/466, loss: 0.02670433558523655
2023-01-22 12:04:17.977069: step: 6/466, loss: 0.09869610518217087
2023-01-22 12:04:18.687025: step: 8/466, loss: 0.0571296364068985
2023-01-22 12:04:19.357777: step: 10/466, loss: 0.005984506104141474
2023-01-22 12:04:20.054989: step: 12/466, loss: 0.0931580662727356
2023-01-22 12:04:20.719541: step: 14/466, loss: 0.05044613778591156
2023-01-22 12:04:21.360437: step: 16/466, loss: 0.07179475575685501
2023-01-22 12:04:21.927565: step: 18/466, loss: 0.05603202059864998
2023-01-22 12:04:22.615096: step: 20/466, loss: 0.011259501799941063
2023-01-22 12:04:23.225356: step: 22/466, loss: 0.03856699913740158
2023-01-22 12:04:23.904414: step: 24/466, loss: 0.505285382270813
2023-01-22 12:04:24.545001: step: 26/466, loss: 0.030787307769060135
2023-01-22 12:04:25.229735: step: 28/466, loss: 4.232536315917969
2023-01-22 12:04:25.841283: step: 30/466, loss: 0.057020630687475204
2023-01-22 12:04:26.533993: step: 32/466, loss: 0.4303550124168396
2023-01-22 12:04:27.192883: step: 34/466, loss: 2.1507062911987305
2023-01-22 12:04:27.840478: step: 36/466, loss: 0.04527447745203972
2023-01-22 12:04:28.493498: step: 38/466, loss: 0.2569637894630432
2023-01-22 12:04:29.211867: step: 40/466, loss: 0.09066056460142136
2023-01-22 12:04:29.851660: step: 42/466, loss: 0.0494978092610836
2023-01-22 12:04:30.496988: step: 44/466, loss: 0.014772189781069756
2023-01-22 12:04:31.160290: step: 46/466, loss: 0.04391703009605408
2023-01-22 12:04:31.736627: step: 48/466, loss: 0.015545777045190334
2023-01-22 12:04:32.454059: step: 50/466, loss: 0.04105439782142639
2023-01-22 12:04:33.135392: step: 52/466, loss: 0.03398992493748665
2023-01-22 12:04:33.780593: step: 54/466, loss: 0.022285019978880882
2023-01-22 12:04:34.465252: step: 56/466, loss: 0.6243164539337158
2023-01-22 12:04:35.104401: step: 58/466, loss: 0.048682548105716705
2023-01-22 12:04:35.691734: step: 60/466, loss: 0.014602897688746452
2023-01-22 12:04:36.347958: step: 62/466, loss: 0.006099842954427004
2023-01-22 12:04:36.971549: step: 64/466, loss: 0.04590804874897003
2023-01-22 12:04:37.653995: step: 66/466, loss: 0.037340402603149414
2023-01-22 12:04:38.305863: step: 68/466, loss: 0.051009513437747955
2023-01-22 12:04:38.947854: step: 70/466, loss: 0.0889776349067688
2023-01-22 12:04:39.560099: step: 72/466, loss: 0.03151462972164154
2023-01-22 12:04:40.203057: step: 74/466, loss: 0.0397343672811985
2023-01-22 12:04:40.878921: step: 76/466, loss: 0.15170085430145264
2023-01-22 12:04:41.554399: step: 78/466, loss: 0.07274332642555237
2023-01-22 12:04:42.236414: step: 80/466, loss: 0.19480833411216736
2023-01-22 12:04:42.887203: step: 82/466, loss: 0.19183169305324554
2023-01-22 12:04:43.513399: step: 84/466, loss: 3.4221458435058594
2023-01-22 12:04:44.065037: step: 86/466, loss: 0.00953746773302555
2023-01-22 12:04:44.751603: step: 88/466, loss: 0.053085751831531525
2023-01-22 12:04:45.406931: step: 90/466, loss: 1.3711509704589844
2023-01-22 12:04:46.096874: step: 92/466, loss: 0.15095512568950653
2023-01-22 12:04:46.728450: step: 94/466, loss: 0.03161424770951271
2023-01-22 12:04:47.389856: step: 96/466, loss: 0.12189152091741562
2023-01-22 12:04:48.066121: step: 98/466, loss: 0.06684818863868713
2023-01-22 12:04:48.735027: step: 100/466, loss: 0.21442358195781708
2023-01-22 12:04:49.426883: step: 102/466, loss: 0.2841276526451111
2023-01-22 12:04:50.085046: step: 104/466, loss: 0.028847578912973404
2023-01-22 12:04:50.665792: step: 106/466, loss: 0.036764275282621384
2023-01-22 12:04:51.360825: step: 108/466, loss: 0.15567131340503693
2023-01-22 12:04:51.961081: step: 110/466, loss: 0.08534884452819824
2023-01-22 12:04:52.661547: step: 112/466, loss: 0.030880440026521683
2023-01-22 12:04:53.398080: step: 114/466, loss: 0.08005496859550476
2023-01-22 12:04:54.018544: step: 116/466, loss: 0.054005514830350876
2023-01-22 12:04:54.669043: step: 118/466, loss: 0.07104286551475525
2023-01-22 12:04:55.332375: step: 120/466, loss: 0.1706767976284027
2023-01-22 12:04:55.980186: step: 122/466, loss: 0.15481732785701752
2023-01-22 12:04:56.648749: step: 124/466, loss: 0.03148510307073593
2023-01-22 12:04:57.263617: step: 126/466, loss: 0.030918629840016365
2023-01-22 12:04:57.863152: step: 128/466, loss: 0.036177732050418854
2023-01-22 12:04:58.526803: step: 130/466, loss: 0.32562559843063354
2023-01-22 12:04:59.225679: step: 132/466, loss: 0.07243402302265167
2023-01-22 12:04:59.831336: step: 134/466, loss: 0.10035238415002823
2023-01-22 12:05:00.498205: step: 136/466, loss: 0.08090130239725113
2023-01-22 12:05:01.090017: step: 138/466, loss: 0.02899058908224106
2023-01-22 12:05:01.773129: step: 140/466, loss: 0.02151150442659855
2023-01-22 12:05:02.380123: step: 142/466, loss: 0.011760477907955647
2023-01-22 12:05:03.061896: step: 144/466, loss: 0.017362717539072037
2023-01-22 12:05:03.720376: step: 146/466, loss: 0.04929214343428612
2023-01-22 12:05:04.382831: step: 148/466, loss: 0.19189995527267456
2023-01-22 12:05:05.081721: step: 150/466, loss: 0.09975867718458176
2023-01-22 12:05:05.730665: step: 152/466, loss: 0.02128298208117485
2023-01-22 12:05:06.370522: step: 154/466, loss: 0.027812689542770386
2023-01-22 12:05:07.043943: step: 156/466, loss: 0.02206970937550068
2023-01-22 12:05:07.721257: step: 158/466, loss: 0.018312718719244003
2023-01-22 12:05:08.406287: step: 160/466, loss: 0.033462077379226685
2023-01-22 12:05:09.035137: step: 162/466, loss: 0.013343071565032005
2023-01-22 12:05:09.645632: step: 164/466, loss: 0.06444109231233597
2023-01-22 12:05:10.286947: step: 166/466, loss: 0.04069790616631508
2023-01-22 12:05:10.941479: step: 168/466, loss: 0.037937380373477936
2023-01-22 12:05:11.535702: step: 170/466, loss: 0.029808631166815758
2023-01-22 12:05:12.197498: step: 172/466, loss: 0.06813343614339828
2023-01-22 12:05:12.778294: step: 174/466, loss: 0.056821562349796295
2023-01-22 12:05:13.408317: step: 176/466, loss: 0.09389083832502365
2023-01-22 12:05:14.047075: step: 178/466, loss: 0.014280026778578758
2023-01-22 12:05:14.733148: step: 180/466, loss: 0.08231594413518906
2023-01-22 12:05:15.393423: step: 182/466, loss: 0.030400605872273445
2023-01-22 12:05:16.057159: step: 184/466, loss: 0.09933170676231384
2023-01-22 12:05:16.676539: step: 186/466, loss: 0.010236128233373165
2023-01-22 12:05:17.315397: step: 188/466, loss: 0.039357565343379974
2023-01-22 12:05:18.017344: step: 190/466, loss: 0.03649383783340454
2023-01-22 12:05:18.660007: step: 192/466, loss: 0.04769815132021904
2023-01-22 12:05:19.382779: step: 194/466, loss: 0.11039624363183975
2023-01-22 12:05:20.040463: step: 196/466, loss: 0.02091108448803425
2023-01-22 12:05:20.634774: step: 198/466, loss: 0.02651154436171055
2023-01-22 12:05:21.259713: step: 200/466, loss: 0.05700225010514259
2023-01-22 12:05:21.934494: step: 202/466, loss: 0.8323856592178345
2023-01-22 12:05:22.623851: step: 204/466, loss: 0.026068931445479393
2023-01-22 12:05:23.277976: step: 206/466, loss: 0.2673957049846649
2023-01-22 12:05:23.989642: step: 208/466, loss: 0.15241274237632751
2023-01-22 12:05:24.631563: step: 210/466, loss: 0.028414934873580933
2023-01-22 12:05:25.309465: step: 212/466, loss: 0.026978882029652596
2023-01-22 12:05:25.927138: step: 214/466, loss: 0.008560284040868282
2023-01-22 12:05:26.604856: step: 216/466, loss: 0.06276308745145798
2023-01-22 12:05:27.229007: step: 218/466, loss: 0.09750475734472275
2023-01-22 12:05:27.908323: step: 220/466, loss: 0.04805998131632805
2023-01-22 12:05:28.558529: step: 222/466, loss: 0.08236956596374512
2023-01-22 12:05:29.162032: step: 224/466, loss: 0.07440599054098129
2023-01-22 12:05:29.758079: step: 226/466, loss: 0.018338710069656372
2023-01-22 12:05:30.383448: step: 228/466, loss: 0.011853711679577827
2023-01-22 12:05:31.105289: step: 230/466, loss: 0.24913370609283447
2023-01-22 12:05:31.740749: step: 232/466, loss: 0.023227758705615997
2023-01-22 12:05:32.398178: step: 234/466, loss: 0.048622407019138336
2023-01-22 12:05:33.036200: step: 236/466, loss: 0.049675896763801575
2023-01-22 12:05:33.787764: step: 238/466, loss: 0.30055010318756104
2023-01-22 12:05:34.419350: step: 240/466, loss: 0.031212367117404938
2023-01-22 12:05:35.036893: step: 242/466, loss: 0.03245452046394348
2023-01-22 12:05:35.753621: step: 244/466, loss: 0.05381162464618683
2023-01-22 12:05:36.378666: step: 246/466, loss: 0.04562469944357872
2023-01-22 12:05:37.045350: step: 248/466, loss: 0.3888448476791382
2023-01-22 12:05:37.705012: step: 250/466, loss: 0.07395334541797638
2023-01-22 12:05:38.421597: step: 252/466, loss: 0.04723105579614639
2023-01-22 12:05:39.038706: step: 254/466, loss: 0.154044970870018
2023-01-22 12:05:39.643808: step: 256/466, loss: 0.0067335874773561954
2023-01-22 12:05:40.300618: step: 258/466, loss: 0.046946655958890915
2023-01-22 12:05:40.949882: step: 260/466, loss: 0.056307390332221985
2023-01-22 12:05:41.572511: step: 262/466, loss: 0.018942169845104218
2023-01-22 12:05:42.229637: step: 264/466, loss: 0.15772342681884766
2023-01-22 12:05:42.894649: step: 266/466, loss: 0.012910989113152027
2023-01-22 12:05:43.497122: step: 268/466, loss: 0.031117776408791542
2023-01-22 12:05:44.160818: step: 270/466, loss: 0.08422558009624481
2023-01-22 12:05:44.892008: step: 272/466, loss: 0.04051937535405159
2023-01-22 12:05:45.537146: step: 274/466, loss: 0.034043360501527786
2023-01-22 12:05:46.164446: step: 276/466, loss: 0.027019595727324486
2023-01-22 12:05:46.764003: step: 278/466, loss: 0.05760733783245087
2023-01-22 12:05:47.475877: step: 280/466, loss: 0.03902026265859604
2023-01-22 12:05:48.113256: step: 282/466, loss: 0.07579785585403442
2023-01-22 12:05:48.739300: step: 284/466, loss: 0.0660325214266777
2023-01-22 12:05:49.380237: step: 286/466, loss: 0.020649529993534088
2023-01-22 12:05:50.070185: step: 288/466, loss: 0.017145643010735512
2023-01-22 12:05:50.664705: step: 290/466, loss: 0.01371070183813572
2023-01-22 12:05:51.257096: step: 292/466, loss: 0.04645758122205734
2023-01-22 12:05:51.899995: step: 294/466, loss: 0.02898515574634075
2023-01-22 12:05:52.566765: step: 296/466, loss: 0.067694291472435
2023-01-22 12:05:53.204576: step: 298/466, loss: 0.19380968809127808
2023-01-22 12:05:53.759414: step: 300/466, loss: 0.04423229768872261
2023-01-22 12:05:54.419172: step: 302/466, loss: 0.13991779088974
2023-01-22 12:05:55.016169: step: 304/466, loss: 0.030483869835734367
2023-01-22 12:05:55.672666: step: 306/466, loss: 0.03580395504832268
2023-01-22 12:05:56.268884: step: 308/466, loss: 0.04315454140305519
2023-01-22 12:05:56.911855: step: 310/466, loss: 0.03765023499727249
2023-01-22 12:05:57.494456: step: 312/466, loss: 0.013311164453625679
2023-01-22 12:05:58.194367: step: 314/466, loss: 0.022211074829101562
2023-01-22 12:05:58.797645: step: 316/466, loss: 0.022172167897224426
2023-01-22 12:05:59.418492: step: 318/466, loss: 0.027014657855033875
2023-01-22 12:06:00.098302: step: 320/466, loss: 1.5955520868301392
2023-01-22 12:06:00.828344: step: 322/466, loss: 0.1916019171476364
2023-01-22 12:06:01.469413: step: 324/466, loss: 0.2803540825843811
2023-01-22 12:06:02.209189: step: 326/466, loss: 0.08756520599126816
2023-01-22 12:06:02.841615: step: 328/466, loss: 0.037374790757894516
2023-01-22 12:06:03.502000: step: 330/466, loss: 0.03666498512029648
2023-01-22 12:06:04.099407: step: 332/466, loss: 0.014097894541919231
2023-01-22 12:06:04.864429: step: 334/466, loss: 0.05914449319243431
2023-01-22 12:06:05.489907: step: 336/466, loss: 0.25361284613609314
2023-01-22 12:06:06.115334: step: 338/466, loss: 0.050735026597976685
2023-01-22 12:06:06.787034: step: 340/466, loss: 0.123032346367836
2023-01-22 12:06:07.479825: step: 342/466, loss: 0.13411374390125275
2023-01-22 12:06:08.071931: step: 344/466, loss: 0.0036818471271544695
2023-01-22 12:06:08.689149: step: 346/466, loss: 0.18625682592391968
2023-01-22 12:06:09.365268: step: 348/466, loss: 0.09510066360235214
2023-01-22 12:06:10.056905: step: 350/466, loss: 0.011853153817355633
2023-01-22 12:06:10.743029: step: 352/466, loss: 0.06537090241909027
2023-01-22 12:06:11.353409: step: 354/466, loss: 0.04980561509728432
2023-01-22 12:06:11.996499: step: 356/466, loss: 0.0770934671163559
2023-01-22 12:06:12.572544: step: 358/466, loss: 0.08176696300506592
2023-01-22 12:06:13.247720: step: 360/466, loss: 0.015116947703063488
2023-01-22 12:06:13.899591: step: 362/466, loss: 0.08408878743648529
2023-01-22 12:06:14.494254: step: 364/466, loss: 0.017760295420885086
2023-01-22 12:06:15.141966: step: 366/466, loss: 0.4415796399116516
2023-01-22 12:06:15.808829: step: 368/466, loss: 0.07064615935087204
2023-01-22 12:06:16.425212: step: 370/466, loss: 0.05070814490318298
2023-01-22 12:06:17.062276: step: 372/466, loss: 0.04469557851552963
2023-01-22 12:06:17.708025: step: 374/466, loss: 0.5184050798416138
2023-01-22 12:06:18.418847: step: 376/466, loss: 0.10490608960390091
2023-01-22 12:06:19.109819: step: 378/466, loss: 0.017590532079339027
2023-01-22 12:06:19.943456: step: 380/466, loss: 0.043248046189546585
2023-01-22 12:06:20.655243: step: 382/466, loss: 0.05493703484535217
2023-01-22 12:06:21.352025: step: 384/466, loss: 0.10812664777040482
2023-01-22 12:06:21.985671: step: 386/466, loss: 0.012005889788269997
2023-01-22 12:06:22.608665: step: 388/466, loss: 0.03784538805484772
2023-01-22 12:06:23.233792: step: 390/466, loss: 0.021849500015378
2023-01-22 12:06:23.836844: step: 392/466, loss: 0.014305876567959785
2023-01-22 12:06:24.410422: step: 394/466, loss: 0.0313371866941452
2023-01-22 12:06:25.021283: step: 396/466, loss: 0.18692046403884888
2023-01-22 12:06:25.656428: step: 398/466, loss: 0.09531613439321518
2023-01-22 12:06:26.306145: step: 400/466, loss: 0.04120203107595444
2023-01-22 12:06:26.934719: step: 402/466, loss: 0.04370715841650963
2023-01-22 12:06:27.595201: step: 404/466, loss: 0.07401634007692337
2023-01-22 12:06:28.284032: step: 406/466, loss: 0.10191718488931656
2023-01-22 12:06:28.918285: step: 408/466, loss: 0.0735027864575386
2023-01-22 12:06:29.584851: step: 410/466, loss: 0.07235123217105865
2023-01-22 12:06:30.246211: step: 412/466, loss: 0.11868435144424438
2023-01-22 12:06:30.909466: step: 414/466, loss: 0.05378936976194382
2023-01-22 12:06:31.535022: step: 416/466, loss: 0.14694419503211975
2023-01-22 12:06:32.251444: step: 418/466, loss: 0.0017634829273447394
2023-01-22 12:06:32.968519: step: 420/466, loss: 0.0756598636507988
2023-01-22 12:06:33.650243: step: 422/466, loss: 0.054010868072509766
2023-01-22 12:06:34.268812: step: 424/466, loss: 0.017388856038451195
2023-01-22 12:06:34.872370: step: 426/466, loss: 11.393009185791016
2023-01-22 12:06:35.536143: step: 428/466, loss: 0.31075289845466614
2023-01-22 12:06:36.193514: step: 430/466, loss: 0.04381495714187622
2023-01-22 12:06:36.823211: step: 432/466, loss: 0.8955109715461731
2023-01-22 12:06:37.417680: step: 434/466, loss: 0.018910974264144897
2023-01-22 12:06:38.078720: step: 436/466, loss: 0.024038417264819145
2023-01-22 12:06:38.684105: step: 438/466, loss: 0.030103906989097595
2023-01-22 12:06:39.282067: step: 440/466, loss: 0.37985509634017944
2023-01-22 12:06:39.882829: step: 442/466, loss: 0.005558432079851627
2023-01-22 12:06:40.523208: step: 444/466, loss: 0.03839689865708351
2023-01-22 12:06:41.145683: step: 446/466, loss: 0.06781277805566788
2023-01-22 12:06:41.807570: step: 448/466, loss: 0.18135598301887512
2023-01-22 12:06:42.433671: step: 450/466, loss: 0.04757753014564514
2023-01-22 12:06:43.103137: step: 452/466, loss: 0.032391536980867386
2023-01-22 12:06:43.741855: step: 454/466, loss: 0.04910852015018463
2023-01-22 12:06:44.412075: step: 456/466, loss: 0.06771580129861832
2023-01-22 12:06:45.087532: step: 458/466, loss: 0.09586554765701294
2023-01-22 12:06:45.714958: step: 460/466, loss: 0.08000804483890533
2023-01-22 12:06:46.391779: step: 462/466, loss: 0.03900667652487755
2023-01-22 12:06:47.021731: step: 464/466, loss: 0.09564217180013657
2023-01-22 12:06:47.688545: step: 466/466, loss: 0.04399758204817772
2023-01-22 12:06:48.376735: step: 468/466, loss: 0.05565526336431503
2023-01-22 12:06:48.994110: step: 470/466, loss: 0.0949612408876419
2023-01-22 12:06:49.680256: step: 472/466, loss: 0.032630555331707
2023-01-22 12:06:50.379470: step: 474/466, loss: 0.03060712106525898
2023-01-22 12:06:51.033321: step: 476/466, loss: 0.034767478704452515
2023-01-22 12:06:51.701397: step: 478/466, loss: 0.10432400554418564
2023-01-22 12:06:52.368340: step: 480/466, loss: 0.11564582586288452
2023-01-22 12:06:53.055608: step: 482/466, loss: 0.06722190976142883
2023-01-22 12:06:53.693277: step: 484/466, loss: 0.053551219403743744
2023-01-22 12:06:54.349701: step: 486/466, loss: 0.0823635533452034
2023-01-22 12:06:55.024486: step: 488/466, loss: 0.09532275795936584
2023-01-22 12:06:55.643005: step: 490/466, loss: 0.0684138834476471
2023-01-22 12:06:56.268640: step: 492/466, loss: 0.013710126280784607
2023-01-22 12:06:56.908850: step: 494/466, loss: 0.03670593351125717
2023-01-22 12:06:57.524924: step: 496/466, loss: 0.034739699214696884
2023-01-22 12:06:58.156663: step: 498/466, loss: 0.0073441630229353905
2023-01-22 12:06:58.809855: step: 500/466, loss: 0.07757313549518585
2023-01-22 12:06:59.501207: step: 502/466, loss: 0.04221266508102417
2023-01-22 12:07:00.200867: step: 504/466, loss: 0.018677473068237305
2023-01-22 12:07:00.883970: step: 506/466, loss: 0.056042835116386414
2023-01-22 12:07:01.506397: step: 508/466, loss: 0.09111560881137848
2023-01-22 12:07:02.121438: step: 510/466, loss: 0.033317744731903076
2023-01-22 12:07:02.860959: step: 512/466, loss: 0.08932971954345703
2023-01-22 12:07:03.483005: step: 514/466, loss: 0.02863481268286705
2023-01-22 12:07:04.117036: step: 516/466, loss: 0.06317055225372314
2023-01-22 12:07:04.745976: step: 518/466, loss: 0.046415556222200394
2023-01-22 12:07:05.391552: step: 520/466, loss: 0.059857502579689026
2023-01-22 12:07:06.038642: step: 522/466, loss: 0.022902199998497963
2023-01-22 12:07:06.701287: step: 524/466, loss: 0.09407820552587509
2023-01-22 12:07:07.339032: step: 526/466, loss: 0.06468775123357773
2023-01-22 12:07:08.023562: step: 528/466, loss: 0.061519160866737366
2023-01-22 12:07:08.677308: step: 530/466, loss: 0.10522399842739105
2023-01-22 12:07:09.317572: step: 532/466, loss: 0.006822334136813879
2023-01-22 12:07:09.940709: step: 534/466, loss: 0.039750613272190094
2023-01-22 12:07:10.576774: step: 536/466, loss: 0.05738213658332825
2023-01-22 12:07:11.171394: step: 538/466, loss: 0.2611234486103058
2023-01-22 12:07:11.916456: step: 540/466, loss: 0.04813788831233978
2023-01-22 12:07:12.622893: step: 542/466, loss: 0.14306648075580597
2023-01-22 12:07:13.325854: step: 544/466, loss: 0.06339039653539658
2023-01-22 12:07:13.999779: step: 546/466, loss: 0.11885727941989899
2023-01-22 12:07:14.699794: step: 548/466, loss: 0.133851557970047
2023-01-22 12:07:15.332823: step: 550/466, loss: 0.034811291843652725
2023-01-22 12:07:15.972255: step: 552/466, loss: 0.07138923555612564
2023-01-22 12:07:16.622935: step: 554/466, loss: 0.06095288693904877
2023-01-22 12:07:17.328583: step: 556/466, loss: 0.041248105466365814
2023-01-22 12:07:17.967928: step: 558/466, loss: 0.2250605970621109
2023-01-22 12:07:18.609218: step: 560/466, loss: 0.02611805871129036
2023-01-22 12:07:19.320757: step: 562/466, loss: 0.17415495216846466
2023-01-22 12:07:19.941376: step: 564/466, loss: 0.012367604300379753
2023-01-22 12:07:20.545165: step: 566/466, loss: 0.008169536478817463
2023-01-22 12:07:21.201028: step: 568/466, loss: 0.007444975897669792
2023-01-22 12:07:21.905080: step: 570/466, loss: 0.06542429327964783
2023-01-22 12:07:22.542594: step: 572/466, loss: 0.07730428129434586
2023-01-22 12:07:23.163210: step: 574/466, loss: 0.055045854300260544
2023-01-22 12:07:23.833089: step: 576/466, loss: 0.01367559190839529
2023-01-22 12:07:24.496424: step: 578/466, loss: 0.24741590023040771
2023-01-22 12:07:25.118674: step: 580/466, loss: 0.055768102407455444
2023-01-22 12:07:25.760738: step: 582/466, loss: 0.01121440064162016
2023-01-22 12:07:26.394803: step: 584/466, loss: 0.058712225407361984
2023-01-22 12:07:27.037420: step: 586/466, loss: 0.14266453683376312
2023-01-22 12:07:27.671917: step: 588/466, loss: 0.019000612199306488
2023-01-22 12:07:28.335965: step: 590/466, loss: 0.08274511992931366
2023-01-22 12:07:28.953529: step: 592/466, loss: 1.2463836669921875
2023-01-22 12:07:29.609577: step: 594/466, loss: 0.0700952559709549
2023-01-22 12:07:30.236494: step: 596/466, loss: 0.05400775372982025
2023-01-22 12:07:30.871501: step: 598/466, loss: 0.09943843632936478
2023-01-22 12:07:31.501422: step: 600/466, loss: 0.051910433918237686
2023-01-22 12:07:32.154029: step: 602/466, loss: 0.0629982128739357
2023-01-22 12:07:32.924045: step: 604/466, loss: 0.14483165740966797
2023-01-22 12:07:33.552786: step: 606/466, loss: 0.0398201122879982
2023-01-22 12:07:34.213341: step: 608/466, loss: 0.016322026029229164
2023-01-22 12:07:34.826445: step: 610/466, loss: 0.09787385165691376
2023-01-22 12:07:35.411306: step: 612/466, loss: 0.05622246488928795
2023-01-22 12:07:36.030782: step: 614/466, loss: 0.02025759033858776
2023-01-22 12:07:36.669274: step: 616/466, loss: 0.07201140373945236
2023-01-22 12:07:37.350457: step: 618/466, loss: 0.03505564108490944
2023-01-22 12:07:37.954922: step: 620/466, loss: 0.01954931952059269
2023-01-22 12:07:38.728845: step: 622/466, loss: 0.054865192621946335
2023-01-22 12:07:39.390522: step: 624/466, loss: 0.04479478299617767
2023-01-22 12:07:40.026695: step: 626/466, loss: 0.0170596893876791
2023-01-22 12:07:40.684127: step: 628/466, loss: 0.06574743986129761
2023-01-22 12:07:41.314105: step: 630/466, loss: 0.10950388759374619
2023-01-22 12:07:41.976602: step: 632/466, loss: 0.05113056302070618
2023-01-22 12:07:42.657018: step: 634/466, loss: 0.08861953020095825
2023-01-22 12:07:43.342347: step: 636/466, loss: 0.004567514173686504
2023-01-22 12:07:44.007033: step: 638/466, loss: 0.04586312919855118
2023-01-22 12:07:44.698849: step: 640/466, loss: 0.08604729920625687
2023-01-22 12:07:45.348930: step: 642/466, loss: 0.039753928780555725
2023-01-22 12:07:45.966196: step: 644/466, loss: 0.1817084401845932
2023-01-22 12:07:46.565210: step: 646/466, loss: 0.08637432008981705
2023-01-22 12:07:47.191179: step: 648/466, loss: 0.02143004909157753
2023-01-22 12:07:47.878591: step: 650/466, loss: 0.024217985570430756
2023-01-22 12:07:48.559665: step: 652/466, loss: 0.017095118761062622
2023-01-22 12:07:49.212982: step: 654/466, loss: 0.016036296263337135
2023-01-22 12:07:49.877917: step: 656/466, loss: 0.06510784476995468
2023-01-22 12:07:50.470656: step: 658/466, loss: 0.08545298129320145
2023-01-22 12:07:51.095328: step: 660/466, loss: 0.04476512596011162
2023-01-22 12:07:51.738487: step: 662/466, loss: 0.04669211059808731
2023-01-22 12:07:52.479839: step: 664/466, loss: 0.03477967903017998
2023-01-22 12:07:53.130748: step: 666/466, loss: 0.07388802617788315
2023-01-22 12:07:53.767038: step: 668/466, loss: 0.3461158275604248
2023-01-22 12:07:54.496865: step: 670/466, loss: 0.06619387865066528
2023-01-22 12:07:55.147640: step: 672/466, loss: 0.034900009632110596
2023-01-22 12:07:55.760389: step: 674/466, loss: 0.037802595645189285
2023-01-22 12:07:56.385914: step: 676/466, loss: 0.24723856151103973
2023-01-22 12:07:56.989187: step: 678/466, loss: 0.026428377255797386
2023-01-22 12:07:57.686722: step: 680/466, loss: 0.01633252017199993
2023-01-22 12:07:58.365201: step: 682/466, loss: 0.029313204810023308
2023-01-22 12:07:59.139779: step: 684/466, loss: 0.3518146276473999
2023-01-22 12:07:59.759567: step: 686/466, loss: 0.0816594809293747
2023-01-22 12:08:00.450414: step: 688/466, loss: 0.06408290565013885
2023-01-22 12:08:01.139966: step: 690/466, loss: 0.049211613833904266
2023-01-22 12:08:01.813975: step: 692/466, loss: 0.03745852783322334
2023-01-22 12:08:02.442476: step: 694/466, loss: 0.018650511279702187
2023-01-22 12:08:03.102290: step: 696/466, loss: 0.18802715837955475
2023-01-22 12:08:03.765352: step: 698/466, loss: 0.018624436110258102
2023-01-22 12:08:04.421689: step: 700/466, loss: 0.09911294281482697
2023-01-22 12:08:05.059757: step: 702/466, loss: 0.0057364520616829395
2023-01-22 12:08:05.705655: step: 704/466, loss: 0.10185503959655762
2023-01-22 12:08:06.342906: step: 706/466, loss: 0.010374201461672783
2023-01-22 12:08:07.066802: step: 708/466, loss: 0.08099198341369629
2023-01-22 12:08:07.757064: step: 710/466, loss: 0.03127642348408699
2023-01-22 12:08:08.476678: step: 712/466, loss: 0.1152448058128357
2023-01-22 12:08:09.181252: step: 714/466, loss: 0.017789151519536972
2023-01-22 12:08:09.786770: step: 716/466, loss: 0.022697532549500465
2023-01-22 12:08:10.485652: step: 718/466, loss: 0.014777543023228645
2023-01-22 12:08:11.212680: step: 720/466, loss: 0.024037595838308334
2023-01-22 12:08:11.813182: step: 722/466, loss: 0.06626082211732864
2023-01-22 12:08:12.590006: step: 724/466, loss: 0.06400647759437561
2023-01-22 12:08:13.228702: step: 726/466, loss: 0.040571171790361404
2023-01-22 12:08:13.795689: step: 728/466, loss: 0.0280370581895113
2023-01-22 12:08:14.504159: step: 730/466, loss: 0.15912574529647827
2023-01-22 12:08:15.155929: step: 732/466, loss: 0.05670500919222832
2023-01-22 12:08:15.813156: step: 734/466, loss: 0.05155463516712189
2023-01-22 12:08:16.432444: step: 736/466, loss: 0.0762219950556755
2023-01-22 12:08:17.074972: step: 738/466, loss: 0.030081335455179214
2023-01-22 12:08:17.704589: step: 740/466, loss: 0.03961065784096718
2023-01-22 12:08:18.392340: step: 742/466, loss: 0.2696669101715088
2023-01-22 12:08:19.090368: step: 744/466, loss: 0.0510166771709919
2023-01-22 12:08:19.737931: step: 746/466, loss: 0.043876972049474716
2023-01-22 12:08:20.339234: step: 748/466, loss: 0.5507307052612305
2023-01-22 12:08:20.952173: step: 750/466, loss: 0.00416531041264534
2023-01-22 12:08:21.635993: step: 752/466, loss: 0.12272489070892334
2023-01-22 12:08:22.257020: step: 754/466, loss: 0.19147373735904694
2023-01-22 12:08:22.907559: step: 756/466, loss: 0.1723286509513855
2023-01-22 12:08:23.674500: step: 758/466, loss: 0.045513223856687546
2023-01-22 12:08:24.299240: step: 760/466, loss: 0.07953735440969467
2023-01-22 12:08:24.957027: step: 762/466, loss: 0.074615478515625
2023-01-22 12:08:25.570056: step: 764/466, loss: 0.48381203413009644
2023-01-22 12:08:26.265822: step: 766/466, loss: 0.04739003628492355
2023-01-22 12:08:26.914392: step: 768/466, loss: 0.04128978028893471
2023-01-22 12:08:27.554102: step: 770/466, loss: 0.3272797763347626
2023-01-22 12:08:28.171392: step: 772/466, loss: 0.00991341657936573
2023-01-22 12:08:28.808014: step: 774/466, loss: 0.0712292268872261
2023-01-22 12:08:29.548332: step: 776/466, loss: 0.05232344567775726
2023-01-22 12:08:30.288690: step: 778/466, loss: 0.18456433713436127
2023-01-22 12:08:30.918615: step: 780/466, loss: 0.8814983367919922
2023-01-22 12:08:31.571563: step: 782/466, loss: 0.2667369544506073
2023-01-22 12:08:32.242676: step: 784/466, loss: 0.10731915384531021
2023-01-22 12:08:32.833348: step: 786/466, loss: 0.006539562717080116
2023-01-22 12:08:33.481974: step: 788/466, loss: 0.13255411386489868
2023-01-22 12:08:34.213596: step: 790/466, loss: 0.033760346472263336
2023-01-22 12:08:34.889668: step: 792/466, loss: 0.03486182168126106
2023-01-22 12:08:35.485786: step: 794/466, loss: 0.08852153271436691
2023-01-22 12:08:36.171273: step: 796/466, loss: 0.03008638136088848
2023-01-22 12:08:36.766252: step: 798/466, loss: 0.04051116853952408
2023-01-22 12:08:37.407568: step: 800/466, loss: 0.10273575782775879
2023-01-22 12:08:38.118865: step: 802/466, loss: 0.09617326408624649
2023-01-22 12:08:38.818444: step: 804/466, loss: 0.05812990292906761
2023-01-22 12:08:39.408245: step: 806/466, loss: 0.06590338051319122
2023-01-22 12:08:40.057954: step: 808/466, loss: 0.05216827243566513
2023-01-22 12:08:40.721663: step: 810/466, loss: 0.01766282506287098
2023-01-22 12:08:41.328776: step: 812/466, loss: 0.04496309161186218
2023-01-22 12:08:41.982540: step: 814/466, loss: 0.1217527985572815
2023-01-22 12:08:42.651679: step: 816/466, loss: 0.15513049066066742
2023-01-22 12:08:43.283431: step: 818/466, loss: 0.024965690448880196
2023-01-22 12:08:43.931093: step: 820/466, loss: 0.13559532165527344
2023-01-22 12:08:44.568747: step: 822/466, loss: 0.04282497987151146
2023-01-22 12:08:45.190773: step: 824/466, loss: 0.007608668878674507
2023-01-22 12:08:45.923593: step: 826/466, loss: 0.049658216536045074
2023-01-22 12:08:46.556408: step: 828/466, loss: 0.5602688789367676
2023-01-22 12:08:47.115687: step: 830/466, loss: 0.14390172064304352
2023-01-22 12:08:47.684083: step: 832/466, loss: 0.018171867355704308
2023-01-22 12:08:48.265365: step: 834/466, loss: 0.19310128688812256
2023-01-22 12:08:48.905154: step: 836/466, loss: 0.0631764605641365
2023-01-22 12:08:49.470579: step: 838/466, loss: 0.0030215552542358637
2023-01-22 12:08:50.095897: step: 840/466, loss: 0.012556682340800762
2023-01-22 12:08:50.787019: step: 842/466, loss: 0.06738331913948059
2023-01-22 12:08:51.442531: step: 844/466, loss: 0.112983338534832
2023-01-22 12:08:52.093489: step: 846/466, loss: 0.04611273854970932
2023-01-22 12:08:52.725215: step: 848/466, loss: 0.08048969507217407
2023-01-22 12:08:53.357877: step: 850/466, loss: 0.06972993165254593
2023-01-22 12:08:53.993054: step: 852/466, loss: 0.06211049109697342
2023-01-22 12:08:54.736085: step: 854/466, loss: 0.012988202273845673
2023-01-22 12:08:55.417646: step: 856/466, loss: 0.3481960892677307
2023-01-22 12:08:56.031929: step: 858/466, loss: 0.026356499642133713
2023-01-22 12:08:56.686994: step: 860/466, loss: 0.017003362998366356
2023-01-22 12:08:57.317081: step: 862/466, loss: 0.07605820149183273
2023-01-22 12:08:57.993045: step: 864/466, loss: 0.027923665940761566
2023-01-22 12:08:58.648026: step: 866/466, loss: 0.035243429243564606
2023-01-22 12:08:59.307738: step: 868/466, loss: 0.024010855704545975
2023-01-22 12:08:59.943722: step: 870/466, loss: 0.30430516600608826
2023-01-22 12:09:00.587123: step: 872/466, loss: 0.021546028554439545
2023-01-22 12:09:01.283706: step: 874/466, loss: 0.056758493185043335
2023-01-22 12:09:01.924776: step: 876/466, loss: 0.01230048481374979
2023-01-22 12:09:02.623058: step: 878/466, loss: 0.2607000470161438
2023-01-22 12:09:03.397248: step: 880/466, loss: 0.02006744220852852
2023-01-22 12:09:04.009800: step: 882/466, loss: 0.2876383066177368
2023-01-22 12:09:04.638968: step: 884/466, loss: 0.8681106567382812
2023-01-22 12:09:05.205036: step: 886/466, loss: 0.015471463091671467
2023-01-22 12:09:05.784916: step: 888/466, loss: 0.017921268939971924
2023-01-22 12:09:06.426428: step: 890/466, loss: 0.12608306109905243
2023-01-22 12:09:07.064952: step: 892/466, loss: 0.11684809625148773
2023-01-22 12:09:07.755883: step: 894/466, loss: 0.03564350679516792
2023-01-22 12:09:08.371027: step: 896/466, loss: 0.06272316724061966
2023-01-22 12:09:09.064999: step: 898/466, loss: 0.021497024223208427
2023-01-22 12:09:09.716588: step: 900/466, loss: 0.11995331943035126
2023-01-22 12:09:10.407081: step: 902/466, loss: 0.013620620593428612
2023-01-22 12:09:11.102951: step: 904/466, loss: 0.3535931408405304
2023-01-22 12:09:11.706621: step: 906/466, loss: 0.04088161885738373
2023-01-22 12:09:12.370954: step: 908/466, loss: 0.0372898168861866
2023-01-22 12:09:13.041072: step: 910/466, loss: 0.0914231464266777
2023-01-22 12:09:13.702712: step: 912/466, loss: 0.24533428251743317
2023-01-22 12:09:14.376228: step: 914/466, loss: 0.8424860835075378
2023-01-22 12:09:15.026152: step: 916/466, loss: 0.03754405677318573
2023-01-22 12:09:15.684758: step: 918/466, loss: 1.756027340888977
2023-01-22 12:09:16.337064: step: 920/466, loss: 0.030273964628577232
2023-01-22 12:09:16.985429: step: 922/466, loss: 0.04297087714076042
2023-01-22 12:09:17.667173: step: 924/466, loss: 3.040848731994629
2023-01-22 12:09:18.386911: step: 926/466, loss: 0.16071191430091858
2023-01-22 12:09:19.044865: step: 928/466, loss: 0.026798753067851067
2023-01-22 12:09:19.645878: step: 930/466, loss: 0.014087713323533535
2023-01-22 12:09:20.359614: step: 932/466, loss: 0.24279646575450897
==================================================
Loss: 0.153
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3178390221402214, 'r': 0.32688567362428844, 'f1': 0.32229887745556596}, 'combined': 0.23748338338831174, 'epoch': 20}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3321255826246752, 'r': 0.2868629806604821, 'f1': 0.30783940200659965}, 'combined': 0.19275925172375868, 'epoch': 20}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2971572249589491, 'r': 0.34339421252371916, 'f1': 0.3186069542253521}, 'combined': 0.23476301890289103, 'epoch': 20}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3386342537033361, 'r': 0.2992084245266841, 'f1': 0.3177028599670015}, 'combined': 0.19688627941616993, 'epoch': 20}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2723052193645991, 'r': 0.34154411764705883, 'f1': 0.3030197811447811}, 'combined': 0.22327773347510185, 'epoch': 20}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.34046994601705843, 'r': 0.3038371037240838, 'f1': 0.32111212299936615}, 'combined': 0.21301497268274786, 'epoch': 20}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25, 'r': 0.36428571428571427, 'f1': 0.2965116279069767}, 'combined': 0.19767441860465113, 'epoch': 20}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3203125, 'r': 0.44565217391304346, 'f1': 0.3727272727272727}, 'combined': 0.18636363636363634, 'epoch': 20}
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': 20}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:12:06.706986: step: 2/466, loss: 0.2881387174129486
2023-01-22 12:12:07.388597: step: 4/466, loss: 0.10788802802562714
2023-01-22 12:12:08.053022: step: 6/466, loss: 0.060809627175331116
2023-01-22 12:12:08.685720: step: 8/466, loss: 0.07192735373973846
2023-01-22 12:12:09.354103: step: 10/466, loss: 0.035257741808891296
2023-01-22 12:12:09.943036: step: 12/466, loss: 0.042483024299144745
2023-01-22 12:12:10.597587: step: 14/466, loss: 0.1682446449995041
2023-01-22 12:12:11.150013: step: 16/466, loss: 0.02340201660990715
2023-01-22 12:12:11.832417: step: 18/466, loss: 0.05219205096364021
2023-01-22 12:12:12.429823: step: 20/466, loss: 0.1132228821516037
2023-01-22 12:12:13.007522: step: 22/466, loss: 0.10254693776369095
2023-01-22 12:12:13.618353: step: 24/466, loss: 0.031528573483228683
2023-01-22 12:12:14.232232: step: 26/466, loss: 1.483457088470459
2023-01-22 12:12:14.934264: step: 28/466, loss: 0.06329408288002014
2023-01-22 12:12:15.688477: step: 30/466, loss: 0.021416379138827324
2023-01-22 12:12:16.323725: step: 32/466, loss: 0.03439817950129509
2023-01-22 12:12:17.024549: step: 34/466, loss: 0.04783051088452339
2023-01-22 12:12:17.680426: step: 36/466, loss: 0.04394936561584473
2023-01-22 12:12:18.367821: step: 38/466, loss: 0.049832724034786224
2023-01-22 12:12:19.020133: step: 40/466, loss: 0.02321450226008892
2023-01-22 12:12:19.655175: step: 42/466, loss: 0.08828366547822952
2023-01-22 12:12:20.286293: step: 44/466, loss: 0.08183683454990387
2023-01-22 12:12:20.939198: step: 46/466, loss: 0.36498403549194336
2023-01-22 12:12:21.564144: step: 48/466, loss: 0.005173651501536369
2023-01-22 12:12:22.237491: step: 50/466, loss: 0.0514238141477108
2023-01-22 12:12:22.899107: step: 52/466, loss: 0.002969948807731271
2023-01-22 12:12:23.683931: step: 54/466, loss: 0.09550666809082031
2023-01-22 12:12:24.290110: step: 56/466, loss: 0.023871449753642082
2023-01-22 12:12:24.933461: step: 58/466, loss: 0.03539581596851349
2023-01-22 12:12:25.561426: step: 60/466, loss: 0.0438140369951725
2023-01-22 12:12:26.186734: step: 62/466, loss: 0.040493231266736984
2023-01-22 12:12:26.802004: step: 64/466, loss: 0.10182592272758484
2023-01-22 12:12:27.437137: step: 66/466, loss: 0.02831822633743286
2023-01-22 12:12:28.122114: step: 68/466, loss: 0.06584684550762177
2023-01-22 12:12:28.738600: step: 70/466, loss: 0.004456068854779005
2023-01-22 12:12:29.378040: step: 72/466, loss: 0.15545929968357086
2023-01-22 12:12:30.077191: step: 74/466, loss: 0.0639757588505745
2023-01-22 12:12:30.707259: step: 76/466, loss: 0.012895762920379639
2023-01-22 12:12:31.357365: step: 78/466, loss: 0.044522590935230255
2023-01-22 12:12:32.070269: step: 80/466, loss: 0.18327957391738892
2023-01-22 12:12:32.678278: step: 82/466, loss: 0.1578586846590042
2023-01-22 12:12:33.306450: step: 84/466, loss: 2.384281635284424
2023-01-22 12:12:33.859983: step: 86/466, loss: 0.11151908338069916
2023-01-22 12:12:34.566512: step: 88/466, loss: 0.10691257566213608
2023-01-22 12:12:35.255697: step: 90/466, loss: 0.10476025938987732
2023-01-22 12:12:35.874096: step: 92/466, loss: 0.01965838298201561
2023-01-22 12:12:36.534235: step: 94/466, loss: 0.1380435824394226
2023-01-22 12:12:37.240090: step: 96/466, loss: 0.01881014183163643
2023-01-22 12:12:37.834408: step: 98/466, loss: 0.03556925803422928
2023-01-22 12:12:38.483890: step: 100/466, loss: 0.32697975635528564
2023-01-22 12:12:39.154513: step: 102/466, loss: 0.03480343520641327
2023-01-22 12:12:39.786646: step: 104/466, loss: 0.08207301050424576
2023-01-22 12:12:40.424811: step: 106/466, loss: 0.2136201113462448
2023-01-22 12:12:41.014733: step: 108/466, loss: 0.09086485207080841
2023-01-22 12:12:41.646589: step: 110/466, loss: 0.050858333706855774
2023-01-22 12:12:42.335592: step: 112/466, loss: 0.09101345390081406
2023-01-22 12:12:43.023784: step: 114/466, loss: 0.025258095934987068
2023-01-22 12:12:43.658134: step: 116/466, loss: 0.05563211441040039
2023-01-22 12:12:44.283138: step: 118/466, loss: 0.0823717713356018
2023-01-22 12:12:44.905713: step: 120/466, loss: 0.029101431369781494
2023-01-22 12:12:45.547438: step: 122/466, loss: 0.021514972671866417
2023-01-22 12:12:46.128895: step: 124/466, loss: 0.03122498281300068
2023-01-22 12:12:46.758840: step: 126/466, loss: 0.07634158432483673
2023-01-22 12:12:47.365631: step: 128/466, loss: 0.04212908074259758
2023-01-22 12:12:47.993183: step: 130/466, loss: 0.009921550750732422
2023-01-22 12:12:48.684038: step: 132/466, loss: 0.01286023948341608
2023-01-22 12:12:49.331484: step: 134/466, loss: 0.04147264361381531
2023-01-22 12:12:50.038914: step: 136/466, loss: 0.06387916952371597
2023-01-22 12:12:50.692227: step: 138/466, loss: 0.03931007161736488
2023-01-22 12:12:51.355542: step: 140/466, loss: 0.0503489151597023
2023-01-22 12:12:51.937750: step: 142/466, loss: 0.0030978983268141747
2023-01-22 12:12:52.683974: step: 144/466, loss: 0.029595546424388885
2023-01-22 12:12:53.307283: step: 146/466, loss: 0.07707898318767548
2023-01-22 12:12:53.932603: step: 148/466, loss: 0.045399896800518036
2023-01-22 12:12:54.511344: step: 150/466, loss: 0.046740684658288956
2023-01-22 12:12:55.144579: step: 152/466, loss: 0.021156247705221176
2023-01-22 12:12:55.830971: step: 154/466, loss: 0.021989645436406136
2023-01-22 12:12:56.511396: step: 156/466, loss: 0.05270089954137802
2023-01-22 12:12:57.185887: step: 158/466, loss: 0.08426899462938309
2023-01-22 12:12:57.804175: step: 160/466, loss: 0.05149581655859947
2023-01-22 12:12:58.369880: step: 162/466, loss: 0.38246864080429077
2023-01-22 12:12:59.084812: step: 164/466, loss: 0.027103828266263008
2023-01-22 12:12:59.758034: step: 166/466, loss: 0.022400904446840286
2023-01-22 12:13:00.503386: step: 168/466, loss: 0.07104605436325073
2023-01-22 12:13:01.154887: step: 170/466, loss: 0.041852835565805435
2023-01-22 12:13:01.739492: step: 172/466, loss: 0.018567143008112907
2023-01-22 12:13:02.355037: step: 174/466, loss: 0.018758349120616913
2023-01-22 12:13:03.003853: step: 176/466, loss: 0.03230084851384163
2023-01-22 12:13:03.705025: step: 178/466, loss: 0.06489178538322449
2023-01-22 12:13:04.308850: step: 180/466, loss: 0.015959657728672028
2023-01-22 12:13:04.988418: step: 182/466, loss: 0.0533185712993145
2023-01-22 12:13:05.705551: step: 184/466, loss: 0.0024304878897964954
2023-01-22 12:13:06.312129: step: 186/466, loss: 0.0210149846971035
2023-01-22 12:13:06.902037: step: 188/466, loss: 0.02649274840950966
2023-01-22 12:13:07.581663: step: 190/466, loss: 0.02087913081049919
2023-01-22 12:13:08.272205: step: 192/466, loss: 0.07188748568296432
2023-01-22 12:13:08.951443: step: 194/466, loss: 0.061781302094459534
2023-01-22 12:13:09.581801: step: 196/466, loss: 0.005796810146421194
2023-01-22 12:13:10.193514: step: 198/466, loss: 0.02908952720463276
2023-01-22 12:13:10.850413: step: 200/466, loss: 0.015466309152543545
2023-01-22 12:13:11.494148: step: 202/466, loss: 0.014555848203599453
2023-01-22 12:13:12.145890: step: 204/466, loss: 0.26382020115852356
2023-01-22 12:13:12.824049: step: 206/466, loss: 0.08366383612155914
2023-01-22 12:13:13.410164: step: 208/466, loss: 0.02350272424519062
2023-01-22 12:13:14.029074: step: 210/466, loss: 0.007414946332573891
2023-01-22 12:13:14.689432: step: 212/466, loss: 0.1358312964439392
2023-01-22 12:13:15.276650: step: 214/466, loss: 0.023835817351937294
2023-01-22 12:13:15.963670: step: 216/466, loss: 0.03659604862332344
2023-01-22 12:13:16.596347: step: 218/466, loss: 0.18813088536262512
2023-01-22 12:13:17.294758: step: 220/466, loss: 0.18920515477657318
2023-01-22 12:13:17.937674: step: 222/466, loss: 0.08653844892978668
2023-01-22 12:13:18.558094: step: 224/466, loss: 0.032764118164777756
2023-01-22 12:13:19.194509: step: 226/466, loss: 0.032470885664224625
2023-01-22 12:13:19.858350: step: 228/466, loss: 0.04481193795800209
2023-01-22 12:13:20.509837: step: 230/466, loss: 0.09721400588750839
2023-01-22 12:13:21.132178: step: 232/466, loss: 0.04957348108291626
2023-01-22 12:13:21.758744: step: 234/466, loss: 0.0030713321175426245
2023-01-22 12:13:22.430954: step: 236/466, loss: 0.06352909654378891
2023-01-22 12:13:23.111586: step: 238/466, loss: 0.07602309435606003
2023-01-22 12:13:23.728489: step: 240/466, loss: 0.05582737177610397
2023-01-22 12:13:24.357206: step: 242/466, loss: 0.08120190352201462
2023-01-22 12:13:24.988364: step: 244/466, loss: 0.376693993806839
2023-01-22 12:13:25.691240: step: 246/466, loss: 0.4345664381980896
2023-01-22 12:13:26.289346: step: 248/466, loss: 0.04912075027823448
2023-01-22 12:13:26.918408: step: 250/466, loss: 0.05676799267530441
2023-01-22 12:13:27.626241: step: 252/466, loss: 0.015716781839728355
2023-01-22 12:13:28.270572: step: 254/466, loss: 0.4627186357975006
2023-01-22 12:13:28.899686: step: 256/466, loss: 0.013965928927063942
2023-01-22 12:13:29.505276: step: 258/466, loss: 0.0017522589769214392
2023-01-22 12:13:30.165431: step: 260/466, loss: 0.2042047530412674
2023-01-22 12:13:30.796061: step: 262/466, loss: 1.5125832557678223
2023-01-22 12:13:31.445457: step: 264/466, loss: 0.01134142279624939
2023-01-22 12:13:32.121910: step: 266/466, loss: 0.04114525020122528
2023-01-22 12:13:32.737818: step: 268/466, loss: 1.2687081098556519
2023-01-22 12:13:33.358908: step: 270/466, loss: 0.050007227808237076
2023-01-22 12:13:33.963363: step: 272/466, loss: 0.007330013904720545
2023-01-22 12:13:34.652825: step: 274/466, loss: 0.01399720087647438
2023-01-22 12:13:35.255234: step: 276/466, loss: 0.23334860801696777
2023-01-22 12:13:35.956271: step: 278/466, loss: 0.0035590690094977617
2023-01-22 12:13:36.630488: step: 280/466, loss: 0.03379582613706589
2023-01-22 12:13:37.221969: step: 282/466, loss: 0.037499357014894485
2023-01-22 12:13:37.837628: step: 284/466, loss: 0.021356504410505295
2023-01-22 12:13:38.469405: step: 286/466, loss: 0.12415394186973572
2023-01-22 12:13:39.070609: step: 288/466, loss: 0.03271034359931946
2023-01-22 12:13:39.747070: step: 290/466, loss: 0.04419732838869095
2023-01-22 12:13:40.446524: step: 292/466, loss: 0.10165723413228989
2023-01-22 12:13:41.226331: step: 294/466, loss: 0.17787736654281616
2023-01-22 12:13:41.886457: step: 296/466, loss: 0.07455705851316452
2023-01-22 12:13:42.558986: step: 298/466, loss: 0.017839863896369934
2023-01-22 12:13:43.306004: step: 300/466, loss: 0.03834192827343941
2023-01-22 12:13:44.000736: step: 302/466, loss: 0.02332369238138199
2023-01-22 12:13:44.635888: step: 304/466, loss: 0.03470650315284729
2023-01-22 12:13:45.259698: step: 306/466, loss: 0.04157089442014694
2023-01-22 12:13:45.957196: step: 308/466, loss: 0.03688224032521248
2023-01-22 12:13:46.588050: step: 310/466, loss: 0.047191083431243896
2023-01-22 12:13:47.272528: step: 312/466, loss: 1.0049819946289062
2023-01-22 12:13:47.869706: step: 314/466, loss: 0.03437206894159317
2023-01-22 12:13:48.472703: step: 316/466, loss: 0.1354771852493286
2023-01-22 12:13:49.130160: step: 318/466, loss: 0.0745021179318428
2023-01-22 12:13:49.759026: step: 320/466, loss: 0.024394439533352852
2023-01-22 12:13:50.423080: step: 322/466, loss: 0.0415155328810215
2023-01-22 12:13:51.084297: step: 324/466, loss: 0.03859580308198929
2023-01-22 12:13:51.676130: step: 326/466, loss: 0.1962372362613678
2023-01-22 12:13:52.366913: step: 328/466, loss: 0.3744176924228668
2023-01-22 12:13:52.985253: step: 330/466, loss: 0.12103322893381119
2023-01-22 12:13:53.664769: step: 332/466, loss: 0.07620114833116531
2023-01-22 12:13:54.458065: step: 334/466, loss: 0.08342382311820984
2023-01-22 12:13:55.069959: step: 336/466, loss: 0.04669582098722458
2023-01-22 12:13:55.671336: step: 338/466, loss: 0.01537937019020319
2023-01-22 12:13:56.387061: step: 340/466, loss: 0.0483732670545578
2023-01-22 12:13:57.041952: step: 342/466, loss: 0.01084462832659483
2023-01-22 12:13:57.711143: step: 344/466, loss: 0.13782353699207306
2023-01-22 12:13:58.368259: step: 346/466, loss: 0.054718755185604095
2023-01-22 12:13:58.992688: step: 348/466, loss: 0.03365980461239815
2023-01-22 12:13:59.650654: step: 350/466, loss: 0.20594370365142822
2023-01-22 12:14:00.320749: step: 352/466, loss: 0.04973024129867554
2023-01-22 12:14:00.939929: step: 354/466, loss: 0.03241625428199768
2023-01-22 12:14:01.636233: step: 356/466, loss: 0.01917138136923313
2023-01-22 12:14:02.293541: step: 358/466, loss: 0.04949241504073143
2023-01-22 12:14:02.929523: step: 360/466, loss: 0.04784351959824562
2023-01-22 12:14:03.585336: step: 362/466, loss: 0.25273874402046204
2023-01-22 12:14:04.246932: step: 364/466, loss: 0.596697211265564
2023-01-22 12:14:04.945483: step: 366/466, loss: 0.0008260474423877895
2023-01-22 12:14:05.627879: step: 368/466, loss: 0.25643035769462585
2023-01-22 12:14:06.227568: step: 370/466, loss: 0.09255601465702057
2023-01-22 12:14:06.931699: step: 372/466, loss: 0.05651896074414253
2023-01-22 12:14:07.539794: step: 374/466, loss: 0.039041806012392044
2023-01-22 12:14:08.399251: step: 376/466, loss: 0.1036134660243988
2023-01-22 12:14:09.033873: step: 378/466, loss: 0.14990819990634918
2023-01-22 12:14:09.692525: step: 380/466, loss: 0.02866818755865097
2023-01-22 12:14:10.367011: step: 382/466, loss: 0.2643183767795563
2023-01-22 12:14:11.005599: step: 384/466, loss: 0.3558858633041382
2023-01-22 12:14:11.719524: step: 386/466, loss: 0.043460335582494736
2023-01-22 12:14:12.345079: step: 388/466, loss: 0.03281353414058685
2023-01-22 12:14:13.017106: step: 390/466, loss: 0.14346811175346375
2023-01-22 12:14:13.745309: step: 392/466, loss: 0.7667785882949829
2023-01-22 12:14:14.389336: step: 394/466, loss: 0.025008998811244965
2023-01-22 12:14:14.985181: step: 396/466, loss: 0.02988959103822708
2023-01-22 12:14:15.552752: step: 398/466, loss: 0.38024312257766724
2023-01-22 12:14:16.213475: step: 400/466, loss: 0.03910621628165245
2023-01-22 12:14:16.894423: step: 402/466, loss: 0.0872785747051239
2023-01-22 12:14:17.521771: step: 404/466, loss: 0.048010170459747314
2023-01-22 12:14:18.159210: step: 406/466, loss: 0.07352911680936813
2023-01-22 12:14:18.833833: step: 408/466, loss: 0.022242622449994087
2023-01-22 12:14:19.462841: step: 410/466, loss: 0.007695019245147705
2023-01-22 12:14:20.124292: step: 412/466, loss: 0.027991732582449913
2023-01-22 12:14:20.824407: step: 414/466, loss: 0.013311603106558323
2023-01-22 12:14:21.486308: step: 416/466, loss: 0.016815369948744774
2023-01-22 12:14:22.148494: step: 418/466, loss: 0.06997986137866974
2023-01-22 12:14:22.805026: step: 420/466, loss: 0.039529308676719666
2023-01-22 12:14:23.493630: step: 422/466, loss: 0.057546790689229965
2023-01-22 12:14:24.124846: step: 424/466, loss: 0.024760199710726738
2023-01-22 12:14:24.756787: step: 426/466, loss: 0.020182352513074875
2023-01-22 12:14:25.471669: step: 428/466, loss: 0.019982418045401573
2023-01-22 12:14:26.153859: step: 430/466, loss: 0.04188135638833046
2023-01-22 12:14:26.756184: step: 432/466, loss: 0.033656615763902664
2023-01-22 12:14:27.387863: step: 434/466, loss: 0.02355225943028927
2023-01-22 12:14:28.034496: step: 436/466, loss: 0.0621369406580925
2023-01-22 12:14:28.667709: step: 438/466, loss: 0.1696689873933792
2023-01-22 12:14:29.370714: step: 440/466, loss: 0.084506556391716
2023-01-22 12:14:30.067572: step: 442/466, loss: 0.13824161887168884
2023-01-22 12:14:30.780352: step: 444/466, loss: 0.023126086220145226
2023-01-22 12:14:31.395282: step: 446/466, loss: 0.04749936982989311
2023-01-22 12:14:32.121918: step: 448/466, loss: 0.031942762434482574
2023-01-22 12:14:32.837005: step: 450/466, loss: 0.03469008207321167
2023-01-22 12:14:33.434082: step: 452/466, loss: 0.008654058910906315
2023-01-22 12:14:34.128667: step: 454/466, loss: 0.09825482219457626
2023-01-22 12:14:34.825645: step: 456/466, loss: 0.034265968948602676
2023-01-22 12:14:35.443089: step: 458/466, loss: 0.06974327564239502
2023-01-22 12:14:36.164792: step: 460/466, loss: 0.031080160290002823
2023-01-22 12:14:36.732929: step: 462/466, loss: 0.41150692105293274
2023-01-22 12:14:37.395142: step: 464/466, loss: 0.006570714525878429
2023-01-22 12:14:38.052490: step: 466/466, loss: 0.16019433736801147
2023-01-22 12:14:38.643867: step: 468/466, loss: 0.023206396028399467
2023-01-22 12:14:39.378485: step: 470/466, loss: 0.053858887404203415
2023-01-22 12:14:40.021079: step: 472/466, loss: 0.3436448276042938
2023-01-22 12:14:40.704353: step: 474/466, loss: 0.30463162064552307
2023-01-22 12:14:41.404155: step: 476/466, loss: 0.5427336096763611
2023-01-22 12:14:42.101343: step: 478/466, loss: 0.06205464527010918
2023-01-22 12:14:42.712403: step: 480/466, loss: 0.03354858234524727
2023-01-22 12:14:43.377881: step: 482/466, loss: 0.015020878054201603
2023-01-22 12:14:44.118252: step: 484/466, loss: 0.014658765867352486
2023-01-22 12:14:44.763745: step: 486/466, loss: 0.06817291676998138
2023-01-22 12:14:45.484592: step: 488/466, loss: 0.02162042073905468
2023-01-22 12:14:46.108079: step: 490/466, loss: 0.07436501979827881
2023-01-22 12:14:46.681712: step: 492/466, loss: 0.043860066682100296
2023-01-22 12:14:47.312464: step: 494/466, loss: 0.028184695169329643
2023-01-22 12:14:47.998113: step: 496/466, loss: 0.0674021914601326
2023-01-22 12:14:48.615168: step: 498/466, loss: 0.05346820876002312
2023-01-22 12:14:49.318608: step: 500/466, loss: 0.020384909585118294
2023-01-22 12:14:50.003967: step: 502/466, loss: 0.02656802535057068
2023-01-22 12:14:50.651467: step: 504/466, loss: 0.09113605320453644
2023-01-22 12:14:51.263576: step: 506/466, loss: 0.031240740790963173
2023-01-22 12:14:51.965921: step: 508/466, loss: 0.09123338013887405
2023-01-22 12:14:52.618657: step: 510/466, loss: 0.634196400642395
2023-01-22 12:14:53.230492: step: 512/466, loss: 0.04012421891093254
2023-01-22 12:14:53.868856: step: 514/466, loss: 0.0730554610490799
2023-01-22 12:14:54.562932: step: 516/466, loss: 0.009127141907811165
2023-01-22 12:14:55.192274: step: 518/466, loss: 0.02245831862092018
2023-01-22 12:14:55.835573: step: 520/466, loss: 0.11491833627223969
2023-01-22 12:14:56.475161: step: 522/466, loss: 0.014328841120004654
2023-01-22 12:14:57.103024: step: 524/466, loss: 0.13443446159362793
2023-01-22 12:14:57.739556: step: 526/466, loss: 0.01783270388841629
2023-01-22 12:14:58.419405: step: 528/466, loss: 0.026168670505285263
2023-01-22 12:14:59.148148: step: 530/466, loss: 0.006085870787501335
2023-01-22 12:14:59.797838: step: 532/466, loss: 0.03878147900104523
2023-01-22 12:15:00.401589: step: 534/466, loss: 0.02244793437421322
2023-01-22 12:15:01.057757: step: 536/466, loss: 0.05535934120416641
2023-01-22 12:15:01.672150: step: 538/466, loss: 0.020007774233818054
2023-01-22 12:15:02.354642: step: 540/466, loss: 0.23324796557426453
2023-01-22 12:15:03.020919: step: 542/466, loss: 0.01911095529794693
2023-01-22 12:15:03.662227: step: 544/466, loss: 0.08553896099328995
2023-01-22 12:15:04.359289: step: 546/466, loss: 0.010592618025839329
2023-01-22 12:15:04.992072: step: 548/466, loss: 0.020420879125595093
2023-01-22 12:15:05.646740: step: 550/466, loss: 0.22198089957237244
2023-01-22 12:15:06.295971: step: 552/466, loss: 0.005745941307395697
2023-01-22 12:15:06.934127: step: 554/466, loss: 0.1390320509672165
2023-01-22 12:15:07.586594: step: 556/466, loss: 0.0484815314412117
2023-01-22 12:15:08.220754: step: 558/466, loss: 0.03415696322917938
2023-01-22 12:15:08.891989: step: 560/466, loss: 0.049011725932359695
2023-01-22 12:15:09.548542: step: 562/466, loss: 0.07793086767196655
2023-01-22 12:15:10.228236: step: 564/466, loss: 0.02373851090669632
2023-01-22 12:15:10.803234: step: 566/466, loss: 0.0372571125626564
2023-01-22 12:15:11.428984: step: 568/466, loss: 0.21455547213554382
2023-01-22 12:15:12.060087: step: 570/466, loss: 0.03172042965888977
2023-01-22 12:15:12.709790: step: 572/466, loss: 0.01622224971652031
2023-01-22 12:15:13.337600: step: 574/466, loss: 0.05237264558672905
2023-01-22 12:15:13.999218: step: 576/466, loss: 0.045655809342861176
2023-01-22 12:15:14.666328: step: 578/466, loss: 0.020912673324346542
2023-01-22 12:15:15.293128: step: 580/466, loss: 0.8630627989768982
2023-01-22 12:15:15.960494: step: 582/466, loss: 0.0424136221408844
2023-01-22 12:15:16.597037: step: 584/466, loss: 0.03257325664162636
2023-01-22 12:15:17.299062: step: 586/466, loss: 0.034630049020051956
2023-01-22 12:15:17.945714: step: 588/466, loss: 0.6312510371208191
2023-01-22 12:15:18.611228: step: 590/466, loss: 0.044650305062532425
2023-01-22 12:15:19.246058: step: 592/466, loss: 0.010726863518357277
2023-01-22 12:15:19.978352: step: 594/466, loss: 0.040749356150627136
2023-01-22 12:15:20.620887: step: 596/466, loss: 0.06677427142858505
2023-01-22 12:15:21.314569: step: 598/466, loss: 0.05118778720498085
2023-01-22 12:15:21.978950: step: 600/466, loss: 0.0253734327852726
2023-01-22 12:15:22.612472: step: 602/466, loss: 0.04381844028830528
2023-01-22 12:15:23.248236: step: 604/466, loss: 0.04041266813874245
2023-01-22 12:15:23.927589: step: 606/466, loss: 0.1804942786693573
2023-01-22 12:15:24.576323: step: 608/466, loss: 0.016160905361175537
2023-01-22 12:15:25.201385: step: 610/466, loss: 0.04123891890048981
2023-01-22 12:15:25.851541: step: 612/466, loss: 0.03186152130365372
2023-01-22 12:15:26.413481: step: 614/466, loss: 0.041749026626348495
2023-01-22 12:15:27.039681: step: 616/466, loss: 0.046115558594465256
2023-01-22 12:15:27.619572: step: 618/466, loss: 0.17633561789989471
2023-01-22 12:15:28.226311: step: 620/466, loss: 0.28329288959503174
2023-01-22 12:15:28.862318: step: 622/466, loss: 0.015036552213132381
2023-01-22 12:15:29.568603: step: 624/466, loss: 0.17075170576572418
2023-01-22 12:15:30.185694: step: 626/466, loss: 0.025837387889623642
2023-01-22 12:15:30.808659: step: 628/466, loss: 0.06743304431438446
2023-01-22 12:15:31.508117: step: 630/466, loss: 0.16815988719463348
2023-01-22 12:15:32.157543: step: 632/466, loss: 0.08669286221265793
2023-01-22 12:15:32.805761: step: 634/466, loss: 0.03428836911916733
2023-01-22 12:15:33.492176: step: 636/466, loss: 0.214237779378891
2023-01-22 12:15:34.128028: step: 638/466, loss: 0.02262129820883274
2023-01-22 12:15:34.793691: step: 640/466, loss: 0.01413120049983263
2023-01-22 12:15:35.414687: step: 642/466, loss: 0.024058640003204346
2023-01-22 12:15:36.037991: step: 644/466, loss: 0.03418533504009247
2023-01-22 12:15:36.698448: step: 646/466, loss: 0.07237999141216278
2023-01-22 12:15:37.325372: step: 648/466, loss: 0.008366351947188377
2023-01-22 12:15:37.933710: step: 650/466, loss: 0.08939099311828613
2023-01-22 12:15:38.554142: step: 652/466, loss: 0.040893878787755966
2023-01-22 12:15:39.180834: step: 654/466, loss: 0.1322600394487381
2023-01-22 12:15:39.789446: step: 656/466, loss: 0.08454293757677078
2023-01-22 12:15:40.441151: step: 658/466, loss: 0.032387323677539825
2023-01-22 12:15:41.130678: step: 660/466, loss: 0.2031060755252838
2023-01-22 12:15:41.763467: step: 662/466, loss: 0.49967092275619507
2023-01-22 12:15:42.447899: step: 664/466, loss: 0.042758241295814514
2023-01-22 12:15:43.109925: step: 666/466, loss: 0.02878168784081936
2023-01-22 12:15:43.832225: step: 668/466, loss: 0.0734516903758049
2023-01-22 12:15:44.501950: step: 670/466, loss: 3.0360729694366455
2023-01-22 12:15:45.184862: step: 672/466, loss: 0.2565597891807556
2023-01-22 12:15:45.832886: step: 674/466, loss: 0.60455721616745
2023-01-22 12:15:46.519573: step: 676/466, loss: 0.05530927702784538
2023-01-22 12:15:47.195192: step: 678/466, loss: 0.07635991275310516
2023-01-22 12:15:47.787009: step: 680/466, loss: 0.04688085615634918
2023-01-22 12:15:48.403118: step: 682/466, loss: 0.016532668843865395
2023-01-22 12:15:49.091183: step: 684/466, loss: 0.06713685393333435
2023-01-22 12:15:49.711436: step: 686/466, loss: 0.028215663507580757
2023-01-22 12:15:50.371220: step: 688/466, loss: 0.027146853506565094
2023-01-22 12:15:50.992172: step: 690/466, loss: 0.04736965522170067
2023-01-22 12:15:51.641800: step: 692/466, loss: 0.03607270121574402
2023-01-22 12:15:52.335347: step: 694/466, loss: 0.04344771057367325
2023-01-22 12:15:52.961093: step: 696/466, loss: 0.004855440929532051
2023-01-22 12:15:53.601093: step: 698/466, loss: 0.05644207075238228
2023-01-22 12:15:54.258468: step: 700/466, loss: 0.2104901671409607
2023-01-22 12:15:54.958969: step: 702/466, loss: 0.11141925305128098
2023-01-22 12:15:55.657895: step: 704/466, loss: 0.0320793054997921
2023-01-22 12:15:56.396869: step: 706/466, loss: 0.013713311403989792
2023-01-22 12:15:56.962736: step: 708/466, loss: 0.3742595911026001
2023-01-22 12:15:57.578715: step: 710/466, loss: 0.027933279052376747
2023-01-22 12:15:58.209350: step: 712/466, loss: 0.049460165202617645
2023-01-22 12:15:58.771339: step: 714/466, loss: 0.005260720383375883
2023-01-22 12:15:59.383571: step: 716/466, loss: 0.04703853651881218
2023-01-22 12:16:00.061551: step: 718/466, loss: 0.12700912356376648
2023-01-22 12:16:00.773528: step: 720/466, loss: 0.04476194083690643
2023-01-22 12:16:01.425424: step: 722/466, loss: 0.8264212608337402
2023-01-22 12:16:02.075739: step: 724/466, loss: 0.007151505909860134
2023-01-22 12:16:02.698011: step: 726/466, loss: 0.032925426959991455
2023-01-22 12:16:03.358459: step: 728/466, loss: 0.09729457646608353
2023-01-22 12:16:03.986747: step: 730/466, loss: 0.015224629081785679
2023-01-22 12:16:04.635770: step: 732/466, loss: 0.023833435028791428
2023-01-22 12:16:05.236443: step: 734/466, loss: 0.04177038371562958
2023-01-22 12:16:05.900115: step: 736/466, loss: 0.012526067905128002
2023-01-22 12:16:06.543674: step: 738/466, loss: 0.21370099484920502
2023-01-22 12:16:07.112830: step: 740/466, loss: 0.04333192855119705
2023-01-22 12:16:07.750562: step: 742/466, loss: 0.019405148923397064
2023-01-22 12:16:08.363409: step: 744/466, loss: 0.047963518649339676
2023-01-22 12:16:09.042117: step: 746/466, loss: 0.09783299267292023
2023-01-22 12:16:09.656580: step: 748/466, loss: 0.1445675790309906
2023-01-22 12:16:10.330826: step: 750/466, loss: 0.07998822629451752
2023-01-22 12:16:10.969330: step: 752/466, loss: 0.03509335592389107
2023-01-22 12:16:11.603738: step: 754/466, loss: 0.042283378541469574
2023-01-22 12:16:12.189509: step: 756/466, loss: 0.16924165189266205
2023-01-22 12:16:12.866609: step: 758/466, loss: 0.003952855244278908
2023-01-22 12:16:13.550357: step: 760/466, loss: 0.07449666410684586
2023-01-22 12:16:14.214712: step: 762/466, loss: 0.0128124188631773
2023-01-22 12:16:14.904919: step: 764/466, loss: 0.5852197408676147
2023-01-22 12:16:15.595030: step: 766/466, loss: 0.10924971848726273
2023-01-22 12:16:16.331040: step: 768/466, loss: 0.013517715968191624
2023-01-22 12:16:16.939157: step: 770/466, loss: 0.040156129747629166
2023-01-22 12:16:17.544889: step: 772/466, loss: 0.26231157779693604
2023-01-22 12:16:18.268496: step: 774/466, loss: 0.035481423139572144
2023-01-22 12:16:18.881963: step: 776/466, loss: 0.8418871164321899
2023-01-22 12:16:19.577305: step: 778/466, loss: 0.027692481875419617
2023-01-22 12:16:20.190004: step: 780/466, loss: 0.05802244693040848
2023-01-22 12:16:20.865162: step: 782/466, loss: 0.10543683171272278
2023-01-22 12:16:21.452413: step: 784/466, loss: 0.031873684376478195
2023-01-22 12:16:22.103769: step: 786/466, loss: 0.10513757169246674
2023-01-22 12:16:22.790892: step: 788/466, loss: 0.08614762127399445
2023-01-22 12:16:23.429701: step: 790/466, loss: 0.11027763038873672
2023-01-22 12:16:24.074963: step: 792/466, loss: 0.1143607497215271
2023-01-22 12:16:24.762856: step: 794/466, loss: 0.17218486964702606
2023-01-22 12:16:25.388262: step: 796/466, loss: 0.08547357469797134
2023-01-22 12:16:26.185047: step: 798/466, loss: 0.03696130961179733
2023-01-22 12:16:26.882223: step: 800/466, loss: 0.13679207861423492
2023-01-22 12:16:27.549595: step: 802/466, loss: 0.06206807866692543
2023-01-22 12:16:28.166612: step: 804/466, loss: 0.01966715045273304
2023-01-22 12:16:28.830360: step: 806/466, loss: 0.09318049997091293
2023-01-22 12:16:29.528864: step: 808/466, loss: 0.02171410620212555
2023-01-22 12:16:30.071451: step: 810/466, loss: 0.012220603413879871
2023-01-22 12:16:30.701872: step: 812/466, loss: 0.03538200631737709
2023-01-22 12:16:31.428070: step: 814/466, loss: 0.04497019946575165
2023-01-22 12:16:32.086486: step: 816/466, loss: 0.08776964992284775
2023-01-22 12:16:32.765716: step: 818/466, loss: 0.049796875566244125
2023-01-22 12:16:33.385166: step: 820/466, loss: 0.11578883230686188
2023-01-22 12:16:34.059813: step: 822/466, loss: 0.02360844425857067
2023-01-22 12:16:34.741490: step: 824/466, loss: 0.07886414974927902
2023-01-22 12:16:35.360898: step: 826/466, loss: 0.2746346890926361
2023-01-22 12:16:36.067243: step: 828/466, loss: 0.053636591881513596
2023-01-22 12:16:36.690629: step: 830/466, loss: 0.0729004293680191
2023-01-22 12:16:37.367288: step: 832/466, loss: 0.013451708480715752
2023-01-22 12:16:38.047752: step: 834/466, loss: 0.031762100756168365
2023-01-22 12:16:38.625140: step: 836/466, loss: 0.024036163464188576
2023-01-22 12:16:39.265851: step: 838/466, loss: 0.04187922924757004
2023-01-22 12:16:39.895861: step: 840/466, loss: 0.016345703974366188
2023-01-22 12:16:40.537006: step: 842/466, loss: 0.02965148165822029
2023-01-22 12:16:41.211386: step: 844/466, loss: 0.050337281078100204
2023-01-22 12:16:41.815290: step: 846/466, loss: 0.005305310245603323
2023-01-22 12:16:42.558313: step: 848/466, loss: 0.05893997102975845
2023-01-22 12:16:43.178181: step: 850/466, loss: 0.017510700970888138
2023-01-22 12:16:43.826337: step: 852/466, loss: 0.043549079447984695
2023-01-22 12:16:44.483620: step: 854/466, loss: 0.05888461694121361
2023-01-22 12:16:45.175445: step: 856/466, loss: 0.12205497175455093
2023-01-22 12:16:45.802475: step: 858/466, loss: 0.035270705819129944
2023-01-22 12:16:46.426725: step: 860/466, loss: 0.014527016319334507
2023-01-22 12:16:47.107555: step: 862/466, loss: 0.031558044254779816
2023-01-22 12:16:47.775717: step: 864/466, loss: 0.04664739593863487
2023-01-22 12:16:48.410514: step: 866/466, loss: 0.08443605154752731
2023-01-22 12:16:49.027380: step: 868/466, loss: 0.11665617674589157
2023-01-22 12:16:49.717391: step: 870/466, loss: 0.06290258467197418
2023-01-22 12:16:50.331349: step: 872/466, loss: 0.01301049068570137
2023-01-22 12:16:50.990813: step: 874/466, loss: 0.031586259603500366
2023-01-22 12:16:51.750805: step: 876/466, loss: 0.0244061928242445
2023-01-22 12:16:52.399954: step: 878/466, loss: 0.05870399996638298
2023-01-22 12:16:53.026961: step: 880/466, loss: 0.007997308857738972
2023-01-22 12:16:53.687748: step: 882/466, loss: 0.16636857390403748
2023-01-22 12:16:54.305227: step: 884/466, loss: 0.030749928206205368
2023-01-22 12:16:54.985759: step: 886/466, loss: 0.014747374691069126
2023-01-22 12:16:55.612558: step: 888/466, loss: 0.05380203574895859
2023-01-22 12:16:56.253074: step: 890/466, loss: 0.057087745517492294
2023-01-22 12:16:56.937062: step: 892/466, loss: 0.5643709897994995
2023-01-22 12:16:57.628083: step: 894/466, loss: 0.10381991416215897
2023-01-22 12:16:58.279906: step: 896/466, loss: 0.044120799750089645
2023-01-22 12:16:58.992224: step: 898/466, loss: 0.051240790635347366
2023-01-22 12:16:59.719617: step: 900/466, loss: 0.1393282115459442
2023-01-22 12:17:00.343470: step: 902/466, loss: 0.03885339945554733
2023-01-22 12:17:01.037110: step: 904/466, loss: 0.04772276058793068
2023-01-22 12:17:01.702109: step: 906/466, loss: 0.029068568721413612
2023-01-22 12:17:02.382667: step: 908/466, loss: 0.013651649467647076
2023-01-22 12:17:03.100397: step: 910/466, loss: 0.13033856451511383
2023-01-22 12:17:03.740346: step: 912/466, loss: 0.011761067435145378
2023-01-22 12:17:04.372892: step: 914/466, loss: 0.49115467071533203
2023-01-22 12:17:05.111808: step: 916/466, loss: 0.02538359723985195
2023-01-22 12:17:05.745012: step: 918/466, loss: 0.061281025409698486
2023-01-22 12:17:06.405122: step: 920/466, loss: 0.27115190029144287
2023-01-22 12:17:07.033230: step: 922/466, loss: 0.06859371811151505
2023-01-22 12:17:07.733270: step: 924/466, loss: 0.0548187717795372
2023-01-22 12:17:08.385302: step: 926/466, loss: 0.06278951466083527
2023-01-22 12:17:09.010873: step: 928/466, loss: 0.038607917726039886
2023-01-22 12:17:09.616504: step: 930/466, loss: 0.02120407484471798
2023-01-22 12:17:10.286540: step: 932/466, loss: 0.3725205063819885
==================================================
Loss: 0.110
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31139763756742367, 'r': 0.3314878077330639, 'f1': 0.32112881374140567}, 'combined': 0.23662123117787784, 'epoch': 21}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3099156957022547, 'r': 0.2872594038684256, 'f1': 0.29815777001050636}, 'combined': 0.18669692140844793, 'epoch': 21}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29484131362165344, 'r': 0.34575319130584786, 'f1': 0.3182741167129814}, 'combined': 0.2345177702095652, 'epoch': 21}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3149280589305069, 'r': 0.29332649532155514, 'f1': 0.3037436979591431}, 'combined': 0.18823553112960978, 'epoch': 21}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2711423382336139, 'r': 0.3508900847729121, 'f1': 0.3059041764686926}, 'combined': 0.22540307739798401, 'epoch': 21}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.30717592895997353, 'r': 0.2907895096031576, 'f1': 0.29875819565359246}, 'combined': 0.19818612979000688, 'epoch': 21}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2925531914893617, 'r': 0.39285714285714285, 'f1': 0.3353658536585366}, 'combined': 0.22357723577235772, 'epoch': 21}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25, 'r': 0.358695652173913, 'f1': 0.2946428571428571}, 'combined': 0.14732142857142855, 'epoch': 21}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.36363636363636365, 'r': 0.27586206896551724, 'f1': 0.3137254901960784}, 'combined': 0.2091503267973856, 'epoch': 21}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:19:58.681752: step: 2/466, loss: 0.06524524092674255
2023-01-22 12:19:59.237943: step: 4/466, loss: 0.9549713730812073
2023-01-22 12:19:59.978163: step: 6/466, loss: 0.10257505625486374
2023-01-22 12:20:00.623496: step: 8/466, loss: 0.05847657844424248
2023-01-22 12:20:01.220321: step: 10/466, loss: 0.047362662851810455
2023-01-22 12:20:01.877701: step: 12/466, loss: 0.03749975562095642
2023-01-22 12:20:02.485233: step: 14/466, loss: 0.0317390151321888
2023-01-22 12:20:03.158043: step: 16/466, loss: 0.026071008294820786
2023-01-22 12:20:03.796964: step: 18/466, loss: 0.049456655979156494
2023-01-22 12:20:04.459799: step: 20/466, loss: 1.5443713665008545
2023-01-22 12:20:05.095333: step: 22/466, loss: 2.770106792449951
2023-01-22 12:20:05.809788: step: 24/466, loss: 0.012899891473352909
2023-01-22 12:20:06.487476: step: 26/466, loss: 0.03178015723824501
2023-01-22 12:20:07.065943: step: 28/466, loss: 0.006744012236595154
2023-01-22 12:20:07.674073: step: 30/466, loss: 0.01676984131336212
2023-01-22 12:20:08.355486: step: 32/466, loss: 0.03753257915377617
2023-01-22 12:20:09.041106: step: 34/466, loss: 0.05055082589387894
2023-01-22 12:20:09.637496: step: 36/466, loss: 0.006336488761007786
2023-01-22 12:20:10.259701: step: 38/466, loss: 0.01944642700254917
2023-01-22 12:20:10.939768: step: 40/466, loss: 0.08281132578849792
2023-01-22 12:20:11.582475: step: 42/466, loss: 0.03852911293506622
2023-01-22 12:20:12.262235: step: 44/466, loss: 0.11461681872606277
2023-01-22 12:20:12.890943: step: 46/466, loss: 0.05935616046190262
2023-01-22 12:20:13.536405: step: 48/466, loss: 0.07514059543609619
2023-01-22 12:20:14.171499: step: 50/466, loss: 0.015336104668676853
2023-01-22 12:20:14.796751: step: 52/466, loss: 0.011880473233759403
2023-01-22 12:20:15.434314: step: 54/466, loss: 0.04381778836250305
2023-01-22 12:20:16.147100: step: 56/466, loss: 0.07939602434635162
2023-01-22 12:20:16.763254: step: 58/466, loss: 0.002874930389225483
2023-01-22 12:20:17.407671: step: 60/466, loss: 0.011842741630971432
2023-01-22 12:20:18.015283: step: 62/466, loss: 0.324677437543869
2023-01-22 12:20:18.675788: step: 64/466, loss: 0.26164790987968445
2023-01-22 12:20:19.265315: step: 66/466, loss: 0.04579608887434006
2023-01-22 12:20:19.945715: step: 68/466, loss: 0.8473932147026062
2023-01-22 12:20:20.628029: step: 70/466, loss: 0.0588836707174778
2023-01-22 12:20:21.284518: step: 72/466, loss: 0.029760386794805527
2023-01-22 12:20:21.899385: step: 74/466, loss: 0.05991767719388008
2023-01-22 12:20:22.549278: step: 76/466, loss: 0.0347471684217453
2023-01-22 12:20:23.268659: step: 78/466, loss: 0.11526650935411453
2023-01-22 12:20:23.879412: step: 80/466, loss: 0.01211107149720192
2023-01-22 12:20:24.498763: step: 82/466, loss: 0.06731019914150238
2023-01-22 12:20:25.152197: step: 84/466, loss: 0.020972801372408867
2023-01-22 12:20:25.802052: step: 86/466, loss: 0.07082726061344147
2023-01-22 12:20:26.506678: step: 88/466, loss: 0.010794714093208313
2023-01-22 12:20:27.119580: step: 90/466, loss: 0.024650154635310173
2023-01-22 12:20:27.769960: step: 92/466, loss: 0.019832108169794083
2023-01-22 12:20:28.402608: step: 94/466, loss: 0.009915913455188274
2023-01-22 12:20:29.055911: step: 96/466, loss: 0.08327384293079376
2023-01-22 12:20:29.759948: step: 98/466, loss: 0.09288603067398071
2023-01-22 12:20:30.380105: step: 100/466, loss: 0.013974449597299099
2023-01-22 12:20:31.068948: step: 102/466, loss: 0.04457048699259758
2023-01-22 12:20:31.659331: step: 104/466, loss: 0.4012412428855896
2023-01-22 12:20:32.252033: step: 106/466, loss: 0.1333913803100586
2023-01-22 12:20:32.841989: step: 108/466, loss: 0.07510756701231003
2023-01-22 12:20:33.532639: step: 110/466, loss: 0.008668056689202785
2023-01-22 12:20:34.201076: step: 112/466, loss: 0.03645727410912514
2023-01-22 12:20:34.836918: step: 114/466, loss: 0.08467361330986023
2023-01-22 12:20:35.508771: step: 116/466, loss: 0.07070888578891754
2023-01-22 12:20:36.122415: step: 118/466, loss: 0.020062562078237534
2023-01-22 12:20:36.695936: step: 120/466, loss: 0.016420189291238785
2023-01-22 12:20:37.348182: step: 122/466, loss: 0.07351458072662354
2023-01-22 12:20:37.987374: step: 124/466, loss: 0.04343784973025322
2023-01-22 12:20:38.639908: step: 126/466, loss: 0.007278779987245798
2023-01-22 12:20:39.273567: step: 128/466, loss: 0.10511089116334915
2023-01-22 12:20:39.954269: step: 130/466, loss: 0.0025861081667244434
2023-01-22 12:20:40.603526: step: 132/466, loss: 0.046648066490888596
2023-01-22 12:20:41.278856: step: 134/466, loss: 0.153986856341362
2023-01-22 12:20:41.980869: step: 136/466, loss: 0.01985854096710682
2023-01-22 12:20:42.587765: step: 138/466, loss: 0.015150061808526516
2023-01-22 12:20:43.242016: step: 140/466, loss: 0.17932286858558655
2023-01-22 12:20:43.862195: step: 142/466, loss: 0.013499271124601364
2023-01-22 12:20:44.532279: step: 144/466, loss: 0.30745261907577515
2023-01-22 12:20:45.174939: step: 146/466, loss: 0.014704683795571327
2023-01-22 12:20:45.850873: step: 148/466, loss: 0.12307847291231155
2023-01-22 12:20:46.463828: step: 150/466, loss: 0.004720141179859638
2023-01-22 12:20:47.235470: step: 152/466, loss: 0.043396204710006714
2023-01-22 12:20:47.854392: step: 154/466, loss: 0.02459942363202572
2023-01-22 12:20:48.537175: step: 156/466, loss: 0.06305425614118576
2023-01-22 12:20:49.105621: step: 158/466, loss: 0.031243721023201942
2023-01-22 12:20:49.733990: step: 160/466, loss: 0.05132858082652092
2023-01-22 12:20:50.362448: step: 162/466, loss: 0.07695545256137848
2023-01-22 12:20:50.995293: step: 164/466, loss: 0.4492061734199524
2023-01-22 12:20:51.632512: step: 166/466, loss: 0.02572566270828247
2023-01-22 12:20:52.302544: step: 168/466, loss: 0.00399467209354043
2023-01-22 12:20:52.918924: step: 170/466, loss: 0.0033108617644757032
2023-01-22 12:20:53.532429: step: 172/466, loss: 0.032420262694358826
2023-01-22 12:20:54.123454: step: 174/466, loss: 0.02495727315545082
2023-01-22 12:20:54.796505: step: 176/466, loss: 0.024452194571495056
2023-01-22 12:20:55.420212: step: 178/466, loss: 0.044989731162786484
2023-01-22 12:20:56.058392: step: 180/466, loss: 0.06311078369617462
2023-01-22 12:20:56.742244: step: 182/466, loss: 0.1478491574525833
2023-01-22 12:20:57.316638: step: 184/466, loss: 0.03128127381205559
2023-01-22 12:20:57.964751: step: 186/466, loss: 0.011426354758441448
2023-01-22 12:20:58.591732: step: 188/466, loss: 0.030414700508117676
2023-01-22 12:20:59.231502: step: 190/466, loss: 0.04100172221660614
2023-01-22 12:20:59.844848: step: 192/466, loss: 0.03840643912553787
2023-01-22 12:21:00.486131: step: 194/466, loss: 0.8019331097602844
2023-01-22 12:21:01.165393: step: 196/466, loss: 0.05144786834716797
2023-01-22 12:21:01.796225: step: 198/466, loss: 0.03573480620980263
2023-01-22 12:21:02.446158: step: 200/466, loss: 0.2057233452796936
2023-01-22 12:21:03.038368: step: 202/466, loss: 0.03584648296236992
2023-01-22 12:21:03.761425: step: 204/466, loss: 0.02789546735584736
2023-01-22 12:21:04.452206: step: 206/466, loss: 0.04161622375249863
2023-01-22 12:21:05.111423: step: 208/466, loss: 0.032335065305233
2023-01-22 12:21:05.733348: step: 210/466, loss: 0.43722274899482727
2023-01-22 12:21:06.396824: step: 212/466, loss: 0.015449839644134045
2023-01-22 12:21:07.068054: step: 214/466, loss: 0.027153804898262024
2023-01-22 12:21:07.666760: step: 216/466, loss: 0.028914693742990494
2023-01-22 12:21:08.336633: step: 218/466, loss: 0.03848309814929962
2023-01-22 12:21:08.996096: step: 220/466, loss: 0.04102660343050957
2023-01-22 12:21:09.623247: step: 222/466, loss: 0.2741301953792572
2023-01-22 12:21:10.303438: step: 224/466, loss: 0.03221369534730911
2023-01-22 12:21:10.976293: step: 226/466, loss: 0.0764458030462265
2023-01-22 12:21:11.625509: step: 228/466, loss: 0.03933442011475563
2023-01-22 12:21:12.259378: step: 230/466, loss: 0.03705897182226181
2023-01-22 12:21:12.880692: step: 232/466, loss: 0.006504240911453962
2023-01-22 12:21:13.541317: step: 234/466, loss: 0.05261344462633133
2023-01-22 12:21:14.185070: step: 236/466, loss: 0.08687302470207214
2023-01-22 12:21:14.879296: step: 238/466, loss: 0.05586743727326393
2023-01-22 12:21:15.502119: step: 240/466, loss: 0.0024894988164305687
2023-01-22 12:21:16.148600: step: 242/466, loss: 0.3717498481273651
2023-01-22 12:21:16.816657: step: 244/466, loss: 0.05251733958721161
2023-01-22 12:21:17.409433: step: 246/466, loss: 0.006758150178939104
2023-01-22 12:21:18.083415: step: 248/466, loss: 0.10216856747865677
2023-01-22 12:21:18.799055: step: 250/466, loss: 0.009869629517197609
2023-01-22 12:21:19.506626: step: 252/466, loss: 0.05833861976861954
2023-01-22 12:21:20.145668: step: 254/466, loss: 0.01736012101173401
2023-01-22 12:21:20.751363: step: 256/466, loss: 0.022860318422317505
2023-01-22 12:21:21.378322: step: 258/466, loss: 0.009119870141148567
2023-01-22 12:21:21.970149: step: 260/466, loss: 0.015188897959887981
2023-01-22 12:21:22.609810: step: 262/466, loss: 0.3766849935054779
2023-01-22 12:21:23.275792: step: 264/466, loss: 0.08701756596565247
2023-01-22 12:21:23.917010: step: 266/466, loss: 0.011309411376714706
2023-01-22 12:21:24.546063: step: 268/466, loss: 0.0732068195939064
2023-01-22 12:21:25.206221: step: 270/466, loss: 0.01978411339223385
2023-01-22 12:21:25.899144: step: 272/466, loss: 0.1555345356464386
2023-01-22 12:21:26.580819: step: 274/466, loss: 0.3639795780181885
2023-01-22 12:21:27.296794: step: 276/466, loss: 0.15518170595169067
2023-01-22 12:21:27.958892: step: 278/466, loss: 0.027007892727851868
2023-01-22 12:21:28.609850: step: 280/466, loss: 0.09517539292573929
2023-01-22 12:21:29.253985: step: 282/466, loss: 0.03286255896091461
2023-01-22 12:21:29.890816: step: 284/466, loss: 0.0063650342635810375
2023-01-22 12:21:30.578237: step: 286/466, loss: 0.045704491436481476
2023-01-22 12:21:31.214294: step: 288/466, loss: 0.00865288358181715
2023-01-22 12:21:31.896371: step: 290/466, loss: 0.13274767994880676
2023-01-22 12:21:32.512191: step: 292/466, loss: 0.056273847818374634
2023-01-22 12:21:33.111142: step: 294/466, loss: 0.038613658398389816
2023-01-22 12:21:33.812588: step: 296/466, loss: 0.07675481587648392
2023-01-22 12:21:34.478540: step: 298/466, loss: 0.10594279319047928
2023-01-22 12:21:35.150204: step: 300/466, loss: 0.029124725610017776
2023-01-22 12:21:35.789978: step: 302/466, loss: 0.08076826483011246
2023-01-22 12:21:36.420179: step: 304/466, loss: 0.008677887730300426
2023-01-22 12:21:37.100657: step: 306/466, loss: 0.04437677562236786
2023-01-22 12:21:37.734295: step: 308/466, loss: 0.03545172140002251
2023-01-22 12:21:38.388461: step: 310/466, loss: 0.0892721489071846
2023-01-22 12:21:39.025508: step: 312/466, loss: 0.09720361232757568
2023-01-22 12:21:39.665126: step: 314/466, loss: 0.02379939705133438
2023-01-22 12:21:40.302807: step: 316/466, loss: 0.07661573588848114
2023-01-22 12:21:40.962656: step: 318/466, loss: 0.18681415915489197
2023-01-22 12:21:41.633421: step: 320/466, loss: 0.0562223419547081
2023-01-22 12:21:42.239458: step: 322/466, loss: 0.056488998234272
2023-01-22 12:21:42.877822: step: 324/466, loss: 0.016898782923817635
2023-01-22 12:21:43.543378: step: 326/466, loss: 0.015045711770653725
2023-01-22 12:21:44.124208: step: 328/466, loss: 0.012584555894136429
2023-01-22 12:21:44.864248: step: 330/466, loss: 0.027717135846614838
2023-01-22 12:21:45.560174: step: 332/466, loss: 0.033037345856428146
2023-01-22 12:21:46.209650: step: 334/466, loss: 0.06914247572422028
2023-01-22 12:21:46.889650: step: 336/466, loss: 0.06818067282438278
2023-01-22 12:21:47.540120: step: 338/466, loss: 0.041885361075401306
2023-01-22 12:21:48.225058: step: 340/466, loss: 0.019851483404636383
2023-01-22 12:21:48.877484: step: 342/466, loss: 0.01451868750154972
2023-01-22 12:21:49.479574: step: 344/466, loss: 0.015311257913708687
2023-01-22 12:21:50.107177: step: 346/466, loss: 0.04596361145377159
2023-01-22 12:21:50.735770: step: 348/466, loss: 0.007450594566762447
2023-01-22 12:21:51.453840: step: 350/466, loss: 0.003928270190954208
2023-01-22 12:21:52.049290: step: 352/466, loss: 0.035604193806648254
2023-01-22 12:21:52.794658: step: 354/466, loss: 0.023971788585186005
2023-01-22 12:21:53.442490: step: 356/466, loss: 0.3693704307079315
2023-01-22 12:21:54.119133: step: 358/466, loss: 0.031583916395902634
2023-01-22 12:21:54.761133: step: 360/466, loss: 0.05496159940958023
2023-01-22 12:21:55.360064: step: 362/466, loss: 0.06164189800620079
2023-01-22 12:21:55.954520: step: 364/466, loss: 0.3457597494125366
2023-01-22 12:21:56.625325: step: 366/466, loss: 0.10331287235021591
2023-01-22 12:21:57.223735: step: 368/466, loss: 0.08303102850914001
2023-01-22 12:21:57.884680: step: 370/466, loss: 0.040373966097831726
2023-01-22 12:21:58.530234: step: 372/466, loss: 0.4742472767829895
2023-01-22 12:21:59.227181: step: 374/466, loss: 0.04618077352643013
2023-01-22 12:21:59.831861: step: 376/466, loss: 0.014955085702240467
2023-01-22 12:22:00.499196: step: 378/466, loss: 0.020503893494606018
2023-01-22 12:22:01.131401: step: 380/466, loss: 0.0315471813082695
2023-01-22 12:22:01.812407: step: 382/466, loss: 0.0067911832593381405
2023-01-22 12:22:02.451017: step: 384/466, loss: 0.03241651877760887
2023-01-22 12:22:03.030687: step: 386/466, loss: 0.03235870972275734
2023-01-22 12:22:03.728533: step: 388/466, loss: 0.07316027581691742
2023-01-22 12:22:04.420907: step: 390/466, loss: 0.11621598899364471
2023-01-22 12:22:05.073950: step: 392/466, loss: 0.03541046753525734
2023-01-22 12:22:05.728251: step: 394/466, loss: 0.02560034766793251
2023-01-22 12:22:06.361052: step: 396/466, loss: 0.032955411821603775
2023-01-22 12:22:06.981011: step: 398/466, loss: 0.2330137938261032
2023-01-22 12:22:07.645043: step: 400/466, loss: 0.1967945694923401
2023-01-22 12:22:08.330318: step: 402/466, loss: 0.03604523837566376
2023-01-22 12:22:08.894467: step: 404/466, loss: 0.1295190453529358
2023-01-22 12:22:09.538913: step: 406/466, loss: 0.05102947726845741
2023-01-22 12:22:10.299452: step: 408/466, loss: 0.1345944106578827
2023-01-22 12:22:10.996592: step: 410/466, loss: 0.05486585572361946
2023-01-22 12:22:11.648132: step: 412/466, loss: 0.05415716767311096
2023-01-22 12:22:12.414222: step: 414/466, loss: 0.03243786841630936
2023-01-22 12:22:13.036666: step: 416/466, loss: 0.9294023513793945
2023-01-22 12:22:13.686285: step: 418/466, loss: 0.03535958379507065
2023-01-22 12:22:14.355402: step: 420/466, loss: 0.0102820610627532
2023-01-22 12:22:14.984515: step: 422/466, loss: 0.27872762084007263
2023-01-22 12:22:15.645988: step: 424/466, loss: 0.014268352650105953
2023-01-22 12:22:16.360619: step: 426/466, loss: 0.055146560072898865
2023-01-22 12:22:16.966167: step: 428/466, loss: 0.05941939726471901
2023-01-22 12:22:17.621694: step: 430/466, loss: 0.0571625716984272
2023-01-22 12:22:18.242914: step: 432/466, loss: 0.1478642076253891
2023-01-22 12:22:18.850815: step: 434/466, loss: 0.017696944996714592
2023-01-22 12:22:19.519909: step: 436/466, loss: 0.02196957729756832
2023-01-22 12:22:20.086014: step: 438/466, loss: 0.03287990763783455
2023-01-22 12:22:20.660234: step: 440/466, loss: 0.3364804685115814
2023-01-22 12:22:21.315541: step: 442/466, loss: 0.018891671672463417
2023-01-22 12:22:22.002495: step: 444/466, loss: 0.079230397939682
2023-01-22 12:22:22.654437: step: 446/466, loss: 0.14929592609405518
2023-01-22 12:22:23.308422: step: 448/466, loss: 0.0891253799200058
2023-01-22 12:22:24.029627: step: 450/466, loss: 0.008315548300743103
2023-01-22 12:22:24.641302: step: 452/466, loss: 0.1016860380768776
2023-01-22 12:22:25.279785: step: 454/466, loss: 0.07582006603479385
2023-01-22 12:22:25.912537: step: 456/466, loss: 0.009356861934065819
2023-01-22 12:22:26.587957: step: 458/466, loss: 0.059819843620061874
2023-01-22 12:22:27.238752: step: 460/466, loss: 0.12198459357023239
2023-01-22 12:22:27.904399: step: 462/466, loss: 0.01760128140449524
2023-01-22 12:22:28.515124: step: 464/466, loss: 0.08083579689264297
2023-01-22 12:22:29.117350: step: 466/466, loss: 0.05634992569684982
2023-01-22 12:22:29.751632: step: 468/466, loss: 0.010742071084678173
2023-01-22 12:22:30.373028: step: 470/466, loss: 0.038598641753196716
2023-01-22 12:22:31.065896: step: 472/466, loss: 0.08225518465042114
2023-01-22 12:22:31.683460: step: 474/466, loss: 0.066253662109375
2023-01-22 12:22:32.261710: step: 476/466, loss: 0.004400709178298712
2023-01-22 12:22:32.878018: step: 478/466, loss: 0.019654320552945137
2023-01-22 12:22:33.523420: step: 480/466, loss: 0.029162848368287086
2023-01-22 12:22:34.187394: step: 482/466, loss: 0.006798680406063795
2023-01-22 12:22:34.804310: step: 484/466, loss: 0.11523490399122238
2023-01-22 12:22:35.499701: step: 486/466, loss: 0.0820143073797226
2023-01-22 12:22:36.150054: step: 488/466, loss: 0.016324078664183617
2023-01-22 12:22:36.772761: step: 490/466, loss: 0.011203078553080559
2023-01-22 12:22:37.376547: step: 492/466, loss: 0.07054407149553299
2023-01-22 12:22:37.960295: step: 494/466, loss: 0.026088794693350792
2023-01-22 12:22:38.603460: step: 496/466, loss: 0.01417471095919609
2023-01-22 12:22:39.297306: step: 498/466, loss: 0.473919153213501
2023-01-22 12:22:39.946700: step: 500/466, loss: 0.011972896754741669
2023-01-22 12:22:40.697571: step: 502/466, loss: 0.028252488002181053
2023-01-22 12:22:41.387869: step: 504/466, loss: 0.019589383155107498
2023-01-22 12:22:42.130603: step: 506/466, loss: 0.18996228277683258
2023-01-22 12:22:42.811936: step: 508/466, loss: 0.04515201225876808
2023-01-22 12:22:43.427838: step: 510/466, loss: 0.08754381537437439
2023-01-22 12:22:44.098283: step: 512/466, loss: 0.002444115001708269
2023-01-22 12:22:44.816698: step: 514/466, loss: 0.14031344652175903
2023-01-22 12:22:45.484036: step: 516/466, loss: 0.04026828706264496
2023-01-22 12:22:46.112376: step: 518/466, loss: 0.13847778737545013
2023-01-22 12:22:46.724859: step: 520/466, loss: 0.006101786624640226
2023-01-22 12:22:47.350319: step: 522/466, loss: 0.03475275635719299
2023-01-22 12:22:47.943939: step: 524/466, loss: 0.010136638768017292
2023-01-22 12:22:48.616851: step: 526/466, loss: 0.09662459045648575
2023-01-22 12:22:49.231611: step: 528/466, loss: 0.09632852673530579
2023-01-22 12:22:49.833331: step: 530/466, loss: 0.04891626909375191
2023-01-22 12:22:50.459484: step: 532/466, loss: 0.02533416822552681
2023-01-22 12:22:51.166987: step: 534/466, loss: 0.06768819689750671
2023-01-22 12:22:51.785622: step: 536/466, loss: 0.037999678403139114
2023-01-22 12:22:52.417758: step: 538/466, loss: 0.16249126195907593
2023-01-22 12:22:53.131960: step: 540/466, loss: 0.05323609337210655
2023-01-22 12:22:53.817042: step: 542/466, loss: 0.03427635878324509
2023-01-22 12:22:54.461992: step: 544/466, loss: 0.029624156653881073
2023-01-22 12:22:55.201623: step: 546/466, loss: 0.5451293587684631
2023-01-22 12:22:55.826116: step: 548/466, loss: 0.028565261512994766
2023-01-22 12:22:56.451033: step: 550/466, loss: 0.05299180746078491
2023-01-22 12:22:57.099921: step: 552/466, loss: 0.053857531398534775
2023-01-22 12:22:57.763967: step: 554/466, loss: 0.0026278712321072817
2023-01-22 12:22:58.482512: step: 556/466, loss: 0.04956957325339317
2023-01-22 12:22:59.131331: step: 558/466, loss: 0.048391908407211304
2023-01-22 12:22:59.866765: step: 560/466, loss: 0.053652457892894745
2023-01-22 12:23:00.543830: step: 562/466, loss: 0.05441490560770035
2023-01-22 12:23:01.211380: step: 564/466, loss: 0.00899538304656744
2023-01-22 12:23:01.825382: step: 566/466, loss: 0.30511531233787537
2023-01-22 12:23:02.461437: step: 568/466, loss: 0.025552192702889442
2023-01-22 12:23:03.093343: step: 570/466, loss: 0.17114883661270142
2023-01-22 12:23:03.776530: step: 572/466, loss: 0.0558360256254673
2023-01-22 12:23:04.468755: step: 574/466, loss: 0.032410457730293274
2023-01-22 12:23:05.141212: step: 576/466, loss: 0.0480712465941906
2023-01-22 12:23:05.854818: step: 578/466, loss: 0.026203026995062828
2023-01-22 12:23:06.470891: step: 580/466, loss: 0.0036527966149151325
2023-01-22 12:23:07.143228: step: 582/466, loss: 0.006195830646902323
2023-01-22 12:23:07.770551: step: 584/466, loss: 0.10995900630950928
2023-01-22 12:23:08.388199: step: 586/466, loss: 0.02922908402979374
2023-01-22 12:23:08.997739: step: 588/466, loss: 0.039502378553152084
2023-01-22 12:23:09.617462: step: 590/466, loss: 0.05805331841111183
2023-01-22 12:23:10.220981: step: 592/466, loss: 0.026140891015529633
2023-01-22 12:23:10.834572: step: 594/466, loss: 0.049084533005952835
2023-01-22 12:23:11.557785: step: 596/466, loss: 0.09888540953397751
2023-01-22 12:23:12.224997: step: 598/466, loss: 0.016056597232818604
2023-01-22 12:23:12.898210: step: 600/466, loss: 0.03200465440750122
2023-01-22 12:23:13.518306: step: 602/466, loss: 0.03161884844303131
2023-01-22 12:23:14.158907: step: 604/466, loss: 0.1447422206401825
2023-01-22 12:23:14.784746: step: 606/466, loss: 0.027576405555009842
2023-01-22 12:23:15.521416: step: 608/466, loss: 0.05594842508435249
2023-01-22 12:23:16.168387: step: 610/466, loss: 0.012763570062816143
2023-01-22 12:23:16.788084: step: 612/466, loss: 1.0796951055526733
2023-01-22 12:23:17.421425: step: 614/466, loss: 0.03139471262693405
2023-01-22 12:23:18.098549: step: 616/466, loss: 0.07075747102499008
2023-01-22 12:23:18.730890: step: 618/466, loss: 0.03813979774713516
2023-01-22 12:23:19.425194: step: 620/466, loss: 0.08887746185064316
2023-01-22 12:23:20.064400: step: 622/466, loss: 2.5260872840881348
2023-01-22 12:23:20.873772: step: 624/466, loss: 0.01851993054151535
2023-01-22 12:23:21.680606: step: 626/466, loss: 0.05724343657493591
2023-01-22 12:23:22.319371: step: 628/466, loss: 0.012389592826366425
2023-01-22 12:23:22.877549: step: 630/466, loss: 0.015039799734950066
2023-01-22 12:23:23.510628: step: 632/466, loss: 0.03112381137907505
2023-01-22 12:23:24.235883: step: 634/466, loss: 0.016538362950086594
2023-01-22 12:23:24.845882: step: 636/466, loss: 0.01323335338383913
2023-01-22 12:23:25.491826: step: 638/466, loss: 0.033239446580410004
2023-01-22 12:23:26.138072: step: 640/466, loss: 0.0349995419383049
2023-01-22 12:23:26.891353: step: 642/466, loss: 0.12855033576488495
2023-01-22 12:23:27.601318: step: 644/466, loss: 0.04696233570575714
2023-01-22 12:23:28.210539: step: 646/466, loss: 0.009281965903937817
2023-01-22 12:23:28.810667: step: 648/466, loss: 0.000963771715760231
2023-01-22 12:23:29.435301: step: 650/466, loss: 0.07592719793319702
2023-01-22 12:23:30.072361: step: 652/466, loss: 0.08561275899410248
2023-01-22 12:23:30.702432: step: 654/466, loss: 0.0015793698839843273
2023-01-22 12:23:31.354572: step: 656/466, loss: 0.09655793756246567
2023-01-22 12:23:31.995210: step: 658/466, loss: 0.028067471459507942
2023-01-22 12:23:32.589767: step: 660/466, loss: 0.04503018036484718
2023-01-22 12:23:33.250696: step: 662/466, loss: 0.03728168457746506
2023-01-22 12:23:33.925016: step: 664/466, loss: 0.3822230100631714
2023-01-22 12:23:34.614231: step: 666/466, loss: 0.0555257648229599
2023-01-22 12:23:35.391483: step: 668/466, loss: 0.06059182435274124
2023-01-22 12:23:36.061378: step: 670/466, loss: 0.027598911896348
2023-01-22 12:23:36.658400: step: 672/466, loss: 0.10212715715169907
2023-01-22 12:23:37.297838: step: 674/466, loss: 0.22003017365932465
2023-01-22 12:23:38.010363: step: 676/466, loss: 0.0722040981054306
2023-01-22 12:23:38.639655: step: 678/466, loss: 0.1438433974981308
2023-01-22 12:23:39.333664: step: 680/466, loss: 0.04073747992515564
2023-01-22 12:23:39.994957: step: 682/466, loss: 0.03020535409450531
2023-01-22 12:23:40.651257: step: 684/466, loss: 0.007457078900188208
2023-01-22 12:23:41.359174: step: 686/466, loss: 0.06697667390108109
2023-01-22 12:23:41.981199: step: 688/466, loss: 0.031219815835356712
2023-01-22 12:23:42.638320: step: 690/466, loss: 0.09386976063251495
2023-01-22 12:23:43.284686: step: 692/466, loss: 0.060721199959516525
2023-01-22 12:23:43.949958: step: 694/466, loss: 0.036306802183389664
2023-01-22 12:23:44.619050: step: 696/466, loss: 0.15226911008358002
2023-01-22 12:23:45.256906: step: 698/466, loss: 0.052767571061849594
2023-01-22 12:23:45.895836: step: 700/466, loss: 0.14551600813865662
2023-01-22 12:23:46.506331: step: 702/466, loss: 0.07331140339374542
2023-01-22 12:23:47.107291: step: 704/466, loss: 0.09488560259342194
2023-01-22 12:23:47.821027: step: 706/466, loss: 0.07346636801958084
2023-01-22 12:23:48.435966: step: 708/466, loss: 0.02112002670764923
2023-01-22 12:23:49.140743: step: 710/466, loss: 0.1378161758184433
2023-01-22 12:23:49.806791: step: 712/466, loss: 0.022499412298202515
2023-01-22 12:23:50.398725: step: 714/466, loss: 0.013000545091927052
2023-01-22 12:23:51.053248: step: 716/466, loss: 0.030715223401784897
2023-01-22 12:23:51.676162: step: 718/466, loss: 0.03894434869289398
2023-01-22 12:23:52.345087: step: 720/466, loss: 0.031011324375867844
2023-01-22 12:23:53.031402: step: 722/466, loss: 0.028001470491290092
2023-01-22 12:23:53.673428: step: 724/466, loss: 0.060471419245004654
2023-01-22 12:23:54.378274: step: 726/466, loss: 0.0355912409722805
2023-01-22 12:23:54.975794: step: 728/466, loss: 0.014043898321688175
2023-01-22 12:23:55.657270: step: 730/466, loss: 0.03688360005617142
2023-01-22 12:23:56.387816: step: 732/466, loss: 0.13661432266235352
2023-01-22 12:23:57.025122: step: 734/466, loss: 0.12804485857486725
2023-01-22 12:23:57.716134: step: 736/466, loss: 0.01817631907761097
2023-01-22 12:23:58.336231: step: 738/466, loss: 0.09710384160280228
2023-01-22 12:23:59.013947: step: 740/466, loss: 0.0344148613512516
2023-01-22 12:23:59.588250: step: 742/466, loss: 0.01592305302619934
2023-01-22 12:24:00.249027: step: 744/466, loss: 0.042749933898448944
2023-01-22 12:24:00.896406: step: 746/466, loss: 0.04967391863465309
2023-01-22 12:24:01.538313: step: 748/466, loss: 0.2840249836444855
2023-01-22 12:24:02.206350: step: 750/466, loss: 0.007397348526865244
2023-01-22 12:24:02.892130: step: 752/466, loss: 0.15602250397205353
2023-01-22 12:24:03.542437: step: 754/466, loss: 0.04240616410970688
2023-01-22 12:24:04.160742: step: 756/466, loss: 0.008856425061821938
2023-01-22 12:24:04.765250: step: 758/466, loss: 0.015032918192446232
2023-01-22 12:24:05.404888: step: 760/466, loss: 0.0599614754319191
2023-01-22 12:24:06.033767: step: 762/466, loss: 0.09908628463745117
2023-01-22 12:24:06.685123: step: 764/466, loss: 0.20481857657432556
2023-01-22 12:24:07.295486: step: 766/466, loss: 0.03759913519024849
2023-01-22 12:24:07.967467: step: 768/466, loss: 0.019100012257695198
2023-01-22 12:24:08.631919: step: 770/466, loss: 0.047631192952394485
2023-01-22 12:24:09.277179: step: 772/466, loss: 0.013122456148266792
2023-01-22 12:24:09.917967: step: 774/466, loss: 0.05599507689476013
2023-01-22 12:24:10.569870: step: 776/466, loss: 0.04072127491235733
2023-01-22 12:24:11.311018: step: 778/466, loss: 0.41633787751197815
2023-01-22 12:24:11.979982: step: 780/466, loss: 0.3024740517139435
2023-01-22 12:24:12.633460: step: 782/466, loss: 0.08349002152681351
2023-01-22 12:24:13.225501: step: 784/466, loss: 0.0031556785106658936
2023-01-22 12:24:13.881903: step: 786/466, loss: 0.06271356344223022
2023-01-22 12:24:14.572293: step: 788/466, loss: 0.06998440623283386
2023-01-22 12:24:15.175819: step: 790/466, loss: 0.028869180008769035
2023-01-22 12:24:15.871440: step: 792/466, loss: 0.055056989192962646
2023-01-22 12:24:16.616007: step: 794/466, loss: 0.1301547735929489
2023-01-22 12:24:17.217976: step: 796/466, loss: 0.019010493531823158
2023-01-22 12:24:17.854836: step: 798/466, loss: 0.04248470067977905
2023-01-22 12:24:18.523464: step: 800/466, loss: 0.0068243108689785
2023-01-22 12:24:19.144462: step: 802/466, loss: 0.028648989275097847
2023-01-22 12:24:19.785739: step: 804/466, loss: 0.01490448322147131
2023-01-22 12:24:20.499483: step: 806/466, loss: 0.08014669269323349
2023-01-22 12:24:21.153591: step: 808/466, loss: 0.06051415577530861
2023-01-22 12:24:21.799587: step: 810/466, loss: 0.050217900425195694
2023-01-22 12:24:22.421566: step: 812/466, loss: 0.010280923917889595
2023-01-22 12:24:23.072558: step: 814/466, loss: 0.0070090824738144875
2023-01-22 12:24:23.747090: step: 816/466, loss: 0.029951807111501694
2023-01-22 12:24:24.397872: step: 818/466, loss: 0.09266568720340729
2023-01-22 12:24:25.051859: step: 820/466, loss: 0.04831046238541603
2023-01-22 12:24:25.713653: step: 822/466, loss: 0.08939031511545181
2023-01-22 12:24:26.421081: step: 824/466, loss: 0.3320868909358978
2023-01-22 12:24:27.104050: step: 826/466, loss: 0.0803196057677269
2023-01-22 12:24:27.794820: step: 828/466, loss: 0.012898766435682774
2023-01-22 12:24:28.503545: step: 830/466, loss: 0.06513816863298416
2023-01-22 12:24:29.141048: step: 832/466, loss: 0.019175000488758087
2023-01-22 12:24:29.782457: step: 834/466, loss: 0.05179853364825249
2023-01-22 12:24:30.463529: step: 836/466, loss: 0.010971073992550373
2023-01-22 12:24:31.058700: step: 838/466, loss: 0.014240525662899017
2023-01-22 12:24:31.641332: step: 840/466, loss: 0.005053781438618898
2023-01-22 12:24:32.298732: step: 842/466, loss: 0.01923801749944687
2023-01-22 12:24:32.906067: step: 844/466, loss: 0.008006543852388859
2023-01-22 12:24:33.533078: step: 846/466, loss: 0.004818916320800781
2023-01-22 12:24:34.168934: step: 848/466, loss: 0.06736943870782852
2023-01-22 12:24:34.862886: step: 850/466, loss: 0.06640961021184921
2023-01-22 12:24:35.517238: step: 852/466, loss: 0.04604225233197212
2023-01-22 12:24:36.200422: step: 854/466, loss: 0.027721967548131943
2023-01-22 12:24:36.819748: step: 856/466, loss: 0.014347330667078495
2023-01-22 12:24:37.523505: step: 858/466, loss: 0.06664622575044632
2023-01-22 12:24:38.172862: step: 860/466, loss: 0.041405536234378815
2023-01-22 12:24:38.898351: step: 862/466, loss: 0.035035353153944016
2023-01-22 12:24:39.539876: step: 864/466, loss: 0.0188984926789999
2023-01-22 12:24:40.160174: step: 866/466, loss: 0.044538602232933044
2023-01-22 12:24:40.819048: step: 868/466, loss: 0.05718390271067619
2023-01-22 12:24:41.491201: step: 870/466, loss: 0.006046994123607874
2023-01-22 12:24:42.187032: step: 872/466, loss: 0.007537276484072208
2023-01-22 12:24:42.848524: step: 874/466, loss: 0.056369852274656296
2023-01-22 12:24:43.470564: step: 876/466, loss: 0.02191542647778988
2023-01-22 12:24:44.077586: step: 878/466, loss: 0.04729026183485985
2023-01-22 12:24:44.735963: step: 880/466, loss: 0.04058125242590904
2023-01-22 12:24:45.392637: step: 882/466, loss: 0.004619591869413853
2023-01-22 12:24:46.043215: step: 884/466, loss: 0.10923773050308228
2023-01-22 12:24:46.685970: step: 886/466, loss: 0.22798533737659454
2023-01-22 12:24:47.381400: step: 888/466, loss: 0.01707821525633335
2023-01-22 12:24:48.027555: step: 890/466, loss: 0.07693028450012207
2023-01-22 12:24:48.701546: step: 892/466, loss: 0.05920485407114029
2023-01-22 12:24:49.421888: step: 894/466, loss: 0.03817473351955414
2023-01-22 12:24:50.055062: step: 896/466, loss: 0.03102230280637741
2023-01-22 12:24:50.757072: step: 898/466, loss: 0.04021405428647995
2023-01-22 12:24:51.487521: step: 900/466, loss: 0.005757685285061598
2023-01-22 12:24:52.167840: step: 902/466, loss: 0.11351823061704636
2023-01-22 12:24:52.881308: step: 904/466, loss: 0.04362649470567703
2023-01-22 12:24:53.529422: step: 906/466, loss: 0.033703770488500595
2023-01-22 12:24:54.197466: step: 908/466, loss: 0.051264479756355286
2023-01-22 12:24:54.849986: step: 910/466, loss: 0.05457863211631775
2023-01-22 12:24:55.420710: step: 912/466, loss: 0.6209095120429993
2023-01-22 12:24:56.053870: step: 914/466, loss: 0.028589626774191856
2023-01-22 12:24:56.729415: step: 916/466, loss: 0.05819375813007355
2023-01-22 12:24:57.341294: step: 918/466, loss: 0.07678476721048355
2023-01-22 12:24:58.015416: step: 920/466, loss: 0.035971250385046005
2023-01-22 12:24:58.633633: step: 922/466, loss: 0.0950455442070961
2023-01-22 12:24:59.251815: step: 924/466, loss: 0.01911776140332222
2023-01-22 12:24:59.974656: step: 926/466, loss: 0.042217954993247986
2023-01-22 12:25:00.554117: step: 928/466, loss: 0.013078675605356693
2023-01-22 12:25:01.210385: step: 930/466, loss: 0.0354284793138504
2023-01-22 12:25:01.800667: step: 932/466, loss: 0.09293639659881592
==================================================
Loss: 0.091
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3180466887980933, 'r': 0.32227121787131274, 'f1': 0.32014501756490443}, 'combined': 0.23589632873203484, 'epoch': 22}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.30642973980592747, 'r': 0.2923378401394691, 'f1': 0.2992179646651327}, 'combined': 0.18736078161274664, 'epoch': 22}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3006470431742171, 'r': 0.34115167327928236, 'f1': 0.3196212121212121}, 'combined': 0.23551036682615625, 'epoch': 22}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3100314510239115, 'r': 0.3044402616456624, 'f1': 0.30721041871250193}, 'combined': 0.19038392145563499, 'epoch': 22}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2834316378066378, 'r': 0.33882719510091425, 'f1': 0.30866366779288135}, 'combined': 0.22743638679475467, 'epoch': 22}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.311519930467549, 'r': 0.2960424271471197, 'f1': 0.3035840359906082}, 'combined': 0.20138742981555197, 'epoch': 22}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.23113207547169812, 'r': 0.35, 'f1': 0.2784090909090909}, 'combined': 0.18560606060606058, 'epoch': 22}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3, 'r': 0.391304347826087, 'f1': 0.33962264150943394}, 'combined': 0.16981132075471697, 'epoch': 22}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.28, 'r': 0.2413793103448276, 'f1': 0.25925925925925924}, 'combined': 0.1728395061728395, 'epoch': 22}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:27:48.791109: step: 2/466, loss: 0.37519821524620056
2023-01-22 12:27:49.448955: step: 4/466, loss: 0.04106681048870087
2023-01-22 12:27:50.104675: step: 6/466, loss: 0.015577426180243492
2023-01-22 12:27:50.817522: step: 8/466, loss: 0.07751546055078506
2023-01-22 12:27:51.455705: step: 10/466, loss: 0.049695976078510284
2023-01-22 12:27:52.115910: step: 12/466, loss: 0.018751537427306175
2023-01-22 12:27:52.789827: step: 14/466, loss: 0.05414804071187973
2023-01-22 12:27:53.396586: step: 16/466, loss: 0.2026587277650833
2023-01-22 12:27:54.064978: step: 18/466, loss: 0.0006938294973224401
2023-01-22 12:27:54.670186: step: 20/466, loss: 0.15780635178089142
2023-01-22 12:27:55.313741: step: 22/466, loss: 0.052532535046339035
2023-01-22 12:27:55.921303: step: 24/466, loss: 0.033414844423532486
2023-01-22 12:27:56.559598: step: 26/466, loss: 0.11205101013183594
2023-01-22 12:27:57.183508: step: 28/466, loss: 0.030356595292687416
2023-01-22 12:27:57.832213: step: 30/466, loss: 0.26295825839042664
2023-01-22 12:27:58.495651: step: 32/466, loss: 0.04312417656183243
2023-01-22 12:27:59.169751: step: 34/466, loss: 0.26988208293914795
2023-01-22 12:27:59.823378: step: 36/466, loss: 0.10601172596216202
2023-01-22 12:28:00.439551: step: 38/466, loss: 0.046130288392305374
2023-01-22 12:28:01.091808: step: 40/466, loss: 0.04392627626657486
2023-01-22 12:28:01.698944: step: 42/466, loss: 0.026971695944666862
2023-01-22 12:28:02.422586: step: 44/466, loss: 0.006729075685143471
2023-01-22 12:28:03.035930: step: 46/466, loss: 0.007654865272343159
2023-01-22 12:28:03.659888: step: 48/466, loss: 0.04854927211999893
2023-01-22 12:28:04.296226: step: 50/466, loss: 0.0065819318406283855
2023-01-22 12:28:04.903991: step: 52/466, loss: 0.061822593212127686
2023-01-22 12:28:05.497837: step: 54/466, loss: 0.1821979433298111
2023-01-22 12:28:06.170676: step: 56/466, loss: 0.028851419687271118
2023-01-22 12:28:06.808830: step: 58/466, loss: 0.05924450606107712
2023-01-22 12:28:07.457969: step: 60/466, loss: 0.055872879922389984
2023-01-22 12:28:08.092258: step: 62/466, loss: 0.048712216317653656
2023-01-22 12:28:08.679480: step: 64/466, loss: 0.007741500623524189
2023-01-22 12:28:09.297140: step: 66/466, loss: 0.025018535554409027
2023-01-22 12:28:09.919860: step: 68/466, loss: 0.10492322593927383
2023-01-22 12:28:10.514962: step: 70/466, loss: 0.21613642573356628
2023-01-22 12:28:11.238108: step: 72/466, loss: 0.029166538268327713
2023-01-22 12:28:11.889470: step: 74/466, loss: 0.016935860738158226
2023-01-22 12:28:12.559047: step: 76/466, loss: 0.04437658563256264
2023-01-22 12:28:13.278462: step: 78/466, loss: 0.025598792359232903
2023-01-22 12:28:13.968246: step: 80/466, loss: 0.09755132347345352
2023-01-22 12:28:14.612047: step: 82/466, loss: 0.02875247597694397
2023-01-22 12:28:15.210295: step: 84/466, loss: 0.021137593314051628
2023-01-22 12:28:15.829999: step: 86/466, loss: 0.03565197065472603
2023-01-22 12:28:16.570808: step: 88/466, loss: 0.1278599053621292
2023-01-22 12:28:17.229858: step: 90/466, loss: 0.02374625951051712
2023-01-22 12:28:17.860549: step: 92/466, loss: 0.026628822088241577
2023-01-22 12:28:18.518039: step: 94/466, loss: 0.019938306882977486
2023-01-22 12:28:19.186208: step: 96/466, loss: 0.007408472243696451
2023-01-22 12:28:19.849782: step: 98/466, loss: 0.02977028861641884
2023-01-22 12:28:20.519995: step: 100/466, loss: 0.004461156204342842
2023-01-22 12:28:21.214193: step: 102/466, loss: 0.10266581177711487
2023-01-22 12:28:21.830322: step: 104/466, loss: 0.1725711077451706
2023-01-22 12:28:22.459466: step: 106/466, loss: 0.0576268695294857
2023-01-22 12:28:23.114364: step: 108/466, loss: 0.2895353138446808
2023-01-22 12:28:23.714273: step: 110/466, loss: 0.026378493756055832
2023-01-22 12:28:24.356526: step: 112/466, loss: 0.045850664377212524
2023-01-22 12:28:25.083802: step: 114/466, loss: 0.051356494426727295
2023-01-22 12:28:25.698325: step: 116/466, loss: 0.030543841421604156
2023-01-22 12:28:26.336563: step: 118/466, loss: 0.14664997160434723
2023-01-22 12:28:27.009735: step: 120/466, loss: 0.006917271763086319
2023-01-22 12:28:27.689613: step: 122/466, loss: 0.07905556261539459
2023-01-22 12:28:28.340752: step: 124/466, loss: 0.08073782175779343
2023-01-22 12:28:28.947040: step: 126/466, loss: 0.03974530100822449
2023-01-22 12:28:29.580057: step: 128/466, loss: 0.013782481662929058
2023-01-22 12:28:30.222940: step: 130/466, loss: 0.022367702797055244
2023-01-22 12:28:30.823478: step: 132/466, loss: 0.015513092279434204
2023-01-22 12:28:31.462879: step: 134/466, loss: 0.04052796587347984
2023-01-22 12:28:32.175198: step: 136/466, loss: 0.17355284094810486
2023-01-22 12:28:32.827112: step: 138/466, loss: 0.04959815740585327
2023-01-22 12:28:33.439733: step: 140/466, loss: 0.06585326790809631
2023-01-22 12:28:34.059441: step: 142/466, loss: 0.01629745215177536
2023-01-22 12:28:34.719154: step: 144/466, loss: 0.029959937557578087
2023-01-22 12:28:35.344053: step: 146/466, loss: 0.1523573398590088
2023-01-22 12:28:36.043442: step: 148/466, loss: 0.07513323426246643
2023-01-22 12:28:36.625066: step: 150/466, loss: 0.0007255334639921784
2023-01-22 12:28:37.253129: step: 152/466, loss: 0.005202392116189003
2023-01-22 12:28:37.829211: step: 154/466, loss: 0.122276172041893
2023-01-22 12:28:38.379820: step: 156/466, loss: 0.036976199597120285
2023-01-22 12:28:39.016677: step: 158/466, loss: 0.05452893674373627
2023-01-22 12:28:39.670743: step: 160/466, loss: 0.08069787919521332
2023-01-22 12:28:40.252708: step: 162/466, loss: 0.3329411745071411
2023-01-22 12:28:40.897386: step: 164/466, loss: 0.05058800056576729
2023-01-22 12:28:41.578389: step: 166/466, loss: 0.14589150249958038
2023-01-22 12:28:42.278392: step: 168/466, loss: 0.03127635642886162
2023-01-22 12:28:42.960802: step: 170/466, loss: 0.006756802089512348
2023-01-22 12:28:43.535880: step: 172/466, loss: 0.005486187059432268
2023-01-22 12:28:44.182078: step: 174/466, loss: 0.024932648986577988
2023-01-22 12:28:44.807739: step: 176/466, loss: 0.008025525137782097
2023-01-22 12:28:45.442662: step: 178/466, loss: 0.05440286546945572
2023-01-22 12:28:46.041506: step: 180/466, loss: 0.0334198996424675
2023-01-22 12:28:46.699768: step: 182/466, loss: 0.0066267079673707485
2023-01-22 12:28:47.308713: step: 184/466, loss: 0.014033726416528225
2023-01-22 12:28:47.864731: step: 186/466, loss: 0.053195107728242874
2023-01-22 12:28:48.507472: step: 188/466, loss: 0.04765544459223747
2023-01-22 12:28:49.208364: step: 190/466, loss: 0.06990660727024078
2023-01-22 12:28:49.845139: step: 192/466, loss: 0.1254531294107437
2023-01-22 12:28:50.461466: step: 194/466, loss: 0.08785541355609894
2023-01-22 12:28:51.052793: step: 196/466, loss: 0.036871835589408875
2023-01-22 12:28:51.676113: step: 198/466, loss: 0.02268662303686142
2023-01-22 12:28:52.231324: step: 200/466, loss: 0.013539185747504234
2023-01-22 12:28:52.848681: step: 202/466, loss: 0.037191201001405716
2023-01-22 12:28:53.486661: step: 204/466, loss: 10.831572532653809
2023-01-22 12:28:54.131797: step: 206/466, loss: 0.23229451477527618
2023-01-22 12:28:54.752458: step: 208/466, loss: 0.029476964846253395
2023-01-22 12:28:55.418404: step: 210/466, loss: 0.07312937080860138
2023-01-22 12:28:56.016572: step: 212/466, loss: 0.004163483157753944
2023-01-22 12:28:56.681573: step: 214/466, loss: 0.1760241836309433
2023-01-22 12:28:57.344434: step: 216/466, loss: 0.07934526354074478
2023-01-22 12:28:58.039585: step: 218/466, loss: 0.07286553829908371
2023-01-22 12:28:58.640712: step: 220/466, loss: 0.008473890833556652
2023-01-22 12:28:59.276154: step: 222/466, loss: 0.006945169530808926
2023-01-22 12:28:59.888790: step: 224/466, loss: 0.07344811409711838
2023-01-22 12:29:00.526466: step: 226/466, loss: 0.09052682667970657
2023-01-22 12:29:01.212354: step: 228/466, loss: 0.0714201033115387
2023-01-22 12:29:01.827529: step: 230/466, loss: 0.09957793354988098
2023-01-22 12:29:02.468292: step: 232/466, loss: 0.050654392689466476
2023-01-22 12:29:03.069847: step: 234/466, loss: 0.057822201400995255
2023-01-22 12:29:03.692698: step: 236/466, loss: 0.04982614144682884
2023-01-22 12:29:04.287137: step: 238/466, loss: 0.016358835622668266
2023-01-22 12:29:04.946479: step: 240/466, loss: 0.07440569251775742
2023-01-22 12:29:05.525114: step: 242/466, loss: 0.009837755002081394
2023-01-22 12:29:06.201088: step: 244/466, loss: 0.4549831449985504
2023-01-22 12:29:06.883738: step: 246/466, loss: 0.06924940645694733
2023-01-22 12:29:07.433442: step: 248/466, loss: 0.0137610649690032
2023-01-22 12:29:08.050138: step: 250/466, loss: 0.06074821576476097
2023-01-22 12:29:08.649224: step: 252/466, loss: 0.002604379318654537
2023-01-22 12:29:09.262722: step: 254/466, loss: 0.011386437341570854
2023-01-22 12:29:09.836432: step: 256/466, loss: 0.08085306733846664
2023-01-22 12:29:10.482344: step: 258/466, loss: 0.02583848498761654
2023-01-22 12:29:11.155098: step: 260/466, loss: 0.06034468859434128
2023-01-22 12:29:11.803247: step: 262/466, loss: 0.04320215806365013
2023-01-22 12:29:12.446565: step: 264/466, loss: 0.0151560939848423
2023-01-22 12:29:13.077707: step: 266/466, loss: 0.029136555269360542
2023-01-22 12:29:13.692694: step: 268/466, loss: 0.03350706771016121
2023-01-22 12:29:14.326845: step: 270/466, loss: 0.03152776136994362
2023-01-22 12:29:14.934855: step: 272/466, loss: 0.0074542067013680935
2023-01-22 12:29:15.668982: step: 274/466, loss: 0.03669152408838272
2023-01-22 12:29:16.334346: step: 276/466, loss: 0.09760794043540955
2023-01-22 12:29:16.986654: step: 278/466, loss: 0.017591552808880806
2023-01-22 12:29:17.678280: step: 280/466, loss: 0.3281540274620056
2023-01-22 12:29:18.329561: step: 282/466, loss: 0.04125038906931877
2023-01-22 12:29:19.003688: step: 284/466, loss: 0.0051215835846960545
2023-01-22 12:29:19.635421: step: 286/466, loss: 0.044143643230199814
2023-01-22 12:29:20.261426: step: 288/466, loss: 0.02551931142807007
2023-01-22 12:29:20.896979: step: 290/466, loss: 0.04671537131071091
2023-01-22 12:29:21.517017: step: 292/466, loss: 0.029295897111296654
2023-01-22 12:29:22.175742: step: 294/466, loss: 0.04605097696185112
2023-01-22 12:29:22.779759: step: 296/466, loss: 1.6217180490493774
2023-01-22 12:29:23.444967: step: 298/466, loss: 0.04257981479167938
2023-01-22 12:29:24.115063: step: 300/466, loss: 0.1730869859457016
2023-01-22 12:29:24.693255: step: 302/466, loss: 0.02628973498940468
2023-01-22 12:29:25.348576: step: 304/466, loss: 0.031872548162937164
2023-01-22 12:29:25.999061: step: 306/466, loss: 0.026138199493288994
2023-01-22 12:29:26.684764: step: 308/466, loss: 0.022182194516062737
2023-01-22 12:29:27.237567: step: 310/466, loss: 0.002576672239229083
2023-01-22 12:29:27.910394: step: 312/466, loss: 0.01716276817023754
2023-01-22 12:29:28.598723: step: 314/466, loss: 0.017801720649003983
2023-01-22 12:29:29.240755: step: 316/466, loss: 0.0345219187438488
2023-01-22 12:29:29.886877: step: 318/466, loss: 0.07362405210733414
2023-01-22 12:29:30.583764: step: 320/466, loss: 0.20261883735656738
2023-01-22 12:29:31.168543: step: 322/466, loss: 0.028519850224256516
2023-01-22 12:29:31.805430: step: 324/466, loss: 0.009284978732466698
2023-01-22 12:29:32.497063: step: 326/466, loss: 0.01323692873120308
2023-01-22 12:29:33.113489: step: 328/466, loss: 0.08233549445867538
2023-01-22 12:29:33.759201: step: 330/466, loss: 0.08232059329748154
2023-01-22 12:29:34.340339: step: 332/466, loss: 0.030916700139641762
2023-01-22 12:29:35.056902: step: 334/466, loss: 0.12881356477737427
2023-01-22 12:29:35.712590: step: 336/466, loss: 0.02648826315999031
2023-01-22 12:29:36.343048: step: 338/466, loss: 0.04425083100795746
2023-01-22 12:29:36.958312: step: 340/466, loss: 0.026341862976551056
2023-01-22 12:29:37.597760: step: 342/466, loss: 0.5152478814125061
2023-01-22 12:29:38.283762: step: 344/466, loss: 0.04249029606580734
2023-01-22 12:29:38.958207: step: 346/466, loss: 0.012758921831846237
2023-01-22 12:29:39.611419: step: 348/466, loss: 0.007210403680801392
2023-01-22 12:29:40.224842: step: 350/466, loss: 0.008182523772120476
2023-01-22 12:29:40.853445: step: 352/466, loss: 0.03701353818178177
2023-01-22 12:29:41.475526: step: 354/466, loss: 0.018237052485346794
2023-01-22 12:29:42.164436: step: 356/466, loss: 0.02028246596455574
2023-01-22 12:29:42.791172: step: 358/466, loss: 0.029217390343546867
2023-01-22 12:29:43.421673: step: 360/466, loss: 0.03913299739360809
2023-01-22 12:29:44.115161: step: 362/466, loss: 0.08187693357467651
2023-01-22 12:29:44.829678: step: 364/466, loss: 0.02423919178545475
2023-01-22 12:29:45.447580: step: 366/466, loss: 0.03357991576194763
2023-01-22 12:29:46.097241: step: 368/466, loss: 0.1829199641942978
2023-01-22 12:29:46.758058: step: 370/466, loss: 0.05848422273993492
2023-01-22 12:29:47.456774: step: 372/466, loss: 0.024354638531804085
2023-01-22 12:29:48.096491: step: 374/466, loss: 0.026888463646173477
2023-01-22 12:29:48.728675: step: 376/466, loss: 0.10239247232675552
2023-01-22 12:29:49.399227: step: 378/466, loss: 0.03820658475160599
2023-01-22 12:29:50.075418: step: 380/466, loss: 0.009456473402678967
2023-01-22 12:29:50.778509: step: 382/466, loss: 0.025725068524479866
2023-01-22 12:29:51.396423: step: 384/466, loss: 0.021409517154097557
2023-01-22 12:29:52.034552: step: 386/466, loss: 0.04017370939254761
2023-01-22 12:29:52.659168: step: 388/466, loss: 0.11360134929418564
2023-01-22 12:29:53.371646: step: 390/466, loss: 0.37669089436531067
2023-01-22 12:29:54.085785: step: 392/466, loss: 0.01950979046523571
2023-01-22 12:29:54.735802: step: 394/466, loss: 0.6004852056503296
2023-01-22 12:29:55.390572: step: 396/466, loss: 0.03134963661432266
2023-01-22 12:29:56.020555: step: 398/466, loss: 0.06417876482009888
2023-01-22 12:29:56.699995: step: 400/466, loss: 0.039448097348213196
2023-01-22 12:29:57.350190: step: 402/466, loss: 0.1267458200454712
2023-01-22 12:29:58.052611: step: 404/466, loss: 0.151803657412529
2023-01-22 12:29:58.693521: step: 406/466, loss: 0.05627970024943352
2023-01-22 12:29:59.356106: step: 408/466, loss: 0.0677432119846344
2023-01-22 12:30:00.065491: step: 410/466, loss: 0.0646536648273468
2023-01-22 12:30:00.670798: step: 412/466, loss: 0.024825256317853928
2023-01-22 12:30:01.311458: step: 414/466, loss: 0.023025576025247574
2023-01-22 12:30:01.881849: step: 416/466, loss: 0.00923093594610691
2023-01-22 12:30:02.555448: step: 418/466, loss: 0.056759439408779144
2023-01-22 12:30:03.130205: step: 420/466, loss: 0.00021462456788867712
2023-01-22 12:30:03.792172: step: 422/466, loss: 0.01586374267935753
2023-01-22 12:30:04.530829: step: 424/466, loss: 0.06646231561899185
2023-01-22 12:30:05.194919: step: 426/466, loss: 0.0559365339577198
2023-01-22 12:30:05.822386: step: 428/466, loss: 0.005602554883807898
2023-01-22 12:30:06.521186: step: 430/466, loss: 0.006315540987998247
2023-01-22 12:30:07.224567: step: 432/466, loss: 0.016006488353013992
2023-01-22 12:30:07.891407: step: 434/466, loss: 0.12325073778629303
2023-01-22 12:30:08.539677: step: 436/466, loss: 0.0388457253575325
2023-01-22 12:30:09.242566: step: 438/466, loss: 0.03605816140770912
2023-01-22 12:30:09.941236: step: 440/466, loss: 0.010683774948120117
2023-01-22 12:30:10.604582: step: 442/466, loss: 0.03860093653202057
2023-01-22 12:30:11.190117: step: 444/466, loss: 0.001220116508193314
2023-01-22 12:30:11.900071: step: 446/466, loss: 0.021517273038625717
2023-01-22 12:30:12.573997: step: 448/466, loss: 0.19745062291622162
2023-01-22 12:30:13.157398: step: 450/466, loss: 0.0030312389135360718
2023-01-22 12:30:13.845061: step: 452/466, loss: 1.378182053565979
2023-01-22 12:30:14.512105: step: 454/466, loss: 0.027963416650891304
2023-01-22 12:30:15.115716: step: 456/466, loss: 0.010036383755505085
2023-01-22 12:30:15.848518: step: 458/466, loss: 0.10758908838033676
2023-01-22 12:30:16.476573: step: 460/466, loss: 0.09921170771121979
2023-01-22 12:30:17.069201: step: 462/466, loss: 0.013041533529758453
2023-01-22 12:30:17.678042: step: 464/466, loss: 0.07727940380573273
2023-01-22 12:30:18.304605: step: 466/466, loss: 0.06255663186311722
2023-01-22 12:30:18.912144: step: 468/466, loss: 0.012556467205286026
2023-01-22 12:30:19.538724: step: 470/466, loss: 0.0022834744304418564
2023-01-22 12:30:20.218143: step: 472/466, loss: 0.016521736979484558
2023-01-22 12:30:20.907548: step: 474/466, loss: 0.039565179497003555
2023-01-22 12:30:21.567226: step: 476/466, loss: 0.07813805341720581
2023-01-22 12:30:22.175266: step: 478/466, loss: 0.011786703020334244
2023-01-22 12:30:22.815855: step: 480/466, loss: 0.02669355645775795
2023-01-22 12:30:23.443882: step: 482/466, loss: 0.2168130725622177
2023-01-22 12:30:24.079316: step: 484/466, loss: 0.030019201338291168
2023-01-22 12:30:24.663164: step: 486/466, loss: 0.040079835802316666
2023-01-22 12:30:25.290009: step: 488/466, loss: 0.04554833844304085
2023-01-22 12:30:25.929980: step: 490/466, loss: 0.0638691708445549
2023-01-22 12:30:26.542066: step: 492/466, loss: 0.025603465735912323
2023-01-22 12:30:27.226121: step: 494/466, loss: 0.06134669482707977
2023-01-22 12:30:27.919071: step: 496/466, loss: 0.03263123333454132
2023-01-22 12:30:28.561850: step: 498/466, loss: 0.004851019941270351
2023-01-22 12:30:29.231299: step: 500/466, loss: 0.018387088552117348
2023-01-22 12:30:29.913435: step: 502/466, loss: 0.06409452110528946
2023-01-22 12:30:30.622473: step: 504/466, loss: 0.038857266306877136
2023-01-22 12:30:31.210677: step: 506/466, loss: 0.051083534955978394
2023-01-22 12:30:31.820947: step: 508/466, loss: 0.013608801178634167
2023-01-22 12:30:32.471801: step: 510/466, loss: 0.028269052505493164
2023-01-22 12:30:33.067505: step: 512/466, loss: 0.09277983009815216
2023-01-22 12:30:33.628949: step: 514/466, loss: 0.01589254103600979
2023-01-22 12:30:34.349116: step: 516/466, loss: 0.05243847891688347
2023-01-22 12:30:34.962916: step: 518/466, loss: 0.08677437901496887
2023-01-22 12:30:35.612540: step: 520/466, loss: 0.01228324044495821
2023-01-22 12:30:36.271288: step: 522/466, loss: 0.08975356817245483
2023-01-22 12:30:36.978745: step: 524/466, loss: 0.4436494708061218
2023-01-22 12:30:37.611838: step: 526/466, loss: 0.17401957511901855
2023-01-22 12:30:38.248884: step: 528/466, loss: 0.005692127626389265
2023-01-22 12:30:38.861814: step: 530/466, loss: 0.03703230246901512
2023-01-22 12:30:39.472082: step: 532/466, loss: 0.03678973764181137
2023-01-22 12:30:40.090266: step: 534/466, loss: 0.016979314386844635
2023-01-22 12:30:40.718131: step: 536/466, loss: 0.061010606586933136
2023-01-22 12:30:41.316900: step: 538/466, loss: 0.004714383743703365
2023-01-22 12:30:42.177844: step: 540/466, loss: 0.0018672322621569037
2023-01-22 12:30:42.870678: step: 542/466, loss: 0.009897676296532154
2023-01-22 12:30:43.443997: step: 544/466, loss: 0.0023059670347720385
2023-01-22 12:30:44.106309: step: 546/466, loss: 0.03340055048465729
2023-01-22 12:30:44.804880: step: 548/466, loss: 0.058384593576192856
2023-01-22 12:30:45.471710: step: 550/466, loss: 0.0411825068295002
2023-01-22 12:30:46.058402: step: 552/466, loss: 0.15804874897003174
2023-01-22 12:30:46.660799: step: 554/466, loss: 0.012139519676566124
2023-01-22 12:30:47.345137: step: 556/466, loss: 0.2800336480140686
2023-01-22 12:30:47.989868: step: 558/466, loss: 0.038609229028224945
2023-01-22 12:30:48.606965: step: 560/466, loss: 0.05266398936510086
2023-01-22 12:30:49.246102: step: 562/466, loss: 0.011620165780186653
2023-01-22 12:30:49.926225: step: 564/466, loss: 0.07682330906391144
2023-01-22 12:30:50.597523: step: 566/466, loss: 0.010016935877501965
2023-01-22 12:30:51.227459: step: 568/466, loss: 0.017387090250849724
2023-01-22 12:30:51.987996: step: 570/466, loss: 0.2580850422382355
2023-01-22 12:30:52.609653: step: 572/466, loss: 0.0044228374026715755
2023-01-22 12:30:53.253377: step: 574/466, loss: 0.03284839168190956
2023-01-22 12:30:53.875687: step: 576/466, loss: 0.017334576696157455
2023-01-22 12:30:54.556273: step: 578/466, loss: 0.013471720740199089
2023-01-22 12:30:55.178768: step: 580/466, loss: 0.022119492292404175
2023-01-22 12:30:55.735510: step: 582/466, loss: 0.006941903382539749
2023-01-22 12:30:56.403756: step: 584/466, loss: 0.11759119480848312
2023-01-22 12:30:57.065586: step: 586/466, loss: 0.0009638160699978471
2023-01-22 12:30:57.752732: step: 588/466, loss: 0.04819343984127045
2023-01-22 12:30:58.336066: step: 590/466, loss: 0.13402827084064484
2023-01-22 12:30:58.990261: step: 592/466, loss: 0.09971284121274948
2023-01-22 12:30:59.635772: step: 594/466, loss: 0.05317353084683418
2023-01-22 12:31:00.296136: step: 596/466, loss: 0.08394022285938263
2023-01-22 12:31:00.902811: step: 598/466, loss: 0.006317528896033764
2023-01-22 12:31:01.584072: step: 600/466, loss: 0.7620943188667297
2023-01-22 12:31:02.281140: step: 602/466, loss: 0.17191177606582642
2023-01-22 12:31:03.077916: step: 604/466, loss: 0.02348541095852852
2023-01-22 12:31:03.713653: step: 606/466, loss: 14.203178405761719
2023-01-22 12:31:04.414232: step: 608/466, loss: 0.03364052623510361
2023-01-22 12:31:05.009075: step: 610/466, loss: 1.0802329778671265
2023-01-22 12:31:05.662497: step: 612/466, loss: 0.00660161767154932
2023-01-22 12:31:06.237058: step: 614/466, loss: 0.07215036451816559
2023-01-22 12:31:06.829946: step: 616/466, loss: 0.03529845178127289
2023-01-22 12:31:07.427782: step: 618/466, loss: 0.004194928798824549
2023-01-22 12:31:08.019180: step: 620/466, loss: 0.017437612637877464
2023-01-22 12:31:08.662272: step: 622/466, loss: 0.010304673574864864
2023-01-22 12:31:09.413820: step: 624/466, loss: 0.010235766880214214
2023-01-22 12:31:10.105199: step: 626/466, loss: 0.07017090171575546
2023-01-22 12:31:10.732316: step: 628/466, loss: 0.006158484611660242
2023-01-22 12:31:11.361129: step: 630/466, loss: 0.626251220703125
2023-01-22 12:31:11.982104: step: 632/466, loss: 0.09788559377193451
2023-01-22 12:31:12.684995: step: 634/466, loss: 0.032463692128658295
2023-01-22 12:31:13.348633: step: 636/466, loss: 0.012290447019040585
2023-01-22 12:31:14.004745: step: 638/466, loss: 2.016979932785034
2023-01-22 12:31:14.649374: step: 640/466, loss: 0.10255640745162964
2023-01-22 12:31:15.267873: step: 642/466, loss: 0.0026204304303973913
2023-01-22 12:31:15.804548: step: 644/466, loss: 0.018390139564871788
2023-01-22 12:31:16.435991: step: 646/466, loss: 0.009616916999220848
2023-01-22 12:31:17.070900: step: 648/466, loss: 0.023441944271326065
2023-01-22 12:31:17.661904: step: 650/466, loss: 0.04400390759110451
2023-01-22 12:31:18.337757: step: 652/466, loss: 0.03810415789484978
2023-01-22 12:31:19.018544: step: 654/466, loss: 0.08098503947257996
2023-01-22 12:31:19.630535: step: 656/466, loss: 0.008242843672633171
2023-01-22 12:31:20.304846: step: 658/466, loss: 0.16538627445697784
2023-01-22 12:31:20.973399: step: 660/466, loss: 0.0010274339001625776
2023-01-22 12:31:21.590876: step: 662/466, loss: 0.05155831202864647
2023-01-22 12:31:22.226703: step: 664/466, loss: 0.03093663789331913
2023-01-22 12:31:22.866674: step: 666/466, loss: 0.016186198219656944
2023-01-22 12:31:23.527328: step: 668/466, loss: 0.08217496424913406
2023-01-22 12:31:24.113767: step: 670/466, loss: 0.09058801829814911
2023-01-22 12:31:24.744031: step: 672/466, loss: 0.05601709708571434
2023-01-22 12:31:25.364421: step: 674/466, loss: 0.007798232138156891
2023-01-22 12:31:26.100942: step: 676/466, loss: 0.02868696302175522
2023-01-22 12:31:26.753946: step: 678/466, loss: 0.04802197962999344
2023-01-22 12:31:27.443089: step: 680/466, loss: 0.01739462837576866
2023-01-22 12:31:28.111317: step: 682/466, loss: 0.0069674295373260975
2023-01-22 12:31:28.806805: step: 684/466, loss: 0.0967487096786499
2023-01-22 12:31:29.433827: step: 686/466, loss: 0.08254416286945343
2023-01-22 12:31:30.059326: step: 688/466, loss: 0.033013731241226196
2023-01-22 12:31:30.732821: step: 690/466, loss: 0.040913742035627365
2023-01-22 12:31:31.278396: step: 692/466, loss: 0.010079664178192616
2023-01-22 12:31:31.876693: step: 694/466, loss: 0.05389615520834923
2023-01-22 12:31:32.501088: step: 696/466, loss: 0.012297890149056911
2023-01-22 12:31:33.080582: step: 698/466, loss: 0.005239218007773161
2023-01-22 12:31:33.767704: step: 700/466, loss: 1.0167995691299438
2023-01-22 12:31:34.439081: step: 702/466, loss: 0.10525007545948029
2023-01-22 12:31:35.015453: step: 704/466, loss: 0.027654528617858887
2023-01-22 12:31:35.707607: step: 706/466, loss: 0.04541835933923721
2023-01-22 12:31:36.397627: step: 708/466, loss: 0.01958831585943699
2023-01-22 12:31:37.106990: step: 710/466, loss: 0.11447075754404068
2023-01-22 12:31:37.753600: step: 712/466, loss: 0.0112985298037529
2023-01-22 12:31:38.372952: step: 714/466, loss: 0.016465893015265465
2023-01-22 12:31:38.996564: step: 716/466, loss: 0.029620099812746048
2023-01-22 12:31:39.607922: step: 718/466, loss: 0.004684635903686285
2023-01-22 12:31:40.212076: step: 720/466, loss: 0.01591295748949051
2023-01-22 12:31:40.885106: step: 722/466, loss: 0.023893725126981735
2023-01-22 12:31:41.507770: step: 724/466, loss: 0.5566367506980896
2023-01-22 12:31:42.167889: step: 726/466, loss: 0.04075148329138756
2023-01-22 12:31:42.878600: step: 728/466, loss: 0.01116813812404871
2023-01-22 12:31:43.517928: step: 730/466, loss: 0.17533671855926514
2023-01-22 12:31:44.194140: step: 732/466, loss: 0.05816694349050522
2023-01-22 12:31:44.844965: step: 734/466, loss: 0.033278536051511765
2023-01-22 12:31:45.427157: step: 736/466, loss: 0.04196491837501526
2023-01-22 12:31:46.049966: step: 738/466, loss: 0.08225072175264359
2023-01-22 12:31:46.724592: step: 740/466, loss: 0.10632101446390152
2023-01-22 12:31:47.306962: step: 742/466, loss: 0.004922711756080389
2023-01-22 12:31:47.909596: step: 744/466, loss: 0.017099060118198395
2023-01-22 12:31:48.535335: step: 746/466, loss: 0.06865949928760529
2023-01-22 12:31:49.179547: step: 748/466, loss: 0.13417190313339233
2023-01-22 12:31:49.850498: step: 750/466, loss: 0.03777005895972252
2023-01-22 12:31:50.526861: step: 752/466, loss: 0.05155256763100624
2023-01-22 12:31:51.149443: step: 754/466, loss: 0.016800545156002045
2023-01-22 12:31:51.842892: step: 756/466, loss: 0.05773625150322914
2023-01-22 12:31:52.507653: step: 758/466, loss: 0.026250790804624557
2023-01-22 12:31:53.189908: step: 760/466, loss: 0.017661169171333313
2023-01-22 12:31:53.815408: step: 762/466, loss: 0.02000456675887108
2023-01-22 12:31:54.474275: step: 764/466, loss: 0.0435657873749733
2023-01-22 12:31:55.186081: step: 766/466, loss: 0.015171305276453495
2023-01-22 12:31:55.786457: step: 768/466, loss: 0.061575550585985184
2023-01-22 12:31:56.438506: step: 770/466, loss: 0.014146787114441395
2023-01-22 12:31:57.036685: step: 772/466, loss: 0.04964570701122284
2023-01-22 12:31:57.616538: step: 774/466, loss: 0.025675414130091667
2023-01-22 12:31:58.258472: step: 776/466, loss: 0.06615062803030014
2023-01-22 12:31:58.921113: step: 778/466, loss: 0.06605000793933868
2023-01-22 12:31:59.501838: step: 780/466, loss: 0.008641757071018219
2023-01-22 12:32:00.109932: step: 782/466, loss: 0.007029538508504629
2023-01-22 12:32:00.705869: step: 784/466, loss: 0.04293414577841759
2023-01-22 12:32:01.288599: step: 786/466, loss: 0.011798088438808918
2023-01-22 12:32:01.893353: step: 788/466, loss: 0.05605228990316391
2023-01-22 12:32:02.499783: step: 790/466, loss: 0.0408843532204628
2023-01-22 12:32:03.149485: step: 792/466, loss: 0.06712520122528076
2023-01-22 12:32:03.721206: step: 794/466, loss: 0.014473170042037964
2023-01-22 12:32:04.330764: step: 796/466, loss: 0.00806282926350832
2023-01-22 12:32:04.989966: step: 798/466, loss: 0.04116816446185112
2023-01-22 12:32:05.631447: step: 800/466, loss: 0.023592161014676094
2023-01-22 12:32:06.258740: step: 802/466, loss: 0.055174462497234344
2023-01-22 12:32:06.952338: step: 804/466, loss: 0.08948253095149994
2023-01-22 12:32:07.557940: step: 806/466, loss: 0.034423716366291046
2023-01-22 12:32:08.177626: step: 808/466, loss: 0.04152939096093178
2023-01-22 12:32:08.811313: step: 810/466, loss: 0.25082412362098694
2023-01-22 12:32:09.452084: step: 812/466, loss: 0.01173321157693863
2023-01-22 12:32:10.022299: step: 814/466, loss: 0.011800372041761875
2023-01-22 12:32:10.673361: step: 816/466, loss: 0.06533826142549515
2023-01-22 12:32:11.300833: step: 818/466, loss: 0.007304074242711067
2023-01-22 12:32:11.997044: step: 820/466, loss: 0.04298927262425423
2023-01-22 12:32:12.586154: step: 822/466, loss: 0.010678119026124477
2023-01-22 12:32:13.218995: step: 824/466, loss: 0.11303430050611496
2023-01-22 12:32:13.890934: step: 826/466, loss: 0.06516654789447784
2023-01-22 12:32:14.507753: step: 828/466, loss: 0.03973430395126343
2023-01-22 12:32:15.213870: step: 830/466, loss: 0.050120484083890915
2023-01-22 12:32:15.822480: step: 832/466, loss: 0.058797042816877365
2023-01-22 12:32:16.420997: step: 834/466, loss: 0.11180714517831802
2023-01-22 12:32:17.127680: step: 836/466, loss: 0.044810060411691666
2023-01-22 12:32:17.748753: step: 838/466, loss: 0.42404794692993164
2023-01-22 12:32:18.483645: step: 840/466, loss: 0.046611882746219635
2023-01-22 12:32:19.132680: step: 842/466, loss: 0.015883365646004677
2023-01-22 12:32:19.797789: step: 844/466, loss: 0.03104478307068348
2023-01-22 12:32:20.413447: step: 846/466, loss: 0.010571775957942009
2023-01-22 12:32:21.002125: step: 848/466, loss: 0.00489027751609683
2023-01-22 12:32:21.613144: step: 850/466, loss: 0.006423996761441231
2023-01-22 12:32:22.273968: step: 852/466, loss: 0.10496664047241211
2023-01-22 12:32:22.890312: step: 854/466, loss: 0.0379096120595932
2023-01-22 12:32:23.486032: step: 856/466, loss: 0.0010135396150872111
2023-01-22 12:32:24.336118: step: 858/466, loss: 0.15507668256759644
2023-01-22 12:32:25.004994: step: 860/466, loss: 0.041714731603860855
2023-01-22 12:32:25.661251: step: 862/466, loss: 0.04817929491400719
2023-01-22 12:32:26.233268: step: 864/466, loss: 0.003338088747113943
2023-01-22 12:32:26.883010: step: 866/466, loss: 0.09543223679065704
2023-01-22 12:32:27.474558: step: 868/466, loss: 0.07428394258022308
2023-01-22 12:32:28.105542: step: 870/466, loss: 0.04204535484313965
2023-01-22 12:32:28.701819: step: 872/466, loss: 0.10000576078891754
2023-01-22 12:32:29.335995: step: 874/466, loss: 0.03834407776594162
2023-01-22 12:32:29.999548: step: 876/466, loss: 0.046376850455999374
2023-01-22 12:32:30.592179: step: 878/466, loss: 0.027334975078701973
2023-01-22 12:32:31.222872: step: 880/466, loss: 0.2535788118839264
2023-01-22 12:32:31.866948: step: 882/466, loss: 0.023781809955835342
2023-01-22 12:32:32.465068: step: 884/466, loss: 0.464969277381897
2023-01-22 12:32:33.122037: step: 886/466, loss: 0.030364157631993294
2023-01-22 12:32:33.722409: step: 888/466, loss: 0.10395995527505875
2023-01-22 12:32:34.386602: step: 890/466, loss: 0.0058978162705898285
2023-01-22 12:32:35.048384: step: 892/466, loss: 0.016039518639445305
2023-01-22 12:32:35.674563: step: 894/466, loss: 0.40252816677093506
2023-01-22 12:32:36.283220: step: 896/466, loss: 0.014576230198144913
2023-01-22 12:32:36.945990: step: 898/466, loss: 0.057729076594114304
2023-01-22 12:32:37.542822: step: 900/466, loss: 0.023492462933063507
2023-01-22 12:32:38.226514: step: 902/466, loss: 0.09623562544584274
2023-01-22 12:32:38.826230: step: 904/466, loss: 0.018250683322548866
2023-01-22 12:32:39.454128: step: 906/466, loss: 0.04059088975191116
2023-01-22 12:32:40.100637: step: 908/466, loss: 0.07524502277374268
2023-01-22 12:32:40.801979: step: 910/466, loss: 0.04556982219219208
2023-01-22 12:32:41.392339: step: 912/466, loss: 0.012496293522417545
2023-01-22 12:32:42.072198: step: 914/466, loss: 1.0032553672790527
2023-01-22 12:32:42.687156: step: 916/466, loss: 0.20766794681549072
2023-01-22 12:32:43.334358: step: 918/466, loss: 0.550917387008667
2023-01-22 12:32:43.930708: step: 920/466, loss: 0.030320841819047928
2023-01-22 12:32:44.614408: step: 922/466, loss: 0.08618208765983582
2023-01-22 12:32:45.220907: step: 924/466, loss: 0.5151544213294983
2023-01-22 12:32:45.830391: step: 926/466, loss: 0.045670926570892334
2023-01-22 12:32:46.504015: step: 928/466, loss: 0.016454020515084267
2023-01-22 12:32:47.270303: step: 930/466, loss: 0.06444823741912842
2023-01-22 12:32:47.882930: step: 932/466, loss: 0.11253959685564041
==================================================
Loss: 0.137
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3155917657481365, 'r': 0.34373752094768567, 'f1': 0.32906389380459644}, 'combined': 0.24246813227707104, 'epoch': 23}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.2916768864044103, 'r': 0.2927298715538847, 'f1': 0.2922024303438777}, 'combined': 0.18296787694429728, 'epoch': 23}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2957418644067797, 'r': 0.35073750522625674, 'f1': 0.32090046051082866}, 'combined': 0.23645297090271583, 'epoch': 23}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.29270062919035134, 'r': 0.30775833303859146, 'f1': 0.3000406801643285}, 'combined': 0.1859407032004289, 'epoch': 23}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27262784162349746, 'r': 0.3486739378638279, 'f1': 0.3059969446365317}, 'combined': 0.22547143289007598, 'epoch': 23}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.29530642269433693, 'r': 0.3027825346612822, 'f1': 0.2989977529780161}, 'combined': 0.19834504405472358, 'epoch': 23}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25, 'r': 0.36428571428571427, 'f1': 0.2965116279069767}, 'combined': 0.19767441860465113, 'epoch': 23}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36607142857142855, 'r': 0.44565217391304346, 'f1': 0.4019607843137254}, 'combined': 0.2009803921568627, 'epoch': 23}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.3103448275862069, 'f1': 0.32142857142857145}, 'combined': 0.2142857142857143, 'epoch': 23}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:35:25.921014: step: 2/466, loss: 0.01775951124727726
2023-01-22 12:35:26.543820: step: 4/466, loss: 0.06998228281736374
2023-01-22 12:35:27.158780: step: 6/466, loss: 0.023496080189943314
2023-01-22 12:35:27.808619: step: 8/466, loss: 0.03171665966510773
2023-01-22 12:35:28.409317: step: 10/466, loss: 0.21160852909088135
2023-01-22 12:35:29.055336: step: 12/466, loss: 0.011140208691358566
2023-01-22 12:35:29.708007: step: 14/466, loss: 0.0045223054476082325
2023-01-22 12:35:30.327285: step: 16/466, loss: 0.02822500467300415
2023-01-22 12:35:30.935226: step: 18/466, loss: 0.007921488024294376
2023-01-22 12:35:31.575010: step: 20/466, loss: 0.07815907150506973
2023-01-22 12:35:32.220062: step: 22/466, loss: 0.08718613535165787
2023-01-22 12:35:32.884886: step: 24/466, loss: 0.08531629294157028
2023-01-22 12:35:33.474786: step: 26/466, loss: 0.01115855947136879
2023-01-22 12:35:34.163941: step: 28/466, loss: 0.3936383128166199
2023-01-22 12:35:34.787540: step: 30/466, loss: 0.04807283356785774
2023-01-22 12:35:35.402664: step: 32/466, loss: 0.0031118232291191816
2023-01-22 12:35:36.051951: step: 34/466, loss: 0.04471299797296524
2023-01-22 12:35:36.737456: step: 36/466, loss: 0.09689126163721085
2023-01-22 12:35:37.426287: step: 38/466, loss: 0.004671262577176094
2023-01-22 12:35:38.061447: step: 40/466, loss: 0.11291002482175827
2023-01-22 12:35:38.675133: step: 42/466, loss: 0.02706337347626686
2023-01-22 12:35:39.262252: step: 44/466, loss: 0.053012263029813766
2023-01-22 12:35:39.891407: step: 46/466, loss: 0.033150896430015564
2023-01-22 12:35:40.455215: step: 48/466, loss: 0.025658225640654564
2023-01-22 12:35:41.084880: step: 50/466, loss: 0.06108486279845238
2023-01-22 12:35:41.724528: step: 52/466, loss: 0.12495020031929016
2023-01-22 12:35:42.374311: step: 54/466, loss: 0.05012280493974686
2023-01-22 12:35:43.049722: step: 56/466, loss: 0.10500068217515945
2023-01-22 12:35:43.632366: step: 58/466, loss: 0.046825896948575974
2023-01-22 12:35:44.320193: step: 60/466, loss: 0.027875442057847977
2023-01-22 12:35:45.005101: step: 62/466, loss: 0.053261008113622665
2023-01-22 12:35:45.692143: step: 64/466, loss: 0.10042470693588257
2023-01-22 12:35:46.313507: step: 66/466, loss: 1.264203429222107
2023-01-22 12:35:46.991513: step: 68/466, loss: 0.024331819266080856
2023-01-22 12:35:47.639158: step: 70/466, loss: 0.015103347599506378
2023-01-22 12:35:48.214121: step: 72/466, loss: 0.05606008321046829
2023-01-22 12:35:48.796855: step: 74/466, loss: 0.004255786072462797
2023-01-22 12:35:49.346242: step: 76/466, loss: 0.015752147883176804
2023-01-22 12:35:49.945096: step: 78/466, loss: 0.01863991469144821
2023-01-22 12:35:50.617791: step: 80/466, loss: 0.02777590975165367
2023-01-22 12:35:51.216921: step: 82/466, loss: 0.019921375438570976
2023-01-22 12:35:51.830781: step: 84/466, loss: 0.004241253715008497
2023-01-22 12:35:52.438441: step: 86/466, loss: 0.1516450047492981
2023-01-22 12:35:53.094000: step: 88/466, loss: 0.03991668298840523
2023-01-22 12:35:53.758426: step: 90/466, loss: 0.05472749099135399
2023-01-22 12:35:54.423823: step: 92/466, loss: 0.00998813845217228
2023-01-22 12:35:55.054013: step: 94/466, loss: 0.16966433823108673
2023-01-22 12:35:55.639826: step: 96/466, loss: 0.03190416842699051
2023-01-22 12:35:56.286970: step: 98/466, loss: 0.06969668716192245
2023-01-22 12:35:56.956924: step: 100/466, loss: 0.010890313424170017
2023-01-22 12:35:57.577760: step: 102/466, loss: 0.02054757997393608
2023-01-22 12:35:58.245169: step: 104/466, loss: 0.026327362284064293
2023-01-22 12:35:58.815823: step: 106/466, loss: 0.0259767584502697
2023-01-22 12:35:59.454824: step: 108/466, loss: 0.01270345039665699
2023-01-22 12:36:00.084957: step: 110/466, loss: 0.012134579010307789
2023-01-22 12:36:00.733417: step: 112/466, loss: 0.23109854757785797
2023-01-22 12:36:01.389076: step: 114/466, loss: 0.05138760060071945
2023-01-22 12:36:01.983666: step: 116/466, loss: 0.03566274419426918
2023-01-22 12:36:02.764284: step: 118/466, loss: 0.05119818449020386
2023-01-22 12:36:03.390246: step: 120/466, loss: 0.011486800387501717
2023-01-22 12:36:04.056359: step: 122/466, loss: 0.1277124136686325
2023-01-22 12:36:04.630645: step: 124/466, loss: 0.07726099342107773
2023-01-22 12:36:05.226677: step: 126/466, loss: 0.016203083097934723
2023-01-22 12:36:05.813718: step: 128/466, loss: 0.044843513518571854
2023-01-22 12:36:06.416519: step: 130/466, loss: 0.03943625092506409
2023-01-22 12:36:07.099630: step: 132/466, loss: 0.7324963808059692
2023-01-22 12:36:07.905056: step: 134/466, loss: 0.2553439140319824
2023-01-22 12:36:08.499962: step: 136/466, loss: 0.012169379740953445
2023-01-22 12:36:09.132803: step: 138/466, loss: 0.03544780984520912
2023-01-22 12:36:09.736085: step: 140/466, loss: 0.03327156603336334
2023-01-22 12:36:10.397868: step: 142/466, loss: 0.2415328174829483
2023-01-22 12:36:10.956979: step: 144/466, loss: 0.013524964451789856
2023-01-22 12:36:11.598367: step: 146/466, loss: 0.052955932915210724
2023-01-22 12:36:12.193427: step: 148/466, loss: 0.0393313430249691
2023-01-22 12:36:12.881403: step: 150/466, loss: 0.006056379992514849
2023-01-22 12:36:13.535839: step: 152/466, loss: 0.028438430279493332
2023-01-22 12:36:14.158568: step: 154/466, loss: 0.11125431954860687
2023-01-22 12:36:14.795585: step: 156/466, loss: 0.022854281589388847
2023-01-22 12:36:15.386653: step: 158/466, loss: 0.3715655207633972
2023-01-22 12:36:16.011273: step: 160/466, loss: 0.020477047190070152
2023-01-22 12:36:16.628156: step: 162/466, loss: 0.01693480834364891
2023-01-22 12:36:17.228289: step: 164/466, loss: 0.06682530045509338
2023-01-22 12:36:17.837974: step: 166/466, loss: 0.042962782084941864
2023-01-22 12:36:18.445164: step: 168/466, loss: 0.05419673025608063
2023-01-22 12:36:19.097510: step: 170/466, loss: 0.027051566168665886
2023-01-22 12:36:19.725389: step: 172/466, loss: 0.01761796325445175
2023-01-22 12:36:20.315609: step: 174/466, loss: 0.03369941934943199
2023-01-22 12:36:20.883392: step: 176/466, loss: 0.02449605241417885
2023-01-22 12:36:21.499027: step: 178/466, loss: 0.02717144787311554
2023-01-22 12:36:22.118644: step: 180/466, loss: 0.03494774550199509
2023-01-22 12:36:22.728512: step: 182/466, loss: 0.03236817568540573
2023-01-22 12:36:23.360575: step: 184/466, loss: 0.005535303149372339
2023-01-22 12:36:24.044092: step: 186/466, loss: 0.05312425643205643
2023-01-22 12:36:24.732855: step: 188/466, loss: 0.016179973259568214
2023-01-22 12:36:25.346780: step: 190/466, loss: 0.04713601991534233
2023-01-22 12:36:25.951282: step: 192/466, loss: 0.10981413722038269
2023-01-22 12:36:26.612237: step: 194/466, loss: 0.01001281850039959
2023-01-22 12:36:27.207332: step: 196/466, loss: 0.000854157842695713
2023-01-22 12:36:27.855687: step: 198/466, loss: 0.02450506016612053
2023-01-22 12:36:28.498593: step: 200/466, loss: 0.0063180020079016685
2023-01-22 12:36:29.105504: step: 202/466, loss: 0.017017902806401253
2023-01-22 12:36:29.796360: step: 204/466, loss: 0.04628724977374077
2023-01-22 12:36:30.406507: step: 206/466, loss: 0.02292279526591301
2023-01-22 12:36:31.044143: step: 208/466, loss: 0.011091941967606544
2023-01-22 12:36:31.675544: step: 210/466, loss: 0.027954787015914917
2023-01-22 12:36:32.312473: step: 212/466, loss: 0.003656168933957815
2023-01-22 12:36:32.828990: step: 214/466, loss: 0.044199857860803604
2023-01-22 12:36:33.502093: step: 216/466, loss: 0.056119684129953384
2023-01-22 12:36:34.128717: step: 218/466, loss: 0.030617576092481613
2023-01-22 12:36:34.697020: step: 220/466, loss: 0.05026071518659592
2023-01-22 12:36:35.328526: step: 222/466, loss: 0.0207377802580595
2023-01-22 12:36:35.929276: step: 224/466, loss: 0.06010458990931511
2023-01-22 12:36:36.510009: step: 226/466, loss: 0.04278656095266342
2023-01-22 12:36:37.128661: step: 228/466, loss: 0.034164175391197205
2023-01-22 12:36:37.767981: step: 230/466, loss: 0.08308444172143936
2023-01-22 12:36:38.436348: step: 232/466, loss: 0.0037873126566410065
2023-01-22 12:36:39.067474: step: 234/466, loss: 0.1749260425567627
2023-01-22 12:36:39.683361: step: 236/466, loss: 0.03200647607445717
2023-01-22 12:36:40.275023: step: 238/466, loss: 0.2304929941892624
2023-01-22 12:36:40.884135: step: 240/466, loss: 0.024186624214053154
2023-01-22 12:36:41.496494: step: 242/466, loss: 0.006505788769572973
2023-01-22 12:36:42.122119: step: 244/466, loss: 5.718115329742432
2023-01-22 12:36:42.737846: step: 246/466, loss: 0.0025009613018482924
2023-01-22 12:36:43.352325: step: 248/466, loss: 0.042459696531295776
2023-01-22 12:36:44.031572: step: 250/466, loss: 0.07881811261177063
2023-01-22 12:36:44.686716: step: 252/466, loss: 0.02184082195162773
2023-01-22 12:36:45.319825: step: 254/466, loss: 0.01406814344227314
2023-01-22 12:36:45.980192: step: 256/466, loss: 0.021873051300644875
2023-01-22 12:36:46.564593: step: 258/466, loss: 0.024203473702073097
2023-01-22 12:36:47.180115: step: 260/466, loss: 0.046456798911094666
2023-01-22 12:36:47.867788: step: 262/466, loss: 0.006486671045422554
2023-01-22 12:36:48.428513: step: 264/466, loss: 0.08957996964454651
2023-01-22 12:36:49.128081: step: 266/466, loss: 0.05139755457639694
2023-01-22 12:36:49.768414: step: 268/466, loss: 0.02413560450077057
2023-01-22 12:36:50.398940: step: 270/466, loss: 0.06363941729068756
2023-01-22 12:36:51.073201: step: 272/466, loss: 0.5705989003181458
2023-01-22 12:36:51.723901: step: 274/466, loss: 0.03353706747293472
2023-01-22 12:36:52.310081: step: 276/466, loss: 0.0007393390405923128
2023-01-22 12:36:52.967119: step: 278/466, loss: 0.006027671508491039
2023-01-22 12:36:53.643734: step: 280/466, loss: 0.012460839934647083
2023-01-22 12:36:54.287023: step: 282/466, loss: 0.029581815004348755
2023-01-22 12:36:54.938224: step: 284/466, loss: 0.09199880063533783
2023-01-22 12:36:55.529261: step: 286/466, loss: 0.02445092611014843
2023-01-22 12:36:56.132607: step: 288/466, loss: 0.08971263468265533
2023-01-22 12:36:56.715816: step: 290/466, loss: 0.01842050813138485
2023-01-22 12:36:57.265428: step: 292/466, loss: 0.022412758320569992
2023-01-22 12:36:57.928462: step: 294/466, loss: 0.8509193658828735
2023-01-22 12:36:58.568557: step: 296/466, loss: 0.18079602718353271
2023-01-22 12:36:59.183721: step: 298/466, loss: 0.09790819883346558
2023-01-22 12:36:59.736426: step: 300/466, loss: 0.02296244353055954
2023-01-22 12:37:00.337438: step: 302/466, loss: 0.007325155194848776
2023-01-22 12:37:00.935342: step: 304/466, loss: 0.037404581904411316
2023-01-22 12:37:01.567586: step: 306/466, loss: 0.02718578651547432
2023-01-22 12:37:02.247471: step: 308/466, loss: 0.03230520710349083
2023-01-22 12:37:02.888882: step: 310/466, loss: 0.028744935989379883
2023-01-22 12:37:03.558300: step: 312/466, loss: 0.04959486797451973
2023-01-22 12:37:04.201008: step: 314/466, loss: 0.03979591652750969
2023-01-22 12:37:04.872778: step: 316/466, loss: 0.01729343831539154
2023-01-22 12:37:05.453231: step: 318/466, loss: 0.007263426668941975
2023-01-22 12:37:06.146800: step: 320/466, loss: 0.04841906949877739
2023-01-22 12:37:06.759625: step: 322/466, loss: 0.02187824435532093
2023-01-22 12:37:07.379709: step: 324/466, loss: 0.02896566316485405
2023-01-22 12:37:07.973966: step: 326/466, loss: 0.10468301177024841
2023-01-22 12:37:08.595496: step: 328/466, loss: 0.0009681862429715693
2023-01-22 12:37:09.207523: step: 330/466, loss: 0.03846053034067154
2023-01-22 12:37:09.833467: step: 332/466, loss: 0.08358601480722427
2023-01-22 12:37:10.367605: step: 334/466, loss: 0.06232349947094917
2023-01-22 12:37:10.989499: step: 336/466, loss: 0.00839509442448616
2023-01-22 12:37:11.671750: step: 338/466, loss: 0.018033072352409363
2023-01-22 12:37:12.311137: step: 340/466, loss: 0.02174694463610649
2023-01-22 12:37:12.921002: step: 342/466, loss: 0.03843015804886818
2023-01-22 12:37:13.514745: step: 344/466, loss: 0.02696356177330017
2023-01-22 12:37:14.147676: step: 346/466, loss: 0.0023052766919136047
2023-01-22 12:37:14.821717: step: 348/466, loss: 0.09128759056329727
2023-01-22 12:37:15.395791: step: 350/466, loss: 0.034821297973394394
2023-01-22 12:37:16.010312: step: 352/466, loss: 0.04999520629644394
2023-01-22 12:37:16.584149: step: 354/466, loss: 0.0011430811136960983
2023-01-22 12:37:17.204823: step: 356/466, loss: 0.012842460535466671
2023-01-22 12:37:17.803722: step: 358/466, loss: 0.010257087647914886
2023-01-22 12:37:18.546054: step: 360/466, loss: 0.06453787535429001
2023-01-22 12:37:19.249685: step: 362/466, loss: 0.0472383126616478
2023-01-22 12:37:19.851195: step: 364/466, loss: 0.013958015479147434
2023-01-22 12:37:20.519445: step: 366/466, loss: 0.023365404456853867
2023-01-22 12:37:21.091758: step: 368/466, loss: 0.12553706765174866
2023-01-22 12:37:21.694734: step: 370/466, loss: 0.03481516242027283
2023-01-22 12:37:22.284862: step: 372/466, loss: 0.016188135370612144
2023-01-22 12:37:22.892118: step: 374/466, loss: 0.03400895744562149
2023-01-22 12:37:23.543959: step: 376/466, loss: 0.061151888221502304
2023-01-22 12:37:24.241559: step: 378/466, loss: 0.0034502113703638315
2023-01-22 12:37:24.859505: step: 380/466, loss: 0.5659694075584412
2023-01-22 12:37:25.521114: step: 382/466, loss: 0.07413993030786514
2023-01-22 12:37:26.116200: step: 384/466, loss: 0.008955743163824081
2023-01-22 12:37:26.754744: step: 386/466, loss: 0.04835180565714836
2023-01-22 12:37:27.435432: step: 388/466, loss: 0.5826194882392883
2023-01-22 12:37:28.082083: step: 390/466, loss: 0.43313485383987427
2023-01-22 12:37:28.703823: step: 392/466, loss: 4.415528746903874e-05
2023-01-22 12:37:29.259664: step: 394/466, loss: 0.03372623771429062
2023-01-22 12:37:29.852734: step: 396/466, loss: 0.0779719427227974
2023-01-22 12:37:30.440266: step: 398/466, loss: 0.03113323450088501
2023-01-22 12:37:31.080198: step: 400/466, loss: 0.014071152545511723
2023-01-22 12:37:31.706245: step: 402/466, loss: 0.26610639691352844
2023-01-22 12:37:32.283893: step: 404/466, loss: 0.026780832558870316
2023-01-22 12:37:32.941089: step: 406/466, loss: 0.042376335710287094
2023-01-22 12:37:33.569990: step: 408/466, loss: 0.04931849613785744
2023-01-22 12:37:34.201907: step: 410/466, loss: 0.03209669142961502
2023-01-22 12:37:34.819774: step: 412/466, loss: 0.04621882364153862
2023-01-22 12:37:35.458220: step: 414/466, loss: 0.23924817144870758
2023-01-22 12:37:35.979550: step: 416/466, loss: 0.004419934935867786
2023-01-22 12:37:36.584908: step: 418/466, loss: 0.018524905666708946
2023-01-22 12:37:37.124729: step: 420/466, loss: 0.04037218168377876
2023-01-22 12:37:37.732945: step: 422/466, loss: 0.005396811757236719
2023-01-22 12:37:38.326592: step: 424/466, loss: 0.025286972522735596
2023-01-22 12:37:38.980108: step: 426/466, loss: 0.006728660315275192
2023-01-22 12:37:39.618522: step: 428/466, loss: 0.033965032547712326
2023-01-22 12:37:40.249011: step: 430/466, loss: 0.1107817143201828
2023-01-22 12:37:40.804786: step: 432/466, loss: 0.03414522856473923
2023-01-22 12:37:41.392169: step: 434/466, loss: 0.11841520667076111
2023-01-22 12:37:42.079101: step: 436/466, loss: 0.029670242220163345
2023-01-22 12:37:42.662391: step: 438/466, loss: 0.07413268089294434
2023-01-22 12:37:43.255057: step: 440/466, loss: 0.05652602016925812
2023-01-22 12:37:43.895880: step: 442/466, loss: 0.004003919195383787
2023-01-22 12:37:44.469538: step: 444/466, loss: 0.20921221375465393
2023-01-22 12:37:45.103551: step: 446/466, loss: 0.01874626986682415
2023-01-22 12:37:45.767871: step: 448/466, loss: 0.2473910003900528
2023-01-22 12:37:46.435756: step: 450/466, loss: 0.2558498680591583
2023-01-22 12:37:47.059233: step: 452/466, loss: 0.04292437061667442
2023-01-22 12:37:47.680411: step: 454/466, loss: 0.040209073573350906
2023-01-22 12:37:48.299009: step: 456/466, loss: 0.02306332066655159
2023-01-22 12:37:48.893252: step: 458/466, loss: 0.020379625260829926
2023-01-22 12:37:49.451580: step: 460/466, loss: 0.0014458958758041263
2023-01-22 12:37:50.042162: step: 462/466, loss: 0.02728479914367199
2023-01-22 12:37:50.626709: step: 464/466, loss: 0.055573392659425735
2023-01-22 12:37:51.200621: step: 466/466, loss: 0.013155962340533733
2023-01-22 12:37:51.860455: step: 468/466, loss: 0.02111225575208664
2023-01-22 12:37:52.417438: step: 470/466, loss: 0.00214797118678689
2023-01-22 12:37:53.009166: step: 472/466, loss: 0.0030293106101453304
2023-01-22 12:37:53.648999: step: 474/466, loss: 0.014872650615870953
2023-01-22 12:37:54.259418: step: 476/466, loss: 0.006019831635057926
2023-01-22 12:37:54.881221: step: 478/466, loss: 0.03690674155950546
2023-01-22 12:37:55.510931: step: 480/466, loss: 0.04174504429101944
2023-01-22 12:37:56.169891: step: 482/466, loss: 0.04920300841331482
2023-01-22 12:37:56.769458: step: 484/466, loss: 0.01668628863990307
2023-01-22 12:37:57.351898: step: 486/466, loss: 0.03446260094642639
2023-01-22 12:37:58.011401: step: 488/466, loss: 0.13341861963272095
2023-01-22 12:37:58.710605: step: 490/466, loss: 0.05224217474460602
2023-01-22 12:37:59.362458: step: 492/466, loss: 0.05532006546854973
2023-01-22 12:37:59.994073: step: 494/466, loss: 0.015033143572509289
2023-01-22 12:38:00.562548: step: 496/466, loss: 0.01447263266891241
2023-01-22 12:38:01.201484: step: 498/466, loss: 0.9773015975952148
2023-01-22 12:38:01.835326: step: 500/466, loss: 0.01731417328119278
2023-01-22 12:38:02.474773: step: 502/466, loss: 0.23520046472549438
2023-01-22 12:38:03.086808: step: 504/466, loss: 0.01694115251302719
2023-01-22 12:38:03.806202: step: 506/466, loss: 0.023830056190490723
2023-01-22 12:38:04.466229: step: 508/466, loss: 0.013624468818306923
2023-01-22 12:38:05.142749: step: 510/466, loss: 0.08544586598873138
2023-01-22 12:38:05.845311: step: 512/466, loss: 0.2895181179046631
2023-01-22 12:38:06.468971: step: 514/466, loss: 0.3380913734436035
2023-01-22 12:38:07.027929: step: 516/466, loss: 0.010832487605512142
2023-01-22 12:38:07.631417: step: 518/466, loss: 0.019181370735168457
2023-01-22 12:38:08.313556: step: 520/466, loss: 0.03397896885871887
2023-01-22 12:38:08.944718: step: 522/466, loss: 0.008898376487195492
2023-01-22 12:38:09.561901: step: 524/466, loss: 0.001290146610699594
2023-01-22 12:38:10.233449: step: 526/466, loss: 0.015028296038508415
2023-01-22 12:38:10.861972: step: 528/466, loss: 0.02278532274067402
2023-01-22 12:38:11.503002: step: 530/466, loss: 0.05829382687807083
2023-01-22 12:38:12.108058: step: 532/466, loss: 0.011463063769042492
2023-01-22 12:38:12.727586: step: 534/466, loss: 0.5001119375228882
2023-01-22 12:38:13.296523: step: 536/466, loss: 0.023553278297185898
2023-01-22 12:38:13.977781: step: 538/466, loss: 0.024624977260828018
2023-01-22 12:38:14.586053: step: 540/466, loss: 0.037908170372247696
2023-01-22 12:38:15.128415: step: 542/466, loss: 0.045436758548021317
2023-01-22 12:38:15.712006: step: 544/466, loss: 1.2077014446258545
2023-01-22 12:38:16.289110: step: 546/466, loss: 0.11791954934597015
2023-01-22 12:38:16.899992: step: 548/466, loss: 0.07331138849258423
2023-01-22 12:38:17.599792: step: 550/466, loss: 0.005301305558532476
2023-01-22 12:38:18.258319: step: 552/466, loss: 0.2202800214290619
2023-01-22 12:38:18.886082: step: 554/466, loss: 0.04418746754527092
2023-01-22 12:38:19.560156: step: 556/466, loss: 0.023405754938721657
2023-01-22 12:38:20.167805: step: 558/466, loss: 0.0036683911457657814
2023-01-22 12:38:20.790118: step: 560/466, loss: 1.2640928030014038
2023-01-22 12:38:21.457472: step: 562/466, loss: 0.026077618822455406
2023-01-22 12:38:22.017321: step: 564/466, loss: 0.05308159068226814
2023-01-22 12:38:22.617011: step: 566/466, loss: 0.015728816390037537
2023-01-22 12:38:23.258518: step: 568/466, loss: 0.028387639671564102
2023-01-22 12:38:23.925675: step: 570/466, loss: 0.043330736458301544
2023-01-22 12:38:24.592101: step: 572/466, loss: 0.06042530760169029
2023-01-22 12:38:25.207805: step: 574/466, loss: 0.013226497918367386
2023-01-22 12:38:25.803740: step: 576/466, loss: 0.03364450857043266
2023-01-22 12:38:26.358999: step: 578/466, loss: 0.054037388414144516
2023-01-22 12:38:26.988416: step: 580/466, loss: 0.01870799995958805
2023-01-22 12:38:27.589604: step: 582/466, loss: 0.04428953677415848
2023-01-22 12:38:28.196125: step: 584/466, loss: 0.024038489907979965
2023-01-22 12:38:28.814544: step: 586/466, loss: 0.01239954773336649
2023-01-22 12:38:29.467178: step: 588/466, loss: 0.010824295692145824
2023-01-22 12:38:30.067701: step: 590/466, loss: 0.049315545707941055
2023-01-22 12:38:30.789546: step: 592/466, loss: 4.014024257659912
2023-01-22 12:38:31.398550: step: 594/466, loss: 0.05163121968507767
2023-01-22 12:38:32.013099: step: 596/466, loss: 0.031344205141067505
2023-01-22 12:38:32.698523: step: 598/466, loss: 0.08736274391412735
2023-01-22 12:38:33.305966: step: 600/466, loss: 0.08165568113327026
2023-01-22 12:38:33.984392: step: 602/466, loss: 0.08569925278425217
2023-01-22 12:38:34.604480: step: 604/466, loss: 0.05095534771680832
2023-01-22 12:38:35.219932: step: 606/466, loss: 0.045369550585746765
2023-01-22 12:38:35.891136: step: 608/466, loss: 0.01282559148967266
2023-01-22 12:38:36.515128: step: 610/466, loss: 0.0015983064658939838
2023-01-22 12:38:37.036577: step: 612/466, loss: 0.01708504930138588
2023-01-22 12:38:37.655843: step: 614/466, loss: 0.018791068345308304
2023-01-22 12:38:38.315163: step: 616/466, loss: 0.07073036581277847
2023-01-22 12:38:38.955716: step: 618/466, loss: 0.029045097529888153
2023-01-22 12:38:39.609136: step: 620/466, loss: 0.020562678575515747
2023-01-22 12:38:40.237967: step: 622/466, loss: 0.05618838593363762
2023-01-22 12:38:40.886495: step: 624/466, loss: 0.04314511641860008
2023-01-22 12:38:41.528939: step: 626/466, loss: 0.0668528750538826
2023-01-22 12:38:42.249290: step: 628/466, loss: 0.010574841871857643
2023-01-22 12:38:42.909373: step: 630/466, loss: 0.01126186829060316
2023-01-22 12:38:43.545916: step: 632/466, loss: 0.016938580200076103
2023-01-22 12:38:44.176535: step: 634/466, loss: 0.03811643272638321
2023-01-22 12:38:44.831250: step: 636/466, loss: 0.03264860808849335
2023-01-22 12:38:45.422632: step: 638/466, loss: 0.04469931125640869
2023-01-22 12:38:45.956752: step: 640/466, loss: 0.08351390063762665
2023-01-22 12:38:46.567022: step: 642/466, loss: 0.018482796847820282
2023-01-22 12:38:47.160999: step: 644/466, loss: 0.027051081880927086
2023-01-22 12:38:47.806739: step: 646/466, loss: 0.014741193503141403
2023-01-22 12:38:48.432091: step: 648/466, loss: 0.02814878523349762
2023-01-22 12:38:49.011051: step: 650/466, loss: 1.3097721338272095
2023-01-22 12:38:49.587143: step: 652/466, loss: 0.0610317625105381
2023-01-22 12:38:50.219810: step: 654/466, loss: 0.03113587759435177
2023-01-22 12:38:50.865653: step: 656/466, loss: 0.2117530256509781
2023-01-22 12:38:51.501458: step: 658/466, loss: 0.6282182931900024
2023-01-22 12:38:52.143751: step: 660/466, loss: 0.012697635218501091
2023-01-22 12:38:52.801802: step: 662/466, loss: 0.010068407282233238
2023-01-22 12:38:53.409942: step: 664/466, loss: 0.03171693906188011
2023-01-22 12:38:54.022366: step: 666/466, loss: 0.35073983669281006
2023-01-22 12:38:54.627401: step: 668/466, loss: 0.027183786034584045
2023-01-22 12:38:55.331123: step: 670/466, loss: 0.005791663192212582
2023-01-22 12:38:55.993835: step: 672/466, loss: 0.033167000859975815
2023-01-22 12:38:56.671075: step: 674/466, loss: 0.02182154357433319
2023-01-22 12:38:57.284315: step: 676/466, loss: 0.015532762743532658
2023-01-22 12:38:57.906735: step: 678/466, loss: 0.14364345371723175
2023-01-22 12:38:58.503924: step: 680/466, loss: 0.03017961047589779
2023-01-22 12:38:59.116278: step: 682/466, loss: 0.03674246743321419
2023-01-22 12:38:59.707408: step: 684/466, loss: 0.3185787498950958
2023-01-22 12:39:00.297919: step: 686/466, loss: 0.010634418576955795
2023-01-22 12:39:00.875460: step: 688/466, loss: 0.7276974320411682
2023-01-22 12:39:01.485805: step: 690/466, loss: 0.01223810762166977
2023-01-22 12:39:02.096854: step: 692/466, loss: 0.025081532076001167
2023-01-22 12:39:02.713853: step: 694/466, loss: 0.016418136656284332
2023-01-22 12:39:03.250756: step: 696/466, loss: 0.014432492665946484
2023-01-22 12:39:03.824212: step: 698/466, loss: 0.022362738847732544
2023-01-22 12:39:04.441202: step: 700/466, loss: 0.036238569766283035
2023-01-22 12:39:05.065427: step: 702/466, loss: 0.022475963458418846
2023-01-22 12:39:05.624030: step: 704/466, loss: 0.009691936895251274
2023-01-22 12:39:06.273952: step: 706/466, loss: 0.019086472690105438
2023-01-22 12:39:06.914154: step: 708/466, loss: 0.03635561466217041
2023-01-22 12:39:07.512208: step: 710/466, loss: 0.05995665863156319
2023-01-22 12:39:08.142925: step: 712/466, loss: 0.08793265372514725
2023-01-22 12:39:08.705070: step: 714/466, loss: 0.04483603686094284
2023-01-22 12:39:09.335783: step: 716/466, loss: 0.0006318181985989213
2023-01-22 12:39:09.935415: step: 718/466, loss: 0.04581335559487343
2023-01-22 12:39:10.584865: step: 720/466, loss: 0.054784007370471954
2023-01-22 12:39:11.175905: step: 722/466, loss: 0.008994770236313343
2023-01-22 12:39:11.914135: step: 724/466, loss: 0.07038211822509766
2023-01-22 12:39:12.594167: step: 726/466, loss: 0.02739771641790867
2023-01-22 12:39:13.247392: step: 728/466, loss: 0.0066716414876282215
2023-01-22 12:39:13.829254: step: 730/466, loss: 0.023032061755657196
2023-01-22 12:39:14.499085: step: 732/466, loss: 0.05693968012928963
2023-01-22 12:39:15.131524: step: 734/466, loss: 0.038457415997982025
2023-01-22 12:39:15.715707: step: 736/466, loss: 0.04100510850548744
2023-01-22 12:39:16.364968: step: 738/466, loss: 0.04011070355772972
2023-01-22 12:39:16.933063: step: 740/466, loss: 0.008213753812015057
2023-01-22 12:39:17.541523: step: 742/466, loss: 0.06475730240345001
2023-01-22 12:39:18.156565: step: 744/466, loss: 0.05782656744122505
2023-01-22 12:39:18.745418: step: 746/466, loss: 0.00479760579764843
2023-01-22 12:39:19.396048: step: 748/466, loss: 0.3707916736602783
2023-01-22 12:39:20.117574: step: 750/466, loss: 0.010022311471402645
2023-01-22 12:39:20.742665: step: 752/466, loss: 0.0010830792598426342
2023-01-22 12:39:21.287511: step: 754/466, loss: 0.017043301835656166
2023-01-22 12:39:21.967586: step: 756/466, loss: 0.03057851642370224
2023-01-22 12:39:22.599418: step: 758/466, loss: 0.07336274534463882
2023-01-22 12:39:23.197282: step: 760/466, loss: 0.18320348858833313
2023-01-22 12:39:23.946273: step: 762/466, loss: 0.0185698289424181
2023-01-22 12:39:24.605402: step: 764/466, loss: 0.017747841775417328
2023-01-22 12:39:25.290970: step: 766/466, loss: 0.04033486172556877
2023-01-22 12:39:25.854671: step: 768/466, loss: 0.030373042449355125
2023-01-22 12:39:26.533019: step: 770/466, loss: 0.02626446820795536
2023-01-22 12:39:27.196277: step: 772/466, loss: 0.0635000541806221
2023-01-22 12:39:27.844175: step: 774/466, loss: 0.028376979753375053
2023-01-22 12:39:28.463040: step: 776/466, loss: 0.015307756140828133
2023-01-22 12:39:29.138144: step: 778/466, loss: 0.031209155917167664
2023-01-22 12:39:29.786302: step: 780/466, loss: 0.01880793273448944
2023-01-22 12:39:30.410958: step: 782/466, loss: 0.04064683988690376
2023-01-22 12:39:31.016370: step: 784/466, loss: 0.02077857404947281
2023-01-22 12:39:31.569867: step: 786/466, loss: 0.07937052100896835
2023-01-22 12:39:32.112576: step: 788/466, loss: 0.017864972352981567
2023-01-22 12:39:32.710055: step: 790/466, loss: 0.06696239113807678
2023-01-22 12:39:33.335757: step: 792/466, loss: 0.10035181045532227
2023-01-22 12:39:33.929041: step: 794/466, loss: 0.01624724082648754
2023-01-22 12:39:34.521849: step: 796/466, loss: 0.016496853902935982
2023-01-22 12:39:35.119210: step: 798/466, loss: 0.021680563688278198
2023-01-22 12:39:35.716258: step: 800/466, loss: 0.13155917823314667
2023-01-22 12:39:36.381138: step: 802/466, loss: 0.0448790118098259
2023-01-22 12:39:37.046137: step: 804/466, loss: 0.04087737947702408
2023-01-22 12:39:37.663027: step: 806/466, loss: 0.06466640532016754
2023-01-22 12:39:38.279911: step: 808/466, loss: 0.021056322380900383
2023-01-22 12:39:38.900875: step: 810/466, loss: 0.05157526209950447
2023-01-22 12:39:39.606974: step: 812/466, loss: 0.15065328776836395
2023-01-22 12:39:40.200911: step: 814/466, loss: 0.11482340097427368
2023-01-22 12:39:40.768503: step: 816/466, loss: 0.015318148769438267
2023-01-22 12:39:41.441184: step: 818/466, loss: 0.06725523620843887
2023-01-22 12:39:42.195903: step: 820/466, loss: 0.12060696631669998
2023-01-22 12:39:42.783108: step: 822/466, loss: 0.03064657375216484
2023-01-22 12:39:43.384527: step: 824/466, loss: 0.004661441780626774
2023-01-22 12:39:43.962089: step: 826/466, loss: 0.04126424714922905
2023-01-22 12:39:44.530193: step: 828/466, loss: 0.009859644807875156
2023-01-22 12:39:45.165436: step: 830/466, loss: 0.03717637434601784
2023-01-22 12:39:45.807539: step: 832/466, loss: 0.025209451094269753
2023-01-22 12:39:46.427770: step: 834/466, loss: 0.015618618577718735
2023-01-22 12:39:47.066747: step: 836/466, loss: 0.042017657309770584
2023-01-22 12:39:47.635396: step: 838/466, loss: 0.05587295815348625
2023-01-22 12:39:48.315801: step: 840/466, loss: 0.09808378666639328
2023-01-22 12:39:49.037714: step: 842/466, loss: 0.019855311140418053
2023-01-22 12:39:49.726840: step: 844/466, loss: 0.18799708783626556
2023-01-22 12:39:50.415996: step: 846/466, loss: 0.18601791560649872
2023-01-22 12:39:51.046565: step: 848/466, loss: 0.057044170796871185
2023-01-22 12:39:51.657405: step: 850/466, loss: 0.04101067781448364
2023-01-22 12:39:52.250055: step: 852/466, loss: 0.033392854034900665
2023-01-22 12:39:52.840151: step: 854/466, loss: 1.741076111793518
2023-01-22 12:39:53.394457: step: 856/466, loss: 0.05415608361363411
2023-01-22 12:39:54.017763: step: 858/466, loss: 0.03163951262831688
2023-01-22 12:39:54.639019: step: 860/466, loss: 0.03953757509589195
2023-01-22 12:39:55.300318: step: 862/466, loss: 0.03556588664650917
2023-01-22 12:39:55.898240: step: 864/466, loss: 0.010855968110263348
2023-01-22 12:39:56.554705: step: 866/466, loss: 0.033087357878685
2023-01-22 12:39:57.250350: step: 868/466, loss: 0.1575131118297577
2023-01-22 12:39:57.833993: step: 870/466, loss: 0.042996399104595184
2023-01-22 12:39:58.445143: step: 872/466, loss: 0.1106543093919754
2023-01-22 12:39:59.121588: step: 874/466, loss: 0.0015727959107607603
2023-01-22 12:39:59.741358: step: 876/466, loss: 0.014399182051420212
2023-01-22 12:40:00.343515: step: 878/466, loss: 0.039629943668842316
2023-01-22 12:40:00.933767: step: 880/466, loss: 0.08232701569795609
2023-01-22 12:40:01.561116: step: 882/466, loss: 0.026552898809313774
2023-01-22 12:40:02.183953: step: 884/466, loss: 0.012258796021342278
2023-01-22 12:40:02.774595: step: 886/466, loss: 0.020021259784698486
2023-01-22 12:40:03.417070: step: 888/466, loss: 0.035042934119701385
2023-01-22 12:40:04.060326: step: 890/466, loss: 0.001964666647836566
2023-01-22 12:40:04.663552: step: 892/466, loss: 0.07394883036613464
2023-01-22 12:40:05.255953: step: 894/466, loss: 0.33917370438575745
2023-01-22 12:40:05.872371: step: 896/466, loss: 0.031111711636185646
2023-01-22 12:40:06.477541: step: 898/466, loss: 0.03684708848595619
2023-01-22 12:40:07.160586: step: 900/466, loss: 0.038802359253168106
2023-01-22 12:40:07.732675: step: 902/466, loss: 0.023610800504684448
2023-01-22 12:40:08.389140: step: 904/466, loss: 0.02906438708305359
2023-01-22 12:40:09.095330: step: 906/466, loss: 0.0029160077683627605
2023-01-22 12:40:09.686147: step: 908/466, loss: 0.020668020471930504
2023-01-22 12:40:10.301542: step: 910/466, loss: 0.026013070717453957
2023-01-22 12:40:10.933806: step: 912/466, loss: 0.0015297239879146218
2023-01-22 12:40:11.543889: step: 914/466, loss: 0.03978642448782921
2023-01-22 12:40:12.171711: step: 916/466, loss: 0.020224010571837425
2023-01-22 12:40:12.783045: step: 918/466, loss: 0.049149610102176666
2023-01-22 12:40:13.351754: step: 920/466, loss: 0.05288805440068245
2023-01-22 12:40:13.919924: step: 922/466, loss: 0.0071567329578101635
2023-01-22 12:40:14.587282: step: 924/466, loss: 0.055217765271663666
2023-01-22 12:40:15.196899: step: 926/466, loss: 0.03580210730433464
2023-01-22 12:40:15.836504: step: 928/466, loss: 0.04881547391414642
2023-01-22 12:40:16.545476: step: 930/466, loss: 0.020376309752464294
2023-01-22 12:40:17.156914: step: 932/466, loss: 0.402281254529953
==================================================
Loss: 0.099
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32142421236171237, 'r': 0.3293530828753789, 'f1': 0.3253403461580594}, 'combined': 0.239724465590149, 'epoch': 24}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.31814115417888034, 'r': 0.2940221497104454, 'f1': 0.3056065120817762}, 'combined': 0.1913610870044767, 'epoch': 24}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3021738728750924, 'r': 0.3526317491806107, 'f1': 0.32545872472536225}, 'combined': 0.23981169190289847, 'epoch': 24}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3206838392301461, 'r': 0.3070808243891561, 'f1': 0.31373495013663905}, 'combined': 0.19442729304242418, 'epoch': 24}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27161237027374396, 'r': 0.3489213940708248, 'f1': 0.3054511207231307}, 'combined': 0.2250692468486226, 'epoch': 24}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.31590879266112915, 'r': 0.30534996219278066, 'f1': 0.31053964919376037}, 'combined': 0.20600154946516777, 'epoch': 24}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24728260869565216, 'r': 0.325, 'f1': 0.28086419753086417}, 'combined': 0.18724279835390945, 'epoch': 24}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3142857142857143, 'r': 0.4782608695652174, 'f1': 0.3793103448275862}, 'combined': 0.1896551724137931, 'epoch': 24}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2692307692307692, 'r': 0.2413793103448276, 'f1': 0.2545454545454545}, 'combined': 0.16969696969696968, 'epoch': 24}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:42:53.995056: step: 2/466, loss: 0.123256616294384
2023-01-22 12:42:54.634149: step: 4/466, loss: 0.11478867381811142
2023-01-22 12:42:55.318447: step: 6/466, loss: 0.15547913312911987
2023-01-22 12:42:55.929691: step: 8/466, loss: 0.04502660036087036
2023-01-22 12:42:56.621072: step: 10/466, loss: 0.06763220578432083
2023-01-22 12:42:57.257804: step: 12/466, loss: 0.043466079980134964
2023-01-22 12:42:57.999661: step: 14/466, loss: 0.3706084191799164
2023-01-22 12:42:58.672294: step: 16/466, loss: 0.06069587543606758
2023-01-22 12:42:59.395962: step: 18/466, loss: 0.0064912224188447
2023-01-22 12:43:00.036322: step: 20/466, loss: 0.007945464923977852
2023-01-22 12:43:00.633227: step: 22/466, loss: 0.00964177306741476
2023-01-22 12:43:01.310915: step: 24/466, loss: 0.003734796540811658
2023-01-22 12:43:01.936348: step: 26/466, loss: 0.02065412513911724
2023-01-22 12:43:02.608780: step: 28/466, loss: 0.08720247447490692
2023-01-22 12:43:03.259168: step: 30/466, loss: 0.022077567875385284
2023-01-22 12:43:03.906254: step: 32/466, loss: 0.1807323545217514
2023-01-22 12:43:04.517042: step: 34/466, loss: 0.006703019607812166
2023-01-22 12:43:05.136644: step: 36/466, loss: 0.00502686807885766
2023-01-22 12:43:05.772336: step: 38/466, loss: 0.0813484638929367
2023-01-22 12:43:06.446252: step: 40/466, loss: 0.0033198362216353416
2023-01-22 12:43:07.071953: step: 42/466, loss: 0.8578417897224426
2023-01-22 12:43:07.653080: step: 44/466, loss: 0.013072691857814789
2023-01-22 12:43:08.282735: step: 46/466, loss: 0.01905766874551773
2023-01-22 12:43:08.912118: step: 48/466, loss: 0.4790077209472656
2023-01-22 12:43:09.563241: step: 50/466, loss: 0.05062977224588394
2023-01-22 12:43:10.169810: step: 52/466, loss: 0.025456015020608902
2023-01-22 12:43:10.724739: step: 54/466, loss: 0.002291387179866433
2023-01-22 12:43:11.342191: step: 56/466, loss: 0.01267669815570116
2023-01-22 12:43:11.966079: step: 58/466, loss: 0.0442313551902771
2023-01-22 12:43:12.570540: step: 60/466, loss: 0.01942724548280239
2023-01-22 12:43:13.150689: step: 62/466, loss: 0.06036658585071564
2023-01-22 12:43:13.722153: step: 64/466, loss: 0.021152399480342865
2023-01-22 12:43:14.278643: step: 66/466, loss: 0.0027935849502682686
2023-01-22 12:43:14.922879: step: 68/466, loss: 2.237856864929199
2023-01-22 12:43:15.667096: step: 70/466, loss: 0.08581312745809555
2023-01-22 12:43:16.294127: step: 72/466, loss: 0.024593474343419075
2023-01-22 12:43:16.856328: step: 74/466, loss: 0.06295838207006454
2023-01-22 12:43:17.515391: step: 76/466, loss: 0.01236707903444767
2023-01-22 12:43:18.194215: step: 78/466, loss: 0.048196546733379364
2023-01-22 12:43:18.865570: step: 80/466, loss: 0.15854839980602264
2023-01-22 12:43:19.479312: step: 82/466, loss: 0.0425398051738739
2023-01-22 12:43:20.198702: step: 84/466, loss: 0.041842229664325714
2023-01-22 12:43:20.763368: step: 86/466, loss: 0.05728701874613762
2023-01-22 12:43:21.325058: step: 88/466, loss: 0.034428469836711884
2023-01-22 12:43:21.978780: step: 90/466, loss: 0.06219211965799332
2023-01-22 12:43:22.673990: step: 92/466, loss: 0.02116026170551777
2023-01-22 12:43:23.270335: step: 94/466, loss: 0.017197037115693092
2023-01-22 12:43:23.926953: step: 96/466, loss: 0.02358037605881691
2023-01-22 12:43:24.576195: step: 98/466, loss: 0.0025120610371232033
2023-01-22 12:43:25.187294: step: 100/466, loss: 0.03598516061902046
2023-01-22 12:43:25.759099: step: 102/466, loss: 0.06651560962200165
2023-01-22 12:43:26.416478: step: 104/466, loss: 0.01988566666841507
2023-01-22 12:43:26.974830: step: 106/466, loss: 0.055231306701898575
2023-01-22 12:43:27.631834: step: 108/466, loss: 0.013693037442862988
2023-01-22 12:43:28.306670: step: 110/466, loss: 0.016922691836953163
2023-01-22 12:43:28.935251: step: 112/466, loss: 0.02427794225513935
2023-01-22 12:43:29.557866: step: 114/466, loss: 1.463797688484192
2023-01-22 12:43:30.164604: step: 116/466, loss: 0.011846937239170074
2023-01-22 12:43:30.817816: step: 118/466, loss: 0.03153500333428383
2023-01-22 12:43:31.474241: step: 120/466, loss: 0.008501111529767513
2023-01-22 12:43:32.098192: step: 122/466, loss: 0.0016625624848529696
2023-01-22 12:43:32.720330: step: 124/466, loss: 1.526236653327942
2023-01-22 12:43:33.347467: step: 126/466, loss: 0.01810932531952858
2023-01-22 12:43:34.063497: step: 128/466, loss: 0.07274865359067917
2023-01-22 12:43:34.708777: step: 130/466, loss: 0.021032212302088737
2023-01-22 12:43:35.442810: step: 132/466, loss: 0.03922904282808304
2023-01-22 12:43:36.044282: step: 134/466, loss: 0.06585580110549927
2023-01-22 12:43:36.693463: step: 136/466, loss: 0.00184637529309839
2023-01-22 12:43:37.280542: step: 138/466, loss: 0.09909527748823166
2023-01-22 12:43:37.922640: step: 140/466, loss: 0.03606913983821869
2023-01-22 12:43:38.572604: step: 142/466, loss: 0.035890597850084305
2023-01-22 12:43:39.182603: step: 144/466, loss: 0.0817774310708046
2023-01-22 12:43:39.827362: step: 146/466, loss: 0.04412094131112099
2023-01-22 12:43:40.453448: step: 148/466, loss: 0.01928979717195034
2023-01-22 12:43:41.002313: step: 150/466, loss: 0.004080347716808319
2023-01-22 12:43:41.616269: step: 152/466, loss: 0.03950808197259903
2023-01-22 12:43:42.241187: step: 154/466, loss: 0.03697212040424347
2023-01-22 12:43:42.811978: step: 156/466, loss: 0.07765532284975052
2023-01-22 12:43:43.434896: step: 158/466, loss: 0.2336684912443161
2023-01-22 12:43:44.052772: step: 160/466, loss: 0.2615325152873993
2023-01-22 12:43:44.668143: step: 162/466, loss: 0.009940821677446365
2023-01-22 12:43:45.312435: step: 164/466, loss: 0.03197099268436432
2023-01-22 12:43:45.925977: step: 166/466, loss: 0.05685582011938095
2023-01-22 12:43:46.533189: step: 168/466, loss: 0.0019060398917645216
2023-01-22 12:43:47.059860: step: 170/466, loss: 0.003438710467889905
2023-01-22 12:43:47.703563: step: 172/466, loss: 0.04050370305776596
2023-01-22 12:43:48.282995: step: 174/466, loss: 0.015799373388290405
2023-01-22 12:43:48.930652: step: 176/466, loss: 0.012722530402243137
2023-01-22 12:43:49.568094: step: 178/466, loss: 0.06495097279548645
2023-01-22 12:43:50.179606: step: 180/466, loss: 0.012860220856964588
2023-01-22 12:43:50.790402: step: 182/466, loss: 0.09234242886304855
2023-01-22 12:43:51.513672: step: 184/466, loss: 0.028211582452058792
2023-01-22 12:43:52.127198: step: 186/466, loss: 0.24828922748565674
2023-01-22 12:43:52.807273: step: 188/466, loss: 0.011880680918693542
2023-01-22 12:43:53.361836: step: 190/466, loss: 0.18462541699409485
2023-01-22 12:43:54.094455: step: 192/466, loss: 0.019765596836805344
2023-01-22 12:43:54.745984: step: 194/466, loss: 0.027054965496063232
2023-01-22 12:43:55.368324: step: 196/466, loss: 0.013658122159540653
2023-01-22 12:43:56.006715: step: 198/466, loss: 0.12429645657539368
2023-01-22 12:43:56.636810: step: 200/466, loss: 0.03704677149653435
2023-01-22 12:43:57.216268: step: 202/466, loss: 0.004386530257761478
2023-01-22 12:43:57.819842: step: 204/466, loss: 0.0045953174121677876
2023-01-22 12:43:58.452231: step: 206/466, loss: 0.06506485491991043
2023-01-22 12:43:59.157873: step: 208/466, loss: 0.027044648304581642
2023-01-22 12:43:59.796560: step: 210/466, loss: 0.007475194986909628
2023-01-22 12:44:00.451220: step: 212/466, loss: 0.03475631773471832
2023-01-22 12:44:01.063319: step: 214/466, loss: 0.037433333694934845
2023-01-22 12:44:01.699196: step: 216/466, loss: 0.09614378213882446
2023-01-22 12:44:02.348782: step: 218/466, loss: 0.014291762374341488
2023-01-22 12:44:02.949104: step: 220/466, loss: 0.0066920192912220955
2023-01-22 12:44:03.603105: step: 222/466, loss: 0.0016438337042927742
2023-01-22 12:44:04.257754: step: 224/466, loss: 0.01268971711397171
2023-01-22 12:44:04.805183: step: 226/466, loss: 0.019960829988121986
2023-01-22 12:44:05.373624: step: 228/466, loss: 0.02156595140695572
2023-01-22 12:44:05.984315: step: 230/466, loss: 0.041490305215120316
2023-01-22 12:44:06.624901: step: 232/466, loss: 0.007419609930366278
2023-01-22 12:44:07.297985: step: 234/466, loss: 0.06077762693166733
2023-01-22 12:44:07.941627: step: 236/466, loss: 0.04927678778767586
2023-01-22 12:44:08.574003: step: 238/466, loss: 0.007565382402390242
2023-01-22 12:44:09.131847: step: 240/466, loss: 0.00638133380562067
2023-01-22 12:44:09.728015: step: 242/466, loss: 0.05720380321145058
2023-01-22 12:44:10.316809: step: 244/466, loss: 0.027775298804044724
2023-01-22 12:44:10.920019: step: 246/466, loss: 0.08375570178031921
2023-01-22 12:44:11.542081: step: 248/466, loss: 0.014697118662297726
2023-01-22 12:44:12.270644: step: 250/466, loss: 0.08780642598867416
2023-01-22 12:44:12.941836: step: 252/466, loss: 0.016955697908997536
2023-01-22 12:44:13.541638: step: 254/466, loss: 0.05962974950671196
2023-01-22 12:44:14.174615: step: 256/466, loss: 0.015877990052103996
2023-01-22 12:44:14.779371: step: 258/466, loss: 0.05827377364039421
2023-01-22 12:44:15.426225: step: 260/466, loss: 0.03235466778278351
2023-01-22 12:44:16.041671: step: 262/466, loss: 0.011585214175283909
2023-01-22 12:44:16.709310: step: 264/466, loss: 0.058018896728754044
2023-01-22 12:44:17.308677: step: 266/466, loss: 0.06219848245382309
2023-01-22 12:44:17.917843: step: 268/466, loss: 0.07465940713882446
2023-01-22 12:44:18.657618: step: 270/466, loss: 0.01665102317929268
2023-01-22 12:44:19.475355: step: 272/466, loss: 0.005275152623653412
2023-01-22 12:44:20.146853: step: 274/466, loss: 0.05236566439270973
2023-01-22 12:44:20.765011: step: 276/466, loss: 0.005467272363603115
2023-01-22 12:44:21.322051: step: 278/466, loss: 0.03000018000602722
2023-01-22 12:44:21.858172: step: 280/466, loss: 1.1425138711929321
2023-01-22 12:44:22.476081: step: 282/466, loss: 0.039501119405031204
2023-01-22 12:44:23.055227: step: 284/466, loss: 0.44520309567451477
2023-01-22 12:44:23.661056: step: 286/466, loss: 0.000496347201988101
2023-01-22 12:44:24.262717: step: 288/466, loss: 0.0023207715712487698
2023-01-22 12:44:24.847510: step: 290/466, loss: 0.02163492515683174
2023-01-22 12:44:25.526250: step: 292/466, loss: 0.0733761414885521
2023-01-22 12:44:26.183720: step: 294/466, loss: 0.013693487271666527
2023-01-22 12:44:26.785783: step: 296/466, loss: 0.025295032188296318
2023-01-22 12:44:27.442299: step: 298/466, loss: 0.030743736773729324
2023-01-22 12:44:28.052901: step: 300/466, loss: 0.01697983592748642
2023-01-22 12:44:28.669115: step: 302/466, loss: 0.006202060729265213
2023-01-22 12:44:29.291665: step: 304/466, loss: 0.002101277466863394
2023-01-22 12:44:29.929257: step: 306/466, loss: 0.036038950085639954
2023-01-22 12:44:30.552256: step: 308/466, loss: 0.010649413801729679
2023-01-22 12:44:31.156679: step: 310/466, loss: 0.0036623121704906225
2023-01-22 12:44:31.768612: step: 312/466, loss: 0.006318286992609501
2023-01-22 12:44:32.390238: step: 314/466, loss: 0.019612329080700874
2023-01-22 12:44:32.968433: step: 316/466, loss: 0.08130209147930145
2023-01-22 12:44:33.605924: step: 318/466, loss: 0.6466153860092163
2023-01-22 12:44:34.228302: step: 320/466, loss: 0.017690975219011307
2023-01-22 12:44:34.878698: step: 322/466, loss: 0.0048448131419718266
2023-01-22 12:44:35.567930: step: 324/466, loss: 0.8842586278915405
2023-01-22 12:44:36.217141: step: 326/466, loss: 0.020062141120433807
2023-01-22 12:44:36.835481: step: 328/466, loss: 0.011810514144599438
2023-01-22 12:44:37.445406: step: 330/466, loss: 0.04219945892691612
2023-01-22 12:44:37.998587: step: 332/466, loss: 0.02550136111676693
2023-01-22 12:44:38.595991: step: 334/466, loss: 0.01426367275416851
2023-01-22 12:44:39.147496: step: 336/466, loss: 0.03547900542616844
2023-01-22 12:44:39.763153: step: 338/466, loss: 0.0798686221241951
2023-01-22 12:44:40.475452: step: 340/466, loss: 0.06922107934951782
2023-01-22 12:44:41.102213: step: 342/466, loss: 0.08623357862234116
2023-01-22 12:44:41.638543: step: 344/466, loss: 0.0029127050656825304
2023-01-22 12:44:42.309197: step: 346/466, loss: 0.0047578406520187855
2023-01-22 12:44:42.940118: step: 348/466, loss: 0.030754726380109787
2023-01-22 12:44:43.508674: step: 350/466, loss: 0.09280386567115784
2023-01-22 12:44:44.111113: step: 352/466, loss: 0.0332859605550766
2023-01-22 12:44:44.718673: step: 354/466, loss: 0.11619105935096741
2023-01-22 12:44:45.257880: step: 356/466, loss: 0.024161159992218018
2023-01-22 12:44:45.860744: step: 358/466, loss: 0.008979431353509426
2023-01-22 12:44:46.485912: step: 360/466, loss: 0.06891241669654846
2023-01-22 12:44:47.158395: step: 362/466, loss: 0.022034132853150368
2023-01-22 12:44:47.726989: step: 364/466, loss: 0.08202984184026718
2023-01-22 12:44:48.379064: step: 366/466, loss: 0.039208486676216125
2023-01-22 12:44:48.968686: step: 368/466, loss: 0.010029909200966358
2023-01-22 12:44:49.606210: step: 370/466, loss: 0.044931963086128235
2023-01-22 12:44:50.183952: step: 372/466, loss: 0.017695071175694466
2023-01-22 12:44:50.829377: step: 374/466, loss: 0.07123210281133652
2023-01-22 12:44:51.492296: step: 376/466, loss: 0.010910790413618088
2023-01-22 12:44:52.115885: step: 378/466, loss: 0.07261643558740616
2023-01-22 12:44:52.741975: step: 380/466, loss: 0.03362992778420448
2023-01-22 12:44:53.455684: step: 382/466, loss: 0.030723733827471733
2023-01-22 12:44:54.039838: step: 384/466, loss: 0.0033833698835223913
2023-01-22 12:44:54.643343: step: 386/466, loss: 0.07037527114152908
2023-01-22 12:44:55.271223: step: 388/466, loss: 0.04732706397771835
2023-01-22 12:44:55.924522: step: 390/466, loss: 0.03024684637784958
2023-01-22 12:44:56.630023: step: 392/466, loss: 0.010613604448735714
2023-01-22 12:44:57.320144: step: 394/466, loss: 0.024162225425243378
2023-01-22 12:44:57.906485: step: 396/466, loss: 0.009866451844573021
2023-01-22 12:44:58.518508: step: 398/466, loss: 0.04842867702245712
2023-01-22 12:44:59.152144: step: 400/466, loss: 0.04632077366113663
2023-01-22 12:44:59.737882: step: 402/466, loss: 0.08502992242574692
2023-01-22 12:45:00.335773: step: 404/466, loss: 0.00219887588173151
2023-01-22 12:45:01.013493: step: 406/466, loss: 0.05578460171818733
2023-01-22 12:45:01.686364: step: 408/466, loss: 0.02796776592731476
2023-01-22 12:45:02.344028: step: 410/466, loss: 0.04815340414643288
2023-01-22 12:45:02.932126: step: 412/466, loss: 0.009533676318824291
2023-01-22 12:45:03.616976: step: 414/466, loss: 0.00020531343761831522
2023-01-22 12:45:04.238296: step: 416/466, loss: 0.03974773734807968
2023-01-22 12:45:04.865206: step: 418/466, loss: 0.0235374066978693
2023-01-22 12:45:05.474924: step: 420/466, loss: 0.017376694828271866
2023-01-22 12:45:06.040155: step: 422/466, loss: 0.01427893154323101
2023-01-22 12:45:06.646767: step: 424/466, loss: 0.002878089901059866
2023-01-22 12:45:07.280228: step: 426/466, loss: 0.008732099086046219
2023-01-22 12:45:07.904782: step: 428/466, loss: 0.05201972275972366
2023-01-22 12:45:08.513919: step: 430/466, loss: 0.03940167650580406
2023-01-22 12:45:09.179011: step: 432/466, loss: 0.7123115062713623
2023-01-22 12:45:09.776998: step: 434/466, loss: 0.014425323344767094
2023-01-22 12:45:10.393715: step: 436/466, loss: 0.020876772701740265
2023-01-22 12:45:11.044713: step: 438/466, loss: 0.01232703123241663
2023-01-22 12:45:11.622115: step: 440/466, loss: 0.013305318541824818
2023-01-22 12:45:12.230098: step: 442/466, loss: 0.00580544862896204
2023-01-22 12:45:12.833414: step: 444/466, loss: 0.024085568264126778
2023-01-22 12:45:13.523088: step: 446/466, loss: 0.0445990227162838
2023-01-22 12:45:14.123738: step: 448/466, loss: 0.00036237595486454666
2023-01-22 12:45:14.724013: step: 450/466, loss: 0.15216988325119019
2023-01-22 12:45:15.411271: step: 452/466, loss: 0.02704990655183792
2023-01-22 12:45:15.986066: step: 454/466, loss: 0.012838363647460938
2023-01-22 12:45:16.656333: step: 456/466, loss: 0.06284131854772568
2023-01-22 12:45:17.264207: step: 458/466, loss: 0.10360924154520035
2023-01-22 12:45:17.860925: step: 460/466, loss: 0.00795061606913805
2023-01-22 12:45:18.464596: step: 462/466, loss: 0.030827568843960762
2023-01-22 12:45:19.109187: step: 464/466, loss: 0.0068170600570738316
2023-01-22 12:45:19.734869: step: 466/466, loss: 0.15848875045776367
2023-01-22 12:45:20.364599: step: 468/466, loss: 0.004579485859721899
2023-01-22 12:45:21.005926: step: 470/466, loss: 0.006150723434984684
2023-01-22 12:45:21.606465: step: 472/466, loss: 0.031934954226017
2023-01-22 12:45:22.245578: step: 474/466, loss: 0.014982946217060089
2023-01-22 12:45:22.892605: step: 476/466, loss: 0.041599661111831665
2023-01-22 12:45:23.540947: step: 478/466, loss: 0.03959587588906288
2023-01-22 12:45:24.201189: step: 480/466, loss: 0.001282591954804957
2023-01-22 12:45:24.778750: step: 482/466, loss: 0.2651715576648712
2023-01-22 12:45:25.432657: step: 484/466, loss: 0.017963455989956856
2023-01-22 12:45:26.091292: step: 486/466, loss: 0.08299870043992996
2023-01-22 12:45:26.693104: step: 488/466, loss: 0.010541216470301151
2023-01-22 12:45:27.290227: step: 490/466, loss: 0.0055192383006215096
2023-01-22 12:45:27.967392: step: 492/466, loss: 0.009777909144759178
2023-01-22 12:45:28.565563: step: 494/466, loss: 0.11229853332042694
2023-01-22 12:45:29.062981: step: 496/466, loss: 0.001413665246218443
2023-01-22 12:45:29.716093: step: 498/466, loss: 0.12335145473480225
2023-01-22 12:45:30.349439: step: 500/466, loss: 0.030117841437458992
2023-01-22 12:45:30.937836: step: 502/466, loss: 0.10821045935153961
2023-01-22 12:45:31.549191: step: 504/466, loss: 0.016559399664402008
2023-01-22 12:45:32.114986: step: 506/466, loss: 0.0051531922072172165
2023-01-22 12:45:32.716514: step: 508/466, loss: 0.05999673530459404
2023-01-22 12:45:33.337780: step: 510/466, loss: 0.08033227920532227
2023-01-22 12:45:33.967797: step: 512/466, loss: 0.05756360664963722
2023-01-22 12:45:34.570276: step: 514/466, loss: 0.1250261515378952
2023-01-22 12:45:35.211337: step: 516/466, loss: 0.024026280269026756
2023-01-22 12:45:35.807235: step: 518/466, loss: 0.02750120684504509
2023-01-22 12:45:36.405983: step: 520/466, loss: 0.05190858244895935
2023-01-22 12:45:37.038242: step: 522/466, loss: 0.08374769240617752
2023-01-22 12:45:37.681104: step: 524/466, loss: 0.19721168279647827
2023-01-22 12:45:38.388812: step: 526/466, loss: 0.14855492115020752
2023-01-22 12:45:38.956904: step: 528/466, loss: 0.029247550293803215
2023-01-22 12:45:39.575639: step: 530/466, loss: 0.028942137956619263
2023-01-22 12:45:40.168226: step: 532/466, loss: 0.1819128692150116
2023-01-22 12:45:40.806044: step: 534/466, loss: 0.006035921163856983
2023-01-22 12:45:41.408467: step: 536/466, loss: 0.16624990105628967
2023-01-22 12:45:42.082996: step: 538/466, loss: 0.029659925028681755
2023-01-22 12:45:42.714841: step: 540/466, loss: 0.0641593262553215
2023-01-22 12:45:43.376992: step: 542/466, loss: 0.0009827445028349757
2023-01-22 12:45:44.020546: step: 544/466, loss: 0.17054708302021027
2023-01-22 12:45:44.600546: step: 546/466, loss: 0.010677242651581764
2023-01-22 12:45:45.208255: step: 548/466, loss: 0.0017253371188417077
2023-01-22 12:45:45.860922: step: 550/466, loss: 0.5802269577980042
2023-01-22 12:45:46.491403: step: 552/466, loss: 0.009611350484192371
2023-01-22 12:45:47.050383: step: 554/466, loss: 0.01147443987429142
2023-01-22 12:45:47.713115: step: 556/466, loss: 0.08705990016460419
2023-01-22 12:45:48.364751: step: 558/466, loss: 1.0124412775039673
2023-01-22 12:45:48.958720: step: 560/466, loss: 0.022383833304047585
2023-01-22 12:45:49.533656: step: 562/466, loss: 0.007344966288655996
2023-01-22 12:45:50.079148: step: 564/466, loss: 0.03636467829346657
2023-01-22 12:45:50.718458: step: 566/466, loss: 0.009142805822193623
2023-01-22 12:45:51.307403: step: 568/466, loss: 0.017209192737936974
2023-01-22 12:45:51.926385: step: 570/466, loss: 0.008467994630336761
2023-01-22 12:45:52.585005: step: 572/466, loss: 0.018438834697008133
2023-01-22 12:45:53.191852: step: 574/466, loss: 0.31713053584098816
2023-01-22 12:45:53.805350: step: 576/466, loss: 0.024290455505251884
2023-01-22 12:45:54.473208: step: 578/466, loss: 0.01887284778058529
2023-01-22 12:45:55.120613: step: 580/466, loss: 0.5228666067123413
2023-01-22 12:45:55.692703: step: 582/466, loss: 0.003434462007135153
2023-01-22 12:45:56.348988: step: 584/466, loss: 0.08324345201253891
2023-01-22 12:45:56.942059: step: 586/466, loss: 0.031138503924012184
2023-01-22 12:45:57.518980: step: 588/466, loss: 0.004604414105415344
2023-01-22 12:45:58.170467: step: 590/466, loss: 0.07915446907281876
2023-01-22 12:45:58.761347: step: 592/466, loss: 0.012631416320800781
2023-01-22 12:45:59.460824: step: 594/466, loss: 0.01816081814467907
2023-01-22 12:46:00.044232: step: 596/466, loss: 0.05987480282783508
2023-01-22 12:46:00.585637: step: 598/466, loss: 0.061415087431669235
2023-01-22 12:46:01.137098: step: 600/466, loss: 0.013928325846791267
2023-01-22 12:46:01.706135: step: 602/466, loss: 0.03612973541021347
2023-01-22 12:46:02.323124: step: 604/466, loss: 0.003916529472917318
2023-01-22 12:46:02.973058: step: 606/466, loss: 0.39525341987609863
2023-01-22 12:46:03.588866: step: 608/466, loss: 0.002376685617491603
2023-01-22 12:46:04.156591: step: 610/466, loss: 0.07487525790929794
2023-01-22 12:46:04.848981: step: 612/466, loss: 0.037955593317747116
2023-01-22 12:46:05.501492: step: 614/466, loss: 0.019716570153832436
2023-01-22 12:46:06.128034: step: 616/466, loss: 0.020672595128417015
2023-01-22 12:46:06.737466: step: 618/466, loss: 0.01101340726017952
2023-01-22 12:46:07.385630: step: 620/466, loss: 0.03404736891388893
2023-01-22 12:46:08.062160: step: 622/466, loss: 0.005758011247962713
2023-01-22 12:46:08.593368: step: 624/466, loss: 0.0057716164737939835
2023-01-22 12:46:09.267292: step: 626/466, loss: 0.037827637046575546
2023-01-22 12:46:09.883432: step: 628/466, loss: 0.07281064242124557
2023-01-22 12:46:10.556870: step: 630/466, loss: 0.024857493117451668
2023-01-22 12:46:11.139361: step: 632/466, loss: 0.004130253568291664
2023-01-22 12:46:11.747076: step: 634/466, loss: 0.013181922025978565
2023-01-22 12:46:12.357628: step: 636/466, loss: 0.003704882925376296
2023-01-22 12:46:12.982370: step: 638/466, loss: 0.033294033259153366
2023-01-22 12:46:13.578601: step: 640/466, loss: 0.787654459476471
2023-01-22 12:46:14.179815: step: 642/466, loss: 0.07885098457336426
2023-01-22 12:46:14.817638: step: 644/466, loss: 0.0641399398446083
2023-01-22 12:46:15.395916: step: 646/466, loss: 0.009171229787170887
2023-01-22 12:46:16.050491: step: 648/466, loss: 0.03740779682993889
2023-01-22 12:46:16.781233: step: 650/466, loss: 0.04201372340321541
2023-01-22 12:46:17.382268: step: 652/466, loss: 0.04712774604558945
2023-01-22 12:46:17.950970: step: 654/466, loss: 0.08313298225402832
2023-01-22 12:46:18.518121: step: 656/466, loss: 0.028765540570020676
2023-01-22 12:46:19.083448: step: 658/466, loss: 0.03196149691939354
2023-01-22 12:46:19.693184: step: 660/466, loss: 0.020120587199926376
2023-01-22 12:46:20.310218: step: 662/466, loss: 0.02490849420428276
2023-01-22 12:46:20.909117: step: 664/466, loss: 0.26444730162620544
2023-01-22 12:46:21.494408: step: 666/466, loss: 0.02657054178416729
2023-01-22 12:46:22.046605: step: 668/466, loss: 0.006359726656228304
2023-01-22 12:46:22.682609: step: 670/466, loss: 0.06964357197284698
2023-01-22 12:46:23.334022: step: 672/466, loss: 0.003294349182397127
2023-01-22 12:46:23.940521: step: 674/466, loss: 0.05599857494235039
2023-01-22 12:46:24.635535: step: 676/466, loss: 0.00530225457623601
2023-01-22 12:46:25.242279: step: 678/466, loss: 0.05987514182925224
2023-01-22 12:46:25.821470: step: 680/466, loss: 0.01196238026022911
2023-01-22 12:46:26.418491: step: 682/466, loss: 0.09103018790483475
2023-01-22 12:46:27.001084: step: 684/466, loss: 0.03690921887755394
2023-01-22 12:46:27.622231: step: 686/466, loss: 0.04676826298236847
2023-01-22 12:46:28.188274: step: 688/466, loss: 0.013362089172005653
2023-01-22 12:46:28.821076: step: 690/466, loss: 0.09177672117948532
2023-01-22 12:46:29.459566: step: 692/466, loss: 0.013591652736067772
2023-01-22 12:46:30.068098: step: 694/466, loss: 0.0038507573772221804
2023-01-22 12:46:30.655789: step: 696/466, loss: 0.011765643954277039
2023-01-22 12:46:31.240062: step: 698/466, loss: 0.16771037876605988
2023-01-22 12:46:31.887189: step: 700/466, loss: 0.05011175945401192
2023-01-22 12:46:32.469576: step: 702/466, loss: 0.036982789635658264
2023-01-22 12:46:33.115286: step: 704/466, loss: 0.6828376650810242
2023-01-22 12:46:33.752803: step: 706/466, loss: 0.0290224552154541
2023-01-22 12:46:34.344458: step: 708/466, loss: 0.02623136155307293
2023-01-22 12:46:34.953007: step: 710/466, loss: 0.3259034752845764
2023-01-22 12:46:35.558326: step: 712/466, loss: 0.005587138235569
2023-01-22 12:46:36.192411: step: 714/466, loss: 0.05836469307541847
2023-01-22 12:46:36.795377: step: 716/466, loss: 0.003592146560549736
2023-01-22 12:46:37.433278: step: 718/466, loss: 0.011633865535259247
2023-01-22 12:46:38.016909: step: 720/466, loss: 0.02132820524275303
2023-01-22 12:46:38.623097: step: 722/466, loss: 0.0905800461769104
2023-01-22 12:46:39.255126: step: 724/466, loss: 0.40397319197654724
2023-01-22 12:46:39.907544: step: 726/466, loss: 0.5215640664100647
2023-01-22 12:46:40.544758: step: 728/466, loss: 0.09964409470558167
2023-01-22 12:46:41.146807: step: 730/466, loss: 0.022946283221244812
2023-01-22 12:46:41.758104: step: 732/466, loss: 0.34767013788223267
2023-01-22 12:46:42.334554: step: 734/466, loss: 0.0024455466773360968
2023-01-22 12:46:42.943589: step: 736/466, loss: 0.06245845928788185
2023-01-22 12:46:43.563509: step: 738/466, loss: 0.3352563679218292
2023-01-22 12:46:44.168156: step: 740/466, loss: 0.4687623977661133
2023-01-22 12:46:44.781984: step: 742/466, loss: 0.014673358760774136
2023-01-22 12:46:45.326676: step: 744/466, loss: 0.07676398754119873
2023-01-22 12:46:45.919526: step: 746/466, loss: 0.022580327466130257
2023-01-22 12:46:46.603497: step: 748/466, loss: 0.05122647061944008
2023-01-22 12:46:47.244259: step: 750/466, loss: 0.07465817034244537
2023-01-22 12:46:47.901025: step: 752/466, loss: 0.07189252227544785
2023-01-22 12:46:48.611683: step: 754/466, loss: 0.0055083101615309715
2023-01-22 12:46:49.240911: step: 756/466, loss: 0.03365939110517502
2023-01-22 12:46:49.785858: step: 758/466, loss: 0.07387290894985199
2023-01-22 12:46:50.407992: step: 760/466, loss: 0.029260363429784775
2023-01-22 12:46:51.017722: step: 762/466, loss: 0.014879300259053707
2023-01-22 12:46:51.633427: step: 764/466, loss: 0.05147287994623184
2023-01-22 12:46:52.286205: step: 766/466, loss: 0.025484487414360046
2023-01-22 12:46:52.871721: step: 768/466, loss: 0.06355484575033188
2023-01-22 12:46:53.434093: step: 770/466, loss: 0.007383082527667284
2023-01-22 12:46:54.065615: step: 772/466, loss: 0.0148489223793149
2023-01-22 12:46:54.751754: step: 774/466, loss: 0.18538230657577515
2023-01-22 12:46:55.389335: step: 776/466, loss: 0.03870323672890663
2023-01-22 12:46:56.046745: step: 778/466, loss: 0.0025325315073132515
2023-01-22 12:46:56.689874: step: 780/466, loss: 0.1094198226928711
2023-01-22 12:46:57.310380: step: 782/466, loss: 0.03620237484574318
2023-01-22 12:46:58.012848: step: 784/466, loss: 0.03306031972169876
2023-01-22 12:46:58.681332: step: 786/466, loss: 0.12057071924209595
2023-01-22 12:46:59.358202: step: 788/466, loss: 0.061688702553510666
2023-01-22 12:47:00.007110: step: 790/466, loss: 0.0335828959941864
2023-01-22 12:47:00.664249: step: 792/466, loss: 0.023003384470939636
2023-01-22 12:47:01.341012: step: 794/466, loss: 0.010956516489386559
2023-01-22 12:47:02.034222: step: 796/466, loss: 0.8769637942314148
2023-01-22 12:47:02.679556: step: 798/466, loss: 0.025993596762418747
2023-01-22 12:47:03.306331: step: 800/466, loss: 0.04359062388539314
2023-01-22 12:47:03.897991: step: 802/466, loss: 0.053605817258358
2023-01-22 12:47:04.536529: step: 804/466, loss: 0.06414834409952164
2023-01-22 12:47:05.153066: step: 806/466, loss: 0.02431272529065609
2023-01-22 12:47:05.781646: step: 808/466, loss: 0.008475328795611858
2023-01-22 12:47:06.421912: step: 810/466, loss: 0.012665689922869205
2023-01-22 12:47:07.013229: step: 812/466, loss: 0.027181055396795273
2023-01-22 12:47:07.632645: step: 814/466, loss: 0.002804344752803445
2023-01-22 12:47:08.313763: step: 816/466, loss: 0.026928989216685295
2023-01-22 12:47:08.932701: step: 818/466, loss: 0.046765200793743134
2023-01-22 12:47:09.604247: step: 820/466, loss: 0.06903944909572601
2023-01-22 12:47:10.220300: step: 822/466, loss: 0.01643381454050541
2023-01-22 12:47:10.870347: step: 824/466, loss: 0.17748354375362396
2023-01-22 12:47:11.476996: step: 826/466, loss: 0.07518330216407776
2023-01-22 12:47:12.136849: step: 828/466, loss: 0.044734109193086624
2023-01-22 12:47:12.767696: step: 830/466, loss: 0.08786842226982117
2023-01-22 12:47:13.461210: step: 832/466, loss: 0.014323107898235321
2023-01-22 12:47:14.083086: step: 834/466, loss: 0.006167815998196602
2023-01-22 12:47:14.713383: step: 836/466, loss: 0.04702593386173248
2023-01-22 12:47:15.300686: step: 838/466, loss: 0.028971809893846512
2023-01-22 12:47:15.901605: step: 840/466, loss: 0.21031683683395386
2023-01-22 12:47:16.492022: step: 842/466, loss: 0.006460993085056543
2023-01-22 12:47:17.204904: step: 844/466, loss: 0.019567999988794327
2023-01-22 12:47:17.792648: step: 846/466, loss: 0.8865355253219604
2023-01-22 12:47:18.382109: step: 848/466, loss: 0.011671203188598156
2023-01-22 12:47:19.019983: step: 850/466, loss: 0.0006757083465345204
2023-01-22 12:47:19.730567: step: 852/466, loss: 0.04617739096283913
2023-01-22 12:47:20.374446: step: 854/466, loss: 0.021671177819371223
2023-01-22 12:47:20.997776: step: 856/466, loss: 0.057586777955293655
2023-01-22 12:47:21.609119: step: 858/466, loss: 0.045462507754564285
2023-01-22 12:47:22.243573: step: 860/466, loss: 0.3865273594856262
2023-01-22 12:47:22.882373: step: 862/466, loss: 0.011022298596799374
2023-01-22 12:47:23.463904: step: 864/466, loss: 0.0045396713539958
2023-01-22 12:47:24.100670: step: 866/466, loss: 0.05541210621595383
2023-01-22 12:47:24.642223: step: 868/466, loss: 0.025362443178892136
2023-01-22 12:47:25.186387: step: 870/466, loss: 0.010455988347530365
2023-01-22 12:47:25.833582: step: 872/466, loss: 0.041592665016651154
2023-01-22 12:47:26.457268: step: 874/466, loss: 0.01976536586880684
2023-01-22 12:47:27.031243: step: 876/466, loss: 0.03550330549478531
2023-01-22 12:47:27.644518: step: 878/466, loss: 0.0005371432052925229
2023-01-22 12:47:28.332270: step: 880/466, loss: 0.45359212160110474
2023-01-22 12:47:28.940976: step: 882/466, loss: 0.031113147735595703
2023-01-22 12:47:29.548022: step: 884/466, loss: 0.04073180630803108
2023-01-22 12:47:30.162563: step: 886/466, loss: 0.07079195231199265
2023-01-22 12:47:30.712468: step: 888/466, loss: 0.01618576981127262
2023-01-22 12:47:31.302134: step: 890/466, loss: 2.57959246635437
2023-01-22 12:47:31.884107: step: 892/466, loss: 0.009884090162813663
2023-01-22 12:47:32.456058: step: 894/466, loss: 0.03281768411397934
2023-01-22 12:47:33.087001: step: 896/466, loss: 0.060086511075496674
2023-01-22 12:47:33.717314: step: 898/466, loss: 0.020023701712489128
2023-01-22 12:47:34.397475: step: 900/466, loss: 0.04844291880726814
2023-01-22 12:47:35.066789: step: 902/466, loss: 0.0430406853556633
2023-01-22 12:47:35.644358: step: 904/466, loss: 0.014855911023914814
2023-01-22 12:47:36.243102: step: 906/466, loss: 0.041675664484500885
2023-01-22 12:47:36.815870: step: 908/466, loss: 0.042056307196617126
2023-01-22 12:47:37.607597: step: 910/466, loss: 0.1248590350151062
2023-01-22 12:47:38.268922: step: 912/466, loss: 0.35482367873191833
2023-01-22 12:47:38.863166: step: 914/466, loss: 0.00630500353872776
2023-01-22 12:47:39.453774: step: 916/466, loss: 0.030308715999126434
2023-01-22 12:47:40.061902: step: 918/466, loss: 0.023932820186018944
2023-01-22 12:47:40.714145: step: 920/466, loss: 0.02819758653640747
2023-01-22 12:47:41.326271: step: 922/466, loss: 0.04101166874170303
2023-01-22 12:47:41.956810: step: 924/466, loss: 0.00014712440315634012
2023-01-22 12:47:42.540403: step: 926/466, loss: 0.38159114122390747
2023-01-22 12:47:43.108904: step: 928/466, loss: 0.007751580327749252
2023-01-22 12:47:43.748761: step: 930/466, loss: 0.02519507147371769
2023-01-22 12:47:44.359048: step: 932/466, loss: 0.06680907309055328
==================================================
Loss: 0.089
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3219419054677207, 'r': 0.3372142918751078, 'f1': 0.32940117111803857}, 'combined': 0.24271665240276524, 'epoch': 25}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.31009606259861755, 'r': 0.28826619537597115, 'f1': 0.29878292280315816}, 'combined': 0.1870883722225383, 'epoch': 25}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30315666966202387, 'r': 0.34917665746650567, 'f1': 0.32454338357116136}, 'combined': 0.23913722999980308, 'epoch': 25}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3248477008162509, 'r': 0.3110680600776554, 'f1': 0.3178085851231371}, 'combined': 0.19695179923123987, 'epoch': 25}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28042652317425387, 'r': 0.35173042090736584, 'f1': 0.31205712427303334}, 'combined': 0.22993682841170876, 'epoch': 25}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3154284160706615, 'r': 0.2997425545119939, 'f1': 0.3073855032825826}, 'combined': 0.2039091952468617, 'epoch': 25}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.26453488372093026, 'r': 0.325, 'f1': 0.29166666666666674}, 'combined': 0.19444444444444448, 'epoch': 25}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3203125, 'r': 0.44565217391304346, 'f1': 0.3727272727272727}, 'combined': 0.18636363636363634, 'epoch': 25}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2692307692307692, 'r': 0.2413793103448276, 'f1': 0.2545454545454545}, 'combined': 0.16969696969696968, 'epoch': 25}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2985390909090909, 'r': 0.354054899085734, 'f1': 0.32393564551767673}, 'combined': 0.23868942301302495, 'epoch': 14}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3238994243213351, 'r': 0.32273011232017507, 'f1': 0.32331371107663104}, 'combined': 0.2003634265827009, 'epoch': 14}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 14}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:50:21.537924: step: 2/466, loss: 0.007889525964856148
2023-01-22 12:50:22.114101: step: 4/466, loss: 0.10208336263895035
2023-01-22 12:50:22.707790: step: 6/466, loss: 0.05998808890581131
2023-01-22 12:50:23.322641: step: 8/466, loss: 0.03341453894972801
2023-01-22 12:50:23.913651: step: 10/466, loss: 0.042030151933431625
2023-01-22 12:50:24.570446: step: 12/466, loss: 0.03125926852226257
2023-01-22 12:50:25.166472: step: 14/466, loss: 0.035212282091379166
2023-01-22 12:50:25.763651: step: 16/466, loss: 0.021042432636022568
2023-01-22 12:50:26.477533: step: 18/466, loss: 0.03849077224731445
2023-01-22 12:50:27.115943: step: 20/466, loss: 0.058912985026836395
2023-01-22 12:50:27.673854: step: 22/466, loss: 0.05570070073008537
2023-01-22 12:50:28.280679: step: 24/466, loss: 0.06585846096277237
2023-01-22 12:50:28.960565: step: 26/466, loss: 0.011703751049935818
2023-01-22 12:50:29.559292: step: 28/466, loss: 0.011850082315504551
2023-01-22 12:50:30.211774: step: 30/466, loss: 0.027266433462500572
2023-01-22 12:50:30.832178: step: 32/466, loss: 0.0038200421258807182
2023-01-22 12:50:31.471110: step: 34/466, loss: 0.18678438663482666
2023-01-22 12:50:32.108047: step: 36/466, loss: 0.04685428738594055
2023-01-22 12:50:32.893873: step: 38/466, loss: 1.2945747375488281
2023-01-22 12:50:33.506647: step: 40/466, loss: 0.005321810953319073
2023-01-22 12:50:34.124847: step: 42/466, loss: 0.0058112493716180325
2023-01-22 12:50:34.765219: step: 44/466, loss: 0.03415434807538986
2023-01-22 12:50:35.404941: step: 46/466, loss: 0.0038346522487699986
2023-01-22 12:50:36.031032: step: 48/466, loss: 0.005778027698397636
2023-01-22 12:50:36.640872: step: 50/466, loss: 0.007281619589775801
2023-01-22 12:50:37.311382: step: 52/466, loss: 0.015835389494895935
2023-01-22 12:50:37.957374: step: 54/466, loss: 0.01310531236231327
2023-01-22 12:50:38.606552: step: 56/466, loss: 0.006166370585560799
2023-01-22 12:50:39.216685: step: 58/466, loss: 0.023539837449789047
2023-01-22 12:50:39.825522: step: 60/466, loss: 0.04465335234999657
2023-01-22 12:50:40.395766: step: 62/466, loss: 0.0011540910927578807
2023-01-22 12:50:41.040285: step: 64/466, loss: 0.014557569287717342
2023-01-22 12:50:41.628707: step: 66/466, loss: 0.010300085879862309
2023-01-22 12:50:42.296336: step: 68/466, loss: 0.06224033609032631
2023-01-22 12:50:42.903954: step: 70/466, loss: 0.026488469913601875
2023-01-22 12:50:43.530348: step: 72/466, loss: 0.03434697911143303
2023-01-22 12:50:44.172540: step: 74/466, loss: 0.015540475025773048
2023-01-22 12:50:44.792374: step: 76/466, loss: 0.2161504030227661
2023-01-22 12:50:45.399113: step: 78/466, loss: 0.012048210948705673
2023-01-22 12:50:46.019920: step: 80/466, loss: 0.03682199865579605
2023-01-22 12:50:46.565263: step: 82/466, loss: 0.01592867448925972
2023-01-22 12:50:47.147891: step: 84/466, loss: 0.013426944613456726
2023-01-22 12:50:47.743467: step: 86/466, loss: 0.004081183113157749
2023-01-22 12:50:48.310251: step: 88/466, loss: 0.01988298073410988
2023-01-22 12:50:48.944129: step: 90/466, loss: 0.018079768866300583
2023-01-22 12:50:49.612675: step: 92/466, loss: 0.019703395664691925
2023-01-22 12:50:50.300545: step: 94/466, loss: 0.005619524046778679
2023-01-22 12:50:51.007658: step: 96/466, loss: 0.020142460241913795
2023-01-22 12:50:51.614026: step: 98/466, loss: 0.007503869011998177
2023-01-22 12:50:52.210935: step: 100/466, loss: 0.007635800633579493
2023-01-22 12:50:52.834069: step: 102/466, loss: 0.0380149781703949
2023-01-22 12:50:53.431571: step: 104/466, loss: 0.004585582297295332
2023-01-22 12:50:54.042805: step: 106/466, loss: 0.00025846846983768046
2023-01-22 12:50:54.714194: step: 108/466, loss: 0.018610037863254547
2023-01-22 12:50:55.308382: step: 110/466, loss: 0.013583391904830933
2023-01-22 12:50:55.929236: step: 112/466, loss: 0.014886787161231041
2023-01-22 12:50:56.531172: step: 114/466, loss: 0.1853538304567337
2023-01-22 12:50:57.126176: step: 116/466, loss: 0.011070048436522484
2023-01-22 12:50:57.669895: step: 118/466, loss: 0.007503334898501635
2023-01-22 12:50:58.308548: step: 120/466, loss: 0.4969816207885742
2023-01-22 12:50:58.930066: step: 122/466, loss: 0.013406869024038315
2023-01-22 12:50:59.567836: step: 124/466, loss: 0.23728245496749878
2023-01-22 12:51:00.241917: step: 126/466, loss: 0.0021659706253558397
2023-01-22 12:51:00.853894: step: 128/466, loss: 0.0159104373306036
2023-01-22 12:51:01.499583: step: 130/466, loss: 0.026894891634583473
2023-01-22 12:51:02.161268: step: 132/466, loss: 0.0010676357196643949
2023-01-22 12:51:02.738802: step: 134/466, loss: 0.008388376794755459
2023-01-22 12:51:03.312565: step: 136/466, loss: 0.10600942373275757
2023-01-22 12:51:03.953631: step: 138/466, loss: 0.047140851616859436
2023-01-22 12:51:04.581480: step: 140/466, loss: 0.030893616378307343
2023-01-22 12:51:05.251012: step: 142/466, loss: 0.0019499821355566382
2023-01-22 12:51:05.849204: step: 144/466, loss: 0.04567256569862366
2023-01-22 12:51:06.521545: step: 146/466, loss: 0.027375293895602226
2023-01-22 12:51:07.072659: step: 148/466, loss: 0.017524300143122673
2023-01-22 12:51:07.632278: step: 150/466, loss: 0.0002785766846500337
2023-01-22 12:51:08.204014: step: 152/466, loss: 0.0372467041015625
2023-01-22 12:51:08.783064: step: 154/466, loss: 0.04227850213646889
2023-01-22 12:51:09.388873: step: 156/466, loss: 0.02953212335705757
2023-01-22 12:51:09.999519: step: 158/466, loss: 0.005038856528699398
2023-01-22 12:51:10.569097: step: 160/466, loss: 0.00554104708135128
2023-01-22 12:51:11.192245: step: 162/466, loss: 0.04864320904016495
2023-01-22 12:51:11.813936: step: 164/466, loss: 0.08262515813112259
2023-01-22 12:51:12.526418: step: 166/466, loss: 0.024860626086592674
2023-01-22 12:51:13.137149: step: 168/466, loss: 0.009989991784095764
2023-01-22 12:51:13.761334: step: 170/466, loss: 0.002989133121445775
2023-01-22 12:51:14.443682: step: 172/466, loss: 0.08360762894153595
2023-01-22 12:51:15.047476: step: 174/466, loss: 0.008303227834403515
2023-01-22 12:51:15.684476: step: 176/466, loss: 0.03197474405169487
2023-01-22 12:51:16.291368: step: 178/466, loss: 0.02286393567919731
2023-01-22 12:51:16.855426: step: 180/466, loss: 0.008490473963320255
2023-01-22 12:51:17.516686: step: 182/466, loss: 0.05364244058728218
2023-01-22 12:51:18.174587: step: 184/466, loss: 0.22248348593711853
2023-01-22 12:51:18.777606: step: 186/466, loss: 0.007184356916695833
2023-01-22 12:51:19.454688: step: 188/466, loss: 0.007733544334769249
2023-01-22 12:51:20.077036: step: 190/466, loss: 0.0249953456223011
2023-01-22 12:51:20.691024: step: 192/466, loss: 0.03881276026368141
2023-01-22 12:51:21.320995: step: 194/466, loss: 0.06749670207500458
2023-01-22 12:51:21.903960: step: 196/466, loss: 0.06935339421033859
2023-01-22 12:51:22.545205: step: 198/466, loss: 0.012322738766670227
2023-01-22 12:51:23.175061: step: 200/466, loss: 0.07050473988056183
2023-01-22 12:51:23.794063: step: 202/466, loss: 0.00030367798171937466
2023-01-22 12:51:24.388468: step: 204/466, loss: 0.040786728262901306
2023-01-22 12:51:25.007695: step: 206/466, loss: 0.049529772251844406
2023-01-22 12:51:25.591225: step: 208/466, loss: 0.0509815588593483
2023-01-22 12:51:26.235516: step: 210/466, loss: 0.006703998893499374
2023-01-22 12:51:26.974013: step: 212/466, loss: 0.013644722290337086
2023-01-22 12:51:27.736472: step: 214/466, loss: 0.04323235899209976
2023-01-22 12:51:28.332522: step: 216/466, loss: 0.0813487246632576
2023-01-22 12:51:28.924465: step: 218/466, loss: 0.01943470537662506
2023-01-22 12:51:29.493372: step: 220/466, loss: 0.0996766909956932
2023-01-22 12:51:30.149163: step: 222/466, loss: 0.013173628598451614
2023-01-22 12:51:30.767665: step: 224/466, loss: 0.07100927829742432
2023-01-22 12:51:31.362096: step: 226/466, loss: 0.030978145077824593
2023-01-22 12:51:31.991580: step: 228/466, loss: 0.006432516500353813
2023-01-22 12:51:32.567844: step: 230/466, loss: 0.16904519498348236
2023-01-22 12:51:33.151211: step: 232/466, loss: 0.016514841467142105
2023-01-22 12:51:33.803324: step: 234/466, loss: 0.017402343451976776
2023-01-22 12:51:34.398426: step: 236/466, loss: 0.027484111487865448
2023-01-22 12:51:35.004480: step: 238/466, loss: 0.07576289772987366
2023-01-22 12:51:35.660077: step: 240/466, loss: 3.778850555419922
2023-01-22 12:51:36.272304: step: 242/466, loss: 0.04886449873447418
2023-01-22 12:51:36.903858: step: 244/466, loss: 0.10850292444229126
2023-01-22 12:51:37.572238: step: 246/466, loss: 0.0247701033949852
2023-01-22 12:51:38.123751: step: 248/466, loss: 0.004330090247094631
2023-01-22 12:51:38.776154: step: 250/466, loss: 0.4619436264038086
2023-01-22 12:51:39.386751: step: 252/466, loss: 0.01035249512642622
2023-01-22 12:51:39.950312: step: 254/466, loss: 0.009742227382957935
2023-01-22 12:51:40.628322: step: 256/466, loss: 0.01020122691988945
2023-01-22 12:51:41.208146: step: 258/466, loss: 0.007446271367371082
2023-01-22 12:51:41.819386: step: 260/466, loss: 0.15225790441036224
2023-01-22 12:51:42.443442: step: 262/466, loss: 0.014964156784117222
2023-01-22 12:51:43.005507: step: 264/466, loss: 0.01936171017587185
2023-01-22 12:51:43.554785: step: 266/466, loss: 0.0006788380560465157
2023-01-22 12:51:44.207752: step: 268/466, loss: 0.021012699231505394
2023-01-22 12:51:44.778070: step: 270/466, loss: 0.01303273718804121
2023-01-22 12:51:45.447694: step: 272/466, loss: 0.0294012650847435
2023-01-22 12:51:46.051154: step: 274/466, loss: 0.012099758721888065
2023-01-22 12:51:46.628199: step: 276/466, loss: 0.05515825003385544
2023-01-22 12:51:47.227504: step: 278/466, loss: 0.02570991776883602
2023-01-22 12:51:47.905840: step: 280/466, loss: 0.3937881588935852
2023-01-22 12:51:48.624939: step: 282/466, loss: 0.035539574921131134
2023-01-22 12:51:49.273485: step: 284/466, loss: 0.026720087975263596
2023-01-22 12:51:49.855797: step: 286/466, loss: 0.027191609144210815
2023-01-22 12:51:50.437393: step: 288/466, loss: 0.12927848100662231
2023-01-22 12:51:51.016836: step: 290/466, loss: 0.02109511010348797
2023-01-22 12:51:51.570009: step: 292/466, loss: 0.020149292424321175
2023-01-22 12:51:52.166220: step: 294/466, loss: 0.09865506738424301
2023-01-22 12:51:52.773232: step: 296/466, loss: 0.010992120020091534
2023-01-22 12:51:53.349161: step: 298/466, loss: 0.1111476942896843
2023-01-22 12:51:53.995007: step: 300/466, loss: 0.0034163333475589752
2023-01-22 12:51:54.630749: step: 302/466, loss: 0.00595430051907897
2023-01-22 12:51:55.286897: step: 304/466, loss: 0.025029225274920464
2023-01-22 12:51:55.893819: step: 306/466, loss: 0.028571361675858498
2023-01-22 12:51:56.533205: step: 308/466, loss: 0.17691342532634735
2023-01-22 12:51:57.109623: step: 310/466, loss: 0.020528914406895638
2023-01-22 12:51:57.689106: step: 312/466, loss: 0.049001604318618774
2023-01-22 12:51:58.289765: step: 314/466, loss: 0.0383269339799881
2023-01-22 12:51:58.894884: step: 316/466, loss: 0.02348129078745842
2023-01-22 12:51:59.542059: step: 318/466, loss: 0.059397753328084946
2023-01-22 12:52:00.239567: step: 320/466, loss: 0.04565797373652458
2023-01-22 12:52:00.788219: step: 322/466, loss: 0.057746272534132004
2023-01-22 12:52:01.415347: step: 324/466, loss: 0.026648664847016335
2023-01-22 12:52:02.062481: step: 326/466, loss: 0.16751256585121155
2023-01-22 12:52:02.695151: step: 328/466, loss: 0.030149096623063087
2023-01-22 12:52:03.271104: step: 330/466, loss: 0.029561301693320274
2023-01-22 12:52:03.903909: step: 332/466, loss: 0.029974963515996933
2023-01-22 12:52:04.498469: step: 334/466, loss: 0.040951766073703766
2023-01-22 12:52:05.118750: step: 336/466, loss: 0.06460101902484894
2023-01-22 12:52:05.730356: step: 338/466, loss: 0.3614656925201416
2023-01-22 12:52:06.372971: step: 340/466, loss: 0.061829160898923874
2023-01-22 12:52:06.969859: step: 342/466, loss: 0.0027699971105903387
2023-01-22 12:52:07.602587: step: 344/466, loss: 0.024076269939541817
2023-01-22 12:52:08.226481: step: 346/466, loss: 0.03276991471648216
2023-01-22 12:52:08.800625: step: 348/466, loss: 0.3131476938724518
2023-01-22 12:52:09.484174: step: 350/466, loss: 0.09210637211799622
2023-01-22 12:52:10.103932: step: 352/466, loss: 0.04329919070005417
2023-01-22 12:52:10.699267: step: 354/466, loss: 0.017054257914423943
2023-01-22 12:52:11.288645: step: 356/466, loss: 0.05004601180553436
2023-01-22 12:52:11.906892: step: 358/466, loss: 0.006824565585702658
2023-01-22 12:52:12.510757: step: 360/466, loss: 0.010391207411885262
2023-01-22 12:52:13.148044: step: 362/466, loss: 0.002363370731472969
2023-01-22 12:52:13.792185: step: 364/466, loss: 0.06585758924484253
2023-01-22 12:52:14.440236: step: 366/466, loss: 0.026189126074314117
2023-01-22 12:52:15.091833: step: 368/466, loss: 0.06721070408821106
2023-01-22 12:52:15.711090: step: 370/466, loss: 0.003301021410152316
2023-01-22 12:52:16.307002: step: 372/466, loss: 0.004242087714374065
2023-01-22 12:52:16.931283: step: 374/466, loss: 0.22085796296596527
2023-01-22 12:52:17.558031: step: 376/466, loss: 0.0024112502578645945
2023-01-22 12:52:18.190348: step: 378/466, loss: 0.28338131308555603
2023-01-22 12:52:18.789079: step: 380/466, loss: 0.0014360016211867332
2023-01-22 12:52:19.415538: step: 382/466, loss: 0.0298091322183609
2023-01-22 12:52:20.033149: step: 384/466, loss: 0.04952583461999893
2023-01-22 12:52:20.648536: step: 386/466, loss: 0.05813305824995041
2023-01-22 12:52:21.234695: step: 388/466, loss: 0.020183315500617027
2023-01-22 12:52:21.826056: step: 390/466, loss: 0.009550157934427261
2023-01-22 12:52:22.382858: step: 392/466, loss: 0.006014412268996239
2023-01-22 12:52:23.015929: step: 394/466, loss: 0.003889001440256834
2023-01-22 12:52:23.611912: step: 396/466, loss: 0.06576824188232422
2023-01-22 12:52:24.264723: step: 398/466, loss: 0.6932088136672974
2023-01-22 12:52:24.891835: step: 400/466, loss: 0.03067278116941452
2023-01-22 12:52:25.537891: step: 402/466, loss: 0.0402335599064827
2023-01-22 12:52:26.069174: step: 404/466, loss: 0.024017097428441048
2023-01-22 12:52:26.765648: step: 406/466, loss: 0.025933636352419853
2023-01-22 12:52:27.395193: step: 408/466, loss: 0.007940349169075489
2023-01-22 12:52:27.975404: step: 410/466, loss: 0.28987357020378113
2023-01-22 12:52:28.592118: step: 412/466, loss: 0.048365600407123566
2023-01-22 12:52:29.185867: step: 414/466, loss: 0.0058062439784407616
2023-01-22 12:52:29.810817: step: 416/466, loss: 0.4432596266269684
2023-01-22 12:52:30.482705: step: 418/466, loss: 0.02553720213472843
2023-01-22 12:52:31.121937: step: 420/466, loss: 0.006183108780533075
2023-01-22 12:52:31.681674: step: 422/466, loss: 0.012993517331779003
2023-01-22 12:52:32.339843: step: 424/466, loss: 0.027333056554198265
2023-01-22 12:52:32.943073: step: 426/466, loss: 0.05770184472203255
2023-01-22 12:52:33.593866: step: 428/466, loss: 0.0065458836033940315
2023-01-22 12:52:34.233812: step: 430/466, loss: 0.03590097278356552
2023-01-22 12:52:34.934977: step: 432/466, loss: 0.0036675333976745605
2023-01-22 12:52:35.575426: step: 434/466, loss: 0.004667150788009167
2023-01-22 12:52:36.231854: step: 436/466, loss: 0.039111293852329254
2023-01-22 12:52:36.844569: step: 438/466, loss: 0.07505755126476288
2023-01-22 12:52:37.429513: step: 440/466, loss: 0.015009235590696335
2023-01-22 12:52:38.018323: step: 442/466, loss: 0.012551910243928432
2023-01-22 12:52:38.590799: step: 444/466, loss: 0.0094830971211195
2023-01-22 12:52:39.244319: step: 446/466, loss: 0.01995844766497612
2023-01-22 12:52:39.847323: step: 448/466, loss: 0.06222337484359741
2023-01-22 12:52:40.517036: step: 450/466, loss: 0.4666108787059784
2023-01-22 12:52:41.158849: step: 452/466, loss: 0.08595582097768784
2023-01-22 12:52:41.832546: step: 454/466, loss: 0.06083333492279053
2023-01-22 12:52:42.495818: step: 456/466, loss: 0.017147425562143326
2023-01-22 12:52:43.168506: step: 458/466, loss: 0.008499028161168098
2023-01-22 12:52:43.754400: step: 460/466, loss: 0.003404253860935569
2023-01-22 12:52:44.357398: step: 462/466, loss: 0.059194836765527725
2023-01-22 12:52:44.969138: step: 464/466, loss: 0.023937981575727463
2023-01-22 12:52:45.607334: step: 466/466, loss: 0.24330773949623108
2023-01-22 12:52:46.241438: step: 468/466, loss: 0.7082357406616211
2023-01-22 12:52:46.864740: step: 470/466, loss: 0.1127346083521843
2023-01-22 12:52:47.525823: step: 472/466, loss: 0.004727509338408709
2023-01-22 12:52:48.167939: step: 474/466, loss: 0.019945118576288223
2023-01-22 12:52:48.853321: step: 476/466, loss: 0.013882302679121494
2023-01-22 12:52:49.458660: step: 478/466, loss: 0.02526629902422428
2023-01-22 12:52:50.087950: step: 480/466, loss: 0.01937795802950859
2023-01-22 12:52:50.698048: step: 482/466, loss: 0.007325158454477787
2023-01-22 12:52:51.362770: step: 484/466, loss: 0.13527823984622955
2023-01-22 12:52:51.993146: step: 486/466, loss: 0.04730508476495743
2023-01-22 12:52:52.625216: step: 488/466, loss: 0.024615265429019928
2023-01-22 12:52:53.203130: step: 490/466, loss: 0.020592007786035538
2023-01-22 12:52:53.774370: step: 492/466, loss: 0.024291126057505608
2023-01-22 12:52:54.310720: step: 494/466, loss: 0.0022951976861804724
2023-01-22 12:52:54.914011: step: 496/466, loss: 0.006601238623261452
2023-01-22 12:52:55.506744: step: 498/466, loss: 0.006386002991348505
2023-01-22 12:52:56.103306: step: 500/466, loss: 0.17011430859565735
2023-01-22 12:52:56.702070: step: 502/466, loss: 0.007931244559586048
2023-01-22 12:52:57.345677: step: 504/466, loss: 0.018457433208823204
2023-01-22 12:52:57.955311: step: 506/466, loss: 0.004319499246776104
2023-01-22 12:52:58.572485: step: 508/466, loss: 0.849025547504425
2023-01-22 12:52:59.209153: step: 510/466, loss: 0.03703732788562775
2023-01-22 12:52:59.887114: step: 512/466, loss: 0.6687430739402771
2023-01-22 12:53:00.518004: step: 514/466, loss: 0.0261391568928957
2023-01-22 12:53:01.121305: step: 516/466, loss: 0.058999765664339066
2023-01-22 12:53:01.747541: step: 518/466, loss: 0.4974743723869324
2023-01-22 12:53:02.416476: step: 520/466, loss: 0.02269855886697769
2023-01-22 12:53:02.985947: step: 522/466, loss: 0.041551124304533005
2023-01-22 12:53:03.538313: step: 524/466, loss: 0.031055569648742676
2023-01-22 12:53:04.153173: step: 526/466, loss: 0.020982986316084862
2023-01-22 12:53:04.865565: step: 528/466, loss: 0.037243373692035675
2023-01-22 12:53:05.483994: step: 530/466, loss: 0.06426267325878143
2023-01-22 12:53:06.170700: step: 532/466, loss: 0.03899231553077698
2023-01-22 12:53:06.780180: step: 534/466, loss: 0.038331370800733566
2023-01-22 12:53:07.420351: step: 536/466, loss: 0.012957875616848469
2023-01-22 12:53:07.966886: step: 538/466, loss: 0.0284006018191576
2023-01-22 12:53:08.598314: step: 540/466, loss: 0.042280081659555435
2023-01-22 12:53:09.258117: step: 542/466, loss: 0.09956970810890198
2023-01-22 12:53:09.947632: step: 544/466, loss: 0.02581607550382614
2023-01-22 12:53:10.547713: step: 546/466, loss: 0.0029468508437275887
2023-01-22 12:53:11.179759: step: 548/466, loss: 0.02818090282380581
2023-01-22 12:53:11.743354: step: 550/466, loss: 0.004466727375984192
2023-01-22 12:53:12.372673: step: 552/466, loss: 0.01916109025478363
2023-01-22 12:53:12.976471: step: 554/466, loss: 0.0018156702863052487
2023-01-22 12:53:13.587350: step: 556/466, loss: 0.054775774478912354
2023-01-22 12:53:14.188202: step: 558/466, loss: 0.006064811255782843
2023-01-22 12:53:14.810692: step: 560/466, loss: 0.010558255948126316
2023-01-22 12:53:15.376749: step: 562/466, loss: 0.01179610937833786
2023-01-22 12:53:15.997802: step: 564/466, loss: 0.010723483748733997
2023-01-22 12:53:16.595870: step: 566/466, loss: 0.008093049749732018
2023-01-22 12:53:17.204714: step: 568/466, loss: 0.1264907270669937
2023-01-22 12:53:17.889854: step: 570/466, loss: 0.0295632965862751
2023-01-22 12:53:18.572053: step: 572/466, loss: 0.09722160547971725
2023-01-22 12:53:19.195338: step: 574/466, loss: 0.029360679909586906
2023-01-22 12:53:19.873391: step: 576/466, loss: 0.06597114354372025
2023-01-22 12:53:20.596427: step: 578/466, loss: 0.012875804677605629
2023-01-22 12:53:21.165806: step: 580/466, loss: 0.013631662353873253
2023-01-22 12:53:21.812798: step: 582/466, loss: 0.026635481044650078
2023-01-22 12:53:22.439964: step: 584/466, loss: 0.01695885695517063
2023-01-22 12:53:23.059255: step: 586/466, loss: 0.0008552673971280456
2023-01-22 12:53:23.647497: step: 588/466, loss: 0.0036454915534704924
2023-01-22 12:53:24.195669: step: 590/466, loss: 0.06252723932266235
2023-01-22 12:53:24.904612: step: 592/466, loss: 0.00505690835416317
2023-01-22 12:53:25.577945: step: 594/466, loss: 0.01895541325211525
2023-01-22 12:53:26.159189: step: 596/466, loss: 0.01808973215520382
2023-01-22 12:53:26.822709: step: 598/466, loss: 0.04847077652812004
2023-01-22 12:53:27.403955: step: 600/466, loss: 0.050853267312049866
2023-01-22 12:53:28.010531: step: 602/466, loss: 0.008160309866070747
2023-01-22 12:53:28.680277: step: 604/466, loss: 0.023656044155359268
2023-01-22 12:53:29.330138: step: 606/466, loss: 0.04210818558931351
2023-01-22 12:53:29.914513: step: 608/466, loss: 0.016821881756186485
2023-01-22 12:53:30.498564: step: 610/466, loss: 0.570462703704834
2023-01-22 12:53:31.182091: step: 612/466, loss: 0.055564701557159424
2023-01-22 12:53:31.800306: step: 614/466, loss: 0.04362868517637253
2023-01-22 12:53:32.372328: step: 616/466, loss: 0.019416680559515953
2023-01-22 12:53:32.951909: step: 618/466, loss: 0.016455095261335373
2023-01-22 12:53:33.577167: step: 620/466, loss: 0.008576720021665096
2023-01-22 12:53:34.143932: step: 622/466, loss: 0.04641371965408325
2023-01-22 12:53:34.705949: step: 624/466, loss: 0.14390678703784943
2023-01-22 12:53:35.312364: step: 626/466, loss: 0.0321093313395977
2023-01-22 12:53:35.924297: step: 628/466, loss: 0.06703966856002808
2023-01-22 12:53:36.541481: step: 630/466, loss: 0.05470241233706474
2023-01-22 12:53:37.121686: step: 632/466, loss: 0.022950900718569756
2023-01-22 12:53:37.845235: step: 634/466, loss: 0.02484145201742649
2023-01-22 12:53:38.464513: step: 636/466, loss: 0.08635030686855316
2023-01-22 12:53:39.072089: step: 638/466, loss: 0.0073463390581309795
2023-01-22 12:53:39.700860: step: 640/466, loss: 0.0007146025891415775
2023-01-22 12:53:40.313657: step: 642/466, loss: 0.029871122911572456
2023-01-22 12:53:40.962289: step: 644/466, loss: 0.02813507243990898
2023-01-22 12:53:41.626305: step: 646/466, loss: 0.009793507866561413
2023-01-22 12:53:42.215529: step: 648/466, loss: 0.0316142812371254
2023-01-22 12:53:42.802146: step: 650/466, loss: 0.028614122420549393
2023-01-22 12:53:43.397499: step: 652/466, loss: 0.019259123131632805
2023-01-22 12:53:44.065700: step: 654/466, loss: 0.06576264649629593
2023-01-22 12:53:44.699440: step: 656/466, loss: 0.10803041607141495
2023-01-22 12:53:45.346670: step: 658/466, loss: 0.06235981360077858
2023-01-22 12:53:45.997830: step: 660/466, loss: 0.012615116313099861
2023-01-22 12:53:46.600019: step: 662/466, loss: 0.001386008458212018
2023-01-22 12:53:47.275388: step: 664/466, loss: 0.017653729766607285
2023-01-22 12:53:47.871949: step: 666/466, loss: 0.01049298606812954
2023-01-22 12:53:48.563898: step: 668/466, loss: 0.009629614651203156
2023-01-22 12:53:49.205574: step: 670/466, loss: 0.014639287255704403
2023-01-22 12:53:49.898677: step: 672/466, loss: 0.01156079862266779
2023-01-22 12:53:50.535211: step: 674/466, loss: 0.01873650960624218
2023-01-22 12:53:51.246965: step: 676/466, loss: 0.019368216395378113
2023-01-22 12:53:51.885165: step: 678/466, loss: 0.05814380198717117
2023-01-22 12:53:52.457073: step: 680/466, loss: 0.01892939954996109
2023-01-22 12:53:53.119069: step: 682/466, loss: 0.025773027911782265
2023-01-22 12:53:53.721986: step: 684/466, loss: 0.00873519852757454
2023-01-22 12:53:54.292896: step: 686/466, loss: 0.0031690082978457212
2023-01-22 12:53:54.916750: step: 688/466, loss: 0.029933644458651543
2023-01-22 12:53:55.481138: step: 690/466, loss: 0.011398996226489544
2023-01-22 12:53:56.066910: step: 692/466, loss: 0.039612822234630585
2023-01-22 12:53:56.682900: step: 694/466, loss: 0.03607015311717987
2023-01-22 12:53:57.305135: step: 696/466, loss: 0.008851285092532635
2023-01-22 12:53:57.910366: step: 698/466, loss: 0.0515628457069397
2023-01-22 12:53:58.587913: step: 700/466, loss: 0.021373560652136803
2023-01-22 12:53:59.220923: step: 702/466, loss: 0.13975434005260468
2023-01-22 12:53:59.858104: step: 704/466, loss: 0.04040196165442467
2023-01-22 12:54:00.482524: step: 706/466, loss: 0.03192339837551117
2023-01-22 12:54:01.105307: step: 708/466, loss: 0.04951074719429016
2023-01-22 12:54:01.812965: step: 710/466, loss: 0.02514973282814026
2023-01-22 12:54:02.368533: step: 712/466, loss: 0.24668730795383453
2023-01-22 12:54:02.996273: step: 714/466, loss: 0.0209896732121706
2023-01-22 12:54:03.620644: step: 716/466, loss: 1.013275146484375
2023-01-22 12:54:04.145969: step: 718/466, loss: 0.0603434182703495
2023-01-22 12:54:04.760986: step: 720/466, loss: 0.05530453100800514
2023-01-22 12:54:05.369188: step: 722/466, loss: 0.02282405085861683
2023-01-22 12:54:06.013750: step: 724/466, loss: 0.49871450662612915
2023-01-22 12:54:06.590079: step: 726/466, loss: 0.016372518613934517
2023-01-22 12:54:07.191519: step: 728/466, loss: 0.02990126982331276
2023-01-22 12:54:07.785868: step: 730/466, loss: 0.011705626733601093
2023-01-22 12:54:08.406360: step: 732/466, loss: 0.008233029395341873
2023-01-22 12:54:09.038429: step: 734/466, loss: 0.09673385322093964
2023-01-22 12:54:09.626286: step: 736/466, loss: 0.04583362862467766
2023-01-22 12:54:10.258325: step: 738/466, loss: 0.007076576817780733
2023-01-22 12:54:10.877228: step: 740/466, loss: 0.001303449971601367
2023-01-22 12:54:11.549000: step: 742/466, loss: 0.12852562963962555
2023-01-22 12:54:12.178810: step: 744/466, loss: 0.016642574220895767
2023-01-22 12:54:12.782950: step: 746/466, loss: 0.007977128028869629
2023-01-22 12:54:13.439778: step: 748/466, loss: 0.12341004610061646
2023-01-22 12:54:14.086823: step: 750/466, loss: 0.010951337404549122
2023-01-22 12:54:14.756014: step: 752/466, loss: 0.016577934846282005
2023-01-22 12:54:15.367932: step: 754/466, loss: 0.03315458819270134
2023-01-22 12:54:16.021433: step: 756/466, loss: 0.06137204170227051
2023-01-22 12:54:16.681782: step: 758/466, loss: 0.02198304980993271
2023-01-22 12:54:17.317170: step: 760/466, loss: 0.03844422474503517
2023-01-22 12:54:17.865398: step: 762/466, loss: 0.681039571762085
2023-01-22 12:54:18.484577: step: 764/466, loss: 0.03540460020303726
2023-01-22 12:54:19.025083: step: 766/466, loss: 0.02652108296751976
2023-01-22 12:54:19.634600: step: 768/466, loss: 0.12025786936283112
2023-01-22 12:54:20.263384: step: 770/466, loss: 0.006684943102300167
2023-01-22 12:54:20.876578: step: 772/466, loss: 0.026162046939134598
2023-01-22 12:54:21.481164: step: 774/466, loss: 0.007701580412685871
2023-01-22 12:54:22.209998: step: 776/466, loss: 0.0641896203160286
2023-01-22 12:54:22.835596: step: 778/466, loss: 0.05006628483533859
2023-01-22 12:54:23.450426: step: 780/466, loss: 0.03685498610138893
2023-01-22 12:54:24.160483: step: 782/466, loss: 0.011374561116099358
2023-01-22 12:54:24.894943: step: 784/466, loss: 0.024460364133119583
2023-01-22 12:54:25.463174: step: 786/466, loss: 0.04770936444401741
2023-01-22 12:54:26.088790: step: 788/466, loss: 0.01947230100631714
2023-01-22 12:54:26.705466: step: 790/466, loss: 0.0377841480076313
2023-01-22 12:54:27.271534: step: 792/466, loss: 0.015739483758807182
2023-01-22 12:54:27.900532: step: 794/466, loss: 0.017583288252353668
2023-01-22 12:54:28.553044: step: 796/466, loss: 0.1661037802696228
2023-01-22 12:54:29.309240: step: 798/466, loss: 0.04773499444127083
2023-01-22 12:54:29.936019: step: 800/466, loss: 0.0025100763887166977
2023-01-22 12:54:30.544684: step: 802/466, loss: 0.02382386289536953
2023-01-22 12:54:31.182557: step: 804/466, loss: 0.13822172582149506
2023-01-22 12:54:31.754748: step: 806/466, loss: 0.021848829463124275
2023-01-22 12:54:32.347127: step: 808/466, loss: 0.1822071373462677
2023-01-22 12:54:32.966392: step: 810/466, loss: 0.019787373021245003
2023-01-22 12:54:33.545568: step: 812/466, loss: 0.02656339854001999
2023-01-22 12:54:34.117706: step: 814/466, loss: 0.007962155155837536
2023-01-22 12:54:34.712814: step: 816/466, loss: 0.04875000938773155
2023-01-22 12:54:35.357905: step: 818/466, loss: 0.014167295768857002
2023-01-22 12:54:35.990985: step: 820/466, loss: 0.0020671940874308348
2023-01-22 12:54:36.618208: step: 822/466, loss: 0.0077877468429505825
2023-01-22 12:54:37.351842: step: 824/466, loss: 0.01249811053276062
2023-01-22 12:54:37.939336: step: 826/466, loss: 0.04537919536232948
2023-01-22 12:54:38.643628: step: 828/466, loss: 0.01676964946091175
2023-01-22 12:54:39.277743: step: 830/466, loss: 0.04484226927161217
2023-01-22 12:54:39.946943: step: 832/466, loss: 0.03277130797505379
2023-01-22 12:54:40.571953: step: 834/466, loss: 0.0016892838757485151
2023-01-22 12:54:41.250702: step: 836/466, loss: 0.06757955253124237
2023-01-22 12:54:41.927526: step: 838/466, loss: 0.015835018828511238
2023-01-22 12:54:42.465052: step: 840/466, loss: 0.04168068617582321
2023-01-22 12:54:43.052512: step: 842/466, loss: 0.015160385519266129
2023-01-22 12:54:43.805977: step: 844/466, loss: 0.09161270409822464
2023-01-22 12:54:44.399147: step: 846/466, loss: 0.03056454285979271
2023-01-22 12:54:44.982939: step: 848/466, loss: 0.009426084347069263
2023-01-22 12:54:45.637607: step: 850/466, loss: 0.04484337940812111
2023-01-22 12:54:46.234955: step: 852/466, loss: 0.02648405358195305
2023-01-22 12:54:46.872164: step: 854/466, loss: 0.019934559240937233
2023-01-22 12:54:47.482847: step: 856/466, loss: 0.009772099554538727
2023-01-22 12:54:48.050780: step: 858/466, loss: 0.0010070321150124073
2023-01-22 12:54:48.765425: step: 860/466, loss: 0.0026540574617683887
2023-01-22 12:54:49.418044: step: 862/466, loss: 0.01820238307118416
2023-01-22 12:54:49.987112: step: 864/466, loss: 0.012328501790761948
2023-01-22 12:54:50.621101: step: 866/466, loss: 0.06458301842212677
2023-01-22 12:54:51.254838: step: 868/466, loss: 0.06785338371992111
2023-01-22 12:54:51.916952: step: 870/466, loss: 0.07444152981042862
2023-01-22 12:54:52.524788: step: 872/466, loss: 0.006764355581253767
2023-01-22 12:54:53.108002: step: 874/466, loss: 0.05087079107761383
2023-01-22 12:54:53.675031: step: 876/466, loss: 0.01839734986424446
2023-01-22 12:54:54.259231: step: 878/466, loss: 0.039690256118774414
2023-01-22 12:54:54.937708: step: 880/466, loss: 0.04079141840338707
2023-01-22 12:54:55.529794: step: 882/466, loss: 0.011542139574885368
2023-01-22 12:54:56.111935: step: 884/466, loss: 0.07851341366767883
2023-01-22 12:54:56.736835: step: 886/466, loss: 0.01554762851446867
2023-01-22 12:54:57.269420: step: 888/466, loss: 0.010157089680433273
2023-01-22 12:54:57.903874: step: 890/466, loss: 0.016509560868144035
2023-01-22 12:54:58.535193: step: 892/466, loss: 0.04192443937063217
2023-01-22 12:54:59.150609: step: 894/466, loss: 0.04110085219144821
2023-01-22 12:54:59.757935: step: 896/466, loss: 0.013482372276484966
2023-01-22 12:55:00.358224: step: 898/466, loss: 0.1777517944574356
2023-01-22 12:55:01.020467: step: 900/466, loss: 0.11353351175785065
2023-01-22 12:55:01.639802: step: 902/466, loss: 0.002722186967730522
2023-01-22 12:55:02.319472: step: 904/466, loss: 0.029758060351014137
2023-01-22 12:55:02.909966: step: 906/466, loss: 0.005375860724598169
2023-01-22 12:55:03.511427: step: 908/466, loss: 0.00414345832541585
2023-01-22 12:55:04.105000: step: 910/466, loss: 0.04140179604291916
2023-01-22 12:55:04.725864: step: 912/466, loss: 0.0016417494043707848
2023-01-22 12:55:05.346456: step: 914/466, loss: 0.026578109711408615
2023-01-22 12:55:05.995327: step: 916/466, loss: 0.15591458976268768
2023-01-22 12:55:06.688186: step: 918/466, loss: 0.01798109896481037
2023-01-22 12:55:07.340965: step: 920/466, loss: 0.006656917277723551
2023-01-22 12:55:07.941626: step: 922/466, loss: 0.004008627030998468
2023-01-22 12:55:08.573175: step: 924/466, loss: 0.038623325526714325
2023-01-22 12:55:09.188945: step: 926/466, loss: 0.006900690030306578
2023-01-22 12:55:09.813931: step: 928/466, loss: 0.013307107612490654
2023-01-22 12:55:10.489122: step: 930/466, loss: 0.9667753577232361
2023-01-22 12:55:11.016549: step: 932/466, loss: 0.07520213723182678
==================================================
Loss: 0.069
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31825345423143353, 'r': 0.3496560721062619, 'f1': 0.33321654611211576}, 'combined': 0.2455279813457695, 'epoch': 26}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.33476707071036205, 'r': 0.3000527216285842, 'f1': 0.31646074016747494}, 'combined': 0.19815765973103575, 'epoch': 26}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3074782091917591, 'r': 0.3681570208728653, 'f1': 0.33509283246977545}, 'combined': 0.246910508135624, 'epoch': 26}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.33647098127232916, 'r': 0.3112660250939868, 'f1': 0.32337811139628453}, 'combined': 0.20040333663995097, 'epoch': 26}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2790776877761414, 'r': 0.35957068311195445, 'f1': 0.3142516583747927}, 'combined': 0.23155385353932093, 'epoch': 26}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3304205072166237, 'r': 0.30743732830453696, 'f1': 0.3185148548742372}, 'combined': 0.2112920324413257, 'epoch': 26}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.24519230769230768, 'r': 0.36428571428571427, 'f1': 0.29310344827586204}, 'combined': 0.1954022988505747, 'epoch': 26}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 26}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.26, 'r': 0.22413793103448276, 'f1': 0.24074074074074073}, 'combined': 0.16049382716049382, 'epoch': 26}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3074782091917591, 'r': 0.3681570208728653, 'f1': 0.33509283246977545}, 'combined': 0.246910508135624, 'epoch': 26}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.33647098127232916, 'r': 0.3112660250939868, 'f1': 0.32337811139628453}, 'combined': 0.20040333663995097, 'epoch': 26}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'epoch': 26}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 12:57:58.305366: step: 2/466, loss: 0.00473618321120739
2023-01-22 12:57:59.011081: step: 4/466, loss: 0.021933015435934067
2023-01-22 12:57:59.567965: step: 6/466, loss: 0.01194464135915041
2023-01-22 12:58:00.195401: step: 8/466, loss: 0.0030708627309650183
2023-01-22 12:58:00.827931: step: 10/466, loss: 0.08510902523994446
2023-01-22 12:58:01.475454: step: 12/466, loss: 0.03904871270060539
2023-01-22 12:58:02.223954: step: 14/466, loss: 0.03710261359810829
2023-01-22 12:58:02.859840: step: 16/466, loss: 0.03612261265516281
2023-01-22 12:58:03.475480: step: 18/466, loss: 0.02608722262084484
2023-01-22 12:58:04.117429: step: 20/466, loss: 0.02009262517094612
2023-01-22 12:58:04.785242: step: 22/466, loss: 0.00886100996285677
2023-01-22 12:58:05.403619: step: 24/466, loss: 0.006947273854166269
2023-01-22 12:58:05.993991: step: 26/466, loss: 0.5168101191520691
2023-01-22 12:58:06.594779: step: 28/466, loss: 0.012647329829633236
2023-01-22 12:58:07.296708: step: 30/466, loss: 0.07058289647102356
2023-01-22 12:58:07.937576: step: 32/466, loss: 0.5412499308586121
2023-01-22 12:58:08.552791: step: 34/466, loss: 1.4842169284820557
2023-01-22 12:58:09.172995: step: 36/466, loss: 0.008719472214579582
2023-01-22 12:58:09.768197: step: 38/466, loss: 0.1013767272233963
2023-01-22 12:58:10.426357: step: 40/466, loss: 0.018471570685505867
2023-01-22 12:58:10.997281: step: 42/466, loss: 0.01053072139620781
2023-01-22 12:58:11.629055: step: 44/466, loss: 0.04705832898616791
2023-01-22 12:58:12.229976: step: 46/466, loss: 0.015392724424600601
2023-01-22 12:58:12.913715: step: 48/466, loss: 0.1451658457517624
2023-01-22 12:58:13.538837: step: 50/466, loss: 0.0006970667745918036
2023-01-22 12:58:14.168100: step: 52/466, loss: 0.017020707949995995
2023-01-22 12:58:14.938713: step: 54/466, loss: 0.01852017641067505
2023-01-22 12:58:15.526074: step: 56/466, loss: 0.0063835615292191505
2023-01-22 12:58:16.201162: step: 58/466, loss: 1.0854027271270752
2023-01-22 12:58:16.839907: step: 60/466, loss: 0.0040357052348554134
2023-01-22 12:58:17.415522: step: 62/466, loss: 0.015983114019036293
2023-01-22 12:58:17.964045: step: 64/466, loss: 0.019109312444925308
2023-01-22 12:58:18.565963: step: 66/466, loss: 0.018166447058320045
2023-01-22 12:58:19.187120: step: 68/466, loss: 0.006958534475415945
2023-01-22 12:58:19.864910: step: 70/466, loss: 0.018533293157815933
2023-01-22 12:58:20.403424: step: 72/466, loss: 0.0011832513846457005
2023-01-22 12:58:21.022792: step: 74/466, loss: 0.00281977909617126
2023-01-22 12:58:21.592941: step: 76/466, loss: 0.02246713638305664
2023-01-22 12:58:22.218855: step: 78/466, loss: 0.010963533073663712
2023-01-22 12:58:22.786785: step: 80/466, loss: 0.1575906127691269
2023-01-22 12:58:23.405535: step: 82/466, loss: 0.004155725706368685
2023-01-22 12:58:24.002371: step: 84/466, loss: 0.004825697746127844
2023-01-22 12:58:24.618633: step: 86/466, loss: 0.09241409599781036
2023-01-22 12:58:25.249734: step: 88/466, loss: 0.036858055740594864
2023-01-22 12:58:25.871016: step: 90/466, loss: 0.025953615084290504
2023-01-22 12:58:26.464229: step: 92/466, loss: 0.06212431564927101
2023-01-22 12:58:27.157146: step: 94/466, loss: 0.009525452740490437
2023-01-22 12:58:27.852511: step: 96/466, loss: 0.009087126702070236
2023-01-22 12:58:28.436859: step: 98/466, loss: 0.11408080905675888
2023-01-22 12:58:29.052797: step: 100/466, loss: 0.0030554882250726223
2023-01-22 12:58:29.819735: step: 102/466, loss: 0.0033673925790935755
2023-01-22 12:58:30.424614: step: 104/466, loss: 0.02337544783949852
2023-01-22 12:58:31.018165: step: 106/466, loss: 0.002787669189274311
2023-01-22 12:58:31.640893: step: 108/466, loss: 0.013979383744299412
2023-01-22 12:58:32.258922: step: 110/466, loss: 0.007575168740004301
2023-01-22 12:58:32.900063: step: 112/466, loss: 0.04922885447740555
2023-01-22 12:58:33.507774: step: 114/466, loss: 0.10226202756166458
2023-01-22 12:58:34.107738: step: 116/466, loss: 0.018735816702246666
2023-01-22 12:58:34.734243: step: 118/466, loss: 0.030529620125889778
2023-01-22 12:58:35.313100: step: 120/466, loss: 0.06682250648736954
2023-01-22 12:58:35.956559: step: 122/466, loss: 0.02575521729886532
2023-01-22 12:58:36.578517: step: 124/466, loss: 0.025370188057422638
2023-01-22 12:58:37.159023: step: 126/466, loss: 0.0212542787194252
2023-01-22 12:58:37.747981: step: 128/466, loss: 0.10935328155755997
2023-01-22 12:58:38.362352: step: 130/466, loss: 0.0003061419993173331
2023-01-22 12:58:38.990143: step: 132/466, loss: 0.08963587135076523
2023-01-22 12:58:39.680940: step: 134/466, loss: 0.01148142758756876
2023-01-22 12:58:40.290263: step: 136/466, loss: 0.10679512470960617
2023-01-22 12:58:40.840587: step: 138/466, loss: 0.02435310184955597
2023-01-22 12:58:41.508761: step: 140/466, loss: 0.013863036409020424
2023-01-22 12:58:42.172878: step: 142/466, loss: 0.0051196301355957985
2023-01-22 12:58:42.764626: step: 144/466, loss: 0.13050124049186707
2023-01-22 12:58:43.424934: step: 146/466, loss: 0.015986185520887375
2023-01-22 12:58:44.058895: step: 148/466, loss: 0.07870206981897354
2023-01-22 12:58:44.687646: step: 150/466, loss: 0.009278064593672752
2023-01-22 12:58:45.268583: step: 152/466, loss: 0.019551480188965797
2023-01-22 12:58:45.884376: step: 154/466, loss: 0.03024390898644924
2023-01-22 12:58:46.418121: step: 156/466, loss: 0.024581238627433777
2023-01-22 12:58:47.072342: step: 158/466, loss: 0.022428328171372414
2023-01-22 12:58:47.737176: step: 160/466, loss: 0.05050790309906006
2023-01-22 12:58:48.371735: step: 162/466, loss: 0.043015267699956894
2023-01-22 12:58:49.001338: step: 164/466, loss: 0.014434296637773514
2023-01-22 12:58:49.642082: step: 166/466, loss: 0.006054923869669437
2023-01-22 12:58:50.213253: step: 168/466, loss: 0.013495230115950108
2023-01-22 12:58:50.854079: step: 170/466, loss: 0.08444388955831528
2023-01-22 12:58:51.470082: step: 172/466, loss: 0.11862921714782715
2023-01-22 12:58:52.097930: step: 174/466, loss: 0.00015126168727874756
2023-01-22 12:58:52.688087: step: 176/466, loss: 0.011310840956866741
2023-01-22 12:58:53.335383: step: 178/466, loss: 0.022712282836437225
2023-01-22 12:58:53.913790: step: 180/466, loss: 0.002795211272314191
2023-01-22 12:58:54.573626: step: 182/466, loss: 0.6242778301239014
2023-01-22 12:58:55.267040: step: 184/466, loss: 0.046207040548324585
2023-01-22 12:58:55.911993: step: 186/466, loss: 0.015958664938807487
2023-01-22 12:58:56.640539: step: 188/466, loss: 0.009933280758559704
2023-01-22 12:58:57.264115: step: 190/466, loss: 0.029680395498871803
2023-01-22 12:58:57.839696: step: 192/466, loss: 0.022134831175208092
2023-01-22 12:58:58.413697: step: 194/466, loss: 0.00868904311209917
2023-01-22 12:58:59.038207: step: 196/466, loss: 0.05578196421265602
2023-01-22 12:58:59.652098: step: 198/466, loss: 0.002785441931337118
2023-01-22 12:59:00.254127: step: 200/466, loss: 0.009689037688076496
2023-01-22 12:59:00.898302: step: 202/466, loss: 0.019714631140232086
2023-01-22 12:59:01.569773: step: 204/466, loss: 0.028808506205677986
2023-01-22 12:59:02.238919: step: 206/466, loss: 0.197043776512146
2023-01-22 12:59:02.835437: step: 208/466, loss: 0.036407601088285446
2023-01-22 12:59:03.458998: step: 210/466, loss: 0.013742203824222088
2023-01-22 12:59:04.021762: step: 212/466, loss: 0.0034784136805683374
2023-01-22 12:59:04.626964: step: 214/466, loss: 0.007334389258176088
2023-01-22 12:59:05.177098: step: 216/466, loss: 2.303227186203003
2023-01-22 12:59:05.761550: step: 218/466, loss: 0.0018344019772484899
2023-01-22 12:59:06.434213: step: 220/466, loss: 0.02117347903549671
2023-01-22 12:59:07.097837: step: 222/466, loss: 0.006467959377914667
2023-01-22 12:59:07.714514: step: 224/466, loss: 0.032383497804403305
2023-01-22 12:59:08.296935: step: 226/466, loss: 0.019396239891648293
2023-01-22 12:59:08.900928: step: 228/466, loss: 0.021252932026982307
2023-01-22 12:59:09.515322: step: 230/466, loss: 0.009483873844146729
2023-01-22 12:59:10.176538: step: 232/466, loss: 0.004131697118282318
2023-01-22 12:59:10.787533: step: 234/466, loss: 0.0014794659800827503
2023-01-22 12:59:11.386523: step: 236/466, loss: 0.04074552655220032
2023-01-22 12:59:12.033031: step: 238/466, loss: 0.005354260094463825
2023-01-22 12:59:12.694295: step: 240/466, loss: 0.0849388837814331
2023-01-22 12:59:13.292958: step: 242/466, loss: 0.02900581806898117
2023-01-22 12:59:13.885720: step: 244/466, loss: 0.022469066083431244
2023-01-22 12:59:14.487592: step: 246/466, loss: 0.007856997661292553
2023-01-22 12:59:15.084231: step: 248/466, loss: 0.23080813884735107
2023-01-22 12:59:15.676724: step: 250/466, loss: 0.030895939096808434
2023-01-22 12:59:16.271985: step: 252/466, loss: 0.03448798879981041
2023-01-22 12:59:16.861783: step: 254/466, loss: 0.03563670441508293
2023-01-22 12:59:17.485782: step: 256/466, loss: 0.00970627460628748
2023-01-22 12:59:18.133315: step: 258/466, loss: 0.01935366541147232
2023-01-22 12:59:18.829867: step: 260/466, loss: 0.006309571210294962
2023-01-22 12:59:19.439961: step: 262/466, loss: 0.06405292451381683
2023-01-22 12:59:20.023471: step: 264/466, loss: 0.006565271411091089
2023-01-22 12:59:20.611013: step: 266/466, loss: 0.057645246386528015
2023-01-22 12:59:21.222054: step: 268/466, loss: 0.024342840537428856
2023-01-22 12:59:21.817879: step: 270/466, loss: 0.0457969568669796
2023-01-22 12:59:22.568720: step: 272/466, loss: 0.1900371015071869
2023-01-22 12:59:23.186478: step: 274/466, loss: 0.034951284527778625
2023-01-22 12:59:23.849338: step: 276/466, loss: 0.048316992819309235
2023-01-22 12:59:24.441784: step: 278/466, loss: 0.04126692935824394
2023-01-22 12:59:25.034702: step: 280/466, loss: 0.04981108009815216
2023-01-22 12:59:25.626811: step: 282/466, loss: 0.0024086672347038984
2023-01-22 12:59:26.260257: step: 284/466, loss: 0.08330139517784119
2023-01-22 12:59:26.870252: step: 286/466, loss: 0.008298112079501152
2023-01-22 12:59:27.489168: step: 288/466, loss: 0.011200077831745148
2023-01-22 12:59:28.068928: step: 290/466, loss: 0.0011140488786622882
2023-01-22 12:59:28.645462: step: 292/466, loss: 0.0024151839315891266
2023-01-22 12:59:29.236956: step: 294/466, loss: 0.008168731816112995
2023-01-22 12:59:29.773125: step: 296/466, loss: 0.010240050032734871
2023-01-22 12:59:30.443861: step: 298/466, loss: 0.014512955211102962
2023-01-22 12:59:31.045957: step: 300/466, loss: 0.009714333340525627
2023-01-22 12:59:31.625528: step: 302/466, loss: 0.08640128374099731
2023-01-22 12:59:32.152053: step: 304/466, loss: 0.04933005943894386
2023-01-22 12:59:32.760388: step: 306/466, loss: 0.05029614269733429
2023-01-22 12:59:33.339900: step: 308/466, loss: 0.05182838439941406
2023-01-22 12:59:33.956299: step: 310/466, loss: 0.005064661148935556
2023-01-22 12:59:34.590049: step: 312/466, loss: 0.026809820905327797
2023-01-22 12:59:35.228128: step: 314/466, loss: 0.002669850131496787
2023-01-22 12:59:35.814913: step: 316/466, loss: 0.027825424447655678
2023-01-22 12:59:36.475962: step: 318/466, loss: 0.0005731211858801544
2023-01-22 12:59:37.116740: step: 320/466, loss: 0.016787687316536903
2023-01-22 12:59:37.747301: step: 322/466, loss: 0.017717620357871056
2023-01-22 12:59:38.379283: step: 324/466, loss: 0.04581868648529053
2023-01-22 12:59:38.969486: step: 326/466, loss: 0.017648017033934593
2023-01-22 12:59:39.601476: step: 328/466, loss: 0.014814457856118679
2023-01-22 12:59:40.213076: step: 330/466, loss: 0.010334369726479053
2023-01-22 12:59:40.876969: step: 332/466, loss: 0.001626111101359129
2023-01-22 12:59:41.520215: step: 334/466, loss: 0.0026082699187099934
2023-01-22 12:59:42.188704: step: 336/466, loss: 0.008969327434897423
2023-01-22 12:59:42.790792: step: 338/466, loss: 0.02104179561138153
2023-01-22 12:59:43.407226: step: 340/466, loss: 0.042626965790987015
2023-01-22 12:59:44.004415: step: 342/466, loss: 0.016393663361668587
2023-01-22 12:59:44.641745: step: 344/466, loss: 0.0356920026242733
2023-01-22 12:59:45.271926: step: 346/466, loss: 0.017763594165444374
2023-01-22 12:59:45.922290: step: 348/466, loss: 0.02152266539633274
2023-01-22 12:59:46.563397: step: 350/466, loss: 0.07866132259368896
2023-01-22 12:59:47.196974: step: 352/466, loss: 0.010813960805535316
2023-01-22 12:59:47.805614: step: 354/466, loss: 0.002389649162068963
2023-01-22 12:59:48.431323: step: 356/466, loss: 0.006263962481170893
2023-01-22 12:59:49.068322: step: 358/466, loss: 0.028872860595583916
2023-01-22 12:59:49.701000: step: 360/466, loss: 0.03761502727866173
2023-01-22 12:59:50.366557: step: 362/466, loss: 0.01260085217654705
2023-01-22 12:59:50.935670: step: 364/466, loss: 0.12152864784002304
2023-01-22 12:59:51.592385: step: 366/466, loss: 0.14280076324939728
2023-01-22 12:59:52.189919: step: 368/466, loss: 0.028131060302257538
2023-01-22 12:59:52.786545: step: 370/466, loss: 0.008670762181282043
2023-01-22 12:59:53.479708: step: 372/466, loss: 0.02223077416419983
2023-01-22 12:59:54.065043: step: 374/466, loss: 0.0015590013936161995
2023-01-22 12:59:54.675455: step: 376/466, loss: 0.04011651873588562
2023-01-22 12:59:55.267778: step: 378/466, loss: 0.012510258704423904
2023-01-22 12:59:55.890909: step: 380/466, loss: 0.010407834313809872
2023-01-22 12:59:56.524774: step: 382/466, loss: 0.016522957012057304
2023-01-22 12:59:57.176306: step: 384/466, loss: 0.04073789343237877
2023-01-22 12:59:57.845940: step: 386/466, loss: 0.06633096933364868
2023-01-22 12:59:58.445599: step: 388/466, loss: 0.013094646856188774
2023-01-22 12:59:59.087934: step: 390/466, loss: 0.01919671520590782
2023-01-22 12:59:59.769911: step: 392/466, loss: 0.28468018770217896
2023-01-22 13:00:00.414962: step: 394/466, loss: 0.025736916810274124
2023-01-22 13:00:01.080592: step: 396/466, loss: 0.10791622847318649
2023-01-22 13:00:01.703787: step: 398/466, loss: 0.03712229058146477
2023-01-22 13:00:02.335004: step: 400/466, loss: 0.04609160125255585
2023-01-22 13:00:02.936578: step: 402/466, loss: 0.028331611305475235
2023-01-22 13:00:03.591831: step: 404/466, loss: 0.006319758482277393
2023-01-22 13:00:04.183499: step: 406/466, loss: 0.001945237978361547
2023-01-22 13:00:04.856363: step: 408/466, loss: 0.04442158341407776
2023-01-22 13:00:05.494030: step: 410/466, loss: 0.0859503522515297
2023-01-22 13:00:06.074192: step: 412/466, loss: 0.033219464123249054
2023-01-22 13:00:06.738128: step: 414/466, loss: 0.05364341661334038
2023-01-22 13:00:07.356064: step: 416/466, loss: 0.10488469153642654
2023-01-22 13:00:08.035829: step: 418/466, loss: 0.0008414004696533084
2023-01-22 13:00:08.683491: step: 420/466, loss: 0.025465134531259537
2023-01-22 13:00:09.257176: step: 422/466, loss: 0.024259982630610466
2023-01-22 13:00:09.934273: step: 424/466, loss: 0.0021938399877399206
2023-01-22 13:00:10.534435: step: 426/466, loss: 0.07630009949207306
2023-01-22 13:00:11.164273: step: 428/466, loss: 0.012023454532027245
2023-01-22 13:00:11.766237: step: 430/466, loss: 0.0048853070475161076
2023-01-22 13:00:12.417009: step: 432/466, loss: 0.4136844277381897
2023-01-22 13:00:13.029362: step: 434/466, loss: 0.007623132783919573
2023-01-22 13:00:13.661515: step: 436/466, loss: 0.0607096329331398
2023-01-22 13:00:14.283331: step: 438/466, loss: 0.004217234905809164
2023-01-22 13:00:14.994085: step: 440/466, loss: 0.018126465380191803
2023-01-22 13:00:15.579170: step: 442/466, loss: 0.014559803530573845
2023-01-22 13:00:16.217420: step: 444/466, loss: 0.007691314909607172
2023-01-22 13:00:16.807858: step: 446/466, loss: 0.012965541332960129
2023-01-22 13:00:17.476297: step: 448/466, loss: 0.05624009296298027
2023-01-22 13:00:18.095634: step: 450/466, loss: 0.1598840355873108
2023-01-22 13:00:18.742193: step: 452/466, loss: 0.037264205515384674
2023-01-22 13:00:19.357050: step: 454/466, loss: 0.005337410140782595
2023-01-22 13:00:19.966549: step: 456/466, loss: 0.0020100458059459925
2023-01-22 13:00:20.503363: step: 458/466, loss: 0.023190123960375786
2023-01-22 13:00:21.088706: step: 460/466, loss: 0.005955295171588659
2023-01-22 13:00:21.710404: step: 462/466, loss: 0.05335367098450661
2023-01-22 13:00:22.228975: step: 464/466, loss: 0.022979112342000008
2023-01-22 13:00:22.922733: step: 466/466, loss: 0.01416210550814867
2023-01-22 13:00:23.537723: step: 468/466, loss: 0.03598571568727493
2023-01-22 13:00:24.169277: step: 470/466, loss: 0.03203276917338371
2023-01-22 13:00:24.827079: step: 472/466, loss: 0.07548796385526657
2023-01-22 13:00:25.483260: step: 474/466, loss: 0.01304719876497984
2023-01-22 13:00:26.091568: step: 476/466, loss: 0.0888737142086029
2023-01-22 13:00:26.665322: step: 478/466, loss: 0.15686488151550293
2023-01-22 13:00:27.323588: step: 480/466, loss: 0.030848558992147446
2023-01-22 13:00:27.981157: step: 482/466, loss: 0.02938656508922577
2023-01-22 13:00:28.565767: step: 484/466, loss: 0.017374135553836823
2023-01-22 13:00:29.178183: step: 486/466, loss: 0.008283546194434166
2023-01-22 13:00:29.795481: step: 488/466, loss: 0.03463687002658844
2023-01-22 13:00:30.512683: step: 490/466, loss: 0.0263261366635561
2023-01-22 13:00:31.178707: step: 492/466, loss: 0.057920608669519424
2023-01-22 13:00:31.743859: step: 494/466, loss: 0.0033012954518198967
2023-01-22 13:00:32.379871: step: 496/466, loss: 0.03663906827569008
2023-01-22 13:00:32.964775: step: 498/466, loss: 0.0053479028865695
2023-01-22 13:00:33.607864: step: 500/466, loss: 0.16667911410331726
2023-01-22 13:00:34.231976: step: 502/466, loss: 0.040800731629133224
2023-01-22 13:00:34.848026: step: 504/466, loss: 0.008014737628400326
2023-01-22 13:00:35.467074: step: 506/466, loss: 0.045118384063243866
2023-01-22 13:00:36.095316: step: 508/466, loss: 0.05529142916202545
2023-01-22 13:00:36.749255: step: 510/466, loss: 0.05914291366934776
2023-01-22 13:00:37.402787: step: 512/466, loss: 0.09540831297636032
2023-01-22 13:00:37.973176: step: 514/466, loss: 0.0009840897982940078
2023-01-22 13:00:38.629465: step: 516/466, loss: 0.061920154839754105
2023-01-22 13:00:39.213411: step: 518/466, loss: 0.029298361390829086
2023-01-22 13:00:39.826865: step: 520/466, loss: 0.08342516422271729
2023-01-22 13:00:40.505669: step: 522/466, loss: 0.5614947080612183
2023-01-22 13:00:41.124317: step: 524/466, loss: 0.005597488954663277
2023-01-22 13:00:41.736957: step: 526/466, loss: 0.014806962572038174
2023-01-22 13:00:42.360290: step: 528/466, loss: 0.0023010680451989174
2023-01-22 13:00:42.915026: step: 530/466, loss: 0.033632270991802216
2023-01-22 13:00:43.571940: step: 532/466, loss: 0.0015359396347776055
2023-01-22 13:00:44.282647: step: 534/466, loss: 0.03112613968551159
2023-01-22 13:00:44.924681: step: 536/466, loss: 0.009359101764857769
2023-01-22 13:00:45.508970: step: 538/466, loss: 0.0030481473077088594
2023-01-22 13:00:46.071115: step: 540/466, loss: 0.004858879372477531
2023-01-22 13:00:46.694985: step: 542/466, loss: 0.006360383238643408
2023-01-22 13:00:47.317128: step: 544/466, loss: 0.04065334051847458
2023-01-22 13:00:47.993852: step: 546/466, loss: 0.014170126989483833
2023-01-22 13:00:48.579554: step: 548/466, loss: 0.006495888810604811
2023-01-22 13:00:49.223923: step: 550/466, loss: 0.009829082526266575
2023-01-22 13:00:49.832794: step: 552/466, loss: 0.011651817709207535
2023-01-22 13:00:50.523109: step: 554/466, loss: 0.7188246846199036
2023-01-22 13:00:51.158682: step: 556/466, loss: 0.15502245724201202
2023-01-22 13:00:51.866980: step: 558/466, loss: 0.0001732190139591694
2023-01-22 13:00:52.470615: step: 560/466, loss: 0.19844211637973785
2023-01-22 13:00:53.118745: step: 562/466, loss: 0.06763464957475662
2023-01-22 13:00:53.739717: step: 564/466, loss: 0.06928513199090958
2023-01-22 13:00:54.368773: step: 566/466, loss: 0.013963966630399227
2023-01-22 13:00:55.065524: step: 568/466, loss: 0.07351906597614288
2023-01-22 13:00:55.683846: step: 570/466, loss: 0.22942838072776794
2023-01-22 13:00:56.279673: step: 572/466, loss: 0.011113603599369526
2023-01-22 13:00:56.875909: step: 574/466, loss: 0.003512877505272627
2023-01-22 13:00:57.487495: step: 576/466, loss: 0.044654857367277145
2023-01-22 13:00:58.091632: step: 578/466, loss: 0.008034838363528252
2023-01-22 13:00:58.806593: step: 580/466, loss: 0.8384864330291748
2023-01-22 13:00:59.446190: step: 582/466, loss: 0.007044475991278887
2023-01-22 13:01:00.011614: step: 584/466, loss: 0.06129581108689308
2023-01-22 13:01:00.626078: step: 586/466, loss: 0.009062034077942371
2023-01-22 13:01:01.218748: step: 588/466, loss: 0.05162311717867851
2023-01-22 13:01:01.824296: step: 590/466, loss: 0.000708371982909739
2023-01-22 13:01:02.413405: step: 592/466, loss: 0.03490292653441429
2023-01-22 13:01:03.035112: step: 594/466, loss: 0.025423798710107803
2023-01-22 13:01:03.681228: step: 596/466, loss: 0.00033729904680512846
2023-01-22 13:01:04.307775: step: 598/466, loss: 0.06699639558792114
2023-01-22 13:01:04.931741: step: 600/466, loss: 0.0021308648865669966
2023-01-22 13:01:05.483675: step: 602/466, loss: 0.003646919270977378
2023-01-22 13:01:06.115815: step: 604/466, loss: 0.02293245680630207
2023-01-22 13:01:06.768785: step: 606/466, loss: 0.013322302140295506
2023-01-22 13:01:07.448319: step: 608/466, loss: 0.043741822242736816
2023-01-22 13:01:08.065293: step: 610/466, loss: 0.0774562880396843
2023-01-22 13:01:08.700069: step: 612/466, loss: 0.0023809592239558697
2023-01-22 13:01:09.294473: step: 614/466, loss: 0.007703673094511032
2023-01-22 13:01:09.871417: step: 616/466, loss: 0.37894806265830994
2023-01-22 13:01:10.554744: step: 618/466, loss: 0.005944686941802502
2023-01-22 13:01:11.145830: step: 620/466, loss: 0.006991254631429911
2023-01-22 13:01:11.803167: step: 622/466, loss: 0.050385165959596634
2023-01-22 13:01:12.530945: step: 624/466, loss: 0.006400011014193296
2023-01-22 13:01:13.151359: step: 626/466, loss: 0.004842943046241999
2023-01-22 13:01:13.885886: step: 628/466, loss: 0.23291310667991638
2023-01-22 13:01:14.535354: step: 630/466, loss: 0.007940417155623436
2023-01-22 13:01:15.116618: step: 632/466, loss: 0.010347411036491394
2023-01-22 13:01:15.788489: step: 634/466, loss: 0.017035510390996933
2023-01-22 13:01:16.438448: step: 636/466, loss: 1.2720946073532104
2023-01-22 13:01:17.049536: step: 638/466, loss: 0.12251061201095581
2023-01-22 13:01:17.619596: step: 640/466, loss: 0.16059669852256775
2023-01-22 13:01:18.245515: step: 642/466, loss: 0.03878507763147354
2023-01-22 13:01:18.928902: step: 644/466, loss: 0.018028240650892258
2023-01-22 13:01:19.540299: step: 646/466, loss: 0.020756619051098824
2023-01-22 13:01:20.187266: step: 648/466, loss: 0.01615186780691147
2023-01-22 13:01:20.797616: step: 650/466, loss: 0.047810375690460205
2023-01-22 13:01:21.419686: step: 652/466, loss: 0.015006436966359615
2023-01-22 13:01:22.052983: step: 654/466, loss: 0.053115393966436386
2023-01-22 13:01:22.696859: step: 656/466, loss: 0.0799861028790474
2023-01-22 13:01:23.297344: step: 658/466, loss: 0.0006414179224520922
2023-01-22 13:01:23.904240: step: 660/466, loss: 0.02255016192793846
2023-01-22 13:01:24.553635: step: 662/466, loss: 0.04278068244457245
2023-01-22 13:01:25.246282: step: 664/466, loss: 0.0029859403148293495
2023-01-22 13:01:25.930674: step: 666/466, loss: 0.06284870207309723
2023-01-22 13:01:26.545560: step: 668/466, loss: 0.015784582123160362
2023-01-22 13:01:27.143785: step: 670/466, loss: 0.022132791578769684
2023-01-22 13:01:27.743476: step: 672/466, loss: 0.0014332809951156378
2023-01-22 13:01:28.386254: step: 674/466, loss: 0.03355376049876213
2023-01-22 13:01:28.996855: step: 676/466, loss: 0.031046321615576744
2023-01-22 13:01:29.627886: step: 678/466, loss: 0.02303227409720421
2023-01-22 13:01:30.211621: step: 680/466, loss: 0.014874064363539219
2023-01-22 13:01:30.792715: step: 682/466, loss: 0.012770193628966808
2023-01-22 13:01:31.407171: step: 684/466, loss: 0.6695691347122192
2023-01-22 13:01:32.023083: step: 686/466, loss: 0.010362708009779453
2023-01-22 13:01:32.735544: step: 688/466, loss: 0.02548399195075035
2023-01-22 13:01:33.389394: step: 690/466, loss: 0.0030976503621786833
2023-01-22 13:01:34.046792: step: 692/466, loss: 0.046513043344020844
2023-01-22 13:01:34.677861: step: 694/466, loss: 0.016862619668245316
2023-01-22 13:01:35.260647: step: 696/466, loss: 0.031665779650211334
2023-01-22 13:01:35.871813: step: 698/466, loss: 0.0098891481757164
2023-01-22 13:01:36.476843: step: 700/466, loss: 0.34672558307647705
2023-01-22 13:01:37.116153: step: 702/466, loss: 0.0001856032758951187
2023-01-22 13:01:37.725308: step: 704/466, loss: 0.020029060542583466
2023-01-22 13:01:38.377336: step: 706/466, loss: 0.0032362567726522684
2023-01-22 13:01:38.976210: step: 708/466, loss: 0.02074238285422325
2023-01-22 13:01:39.623836: step: 710/466, loss: 0.0448627769947052
2023-01-22 13:01:40.256007: step: 712/466, loss: 0.009725132025778294
2023-01-22 13:01:40.955524: step: 714/466, loss: 0.07118083536624908
2023-01-22 13:01:41.583966: step: 716/466, loss: 0.004004801157861948
2023-01-22 13:01:42.237593: step: 718/466, loss: 0.005218241363763809
2023-01-22 13:01:42.866602: step: 720/466, loss: 0.003216929268091917
2023-01-22 13:01:43.519123: step: 722/466, loss: 0.03918952867388725
2023-01-22 13:01:44.225941: step: 724/466, loss: 0.04884127900004387
2023-01-22 13:01:44.891534: step: 726/466, loss: 0.058916158974170685
2023-01-22 13:01:45.429303: step: 728/466, loss: 0.026085475459694862
2023-01-22 13:01:46.060052: step: 730/466, loss: 0.2417844980955124
2023-01-22 13:01:46.643942: step: 732/466, loss: 0.008069354109466076
2023-01-22 13:01:47.244149: step: 734/466, loss: 0.006184478756040335
2023-01-22 13:01:47.847055: step: 736/466, loss: 0.009322668425738811
2023-01-22 13:01:48.420075: step: 738/466, loss: 0.025292107835412025
2023-01-22 13:01:49.070268: step: 740/466, loss: 0.0015159074682742357
2023-01-22 13:01:49.712090: step: 742/466, loss: 0.1141427606344223
2023-01-22 13:01:50.389783: step: 744/466, loss: 0.0584435909986496
2023-01-22 13:01:51.052070: step: 746/466, loss: 0.030674343928694725
2023-01-22 13:01:51.685892: step: 748/466, loss: 0.03274570778012276
2023-01-22 13:01:52.313768: step: 750/466, loss: 0.05589473992586136
2023-01-22 13:01:52.920524: step: 752/466, loss: 0.014640445820987225
2023-01-22 13:01:53.573378: step: 754/466, loss: 0.010607525706291199
2023-01-22 13:01:54.144669: step: 756/466, loss: 0.004988064989447594
2023-01-22 13:01:54.757612: step: 758/466, loss: 0.024294689297676086
2023-01-22 13:01:55.381327: step: 760/466, loss: 0.0023869031574577093
2023-01-22 13:01:55.968775: step: 762/466, loss: 0.001264250953681767
2023-01-22 13:01:56.573199: step: 764/466, loss: 0.009330169297754765
2023-01-22 13:01:57.166067: step: 766/466, loss: 0.006431054789572954
2023-01-22 13:01:57.840782: step: 768/466, loss: 0.020721986889839172
2023-01-22 13:01:58.506672: step: 770/466, loss: 0.24625498056411743
2023-01-22 13:01:59.113120: step: 772/466, loss: 0.013136804103851318
2023-01-22 13:01:59.685845: step: 774/466, loss: 0.011591672897338867
2023-01-22 13:02:00.301874: step: 776/466, loss: 0.0027735396288335323
2023-01-22 13:02:00.940106: step: 778/466, loss: 0.04726502299308777
2023-01-22 13:02:01.574503: step: 780/466, loss: 0.3299539089202881
2023-01-22 13:02:02.225671: step: 782/466, loss: 0.024561433121562004
2023-01-22 13:02:02.743834: step: 784/466, loss: 0.019899209961295128
2023-01-22 13:02:03.365969: step: 786/466, loss: 0.037758611142635345
2023-01-22 13:02:03.964298: step: 788/466, loss: 0.022166717797517776
2023-01-22 13:02:04.597523: step: 790/466, loss: 0.8392122983932495
2023-01-22 13:02:05.257259: step: 792/466, loss: 0.014615439809858799
2023-01-22 13:02:05.881575: step: 794/466, loss: 0.0296429805457592
2023-01-22 13:02:06.508854: step: 796/466, loss: 0.019924568012356758
2023-01-22 13:02:07.095471: step: 798/466, loss: 0.0008745107334107161
2023-01-22 13:02:07.746945: step: 800/466, loss: 0.0896400511264801
2023-01-22 13:02:08.405291: step: 802/466, loss: 0.08619721978902817
2023-01-22 13:02:09.066632: step: 804/466, loss: 0.010402233339846134
2023-01-22 13:02:09.665900: step: 806/466, loss: 0.1356736570596695
2023-01-22 13:02:10.284533: step: 808/466, loss: 0.014810479246079922
2023-01-22 13:02:10.897477: step: 810/466, loss: 0.014135269448161125
2023-01-22 13:02:11.599416: step: 812/466, loss: 0.07043011486530304
2023-01-22 13:02:12.272639: step: 814/466, loss: 0.028513118624687195
2023-01-22 13:02:12.904971: step: 816/466, loss: 0.02211073786020279
2023-01-22 13:02:13.547477: step: 818/466, loss: 0.026882054284214973
2023-01-22 13:02:14.089472: step: 820/466, loss: 0.6213523745536804
2023-01-22 13:02:14.698291: step: 822/466, loss: 0.004070287104696035
2023-01-22 13:02:15.307070: step: 824/466, loss: 0.049383603036403656
2023-01-22 13:02:15.969742: step: 826/466, loss: 0.007738706190139055
2023-01-22 13:02:16.565926: step: 828/466, loss: 0.0017029495211318135
2023-01-22 13:02:17.162818: step: 830/466, loss: 0.20054680109024048
2023-01-22 13:02:17.816110: step: 832/466, loss: 0.019246773794293404
2023-01-22 13:02:18.489384: step: 834/466, loss: 0.01825520396232605
2023-01-22 13:02:19.083918: step: 836/466, loss: 0.012878013774752617
2023-01-22 13:02:19.709220: step: 838/466, loss: 0.009729273617267609
2023-01-22 13:02:20.319585: step: 840/466, loss: 0.026708990335464478
2023-01-22 13:02:21.004191: step: 842/466, loss: 0.004096888471394777
2023-01-22 13:02:21.548507: step: 844/466, loss: 0.0020870447624474764
2023-01-22 13:02:22.225427: step: 846/466, loss: 0.01970016583800316
2023-01-22 13:02:22.843455: step: 848/466, loss: 0.06840378046035767
2023-01-22 13:02:23.542171: step: 850/466, loss: 0.09377360343933105
2023-01-22 13:02:24.154240: step: 852/466, loss: 0.007807820104062557
2023-01-22 13:02:24.779165: step: 854/466, loss: 0.007622482255101204
2023-01-22 13:02:25.404757: step: 856/466, loss: 0.010054780170321465
2023-01-22 13:02:26.005951: step: 858/466, loss: 0.014251005835831165
2023-01-22 13:02:26.612877: step: 860/466, loss: 0.023616626858711243
2023-01-22 13:02:27.235807: step: 862/466, loss: 0.027740897610783577
2023-01-22 13:02:27.868506: step: 864/466, loss: 0.0004946734406985343
2023-01-22 13:02:28.484400: step: 866/466, loss: 0.027191264554858208
2023-01-22 13:02:29.111024: step: 868/466, loss: 0.0035628662444651127
2023-01-22 13:02:29.721289: step: 870/466, loss: 0.00571247236803174
2023-01-22 13:02:30.305848: step: 872/466, loss: 0.008461954072117805
2023-01-22 13:02:30.927903: step: 874/466, loss: 0.008066113106906414
2023-01-22 13:02:31.519978: step: 876/466, loss: 0.003854152048006654
2023-01-22 13:02:32.130279: step: 878/466, loss: 0.0005070980987511575
2023-01-22 13:02:32.761795: step: 880/466, loss: 0.03043699450790882
2023-01-22 13:02:33.419317: step: 882/466, loss: 0.028554614633321762
2023-01-22 13:02:34.019859: step: 884/466, loss: 0.04454214498400688
2023-01-22 13:02:34.633640: step: 886/466, loss: 0.017221003770828247
2023-01-22 13:02:35.284643: step: 888/466, loss: 0.01930846832692623
2023-01-22 13:02:35.920253: step: 890/466, loss: 0.011658270843327045
2023-01-22 13:02:36.473330: step: 892/466, loss: 0.0632919892668724
2023-01-22 13:02:37.060410: step: 894/466, loss: 0.0009290258749388158
2023-01-22 13:02:37.713989: step: 896/466, loss: 0.04633230343461037
2023-01-22 13:02:38.292918: step: 898/466, loss: 0.041435934603214264
2023-01-22 13:02:38.929292: step: 900/466, loss: 0.09117339551448822
2023-01-22 13:02:39.532398: step: 902/466, loss: 0.013194074854254723
2023-01-22 13:02:40.189387: step: 904/466, loss: 1.1540361642837524
2023-01-22 13:02:40.752294: step: 906/466, loss: 0.02288798615336418
2023-01-22 13:02:41.375793: step: 908/466, loss: 0.0001516256743343547
2023-01-22 13:02:42.007726: step: 910/466, loss: 0.019018512219190598
2023-01-22 13:02:42.608781: step: 912/466, loss: 0.028519008308649063
2023-01-22 13:02:43.197618: step: 914/466, loss: 0.016488952562212944
2023-01-22 13:02:43.791964: step: 916/466, loss: 0.04028515890240669
2023-01-22 13:02:44.409517: step: 918/466, loss: 0.11264704912900925
2023-01-22 13:02:45.010612: step: 920/466, loss: 0.09657475352287292
2023-01-22 13:02:45.656808: step: 922/466, loss: 0.0336512066423893
2023-01-22 13:02:46.262848: step: 924/466, loss: 0.024904528632760048
2023-01-22 13:02:46.943725: step: 926/466, loss: 0.0068472339771687984
2023-01-22 13:02:47.509778: step: 928/466, loss: 0.011571408249437809
2023-01-22 13:02:48.104617: step: 930/466, loss: 0.05737202242016792
2023-01-22 13:02:48.653130: step: 932/466, loss: 0.005660996772348881
==================================================
Loss: 0.064
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32890240400393833, 'r': 0.34575319130584786, 'f1': 0.3371173576654613}, 'combined': 0.24840226354297149, 'epoch': 27}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.33977480817632627, 'r': 0.288915819756786, 'f1': 0.3122881521542648}, 'combined': 0.19554491770407237, 'epoch': 27}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2847320925978047, 'r': 0.3490264360876315, 'f1': 0.31361795706424866}, 'combined': 0.23108691573155163, 'epoch': 27}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3434173660948191, 'r': 0.29692584541411254, 'f1': 0.31848386904050024}, 'combined': 0.21127147748231206, 'epoch': 27}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.284375, 'r': 0.325, 'f1': 0.30333333333333334}, 'combined': 0.20222222222222222, 'epoch': 27}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4117647058823529, 'r': 0.2413793103448276, 'f1': 0.3043478260869565}, 'combined': 0.20289855072463764, 'epoch': 27}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:05:34.808732: step: 2/466, loss: 0.023768384009599686
2023-01-22 13:05:35.527224: step: 4/466, loss: 0.03996489197015762
2023-01-22 13:05:36.147628: step: 6/466, loss: 0.004306620452553034
2023-01-22 13:05:36.791293: step: 8/466, loss: 0.010168182663619518
2023-01-22 13:05:37.391262: step: 10/466, loss: 0.006507258862257004
2023-01-22 13:05:38.024681: step: 12/466, loss: 0.011234902776777744
2023-01-22 13:05:38.587284: step: 14/466, loss: 0.03960973396897316
2023-01-22 13:05:39.326131: step: 16/466, loss: 0.014154575765132904
2023-01-22 13:05:39.956643: step: 18/466, loss: 0.018108831718564034
2023-01-22 13:05:40.585806: step: 20/466, loss: 0.023137645795941353
2023-01-22 13:05:41.202655: step: 22/466, loss: 0.06897438317537308
2023-01-22 13:05:41.931693: step: 24/466, loss: 0.03519696742296219
2023-01-22 13:05:42.573946: step: 26/466, loss: 0.014579772017896175
2023-01-22 13:05:43.205937: step: 28/466, loss: 0.037931300699710846
2023-01-22 13:05:43.784189: step: 30/466, loss: 0.0020180256105959415
2023-01-22 13:05:44.409812: step: 32/466, loss: 0.0680442526936531
2023-01-22 13:05:44.975203: step: 34/466, loss: 0.01798325590789318
2023-01-22 13:05:45.530330: step: 36/466, loss: 0.03565318137407303
2023-01-22 13:05:46.105087: step: 38/466, loss: 0.048264279961586
2023-01-22 13:05:46.683098: step: 40/466, loss: 0.03383226692676544
2023-01-22 13:05:47.273879: step: 42/466, loss: 0.00869852863252163
2023-01-22 13:05:47.875264: step: 44/466, loss: 0.011189626529812813
2023-01-22 13:05:48.517445: step: 46/466, loss: 0.03855552524328232
2023-01-22 13:05:49.130119: step: 48/466, loss: 0.0033748524729162455
2023-01-22 13:05:49.779480: step: 50/466, loss: 0.02395116351544857
2023-01-22 13:05:50.408081: step: 52/466, loss: 0.00631840992718935
2023-01-22 13:05:51.072862: step: 54/466, loss: 0.02578447014093399
2023-01-22 13:05:51.662545: step: 56/466, loss: 0.041704658418893814
2023-01-22 13:05:52.328962: step: 58/466, loss: 0.0032002837397158146
2023-01-22 13:05:52.940513: step: 60/466, loss: 0.10665503144264221
2023-01-22 13:05:53.567663: step: 62/466, loss: 0.00679376907646656
2023-01-22 13:05:54.119035: step: 64/466, loss: 0.016809426248073578
2023-01-22 13:05:54.769741: step: 66/466, loss: 0.026661166921257973
2023-01-22 13:05:55.423777: step: 68/466, loss: 0.08407910168170929
2023-01-22 13:05:55.993130: step: 70/466, loss: 0.04843861609697342
2023-01-22 13:05:56.590141: step: 72/466, loss: 0.03017924167215824
2023-01-22 13:05:57.223882: step: 74/466, loss: 0.015387943014502525
2023-01-22 13:05:57.888304: step: 76/466, loss: 0.0035162935964763165
2023-01-22 13:05:58.576725: step: 78/466, loss: 0.002334260381758213
2023-01-22 13:05:59.207789: step: 80/466, loss: 0.026451418176293373
2023-01-22 13:05:59.822367: step: 82/466, loss: 0.00722060352563858
2023-01-22 13:06:00.414075: step: 84/466, loss: 0.19554363191127777
2023-01-22 13:06:01.044906: step: 86/466, loss: 0.018334930762648582
2023-01-22 13:06:01.675967: step: 88/466, loss: 0.04861517250537872
2023-01-22 13:06:02.303131: step: 90/466, loss: 0.029225613921880722
2023-01-22 13:06:02.864062: step: 92/466, loss: 0.015543647110462189
2023-01-22 13:06:03.508600: step: 94/466, loss: 0.04949422925710678
2023-01-22 13:06:04.109636: step: 96/466, loss: 0.09246551990509033
2023-01-22 13:06:04.773238: step: 98/466, loss: 0.25158873200416565
2023-01-22 13:06:05.423865: step: 100/466, loss: 0.014198623597621918
2023-01-22 13:06:06.048633: step: 102/466, loss: 0.022452840581536293
2023-01-22 13:06:06.699894: step: 104/466, loss: 0.016129590570926666
2023-01-22 13:06:07.272811: step: 106/466, loss: 0.0017111928900703788
2023-01-22 13:06:07.935717: step: 108/466, loss: 0.0237188171595335
2023-01-22 13:06:08.495659: step: 110/466, loss: 0.0030442920979112387
2023-01-22 13:06:09.208167: step: 112/466, loss: 0.02442362532019615
2023-01-22 13:06:09.831588: step: 114/466, loss: 0.004675176925957203
2023-01-22 13:06:10.454769: step: 116/466, loss: 0.02758142165839672
2023-01-22 13:06:11.066031: step: 118/466, loss: 0.0414704754948616
2023-01-22 13:06:11.730946: step: 120/466, loss: 0.015966974198818207
2023-01-22 13:06:12.376926: step: 122/466, loss: 0.005912418011575937
2023-01-22 13:06:13.022751: step: 124/466, loss: 0.10807689279317856
2023-01-22 13:06:13.660059: step: 126/466, loss: 0.025736931711435318
2023-01-22 13:06:14.325459: step: 128/466, loss: 0.025900406762957573
2023-01-22 13:06:14.932128: step: 130/466, loss: 0.03595322370529175
2023-01-22 13:06:15.519614: step: 132/466, loss: 0.028274891898036003
2023-01-22 13:06:16.113136: step: 134/466, loss: 0.018205879256129265
2023-01-22 13:06:16.787608: step: 136/466, loss: 0.05391043797135353
2023-01-22 13:06:17.391582: step: 138/466, loss: 0.005010449793189764
2023-01-22 13:06:18.001224: step: 140/466, loss: 0.023384299129247665
2023-01-22 13:06:18.623318: step: 142/466, loss: 0.34657207131385803
2023-01-22 13:06:19.261141: step: 144/466, loss: 0.008673430420458317
2023-01-22 13:06:19.995882: step: 146/466, loss: 0.010439866222441196
2023-01-22 13:06:20.603434: step: 148/466, loss: 0.07247832417488098
2023-01-22 13:06:21.242560: step: 150/466, loss: 0.007264253217726946
2023-01-22 13:06:21.862070: step: 152/466, loss: 0.0024536659475415945
2023-01-22 13:06:22.479120: step: 154/466, loss: 0.05248751863837242
2023-01-22 13:06:23.050167: step: 156/466, loss: 0.03346743807196617
2023-01-22 13:06:23.697639: step: 158/466, loss: 0.0344766303896904
2023-01-22 13:06:24.344657: step: 160/466, loss: 0.057996924966573715
2023-01-22 13:06:24.923926: step: 162/466, loss: 0.0343867689371109
2023-01-22 13:06:25.573269: step: 164/466, loss: 0.010756413452327251
2023-01-22 13:06:26.278156: step: 166/466, loss: 0.01722462847828865
2023-01-22 13:06:26.863642: step: 168/466, loss: 0.02536899968981743
2023-01-22 13:06:27.434566: step: 170/466, loss: 0.014726881869137287
2023-01-22 13:06:28.053299: step: 172/466, loss: 0.003492683405056596
2023-01-22 13:06:28.703605: step: 174/466, loss: 0.010319219902157784
2023-01-22 13:06:29.309421: step: 176/466, loss: 0.001274162670597434
2023-01-22 13:06:29.907425: step: 178/466, loss: 0.05954611673951149
2023-01-22 13:06:30.540695: step: 180/466, loss: 0.010346210561692715
2023-01-22 13:06:31.209359: step: 182/466, loss: 0.041230689734220505
2023-01-22 13:06:31.851808: step: 184/466, loss: 0.01227517332881689
2023-01-22 13:06:32.390430: step: 186/466, loss: 0.0498775951564312
2023-01-22 13:06:33.043174: step: 188/466, loss: 0.020214635878801346
2023-01-22 13:06:33.644297: step: 190/466, loss: 0.02066658064723015
2023-01-22 13:06:34.274694: step: 192/466, loss: 0.013288436457514763
2023-01-22 13:06:34.900160: step: 194/466, loss: 0.03310953825712204
2023-01-22 13:06:35.499216: step: 196/466, loss: 0.0349651537835598
2023-01-22 13:06:36.187149: step: 198/466, loss: 0.264168918132782
2023-01-22 13:06:36.755013: step: 200/466, loss: 0.017585033550858498
2023-01-22 13:06:37.325706: step: 202/466, loss: 0.01101447269320488
2023-01-22 13:06:38.014819: step: 204/466, loss: 0.0085613913834095
2023-01-22 13:06:38.644020: step: 206/466, loss: 0.0034275949001312256
2023-01-22 13:06:39.159402: step: 208/466, loss: 0.0016740479040890932
2023-01-22 13:06:39.812110: step: 210/466, loss: 0.004394230432808399
2023-01-22 13:06:40.358137: step: 212/466, loss: 0.006876669824123383
2023-01-22 13:06:40.987249: step: 214/466, loss: 0.0018812270136550069
2023-01-22 13:06:41.535831: step: 216/466, loss: 0.00029821597854606807
2023-01-22 13:06:42.194248: step: 218/466, loss: 0.002942908788099885
2023-01-22 13:06:42.748892: step: 220/466, loss: 0.024115046486258507
2023-01-22 13:06:43.371275: step: 222/466, loss: 0.017866337671875954
2023-01-22 13:06:43.925214: step: 224/466, loss: 0.02098376490175724
2023-01-22 13:06:44.588091: step: 226/466, loss: 0.023650728166103363
2023-01-22 13:06:45.216288: step: 228/466, loss: 0.024871397763490677
2023-01-22 13:06:45.859485: step: 230/466, loss: 0.02011144533753395
2023-01-22 13:06:46.499454: step: 232/466, loss: 0.0009520826861262321
2023-01-22 13:06:47.102335: step: 234/466, loss: 0.00101017439737916
2023-01-22 13:06:47.680766: step: 236/466, loss: 0.03736605867743492
2023-01-22 13:06:48.275092: step: 238/466, loss: 0.000858426617924124
2023-01-22 13:06:48.882953: step: 240/466, loss: 0.055236946791410446
2023-01-22 13:06:49.568080: step: 242/466, loss: 0.0015216044848784804
2023-01-22 13:06:50.169933: step: 244/466, loss: 0.024074794724583626
2023-01-22 13:06:50.725569: step: 246/466, loss: 0.009139341302216053
2023-01-22 13:06:51.374512: step: 248/466, loss: 0.002656628843396902
2023-01-22 13:06:51.971215: step: 250/466, loss: 0.029650507494807243
2023-01-22 13:06:52.587172: step: 252/466, loss: 0.05830903723835945
2023-01-22 13:06:53.160451: step: 254/466, loss: 0.014021525159478188
2023-01-22 13:06:53.761512: step: 256/466, loss: 0.3828524351119995
2023-01-22 13:06:54.373474: step: 258/466, loss: 0.043327976018190384
2023-01-22 13:06:55.006896: step: 260/466, loss: 0.0033573047257959843
2023-01-22 13:06:55.696193: step: 262/466, loss: 0.004619850777089596
2023-01-22 13:06:56.262238: step: 264/466, loss: 0.08685749024152756
2023-01-22 13:06:56.882368: step: 266/466, loss: 0.01593833789229393
2023-01-22 13:06:57.522365: step: 268/466, loss: 0.036680977791547775
2023-01-22 13:06:58.132550: step: 270/466, loss: 0.0330805778503418
2023-01-22 13:06:58.743534: step: 272/466, loss: 0.007293290924280882
2023-01-22 13:06:59.395636: step: 274/466, loss: 0.047484152019023895
2023-01-22 13:06:59.997766: step: 276/466, loss: 0.351840078830719
2023-01-22 13:07:00.566872: step: 278/466, loss: 0.00860503874719143
2023-01-22 13:07:01.189994: step: 280/466, loss: 0.1977149099111557
2023-01-22 13:07:01.742794: step: 282/466, loss: 0.10114485025405884
2023-01-22 13:07:02.365557: step: 284/466, loss: 0.08704552054405212
2023-01-22 13:07:02.945377: step: 286/466, loss: 0.5295833349227905
2023-01-22 13:07:03.547651: step: 288/466, loss: 0.010039645247161388
2023-01-22 13:07:04.118595: step: 290/466, loss: 0.0005082232528366148
2023-01-22 13:07:04.724873: step: 292/466, loss: 0.008479979820549488
2023-01-22 13:07:05.313884: step: 294/466, loss: 3.3063900470733643
2023-01-22 13:07:05.941096: step: 296/466, loss: 0.019657650962471962
2023-01-22 13:07:06.558098: step: 298/466, loss: 0.026188286021351814
2023-01-22 13:07:07.132892: step: 300/466, loss: 0.010561192408204079
2023-01-22 13:07:07.780453: step: 302/466, loss: 0.010517285205423832
2023-01-22 13:07:08.401182: step: 304/466, loss: 0.011019128374755383
2023-01-22 13:07:08.997787: step: 306/466, loss: 0.008257926441729069
2023-01-22 13:07:09.634575: step: 308/466, loss: 0.014237681403756142
2023-01-22 13:07:10.254714: step: 310/466, loss: 0.031133001670241356
2023-01-22 13:07:10.949129: step: 312/466, loss: 0.00708776293322444
2023-01-22 13:07:11.555431: step: 314/466, loss: 0.02494877204298973
2023-01-22 13:07:12.172250: step: 316/466, loss: 0.025167588144540787
2023-01-22 13:07:12.820711: step: 318/466, loss: 0.002418582094833255
2023-01-22 13:07:13.448194: step: 320/466, loss: 0.06174202635884285
2023-01-22 13:07:14.024284: step: 322/466, loss: 0.12775883078575134
2023-01-22 13:07:14.755356: step: 324/466, loss: 0.019592782482504845
2023-01-22 13:07:15.491126: step: 326/466, loss: 0.010396583937108517
2023-01-22 13:07:16.100432: step: 328/466, loss: 0.013660160824656487
2023-01-22 13:07:16.763759: step: 330/466, loss: 0.037008270621299744
2023-01-22 13:07:17.344289: step: 332/466, loss: 0.005264009814709425
2023-01-22 13:07:17.970183: step: 334/466, loss: 2.1258628368377686
2023-01-22 13:07:18.591257: step: 336/466, loss: 0.0020432898309081793
2023-01-22 13:07:19.219959: step: 338/466, loss: 0.8654299974441528
2023-01-22 13:07:19.819673: step: 340/466, loss: 0.015576314181089401
2023-01-22 13:07:20.396608: step: 342/466, loss: 0.0017202608287334442
2023-01-22 13:07:21.020639: step: 344/466, loss: 0.015618101693689823
2023-01-22 13:07:21.629901: step: 346/466, loss: 0.22508034110069275
2023-01-22 13:07:22.247782: step: 348/466, loss: 0.038267288357019424
2023-01-22 13:07:22.872024: step: 350/466, loss: 0.03531248867511749
2023-01-22 13:07:23.521117: step: 352/466, loss: 0.01732778176665306
2023-01-22 13:07:24.156217: step: 354/466, loss: 0.033080875873565674
2023-01-22 13:07:24.863202: step: 356/466, loss: 0.01420635636895895
2023-01-22 13:07:25.484517: step: 358/466, loss: 0.0015354438219219446
2023-01-22 13:07:26.062767: step: 360/466, loss: 0.028320256620645523
2023-01-22 13:07:26.638504: step: 362/466, loss: 0.002205535303801298
2023-01-22 13:07:27.203711: step: 364/466, loss: 0.009863844141364098
2023-01-22 13:07:27.802779: step: 366/466, loss: 26.99533462524414
2023-01-22 13:07:28.391466: step: 368/466, loss: 0.0035730074159801006
2023-01-22 13:07:29.027092: step: 370/466, loss: 0.025294972583651543
2023-01-22 13:07:29.627270: step: 372/466, loss: 0.014734728261828423
2023-01-22 13:07:30.211963: step: 374/466, loss: 0.0021246871910989285
2023-01-22 13:07:31.040838: step: 376/466, loss: 0.005827118642628193
2023-01-22 13:07:31.618161: step: 378/466, loss: 0.012958161532878876
2023-01-22 13:07:32.189616: step: 380/466, loss: 0.037231847643852234
2023-01-22 13:07:32.791643: step: 382/466, loss: 0.021039549261331558
2023-01-22 13:07:33.428469: step: 384/466, loss: 0.006525214295834303
2023-01-22 13:07:34.075492: step: 386/466, loss: 0.08137285709381104
2023-01-22 13:07:34.674293: step: 388/466, loss: 0.007886284962296486
2023-01-22 13:07:35.238911: step: 390/466, loss: 0.002167411847040057
2023-01-22 13:07:35.819243: step: 392/466, loss: 0.011483059264719486
2023-01-22 13:07:36.406496: step: 394/466, loss: 0.0016958725173026323
2023-01-22 13:07:37.012736: step: 396/466, loss: 0.07811151444911957
2023-01-22 13:07:37.610240: step: 398/466, loss: 0.04621563106775284
2023-01-22 13:07:38.201787: step: 400/466, loss: 0.026535989716649055
2023-01-22 13:07:38.830580: step: 402/466, loss: 0.007337826769798994
2023-01-22 13:07:39.341563: step: 404/466, loss: 0.0006064106128178537
2023-01-22 13:07:39.966482: step: 406/466, loss: 0.09214655309915543
2023-01-22 13:07:40.575878: step: 408/466, loss: 0.0458175353705883
2023-01-22 13:07:41.095061: step: 410/466, loss: 0.019851980730891228
2023-01-22 13:07:41.731024: step: 412/466, loss: 0.03482075780630112
2023-01-22 13:07:42.386256: step: 414/466, loss: 0.023295555263757706
2023-01-22 13:07:42.978143: step: 416/466, loss: 0.0010975089389830828
2023-01-22 13:07:43.597287: step: 418/466, loss: 0.010821403004229069
2023-01-22 13:07:44.232430: step: 420/466, loss: 0.024789204820990562
2023-01-22 13:07:44.913966: step: 422/466, loss: 0.0259927399456501
2023-01-22 13:07:45.468095: step: 424/466, loss: 0.009154855273663998
2023-01-22 13:07:46.096498: step: 426/466, loss: 0.09827637672424316
2023-01-22 13:07:46.692757: step: 428/466, loss: 0.019148392602801323
2023-01-22 13:07:47.344365: step: 430/466, loss: 0.02102496474981308
2023-01-22 13:07:47.904949: step: 432/466, loss: 0.002071237191557884
2023-01-22 13:07:48.505886: step: 434/466, loss: 0.005694160703569651
2023-01-22 13:07:49.194739: step: 436/466, loss: 0.011221546679735184
2023-01-22 13:07:49.803020: step: 438/466, loss: 0.043992385268211365
2023-01-22 13:07:50.439234: step: 440/466, loss: 0.05732232332229614
2023-01-22 13:07:51.025449: step: 442/466, loss: 0.01635921187698841
2023-01-22 13:07:51.626338: step: 444/466, loss: 0.009666459634900093
2023-01-22 13:07:52.307530: step: 446/466, loss: 0.05570024624466896
2023-01-22 13:07:52.874702: step: 448/466, loss: 0.05164948105812073
2023-01-22 13:07:53.468671: step: 450/466, loss: 0.02679915726184845
2023-01-22 13:07:54.148440: step: 452/466, loss: 0.024820327758789062
2023-01-22 13:07:54.752288: step: 454/466, loss: 0.006560258101671934
2023-01-22 13:07:55.505732: step: 456/466, loss: 0.22647497057914734
2023-01-22 13:07:56.153098: step: 458/466, loss: 0.0020619293209165335
2023-01-22 13:07:56.795202: step: 460/466, loss: 0.044577330350875854
2023-01-22 13:07:57.429180: step: 462/466, loss: 0.04522687941789627
2023-01-22 13:07:58.022739: step: 464/466, loss: 0.02234252355992794
2023-01-22 13:07:58.633214: step: 466/466, loss: 0.023085763677954674
2023-01-22 13:07:59.320158: step: 468/466, loss: 0.012092499993741512
2023-01-22 13:07:59.931871: step: 470/466, loss: 0.00947714876383543
2023-01-22 13:08:00.544515: step: 472/466, loss: 0.0202737245708704
2023-01-22 13:08:01.127223: step: 474/466, loss: 0.22844865918159485
2023-01-22 13:08:01.727277: step: 476/466, loss: 0.007046691607683897
2023-01-22 13:08:02.335782: step: 478/466, loss: 0.014844018965959549
2023-01-22 13:08:02.973178: step: 480/466, loss: 0.11203937977552414
2023-01-22 13:08:03.613926: step: 482/466, loss: 0.0071283141151070595
2023-01-22 13:08:04.256887: step: 484/466, loss: 0.012620110996067524
2023-01-22 13:08:04.907593: step: 486/466, loss: 0.0929551050066948
2023-01-22 13:08:05.508162: step: 488/466, loss: 0.020535800606012344
2023-01-22 13:08:06.069246: step: 490/466, loss: 0.03097878210246563
2023-01-22 13:08:06.669027: step: 492/466, loss: 0.14330974221229553
2023-01-22 13:08:07.315756: step: 494/466, loss: 0.028692664578557014
2023-01-22 13:08:07.941073: step: 496/466, loss: 0.0004861719498876482
2023-01-22 13:08:08.586699: step: 498/466, loss: 0.048825427889823914
2023-01-22 13:08:09.233687: step: 500/466, loss: 0.17499829828739166
2023-01-22 13:08:09.812612: step: 502/466, loss: 0.017115101218223572
2023-01-22 13:08:10.425173: step: 504/466, loss: 0.04524501413106918
2023-01-22 13:08:11.054746: step: 506/466, loss: 0.03364171087741852
2023-01-22 13:08:11.707132: step: 508/466, loss: 0.03208279609680176
2023-01-22 13:08:12.361928: step: 510/466, loss: 0.023519242182374
2023-01-22 13:08:12.968824: step: 512/466, loss: 0.007820955477654934
2023-01-22 13:08:13.588787: step: 514/466, loss: 0.004060547798871994
2023-01-22 13:08:14.192274: step: 516/466, loss: 0.00632070004940033
2023-01-22 13:08:14.897997: step: 518/466, loss: 0.02671051397919655
2023-01-22 13:08:15.523145: step: 520/466, loss: 0.018239395692944527
2023-01-22 13:08:16.078960: step: 522/466, loss: 0.019363006576895714
2023-01-22 13:08:16.843522: step: 524/466, loss: 0.7857245206832886
2023-01-22 13:08:17.422168: step: 526/466, loss: 0.004246650729328394
2023-01-22 13:08:17.968475: step: 528/466, loss: 0.007724442519247532
2023-01-22 13:08:18.544789: step: 530/466, loss: 0.2277851402759552
2023-01-22 13:08:19.139097: step: 532/466, loss: 0.02044188231229782
2023-01-22 13:08:19.764013: step: 534/466, loss: 0.02166859433054924
2023-01-22 13:08:20.431437: step: 536/466, loss: 0.0062633054330945015
2023-01-22 13:08:21.116371: step: 538/466, loss: 0.08236105740070343
2023-01-22 13:08:21.677893: step: 540/466, loss: 0.1476522982120514
2023-01-22 13:08:22.340898: step: 542/466, loss: 0.004284419119358063
2023-01-22 13:08:22.965816: step: 544/466, loss: 0.011481350287795067
2023-01-22 13:08:23.574860: step: 546/466, loss: 0.0007513607270084321
2023-01-22 13:08:24.174055: step: 548/466, loss: 0.0015099295414984226
2023-01-22 13:08:24.799278: step: 550/466, loss: 0.0057240622118115425
2023-01-22 13:08:25.388555: step: 552/466, loss: 0.05477767065167427
2023-01-22 13:08:26.016333: step: 554/466, loss: 0.019141511991620064
2023-01-22 13:08:26.711943: step: 556/466, loss: 0.11399663239717484
2023-01-22 13:08:27.321107: step: 558/466, loss: 0.02359907701611519
2023-01-22 13:08:27.961192: step: 560/466, loss: 0.04549015685915947
2023-01-22 13:08:28.574026: step: 562/466, loss: 0.0032001808285713196
2023-01-22 13:08:29.206699: step: 564/466, loss: 0.03296215459704399
2023-01-22 13:08:29.807954: step: 566/466, loss: 0.032535843551158905
2023-01-22 13:08:30.359746: step: 568/466, loss: 0.02791605144739151
2023-01-22 13:08:30.998763: step: 570/466, loss: 0.009045847691595554
2023-01-22 13:08:31.587323: step: 572/466, loss: 0.03438599035143852
2023-01-22 13:08:32.182834: step: 574/466, loss: 0.17986418306827545
2023-01-22 13:08:32.800214: step: 576/466, loss: 0.017250701785087585
2023-01-22 13:08:33.413115: step: 578/466, loss: 0.03292156755924225
2023-01-22 13:08:34.014699: step: 580/466, loss: 0.0006128060049377382
2023-01-22 13:08:34.601631: step: 582/466, loss: 0.005637643858790398
2023-01-22 13:08:35.274202: step: 584/466, loss: 0.013439452275633812
2023-01-22 13:08:35.881129: step: 586/466, loss: 0.00701222475618124
2023-01-22 13:08:36.458170: step: 588/466, loss: 0.030753254890441895
2023-01-22 13:08:37.095478: step: 590/466, loss: 0.046054352074861526
2023-01-22 13:08:37.782505: step: 592/466, loss: 0.1185753121972084
2023-01-22 13:08:38.360071: step: 594/466, loss: 0.048997662961483
2023-01-22 13:08:39.020073: step: 596/466, loss: 0.08898276090621948
2023-01-22 13:08:39.681222: step: 598/466, loss: 0.03522208705544472
2023-01-22 13:08:40.230885: step: 600/466, loss: 0.00015154962602537125
2023-01-22 13:08:40.803750: step: 602/466, loss: 0.0046302746050059795
2023-01-22 13:08:41.414456: step: 604/466, loss: 0.22859686613082886
2023-01-22 13:08:42.089235: step: 606/466, loss: 0.04483726620674133
2023-01-22 13:08:42.721152: step: 608/466, loss: 0.054383255541324615
2023-01-22 13:08:43.447639: step: 610/466, loss: 0.030266225337982178
2023-01-22 13:08:44.091940: step: 612/466, loss: 0.0004396865551825613
2023-01-22 13:08:44.702923: step: 614/466, loss: 0.004917386919260025
2023-01-22 13:08:45.355467: step: 616/466, loss: 0.017483513802289963
2023-01-22 13:08:45.983778: step: 618/466, loss: 0.006055546458810568
2023-01-22 13:08:46.600468: step: 620/466, loss: 0.02891460619866848
2023-01-22 13:08:47.338686: step: 622/466, loss: 0.09455475211143494
2023-01-22 13:08:47.939054: step: 624/466, loss: 0.054718174040317535
2023-01-22 13:08:48.557047: step: 626/466, loss: 0.03614216297864914
2023-01-22 13:08:49.209945: step: 628/466, loss: 0.05073446035385132
2023-01-22 13:08:49.789202: step: 630/466, loss: 0.0009193853475153446
2023-01-22 13:08:50.445531: step: 632/466, loss: 0.11036810278892517
2023-01-22 13:08:51.080833: step: 634/466, loss: 0.004744046367704868
2023-01-22 13:08:51.710858: step: 636/466, loss: 0.06734267622232437
2023-01-22 13:08:52.333939: step: 638/466, loss: 0.04062696173787117
2023-01-22 13:08:52.937485: step: 640/466, loss: 0.02793099544942379
2023-01-22 13:08:53.555993: step: 642/466, loss: 0.0048840404488146305
2023-01-22 13:08:54.170596: step: 644/466, loss: 0.06036311760544777
2023-01-22 13:08:54.794133: step: 646/466, loss: 0.0007871698471717536
2023-01-22 13:08:55.425965: step: 648/466, loss: 0.04189624637365341
2023-01-22 13:08:56.030427: step: 650/466, loss: 0.007794898469001055
2023-01-22 13:08:56.587622: step: 652/466, loss: 0.007587234955281019
2023-01-22 13:08:57.144918: step: 654/466, loss: 0.003714426886290312
2023-01-22 13:08:57.851169: step: 656/466, loss: 0.045027803629636765
2023-01-22 13:08:58.532898: step: 658/466, loss: 0.02378426305949688
2023-01-22 13:08:59.177668: step: 660/466, loss: 0.010064369067549706
2023-01-22 13:08:59.781769: step: 662/466, loss: 0.05422085523605347
2023-01-22 13:09:00.361056: step: 664/466, loss: 0.0013482351787388325
2023-01-22 13:09:01.073099: step: 666/466, loss: 0.0004007349780295044
2023-01-22 13:09:01.695311: step: 668/466, loss: 0.3075380027294159
2023-01-22 13:09:02.246715: step: 670/466, loss: 0.02334265038371086
2023-01-22 13:09:02.840844: step: 672/466, loss: 0.2771427035331726
2023-01-22 13:09:03.474901: step: 674/466, loss: 0.011716392822563648
2023-01-22 13:09:04.078300: step: 676/466, loss: 0.0197080560028553
2023-01-22 13:09:04.725137: step: 678/466, loss: 0.0005337827606126666
2023-01-22 13:09:05.393438: step: 680/466, loss: 0.047744929790496826
2023-01-22 13:09:06.038493: step: 682/466, loss: 0.05141134187579155
2023-01-22 13:09:06.605465: step: 684/466, loss: 0.0003885963815264404
2023-01-22 13:09:07.243533: step: 686/466, loss: 0.046781327575445175
2023-01-22 13:09:07.893991: step: 688/466, loss: 0.03787783905863762
2023-01-22 13:09:08.503103: step: 690/466, loss: 0.02537960559129715
2023-01-22 13:09:09.066694: step: 692/466, loss: 0.007958278059959412
2023-01-22 13:09:09.706456: step: 694/466, loss: 0.057035181671381
2023-01-22 13:09:10.278195: step: 696/466, loss: 0.0502951443195343
2023-01-22 13:09:10.888475: step: 698/466, loss: 0.047478318214416504
2023-01-22 13:09:11.535121: step: 700/466, loss: 0.044125545769929886
2023-01-22 13:09:12.156123: step: 702/466, loss: 0.022803746163845062
2023-01-22 13:09:12.797260: step: 704/466, loss: 0.061728183180093765
2023-01-22 13:09:13.441209: step: 706/466, loss: 0.0735589861869812
2023-01-22 13:09:14.047097: step: 708/466, loss: 0.0005398796638473868
2023-01-22 13:09:14.644075: step: 710/466, loss: 0.019195714965462685
2023-01-22 13:09:15.284739: step: 712/466, loss: 0.014919676817953587
2023-01-22 13:09:15.935239: step: 714/466, loss: 0.10128084570169449
2023-01-22 13:09:16.581110: step: 716/466, loss: 0.007795746438205242
2023-01-22 13:09:17.208884: step: 718/466, loss: 0.0025721562560647726
2023-01-22 13:09:17.860170: step: 720/466, loss: 0.012760023586452007
2023-01-22 13:09:18.463218: step: 722/466, loss: 0.03245546668767929
2023-01-22 13:09:19.058128: step: 724/466, loss: 0.03983759135007858
2023-01-22 13:09:19.731849: step: 726/466, loss: 0.04096521437168121
2023-01-22 13:09:20.390644: step: 728/466, loss: 0.011798517778515816
2023-01-22 13:09:20.985594: step: 730/466, loss: 0.009669964201748371
2023-01-22 13:09:21.594776: step: 732/466, loss: 0.06284675002098083
2023-01-22 13:09:22.110877: step: 734/466, loss: 0.022310523316264153
2023-01-22 13:09:22.719975: step: 736/466, loss: 0.01860705018043518
2023-01-22 13:09:23.385813: step: 738/466, loss: 0.0030016773380339146
2023-01-22 13:09:24.021403: step: 740/466, loss: 0.04680800437927246
2023-01-22 13:09:24.628137: step: 742/466, loss: 0.026600049808621407
2023-01-22 13:09:25.256985: step: 744/466, loss: 0.06729486584663391
2023-01-22 13:09:25.835786: step: 746/466, loss: 0.049576953053474426
2023-01-22 13:09:26.464313: step: 748/466, loss: 0.0032886529807001352
2023-01-22 13:09:27.130088: step: 750/466, loss: 0.0006859523709863424
2023-01-22 13:09:27.793952: step: 752/466, loss: 0.04004330560564995
2023-01-22 13:09:28.452894: step: 754/466, loss: 0.03351690620183945
2023-01-22 13:09:29.127393: step: 756/466, loss: 0.001649754587560892
2023-01-22 13:09:29.776797: step: 758/466, loss: 0.3805055320262909
2023-01-22 13:09:30.502773: step: 760/466, loss: 0.011594302952289581
2023-01-22 13:09:31.129493: step: 762/466, loss: 0.014391475357115269
2023-01-22 13:09:31.753471: step: 764/466, loss: 0.033565498888492584
2023-01-22 13:09:32.381692: step: 766/466, loss: 0.07644869387149811
2023-01-22 13:09:32.996804: step: 768/466, loss: 0.006856882944703102
2023-01-22 13:09:33.625917: step: 770/466, loss: 0.005011100322008133
2023-01-22 13:09:34.192552: step: 772/466, loss: 0.04017748683691025
2023-01-22 13:09:34.824466: step: 774/466, loss: 0.05664641037583351
2023-01-22 13:09:35.480771: step: 776/466, loss: 0.009156241081655025
2023-01-22 13:09:36.114782: step: 778/466, loss: 0.0162956565618515
2023-01-22 13:09:36.720958: step: 780/466, loss: 0.024769090116024017
2023-01-22 13:09:37.385196: step: 782/466, loss: 0.0032476421911269426
2023-01-22 13:09:38.025243: step: 784/466, loss: 0.00945268850773573
2023-01-22 13:09:38.631125: step: 786/466, loss: 0.008953304961323738
2023-01-22 13:09:39.321914: step: 788/466, loss: 0.024789387360215187
2023-01-22 13:09:39.945291: step: 790/466, loss: 0.0331110954284668
2023-01-22 13:09:40.596286: step: 792/466, loss: 0.0029637941624969244
2023-01-22 13:09:41.190119: step: 794/466, loss: 0.003647434990853071
2023-01-22 13:09:41.783391: step: 796/466, loss: 0.01982322335243225
2023-01-22 13:09:42.475136: step: 798/466, loss: 0.03863897547125816
2023-01-22 13:09:43.101080: step: 800/466, loss: 0.033416006714105606
2023-01-22 13:09:43.728045: step: 802/466, loss: 0.013230291195213795
2023-01-22 13:09:44.381918: step: 804/466, loss: 0.03807089850306511
2023-01-22 13:09:45.008951: step: 806/466, loss: 0.036580026149749756
2023-01-22 13:09:45.609823: step: 808/466, loss: 0.0015028535854071379
2023-01-22 13:09:46.351613: step: 810/466, loss: 0.0039765858091413975
2023-01-22 13:09:47.086511: step: 812/466, loss: 0.04079240560531616
2023-01-22 13:09:47.738747: step: 814/466, loss: 0.001219570985995233
2023-01-22 13:09:48.360614: step: 816/466, loss: 0.0005592587986029685
2023-01-22 13:09:48.962450: step: 818/466, loss: 0.007907913997769356
2023-01-22 13:09:49.558831: step: 820/466, loss: 0.04388028383255005
2023-01-22 13:09:50.165383: step: 822/466, loss: 0.018512558192014694
2023-01-22 13:09:50.811477: step: 824/466, loss: 0.019101902842521667
2023-01-22 13:09:51.391627: step: 826/466, loss: 0.0003036137786693871
2023-01-22 13:09:52.045786: step: 828/466, loss: 0.013605811633169651
2023-01-22 13:09:52.681817: step: 830/466, loss: 0.0007750964141450822
2023-01-22 13:09:53.268829: step: 832/466, loss: 0.0010865015210583806
2023-01-22 13:09:53.872404: step: 834/466, loss: 1.5557219982147217
2023-01-22 13:09:54.505645: step: 836/466, loss: 0.028510933741927147
2023-01-22 13:09:55.139716: step: 838/466, loss: 0.013181239366531372
2023-01-22 13:09:55.824526: step: 840/466, loss: 0.007881629280745983
2023-01-22 13:09:56.484580: step: 842/466, loss: 0.5158827900886536
2023-01-22 13:09:57.055284: step: 844/466, loss: 0.060511622577905655
2023-01-22 13:09:57.655242: step: 846/466, loss: 0.029197819530963898
2023-01-22 13:09:58.328057: step: 848/466, loss: 0.0028440975584089756
2023-01-22 13:09:58.910477: step: 850/466, loss: 0.012721743434667587
2023-01-22 13:09:59.562241: step: 852/466, loss: 0.013813858851790428
2023-01-22 13:10:00.203366: step: 854/466, loss: 0.017976820468902588
2023-01-22 13:10:00.819590: step: 856/466, loss: 0.028403783217072487
2023-01-22 13:10:01.445338: step: 858/466, loss: 0.0016109542921185493
2023-01-22 13:10:02.095128: step: 860/466, loss: 0.03347580134868622
2023-01-22 13:10:02.837170: step: 862/466, loss: 0.2174401581287384
2023-01-22 13:10:03.449814: step: 864/466, loss: 0.01822667010128498
2023-01-22 13:10:04.030780: step: 866/466, loss: 0.45253312587738037
2023-01-22 13:10:04.678913: step: 868/466, loss: 0.013842754065990448
2023-01-22 13:10:05.252777: step: 870/466, loss: 0.01675495132803917
2023-01-22 13:10:05.910993: step: 872/466, loss: 0.002902305917814374
2023-01-22 13:10:06.541679: step: 874/466, loss: 0.08422892540693283
2023-01-22 13:10:07.185940: step: 876/466, loss: 0.01864977739751339
2023-01-22 13:10:07.810822: step: 878/466, loss: 0.06614600867033005
2023-01-22 13:10:08.430801: step: 880/466, loss: 0.06060094013810158
2023-01-22 13:10:09.062465: step: 882/466, loss: 0.12300093472003937
2023-01-22 13:10:09.689828: step: 884/466, loss: 0.05484561249613762
2023-01-22 13:10:10.257971: step: 886/466, loss: 0.00846915040165186
2023-01-22 13:10:10.849810: step: 888/466, loss: 0.024216674268245697
2023-01-22 13:10:11.436269: step: 890/466, loss: 0.02085905335843563
2023-01-22 13:10:12.096159: step: 892/466, loss: 0.05968824401497841
2023-01-22 13:10:12.721968: step: 894/466, loss: 0.0692824274301529
2023-01-22 13:10:13.261069: step: 896/466, loss: 0.0036277940962463617
2023-01-22 13:10:13.984167: step: 898/466, loss: 0.022601688280701637
2023-01-22 13:10:14.632782: step: 900/466, loss: 0.018142150714993477
2023-01-22 13:10:15.223229: step: 902/466, loss: 0.033256981521844864
2023-01-22 13:10:15.835195: step: 904/466, loss: 0.341894268989563
2023-01-22 13:10:16.482799: step: 906/466, loss: 0.023613912984728813
2023-01-22 13:10:17.079570: step: 908/466, loss: 0.013277239166200161
2023-01-22 13:10:17.682589: step: 910/466, loss: 0.05817018076777458
2023-01-22 13:10:18.317084: step: 912/466, loss: 0.008494351990520954
2023-01-22 13:10:18.921222: step: 914/466, loss: 0.01082751527428627
2023-01-22 13:10:19.472762: step: 916/466, loss: 0.040563251823186874
2023-01-22 13:10:20.136605: step: 918/466, loss: 0.02546183206140995
2023-01-22 13:10:20.767773: step: 920/466, loss: 0.041106607764959335
2023-01-22 13:10:21.364023: step: 922/466, loss: 0.021582873538136482
2023-01-22 13:10:21.976643: step: 924/466, loss: 0.028529338538646698
2023-01-22 13:10:22.623659: step: 926/466, loss: 0.0011957907117903233
2023-01-22 13:10:23.273900: step: 928/466, loss: 0.02395629696547985
2023-01-22 13:10:23.880674: step: 930/466, loss: 0.019546261057257652
2023-01-22 13:10:24.515231: step: 932/466, loss: 0.21111570298671722
==================================================
Loss: 0.116
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3113965114322982, 'r': 0.34684962468834735, 'f1': 0.3281683163568385}, 'combined': 0.2418082331050389, 'epoch': 28}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3264085693798479, 'r': 0.2983969938684789, 'f1': 0.3117748675907561}, 'combined': 0.19522351522038003, 'epoch': 28}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2897886283011431, 'r': 0.3546748866304313, 'f1': 0.31896529906866433}, 'combined': 0.2350270624716474, 'epoch': 28}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.33432852553078485, 'r': 0.3116979845426902, 'f1': 0.3226168770418503}, 'combined': 0.19993158577241427, 'epoch': 28}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2587041705404181, 'r': 0.34902972534010873, 'f1': 0.2971545480682347}, 'combined': 0.2189559827871203, 'epoch': 28}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.32408353818762564, 'r': 0.30826029129600563, 'f1': 0.3159739408465081}, 'combined': 0.20960647561104995, 'epoch': 28}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.22596153846153846, 'r': 0.3357142857142857, 'f1': 0.27011494252873564}, 'combined': 0.18007662835249041, 'epoch': 28}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2894736842105263, 'r': 0.4782608695652174, 'f1': 0.360655737704918}, 'combined': 0.180327868852459, 'epoch': 28}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2916666666666667, 'r': 0.2413793103448276, 'f1': 0.26415094339622647}, 'combined': 0.17610062893081763, 'epoch': 28}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:13:03.223525: step: 2/466, loss: 0.055458780378103256
2023-01-22 13:13:03.830816: step: 4/466, loss: 0.15405134856700897
2023-01-22 13:13:04.435081: step: 6/466, loss: 0.002567231422290206
2023-01-22 13:13:05.047229: step: 8/466, loss: 0.00362135237082839
2023-01-22 13:13:05.679461: step: 10/466, loss: 0.028957726433873177
2023-01-22 13:13:06.261546: step: 12/466, loss: 0.009880519472062588
2023-01-22 13:13:06.888042: step: 14/466, loss: 0.002181266201660037
2023-01-22 13:13:07.531937: step: 16/466, loss: 0.017766177654266357
2023-01-22 13:13:08.114242: step: 18/466, loss: 0.0003223659878131002
2023-01-22 13:13:08.723573: step: 20/466, loss: 0.03559519350528717
2023-01-22 13:13:09.261826: step: 22/466, loss: 0.0033054545056074858
2023-01-22 13:13:09.860372: step: 24/466, loss: 0.06961570680141449
2023-01-22 13:13:10.437080: step: 26/466, loss: 0.002474683104082942
2023-01-22 13:13:11.050399: step: 28/466, loss: 0.012266730889678001
2023-01-22 13:13:11.723507: step: 30/466, loss: 0.016298441216349602
2023-01-22 13:13:12.390912: step: 32/466, loss: 0.015128509141504765
2023-01-22 13:13:13.021548: step: 34/466, loss: 0.002107497537508607
2023-01-22 13:13:13.658776: step: 36/466, loss: 0.004645375069230795
2023-01-22 13:13:14.316095: step: 38/466, loss: 0.004689569119364023
2023-01-22 13:13:14.917810: step: 40/466, loss: 0.026085158810019493
2023-01-22 13:13:15.584516: step: 42/466, loss: 0.018057744950056076
2023-01-22 13:13:16.202653: step: 44/466, loss: 0.1155918687582016
2023-01-22 13:13:16.836422: step: 46/466, loss: 0.02292424626648426
2023-01-22 13:13:17.457540: step: 48/466, loss: 0.02852936089038849
2023-01-22 13:13:18.094711: step: 50/466, loss: 0.6210425496101379
2023-01-22 13:13:18.716321: step: 52/466, loss: 0.007664544507861137
2023-01-22 13:13:19.319475: step: 54/466, loss: 0.0038290699012577534
2023-01-22 13:13:19.914129: step: 56/466, loss: 0.002938607707619667
2023-01-22 13:13:20.559604: step: 58/466, loss: 0.039176780730485916
2023-01-22 13:13:21.170576: step: 60/466, loss: 0.015739092603325844
2023-01-22 13:13:21.774069: step: 62/466, loss: 0.004881486762315035
2023-01-22 13:13:22.393030: step: 64/466, loss: 0.023610053583979607
2023-01-22 13:13:23.001961: step: 66/466, loss: 0.002876927610486746
2023-01-22 13:13:23.629309: step: 68/466, loss: 0.009272072464227676
2023-01-22 13:13:24.272450: step: 70/466, loss: 0.019138410687446594
2023-01-22 13:13:24.900947: step: 72/466, loss: 0.0038951088208705187
2023-01-22 13:13:25.493276: step: 74/466, loss: 0.0008685383945703506
2023-01-22 13:13:26.180381: step: 76/466, loss: 0.0030801768880337477
2023-01-22 13:13:26.820825: step: 78/466, loss: 0.22644856572151184
2023-01-22 13:13:27.438584: step: 80/466, loss: 0.05866759270429611
2023-01-22 13:13:28.053277: step: 82/466, loss: 0.2155982404947281
2023-01-22 13:13:28.626105: step: 84/466, loss: 0.011491452343761921
2023-01-22 13:13:29.241669: step: 86/466, loss: 0.03202078863978386
2023-01-22 13:13:29.903338: step: 88/466, loss: 0.061069175601005554
2023-01-22 13:13:30.552844: step: 90/466, loss: 0.04516958072781563
2023-01-22 13:13:31.201641: step: 92/466, loss: 0.006477218586951494
2023-01-22 13:13:31.801429: step: 94/466, loss: 0.012834693305194378
2023-01-22 13:13:32.461402: step: 96/466, loss: 0.28558802604675293
2023-01-22 13:13:33.062744: step: 98/466, loss: 0.022234907373785973
2023-01-22 13:13:33.789394: step: 100/466, loss: 0.043298911303281784
2023-01-22 13:13:34.460428: step: 102/466, loss: 0.04294387251138687
2023-01-22 13:13:35.055339: step: 104/466, loss: 0.009048323146998882
2023-01-22 13:13:35.726820: step: 106/466, loss: 0.008321230299770832
2023-01-22 13:13:36.361065: step: 108/466, loss: 0.0036059655249118805
2023-01-22 13:13:36.994218: step: 110/466, loss: 0.0009034308604896069
2023-01-22 13:13:37.588674: step: 112/466, loss: 0.1323184072971344
2023-01-22 13:13:38.216672: step: 114/466, loss: 0.020064985379576683
2023-01-22 13:13:38.830206: step: 116/466, loss: 0.043307989835739136
2023-01-22 13:13:39.438349: step: 118/466, loss: 0.02849368005990982
2023-01-22 13:13:40.054449: step: 120/466, loss: 0.03654780238866806
2023-01-22 13:13:40.746782: step: 122/466, loss: 0.0661456286907196
2023-01-22 13:13:41.409307: step: 124/466, loss: 0.0015133408596739173
2023-01-22 13:13:42.042328: step: 126/466, loss: 0.01084557082504034
2023-01-22 13:13:42.673420: step: 128/466, loss: 0.0015474183019250631
2023-01-22 13:13:43.333736: step: 130/466, loss: 0.008061830885708332
2023-01-22 13:13:43.947246: step: 132/466, loss: 0.013437075540423393
2023-01-22 13:13:44.495457: step: 134/466, loss: 0.01693044602870941
2023-01-22 13:13:45.160372: step: 136/466, loss: 0.02920161932706833
2023-01-22 13:13:45.759475: step: 138/466, loss: 0.0014797192998230457
2023-01-22 13:13:46.420655: step: 140/466, loss: 0.03992298245429993
2023-01-22 13:13:47.004805: step: 142/466, loss: 0.004694981966167688
2023-01-22 13:13:47.609687: step: 144/466, loss: 0.03145284950733185
2023-01-22 13:13:48.289648: step: 146/466, loss: 0.006949796807020903
2023-01-22 13:13:48.894968: step: 148/466, loss: 0.0030344414990395308
2023-01-22 13:13:49.550064: step: 150/466, loss: 0.014086630195379257
2023-01-22 13:13:50.179649: step: 152/466, loss: 0.017930377274751663
2023-01-22 13:13:50.794651: step: 154/466, loss: 0.002964240498840809
2023-01-22 13:13:51.445156: step: 156/466, loss: 0.0010559019865468144
2023-01-22 13:13:52.048015: step: 158/466, loss: 0.03484220802783966
2023-01-22 13:13:52.636138: step: 160/466, loss: 0.018427027389407158
2023-01-22 13:13:53.241331: step: 162/466, loss: 0.012817676179111004
2023-01-22 13:13:53.885502: step: 164/466, loss: 0.5581954121589661
2023-01-22 13:13:54.553767: step: 166/466, loss: 0.014592396095395088
2023-01-22 13:13:55.163058: step: 168/466, loss: 0.0002756986359599978
2023-01-22 13:13:55.816099: step: 170/466, loss: 0.018888216465711594
2023-01-22 13:13:56.437884: step: 172/466, loss: 0.0016108837444335222
2023-01-22 13:13:57.065666: step: 174/466, loss: 0.05931129679083824
2023-01-22 13:13:57.724716: step: 176/466, loss: 0.021158115938305855
2023-01-22 13:13:58.331995: step: 178/466, loss: 0.06505705416202545
2023-01-22 13:13:58.954765: step: 180/466, loss: 0.003004356985911727
2023-01-22 13:13:59.559121: step: 182/466, loss: 0.0010955791221931577
2023-01-22 13:14:00.191154: step: 184/466, loss: 0.3599194586277008
2023-01-22 13:14:00.792280: step: 186/466, loss: 0.0008553531370125711
2023-01-22 13:14:01.358827: step: 188/466, loss: 0.013580508530139923
2023-01-22 13:14:01.967011: step: 190/466, loss: 0.003150248434394598
2023-01-22 13:14:02.555315: step: 192/466, loss: 0.03827475756406784
2023-01-22 13:14:03.200052: step: 194/466, loss: 0.0022326000034809113
2023-01-22 13:14:03.831051: step: 196/466, loss: 0.02307925745844841
2023-01-22 13:14:04.461374: step: 198/466, loss: 0.015358785167336464
2023-01-22 13:14:05.094517: step: 200/466, loss: 0.00849807821214199
2023-01-22 13:14:05.760801: step: 202/466, loss: 0.012090289033949375
2023-01-22 13:14:06.384921: step: 204/466, loss: 0.050176870077848434
2023-01-22 13:14:06.931319: step: 206/466, loss: 1.0662583008524962e-05
2023-01-22 13:14:07.546830: step: 208/466, loss: 0.0032666290644556284
2023-01-22 13:14:08.141908: step: 210/466, loss: 0.021163562312722206
2023-01-22 13:14:08.847414: step: 212/466, loss: 0.0418899804353714
2023-01-22 13:14:09.480859: step: 214/466, loss: 0.025734828785061836
2023-01-22 13:14:10.062223: step: 216/466, loss: 0.001853344147093594
2023-01-22 13:14:10.716045: step: 218/466, loss: 0.02691415511071682
2023-01-22 13:14:11.288503: step: 220/466, loss: 0.023987652733922005
2023-01-22 13:14:11.979970: step: 222/466, loss: 0.11891963332891464
2023-01-22 13:14:12.655768: step: 224/466, loss: 0.024687206372618675
2023-01-22 13:14:13.238182: step: 226/466, loss: 0.034278325736522675
2023-01-22 13:14:13.842536: step: 228/466, loss: 0.4470962584018707
2023-01-22 13:14:14.441222: step: 230/466, loss: 0.00696721114218235
2023-01-22 13:14:15.024606: step: 232/466, loss: 0.09120207279920578
2023-01-22 13:14:15.659396: step: 234/466, loss: 0.01796315237879753
2023-01-22 13:14:16.206289: step: 236/466, loss: 0.02135283127427101
2023-01-22 13:14:16.863871: step: 238/466, loss: 0.026142485439777374
2023-01-22 13:14:17.475402: step: 240/466, loss: 0.012500501237809658
2023-01-22 13:14:18.078618: step: 242/466, loss: 0.003451203927397728
2023-01-22 13:14:18.664769: step: 244/466, loss: 0.009863471612334251
2023-01-22 13:14:19.313611: step: 246/466, loss: 0.00018838015967048705
2023-01-22 13:14:19.923542: step: 248/466, loss: 0.02044462226331234
2023-01-22 13:14:20.571740: step: 250/466, loss: 0.0927266776561737
2023-01-22 13:14:21.170775: step: 252/466, loss: 0.004784509539604187
2023-01-22 13:14:21.803836: step: 254/466, loss: 0.00503066461533308
2023-01-22 13:14:22.439695: step: 256/466, loss: 0.03931424766778946
2023-01-22 13:14:23.047372: step: 258/466, loss: 0.03814157471060753
2023-01-22 13:14:23.696605: step: 260/466, loss: 0.0018558165756985545
2023-01-22 13:14:24.301770: step: 262/466, loss: 0.036332663148641586
2023-01-22 13:14:24.916473: step: 264/466, loss: 0.025819065049290657
2023-01-22 13:14:25.617842: step: 266/466, loss: 0.11118387430906296
2023-01-22 13:14:26.324032: step: 268/466, loss: 0.013089925050735474
2023-01-22 13:14:26.931683: step: 270/466, loss: 0.03624863922595978
2023-01-22 13:14:27.516602: step: 272/466, loss: 0.0682566836476326
2023-01-22 13:14:28.066231: step: 274/466, loss: 0.003062065690755844
2023-01-22 13:14:28.706327: step: 276/466, loss: 0.0594942644238472
2023-01-22 13:14:29.339777: step: 278/466, loss: 0.01250424887984991
2023-01-22 13:14:29.907309: step: 280/466, loss: 0.43067610263824463
2023-01-22 13:14:30.496465: step: 282/466, loss: 0.018741458654403687
2023-01-22 13:14:31.097337: step: 284/466, loss: 0.02757546678185463
2023-01-22 13:14:31.770936: step: 286/466, loss: 0.028583785519003868
2023-01-22 13:14:32.410791: step: 288/466, loss: 0.017362266778945923
2023-01-22 13:14:33.072001: step: 290/466, loss: 0.008303117007017136
2023-01-22 13:14:33.675763: step: 292/466, loss: 0.039173100143671036
2023-01-22 13:14:34.349784: step: 294/466, loss: 0.0017002117820084095
2023-01-22 13:14:34.988577: step: 296/466, loss: 0.0066471220925450325
2023-01-22 13:14:35.639029: step: 298/466, loss: 0.0693783089518547
2023-01-22 13:14:36.226292: step: 300/466, loss: 0.025002075359225273
2023-01-22 13:14:36.873131: step: 302/466, loss: 7.945956167532131e-05
2023-01-22 13:14:37.517535: step: 304/466, loss: 0.0022197526413947344
2023-01-22 13:14:38.128868: step: 306/466, loss: 0.04276476800441742
2023-01-22 13:14:38.741181: step: 308/466, loss: 0.003689938923344016
2023-01-22 13:14:39.340895: step: 310/466, loss: 0.008290175348520279
2023-01-22 13:14:39.911948: step: 312/466, loss: 0.01216474175453186
2023-01-22 13:14:40.541283: step: 314/466, loss: 0.02552063763141632
2023-01-22 13:14:41.197413: step: 316/466, loss: 0.0009075455600395799
2023-01-22 13:14:41.824922: step: 318/466, loss: 0.03220680356025696
2023-01-22 13:14:42.545582: step: 320/466, loss: 0.08709538727998734
2023-01-22 13:14:43.168189: step: 322/466, loss: 0.012743586674332619
2023-01-22 13:14:43.854482: step: 324/466, loss: 0.05030284821987152
2023-01-22 13:14:44.443823: step: 326/466, loss: 0.06070198863744736
2023-01-22 13:14:45.066580: step: 328/466, loss: 0.003046990605071187
2023-01-22 13:14:45.660228: step: 330/466, loss: 0.0012152543058618903
2023-01-22 13:14:46.232287: step: 332/466, loss: 0.006156560033559799
2023-01-22 13:14:46.829529: step: 334/466, loss: 0.015339409001171589
2023-01-22 13:14:47.388432: step: 336/466, loss: 0.02426721528172493
2023-01-22 13:14:48.021277: step: 338/466, loss: 0.009182527661323547
2023-01-22 13:14:48.712060: step: 340/466, loss: 0.009834465570747852
2023-01-22 13:14:49.294062: step: 342/466, loss: 0.011993778869509697
2023-01-22 13:14:49.984778: step: 344/466, loss: 0.07179489731788635
2023-01-22 13:14:50.624567: step: 346/466, loss: 0.027768058702349663
2023-01-22 13:14:51.283279: step: 348/466, loss: 0.19790710508823395
2023-01-22 13:14:51.913869: step: 350/466, loss: 0.14374874532222748
2023-01-22 13:14:52.472973: step: 352/466, loss: 0.0007910241838544607
2023-01-22 13:14:53.104997: step: 354/466, loss: 0.03937764838337898
2023-01-22 13:14:53.751374: step: 356/466, loss: 0.013423875905573368
2023-01-22 13:14:54.327879: step: 358/466, loss: 0.0010883713839575648
2023-01-22 13:14:54.968662: step: 360/466, loss: 0.06256536394357681
2023-01-22 13:14:55.537837: step: 362/466, loss: 0.027907468378543854
2023-01-22 13:14:56.108603: step: 364/466, loss: 0.013393533416092396
2023-01-22 13:14:56.754211: step: 366/466, loss: 0.016689620912075043
2023-01-22 13:14:57.401344: step: 368/466, loss: 0.03434484452009201
2023-01-22 13:14:57.998402: step: 370/466, loss: 0.008721742779016495
2023-01-22 13:14:58.635526: step: 372/466, loss: 0.033357422798871994
2023-01-22 13:14:59.277577: step: 374/466, loss: 0.0007862323545850813
2023-01-22 13:14:59.877273: step: 376/466, loss: 0.014408997260034084
2023-01-22 13:15:00.562920: step: 378/466, loss: 0.0028941782657057047
2023-01-22 13:15:01.164094: step: 380/466, loss: 0.024151837453246117
2023-01-22 13:15:01.822642: step: 382/466, loss: 0.007602432742714882
2023-01-22 13:15:02.409005: step: 384/466, loss: 0.03272564336657524
2023-01-22 13:15:03.062909: step: 386/466, loss: 0.10223985463380814
2023-01-22 13:15:03.623773: step: 388/466, loss: 0.06555671244859695
2023-01-22 13:15:04.168229: step: 390/466, loss: 0.00729301618412137
2023-01-22 13:15:04.773756: step: 392/466, loss: 0.06495516002178192
2023-01-22 13:15:05.358585: step: 394/466, loss: 0.015802623704075813
2023-01-22 13:15:05.974413: step: 396/466, loss: 0.0006967387744225562
2023-01-22 13:15:06.557990: step: 398/466, loss: 0.04170413687825203
2023-01-22 13:15:07.133562: step: 400/466, loss: 0.005518648307770491
2023-01-22 13:15:07.819017: step: 402/466, loss: 0.04218827560544014
2023-01-22 13:15:08.413072: step: 404/466, loss: 0.15756018459796906
2023-01-22 13:15:09.031744: step: 406/466, loss: 0.01472820807248354
2023-01-22 13:15:09.743159: step: 408/466, loss: 0.05414842814207077
2023-01-22 13:15:10.345563: step: 410/466, loss: 0.005775025114417076
2023-01-22 13:15:10.959421: step: 412/466, loss: 0.03359856456518173
2023-01-22 13:15:11.558769: step: 414/466, loss: 0.015876727178692818
2023-01-22 13:15:12.160966: step: 416/466, loss: 0.013207340613007545
2023-01-22 13:15:12.768062: step: 418/466, loss: 0.004693139344453812
2023-01-22 13:15:13.392818: step: 420/466, loss: 0.018074549734592438
2023-01-22 13:15:14.043224: step: 422/466, loss: 0.07072412967681885
2023-01-22 13:15:14.755426: step: 424/466, loss: 0.04876650124788284
2023-01-22 13:15:15.378423: step: 426/466, loss: 0.07074081152677536
2023-01-22 13:15:15.987699: step: 428/466, loss: 0.0248673427850008
2023-01-22 13:15:16.625160: step: 430/466, loss: 0.028261784464120865
2023-01-22 13:15:17.255260: step: 432/466, loss: 0.00232923636212945
2023-01-22 13:15:17.927059: step: 434/466, loss: 0.01668694242835045
2023-01-22 13:15:18.548526: step: 436/466, loss: 0.04731211066246033
2023-01-22 13:15:19.179023: step: 438/466, loss: 0.05076116696000099
2023-01-22 13:15:19.818988: step: 440/466, loss: 0.06597016751766205
2023-01-22 13:15:20.412126: step: 442/466, loss: 0.034215111285448074
2023-01-22 13:15:21.028450: step: 444/466, loss: 0.04960392042994499
2023-01-22 13:15:21.667835: step: 446/466, loss: 0.008371061645448208
2023-01-22 13:15:22.295054: step: 448/466, loss: 0.0910857766866684
2023-01-22 13:15:22.898612: step: 450/466, loss: 0.017675234004855156
2023-01-22 13:15:23.502963: step: 452/466, loss: 0.05704466998577118
2023-01-22 13:15:24.168820: step: 454/466, loss: 0.010572683066129684
2023-01-22 13:15:24.789031: step: 456/466, loss: 0.027380328625440598
2023-01-22 13:15:25.399866: step: 458/466, loss: 0.015812745317816734
2023-01-22 13:15:26.014538: step: 460/466, loss: 0.05687829107046127
2023-01-22 13:15:26.633561: step: 462/466, loss: 0.008855399675667286
2023-01-22 13:15:27.244789: step: 464/466, loss: 0.027346044778823853
2023-01-22 13:15:27.857550: step: 466/466, loss: 0.2506482005119324
2023-01-22 13:15:28.455165: step: 468/466, loss: 0.022388659417629242
2023-01-22 13:15:29.064690: step: 470/466, loss: 0.003716476494446397
2023-01-22 13:15:29.689857: step: 472/466, loss: 0.16157712042331696
2023-01-22 13:15:30.353559: step: 474/466, loss: 0.00471423240378499
2023-01-22 13:15:30.994103: step: 476/466, loss: 0.11767103523015976
2023-01-22 13:15:31.667386: step: 478/466, loss: 0.04689113423228264
2023-01-22 13:15:32.287594: step: 480/466, loss: 0.0326380729675293
2023-01-22 13:15:32.848446: step: 482/466, loss: 0.00017360990750603378
2023-01-22 13:15:33.581014: step: 484/466, loss: 0.006069815717637539
2023-01-22 13:15:34.190904: step: 486/466, loss: 0.00955923181027174
2023-01-22 13:15:34.761154: step: 488/466, loss: 0.0006118972669355571
2023-01-22 13:15:35.458995: step: 490/466, loss: 0.007228366564959288
2023-01-22 13:15:36.040249: step: 492/466, loss: 0.021563038229942322
2023-01-22 13:15:36.616833: step: 494/466, loss: 0.008069528266787529
2023-01-22 13:15:37.198486: step: 496/466, loss: 0.0019346001790836453
2023-01-22 13:15:37.779451: step: 498/466, loss: 0.04826516658067703
2023-01-22 13:15:38.371353: step: 500/466, loss: 0.10739605873823166
2023-01-22 13:15:38.998016: step: 502/466, loss: 0.028787538409233093
2023-01-22 13:15:39.618436: step: 504/466, loss: 0.015625806525349617
2023-01-22 13:15:40.298928: step: 506/466, loss: 0.013151661492884159
2023-01-22 13:15:40.924295: step: 508/466, loss: 0.026067402213811874
2023-01-22 13:15:41.540442: step: 510/466, loss: 0.06838241219520569
2023-01-22 13:15:42.141765: step: 512/466, loss: 0.14713266491889954
2023-01-22 13:15:42.706406: step: 514/466, loss: 0.024375615641474724
2023-01-22 13:15:43.312664: step: 516/466, loss: 0.0011519754771143198
2023-01-22 13:15:43.977085: step: 518/466, loss: 0.0037082030903548002
2023-01-22 13:15:44.575409: step: 520/466, loss: 0.02469959482550621
2023-01-22 13:15:45.108872: step: 522/466, loss: 0.002963092178106308
2023-01-22 13:15:45.671413: step: 524/466, loss: 0.003018419025465846
2023-01-22 13:15:46.196662: step: 526/466, loss: 0.011339960619807243
2023-01-22 13:15:46.798616: step: 528/466, loss: 0.000892937183380127
2023-01-22 13:15:47.380002: step: 530/466, loss: 0.00013537502672988921
2023-01-22 13:15:48.065581: step: 532/466, loss: 0.009031346067786217
2023-01-22 13:15:48.731354: step: 534/466, loss: 0.0035680688451975584
2023-01-22 13:15:49.305817: step: 536/466, loss: 0.024319544434547424
2023-01-22 13:15:50.033385: step: 538/466, loss: 0.013947529718279839
2023-01-22 13:15:50.626842: step: 540/466, loss: 0.019546305760741234
2023-01-22 13:15:51.308892: step: 542/466, loss: 0.029420148581266403
2023-01-22 13:15:51.914746: step: 544/466, loss: 0.016928454861044884
2023-01-22 13:15:52.532422: step: 546/466, loss: 0.004215354565531015
2023-01-22 13:15:53.128762: step: 548/466, loss: 0.036032386124134064
2023-01-22 13:15:53.773362: step: 550/466, loss: 0.11021918803453445
2023-01-22 13:15:54.422101: step: 552/466, loss: 0.13087381422519684
2023-01-22 13:15:54.950445: step: 554/466, loss: 0.003767420072108507
2023-01-22 13:15:55.543107: step: 556/466, loss: 0.01813679188489914
2023-01-22 13:15:56.150267: step: 558/466, loss: 0.005178377032279968
2023-01-22 13:15:56.777283: step: 560/466, loss: 0.00700752018019557
2023-01-22 13:15:57.425743: step: 562/466, loss: 0.024122627452015877
2023-01-22 13:15:58.087981: step: 564/466, loss: 0.006926470436155796
2023-01-22 13:15:58.743786: step: 566/466, loss: 0.002192798303440213
2023-01-22 13:15:59.305813: step: 568/466, loss: 0.005069288890808821
2023-01-22 13:15:59.914085: step: 570/466, loss: 0.0009709860314615071
2023-01-22 13:16:00.542851: step: 572/466, loss: 0.0475449375808239
2023-01-22 13:16:01.169173: step: 574/466, loss: 0.00809780228883028
2023-01-22 13:16:01.803432: step: 576/466, loss: 0.007280854508280754
2023-01-22 13:16:02.416128: step: 578/466, loss: 0.005466064903885126
2023-01-22 13:16:03.007650: step: 580/466, loss: 0.0002499515831004828
2023-01-22 13:16:03.636105: step: 582/466, loss: 0.0017354476731270552
2023-01-22 13:16:04.315201: step: 584/466, loss: 0.02401800826191902
2023-01-22 13:16:04.955148: step: 586/466, loss: 0.05263170227408409
2023-01-22 13:16:05.515814: step: 588/466, loss: 0.010402865707874298
2023-01-22 13:16:06.065200: step: 590/466, loss: 0.012639729306101799
2023-01-22 13:16:06.710996: step: 592/466, loss: 0.0034263322595506907
2023-01-22 13:16:07.364259: step: 594/466, loss: 0.00882495753467083
2023-01-22 13:16:08.016952: step: 596/466, loss: 0.026667889207601547
2023-01-22 13:16:08.604390: step: 598/466, loss: 0.03127731382846832
2023-01-22 13:16:09.234249: step: 600/466, loss: 0.09185895323753357
2023-01-22 13:16:09.834482: step: 602/466, loss: 0.04450776427984238
2023-01-22 13:16:10.449292: step: 604/466, loss: 0.04808002710342407
2023-01-22 13:16:11.136826: step: 606/466, loss: 0.009080737829208374
2023-01-22 13:16:11.760628: step: 608/466, loss: 0.006041831336915493
2023-01-22 13:16:12.418372: step: 610/466, loss: 0.005429220385849476
2023-01-22 13:16:13.006190: step: 612/466, loss: 0.002425620099529624
2023-01-22 13:16:13.614140: step: 614/466, loss: 0.023527776822447777
2023-01-22 13:16:14.214256: step: 616/466, loss: 0.024566251784563065
2023-01-22 13:16:14.848573: step: 618/466, loss: 0.01168688666075468
2023-01-22 13:16:15.624279: step: 620/466, loss: 0.04210988059639931
2023-01-22 13:16:16.222790: step: 622/466, loss: 0.05103759840130806
2023-01-22 13:16:16.852663: step: 624/466, loss: 0.020575957372784615
2023-01-22 13:16:17.469622: step: 626/466, loss: 0.0016736033139750361
2023-01-22 13:16:18.070199: step: 628/466, loss: 0.007483240682631731
2023-01-22 13:16:18.670492: step: 630/466, loss: 0.005836804397404194
2023-01-22 13:16:19.317319: step: 632/466, loss: 0.021505624055862427
2023-01-22 13:16:19.901612: step: 634/466, loss: 0.007295564748346806
2023-01-22 13:16:20.565747: step: 636/466, loss: 0.0020562144927680492
2023-01-22 13:16:21.184408: step: 638/466, loss: 0.08412209153175354
2023-01-22 13:16:21.795128: step: 640/466, loss: 0.00717060687020421
2023-01-22 13:16:22.374325: step: 642/466, loss: 0.03495078906416893
2023-01-22 13:16:23.010752: step: 644/466, loss: 0.013647991232573986
2023-01-22 13:16:23.643622: step: 646/466, loss: 0.08542032539844513
2023-01-22 13:16:24.271070: step: 648/466, loss: 0.05156783014535904
2023-01-22 13:16:24.916828: step: 650/466, loss: 0.011495641432702541
2023-01-22 13:16:25.579614: step: 652/466, loss: 0.021660026162862778
2023-01-22 13:16:26.151016: step: 654/466, loss: 0.004816859494894743
2023-01-22 13:16:26.763745: step: 656/466, loss: 0.0038773231208324432
2023-01-22 13:16:27.365289: step: 658/466, loss: 0.09771724045276642
2023-01-22 13:16:27.891722: step: 660/466, loss: 0.0058814045041799545
2023-01-22 13:16:28.528934: step: 662/466, loss: 0.1017870083451271
2023-01-22 13:16:29.158512: step: 664/466, loss: 0.008702441118657589
2023-01-22 13:16:29.741987: step: 666/466, loss: 0.0007017693133093417
2023-01-22 13:16:30.358585: step: 668/466, loss: 0.06927017867565155
2023-01-22 13:16:30.964784: step: 670/466, loss: 0.0059940507635474205
2023-01-22 13:16:31.544635: step: 672/466, loss: 0.021509302780032158
2023-01-22 13:16:32.127261: step: 674/466, loss: 0.04001140967011452
2023-01-22 13:16:32.724793: step: 676/466, loss: 0.00619617011398077
2023-01-22 13:16:33.400203: step: 678/466, loss: 0.02416771650314331
2023-01-22 13:16:34.035396: step: 680/466, loss: 0.0016998895443975925
2023-01-22 13:16:34.632812: step: 682/466, loss: 0.057930637151002884
2023-01-22 13:16:35.224414: step: 684/466, loss: 0.08490652590990067
2023-01-22 13:16:35.821135: step: 686/466, loss: 0.14410264790058136
2023-01-22 13:16:36.573417: step: 688/466, loss: 0.04748551920056343
2023-01-22 13:16:37.144757: step: 690/466, loss: 0.006760920863598585
2023-01-22 13:16:37.725188: step: 692/466, loss: 0.007869471795856953
2023-01-22 13:16:38.333797: step: 694/466, loss: 0.059117190539836884
2023-01-22 13:16:38.961291: step: 696/466, loss: 0.0007719701388850808
2023-01-22 13:16:39.646321: step: 698/466, loss: 0.03341097757220268
2023-01-22 13:16:40.325085: step: 700/466, loss: 0.003831847570836544
2023-01-22 13:16:40.964619: step: 702/466, loss: 0.040099117904901505
2023-01-22 13:16:41.657703: step: 704/466, loss: 0.022016925737261772
2023-01-22 13:16:42.317515: step: 706/466, loss: 0.004059267230331898
2023-01-22 13:16:42.956800: step: 708/466, loss: 0.1325579285621643
2023-01-22 13:16:43.624122: step: 710/466, loss: 0.04360053315758705
2023-01-22 13:16:44.244556: step: 712/466, loss: 0.0035664194729179144
2023-01-22 13:16:44.837458: step: 714/466, loss: 0.011497018858790398
2023-01-22 13:16:45.548380: step: 716/466, loss: 0.003529996844008565
2023-01-22 13:16:46.105246: step: 718/466, loss: 0.003293456742540002
2023-01-22 13:16:46.713550: step: 720/466, loss: 0.0368904173374176
2023-01-22 13:16:47.320419: step: 722/466, loss: 0.08443581312894821
2023-01-22 13:16:47.958853: step: 724/466, loss: 0.00709934439510107
2023-01-22 13:16:48.567176: step: 726/466, loss: 0.20502182841300964
2023-01-22 13:16:49.163714: step: 728/466, loss: 0.03874938189983368
2023-01-22 13:16:49.765664: step: 730/466, loss: 0.17828691005706787
2023-01-22 13:16:50.345913: step: 732/466, loss: 0.7214789390563965
2023-01-22 13:16:51.024101: step: 734/466, loss: 0.11488200724124908
2023-01-22 13:16:51.790701: step: 736/466, loss: 0.05732061341404915
2023-01-22 13:16:52.444406: step: 738/466, loss: 0.021588746458292007
2023-01-22 13:16:53.100792: step: 740/466, loss: 0.006465683691203594
2023-01-22 13:16:53.681791: step: 742/466, loss: 0.22872889041900635
2023-01-22 13:16:54.313697: step: 744/466, loss: 0.06467809528112411
2023-01-22 13:16:54.866652: step: 746/466, loss: 0.008470224216580391
2023-01-22 13:16:55.482840: step: 748/466, loss: 0.0343211330473423
2023-01-22 13:16:56.083740: step: 750/466, loss: 0.0265874695032835
2023-01-22 13:16:56.953589: step: 752/466, loss: 0.024140940979123116
2023-01-22 13:16:57.513263: step: 754/466, loss: 0.017646193504333496
2023-01-22 13:16:58.113423: step: 756/466, loss: 0.030673718079924583
2023-01-22 13:16:58.726833: step: 758/466, loss: 0.005739795975387096
2023-01-22 13:16:59.322357: step: 760/466, loss: 0.0696202963590622
2023-01-22 13:16:59.971942: step: 762/466, loss: 0.00723445788025856
2023-01-22 13:17:00.614130: step: 764/466, loss: 0.014322903007268906
2023-01-22 13:17:01.200752: step: 766/466, loss: 0.03494839742779732
2023-01-22 13:17:01.853323: step: 768/466, loss: 0.006455695256590843
2023-01-22 13:17:02.501535: step: 770/466, loss: 0.008284795098006725
2023-01-22 13:17:03.165760: step: 772/466, loss: 0.010526874102652073
2023-01-22 13:17:03.810556: step: 774/466, loss: 0.004267999902367592
2023-01-22 13:17:04.432596: step: 776/466, loss: 0.11157587915658951
2023-01-22 13:17:05.079337: step: 778/466, loss: 0.016989924013614655
2023-01-22 13:17:05.766995: step: 780/466, loss: 0.05661598592996597
2023-01-22 13:17:06.404695: step: 782/466, loss: 0.008631090633571148
2023-01-22 13:17:07.064468: step: 784/466, loss: 0.02421271987259388
2023-01-22 13:17:07.675830: step: 786/466, loss: 0.007431394886225462
2023-01-22 13:17:08.300202: step: 788/466, loss: 0.008399268612265587
2023-01-22 13:17:08.847026: step: 790/466, loss: 0.0023318808525800705
2023-01-22 13:17:09.450452: step: 792/466, loss: 0.007587133906781673
2023-01-22 13:17:10.114482: step: 794/466, loss: 0.012428142130374908
2023-01-22 13:17:10.708065: step: 796/466, loss: 0.017512351274490356
2023-01-22 13:17:11.320197: step: 798/466, loss: 0.026235686615109444
2023-01-22 13:17:11.981587: step: 800/466, loss: 0.011647449806332588
2023-01-22 13:17:12.667252: step: 802/466, loss: 0.010017693042755127
2023-01-22 13:17:13.249226: step: 804/466, loss: 0.04299866035580635
2023-01-22 13:17:13.827047: step: 806/466, loss: 0.0018923030002042651
2023-01-22 13:17:14.492327: step: 808/466, loss: 0.043426040560007095
2023-01-22 13:17:15.076638: step: 810/466, loss: 0.07270084321498871
2023-01-22 13:17:15.727886: step: 812/466, loss: 0.09882272034883499
2023-01-22 13:17:16.351983: step: 814/466, loss: 0.060429349541664124
2023-01-22 13:17:16.936730: step: 816/466, loss: 0.007622709032148123
2023-01-22 13:17:17.566853: step: 818/466, loss: 0.05808849260210991
2023-01-22 13:17:18.251653: step: 820/466, loss: 0.02498483657836914
2023-01-22 13:17:18.899821: step: 822/466, loss: 0.01560881920158863
2023-01-22 13:17:19.526223: step: 824/466, loss: 0.015989849343895912
2023-01-22 13:17:20.189754: step: 826/466, loss: 0.019871845841407776
2023-01-22 13:17:20.819835: step: 828/466, loss: 0.01792735420167446
2023-01-22 13:17:21.478230: step: 830/466, loss: 0.0017182455630972981
2023-01-22 13:17:22.114437: step: 832/466, loss: 0.0010431138798594475
2023-01-22 13:17:22.709796: step: 834/466, loss: 0.00454977760091424
2023-01-22 13:17:23.344315: step: 836/466, loss: 0.056652382016181946
2023-01-22 13:17:23.967690: step: 838/466, loss: 0.004974375478923321
2023-01-22 13:17:24.599323: step: 840/466, loss: 0.02224394865334034
2023-01-22 13:17:25.194531: step: 842/466, loss: 0.02503383159637451
2023-01-22 13:17:25.839291: step: 844/466, loss: 0.062120914459228516
2023-01-22 13:17:26.453223: step: 846/466, loss: 0.03201693668961525
2023-01-22 13:17:27.134997: step: 848/466, loss: 0.025600528344511986
2023-01-22 13:17:27.780682: step: 850/466, loss: 0.1290968507528305
2023-01-22 13:17:28.479484: step: 852/466, loss: 0.02363685518503189
2023-01-22 13:17:29.075609: step: 854/466, loss: 0.40937554836273193
2023-01-22 13:17:29.680412: step: 856/466, loss: 0.016148915514349937
2023-01-22 13:17:30.310575: step: 858/466, loss: 0.022587740793824196
2023-01-22 13:17:30.917072: step: 860/466, loss: 0.3588748872280121
2023-01-22 13:17:31.571057: step: 862/466, loss: 0.045865412801504135
2023-01-22 13:17:32.211618: step: 864/466, loss: 0.060815632343292236
2023-01-22 13:17:32.798486: step: 866/466, loss: 0.07046215981245041
2023-01-22 13:17:33.400331: step: 868/466, loss: 0.03324376791715622
2023-01-22 13:17:34.072545: step: 870/466, loss: 0.002355964621528983
2023-01-22 13:17:34.622310: step: 872/466, loss: 0.014346129260957241
2023-01-22 13:17:35.209295: step: 874/466, loss: 0.009171859361231327
2023-01-22 13:17:35.840967: step: 876/466, loss: 0.14728856086730957
2023-01-22 13:17:36.533428: step: 878/466, loss: 0.1031573936343193
2023-01-22 13:17:37.168119: step: 880/466, loss: 0.014084714464843273
2023-01-22 13:17:37.832299: step: 882/466, loss: 0.0013595783384516835
2023-01-22 13:17:38.458452: step: 884/466, loss: 0.017398567870259285
2023-01-22 13:17:39.056660: step: 886/466, loss: 0.028092503547668457
2023-01-22 13:17:39.616069: step: 888/466, loss: 0.014292089268565178
2023-01-22 13:17:40.271063: step: 890/466, loss: 0.05108671635389328
2023-01-22 13:17:40.924161: step: 892/466, loss: 0.02743634209036827
2023-01-22 13:17:41.529590: step: 894/466, loss: 0.2530224323272705
2023-01-22 13:17:42.174390: step: 896/466, loss: 0.03472018241882324
2023-01-22 13:17:42.786407: step: 898/466, loss: 0.003845237661153078
2023-01-22 13:17:43.368243: step: 900/466, loss: 0.032374050468206406
2023-01-22 13:17:44.020519: step: 902/466, loss: 0.008284141309559345
2023-01-22 13:17:44.651060: step: 904/466, loss: 0.024483878165483475
2023-01-22 13:17:45.235790: step: 906/466, loss: 0.007158839143812656
2023-01-22 13:17:45.858152: step: 908/466, loss: 0.015555165708065033
2023-01-22 13:17:46.507664: step: 910/466, loss: 0.0011703958734869957
2023-01-22 13:17:47.117074: step: 912/466, loss: 0.014334444887936115
2023-01-22 13:17:47.722485: step: 914/466, loss: 0.004041311796754599
2023-01-22 13:17:48.368185: step: 916/466, loss: 0.02556944638490677
2023-01-22 13:17:49.004288: step: 918/466, loss: 0.002209881553426385
2023-01-22 13:17:49.581388: step: 920/466, loss: 0.016322242096066475
2023-01-22 13:17:50.220525: step: 922/466, loss: 0.00473765330389142
2023-01-22 13:17:50.833676: step: 924/466, loss: 0.03993857279419899
2023-01-22 13:17:51.372280: step: 926/466, loss: 0.0010968783171847463
2023-01-22 13:17:51.995557: step: 928/466, loss: 0.16139191389083862
2023-01-22 13:17:52.608216: step: 930/466, loss: 0.01240439061075449
2023-01-22 13:17:53.145390: step: 932/466, loss: 0.03332965075969696
==================================================
Loss: 0.040
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3276761193508532, 'r': 0.3345156588439451, 'f1': 0.33106056753194185}, 'combined': 0.24393936554985188, 'epoch': 29}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.31850036573333784, 'r': 0.29293992159423315, 'f1': 0.3051858835584824}, 'combined': 0.1910977027889563, 'epoch': 29}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31160641403548556, 'r': 0.34590085808493176, 'f1': 0.32785926656611336}, 'combined': 0.24158051220660984, 'epoch': 29}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.32730384863843515, 'r': 0.3060350064886452, 'f1': 0.3163123014826668}, 'combined': 0.19602452486249772, 'epoch': 29}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2858162974612764, 'r': 0.3395085430944194, 'f1': 0.31035733254251346}, 'combined': 0.22868435029448358, 'epoch': 29}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3285743387383546, 'r': 0.2985960115363909, 'f1': 0.31286870304854214}, 'combined': 0.2075465653886369, 'epoch': 29}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3125, 'r': 0.3392857142857143, 'f1': 0.3253424657534247}, 'combined': 0.2168949771689498, 'epoch': 29}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.328125, 'r': 0.45652173913043476, 'f1': 0.3818181818181817}, 'combined': 0.19090909090909086, 'epoch': 29}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3, 'r': 0.20689655172413793, 'f1': 0.24489795918367346}, 'combined': 0.16326530612244897, 'epoch': 29}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:20:30.602302: step: 2/466, loss: 0.25535038113594055
2023-01-22 13:20:31.226106: step: 4/466, loss: 0.059584300965070724
2023-01-22 13:20:31.765698: step: 6/466, loss: 0.0011487414594739676
2023-01-22 13:20:32.391699: step: 8/466, loss: 0.01580643281340599
2023-01-22 13:20:33.008918: step: 10/466, loss: 0.0004533784813247621
2023-01-22 13:20:33.576140: step: 12/466, loss: 0.0019115079194307327
2023-01-22 13:20:34.191600: step: 14/466, loss: 0.08677832782268524
2023-01-22 13:20:34.854181: step: 16/466, loss: 0.9424175024032593
2023-01-22 13:20:35.438455: step: 18/466, loss: 0.005752339493483305
2023-01-22 13:20:36.048165: step: 20/466, loss: 0.011783424764871597
2023-01-22 13:20:36.723384: step: 22/466, loss: 0.012505832128226757
2023-01-22 13:20:37.281131: step: 24/466, loss: 0.021198196336627007
2023-01-22 13:20:37.877066: step: 26/466, loss: 0.003726731287315488
2023-01-22 13:20:38.476069: step: 28/466, loss: 0.00993861723691225
2023-01-22 13:20:39.071502: step: 30/466, loss: 0.009253359399735928
2023-01-22 13:20:39.693382: step: 32/466, loss: 0.02724388800561428
2023-01-22 13:20:40.342541: step: 34/466, loss: 0.05642537400126457
2023-01-22 13:20:41.006200: step: 36/466, loss: 0.18135637044906616
2023-01-22 13:20:41.619173: step: 38/466, loss: 0.0024714407045394182
2023-01-22 13:20:42.229905: step: 40/466, loss: 0.027407290413975716
2023-01-22 13:20:42.843524: step: 42/466, loss: 0.021592652425169945
2023-01-22 13:20:43.437285: step: 44/466, loss: 0.06558530032634735
2023-01-22 13:20:44.194708: step: 46/466, loss: 0.001523285172879696
2023-01-22 13:20:44.776199: step: 48/466, loss: 0.00045692603453062475
2023-01-22 13:20:45.346718: step: 50/466, loss: 0.007932682521641254
2023-01-22 13:20:45.940274: step: 52/466, loss: 0.001439443207345903
2023-01-22 13:20:46.620571: step: 54/466, loss: 0.034045495092868805
2023-01-22 13:20:47.228465: step: 56/466, loss: 0.019762855023145676
2023-01-22 13:20:47.906862: step: 58/466, loss: 0.024518828839063644
2023-01-22 13:20:48.538272: step: 60/466, loss: 0.32017919421195984
2023-01-22 13:20:49.115638: step: 62/466, loss: 0.0019085191888734698
2023-01-22 13:20:49.699331: step: 64/466, loss: 0.0019422724144533277
2023-01-22 13:20:50.388201: step: 66/466, loss: 0.028080932796001434
2023-01-22 13:20:50.978241: step: 68/466, loss: 0.001465092645958066
2023-01-22 13:20:51.572951: step: 70/466, loss: 0.0021644604858011007
2023-01-22 13:20:52.160974: step: 72/466, loss: 0.3165663182735443
2023-01-22 13:20:52.737197: step: 74/466, loss: 0.0019387322245165706
2023-01-22 13:20:53.391506: step: 76/466, loss: 0.00856761448085308
2023-01-22 13:20:54.032035: step: 78/466, loss: 0.011682793498039246
2023-01-22 13:20:54.556016: step: 80/466, loss: 0.0014889666344970465
2023-01-22 13:20:55.194978: step: 82/466, loss: 0.002886301139369607
2023-01-22 13:20:55.846915: step: 84/466, loss: 0.013197853229939938
2023-01-22 13:20:56.506413: step: 86/466, loss: 0.0016110630240291357
2023-01-22 13:20:57.138832: step: 88/466, loss: 0.0007182496483437717
2023-01-22 13:20:57.724976: step: 90/466, loss: 0.021293770521879196
2023-01-22 13:20:58.331166: step: 92/466, loss: 0.0070520141161978245
2023-01-22 13:20:58.952296: step: 94/466, loss: 0.003467913717031479
2023-01-22 13:20:59.583806: step: 96/466, loss: 0.017498059198260307
2023-01-22 13:21:00.214354: step: 98/466, loss: 0.002966963918879628
2023-01-22 13:21:00.778333: step: 100/466, loss: 0.03477673977613449
2023-01-22 13:21:01.322612: step: 102/466, loss: 0.003827991895377636
2023-01-22 13:21:01.956251: step: 104/466, loss: 0.005310960579663515
2023-01-22 13:21:02.663471: step: 106/466, loss: 0.009435564279556274
2023-01-22 13:21:03.250936: step: 108/466, loss: 0.004216838628053665
2023-01-22 13:21:03.828115: step: 110/466, loss: 0.010082358494400978
2023-01-22 13:21:04.468794: step: 112/466, loss: 0.009822693653404713
2023-01-22 13:21:05.139867: step: 114/466, loss: 0.0001807942462619394
2023-01-22 13:21:05.752623: step: 116/466, loss: 0.018664024770259857
2023-01-22 13:21:06.363918: step: 118/466, loss: 0.018917158246040344
2023-01-22 13:21:07.023612: step: 120/466, loss: 0.05617400258779526
2023-01-22 13:21:07.670575: step: 122/466, loss: 0.017198363319039345
2023-01-22 13:21:08.245344: step: 124/466, loss: 0.04158959165215492
2023-01-22 13:21:08.838307: step: 126/466, loss: 0.033165402710437775
2023-01-22 13:21:09.414826: step: 128/466, loss: 0.023463696241378784
2023-01-22 13:21:10.054701: step: 130/466, loss: 0.01603042334318161
2023-01-22 13:21:10.631751: step: 132/466, loss: 0.010675805620849133
2023-01-22 13:21:11.266033: step: 134/466, loss: 0.01999947801232338
2023-01-22 13:21:11.834930: step: 136/466, loss: 0.017424974590539932
2023-01-22 13:21:12.493073: step: 138/466, loss: 0.010514659807085991
2023-01-22 13:21:13.143498: step: 140/466, loss: 0.07198095321655273
2023-01-22 13:21:13.694316: step: 142/466, loss: 0.0015183447394520044
2023-01-22 13:21:14.346583: step: 144/466, loss: 0.015799857676029205
2023-01-22 13:21:14.988797: step: 146/466, loss: 0.011465340852737427
2023-01-22 13:21:15.577554: step: 148/466, loss: 0.005793638527393341
2023-01-22 13:21:16.221861: step: 150/466, loss: 0.2577780783176422
2023-01-22 13:21:16.907454: step: 152/466, loss: 0.05551606044173241
2023-01-22 13:21:17.542167: step: 154/466, loss: 4.4543352127075195
2023-01-22 13:21:18.225045: step: 156/466, loss: 0.011444765143096447
2023-01-22 13:21:18.798300: step: 158/466, loss: 0.0006477702409029007
2023-01-22 13:21:19.370380: step: 160/466, loss: 0.0015633396105840802
2023-01-22 13:21:20.012232: step: 162/466, loss: 0.0035987847950309515
2023-01-22 13:21:20.590160: step: 164/466, loss: 0.0012867094483226538
2023-01-22 13:21:21.194343: step: 166/466, loss: 3.6880690004181815e-06
2023-01-22 13:21:21.855639: step: 168/466, loss: 0.014223197475075722
2023-01-22 13:21:22.494675: step: 170/466, loss: 0.031598109751939774
2023-01-22 13:21:23.113456: step: 172/466, loss: 0.003733185352757573
2023-01-22 13:21:23.692829: step: 174/466, loss: 0.07216422259807587
2023-01-22 13:21:24.314690: step: 176/466, loss: 0.0005256884032860398
2023-01-22 13:21:24.905117: step: 178/466, loss: 0.0060292575508356094
2023-01-22 13:21:25.565853: step: 180/466, loss: 0.004464306868612766
2023-01-22 13:21:26.244215: step: 182/466, loss: 0.05793391540646553
2023-01-22 13:21:26.858953: step: 184/466, loss: 0.06362371891736984
2023-01-22 13:21:27.417400: step: 186/466, loss: 0.0032500093802809715
2023-01-22 13:21:28.047568: step: 188/466, loss: 0.013271069154143333
2023-01-22 13:21:28.670251: step: 190/466, loss: 0.05028381943702698
2023-01-22 13:21:29.320447: step: 192/466, loss: 0.007637789938598871
2023-01-22 13:21:29.984268: step: 194/466, loss: 0.00744094792753458
2023-01-22 13:21:30.604131: step: 196/466, loss: 0.010570245794951916
2023-01-22 13:21:31.254138: step: 198/466, loss: 0.0015127696096897125
2023-01-22 13:21:31.865067: step: 200/466, loss: 0.024606024846434593
2023-01-22 13:21:32.493155: step: 202/466, loss: 0.006593392696231604
2023-01-22 13:21:33.160582: step: 204/466, loss: 0.011315795592963696
2023-01-22 13:21:33.791173: step: 206/466, loss: 0.029257386922836304
2023-01-22 13:21:34.393785: step: 208/466, loss: 0.05389769375324249
2023-01-22 13:21:35.037771: step: 210/466, loss: 0.004224174655973911
2023-01-22 13:21:35.706342: step: 212/466, loss: 0.008780408650636673
2023-01-22 13:21:36.350388: step: 214/466, loss: 0.007662737276405096
2023-01-22 13:21:36.911083: step: 216/466, loss: 0.042978685349226
2023-01-22 13:21:37.533396: step: 218/466, loss: 0.016707254573702812
2023-01-22 13:21:38.193211: step: 220/466, loss: 0.00432699266821146
2023-01-22 13:21:38.837915: step: 222/466, loss: 0.0940069779753685
2023-01-22 13:21:39.449481: step: 224/466, loss: 0.05365337058901787
2023-01-22 13:21:40.098016: step: 226/466, loss: 0.01027167122811079
2023-01-22 13:21:40.671276: step: 228/466, loss: 0.11637594550848007
2023-01-22 13:21:41.303449: step: 230/466, loss: 0.09816039353609085
2023-01-22 13:21:41.983571: step: 232/466, loss: 0.02542124129831791
2023-01-22 13:21:42.641760: step: 234/466, loss: 0.046224284917116165
2023-01-22 13:21:43.334414: step: 236/466, loss: 0.0020608706399798393
2023-01-22 13:21:43.909791: step: 238/466, loss: 0.004918182268738747
2023-01-22 13:21:44.550427: step: 240/466, loss: 0.01395337749272585
2023-01-22 13:21:45.203695: step: 242/466, loss: 0.021894754841923714
2023-01-22 13:21:45.808042: step: 244/466, loss: 0.001072632265277207
2023-01-22 13:21:46.395934: step: 246/466, loss: 0.026571357622742653
2023-01-22 13:21:47.014606: step: 248/466, loss: 0.00011169735807925463
2023-01-22 13:21:47.606689: step: 250/466, loss: 0.012831415981054306
2023-01-22 13:21:48.257520: step: 252/466, loss: 0.035040538758039474
2023-01-22 13:21:48.861414: step: 254/466, loss: 0.011681620962917805
2023-01-22 13:21:49.432587: step: 256/466, loss: 0.018262110650539398
2023-01-22 13:21:50.018910: step: 258/466, loss: 0.0010507949627935886
2023-01-22 13:21:50.625742: step: 260/466, loss: 0.012839422561228275
2023-01-22 13:21:51.264831: step: 262/466, loss: 0.0018101419555023313
2023-01-22 13:21:51.888838: step: 264/466, loss: 0.016770323738455772
2023-01-22 13:21:52.481829: step: 266/466, loss: 0.0018701822264119983
2023-01-22 13:21:53.164043: step: 268/466, loss: 0.010127153247594833
2023-01-22 13:21:53.851342: step: 270/466, loss: 0.12128043174743652
2023-01-22 13:21:54.460490: step: 272/466, loss: 0.002511512953788042
2023-01-22 13:21:55.033862: step: 274/466, loss: 0.012186328880488873
2023-01-22 13:21:55.588710: step: 276/466, loss: 0.005697715096175671
2023-01-22 13:21:56.234512: step: 278/466, loss: 0.005176094360649586
2023-01-22 13:21:56.864889: step: 280/466, loss: 0.0028243553824722767
2023-01-22 13:21:57.530148: step: 282/466, loss: 0.000831534736789763
2023-01-22 13:21:58.161570: step: 284/466, loss: 0.005542241036891937
2023-01-22 13:21:58.797981: step: 286/466, loss: 0.012190895155072212
2023-01-22 13:21:59.408663: step: 288/466, loss: 0.0004219510010443628
2023-01-22 13:22:00.117208: step: 290/466, loss: 0.014722839929163456
2023-01-22 13:22:00.749892: step: 292/466, loss: 0.0005669038509950042
2023-01-22 13:22:01.332598: step: 294/466, loss: 0.027332326397299767
2023-01-22 13:22:02.004172: step: 296/466, loss: 0.013245755806565285
2023-01-22 13:22:02.626896: step: 298/466, loss: 0.004525027237832546
2023-01-22 13:22:03.248871: step: 300/466, loss: 0.011388568207621574
2023-01-22 13:22:03.979620: step: 302/466, loss: 0.16052161157131195
2023-01-22 13:22:04.595863: step: 304/466, loss: 0.025578703731298447
2023-01-22 13:22:05.272071: step: 306/466, loss: 0.0348832868039608
2023-01-22 13:22:05.914160: step: 308/466, loss: 0.006878445856273174
2023-01-22 13:22:06.529198: step: 310/466, loss: 0.001989806769415736
2023-01-22 13:22:07.212294: step: 312/466, loss: 0.0032198973931372166
2023-01-22 13:22:07.824838: step: 314/466, loss: 0.1315160095691681
2023-01-22 13:22:08.508713: step: 316/466, loss: 0.04008382931351662
2023-01-22 13:22:09.149691: step: 318/466, loss: 0.0020131836645305157
2023-01-22 13:22:09.808966: step: 320/466, loss: 0.004674920812249184
2023-01-22 13:22:10.556476: step: 322/466, loss: 0.015164303593337536
2023-01-22 13:22:11.194690: step: 324/466, loss: 0.04455585032701492
2023-01-22 13:22:11.764660: step: 326/466, loss: 0.01877361163496971
2023-01-22 13:22:12.373721: step: 328/466, loss: 0.0015368256717920303
2023-01-22 13:22:13.093505: step: 330/466, loss: 0.040641941130161285
2023-01-22 13:22:13.801025: step: 332/466, loss: 0.2505246102809906
2023-01-22 13:22:14.450250: step: 334/466, loss: 0.005070647224783897
2023-01-22 13:22:15.075423: step: 336/466, loss: 0.00018404850561637431
2023-01-22 13:22:15.671252: step: 338/466, loss: 0.031194377690553665
2023-01-22 13:22:16.298810: step: 340/466, loss: 0.005099698901176453
2023-01-22 13:22:16.848706: step: 342/466, loss: 0.0013495985185727477
2023-01-22 13:22:17.483540: step: 344/466, loss: 0.1284133791923523
2023-01-22 13:22:18.113966: step: 346/466, loss: 0.004485417623072863
2023-01-22 13:22:18.742459: step: 348/466, loss: 0.004613775759935379
2023-01-22 13:22:19.349090: step: 350/466, loss: 0.03906206414103508
2023-01-22 13:22:19.979839: step: 352/466, loss: 0.013930348679423332
2023-01-22 13:22:20.573457: step: 354/466, loss: 0.012603990733623505
2023-01-22 13:22:21.198900: step: 356/466, loss: 0.07953281700611115
2023-01-22 13:22:21.806535: step: 358/466, loss: 0.03879635035991669
2023-01-22 13:22:22.336468: step: 360/466, loss: 0.0024805129505693913
2023-01-22 13:22:23.027250: step: 362/466, loss: 0.014602967537939548
2023-01-22 13:22:23.654531: step: 364/466, loss: 0.0034003867767751217
2023-01-22 13:22:24.187548: step: 366/466, loss: 0.012691373936831951
2023-01-22 13:22:24.781567: step: 368/466, loss: 0.0021625852677971125
2023-01-22 13:22:25.511690: step: 370/466, loss: 0.02687658928334713
2023-01-22 13:22:26.222442: step: 372/466, loss: 0.03532731533050537
2023-01-22 13:22:26.815871: step: 374/466, loss: 0.025283852592110634
2023-01-22 13:22:27.450239: step: 376/466, loss: 0.053645867854356766
2023-01-22 13:22:28.064288: step: 378/466, loss: 0.0241458211094141
2023-01-22 13:22:28.709841: step: 380/466, loss: 0.008507013320922852
2023-01-22 13:22:29.319708: step: 382/466, loss: 0.0024003516882658005
2023-01-22 13:22:29.978999: step: 384/466, loss: 0.06329336762428284
2023-01-22 13:22:30.610240: step: 386/466, loss: 0.04357927665114403
2023-01-22 13:22:31.238777: step: 388/466, loss: 0.009667825885117054
2023-01-22 13:22:31.867433: step: 390/466, loss: 0.032328635454177856
2023-01-22 13:22:32.485650: step: 392/466, loss: 0.009936768561601639
2023-01-22 13:22:33.122918: step: 394/466, loss: 0.001956153428182006
2023-01-22 13:22:33.755141: step: 396/466, loss: 0.021120784804224968
2023-01-22 13:22:34.370027: step: 398/466, loss: 0.025271767750382423
2023-01-22 13:22:34.969125: step: 400/466, loss: 0.004417846444994211
2023-01-22 13:22:35.613869: step: 402/466, loss: 0.031339503824710846
2023-01-22 13:22:36.165643: step: 404/466, loss: 0.02603183314204216
2023-01-22 13:22:36.747174: step: 406/466, loss: 0.03182559832930565
2023-01-22 13:22:37.404993: step: 408/466, loss: 0.0009004041203297675
2023-01-22 13:22:37.997631: step: 410/466, loss: 0.003806175896897912
2023-01-22 13:22:38.585244: step: 412/466, loss: 0.45821917057037354
2023-01-22 13:22:39.280663: step: 414/466, loss: 0.0021742149256169796
2023-01-22 13:22:39.928352: step: 416/466, loss: 0.014737543649971485
2023-01-22 13:22:40.496007: step: 418/466, loss: 0.0005118109402246773
2023-01-22 13:22:41.137751: step: 420/466, loss: 0.03900913894176483
2023-01-22 13:22:41.759903: step: 422/466, loss: 0.0010500759817659855
2023-01-22 13:22:42.509664: step: 424/466, loss: 0.005701580550521612
2023-01-22 13:22:43.072440: step: 426/466, loss: 0.009693636558949947
2023-01-22 13:22:43.718767: step: 428/466, loss: 0.005985029973089695
2023-01-22 13:22:44.305543: step: 430/466, loss: 0.009088157676160336
2023-01-22 13:22:44.903301: step: 432/466, loss: 0.001938398228958249
2023-01-22 13:22:45.503670: step: 434/466, loss: 0.020009316504001617
2023-01-22 13:22:46.206071: step: 436/466, loss: 5.809044887428172e-05
2023-01-22 13:22:46.775832: step: 438/466, loss: 0.01283319666981697
2023-01-22 13:22:47.364833: step: 440/466, loss: 0.010783478617668152
2023-01-22 13:22:48.031094: step: 442/466, loss: 0.6042597889900208
2023-01-22 13:22:48.786572: step: 444/466, loss: 0.020227300003170967
2023-01-22 13:22:49.324591: step: 446/466, loss: 0.05583236739039421
2023-01-22 13:22:50.013293: step: 448/466, loss: 0.17182712256908417
2023-01-22 13:22:50.635577: step: 450/466, loss: 0.033569566905498505
2023-01-22 13:22:51.280059: step: 452/466, loss: 0.3938918113708496
2023-01-22 13:22:51.969585: step: 454/466, loss: 0.028887035325169563
2023-01-22 13:22:52.597078: step: 456/466, loss: 0.004464501515030861
2023-01-22 13:22:53.267388: step: 458/466, loss: 0.008131398819386959
2023-01-22 13:22:53.895786: step: 460/466, loss: 0.11341170966625214
2023-01-22 13:22:54.474378: step: 462/466, loss: 0.0030010126065462828
2023-01-22 13:22:55.143773: step: 464/466, loss: 0.08654288202524185
2023-01-22 13:22:55.735037: step: 466/466, loss: 0.01917041465640068
2023-01-22 13:22:56.287241: step: 468/466, loss: 0.017753876745700836
2023-01-22 13:22:56.843232: step: 470/466, loss: 0.0015732371248304844
2023-01-22 13:22:57.492053: step: 472/466, loss: 0.0013067168183624744
2023-01-22 13:22:58.150225: step: 474/466, loss: 0.007370651233941317
2023-01-22 13:22:58.801147: step: 476/466, loss: 0.012751343660056591
2023-01-22 13:22:59.429847: step: 478/466, loss: 0.008689838461577892
2023-01-22 13:23:00.008410: step: 480/466, loss: 0.08662420511245728
2023-01-22 13:23:00.652390: step: 482/466, loss: 0.07603882998228073
2023-01-22 13:23:01.291291: step: 484/466, loss: 0.023959536105394363
2023-01-22 13:23:01.969968: step: 486/466, loss: 0.055649999529123306
2023-01-22 13:23:02.661926: step: 488/466, loss: 0.0018876695539802313
2023-01-22 13:23:03.220246: step: 490/466, loss: 0.047939665615558624
2023-01-22 13:23:03.862065: step: 492/466, loss: 1.2007006406784058
2023-01-22 13:23:04.473327: step: 494/466, loss: 0.020490868017077446
2023-01-22 13:23:05.103963: step: 496/466, loss: 0.009708845987915993
2023-01-22 13:23:05.728007: step: 498/466, loss: 0.034252651035785675
2023-01-22 13:23:06.347026: step: 500/466, loss: 0.008174884133040905
2023-01-22 13:23:06.952020: step: 502/466, loss: 0.0036410826724022627
2023-01-22 13:23:07.602812: step: 504/466, loss: 0.012882047332823277
2023-01-22 13:23:08.247934: step: 506/466, loss: 0.1272018998861313
2023-01-22 13:23:08.853390: step: 508/466, loss: 0.02409953624010086
2023-01-22 13:23:09.405896: step: 510/466, loss: 0.03641194477677345
2023-01-22 13:23:10.023523: step: 512/466, loss: 0.0027759310323745012
2023-01-22 13:23:10.665988: step: 514/466, loss: 0.008434903807938099
2023-01-22 13:23:11.250282: step: 516/466, loss: 0.004168310668319464
2023-01-22 13:23:11.926449: step: 518/466, loss: 0.024747787043452263
2023-01-22 13:23:12.527602: step: 520/466, loss: 0.4482802748680115
2023-01-22 13:23:13.188890: step: 522/466, loss: 0.019972914829850197
2023-01-22 13:23:13.813894: step: 524/466, loss: 0.00814759824424982
2023-01-22 13:23:14.413788: step: 526/466, loss: 0.021629955619573593
2023-01-22 13:23:15.064737: step: 528/466, loss: 0.008018465712666512
2023-01-22 13:23:15.746057: step: 530/466, loss: 0.025636399164795876
2023-01-22 13:23:16.309109: step: 532/466, loss: 0.0006201571086421609
2023-01-22 13:23:16.916743: step: 534/466, loss: 0.04001878201961517
2023-01-22 13:23:17.498860: step: 536/466, loss: 0.016146061941981316
2023-01-22 13:23:18.063827: step: 538/466, loss: 0.02312307059764862
2023-01-22 13:23:18.672323: step: 540/466, loss: 0.00308585655875504
2023-01-22 13:23:19.269645: step: 542/466, loss: 0.02875497005879879
2023-01-22 13:23:19.805786: step: 544/466, loss: 0.010568222962319851
2023-01-22 13:23:20.428974: step: 546/466, loss: 0.0030713172163814306
2023-01-22 13:23:21.049494: step: 548/466, loss: 0.014920078217983246
2023-01-22 13:23:21.674940: step: 550/466, loss: 0.015367996878921986
2023-01-22 13:23:22.339945: step: 552/466, loss: 0.01573663018643856
2023-01-22 13:23:22.925516: step: 554/466, loss: 0.02735070139169693
2023-01-22 13:23:23.565295: step: 556/466, loss: 0.009266615845263004
2023-01-22 13:23:24.224822: step: 558/466, loss: 0.008889292366802692
2023-01-22 13:23:24.891573: step: 560/466, loss: 0.11103135347366333
2023-01-22 13:23:25.510290: step: 562/466, loss: 0.0005813875468447804
2023-01-22 13:23:26.202108: step: 564/466, loss: 0.7120652198791504
2023-01-22 13:23:26.893964: step: 566/466, loss: 0.013271020725369453
2023-01-22 13:23:27.476921: step: 568/466, loss: 0.05157516524195671
2023-01-22 13:23:28.092950: step: 570/466, loss: 0.00710834376513958
2023-01-22 13:23:28.657839: step: 572/466, loss: 0.008108958601951599
2023-01-22 13:23:29.297039: step: 574/466, loss: 0.039710644632577896
2023-01-22 13:23:29.903986: step: 576/466, loss: 0.008387508802115917
2023-01-22 13:23:30.494516: step: 578/466, loss: 0.00163850758690387
2023-01-22 13:23:31.029613: step: 580/466, loss: 0.0025524578522890806
2023-01-22 13:23:31.554949: step: 582/466, loss: 0.007011826615780592
2023-01-22 13:23:32.153605: step: 584/466, loss: 0.048207804560661316
2023-01-22 13:23:32.724914: step: 586/466, loss: 0.0020360019989311695
2023-01-22 13:23:33.413123: step: 588/466, loss: 0.004026514478027821
2023-01-22 13:23:34.040345: step: 590/466, loss: 0.035144511610269547
2023-01-22 13:23:34.574377: step: 592/466, loss: 0.008531235158443451
2023-01-22 13:23:35.143204: step: 594/466, loss: 0.0019683947321027517
2023-01-22 13:23:35.782898: step: 596/466, loss: 0.040554702281951904
2023-01-22 13:23:36.436806: step: 598/466, loss: 0.015702493488788605
2023-01-22 13:23:37.059496: step: 600/466, loss: 0.0009891258087009192
2023-01-22 13:23:37.654298: step: 602/466, loss: 0.03403882682323456
2023-01-22 13:23:38.290861: step: 604/466, loss: 0.013812286779284477
2023-01-22 13:23:38.945474: step: 606/466, loss: 0.005240297876298428
2023-01-22 13:23:39.617243: step: 608/466, loss: 0.02737869881093502
2023-01-22 13:23:40.219788: step: 610/466, loss: 0.04239679500460625
2023-01-22 13:23:40.880555: step: 612/466, loss: 0.020463278517127037
2023-01-22 13:23:41.431316: step: 614/466, loss: 0.008261370472609997
2023-01-22 13:23:42.003708: step: 616/466, loss: 0.0028720779810100794
2023-01-22 13:23:42.584102: step: 618/466, loss: 0.018434986472129822
2023-01-22 13:23:43.157119: step: 620/466, loss: 0.025052722543478012
2023-01-22 13:23:43.848659: step: 622/466, loss: 0.11167764663696289
2023-01-22 13:23:44.434095: step: 624/466, loss: 0.09473086893558502
2023-01-22 13:23:45.060285: step: 626/466, loss: 0.0028115841560065746
2023-01-22 13:23:45.642061: step: 628/466, loss: 0.07390471547842026
2023-01-22 13:23:46.236493: step: 630/466, loss: 0.03992309048771858
2023-01-22 13:23:46.812453: step: 632/466, loss: 0.06804033368825912
2023-01-22 13:23:47.489271: step: 634/466, loss: 0.06968791037797928
2023-01-22 13:23:48.216927: step: 636/466, loss: 0.0007771103992126882
2023-01-22 13:23:48.833417: step: 638/466, loss: 0.028963560238480568
2023-01-22 13:23:49.475479: step: 640/466, loss: 0.006525433622300625
2023-01-22 13:23:50.181724: step: 642/466, loss: 0.060342513024806976
2023-01-22 13:23:50.804063: step: 644/466, loss: 0.029246270656585693
2023-01-22 13:23:51.325196: step: 646/466, loss: 0.00955758336931467
2023-01-22 13:23:51.965257: step: 648/466, loss: 0.01655466854572296
2023-01-22 13:23:52.622927: step: 650/466, loss: 0.0002035806974163279
2023-01-22 13:23:53.234190: step: 652/466, loss: 0.12468570470809937
2023-01-22 13:23:53.845323: step: 654/466, loss: 0.0026691860985010862
2023-01-22 13:23:54.463941: step: 656/466, loss: 0.0038278503343462944
2023-01-22 13:23:55.046245: step: 658/466, loss: 0.0074297040700912476
2023-01-22 13:23:55.636430: step: 660/466, loss: 0.016870766878128052
2023-01-22 13:23:56.267431: step: 662/466, loss: 0.048004359006881714
2023-01-22 13:23:56.865124: step: 664/466, loss: 0.01672959513962269
2023-01-22 13:23:57.507365: step: 666/466, loss: 0.04428689926862717
2023-01-22 13:23:58.099327: step: 668/466, loss: 0.02727423422038555
2023-01-22 13:23:58.719045: step: 670/466, loss: 0.10729333013296127
2023-01-22 13:23:59.343240: step: 672/466, loss: 0.001751934876665473
2023-01-22 13:23:59.968495: step: 674/466, loss: 0.09825156629085541
2023-01-22 13:24:00.580480: step: 676/466, loss: 0.04435792937874794
2023-01-22 13:24:01.227542: step: 678/466, loss: 0.006695875432342291
2023-01-22 13:24:01.859535: step: 680/466, loss: 0.009862974286079407
2023-01-22 13:24:02.465385: step: 682/466, loss: 0.015884706750512123
2023-01-22 13:24:03.088884: step: 684/466, loss: 0.0009615541785024107
2023-01-22 13:24:03.822800: step: 686/466, loss: 0.03612905740737915
2023-01-22 13:24:04.489389: step: 688/466, loss: 0.03043614886701107
2023-01-22 13:24:05.173531: step: 690/466, loss: 0.01803179271519184
2023-01-22 13:24:05.743121: step: 692/466, loss: 0.0025244855787605047
2023-01-22 13:24:06.282408: step: 694/466, loss: 0.004815980792045593
2023-01-22 13:24:06.883970: step: 696/466, loss: 0.007434464525431395
2023-01-22 13:24:07.505917: step: 698/466, loss: 0.13055790960788727
2023-01-22 13:24:08.079576: step: 700/466, loss: 0.0001918329653562978
2023-01-22 13:24:08.675324: step: 702/466, loss: 0.016086140647530556
2023-01-22 13:24:09.261865: step: 704/466, loss: 0.0005090544000267982
2023-01-22 13:24:09.845232: step: 706/466, loss: 0.003033475251868367
2023-01-22 13:24:10.429133: step: 708/466, loss: 0.0037266057915985584
2023-01-22 13:24:11.021263: step: 710/466, loss: 0.01481724064797163
2023-01-22 13:24:11.710182: step: 712/466, loss: 0.03236960247159004
2023-01-22 13:24:12.259024: step: 714/466, loss: 0.0010790909873321652
2023-01-22 13:24:12.828139: step: 716/466, loss: 0.01934128813445568
2023-01-22 13:24:13.409818: step: 718/466, loss: 0.022884057834744453
2023-01-22 13:24:14.142010: step: 720/466, loss: 0.026454202830791473
2023-01-22 13:24:14.767031: step: 722/466, loss: 0.022250041365623474
2023-01-22 13:24:15.351223: step: 724/466, loss: 0.1101565808057785
2023-01-22 13:24:16.008025: step: 726/466, loss: 0.018408456817269325
2023-01-22 13:24:16.632680: step: 728/466, loss: 0.06344349682331085
2023-01-22 13:24:17.244139: step: 730/466, loss: 0.01834847964346409
2023-01-22 13:24:17.883357: step: 732/466, loss: 0.06949294358491898
2023-01-22 13:24:18.500361: step: 734/466, loss: 0.020755456760525703
2023-01-22 13:24:19.103610: step: 736/466, loss: 0.10671348869800568
2023-01-22 13:24:19.753306: step: 738/466, loss: 0.04026241600513458
2023-01-22 13:24:20.335857: step: 740/466, loss: 0.10532877594232559
2023-01-22 13:24:20.961506: step: 742/466, loss: 1.2018945217132568
2023-01-22 13:24:21.553383: step: 744/466, loss: 0.03034796752035618
2023-01-22 13:24:22.172589: step: 746/466, loss: 0.05075696110725403
2023-01-22 13:24:22.827328: step: 748/466, loss: 0.004184384364634752
2023-01-22 13:24:23.482829: step: 750/466, loss: 0.03211819753050804
2023-01-22 13:24:24.069008: step: 752/466, loss: 0.016765151172876358
2023-01-22 13:24:24.593626: step: 754/466, loss: 0.010934228077530861
2023-01-22 13:24:25.255186: step: 756/466, loss: 0.0008892195182852447
2023-01-22 13:24:25.917876: step: 758/466, loss: 0.020512528717517853
2023-01-22 13:24:26.679116: step: 760/466, loss: 0.03005942888557911
2023-01-22 13:24:27.280410: step: 762/466, loss: 0.035132911056280136
2023-01-22 13:24:27.909791: step: 764/466, loss: 0.014512010850012302
2023-01-22 13:24:28.599109: step: 766/466, loss: 0.022986402735114098
2023-01-22 13:24:29.244386: step: 768/466, loss: 0.00485311821103096
2023-01-22 13:24:29.832362: step: 770/466, loss: 0.03989977389574051
2023-01-22 13:24:30.498145: step: 772/466, loss: 0.04922888055443764
2023-01-22 13:24:31.080469: step: 774/466, loss: 0.0006349222967401147
2023-01-22 13:24:31.711297: step: 776/466, loss: 0.06173509359359741
2023-01-22 13:24:32.319399: step: 778/466, loss: 0.016244810074567795
2023-01-22 13:24:32.931080: step: 780/466, loss: 0.024921001866459846
2023-01-22 13:24:33.595049: step: 782/466, loss: 0.01212544646114111
2023-01-22 13:24:34.209913: step: 784/466, loss: 0.002041733590885997
2023-01-22 13:24:34.818145: step: 786/466, loss: 0.005243290215730667
2023-01-22 13:24:35.397864: step: 788/466, loss: 0.03087429516017437
2023-01-22 13:24:36.043625: step: 790/466, loss: 0.055014707148075104
2023-01-22 13:24:36.715067: step: 792/466, loss: 0.006934677716344595
2023-01-22 13:24:37.339663: step: 794/466, loss: 0.13290882110595703
2023-01-22 13:24:38.036590: step: 796/466, loss: 0.09976620972156525
2023-01-22 13:24:38.682120: step: 798/466, loss: 0.020965615287423134
2023-01-22 13:24:39.288194: step: 800/466, loss: 0.018352339044213295
2023-01-22 13:24:39.960126: step: 802/466, loss: 0.0030997898429632187
2023-01-22 13:24:40.559953: step: 804/466, loss: 0.005746449343860149
2023-01-22 13:24:41.282022: step: 806/466, loss: 0.013343226164579391
2023-01-22 13:24:41.980781: step: 808/466, loss: 0.1776353120803833
2023-01-22 13:24:42.665399: step: 810/466, loss: 0.05390021204948425
2023-01-22 13:24:43.338465: step: 812/466, loss: 0.0040868245996534824
2023-01-22 13:24:43.928466: step: 814/466, loss: 0.008829116821289062
2023-01-22 13:24:44.495188: step: 816/466, loss: 0.6879344582557678
2023-01-22 13:24:45.147140: step: 818/466, loss: 0.012122377753257751
2023-01-22 13:24:45.781845: step: 820/466, loss: 0.00031059340108186007
2023-01-22 13:24:46.492819: step: 822/466, loss: 0.15375883877277374
2023-01-22 13:24:47.101360: step: 824/466, loss: 0.005931135267019272
2023-01-22 13:24:47.699895: step: 826/466, loss: 0.00963269080966711
2023-01-22 13:24:48.310921: step: 828/466, loss: 0.006335984915494919
2023-01-22 13:24:48.894584: step: 830/466, loss: 0.02565760910511017
2023-01-22 13:24:49.476324: step: 832/466, loss: 0.019776877015829086
2023-01-22 13:24:50.089491: step: 834/466, loss: 0.013118351809680462
2023-01-22 13:24:50.765048: step: 836/466, loss: 0.2517741918563843
2023-01-22 13:24:51.405548: step: 838/466, loss: 0.019498251378536224
2023-01-22 13:24:52.021459: step: 840/466, loss: 0.02611498534679413
2023-01-22 13:24:52.615554: step: 842/466, loss: 0.011649729683995247
2023-01-22 13:24:53.224710: step: 844/466, loss: 0.03165111690759659
2023-01-22 13:24:53.809412: step: 846/466, loss: 0.01670054905116558
2023-01-22 13:24:54.409425: step: 848/466, loss: 0.04889087378978729
2023-01-22 13:24:55.043183: step: 850/466, loss: 0.1464008092880249
2023-01-22 13:24:55.739539: step: 852/466, loss: 0.01969340443611145
2023-01-22 13:24:56.339898: step: 854/466, loss: 0.05219658836722374
2023-01-22 13:24:56.915785: step: 856/466, loss: 0.0039998069405555725
2023-01-22 13:24:57.508331: step: 858/466, loss: 0.010624684393405914
2023-01-22 13:24:58.192597: step: 860/466, loss: 0.030279122292995453
2023-01-22 13:24:58.782204: step: 862/466, loss: 0.003146994626149535
2023-01-22 13:24:59.367199: step: 864/466, loss: 0.040422990918159485
2023-01-22 13:24:59.926622: step: 866/466, loss: 0.008086932823061943
2023-01-22 13:25:00.547486: step: 868/466, loss: 0.0012018276611343026
2023-01-22 13:25:01.135962: step: 870/466, loss: 0.0007978557841852307
2023-01-22 13:25:01.837026: step: 872/466, loss: 0.02200395241379738
2023-01-22 13:25:02.491403: step: 874/466, loss: 0.004426547791808844
2023-01-22 13:25:03.099518: step: 876/466, loss: 0.007263008039444685
2023-01-22 13:25:03.726896: step: 878/466, loss: 0.015457775443792343
2023-01-22 13:25:04.308628: step: 880/466, loss: 0.09172531962394714
2023-01-22 13:25:04.907698: step: 882/466, loss: 0.17304280400276184
2023-01-22 13:25:05.540927: step: 884/466, loss: 0.001824880950152874
2023-01-22 13:25:06.221035: step: 886/466, loss: 0.07621315866708755
2023-01-22 13:25:06.807107: step: 888/466, loss: 0.013939729891717434
2023-01-22 13:25:07.405335: step: 890/466, loss: 0.00634580384939909
2023-01-22 13:25:07.959336: step: 892/466, loss: 0.006481233984231949
2023-01-22 13:25:08.509009: step: 894/466, loss: 0.0010673175565898418
2023-01-22 13:25:09.151187: step: 896/466, loss: 0.02853173203766346
2023-01-22 13:25:09.782020: step: 898/466, loss: 0.04330425336956978
2023-01-22 13:25:10.403831: step: 900/466, loss: 0.011705813929438591
2023-01-22 13:25:11.039980: step: 902/466, loss: 0.0013577844947576523
2023-01-22 13:25:11.662192: step: 904/466, loss: 0.004012433812022209
2023-01-22 13:25:12.329339: step: 906/466, loss: 0.03765256330370903
2023-01-22 13:25:12.998892: step: 908/466, loss: 0.017649630084633827
2023-01-22 13:25:13.656567: step: 910/466, loss: 0.04798159748315811
2023-01-22 13:25:14.296450: step: 912/466, loss: 0.0020341812632977962
2023-01-22 13:25:14.912701: step: 914/466, loss: 0.0017377976328134537
2023-01-22 13:25:15.514245: step: 916/466, loss: 0.001674551866017282
2023-01-22 13:25:16.142084: step: 918/466, loss: 0.0009396459208801389
2023-01-22 13:25:16.783137: step: 920/466, loss: 0.010935609228909016
2023-01-22 13:25:17.431514: step: 922/466, loss: 0.040163006633520126
2023-01-22 13:25:18.033534: step: 924/466, loss: 0.029091281816363335
2023-01-22 13:25:18.690060: step: 926/466, loss: 0.014700681902468204
2023-01-22 13:25:19.370769: step: 928/466, loss: 0.02362331934273243
2023-01-22 13:25:19.960179: step: 930/466, loss: 0.0006369992042891681
2023-01-22 13:25:20.550250: step: 932/466, loss: 0.33109328150749207
==================================================
Loss: 0.052
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33166279780700536, 'r': 0.3360681860131705, 'f1': 0.3338509595267499}, 'combined': 0.2459954438618157, 'epoch': 30}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3381150108625124, 'r': 0.28262634361546346, 'f1': 0.3078905845476905}, 'combined': 0.19279130060462868, 'epoch': 30}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3169809863040221, 'r': 0.35006249341355, 'f1': 0.33270141393857683}, 'combined': 0.24514841027053028, 'epoch': 30}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3488703006857131, 'r': 0.29664985892392015, 'f1': 0.32064784946065056}, 'combined': 0.19871134332772708, 'epoch': 30}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.29173206660687934, 'r': 0.3493034801308176, 'f1': 0.31793252854739357}, 'combined': 0.2342660736665005, 'epoch': 30}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.34447544694308446, 'r': 0.2882028333179055, 'f1': 0.3138365988365988}, 'combined': 0.2081886348718032, 'epoch': 30}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.28125, 'r': 0.32142857142857145, 'f1': 0.30000000000000004}, 'combined': 0.2, 'epoch': 30}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.26785714285714285, 'r': 0.32608695652173914, 'f1': 0.29411764705882354}, 'combined': 0.14705882352941177, 'epoch': 30}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.20689655172413793, 'f1': 0.2553191489361702}, 'combined': 0.17021276595744678, 'epoch': 30}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:27:57.954610: step: 2/466, loss: 0.007168573793023825
2023-01-22 13:27:58.568062: step: 4/466, loss: 0.0020445086993277073
2023-01-22 13:27:59.197449: step: 6/466, loss: 0.006324405316263437
2023-01-22 13:27:59.747097: step: 8/466, loss: 0.003093923442065716
2023-01-22 13:28:00.565644: step: 10/466, loss: 0.07295311987400055
2023-01-22 13:28:01.195564: step: 12/466, loss: 0.033171072602272034
2023-01-22 13:28:01.830350: step: 14/466, loss: 0.018763521686196327
2023-01-22 13:28:02.446867: step: 16/466, loss: 0.012126329354941845
2023-01-22 13:28:03.100635: step: 18/466, loss: 0.032156869769096375
2023-01-22 13:28:03.753004: step: 20/466, loss: 0.03246133774518967
2023-01-22 13:28:04.414006: step: 22/466, loss: 0.009170664474368095
2023-01-22 13:28:05.035779: step: 24/466, loss: 0.02240617945790291
2023-01-22 13:28:05.661899: step: 26/466, loss: 0.018498243764042854
2023-01-22 13:28:06.244143: step: 28/466, loss: 0.004776320420205593
2023-01-22 13:28:06.790433: step: 30/466, loss: 0.004571563098579645
2023-01-22 13:28:07.444795: step: 32/466, loss: 0.0020251087844371796
2023-01-22 13:28:08.103989: step: 34/466, loss: 0.0005824713734909892
2023-01-22 13:28:08.739491: step: 36/466, loss: 0.025997484102845192
2023-01-22 13:28:09.336213: step: 38/466, loss: 0.005126075353473425
2023-01-22 13:28:09.953313: step: 40/466, loss: 0.0008517690584994853
2023-01-22 13:28:10.588420: step: 42/466, loss: 0.03736488148570061
2023-01-22 13:28:11.279776: step: 44/466, loss: 0.006267243530601263
2023-01-22 13:28:11.883723: step: 46/466, loss: 0.0033513489179313183
2023-01-22 13:28:12.508818: step: 48/466, loss: 0.2597365975379944
2023-01-22 13:28:13.156611: step: 50/466, loss: 0.01199096068739891
2023-01-22 13:28:13.724628: step: 52/466, loss: 0.0017128143226727843
2023-01-22 13:28:14.441149: step: 54/466, loss: 0.00920811016112566
2023-01-22 13:28:15.106275: step: 56/466, loss: 0.0018016818212345243
2023-01-22 13:28:15.705993: step: 58/466, loss: 0.006626426707953215
2023-01-22 13:28:16.284233: step: 60/466, loss: 0.0019828348886221647
2023-01-22 13:28:16.850576: step: 62/466, loss: 0.012216060422360897
2023-01-22 13:28:17.444171: step: 64/466, loss: 0.11005613207817078
2023-01-22 13:28:18.023317: step: 66/466, loss: 0.0032541663385927677
2023-01-22 13:28:18.566540: step: 68/466, loss: 0.011161950416862965
2023-01-22 13:28:19.148683: step: 70/466, loss: 0.019788235425949097
2023-01-22 13:28:19.776357: step: 72/466, loss: 0.007697759661823511
2023-01-22 13:28:20.368993: step: 74/466, loss: 0.008653736673295498
2023-01-22 13:28:20.942485: step: 76/466, loss: 0.040688205510377884
2023-01-22 13:28:21.542823: step: 78/466, loss: 0.015366827137768269
2023-01-22 13:28:22.213104: step: 80/466, loss: 0.001172990771010518
2023-01-22 13:28:22.849977: step: 82/466, loss: 0.0018485992914065719
2023-01-22 13:28:23.409174: step: 84/466, loss: 0.004098563455045223
2023-01-22 13:28:23.998195: step: 86/466, loss: 0.027816014364361763
2023-01-22 13:28:24.614526: step: 88/466, loss: 0.0030274942982941866
2023-01-22 13:28:25.385309: step: 90/466, loss: 0.03170846402645111
2023-01-22 13:28:25.949257: step: 92/466, loss: 0.0002961618884000927
2023-01-22 13:28:26.568887: step: 94/466, loss: 0.0015852575888857245
2023-01-22 13:28:27.228228: step: 96/466, loss: 0.02714916318655014
2023-01-22 13:28:27.824324: step: 98/466, loss: 0.005829785484820604
2023-01-22 13:28:28.509306: step: 100/466, loss: 0.005810820963233709
2023-01-22 13:28:29.082979: step: 102/466, loss: 0.0010619497625157237
2023-01-22 13:28:29.682855: step: 104/466, loss: 0.009592894464731216
2023-01-22 13:28:30.355781: step: 106/466, loss: 0.05438638851046562
2023-01-22 13:28:30.909017: step: 108/466, loss: 3.570752960513346e-05
2023-01-22 13:28:31.516560: step: 110/466, loss: 0.09015724807977676
2023-01-22 13:28:32.198707: step: 112/466, loss: 0.005148747004568577
2023-01-22 13:28:32.804732: step: 114/466, loss: 0.015584941953420639
2023-01-22 13:28:33.532836: step: 116/466, loss: 0.029465945437550545
2023-01-22 13:28:34.145860: step: 118/466, loss: 0.010357551276683807
2023-01-22 13:28:34.762172: step: 120/466, loss: 0.012574763968586922
2023-01-22 13:28:35.422181: step: 122/466, loss: 0.020364994183182716
2023-01-22 13:28:36.009403: step: 124/466, loss: 0.0037056943401694298
2023-01-22 13:28:36.647631: step: 126/466, loss: 0.0012162663042545319
2023-01-22 13:28:37.298080: step: 128/466, loss: 0.016808146610856056
2023-01-22 13:28:37.911298: step: 130/466, loss: 0.01613013446331024
2023-01-22 13:28:38.505082: step: 132/466, loss: 0.010568464174866676
2023-01-22 13:28:39.142167: step: 134/466, loss: 0.01669691875576973
2023-01-22 13:28:39.732525: step: 136/466, loss: 0.0014973332872614264
2023-01-22 13:28:40.371328: step: 138/466, loss: 0.002069574547931552
2023-01-22 13:28:41.011769: step: 140/466, loss: 0.04698267579078674
2023-01-22 13:28:41.677989: step: 142/466, loss: 0.05436408147215843
2023-01-22 13:28:42.287945: step: 144/466, loss: 0.03474747762084007
2023-01-22 13:28:42.884718: step: 146/466, loss: 0.009406505152583122
2023-01-22 13:28:43.463017: step: 148/466, loss: 0.00043175797327421606
2023-01-22 13:28:44.100338: step: 150/466, loss: 0.013636465184390545
2023-01-22 13:28:44.680155: step: 152/466, loss: 0.0016792012611404061
2023-01-22 13:28:45.249014: step: 154/466, loss: 0.029004333540797234
2023-01-22 13:28:45.866291: step: 156/466, loss: 0.005969460587948561
2023-01-22 13:28:46.512339: step: 158/466, loss: 0.24402426183223724
2023-01-22 13:28:47.122063: step: 160/466, loss: 0.017112595960497856
2023-01-22 13:28:47.727925: step: 162/466, loss: 0.020864853635430336
2023-01-22 13:28:48.326655: step: 164/466, loss: 0.008625946007668972
2023-01-22 13:28:48.954100: step: 166/466, loss: 0.041083239018917084
2023-01-22 13:28:49.550389: step: 168/466, loss: 0.011716339737176895
2023-01-22 13:28:50.185756: step: 170/466, loss: 0.07246832549571991
2023-01-22 13:28:50.794316: step: 172/466, loss: 5.223365224082954e-05
2023-01-22 13:28:51.449378: step: 174/466, loss: 0.07541394978761673
2023-01-22 13:28:52.135459: step: 176/466, loss: 0.02161840908229351
2023-01-22 13:28:52.728300: step: 178/466, loss: 0.005124109797179699
2023-01-22 13:28:53.416480: step: 180/466, loss: 0.0006222125375643373
2023-01-22 13:28:54.096162: step: 182/466, loss: 0.00390928378328681
2023-01-22 13:28:54.729990: step: 184/466, loss: 0.009930741041898727
2023-01-22 13:28:55.292837: step: 186/466, loss: 0.006320476066321135
2023-01-22 13:28:55.916029: step: 188/466, loss: 0.013346170075237751
2023-01-22 13:28:56.574008: step: 190/466, loss: 0.0171652901917696
2023-01-22 13:28:57.171983: step: 192/466, loss: 0.03007993847131729
2023-01-22 13:28:57.738786: step: 194/466, loss: 0.012615848332643509
2023-01-22 13:28:58.341799: step: 196/466, loss: 0.011521113105118275
2023-01-22 13:28:58.935639: step: 198/466, loss: 0.06034286320209503
2023-01-22 13:28:59.530596: step: 200/466, loss: 0.05058571696281433
2023-01-22 13:29:00.168148: step: 202/466, loss: 0.009598346427083015
2023-01-22 13:29:00.863674: step: 204/466, loss: 0.2493104636669159
2023-01-22 13:29:01.571122: step: 206/466, loss: 0.029918083921074867
2023-01-22 13:29:02.176392: step: 208/466, loss: 0.22628265619277954
2023-01-22 13:29:02.769312: step: 210/466, loss: 0.04101979732513428
2023-01-22 13:29:03.373017: step: 212/466, loss: 0.004658593330532312
2023-01-22 13:29:03.987206: step: 214/466, loss: 0.05677751824259758
2023-01-22 13:29:04.604787: step: 216/466, loss: 0.000909144408069551
2023-01-22 13:29:05.240595: step: 218/466, loss: 0.020573722198605537
2023-01-22 13:29:05.930194: step: 220/466, loss: 0.041357796639204025
2023-01-22 13:29:06.602979: step: 222/466, loss: 0.25173336267471313
2023-01-22 13:29:07.193714: step: 224/466, loss: 0.012942682951688766
2023-01-22 13:29:07.837001: step: 226/466, loss: 0.012703394517302513
2023-01-22 13:29:08.431969: step: 228/466, loss: 0.011449992656707764
2023-01-22 13:29:09.046790: step: 230/466, loss: 0.023750029504299164
2023-01-22 13:29:09.711456: step: 232/466, loss: 0.00366886961273849
2023-01-22 13:29:10.337050: step: 234/466, loss: 0.03426119312644005
2023-01-22 13:29:10.929969: step: 236/466, loss: 0.012813607230782509
2023-01-22 13:29:11.459647: step: 238/466, loss: 0.0055039008148014545
2023-01-22 13:29:12.056839: step: 240/466, loss: 0.0028869614470750093
2023-01-22 13:29:12.665373: step: 242/466, loss: 0.008536329492926598
2023-01-22 13:29:13.252041: step: 244/466, loss: 0.010767385363578796
2023-01-22 13:29:13.843504: step: 246/466, loss: 0.016502102836966515
2023-01-22 13:29:14.529407: step: 248/466, loss: 0.0004043432418256998
2023-01-22 13:29:15.140776: step: 250/466, loss: 0.041048161685466766
2023-01-22 13:29:15.751036: step: 252/466, loss: 0.049137476831674576
2023-01-22 13:29:16.341855: step: 254/466, loss: 0.004949237685650587
2023-01-22 13:29:16.900759: step: 256/466, loss: 0.04413600638508797
2023-01-22 13:29:17.485733: step: 258/466, loss: 0.005313973408192396
2023-01-22 13:29:18.067540: step: 260/466, loss: 0.004345383029431105
2023-01-22 13:29:18.619020: step: 262/466, loss: 0.009101023897528648
2023-01-22 13:29:19.258347: step: 264/466, loss: 0.03252504765987396
2023-01-22 13:29:19.852939: step: 266/466, loss: 0.010446806438267231
2023-01-22 13:29:20.464315: step: 268/466, loss: 0.024466492235660553
2023-01-22 13:29:21.097467: step: 270/466, loss: 0.002857351675629616
2023-01-22 13:29:21.746489: step: 272/466, loss: 0.0001232354115927592
2023-01-22 13:29:22.400018: step: 274/466, loss: 0.0036861319094896317
2023-01-22 13:29:23.024346: step: 276/466, loss: 0.00023983018763829023
2023-01-22 13:29:23.684179: step: 278/466, loss: 0.01054013054817915
2023-01-22 13:29:24.369266: step: 280/466, loss: 0.0075253816321492195
2023-01-22 13:29:25.024245: step: 282/466, loss: 0.022886738181114197
2023-01-22 13:29:25.567144: step: 284/466, loss: 0.01093977689743042
2023-01-22 13:29:26.195479: step: 286/466, loss: 0.01793520525097847
2023-01-22 13:29:26.838146: step: 288/466, loss: 0.0015383173013105989
2023-01-22 13:29:27.493082: step: 290/466, loss: 0.06609602272510529
2023-01-22 13:29:28.149954: step: 292/466, loss: 0.005888265557587147
2023-01-22 13:29:28.781962: step: 294/466, loss: 0.018412522971630096
2023-01-22 13:29:29.390110: step: 296/466, loss: 0.00010748588829301298
2023-01-22 13:29:29.986196: step: 298/466, loss: 0.03687933087348938
2023-01-22 13:29:30.606777: step: 300/466, loss: 0.00927209947258234
2023-01-22 13:29:31.165067: step: 302/466, loss: 0.04740048199892044
2023-01-22 13:29:31.810301: step: 304/466, loss: 0.013495231047272682
2023-01-22 13:29:32.474913: step: 306/466, loss: 0.06918410211801529
2023-01-22 13:29:33.118134: step: 308/466, loss: 0.036466117948293686
2023-01-22 13:29:33.837838: step: 310/466, loss: 0.003078033681958914
2023-01-22 13:29:34.420943: step: 312/466, loss: 0.09293632954359055
2023-01-22 13:29:35.093808: step: 314/466, loss: 0.04000889137387276
2023-01-22 13:29:35.711099: step: 316/466, loss: 0.03359391167759895
2023-01-22 13:29:36.303130: step: 318/466, loss: 0.0005374500178731978
2023-01-22 13:29:36.898621: step: 320/466, loss: 0.01053704135119915
2023-01-22 13:29:37.488414: step: 322/466, loss: 0.0017169741913676262
2023-01-22 13:29:38.085585: step: 324/466, loss: 0.002009422518312931
2023-01-22 13:29:38.727095: step: 326/466, loss: 0.01806122623383999
2023-01-22 13:29:39.336311: step: 328/466, loss: 0.021779784932732582
2023-01-22 13:29:39.919567: step: 330/466, loss: 0.004365967120975256
2023-01-22 13:29:40.521801: step: 332/466, loss: 0.0009254095493815839
2023-01-22 13:29:41.102015: step: 334/466, loss: 0.012203444726765156
2023-01-22 13:29:41.794760: step: 336/466, loss: 0.004250540863722563
2023-01-22 13:29:42.430640: step: 338/466, loss: 0.014696831814944744
2023-01-22 13:29:43.115356: step: 340/466, loss: 0.3365165591239929
2023-01-22 13:29:43.715806: step: 342/466, loss: 0.014637970365583897
2023-01-22 13:29:44.296036: step: 344/466, loss: 0.04531939700245857
2023-01-22 13:29:44.929477: step: 346/466, loss: 0.0061531332321465015
2023-01-22 13:29:45.554546: step: 348/466, loss: 0.3791632354259491
2023-01-22 13:29:46.181192: step: 350/466, loss: 0.0018494034884497523
2023-01-22 13:29:46.801476: step: 352/466, loss: 0.010231144726276398
2023-01-22 13:29:47.419610: step: 354/466, loss: 0.0032418647315353155
2023-01-22 13:29:48.033644: step: 356/466, loss: 0.0013531928416341543
2023-01-22 13:29:48.612287: step: 358/466, loss: 0.052366409450769424
2023-01-22 13:29:49.206571: step: 360/466, loss: 0.20318692922592163
2023-01-22 13:29:49.813645: step: 362/466, loss: 0.02761739492416382
2023-01-22 13:29:50.491096: step: 364/466, loss: 0.017266161739826202
2023-01-22 13:29:51.060224: step: 366/466, loss: 1.5719159841537476
2023-01-22 13:29:51.620261: step: 368/466, loss: 0.001832455163821578
2023-01-22 13:29:52.187316: step: 370/466, loss: 5.752670040237717e-05
2023-01-22 13:29:52.825154: step: 372/466, loss: 0.004226814955472946
2023-01-22 13:29:53.470836: step: 374/466, loss: 0.0006275619962252676
2023-01-22 13:29:54.057692: step: 376/466, loss: 0.2641673684120178
2023-01-22 13:29:54.679189: step: 378/466, loss: 0.015237389132380486
2023-01-22 13:29:55.243935: step: 380/466, loss: 0.0043543362990021706
2023-01-22 13:29:55.883458: step: 382/466, loss: 0.0103141525760293
2023-01-22 13:29:56.519676: step: 384/466, loss: 0.006467350292950869
2023-01-22 13:29:57.120055: step: 386/466, loss: 0.05341273173689842
2023-01-22 13:29:57.695846: step: 388/466, loss: 4.330767296778504e-06
2023-01-22 13:29:58.380288: step: 390/466, loss: 0.01330084539949894
2023-01-22 13:29:59.022936: step: 392/466, loss: 0.005651859100908041
2023-01-22 13:29:59.634953: step: 394/466, loss: 0.036984048783779144
2023-01-22 13:30:00.282416: step: 396/466, loss: 0.06965211778879166
2023-01-22 13:30:00.926429: step: 398/466, loss: 0.0013999653747305274
2023-01-22 13:30:01.545061: step: 400/466, loss: 0.0007004133658483624
2023-01-22 13:30:02.170264: step: 402/466, loss: 0.029358763247728348
2023-01-22 13:30:02.873810: step: 404/466, loss: 0.05330312252044678
2023-01-22 13:30:03.490293: step: 406/466, loss: 0.023303842172026634
2023-01-22 13:30:04.137673: step: 408/466, loss: 0.026277275756001472
2023-01-22 13:30:04.751831: step: 410/466, loss: 0.05698707327246666
2023-01-22 13:30:05.358969: step: 412/466, loss: 0.0056052375584840775
2023-01-22 13:30:06.030995: step: 414/466, loss: 0.13320933282375336
2023-01-22 13:30:06.639168: step: 416/466, loss: 0.011446727439761162
2023-01-22 13:30:07.256941: step: 418/466, loss: 0.03348606079816818
2023-01-22 13:30:07.878900: step: 420/466, loss: 0.0022945867385715246
2023-01-22 13:30:08.394130: step: 422/466, loss: 0.0809975266456604
2023-01-22 13:30:08.949128: step: 424/466, loss: 0.2196180522441864
2023-01-22 13:30:09.564973: step: 426/466, loss: 0.003923522774130106
2023-01-22 13:30:10.174340: step: 428/466, loss: 0.02230186201632023
2023-01-22 13:30:10.772843: step: 430/466, loss: 0.0052039786241948605
2023-01-22 13:30:11.397075: step: 432/466, loss: 0.03056887723505497
2023-01-22 13:30:12.031311: step: 434/466, loss: 0.008743995800614357
2023-01-22 13:30:12.636748: step: 436/466, loss: 0.021395454183220863
2023-01-22 13:30:13.269660: step: 438/466, loss: 0.04790028929710388
2023-01-22 13:30:13.894392: step: 440/466, loss: 0.006264548283070326
2023-01-22 13:30:14.527351: step: 442/466, loss: 0.038078151643276215
2023-01-22 13:30:15.201538: step: 444/466, loss: 0.0001275623362744227
2023-01-22 13:30:15.815856: step: 446/466, loss: 0.026751041412353516
2023-01-22 13:30:16.387628: step: 448/466, loss: 0.0038514710031449795
2023-01-22 13:30:16.942605: step: 450/466, loss: 0.02506757527589798
2023-01-22 13:30:17.582022: step: 452/466, loss: 0.042471084743738174
2023-01-22 13:30:18.180654: step: 454/466, loss: 0.03619232028722763
2023-01-22 13:30:18.827157: step: 456/466, loss: 0.005140738561749458
2023-01-22 13:30:19.438420: step: 458/466, loss: 0.02874329499900341
2023-01-22 13:30:20.046920: step: 460/466, loss: 0.0004289276257622987
2023-01-22 13:30:20.624949: step: 462/466, loss: 0.01744789257645607
2023-01-22 13:30:21.282631: step: 464/466, loss: 0.13683846592903137
2023-01-22 13:30:21.817893: step: 466/466, loss: 0.023846862837672234
2023-01-22 13:30:22.391645: step: 468/466, loss: 0.1801401525735855
2023-01-22 13:30:23.012340: step: 470/466, loss: 0.017461387440562248
2023-01-22 13:30:23.640753: step: 472/466, loss: 0.011122321709990501
2023-01-22 13:30:24.228313: step: 474/466, loss: 0.0270382072776556
2023-01-22 13:30:24.906580: step: 476/466, loss: 0.014480615966022015
2023-01-22 13:30:25.547822: step: 478/466, loss: 0.0036217127926647663
2023-01-22 13:30:26.186056: step: 480/466, loss: 0.00939874816685915
2023-01-22 13:30:26.884238: step: 482/466, loss: 0.004832264967262745
2023-01-22 13:30:27.532666: step: 484/466, loss: 0.0022632109466940165
2023-01-22 13:30:28.166932: step: 486/466, loss: 0.009170631878077984
2023-01-22 13:30:28.734367: step: 488/466, loss: 0.0702671930193901
2023-01-22 13:30:29.281961: step: 490/466, loss: 0.048669956624507904
2023-01-22 13:30:29.913078: step: 492/466, loss: 0.02539113350212574
2023-01-22 13:30:30.501381: step: 494/466, loss: 0.001394393271766603
2023-01-22 13:30:31.170384: step: 496/466, loss: 0.5365771651268005
2023-01-22 13:30:31.770262: step: 498/466, loss: 0.00293804076500237
2023-01-22 13:30:32.335957: step: 500/466, loss: 0.0036742223892360926
2023-01-22 13:30:32.889090: step: 502/466, loss: 0.03075113706290722
2023-01-22 13:30:33.509304: step: 504/466, loss: 0.002123782876878977
2023-01-22 13:30:34.152739: step: 506/466, loss: 0.03279469907283783
2023-01-22 13:30:34.761509: step: 508/466, loss: 0.0031929186079651117
2023-01-22 13:30:35.398226: step: 510/466, loss: 0.036908939480781555
2023-01-22 13:30:35.998301: step: 512/466, loss: 0.01312875933945179
2023-01-22 13:30:36.644141: step: 514/466, loss: 0.0018731298623606563
2023-01-22 13:30:37.333329: step: 516/466, loss: 0.01972200721502304
2023-01-22 13:30:37.986058: step: 518/466, loss: 0.004691218491643667
2023-01-22 13:30:38.652871: step: 520/466, loss: 0.0034749784972518682
2023-01-22 13:30:39.367219: step: 522/466, loss: 0.0007262931321747601
2023-01-22 13:30:40.021696: step: 524/466, loss: 0.004763578996062279
2023-01-22 13:30:40.672257: step: 526/466, loss: 0.0663839802145958
2023-01-22 13:30:41.287574: step: 528/466, loss: 0.0008546586614102125
2023-01-22 13:30:41.929978: step: 530/466, loss: 0.010287533514201641
2023-01-22 13:30:42.638513: step: 532/466, loss: 0.11529932171106339
2023-01-22 13:30:43.212702: step: 534/466, loss: 0.000512432015966624
2023-01-22 13:30:43.809603: step: 536/466, loss: 0.0006311875185929239
2023-01-22 13:30:44.382144: step: 538/466, loss: 0.009164192713797092
2023-01-22 13:30:45.076228: step: 540/466, loss: 0.00019224986317567527
2023-01-22 13:30:45.715813: step: 542/466, loss: 0.6070622801780701
2023-01-22 13:30:46.270860: step: 544/466, loss: 0.013346142135560513
2023-01-22 13:30:46.898090: step: 546/466, loss: 0.001861819182522595
2023-01-22 13:30:47.473875: step: 548/466, loss: 0.005893387831747532
2023-01-22 13:30:48.088134: step: 550/466, loss: 0.004697396419942379
2023-01-22 13:30:48.585596: step: 552/466, loss: 0.011865999549627304
2023-01-22 13:30:49.208800: step: 554/466, loss: 0.017121572047472
2023-01-22 13:30:49.918652: step: 556/466, loss: 0.016142327338457108
2023-01-22 13:30:50.586427: step: 558/466, loss: 0.035901207476854324
2023-01-22 13:30:51.165153: step: 560/466, loss: 0.013503274880349636
2023-01-22 13:30:51.776676: step: 562/466, loss: 0.0007424255018122494
2023-01-22 13:30:52.402252: step: 564/466, loss: 0.023608192801475525
2023-01-22 13:30:53.058352: step: 566/466, loss: 0.009967315010726452
2023-01-22 13:30:53.722538: step: 568/466, loss: 0.02642383985221386
2023-01-22 13:30:54.357060: step: 570/466, loss: 0.008085076697170734
2023-01-22 13:30:54.991898: step: 572/466, loss: 0.03311021625995636
2023-01-22 13:30:55.624621: step: 574/466, loss: 0.021686946973204613
2023-01-22 13:30:56.284326: step: 576/466, loss: 0.0004531649174168706
2023-01-22 13:30:56.959651: step: 578/466, loss: 0.002955336356535554
2023-01-22 13:30:57.593113: step: 580/466, loss: 0.06833190470933914
2023-01-22 13:30:58.271040: step: 582/466, loss: 0.00976971909403801
2023-01-22 13:30:58.848551: step: 584/466, loss: 0.0088993264362216
2023-01-22 13:30:59.471844: step: 586/466, loss: 0.031838033348321915
2023-01-22 13:31:00.151952: step: 588/466, loss: 0.00427598413079977
2023-01-22 13:31:00.768000: step: 590/466, loss: 0.0013505751267075539
2023-01-22 13:31:01.373743: step: 592/466, loss: 0.006010470911860466
2023-01-22 13:31:01.996447: step: 594/466, loss: 0.005053442902863026
2023-01-22 13:31:02.653536: step: 596/466, loss: 0.12235328555107117
2023-01-22 13:31:03.265807: step: 598/466, loss: 0.013947657309472561
2023-01-22 13:31:03.975995: step: 600/466, loss: 0.017335861921310425
2023-01-22 13:31:04.612744: step: 602/466, loss: 0.017842689529061317
2023-01-22 13:31:05.225141: step: 604/466, loss: 0.013325287960469723
2023-01-22 13:31:05.832331: step: 606/466, loss: 0.007661189418286085
2023-01-22 13:31:06.412706: step: 608/466, loss: 0.0013941368088126183
2023-01-22 13:31:07.110627: step: 610/466, loss: 0.04949084669351578
2023-01-22 13:31:07.710713: step: 612/466, loss: 0.02539418451488018
2023-01-22 13:31:08.303712: step: 614/466, loss: 0.0013708526967093349
2023-01-22 13:31:09.004473: step: 616/466, loss: 0.00775616941973567
2023-01-22 13:31:09.620063: step: 618/466, loss: 0.0025620737578719854
2023-01-22 13:31:10.231918: step: 620/466, loss: 0.008866401389241219
2023-01-22 13:31:10.833428: step: 622/466, loss: 0.013423405587673187
2023-01-22 13:31:11.375802: step: 624/466, loss: 0.000914953532628715
2023-01-22 13:31:12.088672: step: 626/466, loss: 0.00875373650342226
2023-01-22 13:31:12.717170: step: 628/466, loss: 0.2562370300292969
2023-01-22 13:31:13.326735: step: 630/466, loss: 0.003628920065239072
2023-01-22 13:31:13.916754: step: 632/466, loss: 0.0038765915669500828
2023-01-22 13:31:14.579291: step: 634/466, loss: 0.007976152002811432
2023-01-22 13:31:15.142753: step: 636/466, loss: 0.02190847136080265
2023-01-22 13:31:15.769191: step: 638/466, loss: 0.00013066553219687194
2023-01-22 13:31:16.439623: step: 640/466, loss: 0.0046429443173110485
2023-01-22 13:31:17.015032: step: 642/466, loss: 0.0017820323118939996
2023-01-22 13:31:17.619324: step: 644/466, loss: 0.016633784398436546
2023-01-22 13:31:18.217288: step: 646/466, loss: 0.010373415425419807
2023-01-22 13:31:18.752510: step: 648/466, loss: 0.007152173202484846
2023-01-22 13:31:19.362779: step: 650/466, loss: 0.0010419668396934867
2023-01-22 13:31:19.967051: step: 652/466, loss: 0.0006896069389767945
2023-01-22 13:31:20.616860: step: 654/466, loss: 0.0052822246216237545
2023-01-22 13:31:21.239671: step: 656/466, loss: 0.015896180644631386
2023-01-22 13:31:21.898289: step: 658/466, loss: 0.0004061829240527004
2023-01-22 13:31:22.602943: step: 660/466, loss: 0.006516371853649616
2023-01-22 13:31:23.291722: step: 662/466, loss: 0.0069544874131679535
2023-01-22 13:31:23.901739: step: 664/466, loss: 0.008382551372051239
2023-01-22 13:31:24.493533: step: 666/466, loss: 0.001753911143168807
2023-01-22 13:31:25.126687: step: 668/466, loss: 0.10311511904001236
2023-01-22 13:31:25.714884: step: 670/466, loss: 0.0050849937833845615
2023-01-22 13:31:26.360818: step: 672/466, loss: 0.03090570494532585
2023-01-22 13:31:27.012517: step: 674/466, loss: 0.016384674236178398
2023-01-22 13:31:27.635810: step: 676/466, loss: 0.029901500791311264
2023-01-22 13:31:28.194632: step: 678/466, loss: 0.018675347790122032
2023-01-22 13:31:28.838674: step: 680/466, loss: 0.00016065257659647614
2023-01-22 13:31:29.563693: step: 682/466, loss: 0.005745972506701946
2023-01-22 13:31:30.166901: step: 684/466, loss: 0.0024547441862523556
2023-01-22 13:31:30.711690: step: 686/466, loss: 0.002825072268024087
2023-01-22 13:31:31.339261: step: 688/466, loss: 0.0032656663097441196
2023-01-22 13:31:31.953862: step: 690/466, loss: 0.07884236425161362
2023-01-22 13:31:32.606142: step: 692/466, loss: 0.0067831301130354404
2023-01-22 13:31:33.204344: step: 694/466, loss: 0.0012500978773459792
2023-01-22 13:31:33.805829: step: 696/466, loss: 0.009684398770332336
2023-01-22 13:31:34.456663: step: 698/466, loss: 0.020377876237034798
2023-01-22 13:31:35.129148: step: 700/466, loss: 0.00035672361264005303
2023-01-22 13:31:35.810917: step: 702/466, loss: 0.0206731166690588
2023-01-22 13:31:36.410473: step: 704/466, loss: 0.035817913711071014
2023-01-22 13:31:37.008000: step: 706/466, loss: 0.002449051244184375
2023-01-22 13:31:37.626016: step: 708/466, loss: 0.01403097901493311
2023-01-22 13:31:38.223844: step: 710/466, loss: 0.00010961700172629207
2023-01-22 13:31:38.931360: step: 712/466, loss: 0.01196881290525198
2023-01-22 13:31:39.580342: step: 714/466, loss: 0.01933245360851288
2023-01-22 13:31:40.171514: step: 716/466, loss: 0.00016425353533122689
2023-01-22 13:31:40.738427: step: 718/466, loss: 0.006508949212729931
2023-01-22 13:31:41.306122: step: 720/466, loss: 0.016074998304247856
2023-01-22 13:31:41.966076: step: 722/466, loss: 0.007576656527817249
2023-01-22 13:31:42.602961: step: 724/466, loss: 0.004461620468646288
2023-01-22 13:31:43.265372: step: 726/466, loss: 0.22906804084777832
2023-01-22 13:31:43.747201: step: 728/466, loss: 6.266071432037279e-05
2023-01-22 13:31:44.360431: step: 730/466, loss: 0.00867387279868126
2023-01-22 13:31:44.914769: step: 732/466, loss: 0.00040576778701506555
2023-01-22 13:31:45.650287: step: 734/466, loss: 0.0005055777728557587
2023-01-22 13:31:46.240887: step: 736/466, loss: 0.010774249210953712
2023-01-22 13:31:46.986159: step: 738/466, loss: 0.013444541022181511
2023-01-22 13:31:47.690879: step: 740/466, loss: 0.021006938070058823
2023-01-22 13:31:48.325333: step: 742/466, loss: 0.01994216814637184
2023-01-22 13:31:48.941638: step: 744/466, loss: 0.0026697348803281784
2023-01-22 13:31:49.536165: step: 746/466, loss: 0.03117072954773903
2023-01-22 13:31:50.201901: step: 748/466, loss: 0.0825987383723259
2023-01-22 13:31:50.828254: step: 750/466, loss: 0.02095739170908928
2023-01-22 13:31:51.509327: step: 752/466, loss: 0.401014506816864
2023-01-22 13:31:52.087846: step: 754/466, loss: 0.008619406260550022
2023-01-22 13:31:52.673891: step: 756/466, loss: 0.003280237317085266
2023-01-22 13:31:53.296286: step: 758/466, loss: 0.055942706763744354
2023-01-22 13:31:53.878152: step: 760/466, loss: 0.0006331041804514825
2023-01-22 13:31:54.486078: step: 762/466, loss: 0.03507787734270096
2023-01-22 13:31:55.087462: step: 764/466, loss: 0.0024752917233854532
2023-01-22 13:31:55.649025: step: 766/466, loss: 0.008306448347866535
2023-01-22 13:31:56.246362: step: 768/466, loss: 0.005168801639229059
2023-01-22 13:31:56.864861: step: 770/466, loss: 0.005456330720335245
2023-01-22 13:31:57.437357: step: 772/466, loss: 0.00500397989526391
2023-01-22 13:31:58.023221: step: 774/466, loss: 0.0035422630608081818
2023-01-22 13:31:58.654059: step: 776/466, loss: 0.0029776778537780046
2023-01-22 13:31:59.163206: step: 778/466, loss: 0.00010884831863222644
2023-01-22 13:31:59.827078: step: 780/466, loss: 0.015602245926856995
2023-01-22 13:32:00.491436: step: 782/466, loss: 0.0006214018794707954
2023-01-22 13:32:01.174944: step: 784/466, loss: 0.003791040973737836
2023-01-22 13:32:01.804635: step: 786/466, loss: 0.007465250324457884
2023-01-22 13:32:02.435683: step: 788/466, loss: 0.028806166723370552
2023-01-22 13:32:03.080895: step: 790/466, loss: 0.005335021298378706
2023-01-22 13:32:03.645292: step: 792/466, loss: 0.004698272794485092
2023-01-22 13:32:04.265378: step: 794/466, loss: 0.02386847510933876
2023-01-22 13:32:04.878366: step: 796/466, loss: 0.020296594128012657
2023-01-22 13:32:05.472885: step: 798/466, loss: 0.01201885100454092
2023-01-22 13:32:06.132828: step: 800/466, loss: 0.0002638005535118282
2023-01-22 13:32:06.799357: step: 802/466, loss: 8.68512797751464e-05
2023-01-22 13:32:07.425103: step: 804/466, loss: 0.1226978451013565
2023-01-22 13:32:08.048573: step: 806/466, loss: 0.004920917097479105
2023-01-22 13:32:08.759094: step: 808/466, loss: 0.015866786241531372
2023-01-22 13:32:09.308822: step: 810/466, loss: 0.07115912437438965
2023-01-22 13:32:09.911194: step: 812/466, loss: 2.851075123544433e-06
2023-01-22 13:32:10.510596: step: 814/466, loss: 0.014639374800026417
2023-01-22 13:32:11.092158: step: 816/466, loss: 0.007592801470309496
2023-01-22 13:32:11.739539: step: 818/466, loss: 0.05241686850786209
2023-01-22 13:32:12.341956: step: 820/466, loss: 0.007755121681839228
2023-01-22 13:32:12.961633: step: 822/466, loss: 0.01800842583179474
2023-01-22 13:32:13.646171: step: 824/466, loss: 0.027888098731637
2023-01-22 13:32:14.260262: step: 826/466, loss: 0.09318346530199051
2023-01-22 13:32:14.852123: step: 828/466, loss: 0.06418915838003159
2023-01-22 13:32:15.430875: step: 830/466, loss: 0.0030594964046031237
2023-01-22 13:32:16.080322: step: 832/466, loss: 0.0027627507224678993
2023-01-22 13:32:16.682032: step: 834/466, loss: 9.011743532028049e-05
2023-01-22 13:32:17.253361: step: 836/466, loss: 0.005139882210642099
2023-01-22 13:32:17.906952: step: 838/466, loss: 0.014305722899734974
2023-01-22 13:32:18.580142: step: 840/466, loss: 0.00447474978864193
2023-01-22 13:32:19.199193: step: 842/466, loss: 0.022534940391778946
2023-01-22 13:32:19.757957: step: 844/466, loss: 0.003902808530256152
2023-01-22 13:32:20.344816: step: 846/466, loss: 0.06704127788543701
2023-01-22 13:32:20.987455: step: 848/466, loss: 0.0010130038717761636
2023-01-22 13:32:21.644723: step: 850/466, loss: 0.12758488953113556
2023-01-22 13:32:22.261908: step: 852/466, loss: 0.0028329056221991777
2023-01-22 13:32:22.931717: step: 854/466, loss: 0.02403268776834011
2023-01-22 13:32:23.499495: step: 856/466, loss: 0.27932578325271606
2023-01-22 13:32:24.132065: step: 858/466, loss: 0.015459458343684673
2023-01-22 13:32:24.893846: step: 860/466, loss: 0.005626055411994457
2023-01-22 13:32:25.498706: step: 862/466, loss: 0.10774286836385727
2023-01-22 13:32:26.122388: step: 864/466, loss: 0.005312466528266668
2023-01-22 13:32:26.768824: step: 866/466, loss: 0.016016367822885513
2023-01-22 13:32:27.380903: step: 868/466, loss: 0.08760938048362732
2023-01-22 13:32:28.061747: step: 870/466, loss: 0.0036086023319512606
2023-01-22 13:32:28.597735: step: 872/466, loss: 0.004177022725343704
2023-01-22 13:32:29.255340: step: 874/466, loss: 0.20971441268920898
2023-01-22 13:32:29.890650: step: 876/466, loss: 0.00036603506305254996
2023-01-22 13:32:30.472927: step: 878/466, loss: 0.003779512597247958
2023-01-22 13:32:31.066776: step: 880/466, loss: 0.006469182204455137
2023-01-22 13:32:31.665493: step: 882/466, loss: 0.03458406776189804
2023-01-22 13:32:32.271764: step: 884/466, loss: 0.0436847060918808
2023-01-22 13:32:32.916471: step: 886/466, loss: 0.0017953275237232447
2023-01-22 13:32:33.444689: step: 888/466, loss: 0.01645614765584469
2023-01-22 13:32:34.074059: step: 890/466, loss: 0.005720381624996662
2023-01-22 13:32:34.789567: step: 892/466, loss: 0.018691744655370712
2023-01-22 13:32:35.381098: step: 894/466, loss: 0.024546178057789803
2023-01-22 13:32:35.992606: step: 896/466, loss: 0.011327753774821758
2023-01-22 13:32:36.658228: step: 898/466, loss: 0.02763189561665058
2023-01-22 13:32:37.319935: step: 900/466, loss: 0.008905744180083275
2023-01-22 13:32:37.951334: step: 902/466, loss: 0.019306790083646774
2023-01-22 13:32:38.526972: step: 904/466, loss: 0.040599238127470016
2023-01-22 13:32:39.163483: step: 906/466, loss: 0.018303176388144493
2023-01-22 13:32:39.789793: step: 908/466, loss: 0.014783458784222603
2023-01-22 13:32:40.489697: step: 910/466, loss: 0.013032814487814903
2023-01-22 13:32:41.136718: step: 912/466, loss: 0.008820664137601852
2023-01-22 13:32:41.731983: step: 914/466, loss: 0.000625031825620681
2023-01-22 13:32:42.374658: step: 916/466, loss: 0.028586631640791893
2023-01-22 13:32:42.966492: step: 918/466, loss: 0.009524805471301079
2023-01-22 13:32:43.585291: step: 920/466, loss: 0.007127732969820499
2023-01-22 13:32:44.262978: step: 922/466, loss: 0.0053637209348380566
2023-01-22 13:32:44.897478: step: 924/466, loss: 0.005123194307088852
2023-01-22 13:32:45.498481: step: 926/466, loss: 0.0001634888758417219
2023-01-22 13:32:46.116960: step: 928/466, loss: 0.00564478849992156
2023-01-22 13:32:46.696871: step: 930/466, loss: 0.017921369522809982
2023-01-22 13:32:47.458674: step: 932/466, loss: 0.011737722903490067
==================================================
Loss: 0.032
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32169707295129135, 'r': 0.32658051997901494, 'f1': 0.32412040306768525}, 'combined': 0.23882556015513648, 'epoch': 31}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3298880182158158, 'r': 0.3063883307144187, 'f1': 0.3177042157665173}, 'combined': 0.1989362846388473, 'epoch': 31}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31046181730785255, 'r': 0.3481649602067189, 'f1': 0.32823422903209454}, 'combined': 0.24185680033943807, 'epoch': 31}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3319566658040442, 'r': 0.316690849793218, 'f1': 0.32414411852393055}, 'combined': 0.20087804528243583, 'epoch': 31}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2841280895031004, 'r': 0.3375031955008365, 'f1': 0.30852417004152793}, 'combined': 0.22733359897796793, 'epoch': 31}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3363052177336754, 'r': 0.3138443999427981, 'f1': 0.3246868301929228}, 'combined': 0.21538631309827555, 'epoch': 31}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2833333333333333, 'r': 0.36428571428571427, 'f1': 0.31875}, 'combined': 0.21249999999999997, 'epoch': 31}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2972972972972973, 'r': 0.4782608695652174, 'f1': 0.3666666666666667}, 'combined': 0.18333333333333335, 'epoch': 31}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3157894736842105, 'r': 0.20689655172413793, 'f1': 0.25}, 'combined': 0.16666666666666666, 'epoch': 31}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:35:24.617456: step: 2/466, loss: 0.023411225527524948
2023-01-22 13:35:25.221506: step: 4/466, loss: 0.007410215213894844
2023-01-22 13:35:25.821415: step: 6/466, loss: 0.009759167209267616
2023-01-22 13:35:26.455550: step: 8/466, loss: 0.016646098345518112
2023-01-22 13:35:27.147340: step: 10/466, loss: 0.0009101228788495064
2023-01-22 13:35:27.721584: step: 12/466, loss: 0.0028298806864768267
2023-01-22 13:35:28.260492: step: 14/466, loss: 0.006708510220050812
2023-01-22 13:35:28.851991: step: 16/466, loss: 0.013693740591406822
2023-01-22 13:35:29.423839: step: 18/466, loss: 0.05833829566836357
2023-01-22 13:35:30.042982: step: 20/466, loss: 0.0005727614625357091
2023-01-22 13:35:30.606778: step: 22/466, loss: 0.004258910194039345
2023-01-22 13:35:31.238883: step: 24/466, loss: 0.0123649463057518
2023-01-22 13:35:31.925146: step: 26/466, loss: 0.021816201508045197
2023-01-22 13:35:32.492580: step: 28/466, loss: 0.002437890972942114
2023-01-22 13:35:33.108317: step: 30/466, loss: 0.0004007563111372292
2023-01-22 13:35:33.674259: step: 32/466, loss: 0.05183832347393036
2023-01-22 13:35:34.287337: step: 34/466, loss: 0.0009992136619985104
2023-01-22 13:35:34.842561: step: 36/466, loss: 0.0018776083597913384
2023-01-22 13:35:35.474911: step: 38/466, loss: 0.0024277763441205025
2023-01-22 13:35:36.100528: step: 40/466, loss: 0.04051138833165169
2023-01-22 13:35:36.752488: step: 42/466, loss: 0.004881789442151785
2023-01-22 13:35:37.371770: step: 44/466, loss: 0.000656484451610595
2023-01-22 13:35:37.923664: step: 46/466, loss: 0.009599301964044571
2023-01-22 13:35:38.474038: step: 48/466, loss: 0.0040141381323337555
2023-01-22 13:35:39.070697: step: 50/466, loss: 0.009538087993860245
2023-01-22 13:35:39.652686: step: 52/466, loss: 0.00047708090278320014
2023-01-22 13:35:40.279871: step: 54/466, loss: 0.005349311046302319
2023-01-22 13:35:40.930310: step: 56/466, loss: 0.009912590496242046
2023-01-22 13:35:41.547374: step: 58/466, loss: 0.006544522475451231
2023-01-22 13:35:42.200847: step: 60/466, loss: 0.008314132690429688
2023-01-22 13:35:42.839451: step: 62/466, loss: 0.010748178698122501
2023-01-22 13:35:43.424892: step: 64/466, loss: 0.756777286529541
2023-01-22 13:35:44.045777: step: 66/466, loss: 0.0027388925664126873
2023-01-22 13:35:44.617677: step: 68/466, loss: 0.0002909097238443792
2023-01-22 13:35:45.204371: step: 70/466, loss: 0.00019457661255728453
2023-01-22 13:35:45.829507: step: 72/466, loss: 0.031159192323684692
2023-01-22 13:35:46.533901: step: 74/466, loss: 0.014231045730412006
2023-01-22 13:35:47.104801: step: 76/466, loss: 0.007948565296828747
2023-01-22 13:35:47.698338: step: 78/466, loss: 0.0001657801476540044
2023-01-22 13:35:48.307375: step: 80/466, loss: 0.3372848331928253
2023-01-22 13:35:48.966968: step: 82/466, loss: 0.03667658939957619
2023-01-22 13:35:49.629941: step: 84/466, loss: 0.018214678391814232
2023-01-22 13:35:50.256103: step: 86/466, loss: 0.04305468872189522
2023-01-22 13:35:50.871420: step: 88/466, loss: 0.0036728845443576574
2023-01-22 13:35:51.504440: step: 90/466, loss: 0.005807220935821533
2023-01-22 13:35:52.166692: step: 92/466, loss: 0.00411470839753747
2023-01-22 13:35:52.758207: step: 94/466, loss: 0.004546079318970442
2023-01-22 13:35:53.396760: step: 96/466, loss: 0.01811668649315834
2023-01-22 13:35:54.104204: step: 98/466, loss: 0.02663789875805378
2023-01-22 13:35:54.735577: step: 100/466, loss: 0.01967105083167553
2023-01-22 13:35:55.346373: step: 102/466, loss: 0.14476454257965088
2023-01-22 13:35:55.973967: step: 104/466, loss: 0.04371005669236183
2023-01-22 13:35:56.622622: step: 106/466, loss: 0.0020042855758219957
2023-01-22 13:35:57.225590: step: 108/466, loss: 0.0014833958121016622
2023-01-22 13:35:57.862181: step: 110/466, loss: 0.005307415965944529
2023-01-22 13:35:58.473286: step: 112/466, loss: 0.0075561366975307465
2023-01-22 13:35:59.144445: step: 114/466, loss: 0.011789039708673954
2023-01-22 13:35:59.773714: step: 116/466, loss: 0.002293430967256427
2023-01-22 13:36:00.330075: step: 118/466, loss: 0.11512932181358337
2023-01-22 13:36:01.013563: step: 120/466, loss: 6.02415093453601e-05
2023-01-22 13:36:01.651957: step: 122/466, loss: 0.03975168988108635
2023-01-22 13:36:02.217491: step: 124/466, loss: 0.009585501626133919
2023-01-22 13:36:02.804024: step: 126/466, loss: 0.004253715742379427
2023-01-22 13:36:03.495496: step: 128/466, loss: 0.014150316826999187
2023-01-22 13:36:04.084235: step: 130/466, loss: 0.020391590893268585
2023-01-22 13:36:04.754883: step: 132/466, loss: 0.03351735696196556
2023-01-22 13:36:05.466934: step: 134/466, loss: 0.030212484300136566
2023-01-22 13:36:06.083731: step: 136/466, loss: 0.011778630316257477
2023-01-22 13:36:06.716413: step: 138/466, loss: 0.21124117076396942
2023-01-22 13:36:07.375309: step: 140/466, loss: 0.011526920832693577
2023-01-22 13:36:08.040532: step: 142/466, loss: 0.027538979426026344
2023-01-22 13:36:08.652150: step: 144/466, loss: 0.06910871714353561
2023-01-22 13:36:09.310947: step: 146/466, loss: 0.06594354659318924
2023-01-22 13:36:09.959885: step: 148/466, loss: 0.12538748979568481
2023-01-22 13:36:10.583933: step: 150/466, loss: 0.0019299472915008664
2023-01-22 13:36:11.194607: step: 152/466, loss: 0.07830004394054413
2023-01-22 13:36:11.809454: step: 154/466, loss: 0.007638944312930107
2023-01-22 13:36:12.479437: step: 156/466, loss: 0.009758553467690945
2023-01-22 13:36:13.081897: step: 158/466, loss: 8.209812949644402e-05
2023-01-22 13:36:13.659973: step: 160/466, loss: 0.016384704038500786
2023-01-22 13:36:14.247243: step: 162/466, loss: 0.000600729079451412
2023-01-22 13:36:14.912604: step: 164/466, loss: 0.9745030403137207
2023-01-22 13:36:15.507452: step: 166/466, loss: 0.025582611560821533
2023-01-22 13:36:16.141882: step: 168/466, loss: 0.013880142942070961
2023-01-22 13:36:16.783991: step: 170/466, loss: 0.008554169908165932
2023-01-22 13:36:17.556411: step: 172/466, loss: 0.0011577691184356809
2023-01-22 13:36:18.178591: step: 174/466, loss: 0.02661309763789177
2023-01-22 13:36:18.743018: step: 176/466, loss: 0.0473182387650013
2023-01-22 13:36:19.342746: step: 178/466, loss: 0.00834281463176012
2023-01-22 13:36:19.936313: step: 180/466, loss: 0.007583326194435358
2023-01-22 13:36:20.565607: step: 182/466, loss: 0.002567940391600132
2023-01-22 13:36:21.173049: step: 184/466, loss: 0.028543440625071526
2023-01-22 13:36:21.785383: step: 186/466, loss: 0.04543311521410942
2023-01-22 13:36:22.361385: step: 188/466, loss: 0.002355037024244666
2023-01-22 13:36:23.027394: step: 190/466, loss: 0.006026502698659897
2023-01-22 13:36:23.721960: step: 192/466, loss: 0.01346490066498518
2023-01-22 13:36:24.333890: step: 194/466, loss: 0.01777638867497444
2023-01-22 13:36:24.954026: step: 196/466, loss: 0.008044625632464886
2023-01-22 13:36:25.604949: step: 198/466, loss: 0.0005668763187713921
2023-01-22 13:36:26.337158: step: 200/466, loss: 0.028658686205744743
2023-01-22 13:36:27.032153: step: 202/466, loss: 0.6971175670623779
2023-01-22 13:36:27.647350: step: 204/466, loss: 0.0012721081729978323
2023-01-22 13:36:28.251149: step: 206/466, loss: 0.0016366386553272605
2023-01-22 13:36:28.840373: step: 208/466, loss: 0.000262612069491297
2023-01-22 13:36:29.466170: step: 210/466, loss: 0.028013983741402626
2023-01-22 13:36:30.102740: step: 212/466, loss: 0.08432400226593018
2023-01-22 13:36:30.695473: step: 214/466, loss: 0.014807991683483124
2023-01-22 13:36:31.349385: step: 216/466, loss: 0.0009584611980244517
2023-01-22 13:36:31.993832: step: 218/466, loss: 0.003678521839901805
2023-01-22 13:36:32.645166: step: 220/466, loss: 0.012200010009109974
2023-01-22 13:36:33.260931: step: 222/466, loss: 0.08298763632774353
2023-01-22 13:36:33.863527: step: 224/466, loss: 0.0012888513738289475
2023-01-22 13:36:34.534242: step: 226/466, loss: 0.0013545186957344413
2023-01-22 13:36:35.184301: step: 228/466, loss: 0.0001419303735019639
2023-01-22 13:36:35.762086: step: 230/466, loss: 0.0009365221485495567
2023-01-22 13:36:36.375594: step: 232/466, loss: 0.005224217195063829
2023-01-22 13:36:37.009819: step: 234/466, loss: 0.0006510214298032224
2023-01-22 13:36:37.835765: step: 236/466, loss: 0.05415847525000572
2023-01-22 13:36:38.471134: step: 238/466, loss: 0.027244968339800835
2023-01-22 13:36:39.040279: step: 240/466, loss: 0.3291933536529541
2023-01-22 13:36:39.617538: step: 242/466, loss: 0.048413824290037155
2023-01-22 13:36:40.190496: step: 244/466, loss: 0.003729290096089244
2023-01-22 13:36:40.756960: step: 246/466, loss: 0.0262068472802639
2023-01-22 13:36:41.405401: step: 248/466, loss: 0.010029599070549011
2023-01-22 13:36:42.001117: step: 250/466, loss: 0.020009851083159447
2023-01-22 13:36:42.638616: step: 252/466, loss: 0.027754565700888634
2023-01-22 13:36:43.228454: step: 254/466, loss: 0.00015698251081630588
2023-01-22 13:36:43.812800: step: 256/466, loss: 0.00034971226705238223
2023-01-22 13:36:44.453051: step: 258/466, loss: 0.0029135001823306084
2023-01-22 13:36:45.189200: step: 260/466, loss: 0.10238341242074966
2023-01-22 13:36:45.827180: step: 262/466, loss: 0.00717756524682045
2023-01-22 13:36:46.432975: step: 264/466, loss: 0.056868311017751694
2023-01-22 13:36:47.038953: step: 266/466, loss: 0.0049666459672153
2023-01-22 13:36:47.644337: step: 268/466, loss: 0.04420678690075874
2023-01-22 13:36:48.320576: step: 270/466, loss: 0.07952933758497238
2023-01-22 13:36:48.975895: step: 272/466, loss: 0.004162727855145931
2023-01-22 13:36:49.657720: step: 274/466, loss: 0.0005441865650936961
2023-01-22 13:36:50.276887: step: 276/466, loss: 0.15364809334278107
2023-01-22 13:36:50.891488: step: 278/466, loss: 0.01183517649769783
2023-01-22 13:36:51.550683: step: 280/466, loss: 0.08058245480060577
2023-01-22 13:36:52.128764: step: 282/466, loss: 0.0024886305909603834
2023-01-22 13:36:52.833036: step: 284/466, loss: 0.055408552289009094
2023-01-22 13:36:53.439346: step: 286/466, loss: 0.037237122654914856
2023-01-22 13:36:54.072405: step: 288/466, loss: 0.013606084510684013
2023-01-22 13:36:54.643820: step: 290/466, loss: 0.003307209350168705
2023-01-22 13:36:55.305806: step: 292/466, loss: 0.02808493748307228
2023-01-22 13:36:55.950404: step: 294/466, loss: 0.46002358198165894
2023-01-22 13:36:56.552631: step: 296/466, loss: 0.2787669003009796
2023-01-22 13:36:57.222874: step: 298/466, loss: 0.012026851065456867
2023-01-22 13:36:57.807419: step: 300/466, loss: 0.03737563267350197
2023-01-22 13:36:58.425694: step: 302/466, loss: 0.008616953156888485
2023-01-22 13:36:59.049643: step: 304/466, loss: 0.046242013573646545
2023-01-22 13:36:59.595045: step: 306/466, loss: 0.00045969485654495656
2023-01-22 13:37:00.166883: step: 308/466, loss: 0.1616874784231186
2023-01-22 13:37:00.835316: step: 310/466, loss: 0.016417542472481728
2023-01-22 13:37:01.495186: step: 312/466, loss: 0.395427942276001
2023-01-22 13:37:02.090962: step: 314/466, loss: 0.03880275413393974
2023-01-22 13:37:02.809905: step: 316/466, loss: 0.009924361482262611
2023-01-22 13:37:03.503903: step: 318/466, loss: 0.03377104178071022
2023-01-22 13:37:04.169480: step: 320/466, loss: 0.005184852983802557
2023-01-22 13:37:04.793325: step: 322/466, loss: 0.0021988372318446636
2023-01-22 13:37:05.420602: step: 324/466, loss: 0.00976119190454483
2023-01-22 13:37:06.072518: step: 326/466, loss: 0.002342578722164035
2023-01-22 13:37:06.715237: step: 328/466, loss: 0.0007447432144545019
2023-01-22 13:37:07.347554: step: 330/466, loss: 0.04353374242782593
2023-01-22 13:37:07.964945: step: 332/466, loss: 0.0004478727059904486
2023-01-22 13:37:08.635098: step: 334/466, loss: 0.01395033672451973
2023-01-22 13:37:09.311608: step: 336/466, loss: 0.024939075112342834
2023-01-22 13:37:09.906885: step: 338/466, loss: 0.02792339213192463
2023-01-22 13:37:10.512688: step: 340/466, loss: 0.000779581954702735
2023-01-22 13:37:11.136914: step: 342/466, loss: 0.01966101862490177
2023-01-22 13:37:11.827437: step: 344/466, loss: 0.01172749325633049
2023-01-22 13:37:12.426059: step: 346/466, loss: 0.011904709972441196
2023-01-22 13:37:13.054121: step: 348/466, loss: 0.5545079112052917
2023-01-22 13:37:13.651574: step: 350/466, loss: 0.008093088865280151
2023-01-22 13:37:14.324715: step: 352/466, loss: 0.032002806663513184
2023-01-22 13:37:14.991818: step: 354/466, loss: 0.00299689918756485
2023-01-22 13:37:15.581812: step: 356/466, loss: 0.001496439566835761
2023-01-22 13:37:16.212878: step: 358/466, loss: 0.004775097128003836
2023-01-22 13:37:16.846651: step: 360/466, loss: 0.006835389882326126
2023-01-22 13:37:17.443172: step: 362/466, loss: 0.004290407057851553
2023-01-22 13:37:18.021708: step: 364/466, loss: 0.0022695898078382015
2023-01-22 13:37:18.640387: step: 366/466, loss: 0.022341115400195122
2023-01-22 13:37:19.258542: step: 368/466, loss: 0.003539501456543803
2023-01-22 13:37:19.914401: step: 370/466, loss: 0.028464237228035927
2023-01-22 13:37:20.524243: step: 372/466, loss: 0.021883945912122726
2023-01-22 13:37:21.182126: step: 374/466, loss: 0.08412665128707886
2023-01-22 13:37:21.773860: step: 376/466, loss: 0.056779466569423676
2023-01-22 13:37:22.451050: step: 378/466, loss: 0.0023293436970561743
2023-01-22 13:37:23.034846: step: 380/466, loss: 0.004519928712397814
2023-01-22 13:37:23.679132: step: 382/466, loss: 0.015636395663022995
2023-01-22 13:37:24.254173: step: 384/466, loss: 0.0055314707569777966
2023-01-22 13:37:24.878820: step: 386/466, loss: 0.2097301185131073
2023-01-22 13:37:25.484028: step: 388/466, loss: 0.07120423018932343
2023-01-22 13:37:26.197931: step: 390/466, loss: 0.0455934964120388
2023-01-22 13:37:26.788879: step: 392/466, loss: 0.006745305843651295
2023-01-22 13:37:27.369923: step: 394/466, loss: 0.014581529423594475
2023-01-22 13:37:28.030207: step: 396/466, loss: 0.011852283962070942
2023-01-22 13:37:28.677239: step: 398/466, loss: 0.007304691709578037
2023-01-22 13:37:29.366074: step: 400/466, loss: 0.11655885726213455
2023-01-22 13:37:29.987901: step: 402/466, loss: 0.018392568454146385
2023-01-22 13:37:30.599102: step: 404/466, loss: 0.01346831675618887
2023-01-22 13:37:31.130837: step: 406/466, loss: 0.02412579208612442
2023-01-22 13:37:31.808323: step: 408/466, loss: 0.030196748673915863
2023-01-22 13:37:32.385337: step: 410/466, loss: 0.022959111258387566
2023-01-22 13:37:32.992129: step: 412/466, loss: 0.04549776017665863
2023-01-22 13:37:33.581444: step: 414/466, loss: 0.0074821715243160725
2023-01-22 13:37:34.219630: step: 416/466, loss: 0.03170736879110336
2023-01-22 13:37:34.866835: step: 418/466, loss: 1.2644948959350586
2023-01-22 13:37:35.459703: step: 420/466, loss: 0.0130178052932024
2023-01-22 13:37:36.321639: step: 422/466, loss: 0.3240489959716797
2023-01-22 13:37:37.021147: step: 424/466, loss: 0.03748927637934685
2023-01-22 13:37:37.612781: step: 426/466, loss: 0.0007072651060298085
2023-01-22 13:37:38.154781: step: 428/466, loss: 0.00021171310800127685
2023-01-22 13:37:38.807429: step: 430/466, loss: 0.1810675859451294
2023-01-22 13:37:39.423965: step: 432/466, loss: 0.00011003683903254569
2023-01-22 13:37:40.032135: step: 434/466, loss: 0.07037109136581421
2023-01-22 13:37:40.635250: step: 436/466, loss: 0.00043664249824360013
2023-01-22 13:37:41.279155: step: 438/466, loss: 0.016499321907758713
2023-01-22 13:37:41.896901: step: 440/466, loss: 0.00046534600551240146
2023-01-22 13:37:42.438799: step: 442/466, loss: 5.056872760178521e-05
2023-01-22 13:37:43.075557: step: 444/466, loss: 0.0027938506100326777
2023-01-22 13:37:43.738429: step: 446/466, loss: 0.005168906878679991
2023-01-22 13:37:44.304971: step: 448/466, loss: 0.039607737213373184
2023-01-22 13:37:44.948340: step: 450/466, loss: 0.027140803635120392
2023-01-22 13:37:45.591416: step: 452/466, loss: 0.0048378705978393555
2023-01-22 13:37:46.204402: step: 454/466, loss: 0.021167725324630737
2023-01-22 13:37:46.832674: step: 456/466, loss: 0.05374099314212799
2023-01-22 13:37:47.484957: step: 458/466, loss: 0.0035808503162115812
2023-01-22 13:37:48.059764: step: 460/466, loss: 0.004817279055714607
2023-01-22 13:37:48.664235: step: 462/466, loss: 0.8396977782249451
2023-01-22 13:37:49.244119: step: 464/466, loss: 0.003646058263257146
2023-01-22 13:37:49.883689: step: 466/466, loss: 0.016296282410621643
2023-01-22 13:37:50.473672: step: 468/466, loss: 0.060796670615673065
2023-01-22 13:37:51.077924: step: 470/466, loss: 0.05054939538240433
2023-01-22 13:37:51.676738: step: 472/466, loss: 0.02450472302734852
2023-01-22 13:37:52.262934: step: 474/466, loss: 0.0007114399340935051
2023-01-22 13:37:52.866585: step: 476/466, loss: 0.0573386587202549
2023-01-22 13:37:53.486189: step: 478/466, loss: 0.004851747769862413
2023-01-22 13:37:54.075055: step: 480/466, loss: 0.038977328687906265
2023-01-22 13:37:54.683555: step: 482/466, loss: 0.006838818080723286
2023-01-22 13:37:55.257577: step: 484/466, loss: 0.053884100168943405
2023-01-22 13:37:55.799797: step: 486/466, loss: 0.003641329472884536
2023-01-22 13:37:56.422024: step: 488/466, loss: 0.036911703646183014
2023-01-22 13:37:57.059203: step: 490/466, loss: 0.010725787840783596
2023-01-22 13:37:57.714263: step: 492/466, loss: 0.005133012309670448
2023-01-22 13:37:58.330978: step: 494/466, loss: 0.0011553947115316987
2023-01-22 13:37:58.958959: step: 496/466, loss: 0.013483748771250248
2023-01-22 13:37:59.567054: step: 498/466, loss: 0.08920584619045258
2023-01-22 13:38:00.168883: step: 500/466, loss: 0.26528024673461914
2023-01-22 13:38:00.773380: step: 502/466, loss: 0.0017552432836964726
2023-01-22 13:38:01.432442: step: 504/466, loss: 0.0041707539930939674
2023-01-22 13:38:02.009347: step: 506/466, loss: 0.0010291712824255228
2023-01-22 13:38:02.648241: step: 508/466, loss: 0.003643125295639038
2023-01-22 13:38:03.270964: step: 510/466, loss: 0.011014739982783794
2023-01-22 13:38:03.892989: step: 512/466, loss: 0.02263011783361435
2023-01-22 13:38:04.562661: step: 514/466, loss: 0.017728324979543686
2023-01-22 13:38:05.191422: step: 516/466, loss: 0.0007419459288939834
2023-01-22 13:38:05.787924: step: 518/466, loss: 0.002441921504214406
2023-01-22 13:38:06.416394: step: 520/466, loss: 0.0023182809818536043
2023-01-22 13:38:07.012142: step: 522/466, loss: 0.00185644649900496
2023-01-22 13:38:07.653454: step: 524/466, loss: 0.000569177616853267
2023-01-22 13:38:08.336044: step: 526/466, loss: 0.004187730140984058
2023-01-22 13:38:08.946386: step: 528/466, loss: 0.01688574068248272
2023-01-22 13:38:09.446385: step: 530/466, loss: 0.0020011102315038443
2023-01-22 13:38:10.033740: step: 532/466, loss: 0.0068510305136442184
2023-01-22 13:38:10.710500: step: 534/466, loss: 0.017126111313700676
2023-01-22 13:38:11.352131: step: 536/466, loss: 0.06983166933059692
2023-01-22 13:38:12.003586: step: 538/466, loss: 0.0038557236548513174
2023-01-22 13:38:12.612101: step: 540/466, loss: 0.009185834787786007
2023-01-22 13:38:13.232775: step: 542/466, loss: 0.0028127918485552073
2023-01-22 13:38:13.903223: step: 544/466, loss: 0.000843394489493221
2023-01-22 13:38:14.528215: step: 546/466, loss: 0.003618141869083047
2023-01-22 13:38:15.193108: step: 548/466, loss: 9.706970740808174e-05
2023-01-22 13:38:15.833632: step: 550/466, loss: 0.0065374658443033695
2023-01-22 13:38:16.425691: step: 552/466, loss: 0.00029544203425757587
2023-01-22 13:38:17.038756: step: 554/466, loss: 0.018424056470394135
2023-01-22 13:38:17.660367: step: 556/466, loss: 0.005046153906732798
2023-01-22 13:38:18.252964: step: 558/466, loss: 0.01957661285996437
2023-01-22 13:38:18.945362: step: 560/466, loss: 0.04268014803528786
2023-01-22 13:38:19.565178: step: 562/466, loss: 0.00758602237328887
2023-01-22 13:38:20.124346: step: 564/466, loss: 0.0011110709747299552
2023-01-22 13:38:20.730641: step: 566/466, loss: 0.0041378033347427845
2023-01-22 13:38:21.289172: step: 568/466, loss: 0.00987055990844965
2023-01-22 13:38:21.902202: step: 570/466, loss: 0.008387669920921326
2023-01-22 13:38:22.523163: step: 572/466, loss: 0.024874651804566383
2023-01-22 13:38:23.139485: step: 574/466, loss: 0.020754938945174217
2023-01-22 13:38:23.795936: step: 576/466, loss: 0.0061580706387758255
2023-01-22 13:38:24.418576: step: 578/466, loss: 0.008794519118964672
2023-01-22 13:38:25.081702: step: 580/466, loss: 0.003570317290723324
2023-01-22 13:38:25.742127: step: 582/466, loss: 0.010545005090534687
2023-01-22 13:38:26.393451: step: 584/466, loss: 0.01019436027854681
2023-01-22 13:38:27.044061: step: 586/466, loss: 0.006862320005893707
2023-01-22 13:38:27.599509: step: 588/466, loss: 0.009396102279424667
2023-01-22 13:38:28.208377: step: 590/466, loss: 0.011004658415913582
2023-01-22 13:38:28.845609: step: 592/466, loss: 0.008732697926461697
2023-01-22 13:38:29.469595: step: 594/466, loss: 0.0007735695689916611
2023-01-22 13:38:30.030166: step: 596/466, loss: 0.006525528617203236
2023-01-22 13:38:30.641576: step: 598/466, loss: 0.0038592349737882614
2023-01-22 13:38:31.305356: step: 600/466, loss: 0.0046826316975057125
2023-01-22 13:38:31.918869: step: 602/466, loss: 0.024678422138094902
2023-01-22 13:38:32.521515: step: 604/466, loss: 0.0025267021264880896
2023-01-22 13:38:33.096028: step: 606/466, loss: 0.024762844666838646
2023-01-22 13:38:33.710327: step: 608/466, loss: 0.016276901587843895
2023-01-22 13:38:34.367955: step: 610/466, loss: 0.017654333263635635
2023-01-22 13:38:34.997832: step: 612/466, loss: 0.26210862398147583
2023-01-22 13:38:35.598186: step: 614/466, loss: 0.01292844582349062
2023-01-22 13:38:36.144763: step: 616/466, loss: 0.0008593133534304798
2023-01-22 13:38:36.709851: step: 618/466, loss: 0.010108716785907745
2023-01-22 13:38:37.300776: step: 620/466, loss: 0.012292332015931606
2023-01-22 13:38:37.856594: step: 622/466, loss: 0.01431113202124834
2023-01-22 13:38:38.460140: step: 624/466, loss: 0.037744227796792984
2023-01-22 13:38:39.056129: step: 626/466, loss: 1.0760530233383179
2023-01-22 13:38:39.717400: step: 628/466, loss: 0.011397158727049828
2023-01-22 13:38:40.350560: step: 630/466, loss: 0.042986877262592316
2023-01-22 13:38:40.965191: step: 632/466, loss: 0.04665377736091614
2023-01-22 13:38:41.529391: step: 634/466, loss: 0.0028689559549093246
2023-01-22 13:38:42.191228: step: 636/466, loss: 0.010561549104750156
2023-01-22 13:38:42.848491: step: 638/466, loss: 0.00509530259296298
2023-01-22 13:38:43.478446: step: 640/466, loss: 0.0013705334858968854
2023-01-22 13:38:44.054975: step: 642/466, loss: 0.04495071619749069
2023-01-22 13:38:44.693559: step: 644/466, loss: 0.0006146457162685692
2023-01-22 13:38:45.366378: step: 646/466, loss: 0.16979992389678955
2023-01-22 13:38:46.017554: step: 648/466, loss: 0.05898624658584595
2023-01-22 13:38:46.649271: step: 650/466, loss: 0.00024182444030884653
2023-01-22 13:38:47.311410: step: 652/466, loss: 0.01646382175385952
2023-01-22 13:38:47.910950: step: 654/466, loss: 0.2729729115962982
2023-01-22 13:38:48.543867: step: 656/466, loss: 0.43773236870765686
2023-01-22 13:38:49.158752: step: 658/466, loss: 0.06977491825819016
2023-01-22 13:38:49.798706: step: 660/466, loss: 0.011786994524300098
2023-01-22 13:38:50.435419: step: 662/466, loss: 0.01343371532857418
2023-01-22 13:38:51.052333: step: 664/466, loss: 0.004439284559339285
2023-01-22 13:38:51.663513: step: 666/466, loss: 0.014500009827315807
2023-01-22 13:38:52.328005: step: 668/466, loss: 0.008671484887599945
2023-01-22 13:38:52.898008: step: 670/466, loss: 0.0009760663961060345
2023-01-22 13:38:53.516313: step: 672/466, loss: 0.4349953234195709
2023-01-22 13:38:54.154125: step: 674/466, loss: 0.0054158661514520645
2023-01-22 13:38:54.770448: step: 676/466, loss: 0.014271006919443607
2023-01-22 13:38:55.377196: step: 678/466, loss: 0.012837562710046768
2023-01-22 13:38:55.971764: step: 680/466, loss: 1.0666906833648682
2023-01-22 13:38:56.619425: step: 682/466, loss: 0.01808995008468628
2023-01-22 13:38:57.232076: step: 684/466, loss: 0.17323540151119232
2023-01-22 13:38:57.876260: step: 686/466, loss: 0.0014327450189739466
2023-01-22 13:38:58.496574: step: 688/466, loss: 0.003553766990080476
2023-01-22 13:38:59.163720: step: 690/466, loss: 0.026842013001441956
2023-01-22 13:38:59.777225: step: 692/466, loss: 0.031177956610918045
2023-01-22 13:39:00.327947: step: 694/466, loss: 0.0005657792207784951
2023-01-22 13:39:00.976940: step: 696/466, loss: 0.05083481967449188
2023-01-22 13:39:01.576596: step: 698/466, loss: 0.09655691683292389
2023-01-22 13:39:02.176957: step: 700/466, loss: 0.03542042151093483
2023-01-22 13:39:02.799074: step: 702/466, loss: 0.0032076865900307894
2023-01-22 13:39:03.453865: step: 704/466, loss: 0.005588217172771692
2023-01-22 13:39:04.148273: step: 706/466, loss: 0.03496195748448372
2023-01-22 13:39:04.840186: step: 708/466, loss: 0.016073670238256454
2023-01-22 13:39:05.557502: step: 710/466, loss: 0.0002725913655012846
2023-01-22 13:39:06.150972: step: 712/466, loss: 0.0025168531574308872
2023-01-22 13:39:06.761009: step: 714/466, loss: 0.024312369525432587
2023-01-22 13:39:07.467289: step: 716/466, loss: 0.012014505453407764
2023-01-22 13:39:08.084715: step: 718/466, loss: 0.0019410356180742383
2023-01-22 13:39:08.673640: step: 720/466, loss: 0.22631646692752838
2023-01-22 13:39:09.265076: step: 722/466, loss: 0.02366473525762558
2023-01-22 13:39:09.865460: step: 724/466, loss: 0.019449405372142792
2023-01-22 13:39:10.453738: step: 726/466, loss: 0.6188353896141052
2023-01-22 13:39:11.056653: step: 728/466, loss: 0.0034205520059913397
2023-01-22 13:39:11.678410: step: 730/466, loss: 0.10207657516002655
2023-01-22 13:39:12.352208: step: 732/466, loss: 0.03011954389512539
2023-01-22 13:39:12.978371: step: 734/466, loss: 0.0017117736861109734
2023-01-22 13:39:13.635252: step: 736/466, loss: 0.0110403997823596
2023-01-22 13:39:14.307244: step: 738/466, loss: 0.012234913185238838
2023-01-22 13:39:14.918152: step: 740/466, loss: 0.0024288101121783257
2023-01-22 13:39:15.556217: step: 742/466, loss: 0.0033122319728136063
2023-01-22 13:39:16.186235: step: 744/466, loss: 0.002562866546213627
2023-01-22 13:39:16.797280: step: 746/466, loss: 0.22490684688091278
2023-01-22 13:39:17.371670: step: 748/466, loss: 0.07354757189750671
2023-01-22 13:39:18.028081: step: 750/466, loss: 0.008838036097586155
2023-01-22 13:39:18.674692: step: 752/466, loss: 0.0469263531267643
2023-01-22 13:39:19.411120: step: 754/466, loss: 0.008982508443295956
2023-01-22 13:39:20.013289: step: 756/466, loss: 0.0004972777096554637
2023-01-22 13:39:20.656531: step: 758/466, loss: 0.004215892869979143
2023-01-22 13:39:21.230782: step: 760/466, loss: 8.985040039988235e-05
2023-01-22 13:39:21.744324: step: 762/466, loss: 0.0019088794942945242
2023-01-22 13:39:22.382001: step: 764/466, loss: 0.01623927243053913
2023-01-22 13:39:22.971161: step: 766/466, loss: 0.0019317037658765912
2023-01-22 13:39:23.534384: step: 768/466, loss: 0.02090388536453247
2023-01-22 13:39:24.106880: step: 770/466, loss: 0.0030517231207340956
2023-01-22 13:39:24.684490: step: 772/466, loss: 0.001847755047492683
2023-01-22 13:39:25.386517: step: 774/466, loss: 0.0017306302906945348
2023-01-22 13:39:26.012427: step: 776/466, loss: 0.0033409115858376026
2023-01-22 13:39:26.595866: step: 778/466, loss: 0.017179185524582863
2023-01-22 13:39:27.244852: step: 780/466, loss: 0.004775240086019039
2023-01-22 13:39:27.894848: step: 782/466, loss: 0.0027563865296542645
2023-01-22 13:39:28.545652: step: 784/466, loss: 0.021313194185495377
2023-01-22 13:39:29.170610: step: 786/466, loss: 0.06419835239648819
2023-01-22 13:39:29.747172: step: 788/466, loss: 0.00428836839273572
2023-01-22 13:39:30.293344: step: 790/466, loss: 0.01132860966026783
2023-01-22 13:39:30.953841: step: 792/466, loss: 0.03586093336343765
2023-01-22 13:39:31.597188: step: 794/466, loss: 0.015640152618288994
2023-01-22 13:39:32.195485: step: 796/466, loss: 0.010531782172620296
2023-01-22 13:39:32.884497: step: 798/466, loss: 0.000776784960180521
2023-01-22 13:39:33.456098: step: 800/466, loss: 0.0022169083822518587
2023-01-22 13:39:34.106659: step: 802/466, loss: 0.004453351721167564
2023-01-22 13:39:34.721833: step: 804/466, loss: 0.013527227565646172
2023-01-22 13:39:35.402875: step: 806/466, loss: 0.0005594379035755992
2023-01-22 13:39:35.956407: step: 808/466, loss: 0.0028750738129019737
2023-01-22 13:39:36.547267: step: 810/466, loss: 0.0008166292682290077
2023-01-22 13:39:37.200529: step: 812/466, loss: 0.023417195305228233
2023-01-22 13:39:37.817671: step: 814/466, loss: 0.18981100618839264
2023-01-22 13:39:38.427697: step: 816/466, loss: 0.027999037876725197
2023-01-22 13:39:38.968767: step: 818/466, loss: 0.014820974320173264
2023-01-22 13:39:39.603407: step: 820/466, loss: 0.03201407566666603
2023-01-22 13:39:40.299098: step: 822/466, loss: 0.6232259273529053
2023-01-22 13:39:40.871385: step: 824/466, loss: 0.020096469670534134
2023-01-22 13:39:41.501135: step: 826/466, loss: 0.018436051905155182
2023-01-22 13:39:42.126491: step: 828/466, loss: 0.0007196977967396379
2023-01-22 13:39:42.758579: step: 830/466, loss: 0.03440719470381737
2023-01-22 13:39:43.336047: step: 832/466, loss: 0.005299053154885769
2023-01-22 13:39:43.931768: step: 834/466, loss: 0.0396905280649662
2023-01-22 13:39:44.569225: step: 836/466, loss: 0.006178751587867737
2023-01-22 13:39:45.140508: step: 838/466, loss: 0.002416969044134021
2023-01-22 13:39:45.749800: step: 840/466, loss: 0.0021591908298432827
2023-01-22 13:39:46.443439: step: 842/466, loss: 0.06498021632432938
2023-01-22 13:39:47.071378: step: 844/466, loss: 0.381192684173584
2023-01-22 13:39:47.672969: step: 846/466, loss: 0.002702759811654687
2023-01-22 13:39:48.251322: step: 848/466, loss: 0.2226199060678482
2023-01-22 13:39:48.872996: step: 850/466, loss: 0.006855641026049852
2023-01-22 13:39:49.536841: step: 852/466, loss: 0.004108700435608625
2023-01-22 13:39:50.127708: step: 854/466, loss: 0.02524707093834877
2023-01-22 13:39:50.709328: step: 856/466, loss: 0.002686083549633622
2023-01-22 13:39:51.346665: step: 858/466, loss: 0.007875490933656693
2023-01-22 13:39:52.012379: step: 860/466, loss: 0.048078540712594986
2023-01-22 13:39:52.680389: step: 862/466, loss: 0.012722281739115715
2023-01-22 13:39:53.289141: step: 864/466, loss: 0.0064017209224402905
2023-01-22 13:39:53.858116: step: 866/466, loss: 0.021623631939291954
2023-01-22 13:39:54.468454: step: 868/466, loss: 0.08398287743330002
2023-01-22 13:39:55.151658: step: 870/466, loss: 0.15791849792003632
2023-01-22 13:39:55.846901: step: 872/466, loss: 0.009869234636425972
2023-01-22 13:39:56.491189: step: 874/466, loss: 0.055564120411872864
2023-01-22 13:39:57.026614: step: 876/466, loss: 0.022275876253843307
2023-01-22 13:39:57.690886: step: 878/466, loss: 0.012389284558594227
2023-01-22 13:39:58.345338: step: 880/466, loss: 0.039143890142440796
2023-01-22 13:39:58.921306: step: 882/466, loss: 0.001133722485974431
2023-01-22 13:39:59.508182: step: 884/466, loss: 0.0068652331829071045
2023-01-22 13:40:00.057212: step: 886/466, loss: 0.008525632321834564
2023-01-22 13:40:00.734620: step: 888/466, loss: 0.12470296770334244
2023-01-22 13:40:01.408941: step: 890/466, loss: 0.06432314217090607
2023-01-22 13:40:02.009847: step: 892/466, loss: 0.0015465306350961328
2023-01-22 13:40:02.730442: step: 894/466, loss: 0.022779835388064384
2023-01-22 13:40:03.326073: step: 896/466, loss: 0.05004104599356651
2023-01-22 13:40:03.886351: step: 898/466, loss: 0.3507273197174072
2023-01-22 13:40:04.468395: step: 900/466, loss: 0.32218262553215027
2023-01-22 13:40:05.134502: step: 902/466, loss: 0.016275178641080856
2023-01-22 13:40:05.731712: step: 904/466, loss: 0.0206745695322752
2023-01-22 13:40:06.402340: step: 906/466, loss: 0.0029978167731314898
2023-01-22 13:40:07.050573: step: 908/466, loss: 0.009281977079808712
2023-01-22 13:40:07.689393: step: 910/466, loss: 0.022028448060154915
2023-01-22 13:40:08.303870: step: 912/466, loss: 0.02624843269586563
2023-01-22 13:40:08.918905: step: 914/466, loss: 0.007913791574537754
2023-01-22 13:40:09.554639: step: 916/466, loss: 0.15027648210525513
2023-01-22 13:40:10.229683: step: 918/466, loss: 0.10869559645652771
2023-01-22 13:40:10.825840: step: 920/466, loss: 0.0009679266950115561
2023-01-22 13:40:11.357751: step: 922/466, loss: 0.012594206258654594
2023-01-22 13:40:12.138848: step: 924/466, loss: 0.0006866551120765507
2023-01-22 13:40:12.771177: step: 926/466, loss: 0.003792055416852236
2023-01-22 13:40:13.400487: step: 928/466, loss: 0.05514007434248924
2023-01-22 13:40:13.989185: step: 930/466, loss: 0.03771127015352249
2023-01-22 13:40:14.617101: step: 932/466, loss: 0.002431466244161129
==================================================
Loss: 0.051
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3154886363636364, 'r': 0.32925759013282735, 'f1': 0.32222609099350047}, 'combined': 0.23742975125836877, 'epoch': 32}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32615136454060684, 'r': 0.29465479774832803, 'f1': 0.30960409284509005}, 'combined': 0.19386424505253305, 'epoch': 32}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2914075456053068, 'r': 0.3334321631878558, 'f1': 0.3110066371681416}, 'combined': 0.22916278528178852, 'epoch': 32}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.32757229577718305, 'r': 0.31042500953613916, 'f1': 0.318768221099205}, 'combined': 0.1975465032164087, 'epoch': 32}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2686965811965812, 'r': 0.3380376344086022, 'f1': 0.2994047619047619}, 'combined': 0.2206140350877193, 'epoch': 32}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.31993873535860934, 'r': 0.2971066124197384, 'f1': 0.3081002528792978}, 'combined': 0.2043833360684451, 'epoch': 32}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2585227272727273, 'r': 0.325, 'f1': 0.28797468354430383}, 'combined': 0.1919831223628692, 'epoch': 32}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2578125, 'r': 0.358695652173913, 'f1': 0.29999999999999993}, 'combined': 0.14999999999999997, 'epoch': 32}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2916666666666667, 'r': 0.2413793103448276, 'f1': 0.26415094339622647}, 'combined': 0.17610062893081763, 'epoch': 32}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:42:52.523156: step: 2/466, loss: 0.011471913196146488
2023-01-22 13:42:53.149502: step: 4/466, loss: 0.003329317085444927
2023-01-22 13:42:53.769870: step: 6/466, loss: 0.05382179468870163
2023-01-22 13:42:54.309312: step: 8/466, loss: 0.03933628648519516
2023-01-22 13:42:54.931617: step: 10/466, loss: 0.0022515642922371626
2023-01-22 13:42:55.633508: step: 12/466, loss: 0.005104720126837492
2023-01-22 13:42:56.261091: step: 14/466, loss: 0.003365864045917988
2023-01-22 13:42:56.950646: step: 16/466, loss: 0.0024858699180185795
2023-01-22 13:42:57.707041: step: 18/466, loss: 0.005585548467934132
2023-01-22 13:42:58.350241: step: 20/466, loss: 0.023618703708052635
2023-01-22 13:42:58.996148: step: 22/466, loss: 0.05313389003276825
2023-01-22 13:42:59.565541: step: 24/466, loss: 0.016346216201782227
2023-01-22 13:43:00.198824: step: 26/466, loss: 0.016453605145215988
2023-01-22 13:43:00.830178: step: 28/466, loss: 0.018995080143213272
2023-01-22 13:43:01.460432: step: 30/466, loss: 0.022241417318582535
2023-01-22 13:43:02.090013: step: 32/466, loss: 0.012925678864121437
2023-01-22 13:43:02.737475: step: 34/466, loss: 0.0032370146363973618
2023-01-22 13:43:03.385414: step: 36/466, loss: 0.010440031997859478
2023-01-22 13:43:04.037775: step: 38/466, loss: 0.0012315127532929182
2023-01-22 13:43:04.658053: step: 40/466, loss: 0.02326072007417679
2023-01-22 13:43:05.306482: step: 42/466, loss: 0.00437350245192647
2023-01-22 13:43:05.874667: step: 44/466, loss: 0.027784300968050957
2023-01-22 13:43:06.502272: step: 46/466, loss: 5.960246562608518e-05
2023-01-22 13:43:07.096817: step: 48/466, loss: 0.46270838379859924
2023-01-22 13:43:07.726183: step: 50/466, loss: 0.31255415081977844
2023-01-22 13:43:08.364888: step: 52/466, loss: 0.02952492982149124
2023-01-22 13:43:09.095360: step: 54/466, loss: 0.004272154998034239
2023-01-22 13:43:09.685182: step: 56/466, loss: 0.0911722257733345
2023-01-22 13:43:10.346163: step: 58/466, loss: 0.006820019334554672
2023-01-22 13:43:11.010640: step: 60/466, loss: 0.03626310080289841
2023-01-22 13:43:11.576688: step: 62/466, loss: 0.012094401754438877
2023-01-22 13:43:12.247603: step: 64/466, loss: 0.02697291038930416
2023-01-22 13:43:12.825471: step: 66/466, loss: 0.0008113411604426801
2023-01-22 13:43:13.461018: step: 68/466, loss: 1.1584266424179077
2023-01-22 13:43:14.126209: step: 70/466, loss: 0.01978868432343006
2023-01-22 13:43:14.719015: step: 72/466, loss: 0.05368809401988983
2023-01-22 13:43:15.333312: step: 74/466, loss: 0.0010436509037390351
2023-01-22 13:43:15.945365: step: 76/466, loss: 0.006107044406235218
2023-01-22 13:43:16.580044: step: 78/466, loss: 0.022841036319732666
2023-01-22 13:43:17.180960: step: 80/466, loss: 0.0010020930785685778
2023-01-22 13:43:17.847803: step: 82/466, loss: 0.025901824235916138
2023-01-22 13:43:18.430368: step: 84/466, loss: 0.008335251361131668
2023-01-22 13:43:19.023476: step: 86/466, loss: 0.032207243144512177
2023-01-22 13:43:19.654257: step: 88/466, loss: 0.018256762996315956
2023-01-22 13:43:20.235455: step: 90/466, loss: 0.0008741633500903845
2023-01-22 13:43:20.845953: step: 92/466, loss: 0.005068059545010328
2023-01-22 13:43:21.487399: step: 94/466, loss: 0.2405049204826355
2023-01-22 13:43:22.060166: step: 96/466, loss: 0.004374948795884848
2023-01-22 13:43:22.636287: step: 98/466, loss: 0.0037068433593958616
2023-01-22 13:43:23.313251: step: 100/466, loss: 0.003929052967578173
2023-01-22 13:43:23.921795: step: 102/466, loss: 0.02032223902642727
2023-01-22 13:43:24.495099: step: 104/466, loss: 0.0019619495142251253
2023-01-22 13:43:25.137376: step: 106/466, loss: 0.008959521539509296
2023-01-22 13:43:25.751277: step: 108/466, loss: 0.38862621784210205
2023-01-22 13:43:26.393221: step: 110/466, loss: 0.016267826780676842
2023-01-22 13:43:27.037864: step: 112/466, loss: 0.02662738785147667
2023-01-22 13:43:27.640797: step: 114/466, loss: 0.04652956500649452
2023-01-22 13:43:28.279573: step: 116/466, loss: 0.018068883568048477
2023-01-22 13:43:28.868294: step: 118/466, loss: 0.017216501757502556
2023-01-22 13:43:29.473414: step: 120/466, loss: 0.00020992594363633543
2023-01-22 13:43:30.147079: step: 122/466, loss: 0.0007761769229546189
2023-01-22 13:43:30.688602: step: 124/466, loss: 0.02506084553897381
2023-01-22 13:43:31.256974: step: 126/466, loss: 0.004943248815834522
2023-01-22 13:43:31.919064: step: 128/466, loss: 0.0730307549238205
2023-01-22 13:43:32.488277: step: 130/466, loss: 0.012557188980281353
2023-01-22 13:43:33.096464: step: 132/466, loss: 0.0061327372677624226
2023-01-22 13:43:33.732490: step: 134/466, loss: 0.020070943981409073
2023-01-22 13:43:34.419311: step: 136/466, loss: 0.0011945957085117698
2023-01-22 13:43:35.029103: step: 138/466, loss: 0.006863201502710581
2023-01-22 13:43:35.651091: step: 140/466, loss: 0.000985067104920745
2023-01-22 13:43:36.290444: step: 142/466, loss: 3.5155653953552246
2023-01-22 13:43:36.888150: step: 144/466, loss: 0.007382845506072044
2023-01-22 13:43:37.491111: step: 146/466, loss: 0.0032322753686457872
2023-01-22 13:43:38.169464: step: 148/466, loss: 0.006009763106703758
2023-01-22 13:43:38.793366: step: 150/466, loss: 0.00329978228546679
2023-01-22 13:43:39.402748: step: 152/466, loss: 0.00011540047853486612
2023-01-22 13:43:40.045541: step: 154/466, loss: 0.031016090884804726
2023-01-22 13:43:40.656817: step: 156/466, loss: 0.018580617383122444
2023-01-22 13:43:41.308428: step: 158/466, loss: 0.011402607895433903
2023-01-22 13:43:41.912276: step: 160/466, loss: 0.020523978397250175
2023-01-22 13:43:42.520955: step: 162/466, loss: 0.05876913666725159
2023-01-22 13:43:43.167414: step: 164/466, loss: 0.0005150781362317502
2023-01-22 13:43:43.779178: step: 166/466, loss: 0.0001547386054880917
2023-01-22 13:43:44.406222: step: 168/466, loss: 0.07472080737352371
2023-01-22 13:43:45.070954: step: 170/466, loss: 0.12995728850364685
2023-01-22 13:43:45.688424: step: 172/466, loss: 0.005580767057836056
2023-01-22 13:43:46.342819: step: 174/466, loss: 0.018097488209605217
2023-01-22 13:43:46.931312: step: 176/466, loss: 0.014467814937233925
2023-01-22 13:43:47.564660: step: 178/466, loss: 0.06239444389939308
2023-01-22 13:43:48.098405: step: 180/466, loss: 0.013972893357276917
2023-01-22 13:43:48.684465: step: 182/466, loss: 0.21559743583202362
2023-01-22 13:43:49.330038: step: 184/466, loss: 0.004221683833748102
2023-01-22 13:43:49.961383: step: 186/466, loss: 0.008235514163970947
2023-01-22 13:43:50.578221: step: 188/466, loss: 0.00017162322183139622
2023-01-22 13:43:51.248622: step: 190/466, loss: 0.0033084298484027386
2023-01-22 13:43:51.816330: step: 192/466, loss: 0.00020260861492715776
2023-01-22 13:43:52.512079: step: 194/466, loss: 0.013346048071980476
2023-01-22 13:43:53.110447: step: 196/466, loss: 0.1149318590760231
2023-01-22 13:43:53.715986: step: 198/466, loss: 0.009522732347249985
2023-01-22 13:43:54.337222: step: 200/466, loss: 0.01283420529216528
2023-01-22 13:43:54.878181: step: 202/466, loss: 0.08689934760332108
2023-01-22 13:43:55.546260: step: 204/466, loss: 0.0014092724304646254
2023-01-22 13:43:56.161731: step: 206/466, loss: 0.026221109554171562
2023-01-22 13:43:56.791236: step: 208/466, loss: 0.002638742793351412
2023-01-22 13:43:57.446927: step: 210/466, loss: 0.01947478950023651
2023-01-22 13:43:58.087256: step: 212/466, loss: 0.00884014181792736
2023-01-22 13:43:58.758872: step: 214/466, loss: 0.007349574007093906
2023-01-22 13:43:59.417598: step: 216/466, loss: 0.07528423517942429
2023-01-22 13:43:59.997771: step: 218/466, loss: 0.008929373696446419
2023-01-22 13:44:00.606097: step: 220/466, loss: 0.0001904977107187733
2023-01-22 13:44:01.143748: step: 222/466, loss: 0.0016717190155759454
2023-01-22 13:44:01.878694: step: 224/466, loss: 0.006900259293615818
2023-01-22 13:44:02.440196: step: 226/466, loss: 0.12913194298744202
2023-01-22 13:44:03.040172: step: 228/466, loss: 0.0014772651484236121
2023-01-22 13:44:03.666414: step: 230/466, loss: 0.028150325641036034
2023-01-22 13:44:04.294814: step: 232/466, loss: 0.000608698173891753
2023-01-22 13:44:04.903946: step: 234/466, loss: 0.03875589743256569
2023-01-22 13:44:05.548130: step: 236/466, loss: 0.00619150884449482
2023-01-22 13:44:06.072889: step: 238/466, loss: 0.013868349604308605
2023-01-22 13:44:06.696303: step: 240/466, loss: 0.002042794832959771
2023-01-22 13:44:07.271058: step: 242/466, loss: 0.00555034726858139
2023-01-22 13:44:07.840711: step: 244/466, loss: 0.09385880827903748
2023-01-22 13:44:08.475974: step: 246/466, loss: 0.0006551188416779041
2023-01-22 13:44:09.071462: step: 248/466, loss: 0.0023250433150678873
2023-01-22 13:44:09.684010: step: 250/466, loss: 0.03568408265709877
2023-01-22 13:44:10.341187: step: 252/466, loss: 0.005665675271302462
2023-01-22 13:44:10.954674: step: 254/466, loss: 0.01324258279055357
2023-01-22 13:44:11.525223: step: 256/466, loss: 0.0017058087978512049
2023-01-22 13:44:12.150070: step: 258/466, loss: 0.00028060312615707517
2023-01-22 13:44:12.819455: step: 260/466, loss: 0.0016577666392549872
2023-01-22 13:44:13.470307: step: 262/466, loss: 0.0002143417514162138
2023-01-22 13:44:14.105600: step: 264/466, loss: 0.008948958478868008
2023-01-22 13:44:14.806065: step: 266/466, loss: 0.024027816951274872
2023-01-22 13:44:15.459850: step: 268/466, loss: 0.0371001698076725
2023-01-22 13:44:16.071440: step: 270/466, loss: 0.002744163852185011
2023-01-22 13:44:16.708242: step: 272/466, loss: 0.012039094232022762
2023-01-22 13:44:17.336824: step: 274/466, loss: 0.00039196471334435046
2023-01-22 13:44:18.002774: step: 276/466, loss: 0.0013024767395108938
2023-01-22 13:44:18.659127: step: 278/466, loss: 0.5007848143577576
2023-01-22 13:44:19.302379: step: 280/466, loss: 0.019194647669792175
2023-01-22 13:44:19.925022: step: 282/466, loss: 0.0012372337514534593
2023-01-22 13:44:20.547778: step: 284/466, loss: 0.00508892722427845
2023-01-22 13:44:21.120626: step: 286/466, loss: 0.0002391472808085382
2023-01-22 13:44:21.797140: step: 288/466, loss: 0.010844860225915909
2023-01-22 13:44:22.440147: step: 290/466, loss: 0.006039358675479889
2023-01-22 13:44:23.042059: step: 292/466, loss: 0.012529624626040459
2023-01-22 13:44:23.700338: step: 294/466, loss: 0.09980753809213638
2023-01-22 13:44:24.363669: step: 296/466, loss: 0.0014879453228786588
2023-01-22 13:44:24.967218: step: 298/466, loss: 0.010294638574123383
2023-01-22 13:44:25.703413: step: 300/466, loss: 0.1290862262248993
2023-01-22 13:44:26.357981: step: 302/466, loss: 0.07933500409126282
2023-01-22 13:44:27.004517: step: 304/466, loss: 0.37784236669540405
2023-01-22 13:44:27.620518: step: 306/466, loss: 0.01543118804693222
2023-01-22 13:44:28.228951: step: 308/466, loss: 0.0007847215165384114
2023-01-22 13:44:28.860745: step: 310/466, loss: 0.0033282111398875713
2023-01-22 13:44:29.456742: step: 312/466, loss: 0.0855177491903305
2023-01-22 13:44:30.103924: step: 314/466, loss: 0.000362559367204085
2023-01-22 13:44:30.677319: step: 316/466, loss: 0.00028692680643871427
2023-01-22 13:44:31.313567: step: 318/466, loss: 0.0013479833723977208
2023-01-22 13:44:31.847686: step: 320/466, loss: 0.0003531108086463064
2023-01-22 13:44:32.453312: step: 322/466, loss: 0.0015235940227285028
2023-01-22 13:44:32.989457: step: 324/466, loss: 0.0012759566307067871
2023-01-22 13:44:33.640127: step: 326/466, loss: 0.003484574379399419
2023-01-22 13:44:34.197722: step: 328/466, loss: 0.01791924424469471
2023-01-22 13:44:34.777711: step: 330/466, loss: 0.0018407482421025634
2023-01-22 13:44:35.399724: step: 332/466, loss: 0.001974991988390684
2023-01-22 13:44:36.065543: step: 334/466, loss: 0.016238750889897346
2023-01-22 13:44:36.596961: step: 336/466, loss: 0.007455571088939905
2023-01-22 13:44:37.305660: step: 338/466, loss: 0.024535367265343666
2023-01-22 13:44:37.896592: step: 340/466, loss: 0.051678985357284546
2023-01-22 13:44:38.477562: step: 342/466, loss: 0.03882472589612007
2023-01-22 13:44:39.080773: step: 344/466, loss: 0.01984047144651413
2023-01-22 13:44:39.763663: step: 346/466, loss: 0.013271857053041458
2023-01-22 13:44:40.325574: step: 348/466, loss: 0.004043884109705687
2023-01-22 13:44:40.904484: step: 350/466, loss: 0.011178984306752682
2023-01-22 13:44:41.548714: step: 352/466, loss: 0.06485337018966675
2023-01-22 13:44:42.209646: step: 354/466, loss: 0.005821486935019493
2023-01-22 13:44:42.801271: step: 356/466, loss: 0.0008058268576860428
2023-01-22 13:44:43.380618: step: 358/466, loss: 0.0013918459881097078
2023-01-22 13:44:44.028330: step: 360/466, loss: 0.0012359642423689365
2023-01-22 13:44:44.652506: step: 362/466, loss: 0.003919335547834635
2023-01-22 13:44:45.244945: step: 364/466, loss: 0.005641720723360777
2023-01-22 13:44:45.882114: step: 366/466, loss: 0.017113283276557922
2023-01-22 13:44:46.493793: step: 368/466, loss: 0.0023856135085225105
2023-01-22 13:44:47.106793: step: 370/466, loss: 0.00031498647877015173
2023-01-22 13:44:47.791245: step: 372/466, loss: 0.016652140766382217
2023-01-22 13:44:48.460609: step: 374/466, loss: 0.0076950243674218655
2023-01-22 13:44:49.050267: step: 376/466, loss: 0.04501022771000862
2023-01-22 13:44:49.680825: step: 378/466, loss: 0.005576370283961296
2023-01-22 13:44:50.353471: step: 380/466, loss: 0.0011929406318813562
2023-01-22 13:44:50.957392: step: 382/466, loss: 0.05035883188247681
2023-01-22 13:44:51.627848: step: 384/466, loss: 0.019984649494290352
2023-01-22 13:44:52.259205: step: 386/466, loss: 0.01815779134631157
2023-01-22 13:44:52.872775: step: 388/466, loss: 0.003168065333738923
2023-01-22 13:44:53.537225: step: 390/466, loss: 0.011367907747626305
2023-01-22 13:44:54.187809: step: 392/466, loss: 0.010168864391744137
2023-01-22 13:44:54.758786: step: 394/466, loss: 0.004494980908930302
2023-01-22 13:44:55.347111: step: 396/466, loss: 0.08662625402212143
2023-01-22 13:44:55.954338: step: 398/466, loss: 0.0009130419930443168
2023-01-22 13:44:56.537967: step: 400/466, loss: 0.034484755247831345
2023-01-22 13:44:57.143163: step: 402/466, loss: 0.010733877308666706
2023-01-22 13:44:57.775499: step: 404/466, loss: 8.5583480540663e-05
2023-01-22 13:44:58.429331: step: 406/466, loss: 0.0028839707374572754
2023-01-22 13:44:59.070111: step: 408/466, loss: 0.009808849543333054
2023-01-22 13:44:59.672590: step: 410/466, loss: 0.04710133746266365
2023-01-22 13:45:00.285977: step: 412/466, loss: 0.009870425797998905
2023-01-22 13:45:00.870761: step: 414/466, loss: 0.003070020116865635
2023-01-22 13:45:01.490675: step: 416/466, loss: 0.006086159497499466
2023-01-22 13:45:02.143165: step: 418/466, loss: 0.010665013454854488
2023-01-22 13:45:02.717759: step: 420/466, loss: 0.0019336992409080267
2023-01-22 13:45:03.354011: step: 422/466, loss: 0.017348945140838623
2023-01-22 13:45:04.027779: step: 424/466, loss: 0.03703954070806503
2023-01-22 13:45:04.618891: step: 426/466, loss: 0.0038241290021687746
2023-01-22 13:45:05.251926: step: 428/466, loss: 0.00012386307935230434
2023-01-22 13:45:05.843834: step: 430/466, loss: 0.009493958204984665
2023-01-22 13:45:06.437701: step: 432/466, loss: 0.035253990441560745
2023-01-22 13:45:07.095894: step: 434/466, loss: 0.04366471245884895
2023-01-22 13:45:07.666606: step: 436/466, loss: 0.008260741829872131
2023-01-22 13:45:08.294381: step: 438/466, loss: 0.05740272253751755
2023-01-22 13:45:08.953870: step: 440/466, loss: 0.007057404611259699
2023-01-22 13:45:09.560157: step: 442/466, loss: 0.017819110304117203
2023-01-22 13:45:10.139279: step: 444/466, loss: 0.005557534750550985
2023-01-22 13:45:10.736588: step: 446/466, loss: 0.0004817653098143637
2023-01-22 13:45:11.329718: step: 448/466, loss: 0.032076407223939896
2023-01-22 13:45:11.980977: step: 450/466, loss: 1.6345652341842651
2023-01-22 13:45:12.645208: step: 452/466, loss: 0.019103243947029114
2023-01-22 13:45:13.225162: step: 454/466, loss: 0.0009005839237943292
2023-01-22 13:45:13.806452: step: 456/466, loss: 2.51334895438049e-05
2023-01-22 13:45:14.429048: step: 458/466, loss: 0.003000382101163268
2023-01-22 13:45:15.091418: step: 460/466, loss: 0.03360116109251976
2023-01-22 13:45:15.765919: step: 462/466, loss: 0.036374256014823914
2023-01-22 13:45:16.396234: step: 464/466, loss: 0.4118907153606415
2023-01-22 13:45:16.953985: step: 466/466, loss: 0.0010197700466960669
2023-01-22 13:45:17.539713: step: 468/466, loss: 0.11220012605190277
2023-01-22 13:45:18.162161: step: 470/466, loss: 0.01524397637695074
2023-01-22 13:45:18.730385: step: 472/466, loss: 0.008090157993137836
2023-01-22 13:45:19.410176: step: 474/466, loss: 0.009427536278963089
2023-01-22 13:45:20.081240: step: 476/466, loss: 0.0007979574147611856
2023-01-22 13:45:20.728289: step: 478/466, loss: 0.010843045078217983
2023-01-22 13:45:21.323263: step: 480/466, loss: 0.13042069971561432
2023-01-22 13:45:21.929655: step: 482/466, loss: 0.002141157165169716
2023-01-22 13:45:22.508577: step: 484/466, loss: 0.005161554552614689
2023-01-22 13:45:23.160770: step: 486/466, loss: 0.0012545384233817458
2023-01-22 13:45:23.801417: step: 488/466, loss: 0.005698261316865683
2023-01-22 13:45:24.429064: step: 490/466, loss: 0.005855304189026356
2023-01-22 13:45:25.009443: step: 492/466, loss: 0.0001480466453358531
2023-01-22 13:45:25.650054: step: 494/466, loss: 0.011437050998210907
2023-01-22 13:45:26.203803: step: 496/466, loss: 0.06595665216445923
2023-01-22 13:45:26.772310: step: 498/466, loss: 0.0012464667670428753
2023-01-22 13:45:27.340058: step: 500/466, loss: 0.0026049893349409103
2023-01-22 13:45:27.994085: step: 502/466, loss: 0.010979488492012024
2023-01-22 13:45:28.649640: step: 504/466, loss: 0.40448689460754395
2023-01-22 13:45:29.292423: step: 506/466, loss: 0.002377287019044161
2023-01-22 13:45:29.948842: step: 508/466, loss: 0.034350961446762085
2023-01-22 13:45:30.570690: step: 510/466, loss: 3.383839066373184e-05
2023-01-22 13:45:31.164682: step: 512/466, loss: 0.03541983291506767
2023-01-22 13:45:31.829120: step: 514/466, loss: 0.0029128689784556627
2023-01-22 13:45:32.446170: step: 516/466, loss: 0.0017191277584061027
2023-01-22 13:45:33.099810: step: 518/466, loss: 0.004536142572760582
2023-01-22 13:45:33.713436: step: 520/466, loss: 0.022383177652955055
2023-01-22 13:45:34.281776: step: 522/466, loss: 0.0029085720889270306
2023-01-22 13:45:34.921253: step: 524/466, loss: 0.11277299374341965
2023-01-22 13:45:35.494177: step: 526/466, loss: 0.00013020861661061645
2023-01-22 13:45:36.083363: step: 528/466, loss: 0.0013358322903513908
2023-01-22 13:45:36.697141: step: 530/466, loss: 0.006719015073031187
2023-01-22 13:45:37.327249: step: 532/466, loss: 0.02594134397804737
2023-01-22 13:45:37.921651: step: 534/466, loss: 0.0010921203065663576
2023-01-22 13:45:38.581488: step: 536/466, loss: 0.1330503523349762
2023-01-22 13:45:39.183023: step: 538/466, loss: 0.061880066990852356
2023-01-22 13:45:39.830927: step: 540/466, loss: 0.0036926132161170244
2023-01-22 13:45:40.503988: step: 542/466, loss: 0.0010837906738743186
2023-01-22 13:45:41.128220: step: 544/466, loss: 0.009028531610965729
2023-01-22 13:45:41.809665: step: 546/466, loss: 0.0003460723673924804
2023-01-22 13:45:42.455506: step: 548/466, loss: 0.00035746858338825405
2023-01-22 13:45:43.074651: step: 550/466, loss: 0.20476196706295013
2023-01-22 13:45:43.626939: step: 552/466, loss: 0.008912076242268085
2023-01-22 13:45:44.241054: step: 554/466, loss: 0.005757046397775412
2023-01-22 13:45:44.830323: step: 556/466, loss: 0.020501768216490746
2023-01-22 13:45:45.571346: step: 558/466, loss: 0.10718557238578796
2023-01-22 13:45:46.224920: step: 560/466, loss: 0.004823639523237944
2023-01-22 13:45:46.866479: step: 562/466, loss: 0.04855097457766533
2023-01-22 13:45:47.496936: step: 564/466, loss: 0.04375689476728439
2023-01-22 13:45:48.085622: step: 566/466, loss: 0.00026579920086078346
2023-01-22 13:45:48.740533: step: 568/466, loss: 0.00195736694149673
2023-01-22 13:45:49.410205: step: 570/466, loss: 0.011081330478191376
2023-01-22 13:45:50.161015: step: 572/466, loss: 0.06517162173986435
2023-01-22 13:45:50.795059: step: 574/466, loss: 0.013517320156097412
2023-01-22 13:45:51.384833: step: 576/466, loss: 0.018146933987736702
2023-01-22 13:45:51.975327: step: 578/466, loss: 0.004572906531393528
2023-01-22 13:45:52.638840: step: 580/466, loss: 0.0022504201624542475
2023-01-22 13:45:53.234979: step: 582/466, loss: 0.0004263647715561092
2023-01-22 13:45:53.878292: step: 584/466, loss: 0.005549941677600145
2023-01-22 13:45:54.509029: step: 586/466, loss: 0.010425898246467113
2023-01-22 13:45:55.130786: step: 588/466, loss: 0.014032966457307339
2023-01-22 13:45:55.876506: step: 590/466, loss: 0.7224438786506653
2023-01-22 13:45:56.446073: step: 592/466, loss: 0.009805294685065746
2023-01-22 13:45:57.035472: step: 594/466, loss: 0.004754491616040468
2023-01-22 13:45:57.615874: step: 596/466, loss: 0.00016097823390737176
2023-01-22 13:45:58.187232: step: 598/466, loss: 0.010585645213723183
2023-01-22 13:45:58.810387: step: 600/466, loss: 0.018932558596134186
2023-01-22 13:45:59.404809: step: 602/466, loss: 0.016921402886509895
2023-01-22 13:46:00.028704: step: 604/466, loss: 0.06691353023052216
2023-01-22 13:46:00.616229: step: 606/466, loss: 0.026497000828385353
2023-01-22 13:46:01.172598: step: 608/466, loss: 0.056519560515880585
2023-01-22 13:46:01.810655: step: 610/466, loss: 0.0020213983952999115
2023-01-22 13:46:02.410648: step: 612/466, loss: 0.021570589393377304
2023-01-22 13:46:03.010312: step: 614/466, loss: 0.04084527865052223
2023-01-22 13:46:03.677349: step: 616/466, loss: 0.05565088242292404
2023-01-22 13:46:04.308356: step: 618/466, loss: 0.0020173382945358753
2023-01-22 13:46:04.899805: step: 620/466, loss: 0.029354479163885117
2023-01-22 13:46:05.576393: step: 622/466, loss: 0.005398329347372055
2023-01-22 13:46:06.204008: step: 624/466, loss: 0.09820173680782318
2023-01-22 13:46:06.806937: step: 626/466, loss: 0.03491608053445816
2023-01-22 13:46:07.437225: step: 628/466, loss: 0.054343245923519135
2023-01-22 13:46:08.069774: step: 630/466, loss: 0.00017145861056633294
2023-01-22 13:46:08.695339: step: 632/466, loss: 0.012736142612993717
2023-01-22 13:46:09.444633: step: 634/466, loss: 0.13187287747859955
2023-01-22 13:46:10.011212: step: 636/466, loss: 0.0011665790807455778
2023-01-22 13:46:10.676953: step: 638/466, loss: 0.004454441834241152
2023-01-22 13:46:11.263952: step: 640/466, loss: 0.0033450776245445013
2023-01-22 13:46:12.078772: step: 642/466, loss: 0.014408610761165619
2023-01-22 13:46:12.724534: step: 644/466, loss: 0.0001343740150332451
2023-01-22 13:46:13.407795: step: 646/466, loss: 0.018189314752817154
2023-01-22 13:46:14.011061: step: 648/466, loss: 0.0004681172431446612
2023-01-22 13:46:14.632586: step: 650/466, loss: 0.016073819249868393
2023-01-22 13:46:15.269485: step: 652/466, loss: 0.0035687494091689587
2023-01-22 13:46:15.885340: step: 654/466, loss: 0.09453099966049194
2023-01-22 13:46:16.632586: step: 656/466, loss: 0.003925571218132973
2023-01-22 13:46:17.286919: step: 658/466, loss: 0.03393247351050377
2023-01-22 13:46:17.978633: step: 660/466, loss: 0.07539302855730057
2023-01-22 13:46:18.613778: step: 662/466, loss: 0.015005357563495636
2023-01-22 13:46:19.247360: step: 664/466, loss: 0.013056541793048382
2023-01-22 13:46:19.922950: step: 666/466, loss: 0.11358191072940826
2023-01-22 13:46:20.523327: step: 668/466, loss: 0.4263495206832886
2023-01-22 13:46:21.160858: step: 670/466, loss: 0.012658163905143738
2023-01-22 13:46:21.742277: step: 672/466, loss: 0.006221231073141098
2023-01-22 13:46:22.463720: step: 674/466, loss: 0.044858161360025406
2023-01-22 13:46:23.068896: step: 676/466, loss: 0.0036089112982153893
2023-01-22 13:46:23.711106: step: 678/466, loss: 0.0018083082977682352
2023-01-22 13:46:24.322586: step: 680/466, loss: 0.0073106917552649975
2023-01-22 13:46:24.978060: step: 682/466, loss: 0.4257279634475708
2023-01-22 13:46:25.622896: step: 684/466, loss: 0.01332678273320198
2023-01-22 13:46:26.192513: step: 686/466, loss: 0.029636632651090622
2023-01-22 13:46:26.782716: step: 688/466, loss: 0.3315723240375519
2023-01-22 13:46:27.359341: step: 690/466, loss: 0.001709525240585208
2023-01-22 13:46:27.970903: step: 692/466, loss: 0.0014177437406033278
2023-01-22 13:46:28.596823: step: 694/466, loss: 0.0018577645532786846
2023-01-22 13:46:29.201637: step: 696/466, loss: 0.0016431428957730532
2023-01-22 13:46:29.851844: step: 698/466, loss: 0.0236639566719532
2023-01-22 13:46:30.457283: step: 700/466, loss: 0.015035852789878845
2023-01-22 13:46:31.092518: step: 702/466, loss: 0.06029500067234039
2023-01-22 13:46:31.723345: step: 704/466, loss: 0.06643743067979813
2023-01-22 13:46:32.343679: step: 706/466, loss: 0.02140481024980545
2023-01-22 13:46:32.951304: step: 708/466, loss: 0.015438289381563663
2023-01-22 13:46:33.550143: step: 710/466, loss: 0.04029211401939392
2023-01-22 13:46:34.217445: step: 712/466, loss: 0.00407075323164463
2023-01-22 13:46:34.832133: step: 714/466, loss: 0.00291248201392591
2023-01-22 13:46:35.538540: step: 716/466, loss: 0.0033066130708903074
2023-01-22 13:46:36.121123: step: 718/466, loss: 3.5524841223377734e-05
2023-01-22 13:46:36.768620: step: 720/466, loss: 0.0008308955584652722
2023-01-22 13:46:37.338714: step: 722/466, loss: 0.011513054370880127
2023-01-22 13:46:37.999525: step: 724/466, loss: 0.0005869634333066642
2023-01-22 13:46:38.582758: step: 726/466, loss: 0.0005612410604953766
2023-01-22 13:46:39.260576: step: 728/466, loss: 0.47174203395843506
2023-01-22 13:46:39.915736: step: 730/466, loss: 0.03442941606044769
2023-01-22 13:46:40.547062: step: 732/466, loss: 0.008386259898543358
2023-01-22 13:46:41.191618: step: 734/466, loss: 0.0007885558879934251
2023-01-22 13:46:41.723329: step: 736/466, loss: 0.004477986600250006
2023-01-22 13:46:42.375733: step: 738/466, loss: 0.03391421213746071
2023-01-22 13:46:43.056098: step: 740/466, loss: 0.043160002678632736
2023-01-22 13:46:43.672569: step: 742/466, loss: 1.754863977432251
2023-01-22 13:46:44.250924: step: 744/466, loss: 0.009212441742420197
2023-01-22 13:46:44.853618: step: 746/466, loss: 0.03072165511548519
2023-01-22 13:46:45.410092: step: 748/466, loss: 0.018118523061275482
2023-01-22 13:46:46.028011: step: 750/466, loss: 0.02915901690721512
2023-01-22 13:46:46.576651: step: 752/466, loss: 0.016097718849778175
2023-01-22 13:46:47.179975: step: 754/466, loss: 0.000931809947360307
2023-01-22 13:46:47.811190: step: 756/466, loss: 0.013095092959702015
2023-01-22 13:46:48.439059: step: 758/466, loss: 0.0061671980656683445
2023-01-22 13:46:49.074246: step: 760/466, loss: 0.09173333644866943
2023-01-22 13:46:49.636167: step: 762/466, loss: 0.001967896241694689
2023-01-22 13:46:50.312677: step: 764/466, loss: 0.04345665127038956
2023-01-22 13:46:50.916076: step: 766/466, loss: 0.03235586732625961
2023-01-22 13:46:51.592513: step: 768/466, loss: 0.016252994537353516
2023-01-22 13:46:52.118473: step: 770/466, loss: 0.005299590528011322
2023-01-22 13:46:52.715141: step: 772/466, loss: 0.013432987034320831
2023-01-22 13:46:53.283929: step: 774/466, loss: 0.009076020680367947
2023-01-22 13:46:53.871431: step: 776/466, loss: 0.005608452018350363
2023-01-22 13:46:54.498381: step: 778/466, loss: 0.009004445746541023
2023-01-22 13:46:55.090333: step: 780/466, loss: 0.04556947201490402
2023-01-22 13:46:55.676087: step: 782/466, loss: 0.004479180555790663
2023-01-22 13:46:56.269460: step: 784/466, loss: 2.405329942703247
2023-01-22 13:46:56.877682: step: 786/466, loss: 0.0009086414938792586
2023-01-22 13:46:57.488596: step: 788/466, loss: 0.0023360440973192453
2023-01-22 13:46:58.110516: step: 790/466, loss: 0.0355655737221241
2023-01-22 13:46:58.730833: step: 792/466, loss: 0.19567205011844635
2023-01-22 13:46:59.378254: step: 794/466, loss: 0.02821464277803898
2023-01-22 13:46:59.979944: step: 796/466, loss: 0.09833505749702454
2023-01-22 13:47:00.615443: step: 798/466, loss: 0.008969747461378574
2023-01-22 13:47:01.249262: step: 800/466, loss: 0.03653215989470482
2023-01-22 13:47:01.822485: step: 802/466, loss: 0.008475563488900661
2023-01-22 13:47:02.451229: step: 804/466, loss: 0.019438931718468666
2023-01-22 13:47:03.094797: step: 806/466, loss: 0.003730077063664794
2023-01-22 13:47:03.715917: step: 808/466, loss: 0.00568796182051301
2023-01-22 13:47:04.357481: step: 810/466, loss: 0.017519226297736168
2023-01-22 13:47:05.105779: step: 812/466, loss: 0.09852321445941925
2023-01-22 13:47:05.718028: step: 814/466, loss: 0.0025821272283792496
2023-01-22 13:47:06.340326: step: 816/466, loss: 0.006342741195112467
2023-01-22 13:47:06.949822: step: 818/466, loss: 0.003560805693268776
2023-01-22 13:47:07.556344: step: 820/466, loss: 0.004143399652093649
2023-01-22 13:47:08.103170: step: 822/466, loss: 0.0027600382454693317
2023-01-22 13:47:08.680227: step: 824/466, loss: 0.41122865676879883
2023-01-22 13:47:09.329378: step: 826/466, loss: 0.03294564038515091
2023-01-22 13:47:09.904629: step: 828/466, loss: 0.030116839334368706
2023-01-22 13:47:10.555067: step: 830/466, loss: 0.44258734583854675
2023-01-22 13:47:11.207811: step: 832/466, loss: 0.02711624652147293
2023-01-22 13:47:11.824468: step: 834/466, loss: 0.04400736093521118
2023-01-22 13:47:12.464708: step: 836/466, loss: 0.005828135181218386
2023-01-22 13:47:13.067826: step: 838/466, loss: 0.037157755345106125
2023-01-22 13:47:13.642596: step: 840/466, loss: 0.3639180064201355
2023-01-22 13:47:14.215163: step: 842/466, loss: 0.00658583827316761
2023-01-22 13:47:14.832689: step: 844/466, loss: 0.005545522086322308
2023-01-22 13:47:15.357929: step: 846/466, loss: 0.004206244368106127
2023-01-22 13:47:15.984157: step: 848/466, loss: 0.007470234762877226
2023-01-22 13:47:16.626446: step: 850/466, loss: 0.0072822291404008865
2023-01-22 13:47:17.260884: step: 852/466, loss: 0.04417445510625839
2023-01-22 13:47:17.828226: step: 854/466, loss: 0.032138094305992126
2023-01-22 13:47:18.420708: step: 856/466, loss: 0.00297050760127604
2023-01-22 13:47:19.046394: step: 858/466, loss: 0.0018105015624314547
2023-01-22 13:47:19.600412: step: 860/466, loss: 0.012027028016746044
2023-01-22 13:47:20.212321: step: 862/466, loss: 0.002343433443456888
2023-01-22 13:47:20.810211: step: 864/466, loss: 0.03817830607295036
2023-01-22 13:47:21.408419: step: 866/466, loss: 0.01945595256984234
2023-01-22 13:47:22.035638: step: 868/466, loss: 0.00023947417503222823
2023-01-22 13:47:22.638371: step: 870/466, loss: 0.009762587957084179
2023-01-22 13:47:23.237127: step: 872/466, loss: 0.019771510735154152
2023-01-22 13:47:23.811441: step: 874/466, loss: 0.027143366634845734
2023-01-22 13:47:24.420214: step: 876/466, loss: 0.01708270236849785
2023-01-22 13:47:25.157258: step: 878/466, loss: 0.014565062709152699
2023-01-22 13:47:25.770862: step: 880/466, loss: 4.5406017306959257e-05
2023-01-22 13:47:26.398442: step: 882/466, loss: 0.03155679255723953
2023-01-22 13:47:27.040565: step: 884/466, loss: 0.03435644507408142
2023-01-22 13:47:27.662667: step: 886/466, loss: 0.0007988469442352653
2023-01-22 13:47:28.290927: step: 888/466, loss: 0.05017571896314621
2023-01-22 13:47:28.920394: step: 890/466, loss: 0.1087830513715744
2023-01-22 13:47:29.517463: step: 892/466, loss: 0.013522031717002392
2023-01-22 13:47:30.081363: step: 894/466, loss: 0.000354521325789392
2023-01-22 13:47:30.739522: step: 896/466, loss: 0.003120807697996497
2023-01-22 13:47:31.366360: step: 898/466, loss: 0.00011694846034515649
2023-01-22 13:47:31.917723: step: 900/466, loss: 0.00047570542665198445
2023-01-22 13:47:32.579744: step: 902/466, loss: 0.0005460705142468214
2023-01-22 13:47:33.250938: step: 904/466, loss: 0.003993664868175983
2023-01-22 13:47:33.846769: step: 906/466, loss: 0.0007893638103269041
2023-01-22 13:47:34.459844: step: 908/466, loss: 0.00033020504633896053
2023-01-22 13:47:35.019773: step: 910/466, loss: 0.003642172319814563
2023-01-22 13:47:35.650433: step: 912/466, loss: 0.12140356004238129
2023-01-22 13:47:36.312269: step: 914/466, loss: 1.5962437391281128
2023-01-22 13:47:36.955694: step: 916/466, loss: 0.020260266959667206
2023-01-22 13:47:37.666881: step: 918/466, loss: 0.08730872720479965
2023-01-22 13:47:38.285458: step: 920/466, loss: 0.0024628147948533297
2023-01-22 13:47:38.832438: step: 922/466, loss: 0.01657303422689438
2023-01-22 13:47:39.458654: step: 924/466, loss: 0.2514936923980713
2023-01-22 13:47:40.058893: step: 926/466, loss: 0.03157556802034378
2023-01-22 13:47:40.667453: step: 928/466, loss: 0.00018364607240073383
2023-01-22 13:47:41.370005: step: 930/466, loss: 0.14305895566940308
2023-01-22 13:47:42.024407: step: 932/466, loss: 0.002802376402541995
==================================================
Loss: 0.061
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31337172207390046, 'r': 0.3294268197892616, 'f1': 0.32119876786113016}, 'combined': 0.23667277631872746, 'epoch': 33}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32507060310351077, 'r': 0.2983966401797781, 'f1': 0.3111630220586497}, 'combined': 0.19484039698999564, 'epoch': 33}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2946737318359948, 'r': 0.33772852756914773, 'f1': 0.31473551552421014}, 'combined': 0.2319103798599443, 'epoch': 33}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3265458926030614, 'r': 0.29913725721309326, 'f1': 0.31224124445794377}, 'combined': 0.1935016162837961, 'epoch': 33}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.26998174588342033, 'r': 0.3386298558423925, 'f1': 0.3004342323719543}, 'combined': 0.2213725922740716, 'epoch': 33}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.32769326097305973, 'r': 0.3019395900564778, 'f1': 0.3142897284367851}, 'combined': 0.20848922579469903, 'epoch': 33}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.27325581395348836, 'r': 0.3357142857142857, 'f1': 0.30128205128205127}, 'combined': 0.20085470085470084, 'epoch': 33}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.275, 'r': 0.358695652173913, 'f1': 0.3113207547169812}, 'combined': 0.1556603773584906, 'epoch': 33}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.30952380952380953, 'r': 0.22413793103448276, 'f1': 0.26}, 'combined': 0.17333333333333334, 'epoch': 33}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:50:19.694248: step: 2/466, loss: 0.00044776161666959524
2023-01-22 13:50:20.330711: step: 4/466, loss: 0.06525201350450516
2023-01-22 13:50:20.938589: step: 6/466, loss: 0.05276694893836975
2023-01-22 13:50:21.517770: step: 8/466, loss: 0.01285181287676096
2023-01-22 13:50:22.077462: step: 10/466, loss: 0.0017702908953651786
2023-01-22 13:50:22.673768: step: 12/466, loss: 0.012179172597825527
2023-01-22 13:50:23.322434: step: 14/466, loss: 0.009365064091980457
2023-01-22 13:50:24.099899: step: 16/466, loss: 0.017210684716701508
2023-01-22 13:50:24.725616: step: 18/466, loss: 0.010137687437236309
2023-01-22 13:50:25.364607: step: 20/466, loss: 0.038191381841897964
2023-01-22 13:50:25.962157: step: 22/466, loss: 0.0006398653495125473
2023-01-22 13:50:26.619437: step: 24/466, loss: 0.010410054586827755
2023-01-22 13:50:27.258064: step: 26/466, loss: 0.023390959948301315
2023-01-22 13:50:27.933541: step: 28/466, loss: 0.00010038419713964686
2023-01-22 13:50:28.612745: step: 30/466, loss: 0.038161225616931915
2023-01-22 13:50:29.243316: step: 32/466, loss: 0.009207690134644508
2023-01-22 13:50:29.869035: step: 34/466, loss: 0.014065796509385109
2023-01-22 13:50:30.470929: step: 36/466, loss: 0.007660723756998777
2023-01-22 13:50:31.148724: step: 38/466, loss: 0.11670602858066559
2023-01-22 13:50:31.751766: step: 40/466, loss: 0.022145750001072884
2023-01-22 13:50:32.343051: step: 42/466, loss: 0.01542850024998188
2023-01-22 13:50:32.933972: step: 44/466, loss: 0.0018281365046277642
2023-01-22 13:50:33.564349: step: 46/466, loss: 0.033811137080192566
2023-01-22 13:50:34.152149: step: 48/466, loss: 0.0026900717057287693
2023-01-22 13:50:34.760519: step: 50/466, loss: 0.01676148548722267
2023-01-22 13:50:35.331552: step: 52/466, loss: 0.009092275984585285
2023-01-22 13:50:35.968316: step: 54/466, loss: 0.0014002284733578563
2023-01-22 13:50:36.630776: step: 56/466, loss: 0.0008105834713205695
2023-01-22 13:50:37.257205: step: 58/466, loss: 0.015190726146101952
2023-01-22 13:50:37.835266: step: 60/466, loss: 0.0076024350710213184
2023-01-22 13:50:38.576770: step: 62/466, loss: 0.017200469970703125
2023-01-22 13:50:39.155929: step: 64/466, loss: 0.003627775004133582
2023-01-22 13:50:39.764034: step: 66/466, loss: 0.0030399509705603123
2023-01-22 13:50:40.426876: step: 68/466, loss: 0.013998578302562237
2023-01-22 13:50:40.982188: step: 70/466, loss: 0.006730527617037296
2023-01-22 13:50:41.599965: step: 72/466, loss: 0.00045602815225720406
2023-01-22 13:50:42.221168: step: 74/466, loss: 0.01984693855047226
2023-01-22 13:50:42.823541: step: 76/466, loss: 0.008410582318902016
2023-01-22 13:50:43.458263: step: 78/466, loss: 0.004264121875166893
2023-01-22 13:50:44.073996: step: 80/466, loss: 0.011182108893990517
2023-01-22 13:50:44.679890: step: 82/466, loss: 0.0007857290329411626
2023-01-22 13:50:45.265314: step: 84/466, loss: 0.14946375787258148
2023-01-22 13:50:45.973787: step: 86/466, loss: 0.1568223088979721
2023-01-22 13:50:46.577266: step: 88/466, loss: 0.005522684194147587
2023-01-22 13:50:47.212342: step: 90/466, loss: 0.2518271207809448
2023-01-22 13:50:47.927050: step: 92/466, loss: 0.0041334908455610275
2023-01-22 13:50:48.492840: step: 94/466, loss: 0.04081486538052559
2023-01-22 13:50:49.097631: step: 96/466, loss: 0.015616985969245434
2023-01-22 13:50:49.718285: step: 98/466, loss: 0.008200753480196
2023-01-22 13:50:50.281125: step: 100/466, loss: 0.00557843828573823
2023-01-22 13:50:51.036677: step: 102/466, loss: 0.022209985181689262
2023-01-22 13:50:51.636163: step: 104/466, loss: 0.0023639919236302376
2023-01-22 13:50:52.242630: step: 106/466, loss: 0.11503303796052933
2023-01-22 13:50:52.781819: step: 108/466, loss: 0.0006290609599091113
2023-01-22 13:50:53.435306: step: 110/466, loss: 0.0006383599247783422
2023-01-22 13:50:54.058441: step: 112/466, loss: 0.008348631672561169
2023-01-22 13:50:54.657839: step: 114/466, loss: 0.004403615370392799
2023-01-22 13:50:55.218922: step: 116/466, loss: 0.008891992270946503
2023-01-22 13:50:55.897451: step: 118/466, loss: 0.010444930754601955
2023-01-22 13:50:56.479654: step: 120/466, loss: 0.002010609256103635
2023-01-22 13:50:57.103153: step: 122/466, loss: 0.0006103226915001869
2023-01-22 13:50:57.669343: step: 124/466, loss: 0.003745818277820945
2023-01-22 13:50:58.250526: step: 126/466, loss: 0.014827505685389042
2023-01-22 13:50:58.876139: step: 128/466, loss: 0.013629971072077751
2023-01-22 13:50:59.416203: step: 130/466, loss: 0.0016906384844332933
2023-01-22 13:51:00.036574: step: 132/466, loss: 0.006619714200496674
2023-01-22 13:51:00.700402: step: 134/466, loss: 0.008903798647224903
2023-01-22 13:51:01.296970: step: 136/466, loss: 0.007137033622711897
2023-01-22 13:51:01.876242: step: 138/466, loss: 0.07491079717874527
2023-01-22 13:51:02.522413: step: 140/466, loss: 0.0043428814969956875
2023-01-22 13:51:03.151937: step: 142/466, loss: 0.0007345814374275506
2023-01-22 13:51:03.769076: step: 144/466, loss: 0.019647398963570595
2023-01-22 13:51:04.434912: step: 146/466, loss: 0.023039327934384346
2023-01-22 13:51:05.083303: step: 148/466, loss: 0.004542264621704817
2023-01-22 13:51:05.714073: step: 150/466, loss: 0.01884089969098568
2023-01-22 13:51:06.305648: step: 152/466, loss: 0.001451627118512988
2023-01-22 13:51:06.901359: step: 154/466, loss: 0.007424298208206892
2023-01-22 13:51:07.532658: step: 156/466, loss: 0.0035362206399440765
2023-01-22 13:51:08.137257: step: 158/466, loss: 0.00559675507247448
2023-01-22 13:51:08.761580: step: 160/466, loss: 0.0046802363358438015
2023-01-22 13:51:09.402773: step: 162/466, loss: 0.07901641726493835
2023-01-22 13:51:10.017097: step: 164/466, loss: 0.005561268888413906
2023-01-22 13:51:10.676297: step: 166/466, loss: 0.008733381517231464
2023-01-22 13:51:11.299663: step: 168/466, loss: 0.008319716900587082
2023-01-22 13:51:11.955507: step: 170/466, loss: 0.024022787809371948
2023-01-22 13:51:12.631080: step: 172/466, loss: 0.008073654025793076
2023-01-22 13:51:13.234096: step: 174/466, loss: 3.298505180282518e-05
2023-01-22 13:51:13.855666: step: 176/466, loss: 0.016322093084454536
2023-01-22 13:51:14.487242: step: 178/466, loss: 0.6524455547332764
2023-01-22 13:51:15.067476: step: 180/466, loss: 0.003264949657022953
2023-01-22 13:51:15.700777: step: 182/466, loss: 0.00570281594991684
2023-01-22 13:51:16.281502: step: 184/466, loss: 0.04283526912331581
2023-01-22 13:51:16.882434: step: 186/466, loss: 0.00351996929384768
2023-01-22 13:51:17.410265: step: 188/466, loss: 8.80212610354647e-05
2023-01-22 13:51:18.016505: step: 190/466, loss: 0.03641581907868385
2023-01-22 13:51:18.674454: step: 192/466, loss: 0.002388633554801345
2023-01-22 13:51:19.308226: step: 194/466, loss: 0.03432387113571167
2023-01-22 13:51:19.956466: step: 196/466, loss: 0.004611233714967966
2023-01-22 13:51:20.623437: step: 198/466, loss: 0.03649257868528366
2023-01-22 13:51:21.182236: step: 200/466, loss: 0.0010074052261188626
2023-01-22 13:51:21.867338: step: 202/466, loss: 0.0019159098155796528
2023-01-22 13:51:22.457605: step: 204/466, loss: 0.0011125894961878657
2023-01-22 13:51:23.070690: step: 206/466, loss: 0.019255148246884346
2023-01-22 13:51:23.694672: step: 208/466, loss: 0.00870990939438343
2023-01-22 13:51:24.261864: step: 210/466, loss: 0.0029466452542692423
2023-01-22 13:51:24.818226: step: 212/466, loss: 0.01073588989675045
2023-01-22 13:51:25.492588: step: 214/466, loss: 0.0026622465811669827
2023-01-22 13:51:26.100328: step: 216/466, loss: 0.009074680507183075
2023-01-22 13:51:26.760197: step: 218/466, loss: 0.010591430589556694
2023-01-22 13:51:27.340120: step: 220/466, loss: 0.0010342072928324342
2023-01-22 13:51:27.934094: step: 222/466, loss: 0.001506170374341309
2023-01-22 13:51:28.528249: step: 224/466, loss: 0.07824140787124634
2023-01-22 13:51:29.134505: step: 226/466, loss: 0.10094006359577179
2023-01-22 13:51:29.685541: step: 228/466, loss: 0.00027557910652831197
2023-01-22 13:51:30.314145: step: 230/466, loss: 0.002696025650948286
2023-01-22 13:51:30.923087: step: 232/466, loss: 0.0011498354142531753
2023-01-22 13:51:31.495253: step: 234/466, loss: 0.007175063714385033
2023-01-22 13:51:32.115965: step: 236/466, loss: 0.010354211553931236
2023-01-22 13:51:32.738153: step: 238/466, loss: 0.07728850841522217
2023-01-22 13:51:33.367331: step: 240/466, loss: 0.00037491199327632785
2023-01-22 13:51:34.006836: step: 242/466, loss: 0.012333719991147518
2023-01-22 13:51:34.586570: step: 244/466, loss: 0.038081903010606766
2023-01-22 13:51:35.178671: step: 246/466, loss: 8.588692435296252e-05
2023-01-22 13:51:35.742795: step: 248/466, loss: 0.030551902949810028
2023-01-22 13:51:36.331554: step: 250/466, loss: 0.008057349361479282
2023-01-22 13:51:36.930259: step: 252/466, loss: 0.006906131748110056
2023-01-22 13:51:37.562251: step: 254/466, loss: 0.011321410536766052
2023-01-22 13:51:38.184417: step: 256/466, loss: 0.0034377777483314276
2023-01-22 13:51:38.871465: step: 258/466, loss: 9.264093387173489e-05
2023-01-22 13:51:39.500601: step: 260/466, loss: 0.016924438998103142
2023-01-22 13:51:40.105822: step: 262/466, loss: 0.00021807632583659142
2023-01-22 13:51:40.711168: step: 264/466, loss: 0.01791452243924141
2023-01-22 13:51:41.345148: step: 266/466, loss: 0.01496839802712202
2023-01-22 13:51:42.003917: step: 268/466, loss: 0.07914392650127411
2023-01-22 13:51:42.626224: step: 270/466, loss: 0.020682817324995995
2023-01-22 13:51:43.204202: step: 272/466, loss: 0.014893428422510624
2023-01-22 13:51:43.757652: step: 274/466, loss: 0.004114802926778793
2023-01-22 13:51:44.347227: step: 276/466, loss: 0.025077002122998238
2023-01-22 13:51:45.011362: step: 278/466, loss: 0.03476715832948685
2023-01-22 13:51:45.572562: step: 280/466, loss: 0.04227663204073906
2023-01-22 13:51:46.165281: step: 282/466, loss: 3.218621714040637e-06
2023-01-22 13:51:46.759060: step: 284/466, loss: 0.001750446972437203
2023-01-22 13:51:47.420107: step: 286/466, loss: 0.0005400181398727
2023-01-22 13:51:48.056304: step: 288/466, loss: 0.001205334672704339
2023-01-22 13:51:48.717950: step: 290/466, loss: 0.7622677683830261
2023-01-22 13:51:49.312718: step: 292/466, loss: 0.0026643334422260523
2023-01-22 13:51:49.914444: step: 294/466, loss: 0.00021289987489581108
2023-01-22 13:51:50.556954: step: 296/466, loss: 0.017237041145563126
2023-01-22 13:51:51.202616: step: 298/466, loss: 0.002139111515134573
2023-01-22 13:51:51.858769: step: 300/466, loss: 0.0018975037382915616
2023-01-22 13:51:52.508258: step: 302/466, loss: 0.0015305919805541635
2023-01-22 13:51:53.228224: step: 304/466, loss: 0.019873235374689102
2023-01-22 13:51:53.967148: step: 306/466, loss: 0.007630509324371815
2023-01-22 13:51:54.576209: step: 308/466, loss: 0.00576387532055378
2023-01-22 13:51:55.153713: step: 310/466, loss: 0.015104739926755428
2023-01-22 13:51:55.793324: step: 312/466, loss: 0.015948601067066193
2023-01-22 13:51:56.448043: step: 314/466, loss: 0.03411102294921875
2023-01-22 13:51:57.055924: step: 316/466, loss: 0.005596490111202002
2023-01-22 13:51:57.662461: step: 318/466, loss: 2.726545608311426e-05
2023-01-22 13:51:58.292720: step: 320/466, loss: 0.011570059694349766
2023-01-22 13:51:59.010853: step: 322/466, loss: 0.0064280214719474316
2023-01-22 13:51:59.578833: step: 324/466, loss: 0.002828769152984023
2023-01-22 13:52:00.164866: step: 326/466, loss: 0.001282182289287448
2023-01-22 13:52:00.854401: step: 328/466, loss: 0.03785112127661705
2023-01-22 13:52:01.504502: step: 330/466, loss: 0.0014699080493301153
2023-01-22 13:52:02.115175: step: 332/466, loss: 0.3079739809036255
2023-01-22 13:52:02.723887: step: 334/466, loss: 0.005796042736619711
2023-01-22 13:52:03.404439: step: 336/466, loss: 0.001293532201088965
2023-01-22 13:52:04.042904: step: 338/466, loss: 0.005367397330701351
2023-01-22 13:52:04.791859: step: 340/466, loss: 0.03847994655370712
2023-01-22 13:52:05.404482: step: 342/466, loss: 0.04027722403407097
2023-01-22 13:52:06.009937: step: 344/466, loss: 0.017038552090525627
2023-01-22 13:52:06.709586: step: 346/466, loss: 0.0006917880964465439
2023-01-22 13:52:07.326481: step: 348/466, loss: 0.00024127642973326147
2023-01-22 13:52:08.013945: step: 350/466, loss: 0.4475272595882416
2023-01-22 13:52:08.608607: step: 352/466, loss: 0.000668540655169636
2023-01-22 13:52:09.287479: step: 354/466, loss: 0.000448493636213243
2023-01-22 13:52:09.847852: step: 356/466, loss: 0.0029617866966873407
2023-01-22 13:52:10.470542: step: 358/466, loss: 0.006570684257894754
2023-01-22 13:52:11.131635: step: 360/466, loss: 0.006790623534470797
2023-01-22 13:52:11.720885: step: 362/466, loss: 0.0037583005614578724
2023-01-22 13:52:12.308119: step: 364/466, loss: 0.00491564953699708
2023-01-22 13:52:12.957995: step: 366/466, loss: 0.04236968606710434
2023-01-22 13:52:13.552177: step: 368/466, loss: 0.005421468988060951
2023-01-22 13:52:14.195353: step: 370/466, loss: 0.03661723434925079
2023-01-22 13:52:14.815437: step: 372/466, loss: 0.003153814934194088
2023-01-22 13:52:15.473769: step: 374/466, loss: 0.010920863598585129
2023-01-22 13:52:16.136678: step: 376/466, loss: 0.06718513369560242
2023-01-22 13:52:16.656683: step: 378/466, loss: 0.011719964444637299
2023-01-22 13:52:17.198898: step: 380/466, loss: 0.0022813091054558754
2023-01-22 13:52:17.829650: step: 382/466, loss: 0.003214395372197032
2023-01-22 13:52:18.450104: step: 384/466, loss: 0.0005004985723644495
2023-01-22 13:52:19.043816: step: 386/466, loss: 0.011618012562394142
2023-01-22 13:52:19.727548: step: 388/466, loss: 0.0026870244182646275
2023-01-22 13:52:20.355848: step: 390/466, loss: 0.0003367691533640027
2023-01-22 13:52:20.936274: step: 392/466, loss: 0.012099171988666058
2023-01-22 13:52:21.533591: step: 394/466, loss: 0.0068061258643865585
2023-01-22 13:52:22.104190: step: 396/466, loss: 0.0007426588563248515
2023-01-22 13:52:22.752899: step: 398/466, loss: 0.03194461017847061
2023-01-22 13:52:23.372724: step: 400/466, loss: 0.06825070083141327
2023-01-22 13:52:23.972614: step: 402/466, loss: 0.0003770602634176612
2023-01-22 13:52:24.636835: step: 404/466, loss: 1.5576121807098389
2023-01-22 13:52:25.288627: step: 406/466, loss: 0.017388686537742615
2023-01-22 13:52:25.927941: step: 408/466, loss: 0.001316699432209134
2023-01-22 13:52:26.557131: step: 410/466, loss: 0.004049208946526051
2023-01-22 13:52:27.167038: step: 412/466, loss: 0.03801628574728966
2023-01-22 13:52:27.764790: step: 414/466, loss: 0.0003594731679186225
2023-01-22 13:52:28.469215: step: 416/466, loss: 0.04546977952122688
2023-01-22 13:52:29.077128: step: 418/466, loss: 0.004481267649680376
2023-01-22 13:52:29.643696: step: 420/466, loss: 9.061475793714635e-06
2023-01-22 13:52:30.316872: step: 422/466, loss: 0.1406223475933075
2023-01-22 13:52:30.871194: step: 424/466, loss: 0.0019254398066550493
2023-01-22 13:52:31.517114: step: 426/466, loss: 0.007295049726963043
2023-01-22 13:52:32.034872: step: 428/466, loss: 0.002065313747152686
2023-01-22 13:52:32.627529: step: 430/466, loss: 0.5076283812522888
2023-01-22 13:52:33.284379: step: 432/466, loss: 0.0019482868956401944
2023-01-22 13:52:33.877061: step: 434/466, loss: 0.0073101273737847805
2023-01-22 13:52:34.517766: step: 436/466, loss: 0.027784865349531174
2023-01-22 13:52:35.140064: step: 438/466, loss: 0.03103061206638813
2023-01-22 13:52:35.731606: step: 440/466, loss: 0.14775855839252472
2023-01-22 13:52:36.295378: step: 442/466, loss: 0.004521707072854042
2023-01-22 13:52:36.927814: step: 444/466, loss: 0.14504075050354004
2023-01-22 13:52:37.571140: step: 446/466, loss: 0.005193950608372688
2023-01-22 13:52:38.217587: step: 448/466, loss: 0.041242219507694244
2023-01-22 13:52:38.850101: step: 450/466, loss: 0.00013268241309560835
2023-01-22 13:52:39.453189: step: 452/466, loss: 3.4981661883648485e-05
2023-01-22 13:52:40.105260: step: 454/466, loss: 0.01182777713984251
2023-01-22 13:52:40.673399: step: 456/466, loss: 0.03321721404790878
2023-01-22 13:52:41.260455: step: 458/466, loss: 0.0015951005043461919
2023-01-22 13:52:41.858496: step: 460/466, loss: 0.02566281519830227
2023-01-22 13:52:42.455509: step: 462/466, loss: 0.12666575610637665
2023-01-22 13:52:43.055615: step: 464/466, loss: 0.000737195776309818
2023-01-22 13:52:43.710748: step: 466/466, loss: 0.0006672508898191154
2023-01-22 13:52:44.311290: step: 468/466, loss: 0.002969736233353615
2023-01-22 13:52:44.976231: step: 470/466, loss: 0.0104988943785429
2023-01-22 13:52:45.602195: step: 472/466, loss: 0.08003918826580048
2023-01-22 13:52:46.310913: step: 474/466, loss: 0.0009593369322828948
2023-01-22 13:52:46.956814: step: 476/466, loss: 0.0014240005984902382
2023-01-22 13:52:47.611624: step: 478/466, loss: 0.02312459796667099
2023-01-22 13:52:48.269231: step: 480/466, loss: 0.3419071137905121
2023-01-22 13:52:48.916502: step: 482/466, loss: 0.07372163236141205
2023-01-22 13:52:49.474900: step: 484/466, loss: 0.0016719779232516885
2023-01-22 13:52:50.188984: step: 486/466, loss: 0.0037703728303313255
2023-01-22 13:52:50.874772: step: 488/466, loss: 0.006523465272039175
2023-01-22 13:52:51.499084: step: 490/466, loss: 0.11450313776731491
2023-01-22 13:52:52.046488: step: 492/466, loss: 0.004408995155245066
2023-01-22 13:52:52.737459: step: 494/466, loss: 0.012378161773085594
2023-01-22 13:52:53.328061: step: 496/466, loss: 0.0012394912773743272
2023-01-22 13:52:53.890480: step: 498/466, loss: 0.025968529284000397
2023-01-22 13:52:54.497925: step: 500/466, loss: 0.0003646584809757769
2023-01-22 13:52:55.088329: step: 502/466, loss: 0.009832086972892284
2023-01-22 13:52:55.692447: step: 504/466, loss: 0.01419033482670784
2023-01-22 13:52:56.227016: step: 506/466, loss: 0.006501009687781334
2023-01-22 13:52:56.871565: step: 508/466, loss: 0.014940740540623665
2023-01-22 13:52:57.519722: step: 510/466, loss: 0.0006022718735039234
2023-01-22 13:52:58.182253: step: 512/466, loss: 0.002012605080381036
2023-01-22 13:52:58.820341: step: 514/466, loss: 0.3332501947879791
2023-01-22 13:52:59.426864: step: 516/466, loss: 0.003292681649327278
2023-01-22 13:53:00.025072: step: 518/466, loss: 0.0005466737202368677
2023-01-22 13:53:00.661016: step: 520/466, loss: 0.015075303614139557
2023-01-22 13:53:01.302579: step: 522/466, loss: 0.053734585642814636
2023-01-22 13:53:02.010213: step: 524/466, loss: 0.24074675142765045
2023-01-22 13:53:02.671360: step: 526/466, loss: 0.0006083545158617198
2023-01-22 13:53:03.285561: step: 528/466, loss: 0.1092829778790474
2023-01-22 13:53:03.860790: step: 530/466, loss: 0.0009274989715777338
2023-01-22 13:53:04.495021: step: 532/466, loss: 0.009749316610395908
2023-01-22 13:53:05.132230: step: 534/466, loss: 0.0010659914696589112
2023-01-22 13:53:05.740474: step: 536/466, loss: 0.02175002545118332
2023-01-22 13:53:06.311150: step: 538/466, loss: 0.09114664047956467
2023-01-22 13:53:06.992037: step: 540/466, loss: 0.00017733403365127742
2023-01-22 13:53:07.592564: step: 542/466, loss: 0.009102762676775455
2023-01-22 13:53:08.262130: step: 544/466, loss: 0.03955816477537155
2023-01-22 13:53:08.918616: step: 546/466, loss: 0.010862162336707115
2023-01-22 13:53:09.550922: step: 548/466, loss: 0.007654275745153427
2023-01-22 13:53:10.161403: step: 550/466, loss: 0.006650466471910477
2023-01-22 13:53:10.802781: step: 552/466, loss: 0.02752058580517769
2023-01-22 13:53:11.447737: step: 554/466, loss: 0.32176074385643005
2023-01-22 13:53:12.098157: step: 556/466, loss: 0.0178492683917284
2023-01-22 13:53:12.683359: step: 558/466, loss: 0.0002495641529094428
2023-01-22 13:53:13.311397: step: 560/466, loss: 0.0211823508143425
2023-01-22 13:53:13.896275: step: 562/466, loss: 0.0006840778514742851
2023-01-22 13:53:14.484518: step: 564/466, loss: 0.07020992785692215
2023-01-22 13:53:15.105032: step: 566/466, loss: 0.0003941252361983061
2023-01-22 13:53:15.755635: step: 568/466, loss: 0.002252056263387203
2023-01-22 13:53:16.338642: step: 570/466, loss: 0.0008177889394573867
2023-01-22 13:53:16.945507: step: 572/466, loss: 0.017822712659835815
2023-01-22 13:53:17.669744: step: 574/466, loss: 0.0007715900428593159
2023-01-22 13:53:18.267735: step: 576/466, loss: 0.0024609831161797047
2023-01-22 13:53:18.886267: step: 578/466, loss: 0.0806882232427597
2023-01-22 13:53:19.446955: step: 580/466, loss: 0.01499209739267826
2023-01-22 13:53:20.038896: step: 582/466, loss: 0.007676340639591217
2023-01-22 13:53:20.674966: step: 584/466, loss: 0.020366515964269638
2023-01-22 13:53:21.405967: step: 586/466, loss: 0.003409266471862793
2023-01-22 13:53:22.034510: step: 588/466, loss: 0.036261629313230515
2023-01-22 13:53:22.662749: step: 590/466, loss: 0.017820268869400024
2023-01-22 13:53:23.265556: step: 592/466, loss: 1.446390569981304e-06
2023-01-22 13:53:23.867534: step: 594/466, loss: 0.01295681856572628
2023-01-22 13:53:24.541795: step: 596/466, loss: 0.011897056363523006
2023-01-22 13:53:25.087694: step: 598/466, loss: 0.11405541002750397
2023-01-22 13:53:25.755425: step: 600/466, loss: 0.0030295539181679487
2023-01-22 13:53:26.459071: step: 602/466, loss: 0.4915716350078583
2023-01-22 13:53:27.055448: step: 604/466, loss: 0.006803831551223993
2023-01-22 13:53:27.672280: step: 606/466, loss: 0.002284247661009431
2023-01-22 13:53:28.304537: step: 608/466, loss: 0.019854342564940453
2023-01-22 13:53:28.863238: step: 610/466, loss: 6.362621206790209e-05
2023-01-22 13:53:29.559415: step: 612/466, loss: 0.002294174861162901
2023-01-22 13:53:30.105818: step: 614/466, loss: 0.0015062671154737473
2023-01-22 13:53:30.739968: step: 616/466, loss: 0.008126691915094852
2023-01-22 13:53:31.385305: step: 618/466, loss: 0.05395924299955368
2023-01-22 13:53:31.970805: step: 620/466, loss: 0.007703367620706558
2023-01-22 13:53:32.546641: step: 622/466, loss: 0.019608866423368454
2023-01-22 13:53:33.156137: step: 624/466, loss: 0.000382233556592837
2023-01-22 13:53:33.770987: step: 626/466, loss: 0.030930420383810997
2023-01-22 13:53:34.447246: step: 628/466, loss: 0.0010697138495743275
2023-01-22 13:53:35.064290: step: 630/466, loss: 0.000281863467535004
2023-01-22 13:53:35.706075: step: 632/466, loss: 0.028093401342630386
2023-01-22 13:53:36.332953: step: 634/466, loss: 0.050495248287916183
2023-01-22 13:53:37.014372: step: 636/466, loss: 0.053377680480480194
2023-01-22 13:53:37.607071: step: 638/466, loss: 0.05928385630249977
2023-01-22 13:53:38.249492: step: 640/466, loss: 0.007710906211286783
2023-01-22 13:53:38.869949: step: 642/466, loss: 0.05826025456190109
2023-01-22 13:53:39.500161: step: 644/466, loss: 0.0020928012672811747
2023-01-22 13:53:40.130867: step: 646/466, loss: 0.005672491621226072
2023-01-22 13:53:40.715062: step: 648/466, loss: 0.002800034824758768
2023-01-22 13:53:41.337153: step: 650/466, loss: 0.01343744620680809
2023-01-22 13:53:41.919182: step: 652/466, loss: 0.010437189601361752
2023-01-22 13:53:42.519404: step: 654/466, loss: 0.03881608322262764
2023-01-22 13:53:43.118359: step: 656/466, loss: 0.021717675030231476
2023-01-22 13:53:43.718157: step: 658/466, loss: 0.003933850675821304
2023-01-22 13:53:44.336694: step: 660/466, loss: 0.002849757904186845
2023-01-22 13:53:44.975238: step: 662/466, loss: 0.0028018089942634106
2023-01-22 13:53:45.539144: step: 664/466, loss: 0.3200233280658722
2023-01-22 13:53:46.151083: step: 666/466, loss: 0.004376672208309174
2023-01-22 13:53:46.812795: step: 668/466, loss: 0.008337419480085373
2023-01-22 13:53:47.426034: step: 670/466, loss: 0.06835175305604935
2023-01-22 13:53:48.004238: step: 672/466, loss: 0.002413801848888397
2023-01-22 13:53:48.653807: step: 674/466, loss: 0.010170252993702888
2023-01-22 13:53:49.288043: step: 676/466, loss: 0.035940125584602356
2023-01-22 13:53:49.923584: step: 678/466, loss: 0.0006002828013151884
2023-01-22 13:53:50.661564: step: 680/466, loss: 0.056261248886585236
2023-01-22 13:53:51.274033: step: 682/466, loss: 0.003328244900330901
2023-01-22 13:53:51.912420: step: 684/466, loss: 0.18556299805641174
2023-01-22 13:53:52.521051: step: 686/466, loss: 0.0006311447941698134
2023-01-22 13:53:53.219103: step: 688/466, loss: 0.10427706688642502
2023-01-22 13:53:53.866323: step: 690/466, loss: 0.010392026044428349
2023-01-22 13:53:54.478823: step: 692/466, loss: 0.03382410481572151
2023-01-22 13:53:55.055212: step: 694/466, loss: 4.42578129877802e-05
2023-01-22 13:53:55.639304: step: 696/466, loss: 0.0063894083723425865
2023-01-22 13:53:56.318914: step: 698/466, loss: 0.008691796101629734
2023-01-22 13:53:56.929298: step: 700/466, loss: 0.024152379482984543
2023-01-22 13:53:57.586386: step: 702/466, loss: 0.0006300556706264615
2023-01-22 13:53:58.193695: step: 704/466, loss: 0.012121733278036118
2023-01-22 13:53:58.841735: step: 706/466, loss: 0.03641531616449356
2023-01-22 13:53:59.383605: step: 708/466, loss: 0.002240638481453061
2023-01-22 13:54:00.110122: step: 710/466, loss: 0.0114654041826725
2023-01-22 13:54:00.744134: step: 712/466, loss: 0.000776631582994014
2023-01-22 13:54:01.296829: step: 714/466, loss: 0.002134573645889759
2023-01-22 13:54:01.943177: step: 716/466, loss: 0.06929346174001694
2023-01-22 13:54:02.786607: step: 718/466, loss: 0.1391819715499878
2023-01-22 13:54:03.398500: step: 720/466, loss: 0.003451647236943245
2023-01-22 13:54:04.033917: step: 722/466, loss: 0.0002969567140098661
2023-01-22 13:54:04.672572: step: 724/466, loss: 0.019914161413908005
2023-01-22 13:54:05.271098: step: 726/466, loss: 0.007525104563683271
2023-01-22 13:54:05.879749: step: 728/466, loss: 0.07898574322462082
2023-01-22 13:54:06.484912: step: 730/466, loss: 0.0006913370452821255
2023-01-22 13:54:07.138294: step: 732/466, loss: 0.00435532396659255
2023-01-22 13:54:07.756351: step: 734/466, loss: 0.0007360997842624784
2023-01-22 13:54:08.432868: step: 736/466, loss: 0.008413765579462051
2023-01-22 13:54:09.028093: step: 738/466, loss: 0.0005035250214859843
2023-01-22 13:54:09.661041: step: 740/466, loss: 0.04341207072138786
2023-01-22 13:54:10.327832: step: 742/466, loss: 0.005954446271061897
2023-01-22 13:54:10.998352: step: 744/466, loss: 0.06513150781393051
2023-01-22 13:54:11.657115: step: 746/466, loss: 0.0178234726190567
2023-01-22 13:54:12.231885: step: 748/466, loss: 0.00010724266758188605
2023-01-22 13:54:12.831608: step: 750/466, loss: 0.03690279647707939
2023-01-22 13:54:13.516986: step: 752/466, loss: 0.0014993331860750914
2023-01-22 13:54:14.175212: step: 754/466, loss: 0.005447831004858017
2023-01-22 13:54:14.758016: step: 756/466, loss: 0.012812536209821701
2023-01-22 13:54:15.342890: step: 758/466, loss: 0.04598311334848404
2023-01-22 13:54:16.013272: step: 760/466, loss: 0.0032629230991005898
2023-01-22 13:54:16.655219: step: 762/466, loss: 0.0031235897913575172
2023-01-22 13:54:17.263135: step: 764/466, loss: 0.03207147866487503
2023-01-22 13:54:17.896529: step: 766/466, loss: 3.29094473272562e-05
2023-01-22 13:54:18.530654: step: 768/466, loss: 0.004162793979048729
2023-01-22 13:54:19.157434: step: 770/466, loss: 0.0203489288687706
2023-01-22 13:54:19.736344: step: 772/466, loss: 0.02295498736202717
2023-01-22 13:54:20.356173: step: 774/466, loss: 0.004239893052726984
2023-01-22 13:54:20.987697: step: 776/466, loss: 0.010488924570381641
2023-01-22 13:54:21.595207: step: 778/466, loss: 0.0013633416965603828
2023-01-22 13:54:22.240824: step: 780/466, loss: 0.004727499093860388
2023-01-22 13:54:22.820996: step: 782/466, loss: 0.02201392501592636
2023-01-22 13:54:23.424936: step: 784/466, loss: 0.14519967138767242
2023-01-22 13:54:24.061877: step: 786/466, loss: 0.0003717355721164495
2023-01-22 13:54:24.670532: step: 788/466, loss: 0.0064461724832654
2023-01-22 13:54:25.306301: step: 790/466, loss: 0.019439751282334328
2023-01-22 13:54:25.909271: step: 792/466, loss: 0.04224832355976105
2023-01-22 13:54:26.512471: step: 794/466, loss: 0.02717813104391098
2023-01-22 13:54:27.125354: step: 796/466, loss: 0.002636479679495096
2023-01-22 13:54:27.742787: step: 798/466, loss: 0.010049636475741863
2023-01-22 13:54:28.363696: step: 800/466, loss: 0.04448629170656204
2023-01-22 13:54:28.967542: step: 802/466, loss: 0.023999234661459923
2023-01-22 13:54:29.587187: step: 804/466, loss: 0.0019117995398119092
2023-01-22 13:54:30.211323: step: 806/466, loss: 0.053400829434394836
2023-01-22 13:54:30.853733: step: 808/466, loss: 0.0008438857039436698
2023-01-22 13:54:31.501242: step: 810/466, loss: 0.0007542734383605421
2023-01-22 13:54:32.083714: step: 812/466, loss: 0.0002328195550944656
2023-01-22 13:54:32.674932: step: 814/466, loss: 0.015046609565615654
2023-01-22 13:54:33.390150: step: 816/466, loss: 0.33053380250930786
2023-01-22 13:54:33.984059: step: 818/466, loss: 0.0062762959860265255
2023-01-22 13:54:34.596754: step: 820/466, loss: 0.0019862898625433445
2023-01-22 13:54:35.240405: step: 822/466, loss: 0.015598426572978497
2023-01-22 13:54:35.871417: step: 824/466, loss: 0.015153339132666588
2023-01-22 13:54:36.496239: step: 826/466, loss: 0.011167055927217007
2023-01-22 13:54:37.145615: step: 828/466, loss: 0.016412854194641113
2023-01-22 13:54:37.675286: step: 830/466, loss: 0.8337557911872864
2023-01-22 13:54:38.358205: step: 832/466, loss: 0.006227242294698954
2023-01-22 13:54:38.984753: step: 834/466, loss: 0.07353105396032333
2023-01-22 13:54:39.603173: step: 836/466, loss: 0.005039968993514776
2023-01-22 13:54:40.219458: step: 838/466, loss: 0.0008421080419793725
2023-01-22 13:54:40.832822: step: 840/466, loss: 0.0037266360595822334
2023-01-22 13:54:41.409805: step: 842/466, loss: 0.06846221536397934
2023-01-22 13:54:42.082327: step: 844/466, loss: 1.583168159413617e-05
2023-01-22 13:54:42.714117: step: 846/466, loss: 0.017023740336298943
2023-01-22 13:54:43.368598: step: 848/466, loss: 0.009995073080062866
2023-01-22 13:54:43.959827: step: 850/466, loss: 0.10446056723594666
2023-01-22 13:54:44.591453: step: 852/466, loss: 0.1504172831773758
2023-01-22 13:54:45.193621: step: 854/466, loss: 0.0077516851015388966
2023-01-22 13:54:45.844504: step: 856/466, loss: 0.022404974326491356
2023-01-22 13:54:46.446106: step: 858/466, loss: 0.013088853098452091
2023-01-22 13:54:47.035099: step: 860/466, loss: 0.030527258291840553
2023-01-22 13:54:47.651933: step: 862/466, loss: 0.14083844423294067
2023-01-22 13:54:48.255759: step: 864/466, loss: 0.0005255054566077888
2023-01-22 13:54:48.883873: step: 866/466, loss: 0.00027508364291861653
2023-01-22 13:54:49.516546: step: 868/466, loss: 0.7037966251373291
2023-01-22 13:54:50.118083: step: 870/466, loss: 0.0019437418086454272
2023-01-22 13:54:50.750668: step: 872/466, loss: 0.0004972312599420547
2023-01-22 13:54:51.345612: step: 874/466, loss: 0.026913179084658623
2023-01-22 13:54:51.938032: step: 876/466, loss: 0.5285601019859314
2023-01-22 13:54:52.472645: step: 878/466, loss: 0.0006900342414155602
2023-01-22 13:54:53.166938: step: 880/466, loss: 0.006860875058919191
2023-01-22 13:54:53.847929: step: 882/466, loss: 0.02796688862144947
2023-01-22 13:54:54.444569: step: 884/466, loss: 0.02239563688635826
2023-01-22 13:54:55.051764: step: 886/466, loss: 0.0003230464062653482
2023-01-22 13:54:55.676748: step: 888/466, loss: 0.003808454377576709
2023-01-22 13:54:56.308528: step: 890/466, loss: 0.011603298597037792
2023-01-22 13:54:56.903751: step: 892/466, loss: 0.001959197921678424
2023-01-22 13:54:57.507241: step: 894/466, loss: 4.1510764276608825e-05
2023-01-22 13:54:58.173533: step: 896/466, loss: 0.018717242404818535
2023-01-22 13:54:58.809009: step: 898/466, loss: 0.0030486127361655235
2023-01-22 13:54:59.339462: step: 900/466, loss: 0.02749359793961048
2023-01-22 13:54:59.914997: step: 902/466, loss: 0.0013783852336928248
2023-01-22 13:55:00.526747: step: 904/466, loss: 0.13980571925640106
2023-01-22 13:55:01.135773: step: 906/466, loss: 0.03152558207511902
2023-01-22 13:55:01.754470: step: 908/466, loss: 0.021568333730101585
2023-01-22 13:55:02.356074: step: 910/466, loss: 0.007910650223493576
2023-01-22 13:55:02.986359: step: 912/466, loss: 0.00212032999843359
2023-01-22 13:55:03.634751: step: 914/466, loss: 0.001687599578872323
2023-01-22 13:55:04.235322: step: 916/466, loss: 0.00031835469417274
2023-01-22 13:55:04.857236: step: 918/466, loss: 0.006139654200524092
2023-01-22 13:55:05.430406: step: 920/466, loss: 0.22900621592998505
2023-01-22 13:55:06.104430: step: 922/466, loss: 0.03427125886082649
2023-01-22 13:55:06.787045: step: 924/466, loss: 0.00580116780474782
2023-01-22 13:55:07.366452: step: 926/466, loss: 0.009941783733665943
2023-01-22 13:55:07.958324: step: 928/466, loss: 0.0014622800517827272
2023-01-22 13:55:08.592562: step: 930/466, loss: 0.0010867106029763818
2023-01-22 13:55:09.227900: step: 932/466, loss: 0.07350685447454453
==================================================
Loss: 0.038
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32621972882708083, 'r': 0.3373619586541917, 'f1': 0.3316972989006699}, 'combined': 0.24440853603207255, 'epoch': 34}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.32889354323797504, 'r': 0.3021783637330854, 'f1': 0.3149704863746553}, 'combined': 0.19722451015983092, 'epoch': 34}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31279492880325965, 'r': 0.35671679736386913, 'f1': 0.3333151634942536}, 'combined': 0.2456006467852395, 'epoch': 34}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.33615881985596013, 'r': 0.3149213492874428, 'f1': 0.32519371389607327}, 'combined': 0.2015284987524961, 'epoch': 34}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2852848687967655, 'r': 0.34158397003939095, 'f1': 0.3109063077906028}, 'combined': 0.2290888583720231, 'epoch': 34}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.33563565332340034, 'r': 0.30683223230648704, 'f1': 0.3205882785873348}, 'combined': 0.2126674719341726, 'epoch': 34}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2897727272727273, 'r': 0.36428571428571427, 'f1': 0.3227848101265823}, 'combined': 0.2151898734177215, 'epoch': 34}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.275, 'r': 0.358695652173913, 'f1': 0.3113207547169812}, 'combined': 0.1556603773584906, 'epoch': 34}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3333333333333333, 'r': 0.2413793103448276, 'f1': 0.28}, 'combined': 0.18666666666666668, 'epoch': 34}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 13:57:45.982320: step: 2/466, loss: 0.19672130048274994
2023-01-22 13:57:46.657842: step: 4/466, loss: 0.00019182507821824402
2023-01-22 13:57:47.255694: step: 6/466, loss: 0.0061749680899083614
2023-01-22 13:57:47.900935: step: 8/466, loss: 0.0005687942611984909
2023-01-22 13:57:48.566389: step: 10/466, loss: 0.0019311527721583843
2023-01-22 13:57:49.192385: step: 12/466, loss: 0.2713383436203003
2023-01-22 13:57:49.816692: step: 14/466, loss: 0.001256522722542286
2023-01-22 13:57:50.415193: step: 16/466, loss: 0.0015868941554799676
2023-01-22 13:57:50.972381: step: 18/466, loss: 0.003078905399888754
2023-01-22 13:57:51.681316: step: 20/466, loss: 0.007138105109333992
2023-01-22 13:57:52.282034: step: 22/466, loss: 0.03378899395465851
2023-01-22 13:57:52.998103: step: 24/466, loss: 0.057214029133319855
2023-01-22 13:57:53.640574: step: 26/466, loss: 0.020001688972115517
2023-01-22 13:57:54.276809: step: 28/466, loss: 0.0021218005567789078
2023-01-22 13:57:54.905775: step: 30/466, loss: 0.00015065399929881096
2023-01-22 13:57:55.545885: step: 32/466, loss: 0.0314030721783638
2023-01-22 13:57:56.134299: step: 34/466, loss: 0.006553353741765022
2023-01-22 13:57:56.741283: step: 36/466, loss: 0.0008050925098359585
2023-01-22 13:57:57.412533: step: 38/466, loss: 0.026836374774575233
2023-01-22 13:57:57.980873: step: 40/466, loss: 0.0006224775570444763
2023-01-22 13:57:58.527131: step: 42/466, loss: 0.0006816504755988717
2023-01-22 13:57:59.130597: step: 44/466, loss: 0.0022528169211000204
2023-01-22 13:57:59.740608: step: 46/466, loss: 9.378709364682436e-05
2023-01-22 13:58:00.313839: step: 48/466, loss: 0.0031867213547229767
2023-01-22 13:58:00.878484: step: 50/466, loss: 0.0002920925326179713
2023-01-22 13:58:01.547488: step: 52/466, loss: 0.010656697675585747
2023-01-22 13:58:02.114346: step: 54/466, loss: 0.0034762206487357616
2023-01-22 13:58:02.701088: step: 56/466, loss: 4.362952313385904e-05
2023-01-22 13:58:03.368648: step: 58/466, loss: 0.007797377184033394
2023-01-22 13:58:04.007204: step: 60/466, loss: 0.013550630770623684
2023-01-22 13:58:04.613740: step: 62/466, loss: 0.0037805496249347925
2023-01-22 13:58:05.244774: step: 64/466, loss: 0.00014615154941566288
2023-01-22 13:58:05.913184: step: 66/466, loss: 0.004896939266473055
2023-01-22 13:58:06.574599: step: 68/466, loss: 0.005394264589995146
2023-01-22 13:58:07.232173: step: 70/466, loss: 0.0030124287586659193
2023-01-22 13:58:07.855178: step: 72/466, loss: 0.06591653823852539
2023-01-22 13:58:08.467325: step: 74/466, loss: 0.00654204934835434
2023-01-22 13:58:09.043917: step: 76/466, loss: 0.010498001240193844
2023-01-22 13:58:09.780416: step: 78/466, loss: 0.03141288831830025
2023-01-22 13:58:10.376659: step: 80/466, loss: 0.19972841441631317
2023-01-22 13:58:11.002403: step: 82/466, loss: 0.04782477393746376
2023-01-22 13:58:11.600891: step: 84/466, loss: 0.015525314025580883
2023-01-22 13:58:12.218859: step: 86/466, loss: 0.015194829553365707
2023-01-22 13:58:12.764017: step: 88/466, loss: 0.0035464188549667597
2023-01-22 13:58:13.343318: step: 90/466, loss: 0.018129082396626472
2023-01-22 13:58:13.967449: step: 92/466, loss: 0.007922499440610409
2023-01-22 13:58:14.528842: step: 94/466, loss: 0.0006496994174085557
2023-01-22 13:58:15.133896: step: 96/466, loss: 0.020360559225082397
2023-01-22 13:58:15.721941: step: 98/466, loss: 0.0008911642362363636
2023-01-22 13:58:16.372072: step: 100/466, loss: 0.013872869312763214
2023-01-22 13:58:17.000080: step: 102/466, loss: 0.0041520181111991405
2023-01-22 13:58:17.650774: step: 104/466, loss: 0.00037203289684839547
2023-01-22 13:58:18.287797: step: 106/466, loss: 0.027455279603600502
2023-01-22 13:58:18.912922: step: 108/466, loss: 0.015023048967123032
2023-01-22 13:58:19.565576: step: 110/466, loss: 0.0091076185926795
2023-01-22 13:58:20.191901: step: 112/466, loss: 0.0025266988668590784
2023-01-22 13:58:20.767458: step: 114/466, loss: 0.005472118966281414
2023-01-22 13:58:21.379679: step: 116/466, loss: 0.0005205310299061239
2023-01-22 13:58:22.068846: step: 118/466, loss: 0.0006418328848667443
2023-01-22 13:58:22.710029: step: 120/466, loss: 0.006029690615832806
2023-01-22 13:58:23.300320: step: 122/466, loss: 0.0007082900847308338
2023-01-22 13:58:23.930737: step: 124/466, loss: 0.014394117519259453
2023-01-22 13:58:24.500852: step: 126/466, loss: 0.02503759041428566
2023-01-22 13:58:25.096319: step: 128/466, loss: 0.00828527007251978
2023-01-22 13:58:25.752092: step: 130/466, loss: 0.0002908979950007051
2023-01-22 13:58:26.297783: step: 132/466, loss: 0.0011940551921725273
2023-01-22 13:58:27.000002: step: 134/466, loss: 0.0036164771299809217
2023-01-22 13:58:27.660071: step: 136/466, loss: 0.043024443089962006
2023-01-22 13:58:28.225350: step: 138/466, loss: 0.006661163177341223
2023-01-22 13:58:28.837331: step: 140/466, loss: 0.11081206053495407
2023-01-22 13:58:29.426464: step: 142/466, loss: 0.0023321532644331455
2023-01-22 13:58:30.040152: step: 144/466, loss: 0.014660653658211231
2023-01-22 13:58:30.587868: step: 146/466, loss: 0.000896903220564127
2023-01-22 13:58:31.171799: step: 148/466, loss: 0.006206926889717579
2023-01-22 13:58:31.774858: step: 150/466, loss: 0.00997986551374197
2023-01-22 13:58:32.399841: step: 152/466, loss: 0.019994856789708138
2023-01-22 13:58:33.055816: step: 154/466, loss: 0.0007062026998028159
2023-01-22 13:58:33.654124: step: 156/466, loss: 0.0196046382188797
2023-01-22 13:58:34.269150: step: 158/466, loss: 0.06580505520105362
2023-01-22 13:58:34.909257: step: 160/466, loss: 0.0017799704801291227
2023-01-22 13:58:35.567001: step: 162/466, loss: 0.019087480381131172
2023-01-22 13:58:36.114848: step: 164/466, loss: 0.002953437389805913
2023-01-22 13:58:36.790904: step: 166/466, loss: 0.7682852149009705
2023-01-22 13:58:37.496831: step: 168/466, loss: 0.00706633273512125
2023-01-22 13:58:38.112221: step: 170/466, loss: 0.0007466856040991843
2023-01-22 13:58:38.710651: step: 172/466, loss: 0.0010011651320382953
2023-01-22 13:58:39.293454: step: 174/466, loss: 0.01231431309133768
2023-01-22 13:58:39.921864: step: 176/466, loss: 0.0023385584354400635
2023-01-22 13:58:40.504525: step: 178/466, loss: 0.0020545772276818752
2023-01-22 13:58:41.072823: step: 180/466, loss: 0.034714844077825546
2023-01-22 13:58:41.709298: step: 182/466, loss: 0.002392650581896305
2023-01-22 13:58:42.347679: step: 184/466, loss: 0.00034955190494656563
2023-01-22 13:58:42.970364: step: 186/466, loss: 0.0005167002091184258
2023-01-22 13:58:43.569182: step: 188/466, loss: 0.003416383871808648
2023-01-22 13:58:44.241905: step: 190/466, loss: 0.008075198158621788
2023-01-22 13:58:44.824184: step: 192/466, loss: 0.02795613929629326
2023-01-22 13:58:45.446954: step: 194/466, loss: 0.0013707567704841495
2023-01-22 13:58:46.080862: step: 196/466, loss: 0.004438911098986864
2023-01-22 13:58:46.601411: step: 198/466, loss: 0.00027351867174729705
2023-01-22 13:58:47.225901: step: 200/466, loss: 0.05398409068584442
2023-01-22 13:58:47.812974: step: 202/466, loss: 0.04659602418541908
2023-01-22 13:58:48.438868: step: 204/466, loss: 0.012363685294985771
2023-01-22 13:58:49.059488: step: 206/466, loss: 0.0038786998484283686
2023-01-22 13:58:49.651135: step: 208/466, loss: 0.14861993491649628
2023-01-22 13:58:50.283914: step: 210/466, loss: 0.001692389720119536
2023-01-22 13:58:50.961018: step: 212/466, loss: 0.034790534526109695
2023-01-22 13:58:51.536786: step: 214/466, loss: 0.021161269396543503
2023-01-22 13:58:52.123581: step: 216/466, loss: 0.04754173010587692
2023-01-22 13:58:52.812364: step: 218/466, loss: 0.01908714324235916
2023-01-22 13:58:53.440041: step: 220/466, loss: 0.02536274492740631
2023-01-22 13:58:54.041834: step: 222/466, loss: 0.007284355349838734
2023-01-22 13:58:54.709391: step: 224/466, loss: 0.002910307142883539
2023-01-22 13:58:55.341544: step: 226/466, loss: 0.04186934605240822
2023-01-22 13:58:55.987434: step: 228/466, loss: 0.0024629044346511364
2023-01-22 13:58:56.633014: step: 230/466, loss: 1.4538025856018066
2023-01-22 13:58:57.277877: step: 232/466, loss: 0.06269078701734543
2023-01-22 13:58:57.876705: step: 234/466, loss: 0.03725360706448555
2023-01-22 13:58:58.495873: step: 236/466, loss: 0.0020332932472229004
2023-01-22 13:58:59.106717: step: 238/466, loss: 0.0004961374215781689
2023-01-22 13:58:59.690649: step: 240/466, loss: 0.0014273915439844131
2023-01-22 13:59:00.361428: step: 242/466, loss: 0.005457594990730286
2023-01-22 13:59:00.921078: step: 244/466, loss: 0.004949708469212055
2023-01-22 13:59:01.544677: step: 246/466, loss: 0.0017929062014445662
2023-01-22 13:59:02.176543: step: 248/466, loss: 0.016505340114235878
2023-01-22 13:59:02.773470: step: 250/466, loss: 0.006642746273428202
2023-01-22 13:59:03.449043: step: 252/466, loss: 0.039198290556669235
2023-01-22 13:59:04.136426: step: 254/466, loss: 0.03569181263446808
2023-01-22 13:59:04.763205: step: 256/466, loss: 0.07561182975769043
2023-01-22 13:59:05.410466: step: 258/466, loss: 0.006765153259038925
2023-01-22 13:59:06.069810: step: 260/466, loss: 0.009034424088895321
2023-01-22 13:59:06.694939: step: 262/466, loss: 0.0216000284999609
2023-01-22 13:59:07.305902: step: 264/466, loss: 0.013857035897672176
2023-01-22 13:59:07.994995: step: 266/466, loss: 0.012999437749385834
2023-01-22 13:59:08.644373: step: 268/466, loss: 2.2698400020599365
2023-01-22 13:59:09.377361: step: 270/466, loss: 0.011805834248661995
2023-01-22 13:59:09.971816: step: 272/466, loss: 0.005838778801262379
2023-01-22 13:59:10.539795: step: 274/466, loss: 0.005848190281540155
2023-01-22 13:59:11.078671: step: 276/466, loss: 0.002828894881531596
2023-01-22 13:59:11.720257: step: 278/466, loss: 0.032090093940496445
2023-01-22 13:59:12.394387: step: 280/466, loss: 0.006285602226853371
2023-01-22 13:59:12.971984: step: 282/466, loss: 0.004960036836564541
2023-01-22 13:59:13.571964: step: 284/466, loss: 0.001981942215934396
2023-01-22 13:59:14.190132: step: 286/466, loss: 0.001998018939048052
2023-01-22 13:59:14.847745: step: 288/466, loss: 0.06795407086610794
2023-01-22 13:59:15.474758: step: 290/466, loss: 0.0028585109394043684
2023-01-22 13:59:16.059285: step: 292/466, loss: 0.008331945165991783
2023-01-22 13:59:16.609653: step: 294/466, loss: 0.06210816279053688
2023-01-22 13:59:17.247233: step: 296/466, loss: 0.0009348626481369138
2023-01-22 13:59:17.862566: step: 298/466, loss: 0.06100241839885712
2023-01-22 13:59:18.488723: step: 300/466, loss: 0.011931007727980614
2023-01-22 13:59:19.131159: step: 302/466, loss: 0.022689325734972954
2023-01-22 13:59:19.784861: step: 304/466, loss: 0.0016204646090045571
2023-01-22 13:59:20.383956: step: 306/466, loss: 0.031040312722325325
2023-01-22 13:59:20.991337: step: 308/466, loss: 0.030522683635354042
2023-01-22 13:59:21.603177: step: 310/466, loss: 0.0019973935559391975
2023-01-22 13:59:22.200035: step: 312/466, loss: 0.0004837153246626258
2023-01-22 13:59:22.864418: step: 314/466, loss: 0.0034056873992085457
2023-01-22 13:59:23.433392: step: 316/466, loss: 0.004625469446182251
2023-01-22 13:59:24.112931: step: 318/466, loss: 0.006939669139683247
2023-01-22 13:59:24.701439: step: 320/466, loss: 0.00302899070084095
2023-01-22 13:59:25.418999: step: 322/466, loss: 0.0508137084543705
2023-01-22 13:59:26.073814: step: 324/466, loss: 0.008497731760144234
2023-01-22 13:59:26.749878: step: 326/466, loss: 0.03148103505373001
2023-01-22 13:59:27.356042: step: 328/466, loss: 0.10339414328336716
2023-01-22 13:59:27.987066: step: 330/466, loss: 0.08141098916530609
2023-01-22 13:59:28.592935: step: 332/466, loss: 1.042614530888386e-05
2023-01-22 13:59:29.201185: step: 334/466, loss: 0.16875165700912476
2023-01-22 13:59:29.819992: step: 336/466, loss: 0.04247257113456726
2023-01-22 13:59:30.476660: step: 338/466, loss: 0.0014910728204995394
2023-01-22 13:59:31.076694: step: 340/466, loss: 0.0002597893762867898
2023-01-22 13:59:31.678078: step: 342/466, loss: 0.003451672848314047
2023-01-22 13:59:32.290056: step: 344/466, loss: 0.029710598289966583
2023-01-22 13:59:32.969285: step: 346/466, loss: 0.007508716080337763
2023-01-22 13:59:33.586046: step: 348/466, loss: 0.0005733236903324723
2023-01-22 13:59:34.167503: step: 350/466, loss: 0.12284275889396667
2023-01-22 13:59:34.760561: step: 352/466, loss: 0.49797219038009644
2023-01-22 13:59:35.365884: step: 354/466, loss: 0.011442849412560463
2023-01-22 13:59:35.953264: step: 356/466, loss: 0.04998866468667984
2023-01-22 13:59:36.505094: step: 358/466, loss: 0.15562476217746735
2023-01-22 13:59:37.128311: step: 360/466, loss: 0.002112923888489604
2023-01-22 13:59:37.674923: step: 362/466, loss: 0.011992626823484898
2023-01-22 13:59:38.294118: step: 364/466, loss: 0.018306145444512367
2023-01-22 13:59:38.878770: step: 366/466, loss: 0.018336445093154907
2023-01-22 13:59:39.553404: step: 368/466, loss: 0.046762946993112564
2023-01-22 13:59:40.143150: step: 370/466, loss: 0.020381107926368713
2023-01-22 13:59:40.759273: step: 372/466, loss: 0.02027146890759468
2023-01-22 13:59:41.405423: step: 374/466, loss: 0.021069901064038277
2023-01-22 13:59:42.125889: step: 376/466, loss: 0.022868456318974495
2023-01-22 13:59:42.752654: step: 378/466, loss: 0.0026336428709328175
2023-01-22 13:59:43.326887: step: 380/466, loss: 0.023216865956783295
2023-01-22 13:59:43.934814: step: 382/466, loss: 0.00418890081346035
2023-01-22 13:59:44.661366: step: 384/466, loss: 0.04266766458749771
2023-01-22 13:59:45.312568: step: 386/466, loss: 0.0019366155611351132
2023-01-22 13:59:45.927946: step: 388/466, loss: 0.15027840435504913
2023-01-22 13:59:46.504273: step: 390/466, loss: 0.004704800900071859
2023-01-22 13:59:47.094224: step: 392/466, loss: 0.004052850417792797
2023-01-22 13:59:47.814756: step: 394/466, loss: 0.000787840923294425
2023-01-22 13:59:48.402240: step: 396/466, loss: 0.005768901668488979
2023-01-22 13:59:49.051890: step: 398/466, loss: 0.009184678085148335
2023-01-22 13:59:49.681924: step: 400/466, loss: 0.004484910052269697
2023-01-22 13:59:50.273891: step: 402/466, loss: 0.0012350109172984958
2023-01-22 13:59:50.966969: step: 404/466, loss: 0.003340089926496148
2023-01-22 13:59:51.574611: step: 406/466, loss: 0.01358309667557478
2023-01-22 13:59:52.185682: step: 408/466, loss: 0.07484845072031021
2023-01-22 13:59:52.827982: step: 410/466, loss: 0.0009002909064292908
2023-01-22 13:59:53.518315: step: 412/466, loss: 0.025044383481144905
2023-01-22 13:59:54.165161: step: 414/466, loss: 0.001945171388797462
2023-01-22 13:59:54.755267: step: 416/466, loss: 0.0009749350720085204
2023-01-22 13:59:55.406029: step: 418/466, loss: 0.05633292719721794
2023-01-22 13:59:56.023086: step: 420/466, loss: 0.08718458563089371
2023-01-22 13:59:56.671082: step: 422/466, loss: 0.005591679364442825
2023-01-22 13:59:57.286461: step: 424/466, loss: 0.0003500099410302937
2023-01-22 13:59:57.884863: step: 426/466, loss: 0.010241672396659851
2023-01-22 13:59:58.571653: step: 428/466, loss: 0.016269562765955925
2023-01-22 13:59:59.191238: step: 430/466, loss: 0.025463281199336052
2023-01-22 13:59:59.826846: step: 432/466, loss: 0.0015716906636953354
2023-01-22 14:00:00.430806: step: 434/466, loss: 0.00032375584123656154
2023-01-22 14:00:01.122261: step: 436/466, loss: 0.01443261094391346
2023-01-22 14:00:01.702896: step: 438/466, loss: 0.012558290734887123
2023-01-22 14:00:02.419942: step: 440/466, loss: 0.0001916693290695548
2023-01-22 14:00:03.000685: step: 442/466, loss: 0.017497636377811432
2023-01-22 14:00:03.601421: step: 444/466, loss: 0.004431367386132479
2023-01-22 14:00:04.239691: step: 446/466, loss: 0.005800188984721899
2023-01-22 14:00:04.905241: step: 448/466, loss: 0.00022565516701433808
2023-01-22 14:00:05.542420: step: 450/466, loss: 0.00861687958240509
2023-01-22 14:00:06.333258: step: 452/466, loss: 0.00256314966827631
2023-01-22 14:00:06.943743: step: 454/466, loss: 0.0067755659110844135
2023-01-22 14:00:07.662212: step: 456/466, loss: 0.008343460038304329
2023-01-22 14:00:08.314334: step: 458/466, loss: 0.8243575692176819
2023-01-22 14:00:08.914620: step: 460/466, loss: 0.0017933855997398496
2023-01-22 14:00:09.563281: step: 462/466, loss: 0.042824890464544296
2023-01-22 14:00:10.205259: step: 464/466, loss: 0.010092045180499554
2023-01-22 14:00:10.805655: step: 466/466, loss: 0.012770496308803558
2023-01-22 14:00:11.421197: step: 468/466, loss: 0.0638820230960846
2023-01-22 14:00:12.056370: step: 470/466, loss: 0.0006324428832158446
2023-01-22 14:00:12.687191: step: 472/466, loss: 0.016825968399643898
2023-01-22 14:00:13.323978: step: 474/466, loss: 0.0032879516948014498
2023-01-22 14:00:13.935650: step: 476/466, loss: 0.004367944318801165
2023-01-22 14:00:14.527173: step: 478/466, loss: 0.0025375245604664087
2023-01-22 14:00:15.097801: step: 480/466, loss: 0.0017064290586858988
2023-01-22 14:00:15.741384: step: 482/466, loss: 0.06843334436416626
2023-01-22 14:00:16.367298: step: 484/466, loss: 0.35727813839912415
2023-01-22 14:00:16.928189: step: 486/466, loss: 0.0025273372884839773
2023-01-22 14:00:17.494925: step: 488/466, loss: 0.0005819305079057813
2023-01-22 14:00:18.166181: step: 490/466, loss: 0.044151756912469864
2023-01-22 14:00:18.774327: step: 492/466, loss: 0.009603282436728477
2023-01-22 14:00:19.370947: step: 494/466, loss: 0.0023218526039272547
2023-01-22 14:00:20.036430: step: 496/466, loss: 0.10366561263799667
2023-01-22 14:00:20.639980: step: 498/466, loss: 0.02948777936398983
2023-01-22 14:00:21.311357: step: 500/466, loss: 0.0006938776350580156
2023-01-22 14:00:21.952346: step: 502/466, loss: 0.04879922792315483
2023-01-22 14:00:22.563062: step: 504/466, loss: 0.004724626895040274
2023-01-22 14:00:23.159924: step: 506/466, loss: 0.00025952394935302436
2023-01-22 14:00:23.731737: step: 508/466, loss: 0.002397992415353656
2023-01-22 14:00:24.328060: step: 510/466, loss: 0.00031070475233718753
2023-01-22 14:00:24.895912: step: 512/466, loss: 0.001031419262290001
2023-01-22 14:00:25.543487: step: 514/466, loss: 4.788067235494964e-05
2023-01-22 14:00:26.157558: step: 516/466, loss: 0.002394371200352907
2023-01-22 14:00:26.833556: step: 518/466, loss: 0.007762254681438208
2023-01-22 14:00:27.408507: step: 520/466, loss: 0.015812717378139496
2023-01-22 14:00:28.021933: step: 522/466, loss: 0.005003506317734718
2023-01-22 14:00:28.606190: step: 524/466, loss: 0.0646287053823471
2023-01-22 14:00:29.203351: step: 526/466, loss: 0.0006683768006041646
2023-01-22 14:00:29.864564: step: 528/466, loss: 0.010825795121490955
2023-01-22 14:00:30.454348: step: 530/466, loss: 0.05152782052755356
2023-01-22 14:00:30.999886: step: 532/466, loss: 0.00973795261234045
2023-01-22 14:00:31.590006: step: 534/466, loss: 0.001491101342253387
2023-01-22 14:00:32.245135: step: 536/466, loss: 0.022614777088165283
2023-01-22 14:00:32.827352: step: 538/466, loss: 0.0004979691002517939
2023-01-22 14:00:33.529723: step: 540/466, loss: 0.008996004238724709
2023-01-22 14:00:34.097937: step: 542/466, loss: 0.047437675297260284
2023-01-22 14:00:34.703276: step: 544/466, loss: 0.021595099940896034
2023-01-22 14:00:35.352742: step: 546/466, loss: 0.03466839715838432
2023-01-22 14:00:35.929636: step: 548/466, loss: 0.00020024352124892175
2023-01-22 14:00:36.545803: step: 550/466, loss: 0.03670458868145943
2023-01-22 14:00:37.120131: step: 552/466, loss: 0.022422349080443382
2023-01-22 14:00:37.743056: step: 554/466, loss: 0.4138838052749634
2023-01-22 14:00:38.385640: step: 556/466, loss: 0.002338852733373642
2023-01-22 14:00:39.059768: step: 558/466, loss: 0.010339035652577877
2023-01-22 14:00:39.781263: step: 560/466, loss: 0.008293172344565392
2023-01-22 14:00:40.429125: step: 562/466, loss: 0.0033398624509572983
2023-01-22 14:00:41.038992: step: 564/466, loss: 0.0009204355301335454
2023-01-22 14:00:41.701848: step: 566/466, loss: 0.014306855387985706
2023-01-22 14:00:42.357208: step: 568/466, loss: 0.0131671829149127
2023-01-22 14:00:42.952938: step: 570/466, loss: 0.011301815509796143
2023-01-22 14:00:43.553904: step: 572/466, loss: 0.04796997085213661
2023-01-22 14:00:44.143842: step: 574/466, loss: 0.005415166728198528
2023-01-22 14:00:44.773113: step: 576/466, loss: 0.006941391620784998
2023-01-22 14:00:45.391139: step: 578/466, loss: 0.11789073795080185
2023-01-22 14:00:45.935012: step: 580/466, loss: 0.08147279918193817
2023-01-22 14:00:46.587714: step: 582/466, loss: 0.047601763159036636
2023-01-22 14:00:47.252811: step: 584/466, loss: 0.07497742027044296
2023-01-22 14:00:47.794329: step: 586/466, loss: 0.0024831874761730433
2023-01-22 14:00:48.400438: step: 588/466, loss: 0.0021917091216892004
2023-01-22 14:00:48.970509: step: 590/466, loss: 0.0030568272341042757
2023-01-22 14:00:49.687526: step: 592/466, loss: 0.010162237100303173
2023-01-22 14:00:50.274451: step: 594/466, loss: 0.001877710223197937
2023-01-22 14:00:50.882941: step: 596/466, loss: 0.007134966552257538
2023-01-22 14:00:51.400328: step: 598/466, loss: 7.020118209766224e-05
2023-01-22 14:00:52.039334: step: 600/466, loss: 0.008285176940262318
2023-01-22 14:00:52.661931: step: 602/466, loss: 0.06338031589984894
2023-01-22 14:00:53.274238: step: 604/466, loss: 0.0649886354804039
2023-01-22 14:00:53.862274: step: 606/466, loss: 0.02187025547027588
2023-01-22 14:00:54.523917: step: 608/466, loss: 0.08032085746526718
2023-01-22 14:00:55.139958: step: 610/466, loss: 0.03648293390870094
2023-01-22 14:00:55.704389: step: 612/466, loss: 0.010144883766770363
2023-01-22 14:00:56.345006: step: 614/466, loss: 0.0015597706660628319
2023-01-22 14:00:57.037915: step: 616/466, loss: 0.013114754110574722
2023-01-22 14:00:57.594990: step: 618/466, loss: 0.009712484665215015
2023-01-22 14:00:58.200197: step: 620/466, loss: 0.0004671521601267159
2023-01-22 14:00:58.848315: step: 622/466, loss: 0.019531484693288803
2023-01-22 14:00:59.476777: step: 624/466, loss: 0.00597155699506402
2023-01-22 14:01:00.085857: step: 626/466, loss: 0.0009442660957574844
2023-01-22 14:01:00.650342: step: 628/466, loss: 0.013763475231826305
2023-01-22 14:01:01.245584: step: 630/466, loss: 0.02130374312400818
2023-01-22 14:01:01.833064: step: 632/466, loss: 9.01765379239805e-05
2023-01-22 14:01:02.422695: step: 634/466, loss: 0.008411786518990993
2023-01-22 14:01:03.025356: step: 636/466, loss: 0.0007759033469483256
2023-01-22 14:01:03.625361: step: 638/466, loss: 0.011445640586316586
2023-01-22 14:01:04.208609: step: 640/466, loss: 0.004646544344723225
2023-01-22 14:01:04.842613: step: 642/466, loss: 0.006833262275904417
2023-01-22 14:01:05.483883: step: 644/466, loss: 0.1428021341562271
2023-01-22 14:01:06.091111: step: 646/466, loss: 0.003483706619590521
2023-01-22 14:01:06.695497: step: 648/466, loss: 0.0012693015160039067
2023-01-22 14:01:07.330704: step: 650/466, loss: 0.0013372853863984346
2023-01-22 14:01:07.905093: step: 652/466, loss: 0.004944841843098402
2023-01-22 14:01:08.523576: step: 654/466, loss: 0.012301434762775898
2023-01-22 14:01:09.165046: step: 656/466, loss: 0.006135048344731331
2023-01-22 14:01:09.760092: step: 658/466, loss: 0.011722376570105553
2023-01-22 14:01:10.353150: step: 660/466, loss: 0.004831454250961542
2023-01-22 14:01:10.923257: step: 662/466, loss: 0.0010106010595336556
2023-01-22 14:01:11.540949: step: 664/466, loss: 0.0006785733858123422
2023-01-22 14:01:12.226038: step: 666/466, loss: 0.0036645540967583656
2023-01-22 14:01:12.780006: step: 668/466, loss: 0.354581743478775
2023-01-22 14:01:13.430227: step: 670/466, loss: 0.0022827736102044582
2023-01-22 14:01:14.072957: step: 672/466, loss: 0.0003675426996778697
2023-01-22 14:01:14.738011: step: 674/466, loss: 0.032468073070049286
2023-01-22 14:01:15.321383: step: 676/466, loss: 0.0008371906587854028
2023-01-22 14:01:15.912956: step: 678/466, loss: 0.009145176969468594
2023-01-22 14:01:16.481107: step: 680/466, loss: 0.007412533741444349
2023-01-22 14:01:17.136158: step: 682/466, loss: 0.021561123430728912
2023-01-22 14:01:17.809051: step: 684/466, loss: 0.00114986184053123
2023-01-22 14:01:18.422649: step: 686/466, loss: 0.12480369210243225
2023-01-22 14:01:19.027748: step: 688/466, loss: 0.055875711143016815
2023-01-22 14:01:19.672540: step: 690/466, loss: 0.0023874372709542513
2023-01-22 14:01:20.287871: step: 692/466, loss: 0.003263173159211874
2023-01-22 14:01:20.875489: step: 694/466, loss: 0.003564089071005583
2023-01-22 14:01:21.507437: step: 696/466, loss: 0.9798381924629211
2023-01-22 14:01:22.088499: step: 698/466, loss: 0.026384569704532623
2023-01-22 14:01:22.673230: step: 700/466, loss: 0.009991944767534733
2023-01-22 14:01:23.408279: step: 702/466, loss: 0.013687239028513432
2023-01-22 14:01:24.042817: step: 704/466, loss: 0.013689437881112099
2023-01-22 14:01:24.728349: step: 706/466, loss: 0.010718021541833878
2023-01-22 14:01:25.369264: step: 708/466, loss: 0.37827393412590027
2023-01-22 14:01:25.959505: step: 710/466, loss: 0.13925020396709442
2023-01-22 14:01:26.666390: step: 712/466, loss: 0.007778448984026909
2023-01-22 14:01:27.262475: step: 714/466, loss: 0.019935665652155876
2023-01-22 14:01:27.913124: step: 716/466, loss: 0.002576232887804508
2023-01-22 14:01:28.529699: step: 718/466, loss: 0.05597037822008133
2023-01-22 14:01:29.139512: step: 720/466, loss: 0.005296092014759779
2023-01-22 14:01:29.678898: step: 722/466, loss: 5.4547977924812585e-05
2023-01-22 14:01:30.327194: step: 724/466, loss: 0.05543103441596031
2023-01-22 14:01:30.895511: step: 726/466, loss: 0.00011633874964900315
2023-01-22 14:01:31.505478: step: 728/466, loss: 0.0037250141613185406
2023-01-22 14:01:32.120572: step: 730/466, loss: 0.0020853602327406406
2023-01-22 14:01:32.831752: step: 732/466, loss: 0.016643157228827477
2023-01-22 14:01:33.465473: step: 734/466, loss: 0.09759864211082458
2023-01-22 14:01:34.054360: step: 736/466, loss: 0.03504372388124466
2023-01-22 14:01:34.714012: step: 738/466, loss: 0.0022636796347796917
2023-01-22 14:01:35.311835: step: 740/466, loss: 0.009098563343286514
2023-01-22 14:01:35.901754: step: 742/466, loss: 0.01605973392724991
2023-01-22 14:01:36.483784: step: 744/466, loss: 0.013869882561266422
2023-01-22 14:01:37.073290: step: 746/466, loss: 0.00021724813268519938
2023-01-22 14:01:37.674191: step: 748/466, loss: 0.000851553282700479
2023-01-22 14:01:38.260055: step: 750/466, loss: 0.005408648867160082
2023-01-22 14:01:38.900679: step: 752/466, loss: 0.018733207136392593
2023-01-22 14:01:39.549034: step: 754/466, loss: 0.006612854544073343
2023-01-22 14:01:40.148552: step: 756/466, loss: 0.002440654905512929
2023-01-22 14:01:40.782524: step: 758/466, loss: 0.02385859191417694
2023-01-22 14:01:41.398420: step: 760/466, loss: 0.00998731143772602
2023-01-22 14:01:41.995413: step: 762/466, loss: 0.02541702799499035
2023-01-22 14:01:42.529461: step: 764/466, loss: 0.0004247078322805464
2023-01-22 14:01:43.101310: step: 766/466, loss: 0.00015261516091413796
2023-01-22 14:01:43.682713: step: 768/466, loss: 0.004938450176268816
2023-01-22 14:01:44.263048: step: 770/466, loss: 0.012439640238881111
2023-01-22 14:01:44.900637: step: 772/466, loss: 0.058742985129356384
2023-01-22 14:01:45.468266: step: 774/466, loss: 0.022723093628883362
2023-01-22 14:01:46.094859: step: 776/466, loss: 0.006965222768485546
2023-01-22 14:01:46.730791: step: 778/466, loss: 0.0020023758988827467
2023-01-22 14:01:47.387700: step: 780/466, loss: 0.020294897258281708
2023-01-22 14:01:47.949802: step: 782/466, loss: 0.08900012075901031
2023-01-22 14:01:48.620223: step: 784/466, loss: 0.04531180113554001
2023-01-22 14:01:49.177281: step: 786/466, loss: 0.001975729363039136
2023-01-22 14:01:49.808230: step: 788/466, loss: 0.010713978670537472
2023-01-22 14:01:50.432356: step: 790/466, loss: 0.02182890474796295
2023-01-22 14:01:51.115456: step: 792/466, loss: 0.0789024755358696
2023-01-22 14:01:51.716804: step: 794/466, loss: 0.003523700637742877
2023-01-22 14:01:52.318579: step: 796/466, loss: 1.0092992852150928e-05
2023-01-22 14:01:52.949179: step: 798/466, loss: 0.03954795002937317
2023-01-22 14:01:53.548747: step: 800/466, loss: 0.0508272759616375
2023-01-22 14:01:54.164624: step: 802/466, loss: 0.014859997667372227
2023-01-22 14:01:54.838593: step: 804/466, loss: 0.07760845124721527
2023-01-22 14:01:55.504815: step: 806/466, loss: 0.005476176273077726
2023-01-22 14:01:56.119169: step: 808/466, loss: 0.0022972505539655685
2023-01-22 14:01:56.757094: step: 810/466, loss: 0.0020878976210951805
2023-01-22 14:01:57.463646: step: 812/466, loss: 0.03605556860566139
2023-01-22 14:01:58.121185: step: 814/466, loss: 0.03797121345996857
2023-01-22 14:01:58.716990: step: 816/466, loss: 0.004127658903598785
2023-01-22 14:01:59.347397: step: 818/466, loss: 0.002642194740474224
2023-01-22 14:01:59.895586: step: 820/466, loss: 0.003927435725927353
2023-01-22 14:02:00.499102: step: 822/466, loss: 0.002834962448105216
2023-01-22 14:02:01.044111: step: 824/466, loss: 0.014993560500442982
2023-01-22 14:02:01.722317: step: 826/466, loss: 0.019240783527493477
2023-01-22 14:02:02.357355: step: 828/466, loss: 0.010984636843204498
2023-01-22 14:02:02.955837: step: 830/466, loss: 0.004568424075841904
2023-01-22 14:02:03.554136: step: 832/466, loss: 0.03935897722840309
2023-01-22 14:02:04.105419: step: 834/466, loss: 0.0003054741828236729
2023-01-22 14:02:04.662422: step: 836/466, loss: 0.037199921905994415
2023-01-22 14:02:05.311227: step: 838/466, loss: 0.010629761032760143
2023-01-22 14:02:05.892354: step: 840/466, loss: 0.0027806272264569998
2023-01-22 14:02:06.516237: step: 842/466, loss: 0.0029716147109866142
2023-01-22 14:02:07.132504: step: 844/466, loss: 0.0017348077381029725
2023-01-22 14:02:07.764897: step: 846/466, loss: 0.011939690448343754
2023-01-22 14:02:08.383703: step: 848/466, loss: 0.0006046024500392377
2023-01-22 14:02:08.957211: step: 850/466, loss: 0.01060577854514122
2023-01-22 14:02:09.573874: step: 852/466, loss: 0.0018012551590800285
2023-01-22 14:02:10.195023: step: 854/466, loss: 0.02042742818593979
2023-01-22 14:02:10.887977: step: 856/466, loss: 0.026546571403741837
2023-01-22 14:02:11.450369: step: 858/466, loss: 0.007592841051518917
2023-01-22 14:02:12.066722: step: 860/466, loss: 0.1809961050748825
2023-01-22 14:02:12.759823: step: 862/466, loss: 0.00013021420454606414
2023-01-22 14:02:13.415545: step: 864/466, loss: 0.0031625409610569477
2023-01-22 14:02:14.090764: step: 866/466, loss: 0.017291951924562454
2023-01-22 14:02:14.722201: step: 868/466, loss: 0.017253616824746132
2023-01-22 14:02:15.454036: step: 870/466, loss: 0.014447838999330997
2023-01-22 14:02:16.082809: step: 872/466, loss: 0.010009496472775936
2023-01-22 14:02:16.671618: step: 874/466, loss: 0.032422348856925964
2023-01-22 14:02:17.297027: step: 876/466, loss: 0.004229803569614887
2023-01-22 14:02:17.931605: step: 878/466, loss: 0.04559878259897232
2023-01-22 14:02:18.621402: step: 880/466, loss: 0.026000287383794785
2023-01-22 14:02:19.243227: step: 882/466, loss: 0.0010667172027751803
2023-01-22 14:02:19.846462: step: 884/466, loss: 0.00041076657362282276
2023-01-22 14:02:20.526376: step: 886/466, loss: 0.032993000000715256
2023-01-22 14:02:21.203539: step: 888/466, loss: 0.026025397703051567
2023-01-22 14:02:21.808390: step: 890/466, loss: 0.014603899791836739
2023-01-22 14:02:22.465190: step: 892/466, loss: 0.016040993854403496
2023-01-22 14:02:23.067558: step: 894/466, loss: 0.012828697450459003
2023-01-22 14:02:23.658693: step: 896/466, loss: 0.0034813571255654097
2023-01-22 14:02:24.206867: step: 898/466, loss: 0.0012004021555185318
2023-01-22 14:02:24.816343: step: 900/466, loss: 0.0019947951659560204
2023-01-22 14:02:25.419858: step: 902/466, loss: 0.005977644119411707
2023-01-22 14:02:25.992788: step: 904/466, loss: 0.004979805089533329
2023-01-22 14:02:26.677907: step: 906/466, loss: 0.23743489384651184
2023-01-22 14:02:27.267649: step: 908/466, loss: 0.0009202069486491382
2023-01-22 14:02:27.876454: step: 910/466, loss: 0.004790265113115311
2023-01-22 14:02:28.475335: step: 912/466, loss: 6.339549145195633e-05
2023-01-22 14:02:29.126049: step: 914/466, loss: 0.017467763274908066
2023-01-22 14:02:29.714764: step: 916/466, loss: 0.0016730381175875664
2023-01-22 14:02:30.310819: step: 918/466, loss: 0.0036454566288739443
2023-01-22 14:02:30.898032: step: 920/466, loss: 0.047419484704732895
2023-01-22 14:02:31.446527: step: 922/466, loss: 0.005076316650956869
2023-01-22 14:02:32.064460: step: 924/466, loss: 0.010990198701620102
2023-01-22 14:02:32.730480: step: 926/466, loss: 0.016945889219641685
2023-01-22 14:02:33.347197: step: 928/466, loss: 3.716916762641631e-05
2023-01-22 14:02:33.906849: step: 930/466, loss: 0.0017149192281067371
2023-01-22 14:02:34.590468: step: 932/466, loss: 0.005673174746334553
==================================================
Loss: 0.038
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32555112570356476, 'r': 0.32925759013282735, 'f1': 0.32739386792452835}, 'combined': 0.24123758689175773, 'epoch': 35}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3244198532667191, 'r': 0.2913337129967378, 'f1': 0.30698787826950596}, 'combined': 0.19222605461735423, 'epoch': 35}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3141818576388889, 'r': 0.34339421252371916, 'f1': 0.3281391659111514}, 'combined': 0.24178675382926942, 'epoch': 35}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3317813548966799, 'r': 0.30543048916481363, 'f1': 0.3180610733032082}, 'combined': 0.19710827077945295, 'epoch': 35}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28109051036682614, 'r': 0.3344283681214421, 'f1': 0.3054484402079723}, 'combined': 0.2250672717321901, 'epoch': 35}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.33947162538533093, 'r': 0.30205921499959437, 'f1': 0.3196745229489015}, 'combined': 0.21206131720372673, 'epoch': 35}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2897727272727273, 'r': 0.36428571428571427, 'f1': 0.3227848101265823}, 'combined': 0.2151898734177215, 'epoch': 35}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.30303030303030304, 'r': 0.43478260869565216, 'f1': 0.35714285714285715}, 'combined': 0.17857142857142858, 'epoch': 35}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2916666666666667, 'r': 0.2413793103448276, 'f1': 0.26415094339622647}, 'combined': 0.17610062893081763, 'epoch': 35}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 14:05:12.391613: step: 2/466, loss: 0.0028844948392361403
2023-01-22 14:05:13.001054: step: 4/466, loss: 0.004477688577026129
2023-01-22 14:05:13.613628: step: 6/466, loss: 0.0003000227443408221
2023-01-22 14:05:14.254905: step: 8/466, loss: 1.3290955394040793e-05
2023-01-22 14:05:14.932789: step: 10/466, loss: 0.12150408327579498
2023-01-22 14:05:15.615515: step: 12/466, loss: 0.0013362518511712551
2023-01-22 14:05:16.266650: step: 14/466, loss: 0.005980302579700947
2023-01-22 14:05:16.852149: step: 16/466, loss: 0.00017088482854887843
2023-01-22 14:05:17.464281: step: 18/466, loss: 0.0010265213204547763
2023-01-22 14:05:18.064565: step: 20/466, loss: 0.0037992754951119423
2023-01-22 14:05:18.667393: step: 22/466, loss: 0.0003503831976559013
2023-01-22 14:05:19.313253: step: 24/466, loss: 0.009516526944935322
2023-01-22 14:05:19.905095: step: 26/466, loss: 0.0005678251036442816
2023-01-22 14:05:20.516618: step: 28/466, loss: 0.0016911040293052793
2023-01-22 14:05:21.085297: step: 30/466, loss: 0.010018992237746716
2023-01-22 14:05:21.665346: step: 32/466, loss: 0.002980363555252552
2023-01-22 14:05:22.277456: step: 34/466, loss: 0.0024216691963374615
2023-01-22 14:05:22.917418: step: 36/466, loss: 0.020891092717647552
2023-01-22 14:05:23.573192: step: 38/466, loss: 0.010172278620302677
2023-01-22 14:05:24.157679: step: 40/466, loss: 0.03021528571844101
2023-01-22 14:05:24.781317: step: 42/466, loss: 0.0006058058934286237
2023-01-22 14:05:25.375148: step: 44/466, loss: 2.0629704522434622e-05
2023-01-22 14:05:26.009226: step: 46/466, loss: 0.0018936379346996546
2023-01-22 14:05:26.652551: step: 48/466, loss: 0.04245248809456825
2023-01-22 14:05:27.274208: step: 50/466, loss: 0.022075532004237175
2023-01-22 14:05:27.947601: step: 52/466, loss: 0.009132004342973232
2023-01-22 14:05:28.622515: step: 54/466, loss: 0.003254002658650279
2023-01-22 14:05:29.213677: step: 56/466, loss: 0.002954368479549885
2023-01-22 14:05:29.792559: step: 58/466, loss: 0.009963125921785831
2023-01-22 14:05:30.408310: step: 60/466, loss: 0.001487000030465424
2023-01-22 14:05:30.995088: step: 62/466, loss: 0.00010598334483802319
2023-01-22 14:05:31.683818: step: 64/466, loss: 0.007556512951850891
2023-01-22 14:05:32.313812: step: 66/466, loss: 0.002061608247458935
2023-01-22 14:05:32.900653: step: 68/466, loss: 0.06095759943127632
2023-01-22 14:05:33.541127: step: 70/466, loss: 0.03266202658414841
2023-01-22 14:05:34.122067: step: 72/466, loss: 0.03090989775955677
2023-01-22 14:05:34.760440: step: 74/466, loss: 0.0016189554007723927
2023-01-22 14:05:35.344261: step: 76/466, loss: 0.059345971792936325
2023-01-22 14:05:35.972979: step: 78/466, loss: 0.0012508289655670524
2023-01-22 14:05:36.596910: step: 80/466, loss: 0.0017027511494234204
2023-01-22 14:05:37.223093: step: 82/466, loss: 0.08864498883485794
2023-01-22 14:05:37.929497: step: 84/466, loss: 0.008869364857673645
2023-01-22 14:05:38.605659: step: 86/466, loss: 0.1268760859966278
2023-01-22 14:05:39.221954: step: 88/466, loss: 0.004266493953764439
2023-01-22 14:05:39.848389: step: 90/466, loss: 0.0001659767294768244
2023-01-22 14:05:40.513085: step: 92/466, loss: 0.0091606630012393
2023-01-22 14:05:41.157371: step: 94/466, loss: 0.011976691894233227
2023-01-22 14:05:41.685762: step: 96/466, loss: 0.0005975335370749235
2023-01-22 14:05:42.355484: step: 98/466, loss: 0.012866249307990074
2023-01-22 14:05:42.925418: step: 100/466, loss: 0.00027132805553264916
2023-01-22 14:05:43.524249: step: 102/466, loss: 0.003607760416343808
2023-01-22 14:05:44.093980: step: 104/466, loss: 0.004815015941858292
2023-01-22 14:05:44.660057: step: 106/466, loss: 9.031585796037689e-05
2023-01-22 14:05:45.251906: step: 108/466, loss: 0.002620894927531481
2023-01-22 14:05:45.814924: step: 110/466, loss: 0.017637314274907112
2023-01-22 14:05:46.409692: step: 112/466, loss: 0.0327749028801918
2023-01-22 14:05:47.015188: step: 114/466, loss: 0.05157430097460747
2023-01-22 14:05:47.621670: step: 116/466, loss: 0.01633082889020443
2023-01-22 14:05:48.329356: step: 118/466, loss: 0.00734519399702549
2023-01-22 14:05:48.951018: step: 120/466, loss: 0.43789926171302795
2023-01-22 14:05:49.570850: step: 122/466, loss: 0.005928925704210997
2023-01-22 14:05:50.184297: step: 124/466, loss: 0.0004282771551515907
2023-01-22 14:05:50.745036: step: 126/466, loss: 0.011000387370586395
2023-01-22 14:05:51.323657: step: 128/466, loss: 0.005932093132287264
2023-01-22 14:05:52.015813: step: 130/466, loss: 0.4482037425041199
2023-01-22 14:05:52.652575: step: 132/466, loss: 0.01929701678454876
2023-01-22 14:05:53.313712: step: 134/466, loss: 0.047041188925504684
2023-01-22 14:05:53.917818: step: 136/466, loss: 0.0006318792584352195
2023-01-22 14:05:54.541724: step: 138/466, loss: 0.0014515618095174432
2023-01-22 14:05:55.203599: step: 140/466, loss: 0.0021152058616280556
2023-01-22 14:05:55.809793: step: 142/466, loss: 0.0003849035711027682
2023-01-22 14:05:56.448212: step: 144/466, loss: 0.026079481467604637
2023-01-22 14:05:57.076081: step: 146/466, loss: 0.013263884000480175
2023-01-22 14:05:57.669683: step: 148/466, loss: 0.030426165089011192
2023-01-22 14:05:58.312481: step: 150/466, loss: 0.0001940604270203039
2023-01-22 14:05:58.925854: step: 152/466, loss: 0.009219626896083355
2023-01-22 14:05:59.487337: step: 154/466, loss: 0.00032124348217621446
2023-01-22 14:06:00.118679: step: 156/466, loss: 0.011430817656219006
2023-01-22 14:06:00.827214: step: 158/466, loss: 0.11611834913492203
2023-01-22 14:06:01.462694: step: 160/466, loss: 0.000801683112513274
2023-01-22 14:06:02.160849: step: 162/466, loss: 0.0005692451959475875
2023-01-22 14:06:02.753970: step: 164/466, loss: 0.00034218060318380594
2023-01-22 14:06:03.371659: step: 166/466, loss: 0.005028598476201296
2023-01-22 14:06:03.980284: step: 168/466, loss: 0.0063055288046598434
2023-01-22 14:06:04.642498: step: 170/466, loss: 0.006019635125994682
2023-01-22 14:06:05.312091: step: 172/466, loss: 0.00036249557160772383
2023-01-22 14:06:05.932882: step: 174/466, loss: 0.003946827258914709
2023-01-22 14:06:06.626242: step: 176/466, loss: 0.004646969959139824
2023-01-22 14:06:07.303061: step: 178/466, loss: 0.01717056892812252
2023-01-22 14:06:07.905709: step: 180/466, loss: 0.008211605250835419
2023-01-22 14:06:08.657856: step: 182/466, loss: 0.0012590755941346288
2023-01-22 14:06:09.253487: step: 184/466, loss: 0.00900521595031023
2023-01-22 14:06:09.830787: step: 186/466, loss: 0.013704388402402401
2023-01-22 14:06:10.429819: step: 188/466, loss: 0.1032930538058281
2023-01-22 14:06:10.997444: step: 190/466, loss: 0.0007142267422750592
2023-01-22 14:06:11.609237: step: 192/466, loss: 0.001518684788607061
2023-01-22 14:06:12.198154: step: 194/466, loss: 0.041061513125896454
2023-01-22 14:06:12.779426: step: 196/466, loss: 0.00041243646410293877
2023-01-22 14:06:13.400863: step: 198/466, loss: 0.14034345746040344
2023-01-22 14:06:14.020803: step: 200/466, loss: 0.0006125233485363424
2023-01-22 14:06:14.650124: step: 202/466, loss: 0.007131355348974466
2023-01-22 14:06:15.272154: step: 204/466, loss: 0.0033776569180190563
2023-01-22 14:06:15.890673: step: 206/466, loss: 0.1322488784790039
2023-01-22 14:06:16.538367: step: 208/466, loss: 0.00819089449942112
2023-01-22 14:06:17.218459: step: 210/466, loss: 0.04165108874440193
2023-01-22 14:06:17.820535: step: 212/466, loss: 0.00016025331569835544
2023-01-22 14:06:18.479258: step: 214/466, loss: 0.0014197358395904303
2023-01-22 14:06:19.120666: step: 216/466, loss: 0.013069494627416134
2023-01-22 14:06:19.747314: step: 218/466, loss: 0.05171070992946625
2023-01-22 14:06:20.353669: step: 220/466, loss: 0.00040108899702318013
2023-01-22 14:06:21.035789: step: 222/466, loss: 0.0028013801202178
2023-01-22 14:06:21.631925: step: 224/466, loss: 0.0014411675510928035
2023-01-22 14:06:22.282134: step: 226/466, loss: 0.01950146071612835
2023-01-22 14:06:22.885606: step: 228/466, loss: 0.0007650554762221873
2023-01-22 14:06:23.568062: step: 230/466, loss: 0.022157352417707443
2023-01-22 14:06:24.176211: step: 232/466, loss: 0.3453446626663208
2023-01-22 14:06:24.857554: step: 234/466, loss: 0.013007968664169312
2023-01-22 14:06:25.498314: step: 236/466, loss: 0.009503094479441643
2023-01-22 14:06:26.142708: step: 238/466, loss: 0.0013482423964887857
2023-01-22 14:06:26.833675: step: 240/466, loss: 0.0011200150474905968
2023-01-22 14:06:27.435081: step: 242/466, loss: 0.0030352682806551456
2023-01-22 14:06:28.050166: step: 244/466, loss: 0.012318750843405724
2023-01-22 14:06:28.652804: step: 246/466, loss: 0.0367109552025795
2023-01-22 14:06:29.232671: step: 248/466, loss: 2.467216290824581e-05
2023-01-22 14:06:29.858703: step: 250/466, loss: 0.017559640109539032
2023-01-22 14:06:30.647769: step: 252/466, loss: 0.006461227312684059
2023-01-22 14:06:31.225628: step: 254/466, loss: 0.020218346267938614
2023-01-22 14:06:31.995500: step: 256/466, loss: 0.025049136951565742
2023-01-22 14:06:32.592721: step: 258/466, loss: 0.0018531163223087788
2023-01-22 14:06:33.214341: step: 260/466, loss: 0.0019890430849045515
2023-01-22 14:06:33.821236: step: 262/466, loss: 0.02820025011897087
2023-01-22 14:06:34.473941: step: 264/466, loss: 0.03085833229124546
2023-01-22 14:06:35.064701: step: 266/466, loss: 0.02268262393772602
2023-01-22 14:06:35.708097: step: 268/466, loss: 0.013150263577699661
2023-01-22 14:06:36.339280: step: 270/466, loss: 0.004210530314594507
2023-01-22 14:06:36.991998: step: 272/466, loss: 0.011209763586521149
2023-01-22 14:06:37.609320: step: 274/466, loss: 0.0016858786111697555
2023-01-22 14:06:38.230685: step: 276/466, loss: 0.0133918896317482
2023-01-22 14:06:38.831306: step: 278/466, loss: 0.022778602316975594
2023-01-22 14:06:39.478258: step: 280/466, loss: 0.0009834776865318418
2023-01-22 14:06:40.005629: step: 282/466, loss: 0.006443210877478123
2023-01-22 14:06:40.624645: step: 284/466, loss: 0.00044808301026932895
2023-01-22 14:06:41.185031: step: 286/466, loss: 0.001966314623132348
2023-01-22 14:06:41.807725: step: 288/466, loss: 0.032862693071365356
2023-01-22 14:06:42.423771: step: 290/466, loss: 0.002843247726559639
2023-01-22 14:06:42.988198: step: 292/466, loss: 0.00019092507136519998
2023-01-22 14:06:43.586995: step: 294/466, loss: 0.0997622087597847
2023-01-22 14:06:44.170457: step: 296/466, loss: 0.04326612129807472
2023-01-22 14:06:44.764527: step: 298/466, loss: 4.8781112127471715e-05
2023-01-22 14:06:45.364096: step: 300/466, loss: 0.0007119726506061852
2023-01-22 14:06:46.010301: step: 302/466, loss: 0.013141287490725517
2023-01-22 14:06:46.618118: step: 304/466, loss: 0.0002665870124474168
2023-01-22 14:06:47.197825: step: 306/466, loss: 0.006385975982993841
2023-01-22 14:06:47.778351: step: 308/466, loss: 0.02065122500061989
2023-01-22 14:06:48.436695: step: 310/466, loss: 0.6212195754051208
2023-01-22 14:06:49.171656: step: 312/466, loss: 0.03992288187146187
2023-01-22 14:06:49.800484: step: 314/466, loss: 0.0023537592496722937
2023-01-22 14:06:50.404317: step: 316/466, loss: 0.0005659500602632761
2023-01-22 14:06:50.986765: step: 318/466, loss: 0.06017843261361122
2023-01-22 14:06:51.656148: step: 320/466, loss: 0.007353016175329685
2023-01-22 14:06:52.289694: step: 322/466, loss: 0.00731989461928606
2023-01-22 14:06:52.875844: step: 324/466, loss: 0.0017221017042174935
2023-01-22 14:06:53.481616: step: 326/466, loss: 0.014298143796622753
2023-01-22 14:06:54.131931: step: 328/466, loss: 0.0008118084515444934
2023-01-22 14:06:54.779696: step: 330/466, loss: 0.0007438024040311575
2023-01-22 14:06:55.390219: step: 332/466, loss: 0.0015993744600564241
2023-01-22 14:06:56.009450: step: 334/466, loss: 0.0005670600803568959
2023-01-22 14:06:56.662156: step: 336/466, loss: 0.000510596320964396
2023-01-22 14:06:57.381109: step: 338/466, loss: 0.04210871458053589
2023-01-22 14:06:58.055680: step: 340/466, loss: 0.004334737546741962
2023-01-22 14:06:58.698046: step: 342/466, loss: 0.025569146499037743
2023-01-22 14:06:59.337168: step: 344/466, loss: 0.0036312583833932877
2023-01-22 14:06:59.991100: step: 346/466, loss: 0.050589319318532944
2023-01-22 14:07:00.620780: step: 348/466, loss: 0.006575300358235836
2023-01-22 14:07:01.160989: step: 350/466, loss: 0.00393358338624239
2023-01-22 14:07:01.767772: step: 352/466, loss: 0.004188355058431625
2023-01-22 14:07:02.394377: step: 354/466, loss: 0.022143129259347916
2023-01-22 14:07:03.002914: step: 356/466, loss: 0.011643332429230213
2023-01-22 14:07:03.663626: step: 358/466, loss: 0.015739183872938156
2023-01-22 14:07:04.290456: step: 360/466, loss: 0.006921074818819761
2023-01-22 14:07:04.997985: step: 362/466, loss: 0.021753234788775444
2023-01-22 14:07:05.631052: step: 364/466, loss: 0.010252373293042183
2023-01-22 14:07:06.216042: step: 366/466, loss: 0.004911156836897135
2023-01-22 14:07:06.852990: step: 368/466, loss: 0.0020704721100628376
2023-01-22 14:07:07.381647: step: 370/466, loss: 0.01156570389866829
2023-01-22 14:07:07.953490: step: 372/466, loss: 0.010733842849731445
2023-01-22 14:07:08.567287: step: 374/466, loss: 0.47845223546028137
2023-01-22 14:07:09.161820: step: 376/466, loss: 0.002075807424262166
2023-01-22 14:07:09.837666: step: 378/466, loss: 0.15949863195419312
2023-01-22 14:07:10.515637: step: 380/466, loss: 0.004357450176030397
2023-01-22 14:07:11.189451: step: 382/466, loss: 0.002608703449368477
2023-01-22 14:07:11.780126: step: 384/466, loss: 0.00025477929739281535
2023-01-22 14:07:12.404967: step: 386/466, loss: 0.014991780743002892
2023-01-22 14:07:13.004808: step: 388/466, loss: 0.020069321617484093
2023-01-22 14:07:13.649861: step: 390/466, loss: 0.014262584038078785
2023-01-22 14:07:14.271031: step: 392/466, loss: 0.05203903093934059
2023-01-22 14:07:14.928626: step: 394/466, loss: 0.11401324719190598
2023-01-22 14:07:15.555941: step: 396/466, loss: 0.039628949016332626
2023-01-22 14:07:16.212427: step: 398/466, loss: 6.076023055356927e-05
2023-01-22 14:07:16.806423: step: 400/466, loss: 0.01817982643842697
2023-01-22 14:07:17.428016: step: 402/466, loss: 0.0074476925656199455
2023-01-22 14:07:18.013481: step: 404/466, loss: 0.0016515926690772176
2023-01-22 14:07:18.608105: step: 406/466, loss: 0.05185672640800476
2023-01-22 14:07:19.203920: step: 408/466, loss: 0.010113752447068691
2023-01-22 14:07:19.795929: step: 410/466, loss: 0.00014719483442604542
2023-01-22 14:07:20.396612: step: 412/466, loss: 0.0003996268496848643
2023-01-22 14:07:21.068175: step: 414/466, loss: 0.009516970254480839
2023-01-22 14:07:21.689162: step: 416/466, loss: 0.07272463291883469
2023-01-22 14:07:22.291532: step: 418/466, loss: 0.023695437237620354
2023-01-22 14:07:22.851642: step: 420/466, loss: 0.01535420399159193
2023-01-22 14:07:23.459439: step: 422/466, loss: 0.000404239195631817
2023-01-22 14:07:24.028278: step: 424/466, loss: 0.0014723282074555755
2023-01-22 14:07:24.619963: step: 426/466, loss: 4.463467121240683e-05
2023-01-22 14:07:25.275819: step: 428/466, loss: 0.009595575742423534
2023-01-22 14:07:25.900254: step: 430/466, loss: 0.006680773105472326
2023-01-22 14:07:26.488311: step: 432/466, loss: 0.001256832154467702
2023-01-22 14:07:27.126249: step: 434/466, loss: 0.06298192590475082
2023-01-22 14:07:27.797323: step: 436/466, loss: 0.008738339878618717
2023-01-22 14:07:28.502846: step: 438/466, loss: 0.013840259052813053
2023-01-22 14:07:29.181166: step: 440/466, loss: 0.0010939267231151462
2023-01-22 14:07:29.770800: step: 442/466, loss: 0.007236401084810495
2023-01-22 14:07:30.356265: step: 444/466, loss: 0.015179070644080639
2023-01-22 14:07:30.933378: step: 446/466, loss: 0.0005235313437879086
2023-01-22 14:07:31.503518: step: 448/466, loss: 0.0018311061430722475
2023-01-22 14:07:32.086284: step: 450/466, loss: 0.003520967671647668
2023-01-22 14:07:32.657030: step: 452/466, loss: 0.002411621157079935
2023-01-22 14:07:33.291221: step: 454/466, loss: 7.351519161602482e-05
2023-01-22 14:07:33.915687: step: 456/466, loss: 0.025556499138474464
2023-01-22 14:07:34.621313: step: 458/466, loss: 0.06181247904896736
2023-01-22 14:07:35.249549: step: 460/466, loss: 0.0001501685765106231
2023-01-22 14:07:35.849199: step: 462/466, loss: 0.00013221567496657372
2023-01-22 14:07:36.407709: step: 464/466, loss: 8.678200538270175e-05
2023-01-22 14:07:37.004016: step: 466/466, loss: 0.002673679729923606
2023-01-22 14:07:37.575674: step: 468/466, loss: 0.024993278086185455
2023-01-22 14:07:38.204677: step: 470/466, loss: 0.004244156647473574
2023-01-22 14:07:38.910086: step: 472/466, loss: 0.0019127581035718322
2023-01-22 14:07:39.472110: step: 474/466, loss: 5.943119504081551e-06
2023-01-22 14:07:40.066145: step: 476/466, loss: 0.04415856674313545
2023-01-22 14:07:40.718016: step: 478/466, loss: 0.008284655399620533
2023-01-22 14:07:41.295245: step: 480/466, loss: 0.01660160906612873
2023-01-22 14:07:41.987445: step: 482/466, loss: 0.006573822349309921
2023-01-22 14:07:42.628692: step: 484/466, loss: 0.7001836895942688
2023-01-22 14:07:43.236332: step: 486/466, loss: 0.003216114128008485
2023-01-22 14:07:43.896346: step: 488/466, loss: 6.530083192046732e-05
2023-01-22 14:07:44.462745: step: 490/466, loss: 0.0002036297373706475
2023-01-22 14:07:45.056214: step: 492/466, loss: 0.0004934872849844396
2023-01-22 14:07:45.691600: step: 494/466, loss: 0.011126363649964333
2023-01-22 14:07:46.291717: step: 496/466, loss: 0.0009767083683982491
2023-01-22 14:07:46.905845: step: 498/466, loss: 0.0007676812238059938
2023-01-22 14:07:47.560546: step: 500/466, loss: 0.03731703385710716
2023-01-22 14:07:48.164991: step: 502/466, loss: 0.009170123375952244
2023-01-22 14:07:48.803778: step: 504/466, loss: 0.0324895866215229
2023-01-22 14:07:49.384994: step: 506/466, loss: 0.0021355722565203905
2023-01-22 14:07:50.030283: step: 508/466, loss: 0.005301428027451038
2023-01-22 14:07:50.771020: step: 510/466, loss: 0.015567069873213768
2023-01-22 14:07:51.350881: step: 512/466, loss: 0.0011757559841498733
2023-01-22 14:07:52.059325: step: 514/466, loss: 0.00753001356497407
2023-01-22 14:07:52.651446: step: 516/466, loss: 0.00019986425468232483
2023-01-22 14:07:53.313008: step: 518/466, loss: 0.02854587510228157
2023-01-22 14:07:53.966929: step: 520/466, loss: 0.001624485943466425
2023-01-22 14:07:54.581382: step: 522/466, loss: 0.07426968216896057
2023-01-22 14:07:55.168025: step: 524/466, loss: 0.05831073224544525
2023-01-22 14:07:55.776747: step: 526/466, loss: 0.025548964738845825
2023-01-22 14:07:56.447487: step: 528/466, loss: 0.055001456290483475
2023-01-22 14:07:57.091781: step: 530/466, loss: 0.001785986009053886
2023-01-22 14:07:57.677930: step: 532/466, loss: 0.009283631108701229
2023-01-22 14:07:58.367073: step: 534/466, loss: 0.006106048356741667
2023-01-22 14:07:58.905606: step: 536/466, loss: 0.00019283413712400943
2023-01-22 14:07:59.517470: step: 538/466, loss: 0.055529121309518814
2023-01-22 14:08:00.152920: step: 540/466, loss: 0.05571475997567177
2023-01-22 14:08:00.808169: step: 542/466, loss: 0.035128843039274216
2023-01-22 14:08:01.440075: step: 544/466, loss: 0.00015004878514446318
2023-01-22 14:08:02.059897: step: 546/466, loss: 0.01245911605656147
2023-01-22 14:08:02.677324: step: 548/466, loss: 0.0021256059408187866
2023-01-22 14:08:03.266840: step: 550/466, loss: 0.00042605085764080286
2023-01-22 14:08:03.841583: step: 552/466, loss: 0.00026078903465531766
2023-01-22 14:08:04.437460: step: 554/466, loss: 0.006998375058174133
2023-01-22 14:08:05.003660: step: 556/466, loss: 0.025624988600611687
2023-01-22 14:08:05.713209: step: 558/466, loss: 0.055525388568639755
2023-01-22 14:08:06.424360: step: 560/466, loss: 0.04241339489817619
2023-01-22 14:08:07.051536: step: 562/466, loss: 0.000571149168536067
2023-01-22 14:08:07.757572: step: 564/466, loss: 0.003444262547418475
2023-01-22 14:08:08.398969: step: 566/466, loss: 4.600992724590469e-06
2023-01-22 14:08:08.987911: step: 568/466, loss: 0.032708849757909775
2023-01-22 14:08:09.577352: step: 570/466, loss: 0.038914408534765244
2023-01-22 14:08:10.154965: step: 572/466, loss: 0.010325398296117783
2023-01-22 14:08:10.795284: step: 574/466, loss: 0.01143960002809763
2023-01-22 14:08:11.419112: step: 576/466, loss: 0.030573971569538116
2023-01-22 14:08:12.015557: step: 578/466, loss: 0.018395937979221344
2023-01-22 14:08:12.658412: step: 580/466, loss: 0.030351920053362846
2023-01-22 14:08:13.311462: step: 582/466, loss: 0.008664535358548164
2023-01-22 14:08:13.975188: step: 584/466, loss: 0.009360837750136852
2023-01-22 14:08:14.603076: step: 586/466, loss: 0.0016620747046545148
2023-01-22 14:08:15.269481: step: 588/466, loss: 0.030544668436050415
2023-01-22 14:08:15.840712: step: 590/466, loss: 0.006064895074814558
2023-01-22 14:08:16.468570: step: 592/466, loss: 0.009367172606289387
2023-01-22 14:08:17.275722: step: 594/466, loss: 0.005620704032480717
2023-01-22 14:08:17.884310: step: 596/466, loss: 0.20808552205562592
2023-01-22 14:08:18.465033: step: 598/466, loss: 0.00129466294310987
2023-01-22 14:08:19.065684: step: 600/466, loss: 0.00414486788213253
2023-01-22 14:08:19.752101: step: 602/466, loss: 0.0697261318564415
2023-01-22 14:08:20.358592: step: 604/466, loss: 0.0014271108666434884
2023-01-22 14:08:20.955599: step: 606/466, loss: 0.0017695369897410274
2023-01-22 14:08:21.515745: step: 608/466, loss: 0.00022417650325223804
2023-01-22 14:08:22.122350: step: 610/466, loss: 0.005572855472564697
2023-01-22 14:08:22.752586: step: 612/466, loss: 0.009449760429561138
2023-01-22 14:08:23.392504: step: 614/466, loss: 0.010749047622084618
2023-01-22 14:08:23.963061: step: 616/466, loss: 0.04724499210715294
2023-01-22 14:08:24.658606: step: 618/466, loss: 0.0005491743795573711
2023-01-22 14:08:25.258712: step: 620/466, loss: 0.01939254254102707
2023-01-22 14:08:25.868299: step: 622/466, loss: 0.010335844941437244
2023-01-22 14:08:26.454425: step: 624/466, loss: 0.02881159819662571
2023-01-22 14:08:27.039744: step: 626/466, loss: 0.002635092008858919
2023-01-22 14:08:27.663605: step: 628/466, loss: 0.02328282594680786
2023-01-22 14:08:28.270720: step: 630/466, loss: 0.009212059900164604
2023-01-22 14:08:28.825308: step: 632/466, loss: 0.00025175249902531505
2023-01-22 14:08:29.490048: step: 634/466, loss: 0.00782365258783102
2023-01-22 14:08:30.048366: step: 636/466, loss: 0.015573399141430855
2023-01-22 14:08:30.695897: step: 638/466, loss: 0.001913038082420826
2023-01-22 14:08:31.300152: step: 640/466, loss: 1.5752522813272662e-05
2023-01-22 14:08:31.899187: step: 642/466, loss: 0.007720749359577894
2023-01-22 14:08:32.560324: step: 644/466, loss: 8.122907456709072e-05
2023-01-22 14:08:33.136335: step: 646/466, loss: 0.0023835143074393272
2023-01-22 14:08:33.735807: step: 648/466, loss: 0.0002880166284739971
2023-01-22 14:08:34.332956: step: 650/466, loss: 0.013356372714042664
2023-01-22 14:08:34.959846: step: 652/466, loss: 0.04252351447939873
2023-01-22 14:08:35.600580: step: 654/466, loss: 0.0007380394963547587
2023-01-22 14:08:36.240016: step: 656/466, loss: 0.029463758692145348
2023-01-22 14:08:36.827003: step: 658/466, loss: 7.94878214946948e-05
2023-01-22 14:08:37.517571: step: 660/466, loss: 0.006463555619120598
2023-01-22 14:08:38.093326: step: 662/466, loss: 5.085931843495928e-05
2023-01-22 14:08:38.750392: step: 664/466, loss: 0.0656449943780899
2023-01-22 14:08:39.346781: step: 666/466, loss: 7.274935342138633e-05
2023-01-22 14:08:39.933219: step: 668/466, loss: 0.0009882092708721757
2023-01-22 14:08:40.574933: step: 670/466, loss: 0.008753130212426186
2023-01-22 14:08:41.169827: step: 672/466, loss: 0.025208454579114914
2023-01-22 14:08:41.725934: step: 674/466, loss: 0.00046038933214731514
2023-01-22 14:08:42.331385: step: 676/466, loss: 0.04523847997188568
2023-01-22 14:08:42.994257: step: 678/466, loss: 0.04012119024991989
2023-01-22 14:08:43.567744: step: 680/466, loss: 1.3588703950517811e-05
2023-01-22 14:08:44.179334: step: 682/466, loss: 0.004497538786381483
2023-01-22 14:08:44.850522: step: 684/466, loss: 0.0072309295646846294
2023-01-22 14:08:45.494847: step: 686/466, loss: 0.000592927448451519
2023-01-22 14:08:46.103022: step: 688/466, loss: 0.0049162693321704865
2023-01-22 14:08:46.733931: step: 690/466, loss: 0.03505634889006615
2023-01-22 14:08:47.334912: step: 692/466, loss: 0.004243789240717888
2023-01-22 14:08:47.967454: step: 694/466, loss: 0.0038029218558222055
2023-01-22 14:08:48.591956: step: 696/466, loss: 0.3729206919670105
2023-01-22 14:08:49.214885: step: 698/466, loss: 0.002357631688937545
2023-01-22 14:08:49.803874: step: 700/466, loss: 0.005631424952298403
2023-01-22 14:08:50.428918: step: 702/466, loss: 0.001534263021312654
2023-01-22 14:08:51.043348: step: 704/466, loss: 0.027184147387742996
2023-01-22 14:08:51.602123: step: 706/466, loss: 0.00972423143684864
2023-01-22 14:08:52.173306: step: 708/466, loss: 0.0018614258151501417
2023-01-22 14:08:52.820329: step: 710/466, loss: 0.014886019751429558
2023-01-22 14:08:53.436265: step: 712/466, loss: 0.0006989394314587116
2023-01-22 14:08:54.032911: step: 714/466, loss: 0.08167250454425812
2023-01-22 14:08:54.641766: step: 716/466, loss: 0.005497378297150135
2023-01-22 14:08:55.299235: step: 718/466, loss: 0.021845893934369087
2023-01-22 14:08:55.923845: step: 720/466, loss: 0.0031495019793510437
2023-01-22 14:08:56.541023: step: 722/466, loss: 0.003444172441959381
2023-01-22 14:08:57.252005: step: 724/466, loss: 0.10092519968748093
2023-01-22 14:08:57.853835: step: 726/466, loss: 0.018645109608769417
2023-01-22 14:08:58.460341: step: 728/466, loss: 0.010404352098703384
2023-01-22 14:08:59.170352: step: 730/466, loss: 0.11366147547960281
2023-01-22 14:08:59.880021: step: 732/466, loss: 0.009912433102726936
2023-01-22 14:09:00.493457: step: 734/466, loss: 0.0349004864692688
2023-01-22 14:09:01.106835: step: 736/466, loss: 0.001815163530409336
2023-01-22 14:09:01.695912: step: 738/466, loss: 0.004219917114824057
2023-01-22 14:09:02.320961: step: 740/466, loss: 0.08490953594446182
2023-01-22 14:09:02.913832: step: 742/466, loss: 0.0011273091658949852
2023-01-22 14:09:03.542492: step: 744/466, loss: 0.004046041984111071
2023-01-22 14:09:04.160320: step: 746/466, loss: 0.0011817996855825186
2023-01-22 14:09:04.776011: step: 748/466, loss: 0.01741914264857769
2023-01-22 14:09:05.417381: step: 750/466, loss: 5.113750012242235e-05
2023-01-22 14:09:06.013186: step: 752/466, loss: 0.0561121366918087
2023-01-22 14:09:06.589054: step: 754/466, loss: 0.0012292331084609032
2023-01-22 14:09:07.197410: step: 756/466, loss: 0.0034764278680086136
2023-01-22 14:09:07.812525: step: 758/466, loss: 0.0012881318107247353
2023-01-22 14:09:08.531773: step: 760/466, loss: 0.0566745400428772
2023-01-22 14:09:09.172174: step: 762/466, loss: 0.014587437734007835
2023-01-22 14:09:09.799739: step: 764/466, loss: 0.005054814741015434
2023-01-22 14:09:10.365114: step: 766/466, loss: 0.0002718236646614969
2023-01-22 14:09:11.036367: step: 768/466, loss: 9.154299914371222e-05
2023-01-22 14:09:11.661551: step: 770/466, loss: 0.014392387121915817
2023-01-22 14:09:12.341511: step: 772/466, loss: 0.03583939000964165
2023-01-22 14:09:12.955514: step: 774/466, loss: 0.0008179117576219141
2023-01-22 14:09:13.611855: step: 776/466, loss: 0.0015706622507423162
2023-01-22 14:09:14.218628: step: 778/466, loss: 0.0004586191789712757
2023-01-22 14:09:14.792151: step: 780/466, loss: 0.0033738790079951286
2023-01-22 14:09:15.469469: step: 782/466, loss: 0.00022474599245470017
2023-01-22 14:09:16.058836: step: 784/466, loss: 0.04620259627699852
2023-01-22 14:09:16.643405: step: 786/466, loss: 0.0006574672879651189
2023-01-22 14:09:17.304941: step: 788/466, loss: 0.007191939279437065
2023-01-22 14:09:17.942748: step: 790/466, loss: 0.12468365579843521
2023-01-22 14:09:18.515780: step: 792/466, loss: 0.08092932403087616
2023-01-22 14:09:19.105115: step: 794/466, loss: 0.13907642662525177
2023-01-22 14:09:19.727774: step: 796/466, loss: 0.06445979326963425
2023-01-22 14:09:20.341093: step: 798/466, loss: 0.00036164215998724103
2023-01-22 14:09:20.984375: step: 800/466, loss: 0.0062723662704229355
2023-01-22 14:09:21.622198: step: 802/466, loss: 0.21664755046367645
2023-01-22 14:09:22.217136: step: 804/466, loss: 0.00553386053070426
2023-01-22 14:09:22.834009: step: 806/466, loss: 0.004248048644512892
2023-01-22 14:09:23.457748: step: 808/466, loss: 0.00211940030567348
2023-01-22 14:09:24.073374: step: 810/466, loss: 0.049605898559093475
2023-01-22 14:09:24.658522: step: 812/466, loss: 0.917293906211853
2023-01-22 14:09:25.232128: step: 814/466, loss: 0.0008797876071184874
2023-01-22 14:09:25.872061: step: 816/466, loss: 0.02780606597661972
2023-01-22 14:09:26.502196: step: 818/466, loss: 0.06368755549192429
2023-01-22 14:09:27.174300: step: 820/466, loss: 0.03188211843371391
2023-01-22 14:09:27.893579: step: 822/466, loss: 0.02889896184206009
2023-01-22 14:09:28.451910: step: 824/466, loss: 0.020797166973352432
2023-01-22 14:09:29.062660: step: 826/466, loss: 0.0011842402163892984
2023-01-22 14:09:29.677504: step: 828/466, loss: 0.005489708855748177
2023-01-22 14:09:30.295239: step: 830/466, loss: 0.019772449508309364
2023-01-22 14:09:30.955806: step: 832/466, loss: 0.03640015423297882
2023-01-22 14:09:31.559403: step: 834/466, loss: 0.0011282063787803054
2023-01-22 14:09:32.243022: step: 836/466, loss: 0.0023520293179899454
2023-01-22 14:09:32.883730: step: 838/466, loss: 0.020443731918931007
2023-01-22 14:09:33.432861: step: 840/466, loss: 0.000996671849861741
2023-01-22 14:09:34.082960: step: 842/466, loss: 0.02468843385577202
2023-01-22 14:09:34.828344: step: 844/466, loss: 0.0001617139350855723
2023-01-22 14:09:35.454105: step: 846/466, loss: 0.010490602813661098
2023-01-22 14:09:36.047445: step: 848/466, loss: 0.000732666056137532
2023-01-22 14:09:36.607479: step: 850/466, loss: 0.02549736574292183
2023-01-22 14:09:37.221426: step: 852/466, loss: 0.06734530627727509
2023-01-22 14:09:37.846860: step: 854/466, loss: 0.015717370435595512
2023-01-22 14:09:38.501340: step: 856/466, loss: 0.05792534723877907
2023-01-22 14:09:39.085944: step: 858/466, loss: 0.000274793739663437
2023-01-22 14:09:39.671133: step: 860/466, loss: 0.001243875245563686
2023-01-22 14:09:40.327492: step: 862/466, loss: 0.0016297302208840847
2023-01-22 14:09:40.921801: step: 864/466, loss: 0.017735572531819344
2023-01-22 14:09:41.531880: step: 866/466, loss: 0.00045983216841705143
2023-01-22 14:09:42.184804: step: 868/466, loss: 0.0008117897668853402
2023-01-22 14:09:42.791260: step: 870/466, loss: 0.005976210348308086
2023-01-22 14:09:43.384129: step: 872/466, loss: 0.034743718802928925
2023-01-22 14:09:44.027787: step: 874/466, loss: 0.002306940034031868
2023-01-22 14:09:44.606160: step: 876/466, loss: 0.004866317845880985
2023-01-22 14:09:45.207333: step: 878/466, loss: 0.005829141475260258
2023-01-22 14:09:45.814064: step: 880/466, loss: 5.3960906370775774e-05
2023-01-22 14:09:46.376356: step: 882/466, loss: 0.03501942381262779
2023-01-22 14:09:47.011492: step: 884/466, loss: 0.00935305655002594
2023-01-22 14:09:47.605649: step: 886/466, loss: 0.001111685298383236
2023-01-22 14:09:48.263425: step: 888/466, loss: 0.009631190448999405
2023-01-22 14:09:48.823838: step: 890/466, loss: 0.00010575946362223476
2023-01-22 14:09:49.425232: step: 892/466, loss: 0.0009285346022807062
2023-01-22 14:09:50.022978: step: 894/466, loss: 0.3155493438243866
2023-01-22 14:09:50.580402: step: 896/466, loss: 0.0023564333096146584
2023-01-22 14:09:51.198747: step: 898/466, loss: 0.011746902018785477
2023-01-22 14:09:51.831060: step: 900/466, loss: 0.003073877189308405
2023-01-22 14:09:52.428197: step: 902/466, loss: 0.07641258835792542
2023-01-22 14:09:53.051412: step: 904/466, loss: 0.015829866752028465
2023-01-22 14:09:53.662027: step: 906/466, loss: 0.007194718345999718
2023-01-22 14:09:54.301010: step: 908/466, loss: 0.0010927760740742087
2023-01-22 14:09:54.886231: step: 910/466, loss: 0.00888837780803442
2023-01-22 14:09:55.501066: step: 912/466, loss: 0.12945696711540222
2023-01-22 14:09:56.169260: step: 914/466, loss: 0.002949284855276346
2023-01-22 14:09:56.766299: step: 916/466, loss: 0.01856701448559761
2023-01-22 14:09:57.377579: step: 918/466, loss: 0.010092062875628471
2023-01-22 14:09:57.961222: step: 920/466, loss: 0.0028126072138547897
2023-01-22 14:09:58.600217: step: 922/466, loss: 0.012266576290130615
2023-01-22 14:09:59.232416: step: 924/466, loss: 0.00044847832759842277
2023-01-22 14:09:59.826035: step: 926/466, loss: 0.012883850373327732
2023-01-22 14:10:00.433392: step: 928/466, loss: 0.056210801005363464
2023-01-22 14:10:01.015937: step: 930/466, loss: 0.05528941750526428
2023-01-22 14:10:01.680934: step: 932/466, loss: 0.008800864219665527
==================================================
Loss: 0.027
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32351171954269736, 'r': 0.3370169526165861, 'f1': 0.3301262714292581}, 'combined': 0.24325093684261123, 'epoch': 36}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.31837307552031624, 'r': 0.3083070794559883, 'f1': 0.3132592353903433}, 'combined': 0.19615297916965424, 'epoch': 36}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30838877782649976, 'r': 0.34759570024466957, 'f1': 0.32682057810694176}, 'combined': 0.24081516281564128, 'epoch': 36}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.328634659328329, 'r': 0.32181282073216333, 'f1': 0.3251879665948354}, 'combined': 0.2015249370446867, 'epoch': 36}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27611332120055926, 'r': 0.3363657537206054, 'f1': 0.303275880600101}, 'combined': 0.22346643833691654, 'epoch': 36}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3228103705210194, 'r': 0.3105517488556642, 'f1': 0.3165624278657739}, 'combined': 0.20999685808917673, 'epoch': 36}
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': 36}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27702702702702703, 'r': 0.44565217391304346, 'f1': 0.3416666666666667}, 'combined': 0.17083333333333334, 'epoch': 36}
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': 36}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 14:12:38.838169: step: 2/466, loss: 0.011019522324204445
2023-01-22 14:12:39.433917: step: 4/466, loss: 0.010127645917236805
2023-01-22 14:12:40.061202: step: 6/466, loss: 0.0007951930165290833
2023-01-22 14:12:40.696915: step: 8/466, loss: 0.01275271363556385
2023-01-22 14:12:41.257922: step: 10/466, loss: 0.0066956644877791405
2023-01-22 14:12:41.888022: step: 12/466, loss: 0.06437095999717712
2023-01-22 14:12:42.466568: step: 14/466, loss: 0.05077988654375076
2023-01-22 14:12:43.045633: step: 16/466, loss: 0.04438474774360657
2023-01-22 14:12:43.635873: step: 18/466, loss: 0.001817838754504919
2023-01-22 14:12:44.209785: step: 20/466, loss: 0.009348759427666664
2023-01-22 14:12:44.893473: step: 22/466, loss: 0.006619395688176155
2023-01-22 14:12:45.478603: step: 24/466, loss: 0.00030899926787242293
2023-01-22 14:12:46.126108: step: 26/466, loss: 0.003811010392382741
2023-01-22 14:12:46.821956: step: 28/466, loss: 0.05893457308411598
2023-01-22 14:12:47.392673: step: 30/466, loss: 0.014599674381315708
2023-01-22 14:12:48.057666: step: 32/466, loss: 0.4832135736942291
2023-01-22 14:12:48.605161: step: 34/466, loss: 0.0015102779725566506
2023-01-22 14:12:49.178989: step: 36/466, loss: 0.00190758949611336
2023-01-22 14:12:49.798645: step: 38/466, loss: 0.030581766739487648
2023-01-22 14:12:50.444353: step: 40/466, loss: 0.011711365543305874
2023-01-22 14:12:51.016930: step: 42/466, loss: 0.0027332899626344442
2023-01-22 14:12:51.608224: step: 44/466, loss: 0.0058179195038974285
2023-01-22 14:12:52.182856: step: 46/466, loss: 0.03327443450689316
2023-01-22 14:12:52.903712: step: 48/466, loss: 0.005963337607681751
2023-01-22 14:12:53.515828: step: 50/466, loss: 0.00114289834164083
2023-01-22 14:12:54.176780: step: 52/466, loss: 0.0360976941883564
2023-01-22 14:12:54.847083: step: 54/466, loss: 0.0014520614640787244
2023-01-22 14:12:55.475668: step: 56/466, loss: 0.008371063508093357
2023-01-22 14:12:55.993709: step: 58/466, loss: 0.0008297368767671287
2023-01-22 14:12:56.588690: step: 60/466, loss: 0.0015597924357280135
2023-01-22 14:12:57.204241: step: 62/466, loss: 0.0013233617646619678
2023-01-22 14:12:57.918588: step: 64/466, loss: 0.017565947026014328
2023-01-22 14:12:58.584003: step: 66/466, loss: 0.017326395958662033
2023-01-22 14:12:59.170259: step: 68/466, loss: 0.013437674380838871
2023-01-22 14:12:59.846276: step: 70/466, loss: 0.0070917424745857716
2023-01-22 14:13:00.444806: step: 72/466, loss: 0.07519196718931198
2023-01-22 14:13:01.113063: step: 74/466, loss: 0.0027385542634874582
2023-01-22 14:13:01.766692: step: 76/466, loss: 0.021933214738965034
2023-01-22 14:13:02.452798: step: 78/466, loss: 0.01939769834280014
2023-01-22 14:13:03.094468: step: 80/466, loss: 0.02084903046488762
2023-01-22 14:13:03.675261: step: 82/466, loss: 0.0013701777206733823
2023-01-22 14:13:04.321766: step: 84/466, loss: 0.02175498567521572
2023-01-22 14:13:04.993163: step: 86/466, loss: 0.01719932071864605
2023-01-22 14:13:05.577209: step: 88/466, loss: 0.0009665418183431029
2023-01-22 14:13:06.163811: step: 90/466, loss: 0.0013758244458585978
2023-01-22 14:13:06.779870: step: 92/466, loss: 0.02238643541932106
2023-01-22 14:13:07.452253: step: 94/466, loss: 0.0037119691260159016
2023-01-22 14:13:08.092101: step: 96/466, loss: 0.006917356047779322
2023-01-22 14:13:08.697501: step: 98/466, loss: 0.03723670542240143
2023-01-22 14:13:09.286605: step: 100/466, loss: 0.0020379177294671535
2023-01-22 14:13:10.009568: step: 102/466, loss: 0.020293638110160828
2023-01-22 14:13:10.631497: step: 104/466, loss: 0.12235407531261444
2023-01-22 14:13:11.266670: step: 106/466, loss: 0.033439889550209045
2023-01-22 14:13:11.910936: step: 108/466, loss: 0.001259556389413774
2023-01-22 14:13:12.515324: step: 110/466, loss: 0.0005565416067838669
2023-01-22 14:13:13.275188: step: 112/466, loss: 0.047064412385225296
2023-01-22 14:13:13.973231: step: 114/466, loss: 0.02563040517270565
2023-01-22 14:13:14.618672: step: 116/466, loss: 0.09876726567745209
2023-01-22 14:13:15.205209: step: 118/466, loss: 0.001955243293195963
2023-01-22 14:13:15.788502: step: 120/466, loss: 0.009090467356145382
2023-01-22 14:13:16.397513: step: 122/466, loss: 8.463918493362144e-05
2023-01-22 14:13:17.060179: step: 124/466, loss: 0.010689635761082172
2023-01-22 14:13:17.741167: step: 126/466, loss: 0.049118880182504654
2023-01-22 14:13:18.411785: step: 128/466, loss: 0.06984400749206543
2023-01-22 14:13:19.103311: step: 130/466, loss: 0.0016691607888787985
2023-01-22 14:13:19.760074: step: 132/466, loss: 0.0015183526556938887
2023-01-22 14:13:20.330406: step: 134/466, loss: 0.00012503209291025996
2023-01-22 14:13:20.985152: step: 136/466, loss: 0.15007728338241577
2023-01-22 14:13:21.592173: step: 138/466, loss: 0.01478609349578619
2023-01-22 14:13:22.205768: step: 140/466, loss: 0.00026948051527142525
2023-01-22 14:13:22.832180: step: 142/466, loss: 0.015629736706614494
2023-01-22 14:13:23.444723: step: 144/466, loss: 0.005343706347048283
2023-01-22 14:13:24.095524: step: 146/466, loss: 0.000775020569562912
2023-01-22 14:13:24.698387: step: 148/466, loss: 0.0014441086677834392
2023-01-22 14:13:25.331598: step: 150/466, loss: 0.019887277856469154
2023-01-22 14:13:25.882771: step: 152/466, loss: 0.005369046237319708
2023-01-22 14:13:26.539939: step: 154/466, loss: 0.02766246907413006
2023-01-22 14:13:27.168041: step: 156/466, loss: 0.0004748774226754904
2023-01-22 14:13:27.797472: step: 158/466, loss: 0.028046274557709694
2023-01-22 14:13:28.416884: step: 160/466, loss: 0.003485351335257292
2023-01-22 14:13:28.999841: step: 162/466, loss: 0.00030218041501939297
2023-01-22 14:13:29.686841: step: 164/466, loss: 0.00042470174957998097
2023-01-22 14:13:30.284458: step: 166/466, loss: 0.04308995604515076
2023-01-22 14:13:31.002124: step: 168/466, loss: 0.009484400041401386
2023-01-22 14:13:31.602024: step: 170/466, loss: 0.0004260554851498455
2023-01-22 14:13:32.179316: step: 172/466, loss: 0.009698664769530296
2023-01-22 14:13:32.806830: step: 174/466, loss: 0.0035012245643883944
2023-01-22 14:13:33.485635: step: 176/466, loss: 0.01406619232147932
2023-01-22 14:13:34.057288: step: 178/466, loss: 0.0095423748716712
2023-01-22 14:13:34.664449: step: 180/466, loss: 0.0014280936447903514
2023-01-22 14:13:35.234715: step: 182/466, loss: 0.001411979435943067
2023-01-22 14:13:35.836491: step: 184/466, loss: 3.411167926969938e-05
2023-01-22 14:13:36.427302: step: 186/466, loss: 0.0007187300943769515
2023-01-22 14:13:37.061004: step: 188/466, loss: 0.007806873414665461
2023-01-22 14:13:37.675220: step: 190/466, loss: 0.013449162244796753
2023-01-22 14:13:38.324401: step: 192/466, loss: 0.0009487065253779292
2023-01-22 14:13:38.987323: step: 194/466, loss: 0.022043446078896523
2023-01-22 14:13:39.574513: step: 196/466, loss: 0.002760909032076597
2023-01-22 14:13:40.165620: step: 198/466, loss: 0.0002739167248364538
2023-01-22 14:13:40.787789: step: 200/466, loss: 0.0047027189284563065
2023-01-22 14:13:41.344520: step: 202/466, loss: 0.03824473172426224
2023-01-22 14:13:41.956963: step: 204/466, loss: 0.003228937741369009
2023-01-22 14:13:42.629318: step: 206/466, loss: 0.0475756898522377
2023-01-22 14:13:43.198875: step: 208/466, loss: 0.007542956620454788
2023-01-22 14:13:43.827593: step: 210/466, loss: 0.01231348980218172
2023-01-22 14:13:44.395524: step: 212/466, loss: 0.018550366163253784
2023-01-22 14:13:45.032869: step: 214/466, loss: 0.0036698374897241592
2023-01-22 14:13:45.693709: step: 216/466, loss: 0.033354442566633224
2023-01-22 14:13:46.312579: step: 218/466, loss: 6.645784014835954e-05
2023-01-22 14:13:46.940829: step: 220/466, loss: 0.020804526284337044
2023-01-22 14:13:47.608278: step: 222/466, loss: 0.01046005729585886
2023-01-22 14:13:48.249546: step: 224/466, loss: 0.0008722355705685914
2023-01-22 14:13:48.827104: step: 226/466, loss: 0.018724089488387108
2023-01-22 14:13:49.439178: step: 228/466, loss: 0.016693826764822006
2023-01-22 14:13:50.107313: step: 230/466, loss: 0.0009288593428209424
2023-01-22 14:13:50.699210: step: 232/466, loss: 0.0007292639347724617
2023-01-22 14:13:51.272583: step: 234/466, loss: 0.0008308116812258959
2023-01-22 14:13:51.861546: step: 236/466, loss: 0.1941482573747635
2023-01-22 14:13:52.473621: step: 238/466, loss: 0.0003392081707715988
2023-01-22 14:13:53.138776: step: 240/466, loss: 0.010306607000529766
2023-01-22 14:13:53.853691: step: 242/466, loss: 0.0009510318632237613
2023-01-22 14:13:54.424525: step: 244/466, loss: 0.009845195338129997
2023-01-22 14:13:55.072698: step: 246/466, loss: 0.006684688851237297
2023-01-22 14:13:55.711972: step: 248/466, loss: 0.01415190938860178
2023-01-22 14:13:56.385675: step: 250/466, loss: 0.0021747788414359093
2023-01-22 14:13:57.013975: step: 252/466, loss: 0.10681437700986862
2023-01-22 14:13:57.632963: step: 254/466, loss: 0.003000908065587282
2023-01-22 14:13:58.250247: step: 256/466, loss: 0.02510448358952999
2023-01-22 14:13:58.919981: step: 258/466, loss: 0.015247062779963017
2023-01-22 14:13:59.609631: step: 260/466, loss: 0.04318120703101158
2023-01-22 14:14:00.253091: step: 262/466, loss: 0.0001173671189462766
2023-01-22 14:14:00.882448: step: 264/466, loss: 0.0623827762901783
2023-01-22 14:14:01.508543: step: 266/466, loss: 0.0010009552352130413
2023-01-22 14:14:02.173755: step: 268/466, loss: 0.03292268142104149
2023-01-22 14:14:02.836539: step: 270/466, loss: 0.16150562465190887
2023-01-22 14:14:03.430317: step: 272/466, loss: 0.09163973480463028
2023-01-22 14:14:04.058934: step: 274/466, loss: 0.01140571665018797
2023-01-22 14:14:04.758476: step: 276/466, loss: 0.0015015015378594398
2023-01-22 14:14:05.334310: step: 278/466, loss: 2.4360746465390548e-05
2023-01-22 14:14:05.928918: step: 280/466, loss: 0.005441330373287201
2023-01-22 14:14:06.482037: step: 282/466, loss: 0.034476932138204575
2023-01-22 14:14:07.203891: step: 284/466, loss: 0.014575645327568054
2023-01-22 14:14:07.782023: step: 286/466, loss: 0.0428362712264061
2023-01-22 14:14:08.394412: step: 288/466, loss: 1.2249766768945847e-05
2023-01-22 14:14:08.989532: step: 290/466, loss: 0.0012035742402076721
2023-01-22 14:14:09.617253: step: 292/466, loss: 0.03102664276957512
2023-01-22 14:14:10.211397: step: 294/466, loss: 0.006781739182770252
2023-01-22 14:14:10.832404: step: 296/466, loss: 0.0010324480244889855
2023-01-22 14:14:11.510694: step: 298/466, loss: 0.009565313346683979
2023-01-22 14:14:12.158288: step: 300/466, loss: 0.012004152871668339
2023-01-22 14:14:12.828076: step: 302/466, loss: 0.0013970371801406145
2023-01-22 14:14:13.453932: step: 304/466, loss: 0.001083197072148323
2023-01-22 14:14:14.096130: step: 306/466, loss: 0.0037915578577667475
2023-01-22 14:14:14.726102: step: 308/466, loss: 0.0009314219933003187
2023-01-22 14:14:15.332221: step: 310/466, loss: 0.1204252764582634
2023-01-22 14:14:16.006516: step: 312/466, loss: 0.006242868024855852
2023-01-22 14:14:16.646587: step: 314/466, loss: 0.00015747385623399168
2023-01-22 14:14:17.284485: step: 316/466, loss: 0.0005098479450680315
2023-01-22 14:14:17.876000: step: 318/466, loss: 0.012559473514556885
2023-01-22 14:14:18.558846: step: 320/466, loss: 0.0019534605089575052
2023-01-22 14:14:19.201345: step: 322/466, loss: 0.0011656004935503006
2023-01-22 14:14:19.814310: step: 324/466, loss: 0.005038025323301554
2023-01-22 14:14:20.391121: step: 326/466, loss: 0.011869724839925766
2023-01-22 14:14:21.038018: step: 328/466, loss: 0.03267310932278633
2023-01-22 14:14:21.623933: step: 330/466, loss: 0.0036926791071891785
2023-01-22 14:14:22.207828: step: 332/466, loss: 0.029556231573224068
2023-01-22 14:14:22.795866: step: 334/466, loss: 0.010744617320597172
2023-01-22 14:14:23.397400: step: 336/466, loss: 0.0029276181012392044
2023-01-22 14:14:24.051588: step: 338/466, loss: 0.04652019962668419
2023-01-22 14:14:24.646336: step: 340/466, loss: 0.0017216216074302793
2023-01-22 14:14:25.319692: step: 342/466, loss: 1.7856009435490705e-05
2023-01-22 14:14:25.995514: step: 344/466, loss: 0.003602897049859166
2023-01-22 14:14:26.566018: step: 346/466, loss: 0.008376662619411945
2023-01-22 14:14:27.166373: step: 348/466, loss: 0.05960991233587265
2023-01-22 14:14:27.812262: step: 350/466, loss: 0.0006441866280511022
2023-01-22 14:14:28.427687: step: 352/466, loss: 0.0007531185983680189
2023-01-22 14:14:29.056276: step: 354/466, loss: 0.004106097389012575
2023-01-22 14:14:29.694448: step: 356/466, loss: 0.005356463138014078
2023-01-22 14:14:30.298434: step: 358/466, loss: 0.0008049256284721196
2023-01-22 14:14:30.893717: step: 360/466, loss: 0.029184794053435326
2023-01-22 14:14:31.536882: step: 362/466, loss: 0.007187245413661003
2023-01-22 14:14:32.238683: step: 364/466, loss: 0.002978815231472254
2023-01-22 14:14:32.835712: step: 366/466, loss: 0.01251143403351307
2023-01-22 14:14:33.448851: step: 368/466, loss: 0.018451590090990067
2023-01-22 14:14:34.037469: step: 370/466, loss: 0.0023503785487264395
2023-01-22 14:14:34.619451: step: 372/466, loss: 0.0005784441018477082
2023-01-22 14:14:35.233422: step: 374/466, loss: 0.00456195417791605
2023-01-22 14:14:35.919591: step: 376/466, loss: 0.003032136242836714
2023-01-22 14:14:36.443066: step: 378/466, loss: 0.0005832591559737921
2023-01-22 14:14:37.069252: step: 380/466, loss: 0.03324274718761444
2023-01-22 14:14:37.666912: step: 382/466, loss: 0.0004480695934034884
2023-01-22 14:14:38.321198: step: 384/466, loss: 0.0007840922335162759
2023-01-22 14:14:38.890095: step: 386/466, loss: 0.004485865589231253
2023-01-22 14:14:39.499962: step: 388/466, loss: 0.0025899396277964115
2023-01-22 14:14:40.208481: step: 390/466, loss: 0.01471379678696394
2023-01-22 14:14:40.779713: step: 392/466, loss: 0.04674030467867851
2023-01-22 14:14:41.330870: step: 394/466, loss: 0.0004218451213091612
2023-01-22 14:14:41.930412: step: 396/466, loss: 0.0010176504729315639
2023-01-22 14:14:42.497815: step: 398/466, loss: 0.01860765554010868
2023-01-22 14:14:43.202580: step: 400/466, loss: 0.006526969838887453
2023-01-22 14:14:43.877746: step: 402/466, loss: 0.016039496287703514
2023-01-22 14:14:44.509610: step: 404/466, loss: 0.00013114621106069535
2023-01-22 14:14:45.062233: step: 406/466, loss: 0.003917271737009287
2023-01-22 14:14:45.779143: step: 408/466, loss: 0.826931893825531
2023-01-22 14:14:46.468859: step: 410/466, loss: 0.011356177739799023
2023-01-22 14:14:47.066797: step: 412/466, loss: 0.07401003688573837
2023-01-22 14:14:47.613479: step: 414/466, loss: 0.015200392343103886
2023-01-22 14:14:48.266129: step: 416/466, loss: 0.0029499316588044167
2023-01-22 14:14:48.915294: step: 418/466, loss: 0.03140866756439209
2023-01-22 14:14:49.577108: step: 420/466, loss: 7.102837844286114e-05
2023-01-22 14:14:50.166488: step: 422/466, loss: 0.04962131008505821
2023-01-22 14:14:50.742835: step: 424/466, loss: 0.01557162031531334
2023-01-22 14:14:51.363805: step: 426/466, loss: 0.020801618695259094
2023-01-22 14:14:51.941190: step: 428/466, loss: 0.00034787176991812885
2023-01-22 14:14:52.537336: step: 430/466, loss: 0.001129518961533904
2023-01-22 14:14:53.084284: step: 432/466, loss: 0.00616582902148366
2023-01-22 14:14:53.690755: step: 434/466, loss: 0.055054135620594025
2023-01-22 14:14:54.299053: step: 436/466, loss: 0.00042150524677708745
2023-01-22 14:14:54.931676: step: 438/466, loss: 0.0036059392150491476
2023-01-22 14:14:55.526233: step: 440/466, loss: 0.00019929753034375608
2023-01-22 14:14:56.100643: step: 442/466, loss: 0.006033843848854303
2023-01-22 14:14:56.763936: step: 444/466, loss: 3.503536936477758e-05
2023-01-22 14:14:57.338086: step: 446/466, loss: 0.00111696170642972
2023-01-22 14:14:57.949335: step: 448/466, loss: 0.022110553458333015
2023-01-22 14:14:58.549168: step: 450/466, loss: 0.00023391265131067485
2023-01-22 14:14:59.208143: step: 452/466, loss: 0.02570257894694805
2023-01-22 14:14:59.843113: step: 454/466, loss: 0.08661607652902603
2023-01-22 14:15:00.478948: step: 456/466, loss: 4.477473703445867e-05
2023-01-22 14:15:01.061653: step: 458/466, loss: 0.002013164572417736
2023-01-22 14:15:01.654552: step: 460/466, loss: 0.004852669779211283
2023-01-22 14:15:02.233817: step: 462/466, loss: 0.0012019069399684668
2023-01-22 14:15:02.964092: step: 464/466, loss: 0.009157421998679638
2023-01-22 14:15:03.543565: step: 466/466, loss: 0.2808040380477905
2023-01-22 14:15:04.143866: step: 468/466, loss: 0.003522509476169944
2023-01-22 14:15:04.806251: step: 470/466, loss: 0.016518112272024155
2023-01-22 14:15:05.455557: step: 472/466, loss: 0.0008490536129102111
2023-01-22 14:15:06.135426: step: 474/466, loss: 0.02368561364710331
2023-01-22 14:15:06.833035: step: 476/466, loss: 0.002999295713379979
2023-01-22 14:15:07.501317: step: 478/466, loss: 0.7123193740844727
2023-01-22 14:15:08.129740: step: 480/466, loss: 0.04895234480500221
2023-01-22 14:15:08.686546: step: 482/466, loss: 0.00048576542758382857
2023-01-22 14:15:09.274151: step: 484/466, loss: 0.021133853122591972
2023-01-22 14:15:09.873017: step: 486/466, loss: 0.0035724611952900887
2023-01-22 14:15:10.495753: step: 488/466, loss: 0.003965089563280344
2023-01-22 14:15:11.158970: step: 490/466, loss: 0.0005103085422888398
2023-01-22 14:15:11.877191: step: 492/466, loss: 0.002834130311384797
2023-01-22 14:15:12.535672: step: 494/466, loss: 0.10848957300186157
2023-01-22 14:15:13.090213: step: 496/466, loss: 0.0019518728367984295
2023-01-22 14:15:13.656450: step: 498/466, loss: 0.09013953059911728
2023-01-22 14:15:14.300422: step: 500/466, loss: 0.002601301297545433
2023-01-22 14:15:14.955837: step: 502/466, loss: 3.179002305842005e-05
2023-01-22 14:15:15.557913: step: 504/466, loss: 0.030233832076191902
2023-01-22 14:15:16.167041: step: 506/466, loss: 0.00021096097771078348
2023-01-22 14:15:16.827395: step: 508/466, loss: 0.006912588141858578
2023-01-22 14:15:17.345474: step: 510/466, loss: 0.06605498492717743
2023-01-22 14:15:17.881537: step: 512/466, loss: 0.0012793607311323285
2023-01-22 14:15:18.604863: step: 514/466, loss: 0.01516756508499384
2023-01-22 14:15:19.196719: step: 516/466, loss: 0.005258440971374512
2023-01-22 14:15:19.797950: step: 518/466, loss: 0.031163925305008888
2023-01-22 14:15:20.424475: step: 520/466, loss: 0.047974832355976105
2023-01-22 14:15:21.031084: step: 522/466, loss: 0.005257150158286095
2023-01-22 14:15:21.590734: step: 524/466, loss: 0.007114611566066742
2023-01-22 14:15:22.177165: step: 526/466, loss: 0.014129843562841415
2023-01-22 14:15:22.805305: step: 528/466, loss: 0.05840504541993141
2023-01-22 14:15:23.357776: step: 530/466, loss: 0.000509614881593734
2023-01-22 14:15:23.947438: step: 532/466, loss: 0.005425469484180212
2023-01-22 14:15:24.505308: step: 534/466, loss: 0.0015449508791789412
2023-01-22 14:15:25.331484: step: 536/466, loss: 0.001625897828489542
2023-01-22 14:15:26.006906: step: 538/466, loss: 0.006065103225409985
2023-01-22 14:15:26.576186: step: 540/466, loss: 8.518200047546998e-05
2023-01-22 14:15:27.166945: step: 542/466, loss: 0.0006184268859215081
2023-01-22 14:15:27.818881: step: 544/466, loss: 0.030829263851046562
2023-01-22 14:15:28.548796: step: 546/466, loss: 0.07033118605613708
2023-01-22 14:15:29.185074: step: 548/466, loss: 0.014811261557042599
2023-01-22 14:15:29.826102: step: 550/466, loss: 0.07217790931463242
2023-01-22 14:15:30.404237: step: 552/466, loss: 0.00011854747572215274
2023-01-22 14:15:31.043405: step: 554/466, loss: 0.02122669667005539
2023-01-22 14:15:31.663977: step: 556/466, loss: 0.01861976832151413
2023-01-22 14:15:32.298935: step: 558/466, loss: 0.0003908296348527074
2023-01-22 14:15:32.889612: step: 560/466, loss: 0.1115989238023758
2023-01-22 14:15:33.489897: step: 562/466, loss: 0.1496153175830841
2023-01-22 14:15:34.099013: step: 564/466, loss: 0.004777440335601568
2023-01-22 14:15:34.702697: step: 566/466, loss: 0.007495975121855736
2023-01-22 14:15:35.349112: step: 568/466, loss: 0.029308144003152847
2023-01-22 14:15:36.011894: step: 570/466, loss: 0.004541173577308655
2023-01-22 14:15:36.562717: step: 572/466, loss: 0.004064922221004963
2023-01-22 14:15:37.159374: step: 574/466, loss: 0.001175748067907989
2023-01-22 14:15:37.859150: step: 576/466, loss: 0.0008852386381477118
2023-01-22 14:15:38.463456: step: 578/466, loss: 0.04126737266778946
2023-01-22 14:15:39.085763: step: 580/466, loss: 0.0035846279934048653
2023-01-22 14:15:39.768156: step: 582/466, loss: 0.2606767416000366
2023-01-22 14:15:40.369145: step: 584/466, loss: 0.0002340715000173077
2023-01-22 14:15:40.998115: step: 586/466, loss: 0.004101741127669811
2023-01-22 14:15:41.626318: step: 588/466, loss: 0.008464156650006771
2023-01-22 14:15:42.176915: step: 590/466, loss: 0.001931003644131124
2023-01-22 14:15:42.789152: step: 592/466, loss: 0.003803492523729801
2023-01-22 14:15:43.403549: step: 594/466, loss: 0.002909739501774311
2023-01-22 14:15:44.086838: step: 596/466, loss: 0.007848568260669708
2023-01-22 14:15:44.741492: step: 598/466, loss: 0.001027796184644103
2023-01-22 14:15:45.335788: step: 600/466, loss: 0.0002775905013550073
2023-01-22 14:15:45.946060: step: 602/466, loss: 0.002364953514188528
2023-01-22 14:15:46.580582: step: 604/466, loss: 0.008006014861166477
2023-01-22 14:15:47.197615: step: 606/466, loss: 0.014175712130963802
2023-01-22 14:15:47.871065: step: 608/466, loss: 0.03752944618463516
2023-01-22 14:15:48.455354: step: 610/466, loss: 0.02041816897690296
2023-01-22 14:15:49.067225: step: 612/466, loss: 0.018955394625663757
2023-01-22 14:15:49.658288: step: 614/466, loss: 0.004180672578513622
2023-01-22 14:15:50.293173: step: 616/466, loss: 0.007526230067014694
2023-01-22 14:15:50.853820: step: 618/466, loss: 0.013544775545597076
2023-01-22 14:15:51.476129: step: 620/466, loss: 0.0005253756535239518
2023-01-22 14:15:52.084317: step: 622/466, loss: 0.00041710224468261003
2023-01-22 14:15:52.655771: step: 624/466, loss: 0.0052870395593345165
2023-01-22 14:15:53.282916: step: 626/466, loss: 0.13957083225250244
2023-01-22 14:15:53.879491: step: 628/466, loss: 0.0020317896269261837
2023-01-22 14:15:54.618513: step: 630/466, loss: 0.004546259995549917
2023-01-22 14:15:55.203482: step: 632/466, loss: 0.006747208535671234
2023-01-22 14:15:55.805057: step: 634/466, loss: 0.00037356914253905416
2023-01-22 14:15:56.385786: step: 636/466, loss: 0.049915898591279984
2023-01-22 14:15:57.012690: step: 638/466, loss: 0.02618241123855114
2023-01-22 14:15:57.593039: step: 640/466, loss: 0.00983812939375639
2023-01-22 14:15:58.211671: step: 642/466, loss: 0.0003110206453129649
2023-01-22 14:15:58.809394: step: 644/466, loss: 0.017514945939183235
2023-01-22 14:15:59.409925: step: 646/466, loss: 0.015234136953949928
2023-01-22 14:16:00.025178: step: 648/466, loss: 0.016556590795516968
2023-01-22 14:16:00.646279: step: 650/466, loss: 0.0021507632918655872
2023-01-22 14:16:01.285071: step: 652/466, loss: 0.0331457257270813
2023-01-22 14:16:01.955017: step: 654/466, loss: 7.748071220703423e-05
2023-01-22 14:16:02.559734: step: 656/466, loss: 0.005226131994277239
2023-01-22 14:16:03.141325: step: 658/466, loss: 0.01206152606755495
2023-01-22 14:16:03.738276: step: 660/466, loss: 0.009711089543998241
2023-01-22 14:16:04.327859: step: 662/466, loss: 0.0005779156344942749
2023-01-22 14:16:04.937029: step: 664/466, loss: 0.05312402918934822
2023-01-22 14:16:05.577725: step: 666/466, loss: 0.0019117280608043075
2023-01-22 14:16:06.145935: step: 668/466, loss: 0.01204315759241581
2023-01-22 14:16:06.780623: step: 670/466, loss: 0.0220714770257473
2023-01-22 14:16:07.402803: step: 672/466, loss: 0.0005926095182076097
2023-01-22 14:16:07.973379: step: 674/466, loss: 0.005150275304913521
2023-01-22 14:16:08.584414: step: 676/466, loss: 0.00197270093485713
2023-01-22 14:16:09.176976: step: 678/466, loss: 0.020318780094385147
2023-01-22 14:16:09.776588: step: 680/466, loss: 0.11400794237852097
2023-01-22 14:16:10.344785: step: 682/466, loss: 0.00041246210457757115
2023-01-22 14:16:10.932795: step: 684/466, loss: 0.01166682131588459
2023-01-22 14:16:11.560674: step: 686/466, loss: 0.004297053907066584
2023-01-22 14:16:12.240536: step: 688/466, loss: 0.031819894909858704
2023-01-22 14:16:12.912680: step: 690/466, loss: 0.0027910592034459114
2023-01-22 14:16:13.459504: step: 692/466, loss: 0.020834175869822502
2023-01-22 14:16:14.040572: step: 694/466, loss: 0.008798377588391304
2023-01-22 14:16:14.662075: step: 696/466, loss: 0.023229394108057022
2023-01-22 14:16:15.296298: step: 698/466, loss: 0.1519005447626114
2023-01-22 14:16:15.895886: step: 700/466, loss: 0.0005471892072819173
2023-01-22 14:16:16.486350: step: 702/466, loss: 0.0010586096905171871
2023-01-22 14:16:17.155801: step: 704/466, loss: 0.013087703846395016
2023-01-22 14:16:17.700762: step: 706/466, loss: 0.013915506191551685
2023-01-22 14:16:18.327947: step: 708/466, loss: 0.0024498875718563795
2023-01-22 14:16:18.911475: step: 710/466, loss: 0.002289401600137353
2023-01-22 14:16:19.555575: step: 712/466, loss: 0.007158982567489147
2023-01-22 14:16:20.172304: step: 714/466, loss: 0.03404374420642853
2023-01-22 14:16:20.816256: step: 716/466, loss: 0.007108825258910656
2023-01-22 14:16:21.395982: step: 718/466, loss: 0.010414959862828255
2023-01-22 14:16:22.023648: step: 720/466, loss: 0.0224582739174366
2023-01-22 14:16:22.594667: step: 722/466, loss: 0.0011145860189571977
2023-01-22 14:16:23.142186: step: 724/466, loss: 0.0005832858732901514
2023-01-22 14:16:23.775234: step: 726/466, loss: 0.010251102037727833
2023-01-22 14:16:24.447405: step: 728/466, loss: 0.009993134997785091
2023-01-22 14:16:25.066459: step: 730/466, loss: 0.000616840086877346
2023-01-22 14:16:25.674267: step: 732/466, loss: 0.006950164679437876
2023-01-22 14:16:26.302847: step: 734/466, loss: 0.013368867337703705
2023-01-22 14:16:26.878454: step: 736/466, loss: 0.005068691913038492
2023-01-22 14:16:27.582607: step: 738/466, loss: 0.0001408860698575154
2023-01-22 14:16:28.218887: step: 740/466, loss: 0.003125702030956745
2023-01-22 14:16:28.818528: step: 742/466, loss: 0.000734903325792402
2023-01-22 14:16:29.517474: step: 744/466, loss: 0.03700494393706322
2023-01-22 14:16:30.178571: step: 746/466, loss: 0.0028334090020507574
2023-01-22 14:16:30.874356: step: 748/466, loss: 0.005490779411047697
2023-01-22 14:16:31.490246: step: 750/466, loss: 0.0191445704549551
2023-01-22 14:16:32.071558: step: 752/466, loss: 0.0021933047100901604
2023-01-22 14:16:32.682568: step: 754/466, loss: 0.06623340398073196
2023-01-22 14:16:33.346274: step: 756/466, loss: 1.1274349689483643
2023-01-22 14:16:34.032912: step: 758/466, loss: 0.00706103490665555
2023-01-22 14:16:34.598090: step: 760/466, loss: 0.00011960876145167276
2023-01-22 14:16:35.242887: step: 762/466, loss: 0.012318236753344536
2023-01-22 14:16:35.860449: step: 764/466, loss: 0.2550526559352875
2023-01-22 14:16:36.497696: step: 766/466, loss: 8.795595931587741e-05
2023-01-22 14:16:37.049851: step: 768/466, loss: 0.00039759004721418023
2023-01-22 14:16:37.658276: step: 770/466, loss: 9.025069448398426e-05
2023-01-22 14:16:38.261165: step: 772/466, loss: 8.084368164418265e-05
2023-01-22 14:16:38.828623: step: 774/466, loss: 0.007387692574411631
2023-01-22 14:16:39.464563: step: 776/466, loss: 0.0002266254450660199
2023-01-22 14:16:40.068859: step: 778/466, loss: 0.0748785138130188
2023-01-22 14:16:40.644168: step: 780/466, loss: 0.010603842325508595
2023-01-22 14:16:41.254436: step: 782/466, loss: 0.03986622393131256
2023-01-22 14:16:41.896480: step: 784/466, loss: 0.0015694086905568838
2023-01-22 14:16:42.545870: step: 786/466, loss: 0.002429869258776307
2023-01-22 14:16:43.243186: step: 788/466, loss: 0.017495468258857727
2023-01-22 14:16:43.872262: step: 790/466, loss: 0.008161415345966816
2023-01-22 14:16:44.507490: step: 792/466, loss: 0.004917403683066368
2023-01-22 14:16:45.093308: step: 794/466, loss: 0.01133313961327076
2023-01-22 14:16:45.854116: step: 796/466, loss: 0.002892041113227606
2023-01-22 14:16:46.426976: step: 798/466, loss: 0.00031576791661791503
2023-01-22 14:16:47.025225: step: 800/466, loss: 0.00044341786997392774
2023-01-22 14:16:47.645782: step: 802/466, loss: 0.004508330021053553
2023-01-22 14:16:48.296645: step: 804/466, loss: 0.05905351787805557
2023-01-22 14:16:48.904618: step: 806/466, loss: 0.14383766055107117
2023-01-22 14:16:49.533762: step: 808/466, loss: 0.04062948748469353
2023-01-22 14:16:50.196306: step: 810/466, loss: 0.011387858539819717
2023-01-22 14:16:50.851076: step: 812/466, loss: 0.004854270722717047
2023-01-22 14:16:51.559632: step: 814/466, loss: 0.0001678572007222101
2023-01-22 14:16:52.119507: step: 816/466, loss: 0.002151502761989832
2023-01-22 14:16:52.758915: step: 818/466, loss: 4.258429180481471e-05
2023-01-22 14:16:53.360326: step: 820/466, loss: 0.1596289724111557
2023-01-22 14:16:53.958299: step: 822/466, loss: 0.02567148394882679
2023-01-22 14:16:54.591644: step: 824/466, loss: 0.027583090588450432
2023-01-22 14:16:55.199019: step: 826/466, loss: 0.030280442908406258
2023-01-22 14:16:55.790535: step: 828/466, loss: 0.0019176894566044211
2023-01-22 14:16:56.421381: step: 830/466, loss: 0.019382530823349953
2023-01-22 14:16:57.067780: step: 832/466, loss: 0.06708116829395294
2023-01-22 14:16:57.657423: step: 834/466, loss: 0.002640919527038932
2023-01-22 14:16:58.227404: step: 836/466, loss: 0.007880817167460918
2023-01-22 14:16:58.880291: step: 838/466, loss: 0.06637432426214218
2023-01-22 14:16:59.539563: step: 840/466, loss: 0.016892267391085625
2023-01-22 14:17:00.098523: step: 842/466, loss: 5.45619914191775e-05
2023-01-22 14:17:00.669487: step: 844/466, loss: 0.0007705793250352144
2023-01-22 14:17:01.256260: step: 846/466, loss: 0.0003873187815770507
2023-01-22 14:17:01.849935: step: 848/466, loss: 0.0012421660358086228
2023-01-22 14:17:02.445281: step: 850/466, loss: 0.0006693482282571495
2023-01-22 14:17:03.029118: step: 852/466, loss: 0.0021642204374074936
2023-01-22 14:17:03.669341: step: 854/466, loss: 0.00042549276258796453
2023-01-22 14:17:04.313873: step: 856/466, loss: 0.0043931263498961926
2023-01-22 14:17:04.934469: step: 858/466, loss: 0.0002430929453112185
2023-01-22 14:17:05.620334: step: 860/466, loss: 0.00892496295273304
2023-01-22 14:17:06.273289: step: 862/466, loss: 0.02985687181353569
2023-01-22 14:17:06.895529: step: 864/466, loss: 0.001226606429554522
2023-01-22 14:17:07.484254: step: 866/466, loss: 0.0005107595934532583
2023-01-22 14:17:08.047895: step: 868/466, loss: 0.1805555671453476
2023-01-22 14:17:08.766052: step: 870/466, loss: 0.011593032628297806
2023-01-22 14:17:09.366530: step: 872/466, loss: 0.0036725210957229137
2023-01-22 14:17:09.992328: step: 874/466, loss: 0.0036835698410868645
2023-01-22 14:17:10.599570: step: 876/466, loss: 0.003917853347957134
2023-01-22 14:17:11.149459: step: 878/466, loss: 0.0009317730437032878
2023-01-22 14:17:11.799045: step: 880/466, loss: 0.008433650247752666
2023-01-22 14:17:12.432784: step: 882/466, loss: 0.0009968248195946217
2023-01-22 14:17:12.958452: step: 884/466, loss: 0.10775865614414215
2023-01-22 14:17:13.547158: step: 886/466, loss: 0.0008649419178254902
2023-01-22 14:17:14.237931: step: 888/466, loss: 0.0063049462623894215
2023-01-22 14:17:14.880733: step: 890/466, loss: 0.0001419674081262201
2023-01-22 14:17:15.507237: step: 892/466, loss: 9.720688103698194e-05
2023-01-22 14:17:16.211221: step: 894/466, loss: 0.009378932416439056
2023-01-22 14:17:16.863405: step: 896/466, loss: 0.21360918879508972
2023-01-22 14:17:17.449883: step: 898/466, loss: 0.0008198576397262514
2023-01-22 14:17:18.056055: step: 900/466, loss: 3.818368350039236e-05
2023-01-22 14:17:18.675678: step: 902/466, loss: 0.002505519660189748
2023-01-22 14:17:19.328779: step: 904/466, loss: 0.050724759697914124
2023-01-22 14:17:19.931625: step: 906/466, loss: 0.03639456257224083
2023-01-22 14:17:20.562595: step: 908/466, loss: 1.6460932493209839
2023-01-22 14:17:21.243453: step: 910/466, loss: 0.04788459837436676
2023-01-22 14:17:21.909430: step: 912/466, loss: 0.008800013922154903
2023-01-22 14:17:22.588925: step: 914/466, loss: 0.0014374033780768514
2023-01-22 14:17:23.215005: step: 916/466, loss: 0.008077157661318779
2023-01-22 14:17:23.839225: step: 918/466, loss: 0.09034464508295059
2023-01-22 14:17:24.487289: step: 920/466, loss: 0.008930986747145653
2023-01-22 14:17:25.113816: step: 922/466, loss: 0.006056064274162054
2023-01-22 14:17:25.832510: step: 924/466, loss: 0.00033832492772489786
2023-01-22 14:17:26.470614: step: 926/466, loss: 0.0006647157715633512
2023-01-22 14:17:27.046624: step: 928/466, loss: 0.0029178534168750048
2023-01-22 14:17:27.680936: step: 930/466, loss: 0.0412764772772789
2023-01-22 14:17:28.286716: step: 932/466, loss: 0.02187582291662693
==================================================
Loss: 0.030
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32912333754430295, 'r': 0.32787429262003615, 'f1': 0.32849762777710845}, 'combined': 0.2420508836252378, 'epoch': 37}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3328291166053046, 'r': 0.27820792704519154, 'f1': 0.3030772014667165}, 'combined': 0.18977731306794401, 'epoch': 37}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30781094699423317, 'r': 0.32825379926140236, 'f1': 0.3177038608094749}, 'combined': 0.23409758164908673, 'epoch': 37}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34120880820964355, 'r': 0.2910129275795245, 'f1': 0.3141181916786295}, 'combined': 0.19466479484309432, 'epoch': 37}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28286494615888186, 'r': 0.32687808768644977, 'f1': 0.3032830144555617}, 'combined': 0.22347169486199284, 'epoch': 37}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3345748352814891, 'r': 0.2813813655348386, 'f1': 0.3056812283091917}, 'combined': 0.20277863660114698, 'epoch': 37}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3, 'r': 0.3, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 37}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.37962962962962965, 'r': 0.44565217391304346, 'f1': 0.41000000000000003}, 'combined': 0.20500000000000002, 'epoch': 37}
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': 37}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 14:20:05.163266: step: 2/466, loss: 0.022437838837504387
2023-01-22 14:20:05.774778: step: 4/466, loss: 0.13200338184833527
2023-01-22 14:20:06.398863: step: 6/466, loss: 0.010720699094235897
2023-01-22 14:20:07.021362: step: 8/466, loss: 0.0032551377080380917
2023-01-22 14:20:07.638976: step: 10/466, loss: 0.0005900732357986271
2023-01-22 14:20:08.306985: step: 12/466, loss: 0.003145418828353286
2023-01-22 14:20:08.959158: step: 14/466, loss: 0.0015280803199857473
2023-01-22 14:20:09.552638: step: 16/466, loss: 0.01795143447816372
2023-01-22 14:20:10.202123: step: 18/466, loss: 0.004306386690586805
2023-01-22 14:20:10.845597: step: 20/466, loss: 0.07706570625305176
2023-01-22 14:20:11.473573: step: 22/466, loss: 0.005568062420934439
2023-01-22 14:20:12.087767: step: 24/466, loss: 0.00024192110868170857
2023-01-22 14:20:12.708333: step: 26/466, loss: 0.0006435669492930174
2023-01-22 14:20:13.327848: step: 28/466, loss: 0.006629817187786102
2023-01-22 14:20:13.880817: step: 30/466, loss: 4.5981073526490945e-06
2023-01-22 14:20:14.414751: step: 32/466, loss: 0.00011412185267545283
2023-01-22 14:20:15.034629: step: 34/466, loss: 0.002991331508383155
2023-01-22 14:20:15.656195: step: 36/466, loss: 0.03248078003525734
2023-01-22 14:20:16.376105: step: 38/466, loss: 0.9280694127082825
2023-01-22 14:20:17.075494: step: 40/466, loss: 0.18692031502723694
2023-01-22 14:20:17.661498: step: 42/466, loss: 0.005263492465019226
2023-01-22 14:20:18.324052: step: 44/466, loss: 0.002784058451652527
2023-01-22 14:20:19.047979: step: 46/466, loss: 0.023738479241728783
2023-01-22 14:20:19.653581: step: 48/466, loss: 0.0004294861573725939
2023-01-22 14:20:20.348335: step: 50/466, loss: 0.0001612896448932588
2023-01-22 14:20:20.980833: step: 52/466, loss: 0.013227762654423714
2023-01-22 14:20:21.582158: step: 54/466, loss: 0.0059240576811134815
2023-01-22 14:20:22.195741: step: 56/466, loss: 0.007520228624343872
2023-01-22 14:20:22.796878: step: 58/466, loss: 0.0002002977125812322
2023-01-22 14:20:23.454565: step: 60/466, loss: 0.010102560743689537
2023-01-22 14:20:24.093503: step: 62/466, loss: 0.0009014192037284374
2023-01-22 14:20:24.710186: step: 64/466, loss: 0.005567123647779226
2023-01-22 14:20:25.299570: step: 66/466, loss: 0.00010532901796977967
2023-01-22 14:20:25.971974: step: 68/466, loss: 0.0026699909940361977
2023-01-22 14:20:26.689440: step: 70/466, loss: 0.00039817256038077176
2023-01-22 14:20:27.347020: step: 72/466, loss: 0.011175579391419888
2023-01-22 14:20:28.046334: step: 74/466, loss: 0.030114492401480675
2023-01-22 14:20:28.649257: step: 76/466, loss: 0.1101958379149437
2023-01-22 14:20:29.217503: step: 78/466, loss: 0.005225814413279295
2023-01-22 14:20:29.861018: step: 80/466, loss: 0.0245907511562109
2023-01-22 14:20:30.541258: step: 82/466, loss: 0.08617166429758072
2023-01-22 14:20:31.152200: step: 84/466, loss: 0.004091610666364431
2023-01-22 14:20:31.805232: step: 86/466, loss: 0.3025188148021698
2023-01-22 14:20:32.412412: step: 88/466, loss: 0.0014836537884548306
2023-01-22 14:20:33.007790: step: 90/466, loss: 0.0003159225743729621
2023-01-22 14:20:33.644964: step: 92/466, loss: 0.001323531847447157
2023-01-22 14:20:34.221599: step: 94/466, loss: 0.000104486447526142
2023-01-22 14:20:34.782920: step: 96/466, loss: 0.07179936021566391
2023-01-22 14:20:35.381287: step: 98/466, loss: 0.005564398597925901
2023-01-22 14:20:36.018402: step: 100/466, loss: 0.008363309316337109
2023-01-22 14:20:36.645352: step: 102/466, loss: 0.00012066560884704813
2023-01-22 14:20:37.255743: step: 104/466, loss: 0.004050121642649174
2023-01-22 14:20:37.860189: step: 106/466, loss: 0.0018115936545655131
2023-01-22 14:20:38.479194: step: 108/466, loss: 0.009684362448751926
2023-01-22 14:20:39.078243: step: 110/466, loss: 0.0004107225395273417
2023-01-22 14:20:39.711730: step: 112/466, loss: 0.15530163049697876
2023-01-22 14:20:40.328286: step: 114/466, loss: 0.004585616756230593
2023-01-22 14:20:40.931326: step: 116/466, loss: 0.002014612779021263
2023-01-22 14:20:41.513410: step: 118/466, loss: 0.015289516188204288
2023-01-22 14:20:42.125499: step: 120/466, loss: 0.07194361090660095
2023-01-22 14:20:42.766765: step: 122/466, loss: 0.002642291598021984
2023-01-22 14:20:43.373067: step: 124/466, loss: 0.08866244554519653
2023-01-22 14:20:44.042094: step: 126/466, loss: 0.010965188033878803
2023-01-22 14:20:44.695464: step: 128/466, loss: 0.000287467148154974
2023-01-22 14:20:45.327982: step: 130/466, loss: 0.014270431362092495
2023-01-22 14:20:45.997436: step: 132/466, loss: 0.0008079251856543124
2023-01-22 14:20:46.616731: step: 134/466, loss: 0.002872289391234517
2023-01-22 14:20:47.235738: step: 136/466, loss: 0.005854931194335222
2023-01-22 14:20:47.843673: step: 138/466, loss: 0.016251269727945328
2023-01-22 14:20:48.432439: step: 140/466, loss: 0.05686492472887039
2023-01-22 14:20:49.010850: step: 142/466, loss: 0.0037327632308006287
2023-01-22 14:20:49.606270: step: 144/466, loss: 0.0008345603127963841
2023-01-22 14:20:50.190180: step: 146/466, loss: 4.008270479971543e-05
2023-01-22 14:20:50.824997: step: 148/466, loss: 0.00392695888876915
2023-01-22 14:20:51.459462: step: 150/466, loss: 0.030992215499281883
2023-01-22 14:20:52.089382: step: 152/466, loss: 0.02886170893907547
2023-01-22 14:20:52.692915: step: 154/466, loss: 0.0024528333451598883
2023-01-22 14:20:53.346483: step: 156/466, loss: 0.00909585040062666
2023-01-22 14:20:53.983210: step: 158/466, loss: 0.031976863741874695
2023-01-22 14:20:54.625971: step: 160/466, loss: 0.009366384707391262
2023-01-22 14:20:55.249315: step: 162/466, loss: 0.000469852500827983
2023-01-22 14:20:55.907804: step: 164/466, loss: 0.2418440282344818
2023-01-22 14:20:56.574886: step: 166/466, loss: 0.0012514491099864244
2023-01-22 14:20:57.252123: step: 168/466, loss: 0.03002353198826313
2023-01-22 14:20:57.866979: step: 170/466, loss: 0.0030836581718176603
2023-01-22 14:20:58.502227: step: 172/466, loss: 0.011341028846800327
2023-01-22 14:20:59.107902: step: 174/466, loss: 0.007660390343517065
2023-01-22 14:20:59.706904: step: 176/466, loss: 0.0029395518358796835
2023-01-22 14:21:00.330143: step: 178/466, loss: 0.004267183598130941
2023-01-22 14:21:00.925831: step: 180/466, loss: 0.00800000037997961
2023-01-22 14:21:01.527436: step: 182/466, loss: 0.8297370672225952
2023-01-22 14:21:02.210713: step: 184/466, loss: 0.006819949019700289
2023-01-22 14:21:02.837352: step: 186/466, loss: 0.05917951837182045
2023-01-22 14:21:03.519184: step: 188/466, loss: 0.008328716270625591
2023-01-22 14:21:04.092235: step: 190/466, loss: 5.350938954507001e-05
2023-01-22 14:21:04.730894: step: 192/466, loss: 0.0059956153854727745
2023-01-22 14:21:05.308069: step: 194/466, loss: 0.009970581158995628
2023-01-22 14:21:05.961606: step: 196/466, loss: 0.004255726467818022
2023-01-22 14:21:06.555076: step: 198/466, loss: 0.0013649130705744028
2023-01-22 14:21:07.200359: step: 200/466, loss: 0.011420375667512417
2023-01-22 14:21:07.770014: step: 202/466, loss: 0.010235724039375782
2023-01-22 14:21:08.384387: step: 204/466, loss: 0.007816760800778866
2023-01-22 14:21:08.985687: step: 206/466, loss: 0.037151530385017395
2023-01-22 14:21:09.599810: step: 208/466, loss: 0.02781081013381481
2023-01-22 14:21:10.237144: step: 210/466, loss: 0.0002925058361142874
2023-01-22 14:21:10.835413: step: 212/466, loss: 0.001422711880877614
2023-01-22 14:21:11.418075: step: 214/466, loss: 0.0009883105522021651
2023-01-22 14:21:12.044535: step: 216/466, loss: 0.007165312301367521
2023-01-22 14:21:12.602737: step: 218/466, loss: 0.03599708154797554
2023-01-22 14:21:13.190791: step: 220/466, loss: 0.0014106587041169405
2023-01-22 14:21:13.794868: step: 222/466, loss: 0.042335882782936096
2023-01-22 14:21:14.390060: step: 224/466, loss: 0.019867349416017532
2023-01-22 14:21:14.916091: step: 226/466, loss: 0.0019416243303567171
2023-01-22 14:21:15.483059: step: 228/466, loss: 0.08412843197584152
2023-01-22 14:21:16.121897: step: 230/466, loss: 0.001664413372054696
2023-01-22 14:21:16.668741: step: 232/466, loss: 0.000471496838144958
2023-01-22 14:21:17.410532: step: 234/466, loss: 0.007500917185097933
2023-01-22 14:21:18.102986: step: 236/466, loss: 0.02185356430709362
2023-01-22 14:21:18.717624: step: 238/466, loss: 0.00652121240273118
2023-01-22 14:21:19.317517: step: 240/466, loss: 0.008082284592092037
2023-01-22 14:21:19.936735: step: 242/466, loss: 0.002958297962322831
2023-01-22 14:21:20.629466: step: 244/466, loss: 0.01800958812236786
2023-01-22 14:21:21.225709: step: 246/466, loss: 0.0011644359910860658
2023-01-22 14:21:21.853957: step: 248/466, loss: 0.025905592367053032
2023-01-22 14:21:22.498567: step: 250/466, loss: 0.0024262622464448214
2023-01-22 14:21:23.147447: step: 252/466, loss: 0.01273428462445736
2023-01-22 14:21:23.741816: step: 254/466, loss: 0.001079851994290948
2023-01-22 14:21:24.373458: step: 256/466, loss: 0.0021350423339754343
2023-01-22 14:21:24.973673: step: 258/466, loss: 3.1468382076127455e-05
2023-01-22 14:21:25.588980: step: 260/466, loss: 0.00010797793220262975
2023-01-22 14:21:26.146960: step: 262/466, loss: 0.0028548038098961115
2023-01-22 14:21:26.721457: step: 264/466, loss: 0.0009370913612656295
2023-01-22 14:21:27.404025: step: 266/466, loss: 0.003106689313426614
2023-01-22 14:21:27.944724: step: 268/466, loss: 0.010445700958371162
2023-01-22 14:21:28.581909: step: 270/466, loss: 7.891649875091389e-05
2023-01-22 14:21:29.218365: step: 272/466, loss: 0.0008442797116003931
2023-01-22 14:21:29.827906: step: 274/466, loss: 0.028718503192067146
2023-01-22 14:21:30.495789: step: 276/466, loss: 0.00021276797633618116
2023-01-22 14:21:31.084446: step: 278/466, loss: 0.003402187954634428
2023-01-22 14:21:31.684853: step: 280/466, loss: 0.010248236358165741
2023-01-22 14:21:32.293774: step: 282/466, loss: 0.015227698720991611
2023-01-22 14:21:32.920270: step: 284/466, loss: 0.03913683444261551
2023-01-22 14:21:33.507134: step: 286/466, loss: 7.576395091746235e-06
2023-01-22 14:21:34.171996: step: 288/466, loss: 0.0048559121787548065
2023-01-22 14:21:34.908388: step: 290/466, loss: 0.010100842453539371
2023-01-22 14:21:35.493637: step: 292/466, loss: 0.002126762643456459
2023-01-22 14:21:36.033776: step: 294/466, loss: 0.00041677968692965806
2023-01-22 14:21:36.620964: step: 296/466, loss: 0.0007044681697152555
2023-01-22 14:21:37.193528: step: 298/466, loss: 0.0008290159748867154
2023-01-22 14:21:37.791703: step: 300/466, loss: 0.0004512334999162704
2023-01-22 14:21:38.413914: step: 302/466, loss: 0.039500828832387924
2023-01-22 14:21:38.990981: step: 304/466, loss: 0.0011578116100281477
2023-01-22 14:21:39.629853: step: 306/466, loss: 0.023430608212947845
2023-01-22 14:21:40.220660: step: 308/466, loss: 0.021048884838819504
2023-01-22 14:21:40.887012: step: 310/466, loss: 0.008742013014853
2023-01-22 14:21:41.406873: step: 312/466, loss: 1.865769263531547e-05
2023-01-22 14:21:42.091870: step: 314/466, loss: 5.350162973627448e-05
2023-01-22 14:21:42.719037: step: 316/466, loss: 0.08590547740459442
2023-01-22 14:21:43.364329: step: 318/466, loss: 0.00015754085325170308
2023-01-22 14:21:43.931088: step: 320/466, loss: 0.0016338627319782972
2023-01-22 14:21:44.509906: step: 322/466, loss: 0.0017493648920208216
2023-01-22 14:21:45.081399: step: 324/466, loss: 0.00036035527591593564
2023-01-22 14:21:45.749016: step: 326/466, loss: 0.027754299342632294
2023-01-22 14:21:46.426487: step: 328/466, loss: 0.00023671459348406643
2023-01-22 14:21:47.072762: step: 330/466, loss: 0.014487960375845432
2023-01-22 14:21:47.801736: step: 332/466, loss: 0.024945516139268875
2023-01-22 14:21:48.385833: step: 334/466, loss: 0.017370715737342834
2023-01-22 14:21:48.995292: step: 336/466, loss: 0.021477192640304565
2023-01-22 14:21:49.588579: step: 338/466, loss: 0.0010344891343265772
2023-01-22 14:21:50.169293: step: 340/466, loss: 0.0019837208092212677
2023-01-22 14:21:50.732363: step: 342/466, loss: 0.0013008707901462913
2023-01-22 14:21:51.235765: step: 344/466, loss: 0.012516515329480171
2023-01-22 14:21:51.879510: step: 346/466, loss: 0.031781699508428574
2023-01-22 14:21:52.625508: step: 348/466, loss: 0.017205674201250076
2023-01-22 14:21:53.231374: step: 350/466, loss: 0.0004225615703035146
2023-01-22 14:21:53.886091: step: 352/466, loss: 0.0017902185209095478
2023-01-22 14:21:54.502799: step: 354/466, loss: 0.0006667530396953225
2023-01-22 14:21:55.174176: step: 356/466, loss: 13.148250579833984
2023-01-22 14:21:55.776423: step: 358/466, loss: 6.158139876788482e-05
2023-01-22 14:21:56.419342: step: 360/466, loss: 0.01335648912936449
2023-01-22 14:21:56.971049: step: 362/466, loss: 0.00912449136376381
2023-01-22 14:21:57.553270: step: 364/466, loss: 0.002331480849534273
2023-01-22 14:21:58.131975: step: 366/466, loss: 5.07688382640481e-05
2023-01-22 14:21:58.747665: step: 368/466, loss: 0.022180695086717606
2023-01-22 14:21:59.366942: step: 370/466, loss: 0.0009626256069168448
2023-01-22 14:21:59.966008: step: 372/466, loss: 0.000288007955532521
2023-01-22 14:22:00.573842: step: 374/466, loss: 0.011116331443190575
2023-01-22 14:22:01.177095: step: 376/466, loss: 0.0007267410983331501
2023-01-22 14:22:01.791865: step: 378/466, loss: 0.03145395219326019
2023-01-22 14:22:02.416544: step: 380/466, loss: 0.008209649473428726
2023-01-22 14:22:03.032360: step: 382/466, loss: 0.0030028829351067543
2023-01-22 14:22:03.647455: step: 384/466, loss: 4.2137100535910577e-05
2023-01-22 14:22:04.301569: step: 386/466, loss: 0.0022868614178150892
2023-01-22 14:22:04.931659: step: 388/466, loss: 0.02006855420768261
2023-01-22 14:22:05.562024: step: 390/466, loss: 0.0006233835592865944
2023-01-22 14:22:06.151788: step: 392/466, loss: 0.001457541948184371
2023-01-22 14:22:06.816061: step: 394/466, loss: 0.016138330101966858
2023-01-22 14:22:07.499888: step: 396/466, loss: 0.011141076683998108
2023-01-22 14:22:08.037935: step: 398/466, loss: 0.00016360492736566812
2023-01-22 14:22:08.693025: step: 400/466, loss: 0.0023589630145579576
2023-01-22 14:22:09.298546: step: 402/466, loss: 0.3350490927696228
2023-01-22 14:22:09.913407: step: 404/466, loss: 0.02268916554749012
2023-01-22 14:22:10.595383: step: 406/466, loss: 0.025465872138738632
2023-01-22 14:22:11.243557: step: 408/466, loss: 0.02911735139787197
2023-01-22 14:22:11.922455: step: 410/466, loss: 0.003883585799485445
2023-01-22 14:22:12.516656: step: 412/466, loss: 0.014216568320989609
2023-01-22 14:22:13.079243: step: 414/466, loss: 0.018321098759770393
2023-01-22 14:22:13.669066: step: 416/466, loss: 1.0013217433879618e-05
2023-01-22 14:22:14.260186: step: 418/466, loss: 0.00023530589533038437
2023-01-22 14:22:14.885149: step: 420/466, loss: 0.009018952026963234
2023-01-22 14:22:15.469000: step: 422/466, loss: 0.00021789773018099368
2023-01-22 14:22:16.133309: step: 424/466, loss: 0.009294179268181324
2023-01-22 14:22:16.780421: step: 426/466, loss: 0.0018578199669718742
2023-01-22 14:22:17.386832: step: 428/466, loss: 0.08332467079162598
2023-01-22 14:22:18.074249: step: 430/466, loss: 0.008198990486562252
2023-01-22 14:22:18.644968: step: 432/466, loss: 0.0760422796010971
2023-01-22 14:22:19.260331: step: 434/466, loss: 0.048082102090120316
2023-01-22 14:22:19.867290: step: 436/466, loss: 0.7173665165901184
2023-01-22 14:22:20.467612: step: 438/466, loss: 0.0007875600131228566
2023-01-22 14:22:21.117033: step: 440/466, loss: 0.00019213580526411533
2023-01-22 14:22:21.741295: step: 442/466, loss: 0.0004895920865237713
2023-01-22 14:22:22.355153: step: 444/466, loss: 0.027286848053336143
2023-01-22 14:22:22.969980: step: 446/466, loss: 0.0006382520077750087
2023-01-22 14:22:23.586165: step: 448/466, loss: 0.00019963916565757245
2023-01-22 14:22:24.186424: step: 450/466, loss: 0.0013467309763655066
2023-01-22 14:22:24.849596: step: 452/466, loss: 0.0013148612342774868
2023-01-22 14:22:25.453366: step: 454/466, loss: 0.0014030374586582184
2023-01-22 14:22:26.137250: step: 456/466, loss: 0.029512371867895126
2023-01-22 14:22:26.753928: step: 458/466, loss: 0.0027600282337516546
2023-01-22 14:22:27.335431: step: 460/466, loss: 0.01813333109021187
2023-01-22 14:22:28.004134: step: 462/466, loss: 0.018591925501823425
2023-01-22 14:22:28.591682: step: 464/466, loss: 0.0026494336780160666
2023-01-22 14:22:29.211012: step: 466/466, loss: 0.016628867015242577
2023-01-22 14:22:29.846417: step: 468/466, loss: 0.003137952880933881
2023-01-22 14:22:30.539709: step: 470/466, loss: 9.976519584655762
2023-01-22 14:22:31.096222: step: 472/466, loss: 8.773814624873921e-05
2023-01-22 14:22:31.717261: step: 474/466, loss: 0.007623251993209124
2023-01-22 14:22:32.358313: step: 476/466, loss: 0.029763251543045044
2023-01-22 14:22:32.916949: step: 478/466, loss: 0.00034636148484423757
2023-01-22 14:22:33.585646: step: 480/466, loss: 0.14045073091983795
2023-01-22 14:22:34.145668: step: 482/466, loss: 0.10622703284025192
2023-01-22 14:22:34.734193: step: 484/466, loss: 0.0007836679578758776
2023-01-22 14:22:35.367202: step: 486/466, loss: 0.00019406896899454296
2023-01-22 14:22:35.963741: step: 488/466, loss: 0.003651735605672002
2023-01-22 14:22:36.590621: step: 490/466, loss: 0.0036884131841361523
2023-01-22 14:22:37.310051: step: 492/466, loss: 0.027452562004327774
2023-01-22 14:22:37.930124: step: 494/466, loss: 0.012056098319590092
2023-01-22 14:22:38.496688: step: 496/466, loss: 0.001362653449177742
2023-01-22 14:22:39.100915: step: 498/466, loss: 0.0002041674597421661
2023-01-22 14:22:39.750089: step: 500/466, loss: 0.0017715252470225096
2023-01-22 14:22:40.316144: step: 502/466, loss: 0.0030959725845605135
2023-01-22 14:22:40.925284: step: 504/466, loss: 0.011061202734708786
2023-01-22 14:22:41.532552: step: 506/466, loss: 0.06606190651655197
2023-01-22 14:22:42.228542: step: 508/466, loss: 0.09801173955202103
2023-01-22 14:22:42.836828: step: 510/466, loss: 0.0014111229684203863
2023-01-22 14:22:43.439462: step: 512/466, loss: 0.0019478622125461698
2023-01-22 14:22:44.047498: step: 514/466, loss: 0.010642904788255692
2023-01-22 14:22:44.579813: step: 516/466, loss: 0.00015110296953935176
2023-01-22 14:22:45.162965: step: 518/466, loss: 0.003046165220439434
2023-01-22 14:22:45.764277: step: 520/466, loss: 0.05332741141319275
2023-01-22 14:22:46.389858: step: 522/466, loss: 9.049453365150839e-05
2023-01-22 14:22:46.970753: step: 524/466, loss: 0.005797157529741526
2023-01-22 14:22:47.602014: step: 526/466, loss: 0.0008684933418408036
2023-01-22 14:22:48.228785: step: 528/466, loss: 0.030726298689842224
2023-01-22 14:22:48.843316: step: 530/466, loss: 0.0005216370918788016
2023-01-22 14:22:49.450956: step: 532/466, loss: 0.033588308840990067
2023-01-22 14:22:50.020598: step: 534/466, loss: 0.0958075225353241
2023-01-22 14:22:50.643350: step: 536/466, loss: 0.0002483285206835717
2023-01-22 14:22:51.228248: step: 538/466, loss: 0.0002913588541559875
2023-01-22 14:22:51.894930: step: 540/466, loss: 0.0007436099695041776
2023-01-22 14:22:52.553342: step: 542/466, loss: 6.0492820921353996e-05
2023-01-22 14:22:53.074891: step: 544/466, loss: 0.0014556294772773981
2023-01-22 14:22:53.743324: step: 546/466, loss: 0.08864249289035797
2023-01-22 14:22:54.387331: step: 548/466, loss: 0.02043880894780159
2023-01-22 14:22:55.067818: step: 550/466, loss: 0.012917747721076012
2023-01-22 14:22:55.648630: step: 552/466, loss: 0.028537839651107788
2023-01-22 14:22:56.294230: step: 554/466, loss: 3.2078983167593833e-06
2023-01-22 14:22:56.897070: step: 556/466, loss: 0.00022550432186108083
2023-01-22 14:22:57.496558: step: 558/466, loss: 0.00040336415986530483
2023-01-22 14:22:58.154713: step: 560/466, loss: 0.012805212289094925
2023-01-22 14:22:58.756058: step: 562/466, loss: 0.02135901339352131
2023-01-22 14:22:59.368155: step: 564/466, loss: 0.0027558517176657915
2023-01-22 14:22:59.973287: step: 566/466, loss: 0.031806498765945435
2023-01-22 14:23:00.645914: step: 568/466, loss: 0.003004643600434065
2023-01-22 14:23:01.245036: step: 570/466, loss: 0.0016120121581479907
2023-01-22 14:23:01.874227: step: 572/466, loss: 0.007913384586572647
2023-01-22 14:23:02.496112: step: 574/466, loss: 0.013110068626701832
2023-01-22 14:23:03.095354: step: 576/466, loss: 5.770703410235001e-06
2023-01-22 14:23:03.694489: step: 578/466, loss: 0.0206610057502985
2023-01-22 14:23:04.277019: step: 580/466, loss: 3.0003804567968473e-05
2023-01-22 14:23:04.848538: step: 582/466, loss: 7.978229405125603e-05
2023-01-22 14:23:05.513482: step: 584/466, loss: 0.00429700268432498
2023-01-22 14:23:06.168112: step: 586/466, loss: 0.0014660474844276905
2023-01-22 14:23:06.786785: step: 588/466, loss: 0.0036870657932013273
2023-01-22 14:23:07.341399: step: 590/466, loss: 0.003413487458601594
2023-01-22 14:23:07.963674: step: 592/466, loss: 0.001022740500047803
2023-01-22 14:23:08.615899: step: 594/466, loss: 0.011163215152919292
2023-01-22 14:23:09.185814: step: 596/466, loss: 0.009377296082675457
2023-01-22 14:23:09.785274: step: 598/466, loss: 0.012516893446445465
2023-01-22 14:23:10.412797: step: 600/466, loss: 0.061928533017635345
2023-01-22 14:23:11.016773: step: 602/466, loss: 0.004551253281533718
2023-01-22 14:23:11.711914: step: 604/466, loss: 0.0005189354415051639
2023-01-22 14:23:12.324773: step: 606/466, loss: 0.010122747160494328
2023-01-22 14:23:12.972214: step: 608/466, loss: 0.013840803876519203
2023-01-22 14:23:13.610023: step: 610/466, loss: 0.038683075457811356
2023-01-22 14:23:14.237780: step: 612/466, loss: 0.01938362419605255
2023-01-22 14:23:14.877388: step: 614/466, loss: 0.03968636319041252
2023-01-22 14:23:15.549210: step: 616/466, loss: 0.0006703808903694153
2023-01-22 14:23:16.129013: step: 618/466, loss: 0.007403464522212744
2023-01-22 14:23:16.751485: step: 620/466, loss: 0.053251270204782486
2023-01-22 14:23:17.376511: step: 622/466, loss: 0.006112065631896257
2023-01-22 14:23:17.938068: step: 624/466, loss: 0.00026970345061272383
2023-01-22 14:23:18.598298: step: 626/466, loss: 0.00943650584667921
2023-01-22 14:23:19.213206: step: 628/466, loss: 0.03737393021583557
2023-01-22 14:23:19.857824: step: 630/466, loss: 0.0004983880207873881
2023-01-22 14:23:20.544649: step: 632/466, loss: 0.05362514406442642
2023-01-22 14:23:21.174780: step: 634/466, loss: 0.0756533220410347
2023-01-22 14:23:21.821632: step: 636/466, loss: 0.08298175781965256
2023-01-22 14:23:22.413063: step: 638/466, loss: 0.001337780966423452
2023-01-22 14:23:23.067125: step: 640/466, loss: 0.006372489035129547
2023-01-22 14:23:23.770471: step: 642/466, loss: 0.1665182262659073
2023-01-22 14:23:24.440482: step: 644/466, loss: 0.0029575438238680363
2023-01-22 14:23:25.024709: step: 646/466, loss: 0.003067981917411089
2023-01-22 14:23:25.655213: step: 648/466, loss: 0.0019569708965718746
2023-01-22 14:23:26.244714: step: 650/466, loss: 0.0004455255693756044
2023-01-22 14:23:26.853412: step: 652/466, loss: 0.005703385919332504
2023-01-22 14:23:27.553579: step: 654/466, loss: 0.040502529591321945
2023-01-22 14:23:28.175531: step: 656/466, loss: 0.00125522306188941
2023-01-22 14:23:28.813908: step: 658/466, loss: 0.08380692452192307
2023-01-22 14:23:29.521756: step: 660/466, loss: 0.0005227712099440396
2023-01-22 14:23:30.146206: step: 662/466, loss: 0.01361200213432312
2023-01-22 14:23:30.744962: step: 664/466, loss: 2.1812933482578956e-05
2023-01-22 14:23:31.364240: step: 666/466, loss: 0.019716404378414154
2023-01-22 14:23:32.006437: step: 668/466, loss: 0.0013545232359319925
2023-01-22 14:23:32.621945: step: 670/466, loss: 0.15497149527072906
2023-01-22 14:23:33.192355: step: 672/466, loss: 0.01695387251675129
2023-01-22 14:23:33.748116: step: 674/466, loss: 0.005211781244724989
2023-01-22 14:23:34.336068: step: 676/466, loss: 0.005118411034345627
2023-01-22 14:23:34.913246: step: 678/466, loss: 0.00019001048349309713
2023-01-22 14:23:35.500953: step: 680/466, loss: 0.0051450724713504314
2023-01-22 14:23:36.129279: step: 682/466, loss: 0.000495147833134979
2023-01-22 14:23:36.827200: step: 684/466, loss: 0.00042439333628863096
2023-01-22 14:23:37.447245: step: 686/466, loss: 0.013371428474783897
2023-01-22 14:23:38.057424: step: 688/466, loss: 0.29739809036254883
2023-01-22 14:23:38.645503: step: 690/466, loss: 0.0012508954387158155
2023-01-22 14:23:39.224442: step: 692/466, loss: 0.00010261051647830755
2023-01-22 14:23:39.916632: step: 694/466, loss: 0.0014332940336316824
2023-01-22 14:23:40.587536: step: 696/466, loss: 0.0008747635874897242
2023-01-22 14:23:41.119825: step: 698/466, loss: 0.011899001896381378
2023-01-22 14:23:41.723504: step: 700/466, loss: 0.0002116097166435793
2023-01-22 14:23:42.389011: step: 702/466, loss: 0.00435160705819726
2023-01-22 14:23:43.041575: step: 704/466, loss: 0.010911312885582447
2023-01-22 14:23:43.694244: step: 706/466, loss: 0.01379432063549757
2023-01-22 14:23:44.333768: step: 708/466, loss: 0.02665085159242153
2023-01-22 14:23:44.949947: step: 710/466, loss: 0.0011860569939017296
2023-01-22 14:23:45.556115: step: 712/466, loss: 0.0071630934253335
2023-01-22 14:23:46.176204: step: 714/466, loss: 7.17996881576255e-05
2023-01-22 14:23:46.851027: step: 716/466, loss: 0.0008964896551333368
2023-01-22 14:23:47.422328: step: 718/466, loss: 0.0026297878939658403
2023-01-22 14:23:48.002373: step: 720/466, loss: 0.025944450870156288
2023-01-22 14:23:48.577241: step: 722/466, loss: 0.005806812085211277
2023-01-22 14:23:49.208604: step: 724/466, loss: 0.00132958241738379
2023-01-22 14:23:49.822890: step: 726/466, loss: 8.125565364025533e-05
2023-01-22 14:23:50.453326: step: 728/466, loss: 0.010557837784290314
2023-01-22 14:23:51.160576: step: 730/466, loss: 0.011784940026700497
2023-01-22 14:23:51.796505: step: 732/466, loss: 0.01866106316447258
2023-01-22 14:23:52.398293: step: 734/466, loss: 6.802675488870591e-05
2023-01-22 14:23:52.968308: step: 736/466, loss: 0.018818223848938942
2023-01-22 14:23:53.678224: step: 738/466, loss: 0.03583343327045441
2023-01-22 14:23:54.258414: step: 740/466, loss: 0.04375249519944191
2023-01-22 14:23:54.939127: step: 742/466, loss: 0.019149398431181908
2023-01-22 14:23:55.564597: step: 744/466, loss: 0.0026311357505619526
2023-01-22 14:23:56.234241: step: 746/466, loss: 0.00022247993911150843
2023-01-22 14:23:56.882623: step: 748/466, loss: 0.003206611378118396
2023-01-22 14:23:57.483284: step: 750/466, loss: 0.019325412809848785
2023-01-22 14:23:58.083816: step: 752/466, loss: 0.007997137494385242
2023-01-22 14:23:58.700325: step: 754/466, loss: 0.039681576192379
2023-01-22 14:23:59.324205: step: 756/466, loss: 0.00011258641461608931
2023-01-22 14:23:59.938573: step: 758/466, loss: 0.0005655647837556899
2023-01-22 14:24:00.569188: step: 760/466, loss: 0.019853683188557625
2023-01-22 14:24:01.129052: step: 762/466, loss: 0.09221357107162476
2023-01-22 14:24:01.736054: step: 764/466, loss: 0.00041412244900129735
2023-01-22 14:24:02.398671: step: 766/466, loss: 5.017004241381073e-06
2023-01-22 14:24:02.982392: step: 768/466, loss: 0.00016973994206637144
2023-01-22 14:24:03.631598: step: 770/466, loss: 0.325126588344574
2023-01-22 14:24:04.214624: step: 772/466, loss: 0.02632707543671131
2023-01-22 14:24:04.811522: step: 774/466, loss: 0.037189681082963943
2023-01-22 14:24:05.440885: step: 776/466, loss: 0.001395417028106749
2023-01-22 14:24:06.066411: step: 778/466, loss: 0.014405585825443268
2023-01-22 14:24:06.715388: step: 780/466, loss: 0.0018268510466441512
2023-01-22 14:24:07.332468: step: 782/466, loss: 0.00023554843210149556
2023-01-22 14:24:07.909230: step: 784/466, loss: 0.00029686972266063094
2023-01-22 14:24:08.561266: step: 786/466, loss: 0.0013889693655073643
2023-01-22 14:24:09.120398: step: 788/466, loss: 0.0017082897247746587
2023-01-22 14:24:09.724498: step: 790/466, loss: 0.00015379107207991183
2023-01-22 14:24:10.335956: step: 792/466, loss: 0.011510002426803112
2023-01-22 14:24:10.927907: step: 794/466, loss: 0.0012235584435984492
2023-01-22 14:24:11.501682: step: 796/466, loss: 0.0002206399367423728
2023-01-22 14:24:12.101954: step: 798/466, loss: 0.016461864113807678
2023-01-22 14:24:12.722436: step: 800/466, loss: 0.00021372491028159857
2023-01-22 14:24:13.347529: step: 802/466, loss: 0.006961922161281109
2023-01-22 14:24:13.938863: step: 804/466, loss: 0.0021296602208167315
2023-01-22 14:24:14.582959: step: 806/466, loss: 0.004430140368640423
2023-01-22 14:24:15.182678: step: 808/466, loss: 0.01939069665968418
2023-01-22 14:24:15.876203: step: 810/466, loss: 0.018148865550756454
2023-01-22 14:24:16.564503: step: 812/466, loss: 0.032092414796352386
2023-01-22 14:24:17.165385: step: 814/466, loss: 0.002228677272796631
2023-01-22 14:24:17.783675: step: 816/466, loss: 0.46651652455329895
2023-01-22 14:24:18.442683: step: 818/466, loss: 0.0010596377542242408
2023-01-22 14:24:19.122132: step: 820/466, loss: 0.03519681096076965
2023-01-22 14:24:19.748386: step: 822/466, loss: 0.02435610629618168
2023-01-22 14:24:20.291745: step: 824/466, loss: 0.018063798546791077
2023-01-22 14:24:20.893015: step: 826/466, loss: 0.025036821141839027
2023-01-22 14:24:21.521002: step: 828/466, loss: 0.00565796485170722
2023-01-22 14:24:22.189176: step: 830/466, loss: 0.00033403924317099154
2023-01-22 14:24:22.791449: step: 832/466, loss: 0.035529982298612595
2023-01-22 14:24:23.384931: step: 834/466, loss: 0.0027162355836480856
2023-01-22 14:24:24.068936: step: 836/466, loss: 0.28506195545196533
2023-01-22 14:24:24.660042: step: 838/466, loss: 0.003587544895708561
2023-01-22 14:24:25.252268: step: 840/466, loss: 0.0032926108688116074
2023-01-22 14:24:25.944097: step: 842/466, loss: 0.00020436853810679168
2023-01-22 14:24:26.541452: step: 844/466, loss: 0.015589582733809948
2023-01-22 14:24:27.181071: step: 846/466, loss: 0.011255361139774323
2023-01-22 14:24:27.824768: step: 848/466, loss: 0.0009275318589061499
2023-01-22 14:24:28.422000: step: 850/466, loss: 0.010922861285507679
2023-01-22 14:24:29.021060: step: 852/466, loss: 0.0019173540640622377
2023-01-22 14:24:29.732171: step: 854/466, loss: 0.015206730924546719
2023-01-22 14:24:30.337858: step: 856/466, loss: 0.006905407179147005
2023-01-22 14:24:30.921583: step: 858/466, loss: 8.463582344120368e-05
2023-01-22 14:24:31.556970: step: 860/466, loss: 0.008326876908540726
2023-01-22 14:24:32.164546: step: 862/466, loss: 0.01070437952876091
2023-01-22 14:24:32.823936: step: 864/466, loss: 0.023237278684973717
2023-01-22 14:24:33.400225: step: 866/466, loss: 0.001569541753269732
2023-01-22 14:24:33.968476: step: 868/466, loss: 0.6829010844230652
2023-01-22 14:24:34.556614: step: 870/466, loss: 0.024112524464726448
2023-01-22 14:24:35.219569: step: 872/466, loss: 0.04400830343365669
2023-01-22 14:24:35.869065: step: 874/466, loss: 0.0033177779987454414
2023-01-22 14:24:36.423127: step: 876/466, loss: 3.7316167436074466e-05
2023-01-22 14:24:37.024915: step: 878/466, loss: 0.014675674960017204
2023-01-22 14:24:37.628547: step: 880/466, loss: 0.0008311232668347657
2023-01-22 14:24:38.280597: step: 882/466, loss: 0.0009520520106889307
2023-01-22 14:24:38.924508: step: 884/466, loss: 0.02135886438190937
2023-01-22 14:24:39.581906: step: 886/466, loss: 0.0956830233335495
2023-01-22 14:24:40.222943: step: 888/466, loss: 0.0027999801095575094
2023-01-22 14:24:40.856320: step: 890/466, loss: 0.007054173853248358
2023-01-22 14:24:41.418313: step: 892/466, loss: 0.0005048189777880907
2023-01-22 14:24:42.011609: step: 894/466, loss: 0.009962208569049835
2023-01-22 14:24:42.681811: step: 896/466, loss: 2.0304094505263492e-05
2023-01-22 14:24:43.295393: step: 898/466, loss: 0.00035148989991284907
2023-01-22 14:24:43.846916: step: 900/466, loss: 1.965487354027573e-05
2023-01-22 14:24:44.525442: step: 902/466, loss: 1.1942763194383588e-05
2023-01-22 14:24:45.134730: step: 904/466, loss: 0.011142687872052193
2023-01-22 14:24:45.807059: step: 906/466, loss: 7.367681246250868e-05
2023-01-22 14:24:46.479163: step: 908/466, loss: 0.056911956518888474
2023-01-22 14:24:47.169089: step: 910/466, loss: 0.001020154682919383
2023-01-22 14:24:47.762101: step: 912/466, loss: 0.00010358607687521726
2023-01-22 14:24:48.359537: step: 914/466, loss: 0.009350110776722431
2023-01-22 14:24:49.032660: step: 916/466, loss: 0.07540338486433029
2023-01-22 14:24:49.593143: step: 918/466, loss: 0.0008968925685621798
2023-01-22 14:24:50.217197: step: 920/466, loss: 0.0002797171182464808
2023-01-22 14:24:50.853172: step: 922/466, loss: 0.012770457193255424
2023-01-22 14:24:51.567391: step: 924/466, loss: 0.0036673741415143013
2023-01-22 14:24:52.206333: step: 926/466, loss: 0.015117192640900612
2023-01-22 14:24:52.867317: step: 928/466, loss: 0.0056894137524068356
2023-01-22 14:24:53.451972: step: 930/466, loss: 0.00023494100605603307
2023-01-22 14:24:54.061732: step: 932/466, loss: 0.009276535362005234
==================================================
Loss: 0.076
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315149767890364, 'r': 0.34661243303749345, 'f1': 0.3388956441758053}, 'combined': 0.24971257991901444, 'epoch': 38}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3273148573217842, 'r': 0.29570593156959024, 'f1': 0.3107085558834576}, 'combined': 0.19455582471207158, 'epoch': 38}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3084428971417243, 'r': 0.34590085808493176, 'f1': 0.32609973561853145}, 'combined': 0.2402840157189179, 'epoch': 38}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3311522574078027, 'r': 0.30634572549007016, 'f1': 0.3182663514702276}, 'combined': 0.19723548541816918, 'epoch': 38}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.2842213085074828, 'r': 0.3430071199445143, 'f1': 0.3108594191070663}, 'combined': 0.22905430881573308, 'epoch': 38}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.336437895831912, 'r': 0.2996637446163191, 'f1': 0.31698783114215506}, 'combined': 0.21027905630222168, 'epoch': 38}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2897727272727273, 'r': 0.36428571428571427, 'f1': 0.3227848101265823}, 'combined': 0.2151898734177215, 'epoch': 38}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.33064516129032256, 'r': 0.44565217391304346, 'f1': 0.37962962962962965}, 'combined': 0.18981481481481483, 'epoch': 38}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3684210526315789, 'r': 0.2413793103448276, 'f1': 0.2916666666666667}, 'combined': 0.19444444444444445, 'epoch': 38}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}
******************************
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 14:27:30.939049: step: 2/466, loss: 0.015146813355386257
2023-01-22 14:27:31.530078: step: 4/466, loss: 0.0003074166306760162
2023-01-22 14:27:32.104937: step: 6/466, loss: 0.0002357083430979401
2023-01-22 14:27:32.721334: step: 8/466, loss: 0.000184124888619408
2023-01-22 14:27:33.384690: step: 10/466, loss: 0.001829985179938376
2023-01-22 14:27:33.982509: step: 12/466, loss: 0.012212690897285938
2023-01-22 14:27:34.556094: step: 14/466, loss: 0.00026231296942569315
2023-01-22 14:27:35.275656: step: 16/466, loss: 0.020328694954514503
2023-01-22 14:27:35.834551: step: 18/466, loss: 0.0020918946247547865
2023-01-22 14:27:36.459258: step: 20/466, loss: 0.4596867561340332
2023-01-22 14:27:37.076568: step: 22/466, loss: 0.005000561010092497
2023-01-22 14:27:37.753467: step: 24/466, loss: 0.0014943135902285576
2023-01-22 14:27:38.337480: step: 26/466, loss: 0.0005825718399137259
2023-01-22 14:27:38.984601: step: 28/466, loss: 0.0016708880430087447
2023-01-22 14:27:39.646175: step: 30/466, loss: 0.00558796850964427
2023-01-22 14:27:40.430565: step: 32/466, loss: 0.009061440825462341
2023-01-22 14:27:41.102766: step: 34/466, loss: 0.004432479850947857
2023-01-22 14:27:41.698701: step: 36/466, loss: 0.001037839101627469
2023-01-22 14:27:42.378425: step: 38/466, loss: 0.02181771956384182
2023-01-22 14:27:43.063160: step: 40/466, loss: 0.004848001524806023
2023-01-22 14:27:43.660196: step: 42/466, loss: 0.0003929196682292968
2023-01-22 14:27:44.241630: step: 44/466, loss: 0.004267378244549036
2023-01-22 14:27:44.877585: step: 46/466, loss: 0.004441943950951099
2023-01-22 14:27:45.437627: step: 48/466, loss: 0.0002382261009188369
2023-01-22 14:27:45.997939: step: 50/466, loss: 0.022365359589457512
2023-01-22 14:27:46.669670: step: 52/466, loss: 0.003134834812954068
2023-01-22 14:27:47.293396: step: 54/466, loss: 0.01796906441450119
2023-01-22 14:27:47.884921: step: 56/466, loss: 0.00047307138447649777
2023-01-22 14:27:48.483758: step: 58/466, loss: 0.0003856524417642504
2023-01-22 14:27:49.094266: step: 60/466, loss: 0.0001241409918293357
2023-01-22 14:27:49.739708: step: 62/466, loss: 0.0018064368050545454
2023-01-22 14:27:50.292562: step: 64/466, loss: 0.00014263468619901687
2023-01-22 14:27:50.908932: step: 66/466, loss: 0.049406711012125015
2023-01-22 14:27:51.518463: step: 68/466, loss: 0.040563397109508514
2023-01-22 14:27:52.113136: step: 70/466, loss: 6.365009903674945e-05
2023-01-22 14:27:52.783870: step: 72/466, loss: 2.4744760594330728e-05
2023-01-22 14:27:53.373145: step: 74/466, loss: 0.0002055208751698956
2023-01-22 14:27:54.029911: step: 76/466, loss: 0.00016762428276706487
2023-01-22 14:27:54.656377: step: 78/466, loss: 0.0049255709163844585
2023-01-22 14:27:55.256530: step: 80/466, loss: 0.022715115919709206
2023-01-22 14:27:55.933773: step: 82/466, loss: 0.047502294182777405
2023-01-22 14:27:56.577469: step: 84/466, loss: 0.0009096862049773335
2023-01-22 14:27:57.168713: step: 86/466, loss: 0.0430033914744854
2023-01-22 14:27:57.773046: step: 88/466, loss: 0.0008197950082831085
2023-01-22 14:27:58.378511: step: 90/466, loss: 0.010219205170869827
2023-01-22 14:27:59.026176: step: 92/466, loss: 0.000343933526892215
2023-01-22 14:27:59.593181: step: 94/466, loss: 0.0016889260150492191
2023-01-22 14:28:00.304412: step: 96/466, loss: 0.001990893855690956
2023-01-22 14:28:00.939035: step: 98/466, loss: 0.001507123582996428
2023-01-22 14:28:01.492135: step: 100/466, loss: 0.003949206788092852
2023-01-22 14:28:02.133238: step: 102/466, loss: 0.00011206905037397519
2023-01-22 14:28:02.683276: step: 104/466, loss: 0.0004756792332045734
2023-01-22 14:28:03.332743: step: 106/466, loss: 0.19810990989208221
2023-01-22 14:28:03.906405: step: 108/466, loss: 0.0008925989968702197
2023-01-22 14:28:04.596622: step: 110/466, loss: 0.019793085753917694
2023-01-22 14:28:05.197748: step: 112/466, loss: 0.0001608679158380255
2023-01-22 14:28:05.810057: step: 114/466, loss: 0.0023188581690192223
2023-01-22 14:28:06.414471: step: 116/466, loss: 0.00044002002687193453
2023-01-22 14:28:07.036660: step: 118/466, loss: 0.0035514081828296185
2023-01-22 14:28:07.638021: step: 120/466, loss: 0.017122356221079826
2023-01-22 14:28:08.261025: step: 122/466, loss: 0.0045568267814815044
2023-01-22 14:28:08.901430: step: 124/466, loss: 0.0007005815277807415
2023-01-22 14:28:09.511907: step: 126/466, loss: 0.056621044874191284
2023-01-22 14:28:10.153148: step: 128/466, loss: 0.009771609678864479
2023-01-22 14:28:10.788195: step: 130/466, loss: 0.025190964341163635
2023-01-22 14:28:11.329461: step: 132/466, loss: 0.0009690226870588958
2023-01-22 14:28:11.957286: step: 134/466, loss: 0.007555143907666206
2023-01-22 14:28:12.548258: step: 136/466, loss: 0.0006410313653759658
2023-01-22 14:28:13.217182: step: 138/466, loss: 0.0059431311674416065
2023-01-22 14:28:13.842811: step: 140/466, loss: 0.01306483056396246
2023-01-22 14:28:14.431683: step: 142/466, loss: 0.000849867588840425
2023-01-22 14:28:15.029951: step: 144/466, loss: 0.005498063750565052
2023-01-22 14:28:15.654829: step: 146/466, loss: 0.011659790761768818
2023-01-22 14:28:16.256417: step: 148/466, loss: 0.00012292210885789245
2023-01-22 14:28:16.844836: step: 150/466, loss: 0.003171361517161131
2023-01-22 14:28:17.444450: step: 152/466, loss: 0.0027298645582050085
2023-01-22 14:28:18.123464: step: 154/466, loss: 0.0005431473255157471
2023-01-22 14:28:18.705671: step: 156/466, loss: 0.005113815888762474
2023-01-22 14:28:19.270193: step: 158/466, loss: 0.0003711992467287928
2023-01-22 14:28:19.872231: step: 160/466, loss: 0.01225435733795166
2023-01-22 14:28:20.455345: step: 162/466, loss: 0.007259010802954435
2023-01-22 14:28:21.075385: step: 164/466, loss: 0.011203518137335777
2023-01-22 14:28:21.707471: step: 166/466, loss: 0.0008613622630946338
2023-01-22 14:28:22.341790: step: 168/466, loss: 0.015586303547024727
2023-01-22 14:28:22.976921: step: 170/466, loss: 0.032504454255104065
2023-01-22 14:28:23.588553: step: 172/466, loss: 0.0831817090511322
2023-01-22 14:28:24.187782: step: 174/466, loss: 0.051060471683740616
2023-01-22 14:28:24.822095: step: 176/466, loss: 0.0001223188592121005
2023-01-22 14:28:25.461238: step: 178/466, loss: 0.01799921505153179
2023-01-22 14:28:26.040649: step: 180/466, loss: 0.07070158421993256
2023-01-22 14:28:26.583077: step: 182/466, loss: 5.117091131978668e-05
2023-01-22 14:28:27.239438: step: 184/466, loss: 0.026660479605197906
2023-01-22 14:28:27.906485: step: 186/466, loss: 0.0007928465493023396
2023-01-22 14:28:28.581293: step: 188/466, loss: 0.025318864732980728
2023-01-22 14:28:29.173505: step: 190/466, loss: 0.0017006566049531102
2023-01-22 14:28:29.793295: step: 192/466, loss: 0.0001773086842149496
2023-01-22 14:28:30.377711: step: 194/466, loss: 0.0009296719217672944
2023-01-22 14:28:31.006443: step: 196/466, loss: 0.974057674407959
2023-01-22 14:28:31.634468: step: 198/466, loss: 0.002374091884121299
2023-01-22 14:28:32.219273: step: 200/466, loss: 0.0025441867765039206
2023-01-22 14:28:32.891210: step: 202/466, loss: 0.0020350173581391573
2023-01-22 14:28:33.559230: step: 204/466, loss: 0.0001868289109552279
2023-01-22 14:28:34.167096: step: 206/466, loss: 0.007404529023915529
2023-01-22 14:28:34.806041: step: 208/466, loss: 0.06039193645119667
2023-01-22 14:28:35.418421: step: 210/466, loss: 0.034476589411497116
2023-01-22 14:28:36.068025: step: 212/466, loss: 0.0005918517708778381
2023-01-22 14:28:36.712385: step: 214/466, loss: 0.002764403820037842
2023-01-22 14:28:37.293362: step: 216/466, loss: 0.0005349020357243717
2023-01-22 14:28:37.979695: step: 218/466, loss: 0.11122305691242218
2023-01-22 14:28:38.641273: step: 220/466, loss: 0.03173927962779999
2023-01-22 14:28:39.242611: step: 222/466, loss: 0.4182344079017639
2023-01-22 14:28:39.818990: step: 224/466, loss: 0.0015414378140121698
2023-01-22 14:28:40.376389: step: 226/466, loss: 0.005522494204342365
2023-01-22 14:28:41.080501: step: 228/466, loss: 0.0012009440688416362
2023-01-22 14:28:41.684749: step: 230/466, loss: 0.006269220262765884
2023-01-22 14:28:42.330998: step: 232/466, loss: 0.0009267473360523582
2023-01-22 14:28:42.922018: step: 234/466, loss: 0.0010035564191639423
2023-01-22 14:28:43.563142: step: 236/466, loss: 0.007629994302988052
2023-01-22 14:28:44.160377: step: 238/466, loss: 0.0006880948203615844
2023-01-22 14:28:44.794118: step: 240/466, loss: 0.017418693751096725
2023-01-22 14:28:45.436714: step: 242/466, loss: 0.018945759162306786
2023-01-22 14:28:46.058663: step: 244/466, loss: 0.045282479375600815
2023-01-22 14:28:46.630404: step: 246/466, loss: 3.4216670883324696e-06
2023-01-22 14:28:47.160433: step: 248/466, loss: 0.013945143669843674
2023-01-22 14:28:47.812218: step: 250/466, loss: 0.0008457014337182045
2023-01-22 14:28:48.458172: step: 252/466, loss: 0.0006486780475825071
2023-01-22 14:28:49.049263: step: 254/466, loss: 0.0004897922044619918
2023-01-22 14:28:49.652884: step: 256/466, loss: 0.04232799634337425
2023-01-22 14:28:50.263955: step: 258/466, loss: 0.0715564414858818
2023-01-22 14:28:50.939147: step: 260/466, loss: 0.0019753577653318644
2023-01-22 14:28:51.443006: step: 262/466, loss: 1.726490336295683e-05
2023-01-22 14:28:52.020064: step: 264/466, loss: 0.032654985785484314
2023-01-22 14:28:52.628262: step: 266/466, loss: 0.005304881837219
2023-01-22 14:28:53.328386: step: 268/466, loss: 0.00436329934746027
2023-01-22 14:28:53.958106: step: 270/466, loss: 0.025691457092761993
2023-01-22 14:28:54.573046: step: 272/466, loss: 0.11292967945337296
2023-01-22 14:28:55.152234: step: 274/466, loss: 0.02001877874135971
2023-01-22 14:28:55.702548: step: 276/466, loss: 0.031532302498817444
2023-01-22 14:28:56.297386: step: 278/466, loss: 0.01248552929610014
2023-01-22 14:28:56.883201: step: 280/466, loss: 0.007771877571940422
2023-01-22 14:28:57.440632: step: 282/466, loss: 0.00010319840657757595
2023-01-22 14:28:58.037303: step: 284/466, loss: 0.002683585975319147
2023-01-22 14:28:58.620901: step: 286/466, loss: 0.017789045348763466
2023-01-22 14:28:59.176892: step: 288/466, loss: 0.03899354115128517
2023-01-22 14:28:59.794749: step: 290/466, loss: 0.0007138618966564536
2023-01-22 14:29:00.370619: step: 292/466, loss: 0.01902945153415203
2023-01-22 14:29:01.007861: step: 294/466, loss: 0.001563211902976036
2023-01-22 14:29:01.574245: step: 296/466, loss: 0.12047767639160156
2023-01-22 14:29:02.154594: step: 298/466, loss: 0.0019326814217492938
2023-01-22 14:29:02.734986: step: 300/466, loss: 0.1401207000017166
2023-01-22 14:29:03.327209: step: 302/466, loss: 0.0678744688630104
2023-01-22 14:29:03.845131: step: 304/466, loss: 1.8989589079865254e-05
2023-01-22 14:29:04.437203: step: 306/466, loss: 0.0033861834090203047
2023-01-22 14:29:05.079859: step: 308/466, loss: 0.006160313729196787
2023-01-22 14:29:05.758406: step: 310/466, loss: 0.00039482087595388293
2023-01-22 14:29:06.336726: step: 312/466, loss: 0.0005335321184247732
2023-01-22 14:29:06.960667: step: 314/466, loss: 0.003995128907263279
2023-01-22 14:29:07.617435: step: 316/466, loss: 0.006496662739664316
2023-01-22 14:29:08.182814: step: 318/466, loss: 0.013022312894463539
2023-01-22 14:29:08.771163: step: 320/466, loss: 0.004884499125182629
2023-01-22 14:29:09.442183: step: 322/466, loss: 0.006754643749445677
2023-01-22 14:29:10.059881: step: 324/466, loss: 0.003081450704485178
2023-01-22 14:29:10.650780: step: 326/466, loss: 0.0004135740746278316
2023-01-22 14:29:11.238113: step: 328/466, loss: 0.017562659457325935
2023-01-22 14:29:11.916267: step: 330/466, loss: 0.023915909230709076
2023-01-22 14:29:12.540370: step: 332/466, loss: 0.006121632177382708
2023-01-22 14:29:13.139286: step: 334/466, loss: 0.0018397157546132803
2023-01-22 14:29:13.725805: step: 336/466, loss: 0.017214152961969376
2023-01-22 14:29:14.314207: step: 338/466, loss: 0.0007691142382100224
2023-01-22 14:29:14.909175: step: 340/466, loss: 0.0006501898751594126
2023-01-22 14:29:15.509888: step: 342/466, loss: 0.0071964929811656475
2023-01-22 14:29:16.090853: step: 344/466, loss: 0.00021978993027005345
2023-01-22 14:29:16.737431: step: 346/466, loss: 0.0007107586716301739
2023-01-22 14:29:17.343413: step: 348/466, loss: 0.00016834375855978578
2023-01-22 14:29:17.940748: step: 350/466, loss: 0.002281171502545476
2023-01-22 14:29:18.557802: step: 352/466, loss: 0.26626327633857727
2023-01-22 14:29:19.167012: step: 354/466, loss: 0.002194957807660103
2023-01-22 14:29:19.726991: step: 356/466, loss: 0.006199446506798267
2023-01-22 14:29:20.348714: step: 358/466, loss: 0.00025742349680513144
2023-01-22 14:29:20.956041: step: 360/466, loss: 0.0033204129431396723
2023-01-22 14:29:21.543749: step: 362/466, loss: 0.0002158809220418334
2023-01-22 14:29:22.196348: step: 364/466, loss: 0.01004930678755045
2023-01-22 14:29:22.848002: step: 366/466, loss: 0.012771162204444408
2023-01-22 14:29:23.512018: step: 368/466, loss: 0.3831963539123535
2023-01-22 14:29:24.137560: step: 370/466, loss: 0.0004712164809461683
2023-01-22 14:29:24.743877: step: 372/466, loss: 8.565105963498354e-05
2023-01-22 14:29:25.351250: step: 374/466, loss: 0.008703215047717094
2023-01-22 14:29:25.992072: step: 376/466, loss: 0.0017890515737235546
2023-01-22 14:29:26.688286: step: 378/466, loss: 0.030411401763558388
2023-01-22 14:29:27.255377: step: 380/466, loss: 0.011570041067898273
2023-01-22 14:29:27.901061: step: 382/466, loss: 6.799383845645934e-05
2023-01-22 14:29:28.492064: step: 384/466, loss: 0.0009624511003494263
2023-01-22 14:29:29.106068: step: 386/466, loss: 0.010127180255949497
2023-01-22 14:29:29.638270: step: 388/466, loss: 0.04178277775645256
2023-01-22 14:29:30.271090: step: 390/466, loss: 0.29337212443351746
2023-01-22 14:29:30.926645: step: 392/466, loss: 0.01280940417200327
2023-01-22 14:29:31.749448: step: 394/466, loss: 0.0004417002492118627
2023-01-22 14:29:32.356911: step: 396/466, loss: 1.205349326133728
2023-01-22 14:29:33.022100: step: 398/466, loss: 0.01344842929393053
2023-01-22 14:29:33.635003: step: 400/466, loss: 0.009408276528120041
2023-01-22 14:29:34.259959: step: 402/466, loss: 0.004019880201667547
2023-01-22 14:29:34.915722: step: 404/466, loss: 0.0017869789153337479
2023-01-22 14:29:35.579277: step: 406/466, loss: 0.0024829041212797165
2023-01-22 14:29:36.171564: step: 408/466, loss: 0.0006193328881636262
2023-01-22 14:29:36.784851: step: 410/466, loss: 7.454582373611629e-05
2023-01-22 14:29:37.333988: step: 412/466, loss: 0.002369493246078491
2023-01-22 14:29:37.954494: step: 414/466, loss: 0.008629947900772095
2023-01-22 14:29:38.552596: step: 416/466, loss: 0.0034468895755708218
2023-01-22 14:29:39.225095: step: 418/466, loss: 0.043524369597435
2023-01-22 14:29:39.856716: step: 420/466, loss: 9.258293721359223e-05
2023-01-22 14:29:40.440074: step: 422/466, loss: 0.0004924088134430349
2023-01-22 14:29:41.033305: step: 424/466, loss: 0.0020500586833804846
2023-01-22 14:29:41.625417: step: 426/466, loss: 0.000378899450879544
2023-01-22 14:29:42.279583: step: 428/466, loss: 0.0009215320460498333
2023-01-22 14:29:42.872950: step: 430/466, loss: 0.0014220247976481915
2023-01-22 14:29:43.532535: step: 432/466, loss: 0.03277864679694176
2023-01-22 14:29:44.148353: step: 434/466, loss: 0.0034149999264627695
2023-01-22 14:29:44.813991: step: 436/466, loss: 0.05704144015908241
2023-01-22 14:29:45.377865: step: 438/466, loss: 0.0003729193704202771
2023-01-22 14:29:45.953145: step: 440/466, loss: 0.0002809804864227772
2023-01-22 14:29:46.592035: step: 442/466, loss: 0.022944778203964233
2023-01-22 14:29:47.156522: step: 444/466, loss: 1.9058319594478235e-05
2023-01-22 14:29:47.757996: step: 446/466, loss: 0.011696002446115017
2023-01-22 14:29:48.376845: step: 448/466, loss: 0.011733698658645153
2023-01-22 14:29:49.048037: step: 450/466, loss: 0.011339561082422733
2023-01-22 14:29:49.687927: step: 452/466, loss: 0.02468111738562584
2023-01-22 14:29:50.359854: step: 454/466, loss: 0.00014265567006077617
2023-01-22 14:29:51.010275: step: 456/466, loss: 0.005921643693000078
2023-01-22 14:29:51.678036: step: 458/466, loss: 3.866276074404595e-06
2023-01-22 14:29:52.407383: step: 460/466, loss: 0.0376657210290432
2023-01-22 14:29:53.007895: step: 462/466, loss: 0.027660418301820755
2023-01-22 14:29:53.647730: step: 464/466, loss: 0.030926374718546867
2023-01-22 14:29:54.224564: step: 466/466, loss: 0.05319409817457199
2023-01-22 14:29:54.805988: step: 468/466, loss: 0.01862410455942154
2023-01-22 14:29:55.385176: step: 470/466, loss: 0.05574251338839531
2023-01-22 14:29:55.967666: step: 472/466, loss: 1.8421047570882365e-05
2023-01-22 14:29:56.766584: step: 474/466, loss: 0.009457133710384369
2023-01-22 14:29:57.376744: step: 476/466, loss: 0.055761680006980896
2023-01-22 14:29:57.996975: step: 478/466, loss: 0.08062682300806046
2023-01-22 14:29:58.599364: step: 480/466, loss: 0.03951627388596535
2023-01-22 14:29:59.211350: step: 482/466, loss: 0.002509194193407893
2023-01-22 14:29:59.767026: step: 484/466, loss: 0.010882500559091568
2023-01-22 14:30:00.393240: step: 486/466, loss: 0.00012993431300856173
2023-01-22 14:30:00.948436: step: 488/466, loss: 0.0002025272697210312
2023-01-22 14:30:01.640521: step: 490/466, loss: 0.0013053443981334567
2023-01-22 14:30:02.215281: step: 492/466, loss: 0.0002276983723277226
2023-01-22 14:30:02.801606: step: 494/466, loss: 0.00048199991579167545
2023-01-22 14:30:03.449281: step: 496/466, loss: 0.005118025932461023
2023-01-22 14:30:04.055971: step: 498/466, loss: 0.0019508281257003546
2023-01-22 14:30:04.662850: step: 500/466, loss: 0.0013491560239344835
2023-01-22 14:30:05.314887: step: 502/466, loss: 0.007075273897498846
2023-01-22 14:30:05.947882: step: 504/466, loss: 0.005225518252700567
2023-01-22 14:30:06.638400: step: 506/466, loss: 0.003914638888090849
2023-01-22 14:30:07.194356: step: 508/466, loss: 0.0018765986897051334
2023-01-22 14:30:07.821582: step: 510/466, loss: 0.00469422759488225
2023-01-22 14:30:08.437836: step: 512/466, loss: 0.0008197916322387755
2023-01-22 14:30:09.049845: step: 514/466, loss: 0.0004325522168073803
2023-01-22 14:30:09.714167: step: 516/466, loss: 0.02749079279601574
2023-01-22 14:30:10.318515: step: 518/466, loss: 0.010200398974120617
2023-01-22 14:30:10.938080: step: 520/466, loss: 0.006094923242926598
2023-01-22 14:30:11.600625: step: 522/466, loss: 0.029264384880661964
2023-01-22 14:30:12.219461: step: 524/466, loss: 0.008493440225720406
2023-01-22 14:30:12.802067: step: 526/466, loss: 0.010457186959683895
2023-01-22 14:30:13.393831: step: 528/466, loss: 0.0030657630413770676
2023-01-22 14:30:13.985213: step: 530/466, loss: 0.011401893571019173
2023-01-22 14:30:14.560159: step: 532/466, loss: 0.0011566388420760632
2023-01-22 14:30:15.297293: step: 534/466, loss: 0.0009276172495447099
2023-01-22 14:30:15.889528: step: 536/466, loss: 0.0007449205149896443
2023-01-22 14:30:16.488784: step: 538/466, loss: 0.04266156628727913
2023-01-22 14:30:17.104477: step: 540/466, loss: 2.943605613836553e-05
2023-01-22 14:30:17.694828: step: 542/466, loss: 0.005300668999552727
2023-01-22 14:30:18.319531: step: 544/466, loss: 0.004938418511301279
2023-01-22 14:30:18.880128: step: 546/466, loss: 0.0005849276203662157
2023-01-22 14:30:19.508565: step: 548/466, loss: 0.00024039176059886813
2023-01-22 14:30:20.155432: step: 550/466, loss: 0.05814645066857338
2023-01-22 14:30:20.952259: step: 552/466, loss: 0.034741807729005814
2023-01-22 14:30:21.634453: step: 554/466, loss: 0.010376464575529099
2023-01-22 14:30:22.249263: step: 556/466, loss: 0.007738225162029266
2023-01-22 14:30:22.859685: step: 558/466, loss: 0.015268164686858654
2023-01-22 14:30:23.501091: step: 560/466, loss: 0.0005753119476139545
2023-01-22 14:30:24.097735: step: 562/466, loss: 0.004864976741373539
2023-01-22 14:30:24.809975: step: 564/466, loss: 0.00046194621245376766
2023-01-22 14:30:25.352008: step: 566/466, loss: 5.7880228268913925e-05
2023-01-22 14:30:26.013815: step: 568/466, loss: 0.0002593135286588222
2023-01-22 14:30:26.668779: step: 570/466, loss: 0.00015103169425856322
2023-01-22 14:30:27.278121: step: 572/466, loss: 0.0005016021896153688
2023-01-22 14:30:27.930163: step: 574/466, loss: 0.00017170878709293902
2023-01-22 14:30:28.591010: step: 576/466, loss: 0.002684682607650757
2023-01-22 14:30:29.241974: step: 578/466, loss: 0.02178850769996643
2023-01-22 14:30:29.809191: step: 580/466, loss: 0.001377226086333394
2023-01-22 14:30:30.465416: step: 582/466, loss: 0.016383491456508636
2023-01-22 14:30:31.156895: step: 584/466, loss: 0.026128072291612625
2023-01-22 14:30:31.814464: step: 586/466, loss: 0.8927581310272217
2023-01-22 14:30:32.443760: step: 588/466, loss: 0.002846858697012067
2023-01-22 14:30:33.067421: step: 590/466, loss: 0.010788768529891968
2023-01-22 14:30:33.686495: step: 592/466, loss: 0.016432126984000206
2023-01-22 14:30:34.259096: step: 594/466, loss: 0.00408394169062376
2023-01-22 14:30:34.857903: step: 596/466, loss: 0.0014608690980821848
2023-01-22 14:30:35.478371: step: 598/466, loss: 0.021469846367836
2023-01-22 14:30:36.104080: step: 600/466, loss: 0.010216777212917805
2023-01-22 14:30:36.724406: step: 602/466, loss: 0.0032048202119767666
2023-01-22 14:30:37.327837: step: 604/466, loss: 0.001778666046448052
2023-01-22 14:30:37.962794: step: 606/466, loss: 0.0009655572939664125
2023-01-22 14:30:38.579989: step: 608/466, loss: 0.02794690988957882
2023-01-22 14:30:39.162302: step: 610/466, loss: 0.0011128874029964209
2023-01-22 14:30:39.797734: step: 612/466, loss: 0.8146460056304932
2023-01-22 14:30:40.407803: step: 614/466, loss: 0.07190607488155365
2023-01-22 14:30:41.060037: step: 616/466, loss: 0.0043852198868989944
2023-01-22 14:30:41.697065: step: 618/466, loss: 0.00029586939490400255
2023-01-22 14:30:42.358829: step: 620/466, loss: 0.00011438815272413194
2023-01-22 14:30:42.987859: step: 622/466, loss: 0.03767530992627144
2023-01-22 14:30:43.636141: step: 624/466, loss: 0.001130322809331119
2023-01-22 14:30:44.313616: step: 626/466, loss: 0.012164980173110962
2023-01-22 14:30:44.927134: step: 628/466, loss: 0.0004524152318481356
2023-01-22 14:30:45.650175: step: 630/466, loss: 0.5553993582725525
2023-01-22 14:30:46.247553: step: 632/466, loss: 0.0335814394056797
2023-01-22 14:30:46.850328: step: 634/466, loss: 0.006767832674086094
2023-01-22 14:30:47.476444: step: 636/466, loss: 0.0005514143267646432
2023-01-22 14:30:48.103697: step: 638/466, loss: 0.03491172939538956
2023-01-22 14:30:48.725919: step: 640/466, loss: 0.00022917038586456329
2023-01-22 14:30:49.353599: step: 642/466, loss: 0.013450004160404205
2023-01-22 14:30:49.970424: step: 644/466, loss: 0.0004298327548895031
2023-01-22 14:30:50.640575: step: 646/466, loss: 0.05986448749899864
2023-01-22 14:30:51.263199: step: 648/466, loss: 0.09393955022096634
2023-01-22 14:30:51.871163: step: 650/466, loss: 0.01259876973927021
2023-01-22 14:30:52.467663: step: 652/466, loss: 0.005960284266620874
2023-01-22 14:30:53.064871: step: 654/466, loss: 0.0038826039526611567
2023-01-22 14:30:53.690025: step: 656/466, loss: 0.02023625746369362
2023-01-22 14:30:54.284623: step: 658/466, loss: 0.013375281356275082
2023-01-22 14:30:54.922920: step: 660/466, loss: 0.009454164654016495
2023-01-22 14:30:55.517888: step: 662/466, loss: 0.03510063886642456
2023-01-22 14:30:56.153690: step: 664/466, loss: 2.4045333702815697e-05
2023-01-22 14:30:56.879240: step: 666/466, loss: 0.03811146691441536
2023-01-22 14:30:57.499560: step: 668/466, loss: 0.004611080978065729
2023-01-22 14:30:58.185431: step: 670/466, loss: 0.01828666590154171
2023-01-22 14:30:58.923756: step: 672/466, loss: 0.08229411393404007
2023-01-22 14:30:59.564323: step: 674/466, loss: 0.07620945572853088
2023-01-22 14:31:00.191940: step: 676/466, loss: 0.020200613886117935
2023-01-22 14:31:00.870535: step: 678/466, loss: 0.011386757716536522
2023-01-22 14:31:01.514700: step: 680/466, loss: 0.06650497019290924
2023-01-22 14:31:02.147127: step: 682/466, loss: 0.009418701753020287
2023-01-22 14:31:02.801502: step: 684/466, loss: 0.011599413119256496
2023-01-22 14:31:03.337006: step: 686/466, loss: 2.19941957766423e-05
2023-01-22 14:31:03.929030: step: 688/466, loss: 7.218680548248813e-05
2023-01-22 14:31:04.539871: step: 690/466, loss: 0.000757165253162384
2023-01-22 14:31:05.084759: step: 692/466, loss: 0.0006082160398364067
2023-01-22 14:31:05.642562: step: 694/466, loss: 0.009860683232545853
2023-01-22 14:31:06.235260: step: 696/466, loss: 0.0037478036247193813
2023-01-22 14:31:06.864285: step: 698/466, loss: 0.00012133311975048855
2023-01-22 14:31:07.458720: step: 700/466, loss: 1.673118233680725
2023-01-22 14:31:08.037304: step: 702/466, loss: 0.012901155278086662
2023-01-22 14:31:08.584090: step: 704/466, loss: 0.03286221623420715
2023-01-22 14:31:09.174226: step: 706/466, loss: 0.0008559783454984426
2023-01-22 14:31:09.742097: step: 708/466, loss: 0.014345237985253334
2023-01-22 14:31:10.301708: step: 710/466, loss: 0.03778726980090141
2023-01-22 14:31:10.981805: step: 712/466, loss: 0.0023969518952071667
2023-01-22 14:31:11.642713: step: 714/466, loss: 0.0012106853537261486
2023-01-22 14:31:12.263229: step: 716/466, loss: 6.305293209152296e-05
2023-01-22 14:31:12.832264: step: 718/466, loss: 0.0016548899002373219
2023-01-22 14:31:13.444639: step: 720/466, loss: 0.01998119428753853
2023-01-22 14:31:14.089684: step: 722/466, loss: 0.004715107847005129
2023-01-22 14:31:14.659068: step: 724/466, loss: 0.018795287236571312
2023-01-22 14:31:15.319983: step: 726/466, loss: 0.001077094697393477
2023-01-22 14:31:15.957457: step: 728/466, loss: 0.016393447294831276
2023-01-22 14:31:16.635541: step: 730/466, loss: 0.0015165505465120077
2023-01-22 14:31:17.268623: step: 732/466, loss: 0.24392935633659363
2023-01-22 14:31:17.914273: step: 734/466, loss: 0.009406911209225655
2023-01-22 14:31:18.499271: step: 736/466, loss: 0.0006833647494204342
2023-01-22 14:31:19.145481: step: 738/466, loss: 0.01145173143595457
2023-01-22 14:31:19.768899: step: 740/466, loss: 0.017168890684843063
2023-01-22 14:31:20.432700: step: 742/466, loss: 0.039287131279706955
2023-01-22 14:31:21.041519: step: 744/466, loss: 0.0018259059870615602
2023-01-22 14:31:21.685125: step: 746/466, loss: 0.04990117996931076
2023-01-22 14:31:22.327598: step: 748/466, loss: 0.005614149384200573
2023-01-22 14:31:22.944424: step: 750/466, loss: 0.34750282764434814
2023-01-22 14:31:23.573674: step: 752/466, loss: 0.007629684172570705
2023-01-22 14:31:24.335783: step: 754/466, loss: 0.000609358714427799
2023-01-22 14:31:24.915625: step: 756/466, loss: 6.950379611225799e-05
2023-01-22 14:31:25.527494: step: 758/466, loss: 0.007717175409197807
2023-01-22 14:31:26.143875: step: 760/466, loss: 0.0005427895812317729
2023-01-22 14:31:26.781490: step: 762/466, loss: 0.009419084526598454
2023-01-22 14:31:27.400891: step: 764/466, loss: 0.003427655203267932
2023-01-22 14:31:27.942019: step: 766/466, loss: 0.004435101989656687
2023-01-22 14:31:28.618983: step: 768/466, loss: 0.02116675302386284
2023-01-22 14:31:29.260922: step: 770/466, loss: 0.0014157030964270234
2023-01-22 14:31:29.895720: step: 772/466, loss: 0.024654695764183998
2023-01-22 14:31:30.573571: step: 774/466, loss: 0.01110147312283516
2023-01-22 14:31:31.164806: step: 776/466, loss: 0.011182224377989769
2023-01-22 14:31:31.789304: step: 778/466, loss: 0.0026764869689941406
2023-01-22 14:31:32.370933: step: 780/466, loss: 0.03134223818778992
2023-01-22 14:31:33.028646: step: 782/466, loss: 0.04435329511761665
2023-01-22 14:31:33.648069: step: 784/466, loss: 0.0007561178063042462
2023-01-22 14:31:34.264957: step: 786/466, loss: 0.0002951621718239039
2023-01-22 14:31:34.890498: step: 788/466, loss: 0.0003678632201626897
2023-01-22 14:31:35.483069: step: 790/466, loss: 0.00023044607951305807
2023-01-22 14:31:36.134849: step: 792/466, loss: 0.004554104525595903
2023-01-22 14:31:36.768150: step: 794/466, loss: 0.03749992698431015
2023-01-22 14:31:37.372027: step: 796/466, loss: 0.0050889598205685616
2023-01-22 14:31:37.978978: step: 798/466, loss: 0.022501587867736816
2023-01-22 14:31:38.621389: step: 800/466, loss: 0.0016455540899187326
2023-01-22 14:31:39.201018: step: 802/466, loss: 0.02270793356001377
2023-01-22 14:31:39.780086: step: 804/466, loss: 0.02387150004506111
2023-01-22 14:31:40.379794: step: 806/466, loss: 0.00879066064953804
2023-01-22 14:31:40.980560: step: 808/466, loss: 0.02466905117034912
2023-01-22 14:31:41.579022: step: 810/466, loss: 0.0003841761499643326
2023-01-22 14:31:42.160110: step: 812/466, loss: 0.022657496854662895
2023-01-22 14:31:42.769962: step: 814/466, loss: 0.021001193672418594
2023-01-22 14:31:43.372525: step: 816/466, loss: 0.0012862952426075935
2023-01-22 14:31:44.020140: step: 818/466, loss: 0.0014121142448857427
2023-01-22 14:31:44.676826: step: 820/466, loss: 0.07674619555473328
2023-01-22 14:31:45.247205: step: 822/466, loss: 0.00023735903960186988
2023-01-22 14:31:45.829167: step: 824/466, loss: 0.008518465794622898
2023-01-22 14:31:46.469537: step: 826/466, loss: 0.047690004110336304
2023-01-22 14:31:47.101839: step: 828/466, loss: 0.012457768432796001
2023-01-22 14:31:47.746998: step: 830/466, loss: 0.0053737955167889595
2023-01-22 14:31:48.356336: step: 832/466, loss: 0.02782123163342476
2023-01-22 14:31:48.988102: step: 834/466, loss: 0.012997192330658436
2023-01-22 14:31:49.630478: step: 836/466, loss: 0.0006396679091267288
2023-01-22 14:31:50.260116: step: 838/466, loss: 0.06348526477813721
2023-01-22 14:31:50.887482: step: 840/466, loss: 0.009664001874625683
2023-01-22 14:31:51.507056: step: 842/466, loss: 6.664659304078668e-05
2023-01-22 14:31:52.113650: step: 844/466, loss: 0.0036700644996017218
2023-01-22 14:31:52.741776: step: 846/466, loss: 0.00011915640061488375
2023-01-22 14:31:53.327820: step: 848/466, loss: 0.019163085147738457
2023-01-22 14:31:54.035707: step: 850/466, loss: 0.003196119097992778
2023-01-22 14:31:54.707066: step: 852/466, loss: 0.023471256718039513
2023-01-22 14:31:55.341523: step: 854/466, loss: 0.03895140066742897
2023-01-22 14:31:55.924541: step: 856/466, loss: 0.14801856875419617
2023-01-22 14:31:56.497367: step: 858/466, loss: 0.002836451167240739
2023-01-22 14:31:57.092630: step: 860/466, loss: 0.03754058852791786
2023-01-22 14:31:57.675383: step: 862/466, loss: 0.0010937509359791875
2023-01-22 14:31:58.269593: step: 864/466, loss: 0.013703150674700737
2023-01-22 14:31:58.818699: step: 866/466, loss: 0.005252503789961338
2023-01-22 14:31:59.366897: step: 868/466, loss: 0.0045418632216751575
2023-01-22 14:31:59.897581: step: 870/466, loss: 0.001951231388375163
2023-01-22 14:32:00.507668: step: 872/466, loss: 0.00119210802949965
2023-01-22 14:32:01.156507: step: 874/466, loss: 0.030209461227059364
2023-01-22 14:32:01.780956: step: 876/466, loss: 0.011322562582790852
2023-01-22 14:32:02.457406: step: 878/466, loss: 0.010349459014832973
2023-01-22 14:32:03.111496: step: 880/466, loss: 0.012835453264415264
2023-01-22 14:32:03.731374: step: 882/466, loss: 0.01803370751440525
2023-01-22 14:32:04.294721: step: 884/466, loss: 0.01328533235937357
2023-01-22 14:32:04.964585: step: 886/466, loss: 0.04617784172296524
2023-01-22 14:32:05.556649: step: 888/466, loss: 0.004265455529093742
2023-01-22 14:32:06.172481: step: 890/466, loss: 0.0004143684927839786
2023-01-22 14:32:06.796030: step: 892/466, loss: 0.00028480804758146405
2023-01-22 14:32:07.435009: step: 894/466, loss: 0.013935239054262638
2023-01-22 14:32:08.002717: step: 896/466, loss: 0.0036510045174509287
2023-01-22 14:32:08.623173: step: 898/466, loss: 0.01588931865990162
2023-01-22 14:32:09.251446: step: 900/466, loss: 0.0030068140476942062
2023-01-22 14:32:09.865211: step: 902/466, loss: 1.1271354196651373e-05
2023-01-22 14:32:10.457190: step: 904/466, loss: 0.03463272377848625
2023-01-22 14:32:11.055473: step: 906/466, loss: 0.00010575733904261142
2023-01-22 14:32:11.620714: step: 908/466, loss: 0.010893854312598705
2023-01-22 14:32:12.249983: step: 910/466, loss: 0.012717542238533497
2023-01-22 14:32:12.804202: step: 912/466, loss: 0.003962480928748846
2023-01-22 14:32:13.425873: step: 914/466, loss: 0.00039833056507632136
2023-01-22 14:32:14.072698: step: 916/466, loss: 0.02264953963458538
2023-01-22 14:32:14.687883: step: 918/466, loss: 0.019269829615950584
2023-01-22 14:32:15.324162: step: 920/466, loss: 0.016555093228816986
2023-01-22 14:32:15.956243: step: 922/466, loss: 0.0030862840358167887
2023-01-22 14:32:16.550245: step: 924/466, loss: 0.032286155968904495
2023-01-22 14:32:17.224144: step: 926/466, loss: 0.0031867055222392082
2023-01-22 14:32:17.818914: step: 928/466, loss: 0.00030876160599291325
2023-01-22 14:32:18.431860: step: 930/466, loss: 0.004123792517930269
2023-01-22 14:32:19.059643: step: 932/466, loss: 0.022024938836693764
==================================================
Loss: 0.032
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33196869729720335, 'r': 0.34708681633920124, 'f1': 0.3393594660681986}, 'combined': 0.25005434341867266, 'epoch': 39}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.33566765395429426, 'r': 0.2881475262078342, 'f1': 0.31009762888354014}, 'combined': 0.19417328163735692, 'epoch': 39}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3099916387959866, 'r': 0.3517552182163188, 'f1': 0.32955555555555555}, 'combined': 0.24283040935672512, 'epoch': 39}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3473418242078091, 'r': 0.29942180698166415, 'f1': 0.3216065704045187}, 'combined': 0.19930548025068762, 'epoch': 39}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.27992450263599233, 'r': 0.344726759413205, 'f1': 0.30896428947408}, 'combined': 0.22765789750721682, 'epoch': 39}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.35274366886385083, 'r': 0.29734890498089955, 'f1': 0.3226861770017989}, 'combined': 0.21405914712000523, 'epoch': 39}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25, 'r': 0.36428571428571427, 'f1': 0.2965116279069767}, 'combined': 0.19767441860465113, 'epoch': 39}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3203125, 'r': 0.44565217391304346, 'f1': 0.3727272727272727}, 'combined': 0.18636363636363634, 'epoch': 39}
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': 39}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3315222772277228, 'r': 0.31708096590909096, 'f1': 0.32414085188770575}, 'combined': 0.23884062770673053, 'epoch': 9}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3159215514303053, 'r': 0.27771443239451027, 'f1': 0.29558846406639516}, 'combined': 0.18508810366774278, 'epoch': 9}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34285714285714286, 'r': 0.34285714285714286, 'f1': 0.34285714285714286}, 'combined': 0.22857142857142856, 'epoch': 9}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31058557706852213, 'r': 0.3541972140762463, 'f1': 0.33096087201805285}, 'combined': 0.24386590569751262, 'epoch': 27}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.34834896071034976, 'r': 0.30562988166922483, 'f1': 0.3255941774939196}, 'combined': 0.20177667337651356, 'epoch': 27}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'epoch': 27}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.28413817663817664, 'r': 0.31540955091714107, 'f1': 0.2989583333333333}, 'combined': 0.22028508771929822, 'epoch': 9}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.3335445029877535, 'r': 0.2861968655835245, 'f1': 0.3080620275770103}, 'combined': 0.2043579786896999, 'epoch': 9}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.42105263157894735, 'r': 0.27586206896551724, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 9}