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.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-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-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.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.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.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.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.imprisoned-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.imprisoned-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.imprisoned-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.imprisoned-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.corrupt-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.corrupt-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.corrupt-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.corrupt-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.judicial-actions-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.judicial-actions-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.judicial-actions-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.judicial-actions-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.charged-with-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.charged-with-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.charged-with-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.charged-with-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.prison-term-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.prison-term-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.prison-term-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.prison-term-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.fine-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.fine-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.fine-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.fine-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.npi-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.npi-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.npi-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.npi-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.disease-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.disease-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.disease-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.disease-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.infected-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.infected-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.infected-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.infected-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.killed-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.killed-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.killed-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.killed-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.killed-cumulative-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.killed-cumulative-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.killed-cumulative-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.killed-cumulative-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.outbreak-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.outbreak-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.outbreak-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.outbreak-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.infected-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.infected-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.infected-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.infected-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.killed-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.killed-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.killed-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.killed-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.hospitalized-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.hospitalized-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.hospitalized-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.hospitalized-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.hospitalized-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.hospitalized-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.hospitalized-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.hospitalized-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.infected-individuals-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.infected-individuals-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.infected-individuals-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.infected-individuals-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.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-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.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.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.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.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.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.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.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.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.named-perp-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.named-perp-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.named-perp-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.named-perp-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perp-killed-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perp-killed-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perp-killed-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perp-killed-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.target-human-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.target-human-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.target-human-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.target-human-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perp-captured-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perp-captured-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perp-captured-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perp-captured-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perp-objective-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perp-objective-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perp-objective-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perp-objective-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.weapon-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.weapon-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.weapon-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.weapon-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.named-organizer-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.named-organizer-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.named-organizer-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.named-organizer-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.affected-cumulative-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.affected-cumulative-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.affected-cumulative-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.affected-cumulative-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.damage-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.damage-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.damage-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.damage-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.human-displacement-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.human-displacement-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.human-displacement-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.human-displacement-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.major-disaster-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.major-disaster-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.major-disaster-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.major-disaster-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.related-natural-phenomena-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.related-natural-phenomena-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.related-natural-phenomena-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.related-natural-phenomena-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.responders-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.responders-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.responders-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.responders-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.assistance-provided-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.assistance-provided-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.assistance-provided-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.assistance-provided-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.rescue-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.rescue-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.rescue-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.rescue-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.individuals-affected-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.individuals-affected-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.individuals-affected-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.individuals-affected-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.missing-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.missing-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.missing-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.missing-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.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.injured-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.injured-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.injured-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.injured-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.rescued-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.rescued-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.rescued-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.rescued-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.repair-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.repair-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.repair-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.repair-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.declare-emergency-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.declare-emergency-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.declare-emergency-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.declare-emergency-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.announce-disaster-warnings-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.announce-disaster-warnings-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.announce-disaster-warnings-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.announce-disaster-warnings-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.disease-outbreak-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.disease-outbreak-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.disease-outbreak-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.disease-outbreak-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.current-location-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.current-location-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.current-location-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.current-location-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.event-or-soa-at-origin-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.group-identity-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.group-identity-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.group-identity-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.group-identity-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.human-displacement-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.human-displacement-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.human-displacement-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.human-displacement-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.origin-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.origin-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.origin-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.origin-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.total-displaced-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.total-displaced-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.total-displaced-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.total-displaced-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.transitory-events-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.transitory-events-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.transitory-events-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.transitory-events-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.destination-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.destination-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.destination-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.destination-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.transiting-location-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.transiting-location-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.transiting-location-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.transiting-location-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.settlement-status-event-or-soa-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.detained-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.detained-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.detained-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.detained-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.blocked-migration-count-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.blocked-migration-count-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.blocked-migration-count-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.blocked-migration-count-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.cybercrime-event-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.cybercrime-event-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.cybercrime-event-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.cybercrime-event-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.perpetrator-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.perpetrator-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.perpetrator-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.perpetrator-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.victim-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.victim-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.victim-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.victim-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.response-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.response-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.response-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.response-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.information-stolen-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.information-stolen-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.information-stolen-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.information-stolen-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.related-crimes-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.related-crimes-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.related-crimes-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.related-crimes-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.victim-impact-ffn.layers.0.weight: torch.Size([350, 1024])
>>> name2classifier.victim-impact-ffn.layers.0.bias: torch.Size([350])
>>> name2classifier.victim-impact-ffn.layers.1.weight: torch.Size([2, 350])
>>> name2classifier.victim-impact-ffn.layers.1.bias: torch.Size([2])
>>> name2classifier.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, 1128])
>>> 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: 614103147, 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
2023-01-24 00:48:03.333640: step: 2/469, loss: 15.25331974029541
2023-01-24 00:48:03.984477: step: 4/469, loss: 21.970951080322266
2023-01-24 00:48:04.564882: step: 6/469, loss: 13.212173461914062
2023-01-24 00:48:05.143806: step: 8/469, loss: 18.27519989013672
2023-01-24 00:48:05.766329: step: 10/469, loss: 6.163782119750977
2023-01-24 00:48:06.433548: step: 12/469, loss: 10.581079483032227
2023-01-24 00:48:07.052626: step: 14/469, loss: 15.638595581054688
2023-01-24 00:48:07.707692: step: 16/469, loss: 11.160401344299316
2023-01-24 00:48:08.332124: step: 18/469, loss: 9.45910358428955
2023-01-24 00:48:08.950660: step: 20/469, loss: 13.210053443908691
2023-01-24 00:48:09.620891: step: 22/469, loss: 27.54082679748535
2023-01-24 00:48:10.261702: step: 24/469, loss: 9.979040145874023
2023-01-24 00:48:10.960326: step: 26/469, loss: 39.79236602783203
2023-01-24 00:48:11.592272: step: 28/469, loss: 19.85337257385254
2023-01-24 00:48:12.223546: step: 30/469, loss: 8.446556091308594
2023-01-24 00:48:12.781076: step: 32/469, loss: 11.976491928100586
2023-01-24 00:48:13.564423: step: 34/469, loss: 16.93046760559082
2023-01-24 00:48:14.239999: step: 36/469, loss: 11.251506805419922
2023-01-24 00:48:14.859834: step: 38/469, loss: 26.54198455810547
2023-01-24 00:48:15.601514: step: 40/469, loss: 13.888751029968262
2023-01-24 00:48:16.260271: step: 42/469, loss: 14.683391571044922
2023-01-24 00:48:16.891849: step: 44/469, loss: 12.402320861816406
2023-01-24 00:48:17.477167: step: 46/469, loss: 12.877483367919922
2023-01-24 00:48:18.071428: step: 48/469, loss: 12.395111083984375
2023-01-24 00:48:18.622358: step: 50/469, loss: 15.595003128051758
2023-01-24 00:48:19.223407: step: 52/469, loss: 12.594765663146973
2023-01-24 00:48:19.878097: step: 54/469, loss: 17.614059448242188
2023-01-24 00:48:20.514128: step: 56/469, loss: 20.128860473632812
2023-01-24 00:48:21.115509: step: 58/469, loss: 11.931539535522461
2023-01-24 00:48:21.739227: step: 60/469, loss: 11.201589584350586
2023-01-24 00:48:22.365290: step: 62/469, loss: 6.375723838806152
2023-01-24 00:48:23.050374: step: 64/469, loss: 9.771102905273438
2023-01-24 00:48:23.652457: step: 66/469, loss: 14.409685134887695
2023-01-24 00:48:24.256360: step: 68/469, loss: 23.893356323242188
2023-01-24 00:48:24.874975: step: 70/469, loss: 5.700743675231934
2023-01-24 00:48:25.582132: step: 72/469, loss: 13.422945976257324
2023-01-24 00:48:26.227131: step: 74/469, loss: 10.815437316894531
2023-01-24 00:48:26.857255: step: 76/469, loss: 11.343101501464844
2023-01-24 00:48:27.464637: step: 78/469, loss: 18.26156997680664
2023-01-24 00:48:28.129382: step: 80/469, loss: 12.07800006866455
2023-01-24 00:48:28.763352: step: 82/469, loss: 30.563390731811523
2023-01-24 00:48:29.347194: step: 84/469, loss: 15.843639373779297
2023-01-24 00:48:30.055213: step: 86/469, loss: 14.654402732849121
2023-01-24 00:48:30.628107: step: 88/469, loss: 7.263551235198975
2023-01-24 00:48:31.213527: step: 90/469, loss: 6.958093643188477
2023-01-24 00:48:31.823925: step: 92/469, loss: 4.206276893615723
2023-01-24 00:48:32.473077: step: 94/469, loss: 19.03128433227539
2023-01-24 00:48:33.090035: step: 96/469, loss: 29.198678970336914
2023-01-24 00:48:33.729673: step: 98/469, loss: 8.968064308166504
2023-01-24 00:48:34.327262: step: 100/469, loss: 14.914346694946289
2023-01-24 00:48:34.949342: step: 102/469, loss: 22.362733840942383
2023-01-24 00:48:35.542381: step: 104/469, loss: 11.355212211608887
2023-01-24 00:48:36.241403: step: 106/469, loss: 5.288875579833984
2023-01-24 00:48:36.934712: step: 108/469, loss: 11.654914855957031
2023-01-24 00:48:37.589425: step: 110/469, loss: 15.550905227661133
2023-01-24 00:48:38.250068: step: 112/469, loss: 5.483501434326172
2023-01-24 00:48:38.838923: step: 114/469, loss: 7.941393852233887
2023-01-24 00:48:39.430575: step: 116/469, loss: 6.272886276245117
2023-01-24 00:48:40.029160: step: 118/469, loss: 3.443401336669922
2023-01-24 00:48:40.608748: step: 120/469, loss: 19.11764907836914
2023-01-24 00:48:41.413829: step: 122/469, loss: 10.003095626831055
2023-01-24 00:48:42.022611: step: 124/469, loss: 9.644991874694824
2023-01-24 00:48:42.591807: step: 126/469, loss: 4.290789604187012
2023-01-24 00:48:43.270342: step: 128/469, loss: 14.747127532958984
2023-01-24 00:48:43.950596: step: 130/469, loss: 8.645899772644043
2023-01-24 00:48:44.553084: step: 132/469, loss: 12.569320678710938
2023-01-24 00:48:45.177573: step: 134/469, loss: 5.450272560119629
2023-01-24 00:48:45.831229: step: 136/469, loss: 4.271622657775879
2023-01-24 00:48:46.495777: step: 138/469, loss: 13.993158340454102
2023-01-24 00:48:47.172590: step: 140/469, loss: 12.455425262451172
2023-01-24 00:48:47.907136: step: 142/469, loss: 9.445347785949707
2023-01-24 00:48:48.563961: step: 144/469, loss: 12.140447616577148
2023-01-24 00:48:49.135076: step: 146/469, loss: 4.812276363372803
2023-01-24 00:48:49.776136: step: 148/469, loss: 4.675212383270264
2023-01-24 00:48:50.420647: step: 150/469, loss: 10.567374229431152
2023-01-24 00:48:50.983044: step: 152/469, loss: 11.976028442382812
2023-01-24 00:48:51.682537: step: 154/469, loss: 14.886834144592285
2023-01-24 00:48:52.319175: step: 156/469, loss: 6.296490669250488
2023-01-24 00:48:52.971346: step: 158/469, loss: 5.976956367492676
2023-01-24 00:48:53.624703: step: 160/469, loss: 11.025665283203125
2023-01-24 00:48:54.250479: step: 162/469, loss: 4.316882610321045
2023-01-24 00:48:54.894560: step: 164/469, loss: 6.996575355529785
2023-01-24 00:48:55.588580: step: 166/469, loss: 8.291420936584473
2023-01-24 00:48:56.188950: step: 168/469, loss: 11.635712623596191
2023-01-24 00:48:56.826329: step: 170/469, loss: 13.164066314697266
2023-01-24 00:48:57.523982: step: 172/469, loss: 22.71116065979004
2023-01-24 00:48:58.167223: step: 174/469, loss: 4.483279228210449
2023-01-24 00:48:58.804781: step: 176/469, loss: 3.100710153579712
2023-01-24 00:48:59.456789: step: 178/469, loss: 5.378321647644043
2023-01-24 00:49:00.069288: step: 180/469, loss: 4.432587623596191
2023-01-24 00:49:00.747961: step: 182/469, loss: 19.970138549804688
2023-01-24 00:49:01.406195: step: 184/469, loss: 3.3743908405303955
2023-01-24 00:49:02.036378: step: 186/469, loss: 3.5790181159973145
2023-01-24 00:49:02.636973: step: 188/469, loss: 4.171597957611084
2023-01-24 00:49:03.241489: step: 190/469, loss: 2.8348236083984375
2023-01-24 00:49:03.903791: step: 192/469, loss: 4.021544933319092
2023-01-24 00:49:04.516636: step: 194/469, loss: 8.497549057006836
2023-01-24 00:49:05.155458: step: 196/469, loss: 5.995969772338867
2023-01-24 00:49:05.782119: step: 198/469, loss: 16.996166229248047
2023-01-24 00:49:06.363569: step: 200/469, loss: 3.164473533630371
2023-01-24 00:49:07.000561: step: 202/469, loss: 7.8727288246154785
2023-01-24 00:49:07.625135: step: 204/469, loss: 9.354909896850586
2023-01-24 00:49:08.332915: step: 206/469, loss: 4.296377658843994
2023-01-24 00:49:08.954763: step: 208/469, loss: 10.702449798583984
2023-01-24 00:49:09.541224: step: 210/469, loss: 8.718423843383789
2023-01-24 00:49:10.157932: step: 212/469, loss: 5.151759147644043
2023-01-24 00:49:10.795458: step: 214/469, loss: 14.128950119018555
2023-01-24 00:49:11.408426: step: 216/469, loss: 12.070377349853516
2023-01-24 00:49:12.031483: step: 218/469, loss: 2.4820210933685303
2023-01-24 00:49:12.585978: step: 220/469, loss: 5.188449859619141
2023-01-24 00:49:13.175556: step: 222/469, loss: 10.08375358581543
2023-01-24 00:49:13.804562: step: 224/469, loss: 16.227426528930664
2023-01-24 00:49:14.484607: step: 226/469, loss: 3.6772079467773438
2023-01-24 00:49:15.135145: step: 228/469, loss: 10.027013778686523
2023-01-24 00:49:15.820848: step: 230/469, loss: 10.387798309326172
2023-01-24 00:49:16.432144: step: 232/469, loss: 4.331166744232178
2023-01-24 00:49:17.094105: step: 234/469, loss: 8.990900993347168
2023-01-24 00:49:17.718703: step: 236/469, loss: 6.255729675292969
2023-01-24 00:49:18.341161: step: 238/469, loss: 10.792963027954102
2023-01-24 00:49:18.991077: step: 240/469, loss: 14.049783706665039
2023-01-24 00:49:19.600850: step: 242/469, loss: 5.845194339752197
2023-01-24 00:49:20.287818: step: 244/469, loss: 12.815567016601562
2023-01-24 00:49:20.955871: step: 246/469, loss: 2.849949598312378
2023-01-24 00:49:21.676686: step: 248/469, loss: 5.038797855377197
2023-01-24 00:49:22.312304: step: 250/469, loss: 4.091221809387207
2023-01-24 00:49:22.915449: step: 252/469, loss: 1.6356446743011475
2023-01-24 00:49:23.534827: step: 254/469, loss: 5.083172798156738
2023-01-24 00:49:24.127849: step: 256/469, loss: 3.7159621715545654
2023-01-24 00:49:24.737491: step: 258/469, loss: 6.490711212158203
2023-01-24 00:49:25.368193: step: 260/469, loss: 6.164132118225098
2023-01-24 00:49:25.984501: step: 262/469, loss: 10.140697479248047
2023-01-24 00:49:26.684080: step: 264/469, loss: 7.924156188964844
2023-01-24 00:49:27.341754: step: 266/469, loss: 13.918113708496094
2023-01-24 00:49:27.985182: step: 268/469, loss: 8.852334976196289
2023-01-24 00:49:28.579677: step: 270/469, loss: 12.88856315612793
2023-01-24 00:49:29.210378: step: 272/469, loss: 3.2401225566864014
2023-01-24 00:49:29.843289: step: 274/469, loss: 2.070889711380005
2023-01-24 00:49:30.506989: step: 276/469, loss: 5.971617221832275
2023-01-24 00:49:31.103038: step: 278/469, loss: 11.369691848754883
2023-01-24 00:49:31.763796: step: 280/469, loss: 10.891914367675781
2023-01-24 00:49:32.489834: step: 282/469, loss: 9.760658264160156
2023-01-24 00:49:33.154027: step: 284/469, loss: 10.473724365234375
2023-01-24 00:49:33.818703: step: 286/469, loss: 6.3389763832092285
2023-01-24 00:49:34.450228: step: 288/469, loss: 2.5295441150665283
2023-01-24 00:49:35.081646: step: 290/469, loss: 7.045894622802734
2023-01-24 00:49:35.745428: step: 292/469, loss: 3.7562596797943115
2023-01-24 00:49:36.374940: step: 294/469, loss: 1.6220287084579468
2023-01-24 00:49:37.035563: step: 296/469, loss: 10.069462776184082
2023-01-24 00:49:37.681150: step: 298/469, loss: 1.358391523361206
2023-01-24 00:49:38.413427: step: 300/469, loss: 5.900286674499512
2023-01-24 00:49:39.062667: step: 302/469, loss: 9.4619722366333
2023-01-24 00:49:39.684760: step: 304/469, loss: 3.0025548934936523
2023-01-24 00:49:40.333045: step: 306/469, loss: 4.691314697265625
2023-01-24 00:49:40.948872: step: 308/469, loss: 5.232211589813232
2023-01-24 00:49:41.550705: step: 310/469, loss: 1.8659954071044922
2023-01-24 00:49:42.229180: step: 312/469, loss: 2.8411831855773926
2023-01-24 00:49:42.843748: step: 314/469, loss: 8.379655838012695
2023-01-24 00:49:43.501877: step: 316/469, loss: 16.53976058959961
2023-01-24 00:49:44.153594: step: 318/469, loss: 4.165069103240967
2023-01-24 00:49:44.748987: step: 320/469, loss: 4.469231128692627
2023-01-24 00:49:45.311287: step: 322/469, loss: 7.795541763305664
2023-01-24 00:49:45.945282: step: 324/469, loss: 4.559579849243164
2023-01-24 00:49:46.552204: step: 326/469, loss: 1.3640480041503906
2023-01-24 00:49:47.141896: step: 328/469, loss: 5.399559020996094
2023-01-24 00:49:47.769643: step: 330/469, loss: 4.02651309967041
2023-01-24 00:49:48.367478: step: 332/469, loss: 3.0965323448181152
2023-01-24 00:49:49.001307: step: 334/469, loss: 3.435300350189209
2023-01-24 00:49:49.713993: step: 336/469, loss: 3.2126917839050293
2023-01-24 00:49:50.337466: step: 338/469, loss: 3.2306101322174072
2023-01-24 00:49:50.880562: step: 340/469, loss: 1.1037557125091553
2023-01-24 00:49:51.475725: step: 342/469, loss: 2.682487726211548
2023-01-24 00:49:52.077320: step: 344/469, loss: 3.663137912750244
2023-01-24 00:49:52.667836: step: 346/469, loss: 5.510931968688965
2023-01-24 00:49:53.277392: step: 348/469, loss: 4.036832332611084
2023-01-24 00:49:53.991560: step: 350/469, loss: 5.561859607696533
2023-01-24 00:49:54.696756: step: 352/469, loss: 5.070573329925537
2023-01-24 00:49:55.396071: step: 354/469, loss: 7.536715507507324
2023-01-24 00:49:56.037068: step: 356/469, loss: 6.385239124298096
2023-01-24 00:49:56.669446: step: 358/469, loss: 8.187983512878418
2023-01-24 00:49:57.276058: step: 360/469, loss: 3.9256420135498047
2023-01-24 00:49:57.887523: step: 362/469, loss: 2.4221854209899902
2023-01-24 00:49:58.618679: step: 364/469, loss: 5.579275131225586
2023-01-24 00:49:59.219077: step: 366/469, loss: 11.50503158569336
2023-01-24 00:49:59.759358: step: 368/469, loss: 7.054537296295166
2023-01-24 00:50:00.545480: step: 370/469, loss: 13.798737525939941
2023-01-24 00:50:01.168153: step: 372/469, loss: 1.4237483739852905
2023-01-24 00:50:01.788203: step: 374/469, loss: 1.0680210590362549
2023-01-24 00:50:02.412559: step: 376/469, loss: 8.365805625915527
2023-01-24 00:50:03.019942: step: 378/469, loss: 2.9956741333007812
2023-01-24 00:50:03.686655: step: 380/469, loss: 2.4886374473571777
2023-01-24 00:50:04.352892: step: 382/469, loss: 2.274200439453125
2023-01-24 00:50:04.915125: step: 384/469, loss: 2.3594021797180176
2023-01-24 00:50:05.529048: step: 386/469, loss: 3.8289542198181152
2023-01-24 00:50:06.250191: step: 388/469, loss: 3.451693534851074
2023-01-24 00:50:06.927531: step: 390/469, loss: 4.932161331176758
2023-01-24 00:50:07.553889: step: 392/469, loss: 8.29738712310791
2023-01-24 00:50:08.187023: step: 394/469, loss: 2.3075027465820312
2023-01-24 00:50:08.847145: step: 396/469, loss: 6.424660682678223
2023-01-24 00:50:09.514550: step: 398/469, loss: 7.8025360107421875
2023-01-24 00:50:10.164194: step: 400/469, loss: 9.999170303344727
2023-01-24 00:50:10.892849: step: 402/469, loss: 6.752676963806152
2023-01-24 00:50:11.495668: step: 404/469, loss: 4.343136787414551
2023-01-24 00:50:12.122035: step: 406/469, loss: 2.4729204177856445
2023-01-24 00:50:12.767974: step: 408/469, loss: 1.6550145149230957
2023-01-24 00:50:13.395820: step: 410/469, loss: 3.60208797454834
2023-01-24 00:50:14.063958: step: 412/469, loss: 5.994638919830322
2023-01-24 00:50:14.688006: step: 414/469, loss: 2.4971179962158203
2023-01-24 00:50:15.315665: step: 416/469, loss: 1.627087950706482
2023-01-24 00:50:15.908072: step: 418/469, loss: 1.1389089822769165
2023-01-24 00:50:16.564166: step: 420/469, loss: 2.5901660919189453
2023-01-24 00:50:17.184434: step: 422/469, loss: 5.187749862670898
2023-01-24 00:50:17.839094: step: 424/469, loss: 3.3282017707824707
2023-01-24 00:50:18.461721: step: 426/469, loss: 1.9786550998687744
2023-01-24 00:50:19.125285: step: 428/469, loss: 1.9001668691635132
2023-01-24 00:50:19.743354: step: 430/469, loss: 1.549994707107544
2023-01-24 00:50:20.418627: step: 432/469, loss: 1.5623385906219482
2023-01-24 00:50:21.029025: step: 434/469, loss: 1.4152212142944336
2023-01-24 00:50:21.615892: step: 436/469, loss: 5.6168107986450195
2023-01-24 00:50:22.214358: step: 438/469, loss: 4.321221828460693
2023-01-24 00:50:22.811350: step: 440/469, loss: 1.9432930946350098
2023-01-24 00:50:23.431312: step: 442/469, loss: 6.5523271560668945
2023-01-24 00:50:24.052071: step: 444/469, loss: 6.476694107055664
2023-01-24 00:50:24.685090: step: 446/469, loss: 5.213431358337402
2023-01-24 00:50:25.322317: step: 448/469, loss: 2.914058208465576
2023-01-24 00:50:25.946423: step: 450/469, loss: 2.643801212310791
2023-01-24 00:50:26.531416: step: 452/469, loss: 2.708839178085327
2023-01-24 00:50:27.172403: step: 454/469, loss: 2.0420830249786377
2023-01-24 00:50:27.829966: step: 456/469, loss: 3.3017520904541016
2023-01-24 00:50:28.434339: step: 458/469, loss: 2.964846611022949
2023-01-24 00:50:29.098859: step: 460/469, loss: 5.405810356140137
2023-01-24 00:50:29.674733: step: 462/469, loss: 1.0382235050201416
2023-01-24 00:50:30.313598: step: 464/469, loss: 5.912646293640137
2023-01-24 00:50:30.936988: step: 466/469, loss: 2.2638630867004395
2023-01-24 00:50:31.546441: step: 468/469, loss: 1.6986610889434814
2023-01-24 00:50:32.181481: step: 470/469, loss: 3.486217737197876
2023-01-24 00:50:32.792472: step: 472/469, loss: 1.7115916013717651
2023-01-24 00:50:33.504261: step: 474/469, loss: 1.375154733657837
2023-01-24 00:50:34.092965: step: 476/469, loss: 2.235123634338379
2023-01-24 00:50:34.766109: step: 478/469, loss: 0.8839229941368103
2023-01-24 00:50:35.422568: step: 480/469, loss: 4.83689546585083
2023-01-24 00:50:36.038146: step: 482/469, loss: 3.807434558868408
2023-01-24 00:50:36.652309: step: 484/469, loss: 2.270559310913086
2023-01-24 00:50:37.238197: step: 486/469, loss: 4.294483184814453
2023-01-24 00:50:37.923645: step: 488/469, loss: 2.208724021911621
2023-01-24 00:50:38.580749: step: 490/469, loss: 5.8313093185424805
2023-01-24 00:50:39.220131: step: 492/469, loss: 1.0127171277999878
2023-01-24 00:50:39.880374: step: 494/469, loss: 1.4656672477722168
2023-01-24 00:50:40.481286: step: 496/469, loss: 2.5641977787017822
2023-01-24 00:50:41.163640: step: 498/469, loss: 2.8379359245300293
2023-01-24 00:50:41.789427: step: 500/469, loss: 2.2115871906280518
2023-01-24 00:50:42.412911: step: 502/469, loss: 1.2317479848861694
2023-01-24 00:50:43.086015: step: 504/469, loss: 1.4589911699295044
2023-01-24 00:50:43.710768: step: 506/469, loss: 1.1911771297454834
2023-01-24 00:50:44.353593: step: 508/469, loss: 3.527251720428467
2023-01-24 00:50:44.997212: step: 510/469, loss: 0.5120771527290344
2023-01-24 00:50:45.610537: step: 512/469, loss: 0.37717804312705994
2023-01-24 00:50:46.284101: step: 514/469, loss: 8.541683197021484
2023-01-24 00:50:46.901555: step: 516/469, loss: 5.253645896911621
2023-01-24 00:50:47.502477: step: 518/469, loss: 1.1242091655731201
2023-01-24 00:50:48.122733: step: 520/469, loss: 2.308777093887329
2023-01-24 00:50:48.711537: step: 522/469, loss: 1.7971981763839722
2023-01-24 00:50:49.337928: step: 524/469, loss: 1.091801643371582
2023-01-24 00:50:49.949141: step: 526/469, loss: 0.8410761952400208
2023-01-24 00:50:50.558777: step: 528/469, loss: 7.412558555603027
2023-01-24 00:50:51.222637: step: 530/469, loss: 2.230325222015381
2023-01-24 00:50:51.843784: step: 532/469, loss: 1.1105403900146484
2023-01-24 00:50:52.430980: step: 534/469, loss: 1.8819019794464111
2023-01-24 00:50:53.074265: step: 536/469, loss: 3.5490570068359375
2023-01-24 00:50:53.725712: step: 538/469, loss: 3.6693639755249023
2023-01-24 00:50:54.351239: step: 540/469, loss: 0.673589289188385
2023-01-24 00:50:55.005061: step: 542/469, loss: 1.112943172454834
2023-01-24 00:50:55.612845: step: 544/469, loss: 1.9021234512329102
2023-01-24 00:50:56.318630: step: 546/469, loss: 3.3115804195404053
2023-01-24 00:50:56.873077: step: 548/469, loss: 2.3288450241088867
2023-01-24 00:50:57.487853: step: 550/469, loss: 1.0352078676223755
2023-01-24 00:50:58.107484: step: 552/469, loss: 1.2727808952331543
2023-01-24 00:50:58.743874: step: 554/469, loss: 0.9366053342819214
2023-01-24 00:50:59.408943: step: 556/469, loss: 0.9389679431915283
2023-01-24 00:51:00.037089: step: 558/469, loss: 4.485273361206055
2023-01-24 00:51:00.698229: step: 560/469, loss: 3.1431937217712402
2023-01-24 00:51:01.291599: step: 562/469, loss: 2.523747682571411
2023-01-24 00:51:01.951826: step: 564/469, loss: 29.507835388183594
2023-01-24 00:51:02.584643: step: 566/469, loss: 1.6524688005447388
2023-01-24 00:51:03.217756: step: 568/469, loss: 1.1085619926452637
2023-01-24 00:51:03.847243: step: 570/469, loss: 1.5616161823272705
2023-01-24 00:51:04.555929: step: 572/469, loss: 3.4873030185699463
2023-01-24 00:51:05.199315: step: 574/469, loss: 7.625667572021484
2023-01-24 00:51:05.881635: step: 576/469, loss: 2.3042359352111816
2023-01-24 00:51:06.622864: step: 578/469, loss: 2.9243178367614746
2023-01-24 00:51:07.246372: step: 580/469, loss: 9.828018188476562
2023-01-24 00:51:07.855772: step: 582/469, loss: 2.924833059310913
2023-01-24 00:51:08.533224: step: 584/469, loss: 3.211275100708008
2023-01-24 00:51:09.166415: step: 586/469, loss: 9.504095077514648
2023-01-24 00:51:09.809917: step: 588/469, loss: 3.026228666305542
2023-01-24 00:51:10.443955: step: 590/469, loss: 3.233726739883423
2023-01-24 00:51:11.083617: step: 592/469, loss: 2.781447649002075
2023-01-24 00:51:11.796248: step: 594/469, loss: 1.2948658466339111
2023-01-24 00:51:12.460636: step: 596/469, loss: 2.5743391513824463
2023-01-24 00:51:13.162761: step: 598/469, loss: 2.1096224784851074
2023-01-24 00:51:13.785964: step: 600/469, loss: 2.6158783435821533
2023-01-24 00:51:14.438463: step: 602/469, loss: 1.2256364822387695
2023-01-24 00:51:15.052443: step: 604/469, loss: 2.1764283180236816
2023-01-24 00:51:15.745260: step: 606/469, loss: 3.365410327911377
2023-01-24 00:51:16.348693: step: 608/469, loss: 2.545825242996216
2023-01-24 00:51:16.919318: step: 610/469, loss: 2.083864450454712
2023-01-24 00:51:17.553242: step: 612/469, loss: 2.2250077724456787
2023-01-24 00:51:18.148270: step: 614/469, loss: 2.8714287281036377
2023-01-24 00:51:18.794004: step: 616/469, loss: 1.2265431880950928
2023-01-24 00:51:19.455937: step: 618/469, loss: 2.6019041538238525
2023-01-24 00:51:20.056422: step: 620/469, loss: 1.0531139373779297
2023-01-24 00:51:20.632026: step: 622/469, loss: 1.9407305717468262
2023-01-24 00:51:21.296393: step: 624/469, loss: 2.221311330795288
2023-01-24 00:51:21.900500: step: 626/469, loss: 2.031471014022827
2023-01-24 00:51:22.535910: step: 628/469, loss: 1.2906171083450317
2023-01-24 00:51:23.214274: step: 630/469, loss: 3.350187063217163
2023-01-24 00:51:23.846592: step: 632/469, loss: 1.5802769660949707
2023-01-24 00:51:24.468032: step: 634/469, loss: 2.8914926052093506
2023-01-24 00:51:25.006982: step: 636/469, loss: 1.4508517980575562
2023-01-24 00:51:25.684817: step: 638/469, loss: 0.6638691425323486
2023-01-24 00:51:26.305378: step: 640/469, loss: 1.0972434282302856
2023-01-24 00:51:26.917218: step: 642/469, loss: 2.6330790519714355
2023-01-24 00:51:27.523803: step: 644/469, loss: 1.5233993530273438
2023-01-24 00:51:28.103875: step: 646/469, loss: 2.0933659076690674
2023-01-24 00:51:28.705596: step: 648/469, loss: 1.0653287172317505
2023-01-24 00:51:29.380391: step: 650/469, loss: 5.881309509277344
2023-01-24 00:51:30.071358: step: 652/469, loss: 3.5361099243164062
2023-01-24 00:51:30.797148: step: 654/469, loss: 2.0320074558258057
2023-01-24 00:51:31.418974: step: 656/469, loss: 1.1001843214035034
2023-01-24 00:51:32.098564: step: 658/469, loss: 2.1982741355895996
2023-01-24 00:51:32.705068: step: 660/469, loss: 0.8307514190673828
2023-01-24 00:51:33.378439: step: 662/469, loss: 1.8594615459442139
2023-01-24 00:51:34.015148: step: 664/469, loss: 0.6427603363990784
2023-01-24 00:51:34.740290: step: 666/469, loss: 1.2357300519943237
2023-01-24 00:51:35.340315: step: 668/469, loss: 1.6569201946258545
2023-01-24 00:51:35.914497: step: 670/469, loss: 4.301616668701172
2023-01-24 00:51:36.579758: step: 672/469, loss: 0.4775109887123108
2023-01-24 00:51:37.240894: step: 674/469, loss: 7.053918838500977
2023-01-24 00:51:37.858693: step: 676/469, loss: 0.4933178722858429
2023-01-24 00:51:38.689170: step: 678/469, loss: 11.713030815124512
2023-01-24 00:51:39.321700: step: 680/469, loss: 1.852529764175415
2023-01-24 00:51:39.983550: step: 682/469, loss: 1.1127151250839233
2023-01-24 00:51:40.618472: step: 684/469, loss: 1.204505443572998
2023-01-24 00:51:41.215842: step: 686/469, loss: 1.263776183128357
2023-01-24 00:51:41.844615: step: 688/469, loss: 6.019697189331055
2023-01-24 00:51:42.487503: step: 690/469, loss: 2.318279981613159
2023-01-24 00:51:43.174182: step: 692/469, loss: 0.42347732186317444
2023-01-24 00:51:43.821350: step: 694/469, loss: 3.384830951690674
2023-01-24 00:51:44.510043: step: 696/469, loss: 0.8585728406906128
2023-01-24 00:51:45.140157: step: 698/469, loss: 2.9020438194274902
2023-01-24 00:51:45.735690: step: 700/469, loss: 1.2200758457183838
2023-01-24 00:51:46.371089: step: 702/469, loss: 1.8751510381698608
2023-01-24 00:51:47.001255: step: 704/469, loss: 4.669819355010986
2023-01-24 00:51:47.705100: step: 706/469, loss: 2.9634554386138916
2023-01-24 00:51:48.331687: step: 708/469, loss: 1.1599161624908447
2023-01-24 00:51:48.916564: step: 710/469, loss: 0.8766475915908813
2023-01-24 00:51:49.535757: step: 712/469, loss: 1.331620454788208
2023-01-24 00:51:50.148257: step: 714/469, loss: 2.1192688941955566
2023-01-24 00:51:50.818583: step: 716/469, loss: 1.7069741487503052
2023-01-24 00:51:51.441241: step: 718/469, loss: 2.662444591522217
2023-01-24 00:51:52.007019: step: 720/469, loss: 2.0508873462677
2023-01-24 00:51:52.607348: step: 722/469, loss: 0.8278382420539856
2023-01-24 00:51:53.270256: step: 724/469, loss: 0.6639025211334229
2023-01-24 00:51:53.988151: step: 726/469, loss: 4.585159778594971
2023-01-24 00:51:54.618299: step: 728/469, loss: 0.5474594235420227
2023-01-24 00:51:55.306754: step: 730/469, loss: 2.0028669834136963
2023-01-24 00:51:55.975232: step: 732/469, loss: 2.336195945739746
2023-01-24 00:51:56.632753: step: 734/469, loss: 2.4578120708465576
2023-01-24 00:51:57.301050: step: 736/469, loss: 1.6725635528564453
2023-01-24 00:51:57.915719: step: 738/469, loss: 2.13787579536438
2023-01-24 00:51:58.584995: step: 740/469, loss: 1.5839296579360962
2023-01-24 00:51:59.219628: step: 742/469, loss: 6.753298759460449
2023-01-24 00:51:59.827533: step: 744/469, loss: 1.4909178018569946
2023-01-24 00:52:00.493379: step: 746/469, loss: 0.5993936061859131
2023-01-24 00:52:01.116171: step: 748/469, loss: 8.058149337768555
2023-01-24 00:52:01.826947: step: 750/469, loss: 0.4440227150917053
2023-01-24 00:52:02.478080: step: 752/469, loss: 1.278122067451477
2023-01-24 00:52:03.137099: step: 754/469, loss: 1.295558214187622
2023-01-24 00:52:03.750015: step: 756/469, loss: 6.894983768463135
2023-01-24 00:52:04.394212: step: 758/469, loss: 5.87663459777832
2023-01-24 00:52:05.041074: step: 760/469, loss: 0.998386800289154
2023-01-24 00:52:05.602505: step: 762/469, loss: 0.8195573687553406
2023-01-24 00:52:06.217503: step: 764/469, loss: 3.0501463413238525
2023-01-24 00:52:06.901211: step: 766/469, loss: 4.492542743682861
2023-01-24 00:52:07.587111: step: 768/469, loss: 1.9226833581924438
2023-01-24 00:52:08.240372: step: 770/469, loss: 0.6186398863792419
2023-01-24 00:52:08.819445: step: 772/469, loss: 1.1675491333007812
2023-01-24 00:52:09.382831: step: 774/469, loss: 2.159048080444336
2023-01-24 00:52:09.970164: step: 776/469, loss: 1.388982892036438
2023-01-24 00:52:10.608437: step: 778/469, loss: 1.492708683013916
2023-01-24 00:52:11.312376: step: 780/469, loss: 2.3841464519500732
2023-01-24 00:52:11.992963: step: 782/469, loss: 7.847356796264648
2023-01-24 00:52:12.646112: step: 784/469, loss: 3.5350546836853027
2023-01-24 00:52:13.341368: step: 786/469, loss: 5.889021873474121
2023-01-24 00:52:13.918922: step: 788/469, loss: 1.210557460784912
2023-01-24 00:52:14.587911: step: 790/469, loss: 4.059767723083496
2023-01-24 00:52:15.210096: step: 792/469, loss: 1.8310210704803467
2023-01-24 00:52:15.824125: step: 794/469, loss: 0.7778642773628235
2023-01-24 00:52:16.416475: step: 796/469, loss: 4.306910514831543
2023-01-24 00:52:17.136222: step: 798/469, loss: 3.923731565475464
2023-01-24 00:52:17.766411: step: 800/469, loss: 2.197035312652588
2023-01-24 00:52:18.424090: step: 802/469, loss: 0.8405678272247314
2023-01-24 00:52:19.023204: step: 804/469, loss: 0.9253308773040771
2023-01-24 00:52:19.606921: step: 806/469, loss: 1.0027258396148682
2023-01-24 00:52:20.244892: step: 808/469, loss: 2.245345115661621
2023-01-24 00:52:20.929792: step: 810/469, loss: 1.8663848638534546
2023-01-24 00:52:21.505358: step: 812/469, loss: 4.9495134353637695
2023-01-24 00:52:22.073739: step: 814/469, loss: 6.545098304748535
2023-01-24 00:52:22.687447: step: 816/469, loss: 0.43992239236831665
2023-01-24 00:52:23.311018: step: 818/469, loss: 3.352154493331909
2023-01-24 00:52:23.903653: step: 820/469, loss: 1.6969307661056519
2023-01-24 00:52:24.524551: step: 822/469, loss: 2.3811986446380615
2023-01-24 00:52:25.129285: step: 824/469, loss: 8.892226219177246
2023-01-24 00:52:25.725581: step: 826/469, loss: 7.079122543334961
2023-01-24 00:52:26.358687: step: 828/469, loss: 1.0855681896209717
2023-01-24 00:52:27.029125: step: 830/469, loss: 0.5330224633216858
2023-01-24 00:52:27.620154: step: 832/469, loss: 1.5775420665740967
2023-01-24 00:52:28.234921: step: 834/469, loss: 0.6331006288528442
2023-01-24 00:52:28.873243: step: 836/469, loss: 3.898449182510376
2023-01-24 00:52:29.622463: step: 838/469, loss: 1.4449671506881714
2023-01-24 00:52:30.464761: step: 840/469, loss: 2.1984500885009766
2023-01-24 00:52:31.102300: step: 842/469, loss: 1.5962657928466797
2023-01-24 00:52:31.658080: step: 844/469, loss: 2.144331455230713
2023-01-24 00:52:32.317508: step: 846/469, loss: 15.531341552734375
2023-01-24 00:52:32.954055: step: 848/469, loss: 1.8532617092132568
2023-01-24 00:52:33.556766: step: 850/469, loss: 0.6547366380691528
2023-01-24 00:52:34.176522: step: 852/469, loss: 2.006427764892578
2023-01-24 00:52:34.769869: step: 854/469, loss: 1.9097877740859985
2023-01-24 00:52:35.331260: step: 856/469, loss: 1.9105238914489746
2023-01-24 00:52:36.010554: step: 858/469, loss: 1.0565221309661865
2023-01-24 00:52:36.625925: step: 860/469, loss: 0.807134747505188
2023-01-24 00:52:37.284910: step: 862/469, loss: 0.49223843216896057
2023-01-24 00:52:37.923212: step: 864/469, loss: 2.2668728828430176
2023-01-24 00:52:38.546365: step: 866/469, loss: 1.8541752099990845
2023-01-24 00:52:39.101611: step: 868/469, loss: 1.8676748275756836
2023-01-24 00:52:39.799989: step: 870/469, loss: 1.1457188129425049
2023-01-24 00:52:40.527546: step: 872/469, loss: 2.078320026397705
2023-01-24 00:52:41.149067: step: 874/469, loss: 0.7892571687698364
2023-01-24 00:52:41.704251: step: 876/469, loss: 0.4894615709781647
2023-01-24 00:52:42.388096: step: 878/469, loss: 10.354825973510742
2023-01-24 00:52:43.046094: step: 880/469, loss: 1.5977815389633179
2023-01-24 00:52:43.639721: step: 882/469, loss: 0.6383422613143921
2023-01-24 00:52:44.337569: step: 884/469, loss: 1.309027075767517
2023-01-24 00:52:45.041044: step: 886/469, loss: 4.253027439117432
2023-01-24 00:52:45.655707: step: 888/469, loss: 1.439487099647522
2023-01-24 00:52:46.374615: step: 890/469, loss: 2.6710166931152344
2023-01-24 00:52:46.995510: step: 892/469, loss: 0.7880006432533264
2023-01-24 00:52:47.631448: step: 894/469, loss: 1.1811531782150269
2023-01-24 00:52:48.342153: step: 896/469, loss: 2.1026933193206787
2023-01-24 00:52:48.963127: step: 898/469, loss: 2.2342774868011475
2023-01-24 00:52:49.634327: step: 900/469, loss: 3.9589414596557617
2023-01-24 00:52:50.242614: step: 902/469, loss: 1.32570219039917
2023-01-24 00:52:50.877337: step: 904/469, loss: 1.8051782846450806
2023-01-24 00:52:51.500098: step: 906/469, loss: 0.7008894085884094
2023-01-24 00:52:52.133935: step: 908/469, loss: 2.1311097145080566
2023-01-24 00:52:52.786625: step: 910/469, loss: 1.001122236251831
2023-01-24 00:52:53.396541: step: 912/469, loss: 1.2099871635437012
2023-01-24 00:52:54.076258: step: 914/469, loss: 0.3105977177619934
2023-01-24 00:52:54.739107: step: 916/469, loss: 2.5670032501220703
2023-01-24 00:52:55.354059: step: 918/469, loss: 3.0132174491882324
2023-01-24 00:52:55.943219: step: 920/469, loss: 0.9042558670043945
2023-01-24 00:52:56.569587: step: 922/469, loss: 5.169037818908691
2023-01-24 00:52:57.142673: step: 924/469, loss: 5.225088119506836
2023-01-24 00:52:57.726380: step: 926/469, loss: 3.599080801010132
2023-01-24 00:52:58.355768: step: 928/469, loss: 1.2377464771270752
2023-01-24 00:52:58.988984: step: 930/469, loss: 3.1070525646209717
2023-01-24 00:52:59.650033: step: 932/469, loss: 1.3288240432739258
2023-01-24 00:53:00.324840: step: 934/469, loss: 3.260507106781006
2023-01-24 00:53:00.923896: step: 936/469, loss: 3.220916748046875
2023-01-24 00:53:01.589521: step: 938/469, loss: 1.1544103622436523
==================================================
Loss: 5.462
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3336439542684174, 'r': 0.1772286411142255, 'f1': 0.23149123740598837}, 'combined': 0.17057249072020195, 'epoch': 0}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.24617813588850174, 'r': 0.09200823674957677, 'f1': 0.13395227035737983}, 'combined': 0.07306487474038899, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32467987037503143, 'r': 0.16817067009973274, 'f1': 0.22157480568557564}, 'combined': 0.16326564629463466, 'epoch': 0}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2590798361794456, 'r': 0.09052471073057972, 'f1': 0.13416946337546473}, 'combined': 0.0731833436593444, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32113235356491493, 'r': 0.1645120374595311, 'f1': 0.2175671695402299}, 'combined': 0.16031265124016938, 'epoch': 0}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2558840388007055, 'r': 0.09446949472587578, 'f1': 0.13799338976602626}, 'combined': 0.07526912169055977, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2857142857142857, 'r': 0.17142857142857143, 'f1': 0.21428571428571427}, 'combined': 0.14285714285714285, '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': 0.625, 'r': 0.12931034482758622, 'f1': 0.2142857142857143}, 'combined': 0.14285714285714285, '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': 0.3336439542684174, 'r': 0.1772286411142255, 'f1': 0.23149123740598837}, 'combined': 0.17057249072020195, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.24617813588850174, 'r': 0.09200823674957677, 'f1': 0.13395227035737983}, 'combined': 0.07306487474038899, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2857142857142857, 'r': 0.17142857142857143, 'f1': 0.21428571428571427}, 'combined': 0.14285714285714285, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32467987037503143, 'r': 0.16817067009973274, 'f1': 0.22157480568557564}, 'combined': 0.16326564629463466, 'epoch': 0}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2590798361794456, 'r': 0.09052471073057972, 'f1': 0.13416946337546473}, 'combined': 0.0731833436593444, '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': 0.32113235356491493, 'r': 0.1645120374595311, 'f1': 0.2175671695402299}, 'combined': 0.16031265124016938, 'epoch': 0}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2558840388007055, 'r': 0.09446949472587578, 'f1': 0.13799338976602626}, 'combined': 0.07526912169055977, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.12931034482758622, 'f1': 0.2142857142857143}, 'combined': 0.14285714285714285, '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
2023-01-24 00:56:03.799827: step: 2/469, loss: 0.9774237275123596
2023-01-24 00:56:04.489134: step: 4/469, loss: 6.636249542236328
2023-01-24 00:56:05.089629: step: 6/469, loss: 1.990834355354309
2023-01-24 00:56:05.839914: step: 8/469, loss: 1.2279059886932373
2023-01-24 00:56:06.444511: step: 10/469, loss: 2.2220447063446045
2023-01-24 00:56:07.089403: step: 12/469, loss: 1.0082879066467285
2023-01-24 00:56:07.679709: step: 14/469, loss: 2.0571486949920654
2023-01-24 00:56:08.335279: step: 16/469, loss: 3.718430995941162
2023-01-24 00:56:08.932954: step: 18/469, loss: 1.8861489295959473
2023-01-24 00:56:09.617117: step: 20/469, loss: 4.982763767242432
2023-01-24 00:56:10.279609: step: 22/469, loss: 1.4882051944732666
2023-01-24 00:56:10.882215: step: 24/469, loss: 0.5637761950492859
2023-01-24 00:56:11.542169: step: 26/469, loss: 0.5937745571136475
2023-01-24 00:56:12.172945: step: 28/469, loss: 5.643711566925049
2023-01-24 00:56:12.796747: step: 30/469, loss: 2.5158143043518066
2023-01-24 00:56:13.461112: step: 32/469, loss: 3.539027690887451
2023-01-24 00:56:14.119490: step: 34/469, loss: 1.1145998239517212
2023-01-24 00:56:14.709502: step: 36/469, loss: 3.8723175525665283
2023-01-24 00:56:15.311938: step: 38/469, loss: 2.6833505630493164
2023-01-24 00:56:15.962258: step: 40/469, loss: 2.282891273498535
2023-01-24 00:56:16.584989: step: 42/469, loss: 1.2406158447265625
2023-01-24 00:56:17.206165: step: 44/469, loss: 0.4674290418624878
2023-01-24 00:56:17.808876: step: 46/469, loss: 4.22768497467041
2023-01-24 00:56:18.404958: step: 48/469, loss: 1.3391175270080566
2023-01-24 00:56:18.974977: step: 50/469, loss: 0.47300630807876587
2023-01-24 00:56:19.604044: step: 52/469, loss: 1.3602882623672485
2023-01-24 00:56:20.221388: step: 54/469, loss: 4.702951908111572
2023-01-24 00:56:20.888755: step: 56/469, loss: 0.9324207901954651
2023-01-24 00:56:21.460563: step: 58/469, loss: 3.174039363861084
2023-01-24 00:56:22.064794: step: 60/469, loss: 1.0151244401931763
2023-01-24 00:56:22.660213: step: 62/469, loss: 7.272899627685547
2023-01-24 00:56:23.326315: step: 64/469, loss: 1.0152450799942017
2023-01-24 00:56:23.892717: step: 66/469, loss: 2.161332368850708
2023-01-24 00:56:24.510811: step: 68/469, loss: 1.2895456552505493
2023-01-24 00:56:25.126719: step: 70/469, loss: 0.6681989431381226
2023-01-24 00:56:25.741056: step: 72/469, loss: 1.1446471214294434
2023-01-24 00:56:26.341367: step: 74/469, loss: 2.418056011199951
2023-01-24 00:56:26.980203: step: 76/469, loss: 2.500084400177002
2023-01-24 00:56:27.648283: step: 78/469, loss: 4.361448287963867
2023-01-24 00:56:28.237368: step: 80/469, loss: 10.124239921569824
2023-01-24 00:56:28.900363: step: 82/469, loss: 6.290243148803711
2023-01-24 00:56:29.490847: step: 84/469, loss: 0.88554447889328
2023-01-24 00:56:30.098432: step: 86/469, loss: 4.046614646911621
2023-01-24 00:56:30.736787: step: 88/469, loss: 3.138495922088623
2023-01-24 00:56:31.442718: step: 90/469, loss: 2.158499240875244
2023-01-24 00:56:32.140022: step: 92/469, loss: 2.5786585807800293
2023-01-24 00:56:32.821055: step: 94/469, loss: 14.496940612792969
2023-01-24 00:56:33.495864: step: 96/469, loss: 0.9019399285316467
2023-01-24 00:56:34.193015: step: 98/469, loss: 5.931264400482178
2023-01-24 00:56:34.793871: step: 100/469, loss: 0.28076714277267456
2023-01-24 00:56:35.417648: step: 102/469, loss: 2.052495002746582
2023-01-24 00:56:36.019224: step: 104/469, loss: 1.6943092346191406
2023-01-24 00:56:36.613563: step: 106/469, loss: 1.6038990020751953
2023-01-24 00:56:37.211916: step: 108/469, loss: 2.9601356983184814
2023-01-24 00:56:37.778656: step: 110/469, loss: 0.3992002010345459
2023-01-24 00:56:38.411169: step: 112/469, loss: 1.721425175666809
2023-01-24 00:56:39.097559: step: 114/469, loss: 1.7144372463226318
2023-01-24 00:56:39.822644: step: 116/469, loss: 1.106978416442871
2023-01-24 00:56:40.410145: step: 118/469, loss: 1.5618661642074585
2023-01-24 00:56:41.097277: step: 120/469, loss: 4.940499782562256
2023-01-24 00:56:41.704222: step: 122/469, loss: 1.1992238759994507
2023-01-24 00:56:42.408481: step: 124/469, loss: 2.4845125675201416
2023-01-24 00:56:43.091265: step: 126/469, loss: 0.6097687482833862
2023-01-24 00:56:43.665576: step: 128/469, loss: 0.7245121002197266
2023-01-24 00:56:44.314587: step: 130/469, loss: 0.5907683968544006
2023-01-24 00:56:44.990622: step: 132/469, loss: 0.4911862909793854
2023-01-24 00:56:45.668730: step: 134/469, loss: 1.2377562522888184
2023-01-24 00:56:46.303811: step: 136/469, loss: 0.9672662019729614
2023-01-24 00:56:46.939868: step: 138/469, loss: 1.845298409461975
2023-01-24 00:56:47.529931: step: 140/469, loss: 1.1161091327667236
2023-01-24 00:56:48.115485: step: 142/469, loss: 0.8173484802246094
2023-01-24 00:56:48.786909: step: 144/469, loss: 0.5894840955734253
2023-01-24 00:56:49.414162: step: 146/469, loss: 4.70170783996582
2023-01-24 00:56:50.034850: step: 148/469, loss: 0.27044326066970825
2023-01-24 00:56:50.621708: step: 150/469, loss: 1.4389760494232178
2023-01-24 00:56:51.212709: step: 152/469, loss: 0.5464712977409363
2023-01-24 00:56:51.818876: step: 154/469, loss: 1.8928881883621216
2023-01-24 00:56:52.434000: step: 156/469, loss: 4.485570430755615
2023-01-24 00:56:53.179447: step: 158/469, loss: 5.045022964477539
2023-01-24 00:56:53.821219: step: 160/469, loss: 0.9949291944503784
2023-01-24 00:56:54.440747: step: 162/469, loss: 4.282439708709717
2023-01-24 00:56:55.075648: step: 164/469, loss: 1.9260460138320923
2023-01-24 00:56:55.753533: step: 166/469, loss: 5.081108093261719
2023-01-24 00:56:56.416661: step: 168/469, loss: 1.3129239082336426
2023-01-24 00:56:56.992990: step: 170/469, loss: 0.8752832412719727
2023-01-24 00:56:57.638029: step: 172/469, loss: 1.3963277339935303
2023-01-24 00:56:58.290500: step: 174/469, loss: 2.5459213256835938
2023-01-24 00:56:58.881528: step: 176/469, loss: 7.6412248611450195
2023-01-24 00:56:59.478277: step: 178/469, loss: 1.6908068656921387
2023-01-24 00:57:00.078984: step: 180/469, loss: 2.211958169937134
2023-01-24 00:57:00.716232: step: 182/469, loss: 1.1137548685073853
2023-01-24 00:57:01.293420: step: 184/469, loss: 0.7184733748435974
2023-01-24 00:57:01.964543: step: 186/469, loss: 1.2796401977539062
2023-01-24 00:57:02.540141: step: 188/469, loss: 2.113682746887207
2023-01-24 00:57:03.164275: step: 190/469, loss: 2.014291763305664
2023-01-24 00:57:03.793618: step: 192/469, loss: 0.6369805932044983
2023-01-24 00:57:04.402316: step: 194/469, loss: 19.249549865722656
2023-01-24 00:57:05.071651: step: 196/469, loss: 1.919909954071045
2023-01-24 00:57:05.716630: step: 198/469, loss: 1.2311121225357056
2023-01-24 00:57:06.363766: step: 200/469, loss: 3.7839255332946777
2023-01-24 00:57:07.027905: step: 202/469, loss: 1.2812457084655762
2023-01-24 00:57:07.674626: step: 204/469, loss: 0.6068203449249268
2023-01-24 00:57:08.302796: step: 206/469, loss: 1.3794814348220825
2023-01-24 00:57:08.928396: step: 208/469, loss: 1.9105955362319946
2023-01-24 00:57:09.527831: step: 210/469, loss: 0.36456459760665894
2023-01-24 00:57:10.201377: step: 212/469, loss: 0.7991377115249634
2023-01-24 00:57:10.801403: step: 214/469, loss: 1.475459098815918
2023-01-24 00:57:11.485971: step: 216/469, loss: 1.1212122440338135
2023-01-24 00:57:12.125427: step: 218/469, loss: 0.34821829199790955
2023-01-24 00:57:12.765521: step: 220/469, loss: 9.339518547058105
2023-01-24 00:57:13.442572: step: 222/469, loss: 0.6210970878601074
2023-01-24 00:57:14.039437: step: 224/469, loss: 0.5798214077949524
2023-01-24 00:57:14.655635: step: 226/469, loss: 2.763742208480835
2023-01-24 00:57:15.270752: step: 228/469, loss: 0.3588736951351166
2023-01-24 00:57:15.917871: step: 230/469, loss: 1.1018152236938477
2023-01-24 00:57:16.521584: step: 232/469, loss: 0.42224645614624023
2023-01-24 00:57:17.183329: step: 234/469, loss: 1.294297456741333
2023-01-24 00:57:17.825250: step: 236/469, loss: 9.18282413482666
2023-01-24 00:57:18.398603: step: 238/469, loss: 4.582605838775635
2023-01-24 00:57:19.075829: step: 240/469, loss: 1.3106979131698608
2023-01-24 00:57:19.755401: step: 242/469, loss: 1.0300555229187012
2023-01-24 00:57:20.401398: step: 244/469, loss: 0.8543984889984131
2023-01-24 00:57:21.022268: step: 246/469, loss: 0.404795378446579
2023-01-24 00:57:21.654562: step: 248/469, loss: 0.4309930205345154
2023-01-24 00:57:22.284191: step: 250/469, loss: 0.9510715007781982
2023-01-24 00:57:23.006240: step: 252/469, loss: 1.3495937585830688
2023-01-24 00:57:23.670414: step: 254/469, loss: 1.5015547275543213
2023-01-24 00:57:24.251698: step: 256/469, loss: 1.1266480684280396
2023-01-24 00:57:24.905104: step: 258/469, loss: 10.146392822265625
2023-01-24 00:57:25.480006: step: 260/469, loss: 2.3589329719543457
2023-01-24 00:57:26.135114: step: 262/469, loss: 1.3057126998901367
2023-01-24 00:57:26.795710: step: 264/469, loss: 1.6830081939697266
2023-01-24 00:57:27.372782: step: 266/469, loss: 0.7595487833023071
2023-01-24 00:57:27.980080: step: 268/469, loss: 1.0855481624603271
2023-01-24 00:57:28.626532: step: 270/469, loss: 0.8032743334770203
2023-01-24 00:57:29.315373: step: 272/469, loss: 0.6891888380050659
2023-01-24 00:57:29.880308: step: 274/469, loss: 0.5035603642463684
2023-01-24 00:57:30.554826: step: 276/469, loss: 3.7007110118865967
2023-01-24 00:57:31.213806: step: 278/469, loss: 0.6537836790084839
2023-01-24 00:57:31.910025: step: 280/469, loss: 1.039383053779602
2023-01-24 00:57:32.512690: step: 282/469, loss: 0.5192900896072388
2023-01-24 00:57:33.169040: step: 284/469, loss: 0.5746899843215942
2023-01-24 00:57:33.745658: step: 286/469, loss: 0.7903205156326294
2023-01-24 00:57:34.343263: step: 288/469, loss: 0.4842279255390167
2023-01-24 00:57:34.961322: step: 290/469, loss: 0.2623206079006195
2023-01-24 00:57:35.600834: step: 292/469, loss: 1.2897734642028809
2023-01-24 00:57:36.261993: step: 294/469, loss: 3.3858587741851807
2023-01-24 00:57:36.851085: step: 296/469, loss: 2.190295457839966
2023-01-24 00:57:37.504883: step: 298/469, loss: 0.24754571914672852
2023-01-24 00:57:38.157628: step: 300/469, loss: 0.7817400693893433
2023-01-24 00:57:38.779002: step: 302/469, loss: 0.5100713968276978
2023-01-24 00:57:39.353827: step: 304/469, loss: 0.37411972880363464
2023-01-24 00:57:39.944026: step: 306/469, loss: 2.3437163829803467
2023-01-24 00:57:40.672013: step: 308/469, loss: 1.5898593664169312
2023-01-24 00:57:41.351344: step: 310/469, loss: 1.0790491104125977
2023-01-24 00:57:42.031848: step: 312/469, loss: 0.24286043643951416
2023-01-24 00:57:42.631818: step: 314/469, loss: 5.71418571472168
2023-01-24 00:57:43.269932: step: 316/469, loss: 1.5091514587402344
2023-01-24 00:57:43.985288: step: 318/469, loss: 0.9952667951583862
2023-01-24 00:57:44.669535: step: 320/469, loss: 0.8960474729537964
2023-01-24 00:57:45.247935: step: 322/469, loss: 4.323493957519531
2023-01-24 00:57:45.878375: step: 324/469, loss: 0.9344325661659241
2023-01-24 00:57:46.560126: step: 326/469, loss: 0.7204203009605408
2023-01-24 00:57:47.167658: step: 328/469, loss: 0.5804534554481506
2023-01-24 00:57:47.824225: step: 330/469, loss: 0.6996358036994934
2023-01-24 00:57:48.565107: step: 332/469, loss: 3.4042019844055176
2023-01-24 00:57:49.223918: step: 334/469, loss: 0.8509220480918884
2023-01-24 00:57:49.897337: step: 336/469, loss: 1.7719075679779053
2023-01-24 00:57:50.478757: step: 338/469, loss: 0.34857359528541565
2023-01-24 00:57:51.100215: step: 340/469, loss: 1.335108757019043
2023-01-24 00:57:51.774549: step: 342/469, loss: 0.5170474648475647
2023-01-24 00:57:52.471413: step: 344/469, loss: 2.5913052558898926
2023-01-24 00:57:53.117318: step: 346/469, loss: 3.233607769012451
2023-01-24 00:57:53.721354: step: 348/469, loss: 3.2166647911071777
2023-01-24 00:57:54.365290: step: 350/469, loss: 0.8338192105293274
2023-01-24 00:57:54.995489: step: 352/469, loss: 3.7104640007019043
2023-01-24 00:57:55.628145: step: 354/469, loss: 1.0243717432022095
2023-01-24 00:57:56.252434: step: 356/469, loss: 1.4346163272857666
2023-01-24 00:57:56.865430: step: 358/469, loss: 0.8183726668357849
2023-01-24 00:57:57.494333: step: 360/469, loss: 5.192439079284668
2023-01-24 00:57:58.182323: step: 362/469, loss: 6.544826507568359
2023-01-24 00:57:58.804807: step: 364/469, loss: 0.6790279746055603
2023-01-24 00:57:59.527942: step: 366/469, loss: 0.9295821785926819
2023-01-24 00:58:00.088926: step: 368/469, loss: 1.3576148748397827
2023-01-24 00:58:00.750694: step: 370/469, loss: 0.5722967386245728
2023-01-24 00:58:01.416005: step: 372/469, loss: 0.6305257678031921
2023-01-24 00:58:02.066207: step: 374/469, loss: 1.633368968963623
2023-01-24 00:58:02.728043: step: 376/469, loss: 3.1764259338378906
2023-01-24 00:58:03.384348: step: 378/469, loss: 0.44796910881996155
2023-01-24 00:58:04.037841: step: 380/469, loss: 0.6575629711151123
2023-01-24 00:58:04.680265: step: 382/469, loss: 1.8687303066253662
2023-01-24 00:58:05.286927: step: 384/469, loss: 1.4110556840896606
2023-01-24 00:58:05.964730: step: 386/469, loss: 1.8152185678482056
2023-01-24 00:58:06.540496: step: 388/469, loss: 0.3786051571369171
2023-01-24 00:58:07.204498: step: 390/469, loss: 4.476983070373535
2023-01-24 00:58:07.891002: step: 392/469, loss: 2.22505259513855
2023-01-24 00:58:08.546194: step: 394/469, loss: 1.1761585474014282
2023-01-24 00:58:09.206026: step: 396/469, loss: 2.04634952545166
2023-01-24 00:58:09.795128: step: 398/469, loss: 5.857431411743164
2023-01-24 00:58:10.349921: step: 400/469, loss: 1.104049801826477
2023-01-24 00:58:10.983828: step: 402/469, loss: 0.5394413471221924
2023-01-24 00:58:11.598779: step: 404/469, loss: 0.927696943283081
2023-01-24 00:58:12.255477: step: 406/469, loss: 5.998225688934326
2023-01-24 00:58:12.888818: step: 408/469, loss: 0.5810955762863159
2023-01-24 00:58:13.550500: step: 410/469, loss: 1.7282037734985352
2023-01-24 00:58:14.156240: step: 412/469, loss: 2.7687971591949463
2023-01-24 00:58:14.823985: step: 414/469, loss: 2.0616419315338135
2023-01-24 00:58:15.420429: step: 416/469, loss: 0.9342669248580933
2023-01-24 00:58:16.041608: step: 418/469, loss: 1.6862801313400269
2023-01-24 00:58:16.678534: step: 420/469, loss: 2.388059139251709
2023-01-24 00:58:17.279252: step: 422/469, loss: 0.32551687955856323
2023-01-24 00:58:17.912516: step: 424/469, loss: 1.7422549724578857
2023-01-24 00:58:18.554493: step: 426/469, loss: 0.2748425006866455
2023-01-24 00:58:19.222602: step: 428/469, loss: 0.4891715347766876
2023-01-24 00:58:19.875915: step: 430/469, loss: 2.017852306365967
2023-01-24 00:58:20.521036: step: 432/469, loss: 1.773969292640686
2023-01-24 00:58:21.164206: step: 434/469, loss: 0.3198941648006439
2023-01-24 00:58:21.842179: step: 436/469, loss: 1.1070201396942139
2023-01-24 00:58:22.442181: step: 438/469, loss: 2.6657259464263916
2023-01-24 00:58:23.128604: step: 440/469, loss: 0.3954508602619171
2023-01-24 00:58:23.706385: step: 442/469, loss: 0.5992934107780457
2023-01-24 00:58:24.324139: step: 444/469, loss: 1.867953896522522
2023-01-24 00:58:24.941036: step: 446/469, loss: 2.983337163925171
2023-01-24 00:58:25.541538: step: 448/469, loss: 2.466913938522339
2023-01-24 00:58:26.233414: step: 450/469, loss: 0.406933456659317
2023-01-24 00:58:26.956578: step: 452/469, loss: 0.6800675392150879
2023-01-24 00:58:27.653528: step: 454/469, loss: 0.30527159571647644
2023-01-24 00:58:28.376080: step: 456/469, loss: 1.2411680221557617
2023-01-24 00:58:29.039790: step: 458/469, loss: 3.157832145690918
2023-01-24 00:58:29.665444: step: 460/469, loss: 0.5001078844070435
2023-01-24 00:58:30.256257: step: 462/469, loss: 0.9012775421142578
2023-01-24 00:58:30.949392: step: 464/469, loss: 2.03584361076355
2023-01-24 00:58:31.553114: step: 466/469, loss: 1.7823234796524048
2023-01-24 00:58:32.190847: step: 468/469, loss: 1.4428259134292603
2023-01-24 00:58:32.866792: step: 470/469, loss: 1.5176260471343994
2023-01-24 00:58:33.476734: step: 472/469, loss: 1.4027972221374512
2023-01-24 00:58:34.102880: step: 474/469, loss: 0.5751864314079285
2023-01-24 00:58:34.767917: step: 476/469, loss: 0.9515081644058228
2023-01-24 00:58:35.402148: step: 478/469, loss: 0.7199758291244507
2023-01-24 00:58:35.983721: step: 480/469, loss: 1.1840629577636719
2023-01-24 00:58:36.633790: step: 482/469, loss: 1.6275490522384644
2023-01-24 00:58:37.334467: step: 484/469, loss: 0.6351293325424194
2023-01-24 00:58:38.027896: step: 486/469, loss: 0.4245985150337219
2023-01-24 00:58:38.647558: step: 488/469, loss: 0.4057943820953369
2023-01-24 00:58:39.394701: step: 490/469, loss: 4.20799446105957
2023-01-24 00:58:40.016295: step: 492/469, loss: 1.136854887008667
2023-01-24 00:58:40.703962: step: 494/469, loss: 6.3963236808776855
2023-01-24 00:58:41.333256: step: 496/469, loss: 0.7923392057418823
2023-01-24 00:58:42.004190: step: 498/469, loss: 3.3991355895996094
2023-01-24 00:58:42.623370: step: 500/469, loss: 2.36592698097229
2023-01-24 00:58:43.239919: step: 502/469, loss: 2.509711742401123
2023-01-24 00:58:43.903615: step: 504/469, loss: 0.8525946140289307
2023-01-24 00:58:44.462040: step: 506/469, loss: 0.6230922937393188
2023-01-24 00:58:45.055351: step: 508/469, loss: 4.56134557723999
2023-01-24 00:58:45.628766: step: 510/469, loss: 1.9812548160552979
2023-01-24 00:58:46.239065: step: 512/469, loss: 0.4840005040168762
2023-01-24 00:58:46.824046: step: 514/469, loss: 2.0905354022979736
2023-01-24 00:58:47.441915: step: 516/469, loss: 1.3597198724746704
2023-01-24 00:58:48.142433: step: 518/469, loss: 4.797149181365967
2023-01-24 00:58:48.736243: step: 520/469, loss: 0.32428330183029175
2023-01-24 00:58:49.343169: step: 522/469, loss: 5.728045463562012
2023-01-24 00:58:49.944883: step: 524/469, loss: 2.3465561866760254
2023-01-24 00:58:50.494744: step: 526/469, loss: 0.33189481496810913
2023-01-24 00:58:51.143490: step: 528/469, loss: 0.8946348428726196
2023-01-24 00:58:51.753010: step: 530/469, loss: 0.8239257335662842
2023-01-24 00:58:52.430417: step: 532/469, loss: 2.6375632286071777
2023-01-24 00:58:53.026553: step: 534/469, loss: 2.830780506134033
2023-01-24 00:58:53.627869: step: 536/469, loss: 1.2361962795257568
2023-01-24 00:58:54.292352: step: 538/469, loss: 0.996695876121521
2023-01-24 00:58:54.909570: step: 540/469, loss: 3.408931255340576
2023-01-24 00:58:55.500466: step: 542/469, loss: 2.9397573471069336
2023-01-24 00:58:56.135596: step: 544/469, loss: 1.2733079195022583
2023-01-24 00:58:56.744984: step: 546/469, loss: 0.9938843250274658
2023-01-24 00:58:57.352633: step: 548/469, loss: 0.4276813268661499
2023-01-24 00:58:57.941163: step: 550/469, loss: 0.6970816254615784
2023-01-24 00:58:58.630808: step: 552/469, loss: 2.603245496749878
2023-01-24 00:58:59.247672: step: 554/469, loss: 1.8236650228500366
2023-01-24 00:58:59.896156: step: 556/469, loss: 6.190192222595215
2023-01-24 00:59:00.535657: step: 558/469, loss: 0.42915213108062744
2023-01-24 00:59:01.179316: step: 560/469, loss: 0.8009711503982544
2023-01-24 00:59:01.892193: step: 562/469, loss: 1.7196707725524902
2023-01-24 00:59:02.490834: step: 564/469, loss: 0.5973418951034546
2023-01-24 00:59:03.153243: step: 566/469, loss: 3.4538116455078125
2023-01-24 00:59:03.799222: step: 568/469, loss: 0.6614938974380493
2023-01-24 00:59:04.384427: step: 570/469, loss: 0.4046335220336914
2023-01-24 00:59:04.942327: step: 572/469, loss: 0.9673312902450562
2023-01-24 00:59:05.592991: step: 574/469, loss: 2.780062198638916
2023-01-24 00:59:06.224692: step: 576/469, loss: 1.4446372985839844
2023-01-24 00:59:06.847745: step: 578/469, loss: 2.5449981689453125
2023-01-24 00:59:07.518420: step: 580/469, loss: 0.23068566620349884
2023-01-24 00:59:08.146592: step: 582/469, loss: 2.6683239936828613
2023-01-24 00:59:08.776489: step: 584/469, loss: 1.0787433385849
2023-01-24 00:59:09.494736: step: 586/469, loss: 2.1862850189208984
2023-01-24 00:59:10.102910: step: 588/469, loss: 1.7944048643112183
2023-01-24 00:59:10.743602: step: 590/469, loss: 2.3639705181121826
2023-01-24 00:59:11.357505: step: 592/469, loss: 2.702691078186035
2023-01-24 00:59:11.997638: step: 594/469, loss: 3.1447505950927734
2023-01-24 00:59:12.678601: step: 596/469, loss: 3.9168894290924072
2023-01-24 00:59:13.370895: step: 598/469, loss: 1.368726134300232
2023-01-24 00:59:13.993103: step: 600/469, loss: 6.212615966796875
2023-01-24 00:59:14.632022: step: 602/469, loss: 1.748282551765442
2023-01-24 00:59:15.310458: step: 604/469, loss: 0.47934800386428833
2023-01-24 00:59:15.912876: step: 606/469, loss: 0.2283998727798462
2023-01-24 00:59:16.571770: step: 608/469, loss: 12.818977355957031
2023-01-24 00:59:17.241411: step: 610/469, loss: 1.1269757747650146
2023-01-24 00:59:17.831936: step: 612/469, loss: 1.3322343826293945
2023-01-24 00:59:18.485504: step: 614/469, loss: 0.34730276465415955
2023-01-24 00:59:19.099421: step: 616/469, loss: 1.4259893894195557
2023-01-24 00:59:19.764214: step: 618/469, loss: 0.6219801902770996
2023-01-24 00:59:20.413073: step: 620/469, loss: 1.68389093875885
2023-01-24 00:59:21.011051: step: 622/469, loss: 0.4739355444908142
2023-01-24 00:59:21.658638: step: 624/469, loss: 3.3404035568237305
2023-01-24 00:59:22.296030: step: 626/469, loss: 0.9970574378967285
2023-01-24 00:59:22.880446: step: 628/469, loss: 2.1485400199890137
2023-01-24 00:59:23.476240: step: 630/469, loss: 0.563214123249054
2023-01-24 00:59:24.064075: step: 632/469, loss: 0.49547895789146423
2023-01-24 00:59:24.731681: step: 634/469, loss: 0.8724790215492249
2023-01-24 00:59:25.431282: step: 636/469, loss: 0.574462890625
2023-01-24 00:59:26.052326: step: 638/469, loss: 0.618561327457428
2023-01-24 00:59:26.688341: step: 640/469, loss: 1.007251262664795
2023-01-24 00:59:27.282767: step: 642/469, loss: 0.5910242795944214
2023-01-24 00:59:27.869134: step: 644/469, loss: 3.602355480194092
2023-01-24 00:59:28.486784: step: 646/469, loss: 2.5281431674957275
2023-01-24 00:59:29.131691: step: 648/469, loss: 2.624279499053955
2023-01-24 00:59:29.778090: step: 650/469, loss: 1.8061567544937134
2023-01-24 00:59:30.380346: step: 652/469, loss: 0.9593743085861206
2023-01-24 00:59:31.099304: step: 654/469, loss: 1.447396159172058
2023-01-24 00:59:31.774344: step: 656/469, loss: 1.6114580631256104
2023-01-24 00:59:32.398484: step: 658/469, loss: 2.4865214824676514
2023-01-24 00:59:33.020977: step: 660/469, loss: 1.9151530265808105
2023-01-24 00:59:33.602474: step: 662/469, loss: 2.6298186779022217
2023-01-24 00:59:34.291440: step: 664/469, loss: 0.6157950162887573
2023-01-24 00:59:34.898746: step: 666/469, loss: 0.31964510679244995
2023-01-24 00:59:35.537504: step: 668/469, loss: 1.302176594734192
2023-01-24 00:59:36.203410: step: 670/469, loss: 0.8198046088218689
2023-01-24 00:59:36.886033: step: 672/469, loss: 1.230098843574524
2023-01-24 00:59:37.559170: step: 674/469, loss: 1.8937286138534546
2023-01-24 00:59:38.292170: step: 676/469, loss: 1.7790850400924683
2023-01-24 00:59:38.950806: step: 678/469, loss: 0.42032474279403687
2023-01-24 00:59:39.572125: step: 680/469, loss: 3.8505940437316895
2023-01-24 00:59:40.209879: step: 682/469, loss: 0.7740234136581421
2023-01-24 00:59:40.838673: step: 684/469, loss: 0.3754080533981323
2023-01-24 00:59:41.474655: step: 686/469, loss: 1.0969812870025635
2023-01-24 00:59:42.083844: step: 688/469, loss: 2.9668822288513184
2023-01-24 00:59:42.736701: step: 690/469, loss: 2.951083183288574
2023-01-24 00:59:43.348337: step: 692/469, loss: 3.410388469696045
2023-01-24 00:59:43.982533: step: 694/469, loss: 1.3995883464813232
2023-01-24 00:59:44.594255: step: 696/469, loss: 0.7069652080535889
2023-01-24 00:59:45.233703: step: 698/469, loss: 0.6556860208511353
2023-01-24 00:59:45.860268: step: 700/469, loss: 0.6808304190635681
2023-01-24 00:59:46.499969: step: 702/469, loss: 1.951819658279419
2023-01-24 00:59:47.154308: step: 704/469, loss: 0.8062426447868347
2023-01-24 00:59:47.914045: step: 706/469, loss: 0.6777491569519043
2023-01-24 00:59:48.527991: step: 708/469, loss: 1.3558197021484375
2023-01-24 00:59:49.186955: step: 710/469, loss: 0.651256799697876
2023-01-24 00:59:49.819502: step: 712/469, loss: 1.024844765663147
2023-01-24 00:59:50.436825: step: 714/469, loss: 5.307661056518555
2023-01-24 00:59:51.078646: step: 716/469, loss: 1.0373034477233887
2023-01-24 00:59:51.671093: step: 718/469, loss: 1.2897006273269653
2023-01-24 00:59:52.304900: step: 720/469, loss: 1.1747374534606934
2023-01-24 00:59:52.942326: step: 722/469, loss: 2.1981310844421387
2023-01-24 00:59:53.571146: step: 724/469, loss: 0.5594189167022705
2023-01-24 00:59:54.215469: step: 726/469, loss: 0.9148130416870117
2023-01-24 00:59:54.772824: step: 728/469, loss: 2.197479724884033
2023-01-24 00:59:55.378319: step: 730/469, loss: 1.027839183807373
2023-01-24 00:59:55.986547: step: 732/469, loss: 9.317862510681152
2023-01-24 00:59:56.557397: step: 734/469, loss: 2.0460798740386963
2023-01-24 00:59:57.226623: step: 736/469, loss: 2.078953742980957
2023-01-24 00:59:57.920005: step: 738/469, loss: 5.71103572845459
2023-01-24 00:59:58.538901: step: 740/469, loss: 1.327780842781067
2023-01-24 00:59:59.156136: step: 742/469, loss: 1.3744038343429565
2023-01-24 00:59:59.745375: step: 744/469, loss: 5.301520347595215
2023-01-24 01:00:00.402824: step: 746/469, loss: 1.3241816759109497
2023-01-24 01:00:01.024953: step: 748/469, loss: 4.036094665527344
2023-01-24 01:00:01.651501: step: 750/469, loss: 1.3682143688201904
2023-01-24 01:00:02.232261: step: 752/469, loss: 1.1460245847702026
2023-01-24 01:00:02.959954: step: 754/469, loss: 1.4363397359848022
2023-01-24 01:00:03.598318: step: 756/469, loss: 2.2570321559906006
2023-01-24 01:00:04.322859: step: 758/469, loss: 4.692358493804932
2023-01-24 01:00:04.948861: step: 760/469, loss: 0.7012701034545898
2023-01-24 01:00:05.603351: step: 762/469, loss: 2.7670552730560303
2023-01-24 01:00:06.225895: step: 764/469, loss: 1.3826501369476318
2023-01-24 01:00:06.905529: step: 766/469, loss: 0.5983228087425232
2023-01-24 01:00:07.532783: step: 768/469, loss: 0.7576615810394287
2023-01-24 01:00:08.174185: step: 770/469, loss: 1.623666763305664
2023-01-24 01:00:08.814845: step: 772/469, loss: 1.1034537553787231
2023-01-24 01:00:09.463256: step: 774/469, loss: 1.1922709941864014
2023-01-24 01:00:10.137995: step: 776/469, loss: 0.9126417636871338
2023-01-24 01:00:10.794501: step: 778/469, loss: 0.5356414318084717
2023-01-24 01:00:11.409169: step: 780/469, loss: 0.4846305549144745
2023-01-24 01:00:12.079937: step: 782/469, loss: 3.597834587097168
2023-01-24 01:00:12.743768: step: 784/469, loss: 1.1163527965545654
2023-01-24 01:00:13.374671: step: 786/469, loss: 1.3866658210754395
2023-01-24 01:00:13.988160: step: 788/469, loss: 0.658324658870697
2023-01-24 01:00:14.551718: step: 790/469, loss: 1.4993462562561035
2023-01-24 01:00:15.179871: step: 792/469, loss: 1.1692321300506592
2023-01-24 01:00:15.792316: step: 794/469, loss: 4.7747344970703125
2023-01-24 01:00:16.454818: step: 796/469, loss: 0.9007105827331543
2023-01-24 01:00:17.113883: step: 798/469, loss: 0.8143647909164429
2023-01-24 01:00:17.713225: step: 800/469, loss: 6.239959239959717
2023-01-24 01:00:18.357000: step: 802/469, loss: 0.3260728716850281
2023-01-24 01:00:18.953054: step: 804/469, loss: 2.2098755836486816
2023-01-24 01:00:19.560649: step: 806/469, loss: 1.023186445236206
2023-01-24 01:00:20.186998: step: 808/469, loss: 1.4482007026672363
2023-01-24 01:00:20.798032: step: 810/469, loss: 0.33770811557769775
2023-01-24 01:00:21.374852: step: 812/469, loss: 1.0102179050445557
2023-01-24 01:00:21.995655: step: 814/469, loss: 3.1881463527679443
2023-01-24 01:00:22.653793: step: 816/469, loss: 0.9331550598144531
2023-01-24 01:00:23.380359: step: 818/469, loss: 0.8774794340133667
2023-01-24 01:00:24.162397: step: 820/469, loss: 10.5547456741333
2023-01-24 01:00:24.840271: step: 822/469, loss: 1.2317283153533936
2023-01-24 01:00:25.391807: step: 824/469, loss: 0.9386170506477356
2023-01-24 01:00:26.022352: step: 826/469, loss: 1.76652991771698
2023-01-24 01:00:26.780895: step: 828/469, loss: 1.5632579326629639
2023-01-24 01:00:27.380335: step: 830/469, loss: 11.621553421020508
2023-01-24 01:00:28.187811: step: 832/469, loss: 1.3102751970291138
2023-01-24 01:00:28.864008: step: 834/469, loss: 2.7988474369049072
2023-01-24 01:00:29.491854: step: 836/469, loss: 2.1238455772399902
2023-01-24 01:00:30.130633: step: 838/469, loss: 1.6453871726989746
2023-01-24 01:00:30.764661: step: 840/469, loss: 1.2638801336288452
2023-01-24 01:00:31.365060: step: 842/469, loss: 0.5004633069038391
2023-01-24 01:00:32.000981: step: 844/469, loss: 0.9848936200141907
2023-01-24 01:00:32.646697: step: 846/469, loss: 0.4151782989501953
2023-01-24 01:00:33.385805: step: 848/469, loss: 0.4190213978290558
2023-01-24 01:00:34.046555: step: 850/469, loss: 1.2330005168914795
2023-01-24 01:00:34.708916: step: 852/469, loss: 0.44728994369506836
2023-01-24 01:00:35.412835: step: 854/469, loss: 6.191889762878418
2023-01-24 01:00:36.097739: step: 856/469, loss: 1.6545212268829346
2023-01-24 01:00:36.727903: step: 858/469, loss: 1.0753962993621826
2023-01-24 01:00:37.301223: step: 860/469, loss: 0.5099169611930847
2023-01-24 01:00:37.993062: step: 862/469, loss: 0.35161808133125305
2023-01-24 01:00:38.784553: step: 864/469, loss: 0.5195026993751526
2023-01-24 01:00:39.473566: step: 866/469, loss: 1.169761300086975
2023-01-24 01:00:40.027651: step: 868/469, loss: 1.8479701280593872
2023-01-24 01:00:40.703670: step: 870/469, loss: 1.3604129552841187
2023-01-24 01:00:41.353014: step: 872/469, loss: 2.2602038383483887
2023-01-24 01:00:41.966220: step: 874/469, loss: 1.2506535053253174
2023-01-24 01:00:42.586528: step: 876/469, loss: 1.0251960754394531
2023-01-24 01:00:43.203532: step: 878/469, loss: 0.8896273374557495
2023-01-24 01:00:43.853494: step: 880/469, loss: 1.996160626411438
2023-01-24 01:00:44.480520: step: 882/469, loss: 3.311429977416992
2023-01-24 01:00:45.120284: step: 884/469, loss: 0.540127158164978
2023-01-24 01:00:45.676411: step: 886/469, loss: 0.43265557289123535
2023-01-24 01:00:46.313835: step: 888/469, loss: 1.1783123016357422
2023-01-24 01:00:46.967087: step: 890/469, loss: 0.6725778579711914
2023-01-24 01:00:47.597352: step: 892/469, loss: 0.6339295506477356
2023-01-24 01:00:48.288344: step: 894/469, loss: 0.7197149991989136
2023-01-24 01:00:48.967922: step: 896/469, loss: 1.1898581981658936
2023-01-24 01:00:49.526447: step: 898/469, loss: 0.3726484179496765
2023-01-24 01:00:50.097072: step: 900/469, loss: 1.3890084028244019
2023-01-24 01:00:50.689172: step: 902/469, loss: 2.965548276901245
2023-01-24 01:00:51.363175: step: 904/469, loss: 7.361764907836914
2023-01-24 01:00:52.049308: step: 906/469, loss: 1.0197678804397583
2023-01-24 01:00:52.694826: step: 908/469, loss: 0.5380075573921204
2023-01-24 01:00:53.366920: step: 910/469, loss: 0.2265072911977768
2023-01-24 01:00:54.059435: step: 912/469, loss: 6.4279985427856445
2023-01-24 01:00:54.759925: step: 914/469, loss: 0.30310600996017456
2023-01-24 01:00:55.390187: step: 916/469, loss: 3.4315881729125977
2023-01-24 01:00:56.049955: step: 918/469, loss: 0.9987183809280396
2023-01-24 01:00:56.691812: step: 920/469, loss: 1.304203748703003
2023-01-24 01:00:57.246888: step: 922/469, loss: 0.5848813056945801
2023-01-24 01:00:57.901220: step: 924/469, loss: 0.40204232931137085
2023-01-24 01:00:58.547866: step: 926/469, loss: 0.4296698570251465
2023-01-24 01:00:59.243714: step: 928/469, loss: 0.6505110859870911
2023-01-24 01:00:59.877966: step: 930/469, loss: 0.6078650951385498
2023-01-24 01:01:00.574815: step: 932/469, loss: 1.256596565246582
2023-01-24 01:01:01.180482: step: 934/469, loss: 1.8910768032073975
2023-01-24 01:01:01.814183: step: 936/469, loss: 0.4733887314796448
2023-01-24 01:01:02.459881: step: 938/469, loss: 0.3660109341144562
==================================================
Loss: 1.945
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33987657337344146, 'r': 0.22079103156645913, 'f1': 0.26768694527460485}, 'combined': 0.19724301230760355, 'epoch': 1}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.28442259494891076, 'r': 0.13349386203915026, 'f1': 0.18170459677308995}, 'combined': 0.09911159823986723, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32606391845909566, 'r': 0.2112004926382779, 'f1': 0.25635370140922004}, 'combined': 0.18889220103837265, 'epoch': 1}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.27557410267631177, 'r': 0.13011124299877003, 'f1': 0.1767640336025474}, 'combined': 0.09641674560138948, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32511030912058764, 'r': 0.20811985697492164, 'f1': 0.25378125746595526}, 'combined': 0.18699671602754597, 'epoch': 1}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.28843913368185214, 'r': 0.13590681962136675, 'f1': 0.18475889781859933}, 'combined': 0.1007775806283269, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34333333333333327, 'r': 0.2452380952380952, 'f1': 0.28611111111111104}, 'combined': 0.19074074074074068, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25, 'r': 0.11956521739130435, 'f1': 0.16176470588235295}, 'combined': 0.08088235294117647, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.13793103448275862, 'f1': 0.2162162162162162}, 'combined': 0.14414414414414412, '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': 0.33987657337344146, 'r': 0.22079103156645913, 'f1': 0.26768694527460485}, 'combined': 0.19724301230760355, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.28442259494891076, 'r': 0.13349386203915026, 'f1': 0.18170459677308995}, 'combined': 0.09911159823986723, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34333333333333327, 'r': 0.2452380952380952, 'f1': 0.28611111111111104}, 'combined': 0.19074074074074068, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32606391845909566, 'r': 0.2112004926382779, 'f1': 0.25635370140922004}, 'combined': 0.18889220103837265, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.27557410267631177, 'r': 0.13011124299877003, 'f1': 0.1767640336025474}, 'combined': 0.09641674560138948, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25, 'r': 0.11956521739130435, 'f1': 0.16176470588235295}, 'combined': 0.08088235294117647, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32511030912058764, 'r': 0.20811985697492164, 'f1': 0.25378125746595526}, 'combined': 0.18699671602754597, 'epoch': 1}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.28843913368185214, 'r': 0.13590681962136675, 'f1': 0.18475889781859933}, 'combined': 0.1007775806283269, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.13793103448275862, 'f1': 0.2162162162162162}, 'combined': 0.14414414414414412, '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
2023-01-24 01:04:04.200707: step: 2/469, loss: 0.5353066325187683
2023-01-24 01:04:04.853199: step: 4/469, loss: 1.8436578512191772
2023-01-24 01:04:05.478222: step: 6/469, loss: 0.38073140382766724
2023-01-24 01:04:06.155053: step: 8/469, loss: 0.6198972463607788
2023-01-24 01:04:06.873855: step: 10/469, loss: 1.1369569301605225
2023-01-24 01:04:07.524025: step: 12/469, loss: 1.104857325553894
2023-01-24 01:04:08.160679: step: 14/469, loss: 0.5385766625404358
2023-01-24 01:04:08.786012: step: 16/469, loss: 0.813564121723175
2023-01-24 01:04:09.473558: step: 18/469, loss: 0.5973976850509644
2023-01-24 01:04:10.138677: step: 20/469, loss: 3.3589892387390137
2023-01-24 01:04:10.761579: step: 22/469, loss: 0.8600585460662842
2023-01-24 01:04:11.353725: step: 24/469, loss: 0.6128389835357666
2023-01-24 01:04:12.025498: step: 26/469, loss: 1.1072347164154053
2023-01-24 01:04:12.626441: step: 28/469, loss: 1.4190499782562256
2023-01-24 01:04:13.198829: step: 30/469, loss: 0.7740609645843506
2023-01-24 01:04:13.785133: step: 32/469, loss: 1.2469971179962158
2023-01-24 01:04:14.424141: step: 34/469, loss: 1.4400287866592407
2023-01-24 01:04:15.035561: step: 36/469, loss: 1.1377840042114258
2023-01-24 01:04:15.745339: step: 38/469, loss: 1.1450287103652954
2023-01-24 01:04:16.403540: step: 40/469, loss: 1.0870027542114258
2023-01-24 01:04:17.011658: step: 42/469, loss: 0.2694031298160553
2023-01-24 01:04:17.632080: step: 44/469, loss: 0.5426982641220093
2023-01-24 01:04:18.236442: step: 46/469, loss: 0.41402673721313477
2023-01-24 01:04:18.853720: step: 48/469, loss: 0.6934465765953064
2023-01-24 01:04:19.500574: step: 50/469, loss: 1.388898491859436
2023-01-24 01:04:20.158516: step: 52/469, loss: 2.3539657592773438
2023-01-24 01:04:20.758325: step: 54/469, loss: 0.24942156672477722
2023-01-24 01:04:21.397784: step: 56/469, loss: 1.6694965362548828
2023-01-24 01:04:22.032267: step: 58/469, loss: 3.645967483520508
2023-01-24 01:04:22.691681: step: 60/469, loss: 0.7160361409187317
2023-01-24 01:04:23.393346: step: 62/469, loss: 2.0979177951812744
2023-01-24 01:04:24.047026: step: 64/469, loss: 0.8871322870254517
2023-01-24 01:04:24.704012: step: 66/469, loss: 3.3475236892700195
2023-01-24 01:04:25.328204: step: 68/469, loss: 1.5695114135742188
2023-01-24 01:04:25.965085: step: 70/469, loss: 0.3799401819705963
2023-01-24 01:04:26.652741: step: 72/469, loss: 1.5135334730148315
2023-01-24 01:04:27.241977: step: 74/469, loss: 2.1811304092407227
2023-01-24 01:04:27.901397: step: 76/469, loss: 1.3809643983840942
2023-01-24 01:04:28.566800: step: 78/469, loss: 0.36087802052497864
2023-01-24 01:04:29.171837: step: 80/469, loss: 0.8317145109176636
2023-01-24 01:04:29.840431: step: 82/469, loss: 0.38330256938934326
2023-01-24 01:04:30.427398: step: 84/469, loss: 3.9333324432373047
2023-01-24 01:04:31.057780: step: 86/469, loss: 0.3897731602191925
2023-01-24 01:04:31.673200: step: 88/469, loss: 1.5685337781906128
2023-01-24 01:04:32.336186: step: 90/469, loss: 0.732214629650116
2023-01-24 01:04:32.968205: step: 92/469, loss: 1.2500853538513184
2023-01-24 01:04:33.558488: step: 94/469, loss: 0.6063386797904968
2023-01-24 01:04:34.268539: step: 96/469, loss: 3.0048389434814453
2023-01-24 01:04:34.899755: step: 98/469, loss: 0.2374560683965683
2023-01-24 01:04:35.558900: step: 100/469, loss: 0.34000909328460693
2023-01-24 01:04:36.181043: step: 102/469, loss: 0.369872510433197
2023-01-24 01:04:36.799988: step: 104/469, loss: 2.179455518722534
2023-01-24 01:04:37.400053: step: 106/469, loss: 1.6280885934829712
2023-01-24 01:04:38.165861: step: 108/469, loss: 1.45135498046875
2023-01-24 01:04:38.809375: step: 110/469, loss: 0.21561674773693085
2023-01-24 01:04:39.421819: step: 112/469, loss: 4.606247901916504
2023-01-24 01:04:39.992897: step: 114/469, loss: 2.7122511863708496
2023-01-24 01:04:40.545388: step: 116/469, loss: 0.2609219253063202
2023-01-24 01:04:41.155433: step: 118/469, loss: 0.5242354273796082
2023-01-24 01:04:41.798830: step: 120/469, loss: 0.3231472373008728
2023-01-24 01:04:42.440384: step: 122/469, loss: 0.9146525263786316
2023-01-24 01:04:43.029222: step: 124/469, loss: 0.4059615433216095
2023-01-24 01:04:43.598566: step: 126/469, loss: 0.6007198691368103
2023-01-24 01:04:44.251535: step: 128/469, loss: 0.4161914885044098
2023-01-24 01:04:44.868572: step: 130/469, loss: 0.6699537634849548
2023-01-24 01:04:45.586151: step: 132/469, loss: 1.0586177110671997
2023-01-24 01:04:46.212444: step: 134/469, loss: 0.6724517941474915
2023-01-24 01:04:46.816480: step: 136/469, loss: 1.4755992889404297
2023-01-24 01:04:47.471893: step: 138/469, loss: 2.309426784515381
2023-01-24 01:04:48.124896: step: 140/469, loss: 2.3876473903656006
2023-01-24 01:04:48.767809: step: 142/469, loss: 0.5938212275505066
2023-01-24 01:04:49.414689: step: 144/469, loss: 1.8941092491149902
2023-01-24 01:04:49.986948: step: 146/469, loss: 0.20273509621620178
2023-01-24 01:04:50.642232: step: 148/469, loss: 1.0266315937042236
2023-01-24 01:04:51.221913: step: 150/469, loss: 2.066869020462036
2023-01-24 01:04:51.802100: step: 152/469, loss: 2.767587423324585
2023-01-24 01:04:52.376659: step: 154/469, loss: 0.2977367341518402
2023-01-24 01:04:53.008450: step: 156/469, loss: 1.2398371696472168
2023-01-24 01:04:53.555074: step: 158/469, loss: 1.8017405271530151
2023-01-24 01:04:54.242924: step: 160/469, loss: 0.6679936647415161
2023-01-24 01:04:54.879645: step: 162/469, loss: 2.998906373977661
2023-01-24 01:04:55.453706: step: 164/469, loss: 2.467369556427002
2023-01-24 01:04:56.106972: step: 166/469, loss: 4.161844253540039
2023-01-24 01:04:56.736832: step: 168/469, loss: 6.108869552612305
2023-01-24 01:04:57.355198: step: 170/469, loss: 4.873496055603027
2023-01-24 01:04:58.027439: step: 172/469, loss: 1.1807408332824707
2023-01-24 01:04:58.687491: step: 174/469, loss: 0.3957067131996155
2023-01-24 01:04:59.338911: step: 176/469, loss: 0.6589661836624146
2023-01-24 01:04:59.983010: step: 178/469, loss: 0.9177929162979126
2023-01-24 01:05:00.608149: step: 180/469, loss: 1.5773760080337524
2023-01-24 01:05:01.292926: step: 182/469, loss: 4.654255390167236
2023-01-24 01:05:01.942277: step: 184/469, loss: 4.3159260749816895
2023-01-24 01:05:02.582672: step: 186/469, loss: 0.6257660388946533
2023-01-24 01:05:03.201087: step: 188/469, loss: 2.640253782272339
2023-01-24 01:05:03.822093: step: 190/469, loss: 1.3661240339279175
2023-01-24 01:05:04.448721: step: 192/469, loss: 2.0238704681396484
2023-01-24 01:05:05.114660: step: 194/469, loss: 1.169008493423462
2023-01-24 01:05:05.661085: step: 196/469, loss: 0.5621331930160522
2023-01-24 01:05:06.260689: step: 198/469, loss: 2.576171398162842
2023-01-24 01:05:06.882621: step: 200/469, loss: 3.413377046585083
2023-01-24 01:05:07.579902: step: 202/469, loss: 0.6116236448287964
2023-01-24 01:05:08.222537: step: 204/469, loss: 2.3727691173553467
2023-01-24 01:05:08.862049: step: 206/469, loss: 1.110275149345398
2023-01-24 01:05:09.512683: step: 208/469, loss: 1.7331864833831787
2023-01-24 01:05:10.157299: step: 210/469, loss: 1.9998188018798828
2023-01-24 01:05:10.884357: step: 212/469, loss: 4.6289448738098145
2023-01-24 01:05:11.517705: step: 214/469, loss: 5.65755558013916
2023-01-24 01:05:12.128744: step: 216/469, loss: 0.7672577500343323
2023-01-24 01:05:12.716146: step: 218/469, loss: 0.4674344062805176
2023-01-24 01:05:13.344774: step: 220/469, loss: 0.982247531414032
2023-01-24 01:05:14.012777: step: 222/469, loss: 3.89165997505188
2023-01-24 01:05:14.652503: step: 224/469, loss: 0.6990604996681213
2023-01-24 01:05:15.288912: step: 226/469, loss: 0.43852055072784424
2023-01-24 01:05:15.895288: step: 228/469, loss: 0.9134107828140259
2023-01-24 01:05:16.566209: step: 230/469, loss: 0.48390674591064453
2023-01-24 01:05:17.191896: step: 232/469, loss: 0.8309329748153687
2023-01-24 01:05:17.812844: step: 234/469, loss: 1.504846215248108
2023-01-24 01:05:18.497334: step: 236/469, loss: 1.4761226177215576
2023-01-24 01:05:19.101195: step: 238/469, loss: 0.20416758954524994
2023-01-24 01:05:19.762876: step: 240/469, loss: 0.2646782100200653
2023-01-24 01:05:20.446470: step: 242/469, loss: 0.3520800471305847
2023-01-24 01:05:21.165064: step: 244/469, loss: 4.36689567565918
2023-01-24 01:05:21.887965: step: 246/469, loss: 1.7954626083374023
2023-01-24 01:05:22.510392: step: 248/469, loss: 1.6993610858917236
2023-01-24 01:05:23.114785: step: 250/469, loss: 1.2133893966674805
2023-01-24 01:05:23.831952: step: 252/469, loss: 0.7194636464118958
2023-01-24 01:05:24.472866: step: 254/469, loss: 1.1498796939849854
2023-01-24 01:05:25.120326: step: 256/469, loss: 1.4167494773864746
2023-01-24 01:05:25.721026: step: 258/469, loss: 1.2200649976730347
2023-01-24 01:05:26.379198: step: 260/469, loss: 0.3104654848575592
2023-01-24 01:05:26.985367: step: 262/469, loss: 3.2491283416748047
2023-01-24 01:05:27.623575: step: 264/469, loss: 5.202022075653076
2023-01-24 01:05:28.315016: step: 266/469, loss: 1.3647511005401611
2023-01-24 01:05:28.944042: step: 268/469, loss: 1.081467628479004
2023-01-24 01:05:29.599016: step: 270/469, loss: 1.4648642539978027
2023-01-24 01:05:30.233003: step: 272/469, loss: 1.9662424325942993
2023-01-24 01:05:30.864929: step: 274/469, loss: 0.8211962580680847
2023-01-24 01:05:31.543092: step: 276/469, loss: 0.24146252870559692
2023-01-24 01:05:32.212011: step: 278/469, loss: 0.8601873517036438
2023-01-24 01:05:32.851805: step: 280/469, loss: 1.9408857822418213
2023-01-24 01:05:33.465146: step: 282/469, loss: 1.6274000406265259
2023-01-24 01:05:34.111544: step: 284/469, loss: 0.9171558618545532
2023-01-24 01:05:34.746968: step: 286/469, loss: 5.5370869636535645
2023-01-24 01:05:35.408150: step: 288/469, loss: 0.7206916809082031
2023-01-24 01:05:36.019371: step: 290/469, loss: 9.945982933044434
2023-01-24 01:05:36.675234: step: 292/469, loss: 1.080707311630249
2023-01-24 01:05:37.286999: step: 294/469, loss: 0.6142443418502808
2023-01-24 01:05:37.966598: step: 296/469, loss: 2.342301368713379
2023-01-24 01:05:38.628315: step: 298/469, loss: 0.36795201897621155
2023-01-24 01:05:39.382126: step: 300/469, loss: 9.360123634338379
2023-01-24 01:05:39.997783: step: 302/469, loss: 0.8583207130432129
2023-01-24 01:05:40.710007: step: 304/469, loss: 1.77339768409729
2023-01-24 01:05:41.319953: step: 306/469, loss: 0.34043794870376587
2023-01-24 01:05:41.997127: step: 308/469, loss: 2.13614821434021
2023-01-24 01:05:42.621080: step: 310/469, loss: 2.374389171600342
2023-01-24 01:05:43.326128: step: 312/469, loss: 0.537878155708313
2023-01-24 01:05:43.974013: step: 314/469, loss: 0.28871050477027893
2023-01-24 01:05:44.567260: step: 316/469, loss: 0.7118523120880127
2023-01-24 01:05:45.199059: step: 318/469, loss: 0.5514461398124695
2023-01-24 01:05:45.779419: step: 320/469, loss: 1.193490743637085
2023-01-24 01:05:46.361379: step: 322/469, loss: 0.5438361167907715
2023-01-24 01:05:46.980348: step: 324/469, loss: 0.8662155866622925
2023-01-24 01:05:47.648474: step: 326/469, loss: 4.128833770751953
2023-01-24 01:05:48.214945: step: 328/469, loss: 0.26334819197654724
2023-01-24 01:05:48.836180: step: 330/469, loss: 0.6601830720901489
2023-01-24 01:05:49.477668: step: 332/469, loss: 1.41522216796875
2023-01-24 01:05:50.151692: step: 334/469, loss: 1.5807245969772339
2023-01-24 01:05:50.791422: step: 336/469, loss: 0.9234598875045776
2023-01-24 01:05:51.423465: step: 338/469, loss: 0.9473558664321899
2023-01-24 01:05:52.054986: step: 340/469, loss: 0.8189126253128052
2023-01-24 01:05:52.612964: step: 342/469, loss: 1.153841495513916
2023-01-24 01:05:53.266797: step: 344/469, loss: 0.6549341082572937
2023-01-24 01:05:53.934163: step: 346/469, loss: 0.5125113129615784
2023-01-24 01:05:54.600361: step: 348/469, loss: 3.0550527572631836
2023-01-24 01:05:55.259697: step: 350/469, loss: 4.007517337799072
2023-01-24 01:05:55.837046: step: 352/469, loss: 1.2425651550292969
2023-01-24 01:05:56.514726: step: 354/469, loss: 0.4758748412132263
2023-01-24 01:05:57.155197: step: 356/469, loss: 1.3866406679153442
2023-01-24 01:05:57.844465: step: 358/469, loss: 2.6619386672973633
2023-01-24 01:05:58.457071: step: 360/469, loss: 1.7839328050613403
2023-01-24 01:05:59.137306: step: 362/469, loss: 0.40629005432128906
2023-01-24 01:05:59.739489: step: 364/469, loss: 1.3062337636947632
2023-01-24 01:06:00.387317: step: 366/469, loss: 1.236457347869873
2023-01-24 01:06:01.066971: step: 368/469, loss: 1.409936547279358
2023-01-24 01:06:01.728716: step: 370/469, loss: 4.042206764221191
2023-01-24 01:06:02.337008: step: 372/469, loss: 0.6997310519218445
2023-01-24 01:06:02.920689: step: 374/469, loss: 0.41233372688293457
2023-01-24 01:06:03.736426: step: 376/469, loss: 1.12722909450531
2023-01-24 01:06:04.410188: step: 378/469, loss: 0.9107418060302734
2023-01-24 01:06:05.121909: step: 380/469, loss: 0.7936978340148926
2023-01-24 01:06:05.790296: step: 382/469, loss: 1.2343323230743408
2023-01-24 01:06:06.522673: step: 384/469, loss: 1.285002589225769
2023-01-24 01:06:07.123103: step: 386/469, loss: 0.4721754789352417
2023-01-24 01:06:07.699381: step: 388/469, loss: 1.0002391338348389
2023-01-24 01:06:08.330682: step: 390/469, loss: 0.5865353941917419
2023-01-24 01:06:08.914975: step: 392/469, loss: 0.43929287791252136
2023-01-24 01:06:09.476704: step: 394/469, loss: 1.8687264919281006
2023-01-24 01:06:10.116574: step: 396/469, loss: 0.8266392946243286
2023-01-24 01:06:10.729597: step: 398/469, loss: 0.7542542219161987
2023-01-24 01:06:11.310581: step: 400/469, loss: 1.4228665828704834
2023-01-24 01:06:11.945420: step: 402/469, loss: 0.6893333792686462
2023-01-24 01:06:12.597651: step: 404/469, loss: 0.8588920831680298
2023-01-24 01:06:13.256129: step: 406/469, loss: 0.2756017744541168
2023-01-24 01:06:13.853667: step: 408/469, loss: 0.8203291893005371
2023-01-24 01:06:14.486876: step: 410/469, loss: 3.027172803878784
2023-01-24 01:06:15.118254: step: 412/469, loss: 0.7559589743614197
2023-01-24 01:06:15.732060: step: 414/469, loss: 4.531430244445801
2023-01-24 01:06:16.433178: step: 416/469, loss: 1.2973449230194092
2023-01-24 01:06:17.089000: step: 418/469, loss: 0.7788103222846985
2023-01-24 01:06:17.675206: step: 420/469, loss: 0.9620156288146973
2023-01-24 01:06:18.244921: step: 422/469, loss: 1.9674732685089111
2023-01-24 01:06:18.885699: step: 424/469, loss: 0.7176800966262817
2023-01-24 01:06:19.494958: step: 426/469, loss: 1.4385719299316406
2023-01-24 01:06:20.222632: step: 428/469, loss: 0.31072425842285156
2023-01-24 01:06:20.851539: step: 430/469, loss: 0.5030708909034729
2023-01-24 01:06:21.527662: step: 432/469, loss: 0.8212928175926208
2023-01-24 01:06:22.215722: step: 434/469, loss: 5.32388162612915
2023-01-24 01:06:22.869718: step: 436/469, loss: 3.257072925567627
2023-01-24 01:06:23.475636: step: 438/469, loss: 0.6465895771980286
2023-01-24 01:06:24.087939: step: 440/469, loss: 2.1670315265655518
2023-01-24 01:06:24.779045: step: 442/469, loss: 0.7426234483718872
2023-01-24 01:06:25.483658: step: 444/469, loss: 2.1683270931243896
2023-01-24 01:06:26.138923: step: 446/469, loss: 2.1971077919006348
2023-01-24 01:06:26.765388: step: 448/469, loss: 1.287776231765747
2023-01-24 01:06:27.389395: step: 450/469, loss: 0.3704913258552551
2023-01-24 01:06:28.020988: step: 452/469, loss: 0.6952789425849915
2023-01-24 01:06:28.634562: step: 454/469, loss: 2.212874174118042
2023-01-24 01:06:29.235044: step: 456/469, loss: 0.8737174272537231
2023-01-24 01:06:29.832979: step: 458/469, loss: 0.9015182852745056
2023-01-24 01:06:30.444212: step: 460/469, loss: 1.221562147140503
2023-01-24 01:06:31.114037: step: 462/469, loss: 1.1128971576690674
2023-01-24 01:06:31.774584: step: 464/469, loss: 0.8728907108306885
2023-01-24 01:06:32.387066: step: 466/469, loss: 0.25806495547294617
2023-01-24 01:06:33.035856: step: 468/469, loss: 2.4693655967712402
2023-01-24 01:06:33.644344: step: 470/469, loss: 1.1539511680603027
2023-01-24 01:06:34.302197: step: 472/469, loss: 0.7793067693710327
2023-01-24 01:06:34.940036: step: 474/469, loss: 1.5572283267974854
2023-01-24 01:06:35.664923: step: 476/469, loss: 0.9491767883300781
2023-01-24 01:06:36.377226: step: 478/469, loss: 0.8359588980674744
2023-01-24 01:06:37.016808: step: 480/469, loss: 0.9200326800346375
2023-01-24 01:06:37.673892: step: 482/469, loss: 1.0874435901641846
2023-01-24 01:06:38.360234: step: 484/469, loss: 1.3438928127288818
2023-01-24 01:06:39.024653: step: 486/469, loss: 2.581448793411255
2023-01-24 01:06:39.676866: step: 488/469, loss: 1.4607781171798706
2023-01-24 01:06:40.317868: step: 490/469, loss: 2.7576074600219727
2023-01-24 01:06:40.922282: step: 492/469, loss: 1.3457109928131104
2023-01-24 01:06:41.647517: step: 494/469, loss: 1.15946364402771
2023-01-24 01:06:42.310931: step: 496/469, loss: 0.9746388792991638
2023-01-24 01:06:42.985995: step: 498/469, loss: 3.0564427375793457
2023-01-24 01:06:43.640144: step: 500/469, loss: 0.3690948486328125
2023-01-24 01:06:44.303760: step: 502/469, loss: 1.1224571466445923
2023-01-24 01:06:44.932927: step: 504/469, loss: 1.7088745832443237
2023-01-24 01:06:45.606902: step: 506/469, loss: 3.922182559967041
2023-01-24 01:06:46.232683: step: 508/469, loss: 0.7903258204460144
2023-01-24 01:06:46.891650: step: 510/469, loss: 5.102704048156738
2023-01-24 01:06:47.573784: step: 512/469, loss: 1.3014575242996216
2023-01-24 01:06:48.197111: step: 514/469, loss: 1.4630281925201416
2023-01-24 01:06:48.776885: step: 516/469, loss: 1.5601834058761597
2023-01-24 01:06:49.401443: step: 518/469, loss: 0.6343270540237427
2023-01-24 01:06:50.055748: step: 520/469, loss: 1.5897058248519897
2023-01-24 01:06:50.656549: step: 522/469, loss: 0.8664147853851318
2023-01-24 01:06:51.287277: step: 524/469, loss: 0.6561774611473083
2023-01-24 01:06:51.937737: step: 526/469, loss: 0.2877194881439209
2023-01-24 01:06:52.580937: step: 528/469, loss: 0.352175235748291
2023-01-24 01:06:53.210011: step: 530/469, loss: 1.875475287437439
2023-01-24 01:06:53.807102: step: 532/469, loss: 1.1144897937774658
2023-01-24 01:06:54.429309: step: 534/469, loss: 5.207115173339844
2023-01-24 01:06:54.987886: step: 536/469, loss: 0.47226953506469727
2023-01-24 01:06:55.644570: step: 538/469, loss: 0.3436928391456604
2023-01-24 01:06:56.339382: step: 540/469, loss: 1.0703237056732178
2023-01-24 01:06:57.010991: step: 542/469, loss: 5.599519729614258
2023-01-24 01:06:57.594255: step: 544/469, loss: 0.4232501983642578
2023-01-24 01:06:58.238844: step: 546/469, loss: 1.7377922534942627
2023-01-24 01:06:58.841154: step: 548/469, loss: 1.4081114530563354
2023-01-24 01:06:59.440699: step: 550/469, loss: 1.319005012512207
2023-01-24 01:07:00.026321: step: 552/469, loss: 0.7447803616523743
2023-01-24 01:07:00.592969: step: 554/469, loss: 0.9361552000045776
2023-01-24 01:07:01.228194: step: 556/469, loss: 0.48655951023101807
2023-01-24 01:07:01.920925: step: 558/469, loss: 1.8592716455459595
2023-01-24 01:07:02.593378: step: 560/469, loss: 0.7301490306854248
2023-01-24 01:07:03.267683: step: 562/469, loss: 0.5893291234970093
2023-01-24 01:07:03.963766: step: 564/469, loss: 1.2110570669174194
2023-01-24 01:07:04.601839: step: 566/469, loss: 0.45537492632865906
2023-01-24 01:07:05.242887: step: 568/469, loss: 0.3384642004966736
2023-01-24 01:07:05.892914: step: 570/469, loss: 1.717210054397583
2023-01-24 01:07:06.451083: step: 572/469, loss: 1.2995985746383667
2023-01-24 01:07:07.140952: step: 574/469, loss: 2.483738422393799
2023-01-24 01:07:07.812313: step: 576/469, loss: 3.003157615661621
2023-01-24 01:07:08.444463: step: 578/469, loss: 2.044503927230835
2023-01-24 01:07:09.093019: step: 580/469, loss: 1.1646147966384888
2023-01-24 01:07:09.702414: step: 582/469, loss: 1.753267765045166
2023-01-24 01:07:10.393076: step: 584/469, loss: 2.5488531589508057
2023-01-24 01:07:11.039963: step: 586/469, loss: 0.42046964168548584
2023-01-24 01:07:11.665189: step: 588/469, loss: 2.019542694091797
2023-01-24 01:07:12.224316: step: 590/469, loss: 1.6281038522720337
2023-01-24 01:07:12.887797: step: 592/469, loss: 0.3488382399082184
2023-01-24 01:07:13.634346: step: 594/469, loss: 5.730656623840332
2023-01-24 01:07:14.287722: step: 596/469, loss: 0.6978225111961365
2023-01-24 01:07:14.922856: step: 598/469, loss: 2.5393149852752686
2023-01-24 01:07:15.624520: step: 600/469, loss: 3.9996895790100098
2023-01-24 01:07:16.200769: step: 602/469, loss: 0.1451789289712906
2023-01-24 01:07:16.826230: step: 604/469, loss: 2.5012001991271973
2023-01-24 01:07:17.519991: step: 606/469, loss: 0.3928256928920746
2023-01-24 01:07:18.223241: step: 608/469, loss: 4.79415225982666
2023-01-24 01:07:18.868213: step: 610/469, loss: 0.42651355266571045
2023-01-24 01:07:19.456985: step: 612/469, loss: 0.732073187828064
2023-01-24 01:07:20.084104: step: 614/469, loss: 1.5955448150634766
2023-01-24 01:07:20.697909: step: 616/469, loss: 0.35005825757980347
2023-01-24 01:07:21.308428: step: 618/469, loss: 0.4389929175376892
2023-01-24 01:07:21.945661: step: 620/469, loss: 0.5638032555580139
2023-01-24 01:07:22.585736: step: 622/469, loss: 0.6681195497512817
2023-01-24 01:07:23.283930: step: 624/469, loss: 0.3109690845012665
2023-01-24 01:07:23.961561: step: 626/469, loss: 1.2713466882705688
2023-01-24 01:07:24.675274: step: 628/469, loss: 0.49100279808044434
2023-01-24 01:07:25.330127: step: 630/469, loss: 4.195455074310303
2023-01-24 01:07:25.977635: step: 632/469, loss: 0.32286709547042847
2023-01-24 01:07:26.665366: step: 634/469, loss: 0.5429559350013733
2023-01-24 01:07:27.302547: step: 636/469, loss: 4.631080627441406
2023-01-24 01:07:27.886603: step: 638/469, loss: 3.8390443325042725
2023-01-24 01:07:28.520723: step: 640/469, loss: 1.423614263534546
2023-01-24 01:07:29.135543: step: 642/469, loss: 2.320253610610962
2023-01-24 01:07:29.816429: step: 644/469, loss: 0.704879641532898
2023-01-24 01:07:30.645991: step: 646/469, loss: 0.2985306680202484
2023-01-24 01:07:31.227975: step: 648/469, loss: 1.1311973333358765
2023-01-24 01:07:31.826708: step: 650/469, loss: 1.9515068531036377
2023-01-24 01:07:32.459821: step: 652/469, loss: 2.115736246109009
2023-01-24 01:07:33.108369: step: 654/469, loss: 0.6140111088752747
2023-01-24 01:07:33.735713: step: 656/469, loss: 1.2745435237884521
2023-01-24 01:07:34.381426: step: 658/469, loss: 1.8633383512496948
2023-01-24 01:07:34.996074: step: 660/469, loss: 1.288448452949524
2023-01-24 01:07:35.608775: step: 662/469, loss: 1.4117538928985596
2023-01-24 01:07:36.295398: step: 664/469, loss: 10.073023796081543
2023-01-24 01:07:36.947957: step: 666/469, loss: 0.965945839881897
2023-01-24 01:07:37.600408: step: 668/469, loss: 0.662321150302887
2023-01-24 01:07:38.373889: step: 670/469, loss: 0.33532407879829407
2023-01-24 01:07:39.046762: step: 672/469, loss: 4.552870273590088
2023-01-24 01:07:39.763218: step: 674/469, loss: 0.46886712312698364
2023-01-24 01:07:40.424688: step: 676/469, loss: 5.918253421783447
2023-01-24 01:07:41.031029: step: 678/469, loss: 0.5071016550064087
2023-01-24 01:07:41.627806: step: 680/469, loss: 0.7586919665336609
2023-01-24 01:07:42.292291: step: 682/469, loss: 0.2960484027862549
2023-01-24 01:07:43.040537: step: 684/469, loss: 0.4234350025653839
2023-01-24 01:07:43.723290: step: 686/469, loss: 1.6380354166030884
2023-01-24 01:07:44.387567: step: 688/469, loss: 1.306402325630188
2023-01-24 01:07:45.017953: step: 690/469, loss: 1.4292117357254028
2023-01-24 01:07:45.622447: step: 692/469, loss: 0.2863052189350128
2023-01-24 01:07:46.257126: step: 694/469, loss: 1.137115478515625
2023-01-24 01:07:46.852409: step: 696/469, loss: 5.062310695648193
2023-01-24 01:07:47.536987: step: 698/469, loss: 1.6446831226348877
2023-01-24 01:07:48.137222: step: 700/469, loss: 0.8182534575462341
2023-01-24 01:07:48.808961: step: 702/469, loss: 6.349822521209717
2023-01-24 01:07:49.403868: step: 704/469, loss: 0.6283247470855713
2023-01-24 01:07:50.087733: step: 706/469, loss: 0.47316333651542664
2023-01-24 01:07:50.740629: step: 708/469, loss: 0.5101945400238037
2023-01-24 01:07:51.396312: step: 710/469, loss: 0.4977058172225952
2023-01-24 01:07:52.043039: step: 712/469, loss: 1.8934651613235474
2023-01-24 01:07:52.709879: step: 714/469, loss: 1.3311917781829834
2023-01-24 01:07:53.385641: step: 716/469, loss: 0.7333809733390808
2023-01-24 01:07:54.016809: step: 718/469, loss: 0.4255601167678833
2023-01-24 01:07:54.658412: step: 720/469, loss: 0.8671449422836304
2023-01-24 01:07:55.238371: step: 722/469, loss: 0.8723408579826355
2023-01-24 01:07:55.807999: step: 724/469, loss: 0.4028339385986328
2023-01-24 01:07:56.462763: step: 726/469, loss: 0.6326789259910583
2023-01-24 01:07:57.201024: step: 728/469, loss: 0.5795637369155884
2023-01-24 01:07:57.854934: step: 730/469, loss: 1.3285558223724365
2023-01-24 01:07:58.527139: step: 732/469, loss: 0.4316285252571106
2023-01-24 01:07:59.199105: step: 734/469, loss: 2.0834743976593018
2023-01-24 01:07:59.813818: step: 736/469, loss: 0.5148096680641174
2023-01-24 01:08:00.372669: step: 738/469, loss: 0.5455061197280884
2023-01-24 01:08:01.000547: step: 740/469, loss: 0.8825864791870117
2023-01-24 01:08:01.644192: step: 742/469, loss: 0.5048531293869019
2023-01-24 01:08:02.253855: step: 744/469, loss: 0.9531071782112122
2023-01-24 01:08:02.864291: step: 746/469, loss: 2.5482559204101562
2023-01-24 01:08:03.563168: step: 748/469, loss: 1.278427243232727
2023-01-24 01:08:04.195567: step: 750/469, loss: 3.294517993927002
2023-01-24 01:08:04.778516: step: 752/469, loss: 1.537923812866211
2023-01-24 01:08:05.460385: step: 754/469, loss: 1.2817145586013794
2023-01-24 01:08:06.083558: step: 756/469, loss: 1.3262953758239746
2023-01-24 01:08:06.729239: step: 758/469, loss: 2.2460379600524902
2023-01-24 01:08:07.392560: step: 760/469, loss: 0.8554172515869141
2023-01-24 01:08:08.134664: step: 762/469, loss: 1.2948087453842163
2023-01-24 01:08:08.791487: step: 764/469, loss: 0.9453698396682739
2023-01-24 01:08:09.443007: step: 766/469, loss: 2.4158775806427
2023-01-24 01:08:10.085860: step: 768/469, loss: 2.356306552886963
2023-01-24 01:08:10.696705: step: 770/469, loss: 0.622253954410553
2023-01-24 01:08:11.351026: step: 772/469, loss: 3.284148693084717
2023-01-24 01:08:12.022457: step: 774/469, loss: 1.1687579154968262
2023-01-24 01:08:12.667546: step: 776/469, loss: 2.5336499214172363
2023-01-24 01:08:13.281449: step: 778/469, loss: 1.128499150276184
2023-01-24 01:08:13.907511: step: 780/469, loss: 2.3241851329803467
2023-01-24 01:08:14.499074: step: 782/469, loss: 0.908094048500061
2023-01-24 01:08:15.104871: step: 784/469, loss: 1.9209789037704468
2023-01-24 01:08:15.788072: step: 786/469, loss: 0.5153329372406006
2023-01-24 01:08:16.399428: step: 788/469, loss: 0.4622742533683777
2023-01-24 01:08:16.982524: step: 790/469, loss: 0.35491305589675903
2023-01-24 01:08:17.600246: step: 792/469, loss: 0.2799530625343323
2023-01-24 01:08:18.209488: step: 794/469, loss: 0.6011663675308228
2023-01-24 01:08:18.819404: step: 796/469, loss: 0.7505756616592407
2023-01-24 01:08:19.466759: step: 798/469, loss: 0.774082601070404
2023-01-24 01:08:20.048751: step: 800/469, loss: 2.89441180229187
2023-01-24 01:08:20.701878: step: 802/469, loss: 1.2030647993087769
2023-01-24 01:08:21.261947: step: 804/469, loss: 1.4437882900238037
2023-01-24 01:08:21.937378: step: 806/469, loss: 1.3417713642120361
2023-01-24 01:08:22.482616: step: 808/469, loss: 0.897671639919281
2023-01-24 01:08:23.142229: step: 810/469, loss: 1.5458115339279175
2023-01-24 01:08:23.711090: step: 812/469, loss: 2.537576675415039
2023-01-24 01:08:24.386858: step: 814/469, loss: 0.6162286996841431
2023-01-24 01:08:24.970718: step: 816/469, loss: 2.908498764038086
2023-01-24 01:08:25.518769: step: 818/469, loss: 2.7944982051849365
2023-01-24 01:08:26.234609: step: 820/469, loss: 2.1001415252685547
2023-01-24 01:08:26.919751: step: 822/469, loss: 0.516606867313385
2023-01-24 01:08:27.520825: step: 824/469, loss: 1.3633286952972412
2023-01-24 01:08:28.066463: step: 826/469, loss: 0.6928209662437439
2023-01-24 01:08:28.688712: step: 828/469, loss: 6.307271957397461
2023-01-24 01:08:29.265617: step: 830/469, loss: 1.373197317123413
2023-01-24 01:08:29.884558: step: 832/469, loss: 2.2309093475341797
2023-01-24 01:08:30.493571: step: 834/469, loss: 0.9808170795440674
2023-01-24 01:08:31.148064: step: 836/469, loss: 0.8308428525924683
2023-01-24 01:08:31.788581: step: 838/469, loss: 2.0854196548461914
2023-01-24 01:08:32.510756: step: 840/469, loss: 0.5977488160133362
2023-01-24 01:08:33.084818: step: 842/469, loss: 2.2959518432617188
2023-01-24 01:08:33.738175: step: 844/469, loss: 0.8557641506195068
2023-01-24 01:08:34.354193: step: 846/469, loss: 1.5363421440124512
2023-01-24 01:08:34.989020: step: 848/469, loss: 0.9423149228096008
2023-01-24 01:08:35.661802: step: 850/469, loss: 0.31465744972229004
2023-01-24 01:08:36.310977: step: 852/469, loss: 1.1953325271606445
2023-01-24 01:08:36.897474: step: 854/469, loss: 0.9645344018936157
2023-01-24 01:08:37.520824: step: 856/469, loss: 2.452528476715088
2023-01-24 01:08:38.118314: step: 858/469, loss: 0.8919779062271118
2023-01-24 01:08:38.727545: step: 860/469, loss: 0.4718051552772522
2023-01-24 01:08:39.398000: step: 862/469, loss: 0.6578753590583801
2023-01-24 01:08:39.992659: step: 864/469, loss: 0.32035863399505615
2023-01-24 01:08:40.704635: step: 866/469, loss: 0.6884527206420898
2023-01-24 01:08:41.350377: step: 868/469, loss: 1.0650737285614014
2023-01-24 01:08:42.007453: step: 870/469, loss: 1.591570496559143
2023-01-24 01:08:42.665911: step: 872/469, loss: 1.2843754291534424
2023-01-24 01:08:43.394387: step: 874/469, loss: 0.6252328157424927
2023-01-24 01:08:44.165184: step: 876/469, loss: 0.641391932964325
2023-01-24 01:08:44.800516: step: 878/469, loss: 1.5632202625274658
2023-01-24 01:08:45.440792: step: 880/469, loss: 0.32845205068588257
2023-01-24 01:08:46.024109: step: 882/469, loss: 0.8776138424873352
2023-01-24 01:08:46.664538: step: 884/469, loss: 0.8035073280334473
2023-01-24 01:08:47.297623: step: 886/469, loss: 3.431936264038086
2023-01-24 01:08:47.920669: step: 888/469, loss: 1.466493844985962
2023-01-24 01:08:48.521561: step: 890/469, loss: 1.4160956144332886
2023-01-24 01:08:49.224388: step: 892/469, loss: 0.23779946565628052
2023-01-24 01:08:49.829298: step: 894/469, loss: 0.6482412815093994
2023-01-24 01:08:50.464647: step: 896/469, loss: 1.543224573135376
2023-01-24 01:08:51.128888: step: 898/469, loss: 0.6387840509414673
2023-01-24 01:08:51.677065: step: 900/469, loss: 1.2316296100616455
2023-01-24 01:08:52.259945: step: 902/469, loss: 0.20950624346733093
2023-01-24 01:08:52.868189: step: 904/469, loss: 0.31963419914245605
2023-01-24 01:08:53.537772: step: 906/469, loss: 0.23390412330627441
2023-01-24 01:08:54.162232: step: 908/469, loss: 1.7978248596191406
2023-01-24 01:08:54.779061: step: 910/469, loss: 0.3089022636413574
2023-01-24 01:08:55.412378: step: 912/469, loss: 0.5211467146873474
2023-01-24 01:08:56.068025: step: 914/469, loss: 2.172574281692505
2023-01-24 01:08:56.690866: step: 916/469, loss: 1.0389721393585205
2023-01-24 01:08:57.344297: step: 918/469, loss: 0.6100372076034546
2023-01-24 01:08:57.979494: step: 920/469, loss: 0.3743990361690521
2023-01-24 01:08:58.660656: step: 922/469, loss: 0.5694857835769653
2023-01-24 01:08:59.302212: step: 924/469, loss: 1.7047919034957886
2023-01-24 01:08:59.923834: step: 926/469, loss: 1.1307367086410522
2023-01-24 01:09:00.548652: step: 928/469, loss: 1.5924110412597656
2023-01-24 01:09:01.169523: step: 930/469, loss: 0.39301446080207825
2023-01-24 01:09:01.817632: step: 932/469, loss: 2.1423330307006836
2023-01-24 01:09:02.387224: step: 934/469, loss: 1.2712610960006714
2023-01-24 01:09:02.992465: step: 936/469, loss: 1.3836865425109863
2023-01-24 01:09:03.605275: step: 938/469, loss: 1.4844310283660889
==================================================
Loss: 1.479
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33776657501851953, 'r': 0.27944255542329133, 'f1': 0.3058488612836439}, 'combined': 0.22536231884057972, 'epoch': 2}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2779087933808191, 'r': 0.21408893323572706, 'f1': 0.24185964240480584}, 'combined': 0.13192344131171227, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33630569649782754, 'r': 0.27185242259596687, 'f1': 0.3006636447178899}, 'combined': 0.22154163295002413, 'epoch': 2}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2733015176084864, 'r': 0.2115398754773829, 'f1': 0.23848693542731256}, 'combined': 0.1300837829603523, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.335180000093683, 'r': 0.2811187097559922, 'f1': 0.30577824569950024}, 'combined': 0.2253102863048949, 'epoch': 2}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2858628152747975, 'r': 0.22100098710631647, 'f1': 0.24928181517771303}, 'combined': 0.13597189918784347, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29315476190476186, 'r': 0.2345238095238095, 'f1': 0.2605820105820106}, 'combined': 0.17372134038800705, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27941176470588236, 'r': 0.20652173913043478, 'f1': 0.2375}, 'combined': 0.11875, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5714285714285714, 'r': 0.13793103448275862, 'f1': 0.2222222222222222}, 'combined': 0.14814814814814814, 'epoch': 2}
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': 0.33776657501851953, 'r': 0.27944255542329133, 'f1': 0.3058488612836439}, 'combined': 0.22536231884057972, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2779087933808191, 'r': 0.21408893323572706, 'f1': 0.24185964240480584}, 'combined': 0.13192344131171227, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29315476190476186, 'r': 0.2345238095238095, 'f1': 0.2605820105820106}, 'combined': 0.17372134038800705, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33630569649782754, 'r': 0.27185242259596687, 'f1': 0.3006636447178899}, 'combined': 0.22154163295002413, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2733015176084864, 'r': 0.2115398754773829, 'f1': 0.23848693542731256}, 'combined': 0.1300837829603523, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27941176470588236, 'r': 0.20652173913043478, 'f1': 0.2375}, 'combined': 0.11875, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.335180000093683, 'r': 0.2811187097559922, 'f1': 0.30577824569950024}, 'combined': 0.2253102863048949, 'epoch': 2}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2858628152747975, 'r': 0.22100098710631647, 'f1': 0.24928181517771303}, 'combined': 0.13597189918784347, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5714285714285714, 'r': 0.13793103448275862, 'f1': 0.2222222222222222}, 'combined': 0.14814814814814814, 'epoch': 2}
******************************
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
2023-01-24 01:12:09.833713: step: 2/469, loss: 0.7462694644927979
2023-01-24 01:12:10.408765: step: 4/469, loss: 2.308076858520508
2023-01-24 01:12:11.047347: step: 6/469, loss: 0.6802846193313599
2023-01-24 01:12:11.667944: step: 8/469, loss: 1.4681999683380127
2023-01-24 01:12:12.381262: step: 10/469, loss: 1.167622685432434
2023-01-24 01:12:13.091165: step: 12/469, loss: 0.6306251883506775
2023-01-24 01:12:13.744036: step: 14/469, loss: 0.3387022614479065
2023-01-24 01:12:14.410926: step: 16/469, loss: 1.5801018476486206
2023-01-24 01:12:15.041941: step: 18/469, loss: 2.136303663253784
2023-01-24 01:12:15.670986: step: 20/469, loss: 1.0299530029296875
2023-01-24 01:12:16.287604: step: 22/469, loss: 1.8741533756256104
2023-01-24 01:12:16.897347: step: 24/469, loss: 1.4600305557250977
2023-01-24 01:12:17.447552: step: 26/469, loss: 0.3246730864048004
2023-01-24 01:12:18.045847: step: 28/469, loss: 0.8257705569267273
2023-01-24 01:12:18.652625: step: 30/469, loss: 1.4913718700408936
2023-01-24 01:12:19.343234: step: 32/469, loss: 6.998908042907715
2023-01-24 01:12:19.962515: step: 34/469, loss: 0.7767741084098816
2023-01-24 01:12:20.650485: step: 36/469, loss: 1.3027576208114624
2023-01-24 01:12:21.292004: step: 38/469, loss: 2.3133039474487305
2023-01-24 01:12:22.019976: step: 40/469, loss: 1.537103533744812
2023-01-24 01:12:22.709616: step: 42/469, loss: 0.4171549081802368
2023-01-24 01:12:23.283001: step: 44/469, loss: 0.6975013017654419
2023-01-24 01:12:23.983019: step: 46/469, loss: 0.4346381425857544
2023-01-24 01:12:24.574215: step: 48/469, loss: 1.0038912296295166
2023-01-24 01:12:25.170364: step: 50/469, loss: 1.3999648094177246
2023-01-24 01:12:25.851553: step: 52/469, loss: 1.855452060699463
2023-01-24 01:12:26.462292: step: 54/469, loss: 0.5486173033714294
2023-01-24 01:12:27.077019: step: 56/469, loss: 0.7375549077987671
2023-01-24 01:12:27.680835: step: 58/469, loss: 0.20711149275302887
2023-01-24 01:12:28.300995: step: 60/469, loss: 0.5829421877861023
2023-01-24 01:12:28.990030: step: 62/469, loss: 4.038946628570557
2023-01-24 01:12:29.631769: step: 64/469, loss: 1.4320002794265747
2023-01-24 01:12:30.271607: step: 66/469, loss: 0.5214782953262329
2023-01-24 01:12:30.878676: step: 68/469, loss: 1.410658597946167
2023-01-24 01:12:31.495496: step: 70/469, loss: 0.8122127056121826
2023-01-24 01:12:32.174485: step: 72/469, loss: 0.4889269471168518
2023-01-24 01:12:32.813643: step: 74/469, loss: 2.0898125171661377
2023-01-24 01:12:33.395606: step: 76/469, loss: 0.7922834157943726
2023-01-24 01:12:34.001965: step: 78/469, loss: 0.6663730144500732
2023-01-24 01:12:34.661956: step: 80/469, loss: 3.074713706970215
2023-01-24 01:12:35.253426: step: 82/469, loss: 4.164635181427002
2023-01-24 01:12:35.862969: step: 84/469, loss: 2.532348155975342
2023-01-24 01:12:36.453457: step: 86/469, loss: 0.5383509397506714
2023-01-24 01:12:37.062705: step: 88/469, loss: 1.1348263025283813
2023-01-24 01:12:37.714239: step: 90/469, loss: 0.40761780738830566
2023-01-24 01:12:38.346321: step: 92/469, loss: 0.3754013776779175
2023-01-24 01:12:39.006684: step: 94/469, loss: 0.4742070138454437
2023-01-24 01:12:39.629710: step: 96/469, loss: 0.9675819873809814
2023-01-24 01:12:40.239466: step: 98/469, loss: 1.2843284606933594
2023-01-24 01:12:40.910020: step: 100/469, loss: 0.9341386556625366
2023-01-24 01:12:41.565281: step: 102/469, loss: 2.3884425163269043
2023-01-24 01:12:42.232061: step: 104/469, loss: 1.4162704944610596
2023-01-24 01:12:42.941148: step: 106/469, loss: 0.5961185693740845
2023-01-24 01:12:43.583361: step: 108/469, loss: 0.6799505949020386
2023-01-24 01:12:44.241452: step: 110/469, loss: 0.3097529113292694
2023-01-24 01:12:44.823166: step: 112/469, loss: 0.43643665313720703
2023-01-24 01:12:45.460602: step: 114/469, loss: 0.7347835302352905
2023-01-24 01:12:46.105506: step: 116/469, loss: 0.29180267453193665
2023-01-24 01:12:46.823152: step: 118/469, loss: 0.3017939329147339
2023-01-24 01:12:47.418288: step: 120/469, loss: 1.890954852104187
2023-01-24 01:12:48.080799: step: 122/469, loss: 0.3954887092113495
2023-01-24 01:12:48.720502: step: 124/469, loss: 1.7034146785736084
2023-01-24 01:12:49.326639: step: 126/469, loss: 0.5341311693191528
2023-01-24 01:12:49.971470: step: 128/469, loss: 0.38662242889404297
2023-01-24 01:12:50.696040: step: 130/469, loss: 0.4594056308269501
2023-01-24 01:12:51.335741: step: 132/469, loss: 1.335113763809204
2023-01-24 01:12:51.940492: step: 134/469, loss: 0.5873169898986816
2023-01-24 01:12:52.551833: step: 136/469, loss: 0.814865231513977
2023-01-24 01:12:53.168315: step: 138/469, loss: 0.9610941410064697
2023-01-24 01:12:53.801896: step: 140/469, loss: 0.9838212132453918
2023-01-24 01:12:54.517136: step: 142/469, loss: 0.7003613710403442
2023-01-24 01:12:55.246978: step: 144/469, loss: 0.9541289210319519
2023-01-24 01:12:55.901217: step: 146/469, loss: 0.9891658425331116
2023-01-24 01:12:56.484105: step: 148/469, loss: 1.1233322620391846
2023-01-24 01:12:57.125656: step: 150/469, loss: 0.5784217715263367
2023-01-24 01:12:57.747091: step: 152/469, loss: 0.5650678873062134
2023-01-24 01:12:58.382002: step: 154/469, loss: 1.263162612915039
2023-01-24 01:12:58.994929: step: 156/469, loss: 4.338045120239258
2023-01-24 01:12:59.654352: step: 158/469, loss: 0.3969321846961975
2023-01-24 01:13:00.319062: step: 160/469, loss: 0.9037598967552185
2023-01-24 01:13:00.974963: step: 162/469, loss: 0.9089833498001099
2023-01-24 01:13:01.611710: step: 164/469, loss: 2.0887653827667236
2023-01-24 01:13:02.307469: step: 166/469, loss: 0.9849932193756104
2023-01-24 01:13:02.894745: step: 168/469, loss: 0.6771668791770935
2023-01-24 01:13:03.467623: step: 170/469, loss: 3.571570873260498
2023-01-24 01:13:04.090852: step: 172/469, loss: 5.442474842071533
2023-01-24 01:13:04.645270: step: 174/469, loss: 1.5340092182159424
2023-01-24 01:13:05.305722: step: 176/469, loss: 0.504738986492157
2023-01-24 01:13:05.895146: step: 178/469, loss: 0.7917119264602661
2023-01-24 01:13:06.482783: step: 180/469, loss: 1.0336380004882812
2023-01-24 01:13:07.092979: step: 182/469, loss: 0.8102993965148926
2023-01-24 01:13:07.667428: step: 184/469, loss: 2.229205846786499
2023-01-24 01:13:08.292506: step: 186/469, loss: 2.003970146179199
2023-01-24 01:13:08.922933: step: 188/469, loss: 0.8723458647727966
2023-01-24 01:13:09.514146: step: 190/469, loss: 0.7709511518478394
2023-01-24 01:13:10.173979: step: 192/469, loss: 1.1595580577850342
2023-01-24 01:13:10.837331: step: 194/469, loss: 1.3885128498077393
2023-01-24 01:13:11.454748: step: 196/469, loss: 0.6130228042602539
2023-01-24 01:13:12.106954: step: 198/469, loss: 0.4494071900844574
2023-01-24 01:13:12.784205: step: 200/469, loss: 1.9434261322021484
2023-01-24 01:13:13.503553: step: 202/469, loss: 0.2860829830169678
2023-01-24 01:13:14.135336: step: 204/469, loss: 1.2471989393234253
2023-01-24 01:13:14.775034: step: 206/469, loss: 2.7279419898986816
2023-01-24 01:13:15.396789: step: 208/469, loss: 0.5134357213973999
2023-01-24 01:13:16.058941: step: 210/469, loss: 1.6876628398895264
2023-01-24 01:13:16.696255: step: 212/469, loss: 0.38942527770996094
2023-01-24 01:13:17.367156: step: 214/469, loss: 3.4711406230926514
2023-01-24 01:13:17.945713: step: 216/469, loss: 0.9194731116294861
2023-01-24 01:13:18.594200: step: 218/469, loss: 0.2916356325149536
2023-01-24 01:13:19.175868: step: 220/469, loss: 0.3098664879798889
2023-01-24 01:13:19.780078: step: 222/469, loss: 0.2948499023914337
2023-01-24 01:13:20.416906: step: 224/469, loss: 1.8921873569488525
2023-01-24 01:13:21.067247: step: 226/469, loss: 0.43950873613357544
2023-01-24 01:13:21.644625: step: 228/469, loss: 1.2830665111541748
2023-01-24 01:13:22.245117: step: 230/469, loss: 0.6315370798110962
2023-01-24 01:13:22.871492: step: 232/469, loss: 2.4393703937530518
2023-01-24 01:13:23.519693: step: 234/469, loss: 1.4722431898117065
2023-01-24 01:13:24.118447: step: 236/469, loss: 0.4021998345851898
2023-01-24 01:13:24.731661: step: 238/469, loss: 0.47072941064834595
2023-01-24 01:13:25.387264: step: 240/469, loss: 3.191890239715576
2023-01-24 01:13:26.002871: step: 242/469, loss: 1.1580078601837158
2023-01-24 01:13:26.634494: step: 244/469, loss: 2.136058807373047
2023-01-24 01:13:27.220870: step: 246/469, loss: 0.6803306937217712
2023-01-24 01:13:27.930969: step: 248/469, loss: 3.1184935569763184
2023-01-24 01:13:28.616096: step: 250/469, loss: 0.7907870411872864
2023-01-24 01:13:29.197390: step: 252/469, loss: 1.046438455581665
2023-01-24 01:13:29.875115: step: 254/469, loss: 1.5306437015533447
2023-01-24 01:13:30.488251: step: 256/469, loss: 2.008882999420166
2023-01-24 01:13:31.215360: step: 258/469, loss: 1.6360721588134766
2023-01-24 01:13:31.830170: step: 260/469, loss: 3.3590636253356934
2023-01-24 01:13:32.472531: step: 262/469, loss: 0.5646939277648926
2023-01-24 01:13:33.092186: step: 264/469, loss: 9.744297981262207
2023-01-24 01:13:33.758988: step: 266/469, loss: 0.5964086651802063
2023-01-24 01:13:34.358730: step: 268/469, loss: 0.3714085519313812
2023-01-24 01:13:35.016924: step: 270/469, loss: 1.0284358263015747
2023-01-24 01:13:35.649561: step: 272/469, loss: 1.037506103515625
2023-01-24 01:13:36.256701: step: 274/469, loss: 1.135972023010254
2023-01-24 01:13:36.939876: step: 276/469, loss: 0.8764917850494385
2023-01-24 01:13:37.537925: step: 278/469, loss: 1.267731785774231
2023-01-24 01:13:38.190849: step: 280/469, loss: 0.672271728515625
2023-01-24 01:13:38.816813: step: 282/469, loss: 0.7760641574859619
2023-01-24 01:13:39.520934: step: 284/469, loss: 0.41035887598991394
2023-01-24 01:13:40.118422: step: 286/469, loss: 0.3258203864097595
2023-01-24 01:13:40.852021: step: 288/469, loss: 0.7342487573623657
2023-01-24 01:13:41.509334: step: 290/469, loss: 0.48638105392456055
2023-01-24 01:13:42.221560: step: 292/469, loss: 0.19374558329582214
2023-01-24 01:13:42.867530: step: 294/469, loss: 0.8818792700767517
2023-01-24 01:13:43.551643: step: 296/469, loss: 1.3577371835708618
2023-01-24 01:13:44.179508: step: 298/469, loss: 1.1259976625442505
2023-01-24 01:13:44.820099: step: 300/469, loss: 1.1442805528640747
2023-01-24 01:13:45.483372: step: 302/469, loss: 0.4293137192726135
2023-01-24 01:13:46.173310: step: 304/469, loss: 2.314356565475464
2023-01-24 01:13:46.847651: step: 306/469, loss: 2.0014007091522217
2023-01-24 01:13:47.510233: step: 308/469, loss: 0.2514479160308838
2023-01-24 01:13:48.134597: step: 310/469, loss: 0.37805867195129395
2023-01-24 01:13:48.738556: step: 312/469, loss: 0.29183441400527954
2023-01-24 01:13:49.480017: step: 314/469, loss: 0.41868263483047485
2023-01-24 01:13:50.143504: step: 316/469, loss: 0.7934480905532837
2023-01-24 01:13:50.809524: step: 318/469, loss: 0.8494001030921936
2023-01-24 01:13:51.436238: step: 320/469, loss: 1.078753113746643
2023-01-24 01:13:52.045523: step: 322/469, loss: 1.1665825843811035
2023-01-24 01:13:52.663139: step: 324/469, loss: 0.700657308101654
2023-01-24 01:13:53.247647: step: 326/469, loss: 1.3261842727661133
2023-01-24 01:13:53.903644: step: 328/469, loss: 0.9993078708648682
2023-01-24 01:13:54.538331: step: 330/469, loss: 0.39668697118759155
2023-01-24 01:13:55.148371: step: 332/469, loss: 1.7187021970748901
2023-01-24 01:13:55.797674: step: 334/469, loss: 0.6725361347198486
2023-01-24 01:13:56.457013: step: 336/469, loss: 0.47204115986824036
2023-01-24 01:13:57.096484: step: 338/469, loss: 0.36646369099617004
2023-01-24 01:13:57.725700: step: 340/469, loss: 0.686259388923645
2023-01-24 01:13:58.407139: step: 342/469, loss: 1.2658360004425049
2023-01-24 01:13:59.052600: step: 344/469, loss: 1.2248035669326782
2023-01-24 01:13:59.704188: step: 346/469, loss: 0.48144322633743286
2023-01-24 01:14:00.322949: step: 348/469, loss: 0.5733658075332642
2023-01-24 01:14:00.944629: step: 350/469, loss: 0.4137745797634125
2023-01-24 01:14:01.497937: step: 352/469, loss: 0.9133309125900269
2023-01-24 01:14:02.241099: step: 354/469, loss: 1.0647354125976562
2023-01-24 01:14:02.869272: step: 356/469, loss: 1.0498676300048828
2023-01-24 01:14:03.494966: step: 358/469, loss: 1.1451226472854614
2023-01-24 01:14:04.125732: step: 360/469, loss: 0.6535454988479614
2023-01-24 01:14:04.776327: step: 362/469, loss: 3.7403507232666016
2023-01-24 01:14:05.414892: step: 364/469, loss: 5.339025974273682
2023-01-24 01:14:06.032361: step: 366/469, loss: 0.40764179825782776
2023-01-24 01:14:06.683826: step: 368/469, loss: 0.7537856101989746
2023-01-24 01:14:07.268758: step: 370/469, loss: 0.23601745069026947
2023-01-24 01:14:07.882845: step: 372/469, loss: 0.7223626971244812
2023-01-24 01:14:08.533434: step: 374/469, loss: 0.3159669041633606
2023-01-24 01:14:09.133963: step: 376/469, loss: 0.7688659429550171
2023-01-24 01:14:09.765347: step: 378/469, loss: 4.336686134338379
2023-01-24 01:14:10.401674: step: 380/469, loss: 1.7180509567260742
2023-01-24 01:14:11.071155: step: 382/469, loss: 0.6608020067214966
2023-01-24 01:14:11.694667: step: 384/469, loss: 0.7804028987884521
2023-01-24 01:14:12.315503: step: 386/469, loss: 2.748377799987793
2023-01-24 01:14:12.941326: step: 388/469, loss: 0.3519863784313202
2023-01-24 01:14:13.554536: step: 390/469, loss: 1.5813013315200806
2023-01-24 01:14:14.142960: step: 392/469, loss: 0.32403886318206787
2023-01-24 01:14:14.784699: step: 394/469, loss: 1.7431018352508545
2023-01-24 01:14:15.374276: step: 396/469, loss: 0.5060060024261475
2023-01-24 01:14:16.042667: step: 398/469, loss: 0.3230733871459961
2023-01-24 01:14:16.690574: step: 400/469, loss: 3.857712507247925
2023-01-24 01:14:17.354708: step: 402/469, loss: 0.6641594767570496
2023-01-24 01:14:17.947516: step: 404/469, loss: 2.561873435974121
2023-01-24 01:14:18.591740: step: 406/469, loss: 0.4389699101448059
2023-01-24 01:14:19.207557: step: 408/469, loss: 0.5542924404144287
2023-01-24 01:14:19.851788: step: 410/469, loss: 0.47851628065109253
2023-01-24 01:14:20.524415: step: 412/469, loss: 1.3034582138061523
2023-01-24 01:14:21.142017: step: 414/469, loss: 0.903071403503418
2023-01-24 01:14:21.767589: step: 416/469, loss: 0.7119318842887878
2023-01-24 01:14:22.432855: step: 418/469, loss: 0.4629986584186554
2023-01-24 01:14:23.072933: step: 420/469, loss: 4.017146110534668
2023-01-24 01:14:23.734235: step: 422/469, loss: 2.6478612422943115
2023-01-24 01:14:24.386580: step: 424/469, loss: 3.849916934967041
2023-01-24 01:14:25.012209: step: 426/469, loss: 1.000108003616333
2023-01-24 01:14:25.769724: step: 428/469, loss: 0.8655878305435181
2023-01-24 01:14:26.423065: step: 430/469, loss: 0.47275301814079285
2023-01-24 01:14:27.063468: step: 432/469, loss: 0.4634517431259155
2023-01-24 01:14:27.755937: step: 434/469, loss: 0.28048980236053467
2023-01-24 01:14:28.432028: step: 436/469, loss: 1.0606825351715088
2023-01-24 01:14:29.049479: step: 438/469, loss: 1.068650722503662
2023-01-24 01:14:29.624976: step: 440/469, loss: 0.8255683183670044
2023-01-24 01:14:30.291361: step: 442/469, loss: 6.129979610443115
2023-01-24 01:14:30.921550: step: 444/469, loss: 0.5486658811569214
2023-01-24 01:14:31.541207: step: 446/469, loss: 0.8216400742530823
2023-01-24 01:14:32.205478: step: 448/469, loss: 0.4615059196949005
2023-01-24 01:14:32.867487: step: 450/469, loss: 0.6068246960639954
2023-01-24 01:14:33.438201: step: 452/469, loss: 0.5918332934379578
2023-01-24 01:14:33.995037: step: 454/469, loss: 0.3285779356956482
2023-01-24 01:14:34.617363: step: 456/469, loss: 0.5419658422470093
2023-01-24 01:14:35.248694: step: 458/469, loss: 0.2379702776670456
2023-01-24 01:14:35.833701: step: 460/469, loss: 1.733943223953247
2023-01-24 01:14:36.372430: step: 462/469, loss: 0.5931634902954102
2023-01-24 01:14:36.943298: step: 464/469, loss: 2.92630672454834
2023-01-24 01:14:37.683258: step: 466/469, loss: 0.519819438457489
2023-01-24 01:14:38.299763: step: 468/469, loss: 0.8577695488929749
2023-01-24 01:14:38.872668: step: 470/469, loss: 1.3270702362060547
2023-01-24 01:14:39.535713: step: 472/469, loss: 1.971328616142273
2023-01-24 01:14:40.233647: step: 474/469, loss: 0.82817542552948
2023-01-24 01:14:40.898485: step: 476/469, loss: 0.955100953578949
2023-01-24 01:14:41.563329: step: 478/469, loss: 0.8063927888870239
2023-01-24 01:14:42.220697: step: 480/469, loss: 0.644195556640625
2023-01-24 01:14:42.797796: step: 482/469, loss: 0.45841577649116516
2023-01-24 01:14:43.410953: step: 484/469, loss: 1.9108983278274536
2023-01-24 01:14:44.119814: step: 486/469, loss: 0.9897705912590027
2023-01-24 01:14:44.738903: step: 488/469, loss: 2.820888042449951
2023-01-24 01:14:45.508058: step: 490/469, loss: 0.4491350054740906
2023-01-24 01:14:46.151053: step: 492/469, loss: 0.8418124318122864
2023-01-24 01:14:46.783396: step: 494/469, loss: 1.5335557460784912
2023-01-24 01:14:47.396656: step: 496/469, loss: 2.7892379760742188
2023-01-24 01:14:48.014112: step: 498/469, loss: 1.3039991855621338
2023-01-24 01:14:48.691585: step: 500/469, loss: 0.7867889404296875
2023-01-24 01:14:49.319189: step: 502/469, loss: 0.29364848136901855
2023-01-24 01:14:49.964597: step: 504/469, loss: 0.8529661297798157
2023-01-24 01:14:50.523350: step: 506/469, loss: 1.6458814144134521
2023-01-24 01:14:51.175902: step: 508/469, loss: 0.8420606255531311
2023-01-24 01:14:51.793911: step: 510/469, loss: 1.815138578414917
2023-01-24 01:14:52.430922: step: 512/469, loss: 1.5718107223510742
2023-01-24 01:14:53.099260: step: 514/469, loss: 1.2635329961776733
2023-01-24 01:14:53.865981: step: 516/469, loss: 0.8168675899505615
2023-01-24 01:14:54.495031: step: 518/469, loss: 0.31952908635139465
2023-01-24 01:14:55.112123: step: 520/469, loss: 0.42109614610671997
2023-01-24 01:14:55.743468: step: 522/469, loss: 0.6543498635292053
2023-01-24 01:14:56.304428: step: 524/469, loss: 0.34267324209213257
2023-01-24 01:14:56.974410: step: 526/469, loss: 3.5468616485595703
2023-01-24 01:14:57.631973: step: 528/469, loss: 1.022538423538208
2023-01-24 01:14:58.269581: step: 530/469, loss: 0.319031298160553
2023-01-24 01:14:58.907498: step: 532/469, loss: 0.2147497683763504
2023-01-24 01:14:59.508396: step: 534/469, loss: 0.993924081325531
2023-01-24 01:15:00.155472: step: 536/469, loss: 1.1825424432754517
2023-01-24 01:15:00.820274: step: 538/469, loss: 2.5301554203033447
2023-01-24 01:15:01.489017: step: 540/469, loss: 0.9243333339691162
2023-01-24 01:15:02.141244: step: 542/469, loss: 0.12446283549070358
2023-01-24 01:15:02.769028: step: 544/469, loss: 1.8147050142288208
2023-01-24 01:15:03.381175: step: 546/469, loss: 2.3415894508361816
2023-01-24 01:15:04.033083: step: 548/469, loss: 1.674572229385376
2023-01-24 01:15:04.714874: step: 550/469, loss: 1.5341517925262451
2023-01-24 01:15:05.315653: step: 552/469, loss: 3.357795238494873
2023-01-24 01:15:05.994129: step: 554/469, loss: 1.271854043006897
2023-01-24 01:15:06.615763: step: 556/469, loss: 0.6844816207885742
2023-01-24 01:15:07.183261: step: 558/469, loss: 0.4120926558971405
2023-01-24 01:15:07.853417: step: 560/469, loss: 1.2114992141723633
2023-01-24 01:15:08.515216: step: 562/469, loss: 0.7472277879714966
2023-01-24 01:15:09.178164: step: 564/469, loss: 7.392098426818848
2023-01-24 01:15:09.782872: step: 566/469, loss: 0.5819260478019714
2023-01-24 01:15:10.417633: step: 568/469, loss: 0.6787862777709961
2023-01-24 01:15:11.038451: step: 570/469, loss: 2.225268602371216
2023-01-24 01:15:11.641539: step: 572/469, loss: 1.2054699659347534
2023-01-24 01:15:12.285788: step: 574/469, loss: 0.3201145827770233
2023-01-24 01:15:12.939445: step: 576/469, loss: 8.458700180053711
2023-01-24 01:15:13.544098: step: 578/469, loss: 0.7514448165893555
2023-01-24 01:15:14.180258: step: 580/469, loss: 1.1390188932418823
2023-01-24 01:15:14.907201: step: 582/469, loss: 0.8211749792098999
2023-01-24 01:15:15.595304: step: 584/469, loss: 1.5722768306732178
2023-01-24 01:15:16.230045: step: 586/469, loss: 0.17679743468761444
2023-01-24 01:15:16.831548: step: 588/469, loss: 0.49373096227645874
2023-01-24 01:15:17.390156: step: 590/469, loss: 0.975458562374115
2023-01-24 01:15:18.017786: step: 592/469, loss: 0.325543612241745
2023-01-24 01:15:18.714120: step: 594/469, loss: 0.9262832403182983
2023-01-24 01:15:19.343612: step: 596/469, loss: 0.39504551887512207
2023-01-24 01:15:20.039579: step: 598/469, loss: 0.7976389527320862
2023-01-24 01:15:20.640951: step: 600/469, loss: 1.9807462692260742
2023-01-24 01:15:21.276691: step: 602/469, loss: 0.970691442489624
2023-01-24 01:15:22.013533: step: 604/469, loss: 4.698398113250732
2023-01-24 01:15:22.641380: step: 606/469, loss: 0.6179900169372559
2023-01-24 01:15:23.281673: step: 608/469, loss: 3.7843470573425293
2023-01-24 01:15:23.893226: step: 610/469, loss: 2.340299606323242
2023-01-24 01:15:24.549860: step: 612/469, loss: 1.9795724153518677
2023-01-24 01:15:25.167247: step: 614/469, loss: 0.4936739206314087
2023-01-24 01:15:25.796132: step: 616/469, loss: 0.5711659789085388
2023-01-24 01:15:26.493114: step: 618/469, loss: 1.575615406036377
2023-01-24 01:15:27.121732: step: 620/469, loss: 0.4934542179107666
2023-01-24 01:15:27.736348: step: 622/469, loss: 0.42838650941848755
2023-01-24 01:15:28.360122: step: 624/469, loss: 1.5150914192199707
2023-01-24 01:15:29.066912: step: 626/469, loss: 0.5379862785339355
2023-01-24 01:15:29.782405: step: 628/469, loss: 5.567632675170898
2023-01-24 01:15:30.470427: step: 630/469, loss: 1.0272163152694702
2023-01-24 01:15:31.113801: step: 632/469, loss: 0.8592121601104736
2023-01-24 01:15:31.800739: step: 634/469, loss: 0.1969228833913803
2023-01-24 01:15:32.442799: step: 636/469, loss: 0.2630600333213806
2023-01-24 01:15:33.086261: step: 638/469, loss: 0.8592279553413391
2023-01-24 01:15:33.717424: step: 640/469, loss: 0.3999764025211334
2023-01-24 01:15:34.307862: step: 642/469, loss: 0.8150302767753601
2023-01-24 01:15:34.888023: step: 644/469, loss: 1.3769086599349976
2023-01-24 01:15:35.564318: step: 646/469, loss: 0.3551313877105713
2023-01-24 01:15:36.185013: step: 648/469, loss: 0.5282874703407288
2023-01-24 01:15:36.771193: step: 650/469, loss: 0.40043526887893677
2023-01-24 01:15:37.417897: step: 652/469, loss: 0.24054086208343506
2023-01-24 01:15:38.017735: step: 654/469, loss: 0.5337856411933899
2023-01-24 01:15:38.649930: step: 656/469, loss: 1.8747979402542114
2023-01-24 01:15:39.280295: step: 658/469, loss: 8.904938697814941
2023-01-24 01:15:39.933802: step: 660/469, loss: 0.4225645661354065
2023-01-24 01:15:40.552006: step: 662/469, loss: 10.951725006103516
2023-01-24 01:15:41.155244: step: 664/469, loss: 0.9561553001403809
2023-01-24 01:15:41.769202: step: 666/469, loss: 0.28639301657676697
2023-01-24 01:15:42.433019: step: 668/469, loss: 1.4371557235717773
2023-01-24 01:15:43.117853: step: 670/469, loss: 1.474899172782898
2023-01-24 01:15:43.726371: step: 672/469, loss: 0.6126270294189453
2023-01-24 01:15:44.296275: step: 674/469, loss: 0.9130380153656006
2023-01-24 01:15:44.935130: step: 676/469, loss: 0.5676673054695129
2023-01-24 01:15:45.595079: step: 678/469, loss: 0.39143142104148865
2023-01-24 01:15:46.208346: step: 680/469, loss: 1.296806812286377
2023-01-24 01:15:46.806971: step: 682/469, loss: 1.231890320777893
2023-01-24 01:15:47.429585: step: 684/469, loss: 0.690446674823761
2023-01-24 01:15:47.920240: step: 686/469, loss: 0.5328521728515625
2023-01-24 01:15:48.517445: step: 688/469, loss: 0.33294424414634705
2023-01-24 01:15:49.163803: step: 690/469, loss: 0.783265233039856
2023-01-24 01:15:49.846506: step: 692/469, loss: 1.0659931898117065
2023-01-24 01:15:50.535665: step: 694/469, loss: 0.7789087891578674
2023-01-24 01:15:51.143687: step: 696/469, loss: 0.8979896903038025
2023-01-24 01:15:51.691091: step: 698/469, loss: 0.54157555103302
2023-01-24 01:15:52.410771: step: 700/469, loss: 2.14607834815979
2023-01-24 01:15:53.047894: step: 702/469, loss: 0.7440817356109619
2023-01-24 01:15:53.671611: step: 704/469, loss: 0.34577518701553345
2023-01-24 01:15:54.269455: step: 706/469, loss: 0.6384104490280151
2023-01-24 01:15:54.895778: step: 708/469, loss: 0.20221437513828278
2023-01-24 01:15:55.593896: step: 710/469, loss: 0.9820117354393005
2023-01-24 01:15:56.208801: step: 712/469, loss: 0.4067484736442566
2023-01-24 01:15:56.802282: step: 714/469, loss: 0.869258463382721
2023-01-24 01:15:57.400237: step: 716/469, loss: 1.5712285041809082
2023-01-24 01:15:58.022567: step: 718/469, loss: 0.40880221128463745
2023-01-24 01:15:58.609590: step: 720/469, loss: 0.9945792555809021
2023-01-24 01:15:59.262032: step: 722/469, loss: 0.3624591827392578
2023-01-24 01:15:59.894807: step: 724/469, loss: 4.292018890380859
2023-01-24 01:16:00.462385: step: 726/469, loss: 3.2685019969940186
2023-01-24 01:16:01.116873: step: 728/469, loss: 3.2190017700195312
2023-01-24 01:16:01.721965: step: 730/469, loss: 0.9183965921401978
2023-01-24 01:16:02.284574: step: 732/469, loss: 1.8828498125076294
2023-01-24 01:16:02.926235: step: 734/469, loss: 1.029219388961792
2023-01-24 01:16:03.582365: step: 736/469, loss: 1.1005010604858398
2023-01-24 01:16:04.207052: step: 738/469, loss: 1.6785683631896973
2023-01-24 01:16:04.825979: step: 740/469, loss: 0.6691035032272339
2023-01-24 01:16:05.444163: step: 742/469, loss: 0.4262792468070984
2023-01-24 01:16:06.053524: step: 744/469, loss: 1.005275845527649
2023-01-24 01:16:06.635302: step: 746/469, loss: 0.6209067106246948
2023-01-24 01:16:07.256556: step: 748/469, loss: 1.2406554222106934
2023-01-24 01:16:07.858987: step: 750/469, loss: 0.734446108341217
2023-01-24 01:16:08.510395: step: 752/469, loss: 0.2791799008846283
2023-01-24 01:16:09.163171: step: 754/469, loss: 0.5821304321289062
2023-01-24 01:16:09.779629: step: 756/469, loss: 2.020531415939331
2023-01-24 01:16:10.479747: step: 758/469, loss: 3.246051788330078
2023-01-24 01:16:11.131490: step: 760/469, loss: 1.128767490386963
2023-01-24 01:16:11.764053: step: 762/469, loss: 4.814456939697266
2023-01-24 01:16:12.328421: step: 764/469, loss: 2.0687928199768066
2023-01-24 01:16:13.144444: step: 766/469, loss: 0.6035587787628174
2023-01-24 01:16:13.898174: step: 768/469, loss: 1.5669211149215698
2023-01-24 01:16:14.584790: step: 770/469, loss: 0.523723840713501
2023-01-24 01:16:15.207581: step: 772/469, loss: 2.5504186153411865
2023-01-24 01:16:15.825789: step: 774/469, loss: 0.7082122564315796
2023-01-24 01:16:16.497501: step: 776/469, loss: 0.48421937227249146
2023-01-24 01:16:17.105055: step: 778/469, loss: 0.39652830362319946
2023-01-24 01:16:17.733800: step: 780/469, loss: 0.2678658068180084
2023-01-24 01:16:18.408049: step: 782/469, loss: 0.4777577221393585
2023-01-24 01:16:19.052128: step: 784/469, loss: 0.6571331024169922
2023-01-24 01:16:19.669765: step: 786/469, loss: 0.8613175749778748
2023-01-24 01:16:20.309961: step: 788/469, loss: 0.9557031989097595
2023-01-24 01:16:20.969045: step: 790/469, loss: 1.1301566362380981
2023-01-24 01:16:21.603493: step: 792/469, loss: 0.18291328847408295
2023-01-24 01:16:22.189370: step: 794/469, loss: 2.295872688293457
2023-01-24 01:16:22.837735: step: 796/469, loss: 1.6139475107192993
2023-01-24 01:16:23.471382: step: 798/469, loss: 1.0522385835647583
2023-01-24 01:16:24.079834: step: 800/469, loss: 2.877741813659668
2023-01-24 01:16:24.719902: step: 802/469, loss: 0.4607471525669098
2023-01-24 01:16:25.365290: step: 804/469, loss: 0.3273234963417053
2023-01-24 01:16:25.981235: step: 806/469, loss: 0.9092198014259338
2023-01-24 01:16:26.599312: step: 808/469, loss: 0.4638720154762268
2023-01-24 01:16:27.190845: step: 810/469, loss: 4.013354301452637
2023-01-24 01:16:27.777836: step: 812/469, loss: 1.1741557121276855
2023-01-24 01:16:28.357294: step: 814/469, loss: 0.30634838342666626
2023-01-24 01:16:29.038475: step: 816/469, loss: 0.3868986964225769
2023-01-24 01:16:29.779629: step: 818/469, loss: 1.373685359954834
2023-01-24 01:16:30.455930: step: 820/469, loss: 1.350730538368225
2023-01-24 01:16:31.089752: step: 822/469, loss: 0.906842827796936
2023-01-24 01:16:31.682850: step: 824/469, loss: 1.3784503936767578
2023-01-24 01:16:32.353037: step: 826/469, loss: 1.1350330114364624
2023-01-24 01:16:32.932814: step: 828/469, loss: 0.5679834485054016
2023-01-24 01:16:33.541020: step: 830/469, loss: 1.3632066249847412
2023-01-24 01:16:34.189951: step: 832/469, loss: 0.5329816341400146
2023-01-24 01:16:34.825965: step: 834/469, loss: 0.2021186500787735
2023-01-24 01:16:35.408973: step: 836/469, loss: 3.89064621925354
2023-01-24 01:16:36.022478: step: 838/469, loss: 0.15132099390029907
2023-01-24 01:16:36.664656: step: 840/469, loss: 3.3353309631347656
2023-01-24 01:16:37.336002: step: 842/469, loss: 1.9553123712539673
2023-01-24 01:16:37.936746: step: 844/469, loss: 1.1097683906555176
2023-01-24 01:16:38.566325: step: 846/469, loss: 2.360145330429077
2023-01-24 01:16:39.159708: step: 848/469, loss: 1.4597703218460083
2023-01-24 01:16:39.786748: step: 850/469, loss: 1.0837464332580566
2023-01-24 01:16:40.412534: step: 852/469, loss: 0.16399157047271729
2023-01-24 01:16:41.029057: step: 854/469, loss: 0.23961219191551208
2023-01-24 01:16:41.658498: step: 856/469, loss: 1.4256689548492432
2023-01-24 01:16:42.307129: step: 858/469, loss: 0.370321124792099
2023-01-24 01:16:42.951270: step: 860/469, loss: 0.20350167155265808
2023-01-24 01:16:43.568979: step: 862/469, loss: 1.621083378791809
2023-01-24 01:16:44.163374: step: 864/469, loss: 5.380659103393555
2023-01-24 01:16:44.811329: step: 866/469, loss: 1.059912919998169
2023-01-24 01:16:45.460058: step: 868/469, loss: 5.188115119934082
2023-01-24 01:16:46.023787: step: 870/469, loss: 0.8952152729034424
2023-01-24 01:16:46.549776: step: 872/469, loss: 1.1000407934188843
2023-01-24 01:16:47.198922: step: 874/469, loss: 0.8673734664916992
2023-01-24 01:16:47.871793: step: 876/469, loss: 0.7367225289344788
2023-01-24 01:16:48.493721: step: 878/469, loss: 0.8778529763221741
2023-01-24 01:16:49.085389: step: 880/469, loss: 0.6977656483650208
2023-01-24 01:16:49.660160: step: 882/469, loss: 0.7239607572555542
2023-01-24 01:16:50.249325: step: 884/469, loss: 0.5380071997642517
2023-01-24 01:16:50.901579: step: 886/469, loss: 0.4684225022792816
2023-01-24 01:16:51.508111: step: 888/469, loss: 1.7237749099731445
2023-01-24 01:16:52.089462: step: 890/469, loss: 0.6721970438957214
2023-01-24 01:16:52.748360: step: 892/469, loss: 1.1410884857177734
2023-01-24 01:16:53.351660: step: 894/469, loss: 1.1650965213775635
2023-01-24 01:16:53.972346: step: 896/469, loss: 0.6795168519020081
2023-01-24 01:16:54.635430: step: 898/469, loss: 0.4723908603191376
2023-01-24 01:16:55.286962: step: 900/469, loss: 1.431899905204773
2023-01-24 01:16:55.898963: step: 902/469, loss: 1.9521191120147705
2023-01-24 01:16:56.511311: step: 904/469, loss: 0.8847671747207642
2023-01-24 01:16:57.168153: step: 906/469, loss: 1.087672233581543
2023-01-24 01:16:57.771506: step: 908/469, loss: 0.36223340034484863
2023-01-24 01:16:58.451873: step: 910/469, loss: 0.23744481801986694
2023-01-24 01:16:59.096177: step: 912/469, loss: 0.7776368856430054
2023-01-24 01:16:59.701469: step: 914/469, loss: 0.767355740070343
2023-01-24 01:17:00.318871: step: 916/469, loss: 1.4067308902740479
2023-01-24 01:17:00.962274: step: 918/469, loss: 0.6138659119606018
2023-01-24 01:17:01.563385: step: 920/469, loss: 1.3209500312805176
2023-01-24 01:17:02.180716: step: 922/469, loss: 1.3732243776321411
2023-01-24 01:17:02.720469: step: 924/469, loss: 0.24684622883796692
2023-01-24 01:17:03.327676: step: 926/469, loss: 0.3700372874736786
2023-01-24 01:17:03.951720: step: 928/469, loss: 0.6151580810546875
2023-01-24 01:17:04.511300: step: 930/469, loss: 0.5320045948028564
2023-01-24 01:17:05.132439: step: 932/469, loss: 0.9485318660736084
2023-01-24 01:17:05.762328: step: 934/469, loss: 1.2447638511657715
2023-01-24 01:17:06.392502: step: 936/469, loss: 1.3201947212219238
2023-01-24 01:17:06.988664: step: 938/469, loss: 0.31547755002975464
==================================================
Loss: 1.265
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36942859691150365, 'r': 0.20880746781954554, 'f1': 0.26680954221386377}, 'combined': 0.19659650478916277, 'epoch': 3}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.28176883941164615, 'r': 0.1824421069797782, 'f1': 0.22147905448210325}, 'combined': 0.12080675699023813, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36772411616161615, 'r': 0.2064538043478261, 'f1': 0.2644408292978208}, 'combined': 0.19485113737734164, 'epoch': 3}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.29125198310212513, 'r': 0.18725241653323843, 'f1': 0.22795041256686613}, 'combined': 0.12433658867283606, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3647376484949159, 'r': 0.20753503250844932, 'f1': 0.2645446558963125}, 'combined': 0.19492764118675657, 'epoch': 3}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2932069883241758, 'r': 0.18850933313262078, 'f1': 0.22948051115088355}, 'combined': 0.12517118790048193, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5208333333333333, 'r': 0.23809523809523805, 'f1': 0.326797385620915}, 'combined': 0.21786492374727665, 'epoch': 3}
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': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.25, 'r': 0.034482758620689655, 'f1': 0.0606060606060606}, 'combined': 0.0404040404040404, 'epoch': 3}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36942859691150365, 'r': 0.20880746781954554, 'f1': 0.26680954221386377}, 'combined': 0.19659650478916277, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.28176883941164615, 'r': 0.1824421069797782, 'f1': 0.22147905448210325}, 'combined': 0.12080675699023813, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5208333333333333, 'r': 0.23809523809523805, 'f1': 0.326797385620915}, 'combined': 0.21786492374727665, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33630569649782754, 'r': 0.27185242259596687, 'f1': 0.3006636447178899}, 'combined': 0.22154163295002413, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2733015176084864, 'r': 0.2115398754773829, 'f1': 0.23848693542731256}, 'combined': 0.1300837829603523, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27941176470588236, 'r': 0.20652173913043478, 'f1': 0.2375}, 'combined': 0.11875, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.335180000093683, 'r': 0.2811187097559922, 'f1': 0.30577824569950024}, 'combined': 0.2253102863048949, 'epoch': 2}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2858628152747975, 'r': 0.22100098710631647, 'f1': 0.24928181517771303}, 'combined': 0.13597189918784347, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5714285714285714, 'r': 0.13793103448275862, 'f1': 0.2222222222222222}, 'combined': 0.14814814814814814, 'epoch': 2}
******************************
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
2023-01-24 01:19:58.263198: step: 2/469, loss: 0.9050880074501038
2023-01-24 01:19:58.913468: step: 4/469, loss: 1.7855778932571411
2023-01-24 01:19:59.568905: step: 6/469, loss: 1.377054214477539
2023-01-24 01:20:00.187696: step: 8/469, loss: 0.9699809551239014
2023-01-24 01:20:00.859698: step: 10/469, loss: 5.43241024017334
2023-01-24 01:20:01.483575: step: 12/469, loss: 0.7427436113357544
2023-01-24 01:20:02.122168: step: 14/469, loss: 0.2859767973423004
2023-01-24 01:20:02.810024: step: 16/469, loss: 0.3392329216003418
2023-01-24 01:20:03.423330: step: 18/469, loss: 1.175756812095642
2023-01-24 01:20:04.088152: step: 20/469, loss: 0.47212445735931396
2023-01-24 01:20:04.683958: step: 22/469, loss: 0.6327062845230103
2023-01-24 01:20:05.306868: step: 24/469, loss: 0.5672405958175659
2023-01-24 01:20:06.062040: step: 26/469, loss: 0.6528533697128296
2023-01-24 01:20:06.710712: step: 28/469, loss: 1.1529587507247925
2023-01-24 01:20:07.335779: step: 30/469, loss: 2.4324116706848145
2023-01-24 01:20:08.068435: step: 32/469, loss: 1.1140735149383545
2023-01-24 01:20:08.767683: step: 34/469, loss: 0.59650719165802
2023-01-24 01:20:09.470628: step: 36/469, loss: 0.557941734790802
2023-01-24 01:20:10.147760: step: 38/469, loss: 0.6107344627380371
2023-01-24 01:20:10.753086: step: 40/469, loss: 0.46826887130737305
2023-01-24 01:20:11.405580: step: 42/469, loss: 1.0535849332809448
2023-01-24 01:20:11.973544: step: 44/469, loss: 0.12947534024715424
2023-01-24 01:20:12.598399: step: 46/469, loss: 0.728455126285553
2023-01-24 01:20:13.191438: step: 48/469, loss: 0.2109626829624176
2023-01-24 01:20:13.843279: step: 50/469, loss: 0.6350926756858826
2023-01-24 01:20:14.421911: step: 52/469, loss: 0.8698463439941406
2023-01-24 01:20:15.101187: step: 54/469, loss: 0.5368098020553589
2023-01-24 01:20:15.693939: step: 56/469, loss: 0.48263952136039734
2023-01-24 01:20:16.349599: step: 58/469, loss: 0.44925135374069214
2023-01-24 01:20:16.975029: step: 60/469, loss: 0.693838357925415
2023-01-24 01:20:17.568691: step: 62/469, loss: 0.42136090993881226
2023-01-24 01:20:18.188449: step: 64/469, loss: 0.6921431422233582
2023-01-24 01:20:18.813530: step: 66/469, loss: 0.23543782532215118
2023-01-24 01:20:19.401915: step: 68/469, loss: 0.6824563145637512
2023-01-24 01:20:19.991499: step: 70/469, loss: 0.33878639340400696
2023-01-24 01:20:20.558630: step: 72/469, loss: 0.4124892055988312
2023-01-24 01:20:21.170670: step: 74/469, loss: 4.621402740478516
2023-01-24 01:20:21.880700: step: 76/469, loss: 2.4642035961151123
2023-01-24 01:20:22.545175: step: 78/469, loss: 0.4639299511909485
2023-01-24 01:20:23.170283: step: 80/469, loss: 0.8192798495292664
2023-01-24 01:20:23.839836: step: 82/469, loss: 0.8129348754882812
2023-01-24 01:20:24.393276: step: 84/469, loss: 0.5626464486122131
2023-01-24 01:20:25.055478: step: 86/469, loss: 0.6481913328170776
2023-01-24 01:20:25.688598: step: 88/469, loss: 0.5031366348266602
2023-01-24 01:20:26.376946: step: 90/469, loss: 7.856209754943848
2023-01-24 01:20:26.975497: step: 92/469, loss: 0.9202807545661926
2023-01-24 01:20:27.654707: step: 94/469, loss: 0.7684484720230103
2023-01-24 01:20:28.259945: step: 96/469, loss: 0.7751802802085876
2023-01-24 01:20:28.895573: step: 98/469, loss: 0.9721737504005432
2023-01-24 01:20:29.564139: step: 100/469, loss: 1.2791332006454468
2023-01-24 01:20:30.135840: step: 102/469, loss: 1.091760277748108
2023-01-24 01:20:30.704558: step: 104/469, loss: 2.574777603149414
2023-01-24 01:20:31.298301: step: 106/469, loss: 0.768923282623291
2023-01-24 01:20:31.937776: step: 108/469, loss: 1.2980910539627075
2023-01-24 01:20:32.592402: step: 110/469, loss: 0.33849582076072693
2023-01-24 01:20:33.256666: step: 112/469, loss: 2.3791964054107666
2023-01-24 01:20:33.962393: step: 114/469, loss: 3.5567097663879395
2023-01-24 01:20:34.559123: step: 116/469, loss: 0.5802083015441895
2023-01-24 01:20:35.131835: step: 118/469, loss: 1.870171308517456
2023-01-24 01:20:35.752594: step: 120/469, loss: 0.9516633749008179
2023-01-24 01:20:36.376584: step: 122/469, loss: 0.45377635955810547
2023-01-24 01:20:36.924451: step: 124/469, loss: 1.0239235162734985
2023-01-24 01:20:37.627827: step: 126/469, loss: 0.9929549694061279
2023-01-24 01:20:38.265058: step: 128/469, loss: 1.1157602071762085
2023-01-24 01:20:38.905877: step: 130/469, loss: 1.861595630645752
2023-01-24 01:20:39.509680: step: 132/469, loss: 0.6413525342941284
2023-01-24 01:20:40.135704: step: 134/469, loss: 0.5361921787261963
2023-01-24 01:20:40.758934: step: 136/469, loss: 0.8921282887458801
2023-01-24 01:20:41.387536: step: 138/469, loss: 0.2659511864185333
2023-01-24 01:20:42.014986: step: 140/469, loss: 1.3578380346298218
2023-01-24 01:20:42.691309: step: 142/469, loss: 0.2122288942337036
2023-01-24 01:20:43.358656: step: 144/469, loss: 0.5673994421958923
2023-01-24 01:20:43.944022: step: 146/469, loss: 0.2596486508846283
2023-01-24 01:20:44.576420: step: 148/469, loss: 0.8392143249511719
2023-01-24 01:20:45.231560: step: 150/469, loss: 1.1436114311218262
2023-01-24 01:20:45.807371: step: 152/469, loss: 0.6285895705223083
2023-01-24 01:20:46.388199: step: 154/469, loss: 0.6549550890922546
2023-01-24 01:20:47.048302: step: 156/469, loss: 1.0163320302963257
2023-01-24 01:20:47.604993: step: 158/469, loss: 0.9874000549316406
2023-01-24 01:20:48.234094: step: 160/469, loss: 0.7254908680915833
2023-01-24 01:20:48.980100: step: 162/469, loss: 1.7849186658859253
2023-01-24 01:20:49.640708: step: 164/469, loss: 0.49793195724487305
2023-01-24 01:20:50.220211: step: 166/469, loss: 0.19076751172542572
2023-01-24 01:20:50.916658: step: 168/469, loss: 0.9988154768943787
2023-01-24 01:20:51.503853: step: 170/469, loss: 1.3795875310897827
2023-01-24 01:20:52.105128: step: 172/469, loss: 1.5315974950790405
2023-01-24 01:20:52.733111: step: 174/469, loss: 0.7056239247322083
2023-01-24 01:20:53.371565: step: 176/469, loss: 0.3275761604309082
2023-01-24 01:20:53.958474: step: 178/469, loss: 2.3691744804382324
2023-01-24 01:20:54.607587: step: 180/469, loss: 0.6250331997871399
2023-01-24 01:20:55.242353: step: 182/469, loss: 1.0679845809936523
2023-01-24 01:20:55.879287: step: 184/469, loss: 1.6039279699325562
2023-01-24 01:20:56.521169: step: 186/469, loss: 1.0112781524658203
2023-01-24 01:20:57.142822: step: 188/469, loss: 0.4016167223453522
2023-01-24 01:20:57.725859: step: 190/469, loss: 1.3260960578918457
2023-01-24 01:20:58.343560: step: 192/469, loss: 1.1128637790679932
2023-01-24 01:20:58.944453: step: 194/469, loss: 0.8418487310409546
2023-01-24 01:20:59.653056: step: 196/469, loss: 0.3964131772518158
2023-01-24 01:21:00.290579: step: 198/469, loss: 0.2029745727777481
2023-01-24 01:21:00.942293: step: 200/469, loss: 0.6018311381340027
2023-01-24 01:21:01.633299: step: 202/469, loss: 0.6261540651321411
2023-01-24 01:21:02.254422: step: 204/469, loss: 0.1680295318365097
2023-01-24 01:21:02.932590: step: 206/469, loss: 1.5685604810714722
2023-01-24 01:21:03.553319: step: 208/469, loss: 1.788804531097412
2023-01-24 01:21:04.143951: step: 210/469, loss: 0.24198587238788605
2023-01-24 01:21:04.771950: step: 212/469, loss: 0.2349502146244049
2023-01-24 01:21:05.434028: step: 214/469, loss: 0.4023289680480957
2023-01-24 01:21:06.068529: step: 216/469, loss: 0.44897568225860596
2023-01-24 01:21:06.660997: step: 218/469, loss: 1.668560266494751
2023-01-24 01:21:07.254810: step: 220/469, loss: 0.40680357813835144
2023-01-24 01:21:07.838083: step: 222/469, loss: 1.4389904737472534
2023-01-24 01:21:08.526064: step: 224/469, loss: 1.057631015777588
2023-01-24 01:21:09.217089: step: 226/469, loss: 1.1992883682250977
2023-01-24 01:21:09.945271: step: 228/469, loss: 1.7467793226242065
2023-01-24 01:21:10.581200: step: 230/469, loss: 1.4633595943450928
2023-01-24 01:21:11.191423: step: 232/469, loss: 1.3489941358566284
2023-01-24 01:21:11.733027: step: 234/469, loss: 0.4777461290359497
2023-01-24 01:21:12.379001: step: 236/469, loss: 0.1002981960773468
2023-01-24 01:21:12.977838: step: 238/469, loss: 0.7926585674285889
2023-01-24 01:21:13.600523: step: 240/469, loss: 1.6339585781097412
2023-01-24 01:21:14.253606: step: 242/469, loss: 0.6274259686470032
2023-01-24 01:21:14.853960: step: 244/469, loss: 2.0815725326538086
2023-01-24 01:21:15.501982: step: 246/469, loss: 0.2336321324110031
2023-01-24 01:21:16.113910: step: 248/469, loss: 0.8457404375076294
2023-01-24 01:21:16.714833: step: 250/469, loss: 0.5937406420707703
2023-01-24 01:21:17.402653: step: 252/469, loss: 1.0179897546768188
2023-01-24 01:21:18.026356: step: 254/469, loss: 0.622052013874054
2023-01-24 01:21:18.565600: step: 256/469, loss: 0.14757096767425537
2023-01-24 01:21:19.154838: step: 258/469, loss: 0.9615466594696045
2023-01-24 01:21:19.807675: step: 260/469, loss: 0.49650633335113525
2023-01-24 01:21:20.497836: step: 262/469, loss: 0.6913086175918579
2023-01-24 01:21:21.097680: step: 264/469, loss: 2.780974864959717
2023-01-24 01:21:21.704833: step: 266/469, loss: 0.9193152189254761
2023-01-24 01:21:22.392811: step: 268/469, loss: 1.0149012804031372
2023-01-24 01:21:23.008960: step: 270/469, loss: 1.1764382123947144
2023-01-24 01:21:23.671280: step: 272/469, loss: 1.2303965091705322
2023-01-24 01:21:24.317960: step: 274/469, loss: 0.20664067566394806
2023-01-24 01:21:24.871522: step: 276/469, loss: 0.3211139440536499
2023-01-24 01:21:25.485405: step: 278/469, loss: 2.22507381439209
2023-01-24 01:21:26.167735: step: 280/469, loss: 0.9276461601257324
2023-01-24 01:21:26.960505: step: 282/469, loss: 1.9384804964065552
2023-01-24 01:21:27.629377: step: 284/469, loss: 1.841937780380249
2023-01-24 01:21:28.202633: step: 286/469, loss: 1.1619877815246582
2023-01-24 01:21:28.859107: step: 288/469, loss: 4.353485107421875
2023-01-24 01:21:29.495081: step: 290/469, loss: 0.3011418581008911
2023-01-24 01:21:30.167155: step: 292/469, loss: 0.760834813117981
2023-01-24 01:21:30.843095: step: 294/469, loss: 0.5934541821479797
2023-01-24 01:21:31.446368: step: 296/469, loss: 0.13107189536094666
2023-01-24 01:21:32.039810: step: 298/469, loss: 1.6270647048950195
2023-01-24 01:21:32.654285: step: 300/469, loss: 0.38889196515083313
2023-01-24 01:21:33.326640: step: 302/469, loss: 0.344219446182251
2023-01-24 01:21:33.985890: step: 304/469, loss: 0.9043945670127869
2023-01-24 01:21:34.723447: step: 306/469, loss: 0.22975823283195496
2023-01-24 01:21:35.369408: step: 308/469, loss: 1.487387776374817
2023-01-24 01:21:35.989814: step: 310/469, loss: 2.59348201751709
2023-01-24 01:21:36.616099: step: 312/469, loss: 1.0137042999267578
2023-01-24 01:21:37.284590: step: 314/469, loss: 0.2761698365211487
2023-01-24 01:21:37.975013: step: 316/469, loss: 0.6512198448181152
2023-01-24 01:21:38.561575: step: 318/469, loss: 0.48551467061042786
2023-01-24 01:21:39.096979: step: 320/469, loss: 0.6216294765472412
2023-01-24 01:21:39.775468: step: 322/469, loss: 0.5735813975334167
2023-01-24 01:21:40.398780: step: 324/469, loss: 0.34954631328582764
2023-01-24 01:21:40.978632: step: 326/469, loss: 0.31153106689453125
2023-01-24 01:21:41.531833: step: 328/469, loss: 0.4782946705818176
2023-01-24 01:21:42.121778: step: 330/469, loss: 0.7630382776260376
2023-01-24 01:21:42.737953: step: 332/469, loss: 0.30100852251052856
2023-01-24 01:21:43.374159: step: 334/469, loss: 0.5501344203948975
2023-01-24 01:21:44.018643: step: 336/469, loss: 0.9008646607398987
2023-01-24 01:21:44.606234: step: 338/469, loss: 0.39844298362731934
2023-01-24 01:21:45.269781: step: 340/469, loss: 0.30655503273010254
2023-01-24 01:21:45.894287: step: 342/469, loss: 0.9962322115898132
2023-01-24 01:21:46.554233: step: 344/469, loss: 0.9260802268981934
2023-01-24 01:21:47.266721: step: 346/469, loss: 3.0620388984680176
2023-01-24 01:21:47.876626: step: 348/469, loss: 1.3196375370025635
2023-01-24 01:21:48.537937: step: 350/469, loss: 3.8971800804138184
2023-01-24 01:21:49.115542: step: 352/469, loss: 0.5359402894973755
2023-01-24 01:21:49.664966: step: 354/469, loss: 0.6907138824462891
2023-01-24 01:21:50.294748: step: 356/469, loss: 0.3582236170768738
2023-01-24 01:21:50.981355: step: 358/469, loss: 2.1482317447662354
2023-01-24 01:21:51.573963: step: 360/469, loss: 0.34017834067344666
2023-01-24 01:21:52.132862: step: 362/469, loss: 1.7577235698699951
2023-01-24 01:21:52.767713: step: 364/469, loss: 0.723415732383728
2023-01-24 01:21:53.393558: step: 366/469, loss: 2.5710692405700684
2023-01-24 01:21:54.083346: step: 368/469, loss: 0.3038272559642792
2023-01-24 01:21:54.792028: step: 370/469, loss: 1.0049059391021729
2023-01-24 01:21:55.393599: step: 372/469, loss: 0.4403672218322754
2023-01-24 01:21:56.041396: step: 374/469, loss: 0.8747326731681824
2023-01-24 01:21:56.663551: step: 376/469, loss: 0.3144104778766632
2023-01-24 01:21:57.310013: step: 378/469, loss: 1.0310653448104858
2023-01-24 01:21:57.935205: step: 380/469, loss: 0.6088466048240662
2023-01-24 01:21:58.529733: step: 382/469, loss: 0.3269631564617157
2023-01-24 01:21:59.154627: step: 384/469, loss: 0.3779875934123993
2023-01-24 01:21:59.784393: step: 386/469, loss: 0.4860456883907318
2023-01-24 01:22:00.337433: step: 388/469, loss: 1.0699275732040405
2023-01-24 01:22:00.929993: step: 390/469, loss: 0.33538371324539185
2023-01-24 01:22:01.611176: step: 392/469, loss: 0.8100714683532715
2023-01-24 01:22:02.300888: step: 394/469, loss: 0.5360186696052551
2023-01-24 01:22:02.951442: step: 396/469, loss: 0.8737802505493164
2023-01-24 01:22:03.522634: step: 398/469, loss: 1.6417113542556763
2023-01-24 01:22:04.159216: step: 400/469, loss: 0.5677798986434937
2023-01-24 01:22:04.818941: step: 402/469, loss: 0.5191171765327454
2023-01-24 01:22:05.494802: step: 404/469, loss: 1.025195598602295
2023-01-24 01:22:06.121507: step: 406/469, loss: 0.1223532035946846
2023-01-24 01:22:06.793993: step: 408/469, loss: 0.5266261696815491
2023-01-24 01:22:07.352355: step: 410/469, loss: 1.3209253549575806
2023-01-24 01:22:07.975516: step: 412/469, loss: 0.7187099456787109
2023-01-24 01:22:08.657070: step: 414/469, loss: 0.8508545756340027
2023-01-24 01:22:09.335543: step: 416/469, loss: 0.9024240374565125
2023-01-24 01:22:09.962438: step: 418/469, loss: 3.2285799980163574
2023-01-24 01:22:10.561110: step: 420/469, loss: 0.5391601920127869
2023-01-24 01:22:11.252741: step: 422/469, loss: 0.7348294258117676
2023-01-24 01:22:11.925482: step: 424/469, loss: 0.6996200084686279
2023-01-24 01:22:12.620441: step: 426/469, loss: 2.633759021759033
2023-01-24 01:22:13.280576: step: 428/469, loss: 1.1351779699325562
2023-01-24 01:22:13.929410: step: 430/469, loss: 0.646392285823822
2023-01-24 01:22:14.557646: step: 432/469, loss: 1.884870171546936
2023-01-24 01:22:15.154804: step: 434/469, loss: 0.3008376657962799
2023-01-24 01:22:15.795180: step: 436/469, loss: 1.3550143241882324
2023-01-24 01:22:16.440561: step: 438/469, loss: 0.7264467477798462
2023-01-24 01:22:17.051523: step: 440/469, loss: 0.198820561170578
2023-01-24 01:22:17.660752: step: 442/469, loss: 1.4231986999511719
2023-01-24 01:22:18.283948: step: 444/469, loss: 0.7573931813240051
2023-01-24 01:22:18.920643: step: 446/469, loss: 0.7570392489433289
2023-01-24 01:22:19.523634: step: 448/469, loss: 0.6987957954406738
2023-01-24 01:22:20.118059: step: 450/469, loss: 0.960996150970459
2023-01-24 01:22:20.740796: step: 452/469, loss: 0.9436129331588745
2023-01-24 01:22:21.415287: step: 454/469, loss: 2.3032419681549072
2023-01-24 01:22:21.988090: step: 456/469, loss: 0.8013098835945129
2023-01-24 01:22:22.616760: step: 458/469, loss: 1.3922255039215088
2023-01-24 01:22:23.215306: step: 460/469, loss: 0.8197945356369019
2023-01-24 01:22:23.840329: step: 462/469, loss: 0.954828143119812
2023-01-24 01:22:24.437050: step: 464/469, loss: 0.39458319544792175
2023-01-24 01:22:25.035161: step: 466/469, loss: 0.6810545325279236
2023-01-24 01:22:25.661576: step: 468/469, loss: 0.6716473698616028
2023-01-24 01:22:26.294724: step: 470/469, loss: 1.6145966053009033
2023-01-24 01:22:26.884648: step: 472/469, loss: 0.14848540723323822
2023-01-24 01:22:27.490124: step: 474/469, loss: 0.3003862202167511
2023-01-24 01:22:28.041085: step: 476/469, loss: 0.3544888198375702
2023-01-24 01:22:28.726396: step: 478/469, loss: 0.4897359013557434
2023-01-24 01:22:29.354176: step: 480/469, loss: 0.1578856110572815
2023-01-24 01:22:29.957580: step: 482/469, loss: 1.2774384021759033
2023-01-24 01:22:30.606556: step: 484/469, loss: 0.39732471108436584
2023-01-24 01:22:31.151425: step: 486/469, loss: 0.634797215461731
2023-01-24 01:22:31.779802: step: 488/469, loss: 1.6133782863616943
2023-01-24 01:22:32.410493: step: 490/469, loss: 1.0287816524505615
2023-01-24 01:22:33.060148: step: 492/469, loss: 0.3966401219367981
2023-01-24 01:22:33.687131: step: 494/469, loss: 0.4844699203968048
2023-01-24 01:22:34.317460: step: 496/469, loss: 1.137656569480896
2023-01-24 01:22:34.958595: step: 498/469, loss: 0.879274308681488
2023-01-24 01:22:35.614011: step: 500/469, loss: 2.080451726913452
2023-01-24 01:22:36.243843: step: 502/469, loss: 0.8389492034912109
2023-01-24 01:22:36.877452: step: 504/469, loss: 0.9974808692932129
2023-01-24 01:22:37.518661: step: 506/469, loss: 4.700196266174316
2023-01-24 01:22:38.153938: step: 508/469, loss: 1.077690839767456
2023-01-24 01:22:38.828822: step: 510/469, loss: 3.365203380584717
2023-01-24 01:22:39.478536: step: 512/469, loss: 1.383488655090332
2023-01-24 01:22:40.040254: step: 514/469, loss: 0.41354992985725403
2023-01-24 01:22:40.614223: step: 516/469, loss: 0.3490378260612488
2023-01-24 01:22:41.267721: step: 518/469, loss: 3.3838109970092773
2023-01-24 01:22:41.972962: step: 520/469, loss: 0.788618803024292
2023-01-24 01:22:42.652409: step: 522/469, loss: 2.7722554206848145
2023-01-24 01:22:43.302852: step: 524/469, loss: 0.3936830759048462
2023-01-24 01:22:43.842598: step: 526/469, loss: 1.5183649063110352
2023-01-24 01:22:44.426526: step: 528/469, loss: 0.3742457628250122
2023-01-24 01:22:45.047275: step: 530/469, loss: 1.0776413679122925
2023-01-24 01:22:45.655925: step: 532/469, loss: 0.2397650182247162
2023-01-24 01:22:46.299631: step: 534/469, loss: 0.9025579690933228
2023-01-24 01:22:46.914595: step: 536/469, loss: 0.18482525646686554
2023-01-24 01:22:47.572480: step: 538/469, loss: 1.2417709827423096
2023-01-24 01:22:48.214232: step: 540/469, loss: 0.5819209814071655
2023-01-24 01:22:48.827905: step: 542/469, loss: 0.7533178329467773
2023-01-24 01:22:49.487479: step: 544/469, loss: 0.6205441951751709
2023-01-24 01:22:50.128689: step: 546/469, loss: 0.4174264967441559
2023-01-24 01:22:50.784431: step: 548/469, loss: 0.7254074811935425
2023-01-24 01:22:51.428801: step: 550/469, loss: 0.41729649901390076
2023-01-24 01:22:52.047079: step: 552/469, loss: 3.5037264823913574
2023-01-24 01:22:52.700732: step: 554/469, loss: 0.3591243624687195
2023-01-24 01:22:53.300384: step: 556/469, loss: 6.033249378204346
2023-01-24 01:22:53.891242: step: 558/469, loss: 0.7233971357345581
2023-01-24 01:22:54.552849: step: 560/469, loss: 1.761699914932251
2023-01-24 01:22:55.179243: step: 562/469, loss: 0.5329675674438477
2023-01-24 01:22:55.774721: step: 564/469, loss: 0.46260109543800354
2023-01-24 01:22:56.362039: step: 566/469, loss: 2.472346305847168
2023-01-24 01:22:56.988134: step: 568/469, loss: 1.0746632814407349
2023-01-24 01:22:57.601710: step: 570/469, loss: 1.0300151109695435
2023-01-24 01:22:58.232108: step: 572/469, loss: 1.0891962051391602
2023-01-24 01:22:58.811343: step: 574/469, loss: 0.5832064151763916
2023-01-24 01:22:59.437296: step: 576/469, loss: 0.5408498048782349
2023-01-24 01:23:00.047403: step: 578/469, loss: 1.7607018947601318
2023-01-24 01:23:00.670568: step: 580/469, loss: 0.34821629524230957
2023-01-24 01:23:01.336574: step: 582/469, loss: 0.18294112384319305
2023-01-24 01:23:01.980186: step: 584/469, loss: 1.9501097202301025
2023-01-24 01:23:02.581327: step: 586/469, loss: 0.16994327306747437
2023-01-24 01:23:03.176732: step: 588/469, loss: 0.3547922372817993
2023-01-24 01:23:03.887740: step: 590/469, loss: 0.7541895508766174
2023-01-24 01:23:04.441534: step: 592/469, loss: 1.7084599733352661
2023-01-24 01:23:05.099918: step: 594/469, loss: 0.2464788854122162
2023-01-24 01:23:05.848399: step: 596/469, loss: 1.1210328340530396
2023-01-24 01:23:06.473748: step: 598/469, loss: 0.2027255892753601
2023-01-24 01:23:07.039989: step: 600/469, loss: 1.2290934324264526
2023-01-24 01:23:07.661069: step: 602/469, loss: 0.9369786381721497
2023-01-24 01:23:08.292249: step: 604/469, loss: 0.700100839138031
2023-01-24 01:23:08.879904: step: 606/469, loss: 0.4026202857494354
2023-01-24 01:23:09.516846: step: 608/469, loss: 0.398833692073822
2023-01-24 01:23:10.182125: step: 610/469, loss: 0.3640027940273285
2023-01-24 01:23:10.763064: step: 612/469, loss: 0.9620557427406311
2023-01-24 01:23:11.422502: step: 614/469, loss: 1.4510769844055176
2023-01-24 01:23:11.989513: step: 616/469, loss: 0.15558823943138123
2023-01-24 01:23:12.610918: step: 618/469, loss: 1.2236813306808472
2023-01-24 01:23:13.282902: step: 620/469, loss: 1.2272909879684448
2023-01-24 01:23:13.832988: step: 622/469, loss: 0.23699456453323364
2023-01-24 01:23:14.389290: step: 624/469, loss: 0.4633136987686157
2023-01-24 01:23:15.031600: step: 626/469, loss: 1.6583020687103271
2023-01-24 01:23:15.606730: step: 628/469, loss: 0.7730790376663208
2023-01-24 01:23:16.243201: step: 630/469, loss: 0.8075206875801086
2023-01-24 01:23:16.826290: step: 632/469, loss: 0.7500634789466858
2023-01-24 01:23:17.470346: step: 634/469, loss: 0.5523080825805664
2023-01-24 01:23:18.084498: step: 636/469, loss: 0.6977297067642212
2023-01-24 01:23:18.680852: step: 638/469, loss: 0.9085575342178345
2023-01-24 01:23:19.295826: step: 640/469, loss: 1.6701316833496094
2023-01-24 01:23:19.895704: step: 642/469, loss: 1.1490122079849243
2023-01-24 01:23:20.482831: step: 644/469, loss: 1.8123161792755127
2023-01-24 01:23:21.078356: step: 646/469, loss: 0.2635463774204254
2023-01-24 01:23:21.614806: step: 648/469, loss: 0.8812653422355652
2023-01-24 01:23:22.215524: step: 650/469, loss: 0.4694075286388397
2023-01-24 01:23:22.878716: step: 652/469, loss: 0.693772554397583
2023-01-24 01:23:23.511923: step: 654/469, loss: 0.6004814505577087
2023-01-24 01:23:24.149468: step: 656/469, loss: 0.9450744390487671
2023-01-24 01:23:24.749616: step: 658/469, loss: 1.323035717010498
2023-01-24 01:23:25.413368: step: 660/469, loss: 1.7586731910705566
2023-01-24 01:23:26.047174: step: 662/469, loss: 3.1064038276672363
2023-01-24 01:23:26.692825: step: 664/469, loss: 2.1606502532958984
2023-01-24 01:23:27.356924: step: 666/469, loss: 0.5083552598953247
2023-01-24 01:23:27.945374: step: 668/469, loss: 0.5356027483940125
2023-01-24 01:23:28.603780: step: 670/469, loss: 0.4719902575016022
2023-01-24 01:23:29.240141: step: 672/469, loss: 2.2638511657714844
2023-01-24 01:23:29.851376: step: 674/469, loss: 0.540315568447113
2023-01-24 01:23:30.604867: step: 676/469, loss: 0.6927760243415833
2023-01-24 01:23:31.146400: step: 678/469, loss: 0.7447448372840881
2023-01-24 01:23:31.735185: step: 680/469, loss: 0.6245925426483154
2023-01-24 01:23:32.382465: step: 682/469, loss: 1.2349224090576172
2023-01-24 01:23:32.987537: step: 684/469, loss: 4.0819854736328125
2023-01-24 01:23:33.600918: step: 686/469, loss: 3.266864538192749
2023-01-24 01:23:34.185449: step: 688/469, loss: 0.9348659515380859
2023-01-24 01:23:34.904412: step: 690/469, loss: 0.36093536019325256
2023-01-24 01:23:35.539606: step: 692/469, loss: 1.21728515625
2023-01-24 01:23:36.185478: step: 694/469, loss: 2.6873040199279785
2023-01-24 01:23:36.819020: step: 696/469, loss: 1.687104344367981
2023-01-24 01:23:37.496479: step: 698/469, loss: 1.1994125843048096
2023-01-24 01:23:38.135447: step: 700/469, loss: 0.6642340421676636
2023-01-24 01:23:38.807738: step: 702/469, loss: 0.1603505164384842
2023-01-24 01:23:39.507036: step: 704/469, loss: 0.4437829852104187
2023-01-24 01:23:40.223626: step: 706/469, loss: 0.8923883438110352
2023-01-24 01:23:40.868978: step: 708/469, loss: 2.0039939880371094
2023-01-24 01:23:41.423291: step: 710/469, loss: 1.2439526319503784
2023-01-24 01:23:42.128668: step: 712/469, loss: 0.8551022410392761
2023-01-24 01:23:42.803305: step: 714/469, loss: 2.400669574737549
2023-01-24 01:23:43.418274: step: 716/469, loss: 0.8577961325645447
2023-01-24 01:23:44.056386: step: 718/469, loss: 1.4866974353790283
2023-01-24 01:23:44.663873: step: 720/469, loss: 2.898620128631592
2023-01-24 01:23:45.268792: step: 722/469, loss: 1.0206254720687866
2023-01-24 01:23:45.854467: step: 724/469, loss: 0.9223724603652954
2023-01-24 01:23:46.411500: step: 726/469, loss: 1.4209712743759155
2023-01-24 01:23:47.001668: step: 728/469, loss: 0.8991994261741638
2023-01-24 01:23:47.742037: step: 730/469, loss: 1.7733222246170044
2023-01-24 01:23:48.400607: step: 732/469, loss: 0.49927276372909546
2023-01-24 01:23:49.001067: step: 734/469, loss: 1.2421603202819824
2023-01-24 01:23:49.674254: step: 736/469, loss: 0.5845636129379272
2023-01-24 01:23:50.329998: step: 738/469, loss: 0.8476709127426147
2023-01-24 01:23:50.879440: step: 740/469, loss: 0.3768523037433624
2023-01-24 01:23:51.532401: step: 742/469, loss: 0.7133253812789917
2023-01-24 01:23:52.123846: step: 744/469, loss: 1.2328099012374878
2023-01-24 01:23:52.713278: step: 746/469, loss: 0.4945378303527832
2023-01-24 01:23:53.309565: step: 748/469, loss: 0.808287501335144
2023-01-24 01:23:53.977965: step: 750/469, loss: 0.07773157209157944
2023-01-24 01:23:54.653592: step: 752/469, loss: 2.504279375076294
2023-01-24 01:23:55.268379: step: 754/469, loss: 1.210287094116211
2023-01-24 01:23:55.871485: step: 756/469, loss: 0.6139706969261169
2023-01-24 01:23:56.586289: step: 758/469, loss: 3.411437511444092
2023-01-24 01:23:57.237005: step: 760/469, loss: 0.9289321303367615
2023-01-24 01:23:57.817995: step: 762/469, loss: 0.8700323104858398
2023-01-24 01:23:58.445849: step: 764/469, loss: 1.5740787982940674
2023-01-24 01:23:59.063217: step: 766/469, loss: 0.9763445258140564
2023-01-24 01:23:59.666577: step: 768/469, loss: 0.9869160652160645
2023-01-24 01:24:00.296241: step: 770/469, loss: 1.6574498414993286
2023-01-24 01:24:00.839367: step: 772/469, loss: 2.648036003112793
2023-01-24 01:24:01.453654: step: 774/469, loss: 0.25199568271636963
2023-01-24 01:24:02.125257: step: 776/469, loss: 0.5826737284660339
2023-01-24 01:24:02.831730: step: 778/469, loss: 3.072148323059082
2023-01-24 01:24:03.533431: step: 780/469, loss: 1.031497836112976
2023-01-24 01:24:04.101498: step: 782/469, loss: 1.1756263971328735
2023-01-24 01:24:04.823191: step: 784/469, loss: 0.5341236591339111
2023-01-24 01:24:05.504266: step: 786/469, loss: 1.4256523847579956
2023-01-24 01:24:06.142303: step: 788/469, loss: 2.176980495452881
2023-01-24 01:24:06.804887: step: 790/469, loss: 1.3870797157287598
2023-01-24 01:24:07.427449: step: 792/469, loss: 0.4993237853050232
2023-01-24 01:24:08.065999: step: 794/469, loss: 0.2280917912721634
2023-01-24 01:24:08.676816: step: 796/469, loss: 0.6398214101791382
2023-01-24 01:24:09.311399: step: 798/469, loss: 0.5072592496871948
2023-01-24 01:24:10.029075: step: 800/469, loss: 1.4234272241592407
2023-01-24 01:24:10.601505: step: 802/469, loss: 0.8249620795249939
2023-01-24 01:24:11.251198: step: 804/469, loss: 0.5047292113304138
2023-01-24 01:24:11.851683: step: 806/469, loss: 3.447502374649048
2023-01-24 01:24:12.419877: step: 808/469, loss: 0.21030651032924652
2023-01-24 01:24:13.093267: step: 810/469, loss: 0.21714237332344055
2023-01-24 01:24:13.707621: step: 812/469, loss: 0.5368207097053528
2023-01-24 01:24:14.345450: step: 814/469, loss: 0.8567434549331665
2023-01-24 01:24:14.884381: step: 816/469, loss: 0.6117315888404846
2023-01-24 01:24:15.508137: step: 818/469, loss: 0.6387864351272583
2023-01-24 01:24:16.292160: step: 820/469, loss: 0.467052698135376
2023-01-24 01:24:16.932535: step: 822/469, loss: 0.2626565992832184
2023-01-24 01:24:17.547603: step: 824/469, loss: 0.4992005228996277
2023-01-24 01:24:18.303494: step: 826/469, loss: 0.391232967376709
2023-01-24 01:24:18.986131: step: 828/469, loss: 0.8604095578193665
2023-01-24 01:24:19.540974: step: 830/469, loss: 0.48425501585006714
2023-01-24 01:24:20.174439: step: 832/469, loss: 1.2435221672058105
2023-01-24 01:24:20.795146: step: 834/469, loss: 0.4931100308895111
2023-01-24 01:24:21.350428: step: 836/469, loss: 0.2618055045604706
2023-01-24 01:24:21.960376: step: 838/469, loss: 0.3797784447669983
2023-01-24 01:24:22.552001: step: 840/469, loss: 1.1894060373306274
2023-01-24 01:24:23.186547: step: 842/469, loss: 0.2713502049446106
2023-01-24 01:24:23.852847: step: 844/469, loss: 0.3778339624404907
2023-01-24 01:24:24.449864: step: 846/469, loss: 0.5766203999519348
2023-01-24 01:24:25.082323: step: 848/469, loss: 0.48425954580307007
2023-01-24 01:24:25.821526: step: 850/469, loss: 0.25006476044654846
2023-01-24 01:24:26.439555: step: 852/469, loss: 0.5502465963363647
2023-01-24 01:24:27.090537: step: 854/469, loss: 0.6801631450653076
2023-01-24 01:24:27.737676: step: 856/469, loss: 0.9096823334693909
2023-01-24 01:24:28.358621: step: 858/469, loss: 0.21374744176864624
2023-01-24 01:24:29.021850: step: 860/469, loss: 0.5357890129089355
2023-01-24 01:24:29.593944: step: 862/469, loss: 0.20686137676239014
2023-01-24 01:24:30.205451: step: 864/469, loss: 5.894195079803467
2023-01-24 01:24:30.892484: step: 866/469, loss: 1.6604406833648682
2023-01-24 01:24:31.523465: step: 868/469, loss: 1.2137590646743774
2023-01-24 01:24:32.182389: step: 870/469, loss: 0.36408406496047974
2023-01-24 01:24:32.752523: step: 872/469, loss: 4.091287612915039
2023-01-24 01:24:33.398200: step: 874/469, loss: 0.6501983404159546
2023-01-24 01:24:34.010303: step: 876/469, loss: 0.6695119738578796
2023-01-24 01:24:34.573984: step: 878/469, loss: 0.41327884793281555
2023-01-24 01:24:35.218513: step: 880/469, loss: 1.1272549629211426
2023-01-24 01:24:35.815902: step: 882/469, loss: 0.36916837096214294
2023-01-24 01:24:36.439526: step: 884/469, loss: 0.4161912798881531
2023-01-24 01:24:37.083796: step: 886/469, loss: 0.2770214378833771
2023-01-24 01:24:37.727754: step: 888/469, loss: 0.9130086302757263
2023-01-24 01:24:38.407903: step: 890/469, loss: 0.370594322681427
2023-01-24 01:24:39.021465: step: 892/469, loss: 0.7045907974243164
2023-01-24 01:24:39.671321: step: 894/469, loss: 0.5197343826293945
2023-01-24 01:24:40.235214: step: 896/469, loss: 0.6735163927078247
2023-01-24 01:24:40.908534: step: 898/469, loss: 1.0374263525009155
2023-01-24 01:24:41.551131: step: 900/469, loss: 0.24287647008895874
2023-01-24 01:24:42.203400: step: 902/469, loss: 0.6834206581115723
2023-01-24 01:24:42.877692: step: 904/469, loss: 0.47497767210006714
2023-01-24 01:24:43.499889: step: 906/469, loss: 1.5947412252426147
2023-01-24 01:24:44.155022: step: 908/469, loss: 0.2094680666923523
2023-01-24 01:24:44.707226: step: 910/469, loss: 2.8062334060668945
2023-01-24 01:24:45.374391: step: 912/469, loss: 2.472537040710449
2023-01-24 01:24:46.011855: step: 914/469, loss: 0.35665011405944824
2023-01-24 01:24:46.631116: step: 916/469, loss: 1.0690548419952393
2023-01-24 01:24:47.303133: step: 918/469, loss: 0.687286376953125
2023-01-24 01:24:47.938411: step: 920/469, loss: 0.5456666350364685
2023-01-24 01:24:48.565856: step: 922/469, loss: 0.7411112785339355
2023-01-24 01:24:49.151589: step: 924/469, loss: 0.8117825388908386
2023-01-24 01:24:49.751438: step: 926/469, loss: 3.4163637161254883
2023-01-24 01:24:50.405339: step: 928/469, loss: 0.5145717859268188
2023-01-24 01:24:50.977581: step: 930/469, loss: 0.7052063941955566
2023-01-24 01:24:51.570036: step: 932/469, loss: 0.7517820000648499
2023-01-24 01:24:52.171527: step: 934/469, loss: 0.48496013879776
2023-01-24 01:24:52.808996: step: 936/469, loss: 1.1040966510772705
2023-01-24 01:24:53.512343: step: 938/469, loss: 12.866398811340332
==================================================
Loss: 1.053
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377913727219283, 'r': 0.3115115885063703, 'f1': 0.32411965872232407}, 'combined': 0.2388250116901335, 'epoch': 4}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3155624431301183, 'r': 0.18114553408200573, 'f1': 0.23016633482661356}, 'combined': 0.1255452735417892, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3265968351997764, 'r': 0.2980893315580502, 'f1': 0.31169261454581837}, 'combined': 0.2296682422969188, 'epoch': 4}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3057287516930922, 'r': 0.18220762897979534, 'f1': 0.22833350069174813}, 'combined': 0.1245455458318626, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31716683708248133, 'r': 0.2942971220746364, 'f1': 0.30530429790026253}, 'combined': 0.22496106161071974, 'epoch': 4}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31478834153366136, 'r': 0.18444179791871748, 'f1': 0.2325986477499446}, 'combined': 0.12687198968178795, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33095238095238094, 'r': 0.33095238095238094, 'f1': 0.33095238095238094}, 'combined': 0.22063492063492063, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.22058823529411764, 'r': 0.16304347826086957, 'f1': 0.1875}, 'combined': 0.09375, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.13793103448275862, 'f1': 0.2162162162162162}, 'combined': 0.14414414414414412, 'epoch': 4}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377913727219283, 'r': 0.3115115885063703, 'f1': 0.32411965872232407}, 'combined': 0.2388250116901335, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3155624431301183, 'r': 0.18114553408200573, 'f1': 0.23016633482661356}, 'combined': 0.1255452735417892, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33095238095238094, 'r': 0.33095238095238094, 'f1': 0.33095238095238094}, 'combined': 0.22063492063492063, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33630569649782754, 'r': 0.27185242259596687, 'f1': 0.3006636447178899}, 'combined': 0.22154163295002413, 'epoch': 2}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2733015176084864, 'r': 0.2115398754773829, 'f1': 0.23848693542731256}, 'combined': 0.1300837829603523, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27941176470588236, 'r': 0.20652173913043478, 'f1': 0.2375}, 'combined': 0.11875, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.335180000093683, 'r': 0.2811187097559922, 'f1': 0.30577824569950024}, 'combined': 0.2253102863048949, 'epoch': 2}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.2858628152747975, 'r': 0.22100098710631647, 'f1': 0.24928181517771303}, 'combined': 0.13597189918784347, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5714285714285714, 'r': 0.13793103448275862, 'f1': 0.2222222222222222}, 'combined': 0.14814814814814814, 'epoch': 2}
******************************
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
2023-01-24 01:27:43.180515: step: 2/469, loss: 0.23082216084003448
2023-01-24 01:27:43.833203: step: 4/469, loss: 0.24468812346458435
2023-01-24 01:27:44.486055: step: 6/469, loss: 2.715531826019287
2023-01-24 01:27:45.103046: step: 8/469, loss: 0.8829636573791504
2023-01-24 01:27:45.738846: step: 10/469, loss: 0.6191074252128601
2023-01-24 01:27:46.391093: step: 12/469, loss: 0.8923539519309998
2023-01-24 01:27:47.024918: step: 14/469, loss: 0.4938492178916931
2023-01-24 01:27:47.653538: step: 16/469, loss: 8.393678665161133
2023-01-24 01:27:48.213000: step: 18/469, loss: 0.29203730821609497
2023-01-24 01:27:48.865647: step: 20/469, loss: 0.6454170942306519
2023-01-24 01:27:49.492007: step: 22/469, loss: 3.398102283477783
2023-01-24 01:27:50.074349: step: 24/469, loss: 0.4247226417064667
2023-01-24 01:27:50.776394: step: 26/469, loss: 0.14708152413368225
2023-01-24 01:27:51.411190: step: 28/469, loss: 1.7728263139724731
2023-01-24 01:27:52.057993: step: 30/469, loss: 1.058443307876587
2023-01-24 01:27:52.615771: step: 32/469, loss: 2.357333183288574
2023-01-24 01:27:53.177892: step: 34/469, loss: 0.5698264837265015
2023-01-24 01:27:53.768092: step: 36/469, loss: 0.2533670961856842
2023-01-24 01:27:54.426467: step: 38/469, loss: 0.42915767431259155
2023-01-24 01:27:55.049766: step: 40/469, loss: 1.779348373413086
2023-01-24 01:27:55.692364: step: 42/469, loss: 0.4198766350746155
2023-01-24 01:27:56.341183: step: 44/469, loss: 0.5436288118362427
2023-01-24 01:27:56.991483: step: 46/469, loss: 2.6733551025390625
2023-01-24 01:27:57.596785: step: 48/469, loss: 1.272593379020691
2023-01-24 01:27:58.317521: step: 50/469, loss: 0.5839976072311401
2023-01-24 01:27:58.946643: step: 52/469, loss: 0.22010065615177155
2023-01-24 01:27:59.626402: step: 54/469, loss: 0.8428466320037842
2023-01-24 01:28:00.244195: step: 56/469, loss: 0.21989446878433228
2023-01-24 01:28:00.841858: step: 58/469, loss: 0.2790488600730896
2023-01-24 01:28:01.506403: step: 60/469, loss: 0.5408099293708801
2023-01-24 01:28:02.102892: step: 62/469, loss: 0.35421276092529297
2023-01-24 01:28:02.817888: step: 64/469, loss: 2.1708390712738037
2023-01-24 01:28:03.501952: step: 66/469, loss: 0.29272645711898804
2023-01-24 01:28:04.089116: step: 68/469, loss: 0.8206204771995544
2023-01-24 01:28:04.668298: step: 70/469, loss: 0.4898074269294739
2023-01-24 01:28:05.267094: step: 72/469, loss: 1.111472487449646
2023-01-24 01:28:05.916721: step: 74/469, loss: 0.6634534597396851
2023-01-24 01:28:06.555778: step: 76/469, loss: 0.5694586634635925
2023-01-24 01:28:07.229639: step: 78/469, loss: 0.22259896993637085
2023-01-24 01:28:07.797166: step: 80/469, loss: 0.4513004422187805
2023-01-24 01:28:08.418739: step: 82/469, loss: 2.6729772090911865
2023-01-24 01:28:09.090086: step: 84/469, loss: 1.9189927577972412
2023-01-24 01:28:09.714283: step: 86/469, loss: 0.8211997747421265
2023-01-24 01:28:10.347648: step: 88/469, loss: 0.3043842315673828
2023-01-24 01:28:10.998089: step: 90/469, loss: 0.7644754648208618
2023-01-24 01:28:11.673226: step: 92/469, loss: 0.5473629832267761
2023-01-24 01:28:12.324448: step: 94/469, loss: 0.188741073012352
2023-01-24 01:28:13.018765: step: 96/469, loss: 0.3651156723499298
2023-01-24 01:28:13.676750: step: 98/469, loss: 0.1702229380607605
2023-01-24 01:28:14.342808: step: 100/469, loss: 0.7699720859527588
2023-01-24 01:28:14.892310: step: 102/469, loss: 0.21461914479732513
2023-01-24 01:28:15.457089: step: 104/469, loss: 0.40581464767456055
2023-01-24 01:28:16.059382: step: 106/469, loss: 1.7870793342590332
2023-01-24 01:28:16.667423: step: 108/469, loss: 0.23843681812286377
2023-01-24 01:28:17.274361: step: 110/469, loss: 0.7743473649024963
2023-01-24 01:28:17.940941: step: 112/469, loss: 1.068926215171814
2023-01-24 01:28:18.573332: step: 114/469, loss: 0.3782900869846344
2023-01-24 01:28:19.196616: step: 116/469, loss: 0.15446829795837402
2023-01-24 01:28:19.838789: step: 118/469, loss: 1.8861833810806274
2023-01-24 01:28:20.443233: step: 120/469, loss: 0.6652607321739197
2023-01-24 01:28:21.053738: step: 122/469, loss: 0.3511238694190979
2023-01-24 01:28:21.721924: step: 124/469, loss: 0.26555123925209045
2023-01-24 01:28:22.281525: step: 126/469, loss: 0.3291059136390686
2023-01-24 01:28:22.865434: step: 128/469, loss: 0.493099182844162
2023-01-24 01:28:23.494153: step: 130/469, loss: 2.3179497718811035
2023-01-24 01:28:24.123968: step: 132/469, loss: 0.8168757557868958
2023-01-24 01:28:24.811485: step: 134/469, loss: 1.5501023530960083
2023-01-24 01:28:25.463166: step: 136/469, loss: 0.5716238617897034
2023-01-24 01:28:26.089665: step: 138/469, loss: 0.443341463804245
2023-01-24 01:28:26.651008: step: 140/469, loss: 0.6165660619735718
2023-01-24 01:28:27.273873: step: 142/469, loss: 0.5413652062416077
2023-01-24 01:28:27.896989: step: 144/469, loss: 0.8951048254966736
2023-01-24 01:28:28.581965: step: 146/469, loss: 1.015242099761963
2023-01-24 01:28:29.201382: step: 148/469, loss: 0.5760049819946289
2023-01-24 01:28:29.786482: step: 150/469, loss: 0.5865218639373779
2023-01-24 01:28:30.461010: step: 152/469, loss: 0.48217886686325073
2023-01-24 01:28:31.120293: step: 154/469, loss: 1.7473310232162476
2023-01-24 01:28:31.653174: step: 156/469, loss: 0.15513287484645844
2023-01-24 01:28:32.262063: step: 158/469, loss: 0.23924881219863892
2023-01-24 01:28:32.948236: step: 160/469, loss: 0.6334220767021179
2023-01-24 01:28:33.531587: step: 162/469, loss: 0.36883997917175293
2023-01-24 01:28:34.202618: step: 164/469, loss: 0.969382107257843
2023-01-24 01:28:34.793415: step: 166/469, loss: 0.9840506315231323
2023-01-24 01:28:35.434659: step: 168/469, loss: 0.5908848643302917
2023-01-24 01:28:36.127702: step: 170/469, loss: 0.16666610538959503
2023-01-24 01:28:36.785767: step: 172/469, loss: 0.6665465831756592
2023-01-24 01:28:37.459512: step: 174/469, loss: 0.3576303720474243
2023-01-24 01:28:38.135220: step: 176/469, loss: 1.0005073547363281
2023-01-24 01:28:38.811666: step: 178/469, loss: 0.20010122656822205
2023-01-24 01:28:39.503176: step: 180/469, loss: 0.4356316328048706
2023-01-24 01:28:40.201260: step: 182/469, loss: 0.518362820148468
2023-01-24 01:28:40.798235: step: 184/469, loss: 0.1921110451221466
2023-01-24 01:28:41.418394: step: 186/469, loss: 0.44512102007865906
2023-01-24 01:28:42.047014: step: 188/469, loss: 0.590453565120697
2023-01-24 01:28:42.626368: step: 190/469, loss: 1.0626299381256104
2023-01-24 01:28:43.319079: step: 192/469, loss: 0.6436001062393188
2023-01-24 01:28:43.913513: step: 194/469, loss: 1.544126272201538
2023-01-24 01:28:44.513414: step: 196/469, loss: 0.32917964458465576
2023-01-24 01:28:45.111015: step: 198/469, loss: 1.4476020336151123
2023-01-24 01:28:45.729210: step: 200/469, loss: 0.7620005011558533
2023-01-24 01:28:46.367844: step: 202/469, loss: 1.2102952003479004
2023-01-24 01:28:46.974163: step: 204/469, loss: 0.9657041430473328
2023-01-24 01:28:47.602883: step: 206/469, loss: 1.2441942691802979
2023-01-24 01:28:48.196752: step: 208/469, loss: 0.22580377757549286
2023-01-24 01:28:48.845597: step: 210/469, loss: 0.20513802766799927
2023-01-24 01:28:49.548890: step: 212/469, loss: 0.5054277777671814
2023-01-24 01:28:50.202515: step: 214/469, loss: 0.5155064463615417
2023-01-24 01:28:50.818193: step: 216/469, loss: 0.5800778865814209
2023-01-24 01:28:51.551131: step: 218/469, loss: 0.5771896839141846
2023-01-24 01:28:52.156055: step: 220/469, loss: 0.6965882182121277
2023-01-24 01:28:52.814079: step: 222/469, loss: 0.36101800203323364
2023-01-24 01:28:53.484980: step: 224/469, loss: 1.1969101428985596
2023-01-24 01:28:54.108596: step: 226/469, loss: 1.0366992950439453
2023-01-24 01:28:54.830216: step: 228/469, loss: 0.6197690963745117
2023-01-24 01:28:55.413824: step: 230/469, loss: 0.4069611728191376
2023-01-24 01:28:56.027210: step: 232/469, loss: 1.0281972885131836
2023-01-24 01:28:56.670640: step: 234/469, loss: 0.6776111125946045
2023-01-24 01:28:57.243545: step: 236/469, loss: 0.3738084137439728
2023-01-24 01:28:57.883635: step: 238/469, loss: 1.2709115743637085
2023-01-24 01:28:58.428906: step: 240/469, loss: 5.531229496002197
2023-01-24 01:28:59.074453: step: 242/469, loss: 1.31396484375
2023-01-24 01:28:59.622954: step: 244/469, loss: 1.396083116531372
2023-01-24 01:29:00.371040: step: 246/469, loss: 0.8968508243560791
2023-01-24 01:29:00.994570: step: 248/469, loss: 0.14772929251194
2023-01-24 01:29:01.588078: step: 250/469, loss: 0.845439076423645
2023-01-24 01:29:02.184808: step: 252/469, loss: 1.2677044868469238
2023-01-24 01:29:02.843073: step: 254/469, loss: 0.5776054859161377
2023-01-24 01:29:03.496077: step: 256/469, loss: 4.868602752685547
2023-01-24 01:29:04.120047: step: 258/469, loss: 1.289811134338379
2023-01-24 01:29:04.754513: step: 260/469, loss: 0.9429295659065247
2023-01-24 01:29:05.379391: step: 262/469, loss: 0.18802818655967712
2023-01-24 01:29:06.009652: step: 264/469, loss: 0.7797534465789795
2023-01-24 01:29:06.589658: step: 266/469, loss: 1.340875267982483
2023-01-24 01:29:07.197110: step: 268/469, loss: 1.9435718059539795
2023-01-24 01:29:07.767334: step: 270/469, loss: 0.8291800618171692
2023-01-24 01:29:08.420434: step: 272/469, loss: 0.7410264015197754
2023-01-24 01:29:09.079829: step: 274/469, loss: 0.6898849010467529
2023-01-24 01:29:09.777132: step: 276/469, loss: 3.346698760986328
2023-01-24 01:29:10.381642: step: 278/469, loss: 0.8722501397132874
2023-01-24 01:29:11.044388: step: 280/469, loss: 1.635509729385376
2023-01-24 01:29:11.728783: step: 282/469, loss: 0.8487719297409058
2023-01-24 01:29:12.362274: step: 284/469, loss: 0.6330685615539551
2023-01-24 01:29:12.967477: step: 286/469, loss: 2.2650954723358154
2023-01-24 01:29:13.557019: step: 288/469, loss: 0.660061776638031
2023-01-24 01:29:14.145037: step: 290/469, loss: 1.5336778163909912
2023-01-24 01:29:14.735705: step: 292/469, loss: 0.2699785828590393
2023-01-24 01:29:15.387260: step: 294/469, loss: 0.3881272077560425
2023-01-24 01:29:16.052921: step: 296/469, loss: 1.184231162071228
2023-01-24 01:29:16.707220: step: 298/469, loss: 0.5889768600463867
2023-01-24 01:29:17.313592: step: 300/469, loss: 0.7570130228996277
2023-01-24 01:29:17.904929: step: 302/469, loss: 0.5367091298103333
2023-01-24 01:29:18.608549: step: 304/469, loss: 2.8680503368377686
2023-01-24 01:29:19.225667: step: 306/469, loss: 0.05204400420188904
2023-01-24 01:29:19.822533: step: 308/469, loss: 1.35739004611969
2023-01-24 01:29:20.450231: step: 310/469, loss: 0.3258724510669708
2023-01-24 01:29:21.094534: step: 312/469, loss: 0.29013729095458984
2023-01-24 01:29:21.725106: step: 314/469, loss: 0.27146241068840027
2023-01-24 01:29:22.388524: step: 316/469, loss: 0.49948427081108093
2023-01-24 01:29:23.014056: step: 318/469, loss: 1.1261435747146606
2023-01-24 01:29:23.576632: step: 320/469, loss: 0.25626009702682495
2023-01-24 01:29:24.182008: step: 322/469, loss: 0.22019492089748383
2023-01-24 01:29:24.772427: step: 324/469, loss: 0.3955521583557129
2023-01-24 01:29:25.332402: step: 326/469, loss: 0.3750266134738922
2023-01-24 01:29:25.934812: step: 328/469, loss: 0.5368538498878479
2023-01-24 01:29:26.564019: step: 330/469, loss: 0.5084934234619141
2023-01-24 01:29:27.255218: step: 332/469, loss: 1.0227596759796143
2023-01-24 01:29:27.791756: step: 334/469, loss: 0.6266493201255798
2023-01-24 01:29:28.370960: step: 336/469, loss: 0.8267876505851746
2023-01-24 01:29:28.958601: step: 338/469, loss: 4.548115253448486
2023-01-24 01:29:29.551238: step: 340/469, loss: 0.7014940977096558
2023-01-24 01:29:30.240853: step: 342/469, loss: 2.1303517818450928
2023-01-24 01:29:30.887521: step: 344/469, loss: 0.31942474842071533
2023-01-24 01:29:31.535972: step: 346/469, loss: 0.4026111662387848
2023-01-24 01:29:32.142217: step: 348/469, loss: 1.4867360591888428
2023-01-24 01:29:32.913527: step: 350/469, loss: 0.27226313948631287
2023-01-24 01:29:33.594146: step: 352/469, loss: 0.6493767499923706
2023-01-24 01:29:34.237192: step: 354/469, loss: 2.735508441925049
2023-01-24 01:29:34.825662: step: 356/469, loss: 1.5636558532714844
2023-01-24 01:29:35.488192: step: 358/469, loss: 0.47091829776763916
2023-01-24 01:29:36.139501: step: 360/469, loss: 1.05391263961792
2023-01-24 01:29:36.788944: step: 362/469, loss: 0.3859108090400696
2023-01-24 01:29:37.413282: step: 364/469, loss: 0.9916458129882812
2023-01-24 01:29:38.045117: step: 366/469, loss: 1.3550721406936646
2023-01-24 01:29:38.729933: step: 368/469, loss: 0.328305184841156
2023-01-24 01:29:39.379248: step: 370/469, loss: 0.8070709705352783
2023-01-24 01:29:39.966958: step: 372/469, loss: 2.137571334838867
2023-01-24 01:29:40.601031: step: 374/469, loss: 0.5778708457946777
2023-01-24 01:29:41.227618: step: 376/469, loss: 0.2450869083404541
2023-01-24 01:29:41.822917: step: 378/469, loss: 0.4169224798679352
2023-01-24 01:29:42.434406: step: 380/469, loss: 0.37350788712501526
2023-01-24 01:29:43.062935: step: 382/469, loss: 1.5586321353912354
2023-01-24 01:29:43.656370: step: 384/469, loss: 0.21327990293502808
2023-01-24 01:29:44.289895: step: 386/469, loss: 0.5003604292869568
2023-01-24 01:29:44.891022: step: 388/469, loss: 0.7882447838783264
2023-01-24 01:29:45.513818: step: 390/469, loss: 1.6546030044555664
2023-01-24 01:29:46.187644: step: 392/469, loss: 0.2584904730319977
2023-01-24 01:29:46.785088: step: 394/469, loss: 1.1590557098388672
2023-01-24 01:29:47.466885: step: 396/469, loss: 1.5481541156768799
2023-01-24 01:29:48.067668: step: 398/469, loss: 0.8572282791137695
2023-01-24 01:29:48.616307: step: 400/469, loss: 1.0574965476989746
2023-01-24 01:29:49.228241: step: 402/469, loss: 10.332171440124512
2023-01-24 01:29:49.904334: step: 404/469, loss: 0.7423107624053955
2023-01-24 01:29:50.493294: step: 406/469, loss: 0.5139293670654297
2023-01-24 01:29:51.148975: step: 408/469, loss: 4.425941467285156
2023-01-24 01:29:51.816406: step: 410/469, loss: 1.8335258960723877
2023-01-24 01:29:52.413499: step: 412/469, loss: 1.4402554035186768
2023-01-24 01:29:53.043881: step: 414/469, loss: 0.42355209589004517
2023-01-24 01:29:53.627463: step: 416/469, loss: 1.0914325714111328
2023-01-24 01:29:54.197241: step: 418/469, loss: 0.9456291198730469
2023-01-24 01:29:54.833609: step: 420/469, loss: 0.2497742921113968
2023-01-24 01:29:55.468670: step: 422/469, loss: 1.0893634557724
2023-01-24 01:29:56.119698: step: 424/469, loss: 0.17269906401634216
2023-01-24 01:29:56.738121: step: 426/469, loss: 1.409543752670288
2023-01-24 01:29:57.364689: step: 428/469, loss: 0.3833792507648468
2023-01-24 01:29:57.979264: step: 430/469, loss: 0.3209575116634369
2023-01-24 01:29:58.610498: step: 432/469, loss: 0.7200053334236145
2023-01-24 01:29:59.188709: step: 434/469, loss: 1.5605002641677856
2023-01-24 01:29:59.837468: step: 436/469, loss: 1.0715489387512207
2023-01-24 01:30:00.488204: step: 438/469, loss: 1.4137178659439087
2023-01-24 01:30:01.210232: step: 440/469, loss: 4.9024529457092285
2023-01-24 01:30:02.056388: step: 442/469, loss: 0.38857245445251465
2023-01-24 01:30:02.709055: step: 444/469, loss: 0.44481369853019714
2023-01-24 01:30:03.365035: step: 446/469, loss: 0.6289005279541016
2023-01-24 01:30:03.967813: step: 448/469, loss: 0.23422524333000183
2023-01-24 01:30:04.590006: step: 450/469, loss: 0.2247019112110138
2023-01-24 01:30:05.195531: step: 452/469, loss: 0.5358929634094238
2023-01-24 01:30:05.830091: step: 454/469, loss: 0.5743767619132996
2023-01-24 01:30:06.423405: step: 456/469, loss: 0.4127555191516876
2023-01-24 01:30:07.075766: step: 458/469, loss: 1.174877405166626
2023-01-24 01:30:07.632951: step: 460/469, loss: 0.8510198593139648
2023-01-24 01:30:08.249119: step: 462/469, loss: 0.31051793694496155
2023-01-24 01:30:08.835517: step: 464/469, loss: 2.053152084350586
2023-01-24 01:30:09.402468: step: 466/469, loss: 1.6194663047790527
2023-01-24 01:30:09.984001: step: 468/469, loss: 0.8800867199897766
2023-01-24 01:30:10.676832: step: 470/469, loss: 0.22569392621517181
2023-01-24 01:30:11.271024: step: 472/469, loss: 0.4594739079475403
2023-01-24 01:30:11.985166: step: 474/469, loss: 0.5039684176445007
2023-01-24 01:30:12.591833: step: 476/469, loss: 0.3357508182525635
2023-01-24 01:30:13.232972: step: 478/469, loss: 0.2989819347858429
2023-01-24 01:30:13.937885: step: 480/469, loss: 0.8009461164474487
2023-01-24 01:30:14.580113: step: 482/469, loss: 0.4875156283378601
2023-01-24 01:30:15.218248: step: 484/469, loss: 0.7731254696846008
2023-01-24 01:30:15.807791: step: 486/469, loss: 9.65363597869873
2023-01-24 01:30:16.427393: step: 488/469, loss: 1.6249033212661743
2023-01-24 01:30:17.007042: step: 490/469, loss: 0.4438440799713135
2023-01-24 01:30:17.647139: step: 492/469, loss: 1.6996326446533203
2023-01-24 01:30:18.250845: step: 494/469, loss: 1.0711129903793335
2023-01-24 01:30:18.831943: step: 496/469, loss: 0.6992626786231995
2023-01-24 01:30:19.467090: step: 498/469, loss: 0.8322696089744568
2023-01-24 01:30:20.129287: step: 500/469, loss: 0.9370493292808533
2023-01-24 01:30:20.762407: step: 502/469, loss: 4.563638687133789
2023-01-24 01:30:21.362570: step: 504/469, loss: 0.646310031414032
2023-01-24 01:30:22.009080: step: 506/469, loss: 0.26005351543426514
2023-01-24 01:30:22.593490: step: 508/469, loss: 1.821281909942627
2023-01-24 01:30:23.163820: step: 510/469, loss: 0.8955795168876648
2023-01-24 01:30:23.755489: step: 512/469, loss: 0.8382113575935364
2023-01-24 01:30:24.388277: step: 514/469, loss: 0.6199796199798584
2023-01-24 01:30:24.972952: step: 516/469, loss: 0.7629304528236389
2023-01-24 01:30:25.599078: step: 518/469, loss: 0.7643672823905945
2023-01-24 01:30:26.218213: step: 520/469, loss: 2.778000831604004
2023-01-24 01:30:26.916556: step: 522/469, loss: 0.3729744255542755
2023-01-24 01:30:27.527280: step: 524/469, loss: 2.275259256362915
2023-01-24 01:30:28.235137: step: 526/469, loss: 0.3773912489414215
2023-01-24 01:30:28.806980: step: 528/469, loss: 0.48497679829597473
2023-01-24 01:30:29.463854: step: 530/469, loss: 0.49681442975997925
2023-01-24 01:30:30.083206: step: 532/469, loss: 1.2908484935760498
2023-01-24 01:30:30.723660: step: 534/469, loss: 0.43272584676742554
2023-01-24 01:30:31.344074: step: 536/469, loss: 0.5426748991012573
2023-01-24 01:30:31.956989: step: 538/469, loss: 1.1667996644973755
2023-01-24 01:30:32.678705: step: 540/469, loss: 0.8148952722549438
2023-01-24 01:30:33.350825: step: 542/469, loss: 2.1252646446228027
2023-01-24 01:30:33.969480: step: 544/469, loss: 0.38486993312835693
2023-01-24 01:30:34.609607: step: 546/469, loss: 0.33599501848220825
2023-01-24 01:30:35.289505: step: 548/469, loss: 1.1564935445785522
2023-01-24 01:30:35.883806: step: 550/469, loss: 0.3236123025417328
2023-01-24 01:30:36.471964: step: 552/469, loss: 0.4061366617679596
2023-01-24 01:30:37.066673: step: 554/469, loss: 1.3559249639511108
2023-01-24 01:30:37.726471: step: 556/469, loss: 1.3511203527450562
2023-01-24 01:30:38.357335: step: 558/469, loss: 0.9502658843994141
2023-01-24 01:30:38.970304: step: 560/469, loss: 0.4477919936180115
2023-01-24 01:30:39.619360: step: 562/469, loss: 0.549677848815918
2023-01-24 01:30:40.245243: step: 564/469, loss: 0.6040837168693542
2023-01-24 01:30:40.947305: step: 566/469, loss: 1.6376280784606934
2023-01-24 01:30:41.686957: step: 568/469, loss: 0.6095688939094543
2023-01-24 01:30:42.433044: step: 570/469, loss: 0.9783769249916077
2023-01-24 01:30:43.074156: step: 572/469, loss: 0.24008788168430328
2023-01-24 01:30:43.628943: step: 574/469, loss: 0.3771034777164459
2023-01-24 01:30:44.360098: step: 576/469, loss: 0.20061251521110535
2023-01-24 01:30:44.974897: step: 578/469, loss: 0.9132511615753174
2023-01-24 01:30:45.615735: step: 580/469, loss: 0.503856897354126
2023-01-24 01:30:46.368274: step: 582/469, loss: 1.8077858686447144
2023-01-24 01:30:46.996839: step: 584/469, loss: 0.3756069540977478
2023-01-24 01:30:47.663232: step: 586/469, loss: 0.7689679265022278
2023-01-24 01:30:48.304908: step: 588/469, loss: 0.8368195295333862
2023-01-24 01:30:48.893407: step: 590/469, loss: 0.35350868105888367
2023-01-24 01:30:49.553521: step: 592/469, loss: 0.4454704225063324
2023-01-24 01:30:50.239317: step: 594/469, loss: 0.573936939239502
2023-01-24 01:30:50.975942: step: 596/469, loss: 1.1190050840377808
2023-01-24 01:30:51.619163: step: 598/469, loss: 0.4485684335231781
2023-01-24 01:30:52.236698: step: 600/469, loss: 0.6778914332389832
2023-01-24 01:30:52.862198: step: 602/469, loss: 1.0663076639175415
2023-01-24 01:30:53.463976: step: 604/469, loss: 1.1312828063964844
2023-01-24 01:30:54.067149: step: 606/469, loss: 0.3247070610523224
2023-01-24 01:30:54.672818: step: 608/469, loss: 0.8766698837280273
2023-01-24 01:30:55.304240: step: 610/469, loss: 1.199439287185669
2023-01-24 01:30:55.933200: step: 612/469, loss: 1.1807929277420044
2023-01-24 01:30:56.556444: step: 614/469, loss: 8.480010032653809
2023-01-24 01:30:57.154258: step: 616/469, loss: 0.8339220285415649
2023-01-24 01:30:57.856063: step: 618/469, loss: 0.4360521137714386
2023-01-24 01:30:58.541326: step: 620/469, loss: 3.8431954383850098
2023-01-24 01:30:59.216802: step: 622/469, loss: 1.5351340770721436
2023-01-24 01:30:59.796586: step: 624/469, loss: 0.12041905522346497
2023-01-24 01:31:00.433512: step: 626/469, loss: 0.4511202573776245
2023-01-24 01:31:01.123517: step: 628/469, loss: 0.6246999502182007
2023-01-24 01:31:01.719966: step: 630/469, loss: 1.0157084465026855
2023-01-24 01:31:02.371571: step: 632/469, loss: 0.19886675477027893
2023-01-24 01:31:02.978381: step: 634/469, loss: 1.221996545791626
2023-01-24 01:31:03.570479: step: 636/469, loss: 0.64617919921875
2023-01-24 01:31:04.226129: step: 638/469, loss: 0.5407251119613647
2023-01-24 01:31:04.886857: step: 640/469, loss: 1.7271944284439087
2023-01-24 01:31:05.547221: step: 642/469, loss: 0.2501175105571747
2023-01-24 01:31:06.240828: step: 644/469, loss: 0.4819124937057495
2023-01-24 01:31:06.872945: step: 646/469, loss: 0.628630518913269
2023-01-24 01:31:07.423862: step: 648/469, loss: 0.6487637758255005
2023-01-24 01:31:08.069865: step: 650/469, loss: 0.5462210178375244
2023-01-24 01:31:08.647733: step: 652/469, loss: 1.4214494228363037
2023-01-24 01:31:09.244167: step: 654/469, loss: 1.1150355339050293
2023-01-24 01:31:09.872159: step: 656/469, loss: 0.8862869739532471
2023-01-24 01:31:10.524642: step: 658/469, loss: 0.4711628556251526
2023-01-24 01:31:11.177601: step: 660/469, loss: 0.5369870662689209
2023-01-24 01:31:11.833490: step: 662/469, loss: 0.3013482093811035
2023-01-24 01:31:12.473704: step: 664/469, loss: 0.8464496731758118
2023-01-24 01:31:13.104097: step: 666/469, loss: 2.2260985374450684
2023-01-24 01:31:13.826289: step: 668/469, loss: 0.6346535086631775
2023-01-24 01:31:14.520782: step: 670/469, loss: 0.40371185541152954
2023-01-24 01:31:15.201073: step: 672/469, loss: 0.46036118268966675
2023-01-24 01:31:15.795164: step: 674/469, loss: 1.002408742904663
2023-01-24 01:31:16.401266: step: 676/469, loss: 0.8121116161346436
2023-01-24 01:31:17.098455: step: 678/469, loss: 2.1659016609191895
2023-01-24 01:31:17.715402: step: 680/469, loss: 1.4213732481002808
2023-01-24 01:31:18.326687: step: 682/469, loss: 9.95286750793457
2023-01-24 01:31:18.994816: step: 684/469, loss: 0.698919951915741
2023-01-24 01:31:19.553845: step: 686/469, loss: 0.5194299817085266
2023-01-24 01:31:20.179813: step: 688/469, loss: 0.5758535265922546
2023-01-24 01:31:20.813582: step: 690/469, loss: 1.1437273025512695
2023-01-24 01:31:21.406102: step: 692/469, loss: 3.149909496307373
2023-01-24 01:31:22.172328: step: 694/469, loss: 3.176224946975708
2023-01-24 01:31:22.819558: step: 696/469, loss: 1.150980830192566
2023-01-24 01:31:23.442491: step: 698/469, loss: 0.47864046692848206
2023-01-24 01:31:24.039990: step: 700/469, loss: 0.32273152470588684
2023-01-24 01:31:24.708307: step: 702/469, loss: 0.6380746364593506
2023-01-24 01:31:25.333313: step: 704/469, loss: 0.8380205631256104
2023-01-24 01:31:25.984092: step: 706/469, loss: 1.3941864967346191
2023-01-24 01:31:26.657689: step: 708/469, loss: 0.4604773223400116
2023-01-24 01:31:27.275401: step: 710/469, loss: 0.4957902133464813
2023-01-24 01:31:27.896252: step: 712/469, loss: 0.32155537605285645
2023-01-24 01:31:28.528514: step: 714/469, loss: 0.30814430117607117
2023-01-24 01:31:29.147412: step: 716/469, loss: 1.67085599899292
2023-01-24 01:31:29.905020: step: 718/469, loss: 0.6058162450790405
2023-01-24 01:31:30.523686: step: 720/469, loss: 1.4921011924743652
2023-01-24 01:31:31.094615: step: 722/469, loss: 0.1933315545320511
2023-01-24 01:31:31.671541: step: 724/469, loss: 0.4738868474960327
2023-01-24 01:31:32.224471: step: 726/469, loss: 0.4650869369506836
2023-01-24 01:31:32.855424: step: 728/469, loss: 0.25048828125
2023-01-24 01:31:33.512712: step: 730/469, loss: 0.3387415409088135
2023-01-24 01:31:34.145241: step: 732/469, loss: 0.3434506058692932
2023-01-24 01:31:34.754667: step: 734/469, loss: 0.253253310918808
2023-01-24 01:31:35.466161: step: 736/469, loss: 0.3523101210594177
2023-01-24 01:31:36.051357: step: 738/469, loss: 0.5128129124641418
2023-01-24 01:31:36.663428: step: 740/469, loss: 0.9110864400863647
2023-01-24 01:31:37.242162: step: 742/469, loss: 3.7775814533233643
2023-01-24 01:31:37.838166: step: 744/469, loss: 0.6204109191894531
2023-01-24 01:31:38.496175: step: 746/469, loss: 1.1810518503189087
2023-01-24 01:31:39.214550: step: 748/469, loss: 0.7742908000946045
2023-01-24 01:31:39.933789: step: 750/469, loss: 2.7484686374664307
2023-01-24 01:31:40.523647: step: 752/469, loss: 0.34478098154067993
2023-01-24 01:31:41.143966: step: 754/469, loss: 0.5299589037895203
2023-01-24 01:31:41.766900: step: 756/469, loss: 0.6918959617614746
2023-01-24 01:31:42.344969: step: 758/469, loss: 0.6955001950263977
2023-01-24 01:31:42.968386: step: 760/469, loss: 0.3608554005622864
2023-01-24 01:31:43.604659: step: 762/469, loss: 2.166154146194458
2023-01-24 01:31:44.305785: step: 764/469, loss: 0.20256467163562775
2023-01-24 01:31:44.931141: step: 766/469, loss: 0.271989643573761
2023-01-24 01:31:45.548279: step: 768/469, loss: 0.8315707445144653
2023-01-24 01:31:46.147367: step: 770/469, loss: 0.8766003251075745
2023-01-24 01:31:46.752823: step: 772/469, loss: 0.45454347133636475
2023-01-24 01:31:47.288212: step: 774/469, loss: 0.9226114749908447
2023-01-24 01:31:47.955292: step: 776/469, loss: 0.5401996374130249
2023-01-24 01:31:48.648651: step: 778/469, loss: 0.9735084772109985
2023-01-24 01:31:49.282295: step: 780/469, loss: 0.4931544363498688
2023-01-24 01:31:49.904851: step: 782/469, loss: 3.062002658843994
2023-01-24 01:31:50.566287: step: 784/469, loss: 1.9800618886947632
2023-01-24 01:31:51.222395: step: 786/469, loss: 0.2877175509929657
2023-01-24 01:31:51.767818: step: 788/469, loss: 0.6904782056808472
2023-01-24 01:31:52.452581: step: 790/469, loss: 1.2676526308059692
2023-01-24 01:31:53.060210: step: 792/469, loss: 0.347474604845047
2023-01-24 01:31:53.692128: step: 794/469, loss: 0.6748522520065308
2023-01-24 01:31:54.252662: step: 796/469, loss: 0.5393024682998657
2023-01-24 01:31:54.853847: step: 798/469, loss: 0.2017233967781067
2023-01-24 01:31:55.452687: step: 800/469, loss: 0.7778514623641968
2023-01-24 01:31:56.064782: step: 802/469, loss: 0.5172813534736633
2023-01-24 01:31:56.696800: step: 804/469, loss: 0.7103946208953857
2023-01-24 01:31:57.278333: step: 806/469, loss: 0.3048156499862671
2023-01-24 01:31:57.918160: step: 808/469, loss: 0.6835830211639404
2023-01-24 01:31:58.637107: step: 810/469, loss: 0.8040359020233154
2023-01-24 01:31:59.304166: step: 812/469, loss: 0.7363240718841553
2023-01-24 01:31:59.882813: step: 814/469, loss: 0.1961253434419632
2023-01-24 01:32:00.474519: step: 816/469, loss: 0.3886089324951172
2023-01-24 01:32:01.141260: step: 818/469, loss: 1.4280881881713867
2023-01-24 01:32:01.744158: step: 820/469, loss: 0.51703941822052
2023-01-24 01:32:02.404766: step: 822/469, loss: 7.723766803741455
2023-01-24 01:32:03.033000: step: 824/469, loss: 0.4861343801021576
2023-01-24 01:32:03.636465: step: 826/469, loss: 0.2845913767814636
2023-01-24 01:32:04.270861: step: 828/469, loss: 1.5565015077590942
2023-01-24 01:32:04.914854: step: 830/469, loss: 0.479922890663147
2023-01-24 01:32:05.520823: step: 832/469, loss: 0.3722665309906006
2023-01-24 01:32:06.113932: step: 834/469, loss: 0.5464308857917786
2023-01-24 01:32:06.776400: step: 836/469, loss: 1.9788055419921875
2023-01-24 01:32:07.365527: step: 838/469, loss: 1.0019735097885132
2023-01-24 01:32:07.994619: step: 840/469, loss: 1.1319061517715454
2023-01-24 01:32:08.612225: step: 842/469, loss: 0.2502128481864929
2023-01-24 01:32:09.206291: step: 844/469, loss: 1.523635745048523
2023-01-24 01:32:09.875133: step: 846/469, loss: 0.8167132139205933
2023-01-24 01:32:10.494116: step: 848/469, loss: 0.2752529978752136
2023-01-24 01:32:11.156422: step: 850/469, loss: 0.3101945221424103
2023-01-24 01:32:11.813784: step: 852/469, loss: 1.3561729192733765
2023-01-24 01:32:12.450183: step: 854/469, loss: 0.6020959615707397
2023-01-24 01:32:13.092687: step: 856/469, loss: 1.5760339498519897
2023-01-24 01:32:13.756250: step: 858/469, loss: 9.753297805786133
2023-01-24 01:32:14.329085: step: 860/469, loss: 1.0035114288330078
2023-01-24 01:32:14.935013: step: 862/469, loss: 0.16224248707294464
2023-01-24 01:32:15.585851: step: 864/469, loss: 0.3010299503803253
2023-01-24 01:32:16.206609: step: 866/469, loss: 1.1205472946166992
2023-01-24 01:32:16.842405: step: 868/469, loss: 0.31108251214027405
2023-01-24 01:32:17.451205: step: 870/469, loss: 0.3121650218963623
2023-01-24 01:32:18.107035: step: 872/469, loss: 0.4858582019805908
2023-01-24 01:32:18.694759: step: 874/469, loss: 1.6347750425338745
2023-01-24 01:32:19.305234: step: 876/469, loss: 0.514006495475769
2023-01-24 01:32:19.905224: step: 878/469, loss: 0.19382283091545105
2023-01-24 01:32:20.510981: step: 880/469, loss: 0.16118831932544708
2023-01-24 01:32:21.157227: step: 882/469, loss: 0.7053067684173584
2023-01-24 01:32:21.785925: step: 884/469, loss: 1.0186896324157715
2023-01-24 01:32:22.521497: step: 886/469, loss: 0.8057031631469727
2023-01-24 01:32:23.178107: step: 888/469, loss: 0.9202927350997925
2023-01-24 01:32:23.811145: step: 890/469, loss: 0.4016353189945221
2023-01-24 01:32:24.486167: step: 892/469, loss: 0.5799937844276428
2023-01-24 01:32:25.086195: step: 894/469, loss: 0.4366009831428528
2023-01-24 01:32:25.792358: step: 896/469, loss: 0.2307821810245514
2023-01-24 01:32:26.409473: step: 898/469, loss: 1.2212483882904053
2023-01-24 01:32:27.044467: step: 900/469, loss: 0.5073572397232056
2023-01-24 01:32:27.686620: step: 902/469, loss: 0.9757054448127747
2023-01-24 01:32:28.271835: step: 904/469, loss: 0.21069343388080597
2023-01-24 01:32:28.864767: step: 906/469, loss: 2.8934285640716553
2023-01-24 01:32:29.522791: step: 908/469, loss: 0.9867075085639954
2023-01-24 01:32:30.287018: step: 910/469, loss: 1.1562473773956299
2023-01-24 01:32:30.925056: step: 912/469, loss: 2.1939942836761475
2023-01-24 01:32:31.539344: step: 914/469, loss: 0.48719465732574463
2023-01-24 01:32:32.108833: step: 916/469, loss: 1.0412923097610474
2023-01-24 01:32:32.765483: step: 918/469, loss: 1.0130817890167236
2023-01-24 01:32:33.378172: step: 920/469, loss: 5.039875030517578
2023-01-24 01:32:34.058417: step: 922/469, loss: 0.6794548034667969
2023-01-24 01:32:34.604799: step: 924/469, loss: 0.1540706604719162
2023-01-24 01:32:35.269529: step: 926/469, loss: 2.3417463302612305
2023-01-24 01:32:35.843100: step: 928/469, loss: 0.888870894908905
2023-01-24 01:32:36.495064: step: 930/469, loss: 0.41191956400871277
2023-01-24 01:32:37.065789: step: 932/469, loss: 0.402072012424469
2023-01-24 01:32:37.762943: step: 934/469, loss: 1.3436135053634644
2023-01-24 01:32:38.399041: step: 936/469, loss: 0.31931743025779724
2023-01-24 01:32:39.061192: step: 938/469, loss: 0.8803346157073975
==================================================
Loss: 1.023
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35233436248331107, 'r': 0.28614631336405527, 'f1': 0.3158096484667165}, 'combined': 0.2327018462386332, 'epoch': 5}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.329569627776595, 'r': 0.22071817706538657, 'f1': 0.26437804661092335}, 'combined': 0.1442062072423218, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27380952380952384, 'r': 0.25, 'f1': 0.26136363636363635}, 'combined': 0.13068181818181818, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
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': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35233436248331107, 'r': 0.28614631336405527, 'f1': 0.3158096484667165}, 'combined': 0.2327018462386332, 'epoch': 5}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.329569627776595, 'r': 0.22071817706538657, 'f1': 0.26437804661092335}, 'combined': 0.1442062072423218, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27380952380952384, 'r': 0.25, 'f1': 0.26136363636363635}, 'combined': 0.13068181818181818, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, '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
2023-01-24 01:35:49.621397: step: 2/469, loss: 0.582108199596405
2023-01-24 01:35:50.231404: step: 4/469, loss: 0.6165879368782043
2023-01-24 01:35:50.898361: step: 6/469, loss: 1.1597636938095093
2023-01-24 01:35:51.491452: step: 8/469, loss: 1.2105425596237183
2023-01-24 01:35:52.096482: step: 10/469, loss: 0.9095755815505981
2023-01-24 01:35:52.718605: step: 12/469, loss: 0.36189937591552734
2023-01-24 01:35:53.412883: step: 14/469, loss: 0.36565449833869934
2023-01-24 01:35:54.036545: step: 16/469, loss: 0.11751201003789902
2023-01-24 01:35:54.721475: step: 18/469, loss: 0.4030844569206238
2023-01-24 01:35:55.280761: step: 20/469, loss: 1.0583242177963257
2023-01-24 01:35:55.973830: step: 22/469, loss: 0.5221636295318604
2023-01-24 01:35:56.553889: step: 24/469, loss: 0.2243850976228714
2023-01-24 01:35:57.247419: step: 26/469, loss: 0.16562789678573608
2023-01-24 01:35:57.923414: step: 28/469, loss: 0.6720852851867676
2023-01-24 01:35:58.528672: step: 30/469, loss: 1.2087796926498413
2023-01-24 01:35:59.157292: step: 32/469, loss: 0.3587951064109802
2023-01-24 01:35:59.792076: step: 34/469, loss: 0.1405404657125473
2023-01-24 01:36:00.393394: step: 36/469, loss: 0.5024339556694031
2023-01-24 01:36:01.042668: step: 38/469, loss: 0.18670833110809326
2023-01-24 01:36:01.694794: step: 40/469, loss: 1.147240161895752
2023-01-24 01:36:02.372865: step: 42/469, loss: 1.405549168586731
2023-01-24 01:36:03.005381: step: 44/469, loss: 0.9249565601348877
2023-01-24 01:36:03.710693: step: 46/469, loss: 0.253816157579422
2023-01-24 01:36:04.344787: step: 48/469, loss: 0.2027207314968109
2023-01-24 01:36:04.906118: step: 50/469, loss: 0.11158337444067001
2023-01-24 01:36:05.540865: step: 52/469, loss: 1.1416137218475342
2023-01-24 01:36:06.096559: step: 54/469, loss: 0.6252304315567017
2023-01-24 01:36:06.676739: step: 56/469, loss: 0.17594438791275024
2023-01-24 01:36:07.317653: step: 58/469, loss: 1.0408457517623901
2023-01-24 01:36:08.012790: step: 60/469, loss: 0.2611750662326813
2023-01-24 01:36:08.619601: step: 62/469, loss: 0.5898363590240479
2023-01-24 01:36:09.246363: step: 64/469, loss: 1.304792046546936
2023-01-24 01:36:09.928431: step: 66/469, loss: 0.7455921173095703
2023-01-24 01:36:10.595196: step: 68/469, loss: 0.3708344101905823
2023-01-24 01:36:11.194036: step: 70/469, loss: 0.580329954624176
2023-01-24 01:36:11.787761: step: 72/469, loss: 0.8678571581840515
2023-01-24 01:36:12.451079: step: 74/469, loss: 0.8212671279907227
2023-01-24 01:36:13.084325: step: 76/469, loss: 0.4896354377269745
2023-01-24 01:36:13.732255: step: 78/469, loss: 0.7276855707168579
2023-01-24 01:36:14.292672: step: 80/469, loss: 1.178435206413269
2023-01-24 01:36:14.922739: step: 82/469, loss: 0.3564695119857788
2023-01-24 01:36:15.552772: step: 84/469, loss: 0.3392344117164612
2023-01-24 01:36:16.177737: step: 86/469, loss: 0.36357319355010986
2023-01-24 01:36:16.783997: step: 88/469, loss: 0.4256187379360199
2023-01-24 01:36:17.428610: step: 90/469, loss: 0.6775780916213989
2023-01-24 01:36:18.090470: step: 92/469, loss: 0.4577982425689697
2023-01-24 01:36:18.762006: step: 94/469, loss: 0.4166240990161896
2023-01-24 01:36:19.387110: step: 96/469, loss: 0.14975017309188843
2023-01-24 01:36:20.049536: step: 98/469, loss: 0.5553939938545227
2023-01-24 01:36:20.692504: step: 100/469, loss: 1.331783652305603
2023-01-24 01:36:21.282723: step: 102/469, loss: 0.7636451721191406
2023-01-24 01:36:21.859168: step: 104/469, loss: 0.5785241723060608
2023-01-24 01:36:22.487569: step: 106/469, loss: 1.0434573888778687
2023-01-24 01:36:23.085172: step: 108/469, loss: 0.21206778287887573
2023-01-24 01:36:23.753267: step: 110/469, loss: 0.6471192836761475
2023-01-24 01:36:24.367956: step: 112/469, loss: 0.3738044798374176
2023-01-24 01:36:24.959567: step: 114/469, loss: 0.5797178745269775
2023-01-24 01:36:25.675500: step: 116/469, loss: 0.9984303712844849
2023-01-24 01:36:26.313002: step: 118/469, loss: 0.5647268295288086
2023-01-24 01:36:27.001133: step: 120/469, loss: 0.67030268907547
2023-01-24 01:36:27.595912: step: 122/469, loss: 0.4455380141735077
2023-01-24 01:36:28.262286: step: 124/469, loss: 0.7645474672317505
2023-01-24 01:36:28.811677: step: 126/469, loss: 0.41484707593917847
2023-01-24 01:36:29.435595: step: 128/469, loss: 0.1937958002090454
2023-01-24 01:36:30.050230: step: 130/469, loss: 0.4437099099159241
2023-01-24 01:36:30.648186: step: 132/469, loss: 0.49780598282814026
2023-01-24 01:36:31.369215: step: 134/469, loss: 0.5588032007217407
2023-01-24 01:36:31.995948: step: 136/469, loss: 0.32195794582366943
2023-01-24 01:36:32.620709: step: 138/469, loss: 0.568348228931427
2023-01-24 01:36:33.247458: step: 140/469, loss: 0.41528013348579407
2023-01-24 01:36:33.904213: step: 142/469, loss: 0.2227383553981781
2023-01-24 01:36:34.507073: step: 144/469, loss: 0.828467607498169
2023-01-24 01:36:35.085110: step: 146/469, loss: 0.3052496314048767
2023-01-24 01:36:35.611177: step: 148/469, loss: 0.32668405771255493
2023-01-24 01:36:36.256809: step: 150/469, loss: 0.8024691939353943
2023-01-24 01:36:36.845843: step: 152/469, loss: 0.7282994985580444
2023-01-24 01:36:37.511716: step: 154/469, loss: 1.111225962638855
2023-01-24 01:36:38.117017: step: 156/469, loss: 0.2026520073413849
2023-01-24 01:36:38.746688: step: 158/469, loss: 0.09721113741397858
2023-01-24 01:36:39.413081: step: 160/469, loss: 0.5165294408798218
2023-01-24 01:36:39.994319: step: 162/469, loss: 0.32028067111968994
2023-01-24 01:36:40.580595: step: 164/469, loss: 0.34433838725090027
2023-01-24 01:36:41.178222: step: 166/469, loss: 0.5954673886299133
2023-01-24 01:36:41.832707: step: 168/469, loss: 0.32776808738708496
2023-01-24 01:36:42.527180: step: 170/469, loss: 0.7825974225997925
2023-01-24 01:36:43.225075: step: 172/469, loss: 0.1546805500984192
2023-01-24 01:36:43.849035: step: 174/469, loss: 1.407179832458496
2023-01-24 01:36:44.441596: step: 176/469, loss: 1.138911485671997
2023-01-24 01:36:45.133807: step: 178/469, loss: 1.2073984146118164
2023-01-24 01:36:45.749657: step: 180/469, loss: 0.39008909463882446
2023-01-24 01:36:46.403072: step: 182/469, loss: 1.1200722455978394
2023-01-24 01:36:47.050489: step: 184/469, loss: 0.18921564519405365
2023-01-24 01:36:47.711926: step: 186/469, loss: 0.32686442136764526
2023-01-24 01:36:48.347324: step: 188/469, loss: 0.4216076135635376
2023-01-24 01:36:48.955642: step: 190/469, loss: 0.6890570521354675
2023-01-24 01:36:49.627293: step: 192/469, loss: 0.7068150639533997
2023-01-24 01:36:50.200535: step: 194/469, loss: 0.2108181267976761
2023-01-24 01:36:50.964565: step: 196/469, loss: 0.23207297921180725
2023-01-24 01:36:51.610442: step: 198/469, loss: 0.8247882127761841
2023-01-24 01:36:52.216128: step: 200/469, loss: 0.44725847244262695
2023-01-24 01:36:52.843134: step: 202/469, loss: 0.19397661089897156
2023-01-24 01:36:53.562111: step: 204/469, loss: 0.40939685702323914
2023-01-24 01:36:54.229493: step: 206/469, loss: 0.3779168128967285
2023-01-24 01:36:54.824612: step: 208/469, loss: 0.48507606983184814
2023-01-24 01:36:55.432669: step: 210/469, loss: 1.1623269319534302
2023-01-24 01:36:56.045222: step: 212/469, loss: 1.4632008075714111
2023-01-24 01:36:56.669003: step: 214/469, loss: 0.5960787534713745
2023-01-24 01:36:57.275799: step: 216/469, loss: 0.6466684341430664
2023-01-24 01:36:57.894702: step: 218/469, loss: 0.3629465103149414
2023-01-24 01:36:58.505131: step: 220/469, loss: 0.5430543422698975
2023-01-24 01:36:59.139385: step: 222/469, loss: 0.42043596506118774
2023-01-24 01:36:59.755619: step: 224/469, loss: 0.8249005675315857
2023-01-24 01:37:00.368982: step: 226/469, loss: 1.074183702468872
2023-01-24 01:37:00.985273: step: 228/469, loss: 1.0409280061721802
2023-01-24 01:37:01.583164: step: 230/469, loss: 0.6099473237991333
2023-01-24 01:37:02.295605: step: 232/469, loss: 0.995842695236206
2023-01-24 01:37:02.885421: step: 234/469, loss: 1.058698296546936
2023-01-24 01:37:03.523773: step: 236/469, loss: 0.6503398418426514
2023-01-24 01:37:04.162076: step: 238/469, loss: 0.8363496661186218
2023-01-24 01:37:04.855020: step: 240/469, loss: 0.6152865290641785
2023-01-24 01:37:05.463326: step: 242/469, loss: 0.6883412003517151
2023-01-24 01:37:06.034526: step: 244/469, loss: 0.2523246705532074
2023-01-24 01:37:06.703122: step: 246/469, loss: 0.7020666599273682
2023-01-24 01:37:07.376337: step: 248/469, loss: 0.5206868052482605
2023-01-24 01:37:07.955159: step: 250/469, loss: 1.1940706968307495
2023-01-24 01:37:08.536467: step: 252/469, loss: 1.035109519958496
2023-01-24 01:37:09.189316: step: 254/469, loss: 0.22835978865623474
2023-01-24 01:37:09.782535: step: 256/469, loss: 0.3665621876716614
2023-01-24 01:37:10.435918: step: 258/469, loss: 1.1108589172363281
2023-01-24 01:37:11.031322: step: 260/469, loss: 0.31099414825439453
2023-01-24 01:37:11.738206: step: 262/469, loss: 1.4731876850128174
2023-01-24 01:37:12.352430: step: 264/469, loss: 0.10067793726921082
2023-01-24 01:37:13.087795: step: 266/469, loss: 1.7326617240905762
2023-01-24 01:37:13.740103: step: 268/469, loss: 0.31641972064971924
2023-01-24 01:37:14.380384: step: 270/469, loss: 1.152388572692871
2023-01-24 01:37:15.084672: step: 272/469, loss: 0.968422532081604
2023-01-24 01:37:15.673770: step: 274/469, loss: 0.5858252048492432
2023-01-24 01:37:16.277374: step: 276/469, loss: 0.586940586566925
2023-01-24 01:37:16.935725: step: 278/469, loss: 0.5209425687789917
2023-01-24 01:37:17.615658: step: 280/469, loss: 0.40567511320114136
2023-01-24 01:37:18.299036: step: 282/469, loss: 0.6916226744651794
2023-01-24 01:37:19.013774: step: 284/469, loss: 1.2991178035736084
2023-01-24 01:37:19.780632: step: 286/469, loss: 0.5992436408996582
2023-01-24 01:37:20.427373: step: 288/469, loss: 0.3350967764854431
2023-01-24 01:37:21.066909: step: 290/469, loss: 0.3736046254634857
2023-01-24 01:37:21.695036: step: 292/469, loss: 1.1027233600616455
2023-01-24 01:37:22.354358: step: 294/469, loss: 0.7615113854408264
2023-01-24 01:37:23.014177: step: 296/469, loss: 1.3420709371566772
2023-01-24 01:37:23.663927: step: 298/469, loss: 0.3673308491706848
2023-01-24 01:37:24.290742: step: 300/469, loss: 1.106971263885498
2023-01-24 01:37:24.859909: step: 302/469, loss: 0.07255806028842926
2023-01-24 01:37:25.516159: step: 304/469, loss: 0.3658123016357422
2023-01-24 01:37:26.158594: step: 306/469, loss: 0.7242321968078613
2023-01-24 01:37:26.799149: step: 308/469, loss: 1.4762146472930908
2023-01-24 01:37:27.441265: step: 310/469, loss: 0.7645450234413147
2023-01-24 01:37:28.049677: step: 312/469, loss: 0.4076809883117676
2023-01-24 01:37:28.668977: step: 314/469, loss: 0.3468690514564514
2023-01-24 01:37:29.274102: step: 316/469, loss: 0.6406058073043823
2023-01-24 01:37:29.883091: step: 318/469, loss: 0.12084714323282242
2023-01-24 01:37:30.520045: step: 320/469, loss: 1.0068501234054565
2023-01-24 01:37:31.173690: step: 322/469, loss: 1.2782275676727295
2023-01-24 01:37:31.762089: step: 324/469, loss: 1.1477534770965576
2023-01-24 01:37:32.383218: step: 326/469, loss: 0.27162471413612366
2023-01-24 01:37:33.083088: step: 328/469, loss: 1.0024360418319702
2023-01-24 01:37:33.685970: step: 330/469, loss: 0.9895776510238647
2023-01-24 01:37:34.344450: step: 332/469, loss: 0.6782008409500122
2023-01-24 01:37:34.945170: step: 334/469, loss: 0.26413270831108093
2023-01-24 01:37:35.592672: step: 336/469, loss: 0.37584081292152405
2023-01-24 01:37:36.252554: step: 338/469, loss: 0.48382851481437683
2023-01-24 01:37:36.905216: step: 340/469, loss: 0.940863847732544
2023-01-24 01:37:37.508826: step: 342/469, loss: 0.08170486241579056
2023-01-24 01:37:38.092997: step: 344/469, loss: 0.3922652304172516
2023-01-24 01:37:38.737981: step: 346/469, loss: 0.3113369643688202
2023-01-24 01:37:39.409617: step: 348/469, loss: 0.5442818999290466
2023-01-24 01:37:40.069819: step: 350/469, loss: 0.45570242404937744
2023-01-24 01:37:40.750848: step: 352/469, loss: 0.16213591396808624
2023-01-24 01:37:41.349891: step: 354/469, loss: 0.3619459867477417
2023-01-24 01:37:42.017447: step: 356/469, loss: 0.23970070481300354
2023-01-24 01:37:42.651968: step: 358/469, loss: 0.7487192749977112
2023-01-24 01:37:43.245744: step: 360/469, loss: 0.5412108302116394
2023-01-24 01:37:43.832212: step: 362/469, loss: 1.0828173160552979
2023-01-24 01:37:44.440125: step: 364/469, loss: 0.610897958278656
2023-01-24 01:37:45.143114: step: 366/469, loss: 0.2275417000055313
2023-01-24 01:37:45.766566: step: 368/469, loss: 0.4648996591567993
2023-01-24 01:37:46.420698: step: 370/469, loss: 0.6641898155212402
2023-01-24 01:37:47.035959: step: 372/469, loss: 0.25401371717453003
2023-01-24 01:37:47.739152: step: 374/469, loss: 0.42171090841293335
2023-01-24 01:37:48.356951: step: 376/469, loss: 0.14892850816249847
2023-01-24 01:37:49.030505: step: 378/469, loss: 0.8934428691864014
2023-01-24 01:37:49.619152: step: 380/469, loss: 0.22290942072868347
2023-01-24 01:37:50.181936: step: 382/469, loss: 0.6647469401359558
2023-01-24 01:37:50.832131: step: 384/469, loss: 0.4884270429611206
2023-01-24 01:37:51.425157: step: 386/469, loss: 0.36011263728141785
2023-01-24 01:37:52.048104: step: 388/469, loss: 0.5522686243057251
2023-01-24 01:37:52.601982: step: 390/469, loss: 0.4173738360404968
2023-01-24 01:37:53.209930: step: 392/469, loss: 0.4940659701824188
2023-01-24 01:37:53.817541: step: 394/469, loss: 1.0775045156478882
2023-01-24 01:37:54.463493: step: 396/469, loss: 0.7616162300109863
2023-01-24 01:37:55.034857: step: 398/469, loss: 0.1997879147529602
2023-01-24 01:37:55.641946: step: 400/469, loss: 1.7772319316864014
2023-01-24 01:37:56.269038: step: 402/469, loss: 0.2205466330051422
2023-01-24 01:37:56.836519: step: 404/469, loss: 0.41694650053977966
2023-01-24 01:37:57.423391: step: 406/469, loss: 0.2993175983428955
2023-01-24 01:37:58.025663: step: 408/469, loss: 0.8849889039993286
2023-01-24 01:37:58.839215: step: 410/469, loss: 0.48914721608161926
2023-01-24 01:37:59.484444: step: 412/469, loss: 0.7150527238845825
2023-01-24 01:38:00.123252: step: 414/469, loss: 0.4554973840713501
2023-01-24 01:38:00.684491: step: 416/469, loss: 0.29352641105651855
2023-01-24 01:38:01.313905: step: 418/469, loss: 1.387034296989441
2023-01-24 01:38:01.883333: step: 420/469, loss: 0.1845788061618805
2023-01-24 01:38:02.437585: step: 422/469, loss: 0.12556815147399902
2023-01-24 01:38:03.050185: step: 424/469, loss: 1.3801896572113037
2023-01-24 01:38:03.623228: step: 426/469, loss: 0.8334442377090454
2023-01-24 01:38:04.225781: step: 428/469, loss: 0.692019522190094
2023-01-24 01:38:04.906087: step: 430/469, loss: 0.30013611912727356
2023-01-24 01:38:05.572532: step: 432/469, loss: 0.4331887364387512
2023-01-24 01:38:06.172083: step: 434/469, loss: 0.6363438367843628
2023-01-24 01:38:06.806370: step: 436/469, loss: 0.5658471584320068
2023-01-24 01:38:07.461731: step: 438/469, loss: 0.1740536391735077
2023-01-24 01:38:08.029200: step: 440/469, loss: 4.930780410766602
2023-01-24 01:38:08.688682: step: 442/469, loss: 1.058233618736267
2023-01-24 01:38:09.381923: step: 444/469, loss: 0.6602569818496704
2023-01-24 01:38:10.032450: step: 446/469, loss: 0.3973201811313629
2023-01-24 01:38:10.601839: step: 448/469, loss: 0.6186159253120422
2023-01-24 01:38:11.189467: step: 450/469, loss: 0.491231769323349
2023-01-24 01:38:11.842767: step: 452/469, loss: 1.0658018589019775
2023-01-24 01:38:12.479444: step: 454/469, loss: 0.8787103891372681
2023-01-24 01:38:13.180024: step: 456/469, loss: 0.5756931900978088
2023-01-24 01:38:13.816788: step: 458/469, loss: 0.5747436881065369
2023-01-24 01:38:14.510751: step: 460/469, loss: 0.6343942880630493
2023-01-24 01:38:15.124428: step: 462/469, loss: 0.6502560973167419
2023-01-24 01:38:15.837602: step: 464/469, loss: 0.6004595756530762
2023-01-24 01:38:16.568648: step: 466/469, loss: 0.34474602341651917
2023-01-24 01:38:17.180434: step: 468/469, loss: 0.321304589509964
2023-01-24 01:38:17.869176: step: 470/469, loss: 0.2675541639328003
2023-01-24 01:38:18.498120: step: 472/469, loss: 0.9362136125564575
2023-01-24 01:38:19.154541: step: 474/469, loss: 0.3079529404640198
2023-01-24 01:38:19.758052: step: 476/469, loss: 3.6796469688415527
2023-01-24 01:38:20.421805: step: 478/469, loss: 1.3912123441696167
2023-01-24 01:38:20.995562: step: 480/469, loss: 2.4084930419921875
2023-01-24 01:38:21.603537: step: 482/469, loss: 0.26777970790863037
2023-01-24 01:38:22.211022: step: 484/469, loss: 0.4960557222366333
2023-01-24 01:38:22.873423: step: 486/469, loss: 0.7903075814247131
2023-01-24 01:38:23.540250: step: 488/469, loss: 0.8850454688072205
2023-01-24 01:38:24.208288: step: 490/469, loss: 0.7258738875389099
2023-01-24 01:38:24.783939: step: 492/469, loss: 0.17257800698280334
2023-01-24 01:38:25.385301: step: 494/469, loss: 0.6114130616188049
2023-01-24 01:38:26.021579: step: 496/469, loss: 0.5821794271469116
2023-01-24 01:38:26.576465: step: 498/469, loss: 0.5853869318962097
2023-01-24 01:38:27.195415: step: 500/469, loss: 0.8860760927200317
2023-01-24 01:38:27.825884: step: 502/469, loss: 1.057038426399231
2023-01-24 01:38:28.441684: step: 504/469, loss: 0.5471564531326294
2023-01-24 01:38:29.065488: step: 506/469, loss: 0.6805905103683472
2023-01-24 01:38:29.672001: step: 508/469, loss: 0.8268406987190247
2023-01-24 01:38:30.286757: step: 510/469, loss: 0.4200073480606079
2023-01-24 01:38:30.909260: step: 512/469, loss: 0.15350694954395294
2023-01-24 01:38:31.533688: step: 514/469, loss: 0.3868025839328766
2023-01-24 01:38:32.183918: step: 516/469, loss: 0.5283547043800354
2023-01-24 01:38:32.859287: step: 518/469, loss: 0.1625261753797531
2023-01-24 01:38:33.493648: step: 520/469, loss: 0.36215347051620483
2023-01-24 01:38:34.046202: step: 522/469, loss: 0.0768042579293251
2023-01-24 01:38:34.653269: step: 524/469, loss: 0.15860725939273834
2023-01-24 01:38:35.247543: step: 526/469, loss: 0.6164580583572388
2023-01-24 01:38:35.829117: step: 528/469, loss: 0.613944947719574
2023-01-24 01:38:36.399745: step: 530/469, loss: 0.27885621786117554
2023-01-24 01:38:37.120470: step: 532/469, loss: 1.2978847026824951
2023-01-24 01:38:37.790088: step: 534/469, loss: 0.49276411533355713
2023-01-24 01:38:38.378712: step: 536/469, loss: 0.21811699867248535
2023-01-24 01:38:39.040568: step: 538/469, loss: 0.6028008460998535
2023-01-24 01:38:39.659100: step: 540/469, loss: 1.0664536952972412
2023-01-24 01:38:40.271526: step: 542/469, loss: 1.1393210887908936
2023-01-24 01:38:40.937985: step: 544/469, loss: 0.9323995113372803
2023-01-24 01:38:41.571046: step: 546/469, loss: 0.47356510162353516
2023-01-24 01:38:42.258262: step: 548/469, loss: 1.209115982055664
2023-01-24 01:38:42.867714: step: 550/469, loss: 2.5095744132995605
2023-01-24 01:38:43.497936: step: 552/469, loss: 1.9994875192642212
2023-01-24 01:38:44.197221: step: 554/469, loss: 0.7227581143379211
2023-01-24 01:38:44.804184: step: 556/469, loss: 0.23846879601478577
2023-01-24 01:38:45.418702: step: 558/469, loss: 1.4068973064422607
2023-01-24 01:38:46.041634: step: 560/469, loss: 0.7880046963691711
2023-01-24 01:38:46.681440: step: 562/469, loss: 1.1210275888442993
2023-01-24 01:38:47.321381: step: 564/469, loss: 0.5986941456794739
2023-01-24 01:38:47.954388: step: 566/469, loss: 0.5583336353302002
2023-01-24 01:38:48.526098: step: 568/469, loss: 1.992104172706604
2023-01-24 01:38:49.133595: step: 570/469, loss: 0.7541818022727966
2023-01-24 01:38:49.778986: step: 572/469, loss: 1.3579281568527222
2023-01-24 01:38:50.432999: step: 574/469, loss: 2.0197794437408447
2023-01-24 01:38:51.080262: step: 576/469, loss: 0.7188225388526917
2023-01-24 01:38:51.704952: step: 578/469, loss: 1.6764938831329346
2023-01-24 01:38:52.309316: step: 580/469, loss: 0.7155629396438599
2023-01-24 01:38:52.964444: step: 582/469, loss: 0.28579264879226685
2023-01-24 01:38:53.598958: step: 584/469, loss: 0.20873846113681793
2023-01-24 01:38:54.196392: step: 586/469, loss: 1.1142839193344116
2023-01-24 01:38:54.831674: step: 588/469, loss: 0.480831116437912
2023-01-24 01:38:55.450907: step: 590/469, loss: 0.14513547718524933
2023-01-24 01:38:56.041070: step: 592/469, loss: 1.2173819541931152
2023-01-24 01:38:56.650386: step: 594/469, loss: 0.8949723243713379
2023-01-24 01:38:57.270148: step: 596/469, loss: 0.5596634745597839
2023-01-24 01:38:57.869942: step: 598/469, loss: 0.3700833022594452
2023-01-24 01:38:58.589142: step: 600/469, loss: 0.7241194248199463
2023-01-24 01:38:59.222854: step: 602/469, loss: 0.7003096342086792
2023-01-24 01:38:59.862113: step: 604/469, loss: 1.0163302421569824
2023-01-24 01:39:00.502523: step: 606/469, loss: 0.5491389036178589
2023-01-24 01:39:01.118773: step: 608/469, loss: 0.2459547221660614
2023-01-24 01:39:01.724228: step: 610/469, loss: 0.25904160737991333
2023-01-24 01:39:02.334668: step: 612/469, loss: 0.4976344704627991
2023-01-24 01:39:02.945697: step: 614/469, loss: 0.6955742835998535
2023-01-24 01:39:03.568271: step: 616/469, loss: 0.23495228588581085
2023-01-24 01:39:04.244418: step: 618/469, loss: 0.5154277086257935
2023-01-24 01:39:04.827220: step: 620/469, loss: 1.1025559902191162
2023-01-24 01:39:05.494077: step: 622/469, loss: 0.2690567970275879
2023-01-24 01:39:06.211457: step: 624/469, loss: 0.4573833644390106
2023-01-24 01:39:06.849539: step: 626/469, loss: 0.4949929416179657
2023-01-24 01:39:07.438862: step: 628/469, loss: 0.3546310365200043
2023-01-24 01:39:08.071751: step: 630/469, loss: 0.6758636832237244
2023-01-24 01:39:08.674081: step: 632/469, loss: 0.15792903304100037
2023-01-24 01:39:09.318719: step: 634/469, loss: 0.29518723487854004
2023-01-24 01:39:09.928888: step: 636/469, loss: 0.2186373770236969
2023-01-24 01:39:10.586723: step: 638/469, loss: 2.310868740081787
2023-01-24 01:39:11.154698: step: 640/469, loss: 0.8885836005210876
2023-01-24 01:39:11.761521: step: 642/469, loss: 0.9277083873748779
2023-01-24 01:39:12.342711: step: 644/469, loss: 0.5045440793037415
2023-01-24 01:39:13.098043: step: 646/469, loss: 1.30831778049469
2023-01-24 01:39:13.687450: step: 648/469, loss: 0.6179578304290771
2023-01-24 01:39:14.344915: step: 650/469, loss: 0.70857834815979
2023-01-24 01:39:14.928171: step: 652/469, loss: 1.2064461708068848
2023-01-24 01:39:15.524288: step: 654/469, loss: 1.025246024131775
2023-01-24 01:39:16.084596: step: 656/469, loss: 0.4187513291835785
2023-01-24 01:39:16.753860: step: 658/469, loss: 0.2228047400712967
2023-01-24 01:39:17.411822: step: 660/469, loss: 0.6203461289405823
2023-01-24 01:39:18.041407: step: 662/469, loss: 0.19843462109565735
2023-01-24 01:39:18.661679: step: 664/469, loss: 0.7199745178222656
2023-01-24 01:39:19.293426: step: 666/469, loss: 1.5590795278549194
2023-01-24 01:39:19.962646: step: 668/469, loss: 1.0396335124969482
2023-01-24 01:39:20.610702: step: 670/469, loss: 0.20521724224090576
2023-01-24 01:39:21.238213: step: 672/469, loss: 0.23070786893367767
2023-01-24 01:39:21.862574: step: 674/469, loss: 0.8485086560249329
2023-01-24 01:39:22.514359: step: 676/469, loss: 0.34147462248802185
2023-01-24 01:39:23.174124: step: 678/469, loss: 0.39903852343559265
2023-01-24 01:39:23.762409: step: 680/469, loss: 1.0546317100524902
2023-01-24 01:39:24.375812: step: 682/469, loss: 0.28590115904808044
2023-01-24 01:39:24.963614: step: 684/469, loss: 0.31622838973999023
2023-01-24 01:39:25.594232: step: 686/469, loss: 0.9028953313827515
2023-01-24 01:39:26.239859: step: 688/469, loss: 0.6884586215019226
2023-01-24 01:39:26.856370: step: 690/469, loss: 0.5982221364974976
2023-01-24 01:39:27.568731: step: 692/469, loss: 0.451449990272522
2023-01-24 01:39:28.173236: step: 694/469, loss: 1.27504301071167
2023-01-24 01:39:28.760006: step: 696/469, loss: 0.8286892175674438
2023-01-24 01:39:29.380199: step: 698/469, loss: 0.23540833592414856
2023-01-24 01:39:30.046662: step: 700/469, loss: 1.447479486465454
2023-01-24 01:39:30.700576: step: 702/469, loss: 0.14541903138160706
2023-01-24 01:39:31.301648: step: 704/469, loss: 0.14279323816299438
2023-01-24 01:39:31.942909: step: 706/469, loss: 3.02829647064209
2023-01-24 01:39:32.601989: step: 708/469, loss: 0.4244763255119324
2023-01-24 01:39:33.347093: step: 710/469, loss: 0.16301007568836212
2023-01-24 01:39:33.888294: step: 712/469, loss: 0.4454129934310913
2023-01-24 01:39:34.590801: step: 714/469, loss: 0.23517531156539917
2023-01-24 01:39:35.220458: step: 716/469, loss: 0.27578550577163696
2023-01-24 01:39:35.898885: step: 718/469, loss: 0.26431217789649963
2023-01-24 01:39:36.478198: step: 720/469, loss: 0.34922391176223755
2023-01-24 01:39:37.119400: step: 722/469, loss: 0.8056902885437012
2023-01-24 01:39:37.756694: step: 724/469, loss: 1.5670617818832397
2023-01-24 01:39:38.412580: step: 726/469, loss: 0.3796059489250183
2023-01-24 01:39:39.128792: step: 728/469, loss: 0.5573244094848633
2023-01-24 01:39:39.795625: step: 730/469, loss: 1.4573637247085571
2023-01-24 01:39:40.454655: step: 732/469, loss: 1.4007136821746826
2023-01-24 01:39:41.064197: step: 734/469, loss: 0.3005386292934418
2023-01-24 01:39:41.679203: step: 736/469, loss: 0.37273505330085754
2023-01-24 01:39:42.336249: step: 738/469, loss: 0.8748267292976379
2023-01-24 01:39:43.028964: step: 740/469, loss: 1.02974271774292
2023-01-24 01:39:43.640085: step: 742/469, loss: 0.961559534072876
2023-01-24 01:39:44.250589: step: 744/469, loss: 2.440967082977295
2023-01-24 01:39:44.845476: step: 746/469, loss: 0.8475446701049805
2023-01-24 01:39:45.451778: step: 748/469, loss: 0.6550959348678589
2023-01-24 01:39:46.056947: step: 750/469, loss: 0.3683474063873291
2023-01-24 01:39:46.730117: step: 752/469, loss: 1.9358210563659668
2023-01-24 01:39:47.374948: step: 754/469, loss: 0.4114786684513092
2023-01-24 01:39:48.060695: step: 756/469, loss: 0.6471695303916931
2023-01-24 01:39:48.658500: step: 758/469, loss: 0.3643433153629303
2023-01-24 01:39:49.396767: step: 760/469, loss: 0.6222134828567505
2023-01-24 01:39:50.002309: step: 762/469, loss: 0.24578146636486053
2023-01-24 01:39:50.608750: step: 764/469, loss: 0.22691859304904938
2023-01-24 01:39:51.275901: step: 766/469, loss: 1.0229220390319824
2023-01-24 01:39:51.945014: step: 768/469, loss: 0.1557282954454422
2023-01-24 01:39:52.560816: step: 770/469, loss: 0.9089685678482056
2023-01-24 01:39:53.212698: step: 772/469, loss: 1.0979036092758179
2023-01-24 01:39:53.888432: step: 774/469, loss: 1.168755054473877
2023-01-24 01:39:54.515430: step: 776/469, loss: 0.6211987733840942
2023-01-24 01:39:55.164707: step: 778/469, loss: 0.7354152798652649
2023-01-24 01:39:55.804141: step: 780/469, loss: 0.9869888424873352
2023-01-24 01:39:56.496604: step: 782/469, loss: 1.8314378261566162
2023-01-24 01:39:57.145031: step: 784/469, loss: 0.818301796913147
2023-01-24 01:39:57.845085: step: 786/469, loss: 1.2537380456924438
2023-01-24 01:39:58.460785: step: 788/469, loss: 0.8417704701423645
2023-01-24 01:39:59.077903: step: 790/469, loss: 1.2719812393188477
2023-01-24 01:39:59.673506: step: 792/469, loss: 1.78606116771698
2023-01-24 01:40:00.304175: step: 794/469, loss: 0.5059295296669006
2023-01-24 01:40:00.902025: step: 796/469, loss: 0.2696778178215027
2023-01-24 01:40:01.570188: step: 798/469, loss: 1.026119589805603
2023-01-24 01:40:02.155095: step: 800/469, loss: 1.3550070524215698
2023-01-24 01:40:02.829985: step: 802/469, loss: 0.9727777242660522
2023-01-24 01:40:03.435557: step: 804/469, loss: 0.8629355430603027
2023-01-24 01:40:04.019186: step: 806/469, loss: 1.5440435409545898
2023-01-24 01:40:04.596958: step: 808/469, loss: 0.3212146759033203
2023-01-24 01:40:05.217571: step: 810/469, loss: 0.3778342604637146
2023-01-24 01:40:05.914388: step: 812/469, loss: 0.3516838550567627
2023-01-24 01:40:06.577757: step: 814/469, loss: 1.2941991090774536
2023-01-24 01:40:07.269387: step: 816/469, loss: 1.964330792427063
2023-01-24 01:40:07.955829: step: 818/469, loss: 1.1915626525878906
2023-01-24 01:40:08.532601: step: 820/469, loss: 0.3223915994167328
2023-01-24 01:40:09.108627: step: 822/469, loss: 0.3422360420227051
2023-01-24 01:40:09.707511: step: 824/469, loss: 0.5502710342407227
2023-01-24 01:40:10.353827: step: 826/469, loss: 0.3715992271900177
2023-01-24 01:40:10.934517: step: 828/469, loss: 0.5587812662124634
2023-01-24 01:40:11.570009: step: 830/469, loss: 0.5461872816085815
2023-01-24 01:40:12.204811: step: 832/469, loss: 0.49875330924987793
2023-01-24 01:40:12.885572: step: 834/469, loss: 0.6409670114517212
2023-01-24 01:40:13.661768: step: 836/469, loss: 0.6133067607879639
2023-01-24 01:40:14.294595: step: 838/469, loss: 0.9243052005767822
2023-01-24 01:40:14.959990: step: 840/469, loss: 0.3548726439476013
2023-01-24 01:40:15.558806: step: 842/469, loss: 0.5439071655273438
2023-01-24 01:40:16.140589: step: 844/469, loss: 0.49044719338417053
2023-01-24 01:40:16.791631: step: 846/469, loss: 0.2944038510322571
2023-01-24 01:40:17.414342: step: 848/469, loss: 0.25485801696777344
2023-01-24 01:40:18.040566: step: 850/469, loss: 1.390325665473938
2023-01-24 01:40:18.636826: step: 852/469, loss: 0.6629309058189392
2023-01-24 01:40:19.269543: step: 854/469, loss: 0.9643487930297852
2023-01-24 01:40:19.940143: step: 856/469, loss: 0.5227541327476501
2023-01-24 01:40:20.565900: step: 858/469, loss: 0.917007565498352
2023-01-24 01:40:21.249009: step: 860/469, loss: 0.38237178325653076
2023-01-24 01:40:21.916364: step: 862/469, loss: 0.728380024433136
2023-01-24 01:40:22.680406: step: 864/469, loss: 0.5563600659370422
2023-01-24 01:40:23.286608: step: 866/469, loss: 0.7234206199645996
2023-01-24 01:40:23.898760: step: 868/469, loss: 1.027193546295166
2023-01-24 01:40:24.644193: step: 870/469, loss: 0.9818785786628723
2023-01-24 01:40:25.372113: step: 872/469, loss: 4.488598823547363
2023-01-24 01:40:25.946339: step: 874/469, loss: 0.3961482346057892
2023-01-24 01:40:26.593902: step: 876/469, loss: 0.3079904019832611
2023-01-24 01:40:27.242360: step: 878/469, loss: 0.29708707332611084
2023-01-24 01:40:27.857531: step: 880/469, loss: 0.23251432180404663
2023-01-24 01:40:28.501162: step: 882/469, loss: 0.17885802686214447
2023-01-24 01:40:29.101020: step: 884/469, loss: 1.7155933380126953
2023-01-24 01:40:29.764391: step: 886/469, loss: 2.7264580726623535
2023-01-24 01:40:30.423508: step: 888/469, loss: 0.21096928417682648
2023-01-24 01:40:31.063514: step: 890/469, loss: 1.1697462797164917
2023-01-24 01:40:31.691410: step: 892/469, loss: 0.892507791519165
2023-01-24 01:40:32.295785: step: 894/469, loss: 0.3625553846359253
2023-01-24 01:40:32.884828: step: 896/469, loss: 0.2119859904050827
2023-01-24 01:40:33.431949: step: 898/469, loss: 0.2572576701641083
2023-01-24 01:40:34.079787: step: 900/469, loss: 0.23684285581111908
2023-01-24 01:40:34.674265: step: 902/469, loss: 0.2484087198972702
2023-01-24 01:40:35.316848: step: 904/469, loss: 0.43317052721977234
2023-01-24 01:40:35.950222: step: 906/469, loss: 0.4847605228424072
2023-01-24 01:40:36.589751: step: 908/469, loss: 0.446374773979187
2023-01-24 01:40:37.244310: step: 910/469, loss: 0.252265989780426
2023-01-24 01:40:37.834125: step: 912/469, loss: 0.5236475467681885
2023-01-24 01:40:38.447628: step: 914/469, loss: 1.2354389429092407
2023-01-24 01:40:39.018318: step: 916/469, loss: 0.32738977670669556
2023-01-24 01:40:39.702682: step: 918/469, loss: 0.958543062210083
2023-01-24 01:40:40.330401: step: 920/469, loss: 0.6848151087760925
2023-01-24 01:40:40.911793: step: 922/469, loss: 0.35125288367271423
2023-01-24 01:40:41.513751: step: 924/469, loss: 0.7038163542747498
2023-01-24 01:40:42.135949: step: 926/469, loss: 0.4657997190952301
2023-01-24 01:40:42.841228: step: 928/469, loss: 1.0136849880218506
2023-01-24 01:40:43.394593: step: 930/469, loss: 0.5984984040260315
2023-01-24 01:40:44.089682: step: 932/469, loss: 0.19931790232658386
2023-01-24 01:40:44.773387: step: 934/469, loss: 2.58497953414917
2023-01-24 01:40:45.363821: step: 936/469, loss: 0.33287858963012695
2023-01-24 01:40:45.980680: step: 938/469, loss: 0.36068013310432434
==================================================
Loss: 0.701
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34049187956463667, 'r': 0.29526525419551986, 'f1': 0.3162698962622743}, 'combined': 0.23304097619325473, 'epoch': 6}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3215836233004704, 'r': 0.21742936653160808, 'f1': 0.25944355635267213}, 'combined': 0.14151466710145752, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35179640393089057, 'r': 0.2990603206091821, 'f1': 0.32329187479187477}, 'combined': 0.23821506563611825, 'epoch': 6}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31941825131851476, 'r': 0.2185954729974831, 'f1': 0.2595598609301999}, 'combined': 0.14157810596192721, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33365521383378527, 'r': 0.2880704407862852, 'f1': 0.30919169510055455}, 'combined': 0.22782545954777703, 'epoch': 6}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31936077643908967, 'r': 0.21826395242451965, 'f1': 0.2593070652173913}, 'combined': 0.14144021739130433, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3162393162393162, 'r': 0.35238095238095235, 'f1': 0.3333333333333333}, 'combined': 0.2222222222222222, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.33695652173913043, 'r': 0.33695652173913043, 'f1': 0.33695652173913043}, 'combined': 0.16847826086956522, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.375, 'r': 0.10344827586206896, 'f1': 0.16216216216216217}, 'combined': 0.10810810810810811, 'epoch': 6}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35179640393089057, 'r': 0.2990603206091821, 'f1': 0.32329187479187477}, 'combined': 0.23821506563611825, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31941825131851476, 'r': 0.2185954729974831, 'f1': 0.2595598609301999}, 'combined': 0.14157810596192721, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.33695652173913043, 'r': 0.33695652173913043, 'f1': 0.33695652173913043}, 'combined': 0.16847826086956522, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, '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
2023-01-24 01:43:39.016268: step: 2/469, loss: 0.3034147024154663
2023-01-24 01:43:39.693652: step: 4/469, loss: 0.503424882888794
2023-01-24 01:43:40.355430: step: 6/469, loss: 0.6823604702949524
2023-01-24 01:43:40.935960: step: 8/469, loss: 0.33306610584259033
2023-01-24 01:43:41.559460: step: 10/469, loss: 0.2602163255214691
2023-01-24 01:43:42.306073: step: 12/469, loss: 0.3141564726829529
2023-01-24 01:43:42.984914: step: 14/469, loss: 0.7219853401184082
2023-01-24 01:43:43.628234: step: 16/469, loss: 0.2112475484609604
2023-01-24 01:43:44.259169: step: 18/469, loss: 0.885100781917572
2023-01-24 01:43:44.888171: step: 20/469, loss: 0.7438501119613647
2023-01-24 01:43:45.614029: step: 22/469, loss: 1.2695364952087402
2023-01-24 01:43:46.220715: step: 24/469, loss: 0.43204641342163086
2023-01-24 01:43:46.883839: step: 26/469, loss: 0.22428709268569946
2023-01-24 01:43:47.590630: step: 28/469, loss: 0.8295562267303467
2023-01-24 01:43:48.242634: step: 30/469, loss: 0.47287508845329285
2023-01-24 01:43:48.871242: step: 32/469, loss: 1.0738602876663208
2023-01-24 01:43:49.455452: step: 34/469, loss: 1.0092536211013794
2023-01-24 01:43:50.028694: step: 36/469, loss: 0.34260115027427673
2023-01-24 01:43:50.643722: step: 38/469, loss: 0.5713402628898621
2023-01-24 01:43:51.351795: step: 40/469, loss: 0.29429081082344055
2023-01-24 01:43:51.999442: step: 42/469, loss: 0.5646462440490723
2023-01-24 01:43:52.605933: step: 44/469, loss: 0.4239635467529297
2023-01-24 01:43:53.253457: step: 46/469, loss: 0.36079859733581543
2023-01-24 01:43:53.910119: step: 48/469, loss: 0.54287189245224
2023-01-24 01:43:54.583435: step: 50/469, loss: 0.838449239730835
2023-01-24 01:43:55.234624: step: 52/469, loss: 0.4343792498111725
2023-01-24 01:43:55.881280: step: 54/469, loss: 0.8721284866333008
2023-01-24 01:43:56.535746: step: 56/469, loss: 0.2720860540866852
2023-01-24 01:43:57.189712: step: 58/469, loss: 0.19316355884075165
2023-01-24 01:43:57.887350: step: 60/469, loss: 0.5932791829109192
2023-01-24 01:43:58.498945: step: 62/469, loss: 0.5315917134284973
2023-01-24 01:43:59.139476: step: 64/469, loss: 1.0495598316192627
2023-01-24 01:43:59.799399: step: 66/469, loss: 0.46429717540740967
2023-01-24 01:44:00.405440: step: 68/469, loss: 0.29560616612434387
2023-01-24 01:44:01.089444: step: 70/469, loss: 0.7473350167274475
2023-01-24 01:44:01.739254: step: 72/469, loss: 0.3408643305301666
2023-01-24 01:44:02.333708: step: 74/469, loss: 0.10760396718978882
2023-01-24 01:44:03.029332: step: 76/469, loss: 1.275162696838379
2023-01-24 01:44:03.659953: step: 78/469, loss: 0.31276509165763855
2023-01-24 01:44:04.235491: step: 80/469, loss: 0.18019674718379974
2023-01-24 01:44:04.866319: step: 82/469, loss: 0.19032791256904602
2023-01-24 01:44:05.543621: step: 84/469, loss: 0.5119924545288086
2023-01-24 01:44:06.204804: step: 86/469, loss: 0.633182168006897
2023-01-24 01:44:06.854938: step: 88/469, loss: 0.6701422333717346
2023-01-24 01:44:07.405884: step: 90/469, loss: 0.31592199206352234
2023-01-24 01:44:08.013973: step: 92/469, loss: 0.1339643895626068
2023-01-24 01:44:08.592116: step: 94/469, loss: 1.2725943326950073
2023-01-24 01:44:09.214449: step: 96/469, loss: 1.557843565940857
2023-01-24 01:44:09.880329: step: 98/469, loss: 0.16810758411884308
2023-01-24 01:44:10.552544: step: 100/469, loss: 1.3217558860778809
2023-01-24 01:44:11.150769: step: 102/469, loss: 0.16093072295188904
2023-01-24 01:44:11.713984: step: 104/469, loss: 0.39869099855422974
2023-01-24 01:44:12.374878: step: 106/469, loss: 0.2008829414844513
2023-01-24 01:44:13.012698: step: 108/469, loss: 0.46230778098106384
2023-01-24 01:44:13.628896: step: 110/469, loss: 0.25707271695137024
2023-01-24 01:44:14.267537: step: 112/469, loss: 0.5694282650947571
2023-01-24 01:44:14.839489: step: 114/469, loss: 0.1926581710577011
2023-01-24 01:44:15.476678: step: 116/469, loss: 0.2244986742734909
2023-01-24 01:44:16.112119: step: 118/469, loss: 0.19084006547927856
2023-01-24 01:44:16.724170: step: 120/469, loss: 0.2766150236129761
2023-01-24 01:44:17.390975: step: 122/469, loss: 0.2977721095085144
2023-01-24 01:44:18.015014: step: 124/469, loss: 0.1356898695230484
2023-01-24 01:44:18.727842: step: 126/469, loss: 0.5761306285858154
2023-01-24 01:44:19.339893: step: 128/469, loss: 0.38432493805885315
2023-01-24 01:44:19.932835: step: 130/469, loss: 0.26987239718437195
2023-01-24 01:44:20.522115: step: 132/469, loss: 0.6441469788551331
2023-01-24 01:44:21.219847: step: 134/469, loss: 0.3023805022239685
2023-01-24 01:44:21.862675: step: 136/469, loss: 0.5059775114059448
2023-01-24 01:44:22.482664: step: 138/469, loss: 0.3556457459926605
2023-01-24 01:44:23.086054: step: 140/469, loss: 0.39019137620925903
2023-01-24 01:44:23.644964: step: 142/469, loss: 0.13567368686199188
2023-01-24 01:44:24.262182: step: 144/469, loss: 0.3696707785129547
2023-01-24 01:44:24.885227: step: 146/469, loss: 0.23034143447875977
2023-01-24 01:44:25.515700: step: 148/469, loss: 0.4747249186038971
2023-01-24 01:44:26.137078: step: 150/469, loss: 0.5245690941810608
2023-01-24 01:44:26.788560: step: 152/469, loss: 0.45697712898254395
2023-01-24 01:44:27.342486: step: 154/469, loss: 0.11479607969522476
2023-01-24 01:44:27.924412: step: 156/469, loss: 0.4539227783679962
2023-01-24 01:44:28.547101: step: 158/469, loss: 0.6690745949745178
2023-01-24 01:44:29.246208: step: 160/469, loss: 0.44240736961364746
2023-01-24 01:44:29.828821: step: 162/469, loss: 0.7192642688751221
2023-01-24 01:44:30.439971: step: 164/469, loss: 0.21808096766471863
2023-01-24 01:44:31.108335: step: 166/469, loss: 0.38638466596603394
2023-01-24 01:44:31.717840: step: 168/469, loss: 0.5944715142250061
2023-01-24 01:44:32.331816: step: 170/469, loss: 0.5639787316322327
2023-01-24 01:44:32.918152: step: 172/469, loss: 0.9023991823196411
2023-01-24 01:44:33.572470: step: 174/469, loss: 0.7423897981643677
2023-01-24 01:44:34.253001: step: 176/469, loss: 1.2526183128356934
2023-01-24 01:44:34.864185: step: 178/469, loss: 0.31094348430633545
2023-01-24 01:44:35.466377: step: 180/469, loss: 0.4512382745742798
2023-01-24 01:44:36.142262: step: 182/469, loss: 2.056619882583618
2023-01-24 01:44:36.782523: step: 184/469, loss: 0.5389247536659241
2023-01-24 01:44:37.335949: step: 186/469, loss: 0.3956908881664276
2023-01-24 01:44:37.985408: step: 188/469, loss: 1.105033278465271
2023-01-24 01:44:38.656737: step: 190/469, loss: 0.9648261070251465
2023-01-24 01:44:39.246574: step: 192/469, loss: 0.5629838705062866
2023-01-24 01:44:39.904418: step: 194/469, loss: 0.2560095489025116
2023-01-24 01:44:40.621235: step: 196/469, loss: 1.1309959888458252
2023-01-24 01:44:41.215161: step: 198/469, loss: 0.9821249842643738
2023-01-24 01:44:41.778824: step: 200/469, loss: 0.2722633481025696
2023-01-24 01:44:42.395571: step: 202/469, loss: 0.3103010356426239
2023-01-24 01:44:43.013684: step: 204/469, loss: 0.3793702721595764
2023-01-24 01:44:43.607715: step: 206/469, loss: 0.43455466628074646
2023-01-24 01:44:44.219208: step: 208/469, loss: 0.6203905940055847
2023-01-24 01:44:44.871235: step: 210/469, loss: 0.18608418107032776
2023-01-24 01:44:45.534474: step: 212/469, loss: 2.0353469848632812
2023-01-24 01:44:46.186237: step: 214/469, loss: 0.3603098392486572
2023-01-24 01:44:46.785449: step: 216/469, loss: 0.5063532590866089
2023-01-24 01:44:47.359076: step: 218/469, loss: 0.2816372513771057
2023-01-24 01:44:47.924580: step: 220/469, loss: 0.22815579175949097
2023-01-24 01:44:48.527478: step: 222/469, loss: 0.2961884140968323
2023-01-24 01:44:49.215893: step: 224/469, loss: 0.37092456221580505
2023-01-24 01:44:49.835618: step: 226/469, loss: 0.8792437314987183
2023-01-24 01:44:50.528401: step: 228/469, loss: 1.2625809907913208
2023-01-24 01:44:51.126824: step: 230/469, loss: 0.34319931268692017
2023-01-24 01:44:51.802204: step: 232/469, loss: 0.42412394285202026
2023-01-24 01:44:52.424597: step: 234/469, loss: 0.2557583451271057
2023-01-24 01:44:53.050786: step: 236/469, loss: 0.2378799021244049
2023-01-24 01:44:53.668272: step: 238/469, loss: 0.7149409055709839
2023-01-24 01:44:54.330436: step: 240/469, loss: 0.27111420035362244
2023-01-24 01:44:55.005651: step: 242/469, loss: 0.5395912528038025
2023-01-24 01:44:55.594868: step: 244/469, loss: 0.6727349162101746
2023-01-24 01:44:56.250547: step: 246/469, loss: 0.5664801597595215
2023-01-24 01:44:56.798354: step: 248/469, loss: 0.36088114976882935
2023-01-24 01:44:57.440665: step: 250/469, loss: 2.157541275024414
2023-01-24 01:44:58.157654: step: 252/469, loss: 0.1849389523267746
2023-01-24 01:44:58.742252: step: 254/469, loss: 0.34292373061180115
2023-01-24 01:44:59.365643: step: 256/469, loss: 0.46344757080078125
2023-01-24 01:45:00.019139: step: 258/469, loss: 0.6474393606185913
2023-01-24 01:45:00.646699: step: 260/469, loss: 0.667199432849884
2023-01-24 01:45:01.353527: step: 262/469, loss: 0.3647635877132416
2023-01-24 01:45:01.941489: step: 264/469, loss: 0.48776039481163025
2023-01-24 01:45:02.545711: step: 266/469, loss: 0.35894811153411865
2023-01-24 01:45:03.227569: step: 268/469, loss: 0.4408510625362396
2023-01-24 01:45:03.884220: step: 270/469, loss: 0.1577748954296112
2023-01-24 01:45:04.525891: step: 272/469, loss: 9.59257698059082
2023-01-24 01:45:05.146182: step: 274/469, loss: 0.34344255924224854
2023-01-24 01:45:05.729099: step: 276/469, loss: 0.7591780424118042
2023-01-24 01:45:06.315569: step: 278/469, loss: 0.6208717226982117
2023-01-24 01:45:06.973454: step: 280/469, loss: 1.1715564727783203
2023-01-24 01:45:07.624962: step: 282/469, loss: 0.7485136389732361
2023-01-24 01:45:08.195689: step: 284/469, loss: 0.25127243995666504
2023-01-24 01:45:08.834567: step: 286/469, loss: 0.49830514192581177
2023-01-24 01:45:09.465362: step: 288/469, loss: 0.6897481679916382
2023-01-24 01:45:10.221131: step: 290/469, loss: 0.3550090789794922
2023-01-24 01:45:10.842790: step: 292/469, loss: 0.48031723499298096
2023-01-24 01:45:11.472681: step: 294/469, loss: 0.18158164620399475
2023-01-24 01:45:12.055408: step: 296/469, loss: 0.22862082719802856
2023-01-24 01:45:12.662220: step: 298/469, loss: 0.3542085289955139
2023-01-24 01:45:13.293463: step: 300/469, loss: 1.4608161449432373
2023-01-24 01:45:13.907359: step: 302/469, loss: 0.24203746020793915
2023-01-24 01:45:14.491177: step: 304/469, loss: 0.3416796922683716
2023-01-24 01:45:15.223864: step: 306/469, loss: 0.1868167668581009
2023-01-24 01:45:15.777236: step: 308/469, loss: 0.9778412580490112
2023-01-24 01:45:16.453144: step: 310/469, loss: 0.13471634685993195
2023-01-24 01:45:17.100015: step: 312/469, loss: 0.4944702088832855
2023-01-24 01:45:17.761654: step: 314/469, loss: 0.7598327994346619
2023-01-24 01:45:18.442319: step: 316/469, loss: 0.38385286927223206
2023-01-24 01:45:19.078401: step: 318/469, loss: 0.13890638947486877
2023-01-24 01:45:19.687883: step: 320/469, loss: 0.3973208963871002
2023-01-24 01:45:20.291927: step: 322/469, loss: 0.3698139488697052
2023-01-24 01:45:20.918312: step: 324/469, loss: 0.5473549962043762
2023-01-24 01:45:21.560137: step: 326/469, loss: 0.36224818229675293
2023-01-24 01:45:22.131090: step: 328/469, loss: 0.20923873782157898
2023-01-24 01:45:22.757350: step: 330/469, loss: 0.5139366388320923
2023-01-24 01:45:23.386254: step: 332/469, loss: 0.6960780024528503
2023-01-24 01:45:23.996557: step: 334/469, loss: 1.0095466375350952
2023-01-24 01:45:24.645312: step: 336/469, loss: 0.6473803520202637
2023-01-24 01:45:25.267801: step: 338/469, loss: 0.22387218475341797
2023-01-24 01:45:25.910169: step: 340/469, loss: 0.21535411477088928
2023-01-24 01:45:26.542394: step: 342/469, loss: 0.24951550364494324
2023-01-24 01:45:27.188098: step: 344/469, loss: 0.7308018803596497
2023-01-24 01:45:27.937067: step: 346/469, loss: 1.2594232559204102
2023-01-24 01:45:28.597252: step: 348/469, loss: 0.3323275148868561
2023-01-24 01:45:29.256271: step: 350/469, loss: 0.2357524037361145
2023-01-24 01:45:29.789463: step: 352/469, loss: 0.40152549743652344
2023-01-24 01:45:30.415683: step: 354/469, loss: 0.29077887535095215
2023-01-24 01:45:31.021788: step: 356/469, loss: 0.2026900053024292
2023-01-24 01:45:31.693693: step: 358/469, loss: 0.5275459885597229
2023-01-24 01:45:32.338928: step: 360/469, loss: 0.5878629684448242
2023-01-24 01:45:33.014391: step: 362/469, loss: 0.5410671234130859
2023-01-24 01:45:33.626734: step: 364/469, loss: 0.27543145418167114
2023-01-24 01:45:34.280684: step: 366/469, loss: 0.07763580977916718
2023-01-24 01:45:34.964009: step: 368/469, loss: 2.3904075622558594
2023-01-24 01:45:35.596731: step: 370/469, loss: 0.9165710210800171
2023-01-24 01:45:36.250789: step: 372/469, loss: 0.5919375419616699
2023-01-24 01:45:36.962046: step: 374/469, loss: 0.24279849231243134
2023-01-24 01:45:37.634889: step: 376/469, loss: 0.5104106664657593
2023-01-24 01:45:38.289243: step: 378/469, loss: 1.4496835470199585
2023-01-24 01:45:38.900038: step: 380/469, loss: 0.19177675247192383
2023-01-24 01:45:39.530824: step: 382/469, loss: 0.7152149081230164
2023-01-24 01:45:40.270228: step: 384/469, loss: 0.21729762852191925
2023-01-24 01:45:41.027318: step: 386/469, loss: 0.47995713353157043
2023-01-24 01:45:41.635146: step: 388/469, loss: 0.2849056124687195
2023-01-24 01:45:42.296049: step: 390/469, loss: 0.30151689052581787
2023-01-24 01:45:42.962809: step: 392/469, loss: 0.9165915250778198
2023-01-24 01:45:43.522406: step: 394/469, loss: 0.1873292773962021
2023-01-24 01:45:44.135644: step: 396/469, loss: 0.133287250995636
2023-01-24 01:45:44.794501: step: 398/469, loss: 0.5160813927650452
2023-01-24 01:45:45.422053: step: 400/469, loss: 1.4087209701538086
2023-01-24 01:45:46.024985: step: 402/469, loss: 0.40327349305152893
2023-01-24 01:45:46.688660: step: 404/469, loss: 0.23506242036819458
2023-01-24 01:45:47.329383: step: 406/469, loss: 0.38241589069366455
2023-01-24 01:45:47.985078: step: 408/469, loss: 0.4073394536972046
2023-01-24 01:45:48.657539: step: 410/469, loss: 0.26036936044692993
2023-01-24 01:45:49.286166: step: 412/469, loss: 0.8148781061172485
2023-01-24 01:45:49.945308: step: 414/469, loss: 0.20191913843154907
2023-01-24 01:45:50.608918: step: 416/469, loss: 0.22603236138820648
2023-01-24 01:45:51.308018: step: 418/469, loss: 0.900985598564148
2023-01-24 01:45:51.919801: step: 420/469, loss: 0.4961312413215637
2023-01-24 01:45:52.490032: step: 422/469, loss: 0.46023181080818176
2023-01-24 01:45:53.079586: step: 424/469, loss: 0.5713052153587341
2023-01-24 01:45:53.664050: step: 426/469, loss: 1.788339376449585
2023-01-24 01:45:54.363558: step: 428/469, loss: 0.22763192653656006
2023-01-24 01:45:55.001717: step: 430/469, loss: 0.2552791237831116
2023-01-24 01:45:55.662966: step: 432/469, loss: 0.8556559085845947
2023-01-24 01:45:56.267656: step: 434/469, loss: 0.6025184392929077
2023-01-24 01:45:57.015159: step: 436/469, loss: 0.3650805652141571
2023-01-24 01:45:57.654939: step: 438/469, loss: 0.4491713047027588
2023-01-24 01:45:58.354060: step: 440/469, loss: 0.7329959869384766
2023-01-24 01:45:59.009283: step: 442/469, loss: 0.7308976650238037
2023-01-24 01:45:59.658909: step: 444/469, loss: 1.1651263236999512
2023-01-24 01:46:00.340205: step: 446/469, loss: 0.14074893295764923
2023-01-24 01:46:01.005265: step: 448/469, loss: 0.17097920179367065
2023-01-24 01:46:01.592490: step: 450/469, loss: 0.7660448551177979
2023-01-24 01:46:02.163805: step: 452/469, loss: 0.12841929495334625
2023-01-24 01:46:02.814914: step: 454/469, loss: 0.4611152112483978
2023-01-24 01:46:03.384065: step: 456/469, loss: 0.16392871737480164
2023-01-24 01:46:04.013017: step: 458/469, loss: 0.2862749397754669
2023-01-24 01:46:04.658680: step: 460/469, loss: 0.6968491673469543
2023-01-24 01:46:05.244305: step: 462/469, loss: 0.27910956740379333
2023-01-24 01:46:05.915632: step: 464/469, loss: 0.3194659948348999
2023-01-24 01:46:06.481473: step: 466/469, loss: 0.5117559432983398
2023-01-24 01:46:07.118603: step: 468/469, loss: 0.18484525382518768
2023-01-24 01:46:07.693720: step: 470/469, loss: 2.5478875637054443
2023-01-24 01:46:08.295393: step: 472/469, loss: 0.24330207705497742
2023-01-24 01:46:08.894886: step: 474/469, loss: 4.195929050445557
2023-01-24 01:46:09.532292: step: 476/469, loss: 0.2522517740726471
2023-01-24 01:46:10.131092: step: 478/469, loss: 2.127666473388672
2023-01-24 01:46:10.784037: step: 480/469, loss: 0.5200915932655334
2023-01-24 01:46:11.424937: step: 482/469, loss: 0.43802380561828613
2023-01-24 01:46:11.973044: step: 484/469, loss: 0.4296901822090149
2023-01-24 01:46:12.576131: step: 486/469, loss: 0.5036375522613525
2023-01-24 01:46:13.178608: step: 488/469, loss: 0.4596751630306244
2023-01-24 01:46:13.796444: step: 490/469, loss: 0.3468911647796631
2023-01-24 01:46:14.464529: step: 492/469, loss: 2.6914615631103516
2023-01-24 01:46:15.050588: step: 494/469, loss: 0.3425523638725281
2023-01-24 01:46:15.674418: step: 496/469, loss: 0.5966498255729675
2023-01-24 01:46:16.329366: step: 498/469, loss: 0.12489598244428635
2023-01-24 01:46:17.056630: step: 500/469, loss: 0.14763931930065155
2023-01-24 01:46:17.643495: step: 502/469, loss: 0.2640705108642578
2023-01-24 01:46:18.286250: step: 504/469, loss: 0.6138185858726501
2023-01-24 01:46:18.884823: step: 506/469, loss: 0.25276580452919006
2023-01-24 01:46:19.459491: step: 508/469, loss: 0.47454220056533813
2023-01-24 01:46:20.226807: step: 510/469, loss: 0.2023448944091797
2023-01-24 01:46:20.936027: step: 512/469, loss: 0.3868090510368347
2023-01-24 01:46:21.594198: step: 514/469, loss: 0.7646952271461487
2023-01-24 01:46:22.216490: step: 516/469, loss: 0.2611725926399231
2023-01-24 01:46:22.803529: step: 518/469, loss: 0.29690372943878174
2023-01-24 01:46:23.417999: step: 520/469, loss: 0.9276142716407776
2023-01-24 01:46:24.039937: step: 522/469, loss: 0.3030405640602112
2023-01-24 01:46:24.656638: step: 524/469, loss: 0.3247101604938507
2023-01-24 01:46:25.306296: step: 526/469, loss: 0.1622537225484848
2023-01-24 01:46:25.957310: step: 528/469, loss: 0.32321006059646606
2023-01-24 01:46:26.557997: step: 530/469, loss: 0.15134075284004211
2023-01-24 01:46:27.154187: step: 532/469, loss: 0.24118146300315857
2023-01-24 01:46:27.721528: step: 534/469, loss: 0.22268259525299072
2023-01-24 01:46:28.330910: step: 536/469, loss: 0.3385399281978607
2023-01-24 01:46:28.931280: step: 538/469, loss: 1.840336799621582
2023-01-24 01:46:29.576845: step: 540/469, loss: 0.31376150250434875
2023-01-24 01:46:30.258088: step: 542/469, loss: 0.26314258575439453
2023-01-24 01:46:30.832104: step: 544/469, loss: 0.7010689377784729
2023-01-24 01:46:31.468236: step: 546/469, loss: 0.7424901127815247
2023-01-24 01:46:32.122989: step: 548/469, loss: 0.6966558694839478
2023-01-24 01:46:32.762787: step: 550/469, loss: 0.2281423956155777
2023-01-24 01:46:33.455578: step: 552/469, loss: 0.4474644362926483
2023-01-24 01:46:34.124703: step: 554/469, loss: 0.8803151845932007
2023-01-24 01:46:34.729044: step: 556/469, loss: 0.2599521279335022
2023-01-24 01:46:35.452321: step: 558/469, loss: 0.6703866124153137
2023-01-24 01:46:36.023275: step: 560/469, loss: 0.5517482161521912
2023-01-24 01:46:36.612294: step: 562/469, loss: 0.44817402958869934
2023-01-24 01:46:37.300393: step: 564/469, loss: 0.5980182886123657
2023-01-24 01:46:37.847152: step: 566/469, loss: 0.15622496604919434
2023-01-24 01:46:38.493249: step: 568/469, loss: 0.5188809633255005
2023-01-24 01:46:39.093210: step: 570/469, loss: 0.5812439918518066
2023-01-24 01:46:39.646656: step: 572/469, loss: 0.2790174186229706
2023-01-24 01:46:40.238984: step: 574/469, loss: 0.2066507637500763
2023-01-24 01:46:40.878350: step: 576/469, loss: 0.1465393453836441
2023-01-24 01:46:41.481696: step: 578/469, loss: 0.2461715191602707
2023-01-24 01:46:42.111014: step: 580/469, loss: 0.19781449437141418
2023-01-24 01:46:42.790506: step: 582/469, loss: 0.38093888759613037
2023-01-24 01:46:43.481012: step: 584/469, loss: 0.46796655654907227
2023-01-24 01:46:44.154966: step: 586/469, loss: 0.4513213634490967
2023-01-24 01:46:44.801395: step: 588/469, loss: 0.25914958119392395
2023-01-24 01:46:45.410290: step: 590/469, loss: 0.8821139931678772
2023-01-24 01:46:46.032869: step: 592/469, loss: 0.4917592406272888
2023-01-24 01:46:46.708574: step: 594/469, loss: 0.27000677585601807
2023-01-24 01:46:47.419385: step: 596/469, loss: 0.28437694907188416
2023-01-24 01:46:48.036600: step: 598/469, loss: 0.5301434397697449
2023-01-24 01:46:48.610368: step: 600/469, loss: 0.7056336402893066
2023-01-24 01:46:49.330069: step: 602/469, loss: 0.4812750518321991
2023-01-24 01:46:49.924569: step: 604/469, loss: 1.2242769002914429
2023-01-24 01:46:50.557316: step: 606/469, loss: 0.10403191298246384
2023-01-24 01:46:51.179167: step: 608/469, loss: 0.1673997938632965
2023-01-24 01:46:51.848909: step: 610/469, loss: 0.5051147937774658
2023-01-24 01:46:52.393791: step: 612/469, loss: 0.2315412163734436
2023-01-24 01:46:53.075392: step: 614/469, loss: 0.2814974784851074
2023-01-24 01:46:53.751633: step: 616/469, loss: 0.9631189107894897
2023-01-24 01:46:54.391480: step: 618/469, loss: 0.25975683331489563
2023-01-24 01:46:54.982479: step: 620/469, loss: 1.003028154373169
2023-01-24 01:46:55.582315: step: 622/469, loss: 0.23933352530002594
2023-01-24 01:46:56.188409: step: 624/469, loss: 0.38538992404937744
2023-01-24 01:46:56.934307: step: 626/469, loss: 0.2421412318944931
2023-01-24 01:46:57.617741: step: 628/469, loss: 0.3802891969680786
2023-01-24 01:46:58.255793: step: 630/469, loss: 0.4327777624130249
2023-01-24 01:46:58.905478: step: 632/469, loss: 1.3673803806304932
2023-01-24 01:46:59.507946: step: 634/469, loss: 0.2792380154132843
2023-01-24 01:47:00.157671: step: 636/469, loss: 0.6696301698684692
2023-01-24 01:47:00.738133: step: 638/469, loss: 0.40074968338012695
2023-01-24 01:47:01.348399: step: 640/469, loss: 1.3802582025527954
2023-01-24 01:47:01.947210: step: 642/469, loss: 0.7367796897888184
2023-01-24 01:47:02.566300: step: 644/469, loss: 0.8440686464309692
2023-01-24 01:47:03.196317: step: 646/469, loss: 0.15096645057201385
2023-01-24 01:47:03.820558: step: 648/469, loss: 0.35317832231521606
2023-01-24 01:47:04.452595: step: 650/469, loss: 0.1401774138212204
2023-01-24 01:47:05.052495: step: 652/469, loss: 0.18275809288024902
2023-01-24 01:47:05.655040: step: 654/469, loss: 1.1960855722427368
2023-01-24 01:47:06.222768: step: 656/469, loss: 0.44214916229248047
2023-01-24 01:47:06.890637: step: 658/469, loss: 0.833315908908844
2023-01-24 01:47:07.451952: step: 660/469, loss: 0.2281283736228943
2023-01-24 01:47:08.017326: step: 662/469, loss: 0.651561975479126
2023-01-24 01:47:08.668846: step: 664/469, loss: 0.7029745578765869
2023-01-24 01:47:09.318125: step: 666/469, loss: 0.6088948845863342
2023-01-24 01:47:09.952336: step: 668/469, loss: 0.4874654710292816
2023-01-24 01:47:10.632442: step: 670/469, loss: 0.3011801838874817
2023-01-24 01:47:11.322073: step: 672/469, loss: 0.26479166746139526
2023-01-24 01:47:11.981227: step: 674/469, loss: 0.2449568808078766
2023-01-24 01:47:12.594993: step: 676/469, loss: 1.486423373222351
2023-01-24 01:47:13.291862: step: 678/469, loss: 0.18135876953601837
2023-01-24 01:47:13.945694: step: 680/469, loss: 0.2924414873123169
2023-01-24 01:47:14.526881: step: 682/469, loss: 1.2524816989898682
2023-01-24 01:47:15.129811: step: 684/469, loss: 0.6766750812530518
2023-01-24 01:47:15.741448: step: 686/469, loss: 0.6198279857635498
2023-01-24 01:47:16.312423: step: 688/469, loss: 0.6449093222618103
2023-01-24 01:47:16.938386: step: 690/469, loss: 0.23987683653831482
2023-01-24 01:47:17.597409: step: 692/469, loss: 0.9177189469337463
2023-01-24 01:47:18.204957: step: 694/469, loss: 0.8281612992286682
2023-01-24 01:47:18.805958: step: 696/469, loss: 0.5510213375091553
2023-01-24 01:47:19.382212: step: 698/469, loss: 0.09462345391511917
2023-01-24 01:47:20.028480: step: 700/469, loss: 0.2250729352235794
2023-01-24 01:47:20.634057: step: 702/469, loss: 0.13198135793209076
2023-01-24 01:47:21.246669: step: 704/469, loss: 0.7246847748756409
2023-01-24 01:47:21.846187: step: 706/469, loss: 0.7825203537940979
2023-01-24 01:47:22.502331: step: 708/469, loss: 0.7200645804405212
2023-01-24 01:47:23.165208: step: 710/469, loss: 0.39589351415634155
2023-01-24 01:47:23.806578: step: 712/469, loss: 0.33914634585380554
2023-01-24 01:47:24.480191: step: 714/469, loss: 0.9127599596977234
2023-01-24 01:47:25.112493: step: 716/469, loss: 0.6256756782531738
2023-01-24 01:47:25.774707: step: 718/469, loss: 0.6755963563919067
2023-01-24 01:47:26.369815: step: 720/469, loss: 0.6067854762077332
2023-01-24 01:47:26.963666: step: 722/469, loss: 0.2231627255678177
2023-01-24 01:47:27.648134: step: 724/469, loss: 0.5573198795318604
2023-01-24 01:47:28.253635: step: 726/469, loss: 1.5285015106201172
2023-01-24 01:47:28.844574: step: 728/469, loss: 0.2820298671722412
2023-01-24 01:47:29.382601: step: 730/469, loss: 0.335647851228714
2023-01-24 01:47:29.955133: step: 732/469, loss: 0.14330941438674927
2023-01-24 01:47:30.576608: step: 734/469, loss: 0.40038958191871643
2023-01-24 01:47:31.200940: step: 736/469, loss: 0.1632099747657776
2023-01-24 01:47:31.814361: step: 738/469, loss: 0.11054205894470215
2023-01-24 01:47:32.405077: step: 740/469, loss: 0.3448159694671631
2023-01-24 01:47:33.072163: step: 742/469, loss: 1.9047409296035767
2023-01-24 01:47:33.685357: step: 744/469, loss: 0.5617899894714355
2023-01-24 01:47:34.347051: step: 746/469, loss: 0.39616265892982483
2023-01-24 01:47:34.959292: step: 748/469, loss: 0.6567694544792175
2023-01-24 01:47:35.600330: step: 750/469, loss: 3.6219592094421387
2023-01-24 01:47:36.224026: step: 752/469, loss: 0.3712438642978668
2023-01-24 01:47:36.906938: step: 754/469, loss: 0.2743932902812958
2023-01-24 01:47:37.518448: step: 756/469, loss: 0.2320937067270279
2023-01-24 01:47:38.128815: step: 758/469, loss: 0.2250518500804901
2023-01-24 01:47:38.743793: step: 760/469, loss: 0.6834797859191895
2023-01-24 01:47:39.317000: step: 762/469, loss: 1.64217209815979
2023-01-24 01:47:39.957157: step: 764/469, loss: 0.3303803503513336
2023-01-24 01:47:40.577526: step: 766/469, loss: 1.1484766006469727
2023-01-24 01:47:41.242025: step: 768/469, loss: 0.3432031571865082
2023-01-24 01:47:41.875847: step: 770/469, loss: 0.21072743833065033
2023-01-24 01:47:42.470900: step: 772/469, loss: 0.18219800293445587
2023-01-24 01:47:43.113376: step: 774/469, loss: 0.22114837169647217
2023-01-24 01:47:43.715799: step: 776/469, loss: 0.7861373424530029
2023-01-24 01:47:44.329456: step: 778/469, loss: 0.21906259655952454
2023-01-24 01:47:45.026332: step: 780/469, loss: 0.7411484718322754
2023-01-24 01:47:45.652098: step: 782/469, loss: 1.7447690963745117
2023-01-24 01:47:46.261721: step: 784/469, loss: 1.0749149322509766
2023-01-24 01:47:46.886613: step: 786/469, loss: 0.41501766443252563
2023-01-24 01:47:47.508876: step: 788/469, loss: 0.2512631416320801
2023-01-24 01:47:48.139806: step: 790/469, loss: 0.4638896882534027
2023-01-24 01:47:48.701963: step: 792/469, loss: 1.6946717500686646
2023-01-24 01:47:49.266437: step: 794/469, loss: 0.2728288471698761
2023-01-24 01:47:49.901214: step: 796/469, loss: 0.19500260055065155
2023-01-24 01:47:50.535558: step: 798/469, loss: 0.18098615109920502
2023-01-24 01:47:51.196791: step: 800/469, loss: 4.3521904945373535
2023-01-24 01:47:51.826504: step: 802/469, loss: 2.5424928665161133
2023-01-24 01:47:52.377158: step: 804/469, loss: 0.6280380487442017
2023-01-24 01:47:52.988606: step: 806/469, loss: 0.16399222612380981
2023-01-24 01:47:53.586186: step: 808/469, loss: 0.39004218578338623
2023-01-24 01:47:54.314219: step: 810/469, loss: 0.44297417998313904
2023-01-24 01:47:54.941282: step: 812/469, loss: 0.6048476696014404
2023-01-24 01:47:55.552676: step: 814/469, loss: 0.30073437094688416
2023-01-24 01:47:56.199314: step: 816/469, loss: 0.32141587138175964
2023-01-24 01:47:56.774569: step: 818/469, loss: 0.27014002203941345
2023-01-24 01:47:57.384481: step: 820/469, loss: 0.15073515474796295
2023-01-24 01:47:58.018582: step: 822/469, loss: 0.09293115139007568
2023-01-24 01:47:58.678131: step: 824/469, loss: 0.18213669955730438
2023-01-24 01:47:59.243631: step: 826/469, loss: 0.26865479350090027
2023-01-24 01:47:59.834217: step: 828/469, loss: 1.8637187480926514
2023-01-24 01:48:00.492391: step: 830/469, loss: 1.0831323862075806
2023-01-24 01:48:01.178134: step: 832/469, loss: 1.0688282251358032
2023-01-24 01:48:01.813522: step: 834/469, loss: 0.4998587965965271
2023-01-24 01:48:02.480465: step: 836/469, loss: 0.9172436594963074
2023-01-24 01:48:03.123021: step: 838/469, loss: 0.5721681118011475
2023-01-24 01:48:03.819689: step: 840/469, loss: 1.643479824066162
2023-01-24 01:48:04.408939: step: 842/469, loss: 0.251740425825119
2023-01-24 01:48:04.965746: step: 844/469, loss: 0.3436243236064911
2023-01-24 01:48:05.542862: step: 846/469, loss: 1.3460259437561035
2023-01-24 01:48:06.181345: step: 848/469, loss: 0.17538982629776
2023-01-24 01:48:06.777681: step: 850/469, loss: 0.5882743000984192
2023-01-24 01:48:07.404787: step: 852/469, loss: 0.28470170497894287
2023-01-24 01:48:08.056617: step: 854/469, loss: 0.8674442172050476
2023-01-24 01:48:08.694701: step: 856/469, loss: 0.7559859752655029
2023-01-24 01:48:09.329723: step: 858/469, loss: 0.2747848629951477
2023-01-24 01:48:09.991514: step: 860/469, loss: 0.6750397086143494
2023-01-24 01:48:10.589334: step: 862/469, loss: 0.4371977150440216
2023-01-24 01:48:11.108426: step: 864/469, loss: 1.105844259262085
2023-01-24 01:48:11.753255: step: 866/469, loss: 0.44471046328544617
2023-01-24 01:48:12.338040: step: 868/469, loss: 0.62237948179245
2023-01-24 01:48:12.955616: step: 870/469, loss: 0.30178648233413696
2023-01-24 01:48:13.600923: step: 872/469, loss: 0.31751108169555664
2023-01-24 01:48:14.235381: step: 874/469, loss: 0.19263657927513123
2023-01-24 01:48:14.866920: step: 876/469, loss: 0.5150735378265381
2023-01-24 01:48:15.542224: step: 878/469, loss: 0.6839023232460022
2023-01-24 01:48:16.169836: step: 880/469, loss: 0.5650581121444702
2023-01-24 01:48:16.836693: step: 882/469, loss: 0.7526754140853882
2023-01-24 01:48:17.471494: step: 884/469, loss: 0.201514333486557
2023-01-24 01:48:18.091979: step: 886/469, loss: 0.42249104380607605
2023-01-24 01:48:18.726229: step: 888/469, loss: 0.30510246753692627
2023-01-24 01:48:19.366214: step: 890/469, loss: 0.5134368538856506
2023-01-24 01:48:20.009165: step: 892/469, loss: 0.8806252479553223
2023-01-24 01:48:20.636208: step: 894/469, loss: 1.4703314304351807
2023-01-24 01:48:21.256737: step: 896/469, loss: 0.2756319046020508
2023-01-24 01:48:21.883714: step: 898/469, loss: 0.8927412629127502
2023-01-24 01:48:22.494261: step: 900/469, loss: 0.3346920609474182
2023-01-24 01:48:23.125263: step: 902/469, loss: 0.21807126700878143
2023-01-24 01:48:23.673466: step: 904/469, loss: 0.13336999714374542
2023-01-24 01:48:24.288875: step: 906/469, loss: 0.058336127549409866
2023-01-24 01:48:25.026642: step: 908/469, loss: 0.17020748555660248
2023-01-24 01:48:25.657134: step: 910/469, loss: 0.4886654317378998
2023-01-24 01:48:26.277684: step: 912/469, loss: 0.17047971487045288
2023-01-24 01:48:26.998842: step: 914/469, loss: 0.2284172922372818
2023-01-24 01:48:27.647564: step: 916/469, loss: 1.0500428676605225
2023-01-24 01:48:28.258658: step: 918/469, loss: 2.9921510219573975
2023-01-24 01:48:28.828077: step: 920/469, loss: 0.35923266410827637
2023-01-24 01:48:29.397765: step: 922/469, loss: 0.4361855983734131
2023-01-24 01:48:30.028549: step: 924/469, loss: 0.23665739595890045
2023-01-24 01:48:30.588416: step: 926/469, loss: 1.2017784118652344
2023-01-24 01:48:31.195290: step: 928/469, loss: 0.22746577858924866
2023-01-24 01:48:31.809228: step: 930/469, loss: 0.16186939179897308
2023-01-24 01:48:32.442277: step: 932/469, loss: 0.32564249634742737
2023-01-24 01:48:33.115936: step: 934/469, loss: 1.1063103675842285
2023-01-24 01:48:33.737663: step: 936/469, loss: 0.36923596262931824
2023-01-24 01:48:34.382020: step: 938/469, loss: 0.5784530639648438
==================================================
Loss: 0.587
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31531902343071844, 'r': 0.3201056499723612, 'f1': 0.31769430797633585}, 'combined': 0.23409054271940535, 'epoch': 7}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3068417034272141, 'r': 0.23594585779517285, 'f1': 0.2667637731396121}, 'combined': 0.14550751262160658, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3220139082539022, 'r': 0.32018081200198245, 'f1': 0.3210947439106465}, 'combined': 0.23659612709205532, 'epoch': 7}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3180206359476822, 'r': 0.24483232520903753, 'f1': 0.2766681074343613}, 'combined': 0.15090987678237888, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3238901868494911, 'r': 0.3208172249249229, 'f1': 0.3223463823363858}, 'combined': 0.23751838698470532, 'epoch': 7}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31033749010292955, 'r': 0.2390706007929247, 'f1': 0.27008182601205855}, 'combined': 0.14731735964294101, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.308531746031746, 'r': 0.3702380952380952, 'f1': 0.33658008658008653}, 'combined': 0.22438672438672436, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.26136363636363635, 'r': 0.25, 'f1': 0.25555555555555554}, 'combined': 0.12777777777777777, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45454545454545453, 'r': 0.1724137931034483, 'f1': 0.25000000000000006}, 'combined': 0.16666666666666669, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35179640393089057, 'r': 0.2990603206091821, 'f1': 0.32329187479187477}, 'combined': 0.23821506563611825, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31941825131851476, 'r': 0.2185954729974831, 'f1': 0.2595598609301999}, 'combined': 0.14157810596192721, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.33695652173913043, 'r': 0.33695652173913043, 'f1': 0.33695652173913043}, 'combined': 0.16847826086956522, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, '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
2023-01-24 01:51:20.999479: step: 2/469, loss: 0.9961361289024353
2023-01-24 01:51:21.582771: step: 4/469, loss: 0.21724113821983337
2023-01-24 01:51:22.176890: step: 6/469, loss: 0.38133177161216736
2023-01-24 01:51:22.731581: step: 8/469, loss: 0.14478692412376404
2023-01-24 01:51:23.374889: step: 10/469, loss: 0.33363667130470276
2023-01-24 01:51:24.089573: step: 12/469, loss: 0.589388906955719
2023-01-24 01:51:24.744967: step: 14/469, loss: 0.5699613094329834
2023-01-24 01:51:25.350107: step: 16/469, loss: 0.1767663210630417
2023-01-24 01:51:25.964191: step: 18/469, loss: 0.5059394240379333
2023-01-24 01:51:26.653435: step: 20/469, loss: 0.25279659032821655
2023-01-24 01:51:27.335799: step: 22/469, loss: 0.4721870422363281
2023-01-24 01:51:27.913816: step: 24/469, loss: 0.21340186893939972
2023-01-24 01:51:28.593033: step: 26/469, loss: 0.29136303067207336
2023-01-24 01:51:29.235110: step: 28/469, loss: 0.2648336887359619
2023-01-24 01:51:29.834939: step: 30/469, loss: 0.3934226930141449
2023-01-24 01:51:30.522637: step: 32/469, loss: 0.4900856912136078
2023-01-24 01:51:31.147395: step: 34/469, loss: 0.32868123054504395
2023-01-24 01:51:31.768714: step: 36/469, loss: 0.13562451303005219
2023-01-24 01:51:32.388808: step: 38/469, loss: 0.5227346420288086
2023-01-24 01:51:32.973072: step: 40/469, loss: 0.08767542988061905
2023-01-24 01:51:33.627959: step: 42/469, loss: 2.7418696880340576
2023-01-24 01:51:34.233981: step: 44/469, loss: 0.21661318838596344
2023-01-24 01:51:34.843380: step: 46/469, loss: 0.44279196858406067
2023-01-24 01:51:35.480861: step: 48/469, loss: 0.2080720067024231
2023-01-24 01:51:36.137943: step: 50/469, loss: 0.1683308333158493
2023-01-24 01:51:36.724258: step: 52/469, loss: 0.20721568167209625
2023-01-24 01:51:37.334239: step: 54/469, loss: 0.1343807578086853
2023-01-24 01:51:37.900655: step: 56/469, loss: 0.19176188111305237
2023-01-24 01:51:38.488826: step: 58/469, loss: 0.14346924424171448
2023-01-24 01:51:39.121525: step: 60/469, loss: 0.14417722821235657
2023-01-24 01:51:39.718250: step: 62/469, loss: 0.28534001111984253
2023-01-24 01:51:40.286987: step: 64/469, loss: 0.20595861971378326
2023-01-24 01:51:40.967475: step: 66/469, loss: 0.39788079261779785
2023-01-24 01:51:41.640112: step: 68/469, loss: 0.42548391222953796
2023-01-24 01:51:42.212556: step: 70/469, loss: 0.1159709244966507
2023-01-24 01:51:42.839146: step: 72/469, loss: 0.18989577889442444
2023-01-24 01:51:43.535392: step: 74/469, loss: 0.5328851342201233
2023-01-24 01:51:44.166186: step: 76/469, loss: 0.19202660024166107
2023-01-24 01:51:44.750076: step: 78/469, loss: 0.11115836352109909
2023-01-24 01:51:45.377429: step: 80/469, loss: 0.20907065272331238
2023-01-24 01:51:46.083788: step: 82/469, loss: 0.5931469202041626
2023-01-24 01:51:46.749818: step: 84/469, loss: 0.4220855236053467
2023-01-24 01:51:47.399044: step: 86/469, loss: 0.5431109070777893
2023-01-24 01:51:48.077283: step: 88/469, loss: 0.40732496976852417
2023-01-24 01:51:48.665335: step: 90/469, loss: 0.20699037611484528
2023-01-24 01:51:49.279844: step: 92/469, loss: 0.47190195322036743
2023-01-24 01:51:49.897191: step: 94/469, loss: 0.7683658003807068
2023-01-24 01:51:50.495036: step: 96/469, loss: 0.22656986117362976
2023-01-24 01:51:51.073311: step: 98/469, loss: 0.2687866687774658
2023-01-24 01:51:51.676254: step: 100/469, loss: 0.17973271012306213
2023-01-24 01:51:52.286023: step: 102/469, loss: 0.44705235958099365
2023-01-24 01:51:52.834778: step: 104/469, loss: 0.40831154584884644
2023-01-24 01:51:53.424598: step: 106/469, loss: 0.16774891316890717
2023-01-24 01:51:54.016105: step: 108/469, loss: 0.1206790879368782
2023-01-24 01:51:54.606020: step: 110/469, loss: 0.22693736851215363
2023-01-24 01:51:55.207769: step: 112/469, loss: 0.37868762016296387
2023-01-24 01:51:55.792882: step: 114/469, loss: 2.0113837718963623
2023-01-24 01:51:56.425596: step: 116/469, loss: 1.5968806743621826
2023-01-24 01:51:57.050526: step: 118/469, loss: 0.6039673686027527
2023-01-24 01:51:57.675431: step: 120/469, loss: 0.877234160900116
2023-01-24 01:51:58.329943: step: 122/469, loss: 0.8293070793151855
2023-01-24 01:51:58.966009: step: 124/469, loss: 0.24055759608745575
2023-01-24 01:51:59.637247: step: 126/469, loss: 0.5461827516555786
2023-01-24 01:52:00.331714: step: 128/469, loss: 0.5503721237182617
2023-01-24 01:52:00.953396: step: 130/469, loss: 0.513506293296814
2023-01-24 01:52:01.609908: step: 132/469, loss: 1.2275398969650269
2023-01-24 01:52:02.247053: step: 134/469, loss: 0.826102614402771
2023-01-24 01:52:02.895613: step: 136/469, loss: 0.38516363501548767
2023-01-24 01:52:03.540633: step: 138/469, loss: 0.4331507384777069
2023-01-24 01:52:04.166457: step: 140/469, loss: 0.17020680010318756
2023-01-24 01:52:04.789368: step: 142/469, loss: 0.6887328624725342
2023-01-24 01:52:05.404940: step: 144/469, loss: 0.13362735509872437
2023-01-24 01:52:06.024305: step: 146/469, loss: 0.49540039896965027
2023-01-24 01:52:06.717024: step: 148/469, loss: 0.26626360416412354
2023-01-24 01:52:07.296585: step: 150/469, loss: 0.36373767256736755
2023-01-24 01:52:07.953835: step: 152/469, loss: 0.40150022506713867
2023-01-24 01:52:08.575501: step: 154/469, loss: 0.3933314085006714
2023-01-24 01:52:09.128390: step: 156/469, loss: 0.2946799397468567
2023-01-24 01:52:09.759779: step: 158/469, loss: 1.396859049797058
2023-01-24 01:52:10.348990: step: 160/469, loss: 0.12313838303089142
2023-01-24 01:52:10.922233: step: 162/469, loss: 0.5091023445129395
2023-01-24 01:52:11.543128: step: 164/469, loss: 0.4060091972351074
2023-01-24 01:52:12.162551: step: 166/469, loss: 0.5097238421440125
2023-01-24 01:52:12.840017: step: 168/469, loss: 0.3354381322860718
2023-01-24 01:52:13.450659: step: 170/469, loss: 0.13180392980575562
2023-01-24 01:52:14.070797: step: 172/469, loss: 0.22569696605205536
2023-01-24 01:52:14.706222: step: 174/469, loss: 0.043637704104185104
2023-01-24 01:52:15.296160: step: 176/469, loss: 1.1725974082946777
2023-01-24 01:52:15.899863: step: 178/469, loss: 0.29839888215065
2023-01-24 01:52:16.444986: step: 180/469, loss: 0.4605640470981598
2023-01-24 01:52:17.071410: step: 182/469, loss: 0.37565863132476807
2023-01-24 01:52:17.702353: step: 184/469, loss: 0.27172836661338806
2023-01-24 01:52:18.307166: step: 186/469, loss: 0.5739880204200745
2023-01-24 01:52:18.885431: step: 188/469, loss: 0.3598175644874573
2023-01-24 01:52:19.523956: step: 190/469, loss: 0.19782230257987976
2023-01-24 01:52:20.193322: step: 192/469, loss: 0.5162298679351807
2023-01-24 01:52:20.795771: step: 194/469, loss: 0.24618904292583466
2023-01-24 01:52:21.371023: step: 196/469, loss: 0.2614660859107971
2023-01-24 01:52:21.931428: step: 198/469, loss: 0.5913073420524597
2023-01-24 01:52:22.554781: step: 200/469, loss: 0.20946751534938812
2023-01-24 01:52:23.165187: step: 202/469, loss: 0.7523478865623474
2023-01-24 01:52:23.857058: step: 204/469, loss: 0.2856263220310211
2023-01-24 01:52:24.431143: step: 206/469, loss: 0.38644376397132874
2023-01-24 01:52:25.024030: step: 208/469, loss: 0.0799332931637764
2023-01-24 01:52:25.682653: step: 210/469, loss: 0.14310799539089203
2023-01-24 01:52:26.252566: step: 212/469, loss: 0.17182767391204834
2023-01-24 01:52:26.871860: step: 214/469, loss: 0.8383781909942627
2023-01-24 01:52:27.529883: step: 216/469, loss: 0.68065345287323
2023-01-24 01:52:28.170361: step: 218/469, loss: 0.48425042629241943
2023-01-24 01:52:28.809643: step: 220/469, loss: 0.29772573709487915
2023-01-24 01:52:29.451521: step: 222/469, loss: 0.1649387776851654
2023-01-24 01:52:30.015197: step: 224/469, loss: 0.5369493365287781
2023-01-24 01:52:30.658663: step: 226/469, loss: 0.45795154571533203
2023-01-24 01:52:31.231906: step: 228/469, loss: 0.15101347863674164
2023-01-24 01:52:31.837521: step: 230/469, loss: 0.22972552478313446
2023-01-24 01:52:32.445561: step: 232/469, loss: 0.269235759973526
2023-01-24 01:52:33.033906: step: 234/469, loss: 0.6715574860572815
2023-01-24 01:52:33.709767: step: 236/469, loss: 0.6828577518463135
2023-01-24 01:52:34.326312: step: 238/469, loss: 0.07857867330312729
2023-01-24 01:52:34.969877: step: 240/469, loss: 0.16601179540157318
2023-01-24 01:52:35.599358: step: 242/469, loss: 0.29657378792762756
2023-01-24 01:52:36.236713: step: 244/469, loss: 0.1468263566493988
2023-01-24 01:52:36.849416: step: 246/469, loss: 0.3764883875846863
2023-01-24 01:52:37.446800: step: 248/469, loss: 0.2938169538974762
2023-01-24 01:52:38.069517: step: 250/469, loss: 0.135310560464859
2023-01-24 01:52:38.737828: step: 252/469, loss: 0.670644998550415
2023-01-24 01:52:39.297723: step: 254/469, loss: 0.2843133807182312
2023-01-24 01:52:39.894897: step: 256/469, loss: 0.5504776835441589
2023-01-24 01:52:40.539488: step: 258/469, loss: 2.205552577972412
2023-01-24 01:52:41.190021: step: 260/469, loss: 0.5212454795837402
2023-01-24 01:52:41.774226: step: 262/469, loss: 0.16184431314468384
2023-01-24 01:52:42.351692: step: 264/469, loss: 0.9438133835792542
2023-01-24 01:52:42.959174: step: 266/469, loss: 0.5826058387756348
2023-01-24 01:52:43.638243: step: 268/469, loss: 0.2877679467201233
2023-01-24 01:52:44.376020: step: 270/469, loss: 0.21185234189033508
2023-01-24 01:52:44.974885: step: 272/469, loss: 0.31699898838996887
2023-01-24 01:52:45.619905: step: 274/469, loss: 0.25983649492263794
2023-01-24 01:52:46.236493: step: 276/469, loss: 0.8715678453445435
2023-01-24 01:52:46.977309: step: 278/469, loss: 0.3698544502258301
2023-01-24 01:52:47.569586: step: 280/469, loss: 0.2095068395137787
2023-01-24 01:52:48.186722: step: 282/469, loss: 0.3880450427532196
2023-01-24 01:52:48.839549: step: 284/469, loss: 0.19999688863754272
2023-01-24 01:52:49.466493: step: 286/469, loss: 0.43148836493492126
2023-01-24 01:52:50.083082: step: 288/469, loss: 0.15177132189273834
2023-01-24 01:52:50.766634: step: 290/469, loss: 0.3301406502723694
2023-01-24 01:52:51.363070: step: 292/469, loss: 0.460880845785141
2023-01-24 01:52:52.069178: step: 294/469, loss: 0.17909863591194153
2023-01-24 01:52:52.717957: step: 296/469, loss: 0.33465319871902466
2023-01-24 01:52:53.338827: step: 298/469, loss: 0.11174724251031876
2023-01-24 01:52:54.009531: step: 300/469, loss: 0.1678203046321869
2023-01-24 01:52:54.651634: step: 302/469, loss: 0.22508102655410767
2023-01-24 01:52:55.273845: step: 304/469, loss: 0.1979251652956009
2023-01-24 01:52:55.850031: step: 306/469, loss: 0.2560000419616699
2023-01-24 01:52:56.457070: step: 308/469, loss: 0.28345680236816406
2023-01-24 01:52:57.104805: step: 310/469, loss: 0.9701858162879944
2023-01-24 01:52:57.705508: step: 312/469, loss: 0.8830705881118774
2023-01-24 01:52:58.421682: step: 314/469, loss: 0.6692978143692017
2023-01-24 01:52:59.051428: step: 316/469, loss: 0.2865965962409973
2023-01-24 01:52:59.627340: step: 318/469, loss: 0.33784371614456177
2023-01-24 01:53:00.342545: step: 320/469, loss: 0.22370503842830658
2023-01-24 01:53:00.916181: step: 322/469, loss: 0.4606347382068634
2023-01-24 01:53:01.546121: step: 324/469, loss: 0.23428668081760406
2023-01-24 01:53:02.172519: step: 326/469, loss: 0.09276342391967773
2023-01-24 01:53:02.837326: step: 328/469, loss: 0.5830388069152832
2023-01-24 01:53:03.524848: step: 330/469, loss: 1.0051289796829224
2023-01-24 01:53:04.228934: step: 332/469, loss: 0.30512693524360657
2023-01-24 01:53:04.904499: step: 334/469, loss: 0.2026054561138153
2023-01-24 01:53:05.554653: step: 336/469, loss: 0.18126386404037476
2023-01-24 01:53:06.229992: step: 338/469, loss: 0.23084834218025208
2023-01-24 01:53:06.811580: step: 340/469, loss: 0.13632763922214508
2023-01-24 01:53:07.426391: step: 342/469, loss: 0.39497995376586914
2023-01-24 01:53:08.052499: step: 344/469, loss: 0.16630469262599945
2023-01-24 01:53:08.710388: step: 346/469, loss: 0.2959747910499573
2023-01-24 01:53:09.339911: step: 348/469, loss: 0.10582728683948517
2023-01-24 01:53:09.951781: step: 350/469, loss: 0.7902545928955078
2023-01-24 01:53:10.591454: step: 352/469, loss: 0.785956084728241
2023-01-24 01:53:11.289885: step: 354/469, loss: 0.438224732875824
2023-01-24 01:53:11.948315: step: 356/469, loss: 0.18054988980293274
2023-01-24 01:53:12.514220: step: 358/469, loss: 0.19129571318626404
2023-01-24 01:53:13.147950: step: 360/469, loss: 0.21083766222000122
2023-01-24 01:53:13.781001: step: 362/469, loss: 0.6799478530883789
2023-01-24 01:53:14.276391: step: 364/469, loss: 0.32006406784057617
2023-01-24 01:53:14.922951: step: 366/469, loss: 5.038124084472656
2023-01-24 01:53:15.512859: step: 368/469, loss: 0.5870373249053955
2023-01-24 01:53:16.131736: step: 370/469, loss: 0.3491811454296112
2023-01-24 01:53:16.756989: step: 372/469, loss: 0.49556946754455566
2023-01-24 01:53:17.387717: step: 374/469, loss: 0.5719321966171265
2023-01-24 01:53:18.039858: step: 376/469, loss: 0.25649404525756836
2023-01-24 01:53:18.700991: step: 378/469, loss: 0.46808499097824097
2023-01-24 01:53:19.319659: step: 380/469, loss: 0.8488327264785767
2023-01-24 01:53:19.921244: step: 382/469, loss: 0.42529749870300293
2023-01-24 01:53:20.520970: step: 384/469, loss: 0.1451246738433838
2023-01-24 01:53:21.131968: step: 386/469, loss: 0.4919374883174896
2023-01-24 01:53:21.795900: step: 388/469, loss: 0.13510015606880188
2023-01-24 01:53:22.418035: step: 390/469, loss: 0.21749433875083923
2023-01-24 01:53:23.008596: step: 392/469, loss: 0.13819032907485962
2023-01-24 01:53:23.629796: step: 394/469, loss: 0.2085658311843872
2023-01-24 01:53:24.256773: step: 396/469, loss: 0.5387779474258423
2023-01-24 01:53:24.873021: step: 398/469, loss: 0.574633777141571
2023-01-24 01:53:25.462908: step: 400/469, loss: 0.2833281457424164
2023-01-24 01:53:26.072838: step: 402/469, loss: 0.23054522275924683
2023-01-24 01:53:26.630066: step: 404/469, loss: 0.22763407230377197
2023-01-24 01:53:27.276829: step: 406/469, loss: 0.5856924057006836
2023-01-24 01:53:27.814952: step: 408/469, loss: 0.1854855865240097
2023-01-24 01:53:28.414269: step: 410/469, loss: 1.0070726871490479
2023-01-24 01:53:28.997933: step: 412/469, loss: 0.27506905794143677
2023-01-24 01:53:29.610510: step: 414/469, loss: 0.23910748958587646
2023-01-24 01:53:30.260840: step: 416/469, loss: 0.5609286427497864
2023-01-24 01:53:30.890944: step: 418/469, loss: 0.1637156754732132
2023-01-24 01:53:31.436252: step: 420/469, loss: 0.22534653544425964
2023-01-24 01:53:32.053359: step: 422/469, loss: 1.2738531827926636
2023-01-24 01:53:32.648606: step: 424/469, loss: 0.5713269114494324
2023-01-24 01:53:33.241599: step: 426/469, loss: 0.4196932017803192
2023-01-24 01:53:33.818882: step: 428/469, loss: 0.19753192365169525
2023-01-24 01:53:34.483537: step: 430/469, loss: 0.2704198360443115
2023-01-24 01:53:35.131585: step: 432/469, loss: 0.2068815976381302
2023-01-24 01:53:35.755341: step: 434/469, loss: 0.7152396440505981
2023-01-24 01:53:36.383140: step: 436/469, loss: 0.760033905506134
2023-01-24 01:53:37.035654: step: 438/469, loss: 0.8266289830207825
2023-01-24 01:53:37.623781: step: 440/469, loss: 0.2040933072566986
2023-01-24 01:53:38.301713: step: 442/469, loss: 0.19095304608345032
2023-01-24 01:53:38.878696: step: 444/469, loss: 0.25177013874053955
2023-01-24 01:53:39.569971: step: 446/469, loss: 0.7534641623497009
2023-01-24 01:53:40.168758: step: 448/469, loss: 0.19340673089027405
2023-01-24 01:53:40.804409: step: 450/469, loss: 0.1908774971961975
2023-01-24 01:53:41.487410: step: 452/469, loss: 0.2998519241809845
2023-01-24 01:53:42.125398: step: 454/469, loss: 0.34291404485702515
2023-01-24 01:53:42.745780: step: 456/469, loss: 0.18961063027381897
2023-01-24 01:53:43.399279: step: 458/469, loss: 0.2002243995666504
2023-01-24 01:53:43.999635: step: 460/469, loss: 0.30675777792930603
2023-01-24 01:53:44.583946: step: 462/469, loss: 0.1929704248905182
2023-01-24 01:53:45.189275: step: 464/469, loss: 0.3591207265853882
2023-01-24 01:53:45.813798: step: 466/469, loss: 0.13202813267707825
2023-01-24 01:53:46.438433: step: 468/469, loss: 0.7541679739952087
2023-01-24 01:53:47.059419: step: 470/469, loss: 1.4168643951416016
2023-01-24 01:53:47.681351: step: 472/469, loss: 0.5182743072509766
2023-01-24 01:53:48.309900: step: 474/469, loss: 0.7530785202980042
2023-01-24 01:53:48.852009: step: 476/469, loss: 0.5371955037117004
2023-01-24 01:53:49.456633: step: 478/469, loss: 0.156224325299263
2023-01-24 01:53:50.070736: step: 480/469, loss: 1.1019047498703003
2023-01-24 01:53:50.633505: step: 482/469, loss: 0.15114130079746246
2023-01-24 01:53:51.335624: step: 484/469, loss: 0.34647971391677856
2023-01-24 01:53:51.998173: step: 486/469, loss: 0.6130858659744263
2023-01-24 01:53:52.565233: step: 488/469, loss: 0.17797544598579407
2023-01-24 01:53:53.164796: step: 490/469, loss: 0.40765994787216187
2023-01-24 01:53:53.890859: step: 492/469, loss: 0.3031141459941864
2023-01-24 01:53:54.546742: step: 494/469, loss: 0.1624971181154251
2023-01-24 01:53:55.223708: step: 496/469, loss: 0.20007124543190002
2023-01-24 01:53:55.852920: step: 498/469, loss: 0.9323029518127441
2023-01-24 01:53:56.517827: step: 500/469, loss: 0.3443988263607025
2023-01-24 01:53:57.103812: step: 502/469, loss: 0.11479859799146652
2023-01-24 01:53:57.746090: step: 504/469, loss: 0.9197838306427002
2023-01-24 01:53:58.414249: step: 506/469, loss: 1.08487069606781
2023-01-24 01:53:59.029176: step: 508/469, loss: 0.4270364046096802
2023-01-24 01:53:59.635172: step: 510/469, loss: 0.2636466920375824
2023-01-24 01:54:00.237014: step: 512/469, loss: 0.6892208456993103
2023-01-24 01:54:00.945206: step: 514/469, loss: 0.10705716162919998
2023-01-24 01:54:01.705898: step: 516/469, loss: 1.1481060981750488
2023-01-24 01:54:02.264358: step: 518/469, loss: 0.34143489599227905
2023-01-24 01:54:02.842853: step: 520/469, loss: 0.6894757151603699
2023-01-24 01:54:03.498989: step: 522/469, loss: 0.5917198657989502
2023-01-24 01:54:04.156968: step: 524/469, loss: 0.2364565134048462
2023-01-24 01:54:04.748429: step: 526/469, loss: 0.11821852624416351
2023-01-24 01:54:05.477754: step: 528/469, loss: 0.9814774394035339
2023-01-24 01:54:06.122549: step: 530/469, loss: 0.4304909110069275
2023-01-24 01:54:06.759911: step: 532/469, loss: 0.1012810468673706
2023-01-24 01:54:07.382247: step: 534/469, loss: 0.4052692949771881
2023-01-24 01:54:08.008246: step: 536/469, loss: 0.24921931326389313
2023-01-24 01:54:08.720828: step: 538/469, loss: 0.13539421558380127
2023-01-24 01:54:09.316284: step: 540/469, loss: 0.3716905415058136
2023-01-24 01:54:09.909149: step: 542/469, loss: 0.32280153036117554
2023-01-24 01:54:10.560434: step: 544/469, loss: 0.06774081289768219
2023-01-24 01:54:11.193967: step: 546/469, loss: 0.18182620406150818
2023-01-24 01:54:11.905991: step: 548/469, loss: 0.26528051495552063
2023-01-24 01:54:12.555057: step: 550/469, loss: 0.2427050769329071
2023-01-24 01:54:13.189640: step: 552/469, loss: 0.2890981137752533
2023-01-24 01:54:13.825524: step: 554/469, loss: 1.08097243309021
2023-01-24 01:54:14.487147: step: 556/469, loss: 0.14689016342163086
2023-01-24 01:54:15.160334: step: 558/469, loss: 0.1632222980260849
2023-01-24 01:54:15.771780: step: 560/469, loss: 0.25574785470962524
2023-01-24 01:54:16.387682: step: 562/469, loss: 0.5995178818702698
2023-01-24 01:54:16.934015: step: 564/469, loss: 0.1721377968788147
2023-01-24 01:54:17.591695: step: 566/469, loss: 1.2596428394317627
2023-01-24 01:54:18.212133: step: 568/469, loss: 0.2343950867652893
2023-01-24 01:54:18.854721: step: 570/469, loss: 0.24954719841480255
2023-01-24 01:54:19.478188: step: 572/469, loss: 0.5721375942230225
2023-01-24 01:54:20.081018: step: 574/469, loss: 0.5895306468009949
2023-01-24 01:54:20.701024: step: 576/469, loss: 0.1783619225025177
2023-01-24 01:54:21.284584: step: 578/469, loss: 0.2190074622631073
2023-01-24 01:54:21.933175: step: 580/469, loss: 0.1833002269268036
2023-01-24 01:54:22.552152: step: 582/469, loss: 0.27503082156181335
2023-01-24 01:54:23.191140: step: 584/469, loss: 0.3686704635620117
2023-01-24 01:54:23.871759: step: 586/469, loss: 0.2426997572183609
2023-01-24 01:54:24.508506: step: 588/469, loss: 1.4560201168060303
2023-01-24 01:54:25.122400: step: 590/469, loss: 0.41090160608291626
2023-01-24 01:54:25.787005: step: 592/469, loss: 0.7190005779266357
2023-01-24 01:54:26.411442: step: 594/469, loss: 0.2541142404079437
2023-01-24 01:54:27.017963: step: 596/469, loss: 1.2114495038986206
2023-01-24 01:54:27.672403: step: 598/469, loss: 0.43150845170021057
2023-01-24 01:54:28.326707: step: 600/469, loss: 0.16728082299232483
2023-01-24 01:54:29.043352: step: 602/469, loss: 0.32608771324157715
2023-01-24 01:54:29.724732: step: 604/469, loss: 0.8031672835350037
2023-01-24 01:54:30.288391: step: 606/469, loss: 0.46160343289375305
2023-01-24 01:54:30.898403: step: 608/469, loss: 0.5382565259933472
2023-01-24 01:54:31.534303: step: 610/469, loss: 0.5774716138839722
2023-01-24 01:54:32.141630: step: 612/469, loss: 0.6985758543014526
2023-01-24 01:54:32.704105: step: 614/469, loss: 0.5699069499969482
2023-01-24 01:54:33.255416: step: 616/469, loss: 0.39563262462615967
2023-01-24 01:54:33.859441: step: 618/469, loss: 0.31927981972694397
2023-01-24 01:54:34.491636: step: 620/469, loss: 0.16570867598056793
2023-01-24 01:54:35.109256: step: 622/469, loss: 0.19120311737060547
2023-01-24 01:54:35.771941: step: 624/469, loss: 1.4697961807250977
2023-01-24 01:54:36.420875: step: 626/469, loss: 0.5406908392906189
2023-01-24 01:54:37.086466: step: 628/469, loss: 0.34849169850349426
2023-01-24 01:54:37.730303: step: 630/469, loss: 0.09745623916387558
2023-01-24 01:54:38.319574: step: 632/469, loss: 0.20540249347686768
2023-01-24 01:54:38.914101: step: 634/469, loss: 0.4506654143333435
2023-01-24 01:54:39.528712: step: 636/469, loss: 0.47304269671440125
2023-01-24 01:54:40.149818: step: 638/469, loss: 0.28370389342308044
2023-01-24 01:54:40.777549: step: 640/469, loss: 0.10397260636091232
2023-01-24 01:54:41.437813: step: 642/469, loss: 0.16313014924526215
2023-01-24 01:54:42.197387: step: 644/469, loss: 0.614755392074585
2023-01-24 01:54:42.857046: step: 646/469, loss: 0.19631730020046234
2023-01-24 01:54:43.446972: step: 648/469, loss: 1.504908800125122
2023-01-24 01:54:44.065586: step: 650/469, loss: 0.2620968222618103
2023-01-24 01:54:44.735505: step: 652/469, loss: 0.20982445776462555
2023-01-24 01:54:45.337687: step: 654/469, loss: 0.35562485456466675
2023-01-24 01:54:45.965906: step: 656/469, loss: 0.1485298126935959
2023-01-24 01:54:46.586185: step: 658/469, loss: 0.16371245682239532
2023-01-24 01:54:47.203181: step: 660/469, loss: 0.4689534306526184
2023-01-24 01:54:47.875769: step: 662/469, loss: 0.6594911813735962
2023-01-24 01:54:48.505353: step: 664/469, loss: 0.10823681950569153
2023-01-24 01:54:49.208203: step: 666/469, loss: 0.30061373114585876
2023-01-24 01:54:49.862703: step: 668/469, loss: 0.8325690627098083
2023-01-24 01:54:50.520297: step: 670/469, loss: 0.4599584937095642
2023-01-24 01:54:51.072463: step: 672/469, loss: 0.5109724998474121
2023-01-24 01:54:51.688179: step: 674/469, loss: 0.643949568271637
2023-01-24 01:54:52.382560: step: 676/469, loss: 0.19060009717941284
2023-01-24 01:54:53.022332: step: 678/469, loss: 0.1913621574640274
2023-01-24 01:54:53.730212: step: 680/469, loss: 0.22661826014518738
2023-01-24 01:54:54.360552: step: 682/469, loss: 0.5973053574562073
2023-01-24 01:54:55.031457: step: 684/469, loss: 0.253712922334671
2023-01-24 01:54:55.684585: step: 686/469, loss: 0.47143083810806274
2023-01-24 01:54:56.279417: step: 688/469, loss: 0.3521772623062134
2023-01-24 01:54:56.822790: step: 690/469, loss: 0.0996263399720192
2023-01-24 01:54:57.436603: step: 692/469, loss: 0.1923132985830307
2023-01-24 01:54:58.055395: step: 694/469, loss: 0.3770560026168823
2023-01-24 01:54:58.798572: step: 696/469, loss: 0.24515292048454285
2023-01-24 01:54:59.439535: step: 698/469, loss: 0.17921769618988037
2023-01-24 01:55:00.079966: step: 700/469, loss: 0.25507134199142456
2023-01-24 01:55:00.639866: step: 702/469, loss: 0.3950207829475403
2023-01-24 01:55:01.301094: step: 704/469, loss: 0.16794122755527496
2023-01-24 01:55:01.997941: step: 706/469, loss: 0.26940253376960754
2023-01-24 01:55:02.706445: step: 708/469, loss: 0.8904720544815063
2023-01-24 01:55:03.333849: step: 710/469, loss: 0.2583911716938019
2023-01-24 01:55:03.978731: step: 712/469, loss: 0.4519367218017578
2023-01-24 01:55:04.685155: step: 714/469, loss: 0.4631194770336151
2023-01-24 01:55:05.469454: step: 716/469, loss: 0.484460711479187
2023-01-24 01:55:06.079098: step: 718/469, loss: 0.2521439492702484
2023-01-24 01:55:06.803165: step: 720/469, loss: 0.2882177531719208
2023-01-24 01:55:07.461352: step: 722/469, loss: 0.35357216000556946
2023-01-24 01:55:08.088702: step: 724/469, loss: 0.3042793869972229
2023-01-24 01:55:08.670349: step: 726/469, loss: 0.1204552948474884
2023-01-24 01:55:09.336479: step: 728/469, loss: 0.532158374786377
2023-01-24 01:55:09.953516: step: 730/469, loss: 0.2990210950374603
2023-01-24 01:55:10.552366: step: 732/469, loss: 1.4791412353515625
2023-01-24 01:55:11.210849: step: 734/469, loss: 0.34803155064582825
2023-01-24 01:55:11.891624: step: 736/469, loss: 0.2030235081911087
2023-01-24 01:55:12.583136: step: 738/469, loss: 1.250240445137024
2023-01-24 01:55:13.187578: step: 740/469, loss: 0.24611452221870422
2023-01-24 01:55:13.833956: step: 742/469, loss: 0.226565420627594
2023-01-24 01:55:14.525325: step: 744/469, loss: 0.47330066561698914
2023-01-24 01:55:15.159648: step: 746/469, loss: 0.710346519947052
2023-01-24 01:55:15.777944: step: 748/469, loss: 0.8516194820404053
2023-01-24 01:55:16.421235: step: 750/469, loss: 0.6422107815742493
2023-01-24 01:55:17.106122: step: 752/469, loss: 1.0098201036453247
2023-01-24 01:55:17.767821: step: 754/469, loss: 0.6223190426826477
2023-01-24 01:55:18.360451: step: 756/469, loss: 0.5177649855613708
2023-01-24 01:55:18.997718: step: 758/469, loss: 0.39691728353500366
2023-01-24 01:55:19.569732: step: 760/469, loss: 0.4080984890460968
2023-01-24 01:55:20.259150: step: 762/469, loss: 0.383847177028656
2023-01-24 01:55:20.874816: step: 764/469, loss: 0.2949841022491455
2023-01-24 01:55:21.467999: step: 766/469, loss: 0.33717209100723267
2023-01-24 01:55:22.104654: step: 768/469, loss: 0.27422723174095154
2023-01-24 01:55:22.644293: step: 770/469, loss: 0.32133570313453674
2023-01-24 01:55:23.273390: step: 772/469, loss: 0.3171902000904083
2023-01-24 01:55:23.907650: step: 774/469, loss: 0.2577151358127594
2023-01-24 01:55:24.517336: step: 776/469, loss: 0.09333942085504532
2023-01-24 01:55:25.181860: step: 778/469, loss: 0.3875003457069397
2023-01-24 01:55:25.774865: step: 780/469, loss: 0.2966225743293762
2023-01-24 01:55:26.412705: step: 782/469, loss: 1.2088453769683838
2023-01-24 01:55:27.016619: step: 784/469, loss: 0.23390939831733704
2023-01-24 01:55:27.650873: step: 786/469, loss: 0.27754467725753784
2023-01-24 01:55:28.234119: step: 788/469, loss: 0.40995508432388306
2023-01-24 01:55:28.863994: step: 790/469, loss: 0.3927914798259735
2023-01-24 01:55:29.480848: step: 792/469, loss: 0.4827421307563782
2023-01-24 01:55:30.057569: step: 794/469, loss: 0.10398051887750626
2023-01-24 01:55:30.762645: step: 796/469, loss: 0.2812942862510681
2023-01-24 01:55:31.402569: step: 798/469, loss: 0.23930960893630981
2023-01-24 01:55:32.044531: step: 800/469, loss: 0.6100246906280518
2023-01-24 01:55:32.686848: step: 802/469, loss: 0.29489901661872864
2023-01-24 01:55:33.323929: step: 804/469, loss: 0.5952594876289368
2023-01-24 01:55:34.027390: step: 806/469, loss: 0.6478204727172852
2023-01-24 01:55:34.738308: step: 808/469, loss: 0.24434375762939453
2023-01-24 01:55:35.428912: step: 810/469, loss: 0.45539042353630066
2023-01-24 01:55:36.056670: step: 812/469, loss: 0.3725740909576416
2023-01-24 01:55:36.700820: step: 814/469, loss: 0.7191227674484253
2023-01-24 01:55:37.357559: step: 816/469, loss: 0.11773187667131424
2023-01-24 01:55:37.972270: step: 818/469, loss: 0.7031224966049194
2023-01-24 01:55:38.579526: step: 820/469, loss: 0.14404354989528656
2023-01-24 01:55:39.250380: step: 822/469, loss: 1.1291322708129883
2023-01-24 01:55:39.873334: step: 824/469, loss: 0.14968664944171906
2023-01-24 01:55:40.479708: step: 826/469, loss: 0.17701198160648346
2023-01-24 01:55:41.284313: step: 828/469, loss: 0.2988724708557129
2023-01-24 01:55:41.911944: step: 830/469, loss: 0.19408518075942993
2023-01-24 01:55:42.637338: step: 832/469, loss: 0.9875146150588989
2023-01-24 01:55:43.262701: step: 834/469, loss: 0.6374933123588562
2023-01-24 01:55:43.864458: step: 836/469, loss: 0.510638415813446
2023-01-24 01:55:44.483198: step: 838/469, loss: 0.10488545149564743
2023-01-24 01:55:45.131438: step: 840/469, loss: 0.15842315554618835
2023-01-24 01:55:45.921712: step: 842/469, loss: 0.4394344091415405
2023-01-24 01:55:46.533985: step: 844/469, loss: 0.1641053408384323
2023-01-24 01:55:47.203072: step: 846/469, loss: 0.6463753581047058
2023-01-24 01:55:47.814770: step: 848/469, loss: 0.1366187334060669
2023-01-24 01:55:48.435898: step: 850/469, loss: 2.8138809204101562
2023-01-24 01:55:49.058794: step: 852/469, loss: 1.6097359657287598
2023-01-24 01:55:49.775931: step: 854/469, loss: 0.5740014314651489
2023-01-24 01:55:50.369998: step: 856/469, loss: 0.20026065409183502
2023-01-24 01:55:50.970912: step: 858/469, loss: 0.6817509531974792
2023-01-24 01:55:51.654704: step: 860/469, loss: 0.22292299568653107
2023-01-24 01:55:52.312901: step: 862/469, loss: 0.12401055544614792
2023-01-24 01:55:52.897677: step: 864/469, loss: 0.7487518787384033
2023-01-24 01:55:53.485231: step: 866/469, loss: 0.5284701585769653
2023-01-24 01:55:54.139022: step: 868/469, loss: 0.280505895614624
2023-01-24 01:55:54.769718: step: 870/469, loss: 0.24373166263103485
2023-01-24 01:55:55.468635: step: 872/469, loss: 0.16333827376365662
2023-01-24 01:55:56.132211: step: 874/469, loss: 0.5490494966506958
2023-01-24 01:55:56.804943: step: 876/469, loss: 0.2833230197429657
2023-01-24 01:55:57.456204: step: 878/469, loss: 0.8896983861923218
2023-01-24 01:55:58.083831: step: 880/469, loss: 0.324676513671875
2023-01-24 01:55:58.770008: step: 882/469, loss: 0.42407119274139404
2023-01-24 01:55:59.404969: step: 884/469, loss: 0.29535263776779175
2023-01-24 01:56:00.110854: step: 886/469, loss: 0.4275474548339844
2023-01-24 01:56:00.777595: step: 888/469, loss: 0.5988882184028625
2023-01-24 01:56:01.400335: step: 890/469, loss: 0.7113070487976074
2023-01-24 01:56:02.079467: step: 892/469, loss: 0.6220961809158325
2023-01-24 01:56:02.706502: step: 894/469, loss: 0.6407210230827332
2023-01-24 01:56:03.427038: step: 896/469, loss: 0.25663474202156067
2023-01-24 01:56:04.011008: step: 898/469, loss: 0.7068220376968384
2023-01-24 01:56:04.690163: step: 900/469, loss: 0.266611248254776
2023-01-24 01:56:05.283649: step: 902/469, loss: 0.5101432800292969
2023-01-24 01:56:05.926463: step: 904/469, loss: 0.14897340536117554
2023-01-24 01:56:06.519910: step: 906/469, loss: 0.3603914678096771
2023-01-24 01:56:07.165928: step: 908/469, loss: 0.5295233726501465
2023-01-24 01:56:07.851393: step: 910/469, loss: 0.17674796283245087
2023-01-24 01:56:08.476605: step: 912/469, loss: 0.3394225835800171
2023-01-24 01:56:09.124310: step: 914/469, loss: 0.4201357960700989
2023-01-24 01:56:09.765157: step: 916/469, loss: 0.5441609025001526
2023-01-24 01:56:10.357155: step: 918/469, loss: 0.2413608580827713
2023-01-24 01:56:11.005949: step: 920/469, loss: 2.331967353820801
2023-01-24 01:56:11.708259: step: 922/469, loss: 0.4835992753505707
2023-01-24 01:56:12.324465: step: 924/469, loss: 0.47907790541648865
2023-01-24 01:56:12.987038: step: 926/469, loss: 1.3020224571228027
2023-01-24 01:56:13.580858: step: 928/469, loss: 0.3140222132205963
2023-01-24 01:56:14.221406: step: 930/469, loss: 0.8970685005187988
2023-01-24 01:56:14.933223: step: 932/469, loss: 0.29329001903533936
2023-01-24 01:56:15.534960: step: 934/469, loss: 0.35678309202194214
2023-01-24 01:56:16.131255: step: 936/469, loss: 0.5961318612098694
2023-01-24 01:56:16.778504: step: 938/469, loss: 0.22860561311244965
==================================================
Loss: 0.447
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3275157743200196, 'r': 0.32938019049261935, 'f1': 0.3284453365933972}, 'combined': 0.24201235327934528, 'epoch': 8}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3201878107012035, 'r': 0.24607297437237963, 'f1': 0.278280145875852}, 'combined': 0.15178917047773743, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32702587047099246, 'r': 0.3307491251632618, 'f1': 0.32887696030384717}, 'combined': 0.24233039180283475, 'epoch': 8}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3138148407354916, 'r': 0.24490764789329766, 'f1': 0.2751120854546499}, 'combined': 0.15006113752071812, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32323000073235036, 'r': 0.32629669903151876, 'f1': 0.32475611027310747}, 'combined': 0.23929397599071076, 'epoch': 8}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.30979716441293786, 'r': 0.24375623183451653, 'f1': 0.2728372364517425}, 'combined': 0.14882031079185953, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3055555555555555, 'r': 0.28809523809523807, 'f1': 0.2965686274509804}, 'combined': 0.1977124183006536, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2638888888888889, 'r': 0.20652173913043478, 'f1': 0.23170731707317074}, 'combined': 0.11585365853658537, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.475, 'r': 0.16379310344827586, 'f1': 0.24358974358974356}, 'combined': 0.16239316239316237, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35179640393089057, 'r': 0.2990603206091821, 'f1': 0.32329187479187477}, 'combined': 0.23821506563611825, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31941825131851476, 'r': 0.2185954729974831, 'f1': 0.2595598609301999}, 'combined': 0.14157810596192721, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.33695652173913043, 'r': 0.33695652173913043, 'f1': 0.33695652173913043}, 'combined': 0.16847826086956522, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 01:59:02.926624: step: 2/469, loss: 0.39117011427879333
2023-01-24 01:59:03.525506: step: 4/469, loss: 0.0922774225473404
2023-01-24 01:59:04.176854: step: 6/469, loss: 0.2141404002904892
2023-01-24 01:59:04.818972: step: 8/469, loss: 0.13863630592823029
2023-01-24 01:59:05.437574: step: 10/469, loss: 0.29343122243881226
2023-01-24 01:59:06.135118: step: 12/469, loss: 0.23387955129146576
2023-01-24 01:59:06.726157: step: 14/469, loss: 0.6630819439888
2023-01-24 01:59:07.366070: step: 16/469, loss: 0.20282596349716187
2023-01-24 01:59:08.033080: step: 18/469, loss: 0.07033102214336395
2023-01-24 01:59:08.668410: step: 20/469, loss: 0.9723142981529236
2023-01-24 01:59:09.405596: step: 22/469, loss: 0.13188546895980835
2023-01-24 01:59:10.024009: step: 24/469, loss: 0.17766205966472626
2023-01-24 01:59:10.623521: step: 26/469, loss: 0.1398642510175705
2023-01-24 01:59:11.257681: step: 28/469, loss: 0.19310599565505981
2023-01-24 01:59:11.885475: step: 30/469, loss: 0.22215953469276428
2023-01-24 01:59:12.487013: step: 32/469, loss: 0.4158446192741394
2023-01-24 01:59:13.264688: step: 34/469, loss: 0.26109573245048523
2023-01-24 01:59:13.902369: step: 36/469, loss: 0.6764843463897705
2023-01-24 01:59:14.580805: step: 38/469, loss: 0.18109768629074097
2023-01-24 01:59:15.155034: step: 40/469, loss: 0.4471879303455353
2023-01-24 01:59:15.763097: step: 42/469, loss: 0.025926098227500916
2023-01-24 01:59:16.403259: step: 44/469, loss: 0.1759929656982422
2023-01-24 01:59:17.024576: step: 46/469, loss: 0.9183593988418579
2023-01-24 01:59:17.661985: step: 48/469, loss: 0.23044739663600922
2023-01-24 01:59:18.304119: step: 50/469, loss: 0.08991853892803192
2023-01-24 01:59:18.932066: step: 52/469, loss: 1.2173129320144653
2023-01-24 01:59:19.503697: step: 54/469, loss: 0.20458266139030457
2023-01-24 01:59:20.143443: step: 56/469, loss: 0.07910409569740295
2023-01-24 01:59:20.737734: step: 58/469, loss: 1.1281652450561523
2023-01-24 01:59:21.454797: step: 60/469, loss: 0.16504903137683868
2023-01-24 01:59:22.106314: step: 62/469, loss: 0.4823247492313385
2023-01-24 01:59:22.700392: step: 64/469, loss: 0.3919984698295593
2023-01-24 01:59:23.290074: step: 66/469, loss: 0.08961279690265656
2023-01-24 01:59:23.926049: step: 68/469, loss: 0.44954511523246765
2023-01-24 01:59:24.531704: step: 70/469, loss: 0.11863629519939423
2023-01-24 01:59:25.178455: step: 72/469, loss: 0.47804224491119385
2023-01-24 01:59:25.839002: step: 74/469, loss: 0.23678982257843018
2023-01-24 01:59:26.445265: step: 76/469, loss: 0.21039217710494995
2023-01-24 01:59:27.034061: step: 78/469, loss: 0.13153764605522156
2023-01-24 01:59:27.653723: step: 80/469, loss: 0.31582456827163696
2023-01-24 01:59:28.300615: step: 82/469, loss: 0.09279027581214905
2023-01-24 01:59:29.013763: step: 84/469, loss: 1.699034333229065
2023-01-24 01:59:29.635156: step: 86/469, loss: 0.10394525527954102
2023-01-24 01:59:30.287088: step: 88/469, loss: 0.3462316691875458
2023-01-24 01:59:30.912065: step: 90/469, loss: 0.22357968986034393
2023-01-24 01:59:31.539627: step: 92/469, loss: 0.14341087639331818
2023-01-24 01:59:32.218464: step: 94/469, loss: 0.21398556232452393
2023-01-24 01:59:32.818760: step: 96/469, loss: 0.5410624146461487
2023-01-24 01:59:33.484818: step: 98/469, loss: 0.5251842141151428
2023-01-24 01:59:34.113491: step: 100/469, loss: 0.8311374187469482
2023-01-24 01:59:34.727896: step: 102/469, loss: 0.15862813591957092
2023-01-24 01:59:35.379832: step: 104/469, loss: 0.18727891147136688
2023-01-24 01:59:36.012042: step: 106/469, loss: 0.4002154767513275
2023-01-24 01:59:36.650481: step: 108/469, loss: 0.37686851620674133
2023-01-24 01:59:37.281755: step: 110/469, loss: 0.3620848059654236
2023-01-24 01:59:37.891660: step: 112/469, loss: 0.3019811511039734
2023-01-24 01:59:38.514709: step: 114/469, loss: 0.28944191336631775
2023-01-24 01:59:39.235120: step: 116/469, loss: 0.19414857029914856
2023-01-24 01:59:39.851172: step: 118/469, loss: 0.4151228368282318
2023-01-24 01:59:40.474438: step: 120/469, loss: 0.11766630411148071
2023-01-24 01:59:41.100469: step: 122/469, loss: 0.0966775119304657
2023-01-24 01:59:41.733098: step: 124/469, loss: 0.2307339906692505
2023-01-24 01:59:42.389911: step: 126/469, loss: 0.07661121338605881
2023-01-24 01:59:43.057261: step: 128/469, loss: 1.253353238105774
2023-01-24 01:59:43.633885: step: 130/469, loss: 0.3100510835647583
2023-01-24 01:59:44.220123: step: 132/469, loss: 0.07813211530447006
2023-01-24 01:59:44.866920: step: 134/469, loss: 0.5194969773292542
2023-01-24 01:59:45.517140: step: 136/469, loss: 0.22474873065948486
2023-01-24 01:59:46.117634: step: 138/469, loss: 0.8398063778877258
2023-01-24 01:59:46.708225: step: 140/469, loss: 0.18400143086910248
2023-01-24 01:59:47.357048: step: 142/469, loss: 0.12026840448379517
2023-01-24 01:59:48.004041: step: 144/469, loss: 0.44883477687835693
2023-01-24 01:59:48.565347: step: 146/469, loss: 0.13671113550662994
2023-01-24 01:59:49.154603: step: 148/469, loss: 0.271941214799881
2023-01-24 01:59:49.876803: step: 150/469, loss: 0.19189752638339996
2023-01-24 01:59:50.433303: step: 152/469, loss: 0.30071648955345154
2023-01-24 01:59:51.082896: step: 154/469, loss: 0.34274008870124817
2023-01-24 01:59:51.721807: step: 156/469, loss: 0.1937110424041748
2023-01-24 01:59:52.384749: step: 158/469, loss: 0.1706651747226715
2023-01-24 01:59:53.025334: step: 160/469, loss: 0.315620481967926
2023-01-24 01:59:53.608101: step: 162/469, loss: 0.5146969556808472
2023-01-24 01:59:54.210303: step: 164/469, loss: 0.22744236886501312
2023-01-24 01:59:54.866922: step: 166/469, loss: 0.7629155516624451
2023-01-24 01:59:55.451700: step: 168/469, loss: 0.1929679811000824
2023-01-24 01:59:56.083928: step: 170/469, loss: 0.05950044095516205
2023-01-24 01:59:56.662528: step: 172/469, loss: 0.38969722390174866
2023-01-24 01:59:57.298360: step: 174/469, loss: 0.2708067297935486
2023-01-24 01:59:57.875812: step: 176/469, loss: 0.3015950918197632
2023-01-24 01:59:58.473825: step: 178/469, loss: 0.8002981543540955
2023-01-24 01:59:59.029007: step: 180/469, loss: 0.0946851596236229
2023-01-24 01:59:59.644334: step: 182/469, loss: 0.09820695966482162
2023-01-24 02:00:00.287136: step: 184/469, loss: 1.2328671216964722
2023-01-24 02:00:00.930595: step: 186/469, loss: 0.012314117513597012
2023-01-24 02:00:01.543973: step: 188/469, loss: 0.13698436319828033
2023-01-24 02:00:02.212393: step: 190/469, loss: 0.2808561623096466
2023-01-24 02:00:02.801995: step: 192/469, loss: 0.16265708208084106
2023-01-24 02:00:03.380453: step: 194/469, loss: 0.1761542707681656
2023-01-24 02:00:04.020822: step: 196/469, loss: 0.3574264347553253
2023-01-24 02:00:04.641156: step: 198/469, loss: 0.31109192967414856
2023-01-24 02:00:05.248456: step: 200/469, loss: 0.1486627757549286
2023-01-24 02:00:05.911106: step: 202/469, loss: 0.33616459369659424
2023-01-24 02:00:06.520674: step: 204/469, loss: 0.2765996754169464
2023-01-24 02:00:07.123635: step: 206/469, loss: 0.32589688897132874
2023-01-24 02:00:07.681534: step: 208/469, loss: 0.21071374416351318
2023-01-24 02:00:08.309550: step: 210/469, loss: 0.23598650097846985
2023-01-24 02:00:08.960763: step: 212/469, loss: 0.6158100962638855
2023-01-24 02:00:09.533518: step: 214/469, loss: 0.25500190258026123
2023-01-24 02:00:10.213531: step: 216/469, loss: 0.6955997347831726
2023-01-24 02:00:10.807594: step: 218/469, loss: 0.21698550879955292
2023-01-24 02:00:11.377057: step: 220/469, loss: 0.2044127732515335
2023-01-24 02:00:11.999943: step: 222/469, loss: 0.2289697825908661
2023-01-24 02:00:12.694823: step: 224/469, loss: 0.6374063491821289
2023-01-24 02:00:13.371794: step: 226/469, loss: 0.25750455260276794
2023-01-24 02:00:14.084676: step: 228/469, loss: 0.22121837735176086
2023-01-24 02:00:14.697469: step: 230/469, loss: 0.26868629455566406
2023-01-24 02:00:15.341396: step: 232/469, loss: 0.16197511553764343
2023-01-24 02:00:16.045550: step: 234/469, loss: 0.33671021461486816
2023-01-24 02:00:16.674237: step: 236/469, loss: 0.18029142916202545
2023-01-24 02:00:17.299817: step: 238/469, loss: 0.08106422424316406
2023-01-24 02:00:18.009317: step: 240/469, loss: 0.7172487378120422
2023-01-24 02:00:18.725402: step: 242/469, loss: 0.36248961091041565
2023-01-24 02:00:19.345240: step: 244/469, loss: 0.16364188492298126
2023-01-24 02:00:19.956504: step: 246/469, loss: 0.07686292380094528
2023-01-24 02:00:20.538522: step: 248/469, loss: 0.16886407136917114
2023-01-24 02:00:21.109511: step: 250/469, loss: 0.8551551699638367
2023-01-24 02:00:21.720405: step: 252/469, loss: 1.0002883672714233
2023-01-24 02:00:22.302835: step: 254/469, loss: 0.4218061566352844
2023-01-24 02:00:22.988079: step: 256/469, loss: 0.2653208374977112
2023-01-24 02:00:23.658524: step: 258/469, loss: 0.40442734956741333
2023-01-24 02:00:24.272314: step: 260/469, loss: 0.09808026254177094
2023-01-24 02:00:24.852144: step: 262/469, loss: 0.21416310966014862
2023-01-24 02:00:25.484850: step: 264/469, loss: 0.739740788936615
2023-01-24 02:00:26.103794: step: 266/469, loss: 0.18710766732692719
2023-01-24 02:00:26.806687: step: 268/469, loss: 0.38552895188331604
2023-01-24 02:00:27.385928: step: 270/469, loss: 0.15326951444149017
2023-01-24 02:00:28.047252: step: 272/469, loss: 0.10515882074832916
2023-01-24 02:00:28.707220: step: 274/469, loss: 0.3892996609210968
2023-01-24 02:00:29.251910: step: 276/469, loss: 0.40951618552207947
2023-01-24 02:00:29.883566: step: 278/469, loss: 0.1631772369146347
2023-01-24 02:00:30.564724: step: 280/469, loss: 0.17427664995193481
2023-01-24 02:00:31.196526: step: 282/469, loss: 0.16767585277557373
2023-01-24 02:00:31.811651: step: 284/469, loss: 0.2996757924556732
2023-01-24 02:00:32.456131: step: 286/469, loss: 0.4054833948612213
2023-01-24 02:00:33.085046: step: 288/469, loss: 0.19466261565685272
2023-01-24 02:00:33.668474: step: 290/469, loss: 0.5838653445243835
2023-01-24 02:00:34.308988: step: 292/469, loss: 0.18020103871822357
2023-01-24 02:00:34.912963: step: 294/469, loss: 0.7194074988365173
2023-01-24 02:00:35.556876: step: 296/469, loss: 1.1572341918945312
2023-01-24 02:00:36.169773: step: 298/469, loss: 0.24678093194961548
2023-01-24 02:00:36.815797: step: 300/469, loss: 0.13127844035625458
2023-01-24 02:00:37.457611: step: 302/469, loss: 0.1344376504421234
2023-01-24 02:00:38.029605: step: 304/469, loss: 0.5381799340248108
2023-01-24 02:00:38.670445: step: 306/469, loss: 1.9210658073425293
2023-01-24 02:00:39.286022: step: 308/469, loss: 0.6812648177146912
2023-01-24 02:00:39.877767: step: 310/469, loss: 0.29162102937698364
2023-01-24 02:00:40.478849: step: 312/469, loss: 0.17570732533931732
2023-01-24 02:00:41.158622: step: 314/469, loss: 0.21051527559757233
2023-01-24 02:00:41.837381: step: 316/469, loss: 0.4683579206466675
2023-01-24 02:00:42.494693: step: 318/469, loss: 0.1692407876253128
2023-01-24 02:00:43.096773: step: 320/469, loss: 0.08784981817007065
2023-01-24 02:00:43.710383: step: 322/469, loss: 1.063167691230774
2023-01-24 02:00:44.319060: step: 324/469, loss: 0.09959164261817932
2023-01-24 02:00:45.009926: step: 326/469, loss: 0.126796156167984
2023-01-24 02:00:45.615996: step: 328/469, loss: 0.7276470065116882
2023-01-24 02:00:46.186657: step: 330/469, loss: 0.1952531486749649
2023-01-24 02:00:46.880482: step: 332/469, loss: 0.47737717628479004
2023-01-24 02:00:47.574118: step: 334/469, loss: 1.034452199935913
2023-01-24 02:00:48.199885: step: 336/469, loss: 0.6077302694320679
2023-01-24 02:00:48.818698: step: 338/469, loss: 0.3177364766597748
2023-01-24 02:00:49.419156: step: 340/469, loss: 0.3545728027820587
2023-01-24 02:00:50.053602: step: 342/469, loss: 0.33772382140159607
2023-01-24 02:00:50.700794: step: 344/469, loss: 0.22115831077098846
2023-01-24 02:00:51.298323: step: 346/469, loss: 0.23858800530433655
2023-01-24 02:00:51.968333: step: 348/469, loss: 0.34981250762939453
2023-01-24 02:00:52.602994: step: 350/469, loss: 0.19385243952274323
2023-01-24 02:00:53.180036: step: 352/469, loss: 0.18082115054130554
2023-01-24 02:00:53.835028: step: 354/469, loss: 0.6923066973686218
2023-01-24 02:00:54.479020: step: 356/469, loss: 0.2674540877342224
2023-01-24 02:00:55.110087: step: 358/469, loss: 0.12808631360530853
2023-01-24 02:00:55.772654: step: 360/469, loss: 0.334553599357605
2023-01-24 02:00:56.381982: step: 362/469, loss: 0.39071792364120483
2023-01-24 02:00:57.028924: step: 364/469, loss: 0.6498745083808899
2023-01-24 02:00:57.626336: step: 366/469, loss: 0.48026883602142334
2023-01-24 02:00:58.302608: step: 368/469, loss: 0.13347609341144562
2023-01-24 02:00:58.915594: step: 370/469, loss: 0.38516297936439514
2023-01-24 02:00:59.585138: step: 372/469, loss: 0.48706355690956116
2023-01-24 02:01:00.274560: step: 374/469, loss: 0.23065999150276184
2023-01-24 02:01:00.840781: step: 376/469, loss: 0.21758006513118744
2023-01-24 02:01:01.336299: step: 378/469, loss: 0.3067559599876404
2023-01-24 02:01:02.100941: step: 380/469, loss: 0.34745267033576965
2023-01-24 02:01:02.754673: step: 382/469, loss: 0.20142170786857605
2023-01-24 02:01:03.396804: step: 384/469, loss: 0.20668385922908783
2023-01-24 02:01:04.008176: step: 386/469, loss: 0.18116232752799988
2023-01-24 02:01:04.648133: step: 388/469, loss: 0.4907574951648712
2023-01-24 02:01:05.277598: step: 390/469, loss: 0.6749672889709473
2023-01-24 02:01:05.894030: step: 392/469, loss: 0.21538802981376648
2023-01-24 02:01:06.605450: step: 394/469, loss: 0.2518099546432495
2023-01-24 02:01:07.234658: step: 396/469, loss: 0.23233908414840698
2023-01-24 02:01:07.882715: step: 398/469, loss: 1.26188063621521
2023-01-24 02:01:08.520712: step: 400/469, loss: 0.4455063045024872
2023-01-24 02:01:09.164717: step: 402/469, loss: 0.25249287486076355
2023-01-24 02:01:09.747138: step: 404/469, loss: 0.0908951386809349
2023-01-24 02:01:10.361923: step: 406/469, loss: 0.33772221207618713
2023-01-24 02:01:11.044243: step: 408/469, loss: 0.28536897897720337
2023-01-24 02:01:11.658070: step: 410/469, loss: 0.22849786281585693
2023-01-24 02:01:12.353373: step: 412/469, loss: 0.2997598946094513
2023-01-24 02:01:12.992701: step: 414/469, loss: 0.45876169204711914
2023-01-24 02:01:13.591389: step: 416/469, loss: 3.180163860321045
2023-01-24 02:01:14.225011: step: 418/469, loss: 0.848159670829773
2023-01-24 02:01:14.843061: step: 420/469, loss: 0.08702873438596725
2023-01-24 02:01:15.490099: step: 422/469, loss: 0.5647095441818237
2023-01-24 02:01:16.077699: step: 424/469, loss: 0.1951759159564972
2023-01-24 02:01:16.728020: step: 426/469, loss: 0.5742413401603699
2023-01-24 02:01:17.379552: step: 428/469, loss: 0.481643944978714
2023-01-24 02:01:18.026968: step: 430/469, loss: 0.18370461463928223
2023-01-24 02:01:18.680858: step: 432/469, loss: 6.539400100708008
2023-01-24 02:01:19.344753: step: 434/469, loss: 0.19780448079109192
2023-01-24 02:01:19.983773: step: 436/469, loss: 0.2445353865623474
2023-01-24 02:01:20.700865: step: 438/469, loss: 0.454621821641922
2023-01-24 02:01:21.341867: step: 440/469, loss: 0.182010218501091
2023-01-24 02:01:21.974896: step: 442/469, loss: 1.381121277809143
2023-01-24 02:01:22.612529: step: 444/469, loss: 0.3562524914741516
2023-01-24 02:01:23.207649: step: 446/469, loss: 0.4234894812107086
2023-01-24 02:01:23.795254: step: 448/469, loss: 0.6700560450553894
2023-01-24 02:01:24.484042: step: 450/469, loss: 0.6063768267631531
2023-01-24 02:01:25.130017: step: 452/469, loss: 0.8879229426383972
2023-01-24 02:01:25.781860: step: 454/469, loss: 0.2727753818035126
2023-01-24 02:01:26.372708: step: 456/469, loss: 0.10498542338609695
2023-01-24 02:01:26.971136: step: 458/469, loss: 0.7134118676185608
2023-01-24 02:01:27.669271: step: 460/469, loss: 0.5197572708129883
2023-01-24 02:01:28.317271: step: 462/469, loss: 0.06188105791807175
2023-01-24 02:01:28.923056: step: 464/469, loss: 0.2188866138458252
2023-01-24 02:01:29.596964: step: 466/469, loss: 0.2279590666294098
2023-01-24 02:01:30.273815: step: 468/469, loss: 2.0994179248809814
2023-01-24 02:01:30.889593: step: 470/469, loss: 0.1228613406419754
2023-01-24 02:01:31.513795: step: 472/469, loss: 0.7680542469024658
2023-01-24 02:01:32.142504: step: 474/469, loss: 0.14352768659591675
2023-01-24 02:01:32.692248: step: 476/469, loss: 0.20120570063591003
2023-01-24 02:01:33.274132: step: 478/469, loss: 3.547847270965576
2023-01-24 02:01:33.938491: step: 480/469, loss: 3.7162673473358154
2023-01-24 02:01:34.471481: step: 482/469, loss: 0.5510678291320801
2023-01-24 02:01:35.056556: step: 484/469, loss: 0.3959076702594757
2023-01-24 02:01:35.633329: step: 486/469, loss: 0.10709948092699051
2023-01-24 02:01:36.239298: step: 488/469, loss: 0.12302729487419128
2023-01-24 02:01:36.929669: step: 490/469, loss: 1.2091511487960815
2023-01-24 02:01:37.525038: step: 492/469, loss: 0.15840092301368713
2023-01-24 02:01:38.183804: step: 494/469, loss: 0.5001250505447388
2023-01-24 02:01:38.757881: step: 496/469, loss: 0.33823445439338684
2023-01-24 02:01:39.529120: step: 498/469, loss: 0.28428220748901367
2023-01-24 02:01:40.173713: step: 500/469, loss: 0.5808488130569458
2023-01-24 02:01:40.801171: step: 502/469, loss: 0.51570725440979
2023-01-24 02:01:41.371194: step: 504/469, loss: 0.1313687264919281
2023-01-24 02:01:42.036369: step: 506/469, loss: 0.8132759928703308
2023-01-24 02:01:42.741431: step: 508/469, loss: 1.2488203048706055
2023-01-24 02:01:43.330445: step: 510/469, loss: 0.3761872947216034
2023-01-24 02:01:43.943575: step: 512/469, loss: 0.26774799823760986
2023-01-24 02:01:44.506509: step: 514/469, loss: 0.54317307472229
2023-01-24 02:01:45.095232: step: 516/469, loss: 0.3677058815956116
2023-01-24 02:01:45.721071: step: 518/469, loss: 5.430683135986328
2023-01-24 02:01:46.392544: step: 520/469, loss: 0.0835961401462555
2023-01-24 02:01:46.956160: step: 522/469, loss: 0.5383288264274597
2023-01-24 02:01:47.584406: step: 524/469, loss: 0.34538698196411133
2023-01-24 02:01:48.221831: step: 526/469, loss: 0.2064712792634964
2023-01-24 02:01:48.883962: step: 528/469, loss: 0.1574334055185318
2023-01-24 02:01:49.419763: step: 530/469, loss: 0.6473233103752136
2023-01-24 02:01:50.072064: step: 532/469, loss: 0.4723932445049286
2023-01-24 02:01:50.795253: step: 534/469, loss: 1.2586174011230469
2023-01-24 02:01:51.454747: step: 536/469, loss: 0.11741548031568527
2023-01-24 02:01:52.058389: step: 538/469, loss: 2.808222770690918
2023-01-24 02:01:52.719079: step: 540/469, loss: 0.14677190780639648
2023-01-24 02:01:53.328047: step: 542/469, loss: 0.31913504004478455
2023-01-24 02:01:53.982856: step: 544/469, loss: 0.36843451857566833
2023-01-24 02:01:54.600740: step: 546/469, loss: 0.8397376537322998
2023-01-24 02:01:55.234597: step: 548/469, loss: 0.7211434841156006
2023-01-24 02:01:55.901607: step: 550/469, loss: 0.4781056344509125
2023-01-24 02:01:56.513425: step: 552/469, loss: 0.21089711785316467
2023-01-24 02:01:57.139802: step: 554/469, loss: 0.3777916431427002
2023-01-24 02:01:57.708170: step: 556/469, loss: 0.286102294921875
2023-01-24 02:01:58.346235: step: 558/469, loss: 0.454565167427063
2023-01-24 02:01:58.910813: step: 560/469, loss: 0.38984936475753784
2023-01-24 02:01:59.541646: step: 562/469, loss: 0.549746036529541
2023-01-24 02:02:00.221249: step: 564/469, loss: 0.5132108926773071
2023-01-24 02:02:00.878081: step: 566/469, loss: 0.4313230812549591
2023-01-24 02:02:01.544268: step: 568/469, loss: 0.34913328289985657
2023-01-24 02:02:02.152510: step: 570/469, loss: 0.24797344207763672
2023-01-24 02:02:02.844625: step: 572/469, loss: 0.15785956382751465
2023-01-24 02:02:03.460380: step: 574/469, loss: 0.10448366403579712
2023-01-24 02:02:04.092264: step: 576/469, loss: 0.3704490065574646
2023-01-24 02:02:04.715709: step: 578/469, loss: 0.13047370314598083
2023-01-24 02:02:05.263841: step: 580/469, loss: 0.21161755919456482
2023-01-24 02:02:05.860217: step: 582/469, loss: 0.7316820025444031
2023-01-24 02:02:06.495969: step: 584/469, loss: 0.19775795936584473
2023-01-24 02:02:07.121079: step: 586/469, loss: 0.399997353553772
2023-01-24 02:02:07.726581: step: 588/469, loss: 0.06698208302259445
2023-01-24 02:02:08.381031: step: 590/469, loss: 0.4157121777534485
2023-01-24 02:02:09.013736: step: 592/469, loss: 1.3520870208740234
2023-01-24 02:02:09.648832: step: 594/469, loss: 0.39281463623046875
2023-01-24 02:02:10.298895: step: 596/469, loss: 0.23385417461395264
2023-01-24 02:02:10.939370: step: 598/469, loss: 0.16917254030704498
2023-01-24 02:02:11.543506: step: 600/469, loss: 0.3146384358406067
2023-01-24 02:02:12.141522: step: 602/469, loss: 0.2427896410226822
2023-01-24 02:02:12.777307: step: 604/469, loss: 0.22958119213581085
2023-01-24 02:02:13.414838: step: 606/469, loss: 0.20856578648090363
2023-01-24 02:02:14.079707: step: 608/469, loss: 0.5497919321060181
2023-01-24 02:02:14.700690: step: 610/469, loss: 0.29124996066093445
2023-01-24 02:02:15.314016: step: 612/469, loss: 0.11491380631923676
2023-01-24 02:02:15.968223: step: 614/469, loss: 1.065051555633545
2023-01-24 02:02:16.614280: step: 616/469, loss: 0.7414249181747437
2023-01-24 02:02:17.213565: step: 618/469, loss: 0.18989019095897675
2023-01-24 02:02:17.818689: step: 620/469, loss: 0.5554919242858887
2023-01-24 02:02:18.377178: step: 622/469, loss: 0.27418890595436096
2023-01-24 02:02:19.093334: step: 624/469, loss: 0.5021735429763794
2023-01-24 02:02:19.734872: step: 626/469, loss: 0.42460668087005615
2023-01-24 02:02:20.341177: step: 628/469, loss: 0.5467215776443481
2023-01-24 02:02:20.946720: step: 630/469, loss: 0.18194285035133362
2023-01-24 02:02:21.599312: step: 632/469, loss: 0.1417941153049469
2023-01-24 02:02:22.195280: step: 634/469, loss: 1.695264220237732
2023-01-24 02:02:22.873589: step: 636/469, loss: 0.05234282463788986
2023-01-24 02:02:23.456276: step: 638/469, loss: 0.26596134901046753
2023-01-24 02:02:24.112859: step: 640/469, loss: 0.9196944236755371
2023-01-24 02:02:24.681835: step: 642/469, loss: 0.6783714890480042
2023-01-24 02:02:25.260803: step: 644/469, loss: 0.6495234966278076
2023-01-24 02:02:25.879884: step: 646/469, loss: 0.2590858042240143
2023-01-24 02:02:26.489796: step: 648/469, loss: 0.2058669477701187
2023-01-24 02:02:27.182423: step: 650/469, loss: 0.6924328804016113
2023-01-24 02:02:27.877248: step: 652/469, loss: 0.11647651344537735
2023-01-24 02:02:28.553584: step: 654/469, loss: 2.0422580242156982
2023-01-24 02:02:29.143791: step: 656/469, loss: 0.7838826179504395
2023-01-24 02:02:29.807354: step: 658/469, loss: 0.29782330989837646
2023-01-24 02:02:30.485974: step: 660/469, loss: 0.1432504653930664
2023-01-24 02:02:31.103660: step: 662/469, loss: 0.8504621386528015
2023-01-24 02:02:31.668189: step: 664/469, loss: 0.6591264605522156
2023-01-24 02:02:32.328541: step: 666/469, loss: 0.7096976041793823
2023-01-24 02:02:32.949864: step: 668/469, loss: 0.6823020577430725
2023-01-24 02:02:33.594083: step: 670/469, loss: 0.6952880620956421
2023-01-24 02:02:34.190590: step: 672/469, loss: 0.19265688955783844
2023-01-24 02:02:34.832721: step: 674/469, loss: 0.3284139931201935
2023-01-24 02:02:35.377591: step: 676/469, loss: 0.1648135930299759
2023-01-24 02:02:36.017086: step: 678/469, loss: 0.36375126242637634
2023-01-24 02:02:36.748836: step: 680/469, loss: 0.19929485023021698
2023-01-24 02:02:37.333409: step: 682/469, loss: 0.48844996094703674
2023-01-24 02:02:37.973020: step: 684/469, loss: 0.15448260307312012
2023-01-24 02:02:38.557452: step: 686/469, loss: 0.26222851872444153
2023-01-24 02:02:39.208314: step: 688/469, loss: 0.11118326336145401
2023-01-24 02:02:39.814119: step: 690/469, loss: 0.16954626142978668
2023-01-24 02:02:40.447862: step: 692/469, loss: 0.8205360174179077
2023-01-24 02:02:41.065708: step: 694/469, loss: 0.5341930985450745
2023-01-24 02:02:41.677616: step: 696/469, loss: 0.27343830466270447
2023-01-24 02:02:42.284369: step: 698/469, loss: 0.17632602155208588
2023-01-24 02:02:42.943861: step: 700/469, loss: 0.4227660894393921
2023-01-24 02:02:43.558453: step: 702/469, loss: 0.7923645377159119
2023-01-24 02:02:44.218469: step: 704/469, loss: 0.6778087019920349
2023-01-24 02:02:44.903062: step: 706/469, loss: 0.6295285820960999
2023-01-24 02:02:45.502302: step: 708/469, loss: 0.11903341859579086
2023-01-24 02:02:46.139107: step: 710/469, loss: 0.14304491877555847
2023-01-24 02:02:46.754950: step: 712/469, loss: 0.45329543948173523
2023-01-24 02:02:47.348538: step: 714/469, loss: 0.3691706955432892
2023-01-24 02:02:47.929587: step: 716/469, loss: 0.3766706883907318
2023-01-24 02:02:48.588649: step: 718/469, loss: 0.657667338848114
2023-01-24 02:02:49.209502: step: 720/469, loss: 0.10985753685235977
2023-01-24 02:02:49.858290: step: 722/469, loss: 0.6467972993850708
2023-01-24 02:02:50.537326: step: 724/469, loss: 0.46754735708236694
2023-01-24 02:02:51.198873: step: 726/469, loss: 0.15916554629802704
2023-01-24 02:02:51.752913: step: 728/469, loss: 2.8822710514068604
2023-01-24 02:02:52.312780: step: 730/469, loss: 0.42414069175720215
2023-01-24 02:02:52.963462: step: 732/469, loss: 0.2098163366317749
2023-01-24 02:02:53.645270: step: 734/469, loss: 0.20797768235206604
2023-01-24 02:02:54.225285: step: 736/469, loss: 0.3841201364994049
2023-01-24 02:02:54.894167: step: 738/469, loss: 0.05002370849251747
2023-01-24 02:02:55.523739: step: 740/469, loss: 0.29889240860939026
2023-01-24 02:02:56.120543: step: 742/469, loss: 0.17595617473125458
2023-01-24 02:02:56.747524: step: 744/469, loss: 0.4108639657497406
2023-01-24 02:02:57.343746: step: 746/469, loss: 0.3597712516784668
2023-01-24 02:02:58.028674: step: 748/469, loss: 0.23803681135177612
2023-01-24 02:02:58.627162: step: 750/469, loss: 0.18777571618556976
2023-01-24 02:02:59.189019: step: 752/469, loss: 0.10587222874164581
2023-01-24 02:02:59.811089: step: 754/469, loss: 0.7175968885421753
2023-01-24 02:03:00.431663: step: 756/469, loss: 0.4509286880493164
2023-01-24 02:03:01.052535: step: 758/469, loss: 0.7743290066719055
2023-01-24 02:03:01.632599: step: 760/469, loss: 0.9395543932914734
2023-01-24 02:03:02.242317: step: 762/469, loss: 0.231919527053833
2023-01-24 02:03:02.918021: step: 764/469, loss: 0.27963942289352417
2023-01-24 02:03:03.599501: step: 766/469, loss: 0.2812337577342987
2023-01-24 02:03:04.203385: step: 768/469, loss: 0.11665716767311096
2023-01-24 02:03:04.811190: step: 770/469, loss: 0.5176973342895508
2023-01-24 02:03:05.414925: step: 772/469, loss: 0.16111698746681213
2023-01-24 02:03:06.034622: step: 774/469, loss: 0.23417110741138458
2023-01-24 02:03:06.649012: step: 776/469, loss: 0.41849949955940247
2023-01-24 02:03:07.285381: step: 778/469, loss: 0.13244368135929108
2023-01-24 02:03:07.884227: step: 780/469, loss: 0.42881375551223755
2023-01-24 02:03:08.536179: step: 782/469, loss: 0.18922825157642365
2023-01-24 02:03:09.195794: step: 784/469, loss: 0.2613990604877472
2023-01-24 02:03:09.848767: step: 786/469, loss: 0.2780478000640869
2023-01-24 02:03:10.480990: step: 788/469, loss: 0.6603026390075684
2023-01-24 02:03:11.211233: step: 790/469, loss: 0.14456990361213684
2023-01-24 02:03:11.868751: step: 792/469, loss: 0.20027607679367065
2023-01-24 02:03:12.509000: step: 794/469, loss: 0.3052690923213959
2023-01-24 02:03:13.198366: step: 796/469, loss: 0.20652316510677338
2023-01-24 02:03:13.871483: step: 798/469, loss: 0.20102040469646454
2023-01-24 02:03:14.468922: step: 800/469, loss: 0.13201051950454712
2023-01-24 02:03:15.138250: step: 802/469, loss: 0.6680241823196411
2023-01-24 02:03:15.679604: step: 804/469, loss: 0.16611360013484955
2023-01-24 02:03:16.338414: step: 806/469, loss: 0.27408918738365173
2023-01-24 02:03:16.927349: step: 808/469, loss: 0.11027664691209793
2023-01-24 02:03:17.517695: step: 810/469, loss: 0.7532581686973572
2023-01-24 02:03:18.219778: step: 812/469, loss: 3.7997052669525146
2023-01-24 02:03:18.857861: step: 814/469, loss: 1.519590973854065
2023-01-24 02:03:19.437157: step: 816/469, loss: 0.0590866357088089
2023-01-24 02:03:19.989918: step: 818/469, loss: 0.7658993005752563
2023-01-24 02:03:20.605598: step: 820/469, loss: 1.321593165397644
2023-01-24 02:03:21.231283: step: 822/469, loss: 0.2512640953063965
2023-01-24 02:03:21.798072: step: 824/469, loss: 0.08269482851028442
2023-01-24 02:03:22.470255: step: 826/469, loss: 0.2748689353466034
2023-01-24 02:03:23.066266: step: 828/469, loss: 0.16837763786315918
2023-01-24 02:03:23.792792: step: 830/469, loss: 0.5090327858924866
2023-01-24 02:03:24.409158: step: 832/469, loss: 0.15456701815128326
2023-01-24 02:03:25.063244: step: 834/469, loss: 1.3860313892364502
2023-01-24 02:03:25.709451: step: 836/469, loss: 0.1489032357931137
2023-01-24 02:03:26.384693: step: 838/469, loss: 0.23921431601047516
2023-01-24 02:03:26.981108: step: 840/469, loss: 0.7365400195121765
2023-01-24 02:03:27.640899: step: 842/469, loss: 0.3689229488372803
2023-01-24 02:03:28.269156: step: 844/469, loss: 0.1368788778781891
2023-01-24 02:03:28.908620: step: 846/469, loss: 0.4069958031177521
2023-01-24 02:03:29.529103: step: 848/469, loss: 0.13186892867088318
2023-01-24 02:03:30.252234: step: 850/469, loss: 0.14404664933681488
2023-01-24 02:03:30.919335: step: 852/469, loss: 0.4834625720977783
2023-01-24 02:03:31.505346: step: 854/469, loss: 0.3989724814891815
2023-01-24 02:03:32.210104: step: 856/469, loss: 0.49936750531196594
2023-01-24 02:03:32.793998: step: 858/469, loss: 0.18716418743133545
2023-01-24 02:03:33.311589: step: 860/469, loss: 0.31274962425231934
2023-01-24 02:03:33.895046: step: 862/469, loss: 0.17767015099525452
2023-01-24 02:03:34.579526: step: 864/469, loss: 0.08762048929929733
2023-01-24 02:03:35.162400: step: 866/469, loss: 0.18887192010879517
2023-01-24 02:03:35.790202: step: 868/469, loss: 0.2997731566429138
2023-01-24 02:03:36.573529: step: 870/469, loss: 0.10482577234506607
2023-01-24 02:03:37.168884: step: 872/469, loss: 0.22939112782478333
2023-01-24 02:03:37.830348: step: 874/469, loss: 0.9563087821006775
2023-01-24 02:03:38.462437: step: 876/469, loss: 0.15791034698486328
2023-01-24 02:03:39.123308: step: 878/469, loss: 0.1795186847448349
2023-01-24 02:03:39.802777: step: 880/469, loss: 0.45465949177742004
2023-01-24 02:03:40.452205: step: 882/469, loss: 0.10572908818721771
2023-01-24 02:03:41.073792: step: 884/469, loss: 0.2038441002368927
2023-01-24 02:03:41.702846: step: 886/469, loss: 0.34216368198394775
2023-01-24 02:03:42.314751: step: 888/469, loss: 0.43507444858551025
2023-01-24 02:03:43.037774: step: 890/469, loss: 0.21979469060897827
2023-01-24 02:03:43.657535: step: 892/469, loss: 0.09537164121866226
2023-01-24 02:03:44.344181: step: 894/469, loss: 0.6587051153182983
2023-01-24 02:03:44.961717: step: 896/469, loss: 0.27228352427482605
2023-01-24 02:03:45.622270: step: 898/469, loss: 0.2525215148925781
2023-01-24 02:03:46.227526: step: 900/469, loss: 0.15978290140628815
2023-01-24 02:03:46.855976: step: 902/469, loss: 0.236827090382576
2023-01-24 02:03:47.464285: step: 904/469, loss: 0.7649135589599609
2023-01-24 02:03:48.081447: step: 906/469, loss: 0.33343371748924255
2023-01-24 02:03:48.730264: step: 908/469, loss: 0.239822655916214
2023-01-24 02:03:49.339010: step: 910/469, loss: 3.051790475845337
2023-01-24 02:03:50.037109: step: 912/469, loss: 0.4371585547924042
2023-01-24 02:03:50.687863: step: 914/469, loss: 0.30161041021347046
2023-01-24 02:03:51.387429: step: 916/469, loss: 0.3371298313140869
2023-01-24 02:03:51.982425: step: 918/469, loss: 0.19050012528896332
2023-01-24 02:03:52.571684: step: 920/469, loss: 0.6725030541419983
2023-01-24 02:03:53.186004: step: 922/469, loss: 0.2457217574119568
2023-01-24 02:03:53.748470: step: 924/469, loss: 0.16936399042606354
2023-01-24 02:03:54.349775: step: 926/469, loss: 0.11183946579694748
2023-01-24 02:03:54.982293: step: 928/469, loss: 0.15361808240413666
2023-01-24 02:03:55.609908: step: 930/469, loss: 0.42871227860450745
2023-01-24 02:03:56.223688: step: 932/469, loss: 0.43631088733673096
2023-01-24 02:03:56.836553: step: 934/469, loss: 0.4583870768547058
2023-01-24 02:03:57.468030: step: 936/469, loss: 0.34182703495025635
2023-01-24 02:03:58.107057: step: 938/469, loss: 0.5038894414901733
==================================================
Loss: 0.450
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31735747469296066, 'r': 0.29989378063964783, 'f1': 0.3083785802870135}, 'combined': 0.22722632231674678, 'epoch': 9}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31513847954230234, 'r': 0.2375792380081035, 'f1': 0.2709171696847753}, 'combined': 0.14777300164624108, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3284817769320843, 'r': 0.30417287882895094, 'f1': 0.3158603096410978}, 'combined': 0.2327391755250194, 'epoch': 9}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3163012529951711, 'r': 0.23671951047580053, 'f1': 0.2707843275249084}, 'combined': 0.14770054228631366, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3203172494565076, 'r': 0.3014750583120071, 'f1': 0.31061066613964367}, 'combined': 0.2288710171555269, 'epoch': 9}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3133225798640462, 'r': 0.2385035557611038, 'f1': 0.2708409209837781}, 'combined': 0.14773141144569713, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29166666666666663, 'r': 0.3416666666666666, 'f1': 0.3146929824561403}, 'combined': 0.20979532163742687, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2826086956521739, 'r': 0.2826086956521739, 'f1': 0.2826086956521739}, 'combined': 0.14130434782608695, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45454545454545453, 'r': 0.1724137931034483, 'f1': 0.25000000000000006}, 'combined': 0.16666666666666669, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35179640393089057, 'r': 0.2990603206091821, 'f1': 0.32329187479187477}, 'combined': 0.23821506563611825, 'epoch': 6}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31941825131851476, 'r': 0.2185954729974831, 'f1': 0.2595598609301999}, 'combined': 0.14157810596192721, 'epoch': 6}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.33695652173913043, 'r': 0.33695652173913043, 'f1': 0.33695652173913043}, 'combined': 0.16847826086956522, 'epoch': 6}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 02:06:44.345839: step: 2/469, loss: 0.3260871171951294
2023-01-24 02:06:44.918926: step: 4/469, loss: 0.11803068220615387
2023-01-24 02:06:45.577176: step: 6/469, loss: 0.1941731572151184
2023-01-24 02:06:46.250416: step: 8/469, loss: 0.09274458140134811
2023-01-24 02:06:46.902204: step: 10/469, loss: 0.15450076758861542
2023-01-24 02:06:47.521421: step: 12/469, loss: 0.3043484687805176
2023-01-24 02:06:48.133923: step: 14/469, loss: 0.0967775285243988
2023-01-24 02:06:48.741496: step: 16/469, loss: 0.32464948296546936
2023-01-24 02:06:49.363973: step: 18/469, loss: 0.2270539104938507
2023-01-24 02:06:49.995387: step: 20/469, loss: 0.06182711943984032
2023-01-24 02:06:50.641860: step: 22/469, loss: 0.10078060626983643
2023-01-24 02:06:51.190554: step: 24/469, loss: 0.13304398953914642
2023-01-24 02:06:51.853985: step: 26/469, loss: 0.46218162775039673
2023-01-24 02:06:52.476642: step: 28/469, loss: 0.18660806119441986
2023-01-24 02:06:53.080564: step: 30/469, loss: 0.07191115617752075
2023-01-24 02:06:53.706744: step: 32/469, loss: 0.1009015217423439
2023-01-24 02:06:54.345412: step: 34/469, loss: 0.06282003223896027
2023-01-24 02:06:54.934662: step: 36/469, loss: 0.05078323930501938
2023-01-24 02:06:55.527242: step: 38/469, loss: 0.16965973377227783
2023-01-24 02:06:56.134879: step: 40/469, loss: 0.2929583191871643
2023-01-24 02:06:56.808446: step: 42/469, loss: 0.4280208349227905
2023-01-24 02:06:57.437410: step: 44/469, loss: 0.22449113428592682
2023-01-24 02:06:58.114606: step: 46/469, loss: 0.08549151569604874
2023-01-24 02:06:58.768870: step: 48/469, loss: 0.13578908145427704
2023-01-24 02:06:59.390899: step: 50/469, loss: 0.21607942879199982
2023-01-24 02:06:59.967249: step: 52/469, loss: 0.7591243982315063
2023-01-24 02:07:00.624189: step: 54/469, loss: 0.17915067076683044
2023-01-24 02:07:01.224818: step: 56/469, loss: 0.1202983483672142
2023-01-24 02:07:01.828458: step: 58/469, loss: 0.1737108677625656
2023-01-24 02:07:02.427065: step: 60/469, loss: 0.13567295670509338
2023-01-24 02:07:03.044091: step: 62/469, loss: 0.584044873714447
2023-01-24 02:07:03.695994: step: 64/469, loss: 0.18515388667583466
2023-01-24 02:07:04.279718: step: 66/469, loss: 0.20488345623016357
2023-01-24 02:07:04.896235: step: 68/469, loss: 0.148570254445076
2023-01-24 02:07:05.654310: step: 70/469, loss: 0.2079058736562729
2023-01-24 02:07:06.245061: step: 72/469, loss: 0.18115873634815216
2023-01-24 02:07:06.864127: step: 74/469, loss: 0.12436431646347046
2023-01-24 02:07:07.533735: step: 76/469, loss: 0.1123075783252716
2023-01-24 02:07:08.156412: step: 78/469, loss: 0.20267552137374878
2023-01-24 02:07:08.728418: step: 80/469, loss: 0.23112595081329346
2023-01-24 02:07:09.365791: step: 82/469, loss: 0.19608274102210999
2023-01-24 02:07:09.959938: step: 84/469, loss: 0.30020779371261597
2023-01-24 02:07:10.549831: step: 86/469, loss: 0.24599343538284302
2023-01-24 02:07:11.185751: step: 88/469, loss: 0.2468404322862625
2023-01-24 02:07:11.767717: step: 90/469, loss: 1.329355001449585
2023-01-24 02:07:12.366693: step: 92/469, loss: 0.5803744792938232
2023-01-24 02:07:13.105922: step: 94/469, loss: 0.32619214057922363
2023-01-24 02:07:13.732504: step: 96/469, loss: 0.17178703844547272
2023-01-24 02:07:14.341660: step: 98/469, loss: 0.5373564958572388
2023-01-24 02:07:14.995978: step: 100/469, loss: 0.28605222702026367
2023-01-24 02:07:15.623292: step: 102/469, loss: 0.08383268117904663
2023-01-24 02:07:16.279830: step: 104/469, loss: 1.9409605264663696
2023-01-24 02:07:16.997706: step: 106/469, loss: 0.17641407251358032
2023-01-24 02:07:17.638316: step: 108/469, loss: 0.773276686668396
2023-01-24 02:07:18.291357: step: 110/469, loss: 0.11978209018707275
2023-01-24 02:07:18.924641: step: 112/469, loss: 0.34194859862327576
2023-01-24 02:07:19.558496: step: 114/469, loss: 0.18613550066947937
2023-01-24 02:07:20.209351: step: 116/469, loss: 0.12781774997711182
2023-01-24 02:07:20.793313: step: 118/469, loss: 0.16251547634601593
2023-01-24 02:07:21.386484: step: 120/469, loss: 0.3708127439022064
2023-01-24 02:07:21.958867: step: 122/469, loss: 0.14788971841335297
2023-01-24 02:07:22.644750: step: 124/469, loss: 0.2537625730037689
2023-01-24 02:07:23.365348: step: 126/469, loss: 0.5536888241767883
2023-01-24 02:07:24.004529: step: 128/469, loss: 0.16357994079589844
2023-01-24 02:07:24.615596: step: 130/469, loss: 0.24256977438926697
2023-01-24 02:07:25.196192: step: 132/469, loss: 0.08456134796142578
2023-01-24 02:07:25.873125: step: 134/469, loss: 0.24679823219776154
2023-01-24 02:07:26.497471: step: 136/469, loss: 0.31085076928138733
2023-01-24 02:07:27.140549: step: 138/469, loss: 0.10154884308576584
2023-01-24 02:07:27.754524: step: 140/469, loss: 0.6388983130455017
2023-01-24 02:07:28.389250: step: 142/469, loss: 0.4659835696220398
2023-01-24 02:07:29.003335: step: 144/469, loss: 0.2552926242351532
2023-01-24 02:07:29.660525: step: 146/469, loss: 0.2275351583957672
2023-01-24 02:07:30.252023: step: 148/469, loss: 0.14156070351600647
2023-01-24 02:07:30.940165: step: 150/469, loss: 0.10421870648860931
2023-01-24 02:07:31.625400: step: 152/469, loss: 0.08590361475944519
2023-01-24 02:07:32.335976: step: 154/469, loss: 0.19352349638938904
2023-01-24 02:07:32.927853: step: 156/469, loss: 0.20251214504241943
2023-01-24 02:07:33.501738: step: 158/469, loss: 0.37143537402153015
2023-01-24 02:07:34.269666: step: 160/469, loss: 0.29133740067481995
2023-01-24 02:07:34.946513: step: 162/469, loss: 0.18984173238277435
2023-01-24 02:07:35.534483: step: 164/469, loss: 0.127028688788414
2023-01-24 02:07:36.192722: step: 166/469, loss: 0.08901457488536835
2023-01-24 02:07:36.774151: step: 168/469, loss: 0.08538316935300827
2023-01-24 02:07:37.352608: step: 170/469, loss: 1.7103285789489746
2023-01-24 02:07:38.013223: step: 172/469, loss: 0.11412934958934784
2023-01-24 02:07:38.586692: step: 174/469, loss: 0.14428536593914032
2023-01-24 02:07:39.264767: step: 176/469, loss: 0.18397821485996246
2023-01-24 02:07:39.877928: step: 178/469, loss: 0.17066001892089844
2023-01-24 02:07:40.526010: step: 180/469, loss: 0.31434497237205505
2023-01-24 02:07:41.173755: step: 182/469, loss: 0.654872477054596
2023-01-24 02:07:41.812795: step: 184/469, loss: 0.20487254858016968
2023-01-24 02:07:42.474485: step: 186/469, loss: 0.12853318452835083
2023-01-24 02:07:43.129291: step: 188/469, loss: 0.11310946941375732
2023-01-24 02:07:43.724299: step: 190/469, loss: 0.6582525968551636
2023-01-24 02:07:44.336261: step: 192/469, loss: 0.3505593240261078
2023-01-24 02:07:44.912268: step: 194/469, loss: 0.16400399804115295
2023-01-24 02:07:45.528719: step: 196/469, loss: 0.13037331402301788
2023-01-24 02:07:46.185391: step: 198/469, loss: 7.986757755279541
2023-01-24 02:07:46.830159: step: 200/469, loss: 0.15797364711761475
2023-01-24 02:07:47.445382: step: 202/469, loss: 0.7425860166549683
2023-01-24 02:07:47.976094: step: 204/469, loss: 1.7749760150909424
2023-01-24 02:07:48.572633: step: 206/469, loss: 0.4389791786670685
2023-01-24 02:07:49.223828: step: 208/469, loss: 0.14861886203289032
2023-01-24 02:07:49.885580: step: 210/469, loss: 0.08495287597179413
2023-01-24 02:07:50.508499: step: 212/469, loss: 0.13479702174663544
2023-01-24 02:07:51.118265: step: 214/469, loss: 1.7719552516937256
2023-01-24 02:07:51.757058: step: 216/469, loss: 0.17068809270858765
2023-01-24 02:07:52.402519: step: 218/469, loss: 0.1426297277212143
2023-01-24 02:07:52.985784: step: 220/469, loss: 0.1827821433544159
2023-01-24 02:07:53.592307: step: 222/469, loss: 0.16923899948596954
2023-01-24 02:07:54.261111: step: 224/469, loss: 0.8253857493400574
2023-01-24 02:07:54.825714: step: 226/469, loss: 0.28710123896598816
2023-01-24 02:07:55.451759: step: 228/469, loss: 0.14482896029949188
2023-01-24 02:07:56.007786: step: 230/469, loss: 0.1563882976770401
2023-01-24 02:07:56.626151: step: 232/469, loss: 0.12219942361116409
2023-01-24 02:07:57.378492: step: 234/469, loss: 0.1577947735786438
2023-01-24 02:07:57.986475: step: 236/469, loss: 0.11812220513820648
2023-01-24 02:07:58.592752: step: 238/469, loss: 0.06741271167993546
2023-01-24 02:07:59.155477: step: 240/469, loss: 0.8435651659965515
2023-01-24 02:07:59.865270: step: 242/469, loss: 0.43402570486068726
2023-01-24 02:08:00.491310: step: 244/469, loss: 0.2857842743396759
2023-01-24 02:08:01.126218: step: 246/469, loss: 0.2907649278640747
2023-01-24 02:08:01.724330: step: 248/469, loss: 0.19685302674770355
2023-01-24 02:08:02.356465: step: 250/469, loss: 0.29523003101348877
2023-01-24 02:08:02.962971: step: 252/469, loss: 0.7411558628082275
2023-01-24 02:08:03.589924: step: 254/469, loss: 0.14356470108032227
2023-01-24 02:08:04.233210: step: 256/469, loss: 0.3514004945755005
2023-01-24 02:08:04.845893: step: 258/469, loss: 0.40200075507164
2023-01-24 02:08:05.456801: step: 260/469, loss: 0.18726316094398499
2023-01-24 02:08:06.126977: step: 262/469, loss: 0.5279545187950134
2023-01-24 02:08:06.795633: step: 264/469, loss: 0.2940979599952698
2023-01-24 02:08:07.480738: step: 266/469, loss: 0.1055612862110138
2023-01-24 02:08:08.100594: step: 268/469, loss: 1.7026387453079224
2023-01-24 02:08:08.743291: step: 270/469, loss: 0.5599890351295471
2023-01-24 02:08:09.326594: step: 272/469, loss: 0.3769027888774872
2023-01-24 02:08:09.956479: step: 274/469, loss: 1.31482994556427
2023-01-24 02:08:10.735561: step: 276/469, loss: 0.6392829418182373
2023-01-24 02:08:11.412416: step: 278/469, loss: 0.12252487242221832
2023-01-24 02:08:12.056033: step: 280/469, loss: 0.3937845230102539
2023-01-24 02:08:12.673758: step: 282/469, loss: 0.8877031803131104
2023-01-24 02:08:13.341977: step: 284/469, loss: 0.746691107749939
2023-01-24 02:08:13.994928: step: 286/469, loss: 0.14422902464866638
2023-01-24 02:08:14.591473: step: 288/469, loss: 0.18659165501594543
2023-01-24 02:08:15.268868: step: 290/469, loss: 0.18137985467910767
2023-01-24 02:08:15.908136: step: 292/469, loss: 0.3956001400947571
2023-01-24 02:08:16.530435: step: 294/469, loss: 0.3132602274417877
2023-01-24 02:08:17.166141: step: 296/469, loss: 0.1650928407907486
2023-01-24 02:08:17.751702: step: 298/469, loss: 0.1954052895307541
2023-01-24 02:08:18.331566: step: 300/469, loss: 1.538400411605835
2023-01-24 02:08:18.927783: step: 302/469, loss: 0.395701140165329
2023-01-24 02:08:19.592178: step: 304/469, loss: 0.13635271787643433
2023-01-24 02:08:20.293560: step: 306/469, loss: 0.2199510931968689
2023-01-24 02:08:20.946950: step: 308/469, loss: 0.18347452580928802
2023-01-24 02:08:21.492755: step: 310/469, loss: 0.1973084658384323
2023-01-24 02:08:22.069489: step: 312/469, loss: 0.41131314635276794
2023-01-24 02:08:22.705899: step: 314/469, loss: 0.21307218074798584
2023-01-24 02:08:23.335153: step: 316/469, loss: 0.23374679684638977
2023-01-24 02:08:23.971567: step: 318/469, loss: 0.2610156536102295
2023-01-24 02:08:24.583247: step: 320/469, loss: 0.250539630651474
2023-01-24 02:08:25.213203: step: 322/469, loss: 0.11684828996658325
2023-01-24 02:08:25.837884: step: 324/469, loss: 0.3343842923641205
2023-01-24 02:08:26.459321: step: 326/469, loss: 0.19394487142562866
2023-01-24 02:08:27.145667: step: 328/469, loss: 0.15986189246177673
2023-01-24 02:08:27.766680: step: 330/469, loss: 0.16270574927330017
2023-01-24 02:08:28.359011: step: 332/469, loss: 0.1303102821111679
2023-01-24 02:08:28.909073: step: 334/469, loss: 0.2709577977657318
2023-01-24 02:08:29.595073: step: 336/469, loss: 0.22591176629066467
2023-01-24 02:08:30.255128: step: 338/469, loss: 0.07989803701639175
2023-01-24 02:08:30.882756: step: 340/469, loss: 0.3379601836204529
2023-01-24 02:08:31.502713: step: 342/469, loss: 2.177950143814087
2023-01-24 02:08:32.211848: step: 344/469, loss: 0.5851849913597107
2023-01-24 02:08:32.878278: step: 346/469, loss: 0.5799577236175537
2023-01-24 02:08:33.538133: step: 348/469, loss: 0.17609424889087677
2023-01-24 02:08:34.108774: step: 350/469, loss: 0.6569993495941162
2023-01-24 02:08:34.734471: step: 352/469, loss: 0.1533515453338623
2023-01-24 02:08:35.350013: step: 354/469, loss: 0.22334958612918854
2023-01-24 02:08:35.976571: step: 356/469, loss: 0.1917479783296585
2023-01-24 02:08:36.569915: step: 358/469, loss: 0.13376808166503906
2023-01-24 02:08:37.194965: step: 360/469, loss: 0.3077527582645416
2023-01-24 02:08:37.754397: step: 362/469, loss: 0.5522488355636597
2023-01-24 02:08:38.389442: step: 364/469, loss: 0.4673190116882324
2023-01-24 02:08:39.008216: step: 366/469, loss: 0.3516501784324646
2023-01-24 02:08:39.703384: step: 368/469, loss: 0.38323748111724854
2023-01-24 02:08:40.291930: step: 370/469, loss: 2.246837615966797
2023-01-24 02:08:40.909445: step: 372/469, loss: 0.1917182058095932
2023-01-24 02:08:41.495203: step: 374/469, loss: 0.15490412712097168
2023-01-24 02:08:42.149280: step: 376/469, loss: 0.21192680299282074
2023-01-24 02:08:42.888246: step: 378/469, loss: 0.2574155032634735
2023-01-24 02:08:43.557620: step: 380/469, loss: 0.2593514323234558
2023-01-24 02:08:44.200760: step: 382/469, loss: 0.4792279601097107
2023-01-24 02:08:44.961771: step: 384/469, loss: 0.1763969212770462
2023-01-24 02:08:45.563051: step: 386/469, loss: 0.2040223926305771
2023-01-24 02:08:46.224567: step: 388/469, loss: 0.2920312285423279
2023-01-24 02:08:46.805469: step: 390/469, loss: 0.2173030525445938
2023-01-24 02:08:47.369469: step: 392/469, loss: 0.15153872966766357
2023-01-24 02:08:47.969958: step: 394/469, loss: 0.5955541133880615
2023-01-24 02:08:48.546276: step: 396/469, loss: 0.2460816651582718
2023-01-24 02:08:49.174871: step: 398/469, loss: 0.4389353394508362
2023-01-24 02:08:49.749285: step: 400/469, loss: 0.28610822558403015
2023-01-24 02:08:50.321824: step: 402/469, loss: 0.09076850116252899
2023-01-24 02:08:50.906585: step: 404/469, loss: 0.4015452563762665
2023-01-24 02:08:51.571131: step: 406/469, loss: 0.2629058063030243
2023-01-24 02:08:52.183181: step: 408/469, loss: 0.1401469111442566
2023-01-24 02:08:52.762367: step: 410/469, loss: 0.1503347009420395
2023-01-24 02:08:53.417825: step: 412/469, loss: 0.1177896112203598
2023-01-24 02:08:54.129497: step: 414/469, loss: 0.2586066722869873
2023-01-24 02:08:54.753591: step: 416/469, loss: 0.22401678562164307
2023-01-24 02:08:55.381310: step: 418/469, loss: 0.4721553921699524
2023-01-24 02:08:55.946522: step: 420/469, loss: 0.10826145112514496
2023-01-24 02:08:56.601111: step: 422/469, loss: 0.14290405809879303
2023-01-24 02:08:57.256130: step: 424/469, loss: 0.18634554743766785
2023-01-24 02:08:57.883693: step: 426/469, loss: 0.19271937012672424
2023-01-24 02:08:58.571036: step: 428/469, loss: 0.4409353733062744
2023-01-24 02:08:59.201293: step: 430/469, loss: 0.2770993411540985
2023-01-24 02:08:59.844453: step: 432/469, loss: 0.17648662626743317
2023-01-24 02:09:00.439253: step: 434/469, loss: 0.6518418788909912
2023-01-24 02:09:01.162498: step: 436/469, loss: 0.1623111218214035
2023-01-24 02:09:01.780262: step: 438/469, loss: 0.20409198105335236
2023-01-24 02:09:02.423174: step: 440/469, loss: 0.3621858060359955
2023-01-24 02:09:03.106715: step: 442/469, loss: 0.4220235049724579
2023-01-24 02:09:03.707042: step: 444/469, loss: 0.07869580388069153
2023-01-24 02:09:04.324486: step: 446/469, loss: 0.18688485026359558
2023-01-24 02:09:04.872144: step: 448/469, loss: 0.19848749041557312
2023-01-24 02:09:05.520377: step: 450/469, loss: 0.14502377808094025
2023-01-24 02:09:06.174784: step: 452/469, loss: 0.2228161096572876
2023-01-24 02:09:06.903897: step: 454/469, loss: 0.08278413116931915
2023-01-24 02:09:07.552098: step: 456/469, loss: 0.20986926555633545
2023-01-24 02:09:08.172853: step: 458/469, loss: 0.28288328647613525
2023-01-24 02:09:08.841991: step: 460/469, loss: 0.14189527928829193
2023-01-24 02:09:09.502982: step: 462/469, loss: 0.27325865626335144
2023-01-24 02:09:10.142988: step: 464/469, loss: 0.10168289393186569
2023-01-24 02:09:10.725806: step: 466/469, loss: 0.16034327447414398
2023-01-24 02:09:11.358457: step: 468/469, loss: 0.07392926514148712
2023-01-24 02:09:12.048390: step: 470/469, loss: 0.1523371785879135
2023-01-24 02:09:12.682298: step: 472/469, loss: 0.1986953616142273
2023-01-24 02:09:13.331501: step: 474/469, loss: 0.4473738372325897
2023-01-24 02:09:13.938073: step: 476/469, loss: 0.10791049152612686
2023-01-24 02:09:14.546100: step: 478/469, loss: 0.23333097994327545
2023-01-24 02:09:15.163883: step: 480/469, loss: 0.1788780242204666
2023-01-24 02:09:15.886132: step: 482/469, loss: 0.22069504857063293
2023-01-24 02:09:16.505137: step: 484/469, loss: 0.127645343542099
2023-01-24 02:09:17.183661: step: 486/469, loss: 0.18005597591400146
2023-01-24 02:09:17.799533: step: 488/469, loss: 0.17945681512355804
2023-01-24 02:09:18.384454: step: 490/469, loss: 0.19683711230754852
2023-01-24 02:09:18.965537: step: 492/469, loss: 0.15534235537052155
2023-01-24 02:09:19.625624: step: 494/469, loss: 0.5154483914375305
2023-01-24 02:09:20.216082: step: 496/469, loss: 0.11100415885448456
2023-01-24 02:09:20.868599: step: 498/469, loss: 0.2955454885959625
2023-01-24 02:09:21.520208: step: 500/469, loss: 0.10263917595148087
2023-01-24 02:09:22.115904: step: 502/469, loss: 0.3018554747104645
2023-01-24 02:09:22.705697: step: 504/469, loss: 0.37817472219467163
2023-01-24 02:09:23.327159: step: 506/469, loss: 0.20461368560791016
2023-01-24 02:09:23.984677: step: 508/469, loss: 0.25689950585365295
2023-01-24 02:09:24.663383: step: 510/469, loss: 0.2914935350418091
2023-01-24 02:09:25.256705: step: 512/469, loss: 0.05203931778669357
2023-01-24 02:09:25.793743: step: 514/469, loss: 0.16389061510562897
2023-01-24 02:09:26.427687: step: 516/469, loss: 0.2884312868118286
2023-01-24 02:09:27.052681: step: 518/469, loss: 0.13901834189891815
2023-01-24 02:09:27.724472: step: 520/469, loss: 0.2569965720176697
2023-01-24 02:09:28.385071: step: 522/469, loss: 0.26480719447135925
2023-01-24 02:09:28.965204: step: 524/469, loss: 0.24072884023189545
2023-01-24 02:09:29.541392: step: 526/469, loss: 0.2926464080810547
2023-01-24 02:09:30.203263: step: 528/469, loss: 0.6798343062400818
2023-01-24 02:09:30.842707: step: 530/469, loss: 0.04340603947639465
2023-01-24 02:09:31.430830: step: 532/469, loss: 0.5107023119926453
2023-01-24 02:09:32.115852: step: 534/469, loss: 0.2708114683628082
2023-01-24 02:09:32.785981: step: 536/469, loss: 0.8310455679893494
2023-01-24 02:09:33.412501: step: 538/469, loss: 0.1858428567647934
2023-01-24 02:09:34.137747: step: 540/469, loss: 0.4196905195713043
2023-01-24 02:09:34.763492: step: 542/469, loss: 0.15431804955005646
2023-01-24 02:09:35.407622: step: 544/469, loss: 0.2692755162715912
2023-01-24 02:09:36.016334: step: 546/469, loss: 0.3524225950241089
2023-01-24 02:09:36.688192: step: 548/469, loss: 0.6620578169822693
2023-01-24 02:09:37.261492: step: 550/469, loss: 0.7527962327003479
2023-01-24 02:09:37.893030: step: 552/469, loss: 0.38842910528182983
2023-01-24 02:09:38.460319: step: 554/469, loss: 1.2896281480789185
2023-01-24 02:09:39.119222: step: 556/469, loss: 0.28871390223503113
2023-01-24 02:09:39.809339: step: 558/469, loss: 0.3317926824092865
2023-01-24 02:09:40.496904: step: 560/469, loss: 0.37933608889579773
2023-01-24 02:09:41.178941: step: 562/469, loss: 0.7165369987487793
2023-01-24 02:09:41.831720: step: 564/469, loss: 0.14440712332725525
2023-01-24 02:09:42.444308: step: 566/469, loss: 0.0998615026473999
2023-01-24 02:09:43.098496: step: 568/469, loss: 0.08365899324417114
2023-01-24 02:09:43.705480: step: 570/469, loss: 0.4213893413543701
2023-01-24 02:09:44.382698: step: 572/469, loss: 0.06474947929382324
2023-01-24 02:09:45.009964: step: 574/469, loss: 9.069156646728516
2023-01-24 02:09:45.707093: step: 576/469, loss: 0.46241387724876404
2023-01-24 02:09:46.283536: step: 578/469, loss: 0.09412537515163422
2023-01-24 02:09:46.919276: step: 580/469, loss: 0.31065821647644043
2023-01-24 02:09:47.580284: step: 582/469, loss: 0.18173867464065552
2023-01-24 02:09:48.158302: step: 584/469, loss: 0.12756435573101044
2023-01-24 02:09:48.747944: step: 586/469, loss: 0.13833735883235931
2023-01-24 02:09:49.396199: step: 588/469, loss: 1.476247787475586
2023-01-24 02:09:50.000362: step: 590/469, loss: 0.18005362153053284
2023-01-24 02:09:50.550240: step: 592/469, loss: 0.47371673583984375
2023-01-24 02:09:51.181627: step: 594/469, loss: 0.3745899796485901
2023-01-24 02:09:51.809021: step: 596/469, loss: 1.383629560470581
2023-01-24 02:09:52.425438: step: 598/469, loss: 0.32182469964027405
2023-01-24 02:09:53.039433: step: 600/469, loss: 0.16456946730613708
2023-01-24 02:09:53.629524: step: 602/469, loss: 0.096487857401371
2023-01-24 02:09:54.209192: step: 604/469, loss: 0.07716759294271469
2023-01-24 02:09:54.821603: step: 606/469, loss: 0.20448121428489685
2023-01-24 02:09:55.529894: step: 608/469, loss: 0.2204960435628891
2023-01-24 02:09:56.118908: step: 610/469, loss: 0.31164512038230896
2023-01-24 02:09:56.774590: step: 612/469, loss: 0.5891857147216797
2023-01-24 02:09:57.375590: step: 614/469, loss: 0.17195731401443481
2023-01-24 02:09:58.005172: step: 616/469, loss: 0.3017668128013611
2023-01-24 02:09:58.620508: step: 618/469, loss: 0.29598596692085266
2023-01-24 02:09:59.172941: step: 620/469, loss: 0.09344451874494553
2023-01-24 02:09:59.844513: step: 622/469, loss: 0.4150453209877014
2023-01-24 02:10:00.490368: step: 624/469, loss: 0.14968973398208618
2023-01-24 02:10:01.160667: step: 626/469, loss: 0.18221484124660492
2023-01-24 02:10:01.761144: step: 628/469, loss: 0.18337593972682953
2023-01-24 02:10:02.378410: step: 630/469, loss: 1.3400460481643677
2023-01-24 02:10:03.021287: step: 632/469, loss: 1.1392515897750854
2023-01-24 02:10:03.618818: step: 634/469, loss: 0.2779347598552704
2023-01-24 02:10:04.307567: step: 636/469, loss: 0.5234377384185791
2023-01-24 02:10:04.915181: step: 638/469, loss: 0.18483102321624756
2023-01-24 02:10:05.560511: step: 640/469, loss: 0.2284020036458969
2023-01-24 02:10:06.159062: step: 642/469, loss: 0.3503674268722534
2023-01-24 02:10:06.799250: step: 644/469, loss: 0.30721575021743774
2023-01-24 02:10:07.508261: step: 646/469, loss: 0.4204408824443817
2023-01-24 02:10:08.056445: step: 648/469, loss: 0.1218271404504776
2023-01-24 02:10:08.712450: step: 650/469, loss: 0.5836813449859619
2023-01-24 02:10:09.313215: step: 652/469, loss: 1.136457920074463
2023-01-24 02:10:10.032233: step: 654/469, loss: 0.09446422010660172
2023-01-24 02:10:10.657563: step: 656/469, loss: 0.0958859771490097
2023-01-24 02:10:11.251742: step: 658/469, loss: 0.9152986407279968
2023-01-24 02:10:11.909300: step: 660/469, loss: 0.3161552846431732
2023-01-24 02:10:12.527213: step: 662/469, loss: 0.10566958039999008
2023-01-24 02:10:13.197023: step: 664/469, loss: 0.12009944021701813
2023-01-24 02:10:13.789618: step: 666/469, loss: 0.09755319356918335
2023-01-24 02:10:14.459194: step: 668/469, loss: 0.19840706884860992
2023-01-24 02:10:15.107027: step: 670/469, loss: 0.4426737427711487
2023-01-24 02:10:15.718441: step: 672/469, loss: 0.21325407922267914
2023-01-24 02:10:16.395487: step: 674/469, loss: 0.9769893884658813
2023-01-24 02:10:17.035542: step: 676/469, loss: 0.4308414161205292
2023-01-24 02:10:17.652859: step: 678/469, loss: 0.6531209945678711
2023-01-24 02:10:18.302473: step: 680/469, loss: 0.2012004852294922
2023-01-24 02:10:18.959397: step: 682/469, loss: 0.16564176976680756
2023-01-24 02:10:19.570575: step: 684/469, loss: 0.17630264163017273
2023-01-24 02:10:20.246635: step: 686/469, loss: 0.11434575915336609
2023-01-24 02:10:20.917821: step: 688/469, loss: 0.2170795500278473
2023-01-24 02:10:21.564678: step: 690/469, loss: 0.18453888595104218
2023-01-24 02:10:22.346296: step: 692/469, loss: 0.3093826174736023
2023-01-24 02:10:22.920809: step: 694/469, loss: 0.15925228595733643
2023-01-24 02:10:23.526374: step: 696/469, loss: 0.14291183650493622
2023-01-24 02:10:24.155860: step: 698/469, loss: 0.15861262381076813
2023-01-24 02:10:24.763453: step: 700/469, loss: 0.15145477652549744
2023-01-24 02:10:25.391353: step: 702/469, loss: 0.17363622784614563
2023-01-24 02:10:25.960093: step: 704/469, loss: 0.182483971118927
2023-01-24 02:10:26.563929: step: 706/469, loss: 0.25083136558532715
2023-01-24 02:10:27.178843: step: 708/469, loss: 1.0732553005218506
2023-01-24 02:10:27.802320: step: 710/469, loss: 0.5289745330810547
2023-01-24 02:10:28.427276: step: 712/469, loss: 0.261511892080307
2023-01-24 02:10:29.015176: step: 714/469, loss: 0.1922958493232727
2023-01-24 02:10:29.640308: step: 716/469, loss: 0.3829682469367981
2023-01-24 02:10:30.432795: step: 718/469, loss: 0.3605692386627197
2023-01-24 02:10:31.052944: step: 720/469, loss: 0.9098966121673584
2023-01-24 02:10:31.713993: step: 722/469, loss: 0.15860295295715332
2023-01-24 02:10:32.377200: step: 724/469, loss: 0.36241665482521057
2023-01-24 02:10:33.043415: step: 726/469, loss: 0.1308407038450241
2023-01-24 02:10:33.691598: step: 728/469, loss: 0.16541844606399536
2023-01-24 02:10:34.376509: step: 730/469, loss: 0.4544020891189575
2023-01-24 02:10:35.012509: step: 732/469, loss: 0.31413185596466064
2023-01-24 02:10:35.694864: step: 734/469, loss: 0.2734842896461487
2023-01-24 02:10:36.321053: step: 736/469, loss: 0.7730116844177246
2023-01-24 02:10:36.936604: step: 738/469, loss: 0.17564791440963745
2023-01-24 02:10:37.554185: step: 740/469, loss: 0.3019658923149109
2023-01-24 02:10:38.228841: step: 742/469, loss: 0.33448800444602966
2023-01-24 02:10:38.800758: step: 744/469, loss: 0.1786222904920578
2023-01-24 02:10:39.412068: step: 746/469, loss: 0.23682421445846558
2023-01-24 02:10:39.996188: step: 748/469, loss: 0.42194151878356934
2023-01-24 02:10:40.604721: step: 750/469, loss: 0.5432416200637817
2023-01-24 02:10:41.197559: step: 752/469, loss: 0.27042850852012634
2023-01-24 02:10:41.836194: step: 754/469, loss: 0.39941948652267456
2023-01-24 02:10:42.465789: step: 756/469, loss: 0.13691657781600952
2023-01-24 02:10:43.104732: step: 758/469, loss: 0.11036242544651031
2023-01-24 02:10:43.863231: step: 760/469, loss: 0.22094962000846863
2023-01-24 02:10:44.502455: step: 762/469, loss: 0.20506402850151062
2023-01-24 02:10:45.151059: step: 764/469, loss: 0.382031112909317
2023-01-24 02:10:45.726690: step: 766/469, loss: 0.6536380052566528
2023-01-24 02:10:46.370190: step: 768/469, loss: 0.37386325001716614
2023-01-24 02:10:46.978163: step: 770/469, loss: 0.12124766409397125
2023-01-24 02:10:47.603007: step: 772/469, loss: 0.2321719527244568
2023-01-24 02:10:48.204195: step: 774/469, loss: 0.2473437637090683
2023-01-24 02:10:48.824063: step: 776/469, loss: 0.25117436051368713
2023-01-24 02:10:49.453120: step: 778/469, loss: 0.369494765996933
2023-01-24 02:10:50.184882: step: 780/469, loss: 0.4436790645122528
2023-01-24 02:10:50.833053: step: 782/469, loss: 0.6400638818740845
2023-01-24 02:10:51.499735: step: 784/469, loss: 0.5189934968948364
2023-01-24 02:10:52.166270: step: 786/469, loss: 0.48824337124824524
2023-01-24 02:10:52.806945: step: 788/469, loss: 0.16848042607307434
2023-01-24 02:10:53.417060: step: 790/469, loss: 0.16847187280654907
2023-01-24 02:10:54.000883: step: 792/469, loss: 0.6210781931877136
2023-01-24 02:10:54.624494: step: 794/469, loss: 0.34443339705467224
2023-01-24 02:10:55.230650: step: 796/469, loss: 0.1160089299082756
2023-01-24 02:10:55.943129: step: 798/469, loss: 0.28355202078819275
2023-01-24 02:10:56.559617: step: 800/469, loss: 0.3433855175971985
2023-01-24 02:10:57.281280: step: 802/469, loss: 0.24356277287006378
2023-01-24 02:10:57.921775: step: 804/469, loss: 8.318450927734375
2023-01-24 02:10:58.552732: step: 806/469, loss: 0.14145974814891815
2023-01-24 02:10:59.232600: step: 808/469, loss: 0.7049055695533752
2023-01-24 02:10:59.842222: step: 810/469, loss: 0.12125016748905182
2023-01-24 02:11:00.457129: step: 812/469, loss: 0.1970774084329605
2023-01-24 02:11:01.063738: step: 814/469, loss: 0.6058725118637085
2023-01-24 02:11:01.663162: step: 816/469, loss: 0.12787580490112305
2023-01-24 02:11:02.382623: step: 818/469, loss: 0.4807584285736084
2023-01-24 02:11:03.000036: step: 820/469, loss: 0.0792413204908371
2023-01-24 02:11:03.581612: step: 822/469, loss: 0.11749916523694992
2023-01-24 02:11:04.180629: step: 824/469, loss: 0.16650857031345367
2023-01-24 02:11:04.845090: step: 826/469, loss: 0.22886303067207336
2023-01-24 02:11:05.440074: step: 828/469, loss: 0.5567625761032104
2023-01-24 02:11:06.066995: step: 830/469, loss: 0.3949889540672302
2023-01-24 02:11:06.664583: step: 832/469, loss: 0.26541900634765625
2023-01-24 02:11:07.274047: step: 834/469, loss: 0.1304713785648346
2023-01-24 02:11:07.972819: step: 836/469, loss: 0.4830150306224823
2023-01-24 02:11:08.567855: step: 838/469, loss: 0.6056756377220154
2023-01-24 02:11:09.144973: step: 840/469, loss: 0.2323174625635147
2023-01-24 02:11:09.775900: step: 842/469, loss: 0.22079682350158691
2023-01-24 02:11:10.383579: step: 844/469, loss: 0.107571542263031
2023-01-24 02:11:11.039738: step: 846/469, loss: 0.16435562074184418
2023-01-24 02:11:11.617997: step: 848/469, loss: 0.3461824655532837
2023-01-24 02:11:12.320229: step: 850/469, loss: 0.5418260097503662
2023-01-24 02:11:12.951855: step: 852/469, loss: 0.1690748780965805
2023-01-24 02:11:13.577377: step: 854/469, loss: 0.49810123443603516
2023-01-24 02:11:14.219303: step: 856/469, loss: 0.1852003037929535
2023-01-24 02:11:14.855231: step: 858/469, loss: 0.2919261157512665
2023-01-24 02:11:15.491469: step: 860/469, loss: 0.5362018346786499
2023-01-24 02:11:16.106335: step: 862/469, loss: 0.6181149482727051
2023-01-24 02:11:16.753475: step: 864/469, loss: 0.16417354345321655
2023-01-24 02:11:17.387520: step: 866/469, loss: 0.1762048304080963
2023-01-24 02:11:18.123767: step: 868/469, loss: 0.1236971765756607
2023-01-24 02:11:18.703705: step: 870/469, loss: 0.6824985146522522
2023-01-24 02:11:19.317583: step: 872/469, loss: 0.1723754107952118
2023-01-24 02:11:19.903952: step: 874/469, loss: 0.6163443922996521
2023-01-24 02:11:20.495423: step: 876/469, loss: 0.14851923286914825
2023-01-24 02:11:21.114330: step: 878/469, loss: 0.16506151854991913
2023-01-24 02:11:21.753160: step: 880/469, loss: 0.9504268169403076
2023-01-24 02:11:22.354286: step: 882/469, loss: 0.5108989477157593
2023-01-24 02:11:22.975071: step: 884/469, loss: 0.3754722476005554
2023-01-24 02:11:23.614771: step: 886/469, loss: 0.2483329325914383
2023-01-24 02:11:24.189810: step: 888/469, loss: 0.09177801012992859
2023-01-24 02:11:24.930574: step: 890/469, loss: 0.41312384605407715
2023-01-24 02:11:25.579980: step: 892/469, loss: 0.07926923036575317
2023-01-24 02:11:26.191519: step: 894/469, loss: 0.3120330572128296
2023-01-24 02:11:26.798230: step: 896/469, loss: 0.2969527542591095
2023-01-24 02:11:27.401868: step: 898/469, loss: 0.10953614115715027
2023-01-24 02:11:28.038367: step: 900/469, loss: 0.5658564567565918
2023-01-24 02:11:28.684743: step: 902/469, loss: 0.1047172024846077
2023-01-24 02:11:29.292429: step: 904/469, loss: 0.41531217098236084
2023-01-24 02:11:29.937440: step: 906/469, loss: 0.12457849085330963
2023-01-24 02:11:30.528629: step: 908/469, loss: 0.18115508556365967
2023-01-24 02:11:31.231287: step: 910/469, loss: 0.2024720162153244
2023-01-24 02:11:31.863798: step: 912/469, loss: 0.5095484852790833
2023-01-24 02:11:32.520822: step: 914/469, loss: 0.2653312385082245
2023-01-24 02:11:33.142030: step: 916/469, loss: 1.2103748321533203
2023-01-24 02:11:33.743798: step: 918/469, loss: 0.41877707839012146
2023-01-24 02:11:34.332073: step: 920/469, loss: 0.12427324801683426
2023-01-24 02:11:34.901994: step: 922/469, loss: 0.6959134340286255
2023-01-24 02:11:35.414704: step: 924/469, loss: 0.3270226716995239
2023-01-24 02:11:36.026177: step: 926/469, loss: 0.1600121706724167
2023-01-24 02:11:36.659340: step: 928/469, loss: 0.24598374962806702
2023-01-24 02:11:37.325153: step: 930/469, loss: 0.28134551644325256
2023-01-24 02:11:37.956238: step: 932/469, loss: 0.39983755350112915
2023-01-24 02:11:38.579390: step: 934/469, loss: 0.0733414888381958
2023-01-24 02:11:39.206846: step: 936/469, loss: 0.13935169577598572
2023-01-24 02:11:39.812335: step: 938/469, loss: 0.09561121463775635
==================================================
Loss: 0.380
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30622342687074827, 'r': 0.29285883708322036, 'f1': 0.29939206041291394}, 'combined': 0.22060467609372605, 'epoch': 10}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.333465374791404, 'r': 0.2597680042895595, 'f1': 0.2920389781284062}, 'combined': 0.15929398807003972, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30727972695927686, 'r': 0.2979505511882172, 'f1': 0.30254323791173504}, 'combined': 0.22292659635601528, 'epoch': 10}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32720070024476655, 'r': 0.25715041309263903, 'f1': 0.28797684580968697}, 'combined': 0.15707827953255651, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29947916666666663, 'r': 0.2738095238095238, 'f1': 0.28606965174129345}, 'combined': 0.1907131011608623, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45454545454545453, 'r': 0.1724137931034483, 'f1': 0.25000000000000006}, 'combined': 0.16666666666666669, 'epoch': 10}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 02:14:31.191221: step: 2/469, loss: 1.3251230716705322
2023-01-24 02:14:31.803195: step: 4/469, loss: 0.3632338047027588
2023-01-24 02:14:32.439013: step: 6/469, loss: 0.12736497819423676
2023-01-24 02:14:33.117998: step: 8/469, loss: 0.07161015272140503
2023-01-24 02:14:33.761053: step: 10/469, loss: 0.1522126942873001
2023-01-24 02:14:34.419720: step: 12/469, loss: 0.35069236159324646
2023-01-24 02:14:35.096234: step: 14/469, loss: 0.13632357120513916
2023-01-24 02:14:35.667522: step: 16/469, loss: 0.16236285865306854
2023-01-24 02:14:36.251701: step: 18/469, loss: 0.9806352853775024
2023-01-24 02:14:36.871526: step: 20/469, loss: 0.10349486768245697
2023-01-24 02:14:37.443978: step: 22/469, loss: 0.07077273726463318
2023-01-24 02:14:38.149623: step: 24/469, loss: 0.11571285128593445
2023-01-24 02:14:38.775711: step: 26/469, loss: 0.1511596441268921
2023-01-24 02:14:39.485793: step: 28/469, loss: 0.35244497656822205
2023-01-24 02:14:40.112807: step: 30/469, loss: 0.22795195877552032
2023-01-24 02:14:40.680385: step: 32/469, loss: 0.08686845749616623
2023-01-24 02:14:41.341669: step: 34/469, loss: 0.15235574543476105
2023-01-24 02:14:41.930482: step: 36/469, loss: 0.19542719423770905
2023-01-24 02:14:42.688652: step: 38/469, loss: 0.22962529957294464
2023-01-24 02:14:43.374002: step: 40/469, loss: 0.2337765395641327
2023-01-24 02:14:43.884708: step: 42/469, loss: 0.18049144744873047
2023-01-24 02:14:44.480752: step: 44/469, loss: 0.16483674943447113
2023-01-24 02:14:45.134405: step: 46/469, loss: 0.1045350506901741
2023-01-24 02:14:45.780010: step: 48/469, loss: 0.11200503259897232
2023-01-24 02:14:46.525798: step: 50/469, loss: 0.3337440490722656
2023-01-24 02:14:47.211576: step: 52/469, loss: 0.4571230709552765
2023-01-24 02:14:47.859400: step: 54/469, loss: 0.30162525177001953
2023-01-24 02:14:48.466132: step: 56/469, loss: 0.2383003532886505
2023-01-24 02:14:49.186329: step: 58/469, loss: 0.36613091826438904
2023-01-24 02:14:49.802287: step: 60/469, loss: 0.14247438311576843
2023-01-24 02:14:50.405150: step: 62/469, loss: 0.5525928735733032
2023-01-24 02:14:51.040689: step: 64/469, loss: 0.11493909358978271
2023-01-24 02:14:51.664658: step: 66/469, loss: 0.34366175532341003
2023-01-24 02:14:52.260251: step: 68/469, loss: 0.14336878061294556
2023-01-24 02:14:52.861039: step: 70/469, loss: 2.229097604751587
2023-01-24 02:14:53.523415: step: 72/469, loss: 0.43957480788230896
2023-01-24 02:14:54.155229: step: 74/469, loss: 0.13142897188663483
2023-01-24 02:14:54.815881: step: 76/469, loss: 0.048468608409166336
2023-01-24 02:14:55.474133: step: 78/469, loss: 0.15741316974163055
2023-01-24 02:14:56.171596: step: 80/469, loss: 0.23230256140232086
2023-01-24 02:14:56.804521: step: 82/469, loss: 0.23593901097774506
2023-01-24 02:14:57.449474: step: 84/469, loss: 0.028536967933177948
2023-01-24 02:14:58.041499: step: 86/469, loss: 0.27680301666259766
2023-01-24 02:14:58.638673: step: 88/469, loss: 0.17345717549324036
2023-01-24 02:14:59.282879: step: 90/469, loss: 0.10710497200489044
2023-01-24 02:14:59.973906: step: 92/469, loss: 0.1412845402956009
2023-01-24 02:15:00.625681: step: 94/469, loss: 0.15174348652362823
2023-01-24 02:15:01.255128: step: 96/469, loss: 0.1045311912894249
2023-01-24 02:15:01.869220: step: 98/469, loss: 0.2490626722574234
2023-01-24 02:15:02.518154: step: 100/469, loss: 0.4371017813682556
2023-01-24 02:15:03.118678: step: 102/469, loss: 0.19339732825756073
2023-01-24 02:15:03.681643: step: 104/469, loss: 0.3534485101699829
2023-01-24 02:15:04.282812: step: 106/469, loss: 0.1900978982448578
2023-01-24 02:15:04.977403: step: 108/469, loss: 0.35299235582351685
2023-01-24 02:15:05.570237: step: 110/469, loss: 0.11424469947814941
2023-01-24 02:15:06.153741: step: 112/469, loss: 0.18450498580932617
2023-01-24 02:15:06.850039: step: 114/469, loss: 0.059010982513427734
2023-01-24 02:15:07.468218: step: 116/469, loss: 0.11341457813978195
2023-01-24 02:15:08.124928: step: 118/469, loss: 0.15264594554901123
2023-01-24 02:15:08.737490: step: 120/469, loss: 0.18101759254932404
2023-01-24 02:15:09.492301: step: 122/469, loss: 0.11984462291002274
2023-01-24 02:15:10.146324: step: 124/469, loss: 0.204877570271492
2023-01-24 02:15:10.768868: step: 126/469, loss: 0.1533675342798233
2023-01-24 02:15:11.474889: step: 128/469, loss: 0.18753385543823242
2023-01-24 02:15:12.024478: step: 130/469, loss: 0.4244779646396637
2023-01-24 02:15:12.618898: step: 132/469, loss: 0.20273007452487946
2023-01-24 02:15:13.224404: step: 134/469, loss: 0.09168665111064911
2023-01-24 02:15:13.826171: step: 136/469, loss: 0.09097080677747726
2023-01-24 02:15:14.418771: step: 138/469, loss: 0.6875452399253845
2023-01-24 02:15:15.030691: step: 140/469, loss: 0.392515629529953
2023-01-24 02:15:15.632207: step: 142/469, loss: 0.12772968411445618
2023-01-24 02:15:16.225602: step: 144/469, loss: 0.061967186629772186
2023-01-24 02:15:16.811199: step: 146/469, loss: 0.32866227626800537
2023-01-24 02:15:17.521082: step: 148/469, loss: 0.4913073182106018
2023-01-24 02:15:18.143500: step: 150/469, loss: 0.062448833137750626
2023-01-24 02:15:18.773229: step: 152/469, loss: 0.10945477336645126
2023-01-24 02:15:19.442806: step: 154/469, loss: 0.2194628268480301
2023-01-24 02:15:20.209174: step: 156/469, loss: 0.17987900972366333
2023-01-24 02:15:20.761919: step: 158/469, loss: 0.15505167841911316
2023-01-24 02:15:21.405574: step: 160/469, loss: 0.3138388395309448
2023-01-24 02:15:22.040561: step: 162/469, loss: 0.34724023938179016
2023-01-24 02:15:22.684297: step: 164/469, loss: 0.1631927639245987
2023-01-24 02:15:23.317690: step: 166/469, loss: 0.162771075963974
2023-01-24 02:15:23.930857: step: 168/469, loss: 0.08693363517522812
2023-01-24 02:15:24.588489: step: 170/469, loss: 0.20622491836547852
2023-01-24 02:15:25.295502: step: 172/469, loss: 0.1325293332338333
2023-01-24 02:15:25.933746: step: 174/469, loss: 0.12262620031833649
2023-01-24 02:15:26.502026: step: 176/469, loss: 0.37906044721603394
2023-01-24 02:15:27.176393: step: 178/469, loss: 0.20451989769935608
2023-01-24 02:15:27.810685: step: 180/469, loss: 0.2792142629623413
2023-01-24 02:15:28.415421: step: 182/469, loss: 0.10610752552747726
2023-01-24 02:15:29.050255: step: 184/469, loss: 0.11265362799167633
2023-01-24 02:15:29.669873: step: 186/469, loss: 0.14442527294158936
2023-01-24 02:15:30.247216: step: 188/469, loss: 0.1498418003320694
2023-01-24 02:15:30.845474: step: 190/469, loss: 0.3022550344467163
2023-01-24 02:15:31.384398: step: 192/469, loss: 0.13683943450450897
2023-01-24 02:15:32.031848: step: 194/469, loss: 0.24792000651359558
2023-01-24 02:15:32.655979: step: 196/469, loss: 0.3452637195587158
2023-01-24 02:15:33.314766: step: 198/469, loss: 0.3051605224609375
2023-01-24 02:15:33.963948: step: 200/469, loss: 0.12394502758979797
2023-01-24 02:15:34.669163: step: 202/469, loss: 0.12998688220977783
2023-01-24 02:15:35.340612: step: 204/469, loss: 0.18461468815803528
2023-01-24 02:15:35.976433: step: 206/469, loss: 0.16999229788780212
2023-01-24 02:15:36.591905: step: 208/469, loss: 0.0982012152671814
2023-01-24 02:15:37.221168: step: 210/469, loss: 0.09659772366285324
2023-01-24 02:15:37.836859: step: 212/469, loss: 0.11084352433681488
2023-01-24 02:15:38.409252: step: 214/469, loss: 0.2170136719942093
2023-01-24 02:15:39.036873: step: 216/469, loss: 0.19260884821414948
2023-01-24 02:15:39.712201: step: 218/469, loss: 0.20957617461681366
2023-01-24 02:15:40.374395: step: 220/469, loss: 0.1567096710205078
2023-01-24 02:15:41.015444: step: 222/469, loss: 0.7105504870414734
2023-01-24 02:15:41.653601: step: 224/469, loss: 0.12549707293510437
2023-01-24 02:15:42.246996: step: 226/469, loss: 0.1386052370071411
2023-01-24 02:15:42.903308: step: 228/469, loss: 0.24420537054538727
2023-01-24 02:15:43.488277: step: 230/469, loss: 0.12504376471042633
2023-01-24 02:15:44.075430: step: 232/469, loss: 0.12796583771705627
2023-01-24 02:15:44.702526: step: 234/469, loss: 0.2811918556690216
2023-01-24 02:15:45.291019: step: 236/469, loss: 0.17327384650707245
2023-01-24 02:15:45.913371: step: 238/469, loss: 0.12080953270196915
2023-01-24 02:15:46.515472: step: 240/469, loss: 0.17505046725273132
2023-01-24 02:15:47.142525: step: 242/469, loss: 0.31011468172073364
2023-01-24 02:15:47.730919: step: 244/469, loss: 0.12590456008911133
2023-01-24 02:15:48.350457: step: 246/469, loss: 0.4992937445640564
2023-01-24 02:15:49.018378: step: 248/469, loss: 0.10226418823003769
2023-01-24 02:15:49.629661: step: 250/469, loss: 0.29992449283599854
2023-01-24 02:15:50.278582: step: 252/469, loss: 0.13194029033184052
2023-01-24 02:15:50.962294: step: 254/469, loss: 0.43244099617004395
2023-01-24 02:15:51.622667: step: 256/469, loss: 0.46475687623023987
2023-01-24 02:15:52.243331: step: 258/469, loss: 0.07229424268007278
2023-01-24 02:15:52.900149: step: 260/469, loss: 0.1569201499223709
2023-01-24 02:15:53.529524: step: 262/469, loss: 0.033908870071172714
2023-01-24 02:15:54.128700: step: 264/469, loss: 0.20522554218769073
2023-01-24 02:15:54.739044: step: 266/469, loss: 0.16309337317943573
2023-01-24 02:15:55.346686: step: 268/469, loss: 0.10002125799655914
2023-01-24 02:15:56.001599: step: 270/469, loss: 0.14310507476329803
2023-01-24 02:15:56.601226: step: 272/469, loss: 0.09983787685632706
2023-01-24 02:15:57.201458: step: 274/469, loss: 0.7703390717506409
2023-01-24 02:15:57.915542: step: 276/469, loss: 0.16378170251846313
2023-01-24 02:15:58.505338: step: 278/469, loss: 0.7479329109191895
2023-01-24 02:15:59.062337: step: 280/469, loss: 0.5635196566581726
2023-01-24 02:15:59.680541: step: 282/469, loss: 0.14695723354816437
2023-01-24 02:16:00.252788: step: 284/469, loss: 0.11088906228542328
2023-01-24 02:16:00.830497: step: 286/469, loss: 0.3897385001182556
2023-01-24 02:16:01.446642: step: 288/469, loss: 0.16940830647945404
2023-01-24 02:16:02.004731: step: 290/469, loss: 0.18020634353160858
2023-01-24 02:16:02.613903: step: 292/469, loss: 0.08611126244068146
2023-01-24 02:16:03.301852: step: 294/469, loss: 0.18027669191360474
2023-01-24 02:16:03.931797: step: 296/469, loss: 0.23933443427085876
2023-01-24 02:16:04.568202: step: 298/469, loss: 0.2507540285587311
2023-01-24 02:16:05.151842: step: 300/469, loss: 0.27553731203079224
2023-01-24 02:16:05.767586: step: 302/469, loss: 0.21468937397003174
2023-01-24 02:16:06.315352: step: 304/469, loss: 0.29174986481666565
2023-01-24 02:16:06.919074: step: 306/469, loss: 0.31253933906555176
2023-01-24 02:16:07.510089: step: 308/469, loss: 0.24606849253177643
2023-01-24 02:16:08.147805: step: 310/469, loss: 0.11470603942871094
2023-01-24 02:16:08.778717: step: 312/469, loss: 0.11838089674711227
2023-01-24 02:16:09.409919: step: 314/469, loss: 0.06810196489095688
2023-01-24 02:16:10.094927: step: 316/469, loss: 0.5085752010345459
2023-01-24 02:16:10.681927: step: 318/469, loss: 0.7989282608032227
2023-01-24 02:16:11.279008: step: 320/469, loss: 0.1279248297214508
2023-01-24 02:16:11.913393: step: 322/469, loss: 1.1774379014968872
2023-01-24 02:16:12.557258: step: 324/469, loss: 1.7839431762695312
2023-01-24 02:16:13.161545: step: 326/469, loss: 0.08726254850625992
2023-01-24 02:16:13.920657: step: 328/469, loss: 0.12255539000034332
2023-01-24 02:16:14.556394: step: 330/469, loss: 0.2260095477104187
2023-01-24 02:16:15.178878: step: 332/469, loss: 0.29294177889823914
2023-01-24 02:16:15.836692: step: 334/469, loss: 0.3267204761505127
2023-01-24 02:16:16.394646: step: 336/469, loss: 0.46942639350891113
2023-01-24 02:16:17.039819: step: 338/469, loss: 0.167597696185112
2023-01-24 02:16:17.644769: step: 340/469, loss: 2.3828961849212646
2023-01-24 02:16:18.226546: step: 342/469, loss: 0.14724482595920563
2023-01-24 02:16:18.844643: step: 344/469, loss: 0.24119175970554352
2023-01-24 02:16:19.460741: step: 346/469, loss: 0.15888085961341858
2023-01-24 02:16:20.068299: step: 348/469, loss: 0.22132325172424316
2023-01-24 02:16:20.671845: step: 350/469, loss: 0.11238407343626022
2023-01-24 02:16:21.265821: step: 352/469, loss: 0.23809415102005005
2023-01-24 02:16:21.929296: step: 354/469, loss: 0.1637771725654602
2023-01-24 02:16:22.581347: step: 356/469, loss: 0.39375394582748413
2023-01-24 02:16:23.253710: step: 358/469, loss: 0.30669301748275757
2023-01-24 02:16:23.871941: step: 360/469, loss: 0.22790245711803436
2023-01-24 02:16:24.486612: step: 362/469, loss: 0.13602589070796967
2023-01-24 02:16:25.116480: step: 364/469, loss: 0.22972773015499115
2023-01-24 02:16:25.813138: step: 366/469, loss: 0.08034169673919678
2023-01-24 02:16:26.408604: step: 368/469, loss: 0.22970351576805115
2023-01-24 02:16:27.058212: step: 370/469, loss: 0.3514385223388672
2023-01-24 02:16:27.747144: step: 372/469, loss: 0.03130142763257027
2023-01-24 02:16:28.340825: step: 374/469, loss: 0.43215981125831604
2023-01-24 02:16:28.927106: step: 376/469, loss: 0.12602467834949493
2023-01-24 02:16:29.574366: step: 378/469, loss: 0.140254408121109
2023-01-24 02:16:30.250464: step: 380/469, loss: 0.6630123853683472
2023-01-24 02:16:30.869660: step: 382/469, loss: 0.0608147494494915
2023-01-24 02:16:31.574860: step: 384/469, loss: 0.4181896448135376
2023-01-24 02:16:32.158707: step: 386/469, loss: 0.13040032982826233
2023-01-24 02:16:32.763194: step: 388/469, loss: 0.14064259827136993
2023-01-24 02:16:33.419955: step: 390/469, loss: 0.42392319440841675
2023-01-24 02:16:34.026595: step: 392/469, loss: 0.11747951805591583
2023-01-24 02:16:34.617165: step: 394/469, loss: 0.18643918633460999
2023-01-24 02:16:35.201898: step: 396/469, loss: 0.29469653964042664
2023-01-24 02:16:35.859373: step: 398/469, loss: 1.9678469896316528
2023-01-24 02:16:36.494918: step: 400/469, loss: 0.29438015818595886
2023-01-24 02:16:37.134557: step: 402/469, loss: 0.19751419126987457
2023-01-24 02:16:37.754798: step: 404/469, loss: 0.09369108080863953
2023-01-24 02:16:38.329804: step: 406/469, loss: 0.15228500962257385
2023-01-24 02:16:38.931476: step: 408/469, loss: 0.3336558938026428
2023-01-24 02:16:39.511398: step: 410/469, loss: 0.3445265591144562
2023-01-24 02:16:40.066754: step: 412/469, loss: 0.19449476897716522
2023-01-24 02:16:40.675980: step: 414/469, loss: 0.04109570384025574
2023-01-24 02:16:41.403521: step: 416/469, loss: 0.0452982597053051
2023-01-24 02:16:42.029280: step: 418/469, loss: 0.06610807776451111
2023-01-24 02:16:42.668475: step: 420/469, loss: 0.25247299671173096
2023-01-24 02:16:43.266854: step: 422/469, loss: 0.4787249267101288
2023-01-24 02:16:43.871089: step: 424/469, loss: 0.19258639216423035
2023-01-24 02:16:44.504385: step: 426/469, loss: 0.09108295291662216
2023-01-24 02:16:45.070204: step: 428/469, loss: 0.1806219518184662
2023-01-24 02:16:45.701166: step: 430/469, loss: 0.24744611978530884
2023-01-24 02:16:46.287371: step: 432/469, loss: 0.31874167919158936
2023-01-24 02:16:46.929447: step: 434/469, loss: 0.08911796659231186
2023-01-24 02:16:47.569324: step: 436/469, loss: 0.23850701749324799
2023-01-24 02:16:48.177108: step: 438/469, loss: 0.20409946143627167
2023-01-24 02:16:48.899840: step: 440/469, loss: 0.5788114070892334
2023-01-24 02:16:49.525177: step: 442/469, loss: 0.9260547161102295
2023-01-24 02:16:50.162057: step: 444/469, loss: 0.08772344142198563
2023-01-24 02:16:50.764382: step: 446/469, loss: 0.36653298139572144
2023-01-24 02:16:51.426577: step: 448/469, loss: 0.14815068244934082
2023-01-24 02:16:52.036569: step: 450/469, loss: 0.28155285120010376
2023-01-24 02:16:52.720324: step: 452/469, loss: 0.07654920965433121
2023-01-24 02:16:53.323748: step: 454/469, loss: 0.1313786804676056
2023-01-24 02:16:53.930245: step: 456/469, loss: 0.263245552778244
2023-01-24 02:16:54.582307: step: 458/469, loss: 0.11381533741950989
2023-01-24 02:16:55.256840: step: 460/469, loss: 0.16223829984664917
2023-01-24 02:16:55.964085: step: 462/469, loss: 0.2280503362417221
2023-01-24 02:16:56.565997: step: 464/469, loss: 0.5836884379386902
2023-01-24 02:16:57.161445: step: 466/469, loss: 0.3427771329879761
2023-01-24 02:16:57.769974: step: 468/469, loss: 0.15839408338069916
2023-01-24 02:16:58.359109: step: 470/469, loss: 0.4516873061656952
2023-01-24 02:16:58.973397: step: 472/469, loss: 0.056761328130960464
2023-01-24 02:16:59.589581: step: 474/469, loss: 0.13814318180084229
2023-01-24 02:17:00.269632: step: 476/469, loss: 0.42337143421173096
2023-01-24 02:17:00.927612: step: 478/469, loss: 0.40164101123809814
2023-01-24 02:17:01.534215: step: 480/469, loss: 0.10862606018781662
2023-01-24 02:17:02.121780: step: 482/469, loss: 0.2292182892560959
2023-01-24 02:17:02.766706: step: 484/469, loss: 0.5554975271224976
2023-01-24 02:17:03.429242: step: 486/469, loss: 0.09619907289743423
2023-01-24 02:17:04.014394: step: 488/469, loss: 0.05585966631770134
2023-01-24 02:17:04.659871: step: 490/469, loss: 0.2571108341217041
2023-01-24 02:17:05.307731: step: 492/469, loss: 0.45524880290031433
2023-01-24 02:17:05.938741: step: 494/469, loss: 0.15589767694473267
2023-01-24 02:17:06.635861: step: 496/469, loss: 0.09902490675449371
2023-01-24 02:17:07.226968: step: 498/469, loss: 0.3878598213195801
2023-01-24 02:17:07.846807: step: 500/469, loss: 0.09806180000305176
2023-01-24 02:17:08.519893: step: 502/469, loss: 0.08868704736232758
2023-01-24 02:17:09.135417: step: 504/469, loss: 0.0991825982928276
2023-01-24 02:17:09.756711: step: 506/469, loss: 0.3053373396396637
2023-01-24 02:17:10.380455: step: 508/469, loss: 0.18532225489616394
2023-01-24 02:17:11.020179: step: 510/469, loss: 0.2965945601463318
2023-01-24 02:17:11.649136: step: 512/469, loss: 0.18866781890392303
2023-01-24 02:17:12.359396: step: 514/469, loss: 0.21066582202911377
2023-01-24 02:17:12.977192: step: 516/469, loss: 0.30293014645576477
2023-01-24 02:17:13.651849: step: 518/469, loss: 0.3269627094268799
2023-01-24 02:17:14.215295: step: 520/469, loss: 0.07745165377855301
2023-01-24 02:17:14.791886: step: 522/469, loss: 0.05759430676698685
2023-01-24 02:17:15.384471: step: 524/469, loss: 0.19504407048225403
2023-01-24 02:17:16.002291: step: 526/469, loss: 0.20144660770893097
2023-01-24 02:17:16.667668: step: 528/469, loss: 0.20814774930477142
2023-01-24 02:17:17.274398: step: 530/469, loss: 0.12292114645242691
2023-01-24 02:17:17.956164: step: 532/469, loss: 0.3041295111179352
2023-01-24 02:17:18.567471: step: 534/469, loss: 0.10824405401945114
2023-01-24 02:17:19.144003: step: 536/469, loss: 0.16285809874534607
2023-01-24 02:17:19.841971: step: 538/469, loss: 0.14948678016662598
2023-01-24 02:17:20.553167: step: 540/469, loss: 0.38732603192329407
2023-01-24 02:17:21.125671: step: 542/469, loss: 0.3438386023044586
2023-01-24 02:17:21.745640: step: 544/469, loss: 0.014788689091801643
2023-01-24 02:17:22.472972: step: 546/469, loss: 0.15183618664741516
2023-01-24 02:17:23.146249: step: 548/469, loss: 0.25229960680007935
2023-01-24 02:17:23.733018: step: 550/469, loss: 0.06977144628763199
2023-01-24 02:17:24.304414: step: 552/469, loss: 0.26242679357528687
2023-01-24 02:17:24.928589: step: 554/469, loss: 0.20218858122825623
2023-01-24 02:17:25.563079: step: 556/469, loss: 0.16469812393188477
2023-01-24 02:17:26.167039: step: 558/469, loss: 0.12485162168741226
2023-01-24 02:17:26.791204: step: 560/469, loss: 0.2898695170879364
2023-01-24 02:17:27.368827: step: 562/469, loss: 0.20773828029632568
2023-01-24 02:17:28.009082: step: 564/469, loss: 0.2075953632593155
2023-01-24 02:17:28.642058: step: 566/469, loss: 0.1356946974992752
2023-01-24 02:17:29.304271: step: 568/469, loss: 0.2844195067882538
2023-01-24 02:17:29.909343: step: 570/469, loss: 0.17094819247722626
2023-01-24 02:17:30.563655: step: 572/469, loss: 0.24282239377498627
2023-01-24 02:17:31.150621: step: 574/469, loss: 0.13948263227939606
2023-01-24 02:17:31.763521: step: 576/469, loss: 0.08740594983100891
2023-01-24 02:17:32.399232: step: 578/469, loss: 0.3155202269554138
2023-01-24 02:17:32.948168: step: 580/469, loss: 0.07801327854394913
2023-01-24 02:17:33.683408: step: 582/469, loss: 0.3262689411640167
2023-01-24 02:17:34.279500: step: 584/469, loss: 0.07614899426698685
2023-01-24 02:17:34.960550: step: 586/469, loss: 0.1717415601015091
2023-01-24 02:17:35.596291: step: 588/469, loss: 0.46940499544143677
2023-01-24 02:17:36.220835: step: 590/469, loss: 0.1658959835767746
2023-01-24 02:17:36.879141: step: 592/469, loss: 0.21351441740989685
2023-01-24 02:17:37.503763: step: 594/469, loss: 0.07654142379760742
2023-01-24 02:17:38.158222: step: 596/469, loss: 0.09888766705989838
2023-01-24 02:17:38.784593: step: 598/469, loss: 0.2221735268831253
2023-01-24 02:17:39.412241: step: 600/469, loss: 0.6418651938438416
2023-01-24 02:17:40.044801: step: 602/469, loss: 0.27026283740997314
2023-01-24 02:17:40.681140: step: 604/469, loss: 0.21834880113601685
2023-01-24 02:17:41.327287: step: 606/469, loss: 0.36651134490966797
2023-01-24 02:17:41.896237: step: 608/469, loss: 0.06847436726093292
2023-01-24 02:17:42.601292: step: 610/469, loss: 0.10016592592000961
2023-01-24 02:17:43.225823: step: 612/469, loss: 0.47368985414505005
2023-01-24 02:17:43.870552: step: 614/469, loss: 0.22600539028644562
2023-01-24 02:17:44.473680: step: 616/469, loss: 0.16001629829406738
2023-01-24 02:17:45.082975: step: 618/469, loss: 0.11494092643260956
2023-01-24 02:17:45.678211: step: 620/469, loss: 0.39927324652671814
2023-01-24 02:17:46.373045: step: 622/469, loss: 0.4548013508319855
2023-01-24 02:17:47.010643: step: 624/469, loss: 0.07355457544326782
2023-01-24 02:17:47.644330: step: 626/469, loss: 0.21411897242069244
2023-01-24 02:17:48.333314: step: 628/469, loss: 0.1988099217414856
2023-01-24 02:17:48.948376: step: 630/469, loss: 0.5104672908782959
2023-01-24 02:17:49.510711: step: 632/469, loss: 0.18827183544635773
2023-01-24 02:17:50.095310: step: 634/469, loss: 0.10365868359804153
2023-01-24 02:17:50.777613: step: 636/469, loss: 0.30276229977607727
2023-01-24 02:17:51.469694: step: 638/469, loss: 0.1437106877565384
2023-01-24 02:17:52.022472: step: 640/469, loss: 0.04100235179066658
2023-01-24 02:17:52.649614: step: 642/469, loss: 1.0136048793792725
2023-01-24 02:17:53.228989: step: 644/469, loss: 0.17712734639644623
2023-01-24 02:17:53.841274: step: 646/469, loss: 0.6398909091949463
2023-01-24 02:17:54.459545: step: 648/469, loss: 0.13892191648483276
2023-01-24 02:17:55.100151: step: 650/469, loss: 0.19111551344394684
2023-01-24 02:17:55.746881: step: 652/469, loss: 0.7705939412117004
2023-01-24 02:17:56.394526: step: 654/469, loss: 0.15863873064517975
2023-01-24 02:17:57.048056: step: 656/469, loss: 0.4326806664466858
2023-01-24 02:17:57.696536: step: 658/469, loss: 0.1146983727812767
2023-01-24 02:17:58.390959: step: 660/469, loss: 0.23201973736286163
2023-01-24 02:17:59.052006: step: 662/469, loss: 0.9465963244438171
2023-01-24 02:17:59.720751: step: 664/469, loss: 0.15898959338665009
2023-01-24 02:18:00.355002: step: 666/469, loss: 0.5527649521827698
2023-01-24 02:18:00.968632: step: 668/469, loss: 0.49680909514427185
2023-01-24 02:18:01.599322: step: 670/469, loss: 0.17138074338436127
2023-01-24 02:18:02.268452: step: 672/469, loss: 0.15890038013458252
2023-01-24 02:18:02.886317: step: 674/469, loss: 0.12234514206647873
2023-01-24 02:18:03.580077: step: 676/469, loss: 0.3505050241947174
2023-01-24 02:18:04.338897: step: 678/469, loss: 0.137950599193573
2023-01-24 02:18:05.113892: step: 680/469, loss: 0.7775441408157349
2023-01-24 02:18:05.801016: step: 682/469, loss: 0.09802941232919693
2023-01-24 02:18:06.508456: step: 684/469, loss: 0.2668774425983429
2023-01-24 02:18:07.096771: step: 686/469, loss: 0.2370632290840149
2023-01-24 02:18:07.703576: step: 688/469, loss: 0.3069482445716858
2023-01-24 02:18:08.356612: step: 690/469, loss: 0.6174138188362122
2023-01-24 02:18:08.925354: step: 692/469, loss: 0.1225072517991066
2023-01-24 02:18:09.569755: step: 694/469, loss: 0.03507116809487343
2023-01-24 02:18:10.211351: step: 696/469, loss: 0.1423187255859375
2023-01-24 02:18:10.738785: step: 698/469, loss: 0.10632891207933426
2023-01-24 02:18:11.406372: step: 700/469, loss: 0.07801169157028198
2023-01-24 02:18:12.054097: step: 702/469, loss: 0.17713706195354462
2023-01-24 02:18:12.636717: step: 704/469, loss: 0.10139768570661545
2023-01-24 02:18:13.250805: step: 706/469, loss: 0.12162438780069351
2023-01-24 02:18:13.758523: step: 708/469, loss: 0.37717896699905396
2023-01-24 02:18:14.452609: step: 710/469, loss: 0.14772465825080872
2023-01-24 02:18:15.149354: step: 712/469, loss: 0.3026566505432129
2023-01-24 02:18:15.771247: step: 714/469, loss: 0.16358682513237
2023-01-24 02:18:16.377509: step: 716/469, loss: 0.11009292304515839
2023-01-24 02:18:17.015493: step: 718/469, loss: 0.47127994894981384
2023-01-24 02:18:17.664152: step: 720/469, loss: 0.573236882686615
2023-01-24 02:18:18.257273: step: 722/469, loss: 0.26310306787490845
2023-01-24 02:18:18.942842: step: 724/469, loss: 0.14633750915527344
2023-01-24 02:18:19.608417: step: 726/469, loss: 0.39093732833862305
2023-01-24 02:18:20.385206: step: 728/469, loss: 0.09805526584386826
2023-01-24 02:18:21.090896: step: 730/469, loss: 0.07600551098585129
2023-01-24 02:18:21.698065: step: 732/469, loss: 0.30992385745048523
2023-01-24 02:18:22.343964: step: 734/469, loss: 1.5432090759277344
2023-01-24 02:18:22.944812: step: 736/469, loss: 0.25338101387023926
2023-01-24 02:18:23.572209: step: 738/469, loss: 0.42322248220443726
2023-01-24 02:18:24.210102: step: 740/469, loss: 0.4659385085105896
2023-01-24 02:18:24.840382: step: 742/469, loss: 0.14605183899402618
2023-01-24 02:18:25.516514: step: 744/469, loss: 0.08464605361223221
2023-01-24 02:18:26.118032: step: 746/469, loss: 0.8135920763015747
2023-01-24 02:18:26.693431: step: 748/469, loss: 0.1676606982946396
2023-01-24 02:18:27.375025: step: 750/469, loss: 0.1331390142440796
2023-01-24 02:18:28.015325: step: 752/469, loss: 0.10761026293039322
2023-01-24 02:18:28.668496: step: 754/469, loss: 0.13111016154289246
2023-01-24 02:18:29.329456: step: 756/469, loss: 0.25879067182540894
2023-01-24 02:18:30.014684: step: 758/469, loss: 0.30239158868789673
2023-01-24 02:18:30.631876: step: 760/469, loss: 0.14022549986839294
2023-01-24 02:18:31.357100: step: 762/469, loss: 0.16620653867721558
2023-01-24 02:18:31.952233: step: 764/469, loss: 0.18070916831493378
2023-01-24 02:18:32.578283: step: 766/469, loss: 0.25677546858787537
2023-01-24 02:18:33.229902: step: 768/469, loss: 0.10850760340690613
2023-01-24 02:18:33.816806: step: 770/469, loss: 0.6034120917320251
2023-01-24 02:18:34.453415: step: 772/469, loss: 1.017383098602295
2023-01-24 02:18:35.026679: step: 774/469, loss: 0.1369587481021881
2023-01-24 02:18:35.677992: step: 776/469, loss: 0.3048272728919983
2023-01-24 02:18:36.288927: step: 778/469, loss: 0.13232165575027466
2023-01-24 02:18:36.916547: step: 780/469, loss: 0.209258571267128
2023-01-24 02:18:37.601437: step: 782/469, loss: 0.14465820789337158
2023-01-24 02:18:38.216067: step: 784/469, loss: 0.05674801766872406
2023-01-24 02:18:38.815497: step: 786/469, loss: 0.1617845743894577
2023-01-24 02:18:39.448122: step: 788/469, loss: 0.1544911116361618
2023-01-24 02:18:40.043454: step: 790/469, loss: 0.08833402395248413
2023-01-24 02:18:40.636466: step: 792/469, loss: 0.2832323908805847
2023-01-24 02:18:41.224231: step: 794/469, loss: 1.1684081554412842
2023-01-24 02:18:41.858891: step: 796/469, loss: 0.11391933262348175
2023-01-24 02:18:42.437366: step: 798/469, loss: 0.05843877047300339
2023-01-24 02:18:43.105979: step: 800/469, loss: 0.13185347616672516
2023-01-24 02:18:43.747742: step: 802/469, loss: 0.1924135386943817
2023-01-24 02:18:44.332649: step: 804/469, loss: 0.20566807687282562
2023-01-24 02:18:44.929559: step: 806/469, loss: 0.1436580866575241
2023-01-24 02:18:45.478654: step: 808/469, loss: 0.19666725397109985
2023-01-24 02:18:46.101182: step: 810/469, loss: 0.14203034341335297
2023-01-24 02:18:46.764641: step: 812/469, loss: 0.12521588802337646
2023-01-24 02:18:47.398483: step: 814/469, loss: 0.20856155455112457
2023-01-24 02:18:47.977817: step: 816/469, loss: 0.18280331790447235
2023-01-24 02:18:48.672081: step: 818/469, loss: 0.5503715872764587
2023-01-24 02:18:49.248017: step: 820/469, loss: 0.09337566047906876
2023-01-24 02:18:49.960531: step: 822/469, loss: 0.27005404233932495
2023-01-24 02:18:50.627116: step: 824/469, loss: 0.25442826747894287
2023-01-24 02:18:51.350123: step: 826/469, loss: 0.12735864520072937
2023-01-24 02:18:51.967004: step: 828/469, loss: 1.8254402875900269
2023-01-24 02:18:52.628137: step: 830/469, loss: 0.19316191971302032
2023-01-24 02:18:53.288028: step: 832/469, loss: 0.11748109012842178
2023-01-24 02:18:53.930791: step: 834/469, loss: 1.3834993839263916
2023-01-24 02:18:54.613446: step: 836/469, loss: 0.3081236183643341
2023-01-24 02:18:55.217980: step: 838/469, loss: 0.19454190135002136
2023-01-24 02:18:55.871240: step: 840/469, loss: 0.16552944481372833
2023-01-24 02:18:56.468147: step: 842/469, loss: 0.2136889398097992
2023-01-24 02:18:57.104763: step: 844/469, loss: 0.2318936586380005
2023-01-24 02:18:57.715419: step: 846/469, loss: 0.46329569816589355
2023-01-24 02:18:58.321230: step: 848/469, loss: 0.36109212040901184
2023-01-24 02:18:58.947414: step: 850/469, loss: 0.09724821150302887
2023-01-24 02:18:59.594669: step: 852/469, loss: 0.15499748289585114
2023-01-24 02:19:00.197422: step: 854/469, loss: 0.24015632271766663
2023-01-24 02:19:00.806358: step: 856/469, loss: 0.09081809967756271
2023-01-24 02:19:01.471771: step: 858/469, loss: 0.18688549101352692
2023-01-24 02:19:02.111678: step: 860/469, loss: 0.1367340087890625
2023-01-24 02:19:02.707126: step: 862/469, loss: 0.13588404655456543
2023-01-24 02:19:03.350718: step: 864/469, loss: 1.043573260307312
2023-01-24 02:19:03.934680: step: 866/469, loss: 0.0923236832022667
2023-01-24 02:19:04.525271: step: 868/469, loss: 0.17240412533283234
2023-01-24 02:19:05.087287: step: 870/469, loss: 0.5087149739265442
2023-01-24 02:19:05.698008: step: 872/469, loss: 0.4754045307636261
2023-01-24 02:19:06.362321: step: 874/469, loss: 0.42853158712387085
2023-01-24 02:19:07.019570: step: 876/469, loss: 0.8060194253921509
2023-01-24 02:19:07.599450: step: 878/469, loss: 0.08807642012834549
2023-01-24 02:19:08.329346: step: 880/469, loss: 1.2634409666061401
2023-01-24 02:19:08.912380: step: 882/469, loss: 0.10770653188228607
2023-01-24 02:19:09.501103: step: 884/469, loss: 0.1813407838344574
2023-01-24 02:19:10.138140: step: 886/469, loss: 0.14426329731941223
2023-01-24 02:19:10.728512: step: 888/469, loss: 0.1587604135274887
2023-01-24 02:19:11.398157: step: 890/469, loss: 0.08517385274171829
2023-01-24 02:19:12.020280: step: 892/469, loss: 0.17000234127044678
2023-01-24 02:19:12.698079: step: 894/469, loss: 0.41661056876182556
2023-01-24 02:19:13.355778: step: 896/469, loss: 0.8561276197433472
2023-01-24 02:19:13.945660: step: 898/469, loss: 0.060232289135456085
2023-01-24 02:19:14.532932: step: 900/469, loss: 0.25848907232284546
2023-01-24 02:19:15.162999: step: 902/469, loss: 0.3494167923927307
2023-01-24 02:19:15.784821: step: 904/469, loss: 0.08899218589067459
2023-01-24 02:19:16.475453: step: 906/469, loss: 0.1723947674036026
2023-01-24 02:19:17.144136: step: 908/469, loss: 0.3268420100212097
2023-01-24 02:19:17.762928: step: 910/469, loss: 0.09955978393554688
2023-01-24 02:19:18.409808: step: 912/469, loss: 0.3480122983455658
2023-01-24 02:19:19.072314: step: 914/469, loss: 0.24432191252708435
2023-01-24 02:19:19.687431: step: 916/469, loss: 0.5372911691665649
2023-01-24 02:19:20.358369: step: 918/469, loss: 0.1267661452293396
2023-01-24 02:19:21.006537: step: 920/469, loss: 0.10970328748226166
2023-01-24 02:19:21.680472: step: 922/469, loss: 0.447407066822052
2023-01-24 02:19:22.296051: step: 924/469, loss: 0.173196479678154
2023-01-24 02:19:22.913012: step: 926/469, loss: 0.4349397122859955
2023-01-24 02:19:23.467435: step: 928/469, loss: 0.10653305798768997
2023-01-24 02:19:24.088444: step: 930/469, loss: 0.1968565434217453
2023-01-24 02:19:24.727135: step: 932/469, loss: 0.17384858429431915
2023-01-24 02:19:25.369907: step: 934/469, loss: 0.21895577013492584
2023-01-24 02:19:26.040548: step: 936/469, loss: 0.09605295211076736
2023-01-24 02:19:26.596889: step: 938/469, loss: 0.15988856554031372
==================================================
Loss: 0.270
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3293802921328997, 'r': 0.3168800912929414, 'f1': 0.3230093000220119}, 'combined': 0.23800685264779822, 'epoch': 11}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3258391645205199, 'r': 0.25531507137772247, 'f1': 0.2862980063068163}, 'combined': 0.15616254889462705, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3374512001156738, 'r': 0.31632047980482514, 'f1': 0.3265443542745208}, 'combined': 0.24061162946543635, 'epoch': 11}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3332772427937594, 'r': 0.2649752278021747, 'f1': 0.2952272415777543}, 'combined': 0.16103304086059325, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3274639321114214, 'r': 0.31627920577744495, 'f1': 0.32177440433342375}, 'combined': 0.23709692950883854, 'epoch': 11}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32741567997571774, 'r': 0.2612136074463183, 'f1': 0.29059182996318156}, 'combined': 0.15850463452537175, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.287037037037037, 'r': 0.2952380952380952, 'f1': 0.2910798122065727}, 'combined': 0.19405320813771512, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.30952380952380953, 'r': 0.2826086956521739, 'f1': 0.29545454545454547}, 'combined': 0.14772727272727273, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.1724137931034483, 'f1': 0.25641025641025644}, 'combined': 0.17094017094017094, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 02:22:13.078937: step: 2/469, loss: 0.09010709822177887
2023-01-24 02:22:13.713931: step: 4/469, loss: 0.3958519697189331
2023-01-24 02:22:14.393991: step: 6/469, loss: 0.12911579012870789
2023-01-24 02:22:15.046148: step: 8/469, loss: 0.14571508765220642
2023-01-24 02:22:15.707066: step: 10/469, loss: 0.18585599958896637
2023-01-24 02:22:16.311868: step: 12/469, loss: 0.7505022287368774
2023-01-24 02:22:16.843978: step: 14/469, loss: 0.42242422699928284
2023-01-24 02:22:17.477317: step: 16/469, loss: 0.06319308280944824
2023-01-24 02:22:18.091522: step: 18/469, loss: 0.17724671959877014
2023-01-24 02:22:18.646278: step: 20/469, loss: 0.2355174422264099
2023-01-24 02:22:19.246922: step: 22/469, loss: 0.06950865685939789
2023-01-24 02:22:19.842071: step: 24/469, loss: 0.09060060977935791
2023-01-24 02:22:20.586437: step: 26/469, loss: 0.21231645345687866
2023-01-24 02:22:21.187343: step: 28/469, loss: 0.18261641263961792
2023-01-24 02:22:21.845630: step: 30/469, loss: 0.40979400277137756
2023-01-24 02:22:22.528551: step: 32/469, loss: 0.11734183132648468
2023-01-24 02:22:23.144925: step: 34/469, loss: 0.26135605573654175
2023-01-24 02:22:23.735492: step: 36/469, loss: 0.222601518034935
2023-01-24 02:22:24.333037: step: 38/469, loss: 0.16646534204483032
2023-01-24 02:22:24.883828: step: 40/469, loss: 0.4240712821483612
2023-01-24 02:22:25.584896: step: 42/469, loss: 0.1280793845653534
2023-01-24 02:22:26.282592: step: 44/469, loss: 1.9127705097198486
2023-01-24 02:22:26.889183: step: 46/469, loss: 0.3722122609615326
2023-01-24 02:22:27.525537: step: 48/469, loss: 0.1303377002477646
2023-01-24 02:22:28.155245: step: 50/469, loss: 0.5981952548027039
2023-01-24 02:22:28.809260: step: 52/469, loss: 0.4974333345890045
2023-01-24 02:22:29.405834: step: 54/469, loss: 0.13185831904411316
2023-01-24 02:22:30.001492: step: 56/469, loss: 0.19388312101364136
2023-01-24 02:22:30.640238: step: 58/469, loss: 1.2019239664077759
2023-01-24 02:22:31.235506: step: 60/469, loss: 0.22199219465255737
2023-01-24 02:22:31.881208: step: 62/469, loss: 0.05821703374385834
2023-01-24 02:22:32.586104: step: 64/469, loss: 0.06818190217018127
2023-01-24 02:22:33.266838: step: 66/469, loss: 0.05169495567679405
2023-01-24 02:22:33.889783: step: 68/469, loss: 0.03145342320203781
2023-01-24 02:22:34.503144: step: 70/469, loss: 0.11096139252185822
2023-01-24 02:22:35.115532: step: 72/469, loss: 0.5940859913825989
2023-01-24 02:22:35.688257: step: 74/469, loss: 0.08544835448265076
2023-01-24 02:22:36.361674: step: 76/469, loss: 0.11480628699064255
2023-01-24 02:22:37.026190: step: 78/469, loss: 0.6271916627883911
2023-01-24 02:22:37.641379: step: 80/469, loss: 0.1922295242547989
2023-01-24 02:22:38.352616: step: 82/469, loss: 0.2981243133544922
2023-01-24 02:22:38.958690: step: 84/469, loss: 0.13314944505691528
2023-01-24 02:22:39.611210: step: 86/469, loss: 0.14996854960918427
2023-01-24 02:22:40.234401: step: 88/469, loss: 0.19276639819145203
2023-01-24 02:22:40.922859: step: 90/469, loss: 0.7176858186721802
2023-01-24 02:22:41.482953: step: 92/469, loss: 0.06875741481781006
2023-01-24 02:22:42.093164: step: 94/469, loss: 0.10084113478660583
2023-01-24 02:22:42.847146: step: 96/469, loss: 0.26804348826408386
2023-01-24 02:22:43.496151: step: 98/469, loss: 0.11273273825645447
2023-01-24 02:22:44.104842: step: 100/469, loss: 0.09384886920452118
2023-01-24 02:22:44.731473: step: 102/469, loss: 1.07734215259552
2023-01-24 02:22:45.353075: step: 104/469, loss: 0.09534644335508347
2023-01-24 02:22:46.027474: step: 106/469, loss: 0.06335356831550598
2023-01-24 02:22:46.665421: step: 108/469, loss: 0.044890131801366806
2023-01-24 02:22:47.331670: step: 110/469, loss: 0.4320107102394104
2023-01-24 02:22:47.943997: step: 112/469, loss: 0.15150602161884308
2023-01-24 02:22:48.560086: step: 114/469, loss: 0.1361083835363388
2023-01-24 02:22:49.186059: step: 116/469, loss: 0.08271677792072296
2023-01-24 02:22:49.843179: step: 118/469, loss: 0.16889916360378265
2023-01-24 02:22:50.452384: step: 120/469, loss: 0.3423912525177002
2023-01-24 02:22:51.078225: step: 122/469, loss: 0.10864198952913284
2023-01-24 02:22:51.630376: step: 124/469, loss: 0.13169211149215698
2023-01-24 02:22:52.253873: step: 126/469, loss: 0.08829011768102646
2023-01-24 02:22:52.886058: step: 128/469, loss: 0.028931546956300735
2023-01-24 02:22:53.506388: step: 130/469, loss: 0.7551465034484863
2023-01-24 02:22:54.190637: step: 132/469, loss: 0.17933650314807892
2023-01-24 02:22:54.911414: step: 134/469, loss: 0.16171324253082275
2023-01-24 02:22:55.523603: step: 136/469, loss: 0.04460104927420616
2023-01-24 02:22:56.145238: step: 138/469, loss: 0.4347587525844574
2023-01-24 02:22:56.745718: step: 140/469, loss: 0.10114738345146179
2023-01-24 02:22:57.405607: step: 142/469, loss: 0.623106062412262
2023-01-24 02:22:58.073708: step: 144/469, loss: 0.18777582049369812
2023-01-24 02:22:58.752594: step: 146/469, loss: 0.14334578812122345
2023-01-24 02:22:59.380932: step: 148/469, loss: 0.09308890998363495
2023-01-24 02:23:00.061000: step: 150/469, loss: 0.28365811705589294
2023-01-24 02:23:00.657578: step: 152/469, loss: 0.13981464505195618
2023-01-24 02:23:01.272848: step: 154/469, loss: 0.24605931341648102
2023-01-24 02:23:01.922784: step: 156/469, loss: 0.1875181943178177
2023-01-24 02:23:02.557291: step: 158/469, loss: 0.20010283589363098
2023-01-24 02:23:03.121000: step: 160/469, loss: 0.16939972341060638
2023-01-24 02:23:03.751937: step: 162/469, loss: 0.20508363842964172
2023-01-24 02:23:04.333059: step: 164/469, loss: 0.07715775817632675
2023-01-24 02:23:04.929408: step: 166/469, loss: 0.05183357745409012
2023-01-24 02:23:05.475111: step: 168/469, loss: 0.1138022318482399
2023-01-24 02:23:06.072228: step: 170/469, loss: 0.10665109008550644
2023-01-24 02:23:06.716673: step: 172/469, loss: 0.14467765390872955
2023-01-24 02:23:07.290528: step: 174/469, loss: 0.17302070558071136
2023-01-24 02:23:07.913495: step: 176/469, loss: 0.06281275302171707
2023-01-24 02:23:08.557744: step: 178/469, loss: 0.106350839138031
2023-01-24 02:23:09.163070: step: 180/469, loss: 0.12620073556900024
2023-01-24 02:23:09.797239: step: 182/469, loss: 0.15765975415706635
2023-01-24 02:23:10.389970: step: 184/469, loss: 0.1896129697561264
2023-01-24 02:23:11.099400: step: 186/469, loss: 0.1435815989971161
2023-01-24 02:23:11.713309: step: 188/469, loss: 0.04556216672062874
2023-01-24 02:23:12.375149: step: 190/469, loss: 0.3126879632472992
2023-01-24 02:23:13.050150: step: 192/469, loss: 0.6106399297714233
2023-01-24 02:23:13.719491: step: 194/469, loss: 0.07210603356361389
2023-01-24 02:23:14.323756: step: 196/469, loss: 0.09808190912008286
2023-01-24 02:23:14.925927: step: 198/469, loss: 0.07551100105047226
2023-01-24 02:23:15.532825: step: 200/469, loss: 0.08211780339479446
2023-01-24 02:23:16.141632: step: 202/469, loss: 0.15985342860221863
2023-01-24 02:23:16.720408: step: 204/469, loss: 0.2892969846725464
2023-01-24 02:23:17.284125: step: 206/469, loss: 0.10105925798416138
2023-01-24 02:23:17.923590: step: 208/469, loss: 0.1534845530986786
2023-01-24 02:23:18.518583: step: 210/469, loss: 0.152360200881958
2023-01-24 02:23:19.182060: step: 212/469, loss: 0.071222685277462
2023-01-24 02:23:19.848476: step: 214/469, loss: 0.2626939117908478
2023-01-24 02:23:20.438467: step: 216/469, loss: 0.11798075586557388
2023-01-24 02:23:21.090110: step: 218/469, loss: 0.17177097499370575
2023-01-24 02:23:21.661497: step: 220/469, loss: 0.0783061608672142
2023-01-24 02:23:22.253570: step: 222/469, loss: 0.4897153973579407
2023-01-24 02:23:22.891218: step: 224/469, loss: 0.10043233633041382
2023-01-24 02:23:23.505744: step: 226/469, loss: 0.2859938442707062
2023-01-24 02:23:24.126425: step: 228/469, loss: 0.11709606647491455
2023-01-24 02:23:24.737270: step: 230/469, loss: 0.10491877794265747
2023-01-24 02:23:25.336238: step: 232/469, loss: 0.38725748658180237
2023-01-24 02:23:26.058298: step: 234/469, loss: 0.11682604253292084
2023-01-24 02:23:26.668072: step: 236/469, loss: 0.3147163987159729
2023-01-24 02:23:27.335944: step: 238/469, loss: 0.07728300988674164
2023-01-24 02:23:27.966379: step: 240/469, loss: 0.15843608975410461
2023-01-24 02:23:28.565948: step: 242/469, loss: 0.1569214016199112
2023-01-24 02:23:29.147385: step: 244/469, loss: 0.23852930963039398
2023-01-24 02:23:29.748202: step: 246/469, loss: 0.37657713890075684
2023-01-24 02:23:30.338029: step: 248/469, loss: 0.27573999762535095
2023-01-24 02:23:30.950113: step: 250/469, loss: 0.33493033051490784
2023-01-24 02:23:31.553857: step: 252/469, loss: 0.094824880361557
2023-01-24 02:23:32.149167: step: 254/469, loss: 0.0782121792435646
2023-01-24 02:23:32.801720: step: 256/469, loss: 0.21393126249313354
2023-01-24 02:23:33.384296: step: 258/469, loss: 0.050006359815597534
2023-01-24 02:23:34.017268: step: 260/469, loss: 0.10235308855772018
2023-01-24 02:23:34.654557: step: 262/469, loss: 0.5770941972732544
2023-01-24 02:23:35.303360: step: 264/469, loss: 0.6711481809616089
2023-01-24 02:23:35.921139: step: 266/469, loss: 0.18015974760055542
2023-01-24 02:23:36.545800: step: 268/469, loss: 0.6386641263961792
2023-01-24 02:23:37.134549: step: 270/469, loss: 0.02753409929573536
2023-01-24 02:23:37.742971: step: 272/469, loss: 0.11631710082292557
2023-01-24 02:23:38.303109: step: 274/469, loss: 0.540796160697937
2023-01-24 02:23:38.983779: step: 276/469, loss: 0.06846290081739426
2023-01-24 02:23:39.643793: step: 278/469, loss: 0.21025104820728302
2023-01-24 02:23:40.279955: step: 280/469, loss: 0.36336255073547363
2023-01-24 02:23:40.918154: step: 282/469, loss: 0.10736263543367386
2023-01-24 02:23:41.582704: step: 284/469, loss: 0.15782277286052704
2023-01-24 02:23:42.169253: step: 286/469, loss: 0.16212287545204163
2023-01-24 02:23:42.896777: step: 288/469, loss: 0.1548091173171997
2023-01-24 02:23:43.577003: step: 290/469, loss: 0.0778033435344696
2023-01-24 02:23:44.228548: step: 292/469, loss: 0.0829491838812828
2023-01-24 02:23:44.852163: step: 294/469, loss: 0.1539023071527481
2023-01-24 02:23:45.519563: step: 296/469, loss: 0.1201256662607193
2023-01-24 02:23:46.150630: step: 298/469, loss: 0.09404920041561127
2023-01-24 02:23:46.814125: step: 300/469, loss: 0.14464302361011505
2023-01-24 02:23:47.483511: step: 302/469, loss: 0.059379640966653824
2023-01-24 02:23:48.179207: step: 304/469, loss: 0.18006101250648499
2023-01-24 02:23:48.781556: step: 306/469, loss: 0.14657913148403168
2023-01-24 02:23:49.391684: step: 308/469, loss: 0.15113556385040283
2023-01-24 02:23:49.951912: step: 310/469, loss: 0.06717038154602051
2023-01-24 02:23:50.598065: step: 312/469, loss: 0.18208912014961243
2023-01-24 02:23:51.230997: step: 314/469, loss: 0.12528879940509796
2023-01-24 02:23:51.886788: step: 316/469, loss: 0.16097323596477509
2023-01-24 02:23:52.533058: step: 318/469, loss: 0.323387086391449
2023-01-24 02:23:53.280913: step: 320/469, loss: 0.054082948714494705
2023-01-24 02:23:53.981451: step: 322/469, loss: 0.04615125432610512
2023-01-24 02:23:54.614557: step: 324/469, loss: 0.3247581124305725
2023-01-24 02:23:55.264525: step: 326/469, loss: 0.3015666604042053
2023-01-24 02:23:55.952740: step: 328/469, loss: 0.12031938880681992
2023-01-24 02:23:56.592750: step: 330/469, loss: 0.823621392250061
2023-01-24 02:23:57.211753: step: 332/469, loss: 0.6472270488739014
2023-01-24 02:23:57.783893: step: 334/469, loss: 0.1509711742401123
2023-01-24 02:23:58.512294: step: 336/469, loss: 0.09899154305458069
2023-01-24 02:23:59.084535: step: 338/469, loss: 0.34739452600479126
2023-01-24 02:23:59.683089: step: 340/469, loss: 0.1512516736984253
2023-01-24 02:24:00.298358: step: 342/469, loss: 0.3168966770172119
2023-01-24 02:24:00.891720: step: 344/469, loss: 0.11273898929357529
2023-01-24 02:24:01.502828: step: 346/469, loss: 0.09030656516551971
2023-01-24 02:24:02.077951: step: 348/469, loss: 0.12679389119148254
2023-01-24 02:24:02.699319: step: 350/469, loss: 0.22046662867069244
2023-01-24 02:24:03.326407: step: 352/469, loss: 0.2992478311061859
2023-01-24 02:24:03.937733: step: 354/469, loss: 0.2764323651790619
2023-01-24 02:24:04.526802: step: 356/469, loss: 0.16730737686157227
2023-01-24 02:24:05.154551: step: 358/469, loss: 0.4008782207965851
2023-01-24 02:24:05.848783: step: 360/469, loss: 0.08393470197916031
2023-01-24 02:24:06.411235: step: 362/469, loss: 0.023924363777041435
2023-01-24 02:24:07.066812: step: 364/469, loss: 0.027280492708086967
2023-01-24 02:24:07.751290: step: 366/469, loss: 0.5706105828285217
2023-01-24 02:24:08.343684: step: 368/469, loss: 0.12655659019947052
2023-01-24 02:24:08.954753: step: 370/469, loss: 0.1514558345079422
2023-01-24 02:24:09.563460: step: 372/469, loss: 0.16106680035591125
2023-01-24 02:24:10.208567: step: 374/469, loss: 0.06775608658790588
2023-01-24 02:24:10.906115: step: 376/469, loss: 0.13861997425556183
2023-01-24 02:24:11.484683: step: 378/469, loss: 0.02835659123957157
2023-01-24 02:24:12.164358: step: 380/469, loss: 0.11011745780706406
2023-01-24 02:24:12.848066: step: 382/469, loss: 0.5650831460952759
2023-01-24 02:24:13.555952: step: 384/469, loss: 0.08820359408855438
2023-01-24 02:24:14.133960: step: 386/469, loss: 0.06612352281808853
2023-01-24 02:24:14.706461: step: 388/469, loss: 0.06718561053276062
2023-01-24 02:24:15.402618: step: 390/469, loss: 0.5960380434989929
2023-01-24 02:24:15.987671: step: 392/469, loss: 0.2348286658525467
2023-01-24 02:24:16.571156: step: 394/469, loss: 0.14006319642066956
2023-01-24 02:24:17.205465: step: 396/469, loss: 0.18940773606300354
2023-01-24 02:24:17.845537: step: 398/469, loss: 0.13046416640281677
2023-01-24 02:24:18.475361: step: 400/469, loss: 0.1405685991048813
2023-01-24 02:24:19.144104: step: 402/469, loss: 0.10449093580245972
2023-01-24 02:24:19.836027: step: 404/469, loss: 0.2600097358226776
2023-01-24 02:24:20.436061: step: 406/469, loss: 0.2757759988307953
2023-01-24 02:24:21.094215: step: 408/469, loss: 0.2753802239894867
2023-01-24 02:24:21.733272: step: 410/469, loss: 0.18735244870185852
2023-01-24 02:24:22.362047: step: 412/469, loss: 0.18760113418102264
2023-01-24 02:24:23.026430: step: 414/469, loss: 0.13700029253959656
2023-01-24 02:24:23.640687: step: 416/469, loss: 0.27538928389549255
2023-01-24 02:24:24.237606: step: 418/469, loss: 0.05533416569232941
2023-01-24 02:24:24.849518: step: 420/469, loss: 0.37720417976379395
2023-01-24 02:24:25.417991: step: 422/469, loss: 0.16215504705905914
2023-01-24 02:24:26.117609: step: 424/469, loss: 0.1332855224609375
2023-01-24 02:24:26.729739: step: 426/469, loss: 0.044950053095817566
2023-01-24 02:24:27.302230: step: 428/469, loss: 0.07420222461223602
2023-01-24 02:24:27.997019: step: 430/469, loss: 0.17046400904655457
2023-01-24 02:24:28.624895: step: 432/469, loss: 0.1962832808494568
2023-01-24 02:24:29.261584: step: 434/469, loss: 0.08419742435216904
2023-01-24 02:24:29.930241: step: 436/469, loss: 0.23773783445358276
2023-01-24 02:24:30.631754: step: 438/469, loss: 0.20467659831047058
2023-01-24 02:24:31.211463: step: 440/469, loss: 0.5752460956573486
2023-01-24 02:24:31.801945: step: 442/469, loss: 0.1751350611448288
2023-01-24 02:24:32.446416: step: 444/469, loss: 0.23590019345283508
2023-01-24 02:24:33.048808: step: 446/469, loss: 0.11765924096107483
2023-01-24 02:24:33.691732: step: 448/469, loss: 0.12432537972927094
2023-01-24 02:24:34.288389: step: 450/469, loss: 1.031097412109375
2023-01-24 02:24:34.964584: step: 452/469, loss: 0.5516473054885864
2023-01-24 02:24:35.555205: step: 454/469, loss: 0.7052913308143616
2023-01-24 02:24:36.170947: step: 456/469, loss: 0.13842427730560303
2023-01-24 02:24:36.765532: step: 458/469, loss: 0.15683257579803467
2023-01-24 02:24:37.427317: step: 460/469, loss: 0.21235518157482147
2023-01-24 02:24:38.025059: step: 462/469, loss: 0.18652980029582977
2023-01-24 02:24:38.709830: step: 464/469, loss: 0.08775254338979721
2023-01-24 02:24:39.297164: step: 466/469, loss: 0.16776995360851288
2023-01-24 02:24:39.933509: step: 468/469, loss: 1.0242727994918823
2023-01-24 02:24:40.492846: step: 470/469, loss: 0.25791946053504944
2023-01-24 02:24:41.040468: step: 472/469, loss: 0.09766504168510437
2023-01-24 02:24:41.645512: step: 474/469, loss: 0.2593061923980713
2023-01-24 02:24:42.294410: step: 476/469, loss: 0.15998785197734833
2023-01-24 02:24:42.945149: step: 478/469, loss: 0.33104825019836426
2023-01-24 02:24:43.576254: step: 480/469, loss: 0.2022796869277954
2023-01-24 02:24:44.223425: step: 482/469, loss: 0.14389175176620483
2023-01-24 02:24:44.853535: step: 484/469, loss: 0.43419936299324036
2023-01-24 02:24:45.535683: step: 486/469, loss: 0.10547473281621933
2023-01-24 02:24:46.179385: step: 488/469, loss: 0.14546909928321838
2023-01-24 02:24:46.858753: step: 490/469, loss: 0.26507213711738586
2023-01-24 02:24:47.468704: step: 492/469, loss: 0.11528874933719635
2023-01-24 02:24:48.088321: step: 494/469, loss: 0.12346061319112778
2023-01-24 02:24:48.677073: step: 496/469, loss: 0.14933393895626068
2023-01-24 02:24:49.284533: step: 498/469, loss: 0.1556585431098938
2023-01-24 02:24:49.983056: step: 500/469, loss: 0.11973549425601959
2023-01-24 02:24:50.666238: step: 502/469, loss: 0.09847920387983322
2023-01-24 02:24:51.327164: step: 504/469, loss: 0.11896110326051712
2023-01-24 02:24:51.941314: step: 506/469, loss: 0.29117506742477417
2023-01-24 02:24:52.562638: step: 508/469, loss: 0.16343897581100464
2023-01-24 02:24:53.178143: step: 510/469, loss: 0.06698044389486313
2023-01-24 02:24:53.884334: step: 512/469, loss: 0.317922443151474
2023-01-24 02:24:54.474518: step: 514/469, loss: 0.06957085430622101
2023-01-24 02:24:55.114401: step: 516/469, loss: 0.09205619245767593
2023-01-24 02:24:55.741848: step: 518/469, loss: 0.18013393878936768
2023-01-24 02:24:56.316116: step: 520/469, loss: 0.12401673942804337
2023-01-24 02:24:56.959771: step: 522/469, loss: 0.36328259110450745
2023-01-24 02:24:57.544106: step: 524/469, loss: 0.31907233595848083
2023-01-24 02:24:58.203436: step: 526/469, loss: 0.2107231318950653
2023-01-24 02:24:58.842517: step: 528/469, loss: 0.06706923991441727
2023-01-24 02:24:59.438574: step: 530/469, loss: 0.21510553359985352
2023-01-24 02:25:00.057918: step: 532/469, loss: 0.1253836452960968
2023-01-24 02:25:00.669987: step: 534/469, loss: 0.1771828830242157
2023-01-24 02:25:01.300637: step: 536/469, loss: 0.24723005294799805
2023-01-24 02:25:01.908342: step: 538/469, loss: 0.9632300734519958
2023-01-24 02:25:02.569984: step: 540/469, loss: 0.6564993262290955
2023-01-24 02:25:03.198855: step: 542/469, loss: 0.3365788161754608
2023-01-24 02:25:03.836448: step: 544/469, loss: 0.1955217570066452
2023-01-24 02:25:04.465739: step: 546/469, loss: 0.27033689618110657
2023-01-24 02:25:05.148493: step: 548/469, loss: 0.1297452598810196
2023-01-24 02:25:05.759193: step: 550/469, loss: 0.17727072536945343
2023-01-24 02:25:06.388291: step: 552/469, loss: 0.22598281502723694
2023-01-24 02:25:07.013072: step: 554/469, loss: 0.09274069219827652
2023-01-24 02:25:07.659210: step: 556/469, loss: 0.17935216426849365
2023-01-24 02:25:08.274199: step: 558/469, loss: 0.09343497455120087
2023-01-24 02:25:09.122376: step: 560/469, loss: 0.14464518427848816
2023-01-24 02:25:09.652022: step: 562/469, loss: 0.10873056948184967
2023-01-24 02:25:10.210159: step: 564/469, loss: 0.0771813839673996
2023-01-24 02:25:10.889943: step: 566/469, loss: 0.16872255504131317
2023-01-24 02:25:11.458104: step: 568/469, loss: 0.12507933378219604
2023-01-24 02:25:12.114768: step: 570/469, loss: 0.14560864865779877
2023-01-24 02:25:12.704667: step: 572/469, loss: 0.35550230741500854
2023-01-24 02:25:13.325413: step: 574/469, loss: 0.2243213653564453
2023-01-24 02:25:13.945643: step: 576/469, loss: 0.12023797631263733
2023-01-24 02:25:14.504339: step: 578/469, loss: 0.12230618298053741
2023-01-24 02:25:15.186333: step: 580/469, loss: 0.10368078202009201
2023-01-24 02:25:15.802605: step: 582/469, loss: 0.2484348863363266
2023-01-24 02:25:16.437265: step: 584/469, loss: 0.1614336222410202
2023-01-24 02:25:17.102816: step: 586/469, loss: 0.20537163317203522
2023-01-24 02:25:17.790145: step: 588/469, loss: 0.3633364737033844
2023-01-24 02:25:18.410228: step: 590/469, loss: 0.10143674910068512
2023-01-24 02:25:19.076279: step: 592/469, loss: 0.40851813554763794
2023-01-24 02:25:19.636994: step: 594/469, loss: 0.13826799392700195
2023-01-24 02:25:20.257781: step: 596/469, loss: 0.1731613278388977
2023-01-24 02:25:20.871815: step: 598/469, loss: 1.3614288568496704
2023-01-24 02:25:21.506434: step: 600/469, loss: 0.2950364947319031
2023-01-24 02:25:22.143991: step: 602/469, loss: 0.15174712240695953
2023-01-24 02:25:22.797465: step: 604/469, loss: 0.17593331634998322
2023-01-24 02:25:23.409529: step: 606/469, loss: 0.23934026062488556
2023-01-24 02:25:24.095215: step: 608/469, loss: 0.20558743178844452
2023-01-24 02:25:24.751101: step: 610/469, loss: 0.039850398898124695
2023-01-24 02:25:25.349062: step: 612/469, loss: 0.5241489410400391
2023-01-24 02:25:25.946744: step: 614/469, loss: 0.3212416470050812
2023-01-24 02:25:26.551524: step: 616/469, loss: 0.17849406599998474
2023-01-24 02:25:27.203013: step: 618/469, loss: 0.1348249614238739
2023-01-24 02:25:27.850077: step: 620/469, loss: 0.11664216965436935
2023-01-24 02:25:28.432992: step: 622/469, loss: 0.22106176614761353
2023-01-24 02:25:29.078773: step: 624/469, loss: 0.08235683292150497
2023-01-24 02:25:29.709832: step: 626/469, loss: 0.3486630320549011
2023-01-24 02:25:30.328235: step: 628/469, loss: 0.13559679687023163
2023-01-24 02:25:30.982840: step: 630/469, loss: 0.13814496994018555
2023-01-24 02:25:31.564820: step: 632/469, loss: 0.10115935653448105
2023-01-24 02:25:32.162243: step: 634/469, loss: 0.15298683941364288
2023-01-24 02:25:32.773795: step: 636/469, loss: 0.05955592542886734
2023-01-24 02:25:33.316531: step: 638/469, loss: 0.10162433236837387
2023-01-24 02:25:33.911076: step: 640/469, loss: 1.179209589958191
2023-01-24 02:25:34.508977: step: 642/469, loss: 0.5895562767982483
2023-01-24 02:25:35.063411: step: 644/469, loss: 0.08995138853788376
2023-01-24 02:25:35.731665: step: 646/469, loss: 0.1272493600845337
2023-01-24 02:25:36.337145: step: 648/469, loss: 0.18245941400527954
2023-01-24 02:25:36.920929: step: 650/469, loss: 0.277253657579422
2023-01-24 02:25:37.541188: step: 652/469, loss: 0.8337023854255676
2023-01-24 02:25:38.199632: step: 654/469, loss: 0.45173418521881104
2023-01-24 02:25:38.808329: step: 656/469, loss: 0.18245379626750946
2023-01-24 02:25:39.523097: step: 658/469, loss: 0.2845979332923889
2023-01-24 02:25:40.066143: step: 660/469, loss: 0.1612120270729065
2023-01-24 02:25:40.744623: step: 662/469, loss: 0.4129007160663605
2023-01-24 02:25:41.457100: step: 664/469, loss: 0.3531123697757721
2023-01-24 02:25:42.054081: step: 666/469, loss: 0.3081263601779938
2023-01-24 02:25:42.662589: step: 668/469, loss: 1.1761054992675781
2023-01-24 02:25:43.329554: step: 670/469, loss: 0.2595185339450836
2023-01-24 02:25:44.034609: step: 672/469, loss: 0.24489150941371918
2023-01-24 02:25:44.627304: step: 674/469, loss: 0.1660284399986267
2023-01-24 02:25:45.295389: step: 676/469, loss: 0.047580648213624954
2023-01-24 02:25:45.909858: step: 678/469, loss: 0.21147482097148895
2023-01-24 02:25:46.519395: step: 680/469, loss: 0.05559933930635452
2023-01-24 02:25:47.098786: step: 682/469, loss: 0.18751806020736694
2023-01-24 02:25:47.715826: step: 684/469, loss: 0.054852958768606186
2023-01-24 02:25:48.365691: step: 686/469, loss: 0.14558443427085876
2023-01-24 02:25:49.012360: step: 688/469, loss: 0.24283434450626373
2023-01-24 02:25:49.605391: step: 690/469, loss: 0.1446641981601715
2023-01-24 02:25:50.259964: step: 692/469, loss: 0.07388562709093094
2023-01-24 02:25:50.809091: step: 694/469, loss: 0.053731344640254974
2023-01-24 02:25:51.498332: step: 696/469, loss: 0.11538675427436829
2023-01-24 02:25:52.261001: step: 698/469, loss: 0.18003545701503754
2023-01-24 02:25:52.839494: step: 700/469, loss: 0.5147695541381836
2023-01-24 02:25:53.479815: step: 702/469, loss: 0.11726795881986618
2023-01-24 02:25:54.100871: step: 704/469, loss: 0.30476054549217224
2023-01-24 02:25:54.721861: step: 706/469, loss: 0.20852771401405334
2023-01-24 02:25:55.299512: step: 708/469, loss: 0.12997330725193024
2023-01-24 02:25:55.910408: step: 710/469, loss: 0.6460703611373901
2023-01-24 02:25:56.462666: step: 712/469, loss: 0.5039768815040588
2023-01-24 02:25:57.091155: step: 714/469, loss: 0.355660617351532
2023-01-24 02:25:57.717804: step: 716/469, loss: 0.14265164732933044
2023-01-24 02:25:58.357581: step: 718/469, loss: 0.1854066252708435
2023-01-24 02:25:58.990161: step: 720/469, loss: 0.22185933589935303
2023-01-24 02:25:59.617195: step: 722/469, loss: 0.1451837569475174
2023-01-24 02:26:00.206447: step: 724/469, loss: 0.03779136762022972
2023-01-24 02:26:00.794771: step: 726/469, loss: 0.11523859947919846
2023-01-24 02:26:01.434546: step: 728/469, loss: 0.47882261872291565
2023-01-24 02:26:02.062896: step: 730/469, loss: 0.31595316529273987
2023-01-24 02:26:02.653721: step: 732/469, loss: 1.2247695922851562
2023-01-24 02:26:03.316260: step: 734/469, loss: 0.18435610830783844
2023-01-24 02:26:04.060672: step: 736/469, loss: 0.12068726867437363
2023-01-24 02:26:04.688714: step: 738/469, loss: 0.08250205963850021
2023-01-24 02:26:05.324996: step: 740/469, loss: 0.10171730071306229
2023-01-24 02:26:05.993885: step: 742/469, loss: 0.16402065753936768
2023-01-24 02:26:06.630094: step: 744/469, loss: 0.13324828445911407
2023-01-24 02:26:07.261177: step: 746/469, loss: 0.12444313615560532
2023-01-24 02:26:07.874771: step: 748/469, loss: 0.10346558690071106
2023-01-24 02:26:08.449350: step: 750/469, loss: 0.5168923139572144
2023-01-24 02:26:09.051419: step: 752/469, loss: 0.1270841658115387
2023-01-24 02:26:09.726681: step: 754/469, loss: 0.26641565561294556
2023-01-24 02:26:10.351997: step: 756/469, loss: 0.18214882910251617
2023-01-24 02:26:10.998898: step: 758/469, loss: 0.5728313326835632
2023-01-24 02:26:11.586928: step: 760/469, loss: 0.3768772482872009
2023-01-24 02:26:12.177245: step: 762/469, loss: 0.1931002140045166
2023-01-24 02:26:12.854935: step: 764/469, loss: 0.32628846168518066
2023-01-24 02:26:13.462903: step: 766/469, loss: 0.18113891780376434
2023-01-24 02:26:14.053231: step: 768/469, loss: 0.05588013678789139
2023-01-24 02:26:14.857869: step: 770/469, loss: 0.07006081938743591
2023-01-24 02:26:15.498330: step: 772/469, loss: 0.05329433083534241
2023-01-24 02:26:16.137504: step: 774/469, loss: 0.12903809547424316
2023-01-24 02:26:16.779873: step: 776/469, loss: 0.20359189808368683
2023-01-24 02:26:17.412177: step: 778/469, loss: 0.775844395160675
2023-01-24 02:26:17.995443: step: 780/469, loss: 0.10517729073762894
2023-01-24 02:26:18.548509: step: 782/469, loss: 0.3936934471130371
2023-01-24 02:26:19.111629: step: 784/469, loss: 0.5093246102333069
2023-01-24 02:26:19.778566: step: 786/469, loss: 0.5735411047935486
2023-01-24 02:26:20.437563: step: 788/469, loss: 0.16819803416728973
2023-01-24 02:26:21.030670: step: 790/469, loss: 0.27249181270599365
2023-01-24 02:26:21.623702: step: 792/469, loss: 0.1117519810795784
2023-01-24 02:26:22.284416: step: 794/469, loss: 0.08045224100351334
2023-01-24 02:26:22.919214: step: 796/469, loss: 0.1268969476222992
2023-01-24 02:26:23.532184: step: 798/469, loss: 0.3834597170352936
2023-01-24 02:26:24.153509: step: 800/469, loss: 0.6271202564239502
2023-01-24 02:26:24.843219: step: 802/469, loss: 0.16394072771072388
2023-01-24 02:26:25.437039: step: 804/469, loss: 0.10925667732954025
2023-01-24 02:26:26.107583: step: 806/469, loss: 0.06161484122276306
2023-01-24 02:26:26.805890: step: 808/469, loss: 0.1299452930688858
2023-01-24 02:26:27.491992: step: 810/469, loss: 0.13461150228977203
2023-01-24 02:26:28.168106: step: 812/469, loss: 0.16261617839336395
2023-01-24 02:26:28.774234: step: 814/469, loss: 0.49927422404289246
2023-01-24 02:26:29.422052: step: 816/469, loss: 0.27267399430274963
2023-01-24 02:26:30.110437: step: 818/469, loss: 0.4247361123561859
2023-01-24 02:26:30.737379: step: 820/469, loss: 0.17890776693820953
2023-01-24 02:26:31.360949: step: 822/469, loss: 0.17473213374614716
2023-01-24 02:26:32.016498: step: 824/469, loss: 0.2757745087146759
2023-01-24 02:26:32.648731: step: 826/469, loss: 0.1165783554315567
2023-01-24 02:26:33.377264: step: 828/469, loss: 0.19895058870315552
2023-01-24 02:26:33.940106: step: 830/469, loss: 0.16803598403930664
2023-01-24 02:26:34.559705: step: 832/469, loss: 0.5686655640602112
2023-01-24 02:26:35.191314: step: 834/469, loss: 0.2641165852546692
2023-01-24 02:26:35.800193: step: 836/469, loss: 0.0898580402135849
2023-01-24 02:26:36.386099: step: 838/469, loss: 0.21407265961170197
2023-01-24 02:26:37.029003: step: 840/469, loss: 0.13167890906333923
2023-01-24 02:26:37.636791: step: 842/469, loss: 0.49524736404418945
2023-01-24 02:26:38.189435: step: 844/469, loss: 0.1604488641023636
2023-01-24 02:26:38.794077: step: 846/469, loss: 0.12622714042663574
2023-01-24 02:26:39.462049: step: 848/469, loss: 0.12502378225326538
2023-01-24 02:26:40.094299: step: 850/469, loss: 1.2619335651397705
2023-01-24 02:26:40.759332: step: 852/469, loss: 0.13600540161132812
2023-01-24 02:26:41.380431: step: 854/469, loss: 0.4233364164829254
2023-01-24 02:26:41.949405: step: 856/469, loss: 0.15904124081134796
2023-01-24 02:26:42.488376: step: 858/469, loss: 0.8725924491882324
2023-01-24 02:26:43.142686: step: 860/469, loss: 0.21988923847675323
2023-01-24 02:26:43.710250: step: 862/469, loss: 0.123007632791996
2023-01-24 02:26:44.408599: step: 864/469, loss: 0.15686100721359253
2023-01-24 02:26:45.029748: step: 866/469, loss: 0.09428158402442932
2023-01-24 02:26:45.656599: step: 868/469, loss: 0.15478846430778503
2023-01-24 02:26:46.279000: step: 870/469, loss: 0.46862301230430603
2023-01-24 02:26:46.891750: step: 872/469, loss: 0.07323585450649261
2023-01-24 02:26:47.480535: step: 874/469, loss: 0.17957401275634766
2023-01-24 02:26:48.082953: step: 876/469, loss: 0.0937713235616684
2023-01-24 02:26:48.678609: step: 878/469, loss: 0.363863080739975
2023-01-24 02:26:49.291425: step: 880/469, loss: 0.11538223922252655
2023-01-24 02:26:49.873517: step: 882/469, loss: 0.030977336689829826
2023-01-24 02:26:50.490340: step: 884/469, loss: 0.4014894664287567
2023-01-24 02:26:51.071933: step: 886/469, loss: 0.227244034409523
2023-01-24 02:26:51.596867: step: 888/469, loss: 0.24971428513526917
2023-01-24 02:26:52.227543: step: 890/469, loss: 1.621824026107788
2023-01-24 02:26:52.896839: step: 892/469, loss: 0.1848357617855072
2023-01-24 02:26:53.497710: step: 894/469, loss: 0.39088448882102966
2023-01-24 02:26:54.144964: step: 896/469, loss: 0.1631229817867279
2023-01-24 02:26:54.766218: step: 898/469, loss: 1.3466644287109375
2023-01-24 02:26:55.332332: step: 900/469, loss: 0.07818323373794556
2023-01-24 02:26:55.956169: step: 902/469, loss: 0.1619444489479065
2023-01-24 02:26:56.555862: step: 904/469, loss: 0.1829451024532318
2023-01-24 02:26:57.207116: step: 906/469, loss: 0.06281502544879913
2023-01-24 02:26:57.754538: step: 908/469, loss: 0.1573103964328766
2023-01-24 02:26:58.334225: step: 910/469, loss: 0.12201010435819626
2023-01-24 02:26:59.026913: step: 912/469, loss: 0.28905412554740906
2023-01-24 02:26:59.691748: step: 914/469, loss: 0.18813428282737732
2023-01-24 02:27:00.327859: step: 916/469, loss: 0.536222517490387
2023-01-24 02:27:00.993298: step: 918/469, loss: 0.03911914303898811
2023-01-24 02:27:01.620245: step: 920/469, loss: 1.827509880065918
2023-01-24 02:27:02.301425: step: 922/469, loss: 0.13335424661636353
2023-01-24 02:27:03.063801: step: 924/469, loss: 0.11065218597650528
2023-01-24 02:27:03.745222: step: 926/469, loss: 0.2032957822084427
2023-01-24 02:27:04.356357: step: 928/469, loss: 1.170350432395935
2023-01-24 02:27:05.006348: step: 930/469, loss: 0.6633148193359375
2023-01-24 02:27:05.629898: step: 932/469, loss: 0.30619141459465027
2023-01-24 02:27:06.324332: step: 934/469, loss: 2.020390748977661
2023-01-24 02:27:06.897187: step: 936/469, loss: 0.23759694397449493
2023-01-24 02:27:07.516217: step: 938/469, loss: 0.6831357479095459
==================================================
Loss: 0.253
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32569014052989614, 'r': 0.3244541248163102, 'f1': 0.3250709577532233}, 'combined': 0.2395259688707961, 'epoch': 12}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31316711208292836, 'r': 0.2527112468958306, 'f1': 0.27970976491862565}, 'combined': 0.1525689626828867, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34088004839643143, 'r': 0.33053074901437657, 'f1': 0.3356256353190298}, 'combined': 0.24730309970875877, 'epoch': 12}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3134426028260679, 'r': 0.2538483968042926, 'f1': 0.2805152990948446}, 'combined': 0.1530083449608243, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3220156767738635, 'r': 0.32629292485245376, 'f1': 0.32414019113523673}, 'combined': 0.23884014083649022, 'epoch': 12}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.309438336020083, 'r': 0.2523547343067892, 'f1': 0.27799641254118124}, 'combined': 0.1516344068406443, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29838709677419356, 'r': 0.2642857142857143, 'f1': 0.28030303030303033}, 'combined': 0.18686868686868688, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2976190476190476, 'r': 0.2717391304347826, 'f1': 0.28409090909090906}, 'combined': 0.14204545454545453, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4444444444444444, 'r': 0.13793103448275862, 'f1': 0.21052631578947367}, 'combined': 0.14035087719298245, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 02:29:54.494740: step: 2/469, loss: 0.2294110655784607
2023-01-24 02:29:55.130771: step: 4/469, loss: 0.10552580654621124
2023-01-24 02:29:55.716856: step: 6/469, loss: 0.15640881657600403
2023-01-24 02:29:56.316350: step: 8/469, loss: 0.034205976873636246
2023-01-24 02:29:56.953141: step: 10/469, loss: 0.06980501860380173
2023-01-24 02:29:57.575482: step: 12/469, loss: 0.095150887966156
2023-01-24 02:29:58.165054: step: 14/469, loss: 0.05807060748338699
2023-01-24 02:29:58.790089: step: 16/469, loss: 0.06640897691249847
2023-01-24 02:29:59.420193: step: 18/469, loss: 0.29062190651893616
2023-01-24 02:30:00.094482: step: 20/469, loss: 0.07286447286605835
2023-01-24 02:30:00.760672: step: 22/469, loss: 0.10701128840446472
2023-01-24 02:30:01.387082: step: 24/469, loss: 0.1147419810295105
2023-01-24 02:30:02.005957: step: 26/469, loss: 0.1374412178993225
2023-01-24 02:30:02.693610: step: 28/469, loss: 0.0968305692076683
2023-01-24 02:30:03.316740: step: 30/469, loss: 0.1279314160346985
2023-01-24 02:30:03.880733: step: 32/469, loss: 0.1515100598335266
2023-01-24 02:30:04.461760: step: 34/469, loss: 0.0876307263970375
2023-01-24 02:30:05.160754: step: 36/469, loss: 0.036387212574481964
2023-01-24 02:30:05.818337: step: 38/469, loss: 0.13604223728179932
2023-01-24 02:30:06.406886: step: 40/469, loss: 0.06580393761396408
2023-01-24 02:30:07.102064: step: 42/469, loss: 0.052817728370428085
2023-01-24 02:30:07.634534: step: 44/469, loss: 0.13042756915092468
2023-01-24 02:30:08.278194: step: 46/469, loss: 0.317474901676178
2023-01-24 02:30:09.000583: step: 48/469, loss: 0.29092055559158325
2023-01-24 02:30:09.668919: step: 50/469, loss: 0.029858211055397987
2023-01-24 02:30:10.277252: step: 52/469, loss: 0.12260261923074722
2023-01-24 02:30:10.849786: step: 54/469, loss: 0.05783361196517944
2023-01-24 02:30:11.470384: step: 56/469, loss: 0.1679166555404663
2023-01-24 02:30:12.141111: step: 58/469, loss: 0.4225844740867615
2023-01-24 02:30:12.800628: step: 60/469, loss: 0.26760512590408325
2023-01-24 02:30:13.426686: step: 62/469, loss: 0.06546816974878311
2023-01-24 02:30:14.065691: step: 64/469, loss: 0.25032976269721985
2023-01-24 02:30:14.618765: step: 66/469, loss: 1.215293288230896
2023-01-24 02:30:15.213532: step: 68/469, loss: 0.09485647827386856
2023-01-24 02:30:15.791060: step: 70/469, loss: 0.1537492573261261
2023-01-24 02:30:16.443903: step: 72/469, loss: 0.21111547946929932
2023-01-24 02:30:17.040745: step: 74/469, loss: 0.40520209074020386
2023-01-24 02:30:17.706071: step: 76/469, loss: 0.09451662749052048
2023-01-24 02:30:18.350191: step: 78/469, loss: 0.06155052036046982
2023-01-24 02:30:19.067252: step: 80/469, loss: 0.1046370193362236
2023-01-24 02:30:19.692861: step: 82/469, loss: 0.15164315700531006
2023-01-24 02:30:20.318076: step: 84/469, loss: 0.22775579988956451
2023-01-24 02:30:20.920280: step: 86/469, loss: 0.05479899421334267
2023-01-24 02:30:21.475910: step: 88/469, loss: 0.07875333726406097
2023-01-24 02:30:22.200721: step: 90/469, loss: 0.21325896680355072
2023-01-24 02:30:22.851268: step: 92/469, loss: 0.11635953187942505
2023-01-24 02:30:23.497730: step: 94/469, loss: 0.2095092236995697
2023-01-24 02:30:24.127097: step: 96/469, loss: 0.1170249804854393
2023-01-24 02:30:24.757661: step: 98/469, loss: 0.04608559235930443
2023-01-24 02:30:25.401216: step: 100/469, loss: 0.03804682567715645
2023-01-24 02:30:26.022321: step: 102/469, loss: 0.36065393686294556
2023-01-24 02:30:26.826572: step: 104/469, loss: 0.08604159951210022
2023-01-24 02:30:27.481754: step: 106/469, loss: 0.07397216558456421
2023-01-24 02:30:28.107360: step: 108/469, loss: 0.186575248837471
2023-01-24 02:30:28.734594: step: 110/469, loss: 0.3155174255371094
2023-01-24 02:30:29.362389: step: 112/469, loss: 0.579622745513916
2023-01-24 02:30:29.955143: step: 114/469, loss: 0.037597622722387314
2023-01-24 02:30:30.645422: step: 116/469, loss: 0.04044022038578987
2023-01-24 02:30:31.225365: step: 118/469, loss: 0.05252430960536003
2023-01-24 02:30:31.831659: step: 120/469, loss: 0.13036908209323883
2023-01-24 02:30:32.452993: step: 122/469, loss: 0.033417362719774246
2023-01-24 02:30:33.075788: step: 124/469, loss: 0.19477954506874084
2023-01-24 02:30:33.719930: step: 126/469, loss: 0.08658799529075623
2023-01-24 02:30:34.357377: step: 128/469, loss: 0.03600918874144554
2023-01-24 02:30:35.024180: step: 130/469, loss: 0.05813496559858322
2023-01-24 02:30:35.621217: step: 132/469, loss: 0.4854338467121124
2023-01-24 02:30:36.277112: step: 134/469, loss: 0.0947144627571106
2023-01-24 02:30:36.970717: step: 136/469, loss: 0.11194200813770294
2023-01-24 02:30:37.645983: step: 138/469, loss: 0.1804186999797821
2023-01-24 02:30:38.269941: step: 140/469, loss: 0.21446490287780762
2023-01-24 02:30:38.901498: step: 142/469, loss: 0.30432432889938354
2023-01-24 02:30:39.500223: step: 144/469, loss: 0.34499290585517883
2023-01-24 02:30:40.068417: step: 146/469, loss: 0.049611784517765045
2023-01-24 02:30:40.743077: step: 148/469, loss: 0.04391444846987724
2023-01-24 02:30:41.345582: step: 150/469, loss: 0.22266417741775513
2023-01-24 02:30:41.980930: step: 152/469, loss: 0.09504599869251251
2023-01-24 02:30:42.592581: step: 154/469, loss: 0.7208542823791504
2023-01-24 02:30:43.185367: step: 156/469, loss: 0.0622759573161602
2023-01-24 02:30:43.797208: step: 158/469, loss: 0.03672638535499573
2023-01-24 02:30:44.376434: step: 160/469, loss: 0.03442857041954994
2023-01-24 02:30:44.943842: step: 162/469, loss: 0.09264393895864487
2023-01-24 02:30:45.565022: step: 164/469, loss: 0.044600196182727814
2023-01-24 02:30:46.285482: step: 166/469, loss: 0.3165144920349121
2023-01-24 02:30:46.867188: step: 168/469, loss: 0.11863255500793457
2023-01-24 02:30:47.488808: step: 170/469, loss: 0.1762791872024536
2023-01-24 02:30:48.182574: step: 172/469, loss: 0.10699054598808289
2023-01-24 02:30:48.811928: step: 174/469, loss: 0.09779482334852219
2023-01-24 02:30:49.376995: step: 176/469, loss: 0.19619430601596832
2023-01-24 02:30:50.026022: step: 178/469, loss: 0.08160151541233063
2023-01-24 02:30:50.604546: step: 180/469, loss: 0.02518235705792904
2023-01-24 02:30:51.238232: step: 182/469, loss: 0.14843423664569855
2023-01-24 02:30:51.806676: step: 184/469, loss: 0.019742164760828018
2023-01-24 02:30:52.483716: step: 186/469, loss: 0.019009260460734367
2023-01-24 02:30:53.075866: step: 188/469, loss: 0.22973763942718506
2023-01-24 02:30:53.817041: step: 190/469, loss: 0.13438567519187927
2023-01-24 02:30:54.431631: step: 192/469, loss: 0.07546482980251312
2023-01-24 02:30:55.075225: step: 194/469, loss: 0.05986330285668373
2023-01-24 02:30:55.773856: step: 196/469, loss: 0.044918037950992584
2023-01-24 02:30:56.410759: step: 198/469, loss: 0.07734072208404541
2023-01-24 02:30:56.971360: step: 200/469, loss: 0.207444429397583
2023-01-24 02:30:57.649820: step: 202/469, loss: 0.20675028860569
2023-01-24 02:30:58.283220: step: 204/469, loss: 0.22096797823905945
2023-01-24 02:30:58.892548: step: 206/469, loss: 0.11853277683258057
2023-01-24 02:30:59.559371: step: 208/469, loss: 0.1394554078578949
2023-01-24 02:31:00.120334: step: 210/469, loss: 0.12088552862405777
2023-01-24 02:31:00.725213: step: 212/469, loss: 0.34791815280914307
2023-01-24 02:31:01.281371: step: 214/469, loss: 0.08338740468025208
2023-01-24 02:31:01.923889: step: 216/469, loss: 0.14494885504245758
2023-01-24 02:31:02.602197: step: 218/469, loss: 1.0744656324386597
2023-01-24 02:31:03.214640: step: 220/469, loss: 0.07820221036672592
2023-01-24 02:31:03.834584: step: 222/469, loss: 0.09651470929384232
2023-01-24 02:31:04.476066: step: 224/469, loss: 0.22024601697921753
2023-01-24 02:31:05.114301: step: 226/469, loss: 0.1264672875404358
2023-01-24 02:31:05.728055: step: 228/469, loss: 0.0487193688750267
2023-01-24 02:31:06.456952: step: 230/469, loss: 0.13652971386909485
2023-01-24 02:31:07.119531: step: 232/469, loss: 0.15800170600414276
2023-01-24 02:31:07.749277: step: 234/469, loss: 0.1348744034767151
2023-01-24 02:31:08.431194: step: 236/469, loss: 0.0199300404638052
2023-01-24 02:31:09.110212: step: 238/469, loss: 0.04722470045089722
2023-01-24 02:31:09.698409: step: 240/469, loss: 0.13642564415931702
2023-01-24 02:31:10.319717: step: 242/469, loss: 0.10824882984161377
2023-01-24 02:31:10.926232: step: 244/469, loss: 0.12253447622060776
2023-01-24 02:31:11.564018: step: 246/469, loss: 0.12152257561683655
2023-01-24 02:31:12.175466: step: 248/469, loss: 0.17997433245182037
2023-01-24 02:31:12.792204: step: 250/469, loss: 8.4161958694458
2023-01-24 02:31:13.474183: step: 252/469, loss: 0.08476436883211136
2023-01-24 02:31:14.089446: step: 254/469, loss: 0.07402852922677994
2023-01-24 02:31:14.811621: step: 256/469, loss: 0.36886370182037354
2023-01-24 02:31:15.420479: step: 258/469, loss: 0.09367343783378601
2023-01-24 02:31:16.007061: step: 260/469, loss: 0.18831424415111542
2023-01-24 02:31:16.631850: step: 262/469, loss: 0.13770127296447754
2023-01-24 02:31:17.255703: step: 264/469, loss: 0.0983630120754242
2023-01-24 02:31:17.876236: step: 266/469, loss: 0.1506970226764679
2023-01-24 02:31:18.535737: step: 268/469, loss: 0.07185398042201996
2023-01-24 02:31:19.139720: step: 270/469, loss: 0.3573124408721924
2023-01-24 02:31:19.824925: step: 272/469, loss: 1.5084404945373535
2023-01-24 02:31:20.442895: step: 274/469, loss: 0.07283905893564224
2023-01-24 02:31:21.064406: step: 276/469, loss: 0.12669117748737335
2023-01-24 02:31:21.716234: step: 278/469, loss: 0.18776993453502655
2023-01-24 02:31:22.382378: step: 280/469, loss: 0.429730087518692
2023-01-24 02:31:22.999391: step: 282/469, loss: 0.3037673234939575
2023-01-24 02:31:23.622205: step: 284/469, loss: 0.03288634866476059
2023-01-24 02:31:24.328375: step: 286/469, loss: 0.29557883739471436
2023-01-24 02:31:24.930723: step: 288/469, loss: 0.16269901394844055
2023-01-24 02:31:25.568007: step: 290/469, loss: 0.20090721547603607
2023-01-24 02:31:26.210655: step: 292/469, loss: 0.01363021694123745
2023-01-24 02:31:26.802206: step: 294/469, loss: 0.1702626496553421
2023-01-24 02:31:27.382428: step: 296/469, loss: 0.09344138950109482
2023-01-24 02:31:27.995802: step: 298/469, loss: 0.1148252934217453
2023-01-24 02:31:28.627172: step: 300/469, loss: 0.06467646360397339
2023-01-24 02:31:29.272336: step: 302/469, loss: 0.04325678572058678
2023-01-24 02:31:29.892915: step: 304/469, loss: 0.12897565960884094
2023-01-24 02:31:30.486840: step: 306/469, loss: 0.14464987814426422
2023-01-24 02:31:31.045483: step: 308/469, loss: 0.07649722695350647
2023-01-24 02:31:31.708779: step: 310/469, loss: 0.18311582505702972
2023-01-24 02:31:32.332698: step: 312/469, loss: 0.10752494633197784
2023-01-24 02:31:32.959042: step: 314/469, loss: 0.16310743987560272
2023-01-24 02:31:33.564457: step: 316/469, loss: 0.16025860607624054
2023-01-24 02:31:34.234552: step: 318/469, loss: 0.06761769205331802
2023-01-24 02:31:34.900483: step: 320/469, loss: 0.24413201212882996
2023-01-24 02:31:35.635468: step: 322/469, loss: 0.08819463849067688
2023-01-24 02:31:36.278713: step: 324/469, loss: 0.055806148797273636
2023-01-24 02:31:36.846421: step: 326/469, loss: 0.09786657243967056
2023-01-24 02:31:37.443679: step: 328/469, loss: 0.20256228744983673
2023-01-24 02:31:38.047700: step: 330/469, loss: 0.10871902108192444
2023-01-24 02:31:38.661229: step: 332/469, loss: 0.7324473261833191
2023-01-24 02:31:39.327069: step: 334/469, loss: 0.4415014684200287
2023-01-24 02:31:40.021974: step: 336/469, loss: 0.18037280440330505
2023-01-24 02:31:40.692807: step: 338/469, loss: 0.13206717371940613
2023-01-24 02:31:41.317361: step: 340/469, loss: 0.13370883464813232
2023-01-24 02:31:41.904346: step: 342/469, loss: 0.04568473622202873
2023-01-24 02:31:42.503082: step: 344/469, loss: 0.10528954863548279
2023-01-24 02:31:43.079187: step: 346/469, loss: 0.06718618422746658
2023-01-24 02:31:43.702465: step: 348/469, loss: 0.4360056519508362
2023-01-24 02:31:44.337488: step: 350/469, loss: 0.20691066980361938
2023-01-24 02:31:44.958935: step: 352/469, loss: 0.22220776975154877
2023-01-24 02:31:45.630252: step: 354/469, loss: 0.14346978068351746
2023-01-24 02:31:46.239521: step: 356/469, loss: 0.022748466581106186
2023-01-24 02:31:46.793287: step: 358/469, loss: 0.04106808826327324
2023-01-24 02:31:47.573344: step: 360/469, loss: 0.0920754000544548
2023-01-24 02:31:48.171474: step: 362/469, loss: 0.1296059489250183
2023-01-24 02:31:48.796291: step: 364/469, loss: 4.278023719787598
2023-01-24 02:31:49.417925: step: 366/469, loss: 0.2297745794057846
2023-01-24 02:31:50.099392: step: 368/469, loss: 0.1554986536502838
2023-01-24 02:31:50.805826: step: 370/469, loss: 0.2550108730792999
2023-01-24 02:31:51.489508: step: 372/469, loss: 0.7753260731697083
2023-01-24 02:31:52.131868: step: 374/469, loss: 0.09382228553295135
2023-01-24 02:31:52.771826: step: 376/469, loss: 0.1605989933013916
2023-01-24 02:31:53.348206: step: 378/469, loss: 0.10666244477033615
2023-01-24 02:31:54.046420: step: 380/469, loss: 0.07900448143482208
2023-01-24 02:31:54.666175: step: 382/469, loss: 0.1279546618461609
2023-01-24 02:31:55.248604: step: 384/469, loss: 0.22945332527160645
2023-01-24 02:31:55.932161: step: 386/469, loss: 0.09080290794372559
2023-01-24 02:31:56.575316: step: 388/469, loss: 0.1418457180261612
2023-01-24 02:31:57.252783: step: 390/469, loss: 0.24508439004421234
2023-01-24 02:31:57.848906: step: 392/469, loss: 0.17116393148899078
2023-01-24 02:31:58.458362: step: 394/469, loss: 0.242109015583992
2023-01-24 02:31:59.086269: step: 396/469, loss: 0.1886899173259735
2023-01-24 02:31:59.723339: step: 398/469, loss: 0.1522700935602188
2023-01-24 02:32:00.338436: step: 400/469, loss: 0.12411347031593323
2023-01-24 02:32:00.955343: step: 402/469, loss: 0.04242609441280365
2023-01-24 02:32:01.581789: step: 404/469, loss: 0.11626464128494263
2023-01-24 02:32:02.209534: step: 406/469, loss: 0.055477697402238846
2023-01-24 02:32:02.837992: step: 408/469, loss: 1.790461778640747
2023-01-24 02:32:03.538319: step: 410/469, loss: 0.07347521930932999
2023-01-24 02:32:04.141996: step: 412/469, loss: 0.26559871435165405
2023-01-24 02:32:04.863213: step: 414/469, loss: 0.14984188973903656
2023-01-24 02:32:05.413739: step: 416/469, loss: 0.09180110692977905
2023-01-24 02:32:06.022773: step: 418/469, loss: 0.020643198862671852
2023-01-24 02:32:06.652580: step: 420/469, loss: 1.720484733581543
2023-01-24 02:32:07.303681: step: 422/469, loss: 0.2571749985218048
2023-01-24 02:32:07.953214: step: 424/469, loss: 0.729462206363678
2023-01-24 02:32:08.572077: step: 426/469, loss: 0.09000333398580551
2023-01-24 02:32:09.228495: step: 428/469, loss: 0.14303572475910187
2023-01-24 02:32:09.785944: step: 430/469, loss: 0.43912845849990845
2023-01-24 02:32:10.413905: step: 432/469, loss: 0.1708480715751648
2023-01-24 02:32:10.976182: step: 434/469, loss: 0.12771329283714294
2023-01-24 02:32:11.652506: step: 436/469, loss: 0.13828711211681366
2023-01-24 02:32:12.290799: step: 438/469, loss: 0.05810357257723808
2023-01-24 02:32:12.878479: step: 440/469, loss: 0.10804131627082825
2023-01-24 02:32:13.546708: step: 442/469, loss: 0.39033204317092896
2023-01-24 02:32:14.178997: step: 444/469, loss: 0.24288532137870789
2023-01-24 02:32:14.843285: step: 446/469, loss: 0.06511227786540985
2023-01-24 02:32:15.512154: step: 448/469, loss: 0.1720336675643921
2023-01-24 02:32:16.129565: step: 450/469, loss: 0.03472485765814781
2023-01-24 02:32:16.751117: step: 452/469, loss: 0.1822018325328827
2023-01-24 02:32:17.398663: step: 454/469, loss: 0.3212077021598816
2023-01-24 02:32:18.029902: step: 456/469, loss: 0.15403354167938232
2023-01-24 02:32:18.648877: step: 458/469, loss: 0.06975863128900528
2023-01-24 02:32:19.343565: step: 460/469, loss: 0.09824459254741669
2023-01-24 02:32:19.961316: step: 462/469, loss: 0.23142506182193756
2023-01-24 02:32:20.495962: step: 464/469, loss: 0.3873835802078247
2023-01-24 02:32:21.100443: step: 466/469, loss: 0.06888294219970703
2023-01-24 02:32:21.677720: step: 468/469, loss: 0.09126056730747223
2023-01-24 02:32:22.238479: step: 470/469, loss: 0.17858542501926422
2023-01-24 02:32:22.866767: step: 472/469, loss: 0.3323478102684021
2023-01-24 02:32:23.547240: step: 474/469, loss: 0.17380979657173157
2023-01-24 02:32:24.175456: step: 476/469, loss: 0.062146540731191635
2023-01-24 02:32:24.820862: step: 478/469, loss: 0.27766653895378113
2023-01-24 02:32:25.404961: step: 480/469, loss: 0.23081547021865845
2023-01-24 02:32:26.031213: step: 482/469, loss: 0.08713293820619583
2023-01-24 02:32:26.655256: step: 484/469, loss: 0.14310593903064728
2023-01-24 02:32:27.315946: step: 486/469, loss: 0.12722964584827423
2023-01-24 02:32:27.927511: step: 488/469, loss: 0.11158411204814911
2023-01-24 02:32:28.545833: step: 490/469, loss: 0.15808811783790588
2023-01-24 02:32:29.187708: step: 492/469, loss: 0.1756688505411148
2023-01-24 02:32:29.801166: step: 494/469, loss: 0.24683654308319092
2023-01-24 02:32:30.452267: step: 496/469, loss: 0.08902494609355927
2023-01-24 02:32:31.143494: step: 498/469, loss: 0.795413613319397
2023-01-24 02:32:31.721720: step: 500/469, loss: 0.09781542420387268
2023-01-24 02:32:32.291267: step: 502/469, loss: 0.08164943754673004
2023-01-24 02:32:32.904722: step: 504/469, loss: 0.2103188931941986
2023-01-24 02:32:33.509699: step: 506/469, loss: 0.0565982349216938
2023-01-24 02:32:34.072544: step: 508/469, loss: 5.4032769203186035
2023-01-24 02:32:34.750598: step: 510/469, loss: 0.10968939960002899
2023-01-24 02:32:35.368149: step: 512/469, loss: 0.28326985239982605
2023-01-24 02:32:35.990583: step: 514/469, loss: 0.3121934235095978
2023-01-24 02:32:36.670619: step: 516/469, loss: 0.24992839992046356
2023-01-24 02:32:37.292916: step: 518/469, loss: 0.08476626873016357
2023-01-24 02:32:37.912591: step: 520/469, loss: 0.10821449011564255
2023-01-24 02:32:38.512883: step: 522/469, loss: 0.1344277411699295
2023-01-24 02:32:39.163341: step: 524/469, loss: 0.13020645081996918
2023-01-24 02:32:39.873206: step: 526/469, loss: 0.08565562218427658
2023-01-24 02:32:40.509399: step: 528/469, loss: 0.07130774110555649
2023-01-24 02:32:41.173718: step: 530/469, loss: 0.2628646492958069
2023-01-24 02:32:41.804824: step: 532/469, loss: 0.1671563684940338
2023-01-24 02:32:42.417970: step: 534/469, loss: 0.5488623976707458
2023-01-24 02:32:43.110281: step: 536/469, loss: 0.39646124839782715
2023-01-24 02:32:43.696334: step: 538/469, loss: 0.17689861357212067
2023-01-24 02:32:44.311748: step: 540/469, loss: 0.10598752647638321
2023-01-24 02:32:44.982181: step: 542/469, loss: 0.06343793123960495
2023-01-24 02:32:45.589575: step: 544/469, loss: 0.7502897381782532
2023-01-24 02:32:46.178074: step: 546/469, loss: 0.15774798393249512
2023-01-24 02:32:46.798641: step: 548/469, loss: 0.3987104296684265
2023-01-24 02:32:47.434769: step: 550/469, loss: 0.08389110118150711
2023-01-24 02:32:48.046594: step: 552/469, loss: 0.08007057011127472
2023-01-24 02:32:48.661720: step: 554/469, loss: 0.0611308217048645
2023-01-24 02:32:49.281220: step: 556/469, loss: 0.15443934500217438
2023-01-24 02:32:49.940548: step: 558/469, loss: 0.6160106658935547
2023-01-24 02:32:50.558372: step: 560/469, loss: 0.10961678624153137
2023-01-24 02:32:51.107184: step: 562/469, loss: 0.305407851934433
2023-01-24 02:32:51.771552: step: 564/469, loss: 0.14642421901226044
2023-01-24 02:32:52.391995: step: 566/469, loss: 0.0951080173254013
2023-01-24 02:32:53.049572: step: 568/469, loss: 0.5984731912612915
2023-01-24 02:32:53.613182: step: 570/469, loss: 0.11568977683782578
2023-01-24 02:32:54.239615: step: 572/469, loss: 6.023694038391113
2023-01-24 02:32:54.868586: step: 574/469, loss: 0.09959385544061661
2023-01-24 02:32:55.481300: step: 576/469, loss: 0.18258406221866608
2023-01-24 02:32:56.244917: step: 578/469, loss: 0.11768639832735062
2023-01-24 02:32:56.957647: step: 580/469, loss: 0.09279417246580124
2023-01-24 02:32:57.631514: step: 582/469, loss: 0.24119991064071655
2023-01-24 02:32:58.320700: step: 584/469, loss: 0.09772532433271408
2023-01-24 02:32:59.071539: step: 586/469, loss: 0.08091095834970474
2023-01-24 02:32:59.661257: step: 588/469, loss: 0.13571064174175262
2023-01-24 02:33:00.341430: step: 590/469, loss: 0.2654077112674713
2023-01-24 02:33:00.955046: step: 592/469, loss: 0.2599298655986786
2023-01-24 02:33:01.575976: step: 594/469, loss: 0.2853321433067322
2023-01-24 02:33:02.145506: step: 596/469, loss: 0.22529801726341248
2023-01-24 02:33:02.758465: step: 598/469, loss: 0.030955595895648003
2023-01-24 02:33:03.414317: step: 600/469, loss: 0.4796280860900879
2023-01-24 02:33:04.101610: step: 602/469, loss: 1.3972283601760864
2023-01-24 02:33:04.690499: step: 604/469, loss: 0.03801490366458893
2023-01-24 02:33:05.296512: step: 606/469, loss: 0.15013805031776428
2023-01-24 02:33:05.912639: step: 608/469, loss: 0.14290277659893036
2023-01-24 02:33:06.493125: step: 610/469, loss: 0.2417699247598648
2023-01-24 02:33:07.128465: step: 612/469, loss: 0.14221957325935364
2023-01-24 02:33:07.796356: step: 614/469, loss: 0.10216628015041351
2023-01-24 02:33:08.442569: step: 616/469, loss: 0.05295451357960701
2023-01-24 02:33:09.110337: step: 618/469, loss: 0.30216163396835327
2023-01-24 02:33:09.711155: step: 620/469, loss: 0.15360566973686218
2023-01-24 02:33:10.346804: step: 622/469, loss: 0.05645817890763283
2023-01-24 02:33:10.953439: step: 624/469, loss: 0.2515581250190735
2023-01-24 02:33:11.488253: step: 626/469, loss: 0.11840242147445679
2023-01-24 02:33:12.084883: step: 628/469, loss: 0.22216592729091644
2023-01-24 02:33:12.670468: step: 630/469, loss: 0.503872811794281
2023-01-24 02:33:13.279903: step: 632/469, loss: 0.19764861464500427
2023-01-24 02:33:13.872510: step: 634/469, loss: 0.1398444026708603
2023-01-24 02:33:14.467358: step: 636/469, loss: 0.055364448577165604
2023-01-24 02:33:15.080696: step: 638/469, loss: 0.25784334540367126
2023-01-24 02:33:15.679925: step: 640/469, loss: 0.10682844370603561
2023-01-24 02:33:16.325199: step: 642/469, loss: 0.06462714076042175
2023-01-24 02:33:17.164472: step: 644/469, loss: 0.22312414646148682
2023-01-24 02:33:17.849142: step: 646/469, loss: 0.15961511433124542
2023-01-24 02:33:18.505689: step: 648/469, loss: 0.20165929198265076
2023-01-24 02:33:19.206793: step: 650/469, loss: 0.06946925818920135
2023-01-24 02:33:19.796784: step: 652/469, loss: 0.12248215079307556
2023-01-24 02:33:20.452788: step: 654/469, loss: 0.05839003622531891
2023-01-24 02:33:21.087127: step: 656/469, loss: 0.21611042320728302
2023-01-24 02:33:21.699919: step: 658/469, loss: 0.11688397824764252
2023-01-24 02:33:22.248470: step: 660/469, loss: 0.06755553185939789
2023-01-24 02:33:22.849713: step: 662/469, loss: 0.7772153615951538
2023-01-24 02:33:23.437454: step: 664/469, loss: 0.026373213157057762
2023-01-24 02:33:24.036388: step: 666/469, loss: 0.5589932203292847
2023-01-24 02:33:24.676372: step: 668/469, loss: 0.13581423461437225
2023-01-24 02:33:25.217307: step: 670/469, loss: 0.03913614898920059
2023-01-24 02:33:25.871620: step: 672/469, loss: 0.04955853521823883
2023-01-24 02:33:26.520456: step: 674/469, loss: 0.11273442953824997
2023-01-24 02:33:27.207707: step: 676/469, loss: 0.23610681295394897
2023-01-24 02:33:27.893570: step: 678/469, loss: 0.3757669925689697
2023-01-24 02:33:28.507738: step: 680/469, loss: 0.10171528160572052
2023-01-24 02:33:29.147056: step: 682/469, loss: 0.16474813222885132
2023-01-24 02:33:29.764747: step: 684/469, loss: 0.08703788369894028
2023-01-24 02:33:30.357464: step: 686/469, loss: 0.08651354163885117
2023-01-24 02:33:30.969810: step: 688/469, loss: 0.06881536543369293
2023-01-24 02:33:31.579342: step: 690/469, loss: 0.058468058705329895
2023-01-24 02:33:32.233066: step: 692/469, loss: 0.21539010107517242
2023-01-24 02:33:32.818355: step: 694/469, loss: 0.1317528784275055
2023-01-24 02:33:33.490668: step: 696/469, loss: 0.10898716002702713
2023-01-24 02:33:34.094043: step: 698/469, loss: 0.0771978348493576
2023-01-24 02:33:34.744669: step: 700/469, loss: 0.2742895483970642
2023-01-24 02:33:35.319962: step: 702/469, loss: 0.6433630585670471
2023-01-24 02:33:35.903880: step: 704/469, loss: 0.09457377344369888
2023-01-24 02:33:36.511790: step: 706/469, loss: 0.1278889775276184
2023-01-24 02:33:37.099333: step: 708/469, loss: 0.18659457564353943
2023-01-24 02:33:37.672362: step: 710/469, loss: 0.02622041292488575
2023-01-24 02:33:38.380222: step: 712/469, loss: 0.20351165533065796
2023-01-24 02:33:39.022718: step: 714/469, loss: 0.1452672928571701
2023-01-24 02:33:39.638618: step: 716/469, loss: 0.05882904306054115
2023-01-24 02:33:40.233795: step: 718/469, loss: 0.37130770087242126
2023-01-24 02:33:40.911453: step: 720/469, loss: 0.31439873576164246
2023-01-24 02:33:41.573257: step: 722/469, loss: 0.3346779942512512
2023-01-24 02:33:42.209998: step: 724/469, loss: 0.10287675261497498
2023-01-24 02:33:42.783790: step: 726/469, loss: 0.12727101147174835
2023-01-24 02:33:43.390298: step: 728/469, loss: 0.11457782983779907
2023-01-24 02:33:43.999209: step: 730/469, loss: 0.09384400397539139
2023-01-24 02:33:44.635125: step: 732/469, loss: 0.22653897106647491
2023-01-24 02:33:45.227471: step: 734/469, loss: 0.13181161880493164
2023-01-24 02:33:45.843259: step: 736/469, loss: 0.10666980594396591
2023-01-24 02:33:46.482347: step: 738/469, loss: 0.30227920413017273
2023-01-24 02:33:47.106438: step: 740/469, loss: 0.009498314931988716
2023-01-24 02:33:47.768951: step: 742/469, loss: 0.10703202337026596
2023-01-24 02:33:48.383782: step: 744/469, loss: 0.09349490702152252
2023-01-24 02:33:48.976189: step: 746/469, loss: 0.11710042506456375
2023-01-24 02:33:49.615806: step: 748/469, loss: 0.13578684628009796
2023-01-24 02:33:50.248770: step: 750/469, loss: 0.5420204401016235
2023-01-24 02:33:50.927292: step: 752/469, loss: 0.09380146116018295
2023-01-24 02:33:51.627837: step: 754/469, loss: 0.13721023499965668
2023-01-24 02:33:52.361613: step: 756/469, loss: 0.06682857125997543
2023-01-24 02:33:52.962995: step: 758/469, loss: 0.18444392085075378
2023-01-24 02:33:53.596361: step: 760/469, loss: 0.10151823610067368
2023-01-24 02:33:54.134677: step: 762/469, loss: 0.13188521564006805
2023-01-24 02:33:54.780030: step: 764/469, loss: 0.05160628259181976
2023-01-24 02:33:55.442515: step: 766/469, loss: 0.05794839188456535
2023-01-24 02:33:56.107076: step: 768/469, loss: 0.22263142466545105
2023-01-24 02:33:56.709572: step: 770/469, loss: 0.1093907505273819
2023-01-24 02:33:57.275290: step: 772/469, loss: 0.430452823638916
2023-01-24 02:33:57.871234: step: 774/469, loss: 0.26735109090805054
2023-01-24 02:33:58.565951: step: 776/469, loss: 0.07764904201030731
2023-01-24 02:33:59.245726: step: 778/469, loss: 0.1075054332613945
2023-01-24 02:33:59.893325: step: 780/469, loss: 0.08013945072889328
2023-01-24 02:34:00.475597: step: 782/469, loss: 0.11447945237159729
2023-01-24 02:34:01.057865: step: 784/469, loss: 0.1060430034995079
2023-01-24 02:34:01.727491: step: 786/469, loss: 0.05648250877857208
2023-01-24 02:34:02.527892: step: 788/469, loss: 0.18438391387462616
2023-01-24 02:34:03.135514: step: 790/469, loss: 0.7078243494033813
2023-01-24 02:34:03.725662: step: 792/469, loss: 0.151078462600708
2023-01-24 02:34:04.274375: step: 794/469, loss: 0.1268588751554489
2023-01-24 02:34:04.908802: step: 796/469, loss: 0.23044250905513763
2023-01-24 02:34:05.537539: step: 798/469, loss: 0.08206214010715485
2023-01-24 02:34:06.094585: step: 800/469, loss: 4.870852470397949
2023-01-24 02:34:06.687176: step: 802/469, loss: 0.12381969392299652
2023-01-24 02:34:07.242927: step: 804/469, loss: 0.7066172361373901
2023-01-24 02:34:07.891940: step: 806/469, loss: 0.10656490176916122
2023-01-24 02:34:08.498528: step: 808/469, loss: 0.2443525493144989
2023-01-24 02:34:09.112632: step: 810/469, loss: 0.15172456204891205
2023-01-24 02:34:09.754783: step: 812/469, loss: 0.6226106286048889
2023-01-24 02:34:10.403242: step: 814/469, loss: 0.07676031440496445
2023-01-24 02:34:11.081129: step: 816/469, loss: 0.24102750420570374
2023-01-24 02:34:11.737360: step: 818/469, loss: 0.33800965547561646
2023-01-24 02:34:12.348933: step: 820/469, loss: 0.11378297954797745
2023-01-24 02:34:13.081361: step: 822/469, loss: 0.16470292210578918
2023-01-24 02:34:13.742140: step: 824/469, loss: 0.6618489027023315
2023-01-24 02:34:14.323429: step: 826/469, loss: 0.3794376254081726
2023-01-24 02:34:14.936045: step: 828/469, loss: 0.626031756401062
2023-01-24 02:34:15.558494: step: 830/469, loss: 0.07717182487249374
2023-01-24 02:34:16.202869: step: 832/469, loss: 0.44119834899902344
2023-01-24 02:34:16.804912: step: 834/469, loss: 0.10924064368009567
2023-01-24 02:34:17.417220: step: 836/469, loss: 0.7192559242248535
2023-01-24 02:34:18.149190: step: 838/469, loss: 0.4965914785861969
2023-01-24 02:34:18.731636: step: 840/469, loss: 0.16419176757335663
2023-01-24 02:34:19.357961: step: 842/469, loss: 0.0885121151804924
2023-01-24 02:34:20.018937: step: 844/469, loss: 0.1369175910949707
2023-01-24 02:34:20.641887: step: 846/469, loss: 0.099001444876194
2023-01-24 02:34:21.264910: step: 848/469, loss: 0.10022465139627457
2023-01-24 02:34:21.881755: step: 850/469, loss: 0.08107144385576248
2023-01-24 02:34:22.501632: step: 852/469, loss: 0.17233121395111084
2023-01-24 02:34:23.095237: step: 854/469, loss: 0.2208385467529297
2023-01-24 02:34:23.673544: step: 856/469, loss: 0.06338278204202652
2023-01-24 02:34:24.334698: step: 858/469, loss: 0.16312026977539062
2023-01-24 02:34:24.965050: step: 860/469, loss: 0.060767509043216705
2023-01-24 02:34:25.594085: step: 862/469, loss: 0.1104615107178688
2023-01-24 02:34:26.138225: step: 864/469, loss: 0.12299557030200958
2023-01-24 02:34:26.757160: step: 866/469, loss: 0.4790195822715759
2023-01-24 02:34:27.423560: step: 868/469, loss: 0.186064213514328
2023-01-24 02:34:28.115480: step: 870/469, loss: 0.11863426119089127
2023-01-24 02:34:28.739137: step: 872/469, loss: 0.17843379080295563
2023-01-24 02:34:29.352554: step: 874/469, loss: 0.09139204770326614
2023-01-24 02:34:29.916281: step: 876/469, loss: 0.08099238574504852
2023-01-24 02:34:30.572297: step: 878/469, loss: 0.6278374195098877
2023-01-24 02:34:31.197913: step: 880/469, loss: 0.1151077151298523
2023-01-24 02:34:31.795564: step: 882/469, loss: 0.193647563457489
2023-01-24 02:34:32.408162: step: 884/469, loss: 0.11502914875745773
2023-01-24 02:34:33.053594: step: 886/469, loss: 0.11790961772203445
2023-01-24 02:34:33.734672: step: 888/469, loss: 0.06212463602423668
2023-01-24 02:34:34.432723: step: 890/469, loss: 0.13378936052322388
2023-01-24 02:34:35.055393: step: 892/469, loss: 0.10703791677951813
2023-01-24 02:34:35.666873: step: 894/469, loss: 0.4593944847583771
2023-01-24 02:34:36.325395: step: 896/469, loss: 0.10451531410217285
2023-01-24 02:34:36.962320: step: 898/469, loss: 1.5565106868743896
2023-01-24 02:34:37.572673: step: 900/469, loss: 0.6149523854255676
2023-01-24 02:34:38.214418: step: 902/469, loss: 0.19858333468437195
2023-01-24 02:34:38.887908: step: 904/469, loss: 0.13087432086467743
2023-01-24 02:34:39.490401: step: 906/469, loss: 0.129456028342247
2023-01-24 02:34:40.108217: step: 908/469, loss: 0.08298467099666595
2023-01-24 02:34:40.711674: step: 910/469, loss: 0.061458345502614975
2023-01-24 02:34:41.344139: step: 912/469, loss: 0.10581742227077484
2023-01-24 02:34:42.038320: step: 914/469, loss: 0.11968250572681427
2023-01-24 02:34:42.659015: step: 916/469, loss: 0.061378706246614456
2023-01-24 02:34:43.391680: step: 918/469, loss: 0.10897963494062424
2023-01-24 02:34:44.048925: step: 920/469, loss: 0.053679272532463074
2023-01-24 02:34:44.714785: step: 922/469, loss: 0.12484706193208694
2023-01-24 02:34:45.319895: step: 924/469, loss: 0.052165526896715164
2023-01-24 02:34:46.034148: step: 926/469, loss: 0.09519276767969131
2023-01-24 02:34:46.578640: step: 928/469, loss: 0.11334328353404999
2023-01-24 02:34:47.240521: step: 930/469, loss: 0.14731420576572418
2023-01-24 02:34:47.839444: step: 932/469, loss: 0.27927833795547485
2023-01-24 02:34:48.497191: step: 934/469, loss: 0.12212363630533218
2023-01-24 02:34:49.097705: step: 936/469, loss: 0.07453291863203049
2023-01-24 02:34:49.781056: step: 938/469, loss: 0.12962879240512848
==================================================
Loss: 0.253
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3174178048158441, 'r': 0.3156108723406116, 'f1': 0.31651175970219275}, 'combined': 0.23321919135951044, 'epoch': 13}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32415176670519175, 'r': 0.253271371240836, 'f1': 0.28436118003722005}, 'combined': 0.15510609820212, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3306888267355135, 'r': 0.3124915288696124, 'f1': 0.3213327526132404}, 'combined': 0.23677150192554555, 'epoch': 13}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3274935202969598, 'r': 0.2528861218029589, 'f1': 0.2853944565107218}, 'combined': 0.1556697035513028, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3142584470435348, 'r': 0.30591002530044276, 'f1': 0.31002804487179486}, 'combined': 0.2284417172739541, 'epoch': 13}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3150092717927619, 'r': 0.2504511044720129, 'f1': 0.2790449104871663}, 'combined': 0.1522063148111816, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2300724637681159, 'r': 0.30238095238095236, 'f1': 0.2613168724279835}, 'combined': 0.17421124828532233, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2826086956521739, 'r': 0.2826086956521739, 'f1': 0.2826086956521739}, 'combined': 0.14130434782608695, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4, 'r': 0.13793103448275862, 'f1': 0.20512820512820515}, 'combined': 0.13675213675213677, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 02:37:35.628892: step: 2/469, loss: 0.10332942008972168
2023-01-24 02:37:36.228165: step: 4/469, loss: 0.15318186581134796
2023-01-24 02:37:36.776641: step: 6/469, loss: 0.02971917763352394
2023-01-24 02:37:37.385015: step: 8/469, loss: 0.23199088871479034
2023-01-24 02:37:38.040409: step: 10/469, loss: 0.4790060818195343
2023-01-24 02:37:38.717177: step: 12/469, loss: 0.10452570021152496
2023-01-24 02:37:39.278839: step: 14/469, loss: 0.29724445939064026
2023-01-24 02:37:39.878802: step: 16/469, loss: 0.08338034898042679
2023-01-24 02:37:40.520787: step: 18/469, loss: 0.17674116790294647
2023-01-24 02:37:41.173950: step: 20/469, loss: 0.2040647268295288
2023-01-24 02:37:41.846977: step: 22/469, loss: 0.06422922760248184
2023-01-24 02:37:42.465033: step: 24/469, loss: 0.04940135404467583
2023-01-24 02:37:43.189649: step: 26/469, loss: 0.8426660299301147
2023-01-24 02:37:43.833606: step: 28/469, loss: 0.1423974633216858
2023-01-24 02:37:44.474029: step: 30/469, loss: 0.11744549870491028
2023-01-24 02:37:45.139327: step: 32/469, loss: 0.11263231188058853
2023-01-24 02:37:45.790624: step: 34/469, loss: 0.1099047139286995
2023-01-24 02:37:46.411238: step: 36/469, loss: 0.041722141206264496
2023-01-24 02:37:47.046017: step: 38/469, loss: 0.14946915209293365
2023-01-24 02:37:47.649631: step: 40/469, loss: 0.020181039348244667
2023-01-24 02:37:48.290246: step: 42/469, loss: 0.0604877732694149
2023-01-24 02:37:48.934766: step: 44/469, loss: 0.24753527343273163
2023-01-24 02:37:49.577120: step: 46/469, loss: 0.07693887501955032
2023-01-24 02:37:50.179184: step: 48/469, loss: 0.12376142293214798
2023-01-24 02:37:50.739113: step: 50/469, loss: 0.17435595393180847
2023-01-24 02:37:51.393180: step: 52/469, loss: 0.08856833726167679
2023-01-24 02:37:52.013330: step: 54/469, loss: 0.09702426940202713
2023-01-24 02:37:52.633013: step: 56/469, loss: 0.09591094404459
2023-01-24 02:37:53.266407: step: 58/469, loss: 0.23975864052772522
2023-01-24 02:37:53.977350: step: 60/469, loss: 0.12130329757928848
2023-01-24 02:37:54.595422: step: 62/469, loss: 0.5318564176559448
2023-01-24 02:37:55.317754: step: 64/469, loss: 0.03839130699634552
2023-01-24 02:37:55.917467: step: 66/469, loss: 0.1523742824792862
2023-01-24 02:37:56.589011: step: 68/469, loss: 0.07893607020378113
2023-01-24 02:37:57.210411: step: 70/469, loss: 0.03052467294037342
2023-01-24 02:37:57.789439: step: 72/469, loss: 0.07498115301132202
2023-01-24 02:37:58.369222: step: 74/469, loss: 0.17781122028827667
2023-01-24 02:37:58.982749: step: 76/469, loss: 0.14667977392673492
2023-01-24 02:37:59.683679: step: 78/469, loss: 0.13367553055286407
2023-01-24 02:38:00.310486: step: 80/469, loss: 0.06649041175842285
2023-01-24 02:38:00.876358: step: 82/469, loss: 0.05659692734479904
2023-01-24 02:38:01.502891: step: 84/469, loss: 0.13454948365688324
2023-01-24 02:38:02.125655: step: 86/469, loss: 0.0643838495016098
2023-01-24 02:38:02.733450: step: 88/469, loss: 0.026117002591490746
2023-01-24 02:38:03.358841: step: 90/469, loss: 0.13594715297222137
2023-01-24 02:38:03.977273: step: 92/469, loss: 0.07614948600530624
2023-01-24 02:38:04.552655: step: 94/469, loss: 0.047005388885736465
2023-01-24 02:38:05.152329: step: 96/469, loss: 0.0802338495850563
2023-01-24 02:38:05.807427: step: 98/469, loss: 0.3998774588108063
2023-01-24 02:38:06.432932: step: 100/469, loss: 0.31478893756866455
2023-01-24 02:38:07.130497: step: 102/469, loss: 0.1145135685801506
2023-01-24 02:38:07.749555: step: 104/469, loss: 0.2985832691192627
2023-01-24 02:38:08.369091: step: 106/469, loss: 0.20097951591014862
2023-01-24 02:38:08.920473: step: 108/469, loss: 0.16306962072849274
2023-01-24 02:38:09.555212: step: 110/469, loss: 0.082069993019104
2023-01-24 02:38:10.213185: step: 112/469, loss: 0.06915789842605591
2023-01-24 02:38:10.862605: step: 114/469, loss: 0.15192940831184387
2023-01-24 02:38:11.447827: step: 116/469, loss: 0.0210536178201437
2023-01-24 02:38:12.172025: step: 118/469, loss: 0.088052898645401
2023-01-24 02:38:12.865016: step: 120/469, loss: 0.3189176619052887
2023-01-24 02:38:13.503526: step: 122/469, loss: 0.15892644226551056
2023-01-24 02:38:14.116337: step: 124/469, loss: 0.09577824920415878
2023-01-24 02:38:14.722536: step: 126/469, loss: 0.45442742109298706
2023-01-24 02:38:15.398405: step: 128/469, loss: 0.11800581961870193
2023-01-24 02:38:16.051014: step: 130/469, loss: 0.9997729063034058
2023-01-24 02:38:16.665150: step: 132/469, loss: 0.07901173084974289
2023-01-24 02:38:17.308437: step: 134/469, loss: 0.06526058912277222
2023-01-24 02:38:17.889656: step: 136/469, loss: 0.04950903728604317
2023-01-24 02:38:18.523850: step: 138/469, loss: 0.08496760576963425
2023-01-24 02:38:19.117414: step: 140/469, loss: 0.1285533308982849
2023-01-24 02:38:19.805049: step: 142/469, loss: 0.5144191980361938
2023-01-24 02:38:20.415457: step: 144/469, loss: 0.060713667422533035
2023-01-24 02:38:21.101359: step: 146/469, loss: 0.05216887965798378
2023-01-24 02:38:21.748686: step: 148/469, loss: 0.13779819011688232
2023-01-24 02:38:22.350032: step: 150/469, loss: 0.004605674184858799
2023-01-24 02:38:22.974445: step: 152/469, loss: 0.08874347805976868
2023-01-24 02:38:23.738865: step: 154/469, loss: 0.14072492718696594
2023-01-24 02:38:24.454451: step: 156/469, loss: 0.29532474279403687
2023-01-24 02:38:25.059212: step: 158/469, loss: 0.13115055859088898
2023-01-24 02:38:25.734831: step: 160/469, loss: 0.24021399021148682
2023-01-24 02:38:26.341227: step: 162/469, loss: 0.1281098872423172
2023-01-24 02:38:26.991980: step: 164/469, loss: 0.32909175753593445
2023-01-24 02:38:27.648320: step: 166/469, loss: 0.07739514857530594
2023-01-24 02:38:28.219525: step: 168/469, loss: 0.1669360101222992
2023-01-24 02:38:28.830620: step: 170/469, loss: 0.08854109048843384
2023-01-24 02:38:29.447477: step: 172/469, loss: 0.17195796966552734
2023-01-24 02:38:30.086596: step: 174/469, loss: 0.05586585775017738
2023-01-24 02:38:30.690644: step: 176/469, loss: 0.05410011112689972
2023-01-24 02:38:31.405642: step: 178/469, loss: 0.09139525145292282
2023-01-24 02:38:32.010381: step: 180/469, loss: 0.19453096389770508
2023-01-24 02:38:32.588518: step: 182/469, loss: 0.07657577097415924
2023-01-24 02:38:33.185131: step: 184/469, loss: 0.059658583253622055
2023-01-24 02:38:33.839305: step: 186/469, loss: 0.1249004378914833
2023-01-24 02:38:34.478259: step: 188/469, loss: 0.05884033069014549
2023-01-24 02:38:35.071568: step: 190/469, loss: 0.05664648860692978
2023-01-24 02:38:35.687332: step: 192/469, loss: 0.08319837599992752
2023-01-24 02:38:36.300942: step: 194/469, loss: 0.06288447231054306
2023-01-24 02:38:36.967901: step: 196/469, loss: 0.04063792526721954
2023-01-24 02:38:37.628262: step: 198/469, loss: 0.11769529432058334
2023-01-24 02:38:38.228029: step: 200/469, loss: 0.21704784035682678
2023-01-24 02:38:38.871164: step: 202/469, loss: 0.09529057890176773
2023-01-24 02:38:39.528784: step: 204/469, loss: 0.1181119978427887
2023-01-24 02:38:40.156902: step: 206/469, loss: 0.3056814968585968
2023-01-24 02:38:40.750463: step: 208/469, loss: 0.14676477015018463
2023-01-24 02:38:41.401897: step: 210/469, loss: 0.13852152228355408
2023-01-24 02:38:41.974454: step: 212/469, loss: 0.05900540575385094
2023-01-24 02:38:42.670596: step: 214/469, loss: 0.508470892906189
2023-01-24 02:38:43.308721: step: 216/469, loss: 0.08568944782018661
2023-01-24 02:38:43.980005: step: 218/469, loss: 1.2057976722717285
2023-01-24 02:38:44.615984: step: 220/469, loss: 0.13676388561725616
2023-01-24 02:38:45.258750: step: 222/469, loss: 1.3510915040969849
2023-01-24 02:38:45.899232: step: 224/469, loss: 0.061254069209098816
2023-01-24 02:38:46.475666: step: 226/469, loss: 0.06155312433838844
2023-01-24 02:38:47.137905: step: 228/469, loss: 0.12289540469646454
2023-01-24 02:38:47.773921: step: 230/469, loss: 0.10985579341650009
2023-01-24 02:38:48.339608: step: 232/469, loss: 0.06253089755773544
2023-01-24 02:38:48.968829: step: 234/469, loss: 0.0936756283044815
2023-01-24 02:38:49.575621: step: 236/469, loss: 0.22473719716072083
2023-01-24 02:38:50.186791: step: 238/469, loss: 0.17043496668338776
2023-01-24 02:38:50.817895: step: 240/469, loss: 0.17724712193012238
2023-01-24 02:38:51.430509: step: 242/469, loss: 0.19856032729148865
2023-01-24 02:38:52.072484: step: 244/469, loss: 0.14592309296131134
2023-01-24 02:38:52.669723: step: 246/469, loss: 0.2929247319698334
2023-01-24 02:38:53.302966: step: 248/469, loss: 0.03559292107820511
2023-01-24 02:38:54.011480: step: 250/469, loss: 0.18467766046524048
2023-01-24 02:38:54.657510: step: 252/469, loss: 0.22038336098194122
2023-01-24 02:38:55.362139: step: 254/469, loss: 0.2405225783586502
2023-01-24 02:38:55.973526: step: 256/469, loss: 0.06776655465364456
2023-01-24 02:38:56.665821: step: 258/469, loss: 0.39306890964508057
2023-01-24 02:38:57.307561: step: 260/469, loss: 0.197803795337677
2023-01-24 02:38:57.891844: step: 262/469, loss: 0.32039666175842285
2023-01-24 02:38:58.617298: step: 264/469, loss: 0.4617033302783966
2023-01-24 02:38:59.218082: step: 266/469, loss: 0.07465508580207825
2023-01-24 02:38:59.828449: step: 268/469, loss: 0.040636174380779266
2023-01-24 02:39:00.425074: step: 270/469, loss: 0.15625329315662384
2023-01-24 02:39:01.071061: step: 272/469, loss: 0.11528942734003067
2023-01-24 02:39:01.684923: step: 274/469, loss: 0.645728349685669
2023-01-24 02:39:02.331751: step: 276/469, loss: 0.10598640888929367
2023-01-24 02:39:02.952438: step: 278/469, loss: 0.043184954673051834
2023-01-24 02:39:03.579014: step: 280/469, loss: 0.07680285722017288
2023-01-24 02:39:04.221688: step: 282/469, loss: 0.11312734335660934
2023-01-24 02:39:04.829993: step: 284/469, loss: 0.15231028199195862
2023-01-24 02:39:05.482926: step: 286/469, loss: 0.16574519872665405
2023-01-24 02:39:06.103571: step: 288/469, loss: 0.06007889658212662
2023-01-24 02:39:06.748308: step: 290/469, loss: 0.1410341113805771
2023-01-24 02:39:07.359935: step: 292/469, loss: 0.05999002233147621
2023-01-24 02:39:07.929949: step: 294/469, loss: 0.3854758143424988
2023-01-24 02:39:08.630349: step: 296/469, loss: 0.11680712550878525
2023-01-24 02:39:09.298837: step: 298/469, loss: 0.02858937531709671
2023-01-24 02:39:09.900422: step: 300/469, loss: 0.2283831387758255
2023-01-24 02:39:10.568096: step: 302/469, loss: 0.09304335713386536
2023-01-24 02:39:11.231010: step: 304/469, loss: 0.21670663356781006
2023-01-24 02:39:11.863190: step: 306/469, loss: 0.41721203923225403
2023-01-24 02:39:12.470884: step: 308/469, loss: 0.04842031002044678
2023-01-24 02:39:13.152621: step: 310/469, loss: 0.02417251467704773
2023-01-24 02:39:13.789324: step: 312/469, loss: 0.01337968185544014
2023-01-24 02:39:14.403016: step: 314/469, loss: 1.1121264696121216
2023-01-24 02:39:15.071939: step: 316/469, loss: 0.08640328049659729
2023-01-24 02:39:15.705077: step: 318/469, loss: 0.19282464683055878
2023-01-24 02:39:16.365480: step: 320/469, loss: 0.028221305459737778
2023-01-24 02:39:17.050899: step: 322/469, loss: 0.14507897198200226
2023-01-24 02:39:17.649749: step: 324/469, loss: 1.0240217447280884
2023-01-24 02:39:18.297741: step: 326/469, loss: 0.09105583280324936
2023-01-24 02:39:18.923046: step: 328/469, loss: 0.13023589551448822
2023-01-24 02:39:19.571685: step: 330/469, loss: 0.07880572974681854
2023-01-24 02:39:20.151305: step: 332/469, loss: 0.16874323785305023
2023-01-24 02:39:20.871639: step: 334/469, loss: 0.05689356103539467
2023-01-24 02:39:21.530807: step: 336/469, loss: 0.07699718326330185
2023-01-24 02:39:22.117773: step: 338/469, loss: 0.07749658077955246
2023-01-24 02:39:22.699027: step: 340/469, loss: 0.12395375221967697
2023-01-24 02:39:23.365305: step: 342/469, loss: 0.08001910150051117
2023-01-24 02:39:23.978981: step: 344/469, loss: 0.20075903832912445
2023-01-24 02:39:24.584987: step: 346/469, loss: 0.10846106708049774
2023-01-24 02:39:25.228504: step: 348/469, loss: 0.04375477507710457
2023-01-24 02:39:25.877397: step: 350/469, loss: 0.09713562577962875
2023-01-24 02:39:26.426873: step: 352/469, loss: 0.030647573992609978
2023-01-24 02:39:27.064154: step: 354/469, loss: 0.07991889864206314
2023-01-24 02:39:27.631127: step: 356/469, loss: 0.11926233768463135
2023-01-24 02:39:28.241255: step: 358/469, loss: 0.15816357731819153
2023-01-24 02:39:28.945339: step: 360/469, loss: 0.0826299861073494
2023-01-24 02:39:29.525856: step: 362/469, loss: 0.18181084096431732
2023-01-24 02:39:30.108919: step: 364/469, loss: 0.06405311077833176
2023-01-24 02:39:30.700973: step: 366/469, loss: 0.939147412776947
2023-01-24 02:39:31.296917: step: 368/469, loss: 0.09762299060821533
2023-01-24 02:39:31.864522: step: 370/469, loss: 0.04762081056833267
2023-01-24 02:39:32.487575: step: 372/469, loss: 0.06453923135995865
2023-01-24 02:39:33.098928: step: 374/469, loss: 0.03962532430887222
2023-01-24 02:39:33.737303: step: 376/469, loss: 0.14591509103775024
2023-01-24 02:39:34.401420: step: 378/469, loss: 0.2262595146894455
2023-01-24 02:39:35.021042: step: 380/469, loss: 0.3208789825439453
2023-01-24 02:39:35.732973: step: 382/469, loss: 0.059827160090208054
2023-01-24 02:39:36.317585: step: 384/469, loss: 0.031631890684366226
2023-01-24 02:39:36.916860: step: 386/469, loss: 0.46747565269470215
2023-01-24 02:39:37.608464: step: 388/469, loss: 0.08008897304534912
2023-01-24 02:39:38.267149: step: 390/469, loss: 0.2304515391588211
2023-01-24 02:39:38.904130: step: 392/469, loss: 0.08552771061658859
2023-01-24 02:39:39.571316: step: 394/469, loss: 0.03198418766260147
2023-01-24 02:39:40.201782: step: 396/469, loss: 0.08952928334474564
2023-01-24 02:39:40.853301: step: 398/469, loss: 0.04365219548344612
2023-01-24 02:39:41.520051: step: 400/469, loss: 2.0542235374450684
2023-01-24 02:39:42.178439: step: 402/469, loss: 0.2224007099866867
2023-01-24 02:39:42.788160: step: 404/469, loss: 0.04883831366896629
2023-01-24 02:39:43.519635: step: 406/469, loss: 0.23871919512748718
2023-01-24 02:39:44.184098: step: 408/469, loss: 0.09538616240024567
2023-01-24 02:39:44.763000: step: 410/469, loss: 0.13070595264434814
2023-01-24 02:39:45.392955: step: 412/469, loss: 0.06503377854824066
2023-01-24 02:39:46.069635: step: 414/469, loss: 0.2566741704940796
2023-01-24 02:39:46.650487: step: 416/469, loss: 0.46768027544021606
2023-01-24 02:39:47.250303: step: 418/469, loss: 0.9209142923355103
2023-01-24 02:39:47.823914: step: 420/469, loss: 0.09707845747470856
2023-01-24 02:39:48.479645: step: 422/469, loss: 0.3248916268348694
2023-01-24 02:39:49.121239: step: 424/469, loss: 0.04956451803445816
2023-01-24 02:39:49.777436: step: 426/469, loss: 0.03982264921069145
2023-01-24 02:39:50.478488: step: 428/469, loss: 0.27753764390945435
2023-01-24 02:39:51.121637: step: 430/469, loss: 0.012592037208378315
2023-01-24 02:39:51.733844: step: 432/469, loss: 1.000629186630249
2023-01-24 02:39:52.428247: step: 434/469, loss: 0.07920895516872406
2023-01-24 02:39:53.064577: step: 436/469, loss: 0.21137556433677673
2023-01-24 02:39:53.660427: step: 438/469, loss: 0.03702995553612709
2023-01-24 02:39:54.295105: step: 440/469, loss: 0.06917298585176468
2023-01-24 02:39:54.908147: step: 442/469, loss: 0.03820595145225525
2023-01-24 02:39:55.604815: step: 444/469, loss: 0.04671890661120415
2023-01-24 02:39:56.244059: step: 446/469, loss: 0.37693044543266296
2023-01-24 02:39:56.803797: step: 448/469, loss: 0.029523273929953575
2023-01-24 02:39:57.385136: step: 450/469, loss: 0.1540946364402771
2023-01-24 02:39:57.995658: step: 452/469, loss: 0.10862761735916138
2023-01-24 02:39:58.613773: step: 454/469, loss: 0.3979809880256653
2023-01-24 02:39:59.195203: step: 456/469, loss: 0.5188076496124268
2023-01-24 02:39:59.808558: step: 458/469, loss: 0.25342944264411926
2023-01-24 02:40:00.446083: step: 460/469, loss: 0.18251484632492065
2023-01-24 02:40:01.137414: step: 462/469, loss: 0.04423234239220619
2023-01-24 02:40:01.720084: step: 464/469, loss: 0.12601114809513092
2023-01-24 02:40:02.332992: step: 466/469, loss: 0.0514974519610405
2023-01-24 02:40:03.010377: step: 468/469, loss: 0.24102641642093658
2023-01-24 02:40:03.636092: step: 470/469, loss: 0.35460788011550903
2023-01-24 02:40:04.317373: step: 472/469, loss: 0.7224856019020081
2023-01-24 02:40:04.883913: step: 474/469, loss: 0.18925578892230988
2023-01-24 02:40:05.558736: step: 476/469, loss: 0.03882612660527229
2023-01-24 02:40:06.161612: step: 478/469, loss: 0.05779165029525757
2023-01-24 02:40:06.801546: step: 480/469, loss: 0.169854998588562
2023-01-24 02:40:07.402214: step: 482/469, loss: 0.45715466141700745
2023-01-24 02:40:08.160517: step: 484/469, loss: 0.44506722688674927
2023-01-24 02:40:08.910165: step: 486/469, loss: 0.12539318203926086
2023-01-24 02:40:09.544371: step: 488/469, loss: 0.32278648018836975
2023-01-24 02:40:10.161918: step: 490/469, loss: 0.12357121706008911
2023-01-24 02:40:10.738759: step: 492/469, loss: 0.061674635857343674
2023-01-24 02:40:11.337061: step: 494/469, loss: 0.10104820877313614
2023-01-24 02:40:12.003239: step: 496/469, loss: 0.15971069037914276
2023-01-24 02:40:12.547529: step: 498/469, loss: 0.18366794288158417
2023-01-24 02:40:13.167506: step: 500/469, loss: 0.09132558852434158
2023-01-24 02:40:13.813916: step: 502/469, loss: 0.08771282434463501
2023-01-24 02:40:14.466882: step: 504/469, loss: 0.06579511612653732
2023-01-24 02:40:15.116171: step: 506/469, loss: 0.13895754516124725
2023-01-24 02:40:15.710161: step: 508/469, loss: 0.09910660237073898
2023-01-24 02:40:16.395135: step: 510/469, loss: 0.1334264576435089
2023-01-24 02:40:16.994415: step: 512/469, loss: 0.1699783354997635
2023-01-24 02:40:17.664159: step: 514/469, loss: 0.1673431396484375
2023-01-24 02:40:18.350698: step: 516/469, loss: 0.12258341163396835
2023-01-24 02:40:19.035233: step: 518/469, loss: 0.09879224002361298
2023-01-24 02:40:19.680614: step: 520/469, loss: 0.061435267329216
2023-01-24 02:40:20.242557: step: 522/469, loss: 0.19045239686965942
2023-01-24 02:40:20.902467: step: 524/469, loss: 0.0746120736002922
2023-01-24 02:40:21.572452: step: 526/469, loss: 0.030568497255444527
2023-01-24 02:40:22.169461: step: 528/469, loss: 0.08450386673212051
2023-01-24 02:40:22.906145: step: 530/469, loss: 0.13238397240638733
2023-01-24 02:40:23.653786: step: 532/469, loss: 0.21052587032318115
2023-01-24 02:40:24.261138: step: 534/469, loss: 0.11684330552816391
2023-01-24 02:40:24.916372: step: 536/469, loss: 0.17130185663700104
2023-01-24 02:40:25.557970: step: 538/469, loss: 0.3248347043991089
2023-01-24 02:40:26.165914: step: 540/469, loss: 0.09218096733093262
2023-01-24 02:40:26.830331: step: 542/469, loss: 0.07498276978731155
2023-01-24 02:40:27.364327: step: 544/469, loss: 0.05229423567652702
2023-01-24 02:40:27.986395: step: 546/469, loss: 0.09544291347265244
2023-01-24 02:40:28.542235: step: 548/469, loss: 0.09195572882890701
2023-01-24 02:40:29.191953: step: 550/469, loss: 0.16590982675552368
2023-01-24 02:40:29.854084: step: 552/469, loss: 0.06954732537269592
2023-01-24 02:40:30.449826: step: 554/469, loss: 0.11550594866275787
2023-01-24 02:40:31.070399: step: 556/469, loss: 0.06166649982333183
2023-01-24 02:40:31.695371: step: 558/469, loss: 0.11040358245372772
2023-01-24 02:40:32.350141: step: 560/469, loss: 0.18325157463550568
2023-01-24 02:40:32.997074: step: 562/469, loss: 0.07799236476421356
2023-01-24 02:40:33.616982: step: 564/469, loss: 0.17693808674812317
2023-01-24 02:40:34.184378: step: 566/469, loss: 0.08517203480005264
2023-01-24 02:40:34.815179: step: 568/469, loss: 0.37244269251823425
2023-01-24 02:40:35.424299: step: 570/469, loss: 0.16834932565689087
2023-01-24 02:40:36.064254: step: 572/469, loss: 0.14932765066623688
2023-01-24 02:40:36.667664: step: 574/469, loss: 0.015989581122994423
2023-01-24 02:40:37.324095: step: 576/469, loss: 0.12025109678506851
2023-01-24 02:40:37.980499: step: 578/469, loss: 0.07602535933256149
2023-01-24 02:40:38.661055: step: 580/469, loss: 0.2487332969903946
2023-01-24 02:40:39.302484: step: 582/469, loss: 0.2300061285495758
2023-01-24 02:40:39.925369: step: 584/469, loss: 0.05116070806980133
2023-01-24 02:40:40.586889: step: 586/469, loss: 1.4883637428283691
2023-01-24 02:40:41.277339: step: 588/469, loss: 0.030584409832954407
2023-01-24 02:40:41.898344: step: 590/469, loss: 0.07932163029909134
2023-01-24 02:40:42.509164: step: 592/469, loss: 0.08053095638751984
2023-01-24 02:40:43.088014: step: 594/469, loss: 0.0786694809794426
2023-01-24 02:40:43.740744: step: 596/469, loss: 0.21005229651927948
2023-01-24 02:40:44.375249: step: 598/469, loss: 0.12650232017040253
2023-01-24 02:40:45.028155: step: 600/469, loss: 0.07539433240890503
2023-01-24 02:40:45.691032: step: 602/469, loss: 0.3110903799533844
2023-01-24 02:40:46.294478: step: 604/469, loss: 0.06634613126516342
2023-01-24 02:40:46.912216: step: 606/469, loss: 0.09259108453989029
2023-01-24 02:40:47.535352: step: 608/469, loss: 0.1963626742362976
2023-01-24 02:40:48.135129: step: 610/469, loss: 0.07385430485010147
2023-01-24 02:40:48.753489: step: 612/469, loss: 0.41075727343559265
2023-01-24 02:40:49.406965: step: 614/469, loss: 0.07688222825527191
2023-01-24 02:40:49.980188: step: 616/469, loss: 0.06205300614237785
2023-01-24 02:40:50.605327: step: 618/469, loss: 0.3063707649707794
2023-01-24 02:40:51.207003: step: 620/469, loss: 0.1841689795255661
2023-01-24 02:40:51.867189: step: 622/469, loss: 1.570283055305481
2023-01-24 02:40:52.431513: step: 624/469, loss: 0.05395738407969475
2023-01-24 02:40:53.026234: step: 626/469, loss: 0.11619783937931061
2023-01-24 02:40:53.624685: step: 628/469, loss: 0.04714583978056908
2023-01-24 02:40:54.218518: step: 630/469, loss: 0.04560321196913719
2023-01-24 02:40:54.863117: step: 632/469, loss: 1.0108449459075928
2023-01-24 02:40:55.412035: step: 634/469, loss: 3.4579665660858154
2023-01-24 02:40:56.020421: step: 636/469, loss: 0.09656395763158798
2023-01-24 02:40:56.641203: step: 638/469, loss: 0.11232117563486099
2023-01-24 02:40:57.266877: step: 640/469, loss: 0.4612281322479248
2023-01-24 02:40:57.875258: step: 642/469, loss: 0.09604386240243912
2023-01-24 02:40:58.523031: step: 644/469, loss: 0.1310945302248001
2023-01-24 02:40:59.129240: step: 646/469, loss: 0.057665999978780746
2023-01-24 02:40:59.759002: step: 648/469, loss: 0.02677675150334835
2023-01-24 02:41:00.482521: step: 650/469, loss: 0.116474449634552
2023-01-24 02:41:01.049403: step: 652/469, loss: 0.15412276983261108
2023-01-24 02:41:01.689674: step: 654/469, loss: 0.10318965464830399
2023-01-24 02:41:02.330510: step: 656/469, loss: 0.7221606969833374
2023-01-24 02:41:02.921197: step: 658/469, loss: 0.10014528036117554
2023-01-24 02:41:03.567808: step: 660/469, loss: 0.23871949315071106
2023-01-24 02:41:04.170200: step: 662/469, loss: 0.06811057776212692
2023-01-24 02:41:04.780883: step: 664/469, loss: 0.12492357939481735
2023-01-24 02:41:05.385652: step: 666/469, loss: 0.060884740203619
2023-01-24 02:41:06.010275: step: 668/469, loss: 0.07236185669898987
2023-01-24 02:41:06.742333: step: 670/469, loss: 0.16880032420158386
2023-01-24 02:41:07.327646: step: 672/469, loss: 0.09256527572870255
2023-01-24 02:41:07.981409: step: 674/469, loss: 0.10509645938873291
2023-01-24 02:41:08.615784: step: 676/469, loss: 0.12360022962093353
2023-01-24 02:41:09.247752: step: 678/469, loss: 0.08761170506477356
2023-01-24 02:41:09.917489: step: 680/469, loss: 0.07590088993310928
2023-01-24 02:41:10.632104: step: 682/469, loss: 0.3243628740310669
2023-01-24 02:41:11.226511: step: 684/469, loss: 0.07249685376882553
2023-01-24 02:41:11.834211: step: 686/469, loss: 0.027272187173366547
2023-01-24 02:41:12.490288: step: 688/469, loss: 11.247618675231934
2023-01-24 02:41:13.174246: step: 690/469, loss: 0.5154850482940674
2023-01-24 02:41:13.843906: step: 692/469, loss: 0.06237754598259926
2023-01-24 02:41:14.440006: step: 694/469, loss: 0.07400119304656982
2023-01-24 02:41:15.016627: step: 696/469, loss: 0.13597814738750458
2023-01-24 02:41:15.618528: step: 698/469, loss: 0.08082101494073868
2023-01-24 02:41:16.198366: step: 700/469, loss: 0.5380794405937195
2023-01-24 02:41:16.803633: step: 702/469, loss: 0.04616934806108475
2023-01-24 02:41:17.589063: step: 704/469, loss: 0.03679390624165535
2023-01-24 02:41:18.198530: step: 706/469, loss: 8.062114715576172
2023-01-24 02:41:18.781546: step: 708/469, loss: 0.09626629203557968
2023-01-24 02:41:19.375435: step: 710/469, loss: 0.06008496880531311
2023-01-24 02:41:19.950092: step: 712/469, loss: 0.08474749326705933
2023-01-24 02:41:20.585979: step: 714/469, loss: 0.17426146566867828
2023-01-24 02:41:21.234029: step: 716/469, loss: 0.09438607841730118
2023-01-24 02:41:21.861110: step: 718/469, loss: 0.12769052386283875
2023-01-24 02:41:22.498212: step: 720/469, loss: 0.424898624420166
2023-01-24 02:41:23.126200: step: 722/469, loss: 0.08442848175764084
2023-01-24 02:41:23.717671: step: 724/469, loss: 0.24904683232307434
2023-01-24 02:41:24.309934: step: 726/469, loss: 0.19199064373970032
2023-01-24 02:41:25.017006: step: 728/469, loss: 0.18863005936145782
2023-01-24 02:41:25.642014: step: 730/469, loss: 0.056691914796829224
2023-01-24 02:41:26.231964: step: 732/469, loss: 0.06619631499052048
2023-01-24 02:41:26.853665: step: 734/469, loss: 0.12168781459331512
2023-01-24 02:41:27.423846: step: 736/469, loss: 0.1374291628599167
2023-01-24 02:41:28.114442: step: 738/469, loss: 0.31519442796707153
2023-01-24 02:41:28.718823: step: 740/469, loss: 0.053980860859155655
2023-01-24 02:41:29.331388: step: 742/469, loss: 0.144709050655365
2023-01-24 02:41:29.952234: step: 744/469, loss: 0.1715642511844635
2023-01-24 02:41:30.606255: step: 746/469, loss: 0.09068422764539719
2023-01-24 02:41:31.259141: step: 748/469, loss: 0.14486458897590637
2023-01-24 02:41:31.868638: step: 750/469, loss: 0.12170708924531937
2023-01-24 02:41:32.469399: step: 752/469, loss: 0.1538146436214447
2023-01-24 02:41:33.185264: step: 754/469, loss: 0.3749336898326874
2023-01-24 02:41:33.832551: step: 756/469, loss: 0.7911332249641418
2023-01-24 02:41:34.444920: step: 758/469, loss: 0.1352866291999817
2023-01-24 02:41:35.081875: step: 760/469, loss: 0.3471243977546692
2023-01-24 02:41:35.703600: step: 762/469, loss: 0.7950724363327026
2023-01-24 02:41:36.313845: step: 764/469, loss: 0.13323654234409332
2023-01-24 02:41:37.022750: step: 766/469, loss: 0.34459856152534485
2023-01-24 02:41:37.666059: step: 768/469, loss: 0.34449002146720886
2023-01-24 02:41:38.275630: step: 770/469, loss: 0.048628631979227066
2023-01-24 02:41:38.824736: step: 772/469, loss: 0.2818205654621124
2023-01-24 02:41:39.452604: step: 774/469, loss: 0.1073806881904602
2023-01-24 02:41:40.122938: step: 776/469, loss: 0.2336321771144867
2023-01-24 02:41:40.753116: step: 778/469, loss: 0.0834648609161377
2023-01-24 02:41:41.400511: step: 780/469, loss: 0.19987352192401886
2023-01-24 02:41:42.051603: step: 782/469, loss: 0.1378486305475235
2023-01-24 02:41:42.721016: step: 784/469, loss: 0.09632925689220428
2023-01-24 02:41:43.370522: step: 786/469, loss: 0.08961453288793564
2023-01-24 02:41:44.029654: step: 788/469, loss: 0.11353462934494019
2023-01-24 02:41:44.640774: step: 790/469, loss: 0.353186696767807
2023-01-24 02:41:45.252448: step: 792/469, loss: 0.35332679748535156
2023-01-24 02:41:45.921673: step: 794/469, loss: 0.4996044933795929
2023-01-24 02:41:46.519800: step: 796/469, loss: 0.11995209008455276
2023-01-24 02:41:47.112914: step: 798/469, loss: 0.11936438828706741
2023-01-24 02:41:47.711980: step: 800/469, loss: 0.1804143637418747
2023-01-24 02:41:48.334898: step: 802/469, loss: 0.10060111433267593
2023-01-24 02:41:48.900111: step: 804/469, loss: 0.18791353702545166
2023-01-24 02:41:49.522666: step: 806/469, loss: 0.04781004786491394
2023-01-24 02:41:50.051210: step: 808/469, loss: 0.1525021195411682
2023-01-24 02:41:50.729341: step: 810/469, loss: 0.044144872575998306
2023-01-24 02:41:51.335583: step: 812/469, loss: 0.08868099004030228
2023-01-24 02:41:51.927656: step: 814/469, loss: 0.08810263872146606
2023-01-24 02:41:52.598682: step: 816/469, loss: 0.15583884716033936
2023-01-24 02:41:53.289415: step: 818/469, loss: 0.22324155271053314
2023-01-24 02:41:53.896962: step: 820/469, loss: 0.5118790864944458
2023-01-24 02:41:54.522891: step: 822/469, loss: 0.13022835552692413
2023-01-24 02:41:55.206479: step: 824/469, loss: 0.5483819246292114
2023-01-24 02:41:55.824269: step: 826/469, loss: 0.12466764450073242
2023-01-24 02:41:56.419381: step: 828/469, loss: 0.25863000750541687
2023-01-24 02:41:57.038155: step: 830/469, loss: 0.21080994606018066
2023-01-24 02:41:57.798708: step: 832/469, loss: 0.2235356718301773
2023-01-24 02:41:58.473246: step: 834/469, loss: 0.11213290691375732
2023-01-24 02:41:59.093332: step: 836/469, loss: 0.08789695799350739
2023-01-24 02:41:59.830308: step: 838/469, loss: 0.2734290659427643
2023-01-24 02:42:00.522538: step: 840/469, loss: 0.04577796533703804
2023-01-24 02:42:01.119684: step: 842/469, loss: 0.036078400909900665
2023-01-24 02:42:01.706314: step: 844/469, loss: 0.14965537190437317
2023-01-24 02:42:02.298696: step: 846/469, loss: 0.06764727830886841
2023-01-24 02:42:02.837694: step: 848/469, loss: 0.9656215906143188
2023-01-24 02:42:03.410278: step: 850/469, loss: 0.09858908504247665
2023-01-24 02:42:04.107348: step: 852/469, loss: 0.6077346801757812
2023-01-24 02:42:04.805474: step: 854/469, loss: 0.3041757047176361
2023-01-24 02:42:05.414015: step: 856/469, loss: 0.08208796381950378
2023-01-24 02:42:06.035911: step: 858/469, loss: 0.26135125756263733
2023-01-24 02:42:06.640412: step: 860/469, loss: 0.03435799852013588
2023-01-24 02:42:07.261546: step: 862/469, loss: 0.29631078243255615
2023-01-24 02:42:07.914210: step: 864/469, loss: 0.05846825987100601
2023-01-24 02:42:08.528320: step: 866/469, loss: 0.03833848983049393
2023-01-24 02:42:09.227808: step: 868/469, loss: 0.02671683393418789
2023-01-24 02:42:09.908038: step: 870/469, loss: 0.0951947271823883
2023-01-24 02:42:10.561518: step: 872/469, loss: 0.04014415666460991
2023-01-24 02:42:11.166171: step: 874/469, loss: 1.1296528577804565
2023-01-24 02:42:11.779123: step: 876/469, loss: 0.02556871622800827
2023-01-24 02:42:12.317784: step: 878/469, loss: 0.1425725668668747
2023-01-24 02:42:12.925486: step: 880/469, loss: 0.061103127896785736
2023-01-24 02:42:13.650308: step: 882/469, loss: 0.11434217542409897
2023-01-24 02:42:14.255697: step: 884/469, loss: 0.12422147393226624
2023-01-24 02:42:14.889688: step: 886/469, loss: 0.36362916231155396
2023-01-24 02:42:15.533456: step: 888/469, loss: 0.1230747327208519
2023-01-24 02:42:16.219144: step: 890/469, loss: 0.22097797691822052
2023-01-24 02:42:16.877103: step: 892/469, loss: 0.12863381206989288
2023-01-24 02:42:17.518766: step: 894/469, loss: 0.6501291394233704
2023-01-24 02:42:18.122029: step: 896/469, loss: 0.07268564403057098
2023-01-24 02:42:18.762185: step: 898/469, loss: 0.2855556011199951
2023-01-24 02:42:19.374025: step: 900/469, loss: 0.09046179056167603
2023-01-24 02:42:20.034192: step: 902/469, loss: 0.040060173720121384
2023-01-24 02:42:20.645568: step: 904/469, loss: 0.12873654067516327
2023-01-24 02:42:21.265773: step: 906/469, loss: 0.19196546077728271
2023-01-24 02:42:21.972818: step: 908/469, loss: 0.36106956005096436
2023-01-24 02:42:22.606468: step: 910/469, loss: 0.13236966729164124
2023-01-24 02:42:23.255632: step: 912/469, loss: 0.08896508067846298
2023-01-24 02:42:23.850769: step: 914/469, loss: 0.06155938282608986
2023-01-24 02:42:24.455116: step: 916/469, loss: 0.17571577429771423
2023-01-24 02:42:25.094562: step: 918/469, loss: 0.1279701441526413
2023-01-24 02:42:25.713400: step: 920/469, loss: 0.09901431202888489
2023-01-24 02:42:26.297719: step: 922/469, loss: 0.10144391655921936
2023-01-24 02:42:26.883715: step: 924/469, loss: 0.08618828654289246
2023-01-24 02:42:27.561898: step: 926/469, loss: 0.08711037039756775
2023-01-24 02:42:28.145871: step: 928/469, loss: 0.07481534034013748
2023-01-24 02:42:28.774141: step: 930/469, loss: 0.26995033025741577
2023-01-24 02:42:29.421356: step: 932/469, loss: 0.0866168811917305
2023-01-24 02:42:29.993072: step: 934/469, loss: 0.11633653193712234
2023-01-24 02:42:30.618683: step: 936/469, loss: 0.7510954141616821
2023-01-24 02:42:31.234454: step: 938/469, loss: 0.8718492984771729
==================================================
Loss: 0.237
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32795620196130393, 'r': 0.3049308139678158, 'f1': 0.31602465872377367}, 'combined': 0.23286027484909638, 'epoch': 14}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.34533091078907807, 'r': 0.2379086695555131, 'f1': 0.2817271677401688}, 'combined': 0.15366936422191024, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33608097389153285, 'r': 0.3080210823332265, 'f1': 0.3214398225536839}, 'combined': 0.23685039556587234, 'epoch': 14}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3446926284434606, 'r': 0.23683821039436315, 'f1': 0.28076373531566046}, 'combined': 0.15314385562672386, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32292405575259786, 'r': 0.29841369098959236, 'f1': 0.31018543422389583}, 'combined': 0.22855768837550217, 'epoch': 14}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33628741765295045, 'r': 0.23945877363039159, 'f1': 0.2797308044331537}, 'combined': 0.15258043878172017, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29557291666666663, 'r': 0.2702380952380952, 'f1': 0.2823383084577114}, 'combined': 0.1882255389718076, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2638888888888889, 'r': 0.20652173913043478, 'f1': 0.23170731707317074}, 'combined': 0.11585365853658537, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4444444444444444, 'r': 0.13793103448275862, 'f1': 0.21052631578947367}, 'combined': 0.14035087719298245, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 02:45:16.645411: step: 2/469, loss: 0.11154310405254364
2023-01-24 02:45:17.302115: step: 4/469, loss: 0.10185451060533524
2023-01-24 02:45:17.901748: step: 6/469, loss: 0.09049303829669952
2023-01-24 02:45:18.612258: step: 8/469, loss: 0.08959893882274628
2023-01-24 02:45:19.340869: step: 10/469, loss: 0.07926318049430847
2023-01-24 02:45:19.933440: step: 12/469, loss: 0.13308602571487427
2023-01-24 02:45:20.600774: step: 14/469, loss: 0.08020301908254623
2023-01-24 02:45:21.341586: step: 16/469, loss: 0.05582220107316971
2023-01-24 02:45:22.014537: step: 18/469, loss: 0.08290795236825943
2023-01-24 02:45:22.665531: step: 20/469, loss: 0.3549378514289856
2023-01-24 02:45:23.404122: step: 22/469, loss: 0.8654332160949707
2023-01-24 02:45:24.092201: step: 24/469, loss: 0.06048708036541939
2023-01-24 02:45:24.727132: step: 26/469, loss: 0.08002801984548569
2023-01-24 02:45:25.378326: step: 28/469, loss: 0.07778247445821762
2023-01-24 02:45:25.982441: step: 30/469, loss: 0.6301714777946472
2023-01-24 02:45:26.584329: step: 32/469, loss: 0.11404713243246078
2023-01-24 02:45:27.232987: step: 34/469, loss: 3.1983845233917236
2023-01-24 02:45:27.887470: step: 36/469, loss: 0.1961783915758133
2023-01-24 02:45:28.488641: step: 38/469, loss: 0.06832145899534225
2023-01-24 02:45:29.078635: step: 40/469, loss: 0.17111967504024506
2023-01-24 02:45:29.702473: step: 42/469, loss: 0.06059175729751587
2023-01-24 02:45:30.272267: step: 44/469, loss: 0.08661918342113495
2023-01-24 02:45:30.894488: step: 46/469, loss: 0.16389034688472748
2023-01-24 02:45:31.486218: step: 48/469, loss: 0.05933493375778198
2023-01-24 02:45:32.141194: step: 50/469, loss: 0.25778016448020935
2023-01-24 02:45:32.797198: step: 52/469, loss: 0.07134124636650085
2023-01-24 02:45:33.511929: step: 54/469, loss: 0.07459121942520142
2023-01-24 02:45:34.135121: step: 56/469, loss: 0.05604968219995499
2023-01-24 02:45:34.794690: step: 58/469, loss: 0.07312927395105362
2023-01-24 02:45:35.357188: step: 60/469, loss: 0.08122636377811432
2023-01-24 02:45:35.967819: step: 62/469, loss: 0.10961474478244781
2023-01-24 02:45:36.590811: step: 64/469, loss: 0.06546129286289215
2023-01-24 02:45:37.178325: step: 66/469, loss: 0.1335621178150177
2023-01-24 02:45:37.818452: step: 68/469, loss: 0.09232518821954727
2023-01-24 02:45:38.422627: step: 70/469, loss: 0.03416675329208374
2023-01-24 02:45:39.034743: step: 72/469, loss: 0.4200380742549896
2023-01-24 02:45:39.645271: step: 74/469, loss: 0.012624003924429417
2023-01-24 02:45:40.258706: step: 76/469, loss: 0.13828982412815094
2023-01-24 02:45:40.872805: step: 78/469, loss: 0.14082835614681244
2023-01-24 02:45:41.554228: step: 80/469, loss: 1.0979188680648804
2023-01-24 02:45:42.184353: step: 82/469, loss: 0.08209765702486038
2023-01-24 02:45:42.847666: step: 84/469, loss: 0.0791550725698471
2023-01-24 02:45:43.521892: step: 86/469, loss: 0.333895206451416
2023-01-24 02:45:44.122065: step: 88/469, loss: 0.1241508275270462
2023-01-24 02:45:44.756234: step: 90/469, loss: 0.07102589309215546
2023-01-24 02:45:45.384174: step: 92/469, loss: 0.043671127408742905
2023-01-24 02:45:46.010506: step: 94/469, loss: 0.178281769156456
2023-01-24 02:45:46.556655: step: 96/469, loss: 0.02716628648340702
2023-01-24 02:45:47.237187: step: 98/469, loss: 0.2626620829105377
2023-01-24 02:45:47.792629: step: 100/469, loss: 0.5035622119903564
2023-01-24 02:45:48.551064: step: 102/469, loss: 0.057853054255247116
2023-01-24 02:45:49.163105: step: 104/469, loss: 0.06141258776187897
2023-01-24 02:45:49.817462: step: 106/469, loss: 0.0898313969373703
2023-01-24 02:45:50.457329: step: 108/469, loss: 0.06163856014609337
2023-01-24 02:45:51.102192: step: 110/469, loss: 0.14861513674259186
2023-01-24 02:45:51.765663: step: 112/469, loss: 0.04367325082421303
2023-01-24 02:45:52.410137: step: 114/469, loss: 0.12304690480232239
2023-01-24 02:45:53.082273: step: 116/469, loss: 0.09863568842411041
2023-01-24 02:45:53.707174: step: 118/469, loss: 0.2262677103281021
2023-01-24 02:45:54.342614: step: 120/469, loss: 0.14186064898967743
2023-01-24 02:45:54.888981: step: 122/469, loss: 0.11820931732654572
2023-01-24 02:45:55.555049: step: 124/469, loss: 0.23409591615200043
2023-01-24 02:45:56.164330: step: 126/469, loss: 0.04979797080159187
2023-01-24 02:45:56.788017: step: 128/469, loss: 0.1126193255186081
2023-01-24 02:45:57.498885: step: 130/469, loss: 0.175623819231987
2023-01-24 02:45:58.074141: step: 132/469, loss: 0.0966227650642395
2023-01-24 02:45:58.659532: step: 134/469, loss: 0.15038621425628662
2023-01-24 02:45:59.312895: step: 136/469, loss: 0.042864251881837845
2023-01-24 02:45:59.889407: step: 138/469, loss: 0.1660320907831192
2023-01-24 02:46:00.538145: step: 140/469, loss: 0.10542742162942886
2023-01-24 02:46:01.111526: step: 142/469, loss: 0.03676040098071098
2023-01-24 02:46:01.690860: step: 144/469, loss: 0.07163447886705399
2023-01-24 02:46:02.261627: step: 146/469, loss: 0.0900966227054596
2023-01-24 02:46:02.862101: step: 148/469, loss: 0.059078194200992584
2023-01-24 02:46:03.455447: step: 150/469, loss: 0.06749924272298813
2023-01-24 02:46:04.059875: step: 152/469, loss: 0.07475146651268005
2023-01-24 02:46:04.773451: step: 154/469, loss: 0.3347472548484802
2023-01-24 02:46:05.417222: step: 156/469, loss: 0.1510920375585556
2023-01-24 02:46:05.997352: step: 158/469, loss: 0.06703579425811768
2023-01-24 02:46:06.613967: step: 160/469, loss: 0.0176719781011343
2023-01-24 02:46:07.240926: step: 162/469, loss: 0.13784371316432953
2023-01-24 02:46:07.907347: step: 164/469, loss: 0.03905270993709564
2023-01-24 02:46:08.554369: step: 166/469, loss: 0.14107176661491394
2023-01-24 02:46:09.180529: step: 168/469, loss: 0.13379943370819092
2023-01-24 02:46:09.822299: step: 170/469, loss: 0.04197041317820549
2023-01-24 02:46:10.418313: step: 172/469, loss: 0.10158641636371613
2023-01-24 02:46:11.067286: step: 174/469, loss: 0.12034301459789276
2023-01-24 02:46:11.650574: step: 176/469, loss: 0.07145047187805176
2023-01-24 02:46:12.370153: step: 178/469, loss: 0.10873144865036011
2023-01-24 02:46:13.062388: step: 180/469, loss: 0.05998546630144119
2023-01-24 02:46:13.721934: step: 182/469, loss: 0.09499622881412506
2023-01-24 02:46:14.336148: step: 184/469, loss: 0.0694514662027359
2023-01-24 02:46:14.905074: step: 186/469, loss: 0.09403524547815323
2023-01-24 02:46:15.584250: step: 188/469, loss: 0.19487684965133667
2023-01-24 02:46:16.239048: step: 190/469, loss: 0.2548619210720062
2023-01-24 02:46:16.845895: step: 192/469, loss: 0.1119566336274147
2023-01-24 02:46:17.507626: step: 194/469, loss: 0.2044508457183838
2023-01-24 02:46:18.140561: step: 196/469, loss: 0.4984990656375885
2023-01-24 02:46:18.810063: step: 198/469, loss: 0.2978976368904114
2023-01-24 02:46:19.456265: step: 200/469, loss: 0.06300626695156097
2023-01-24 02:46:20.042533: step: 202/469, loss: 0.09145215153694153
2023-01-24 02:46:20.663346: step: 204/469, loss: 0.06325855106115341
2023-01-24 02:46:21.258503: step: 206/469, loss: 0.15226240456104279
2023-01-24 02:46:21.897896: step: 208/469, loss: 0.15415604412555695
2023-01-24 02:46:22.553893: step: 210/469, loss: 0.042729929089546204
2023-01-24 02:46:23.176277: step: 212/469, loss: 0.15243494510650635
2023-01-24 02:46:23.821256: step: 214/469, loss: 0.1374005228281021
2023-01-24 02:46:24.382330: step: 216/469, loss: 0.0484742633998394
2023-01-24 02:46:25.039454: step: 218/469, loss: 0.1367819905281067
2023-01-24 02:46:25.696922: step: 220/469, loss: 0.060447901487350464
2023-01-24 02:46:26.290672: step: 222/469, loss: 0.0830463171005249
2023-01-24 02:46:26.922524: step: 224/469, loss: 0.1643836349248886
2023-01-24 02:46:27.562873: step: 226/469, loss: 0.04430633410811424
2023-01-24 02:46:28.195709: step: 228/469, loss: 0.05016676336526871
2023-01-24 02:46:28.943919: step: 230/469, loss: 0.10828897356987
2023-01-24 02:46:29.542862: step: 232/469, loss: 0.150638148188591
2023-01-24 02:46:30.178270: step: 234/469, loss: 0.03905714303255081
2023-01-24 02:46:30.800299: step: 236/469, loss: 0.09422975033521652
2023-01-24 02:46:31.400471: step: 238/469, loss: 0.4546284079551697
2023-01-24 02:46:32.002819: step: 240/469, loss: 0.08964105695486069
2023-01-24 02:46:32.562796: step: 242/469, loss: 0.0595172718167305
2023-01-24 02:46:33.138982: step: 244/469, loss: 0.12783460319042206
2023-01-24 02:46:33.832883: step: 246/469, loss: 0.07300969213247299
2023-01-24 02:46:34.505004: step: 248/469, loss: 0.07457521557807922
2023-01-24 02:46:35.166905: step: 250/469, loss: 0.19303950667381287
2023-01-24 02:46:35.771339: step: 252/469, loss: 0.07444415241479874
2023-01-24 02:46:36.384120: step: 254/469, loss: 0.021184952929615974
2023-01-24 02:46:37.011443: step: 256/469, loss: 0.2046414017677307
2023-01-24 02:46:37.617119: step: 258/469, loss: 0.10218964517116547
2023-01-24 02:46:38.228058: step: 260/469, loss: 0.05558760091662407
2023-01-24 02:46:38.886259: step: 262/469, loss: 0.510052502155304
2023-01-24 02:46:39.672004: step: 264/469, loss: 0.1685366928577423
2023-01-24 02:46:40.285472: step: 266/469, loss: 0.28381720185279846
2023-01-24 02:46:40.937078: step: 268/469, loss: 0.0380496121942997
2023-01-24 02:46:41.537282: step: 270/469, loss: 0.09100587666034698
2023-01-24 02:46:42.203316: step: 272/469, loss: 0.06771304458379745
2023-01-24 02:46:42.864679: step: 274/469, loss: 0.05137787014245987
2023-01-24 02:46:43.520576: step: 276/469, loss: 0.08808694779872894
2023-01-24 02:46:44.160378: step: 278/469, loss: 0.14675672352313995
2023-01-24 02:46:44.793976: step: 280/469, loss: 0.9552887678146362
2023-01-24 02:46:45.441112: step: 282/469, loss: 0.1043744906783104
2023-01-24 02:46:46.032063: step: 284/469, loss: 0.06530353426933289
2023-01-24 02:46:46.666780: step: 286/469, loss: 0.20721475780010223
2023-01-24 02:46:47.306758: step: 288/469, loss: 0.08885453641414642
2023-01-24 02:46:47.925917: step: 290/469, loss: 0.07269501686096191
2023-01-24 02:46:48.519936: step: 292/469, loss: 0.10241696238517761
2023-01-24 02:46:49.128541: step: 294/469, loss: 0.036570511758327484
2023-01-24 02:46:49.735812: step: 296/469, loss: 0.02546403370797634
2023-01-24 02:46:50.333344: step: 298/469, loss: 0.02204526960849762
2023-01-24 02:46:50.973074: step: 300/469, loss: 0.09121332317590714
2023-01-24 02:46:51.606088: step: 302/469, loss: 0.13340415060520172
2023-01-24 02:46:52.201556: step: 304/469, loss: 0.059527646750211716
2023-01-24 02:46:52.825734: step: 306/469, loss: 0.22927415370941162
2023-01-24 02:46:53.499384: step: 308/469, loss: 0.10273823142051697
2023-01-24 02:46:54.081064: step: 310/469, loss: 0.02172967605292797
2023-01-24 02:46:54.709688: step: 312/469, loss: 0.09245534241199493
2023-01-24 02:46:55.369228: step: 314/469, loss: 0.15194593369960785
2023-01-24 02:46:56.023862: step: 316/469, loss: 0.11920594424009323
2023-01-24 02:46:56.670850: step: 318/469, loss: 0.08647657185792923
2023-01-24 02:46:57.300259: step: 320/469, loss: 0.09207209199666977
2023-01-24 02:46:57.922480: step: 322/469, loss: 0.07460210472345352
2023-01-24 02:46:58.607912: step: 324/469, loss: 0.24142161011695862
2023-01-24 02:46:59.233089: step: 326/469, loss: 0.274515300989151
2023-01-24 02:46:59.851162: step: 328/469, loss: 0.08760512620210648
2023-01-24 02:47:00.536743: step: 330/469, loss: 0.13139471411705017
2023-01-24 02:47:01.149935: step: 332/469, loss: 0.07570262253284454
2023-01-24 02:47:01.790043: step: 334/469, loss: 0.18965232372283936
2023-01-24 02:47:02.415708: step: 336/469, loss: 0.021007876843214035
2023-01-24 02:47:03.038810: step: 338/469, loss: 0.5936605930328369
2023-01-24 02:47:03.703523: step: 340/469, loss: 0.06285455077886581
2023-01-24 02:47:04.357611: step: 342/469, loss: 0.3930582106113434
2023-01-24 02:47:05.029976: step: 344/469, loss: 0.17667238414287567
2023-01-24 02:47:05.668642: step: 346/469, loss: 0.28818178176879883
2023-01-24 02:47:06.307289: step: 348/469, loss: 0.08660731464624405
2023-01-24 02:47:06.904364: step: 350/469, loss: 0.09201332926750183
2023-01-24 02:47:07.629056: step: 352/469, loss: 0.46005502343177795
2023-01-24 02:47:08.244944: step: 354/469, loss: 0.05712362006306648
2023-01-24 02:47:08.859243: step: 356/469, loss: 0.31637391448020935
2023-01-24 02:47:09.466711: step: 358/469, loss: 0.013937942683696747
2023-01-24 02:47:10.060193: step: 360/469, loss: 0.06425005197525024
2023-01-24 02:47:10.686752: step: 362/469, loss: 0.10494048148393631
2023-01-24 02:47:11.302748: step: 364/469, loss: 0.10669367015361786
2023-01-24 02:47:11.915817: step: 366/469, loss: 0.14803123474121094
2023-01-24 02:47:12.526986: step: 368/469, loss: 0.1849016696214676
2023-01-24 02:47:13.185928: step: 370/469, loss: 0.04781125858426094
2023-01-24 02:47:13.746535: step: 372/469, loss: 0.0616668276488781
2023-01-24 02:47:14.343629: step: 374/469, loss: 0.07190537452697754
2023-01-24 02:47:15.019891: step: 376/469, loss: 0.0524645559489727
2023-01-24 02:47:15.651122: step: 378/469, loss: 0.6494707465171814
2023-01-24 02:47:16.291952: step: 380/469, loss: 0.18243408203125
2023-01-24 02:47:16.935069: step: 382/469, loss: 0.21436278522014618
2023-01-24 02:47:17.502167: step: 384/469, loss: 0.01952657476067543
2023-01-24 02:47:18.179841: step: 386/469, loss: 0.07805640250444412
2023-01-24 02:47:18.800500: step: 388/469, loss: 0.16420702636241913
2023-01-24 02:47:19.427862: step: 390/469, loss: 0.22387485206127167
2023-01-24 02:47:20.123150: step: 392/469, loss: 0.16565045714378357
2023-01-24 02:47:20.775413: step: 394/469, loss: 0.13501045107841492
2023-01-24 02:47:21.337906: step: 396/469, loss: 0.08366989344358444
2023-01-24 02:47:21.942005: step: 398/469, loss: 0.2138056457042694
2023-01-24 02:47:22.565284: step: 400/469, loss: 0.8156818747520447
2023-01-24 02:47:23.225942: step: 402/469, loss: 0.07744881510734558
2023-01-24 02:47:23.844680: step: 404/469, loss: 0.7006872892379761
2023-01-24 02:47:24.485771: step: 406/469, loss: 0.10675997287034988
2023-01-24 02:47:25.093761: step: 408/469, loss: 0.041311345994472504
2023-01-24 02:47:25.767660: step: 410/469, loss: 0.09614323079586029
2023-01-24 02:47:26.414578: step: 412/469, loss: 1.5351543426513672
2023-01-24 02:47:27.071730: step: 414/469, loss: 0.24632766842842102
2023-01-24 02:47:27.646869: step: 416/469, loss: 0.025399502366781235
2023-01-24 02:47:28.228130: step: 418/469, loss: 0.12387553602457047
2023-01-24 02:47:28.836471: step: 420/469, loss: 0.09193819761276245
2023-01-24 02:47:29.419426: step: 422/469, loss: 0.12497454136610031
2023-01-24 02:47:30.014177: step: 424/469, loss: 0.05305212363600731
2023-01-24 02:47:30.645348: step: 426/469, loss: 0.07651476562023163
2023-01-24 02:47:31.362092: step: 428/469, loss: 0.12583063542842865
2023-01-24 02:47:32.020100: step: 430/469, loss: 0.596038818359375
2023-01-24 02:47:32.635341: step: 432/469, loss: 0.6904774904251099
2023-01-24 02:47:33.268424: step: 434/469, loss: 0.08197285234928131
2023-01-24 02:47:33.898102: step: 436/469, loss: 0.11234140396118164
2023-01-24 02:47:34.527060: step: 438/469, loss: 0.1009846031665802
2023-01-24 02:47:35.164589: step: 440/469, loss: 0.21016834676265717
2023-01-24 02:47:35.802275: step: 442/469, loss: 0.2865082025527954
2023-01-24 02:47:36.463968: step: 444/469, loss: 0.09421136975288391
2023-01-24 02:47:37.103849: step: 446/469, loss: 0.2870556712150574
2023-01-24 02:47:37.672945: step: 448/469, loss: 0.08144180476665497
2023-01-24 02:47:38.327294: step: 450/469, loss: 0.060530755668878555
2023-01-24 02:47:38.950022: step: 452/469, loss: 0.06883741915225983
2023-01-24 02:47:39.514387: step: 454/469, loss: 0.34555795788764954
2023-01-24 02:47:40.231662: step: 456/469, loss: 0.5633630156517029
2023-01-24 02:47:40.842650: step: 458/469, loss: 0.048432573676109314
2023-01-24 02:47:41.573388: step: 460/469, loss: 0.4532848000526428
2023-01-24 02:47:42.190179: step: 462/469, loss: 0.21483466029167175
2023-01-24 02:47:42.870861: step: 464/469, loss: 0.13238316774368286
2023-01-24 02:47:43.652110: step: 466/469, loss: 0.12196317315101624
2023-01-24 02:47:44.373501: step: 468/469, loss: 0.09013567864894867
2023-01-24 02:47:44.973147: step: 470/469, loss: 0.18008871376514435
2023-01-24 02:47:45.549498: step: 472/469, loss: 0.02501816675066948
2023-01-24 02:47:46.153696: step: 474/469, loss: 0.34291648864746094
2023-01-24 02:47:46.725466: step: 476/469, loss: 0.07923520356416702
2023-01-24 02:47:47.355010: step: 478/469, loss: 0.03828778117895126
2023-01-24 02:47:47.992765: step: 480/469, loss: 0.12524761259555817
2023-01-24 02:47:48.659714: step: 482/469, loss: 0.5911293029785156
2023-01-24 02:47:49.302123: step: 484/469, loss: 0.0678834468126297
2023-01-24 02:47:49.974436: step: 486/469, loss: 0.019243234768509865
2023-01-24 02:47:50.590153: step: 488/469, loss: 0.01733345352113247
2023-01-24 02:47:51.241973: step: 490/469, loss: 0.1415814459323883
2023-01-24 02:47:51.896856: step: 492/469, loss: 0.17629176378250122
2023-01-24 02:47:52.463261: step: 494/469, loss: 0.41696739196777344
2023-01-24 02:47:53.121175: step: 496/469, loss: 0.06588204205036163
2023-01-24 02:47:53.752422: step: 498/469, loss: 0.09903915226459503
2023-01-24 02:47:54.424520: step: 500/469, loss: 0.1281720995903015
2023-01-24 02:47:54.994691: step: 502/469, loss: 0.01150738075375557
2023-01-24 02:47:55.590656: step: 504/469, loss: 0.094943568110466
2023-01-24 02:47:56.234626: step: 506/469, loss: 0.06442873924970627
2023-01-24 02:47:56.821119: step: 508/469, loss: 0.09710308164358139
2023-01-24 02:47:57.477219: step: 510/469, loss: 0.31544438004493713
2023-01-24 02:47:58.138039: step: 512/469, loss: 0.06528124958276749
2023-01-24 02:47:58.965225: step: 514/469, loss: 0.0361175574362278
2023-01-24 02:47:59.544404: step: 516/469, loss: 0.13634465634822845
2023-01-24 02:48:00.162151: step: 518/469, loss: 0.13550400733947754
2023-01-24 02:48:00.785852: step: 520/469, loss: 0.20977728068828583
2023-01-24 02:48:01.470131: step: 522/469, loss: 0.06899198889732361
2023-01-24 02:48:02.070622: step: 524/469, loss: 0.07991157472133636
2023-01-24 02:48:02.675673: step: 526/469, loss: 0.08164144307374954
2023-01-24 02:48:03.287658: step: 528/469, loss: 0.07033399492502213
2023-01-24 02:48:03.943765: step: 530/469, loss: 0.04005934298038483
2023-01-24 02:48:04.563675: step: 532/469, loss: 0.053803931921720505
2023-01-24 02:48:05.223838: step: 534/469, loss: 0.05650361627340317
2023-01-24 02:48:05.852436: step: 536/469, loss: 0.04314383864402771
2023-01-24 02:48:06.504145: step: 538/469, loss: 0.23455005884170532
2023-01-24 02:48:07.185652: step: 540/469, loss: 0.41306638717651367
2023-01-24 02:48:07.778711: step: 542/469, loss: 0.46649155020713806
2023-01-24 02:48:08.450368: step: 544/469, loss: 0.21067191660404205
2023-01-24 02:48:09.109038: step: 546/469, loss: 0.05309181287884712
2023-01-24 02:48:09.778386: step: 548/469, loss: 0.21252405643463135
2023-01-24 02:48:10.337164: step: 550/469, loss: 0.04839169234037399
2023-01-24 02:48:10.944635: step: 552/469, loss: 0.058077406138181686
2023-01-24 02:48:11.569340: step: 554/469, loss: 0.12673555314540863
2023-01-24 02:48:12.198062: step: 556/469, loss: 0.08447688817977905
2023-01-24 02:48:12.804707: step: 558/469, loss: 0.10869933664798737
2023-01-24 02:48:13.464931: step: 560/469, loss: 0.09575501084327698
2023-01-24 02:48:14.097508: step: 562/469, loss: 0.0852009505033493
2023-01-24 02:48:14.702900: step: 564/469, loss: 0.03301452100276947
2023-01-24 02:48:15.331111: step: 566/469, loss: 0.2083071917295456
2023-01-24 02:48:15.888185: step: 568/469, loss: 0.10271920263767242
2023-01-24 02:48:16.488840: step: 570/469, loss: 0.07137446850538254
2023-01-24 02:48:17.117601: step: 572/469, loss: 0.04790101200342178
2023-01-24 02:48:17.748056: step: 574/469, loss: 0.099668949842453
2023-01-24 02:48:18.444964: step: 576/469, loss: 0.1455017626285553
2023-01-24 02:48:19.067731: step: 578/469, loss: 0.07785852253437042
2023-01-24 02:48:19.647075: step: 580/469, loss: 0.25632062554359436
2023-01-24 02:48:20.268543: step: 582/469, loss: 0.07538482546806335
2023-01-24 02:48:20.854699: step: 584/469, loss: 0.09727531671524048
2023-01-24 02:48:21.440223: step: 586/469, loss: 0.13240544497966766
2023-01-24 02:48:22.007855: step: 588/469, loss: 0.04293511062860489
2023-01-24 02:48:22.628280: step: 590/469, loss: 0.2791767716407776
2023-01-24 02:48:23.256014: step: 592/469, loss: 0.34410086274147034
2023-01-24 02:48:23.868118: step: 594/469, loss: 0.2836783230304718
2023-01-24 02:48:24.465785: step: 596/469, loss: 0.05330923944711685
2023-01-24 02:48:25.111151: step: 598/469, loss: 0.12309497594833374
2023-01-24 02:48:25.763075: step: 600/469, loss: 0.09553201496601105
2023-01-24 02:48:26.428842: step: 602/469, loss: 0.08250755816698074
2023-01-24 02:48:27.045589: step: 604/469, loss: 1.0477052927017212
2023-01-24 02:48:27.611589: step: 606/469, loss: 0.14281758666038513
2023-01-24 02:48:28.266989: step: 608/469, loss: 0.09342851489782333
2023-01-24 02:48:28.882598: step: 610/469, loss: 0.014582914300262928
2023-01-24 02:48:29.508433: step: 612/469, loss: 0.6999114155769348
2023-01-24 02:48:30.072614: step: 614/469, loss: 0.11366409063339233
2023-01-24 02:48:30.679917: step: 616/469, loss: 0.10880661010742188
2023-01-24 02:48:31.241364: step: 618/469, loss: 0.4414944052696228
2023-01-24 02:48:31.911733: step: 620/469, loss: 0.01519444677978754
2023-01-24 02:48:32.454547: step: 622/469, loss: 0.08215223252773285
2023-01-24 02:48:33.032270: step: 624/469, loss: 0.251505047082901
2023-01-24 02:48:33.649121: step: 626/469, loss: 0.13148269057273865
2023-01-24 02:48:34.249759: step: 628/469, loss: 0.17193777859210968
2023-01-24 02:48:34.857759: step: 630/469, loss: 0.07418045401573181
2023-01-24 02:48:35.550879: step: 632/469, loss: 0.10217420756816864
2023-01-24 02:48:36.196777: step: 634/469, loss: 0.26963257789611816
2023-01-24 02:48:36.844408: step: 636/469, loss: 0.10058349370956421
2023-01-24 02:48:37.428894: step: 638/469, loss: 0.10942566394805908
2023-01-24 02:48:38.044367: step: 640/469, loss: 0.04665057733654976
2023-01-24 02:48:38.657798: step: 642/469, loss: 0.0690917894244194
2023-01-24 02:48:39.295849: step: 644/469, loss: 0.05420218035578728
2023-01-24 02:48:39.965657: step: 646/469, loss: 0.05774494633078575
2023-01-24 02:48:40.616470: step: 648/469, loss: 0.40795964002609253
2023-01-24 02:48:41.222061: step: 650/469, loss: 0.08505664020776749
2023-01-24 02:48:41.908571: step: 652/469, loss: 0.17751897871494293
2023-01-24 02:48:42.607356: step: 654/469, loss: 0.5836828947067261
2023-01-24 02:48:43.303567: step: 656/469, loss: 0.12484271079301834
2023-01-24 02:48:43.979074: step: 658/469, loss: 0.06690538674592972
2023-01-24 02:48:44.673573: step: 660/469, loss: 0.0452662892639637
2023-01-24 02:48:45.313325: step: 662/469, loss: 0.24605311453342438
2023-01-24 02:48:45.890035: step: 664/469, loss: 0.2452179491519928
2023-01-24 02:48:46.463585: step: 666/469, loss: 0.015766263008117676
2023-01-24 02:48:47.150400: step: 668/469, loss: 0.1808127462863922
2023-01-24 02:48:47.795669: step: 670/469, loss: 0.5678360462188721
2023-01-24 02:48:48.417524: step: 672/469, loss: 0.8446255326271057
2023-01-24 02:48:49.011030: step: 674/469, loss: 0.07731617242097855
2023-01-24 02:48:49.663969: step: 676/469, loss: 0.12699292600154877
2023-01-24 02:48:50.296967: step: 678/469, loss: 0.08847266435623169
2023-01-24 02:48:50.899554: step: 680/469, loss: 1.6162434816360474
2023-01-24 02:48:51.585546: step: 682/469, loss: 0.11218369752168655
2023-01-24 02:48:52.226538: step: 684/469, loss: 0.2254307121038437
2023-01-24 02:48:52.891632: step: 686/469, loss: 0.15231843292713165
2023-01-24 02:48:53.522310: step: 688/469, loss: 0.11132191121578217
2023-01-24 02:48:54.129076: step: 690/469, loss: 0.17959937453269958
2023-01-24 02:48:54.767709: step: 692/469, loss: 0.15276867151260376
2023-01-24 02:48:55.359023: step: 694/469, loss: 0.2105720043182373
2023-01-24 02:48:55.976483: step: 696/469, loss: 0.3055950403213501
2023-01-24 02:48:56.540064: step: 698/469, loss: 0.19766704738140106
2023-01-24 02:48:57.159073: step: 700/469, loss: 0.11132828891277313
2023-01-24 02:48:57.773349: step: 702/469, loss: 0.017213527113199234
2023-01-24 02:48:58.310411: step: 704/469, loss: 0.07785165309906006
2023-01-24 02:48:58.947080: step: 706/469, loss: 0.21710491180419922
2023-01-24 02:48:59.578843: step: 708/469, loss: 0.10139473527669907
2023-01-24 02:49:00.200345: step: 710/469, loss: 0.040440790355205536
2023-01-24 02:49:00.868761: step: 712/469, loss: 0.11204468458890915
2023-01-24 02:49:01.447682: step: 714/469, loss: 0.19281946122646332
2023-01-24 02:49:02.069238: step: 716/469, loss: 0.20367039740085602
2023-01-24 02:49:02.669260: step: 718/469, loss: 0.060095809400081635
2023-01-24 02:49:03.299375: step: 720/469, loss: 0.11108577251434326
2023-01-24 02:49:03.908450: step: 722/469, loss: 0.0680357813835144
2023-01-24 02:49:04.477275: step: 724/469, loss: 0.3617883324623108
2023-01-24 02:49:05.127051: step: 726/469, loss: 0.32320207357406616
2023-01-24 02:49:05.737558: step: 728/469, loss: 0.019802497699856758
2023-01-24 02:49:06.430966: step: 730/469, loss: 0.07566557824611664
2023-01-24 02:49:07.070495: step: 732/469, loss: 0.08792748302221298
2023-01-24 02:49:07.656971: step: 734/469, loss: 0.0913555771112442
2023-01-24 02:49:08.313450: step: 736/469, loss: 0.03404795378446579
2023-01-24 02:49:08.992765: step: 738/469, loss: 0.11625602841377258
2023-01-24 02:49:09.609861: step: 740/469, loss: 0.07428066432476044
2023-01-24 02:49:10.252012: step: 742/469, loss: 0.09052813798189163
2023-01-24 02:49:10.898062: step: 744/469, loss: 0.08908706903457642
2023-01-24 02:49:11.543059: step: 746/469, loss: 0.06369903683662415
2023-01-24 02:49:12.124126: step: 748/469, loss: 0.2825640141963959
2023-01-24 02:49:12.736292: step: 750/469, loss: 0.0785973072052002
2023-01-24 02:49:13.439629: step: 752/469, loss: 0.05707874149084091
2023-01-24 02:49:14.197482: step: 754/469, loss: 0.11375433951616287
2023-01-24 02:49:14.753065: step: 756/469, loss: 0.24645879864692688
2023-01-24 02:49:15.376239: step: 758/469, loss: 0.36877089738845825
2023-01-24 02:49:16.052617: step: 760/469, loss: 0.21835432946681976
2023-01-24 02:49:16.613043: step: 762/469, loss: 0.1805793195962906
2023-01-24 02:49:17.246630: step: 764/469, loss: 0.023476416245102882
2023-01-24 02:49:17.921773: step: 766/469, loss: 0.10177686810493469
2023-01-24 02:49:18.634546: step: 768/469, loss: 0.07214643061161041
2023-01-24 02:49:19.251380: step: 770/469, loss: 0.09948726743459702
2023-01-24 02:49:19.823456: step: 772/469, loss: 0.08886440843343735
2023-01-24 02:49:20.442827: step: 774/469, loss: 0.07293224334716797
2023-01-24 02:49:21.047120: step: 776/469, loss: 0.08997739851474762
2023-01-24 02:49:21.708468: step: 778/469, loss: 0.07979803532361984
2023-01-24 02:49:22.347982: step: 780/469, loss: 0.41471773386001587
2023-01-24 02:49:22.935114: step: 782/469, loss: 0.08494696021080017
2023-01-24 02:49:23.598171: step: 784/469, loss: 0.3089362680912018
2023-01-24 02:49:24.154632: step: 786/469, loss: 0.0335184782743454
2023-01-24 02:49:24.780501: step: 788/469, loss: 0.665024995803833
2023-01-24 02:49:25.347722: step: 790/469, loss: 0.5938014388084412
2023-01-24 02:49:25.976641: step: 792/469, loss: 0.07881605625152588
2023-01-24 02:49:26.654548: step: 794/469, loss: 0.0684218630194664
2023-01-24 02:49:27.250990: step: 796/469, loss: 0.1532132923603058
2023-01-24 02:49:27.925591: step: 798/469, loss: 0.09592583775520325
2023-01-24 02:49:28.493510: step: 800/469, loss: 0.15151216089725494
2023-01-24 02:49:29.114347: step: 802/469, loss: 0.05796181038022041
2023-01-24 02:49:29.754786: step: 804/469, loss: 0.07139807194471359
2023-01-24 02:49:30.420086: step: 806/469, loss: 0.060344018042087555
2023-01-24 02:49:31.034288: step: 808/469, loss: 0.563513994216919
2023-01-24 02:49:31.720489: step: 810/469, loss: 0.11856386810541153
2023-01-24 02:49:32.305867: step: 812/469, loss: 0.5364812612533569
2023-01-24 02:49:32.962825: step: 814/469, loss: 0.08153276890516281
2023-01-24 02:49:33.511297: step: 816/469, loss: 0.09765459597110748
2023-01-24 02:49:34.155108: step: 818/469, loss: 0.12858854234218597
2023-01-24 02:49:34.833140: step: 820/469, loss: 0.047056447714567184
2023-01-24 02:49:35.493030: step: 822/469, loss: 0.13528740406036377
2023-01-24 02:49:36.082227: step: 824/469, loss: 0.046440061181783676
2023-01-24 02:49:36.736884: step: 826/469, loss: 0.07523783296346664
2023-01-24 02:49:37.397795: step: 828/469, loss: 0.0931289866566658
2023-01-24 02:49:38.067105: step: 830/469, loss: 0.3882063925266266
2023-01-24 02:49:38.716783: step: 832/469, loss: 0.2032158076763153
2023-01-24 02:49:39.288541: step: 834/469, loss: 0.09220840036869049
2023-01-24 02:49:39.921838: step: 836/469, loss: 0.06647709012031555
2023-01-24 02:49:40.562862: step: 838/469, loss: 0.08813027292490005
2023-01-24 02:49:41.228194: step: 840/469, loss: 0.7979458570480347
2023-01-24 02:49:41.922586: step: 842/469, loss: 0.125069260597229
2023-01-24 02:49:42.536395: step: 844/469, loss: 0.05929647758603096
2023-01-24 02:49:43.116080: step: 846/469, loss: 0.7311899662017822
2023-01-24 02:49:43.740477: step: 848/469, loss: 0.07078272849321365
2023-01-24 02:49:44.413350: step: 850/469, loss: 0.15644574165344238
2023-01-24 02:49:44.999871: step: 852/469, loss: 0.309980183839798
2023-01-24 02:49:45.635035: step: 854/469, loss: 0.1734669804573059
2023-01-24 02:49:46.216723: step: 856/469, loss: 0.11677585542201996
2023-01-24 02:49:46.805259: step: 858/469, loss: 0.11954693496227264
2023-01-24 02:49:47.423765: step: 860/469, loss: 0.7869711518287659
2023-01-24 02:49:48.049063: step: 862/469, loss: 0.16252881288528442
2023-01-24 02:49:48.601447: step: 864/469, loss: 0.04953162744641304
2023-01-24 02:49:49.229553: step: 866/469, loss: 0.03249672055244446
2023-01-24 02:49:49.857838: step: 868/469, loss: 0.06179596856236458
2023-01-24 02:49:50.459688: step: 870/469, loss: 0.11205118149518967
2023-01-24 02:49:51.148436: step: 872/469, loss: 0.0674152597784996
2023-01-24 02:49:51.762266: step: 874/469, loss: 0.685667097568512
2023-01-24 02:49:52.352757: step: 876/469, loss: 0.1429910510778427
2023-01-24 02:49:53.036137: step: 878/469, loss: 0.26832348108291626
2023-01-24 02:49:53.688891: step: 880/469, loss: 0.05928882211446762
2023-01-24 02:49:54.327718: step: 882/469, loss: 0.07628697901964188
2023-01-24 02:49:54.954101: step: 884/469, loss: 0.5264723300933838
2023-01-24 02:49:55.626293: step: 886/469, loss: 0.08741269260644913
2023-01-24 02:49:56.192223: step: 888/469, loss: 0.03884569928050041
2023-01-24 02:49:56.873621: step: 890/469, loss: 0.19749529659748077
2023-01-24 02:49:57.424985: step: 892/469, loss: 0.09642384946346283
2023-01-24 02:49:58.031708: step: 894/469, loss: 0.027745483443140984
2023-01-24 02:49:58.639135: step: 896/469, loss: 0.24407720565795898
2023-01-24 02:49:59.348352: step: 898/469, loss: 0.10440047830343246
2023-01-24 02:49:59.921662: step: 900/469, loss: 0.09144382923841476
2023-01-24 02:50:00.553643: step: 902/469, loss: 0.09869574755430222
2023-01-24 02:50:01.140064: step: 904/469, loss: 0.015571353957057
2023-01-24 02:50:01.851348: step: 906/469, loss: 0.27356794476509094
2023-01-24 02:50:02.537433: step: 908/469, loss: 0.09513689577579498
2023-01-24 02:50:03.161298: step: 910/469, loss: 0.16539962589740753
2023-01-24 02:50:03.808984: step: 912/469, loss: 0.9347312450408936
2023-01-24 02:50:04.427310: step: 914/469, loss: 0.16957257688045502
2023-01-24 02:50:05.089753: step: 916/469, loss: 0.10880465060472488
2023-01-24 02:50:05.671573: step: 918/469, loss: 0.021691981703042984
2023-01-24 02:50:06.299640: step: 920/469, loss: 0.03262234851717949
2023-01-24 02:50:06.934261: step: 922/469, loss: 0.08738932013511658
2023-01-24 02:50:07.502688: step: 924/469, loss: 0.051625512540340424
2023-01-24 02:50:08.095923: step: 926/469, loss: 0.09986802935600281
2023-01-24 02:50:08.680539: step: 928/469, loss: 0.07723455131053925
2023-01-24 02:50:09.276053: step: 930/469, loss: 0.40475204586982727
2023-01-24 02:50:09.860268: step: 932/469, loss: 0.1682518869638443
2023-01-24 02:50:10.428363: step: 934/469, loss: 4.520831108093262
2023-01-24 02:50:11.075074: step: 936/469, loss: 0.018113207072019577
2023-01-24 02:50:11.778367: step: 938/469, loss: 0.07507234811782837
==================================================
Loss: 0.183
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3238334058864785, 'r': 0.3299782522979866, 'f1': 0.32687695293428376}, 'combined': 0.2408567021621038, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31167664464629785, 'r': 0.24666083954167212, 'f1': 0.27538334792548275}, 'combined': 0.15020909886844513, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3236162646876932, 'r': 0.32238811947066215, 'f1': 0.32300102464075847}, 'combined': 0.2380007549984536, 'epoch': 15}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3193100249298657, 'r': 0.24773549967111266, 'f1': 0.2790055653173891}, 'combined': 0.15218485380948496, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3226174140325084, 'r': 0.3244539458011944, 'f1': 0.32353307367498474}, 'combined': 0.2383927911289361, 'epoch': 15}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3082729674540019, 'r': 0.24537738489019364, 'f1': 0.2732526558176074}, 'combined': 0.14904690317324037, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2883771929824561, 'r': 0.31309523809523804, 'f1': 0.30022831050228305}, 'combined': 0.20015220700152203, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2826086956521739, 'r': 0.2826086956521739, 'f1': 0.2826086956521739}, 'combined': 0.14130434782608695, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.46875, 'r': 0.12931034482758622, 'f1': 0.20270270270270271}, 'combined': 0.13513513513513514, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 02:52:58.239002: step: 2/469, loss: 0.08759817481040955
2023-01-24 02:52:58.867844: step: 4/469, loss: 0.10862677544355392
2023-01-24 02:52:59.471243: step: 6/469, loss: 0.032449740916490555
2023-01-24 02:53:00.177820: step: 8/469, loss: 0.3330148458480835
2023-01-24 02:53:00.746638: step: 10/469, loss: 0.25631821155548096
2023-01-24 02:53:01.347740: step: 12/469, loss: 0.35224202275276184
2023-01-24 02:53:01.886138: step: 14/469, loss: 0.0253142099827528
2023-01-24 02:53:02.546231: step: 16/469, loss: 0.042935147881507874
2023-01-24 02:53:03.157071: step: 18/469, loss: 0.055103935301303864
2023-01-24 02:53:03.784004: step: 20/469, loss: 0.457619309425354
2023-01-24 02:53:04.482739: step: 22/469, loss: 0.1297680288553238
2023-01-24 02:53:05.034715: step: 24/469, loss: 0.13178087770938873
2023-01-24 02:53:05.611921: step: 26/469, loss: 0.021845370531082153
2023-01-24 02:53:06.243901: step: 28/469, loss: 0.09020737558603287
2023-01-24 02:53:06.856239: step: 30/469, loss: 0.11093532294034958
2023-01-24 02:53:07.458474: step: 32/469, loss: 0.1392078697681427
2023-01-24 02:53:08.042128: step: 34/469, loss: 0.16760289669036865
2023-01-24 02:53:08.611088: step: 36/469, loss: 0.14420682191848755
2023-01-24 02:53:09.236176: step: 38/469, loss: 0.05341527611017227
2023-01-24 02:53:09.829628: step: 40/469, loss: 0.634558379650116
2023-01-24 02:53:10.457951: step: 42/469, loss: 0.09511689841747284
2023-01-24 02:53:11.083126: step: 44/469, loss: 0.05534956604242325
2023-01-24 02:53:11.692857: step: 46/469, loss: 0.05722063034772873
2023-01-24 02:53:12.262684: step: 48/469, loss: 0.067926324903965
2023-01-24 02:53:12.894190: step: 50/469, loss: 0.17107677459716797
2023-01-24 02:53:13.498901: step: 52/469, loss: 0.5963416695594788
2023-01-24 02:53:14.155952: step: 54/469, loss: 0.1161472350358963
2023-01-24 02:53:14.800005: step: 56/469, loss: 0.45169392228126526
2023-01-24 02:53:15.424846: step: 58/469, loss: 0.09179622679948807
2023-01-24 02:53:16.097533: step: 60/469, loss: 0.12391123175621033
2023-01-24 02:53:16.807549: step: 62/469, loss: 0.11153832077980042
2023-01-24 02:53:17.413103: step: 64/469, loss: 0.2734530568122864
2023-01-24 02:53:18.067120: step: 66/469, loss: 0.08586464822292328
2023-01-24 02:53:18.679295: step: 68/469, loss: 0.027291813865303993
2023-01-24 02:53:19.254297: step: 70/469, loss: 0.12208575755357742
2023-01-24 02:53:19.887626: step: 72/469, loss: 0.04789937660098076
2023-01-24 02:53:20.510515: step: 74/469, loss: 0.06785420328378677
2023-01-24 02:53:21.131424: step: 76/469, loss: 0.8196120262145996
2023-01-24 02:53:21.756731: step: 78/469, loss: 0.03966684639453888
2023-01-24 02:53:22.436519: step: 80/469, loss: 0.19919990003108978
2023-01-24 02:53:23.064026: step: 82/469, loss: 1.3733240365982056
2023-01-24 02:53:23.685184: step: 84/469, loss: 0.17070399224758148
2023-01-24 02:53:24.366046: step: 86/469, loss: 0.041026100516319275
2023-01-24 02:53:25.039109: step: 88/469, loss: 0.031869444996118546
2023-01-24 02:53:25.714015: step: 90/469, loss: 0.10911519825458527
2023-01-24 02:53:26.401732: step: 92/469, loss: 0.04875505343079567
2023-01-24 02:53:27.080108: step: 94/469, loss: 0.016226528212428093
2023-01-24 02:53:27.651191: step: 96/469, loss: 0.09847255796194077
2023-01-24 02:53:28.339070: step: 98/469, loss: 0.08935950696468353
2023-01-24 02:53:29.017925: step: 100/469, loss: 0.38560184836387634
2023-01-24 02:53:29.669237: step: 102/469, loss: 0.03775491565465927
2023-01-24 02:53:30.249128: step: 104/469, loss: 0.11571477353572845
2023-01-24 02:53:30.894101: step: 106/469, loss: 0.1439637988805771
2023-01-24 02:53:31.585056: step: 108/469, loss: 0.3509625494480133
2023-01-24 02:53:32.234182: step: 110/469, loss: 0.8873723149299622
2023-01-24 02:53:32.844946: step: 112/469, loss: 0.030410833656787872
2023-01-24 02:53:33.526068: step: 114/469, loss: 0.1051577776670456
2023-01-24 02:53:34.078971: step: 116/469, loss: 0.24868875741958618
2023-01-24 02:53:34.709712: step: 118/469, loss: 0.027866119518876076
2023-01-24 02:53:35.423018: step: 120/469, loss: 0.05933655425906181
2023-01-24 02:53:36.001971: step: 122/469, loss: 0.058191679418087006
2023-01-24 02:53:36.575884: step: 124/469, loss: 0.04560903459787369
2023-01-24 02:53:37.231725: step: 126/469, loss: 0.1586115062236786
2023-01-24 02:53:37.838900: step: 128/469, loss: 0.0660063773393631
2023-01-24 02:53:38.485684: step: 130/469, loss: 0.07444681227207184
2023-01-24 02:53:39.110533: step: 132/469, loss: 0.03317635506391525
2023-01-24 02:53:39.710978: step: 134/469, loss: 0.027760345488786697
2023-01-24 02:53:40.373259: step: 136/469, loss: 0.034100595861673355
2023-01-24 02:53:40.956091: step: 138/469, loss: 0.07568786293268204
2023-01-24 02:53:41.546515: step: 140/469, loss: 0.03036593459546566
2023-01-24 02:53:42.173494: step: 142/469, loss: 0.05914986878633499
2023-01-24 02:53:42.851784: step: 144/469, loss: 0.06908878684043884
2023-01-24 02:53:43.524670: step: 146/469, loss: 0.10080679506063461
2023-01-24 02:53:44.072979: step: 148/469, loss: 0.04087192565202713
2023-01-24 02:53:44.726723: step: 150/469, loss: 0.10990936309099197
2023-01-24 02:53:45.327656: step: 152/469, loss: 0.07776656746864319
2023-01-24 02:53:45.975943: step: 154/469, loss: 0.10193280130624771
2023-01-24 02:53:46.615578: step: 156/469, loss: 0.1123528778553009
2023-01-24 02:53:47.238339: step: 158/469, loss: 0.0585317388176918
2023-01-24 02:53:47.832910: step: 160/469, loss: 0.04772958159446716
2023-01-24 02:53:48.471254: step: 162/469, loss: 0.03404593840241432
2023-01-24 02:53:49.120424: step: 164/469, loss: 0.061102382838726044
2023-01-24 02:53:49.739455: step: 166/469, loss: 0.14992041885852814
2023-01-24 02:53:50.476125: step: 168/469, loss: 0.0859682634472847
2023-01-24 02:53:51.100616: step: 170/469, loss: 0.10439613461494446
2023-01-24 02:53:51.758149: step: 172/469, loss: 0.326616495847702
2023-01-24 02:53:52.375456: step: 174/469, loss: 0.09904137253761292
2023-01-24 02:53:52.980201: step: 176/469, loss: 0.4188278615474701
2023-01-24 02:53:53.606083: step: 178/469, loss: 0.07928576320409775
2023-01-24 02:53:54.266324: step: 180/469, loss: 0.10259288549423218
2023-01-24 02:53:54.883777: step: 182/469, loss: 0.16187797486782074
2023-01-24 02:53:55.473991: step: 184/469, loss: 0.1374415159225464
2023-01-24 02:53:56.166915: step: 186/469, loss: 0.11020496487617493
2023-01-24 02:53:56.756704: step: 188/469, loss: 0.1418713927268982
2023-01-24 02:53:57.392742: step: 190/469, loss: 0.034615661948919296
2023-01-24 02:53:57.953432: step: 192/469, loss: 0.029697706922888756
2023-01-24 02:53:58.558319: step: 194/469, loss: 0.04615360498428345
2023-01-24 02:53:59.202328: step: 196/469, loss: 0.19317340850830078
2023-01-24 02:53:59.867594: step: 198/469, loss: 0.12580899894237518
2023-01-24 02:54:00.426647: step: 200/469, loss: 0.032612282782793045
2023-01-24 02:54:00.981151: step: 202/469, loss: 0.03660755231976509
2023-01-24 02:54:01.559875: step: 204/469, loss: 0.08443994075059891
2023-01-24 02:54:02.178836: step: 206/469, loss: 0.016526829451322556
2023-01-24 02:54:02.744265: step: 208/469, loss: 0.13248567283153534
2023-01-24 02:54:03.402368: step: 210/469, loss: 0.11488926410675049
2023-01-24 02:54:04.005123: step: 212/469, loss: 0.05002579838037491
2023-01-24 02:54:04.641848: step: 214/469, loss: 0.14463454484939575
2023-01-24 02:54:05.264742: step: 216/469, loss: 0.036352042108774185
2023-01-24 02:54:05.890530: step: 218/469, loss: 0.10473927855491638
2023-01-24 02:54:06.487798: step: 220/469, loss: 0.07550850510597229
2023-01-24 02:54:07.134606: step: 222/469, loss: 0.08478794991970062
2023-01-24 02:54:07.688455: step: 224/469, loss: 0.14666549861431122
2023-01-24 02:54:08.381447: step: 226/469, loss: 0.12549607455730438
2023-01-24 02:54:08.999342: step: 228/469, loss: 0.0864592120051384
2023-01-24 02:54:09.625949: step: 230/469, loss: 0.890785276889801
2023-01-24 02:54:10.274735: step: 232/469, loss: 0.02598583698272705
2023-01-24 02:54:10.991646: step: 234/469, loss: 0.3216521143913269
2023-01-24 02:54:11.646752: step: 236/469, loss: 0.11896971613168716
2023-01-24 02:54:12.317600: step: 238/469, loss: 0.13987763226032257
2023-01-24 02:54:12.970192: step: 240/469, loss: 0.14266404509544373
2023-01-24 02:54:13.548753: step: 242/469, loss: 0.039546750485897064
2023-01-24 02:54:14.211856: step: 244/469, loss: 0.059781335294246674
2023-01-24 02:54:14.769083: step: 246/469, loss: 0.03459937497973442
2023-01-24 02:54:15.404046: step: 248/469, loss: 0.07345850765705109
2023-01-24 02:54:16.041186: step: 250/469, loss: 0.2378780096769333
2023-01-24 02:54:16.617777: step: 252/469, loss: 0.048793938010931015
2023-01-24 02:54:17.276230: step: 254/469, loss: 0.04427121952176094
2023-01-24 02:54:17.917056: step: 256/469, loss: 0.400473415851593
2023-01-24 02:54:18.520430: step: 258/469, loss: 0.11825111508369446
2023-01-24 02:54:19.104421: step: 260/469, loss: 0.35052287578582764
2023-01-24 02:54:19.759871: step: 262/469, loss: 0.07198025286197662
2023-01-24 02:54:20.368836: step: 264/469, loss: 0.027040036395192146
2023-01-24 02:54:20.990272: step: 266/469, loss: 0.14885684847831726
2023-01-24 02:54:21.635181: step: 268/469, loss: 0.17571820318698883
2023-01-24 02:54:22.242382: step: 270/469, loss: 0.0809444785118103
2023-01-24 02:54:22.830995: step: 272/469, loss: 0.058086540549993515
2023-01-24 02:54:23.503525: step: 274/469, loss: 0.032617341727018356
2023-01-24 02:54:24.176322: step: 276/469, loss: 0.15086044371128082
2023-01-24 02:54:24.847759: step: 278/469, loss: 0.02176734246313572
2023-01-24 02:54:25.455061: step: 280/469, loss: 0.1225871592760086
2023-01-24 02:54:26.043746: step: 282/469, loss: 0.07715824991464615
2023-01-24 02:54:26.752258: step: 284/469, loss: 0.09599995613098145
2023-01-24 02:54:27.318450: step: 286/469, loss: 0.0792052149772644
2023-01-24 02:54:27.901096: step: 288/469, loss: 0.0774022787809372
2023-01-24 02:54:28.526212: step: 290/469, loss: 0.0499991774559021
2023-01-24 02:54:29.139198: step: 292/469, loss: 0.07230868935585022
2023-01-24 02:54:29.793253: step: 294/469, loss: 0.07355786114931107
2023-01-24 02:54:30.334889: step: 296/469, loss: 0.3096159100532532
2023-01-24 02:54:30.975123: step: 298/469, loss: 0.06396185606718063
2023-01-24 02:54:31.641602: step: 300/469, loss: 0.08230949938297272
2023-01-24 02:54:32.267995: step: 302/469, loss: 0.10528390854597092
2023-01-24 02:54:32.884522: step: 304/469, loss: 0.06791137158870697
2023-01-24 02:54:33.521340: step: 306/469, loss: 0.12583978474140167
2023-01-24 02:54:34.208080: step: 308/469, loss: 0.0679018422961235
2023-01-24 02:54:34.835335: step: 310/469, loss: 0.12969493865966797
2023-01-24 02:54:35.475895: step: 312/469, loss: 0.10740697383880615
2023-01-24 02:54:36.223704: step: 314/469, loss: 0.0835144892334938
2023-01-24 02:54:36.866342: step: 316/469, loss: 0.10374576598405838
2023-01-24 02:54:37.539696: step: 318/469, loss: 0.12236394733190536
2023-01-24 02:54:38.118818: step: 320/469, loss: 0.06672445684671402
2023-01-24 02:54:38.720464: step: 322/469, loss: 0.07186823338270187
2023-01-24 02:54:39.382300: step: 324/469, loss: 0.7088342905044556
2023-01-24 02:54:40.010306: step: 326/469, loss: 0.09231613576412201
2023-01-24 02:54:40.636057: step: 328/469, loss: 0.2536635398864746
2023-01-24 02:54:41.243716: step: 330/469, loss: 0.07841683179140091
2023-01-24 02:54:41.888854: step: 332/469, loss: 0.09141992777585983
2023-01-24 02:54:42.511792: step: 334/469, loss: 0.086724191904068
2023-01-24 02:54:43.178312: step: 336/469, loss: 0.09820393472909927
2023-01-24 02:54:43.866771: step: 338/469, loss: 0.0037140275817364454
2023-01-24 02:54:44.515999: step: 340/469, loss: 0.8518657088279724
2023-01-24 02:54:45.080134: step: 342/469, loss: 0.1746920794248581
2023-01-24 02:54:45.633693: step: 344/469, loss: 0.06727604568004608
2023-01-24 02:54:46.315051: step: 346/469, loss: 0.19728432595729828
2023-01-24 02:54:46.949538: step: 348/469, loss: 0.05319666862487793
2023-01-24 02:54:47.559860: step: 350/469, loss: 2.291508197784424
2023-01-24 02:54:48.156492: step: 352/469, loss: 0.04678662121295929
2023-01-24 02:54:48.781771: step: 354/469, loss: 0.1769683063030243
2023-01-24 02:54:49.371464: step: 356/469, loss: 0.11278193444013596
2023-01-24 02:54:50.013314: step: 358/469, loss: 0.048480868339538574
2023-01-24 02:54:50.671510: step: 360/469, loss: 0.1318223625421524
2023-01-24 02:54:51.276501: step: 362/469, loss: 0.06999413669109344
2023-01-24 02:54:51.907797: step: 364/469, loss: 0.12965962290763855
2023-01-24 02:54:52.527088: step: 366/469, loss: 0.13442222774028778
2023-01-24 02:54:53.155998: step: 368/469, loss: 1.2415266036987305
2023-01-24 02:54:53.734415: step: 370/469, loss: 0.09754236042499542
2023-01-24 02:54:54.403893: step: 372/469, loss: 0.11386800557374954
2023-01-24 02:54:55.004441: step: 374/469, loss: 0.06985150277614594
2023-01-24 02:54:55.638929: step: 376/469, loss: 0.020396117120981216
2023-01-24 02:54:56.284147: step: 378/469, loss: 0.10593730211257935
2023-01-24 02:54:56.901559: step: 380/469, loss: 0.06065959483385086
2023-01-24 02:54:57.540773: step: 382/469, loss: 0.08820229768753052
2023-01-24 02:54:58.117984: step: 384/469, loss: 0.03810331970453262
2023-01-24 02:54:58.811341: step: 386/469, loss: 0.12489712238311768
2023-01-24 02:54:59.425859: step: 388/469, loss: 0.8214848637580872
2023-01-24 02:55:00.064313: step: 390/469, loss: 0.03253836929798126
2023-01-24 02:55:00.683182: step: 392/469, loss: 0.12141628563404083
2023-01-24 02:55:01.276852: step: 394/469, loss: 0.04173850268125534
2023-01-24 02:55:01.930828: step: 396/469, loss: 0.7022337317466736
2023-01-24 02:55:02.594436: step: 398/469, loss: 0.330159068107605
2023-01-24 02:55:03.234295: step: 400/469, loss: 0.1802656650543213
2023-01-24 02:55:03.850484: step: 402/469, loss: 0.09463348984718323
2023-01-24 02:55:04.542812: step: 404/469, loss: 0.16628727316856384
2023-01-24 02:55:05.164529: step: 406/469, loss: 0.08815762400627136
2023-01-24 02:55:05.853328: step: 408/469, loss: 0.5145547389984131
2023-01-24 02:55:06.659095: step: 410/469, loss: 0.18800586462020874
2023-01-24 02:55:07.281289: step: 412/469, loss: 0.15183062851428986
2023-01-24 02:55:07.890049: step: 414/469, loss: 0.05885807424783707
2023-01-24 02:55:08.466243: step: 416/469, loss: 0.07807522267103195
2023-01-24 02:55:09.130469: step: 418/469, loss: 0.10117263346910477
2023-01-24 02:55:09.746028: step: 420/469, loss: 0.11940769851207733
2023-01-24 02:55:10.359422: step: 422/469, loss: 0.0769347995519638
2023-01-24 02:55:11.051485: step: 424/469, loss: 0.0977262333035469
2023-01-24 02:55:11.597391: step: 426/469, loss: 0.049495261162519455
2023-01-24 02:55:12.240053: step: 428/469, loss: 1.361379623413086
2023-01-24 02:55:12.841261: step: 430/469, loss: 0.0919654443860054
2023-01-24 02:55:13.451551: step: 432/469, loss: 0.11428482830524445
2023-01-24 02:55:14.055684: step: 434/469, loss: 0.4065563678741455
2023-01-24 02:55:14.690618: step: 436/469, loss: 0.07156356424093246
2023-01-24 02:55:15.348803: step: 438/469, loss: 0.05355653911828995
2023-01-24 02:55:15.985014: step: 440/469, loss: 0.05762242525815964
2023-01-24 02:55:16.634651: step: 442/469, loss: 0.02817855402827263
2023-01-24 02:55:17.228155: step: 444/469, loss: 0.05692010372877121
2023-01-24 02:55:17.853476: step: 446/469, loss: 0.07883297652006149
2023-01-24 02:55:18.494412: step: 448/469, loss: 0.031249063089489937
2023-01-24 02:55:19.141361: step: 450/469, loss: 0.15502671897411346
2023-01-24 02:55:19.689764: step: 452/469, loss: 0.1220131367444992
2023-01-24 02:55:20.362391: step: 454/469, loss: 0.20052069425582886
2023-01-24 02:55:21.071114: step: 456/469, loss: 0.1365944892168045
2023-01-24 02:55:21.719062: step: 458/469, loss: 0.05433924123644829
2023-01-24 02:55:22.359338: step: 460/469, loss: 0.7227022647857666
2023-01-24 02:55:23.026785: step: 462/469, loss: 0.8336557149887085
2023-01-24 02:55:23.632737: step: 464/469, loss: 0.054121725261211395
2023-01-24 02:55:24.252591: step: 466/469, loss: 0.16045308113098145
2023-01-24 02:55:24.862535: step: 468/469, loss: 0.8711228966712952
2023-01-24 02:55:25.460423: step: 470/469, loss: 0.07353794574737549
2023-01-24 02:55:26.123143: step: 472/469, loss: 0.21562889218330383
2023-01-24 02:55:26.759498: step: 474/469, loss: 0.11944035440683365
2023-01-24 02:55:27.408255: step: 476/469, loss: 0.19969020783901215
2023-01-24 02:55:27.989946: step: 478/469, loss: 0.032023049890995026
2023-01-24 02:55:28.608615: step: 480/469, loss: 0.23766747117042542
2023-01-24 02:55:29.237318: step: 482/469, loss: 0.11172518134117126
2023-01-24 02:55:29.876976: step: 484/469, loss: 0.13469244539737701
2023-01-24 02:55:30.528266: step: 486/469, loss: 0.0978257805109024
2023-01-24 02:55:31.157502: step: 488/469, loss: 0.17340059578418732
2023-01-24 02:55:31.754807: step: 490/469, loss: 0.028775939717888832
2023-01-24 02:55:32.409603: step: 492/469, loss: 0.058825958520174026
2023-01-24 02:55:33.077806: step: 494/469, loss: 0.09280989319086075
2023-01-24 02:55:33.688863: step: 496/469, loss: 0.050323184579610825
2023-01-24 02:55:34.298951: step: 498/469, loss: 0.048042405396699905
2023-01-24 02:55:34.905205: step: 500/469, loss: 0.13777221739292145
2023-01-24 02:55:35.597831: step: 502/469, loss: 0.23255488276481628
2023-01-24 02:55:36.212725: step: 504/469, loss: 0.12181255221366882
2023-01-24 02:55:36.826144: step: 506/469, loss: 0.10417280346155167
2023-01-24 02:55:37.461781: step: 508/469, loss: 0.19356317818164825
2023-01-24 02:55:38.130906: step: 510/469, loss: 0.17776364088058472
2023-01-24 02:55:38.748639: step: 512/469, loss: 0.11597738415002823
2023-01-24 02:55:39.423313: step: 514/469, loss: 0.1397777944803238
2023-01-24 02:55:40.024295: step: 516/469, loss: 0.1986369490623474
2023-01-24 02:55:40.689890: step: 518/469, loss: 0.06437753140926361
2023-01-24 02:55:41.401947: step: 520/469, loss: 0.06670169532299042
2023-01-24 02:55:42.104458: step: 522/469, loss: 0.045091353356838226
2023-01-24 02:55:42.734208: step: 524/469, loss: 0.03746681287884712
2023-01-24 02:55:43.367109: step: 526/469, loss: 0.09841018915176392
2023-01-24 02:55:44.102833: step: 528/469, loss: 0.08979086577892303
2023-01-24 02:55:44.776648: step: 530/469, loss: 0.14209061861038208
2023-01-24 02:55:45.363457: step: 532/469, loss: 0.1265891194343567
2023-01-24 02:55:45.994132: step: 534/469, loss: 0.3015148937702179
2023-01-24 02:55:46.622721: step: 536/469, loss: 0.05998941510915756
2023-01-24 02:55:47.168236: step: 538/469, loss: 0.04750685766339302
2023-01-24 02:55:47.816449: step: 540/469, loss: 0.07647495716810226
2023-01-24 02:55:48.495198: step: 542/469, loss: 0.01271448377519846
2023-01-24 02:55:49.148504: step: 544/469, loss: 0.3825611472129822
2023-01-24 02:55:49.766033: step: 546/469, loss: 0.1054229736328125
2023-01-24 02:55:50.407717: step: 548/469, loss: 0.06574345380067825
2023-01-24 02:55:51.018016: step: 550/469, loss: 0.07906662672758102
2023-01-24 02:55:51.594988: step: 552/469, loss: 0.07441949099302292
2023-01-24 02:55:52.212203: step: 554/469, loss: 0.038098521530628204
2023-01-24 02:55:52.845867: step: 556/469, loss: 0.5081790685653687
2023-01-24 02:55:53.478306: step: 558/469, loss: 0.2299017757177353
2023-01-24 02:55:54.121161: step: 560/469, loss: 0.02400112897157669
2023-01-24 02:55:54.735141: step: 562/469, loss: 0.05662433058023453
2023-01-24 02:55:55.330746: step: 564/469, loss: 0.056243449449539185
2023-01-24 02:55:55.979030: step: 566/469, loss: 0.167400062084198
2023-01-24 02:55:56.599737: step: 568/469, loss: 0.0932585820555687
2023-01-24 02:55:57.246974: step: 570/469, loss: 0.6299592852592468
2023-01-24 02:55:57.878684: step: 572/469, loss: 0.030439546331763268
2023-01-24 02:55:58.511558: step: 574/469, loss: 0.4335290789604187
2023-01-24 02:55:59.190103: step: 576/469, loss: 0.13615505397319794
2023-01-24 02:55:59.885323: step: 578/469, loss: 0.12170863151550293
2023-01-24 02:56:00.501185: step: 580/469, loss: 0.17706061899662018
2023-01-24 02:56:01.114925: step: 582/469, loss: 0.07675725966691971
2023-01-24 02:56:01.743601: step: 584/469, loss: 0.11557069420814514
2023-01-24 02:56:02.398246: step: 586/469, loss: 0.13605904579162598
2023-01-24 02:56:02.994760: step: 588/469, loss: 0.6559314131736755
2023-01-24 02:56:03.600325: step: 590/469, loss: 0.08097304403781891
2023-01-24 02:56:04.281893: step: 592/469, loss: 0.029244577512145042
2023-01-24 02:56:04.882584: step: 594/469, loss: 0.06050251051783562
2023-01-24 02:56:05.543826: step: 596/469, loss: 0.11156366020441055
2023-01-24 02:56:06.137090: step: 598/469, loss: 0.07792611420154572
2023-01-24 02:56:06.833001: step: 600/469, loss: 0.14440956711769104
2023-01-24 02:56:07.454484: step: 602/469, loss: 0.07254817336797714
2023-01-24 02:56:08.093088: step: 604/469, loss: 0.0520678274333477
2023-01-24 02:56:08.776054: step: 606/469, loss: 0.0892920047044754
2023-01-24 02:56:09.437839: step: 608/469, loss: 0.03410578519105911
2023-01-24 02:56:10.081051: step: 610/469, loss: 0.10717874020338058
2023-01-24 02:56:10.693680: step: 612/469, loss: 0.02829250507056713
2023-01-24 02:56:11.370089: step: 614/469, loss: 0.2779192328453064
2023-01-24 02:56:11.959910: step: 616/469, loss: 0.6068034172058105
2023-01-24 02:56:12.619415: step: 618/469, loss: 0.009849566966295242
2023-01-24 02:56:13.260048: step: 620/469, loss: 0.40928858518600464
2023-01-24 02:56:13.912655: step: 622/469, loss: 0.11569209396839142
2023-01-24 02:56:14.570348: step: 624/469, loss: 0.6247853636741638
2023-01-24 02:56:15.221273: step: 626/469, loss: 0.25124236941337585
2023-01-24 02:56:15.774757: step: 628/469, loss: 0.07776015251874924
2023-01-24 02:56:16.393879: step: 630/469, loss: 0.10470916330814362
2023-01-24 02:56:17.042094: step: 632/469, loss: 0.11792066693305969
2023-01-24 02:56:17.644822: step: 634/469, loss: 0.05234258621931076
2023-01-24 02:56:18.289354: step: 636/469, loss: 0.060398586094379425
2023-01-24 02:56:18.850205: step: 638/469, loss: 0.08910928666591644
2023-01-24 02:56:19.502870: step: 640/469, loss: 0.2223726212978363
2023-01-24 02:56:20.090388: step: 642/469, loss: 0.05613243207335472
2023-01-24 02:56:20.667826: step: 644/469, loss: 0.11752267926931381
2023-01-24 02:56:21.318843: step: 646/469, loss: 0.13896889984607697
2023-01-24 02:56:21.954601: step: 648/469, loss: 0.06304564327001572
2023-01-24 02:56:22.617799: step: 650/469, loss: 0.1676894724369049
2023-01-24 02:56:23.245839: step: 652/469, loss: 0.09562228620052338
2023-01-24 02:56:23.843450: step: 654/469, loss: 0.1165279820561409
2023-01-24 02:56:24.409893: step: 656/469, loss: 0.037642642855644226
2023-01-24 02:56:25.108143: step: 658/469, loss: 0.2296856939792633
2023-01-24 02:56:25.667262: step: 660/469, loss: 0.11191833019256592
2023-01-24 02:56:26.324585: step: 662/469, loss: 0.06068938970565796
2023-01-24 02:56:26.937670: step: 664/469, loss: 0.06496302038431168
2023-01-24 02:56:27.594250: step: 666/469, loss: 0.10366479307413101
2023-01-24 02:56:28.224603: step: 668/469, loss: 0.04444766789674759
2023-01-24 02:56:28.812520: step: 670/469, loss: 0.07094904780387878
2023-01-24 02:56:29.497135: step: 672/469, loss: 0.05575162172317505
2023-01-24 02:56:30.133703: step: 674/469, loss: 0.08301182836294174
2023-01-24 02:56:30.760231: step: 676/469, loss: 0.11818315833806992
2023-01-24 02:56:31.416366: step: 678/469, loss: 0.10328830033540726
2023-01-24 02:56:32.033522: step: 680/469, loss: 0.056759145110845566
2023-01-24 02:56:32.699039: step: 682/469, loss: 0.051041826605796814
2023-01-24 02:56:33.338377: step: 684/469, loss: 0.04933523014187813
2023-01-24 02:56:33.982929: step: 686/469, loss: 0.0768188014626503
2023-01-24 02:56:34.567899: step: 688/469, loss: 0.04857207462191582
2023-01-24 02:56:35.161572: step: 690/469, loss: 0.3262181282043457
2023-01-24 02:56:35.715815: step: 692/469, loss: 0.05440818890929222
2023-01-24 02:56:36.312541: step: 694/469, loss: 0.08826557546854019
2023-01-24 02:56:36.957455: step: 696/469, loss: 0.05439550429582596
2023-01-24 02:56:37.610709: step: 698/469, loss: 0.12256674468517303
2023-01-24 02:56:38.215300: step: 700/469, loss: 0.011911711655557156
2023-01-24 02:56:38.826557: step: 702/469, loss: 0.0815141573548317
2023-01-24 02:56:39.437398: step: 704/469, loss: 0.026219012215733528
2023-01-24 02:56:40.082829: step: 706/469, loss: 0.034951936453580856
2023-01-24 02:56:40.692097: step: 708/469, loss: 0.07204972952604294
2023-01-24 02:56:41.352709: step: 710/469, loss: 0.2694944441318512
2023-01-24 02:56:41.983260: step: 712/469, loss: 0.0628601685166359
2023-01-24 02:56:42.662297: step: 714/469, loss: 0.1304217427968979
2023-01-24 02:56:43.265049: step: 716/469, loss: 0.3279553949832916
2023-01-24 02:56:44.016142: step: 718/469, loss: 0.10063020139932632
2023-01-24 02:56:44.670419: step: 720/469, loss: 0.03350721672177315
2023-01-24 02:56:45.282159: step: 722/469, loss: 1.0422238111495972
2023-01-24 02:56:45.911387: step: 724/469, loss: 0.09029338508844376
2023-01-24 02:56:46.497561: step: 726/469, loss: 0.039478544145822525
2023-01-24 02:56:47.192883: step: 728/469, loss: 0.05626051500439644
2023-01-24 02:56:47.771016: step: 730/469, loss: 0.01795123890042305
2023-01-24 02:56:48.406592: step: 732/469, loss: 0.274331659078598
2023-01-24 02:56:48.937104: step: 734/469, loss: 0.032300472259521484
2023-01-24 02:56:49.522872: step: 736/469, loss: 0.5453379154205322
2023-01-24 02:56:50.077563: step: 738/469, loss: 0.023605981841683388
2023-01-24 02:56:50.725232: step: 740/469, loss: 0.04688532277941704
2023-01-24 02:56:51.318411: step: 742/469, loss: 0.1466190367937088
2023-01-24 02:56:52.086839: step: 744/469, loss: 0.07332953810691833
2023-01-24 02:56:52.707218: step: 746/469, loss: 0.08779364079236984
2023-01-24 02:56:53.354421: step: 748/469, loss: 0.04206997901201248
2023-01-24 02:56:54.083523: step: 750/469, loss: 0.1415180265903473
2023-01-24 02:56:54.770120: step: 752/469, loss: 1.082939624786377
2023-01-24 02:56:55.367980: step: 754/469, loss: 0.11613138020038605
2023-01-24 02:56:55.935902: step: 756/469, loss: 0.06066060811281204
2023-01-24 02:56:56.570254: step: 758/469, loss: 1.5213011503219604
2023-01-24 02:56:57.169489: step: 760/469, loss: 0.059715114533901215
2023-01-24 02:56:57.772002: step: 762/469, loss: 0.07200370728969574
2023-01-24 02:56:58.352276: step: 764/469, loss: 0.04771013930439949
2023-01-24 02:56:59.002158: step: 766/469, loss: 0.03102451004087925
2023-01-24 02:56:59.526039: step: 768/469, loss: 0.6230573654174805
2023-01-24 02:57:00.175507: step: 770/469, loss: 0.0779312327504158
2023-01-24 02:57:00.787332: step: 772/469, loss: 0.08453252166509628
2023-01-24 02:57:01.425701: step: 774/469, loss: 0.12380822002887726
2023-01-24 02:57:01.996397: step: 776/469, loss: 0.06706444174051285
2023-01-24 02:57:02.609051: step: 778/469, loss: 0.05670267343521118
2023-01-24 02:57:03.213263: step: 780/469, loss: 0.0678911879658699
2023-01-24 02:57:03.838215: step: 782/469, loss: 0.0839771181344986
2023-01-24 02:57:04.487746: step: 784/469, loss: 0.06591266393661499
2023-01-24 02:57:05.094172: step: 786/469, loss: 0.06710683554410934
2023-01-24 02:57:05.712649: step: 788/469, loss: 0.11415842920541763
2023-01-24 02:57:06.350563: step: 790/469, loss: 0.12424782663583755
2023-01-24 02:57:07.078886: step: 792/469, loss: 0.22576430439949036
2023-01-24 02:57:07.704923: step: 794/469, loss: 0.05598742142319679
2023-01-24 02:57:08.409760: step: 796/469, loss: 0.12410330027341843
2023-01-24 02:57:09.047348: step: 798/469, loss: 0.1357264667749405
2023-01-24 02:57:09.701320: step: 800/469, loss: 0.4761008620262146
2023-01-24 02:57:10.304261: step: 802/469, loss: 0.10413392633199692
2023-01-24 02:57:10.969236: step: 804/469, loss: 0.07092542946338654
2023-01-24 02:57:11.607298: step: 806/469, loss: 0.11728647351264954
2023-01-24 02:57:12.187782: step: 808/469, loss: 0.10438113659620285
2023-01-24 02:57:12.883063: step: 810/469, loss: 0.10724121332168579
2023-01-24 02:57:13.488838: step: 812/469, loss: 0.023226801306009293
2023-01-24 02:57:14.161425: step: 814/469, loss: 0.08560799062252045
2023-01-24 02:57:14.848051: step: 816/469, loss: 0.9491845369338989
2023-01-24 02:57:15.440691: step: 818/469, loss: 0.023172764107584953
2023-01-24 02:57:16.026312: step: 820/469, loss: 1.796709656715393
2023-01-24 02:57:16.691618: step: 822/469, loss: 0.0500091128051281
2023-01-24 02:57:17.305272: step: 824/469, loss: 0.6142128705978394
2023-01-24 02:57:17.881493: step: 826/469, loss: 0.013409084640443325
2023-01-24 02:57:18.545491: step: 828/469, loss: 0.22463026642799377
2023-01-24 02:57:19.187193: step: 830/469, loss: 0.17779836058616638
2023-01-24 02:57:19.800482: step: 832/469, loss: 0.07775621861219406
2023-01-24 02:57:20.419322: step: 834/469, loss: 0.13510532677173615
2023-01-24 02:57:21.093663: step: 836/469, loss: 0.5249348282814026
2023-01-24 02:57:21.690490: step: 838/469, loss: 0.10932567715644836
2023-01-24 02:57:22.261532: step: 840/469, loss: 0.08818814903497696
2023-01-24 02:57:22.970788: step: 842/469, loss: 0.10375554859638214
2023-01-24 02:57:23.592415: step: 844/469, loss: 0.4173268973827362
2023-01-24 02:57:24.209825: step: 846/469, loss: 0.06288052350282669
2023-01-24 02:57:24.769361: step: 848/469, loss: 0.09162698686122894
2023-01-24 02:57:25.399009: step: 850/469, loss: 0.30981189012527466
2023-01-24 02:57:25.989138: step: 852/469, loss: 0.047051552683115005
2023-01-24 02:57:26.579124: step: 854/469, loss: 0.31900516152381897
2023-01-24 02:57:27.228105: step: 856/469, loss: 0.13337601721286774
2023-01-24 02:57:27.860813: step: 858/469, loss: 0.20193684101104736
2023-01-24 02:57:28.550484: step: 860/469, loss: 0.07986877113580704
2023-01-24 02:57:29.131323: step: 862/469, loss: 0.10771413892507553
2023-01-24 02:57:29.751147: step: 864/469, loss: 0.07494720816612244
2023-01-24 02:57:30.405467: step: 866/469, loss: 0.15828967094421387
2023-01-24 02:57:31.132694: step: 868/469, loss: 0.05749820917844772
2023-01-24 02:57:31.775680: step: 870/469, loss: 0.169984832406044
2023-01-24 02:57:32.355419: step: 872/469, loss: 0.0744345560669899
2023-01-24 02:57:33.024437: step: 874/469, loss: 0.21342425048351288
2023-01-24 02:57:33.661381: step: 876/469, loss: 0.1242813766002655
2023-01-24 02:57:34.370147: step: 878/469, loss: 0.02060120925307274
2023-01-24 02:57:34.974417: step: 880/469, loss: 0.0629616379737854
2023-01-24 02:57:35.615564: step: 882/469, loss: 0.10362087935209274
2023-01-24 02:57:36.289260: step: 884/469, loss: 0.1605091094970703
2023-01-24 02:57:37.012093: step: 886/469, loss: 0.31162071228027344
2023-01-24 02:57:37.627989: step: 888/469, loss: 0.3976716995239258
2023-01-24 02:57:38.228249: step: 890/469, loss: 0.11037041246891022
2023-01-24 02:57:38.884274: step: 892/469, loss: 0.10884872823953629
2023-01-24 02:57:39.569135: step: 894/469, loss: 0.08175639808177948
2023-01-24 02:57:40.220992: step: 896/469, loss: 0.20332136750221252
2023-01-24 02:57:40.837044: step: 898/469, loss: 0.17498016357421875
2023-01-24 02:57:41.453342: step: 900/469, loss: 0.062188196927309036
2023-01-24 02:57:42.025480: step: 902/469, loss: 0.03288247808814049
2023-01-24 02:57:42.604654: step: 904/469, loss: 1.3207803964614868
2023-01-24 02:57:43.241189: step: 906/469, loss: 0.2592983841896057
2023-01-24 02:57:43.871898: step: 908/469, loss: 0.6696668863296509
2023-01-24 02:57:44.471121: step: 910/469, loss: 0.09069929271936417
2023-01-24 02:57:45.121797: step: 912/469, loss: 0.09416594356298447
2023-01-24 02:57:45.715404: step: 914/469, loss: 0.29435089230537415
2023-01-24 02:57:46.442084: step: 916/469, loss: 0.09426331520080566
2023-01-24 02:57:47.150039: step: 918/469, loss: 0.13866384327411652
2023-01-24 02:57:47.785398: step: 920/469, loss: 0.06049207225441933
2023-01-24 02:57:48.442299: step: 922/469, loss: 0.10886509716510773
2023-01-24 02:57:49.060940: step: 924/469, loss: 0.22822241485118866
2023-01-24 02:57:49.644629: step: 926/469, loss: 0.12083389610052109
2023-01-24 02:57:50.307955: step: 928/469, loss: 0.09527838230133057
2023-01-24 02:57:50.903688: step: 930/469, loss: 0.051837168633937836
2023-01-24 02:57:51.469609: step: 932/469, loss: 0.1378217339515686
2023-01-24 02:57:52.099734: step: 934/469, loss: 0.03517038747668266
2023-01-24 02:57:52.721439: step: 936/469, loss: 0.052448615431785583
2023-01-24 02:57:53.320918: step: 938/469, loss: 0.3225906491279602
==================================================
Loss: 0.168
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3465266719745223, 'r': 0.3097041034155598, 'f1': 0.3270822895791583}, 'combined': 0.24100800284780083, 'epoch': 16}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32013470181511244, 'r': 0.24083259560679848, 'f1': 0.2748783094354069}, 'combined': 0.14993362332840376, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3556024332810047, 'r': 0.3070191786391976, 'f1': 0.3295297497817864}, 'combined': 0.2428113945760531, 'epoch': 16}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33502875220593786, 'r': 0.24560608708332923, 'f1': 0.2834314971193694}, 'combined': 0.15459899842874691, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3432126497533474, 'r': 0.30804475015812777, 'f1': 0.32467916666666663}, 'combined': 0.23923728070175435, 'epoch': 16}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3201876852612147, 'r': 0.23823836910660764, 'f1': 0.2731999746358792}, 'combined': 0.14901816798320683, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4158333333333333, 'r': 0.29702380952380947, 'f1': 0.3465277777777777}, 'combined': 0.23101851851851846, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.32142857142857145, 'r': 0.29347826086956524, 'f1': 0.3068181818181819}, 'combined': 0.15340909090909094, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4166666666666667, 'r': 0.12931034482758622, 'f1': 0.19736842105263158}, 'combined': 0.13157894736842105, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:00:38.726804: step: 2/469, loss: 0.08634264767169952
2023-01-24 03:00:39.386292: step: 4/469, loss: 0.09594616293907166
2023-01-24 03:00:40.059424: step: 6/469, loss: 0.0449104905128479
2023-01-24 03:00:40.657278: step: 8/469, loss: 0.002346464665606618
2023-01-24 03:00:41.348224: step: 10/469, loss: 0.04650544375181198
2023-01-24 03:00:42.000679: step: 12/469, loss: 0.05193765461444855
2023-01-24 03:00:42.666341: step: 14/469, loss: 0.08693695813417435
2023-01-24 03:00:43.320144: step: 16/469, loss: 0.9412013292312622
2023-01-24 03:00:43.969539: step: 18/469, loss: 0.05715508013963699
2023-01-24 03:00:44.559297: step: 20/469, loss: 0.17629854381084442
2023-01-24 03:00:45.234410: step: 22/469, loss: 0.08444023877382278
2023-01-24 03:00:45.861723: step: 24/469, loss: 0.07957160472869873
2023-01-24 03:00:46.605653: step: 26/469, loss: 0.04437550529837608
2023-01-24 03:00:47.215608: step: 28/469, loss: 0.05539350584149361
2023-01-24 03:00:47.845919: step: 30/469, loss: 0.08054979890584946
2023-01-24 03:00:48.479443: step: 32/469, loss: 0.4293166697025299
2023-01-24 03:00:49.094542: step: 34/469, loss: 0.2442564070224762
2023-01-24 03:00:49.691185: step: 36/469, loss: 0.1444416642189026
2023-01-24 03:00:50.360534: step: 38/469, loss: 0.09923011064529419
2023-01-24 03:00:51.024522: step: 40/469, loss: 0.1501404345035553
2023-01-24 03:00:51.629592: step: 42/469, loss: 0.022317150607705116
2023-01-24 03:00:52.225167: step: 44/469, loss: 0.18897463381290436
2023-01-24 03:00:52.874990: step: 46/469, loss: 0.1063184142112732
2023-01-24 03:00:53.451638: step: 48/469, loss: 0.012038880959153175
2023-01-24 03:00:54.170324: step: 50/469, loss: 0.13240452110767365
2023-01-24 03:00:54.797563: step: 52/469, loss: 0.023567305877804756
2023-01-24 03:00:55.439430: step: 54/469, loss: 0.05520399287343025
2023-01-24 03:00:56.063314: step: 56/469, loss: 0.05590912327170372
2023-01-24 03:00:56.689366: step: 58/469, loss: 0.05357128754258156
2023-01-24 03:00:57.342178: step: 60/469, loss: 0.06377561390399933
2023-01-24 03:00:57.937995: step: 62/469, loss: 0.07197009772062302
2023-01-24 03:00:58.591986: step: 64/469, loss: 0.08526509255170822
2023-01-24 03:00:59.176551: step: 66/469, loss: 0.16183842718601227
2023-01-24 03:00:59.833806: step: 68/469, loss: 0.03890698775649071
2023-01-24 03:01:00.455093: step: 70/469, loss: 0.08364640921354294
2023-01-24 03:01:01.122963: step: 72/469, loss: 0.06541049480438232
2023-01-24 03:01:01.754690: step: 74/469, loss: 0.1643519103527069
2023-01-24 03:01:02.388756: step: 76/469, loss: 0.04508458450436592
2023-01-24 03:01:02.996490: step: 78/469, loss: 0.027948787435889244
2023-01-24 03:01:03.585714: step: 80/469, loss: 0.12359713017940521
2023-01-24 03:01:04.189817: step: 82/469, loss: 0.09651672095060349
2023-01-24 03:01:04.781753: step: 84/469, loss: 0.47778555750846863
2023-01-24 03:01:05.403466: step: 86/469, loss: 0.35092127323150635
2023-01-24 03:01:05.959638: step: 88/469, loss: 0.05257191136479378
2023-01-24 03:01:06.613306: step: 90/469, loss: 0.03308539092540741
2023-01-24 03:01:07.322147: step: 92/469, loss: 0.22135744988918304
2023-01-24 03:01:07.906291: step: 94/469, loss: 0.08995926380157471
2023-01-24 03:01:08.510352: step: 96/469, loss: 1.2354682683944702
2023-01-24 03:01:09.104732: step: 98/469, loss: 0.024919720366597176
2023-01-24 03:01:09.712536: step: 100/469, loss: 0.06241423636674881
2023-01-24 03:01:10.370245: step: 102/469, loss: 0.07183968275785446
2023-01-24 03:01:10.944232: step: 104/469, loss: 0.1211848109960556
2023-01-24 03:01:11.552204: step: 106/469, loss: 0.11559804528951645
2023-01-24 03:01:12.227341: step: 108/469, loss: 0.12789353728294373
2023-01-24 03:01:12.893097: step: 110/469, loss: 0.08593995869159698
2023-01-24 03:01:13.519805: step: 112/469, loss: 0.13324569165706635
2023-01-24 03:01:14.132449: step: 114/469, loss: 0.15789788961410522
2023-01-24 03:01:14.713743: step: 116/469, loss: 0.04587888345122337
2023-01-24 03:01:15.340745: step: 118/469, loss: 0.23107899725437164
2023-01-24 03:01:15.958437: step: 120/469, loss: 0.20080715417861938
2023-01-24 03:01:16.620267: step: 122/469, loss: 0.3319023847579956
2023-01-24 03:01:17.288202: step: 124/469, loss: 0.08711359649896622
2023-01-24 03:01:17.868115: step: 126/469, loss: 0.07506758719682693
2023-01-24 03:01:18.451440: step: 128/469, loss: 0.062093090265989304
2023-01-24 03:01:19.092925: step: 130/469, loss: 0.06379514187574387
2023-01-24 03:01:19.699817: step: 132/469, loss: 0.02370130456984043
2023-01-24 03:01:20.283357: step: 134/469, loss: 0.0908806174993515
2023-01-24 03:01:20.934621: step: 136/469, loss: 0.1807468831539154
2023-01-24 03:01:21.616681: step: 138/469, loss: 0.8564741015434265
2023-01-24 03:01:22.243516: step: 140/469, loss: 0.15068039298057556
2023-01-24 03:01:22.891603: step: 142/469, loss: 0.10965810716152191
2023-01-24 03:01:23.511356: step: 144/469, loss: 0.05497078225016594
2023-01-24 03:01:24.196158: step: 146/469, loss: 0.055678028613328934
2023-01-24 03:01:24.838649: step: 148/469, loss: 1.1616432666778564
2023-01-24 03:01:25.414980: step: 150/469, loss: 0.16371865570545197
2023-01-24 03:01:26.046659: step: 152/469, loss: 0.03400680050253868
2023-01-24 03:01:26.780397: step: 154/469, loss: 0.06986163556575775
2023-01-24 03:01:27.473956: step: 156/469, loss: 0.04563900828361511
2023-01-24 03:01:28.121866: step: 158/469, loss: 0.0924905389547348
2023-01-24 03:01:28.772490: step: 160/469, loss: 0.1355503350496292
2023-01-24 03:01:29.329814: step: 162/469, loss: 0.03501926735043526
2023-01-24 03:01:30.001481: step: 164/469, loss: 0.05254092067480087
2023-01-24 03:01:30.642188: step: 166/469, loss: 0.10394218564033508
2023-01-24 03:01:31.282349: step: 168/469, loss: 0.1005459800362587
2023-01-24 03:01:31.901533: step: 170/469, loss: 0.23538199067115784
2023-01-24 03:01:32.514593: step: 172/469, loss: 0.09074113517999649
2023-01-24 03:01:33.136319: step: 174/469, loss: 0.04362407326698303
2023-01-24 03:01:33.761283: step: 176/469, loss: 0.061876360327005386
2023-01-24 03:01:34.440386: step: 178/469, loss: 0.05744713544845581
2023-01-24 03:01:35.063377: step: 180/469, loss: 0.041415516287088394
2023-01-24 03:01:35.700077: step: 182/469, loss: 0.06296899169683456
2023-01-24 03:01:36.311667: step: 184/469, loss: 0.017496343702077866
2023-01-24 03:01:36.944930: step: 186/469, loss: 0.05537179112434387
2023-01-24 03:01:37.532277: step: 188/469, loss: 0.10990407317876816
2023-01-24 03:01:38.125067: step: 190/469, loss: 0.05061742663383484
2023-01-24 03:01:38.730066: step: 192/469, loss: 0.15230831503868103
2023-01-24 03:01:39.385135: step: 194/469, loss: 0.17597559094429016
2023-01-24 03:01:39.996201: step: 196/469, loss: 0.2093985229730606
2023-01-24 03:01:40.666026: step: 198/469, loss: 0.35954588651657104
2023-01-24 03:01:41.247649: step: 200/469, loss: 0.015171553939580917
2023-01-24 03:01:41.886917: step: 202/469, loss: 0.29540735483169556
2023-01-24 03:01:42.497168: step: 204/469, loss: 0.2296929508447647
2023-01-24 03:01:43.166317: step: 206/469, loss: 0.2057746797800064
2023-01-24 03:01:43.767221: step: 208/469, loss: 0.06798412650823593
2023-01-24 03:01:44.360323: step: 210/469, loss: 0.04519176483154297
2023-01-24 03:01:44.986389: step: 212/469, loss: 0.06705667823553085
2023-01-24 03:01:45.612083: step: 214/469, loss: 0.13999922573566437
2023-01-24 03:01:46.239506: step: 216/469, loss: 0.03609000891447067
2023-01-24 03:01:46.835591: step: 218/469, loss: 0.8149121403694153
2023-01-24 03:01:47.565364: step: 220/469, loss: 0.047628432512283325
2023-01-24 03:01:48.192050: step: 222/469, loss: 0.10824434459209442
2023-01-24 03:01:48.751355: step: 224/469, loss: 0.04613751173019409
2023-01-24 03:01:49.316477: step: 226/469, loss: 0.045456916093826294
2023-01-24 03:01:49.880189: step: 228/469, loss: 0.09128410369157791
2023-01-24 03:01:50.590875: step: 230/469, loss: 0.08247118443250656
2023-01-24 03:01:51.225988: step: 232/469, loss: 0.041743699461221695
2023-01-24 03:01:51.856298: step: 234/469, loss: 0.12287967652082443
2023-01-24 03:01:52.495403: step: 236/469, loss: 0.0729488879442215
2023-01-24 03:01:53.100677: step: 238/469, loss: 0.08309607952833176
2023-01-24 03:01:53.697205: step: 240/469, loss: 0.26476842164993286
2023-01-24 03:01:54.358568: step: 242/469, loss: 0.29417094588279724
2023-01-24 03:01:54.968122: step: 244/469, loss: 0.054838959127664566
2023-01-24 03:01:55.630052: step: 246/469, loss: 0.14131005108356476
2023-01-24 03:01:56.240848: step: 248/469, loss: 0.2602645754814148
2023-01-24 03:01:56.893619: step: 250/469, loss: 0.17374669015407562
2023-01-24 03:01:57.394719: step: 252/469, loss: 0.10324373841285706
2023-01-24 03:01:58.114405: step: 254/469, loss: 0.025312131270766258
2023-01-24 03:01:58.711673: step: 256/469, loss: 0.03437881916761398
2023-01-24 03:01:59.344320: step: 258/469, loss: 0.0893375501036644
2023-01-24 03:01:59.950145: step: 260/469, loss: 0.4117080867290497
2023-01-24 03:02:00.603824: step: 262/469, loss: 0.20586228370666504
2023-01-24 03:02:01.217095: step: 264/469, loss: 0.031112268567085266
2023-01-24 03:02:01.847821: step: 266/469, loss: 0.1244141235947609
2023-01-24 03:02:02.509644: step: 268/469, loss: 7.396092414855957
2023-01-24 03:02:03.291304: step: 270/469, loss: 0.007993660867214203
2023-01-24 03:02:03.992125: step: 272/469, loss: 0.29955166578292847
2023-01-24 03:02:04.607020: step: 274/469, loss: 0.5268498659133911
2023-01-24 03:02:05.234339: step: 276/469, loss: 0.06592971831560135
2023-01-24 03:02:05.803428: step: 278/469, loss: 0.12488150596618652
2023-01-24 03:02:06.487431: step: 280/469, loss: 0.06631255149841309
2023-01-24 03:02:07.174884: step: 282/469, loss: 0.13297708332538605
2023-01-24 03:02:07.870069: step: 284/469, loss: 0.1295710951089859
2023-01-24 03:02:08.534691: step: 286/469, loss: 0.06153430789709091
2023-01-24 03:02:09.120777: step: 288/469, loss: 0.14072281122207642
2023-01-24 03:02:09.729951: step: 290/469, loss: 0.23823054134845734
2023-01-24 03:02:10.400127: step: 292/469, loss: 0.2127118706703186
2023-01-24 03:02:11.071047: step: 294/469, loss: 0.3261911869049072
2023-01-24 03:02:11.727777: step: 296/469, loss: 0.2718924283981323
2023-01-24 03:02:12.447629: step: 298/469, loss: 0.08088023215532303
2023-01-24 03:02:13.116615: step: 300/469, loss: 0.10450479388237
2023-01-24 03:02:13.723957: step: 302/469, loss: 0.04016311839222908
2023-01-24 03:02:14.382135: step: 304/469, loss: 0.2258114218711853
2023-01-24 03:02:15.061249: step: 306/469, loss: 0.1637382060289383
2023-01-24 03:02:15.704250: step: 308/469, loss: 0.07216216623783112
2023-01-24 03:02:16.389182: step: 310/469, loss: 0.07098806649446487
2023-01-24 03:02:17.015178: step: 312/469, loss: 0.009943253360688686
2023-01-24 03:02:17.653933: step: 314/469, loss: 0.03714841231703758
2023-01-24 03:02:18.230090: step: 316/469, loss: 0.3185752034187317
2023-01-24 03:02:18.958474: step: 318/469, loss: 0.11142365634441376
2023-01-24 03:02:19.604491: step: 320/469, loss: 0.1205689013004303
2023-01-24 03:02:20.347214: step: 322/469, loss: 0.04325685650110245
2023-01-24 03:02:21.033588: step: 324/469, loss: 0.09570005536079407
2023-01-24 03:02:21.669460: step: 326/469, loss: 0.5498594045639038
2023-01-24 03:02:22.245490: step: 328/469, loss: 0.07359788566827774
2023-01-24 03:02:22.874126: step: 330/469, loss: 0.049295492470264435
2023-01-24 03:02:23.579200: step: 332/469, loss: 0.04479082301259041
2023-01-24 03:02:24.170446: step: 334/469, loss: 0.11111129075288773
2023-01-24 03:02:24.808493: step: 336/469, loss: 0.16752097010612488
2023-01-24 03:02:25.470082: step: 338/469, loss: 0.1825641393661499
2023-01-24 03:02:26.133667: step: 340/469, loss: 0.0881267786026001
2023-01-24 03:02:26.730920: step: 342/469, loss: 0.10761849582195282
2023-01-24 03:02:27.365655: step: 344/469, loss: 0.1531354784965515
2023-01-24 03:02:27.978669: step: 346/469, loss: 0.03438398614525795
2023-01-24 03:02:28.559928: step: 348/469, loss: 0.02145991101861
2023-01-24 03:02:29.293804: step: 350/469, loss: 0.1290917545557022
2023-01-24 03:02:29.891366: step: 352/469, loss: 0.24007418751716614
2023-01-24 03:02:30.542018: step: 354/469, loss: 0.09991821646690369
2023-01-24 03:02:31.128824: step: 356/469, loss: 0.04672125354409218
2023-01-24 03:02:31.791790: step: 358/469, loss: 0.07012709975242615
2023-01-24 03:02:32.375618: step: 360/469, loss: 0.17604485154151917
2023-01-24 03:02:32.936614: step: 362/469, loss: 0.09747768938541412
2023-01-24 03:02:33.540909: step: 364/469, loss: 0.03829443082213402
2023-01-24 03:02:34.163338: step: 366/469, loss: 0.06037236377596855
2023-01-24 03:02:34.835395: step: 368/469, loss: 0.06923611462116241
2023-01-24 03:02:35.529766: step: 370/469, loss: 0.10725891590118408
2023-01-24 03:02:36.156861: step: 372/469, loss: 0.06752616912126541
2023-01-24 03:02:36.732066: step: 374/469, loss: 0.07115186750888824
2023-01-24 03:02:37.355251: step: 376/469, loss: 0.12045502662658691
2023-01-24 03:02:37.912677: step: 378/469, loss: 0.07575985044240952
2023-01-24 03:02:38.496047: step: 380/469, loss: 0.16566957533359528
2023-01-24 03:02:39.095964: step: 382/469, loss: 0.13173000514507294
2023-01-24 03:02:39.689284: step: 384/469, loss: 0.0986829400062561
2023-01-24 03:02:40.364608: step: 386/469, loss: 0.3410768508911133
2023-01-24 03:02:41.020658: step: 388/469, loss: 0.010278942063450813
2023-01-24 03:02:41.594559: step: 390/469, loss: 0.0442851297557354
2023-01-24 03:02:42.292667: step: 392/469, loss: 0.14880037307739258
2023-01-24 03:02:42.891939: step: 394/469, loss: 0.05399356782436371
2023-01-24 03:02:43.489878: step: 396/469, loss: 0.36965230107307434
2023-01-24 03:02:44.072886: step: 398/469, loss: 0.13781239092350006
2023-01-24 03:02:44.607220: step: 400/469, loss: 0.06432560086250305
2023-01-24 03:02:45.220363: step: 402/469, loss: 0.5758511424064636
2023-01-24 03:02:45.819658: step: 404/469, loss: 0.02899148315191269
2023-01-24 03:02:46.432159: step: 406/469, loss: 0.13911819458007812
2023-01-24 03:02:47.087027: step: 408/469, loss: 0.04071029648184776
2023-01-24 03:02:47.685951: step: 410/469, loss: 0.09789225459098816
2023-01-24 03:02:48.350003: step: 412/469, loss: 0.14823314547538757
2023-01-24 03:02:48.964593: step: 414/469, loss: 0.04966295510530472
2023-01-24 03:02:49.563446: step: 416/469, loss: 0.17922964692115784
2023-01-24 03:02:50.210755: step: 418/469, loss: 0.10353213548660278
2023-01-24 03:02:50.876116: step: 420/469, loss: 0.6564441323280334
2023-01-24 03:02:51.570542: step: 422/469, loss: 0.17564235627651215
2023-01-24 03:02:52.195517: step: 424/469, loss: 0.12924504280090332
2023-01-24 03:02:52.783549: step: 426/469, loss: 0.024177247658371925
2023-01-24 03:02:53.407178: step: 428/469, loss: 0.031831398606300354
2023-01-24 03:02:53.975313: step: 430/469, loss: 0.07344602793455124
2023-01-24 03:02:54.533833: step: 432/469, loss: 1.1346118450164795
2023-01-24 03:02:55.146473: step: 434/469, loss: 0.06825843453407288
2023-01-24 03:02:55.766548: step: 436/469, loss: 0.2813493311405182
2023-01-24 03:02:56.526706: step: 438/469, loss: 0.12063251435756683
2023-01-24 03:02:57.150206: step: 440/469, loss: 0.08347788453102112
2023-01-24 03:02:57.796924: step: 442/469, loss: 0.1416632980108261
2023-01-24 03:02:58.424285: step: 444/469, loss: 0.25256383419036865
2023-01-24 03:02:59.089298: step: 446/469, loss: 0.10278443247079849
2023-01-24 03:02:59.717383: step: 448/469, loss: 0.04323122277855873
2023-01-24 03:03:00.357724: step: 450/469, loss: 0.07204969972372055
2023-01-24 03:03:00.992914: step: 452/469, loss: 0.09187383204698563
2023-01-24 03:03:01.627224: step: 454/469, loss: 0.015891987830400467
2023-01-24 03:03:02.289502: step: 456/469, loss: 0.09873911738395691
2023-01-24 03:03:02.873819: step: 458/469, loss: 0.11525193601846695
2023-01-24 03:03:03.470989: step: 460/469, loss: 0.10839619487524033
2023-01-24 03:03:04.125819: step: 462/469, loss: 0.09071864932775497
2023-01-24 03:03:04.690555: step: 464/469, loss: 0.2341710329055786
2023-01-24 03:03:05.367399: step: 466/469, loss: 0.07345566898584366
2023-01-24 03:03:06.004426: step: 468/469, loss: 0.09756768494844437
2023-01-24 03:03:06.641982: step: 470/469, loss: 0.049766022711992264
2023-01-24 03:03:07.199920: step: 472/469, loss: 0.017392940819263458
2023-01-24 03:03:07.848813: step: 474/469, loss: 0.6033975481987
2023-01-24 03:03:08.504194: step: 476/469, loss: 0.19872227311134338
2023-01-24 03:03:09.146546: step: 478/469, loss: 0.05665751174092293
2023-01-24 03:03:09.832573: step: 480/469, loss: 0.03284783661365509
2023-01-24 03:03:10.400878: step: 482/469, loss: 0.12822693586349487
2023-01-24 03:03:11.017254: step: 484/469, loss: 0.021034792065620422
2023-01-24 03:03:11.675809: step: 486/469, loss: 0.7361587882041931
2023-01-24 03:03:12.242443: step: 488/469, loss: 0.13983362913131714
2023-01-24 03:03:12.874589: step: 490/469, loss: 0.08609239757061005
2023-01-24 03:03:13.475257: step: 492/469, loss: 0.1935974508523941
2023-01-24 03:03:14.057421: step: 494/469, loss: 0.10512497276067734
2023-01-24 03:03:14.683787: step: 496/469, loss: 0.09545408189296722
2023-01-24 03:03:15.343651: step: 498/469, loss: 0.031101834028959274
2023-01-24 03:03:15.928065: step: 500/469, loss: 0.015330853872001171
2023-01-24 03:03:16.617895: step: 502/469, loss: 0.10156291723251343
2023-01-24 03:03:17.248751: step: 504/469, loss: 0.07097966223955154
2023-01-24 03:03:17.860418: step: 506/469, loss: 0.04172803834080696
2023-01-24 03:03:18.444783: step: 508/469, loss: 0.027415333315730095
2023-01-24 03:03:19.015433: step: 510/469, loss: 0.30458492040634155
2023-01-24 03:03:19.651875: step: 512/469, loss: 0.1232391893863678
2023-01-24 03:03:20.177244: step: 514/469, loss: 0.04923182725906372
2023-01-24 03:03:20.780780: step: 516/469, loss: 0.03774645924568176
2023-01-24 03:03:21.445444: step: 518/469, loss: 0.057874489575624466
2023-01-24 03:03:22.125368: step: 520/469, loss: 0.0945911705493927
2023-01-24 03:03:22.739750: step: 522/469, loss: 0.060389697551727295
2023-01-24 03:03:23.413428: step: 524/469, loss: 0.13009800016880035
2023-01-24 03:03:24.055543: step: 526/469, loss: 0.1300317347049713
2023-01-24 03:03:24.692796: step: 528/469, loss: 0.6446691751480103
2023-01-24 03:03:25.310620: step: 530/469, loss: 0.03245815634727478
2023-01-24 03:03:25.925236: step: 532/469, loss: 0.7724708318710327
2023-01-24 03:03:26.546039: step: 534/469, loss: 0.07497677952051163
2023-01-24 03:03:27.148049: step: 536/469, loss: 0.12525536119937897
2023-01-24 03:03:27.744718: step: 538/469, loss: 0.051523033529520035
2023-01-24 03:03:28.349609: step: 540/469, loss: 0.03323983773589134
2023-01-24 03:03:28.929767: step: 542/469, loss: 0.07192233949899673
2023-01-24 03:03:29.547020: step: 544/469, loss: 0.03610096499323845
2023-01-24 03:03:30.234992: step: 546/469, loss: 0.39437055587768555
2023-01-24 03:03:30.882888: step: 548/469, loss: 0.04011363908648491
2023-01-24 03:03:31.521209: step: 550/469, loss: 0.03484440967440605
2023-01-24 03:03:32.137212: step: 552/469, loss: 0.08329173177480698
2023-01-24 03:03:32.783428: step: 554/469, loss: 0.02134370617568493
2023-01-24 03:03:33.364966: step: 556/469, loss: 0.10893407464027405
2023-01-24 03:03:34.042544: step: 558/469, loss: 0.07246120274066925
2023-01-24 03:03:34.614504: step: 560/469, loss: 0.07137060165405273
2023-01-24 03:03:35.212356: step: 562/469, loss: 0.04064168781042099
2023-01-24 03:03:35.929109: step: 564/469, loss: 0.14694608747959137
2023-01-24 03:03:36.534787: step: 566/469, loss: 0.14777693152427673
2023-01-24 03:03:37.175323: step: 568/469, loss: 0.06216861680150032
2023-01-24 03:03:37.781856: step: 570/469, loss: 0.4101116955280304
2023-01-24 03:03:38.353876: step: 572/469, loss: 0.05989619717001915
2023-01-24 03:03:38.989345: step: 574/469, loss: 0.5068990588188171
2023-01-24 03:03:39.620323: step: 576/469, loss: 0.038708191365003586
2023-01-24 03:03:40.312258: step: 578/469, loss: 0.1284210979938507
2023-01-24 03:03:40.968929: step: 580/469, loss: 0.1254810243844986
2023-01-24 03:03:41.659201: step: 582/469, loss: 0.09927408397197723
2023-01-24 03:03:42.355930: step: 584/469, loss: 0.053538136184215546
2023-01-24 03:03:42.960742: step: 586/469, loss: 0.28132787346839905
2023-01-24 03:03:43.565676: step: 588/469, loss: 0.040789805352687836
2023-01-24 03:03:44.237229: step: 590/469, loss: 0.33965402841567993
2023-01-24 03:03:44.875226: step: 592/469, loss: 0.4397242069244385
2023-01-24 03:03:45.508364: step: 594/469, loss: 0.026430943980813026
2023-01-24 03:03:46.136783: step: 596/469, loss: 0.06564439088106155
2023-01-24 03:03:46.786395: step: 598/469, loss: 0.04646633565425873
2023-01-24 03:03:47.432273: step: 600/469, loss: 0.05953690782189369
2023-01-24 03:03:48.013565: step: 602/469, loss: 0.2873972952365875
2023-01-24 03:03:48.705532: step: 604/469, loss: 0.0905509889125824
2023-01-24 03:03:49.328196: step: 606/469, loss: 0.01976645365357399
2023-01-24 03:03:49.897609: step: 608/469, loss: 0.09676215052604675
2023-01-24 03:03:50.595458: step: 610/469, loss: 0.0774192363023758
2023-01-24 03:03:51.189184: step: 612/469, loss: 0.08369574695825577
2023-01-24 03:03:51.848973: step: 614/469, loss: 0.09718339145183563
2023-01-24 03:03:52.516769: step: 616/469, loss: 0.010038639418780804
2023-01-24 03:03:53.128014: step: 618/469, loss: 0.08482632040977478
2023-01-24 03:03:53.746795: step: 620/469, loss: 0.07307785004377365
2023-01-24 03:03:54.364725: step: 622/469, loss: 0.15806318819522858
2023-01-24 03:03:54.948450: step: 624/469, loss: 0.03540217503905296
2023-01-24 03:03:55.557693: step: 626/469, loss: 0.19698740541934967
2023-01-24 03:03:56.100470: step: 628/469, loss: 0.07642629742622375
2023-01-24 03:03:56.748378: step: 630/469, loss: 0.05173496901988983
2023-01-24 03:03:57.391175: step: 632/469, loss: 0.04774576798081398
2023-01-24 03:03:57.976305: step: 634/469, loss: 0.15093399584293365
2023-01-24 03:03:58.643689: step: 636/469, loss: 0.01514753233641386
2023-01-24 03:03:59.316145: step: 638/469, loss: 0.04531419277191162
2023-01-24 03:03:59.968374: step: 640/469, loss: 0.10500968247652054
2023-01-24 03:04:00.667112: step: 642/469, loss: 0.061558909714221954
2023-01-24 03:04:01.373944: step: 644/469, loss: 0.21592919528484344
2023-01-24 03:04:02.093914: step: 646/469, loss: 0.02345101721584797
2023-01-24 03:04:02.756199: step: 648/469, loss: 0.22797884047031403
2023-01-24 03:04:03.442984: step: 650/469, loss: 0.05320119857788086
2023-01-24 03:04:04.070667: step: 652/469, loss: 0.03165804594755173
2023-01-24 03:04:04.731597: step: 654/469, loss: 0.13139890134334564
2023-01-24 03:04:05.422668: step: 656/469, loss: 0.11664785444736481
2023-01-24 03:04:06.043502: step: 658/469, loss: 0.09250274300575256
2023-01-24 03:04:06.767055: step: 660/469, loss: 0.10019751638174057
2023-01-24 03:04:07.402706: step: 662/469, loss: 0.09804801642894745
2023-01-24 03:04:07.957979: step: 664/469, loss: 0.2572440505027771
2023-01-24 03:04:08.633920: step: 666/469, loss: 0.05931685119867325
2023-01-24 03:04:09.353530: step: 668/469, loss: 0.23405978083610535
2023-01-24 03:04:10.003645: step: 670/469, loss: 0.08222799748182297
2023-01-24 03:04:10.603459: step: 672/469, loss: 0.054324980825185776
2023-01-24 03:04:11.236397: step: 674/469, loss: 0.016847794875502586
2023-01-24 03:04:11.820720: step: 676/469, loss: 0.07167066633701324
2023-01-24 03:04:12.440118: step: 678/469, loss: 0.04647509753704071
2023-01-24 03:04:13.076080: step: 680/469, loss: 0.14157341420650482
2023-01-24 03:04:13.696911: step: 682/469, loss: 0.34782132506370544
2023-01-24 03:04:14.333229: step: 684/469, loss: 0.0348874069750309
2023-01-24 03:04:14.946631: step: 686/469, loss: 0.02658282406628132
2023-01-24 03:04:15.645601: step: 688/469, loss: 0.10351291298866272
2023-01-24 03:04:16.289256: step: 690/469, loss: 0.06464104354381561
2023-01-24 03:04:16.920044: step: 692/469, loss: 0.03564321622252464
2023-01-24 03:04:17.544770: step: 694/469, loss: 0.024245334789156914
2023-01-24 03:04:18.132627: step: 696/469, loss: 0.0168426763266325
2023-01-24 03:04:18.825344: step: 698/469, loss: 0.22257305681705475
2023-01-24 03:04:19.438789: step: 700/469, loss: 0.07273201644420624
2023-01-24 03:04:20.056341: step: 702/469, loss: 0.030290089547634125
2023-01-24 03:04:20.594778: step: 704/469, loss: 0.08865196257829666
2023-01-24 03:04:21.208110: step: 706/469, loss: 0.056786973029375076
2023-01-24 03:04:21.773854: step: 708/469, loss: 0.0938844084739685
2023-01-24 03:04:22.418210: step: 710/469, loss: 0.03709043934941292
2023-01-24 03:04:23.114831: step: 712/469, loss: 0.5903059244155884
2023-01-24 03:04:23.799058: step: 714/469, loss: 0.09487691521644592
2023-01-24 03:04:24.422208: step: 716/469, loss: 0.0641891285777092
2023-01-24 03:04:25.034285: step: 718/469, loss: 0.07937748730182648
2023-01-24 03:04:25.640526: step: 720/469, loss: 0.011846196837723255
2023-01-24 03:04:26.284760: step: 722/469, loss: 0.06773900240659714
2023-01-24 03:04:26.884254: step: 724/469, loss: 0.03862158954143524
2023-01-24 03:04:27.465775: step: 726/469, loss: 0.06925870478153229
2023-01-24 03:04:28.072971: step: 728/469, loss: 0.18467117846012115
2023-01-24 03:04:28.699544: step: 730/469, loss: 0.010339128784835339
2023-01-24 03:04:29.302525: step: 732/469, loss: 0.024314304813742638
2023-01-24 03:04:29.907438: step: 734/469, loss: 0.1926196962594986
2023-01-24 03:04:30.541412: step: 736/469, loss: 0.08903618901968002
2023-01-24 03:04:31.270138: step: 738/469, loss: 0.2919049561023712
2023-01-24 03:04:31.912483: step: 740/469, loss: 0.24509607255458832
2023-01-24 03:04:32.540500: step: 742/469, loss: 0.1600656658411026
2023-01-24 03:04:33.179367: step: 744/469, loss: 0.27825015783309937
2023-01-24 03:04:33.766935: step: 746/469, loss: 0.014659815467894077
2023-01-24 03:04:34.364029: step: 748/469, loss: 0.04364389181137085
2023-01-24 03:04:35.042450: step: 750/469, loss: 0.020093008875846863
2023-01-24 03:04:35.648284: step: 752/469, loss: 0.03338088467717171
2023-01-24 03:04:36.247841: step: 754/469, loss: 0.03906276449561119
2023-01-24 03:04:36.879587: step: 756/469, loss: 0.15745244920253754
2023-01-24 03:04:37.609131: step: 758/469, loss: 0.14484204351902008
2023-01-24 03:04:38.253392: step: 760/469, loss: 0.1907242387533188
2023-01-24 03:04:38.891123: step: 762/469, loss: 0.04675031825900078
2023-01-24 03:04:39.515645: step: 764/469, loss: 0.42667675018310547
2023-01-24 03:04:40.151501: step: 766/469, loss: 0.07432986050844193
2023-01-24 03:04:40.837153: step: 768/469, loss: 0.06683173030614853
2023-01-24 03:04:41.441876: step: 770/469, loss: 0.029909415170550346
2023-01-24 03:04:42.068553: step: 772/469, loss: 0.13913476467132568
2023-01-24 03:04:42.682903: step: 774/469, loss: 0.1444622278213501
2023-01-24 03:04:43.355139: step: 776/469, loss: 0.06301633268594742
2023-01-24 03:04:44.022635: step: 778/469, loss: 0.09481874853372574
2023-01-24 03:04:44.651105: step: 780/469, loss: 0.07913465052843094
2023-01-24 03:04:45.298865: step: 782/469, loss: 0.04400838539004326
2023-01-24 03:04:45.919083: step: 784/469, loss: 1.2909154891967773
2023-01-24 03:04:46.515448: step: 786/469, loss: 0.07545351982116699
2023-01-24 03:04:47.150658: step: 788/469, loss: 0.033128563314676285
2023-01-24 03:04:47.765406: step: 790/469, loss: 0.029645385220646858
2023-01-24 03:04:48.372492: step: 792/469, loss: 0.08934933692216873
2023-01-24 03:04:49.039895: step: 794/469, loss: 0.07333355396986008
2023-01-24 03:04:49.690157: step: 796/469, loss: 0.11897078156471252
2023-01-24 03:04:50.390305: step: 798/469, loss: 0.20713704824447632
2023-01-24 03:04:51.018330: step: 800/469, loss: 0.061616744846105576
2023-01-24 03:04:51.638405: step: 802/469, loss: 0.11730055510997772
2023-01-24 03:04:52.300269: step: 804/469, loss: 0.01770954020321369
2023-01-24 03:04:52.898230: step: 806/469, loss: 0.038086600601673126
2023-01-24 03:04:53.535201: step: 808/469, loss: 0.4315366744995117
2023-01-24 03:04:54.146813: step: 810/469, loss: 0.11874110996723175
2023-01-24 03:04:54.750791: step: 812/469, loss: 0.037262242287397385
2023-01-24 03:04:55.414502: step: 814/469, loss: 0.12709051370620728
2023-01-24 03:04:56.017377: step: 816/469, loss: 0.042711228132247925
2023-01-24 03:04:56.694217: step: 818/469, loss: 0.1240357831120491
2023-01-24 03:04:57.319460: step: 820/469, loss: 0.40984612703323364
2023-01-24 03:04:57.924976: step: 822/469, loss: 0.07238990813493729
2023-01-24 03:04:58.573183: step: 824/469, loss: 0.023135146126151085
2023-01-24 03:04:59.198308: step: 826/469, loss: 0.09719256311655045
2023-01-24 03:04:59.791672: step: 828/469, loss: 0.2386380136013031
2023-01-24 03:05:00.440790: step: 830/469, loss: 0.06977793574333191
2023-01-24 03:05:01.073210: step: 832/469, loss: 0.06054136902093887
2023-01-24 03:05:01.714558: step: 834/469, loss: 0.031856805086135864
2023-01-24 03:05:02.328952: step: 836/469, loss: 0.07626467198133469
2023-01-24 03:05:02.941176: step: 838/469, loss: 0.033375199884176254
2023-01-24 03:05:03.600654: step: 840/469, loss: 0.056133005768060684
2023-01-24 03:05:04.212443: step: 842/469, loss: 0.5592582821846008
2023-01-24 03:05:04.915644: step: 844/469, loss: 0.09973210841417313
2023-01-24 03:05:05.562695: step: 846/469, loss: 0.03469455987215042
2023-01-24 03:05:06.187664: step: 848/469, loss: 0.07881100475788116
2023-01-24 03:05:06.794779: step: 850/469, loss: 0.21256226301193237
2023-01-24 03:05:07.397398: step: 852/469, loss: 0.4514442980289459
2023-01-24 03:05:08.021634: step: 854/469, loss: 0.1232815682888031
2023-01-24 03:05:08.636916: step: 856/469, loss: 0.04068541154265404
2023-01-24 03:05:09.348032: step: 858/469, loss: 0.06511027365922928
2023-01-24 03:05:09.992829: step: 860/469, loss: 0.11577273905277252
2023-01-24 03:05:10.584530: step: 862/469, loss: 0.054723381996154785
2023-01-24 03:05:11.177840: step: 864/469, loss: 0.039099425077438354
2023-01-24 03:05:11.775535: step: 866/469, loss: 0.11966274678707123
2023-01-24 03:05:12.362840: step: 868/469, loss: 0.03956418111920357
2023-01-24 03:05:12.947414: step: 870/469, loss: 0.06148413568735123
2023-01-24 03:05:13.609484: step: 872/469, loss: 0.0326245054602623
2023-01-24 03:05:14.185911: step: 874/469, loss: 0.09194914251565933
2023-01-24 03:05:14.851832: step: 876/469, loss: 0.017667468637228012
2023-01-24 03:05:15.492495: step: 878/469, loss: 0.054720357060432434
2023-01-24 03:05:16.134806: step: 880/469, loss: 0.07401636242866516
2023-01-24 03:05:16.661795: step: 882/469, loss: 0.10553588718175888
2023-01-24 03:05:17.225522: step: 884/469, loss: 0.020038213580846786
2023-01-24 03:05:17.885136: step: 886/469, loss: 0.3735326826572418
2023-01-24 03:05:18.525161: step: 888/469, loss: 0.03890379145741463
2023-01-24 03:05:19.128471: step: 890/469, loss: 0.2949785590171814
2023-01-24 03:05:19.750096: step: 892/469, loss: 0.029529161751270294
2023-01-24 03:05:20.306877: step: 894/469, loss: 0.03258060663938522
2023-01-24 03:05:20.943919: step: 896/469, loss: 0.12606225907802582
2023-01-24 03:05:21.585759: step: 898/469, loss: 0.15128742158412933
2023-01-24 03:05:22.203989: step: 900/469, loss: 0.2061641663312912
2023-01-24 03:05:22.897289: step: 902/469, loss: 0.04568546265363693
2023-01-24 03:05:23.556955: step: 904/469, loss: 0.012844710610806942
2023-01-24 03:05:24.186497: step: 906/469, loss: 0.0550975538790226
2023-01-24 03:05:24.805767: step: 908/469, loss: 0.07844427973031998
2023-01-24 03:05:25.382987: step: 910/469, loss: 0.2863953113555908
2023-01-24 03:05:25.991996: step: 912/469, loss: 0.14482593536376953
2023-01-24 03:05:26.552476: step: 914/469, loss: 0.2245837152004242
2023-01-24 03:05:27.234098: step: 916/469, loss: 0.059523265808820724
2023-01-24 03:05:27.922490: step: 918/469, loss: 0.09413760900497437
2023-01-24 03:05:28.546612: step: 920/469, loss: 0.13847032189369202
2023-01-24 03:05:29.172748: step: 922/469, loss: 0.12438680231571198
2023-01-24 03:05:29.838132: step: 924/469, loss: 0.19039230048656464
2023-01-24 03:05:30.470699: step: 926/469, loss: 0.04897954687476158
2023-01-24 03:05:31.148310: step: 928/469, loss: 0.32136696577072144
2023-01-24 03:05:31.730114: step: 930/469, loss: 0.061080172657966614
2023-01-24 03:05:32.374815: step: 932/469, loss: 0.023968001827597618
2023-01-24 03:05:33.044660: step: 934/469, loss: 0.8745543956756592
2023-01-24 03:05:33.704152: step: 936/469, loss: 0.07717323303222656
2023-01-24 03:05:34.303875: step: 938/469, loss: 0.09064988791942596
==================================================
Loss: 0.151
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31347417684545936, 'r': 0.32001728110599076, 'f1': 0.31671193829644534}, 'combined': 0.23336669137632812, 'epoch': 17}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3242741939433116, 'r': 0.2547868666697448, 'f1': 0.2853612906701142}, 'combined': 0.15565161309278955, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32005751738897803, 'r': 0.32430875576036866, 'f1': 0.3221691126969166}, 'combined': 0.2373877672503596, 'epoch': 17}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3288283796603451, 'r': 0.2616775292352014, 'f1': 0.29143484133079034}, 'combined': 0.1589644589077038, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31460540014484883, 'r': 0.31400842595102557, 'f1': 0.31430662958440736}, 'combined': 0.23159435864114225, 'epoch': 17}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3221547641878145, 'r': 0.2575468032380605, 'f1': 0.28625049275924896}, 'combined': 0.15613663241413578, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3223039215686274, 'r': 0.31309523809523804, 'f1': 0.3176328502415458}, 'combined': 0.21175523349436387, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.24074074074074073, 'r': 0.2826086956521739, 'f1': 0.26}, 'combined': 0.13, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4, 'r': 0.13793103448275862, 'f1': 0.20512820512820515}, 'combined': 0.13675213675213677, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:08:20.061205: step: 2/469, loss: 0.19739031791687012
2023-01-24 03:08:20.793999: step: 4/469, loss: 0.10926885902881622
2023-01-24 03:08:21.365975: step: 6/469, loss: 0.040194518864154816
2023-01-24 03:08:21.988698: step: 8/469, loss: 0.07396736741065979
2023-01-24 03:08:22.632979: step: 10/469, loss: 0.03645572066307068
2023-01-24 03:08:23.251844: step: 12/469, loss: 0.031731922179460526
2023-01-24 03:08:23.878320: step: 14/469, loss: 0.05556264519691467
2023-01-24 03:08:24.479472: step: 16/469, loss: 0.013722613453865051
2023-01-24 03:08:25.077878: step: 18/469, loss: 0.07098843902349472
2023-01-24 03:08:25.715455: step: 20/469, loss: 0.04062904417514801
2023-01-24 03:08:26.302962: step: 22/469, loss: 0.09956200420856476
2023-01-24 03:08:26.955287: step: 24/469, loss: 0.01884957030415535
2023-01-24 03:08:27.691467: step: 26/469, loss: 0.06453052163124084
2023-01-24 03:08:28.343705: step: 28/469, loss: 0.1731313169002533
2023-01-24 03:08:28.937113: step: 30/469, loss: 0.07862535119056702
2023-01-24 03:08:29.553964: step: 32/469, loss: 0.4284873902797699
2023-01-24 03:08:30.157398: step: 34/469, loss: 0.0994366854429245
2023-01-24 03:08:30.797582: step: 36/469, loss: 0.06237749755382538
2023-01-24 03:08:31.412428: step: 38/469, loss: 0.795730471611023
2023-01-24 03:08:32.043587: step: 40/469, loss: 0.4500488042831421
2023-01-24 03:08:32.707905: step: 42/469, loss: 0.0233334768563509
2023-01-24 03:08:33.296977: step: 44/469, loss: 0.05385006219148636
2023-01-24 03:08:33.991576: step: 46/469, loss: 0.004826133605092764
2023-01-24 03:08:34.658862: step: 48/469, loss: 0.029154714196920395
2023-01-24 03:08:35.238965: step: 50/469, loss: 0.0385696142911911
2023-01-24 03:08:35.861109: step: 52/469, loss: 0.022908968850970268
2023-01-24 03:08:36.501146: step: 54/469, loss: 0.05257021263241768
2023-01-24 03:08:37.169001: step: 56/469, loss: 0.044094886630773544
2023-01-24 03:08:37.801282: step: 58/469, loss: 0.058982107788324356
2023-01-24 03:08:38.606060: step: 60/469, loss: 0.04889293015003204
2023-01-24 03:08:39.215666: step: 62/469, loss: 0.005112671758979559
2023-01-24 03:08:39.863269: step: 64/469, loss: 0.045796558260917664
2023-01-24 03:08:40.520548: step: 66/469, loss: 0.04271983355283737
2023-01-24 03:08:41.204406: step: 68/469, loss: 0.7052487134933472
2023-01-24 03:08:42.012801: step: 70/469, loss: 0.050847891718149185
2023-01-24 03:08:42.708188: step: 72/469, loss: 0.018044590950012207
2023-01-24 03:08:43.388800: step: 74/469, loss: 0.07699897885322571
2023-01-24 03:08:44.054675: step: 76/469, loss: 0.017341425642371178
2023-01-24 03:08:44.709572: step: 78/469, loss: 0.1727791130542755
2023-01-24 03:08:45.301510: step: 80/469, loss: 0.05113661661744118
2023-01-24 03:08:45.883070: step: 82/469, loss: 0.1645323485136032
2023-01-24 03:08:46.525076: step: 84/469, loss: 0.3509819209575653
2023-01-24 03:08:47.179760: step: 86/469, loss: 0.03935866802930832
2023-01-24 03:08:47.906107: step: 88/469, loss: 0.020971398800611496
2023-01-24 03:08:48.530555: step: 90/469, loss: 0.037076156586408615
2023-01-24 03:08:49.219149: step: 92/469, loss: 0.023122401908040047
2023-01-24 03:08:49.838273: step: 94/469, loss: 0.024980712682008743
2023-01-24 03:08:50.504226: step: 96/469, loss: 0.04867185652256012
2023-01-24 03:08:51.168414: step: 98/469, loss: 0.20667971670627594
2023-01-24 03:08:51.863087: step: 100/469, loss: 0.05252702906727791
2023-01-24 03:08:52.447750: step: 102/469, loss: 0.0459345281124115
2023-01-24 03:08:53.124675: step: 104/469, loss: 0.043612752109766006
2023-01-24 03:08:53.744875: step: 106/469, loss: 1.084824800491333
2023-01-24 03:08:54.361509: step: 108/469, loss: 0.03055424429476261
2023-01-24 03:08:54.949126: step: 110/469, loss: 0.019144048914313316
2023-01-24 03:08:55.539528: step: 112/469, loss: 0.059906549751758575
2023-01-24 03:08:56.159420: step: 114/469, loss: 0.05591762065887451
2023-01-24 03:08:56.767611: step: 116/469, loss: 0.032409392297267914
2023-01-24 03:08:57.412397: step: 118/469, loss: 0.1541178822517395
2023-01-24 03:08:58.013408: step: 120/469, loss: 0.04238314554095268
2023-01-24 03:08:58.647823: step: 122/469, loss: 0.07870107889175415
2023-01-24 03:08:59.264516: step: 124/469, loss: 0.05513609200716019
2023-01-24 03:08:59.861469: step: 126/469, loss: 0.03067687526345253
2023-01-24 03:09:00.486208: step: 128/469, loss: 0.12483498454093933
2023-01-24 03:09:01.129248: step: 130/469, loss: 0.0701747015118599
2023-01-24 03:09:01.663368: step: 132/469, loss: 0.07155679166316986
2023-01-24 03:09:02.335443: step: 134/469, loss: 0.05490366369485855
2023-01-24 03:09:03.002119: step: 136/469, loss: 0.04038708284497261
2023-01-24 03:09:03.616700: step: 138/469, loss: 0.058350540697574615
2023-01-24 03:09:04.187662: step: 140/469, loss: 0.2995723783969879
2023-01-24 03:09:04.856247: step: 142/469, loss: 0.08722950518131256
2023-01-24 03:09:05.453330: step: 144/469, loss: 0.0608787015080452
2023-01-24 03:09:06.106845: step: 146/469, loss: 0.057359132915735245
2023-01-24 03:09:06.818106: step: 148/469, loss: 1.2829951047897339
2023-01-24 03:09:07.391983: step: 150/469, loss: 0.05402109771966934
2023-01-24 03:09:08.092535: step: 152/469, loss: 0.2886006534099579
2023-01-24 03:09:08.667039: step: 154/469, loss: 0.021217528730630875
2023-01-24 03:09:09.266899: step: 156/469, loss: 0.04665805771946907
2023-01-24 03:09:09.934430: step: 158/469, loss: 0.035669777542352676
2023-01-24 03:09:10.576544: step: 160/469, loss: 0.019087495282292366
2023-01-24 03:09:11.247494: step: 162/469, loss: 0.360222190618515
2023-01-24 03:09:11.966328: step: 164/469, loss: 0.051359906792640686
2023-01-24 03:09:12.586576: step: 166/469, loss: 0.14188361167907715
2023-01-24 03:09:13.209618: step: 168/469, loss: 0.03651672601699829
2023-01-24 03:09:13.831899: step: 170/469, loss: 0.17242644727230072
2023-01-24 03:09:14.449196: step: 172/469, loss: 0.07706030458211899
2023-01-24 03:09:15.032501: step: 174/469, loss: 0.03869843855500221
2023-01-24 03:09:15.697141: step: 176/469, loss: 0.07919766008853912
2023-01-24 03:09:16.251624: step: 178/469, loss: 0.013099395669996738
2023-01-24 03:09:16.855198: step: 180/469, loss: 0.04147225618362427
2023-01-24 03:09:17.435713: step: 182/469, loss: 0.011648968793451786
2023-01-24 03:09:18.029497: step: 184/469, loss: 0.027431631460785866
2023-01-24 03:09:18.655195: step: 186/469, loss: 0.021427946165204048
2023-01-24 03:09:19.282764: step: 188/469, loss: 0.023229064419865608
2023-01-24 03:09:19.880756: step: 190/469, loss: 0.09563391655683517
2023-01-24 03:09:20.511933: step: 192/469, loss: 0.10777001082897186
2023-01-24 03:09:21.130087: step: 194/469, loss: 0.007140179164707661
2023-01-24 03:09:21.700881: step: 196/469, loss: 0.057528965175151825
2023-01-24 03:09:22.346571: step: 198/469, loss: 0.04632630944252014
2023-01-24 03:09:23.023828: step: 200/469, loss: 0.06112738698720932
2023-01-24 03:09:23.618165: step: 202/469, loss: 0.05195877328515053
2023-01-24 03:09:24.290202: step: 204/469, loss: 0.11310620605945587
2023-01-24 03:09:24.912954: step: 206/469, loss: 0.05004100129008293
2023-01-24 03:09:25.528367: step: 208/469, loss: 0.026865439489483833
2023-01-24 03:09:26.224782: step: 210/469, loss: 0.2298719733953476
2023-01-24 03:09:26.885257: step: 212/469, loss: 0.02781570330262184
2023-01-24 03:09:27.480785: step: 214/469, loss: 0.06808027625083923
2023-01-24 03:09:28.104448: step: 216/469, loss: 0.0895877555012703
2023-01-24 03:09:28.771962: step: 218/469, loss: 0.028829757124185562
2023-01-24 03:09:29.436541: step: 220/469, loss: 0.12048055231571198
2023-01-24 03:09:30.062619: step: 222/469, loss: 0.040304020047187805
2023-01-24 03:09:30.644003: step: 224/469, loss: 0.08068827539682388
2023-01-24 03:09:31.252461: step: 226/469, loss: 0.019230065867304802
2023-01-24 03:09:31.866667: step: 228/469, loss: 0.04150177910923958
2023-01-24 03:09:32.497227: step: 230/469, loss: 0.014615689404308796
2023-01-24 03:09:33.090738: step: 232/469, loss: 0.11862577497959137
2023-01-24 03:09:33.739093: step: 234/469, loss: 0.04175734892487526
2023-01-24 03:09:34.362378: step: 236/469, loss: 0.057141244411468506
2023-01-24 03:09:34.963209: step: 238/469, loss: 0.14053361117839813
2023-01-24 03:09:35.608546: step: 240/469, loss: 0.129434272646904
2023-01-24 03:09:36.219984: step: 242/469, loss: 0.071467824280262
2023-01-24 03:09:36.825356: step: 244/469, loss: 0.07568236440420151
2023-01-24 03:09:37.423892: step: 246/469, loss: 0.0067124986089766026
2023-01-24 03:09:38.060567: step: 248/469, loss: 0.004839214496314526
2023-01-24 03:09:38.753266: step: 250/469, loss: 0.1291448026895523
2023-01-24 03:09:39.393644: step: 252/469, loss: 0.02901940979063511
2023-01-24 03:09:40.114927: step: 254/469, loss: 0.046936552971601486
2023-01-24 03:09:40.708594: step: 256/469, loss: 0.0028923400677740574
2023-01-24 03:09:41.327636: step: 258/469, loss: 0.30275511741638184
2023-01-24 03:09:41.940452: step: 260/469, loss: 0.017310112714767456
2023-01-24 03:09:42.496919: step: 262/469, loss: 0.06175096333026886
2023-01-24 03:09:43.134649: step: 264/469, loss: 0.056193944066762924
2023-01-24 03:09:43.768574: step: 266/469, loss: 0.04413291811943054
2023-01-24 03:09:44.355824: step: 268/469, loss: 0.045018505305051804
2023-01-24 03:09:44.947503: step: 270/469, loss: 1.209478735923767
2023-01-24 03:09:45.617040: step: 272/469, loss: 0.1236867606639862
2023-01-24 03:09:46.291254: step: 274/469, loss: 0.1417955607175827
2023-01-24 03:09:46.954123: step: 276/469, loss: 0.07055442780256271
2023-01-24 03:09:47.698893: step: 278/469, loss: 0.050440967082977295
2023-01-24 03:09:48.267294: step: 280/469, loss: 0.10773095488548279
2023-01-24 03:09:48.893885: step: 282/469, loss: 0.051065798848867416
2023-01-24 03:09:49.544634: step: 284/469, loss: 0.052638184279203415
2023-01-24 03:09:50.167779: step: 286/469, loss: 0.042986348271369934
2023-01-24 03:09:50.844689: step: 288/469, loss: 0.039752598851919174
2023-01-24 03:09:51.406617: step: 290/469, loss: 0.05830540508031845
2023-01-24 03:09:52.044277: step: 292/469, loss: 0.05978779494762421
2023-01-24 03:09:52.660966: step: 294/469, loss: 0.23868657648563385
2023-01-24 03:09:53.262022: step: 296/469, loss: 0.01042854506522417
2023-01-24 03:09:53.855665: step: 298/469, loss: 0.10877780616283417
2023-01-24 03:09:54.425448: step: 300/469, loss: 0.11008822172880173
2023-01-24 03:09:55.029084: step: 302/469, loss: 0.03987894952297211
2023-01-24 03:09:55.687293: step: 304/469, loss: 0.02829763852059841
2023-01-24 03:09:56.303560: step: 306/469, loss: 0.020535774528980255
2023-01-24 03:09:56.919239: step: 308/469, loss: 0.02137993648648262
2023-01-24 03:09:57.543651: step: 310/469, loss: 0.026447640731930733
2023-01-24 03:09:58.131564: step: 312/469, loss: 0.03280575945973396
2023-01-24 03:09:58.776964: step: 314/469, loss: 0.1060236468911171
2023-01-24 03:09:59.384324: step: 316/469, loss: 0.11234564334154129
2023-01-24 03:10:00.011196: step: 318/469, loss: 0.028679821640253067
2023-01-24 03:10:00.674082: step: 320/469, loss: 0.05580789968371391
2023-01-24 03:10:01.224896: step: 322/469, loss: 0.11312264204025269
2023-01-24 03:10:01.837966: step: 324/469, loss: 0.08738502115011215
2023-01-24 03:10:02.477133: step: 326/469, loss: 0.09100356698036194
2023-01-24 03:10:03.090418: step: 328/469, loss: 0.09819810092449188
2023-01-24 03:10:03.724286: step: 330/469, loss: 0.01844073086977005
2023-01-24 03:10:04.365338: step: 332/469, loss: 0.05894249677658081
2023-01-24 03:10:04.957552: step: 334/469, loss: 0.10026882588863373
2023-01-24 03:10:05.689767: step: 336/469, loss: 0.0325361005961895
2023-01-24 03:10:06.299183: step: 338/469, loss: 0.08915646374225616
2023-01-24 03:10:06.894297: step: 340/469, loss: 0.01552667748183012
2023-01-24 03:10:07.499104: step: 342/469, loss: 0.07285908609628677
2023-01-24 03:10:08.114764: step: 344/469, loss: 0.14017005264759064
2023-01-24 03:10:08.646372: step: 346/469, loss: 0.04775165393948555
2023-01-24 03:10:09.298885: step: 348/469, loss: 0.31016653776168823
2023-01-24 03:10:09.873902: step: 350/469, loss: 0.016111040487885475
2023-01-24 03:10:10.549572: step: 352/469, loss: 0.13392649590969086
2023-01-24 03:10:11.148021: step: 354/469, loss: 0.09390953183174133
2023-01-24 03:10:11.928828: step: 356/469, loss: 0.07702707499265671
2023-01-24 03:10:12.581994: step: 358/469, loss: 0.27382218837738037
2023-01-24 03:10:13.197038: step: 360/469, loss: 0.07126467674970627
2023-01-24 03:10:13.835672: step: 362/469, loss: 0.05109051242470741
2023-01-24 03:10:14.433951: step: 364/469, loss: 0.04137686267495155
2023-01-24 03:10:15.022427: step: 366/469, loss: 0.047433849424123764
2023-01-24 03:10:15.589716: step: 368/469, loss: 0.060302574187517166
2023-01-24 03:10:16.266916: step: 370/469, loss: 0.04694000631570816
2023-01-24 03:10:16.854657: step: 372/469, loss: 0.044354137033224106
2023-01-24 03:10:17.476926: step: 374/469, loss: 0.05950804427266121
2023-01-24 03:10:18.095840: step: 376/469, loss: 0.06666885316371918
2023-01-24 03:10:18.717722: step: 378/469, loss: 0.11413034796714783
2023-01-24 03:10:19.397927: step: 380/469, loss: 0.035895489156246185
2023-01-24 03:10:20.124982: step: 382/469, loss: 0.2797907888889313
2023-01-24 03:10:20.775310: step: 384/469, loss: 0.06916212290525436
2023-01-24 03:10:21.443775: step: 386/469, loss: 0.2177465707063675
2023-01-24 03:10:22.155939: step: 388/469, loss: 0.06521226465702057
2023-01-24 03:10:22.791896: step: 390/469, loss: 0.1160454973578453
2023-01-24 03:10:23.409737: step: 392/469, loss: 0.10225497931241989
2023-01-24 03:10:24.029347: step: 394/469, loss: 0.023697322234511375
2023-01-24 03:10:24.685268: step: 396/469, loss: 0.033800724893808365
2023-01-24 03:10:25.282966: step: 398/469, loss: 0.31401947140693665
2023-01-24 03:10:25.912521: step: 400/469, loss: 0.20775017142295837
2023-01-24 03:10:26.578768: step: 402/469, loss: 0.21333889663219452
2023-01-24 03:10:27.249733: step: 404/469, loss: 0.04311218112707138
2023-01-24 03:10:27.951171: step: 406/469, loss: 0.22380219399929047
2023-01-24 03:10:28.599852: step: 408/469, loss: 0.10484687238931656
2023-01-24 03:10:29.256833: step: 410/469, loss: 0.060690879821777344
2023-01-24 03:10:29.870201: step: 412/469, loss: 0.1567976027727127
2023-01-24 03:10:30.585269: step: 414/469, loss: 0.23510277271270752
2023-01-24 03:10:31.269809: step: 416/469, loss: 0.10009729862213135
2023-01-24 03:10:31.888533: step: 418/469, loss: 0.1717015951871872
2023-01-24 03:10:32.518771: step: 420/469, loss: 0.05372271314263344
2023-01-24 03:10:33.178281: step: 422/469, loss: 0.2950482666492462
2023-01-24 03:10:33.846883: step: 424/469, loss: 0.0671352669596672
2023-01-24 03:10:34.494505: step: 426/469, loss: 0.13671229779720306
2023-01-24 03:10:35.059620: step: 428/469, loss: 0.34977227449417114
2023-01-24 03:10:35.741229: step: 430/469, loss: 0.08556195348501205
2023-01-24 03:10:36.370094: step: 432/469, loss: 0.2947121858596802
2023-01-24 03:10:36.998101: step: 434/469, loss: 0.051985498517751694
2023-01-24 03:10:37.618465: step: 436/469, loss: 0.13081999123096466
2023-01-24 03:10:38.224979: step: 438/469, loss: 0.16685709357261658
2023-01-24 03:10:38.795076: step: 440/469, loss: 0.43547242879867554
2023-01-24 03:10:39.477230: step: 442/469, loss: 0.07016035169363022
2023-01-24 03:10:40.085482: step: 444/469, loss: 0.1425005942583084
2023-01-24 03:10:40.771341: step: 446/469, loss: 0.055922720581293106
2023-01-24 03:10:41.339192: step: 448/469, loss: 0.03692716360092163
2023-01-24 03:10:41.917815: step: 450/469, loss: 0.04559524357318878
2023-01-24 03:10:42.586820: step: 452/469, loss: 0.23842787742614746
2023-01-24 03:10:43.228957: step: 454/469, loss: 0.16788306832313538
2023-01-24 03:10:43.819944: step: 456/469, loss: 0.07471518963575363
2023-01-24 03:10:44.417979: step: 458/469, loss: 0.06382163614034653
2023-01-24 03:10:45.050923: step: 460/469, loss: 0.025148622691631317
2023-01-24 03:10:45.713256: step: 462/469, loss: 0.09097937494516373
2023-01-24 03:10:46.297098: step: 464/469, loss: 0.02212938666343689
2023-01-24 03:10:46.956132: step: 466/469, loss: 0.057925183326005936
2023-01-24 03:10:47.542784: step: 468/469, loss: 0.04108898341655731
2023-01-24 03:10:48.118338: step: 470/469, loss: 0.0179759431630373
2023-01-24 03:10:48.726739: step: 472/469, loss: 0.04561353102326393
2023-01-24 03:10:49.289090: step: 474/469, loss: 0.020289180800318718
2023-01-24 03:10:49.966889: step: 476/469, loss: 0.07113469392061234
2023-01-24 03:10:50.521849: step: 478/469, loss: 0.019822226837277412
2023-01-24 03:10:51.120078: step: 480/469, loss: 0.07940469682216644
2023-01-24 03:10:51.753706: step: 482/469, loss: 0.06818144768476486
2023-01-24 03:10:52.393610: step: 484/469, loss: 0.028329774737358093
2023-01-24 03:10:53.028436: step: 486/469, loss: 0.1307142972946167
2023-01-24 03:10:53.601373: step: 488/469, loss: 0.03568470850586891
2023-01-24 03:10:54.259280: step: 490/469, loss: 0.1567821055650711
2023-01-24 03:10:54.865523: step: 492/469, loss: 0.2452036738395691
2023-01-24 03:10:55.405041: step: 494/469, loss: 0.4887661635875702
2023-01-24 03:10:55.994182: step: 496/469, loss: 0.23095785081386566
2023-01-24 03:10:56.640533: step: 498/469, loss: 0.33275020122528076
2023-01-24 03:10:57.279783: step: 500/469, loss: 0.25882789492607117
2023-01-24 03:10:57.937760: step: 502/469, loss: 0.08737694472074509
2023-01-24 03:10:58.542753: step: 504/469, loss: 0.034016311168670654
2023-01-24 03:10:59.149835: step: 506/469, loss: 0.024603933095932007
2023-01-24 03:10:59.803497: step: 508/469, loss: 0.042490214109420776
2023-01-24 03:11:00.415002: step: 510/469, loss: 0.0801747739315033
2023-01-24 03:11:01.072961: step: 512/469, loss: 0.030629804357886314
2023-01-24 03:11:01.706936: step: 514/469, loss: 0.08940828591585159
2023-01-24 03:11:02.320371: step: 516/469, loss: 0.17327681183815002
2023-01-24 03:11:02.957046: step: 518/469, loss: 0.08095608651638031
2023-01-24 03:11:03.594815: step: 520/469, loss: 0.05163678526878357
2023-01-24 03:11:04.161831: step: 522/469, loss: 0.6049695014953613
2023-01-24 03:11:04.752106: step: 524/469, loss: 0.05464332178235054
2023-01-24 03:11:05.367145: step: 526/469, loss: 0.07438329607248306
2023-01-24 03:11:05.966730: step: 528/469, loss: 0.01273268274962902
2023-01-24 03:11:06.750868: step: 530/469, loss: 0.05413738265633583
2023-01-24 03:11:07.348957: step: 532/469, loss: 0.1312224566936493
2023-01-24 03:11:07.984822: step: 534/469, loss: 0.031502481549978256
2023-01-24 03:11:08.574891: step: 536/469, loss: 0.027119850739836693
2023-01-24 03:11:09.165694: step: 538/469, loss: 0.029854027554392815
2023-01-24 03:11:09.774766: step: 540/469, loss: 0.047307178378105164
2023-01-24 03:11:10.390191: step: 542/469, loss: 0.23962295055389404
2023-01-24 03:11:10.985514: step: 544/469, loss: 0.10581046342849731
2023-01-24 03:11:11.582870: step: 546/469, loss: 0.11889756470918655
2023-01-24 03:11:12.207383: step: 548/469, loss: 0.021439019590616226
2023-01-24 03:11:12.855802: step: 550/469, loss: 0.0780877098441124
2023-01-24 03:11:13.478734: step: 552/469, loss: 0.12498989701271057
2023-01-24 03:11:14.063802: step: 554/469, loss: 0.025048013776540756
2023-01-24 03:11:14.693549: step: 556/469, loss: 0.09084697812795639
2023-01-24 03:11:15.319070: step: 558/469, loss: 0.2633206844329834
2023-01-24 03:11:15.972084: step: 560/469, loss: 0.33507969975471497
2023-01-24 03:11:16.556557: step: 562/469, loss: 0.05256320908665657
2023-01-24 03:11:17.134407: step: 564/469, loss: 0.09941021353006363
2023-01-24 03:11:17.771311: step: 566/469, loss: 1.0583281517028809
2023-01-24 03:11:18.326522: step: 568/469, loss: 0.085181824862957
2023-01-24 03:11:18.918441: step: 570/469, loss: 0.016662290319800377
2023-01-24 03:11:19.556494: step: 572/469, loss: 0.15421420335769653
2023-01-24 03:11:20.122910: step: 574/469, loss: 0.028988031670451164
2023-01-24 03:11:20.747868: step: 576/469, loss: 0.043274663388729095
2023-01-24 03:11:21.349738: step: 578/469, loss: 0.0947754830121994
2023-01-24 03:11:22.018231: step: 580/469, loss: 0.6166610717773438
2023-01-24 03:11:22.652105: step: 582/469, loss: 0.24353112280368805
2023-01-24 03:11:23.236805: step: 584/469, loss: 0.047448042780160904
2023-01-24 03:11:23.845857: step: 586/469, loss: 0.08495884388685226
2023-01-24 03:11:24.458383: step: 588/469, loss: 0.07763383537530899
2023-01-24 03:11:25.015185: step: 590/469, loss: 0.009391697123646736
2023-01-24 03:11:25.621542: step: 592/469, loss: 0.0663059800863266
2023-01-24 03:11:26.313671: step: 594/469, loss: 0.08508490025997162
2023-01-24 03:11:26.951475: step: 596/469, loss: 0.07409289479255676
2023-01-24 03:11:27.581145: step: 598/469, loss: 0.14681270718574524
2023-01-24 03:11:28.202743: step: 600/469, loss: 0.09062065184116364
2023-01-24 03:11:28.879567: step: 602/469, loss: 0.14468273520469666
2023-01-24 03:11:29.563587: step: 604/469, loss: 0.34246498346328735
2023-01-24 03:11:30.215175: step: 606/469, loss: 0.040256209671497345
2023-01-24 03:11:30.895825: step: 608/469, loss: 0.13727182149887085
2023-01-24 03:11:31.457181: step: 610/469, loss: 0.0571071021258831
2023-01-24 03:11:32.065887: step: 612/469, loss: 0.03979555889964104
2023-01-24 03:11:32.690363: step: 614/469, loss: 0.054563213139772415
2023-01-24 03:11:33.285866: step: 616/469, loss: 0.06938362121582031
2023-01-24 03:11:33.919856: step: 618/469, loss: 0.1778077483177185
2023-01-24 03:11:34.530349: step: 620/469, loss: 0.03375286981463432
2023-01-24 03:11:35.159551: step: 622/469, loss: 0.1744992434978485
2023-01-24 03:11:35.733602: step: 624/469, loss: 0.06956393271684647
2023-01-24 03:11:36.321047: step: 626/469, loss: 0.04866023361682892
2023-01-24 03:11:36.923795: step: 628/469, loss: 0.029239829629659653
2023-01-24 03:11:37.561691: step: 630/469, loss: 0.03168150782585144
2023-01-24 03:11:38.145547: step: 632/469, loss: 0.1776774525642395
2023-01-24 03:11:38.767572: step: 634/469, loss: 0.13768786191940308
2023-01-24 03:11:39.356925: step: 636/469, loss: 0.11766307801008224
2023-01-24 03:11:39.992965: step: 638/469, loss: 1.0542603731155396
2023-01-24 03:11:40.657691: step: 640/469, loss: 0.04736362025141716
2023-01-24 03:11:41.235344: step: 642/469, loss: 0.014209137298166752
2023-01-24 03:11:41.780219: step: 644/469, loss: 0.09848280996084213
2023-01-24 03:11:42.402126: step: 646/469, loss: 0.0741153210401535
2023-01-24 03:11:43.110386: step: 648/469, loss: 0.07008747011423111
2023-01-24 03:11:43.694415: step: 650/469, loss: 0.33517831563949585
2023-01-24 03:11:44.321265: step: 652/469, loss: 0.10690117627382278
2023-01-24 03:11:44.916087: step: 654/469, loss: 0.031678080558776855
2023-01-24 03:11:45.576529: step: 656/469, loss: 0.13064999878406525
2023-01-24 03:11:46.186114: step: 658/469, loss: 0.09064306318759918
2023-01-24 03:11:46.817955: step: 660/469, loss: 0.07991311699151993
2023-01-24 03:11:47.438283: step: 662/469, loss: 0.11285699903964996
2023-01-24 03:11:48.126362: step: 664/469, loss: 0.04991097375750542
2023-01-24 03:11:48.722887: step: 666/469, loss: 0.039659518748521805
2023-01-24 03:11:49.413920: step: 668/469, loss: 0.034752923995256424
2023-01-24 03:11:50.032353: step: 670/469, loss: 0.035021405667066574
2023-01-24 03:11:50.634122: step: 672/469, loss: 0.15889544785022736
2023-01-24 03:11:51.268515: step: 674/469, loss: 0.5652160048484802
2023-01-24 03:11:51.890304: step: 676/469, loss: 0.020960049703717232
2023-01-24 03:11:52.454917: step: 678/469, loss: 0.07413636893033981
2023-01-24 03:11:53.108624: step: 680/469, loss: 0.03034192882478237
2023-01-24 03:11:53.760836: step: 682/469, loss: 0.018978828564286232
2023-01-24 03:11:54.397925: step: 684/469, loss: 0.05151795968413353
2023-01-24 03:11:54.941382: step: 686/469, loss: 0.06589885801076889
2023-01-24 03:11:55.553501: step: 688/469, loss: 0.03908786550164223
2023-01-24 03:11:56.257691: step: 690/469, loss: 0.11488750576972961
2023-01-24 03:11:56.902138: step: 692/469, loss: 0.06972968578338623
2023-01-24 03:11:57.538149: step: 694/469, loss: 0.30625277757644653
2023-01-24 03:11:58.143663: step: 696/469, loss: 0.038411471992731094
2023-01-24 03:11:58.888963: step: 698/469, loss: 0.18217110633850098
2023-01-24 03:11:59.529324: step: 700/469, loss: 0.060849037021398544
2023-01-24 03:12:00.229147: step: 702/469, loss: 0.10439438372850418
2023-01-24 03:12:00.867849: step: 704/469, loss: 0.044746894389390945
2023-01-24 03:12:01.540250: step: 706/469, loss: 0.037626005709171295
2023-01-24 03:12:02.094381: step: 708/469, loss: 0.08274061977863312
2023-01-24 03:12:02.707219: step: 710/469, loss: 0.4294675588607788
2023-01-24 03:12:03.401504: step: 712/469, loss: 0.3394537568092346
2023-01-24 03:12:04.037858: step: 714/469, loss: 0.12252811342477798
2023-01-24 03:12:04.646332: step: 716/469, loss: 0.1321982890367508
2023-01-24 03:12:05.261963: step: 718/469, loss: 0.14044569432735443
2023-01-24 03:12:05.869441: step: 720/469, loss: 0.057032596319913864
2023-01-24 03:12:06.466688: step: 722/469, loss: 0.05181776359677315
2023-01-24 03:12:07.094637: step: 724/469, loss: 0.022135816514492035
2023-01-24 03:12:07.871291: step: 726/469, loss: 0.33438247442245483
2023-01-24 03:12:08.629551: step: 728/469, loss: 0.11679305881261826
2023-01-24 03:12:09.294131: step: 730/469, loss: 0.06900320947170258
2023-01-24 03:12:09.950350: step: 732/469, loss: 0.006501945201307535
2023-01-24 03:12:10.594715: step: 734/469, loss: 0.13831335306167603
2023-01-24 03:12:11.318316: step: 736/469, loss: 0.12699875235557556
2023-01-24 03:12:11.919203: step: 738/469, loss: 0.07961904257535934
2023-01-24 03:12:12.530807: step: 740/469, loss: 0.15678110718727112
2023-01-24 03:12:13.173486: step: 742/469, loss: 0.04896744340658188
2023-01-24 03:12:13.709652: step: 744/469, loss: 0.0030765822157263756
2023-01-24 03:12:14.377396: step: 746/469, loss: 0.1713375300168991
2023-01-24 03:12:15.026465: step: 748/469, loss: 0.11107548326253891
2023-01-24 03:12:15.633940: step: 750/469, loss: 0.11765393614768982
2023-01-24 03:12:16.267560: step: 752/469, loss: 1.6821019649505615
2023-01-24 03:12:16.866169: step: 754/469, loss: 0.04893473535776138
2023-01-24 03:12:17.426149: step: 756/469, loss: 0.009994837455451488
2023-01-24 03:12:18.027427: step: 758/469, loss: 0.03376145660877228
2023-01-24 03:12:18.621235: step: 760/469, loss: 0.005881036631762981
2023-01-24 03:12:19.242240: step: 762/469, loss: 0.40421125292778015
2023-01-24 03:12:19.859712: step: 764/469, loss: 0.04221811890602112
2023-01-24 03:12:20.447311: step: 766/469, loss: 0.06776021420955658
2023-01-24 03:12:21.163391: step: 768/469, loss: 0.0718628540635109
2023-01-24 03:12:21.733465: step: 770/469, loss: 0.03564952686429024
2023-01-24 03:12:22.350543: step: 772/469, loss: 0.03369288519024849
2023-01-24 03:12:22.978140: step: 774/469, loss: 0.07828546315431595
2023-01-24 03:12:23.608229: step: 776/469, loss: 8.004802703857422
2023-01-24 03:12:24.257006: step: 778/469, loss: 0.024500887840986252
2023-01-24 03:12:24.890731: step: 780/469, loss: 0.09504243731498718
2023-01-24 03:12:25.487875: step: 782/469, loss: 0.0616409070789814
2023-01-24 03:12:26.111406: step: 784/469, loss: 0.06164541840553284
2023-01-24 03:12:26.743574: step: 786/469, loss: 0.03968252241611481
2023-01-24 03:12:27.313024: step: 788/469, loss: 0.0373171903192997
2023-01-24 03:12:27.942152: step: 790/469, loss: 0.2389187514781952
2023-01-24 03:12:28.512865: step: 792/469, loss: 0.3723146915435791
2023-01-24 03:12:29.158878: step: 794/469, loss: 0.17175130546092987
2023-01-24 03:12:29.860667: step: 796/469, loss: 0.10480652004480362
2023-01-24 03:12:30.476657: step: 798/469, loss: 0.06773378700017929
2023-01-24 03:12:31.049394: step: 800/469, loss: 0.07876768708229065
2023-01-24 03:12:31.764151: step: 802/469, loss: 0.2700870931148529
2023-01-24 03:12:32.424194: step: 804/469, loss: 0.43686532974243164
2023-01-24 03:12:32.982459: step: 806/469, loss: 0.04280206188559532
2023-01-24 03:12:33.658911: step: 808/469, loss: 0.033104076981544495
2023-01-24 03:12:34.279826: step: 810/469, loss: 0.029829207807779312
2023-01-24 03:12:34.869782: step: 812/469, loss: 0.10313430428504944
2023-01-24 03:12:35.530087: step: 814/469, loss: 0.42771920561790466
2023-01-24 03:12:36.121765: step: 816/469, loss: 0.08053378760814667
2023-01-24 03:12:36.786935: step: 818/469, loss: 0.09287554770708084
2023-01-24 03:12:37.358977: step: 820/469, loss: 0.06805162876844406
2023-01-24 03:12:38.039509: step: 822/469, loss: 0.2878781855106354
2023-01-24 03:12:38.667176: step: 824/469, loss: 0.03173014521598816
2023-01-24 03:12:39.325987: step: 826/469, loss: 0.11142918467521667
2023-01-24 03:12:39.928257: step: 828/469, loss: 0.08547961711883545
2023-01-24 03:12:40.574611: step: 830/469, loss: 0.162267804145813
2023-01-24 03:12:41.191816: step: 832/469, loss: 0.028734391555190086
2023-01-24 03:12:41.774791: step: 834/469, loss: 0.06410735845565796
2023-01-24 03:12:42.407954: step: 836/469, loss: 0.05783946439623833
2023-01-24 03:12:43.048955: step: 838/469, loss: 0.03225059434771538
2023-01-24 03:12:43.630012: step: 840/469, loss: 0.025671130046248436
2023-01-24 03:12:44.305837: step: 842/469, loss: 0.10866212099790573
2023-01-24 03:12:44.923449: step: 844/469, loss: 0.025387661531567574
2023-01-24 03:12:45.530937: step: 846/469, loss: 0.03339289501309395
2023-01-24 03:12:46.146276: step: 848/469, loss: 0.08237258344888687
2023-01-24 03:12:46.798642: step: 850/469, loss: 0.17484375834465027
2023-01-24 03:12:47.432647: step: 852/469, loss: 0.4390253722667694
2023-01-24 03:12:48.091300: step: 854/469, loss: 0.022874411195516586
2023-01-24 03:12:48.695789: step: 856/469, loss: 0.009351754561066628
2023-01-24 03:12:49.288904: step: 858/469, loss: 0.057364121079444885
2023-01-24 03:12:49.888449: step: 860/469, loss: 0.0667007640004158
2023-01-24 03:12:50.512244: step: 862/469, loss: 0.0047980910167098045
2023-01-24 03:12:51.155342: step: 864/469, loss: 0.07276533544063568
2023-01-24 03:12:51.709583: step: 866/469, loss: 1.0267325639724731
2023-01-24 03:12:52.264251: step: 868/469, loss: 0.017963893711566925
2023-01-24 03:12:52.891444: step: 870/469, loss: 0.004995882976800203
2023-01-24 03:12:53.441542: step: 872/469, loss: 0.10431088507175446
2023-01-24 03:12:54.093276: step: 874/469, loss: 0.10473817586898804
2023-01-24 03:12:54.680667: step: 876/469, loss: 0.09909619390964508
2023-01-24 03:12:55.321303: step: 878/469, loss: 0.10541045665740967
2023-01-24 03:12:55.944354: step: 880/469, loss: 0.07159728556871414
2023-01-24 03:12:56.621474: step: 882/469, loss: 0.03213709220290184
2023-01-24 03:12:57.308312: step: 884/469, loss: 0.10682906210422516
2023-01-24 03:12:57.995077: step: 886/469, loss: 0.042151015251874924
2023-01-24 03:12:58.583755: step: 888/469, loss: 0.10631813108921051
2023-01-24 03:12:59.195297: step: 890/469, loss: 0.07333306223154068
2023-01-24 03:12:59.840481: step: 892/469, loss: 0.04904847592115402
2023-01-24 03:13:00.434361: step: 894/469, loss: 0.03820941969752312
2023-01-24 03:13:01.082899: step: 896/469, loss: 0.04050300270318985
2023-01-24 03:13:01.741063: step: 898/469, loss: 0.07567108422517776
2023-01-24 03:13:02.430991: step: 900/469, loss: 0.06121153384447098
2023-01-24 03:13:03.040397: step: 902/469, loss: 0.012447827495634556
2023-01-24 03:13:03.777714: step: 904/469, loss: 0.08087782561779022
2023-01-24 03:13:04.387230: step: 906/469, loss: 0.05531115084886551
2023-01-24 03:13:05.010130: step: 908/469, loss: 0.049140430986881256
2023-01-24 03:13:05.681012: step: 910/469, loss: 0.07221703976392746
2023-01-24 03:13:06.314033: step: 912/469, loss: 0.015738114714622498
2023-01-24 03:13:06.930513: step: 914/469, loss: 0.08920235186815262
2023-01-24 03:13:07.526295: step: 916/469, loss: 0.1762600690126419
2023-01-24 03:13:08.132735: step: 918/469, loss: 0.06889771670103073
2023-01-24 03:13:08.757226: step: 920/469, loss: 0.0878787487745285
2023-01-24 03:13:09.389507: step: 922/469, loss: 0.023091405630111694
2023-01-24 03:13:10.051929: step: 924/469, loss: 0.11318391561508179
2023-01-24 03:13:10.757262: step: 926/469, loss: 0.030088823288679123
2023-01-24 03:13:11.388568: step: 928/469, loss: 0.11263003945350647
2023-01-24 03:13:12.040059: step: 930/469, loss: 0.1936572790145874
2023-01-24 03:13:12.642180: step: 932/469, loss: 0.5855045914649963
2023-01-24 03:13:13.283993: step: 934/469, loss: 0.022066129371523857
2023-01-24 03:13:13.937816: step: 936/469, loss: 0.05266191437840462
2023-01-24 03:13:14.642749: step: 938/469, loss: 0.0818169042468071
==================================================
Loss: 0.133
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33652748962655604, 'r': 0.3077917457305503, 'f1': 0.3215188305252726}, 'combined': 0.2369086119659903, 'epoch': 18}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3288173889014824, 'r': 0.26383609338206776, 'f1': 0.2927643147884265}, 'combined': 0.15968962624823263, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35312931142606296, 'r': 0.31426498493135396, 'f1': 0.3325655563430192}, 'combined': 0.24504830467380362, 'epoch': 18}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32742416618861975, 'r': 0.26301776570320967, 'f1': 0.2917081866195922}, 'combined': 0.15911355633795937, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3406550068587106, 'r': 0.31415243516761543, 'f1': 0.32686739058900954}, 'combined': 0.2408496562234807, 'epoch': 18}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31789101578775497, 'r': 0.261758384454693, 'f1': 0.2871067879668635}, 'combined': 0.1566037025273801, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.35493827160493824, 'r': 0.2738095238095238, 'f1': 0.3091397849462365}, 'combined': 0.20609318996415765, 'epoch': 18}
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': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4318181818181818, 'r': 0.16379310344827586, 'f1': 0.23750000000000002}, 'combined': 0.15833333333333333, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:16:01.246918: step: 2/469, loss: 0.018929224461317062
2023-01-24 03:16:01.863308: step: 4/469, loss: 0.07124216854572296
2023-01-24 03:16:02.471753: step: 6/469, loss: 0.012717709876596928
2023-01-24 03:16:03.171333: step: 8/469, loss: 0.2143086940050125
2023-01-24 03:16:03.814935: step: 10/469, loss: 0.13849379122257233
2023-01-24 03:16:04.427679: step: 12/469, loss: 0.6477763652801514
2023-01-24 03:16:05.015502: step: 14/469, loss: 0.017020374536514282
2023-01-24 03:16:05.624037: step: 16/469, loss: 0.012251926586031914
2023-01-24 03:16:06.289267: step: 18/469, loss: 0.19579367339611053
2023-01-24 03:16:06.847408: step: 20/469, loss: 0.028920970857143402
2023-01-24 03:16:07.481480: step: 22/469, loss: 0.027898535132408142
2023-01-24 03:16:08.020490: step: 24/469, loss: 0.6761677265167236
2023-01-24 03:16:08.616546: step: 26/469, loss: 0.047446198761463165
2023-01-24 03:16:09.250018: step: 28/469, loss: 0.05728962644934654
2023-01-24 03:16:09.887734: step: 30/469, loss: 0.078557088971138
2023-01-24 03:16:10.559959: step: 32/469, loss: 0.004781062249094248
2023-01-24 03:16:11.326262: step: 34/469, loss: 0.02646014466881752
2023-01-24 03:16:11.960118: step: 36/469, loss: 0.14936614036560059
2023-01-24 03:16:12.639540: step: 38/469, loss: 0.550441324710846
2023-01-24 03:16:13.351648: step: 40/469, loss: 0.02781039848923683
2023-01-24 03:16:14.034046: step: 42/469, loss: 0.06678663194179535
2023-01-24 03:16:14.654852: step: 44/469, loss: 0.006737399846315384
2023-01-24 03:16:15.295638: step: 46/469, loss: 0.05446932837367058
2023-01-24 03:16:15.879381: step: 48/469, loss: 0.5689120292663574
2023-01-24 03:16:16.555254: step: 50/469, loss: 0.08718938380479813
2023-01-24 03:16:17.197505: step: 52/469, loss: 0.05114837363362312
2023-01-24 03:16:17.786160: step: 54/469, loss: 0.03601820394396782
2023-01-24 03:16:18.384016: step: 56/469, loss: 0.03832560405135155
2023-01-24 03:16:18.935441: step: 58/469, loss: 0.047735635191202164
2023-01-24 03:16:19.530354: step: 60/469, loss: 0.019638512283563614
2023-01-24 03:16:20.203343: step: 62/469, loss: 0.044903937727212906
2023-01-24 03:16:20.770515: step: 64/469, loss: 0.05493366718292236
2023-01-24 03:16:21.404481: step: 66/469, loss: 0.050387073308229446
2023-01-24 03:16:22.076495: step: 68/469, loss: 0.14744219183921814
2023-01-24 03:16:22.735081: step: 70/469, loss: 0.15553677082061768
2023-01-24 03:16:23.350999: step: 72/469, loss: 0.022997574880719185
2023-01-24 03:16:23.995847: step: 74/469, loss: 0.09190671890974045
2023-01-24 03:16:24.635025: step: 76/469, loss: 0.033066220581531525
2023-01-24 03:16:25.250815: step: 78/469, loss: 0.16749121248722076
2023-01-24 03:16:25.875686: step: 80/469, loss: 0.04895635321736336
2023-01-24 03:16:26.424947: step: 82/469, loss: 0.07094690948724747
2023-01-24 03:16:27.125539: step: 84/469, loss: 0.0862123891711235
2023-01-24 03:16:27.773765: step: 86/469, loss: 0.060779884457588196
2023-01-24 03:16:28.435454: step: 88/469, loss: 0.048247966915369034
2023-01-24 03:16:29.075316: step: 90/469, loss: 0.0992327481508255
2023-01-24 03:16:29.657021: step: 92/469, loss: 0.036462124437093735
2023-01-24 03:16:30.362359: step: 94/469, loss: 0.1935470998287201
2023-01-24 03:16:31.002982: step: 96/469, loss: 0.14669057726860046
2023-01-24 03:16:31.629504: step: 98/469, loss: 0.04491839185357094
2023-01-24 03:16:32.216085: step: 100/469, loss: 0.047788821160793304
2023-01-24 03:16:32.855859: step: 102/469, loss: 0.04154706001281738
2023-01-24 03:16:33.477447: step: 104/469, loss: 0.23734036087989807
2023-01-24 03:16:34.134168: step: 106/469, loss: 0.03720643371343613
2023-01-24 03:16:34.814769: step: 108/469, loss: 0.12194491922855377
2023-01-24 03:16:35.405972: step: 110/469, loss: 0.011648233979940414
2023-01-24 03:16:36.051710: step: 112/469, loss: 0.12670712172985077
2023-01-24 03:16:36.660660: step: 114/469, loss: 0.037595465779304504
2023-01-24 03:16:37.306457: step: 116/469, loss: 0.20394590497016907
2023-01-24 03:16:37.952033: step: 118/469, loss: 0.08047802746295929
2023-01-24 03:16:38.589830: step: 120/469, loss: 0.08986532688140869
2023-01-24 03:16:39.233123: step: 122/469, loss: 0.03558919206261635
2023-01-24 03:16:39.899660: step: 124/469, loss: 0.6305689811706543
2023-01-24 03:16:40.470508: step: 126/469, loss: 0.0626261755824089
2023-01-24 03:16:41.112548: step: 128/469, loss: 0.12280867993831635
2023-01-24 03:16:41.689051: step: 130/469, loss: 0.005101164802908897
2023-01-24 03:16:42.284788: step: 132/469, loss: 0.08405684679746628
2023-01-24 03:16:42.951505: step: 134/469, loss: 0.02904880978167057
2023-01-24 03:16:43.587238: step: 136/469, loss: 0.09489244222640991
2023-01-24 03:16:44.184928: step: 138/469, loss: 0.023128828033804893
2023-01-24 03:16:44.806282: step: 140/469, loss: 0.3496091067790985
2023-01-24 03:16:45.532121: step: 142/469, loss: 0.10941021889448166
2023-01-24 03:16:46.123136: step: 144/469, loss: 0.06683848798274994
2023-01-24 03:16:46.751501: step: 146/469, loss: 0.0493616908788681
2023-01-24 03:16:47.352132: step: 148/469, loss: 0.05016420781612396
2023-01-24 03:16:48.007073: step: 150/469, loss: 0.018090449273586273
2023-01-24 03:16:48.787525: step: 152/469, loss: 0.056030020117759705
2023-01-24 03:16:49.406094: step: 154/469, loss: 0.023635540157556534
2023-01-24 03:16:50.041425: step: 156/469, loss: 0.1983170062303543
2023-01-24 03:16:50.627905: step: 158/469, loss: 0.06616871803998947
2023-01-24 03:16:51.221260: step: 160/469, loss: 0.03202993422746658
2023-01-24 03:16:51.909303: step: 162/469, loss: 0.052251845598220825
2023-01-24 03:16:52.503698: step: 164/469, loss: 0.03300376981496811
2023-01-24 03:16:53.118934: step: 166/469, loss: 0.02477295882999897
2023-01-24 03:16:53.712607: step: 168/469, loss: 0.09509236365556717
2023-01-24 03:16:54.325398: step: 170/469, loss: 0.032363831996917725
2023-01-24 03:16:54.874490: step: 172/469, loss: 0.057401143014431
2023-01-24 03:16:55.485231: step: 174/469, loss: 0.06967420876026154
2023-01-24 03:16:56.095488: step: 176/469, loss: 0.044526536017656326
2023-01-24 03:16:56.665930: step: 178/469, loss: 0.033370111137628555
2023-01-24 03:16:57.239994: step: 180/469, loss: 0.12208925187587738
2023-01-24 03:16:57.873430: step: 182/469, loss: 0.02538391202688217
2023-01-24 03:16:58.583660: step: 184/469, loss: 0.13505543768405914
2023-01-24 03:16:59.185397: step: 186/469, loss: 0.03145289421081543
2023-01-24 03:16:59.888828: step: 188/469, loss: 0.044486016035079956
2023-01-24 03:17:00.554890: step: 190/469, loss: 0.0313517265021801
2023-01-24 03:17:01.262003: step: 192/469, loss: 0.06423280388116837
2023-01-24 03:17:01.793466: step: 194/469, loss: 0.01541607454419136
2023-01-24 03:17:02.415782: step: 196/469, loss: 0.05059881880879402
2023-01-24 03:17:03.067743: step: 198/469, loss: 0.12829285860061646
2023-01-24 03:17:03.679891: step: 200/469, loss: 0.05785709246993065
2023-01-24 03:17:04.293277: step: 202/469, loss: 0.12866155803203583
2023-01-24 03:17:04.852108: step: 204/469, loss: 0.04007976874709129
2023-01-24 03:17:05.500736: step: 206/469, loss: 0.06201403960585594
2023-01-24 03:17:06.138017: step: 208/469, loss: 0.1389927864074707
2023-01-24 03:17:06.743430: step: 210/469, loss: 0.03748631477355957
2023-01-24 03:17:07.360003: step: 212/469, loss: 0.024779140949249268
2023-01-24 03:17:07.963111: step: 214/469, loss: 0.052954625338315964
2023-01-24 03:17:08.551462: step: 216/469, loss: 0.01910155639052391
2023-01-24 03:17:09.146719: step: 218/469, loss: 0.011671827174723148
2023-01-24 03:17:09.814223: step: 220/469, loss: 0.09201599657535553
2023-01-24 03:17:10.436046: step: 222/469, loss: 0.06708290427923203
2023-01-24 03:17:11.103600: step: 224/469, loss: 0.04028232395648956
2023-01-24 03:17:11.705393: step: 226/469, loss: 0.003531606635078788
2023-01-24 03:17:12.351547: step: 228/469, loss: 0.1363021582365036
2023-01-24 03:17:13.038536: step: 230/469, loss: 0.05296606943011284
2023-01-24 03:17:13.700879: step: 232/469, loss: 0.02427266724407673
2023-01-24 03:17:14.401477: step: 234/469, loss: 0.03873661160469055
2023-01-24 03:17:15.030881: step: 236/469, loss: 0.05802200734615326
2023-01-24 03:17:15.634449: step: 238/469, loss: 0.20271986722946167
2023-01-24 03:17:16.235406: step: 240/469, loss: 0.01666843146085739
2023-01-24 03:17:16.900575: step: 242/469, loss: 0.169260635972023
2023-01-24 03:17:17.560097: step: 244/469, loss: 0.042294830083847046
2023-01-24 03:17:18.139160: step: 246/469, loss: 0.42812588810920715
2023-01-24 03:17:18.761032: step: 248/469, loss: 0.03527240827679634
2023-01-24 03:17:19.338591: step: 250/469, loss: 0.0908576101064682
2023-01-24 03:17:19.978173: step: 252/469, loss: 0.33815500140190125
2023-01-24 03:17:20.569314: step: 254/469, loss: 0.09581713378429413
2023-01-24 03:17:21.201385: step: 256/469, loss: 0.05028152093291283
2023-01-24 03:17:21.856241: step: 258/469, loss: 0.011085795238614082
2023-01-24 03:17:22.601701: step: 260/469, loss: 0.009318886324763298
2023-01-24 03:17:23.270134: step: 262/469, loss: 0.15508833527565002
2023-01-24 03:17:23.928174: step: 264/469, loss: 0.03315415978431702
2023-01-24 03:17:24.534476: step: 266/469, loss: 0.059173837304115295
2023-01-24 03:17:25.117433: step: 268/469, loss: 0.11708611994981766
2023-01-24 03:17:25.720581: step: 270/469, loss: 0.007663907017558813
2023-01-24 03:17:26.349895: step: 272/469, loss: 0.11967768520116806
2023-01-24 03:17:26.978873: step: 274/469, loss: 0.07220719754695892
2023-01-24 03:17:27.638961: step: 276/469, loss: 0.09503638744354248
2023-01-24 03:17:28.254933: step: 278/469, loss: 0.017050940543413162
2023-01-24 03:17:28.996433: step: 280/469, loss: 0.029534464702010155
2023-01-24 03:17:29.621432: step: 282/469, loss: 0.026098623871803284
2023-01-24 03:17:30.190449: step: 284/469, loss: 0.08735086768865585
2023-01-24 03:17:30.856693: step: 286/469, loss: 0.03122876212000847
2023-01-24 03:17:31.414646: step: 288/469, loss: 0.0493474155664444
2023-01-24 03:17:32.008450: step: 290/469, loss: 0.11733286827802658
2023-01-24 03:17:32.664336: step: 292/469, loss: 0.05277036875486374
2023-01-24 03:17:33.273057: step: 294/469, loss: 0.1768314391374588
2023-01-24 03:17:33.878946: step: 296/469, loss: 0.03973815590143204
2023-01-24 03:17:34.403227: step: 298/469, loss: 0.09797105193138123
2023-01-24 03:17:35.005045: step: 300/469, loss: 0.06105200573801994
2023-01-24 03:17:35.619407: step: 302/469, loss: 0.31381016969680786
2023-01-24 03:17:36.381556: step: 304/469, loss: 0.22844883799552917
2023-01-24 03:17:37.038193: step: 306/469, loss: 0.07330922037363052
2023-01-24 03:17:37.722805: step: 308/469, loss: 0.038831692188978195
2023-01-24 03:17:38.305479: step: 310/469, loss: 0.02562355436384678
2023-01-24 03:17:38.904320: step: 312/469, loss: 0.039489179849624634
2023-01-24 03:17:39.582054: step: 314/469, loss: 0.07543668150901794
2023-01-24 03:17:40.325115: step: 316/469, loss: 0.03310641646385193
2023-01-24 03:17:41.007327: step: 318/469, loss: 0.08928314596414566
2023-01-24 03:17:41.651103: step: 320/469, loss: 0.026486938819289207
2023-01-24 03:17:42.320925: step: 322/469, loss: 0.01166245061904192
2023-01-24 03:17:42.966989: step: 324/469, loss: 0.06775911152362823
2023-01-24 03:17:43.607250: step: 326/469, loss: 0.14716047048568726
2023-01-24 03:17:44.248362: step: 328/469, loss: 0.026105301454663277
2023-01-24 03:17:44.852756: step: 330/469, loss: 0.12618499994277954
2023-01-24 03:17:45.461300: step: 332/469, loss: 0.015240269713103771
2023-01-24 03:17:46.099095: step: 334/469, loss: 0.09497291594743729
2023-01-24 03:17:46.670816: step: 336/469, loss: 0.07686266303062439
2023-01-24 03:17:47.286470: step: 338/469, loss: 0.08008912950754166
2023-01-24 03:17:47.899868: step: 340/469, loss: 0.1150628849864006
2023-01-24 03:17:48.533744: step: 342/469, loss: 0.09120073169469833
2023-01-24 03:17:49.238277: step: 344/469, loss: 0.04809346795082092
2023-01-24 03:17:49.889578: step: 346/469, loss: 0.07628106325864792
2023-01-24 03:17:50.505802: step: 348/469, loss: 0.13730362057685852
2023-01-24 03:17:51.153911: step: 350/469, loss: 0.24316351115703583
2023-01-24 03:17:51.701827: step: 352/469, loss: 0.047220487147569656
2023-01-24 03:17:52.340704: step: 354/469, loss: 0.02312900871038437
2023-01-24 03:17:52.949536: step: 356/469, loss: 0.045622896403074265
2023-01-24 03:17:53.582628: step: 358/469, loss: 0.042554911226034164
2023-01-24 03:17:54.246823: step: 360/469, loss: 0.1307445615530014
2023-01-24 03:17:54.894666: step: 362/469, loss: 0.002914142096415162
2023-01-24 03:17:55.525924: step: 364/469, loss: 0.012220010161399841
2023-01-24 03:17:56.170591: step: 366/469, loss: 0.13123634457588196
2023-01-24 03:17:56.885421: step: 368/469, loss: 0.054937299340963364
2023-01-24 03:17:57.460820: step: 370/469, loss: 0.03938545286655426
2023-01-24 03:17:58.069692: step: 372/469, loss: 0.0792742520570755
2023-01-24 03:17:58.671262: step: 374/469, loss: 0.0925876721739769
2023-01-24 03:17:59.256692: step: 376/469, loss: 0.054532501846551895
2023-01-24 03:17:59.853590: step: 378/469, loss: 0.041149165481328964
2023-01-24 03:18:00.495330: step: 380/469, loss: 0.038725558668375015
2023-01-24 03:18:01.078162: step: 382/469, loss: 0.15061764419078827
2023-01-24 03:18:01.670618: step: 384/469, loss: 0.7279587984085083
2023-01-24 03:18:02.309294: step: 386/469, loss: 0.02412373758852482
2023-01-24 03:18:03.023678: step: 388/469, loss: 0.10511638969182968
2023-01-24 03:18:03.697682: step: 390/469, loss: 0.03942331299185753
2023-01-24 03:18:04.373440: step: 392/469, loss: 0.09832076728343964
2023-01-24 03:18:04.940405: step: 394/469, loss: 0.07461059838533401
2023-01-24 03:18:05.559576: step: 396/469, loss: 0.1348385512828827
2023-01-24 03:18:06.200885: step: 398/469, loss: 0.2990141212940216
2023-01-24 03:18:06.825415: step: 400/469, loss: 0.06430903822183609
2023-01-24 03:18:07.529787: step: 402/469, loss: 0.06335035711526871
2023-01-24 03:18:08.161011: step: 404/469, loss: 0.12693028151988983
2023-01-24 03:18:08.915332: step: 406/469, loss: 0.09448190778493881
2023-01-24 03:18:09.572587: step: 408/469, loss: 0.006209980696439743
2023-01-24 03:18:10.176846: step: 410/469, loss: 0.35782331228256226
2023-01-24 03:18:10.819865: step: 412/469, loss: 0.337869793176651
2023-01-24 03:18:11.382915: step: 414/469, loss: 0.05059871822595596
2023-01-24 03:18:11.983314: step: 416/469, loss: 0.5286617279052734
2023-01-24 03:18:12.566648: step: 418/469, loss: 0.04364926367998123
2023-01-24 03:18:13.182814: step: 420/469, loss: 0.08338271826505661
2023-01-24 03:18:13.798975: step: 422/469, loss: 0.06525425612926483
2023-01-24 03:18:14.556716: step: 424/469, loss: 0.07388177514076233
2023-01-24 03:18:15.168769: step: 426/469, loss: 0.07868321239948273
2023-01-24 03:18:15.741430: step: 428/469, loss: 0.14537185430526733
2023-01-24 03:18:16.374179: step: 430/469, loss: 0.05447091907262802
2023-01-24 03:18:17.033270: step: 432/469, loss: 0.12325700372457504
2023-01-24 03:18:17.703821: step: 434/469, loss: 0.02149268426001072
2023-01-24 03:18:18.394798: step: 436/469, loss: 0.01476992852985859
2023-01-24 03:18:18.993861: step: 438/469, loss: 0.09142114222049713
2023-01-24 03:18:19.630029: step: 440/469, loss: 0.019309429451823235
2023-01-24 03:18:20.210222: step: 442/469, loss: 0.11012211441993713
2023-01-24 03:18:20.838122: step: 444/469, loss: 0.05216379091143608
2023-01-24 03:18:21.594503: step: 446/469, loss: 0.08407919108867645
2023-01-24 03:18:22.281960: step: 448/469, loss: 0.0027140469755977392
2023-01-24 03:18:22.931152: step: 450/469, loss: 0.07924195379018784
2023-01-24 03:18:23.537051: step: 452/469, loss: 0.0822845846414566
2023-01-24 03:18:24.136654: step: 454/469, loss: 0.5457114577293396
2023-01-24 03:18:24.701528: step: 456/469, loss: 0.01041316892951727
2023-01-24 03:18:25.319409: step: 458/469, loss: 0.20511150360107422
2023-01-24 03:18:25.924748: step: 460/469, loss: 0.09668281674385071
2023-01-24 03:18:26.570116: step: 462/469, loss: 0.09260792285203934
2023-01-24 03:18:27.225065: step: 464/469, loss: 0.529384195804596
2023-01-24 03:18:27.767744: step: 466/469, loss: 0.03033657744526863
2023-01-24 03:18:28.418918: step: 468/469, loss: 0.18193933367729187
2023-01-24 03:18:29.005402: step: 470/469, loss: 0.03623465076088905
2023-01-24 03:18:29.593159: step: 472/469, loss: 0.0743374228477478
2023-01-24 03:18:30.158703: step: 474/469, loss: 0.14177709817886353
2023-01-24 03:18:30.864765: step: 476/469, loss: 0.11012189835309982
2023-01-24 03:18:31.510097: step: 478/469, loss: 0.023035774007439613
2023-01-24 03:18:32.227680: step: 480/469, loss: 0.01576581783592701
2023-01-24 03:18:32.857791: step: 482/469, loss: 0.006357547827064991
2023-01-24 03:18:33.480096: step: 484/469, loss: 0.01665729470551014
2023-01-24 03:18:34.055697: step: 486/469, loss: 0.0113474540412426
2023-01-24 03:18:34.701927: step: 488/469, loss: 0.015080654062330723
2023-01-24 03:18:35.265224: step: 490/469, loss: 0.03376530110836029
2023-01-24 03:18:35.947385: step: 492/469, loss: 0.19623930752277374
2023-01-24 03:18:36.541633: step: 494/469, loss: 0.042401209473609924
2023-01-24 03:18:37.139433: step: 496/469, loss: 0.06177276372909546
2023-01-24 03:18:37.791745: step: 498/469, loss: 0.04665808379650116
2023-01-24 03:18:38.445996: step: 500/469, loss: 0.03664287179708481
2023-01-24 03:18:39.128159: step: 502/469, loss: 0.01018795557320118
2023-01-24 03:18:39.697113: step: 504/469, loss: 0.025340456515550613
2023-01-24 03:18:40.347580: step: 506/469, loss: 0.02340005151927471
2023-01-24 03:18:41.036982: step: 508/469, loss: 0.037303630262613297
2023-01-24 03:18:41.649960: step: 510/469, loss: 0.18455928564071655
2023-01-24 03:18:42.304028: step: 512/469, loss: 0.07283520698547363
2023-01-24 03:18:42.895816: step: 514/469, loss: 0.07054881006479263
2023-01-24 03:18:43.488399: step: 516/469, loss: 0.058443740010261536
2023-01-24 03:18:44.065627: step: 518/469, loss: 0.26618072390556335
2023-01-24 03:18:44.668653: step: 520/469, loss: 0.06527213007211685
2023-01-24 03:18:45.289159: step: 522/469, loss: 0.29998257756233215
2023-01-24 03:18:45.830276: step: 524/469, loss: 0.1015496775507927
2023-01-24 03:18:46.506464: step: 526/469, loss: 0.036368899047374725
2023-01-24 03:18:47.165780: step: 528/469, loss: 0.0736686959862709
2023-01-24 03:18:47.782821: step: 530/469, loss: 0.07465191185474396
2023-01-24 03:18:48.424026: step: 532/469, loss: 0.047213707119226456
2023-01-24 03:18:49.029761: step: 534/469, loss: 0.2612151503562927
2023-01-24 03:18:49.606283: step: 536/469, loss: 1.1983392238616943
2023-01-24 03:18:50.224464: step: 538/469, loss: 0.043709646910429
2023-01-24 03:18:50.892015: step: 540/469, loss: 0.035532061010599136
2023-01-24 03:18:51.445852: step: 542/469, loss: 0.08896960318088531
2023-01-24 03:18:52.125646: step: 544/469, loss: 0.07250703871250153
2023-01-24 03:18:52.734665: step: 546/469, loss: 0.10077698528766632
2023-01-24 03:18:53.335434: step: 548/469, loss: 0.07578820735216141
2023-01-24 03:18:53.983887: step: 550/469, loss: 0.04982491955161095
2023-01-24 03:18:54.580228: step: 552/469, loss: 0.15638543665409088
2023-01-24 03:18:55.244498: step: 554/469, loss: 0.1810380220413208
2023-01-24 03:18:55.831620: step: 556/469, loss: 0.08028022944927216
2023-01-24 03:18:56.443099: step: 558/469, loss: 0.09091662615537643
2023-01-24 03:18:57.131915: step: 560/469, loss: 0.3924740254878998
2023-01-24 03:18:57.845438: step: 562/469, loss: 0.04054803401231766
2023-01-24 03:18:58.456887: step: 564/469, loss: 0.06324775516986847
2023-01-24 03:18:59.133480: step: 566/469, loss: 0.012863770127296448
2023-01-24 03:18:59.857604: step: 568/469, loss: 0.008546368218958378
2023-01-24 03:19:00.524039: step: 570/469, loss: 0.24474714696407318
2023-01-24 03:19:01.108649: step: 572/469, loss: 0.06525484472513199
2023-01-24 03:19:01.766912: step: 574/469, loss: 0.12211792916059494
2023-01-24 03:19:02.363607: step: 576/469, loss: 0.07190366089344025
2023-01-24 03:19:03.003061: step: 578/469, loss: 0.05851425230503082
2023-01-24 03:19:03.574218: step: 580/469, loss: 0.04802209883928299
2023-01-24 03:19:04.178220: step: 582/469, loss: 0.35618269443511963
2023-01-24 03:19:04.748431: step: 584/469, loss: 0.12805816531181335
2023-01-24 03:19:05.449576: step: 586/469, loss: 0.05296118184924126
2023-01-24 03:19:06.029523: step: 588/469, loss: 0.032306186854839325
2023-01-24 03:19:06.649708: step: 590/469, loss: 0.09688515961170197
2023-01-24 03:19:07.241135: step: 592/469, loss: 0.2450237274169922
2023-01-24 03:19:07.844419: step: 594/469, loss: 0.07718102633953094
2023-01-24 03:19:08.458490: step: 596/469, loss: 0.029232105240225792
2023-01-24 03:19:09.088509: step: 598/469, loss: 0.15836860239505768
2023-01-24 03:19:09.720168: step: 600/469, loss: 0.038774676620960236
2023-01-24 03:19:10.317799: step: 602/469, loss: 0.045867323875427246
2023-01-24 03:19:10.952606: step: 604/469, loss: 0.09482081979513168
2023-01-24 03:19:11.568683: step: 606/469, loss: 0.05104031786322594
2023-01-24 03:19:12.175066: step: 608/469, loss: 0.19461925327777863
2023-01-24 03:19:12.761183: step: 610/469, loss: 0.03330017998814583
2023-01-24 03:19:13.343136: step: 612/469, loss: 0.049013689160346985
2023-01-24 03:19:13.965064: step: 614/469, loss: 0.03244650363922119
2023-01-24 03:19:14.570554: step: 616/469, loss: 0.15915901958942413
2023-01-24 03:19:15.205342: step: 618/469, loss: 0.09447059780359268
2023-01-24 03:19:15.834954: step: 620/469, loss: 0.039652321487665176
2023-01-24 03:19:16.537790: step: 622/469, loss: 0.02297951653599739
2023-01-24 03:19:17.150222: step: 624/469, loss: 0.07330049574375153
2023-01-24 03:19:17.685119: step: 626/469, loss: 0.06333385407924652
2023-01-24 03:19:18.301577: step: 628/469, loss: 0.02523375116288662
2023-01-24 03:19:18.919690: step: 630/469, loss: 0.13307152688503265
2023-01-24 03:19:19.528546: step: 632/469, loss: 0.03397560864686966
2023-01-24 03:19:20.199235: step: 634/469, loss: 0.144926056265831
2023-01-24 03:19:20.759760: step: 636/469, loss: 0.4149293005466461
2023-01-24 03:19:21.415605: step: 638/469, loss: 0.03584090992808342
2023-01-24 03:19:22.040355: step: 640/469, loss: 0.15646037459373474
2023-01-24 03:19:22.653674: step: 642/469, loss: 0.3996548652648926
2023-01-24 03:19:23.249883: step: 644/469, loss: 0.03151587396860123
2023-01-24 03:19:23.939870: step: 646/469, loss: 0.07914189994335175
2023-01-24 03:19:24.587465: step: 648/469, loss: 0.13150370121002197
2023-01-24 03:19:25.146242: step: 650/469, loss: 0.0494757704436779
2023-01-24 03:19:25.759641: step: 652/469, loss: 0.040536068379879
2023-01-24 03:19:26.400907: step: 654/469, loss: 0.021079814061522484
2023-01-24 03:19:27.006449: step: 656/469, loss: 0.04168560355901718
2023-01-24 03:19:27.663362: step: 658/469, loss: 0.02781490981578827
2023-01-24 03:19:28.388154: step: 660/469, loss: 0.033152054995298386
2023-01-24 03:19:29.073403: step: 662/469, loss: 0.024538125842809677
2023-01-24 03:19:29.677725: step: 664/469, loss: 0.20348501205444336
2023-01-24 03:19:30.281131: step: 666/469, loss: 0.09490671008825302
2023-01-24 03:19:30.879429: step: 668/469, loss: 0.0413602776825428
2023-01-24 03:19:31.526027: step: 670/469, loss: 0.1584605574607849
2023-01-24 03:19:32.191806: step: 672/469, loss: 0.044671401381492615
2023-01-24 03:19:32.810427: step: 674/469, loss: 0.04014156013727188
2023-01-24 03:19:33.465109: step: 676/469, loss: 0.05848986282944679
2023-01-24 03:19:34.072640: step: 678/469, loss: 0.029924491420388222
2023-01-24 03:19:34.735113: step: 680/469, loss: 0.05231635272502899
2023-01-24 03:19:35.325041: step: 682/469, loss: 0.02725483849644661
2023-01-24 03:19:35.916327: step: 684/469, loss: 0.05583032965660095
2023-01-24 03:19:36.562233: step: 686/469, loss: 0.10990659892559052
2023-01-24 03:19:37.213784: step: 688/469, loss: 2.1754565238952637
2023-01-24 03:19:37.870486: step: 690/469, loss: 1.2818113565444946
2023-01-24 03:19:38.462757: step: 692/469, loss: 0.012957548722624779
2023-01-24 03:19:39.070143: step: 694/469, loss: 1.400787115097046
2023-01-24 03:19:39.694127: step: 696/469, loss: 0.26420241594314575
2023-01-24 03:19:40.354805: step: 698/469, loss: 0.04386802390217781
2023-01-24 03:19:40.978787: step: 700/469, loss: 0.12666882574558258
2023-01-24 03:19:41.588160: step: 702/469, loss: 0.029134169220924377
2023-01-24 03:19:42.199244: step: 704/469, loss: 0.052265509963035583
2023-01-24 03:19:42.756119: step: 706/469, loss: 0.06697551161050797
2023-01-24 03:19:43.361566: step: 708/469, loss: 1.072249412536621
2023-01-24 03:19:43.980889: step: 710/469, loss: 0.047012750059366226
2023-01-24 03:19:44.614848: step: 712/469, loss: 0.07216726988554001
2023-01-24 03:19:45.236868: step: 714/469, loss: 0.09166297316551208
2023-01-24 03:19:45.819153: step: 716/469, loss: 0.0377233549952507
2023-01-24 03:19:46.434327: step: 718/469, loss: 0.11211255192756653
2023-01-24 03:19:47.089332: step: 720/469, loss: 0.013600067235529423
2023-01-24 03:19:47.709636: step: 722/469, loss: 0.057414460927248
2023-01-24 03:19:48.335852: step: 724/469, loss: 0.04966941848397255
2023-01-24 03:19:48.947379: step: 726/469, loss: 0.19014638662338257
2023-01-24 03:19:49.517491: step: 728/469, loss: 0.05566960200667381
2023-01-24 03:19:50.131167: step: 730/469, loss: 0.02851691283285618
2023-01-24 03:19:50.825620: step: 732/469, loss: 0.007818255573511124
2023-01-24 03:19:51.534137: step: 734/469, loss: 0.16576926410198212
2023-01-24 03:19:52.147942: step: 736/469, loss: 0.19522695243358612
2023-01-24 03:19:52.842774: step: 738/469, loss: 0.10008224099874496
2023-01-24 03:19:53.392444: step: 740/469, loss: 0.27343299984931946
2023-01-24 03:19:54.011470: step: 742/469, loss: 0.07809916138648987
2023-01-24 03:19:54.614502: step: 744/469, loss: 0.048946261405944824
2023-01-24 03:19:55.275983: step: 746/469, loss: 0.04034539684653282
2023-01-24 03:19:55.939790: step: 748/469, loss: 0.5958285331726074
2023-01-24 03:19:56.515596: step: 750/469, loss: 0.13611815869808197
2023-01-24 03:19:57.194737: step: 752/469, loss: 0.14315664768218994
2023-01-24 03:19:57.805409: step: 754/469, loss: 0.057231444865465164
2023-01-24 03:19:58.437898: step: 756/469, loss: 0.04199300333857536
2023-01-24 03:19:59.050151: step: 758/469, loss: 0.6869280338287354
2023-01-24 03:19:59.686777: step: 760/469, loss: 0.5277479290962219
2023-01-24 03:20:00.330522: step: 762/469, loss: 0.04274006560444832
2023-01-24 03:20:01.016794: step: 764/469, loss: 0.16983969509601593
2023-01-24 03:20:01.693189: step: 766/469, loss: 0.05037027969956398
2023-01-24 03:20:02.374654: step: 768/469, loss: 0.08371130377054214
2023-01-24 03:20:03.005802: step: 770/469, loss: 0.04516316205263138
2023-01-24 03:20:03.622014: step: 772/469, loss: 0.08145400881767273
2023-01-24 03:20:04.269709: step: 774/469, loss: 0.09240426123142242
2023-01-24 03:20:04.910252: step: 776/469, loss: 0.09877298027276993
2023-01-24 03:20:05.533675: step: 778/469, loss: 0.03335174545645714
2023-01-24 03:20:06.223432: step: 780/469, loss: 0.10467829555273056
2023-01-24 03:20:06.879568: step: 782/469, loss: 0.0621492974460125
2023-01-24 03:20:07.548656: step: 784/469, loss: 0.17362046241760254
2023-01-24 03:20:08.183922: step: 786/469, loss: 0.03309227153658867
2023-01-24 03:20:08.846632: step: 788/469, loss: 0.013662155717611313
2023-01-24 03:20:09.497269: step: 790/469, loss: 0.09494443982839584
2023-01-24 03:20:10.080707: step: 792/469, loss: 0.47435706853866577
2023-01-24 03:20:10.693340: step: 794/469, loss: 0.1012163907289505
2023-01-24 03:20:11.361811: step: 796/469, loss: 0.03549069166183472
2023-01-24 03:20:12.018967: step: 798/469, loss: 0.21971246600151062
2023-01-24 03:20:12.606131: step: 800/469, loss: 0.03983674198389053
2023-01-24 03:20:13.194822: step: 802/469, loss: 0.10834245383739471
2023-01-24 03:20:13.859018: step: 804/469, loss: 0.1180226057767868
2023-01-24 03:20:14.458315: step: 806/469, loss: 0.06949001550674438
2023-01-24 03:20:15.105168: step: 808/469, loss: 0.14765363931655884
2023-01-24 03:20:15.713197: step: 810/469, loss: 0.013524406589567661
2023-01-24 03:20:16.443650: step: 812/469, loss: 0.016234934329986572
2023-01-24 03:20:17.066751: step: 814/469, loss: 0.096228688955307
2023-01-24 03:20:17.689348: step: 816/469, loss: 0.05443071573972702
2023-01-24 03:20:18.288224: step: 818/469, loss: 0.0037955818697810173
2023-01-24 03:20:18.858575: step: 820/469, loss: 0.018657274544239044
2023-01-24 03:20:19.500904: step: 822/469, loss: 0.0553579144179821
2023-01-24 03:20:20.063816: step: 824/469, loss: 0.07699181139469147
2023-01-24 03:20:20.699403: step: 826/469, loss: 0.046694591641426086
2023-01-24 03:20:21.416206: step: 828/469, loss: 0.02631101943552494
2023-01-24 03:20:22.099235: step: 830/469, loss: 0.04948659613728523
2023-01-24 03:20:22.748466: step: 832/469, loss: 0.12073986977338791
2023-01-24 03:20:23.352077: step: 834/469, loss: 0.14491772651672363
2023-01-24 03:20:23.971453: step: 836/469, loss: 0.014389042742550373
2023-01-24 03:20:24.571041: step: 838/469, loss: 0.03447839617729187
2023-01-24 03:20:25.144922: step: 840/469, loss: 0.08541145920753479
2023-01-24 03:20:25.762700: step: 842/469, loss: 0.046071138232946396
2023-01-24 03:20:26.444991: step: 844/469, loss: 0.04955539479851723
2023-01-24 03:20:27.017250: step: 846/469, loss: 0.14975903928279877
2023-01-24 03:20:27.703489: step: 848/469, loss: 0.2417968213558197
2023-01-24 03:20:28.324957: step: 850/469, loss: 0.10400690883398056
2023-01-24 03:20:28.952990: step: 852/469, loss: 0.053718503564596176
2023-01-24 03:20:29.582280: step: 854/469, loss: 0.6984888315200806
2023-01-24 03:20:30.210857: step: 856/469, loss: 0.011281779035925865
2023-01-24 03:20:30.819936: step: 858/469, loss: 0.1161065623164177
2023-01-24 03:20:31.459484: step: 860/469, loss: 0.08705775439739227
2023-01-24 03:20:32.102629: step: 862/469, loss: 0.1465783566236496
2023-01-24 03:20:32.758220: step: 864/469, loss: 0.03391014039516449
2023-01-24 03:20:33.328128: step: 866/469, loss: 0.04508693516254425
2023-01-24 03:20:33.942885: step: 868/469, loss: 0.13874170184135437
2023-01-24 03:20:34.493217: step: 870/469, loss: 0.02841523289680481
2023-01-24 03:20:35.138098: step: 872/469, loss: 0.032101888209581375
2023-01-24 03:20:35.782373: step: 874/469, loss: 0.05137887969613075
2023-01-24 03:20:36.442365: step: 876/469, loss: 0.06377363950014114
2023-01-24 03:20:37.094956: step: 878/469, loss: 0.09423363953828812
2023-01-24 03:20:37.711024: step: 880/469, loss: 0.07486584037542343
2023-01-24 03:20:38.246543: step: 882/469, loss: 0.029756108298897743
2023-01-24 03:20:38.877623: step: 884/469, loss: 0.2824748456478119
2023-01-24 03:20:39.492180: step: 886/469, loss: 0.0750042125582695
2023-01-24 03:20:40.087604: step: 888/469, loss: 0.017358288168907166
2023-01-24 03:20:40.708621: step: 890/469, loss: 0.08023647964000702
2023-01-24 03:20:41.327401: step: 892/469, loss: 0.28052639961242676
2023-01-24 03:20:41.947582: step: 894/469, loss: 0.0015651097055524588
2023-01-24 03:20:42.660796: step: 896/469, loss: 0.1067228838801384
2023-01-24 03:20:43.297333: step: 898/469, loss: 0.028684962540864944
2023-01-24 03:20:43.954815: step: 900/469, loss: 0.04417888820171356
2023-01-24 03:20:44.618793: step: 902/469, loss: 0.06779541075229645
2023-01-24 03:20:45.218622: step: 904/469, loss: 0.02422582544386387
2023-01-24 03:20:45.867641: step: 906/469, loss: 0.008805841207504272
2023-01-24 03:20:46.492542: step: 908/469, loss: 0.13440413773059845
2023-01-24 03:20:47.230249: step: 910/469, loss: 0.10930266976356506
2023-01-24 03:20:47.867868: step: 912/469, loss: 0.2258804440498352
2023-01-24 03:20:48.482315: step: 914/469, loss: 0.051467251032590866
2023-01-24 03:20:49.187540: step: 916/469, loss: 0.051162056624889374
2023-01-24 03:20:49.831262: step: 918/469, loss: 0.2344721555709839
2023-01-24 03:20:50.461596: step: 920/469, loss: 0.02741030976176262
2023-01-24 03:20:51.031691: step: 922/469, loss: 0.10001194477081299
2023-01-24 03:20:51.679417: step: 924/469, loss: 0.10465575754642487
2023-01-24 03:20:52.243278: step: 926/469, loss: 0.06605175137519836
2023-01-24 03:20:52.842734: step: 928/469, loss: 0.016095291823148727
2023-01-24 03:20:53.502944: step: 930/469, loss: 0.032779280096292496
2023-01-24 03:20:54.069884: step: 932/469, loss: 0.17856554687023163
2023-01-24 03:20:54.778912: step: 934/469, loss: 0.1468569040298462
2023-01-24 03:20:55.386038: step: 936/469, loss: 0.008212044835090637
2023-01-24 03:20:56.056413: step: 938/469, loss: 0.1104971319437027
==================================================
Loss: 0.112
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33001237623762375, 'r': 0.31623576850094876, 'f1': 0.32297722868217055}, 'combined': 0.23798322113423093, 'epoch': 19}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3388060071606214, 'r': 0.25883167061218565, 'f1': 0.29346785889950094}, 'combined': 0.16007337758154597, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3292617394179894, 'r': 0.3148916824794434, 'f1': 0.32191642418364047}, 'combined': 0.2372015757142614, 'epoch': 19}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33964793413522637, 'r': 0.25729962439521264, 'f1': 0.29279384639663447}, 'combined': 0.15970573439816424, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3258917146513116, 'r': 0.32218137254901963, 'f1': 0.3240259223918575}, 'combined': 0.23875594281505289, 'epoch': 19}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3347396618564706, 'r': 0.25786898013096815, 'f1': 0.29131865145545033}, 'combined': 0.15890108261206382, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3304597701149425, 'r': 0.2738095238095238, 'f1': 0.29947916666666663}, 'combined': 0.19965277777777773, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.32608695652173914, 'r': 0.32608695652173914, 'f1': 0.32608695652173914}, 'combined': 0.16304347826086957, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:23:41.708286: step: 2/469, loss: 0.03047036938369274
2023-01-24 03:23:42.327017: step: 4/469, loss: 0.05100470036268234
2023-01-24 03:23:42.964708: step: 6/469, loss: 0.042807795107364655
2023-01-24 03:23:43.664302: step: 8/469, loss: 0.09654735773801804
2023-01-24 03:23:44.316188: step: 10/469, loss: 0.06212793290615082
2023-01-24 03:23:44.945908: step: 12/469, loss: 0.05861250311136246
2023-01-24 03:23:45.509829: step: 14/469, loss: 0.003254307433962822
2023-01-24 03:23:46.161259: step: 16/469, loss: 0.2485588937997818
2023-01-24 03:23:46.758918: step: 18/469, loss: 0.007442878559231758
2023-01-24 03:23:47.360146: step: 20/469, loss: 0.0058508082292973995
2023-01-24 03:23:47.996218: step: 22/469, loss: 0.06172182410955429
2023-01-24 03:23:48.613534: step: 24/469, loss: 0.008548441343009472
2023-01-24 03:23:49.173124: step: 26/469, loss: 0.016516586765646935
2023-01-24 03:23:49.905600: step: 28/469, loss: 0.22133564949035645
2023-01-24 03:23:50.517637: step: 30/469, loss: 0.04281838238239288
2023-01-24 03:23:51.180063: step: 32/469, loss: 0.03429471328854561
2023-01-24 03:23:51.785426: step: 34/469, loss: 0.1065850630402565
2023-01-24 03:23:52.435829: step: 36/469, loss: 1.7446966171264648
2023-01-24 03:23:53.072118: step: 38/469, loss: 0.026223506778478622
2023-01-24 03:23:53.732809: step: 40/469, loss: 0.02093130722641945
2023-01-24 03:23:54.391600: step: 42/469, loss: 0.10036730021238327
2023-01-24 03:23:54.995412: step: 44/469, loss: 0.10938212275505066
2023-01-24 03:23:55.647017: step: 46/469, loss: 0.10657904297113419
2023-01-24 03:23:56.312725: step: 48/469, loss: 0.038341887295246124
2023-01-24 03:23:56.951185: step: 50/469, loss: 0.07101305574178696
2023-01-24 03:23:57.653668: step: 52/469, loss: 0.056344833225011826
2023-01-24 03:23:58.278647: step: 54/469, loss: 0.10123838484287262
2023-01-24 03:23:58.929049: step: 56/469, loss: 0.08034262806177139
2023-01-24 03:23:59.542931: step: 58/469, loss: 0.21524883806705475
2023-01-24 03:24:00.133857: step: 60/469, loss: 0.044186532497406006
2023-01-24 03:24:00.792968: step: 62/469, loss: 0.13733619451522827
2023-01-24 03:24:01.456119: step: 64/469, loss: 0.367906779050827
2023-01-24 03:24:02.080725: step: 66/469, loss: 0.08909911662340164
2023-01-24 03:24:02.610421: step: 68/469, loss: 0.0975717082619667
2023-01-24 03:24:03.238912: step: 70/469, loss: 0.027646176517009735
2023-01-24 03:24:03.872604: step: 72/469, loss: 0.1450171321630478
2023-01-24 03:24:04.528494: step: 74/469, loss: 0.21010150015354156
2023-01-24 03:24:05.166606: step: 76/469, loss: 0.004874587524682283
2023-01-24 03:24:05.789562: step: 78/469, loss: 0.10334936529397964
2023-01-24 03:24:06.361280: step: 80/469, loss: 0.08851306885480881
2023-01-24 03:24:06.964335: step: 82/469, loss: 0.06980957835912704
2023-01-24 03:24:07.580842: step: 84/469, loss: 0.02645646035671234
2023-01-24 03:24:08.130424: step: 86/469, loss: 0.02716509811580181
2023-01-24 03:24:08.808490: step: 88/469, loss: 0.0896650105714798
2023-01-24 03:24:09.414761: step: 90/469, loss: 0.09851191192865372
2023-01-24 03:24:10.007428: step: 92/469, loss: 0.009893715381622314
2023-01-24 03:24:10.597825: step: 94/469, loss: 0.027347829192876816
2023-01-24 03:24:11.287723: step: 96/469, loss: 0.7567307353019714
2023-01-24 03:24:11.949050: step: 98/469, loss: 0.11436711251735687
2023-01-24 03:24:12.563241: step: 100/469, loss: 0.008082532323896885
2023-01-24 03:24:13.191415: step: 102/469, loss: 0.021137690171599388
2023-01-24 03:24:13.793684: step: 104/469, loss: 0.08700376749038696
2023-01-24 03:24:14.384341: step: 106/469, loss: 0.06389729678630829
2023-01-24 03:24:14.983541: step: 108/469, loss: 0.032811857759952545
2023-01-24 03:24:15.630975: step: 110/469, loss: 0.026620911434292793
2023-01-24 03:24:16.146405: step: 112/469, loss: 0.02649720199406147
2023-01-24 03:24:16.744613: step: 114/469, loss: 0.03372364863753319
2023-01-24 03:24:17.453248: step: 116/469, loss: 0.0719013512134552
2023-01-24 03:24:18.136779: step: 118/469, loss: 0.046262580901384354
2023-01-24 03:24:18.703117: step: 120/469, loss: 0.08907566964626312
2023-01-24 03:24:19.277030: step: 122/469, loss: 0.011383886449038982
2023-01-24 03:24:19.969823: step: 124/469, loss: 0.0537852980196476
2023-01-24 03:24:20.548374: step: 126/469, loss: 0.11244861781597137
2023-01-24 03:24:21.161801: step: 128/469, loss: 0.06547487527132034
2023-01-24 03:24:21.811315: step: 130/469, loss: 0.034582287073135376
2023-01-24 03:24:22.373262: step: 132/469, loss: 0.052909255027770996
2023-01-24 03:24:23.060529: step: 134/469, loss: 0.012787334620952606
2023-01-24 03:24:23.684967: step: 136/469, loss: 0.038171760737895966
2023-01-24 03:24:24.294465: step: 138/469, loss: 0.040770165622234344
2023-01-24 03:24:24.908493: step: 140/469, loss: 0.07857181131839752
2023-01-24 03:24:25.514046: step: 142/469, loss: 0.07648767530918121
2023-01-24 03:24:26.349037: step: 144/469, loss: 0.016063101589679718
2023-01-24 03:24:26.923574: step: 146/469, loss: 0.018572650849819183
2023-01-24 03:24:27.514431: step: 148/469, loss: 0.027876758947968483
2023-01-24 03:24:28.144990: step: 150/469, loss: 0.020173287019133568
2023-01-24 03:24:28.730141: step: 152/469, loss: 0.036739833652973175
2023-01-24 03:24:29.336068: step: 154/469, loss: 0.03203282877802849
2023-01-24 03:24:29.941481: step: 156/469, loss: 0.007034297101199627
2023-01-24 03:24:30.518273: step: 158/469, loss: 0.14537259936332703
2023-01-24 03:24:31.151380: step: 160/469, loss: 0.3501514792442322
2023-01-24 03:24:31.883791: step: 162/469, loss: 0.08837326616048813
2023-01-24 03:24:32.438067: step: 164/469, loss: 0.007120220456272364
2023-01-24 03:24:32.994277: step: 166/469, loss: 0.07574304938316345
2023-01-24 03:24:33.599930: step: 168/469, loss: 0.02238650806248188
2023-01-24 03:24:34.217582: step: 170/469, loss: 0.06542760878801346
2023-01-24 03:24:34.824720: step: 172/469, loss: 0.08846171945333481
2023-01-24 03:24:35.410561: step: 174/469, loss: 0.015145599842071533
2023-01-24 03:24:35.998406: step: 176/469, loss: 0.09192009270191193
2023-01-24 03:24:36.650958: step: 178/469, loss: 0.039436232298612595
2023-01-24 03:24:37.234842: step: 180/469, loss: 0.02832731418311596
2023-01-24 03:24:37.869639: step: 182/469, loss: 0.039854180067777634
2023-01-24 03:24:38.512120: step: 184/469, loss: 0.08265795558691025
2023-01-24 03:24:39.116450: step: 186/469, loss: 0.42919960618019104
2023-01-24 03:24:39.760680: step: 188/469, loss: 0.13242118060588837
2023-01-24 03:24:40.395954: step: 190/469, loss: 0.045264072716236115
2023-01-24 03:24:40.994585: step: 192/469, loss: 0.03616106137633324
2023-01-24 03:24:41.668416: step: 194/469, loss: 0.03622110188007355
2023-01-24 03:24:42.247332: step: 196/469, loss: 0.08620048314332962
2023-01-24 03:24:42.882070: step: 198/469, loss: 0.10974568128585815
2023-01-24 03:24:43.520936: step: 200/469, loss: 0.5377477407455444
2023-01-24 03:24:44.159814: step: 202/469, loss: 0.05585261806845665
2023-01-24 03:24:44.767365: step: 204/469, loss: 0.12974366545677185
2023-01-24 03:24:45.355660: step: 206/469, loss: 0.013405867852270603
2023-01-24 03:24:45.967608: step: 208/469, loss: 0.009080920368432999
2023-01-24 03:24:46.578305: step: 210/469, loss: 0.03891652822494507
2023-01-24 03:24:47.200337: step: 212/469, loss: 0.03136589750647545
2023-01-24 03:24:47.802872: step: 214/469, loss: 0.37084153294563293
2023-01-24 03:24:48.418765: step: 216/469, loss: 0.01203848049044609
2023-01-24 03:24:49.045355: step: 218/469, loss: 0.055246707051992416
2023-01-24 03:24:49.635636: step: 220/469, loss: 0.039372049272060394
2023-01-24 03:24:50.268144: step: 222/469, loss: 0.17466673254966736
2023-01-24 03:24:50.901930: step: 224/469, loss: 0.07062588632106781
2023-01-24 03:24:51.482400: step: 226/469, loss: 0.05622119456529617
2023-01-24 03:24:52.077940: step: 228/469, loss: 0.025270016863942146
2023-01-24 03:24:52.709223: step: 230/469, loss: 0.04417979717254639
2023-01-24 03:24:53.317403: step: 232/469, loss: 0.07498948276042938
2023-01-24 03:24:53.905014: step: 234/469, loss: 0.05173995718359947
2023-01-24 03:24:54.536176: step: 236/469, loss: 0.07530031353235245
2023-01-24 03:24:55.166549: step: 238/469, loss: 0.009907389990985394
2023-01-24 03:24:55.751986: step: 240/469, loss: 0.026475517079234123
2023-01-24 03:24:56.364816: step: 242/469, loss: 0.027065781876444817
2023-01-24 03:24:57.013695: step: 244/469, loss: 0.03740336373448372
2023-01-24 03:24:57.641671: step: 246/469, loss: 0.02053188905119896
2023-01-24 03:24:58.293675: step: 248/469, loss: 0.02678452804684639
2023-01-24 03:24:58.891242: step: 250/469, loss: 0.2260783165693283
2023-01-24 03:24:59.497925: step: 252/469, loss: 0.06816305220127106
2023-01-24 03:25:00.106551: step: 254/469, loss: 0.07353334873914719
2023-01-24 03:25:00.733500: step: 256/469, loss: 0.09397629648447037
2023-01-24 03:25:01.330717: step: 258/469, loss: 0.009656384587287903
2023-01-24 03:25:01.968408: step: 260/469, loss: 0.03368005156517029
2023-01-24 03:25:02.589297: step: 262/469, loss: 0.053902022540569305
2023-01-24 03:25:03.252017: step: 264/469, loss: 0.2720509171485901
2023-01-24 03:25:03.864180: step: 266/469, loss: 0.056828852742910385
2023-01-24 03:25:04.504766: step: 268/469, loss: 0.21532544493675232
2023-01-24 03:25:05.139695: step: 270/469, loss: 0.09514371305704117
2023-01-24 03:25:05.794034: step: 272/469, loss: 0.008572185412049294
2023-01-24 03:25:06.557973: step: 274/469, loss: 0.14297889173030853
2023-01-24 03:25:07.241223: step: 276/469, loss: 0.01746690645813942
2023-01-24 03:25:07.833520: step: 278/469, loss: 0.026987843215465546
2023-01-24 03:25:08.412621: step: 280/469, loss: 0.05808243900537491
2023-01-24 03:25:08.985852: step: 282/469, loss: 0.002617048332467675
2023-01-24 03:25:09.545673: step: 284/469, loss: 0.03153465315699577
2023-01-24 03:25:10.243173: step: 286/469, loss: 0.039475131779909134
2023-01-24 03:25:10.877299: step: 288/469, loss: 0.03739848732948303
2023-01-24 03:25:11.461700: step: 290/469, loss: 0.05013378709554672
2023-01-24 03:25:12.089229: step: 292/469, loss: 0.08018413931131363
2023-01-24 03:25:12.669114: step: 294/469, loss: 0.010611064732074738
2023-01-24 03:25:13.421067: step: 296/469, loss: 0.10344908386468887
2023-01-24 03:25:14.210797: step: 298/469, loss: 0.07918503880500793
2023-01-24 03:25:14.834008: step: 300/469, loss: 0.4584823250770569
2023-01-24 03:25:15.495388: step: 302/469, loss: 0.02735855244100094
2023-01-24 03:25:16.110599: step: 304/469, loss: 0.09685743600130081
2023-01-24 03:25:16.691089: step: 306/469, loss: 0.06576409190893173
2023-01-24 03:25:17.309695: step: 308/469, loss: 0.04262363165616989
2023-01-24 03:25:17.883092: step: 310/469, loss: 0.018736232072114944
2023-01-24 03:25:18.499938: step: 312/469, loss: 0.04727477207779884
2023-01-24 03:25:19.103269: step: 314/469, loss: 0.028145043179392815
2023-01-24 03:25:19.784564: step: 316/469, loss: 0.022955063730478287
2023-01-24 03:25:20.390775: step: 318/469, loss: 0.1341588795185089
2023-01-24 03:25:21.094620: step: 320/469, loss: 0.02380920760333538
2023-01-24 03:25:21.746521: step: 322/469, loss: 0.007822670973837376
2023-01-24 03:25:22.389480: step: 324/469, loss: 0.03533836826682091
2023-01-24 03:25:23.063016: step: 326/469, loss: 0.014371704310178757
2023-01-24 03:25:23.704268: step: 328/469, loss: 0.05644243583083153
2023-01-24 03:25:24.359665: step: 330/469, loss: 0.05656706169247627
2023-01-24 03:25:25.062293: step: 332/469, loss: 0.43775734305381775
2023-01-24 03:25:25.712679: step: 334/469, loss: 0.00509157869964838
2023-01-24 03:25:26.338700: step: 336/469, loss: 0.10166650265455246
2023-01-24 03:25:26.962706: step: 338/469, loss: 0.01550217717885971
2023-01-24 03:25:27.582515: step: 340/469, loss: 0.0271731186658144
2023-01-24 03:25:28.220825: step: 342/469, loss: 0.07601156085729599
2023-01-24 03:25:28.826950: step: 344/469, loss: 0.006699007004499435
2023-01-24 03:25:29.448923: step: 346/469, loss: 0.024352973327040672
2023-01-24 03:25:30.124040: step: 348/469, loss: 0.09689823538064957
2023-01-24 03:25:30.692136: step: 350/469, loss: 0.029600057750940323
2023-01-24 03:25:31.373724: step: 352/469, loss: 0.10261412709951401
2023-01-24 03:25:31.897167: step: 354/469, loss: 0.1763852834701538
2023-01-24 03:25:32.498173: step: 356/469, loss: 0.06254316121339798
2023-01-24 03:25:33.104298: step: 358/469, loss: 3.0973660945892334
2023-01-24 03:25:33.701843: step: 360/469, loss: 0.010241741314530373
2023-01-24 03:25:34.365108: step: 362/469, loss: 0.0581340491771698
2023-01-24 03:25:35.071197: step: 364/469, loss: 0.037835244089365005
2023-01-24 03:25:35.631328: step: 366/469, loss: 0.15622061491012573
2023-01-24 03:25:36.206626: step: 368/469, loss: 0.023382317274808884
2023-01-24 03:25:36.809526: step: 370/469, loss: 0.0449327677488327
2023-01-24 03:25:37.430526: step: 372/469, loss: 0.07265295833349228
2023-01-24 03:25:38.048672: step: 374/469, loss: 0.07179847359657288
2023-01-24 03:25:38.703940: step: 376/469, loss: 0.10519182682037354
2023-01-24 03:25:39.261687: step: 378/469, loss: 0.0063442569226026535
2023-01-24 03:25:39.834865: step: 380/469, loss: 0.027087777853012085
2023-01-24 03:25:40.456385: step: 382/469, loss: 0.0908999815583229
2023-01-24 03:25:41.074484: step: 384/469, loss: 0.017228519544005394
2023-01-24 03:25:41.661380: step: 386/469, loss: 0.13921339809894562
2023-01-24 03:25:42.386190: step: 388/469, loss: 0.04351751506328583
2023-01-24 03:25:42.970543: step: 390/469, loss: 0.06499644368886948
2023-01-24 03:25:43.624990: step: 392/469, loss: 0.6581273674964905
2023-01-24 03:25:44.220106: step: 394/469, loss: 0.043974511325359344
2023-01-24 03:25:44.842313: step: 396/469, loss: 0.15624815225601196
2023-01-24 03:25:45.451808: step: 398/469, loss: 0.0968884751200676
2023-01-24 03:25:46.137411: step: 400/469, loss: 0.08363330364227295
2023-01-24 03:25:46.776065: step: 402/469, loss: 0.13590368628501892
2023-01-24 03:25:47.292867: step: 404/469, loss: 0.04422525316476822
2023-01-24 03:25:47.994257: step: 406/469, loss: 0.023506473749876022
2023-01-24 03:25:48.647454: step: 408/469, loss: 0.04093289375305176
2023-01-24 03:25:49.243179: step: 410/469, loss: 0.008529514074325562
2023-01-24 03:25:49.853093: step: 412/469, loss: 0.11678679287433624
2023-01-24 03:25:50.474601: step: 414/469, loss: 0.07076162099838257
2023-01-24 03:25:51.084756: step: 416/469, loss: 0.04140174388885498
2023-01-24 03:25:51.748174: step: 418/469, loss: 0.14785248041152954
2023-01-24 03:25:52.393300: step: 420/469, loss: 0.05215369164943695
2023-01-24 03:25:52.996018: step: 422/469, loss: 0.04422905296087265
2023-01-24 03:25:53.574459: step: 424/469, loss: 0.010338985361158848
2023-01-24 03:25:54.182823: step: 426/469, loss: 0.0835152268409729
2023-01-24 03:25:54.818282: step: 428/469, loss: 0.053154680877923965
2023-01-24 03:25:55.469075: step: 430/469, loss: 0.025039631873369217
2023-01-24 03:25:56.114868: step: 432/469, loss: 0.05907084420323372
2023-01-24 03:25:56.730997: step: 434/469, loss: 0.05137882009148598
2023-01-24 03:25:57.356814: step: 436/469, loss: 0.010029279626905918
2023-01-24 03:25:58.014934: step: 438/469, loss: 0.09758265316486359
2023-01-24 03:25:58.631265: step: 440/469, loss: 0.012394366785883904
2023-01-24 03:25:59.339364: step: 442/469, loss: 0.24575424194335938
2023-01-24 03:26:00.056885: step: 444/469, loss: 0.02452407404780388
2023-01-24 03:26:00.687235: step: 446/469, loss: 0.07089190185070038
2023-01-24 03:26:01.383464: step: 448/469, loss: 0.07185640931129456
2023-01-24 03:26:01.984532: step: 450/469, loss: 0.0554225891828537
2023-01-24 03:26:02.557253: step: 452/469, loss: 0.01690843142569065
2023-01-24 03:26:03.219712: step: 454/469, loss: 0.05314760282635689
2023-01-24 03:26:03.870624: step: 456/469, loss: 0.11660072207450867
2023-01-24 03:26:04.421972: step: 458/469, loss: 0.03748758137226105
2023-01-24 03:26:05.052349: step: 460/469, loss: 0.012262248434126377
2023-01-24 03:26:05.695961: step: 462/469, loss: 0.013085789978504181
2023-01-24 03:26:06.249470: step: 464/469, loss: 0.017730453982949257
2023-01-24 03:26:06.939394: step: 466/469, loss: 0.1118144616484642
2023-01-24 03:26:07.501872: step: 468/469, loss: 0.06439069658517838
2023-01-24 03:26:08.062934: step: 470/469, loss: 0.021769510582089424
2023-01-24 03:26:08.762444: step: 472/469, loss: 0.04408632591366768
2023-01-24 03:26:09.359092: step: 474/469, loss: 0.0401419959962368
2023-01-24 03:26:09.982216: step: 476/469, loss: 0.12251318991184235
2023-01-24 03:26:10.605569: step: 478/469, loss: 0.015362037345767021
2023-01-24 03:26:11.247951: step: 480/469, loss: 0.34135302901268005
2023-01-24 03:26:11.919390: step: 482/469, loss: 0.44757020473480225
2023-01-24 03:26:12.520036: step: 484/469, loss: 0.005609733052551746
2023-01-24 03:26:13.199213: step: 486/469, loss: 0.2649969458580017
2023-01-24 03:26:13.788678: step: 488/469, loss: 0.12505537271499634
2023-01-24 03:26:14.330467: step: 490/469, loss: 0.029974080622196198
2023-01-24 03:26:14.968777: step: 492/469, loss: 0.03520739823579788
2023-01-24 03:26:15.551520: step: 494/469, loss: 0.017011066898703575
2023-01-24 03:26:16.193838: step: 496/469, loss: 0.16647648811340332
2023-01-24 03:26:16.835924: step: 498/469, loss: 0.030338849872350693
2023-01-24 03:26:17.431241: step: 500/469, loss: 0.04297623038291931
2023-01-24 03:26:18.045140: step: 502/469, loss: 0.07026848942041397
2023-01-24 03:26:18.650702: step: 504/469, loss: 0.06991925090551376
2023-01-24 03:26:19.300349: step: 506/469, loss: 0.03671690821647644
2023-01-24 03:26:19.944019: step: 508/469, loss: 0.0319366492331028
2023-01-24 03:26:20.560380: step: 510/469, loss: 0.02633335255086422
2023-01-24 03:26:21.225411: step: 512/469, loss: 0.0641055777668953
2023-01-24 03:26:21.898844: step: 514/469, loss: 0.034385669976472855
2023-01-24 03:26:22.508660: step: 516/469, loss: 0.21503835916519165
2023-01-24 03:26:23.214824: step: 518/469, loss: 0.04159834608435631
2023-01-24 03:26:23.845579: step: 520/469, loss: 0.06328455358743668
2023-01-24 03:26:24.452739: step: 522/469, loss: 0.12873534858226776
2023-01-24 03:26:25.104795: step: 524/469, loss: 0.07574222981929779
2023-01-24 03:26:25.715639: step: 526/469, loss: 0.30191078782081604
2023-01-24 03:26:26.327865: step: 528/469, loss: 0.010558957234025002
2023-01-24 03:26:27.027098: step: 530/469, loss: 0.01265162043273449
2023-01-24 03:26:27.642250: step: 532/469, loss: 0.25568991899490356
2023-01-24 03:26:28.235427: step: 534/469, loss: 0.01884031482040882
2023-01-24 03:26:28.846452: step: 536/469, loss: 0.068267323076725
2023-01-24 03:26:29.514280: step: 538/469, loss: 0.43168628215789795
2023-01-24 03:26:30.158999: step: 540/469, loss: 0.041933536529541016
2023-01-24 03:26:30.785548: step: 542/469, loss: 0.01796361431479454
2023-01-24 03:26:31.368164: step: 544/469, loss: 0.06711485981941223
2023-01-24 03:26:32.046735: step: 546/469, loss: 0.18310546875
2023-01-24 03:26:32.620852: step: 548/469, loss: 0.03469279408454895
2023-01-24 03:26:33.308556: step: 550/469, loss: 0.25317585468292236
2023-01-24 03:26:33.954701: step: 552/469, loss: 0.08416194468736649
2023-01-24 03:26:34.598720: step: 554/469, loss: 0.10092373937368393
2023-01-24 03:26:35.201394: step: 556/469, loss: 0.022695761173963547
2023-01-24 03:26:35.771323: step: 558/469, loss: 0.018745919689536095
2023-01-24 03:26:36.416926: step: 560/469, loss: 0.04302777349948883
2023-01-24 03:26:37.033010: step: 562/469, loss: 0.036813780665397644
2023-01-24 03:26:37.665156: step: 564/469, loss: 0.21906541287899017
2023-01-24 03:26:38.269163: step: 566/469, loss: 0.02576979622244835
2023-01-24 03:26:38.877151: step: 568/469, loss: 0.04847199097275734
2023-01-24 03:26:39.540714: step: 570/469, loss: 0.21244098246097565
2023-01-24 03:26:40.191232: step: 572/469, loss: 0.018672136589884758
2023-01-24 03:26:40.842421: step: 574/469, loss: 0.07828520238399506
2023-01-24 03:26:41.486740: step: 576/469, loss: 0.024596504867076874
2023-01-24 03:26:42.130087: step: 578/469, loss: 0.02514028549194336
2023-01-24 03:26:42.749630: step: 580/469, loss: 0.10482020676136017
2023-01-24 03:26:43.391170: step: 582/469, loss: 0.04049116373062134
2023-01-24 03:26:43.977974: step: 584/469, loss: 0.01845908910036087
2023-01-24 03:26:44.650164: step: 586/469, loss: 0.06948646157979965
2023-01-24 03:26:45.353997: step: 588/469, loss: 0.1130063384771347
2023-01-24 03:26:45.942366: step: 590/469, loss: 0.030685599893331528
2023-01-24 03:26:46.562499: step: 592/469, loss: 0.03612568974494934
2023-01-24 03:26:47.176805: step: 594/469, loss: 0.03292441368103027
2023-01-24 03:26:47.844392: step: 596/469, loss: 0.026473393663764
2023-01-24 03:26:48.481357: step: 598/469, loss: 0.007028055377304554
2023-01-24 03:26:49.080888: step: 600/469, loss: 0.09396176040172577
2023-01-24 03:26:49.730240: step: 602/469, loss: 0.009699969552457333
2023-01-24 03:26:50.364939: step: 604/469, loss: 0.06945517659187317
2023-01-24 03:26:50.935806: step: 606/469, loss: 0.04944532737135887
2023-01-24 03:26:51.582913: step: 608/469, loss: 0.02853280119597912
2023-01-24 03:26:52.277095: step: 610/469, loss: 0.05194087699055672
2023-01-24 03:26:52.936008: step: 612/469, loss: 0.01059517078101635
2023-01-24 03:26:53.518373: step: 614/469, loss: 0.028247060254216194
2023-01-24 03:26:54.109673: step: 616/469, loss: 0.08249138295650482
2023-01-24 03:26:54.738086: step: 618/469, loss: 0.11553860455751419
2023-01-24 03:26:55.395040: step: 620/469, loss: 1.2491940259933472
2023-01-24 03:26:56.122992: step: 622/469, loss: 0.044590745121240616
2023-01-24 03:26:56.769329: step: 624/469, loss: 0.03426634520292282
2023-01-24 03:26:57.539916: step: 626/469, loss: 0.14192095398902893
2023-01-24 03:26:58.161209: step: 628/469, loss: 0.08071822673082352
2023-01-24 03:26:58.745127: step: 630/469, loss: 0.08231334388256073
2023-01-24 03:26:59.338949: step: 632/469, loss: 0.10219614207744598
2023-01-24 03:26:59.968060: step: 634/469, loss: 0.040496576577425
2023-01-24 03:27:00.610254: step: 636/469, loss: 0.11740805953741074
2023-01-24 03:27:01.235208: step: 638/469, loss: 0.4533992111682892
2023-01-24 03:27:01.830934: step: 640/469, loss: 0.012210090644657612
2023-01-24 03:27:02.478644: step: 642/469, loss: 0.09341727197170258
2023-01-24 03:27:03.137284: step: 644/469, loss: 0.11014952510595322
2023-01-24 03:27:03.723105: step: 646/469, loss: 0.06683366745710373
2023-01-24 03:27:04.356722: step: 648/469, loss: 0.05329553037881851
2023-01-24 03:27:04.994016: step: 650/469, loss: 0.00910886935889721
2023-01-24 03:27:05.615424: step: 652/469, loss: 0.11005696654319763
2023-01-24 03:27:06.249642: step: 654/469, loss: 0.029744772240519524
2023-01-24 03:27:06.915600: step: 656/469, loss: 0.2145126760005951
2023-01-24 03:27:07.583256: step: 658/469, loss: 0.09931598603725433
2023-01-24 03:27:08.116406: step: 660/469, loss: 0.020429594442248344
2023-01-24 03:27:08.711875: step: 662/469, loss: 0.016593294218182564
2023-01-24 03:27:09.321418: step: 664/469, loss: 0.04810403287410736
2023-01-24 03:27:09.956521: step: 666/469, loss: 0.05423254147171974
2023-01-24 03:27:10.550210: step: 668/469, loss: 0.06478362530469894
2023-01-24 03:27:11.104833: step: 670/469, loss: 0.3711676299571991
2023-01-24 03:27:11.817997: step: 672/469, loss: 0.07412133365869522
2023-01-24 03:27:12.520865: step: 674/469, loss: 1.1227519512176514
2023-01-24 03:27:13.183993: step: 676/469, loss: 0.04790123179554939
2023-01-24 03:27:13.766330: step: 678/469, loss: 0.5525271892547607
2023-01-24 03:27:14.349457: step: 680/469, loss: 0.02655475027859211
2023-01-24 03:27:15.065860: step: 682/469, loss: 0.13081642985343933
2023-01-24 03:27:15.617439: step: 684/469, loss: 0.005491634830832481
2023-01-24 03:27:16.282005: step: 686/469, loss: 0.01846947707235813
2023-01-24 03:27:16.901943: step: 688/469, loss: 0.08562768995761871
2023-01-24 03:27:17.490289: step: 690/469, loss: 0.05332883074879646
2023-01-24 03:27:18.140920: step: 692/469, loss: 0.016642436385154724
2023-01-24 03:27:18.755178: step: 694/469, loss: 0.04887961596250534
2023-01-24 03:27:19.384404: step: 696/469, loss: 0.09840194880962372
2023-01-24 03:27:20.012114: step: 698/469, loss: 0.07446332275867462
2023-01-24 03:27:20.653295: step: 700/469, loss: 0.044743407517671585
2023-01-24 03:27:21.246415: step: 702/469, loss: 0.03826627880334854
2023-01-24 03:27:21.863082: step: 704/469, loss: 0.15556564927101135
2023-01-24 03:27:22.479234: step: 706/469, loss: 0.16377954185009003
2023-01-24 03:27:23.110511: step: 708/469, loss: 0.061064738780260086
2023-01-24 03:27:23.744880: step: 710/469, loss: 0.1336861401796341
2023-01-24 03:27:24.359871: step: 712/469, loss: 0.10853223502635956
2023-01-24 03:27:25.007004: step: 714/469, loss: 0.03462926298379898
2023-01-24 03:27:25.606057: step: 716/469, loss: 0.0771002247929573
2023-01-24 03:27:26.256675: step: 718/469, loss: 0.03590358421206474
2023-01-24 03:27:26.880225: step: 720/469, loss: 0.012811330147087574
2023-01-24 03:27:27.482819: step: 722/469, loss: 0.24002225697040558
2023-01-24 03:27:28.138169: step: 724/469, loss: 0.08062081784009933
2023-01-24 03:27:28.765399: step: 726/469, loss: 0.06410007178783417
2023-01-24 03:27:29.466188: step: 728/469, loss: 0.09805223345756531
2023-01-24 03:27:30.216257: step: 730/469, loss: 0.02737535536289215
2023-01-24 03:27:30.822654: step: 732/469, loss: 0.07163655757904053
2023-01-24 03:27:31.592631: step: 734/469, loss: 0.02471967041492462
2023-01-24 03:27:32.201767: step: 736/469, loss: 0.32227209210395813
2023-01-24 03:27:32.818274: step: 738/469, loss: 0.9016312956809998
2023-01-24 03:27:33.484309: step: 740/469, loss: 0.05750349536538124
2023-01-24 03:27:34.138878: step: 742/469, loss: 0.08736299723386765
2023-01-24 03:27:34.708773: step: 744/469, loss: 0.05938255414366722
2023-01-24 03:27:35.399424: step: 746/469, loss: 0.046954963356256485
2023-01-24 03:27:35.938872: step: 748/469, loss: 0.05033650994300842
2023-01-24 03:27:36.553391: step: 750/469, loss: 0.3463425934314728
2023-01-24 03:27:37.231121: step: 752/469, loss: 0.05690761283040047
2023-01-24 03:27:37.906081: step: 754/469, loss: 0.06557939946651459
2023-01-24 03:27:38.471714: step: 756/469, loss: 0.04945741966366768
2023-01-24 03:27:39.050916: step: 758/469, loss: 0.08173562586307526
2023-01-24 03:27:39.627348: step: 760/469, loss: 0.034592051059007645
2023-01-24 03:27:40.263278: step: 762/469, loss: 0.03938683494925499
2023-01-24 03:27:40.805613: step: 764/469, loss: 0.10660931468009949
2023-01-24 03:27:41.434433: step: 766/469, loss: 0.06772271543741226
2023-01-24 03:27:41.980408: step: 768/469, loss: 0.13811947405338287
2023-01-24 03:27:42.551668: step: 770/469, loss: 0.032920584082603455
2023-01-24 03:27:43.164902: step: 772/469, loss: 0.021953996270895004
2023-01-24 03:27:43.797994: step: 774/469, loss: 0.05240635573863983
2023-01-24 03:27:44.412679: step: 776/469, loss: 0.20037932693958282
2023-01-24 03:27:45.102477: step: 778/469, loss: 0.04232468828558922
2023-01-24 03:27:45.818669: step: 780/469, loss: 0.039521485567092896
2023-01-24 03:27:46.522196: step: 782/469, loss: 0.009970891289412975
2023-01-24 03:27:47.240550: step: 784/469, loss: 0.03995884954929352
2023-01-24 03:27:47.924366: step: 786/469, loss: 0.011412148363888264
2023-01-24 03:27:48.522640: step: 788/469, loss: 0.1112995371222496
2023-01-24 03:27:49.127113: step: 790/469, loss: 0.12103532254695892
2023-01-24 03:27:49.707567: step: 792/469, loss: 0.21943050622940063
2023-01-24 03:27:50.304479: step: 794/469, loss: 0.004217034671455622
2023-01-24 03:27:50.867982: step: 796/469, loss: 0.14052830636501312
2023-01-24 03:27:51.502293: step: 798/469, loss: 0.016933167353272438
2023-01-24 03:27:52.143738: step: 800/469, loss: 0.12630292773246765
2023-01-24 03:27:52.812393: step: 802/469, loss: 0.14411765336990356
2023-01-24 03:27:53.423231: step: 804/469, loss: 0.0805254876613617
2023-01-24 03:27:54.026216: step: 806/469, loss: 0.030944321304559708
2023-01-24 03:27:54.627049: step: 808/469, loss: 0.04941081628203392
2023-01-24 03:27:55.218714: step: 810/469, loss: 0.12576352059841156
2023-01-24 03:27:55.796892: step: 812/469, loss: 0.11210504174232483
2023-01-24 03:27:56.386678: step: 814/469, loss: 0.09459513425827026
2023-01-24 03:27:57.033394: step: 816/469, loss: 0.05020858719944954
2023-01-24 03:27:57.633388: step: 818/469, loss: 0.02079484611749649
2023-01-24 03:27:58.305499: step: 820/469, loss: 0.12901917099952698
2023-01-24 03:27:58.927336: step: 822/469, loss: 0.35205814242362976
2023-01-24 03:27:59.539090: step: 824/469, loss: 0.014864898286759853
2023-01-24 03:28:00.148369: step: 826/469, loss: 0.03730570897459984
2023-01-24 03:28:00.788220: step: 828/469, loss: 0.41891026496887207
2023-01-24 03:28:01.472578: step: 830/469, loss: 0.01630174182355404
2023-01-24 03:28:02.128677: step: 832/469, loss: 0.0619516558945179
2023-01-24 03:28:02.789152: step: 834/469, loss: 0.03761196881532669
2023-01-24 03:28:03.403014: step: 836/469, loss: 0.028952032327651978
2023-01-24 03:28:03.960368: step: 838/469, loss: 0.03119269758462906
2023-01-24 03:28:04.551771: step: 840/469, loss: 0.014045340940356255
2023-01-24 03:28:05.152840: step: 842/469, loss: 0.0033642761409282684
2023-01-24 03:28:05.784193: step: 844/469, loss: 0.4119490385055542
2023-01-24 03:28:06.486691: step: 846/469, loss: 0.09381299465894699
2023-01-24 03:28:07.124935: step: 848/469, loss: 0.05417989194393158
2023-01-24 03:28:07.817487: step: 850/469, loss: 0.10595797747373581
2023-01-24 03:28:08.460349: step: 852/469, loss: 0.1034916415810585
2023-01-24 03:28:09.088417: step: 854/469, loss: 0.04896261543035507
2023-01-24 03:28:09.695415: step: 856/469, loss: 0.4186862111091614
2023-01-24 03:28:10.355223: step: 858/469, loss: 0.06940488517284393
2023-01-24 03:28:10.927503: step: 860/469, loss: 0.5892264246940613
2023-01-24 03:28:11.654732: step: 862/469, loss: 0.030064817517995834
2023-01-24 03:28:12.284016: step: 864/469, loss: 0.058277588337659836
2023-01-24 03:28:12.899161: step: 866/469, loss: 0.1297154426574707
2023-01-24 03:28:13.478445: step: 868/469, loss: 0.11072082072496414
2023-01-24 03:28:14.099619: step: 870/469, loss: 0.03493410348892212
2023-01-24 03:28:14.773329: step: 872/469, loss: 0.10401593893766403
2023-01-24 03:28:15.430741: step: 874/469, loss: 0.0552351213991642
2023-01-24 03:28:16.140721: step: 876/469, loss: 0.04945047199726105
2023-01-24 03:28:16.838556: step: 878/469, loss: 0.07825034856796265
2023-01-24 03:28:17.486296: step: 880/469, loss: 0.10247155278921127
2023-01-24 03:28:18.108225: step: 882/469, loss: 0.026932446286082268
2023-01-24 03:28:18.705313: step: 884/469, loss: 0.05905936658382416
2023-01-24 03:28:19.318826: step: 886/469, loss: 0.03196587786078453
2023-01-24 03:28:19.923953: step: 888/469, loss: 0.03644465282559395
2023-01-24 03:28:20.636346: step: 890/469, loss: 0.038065653294324875
2023-01-24 03:28:21.292497: step: 892/469, loss: 0.032983966171741486
2023-01-24 03:28:21.887002: step: 894/469, loss: 0.03079654462635517
2023-01-24 03:28:22.471694: step: 896/469, loss: 0.5434918999671936
2023-01-24 03:28:23.082668: step: 898/469, loss: 0.03318360075354576
2023-01-24 03:28:23.716707: step: 900/469, loss: 0.040477193892002106
2023-01-24 03:28:24.296720: step: 902/469, loss: 0.062321316450834274
2023-01-24 03:28:24.910676: step: 904/469, loss: 0.07525224983692169
2023-01-24 03:28:25.537904: step: 906/469, loss: 0.045330729335546494
2023-01-24 03:28:26.114742: step: 908/469, loss: 0.061386313289403915
2023-01-24 03:28:26.751294: step: 910/469, loss: 0.10755674540996552
2023-01-24 03:28:27.346419: step: 912/469, loss: 0.007984045892953873
2023-01-24 03:28:27.972446: step: 914/469, loss: 0.13335135579109192
2023-01-24 03:28:28.559410: step: 916/469, loss: 0.047902025282382965
2023-01-24 03:28:29.203370: step: 918/469, loss: 0.04972464591264725
2023-01-24 03:28:29.846894: step: 920/469, loss: 0.09323792904615402
2023-01-24 03:28:30.477213: step: 922/469, loss: 0.010326355695724487
2023-01-24 03:28:31.180804: step: 924/469, loss: 4.266698360443115
2023-01-24 03:28:31.830431: step: 926/469, loss: 0.04964417964220047
2023-01-24 03:28:32.438834: step: 928/469, loss: 0.02595529705286026
2023-01-24 03:28:33.210446: step: 930/469, loss: 0.09018541872501373
2023-01-24 03:28:33.830776: step: 932/469, loss: 0.024961672723293304
2023-01-24 03:28:34.425099: step: 934/469, loss: 0.0686643049120903
2023-01-24 03:28:35.090922: step: 936/469, loss: 0.04848860204219818
2023-01-24 03:28:35.783038: step: 938/469, loss: 0.21141712367534637
==================================================
Loss: 0.109
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3314417069014484, 'r': 0.3163475874220656, 'f1': 0.32371879334257975}, 'combined': 0.23852963719979559, 'epoch': 20}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3283915713200735, 'r': 0.26709982333352733, 'f1': 0.2945914297714888}, 'combined': 0.16068623442081204, 'epoch': 20}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3360565476190476, 'r': 0.3188392292400831, 'f1': 0.3272215653544767}, 'combined': 0.2411106271032986, 'epoch': 20}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33512832294538303, 'r': 0.269513079477577, 'f1': 0.2987604420578009}, 'combined': 0.16296024112243684, 'epoch': 20}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32196664309288076, 'r': 0.3085259103641457, 'f1': 0.3151030131044666}, 'combined': 0.23218116755065957, 'epoch': 20}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32389827764985984, 'r': 0.26818658853899646, 'f1': 0.29342136263575896}, 'combined': 0.16004801598314125, 'epoch': 20}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.27746212121212116, 'r': 0.3488095238095238, 'f1': 0.3090717299578058}, 'combined': 0.20604781997187052, 'epoch': 20}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2717391304347826, 'r': 0.2717391304347826, 'f1': 0.2717391304347826}, 'combined': 0.1358695652173913, 'epoch': 20}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45454545454545453, 'r': 0.1724137931034483, 'f1': 0.25000000000000006}, 'combined': 0.16666666666666669, 'epoch': 20}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:31:22.597721: step: 2/469, loss: 0.02392192929983139
2023-01-24 03:31:23.245237: step: 4/469, loss: 0.01966254599392414
2023-01-24 03:31:23.900020: step: 6/469, loss: 0.05299926921725273
2023-01-24 03:31:24.520741: step: 8/469, loss: 0.044818371534347534
2023-01-24 03:31:25.123678: step: 10/469, loss: 0.022025851532816887
2023-01-24 03:31:25.823222: step: 12/469, loss: 0.012700133956968784
2023-01-24 03:31:26.417639: step: 14/469, loss: 0.037772346287965775
2023-01-24 03:31:27.048189: step: 16/469, loss: 0.02254267781972885
2023-01-24 03:31:27.704233: step: 18/469, loss: 0.07363095134496689
2023-01-24 03:31:28.355870: step: 20/469, loss: 0.008026142604649067
2023-01-24 03:31:29.069286: step: 22/469, loss: 0.005653323605656624
2023-01-24 03:31:29.739662: step: 24/469, loss: 0.07869891822338104
2023-01-24 03:31:30.354025: step: 26/469, loss: 0.028066422790288925
2023-01-24 03:31:30.994000: step: 28/469, loss: 0.010528797283768654
2023-01-24 03:31:31.575444: step: 30/469, loss: 0.07387077063322067
2023-01-24 03:31:32.204202: step: 32/469, loss: 0.032999083399772644
2023-01-24 03:31:32.817338: step: 34/469, loss: 0.023119498044252396
2023-01-24 03:31:33.443274: step: 36/469, loss: 0.04699590429663658
2023-01-24 03:31:34.055011: step: 38/469, loss: 0.00793388020247221
2023-01-24 03:31:34.656009: step: 40/469, loss: 0.10146583616733551
2023-01-24 03:31:35.323232: step: 42/469, loss: 0.006985010579228401
2023-01-24 03:31:35.925126: step: 44/469, loss: 0.02706150896847248
2023-01-24 03:31:36.514407: step: 46/469, loss: 0.00024393167404923588
2023-01-24 03:31:37.181202: step: 48/469, loss: 0.028532344847917557
2023-01-24 03:31:37.770840: step: 50/469, loss: 0.0009933767141774297
2023-01-24 03:31:38.337958: step: 52/469, loss: 0.044913098216056824
2023-01-24 03:31:38.950490: step: 54/469, loss: 0.03143681585788727
2023-01-24 03:31:39.598137: step: 56/469, loss: 0.037025924772024155
2023-01-24 03:31:40.278304: step: 58/469, loss: 0.037975575774908066
2023-01-24 03:31:40.943698: step: 60/469, loss: 0.020727310329675674
2023-01-24 03:31:41.560174: step: 62/469, loss: 0.020771190524101257
2023-01-24 03:31:42.130094: step: 64/469, loss: 0.003391948761418462
2023-01-24 03:31:42.798909: step: 66/469, loss: 0.038785479962825775
2023-01-24 03:31:43.449524: step: 68/469, loss: 0.09054183959960938
2023-01-24 03:31:44.050978: step: 70/469, loss: 0.024149758741259575
2023-01-24 03:31:44.699621: step: 72/469, loss: 0.010785935446619987
2023-01-24 03:31:45.352694: step: 74/469, loss: 0.1472344696521759
2023-01-24 03:31:45.952755: step: 76/469, loss: 0.021318616345524788
2023-01-24 03:31:46.579862: step: 78/469, loss: 0.06855437159538269
2023-01-24 03:31:47.248026: step: 80/469, loss: 0.03193723410367966
2023-01-24 03:31:47.901881: step: 82/469, loss: 0.03750784695148468
2023-01-24 03:31:48.522677: step: 84/469, loss: 0.7567758560180664
2023-01-24 03:31:49.105562: step: 86/469, loss: 0.06039344519376755
2023-01-24 03:31:49.764508: step: 88/469, loss: 0.04281849414110184
2023-01-24 03:31:50.423654: step: 90/469, loss: 0.0049997554160654545
2023-01-24 03:31:51.014346: step: 92/469, loss: 0.04772511497139931
2023-01-24 03:31:51.582792: step: 94/469, loss: 0.036539532244205475
2023-01-24 03:31:52.182036: step: 96/469, loss: 0.013883134350180626
2023-01-24 03:31:52.796956: step: 98/469, loss: 0.0762481614947319
2023-01-24 03:31:53.462788: step: 100/469, loss: 0.05380294471979141
2023-01-24 03:31:54.055847: step: 102/469, loss: 0.05062882974743843
2023-01-24 03:31:54.710304: step: 104/469, loss: 0.16701483726501465
2023-01-24 03:31:55.315154: step: 106/469, loss: 0.014210863038897514
2023-01-24 03:31:55.939301: step: 108/469, loss: 0.01780262403190136
2023-01-24 03:31:56.550488: step: 110/469, loss: 0.13959628343582153
2023-01-24 03:31:57.160758: step: 112/469, loss: 0.024026265367865562
2023-01-24 03:31:57.712176: step: 114/469, loss: 0.03967355564236641
2023-01-24 03:31:58.338712: step: 116/469, loss: 0.06304628401994705
2023-01-24 03:31:58.933253: step: 118/469, loss: 0.01931256242096424
2023-01-24 03:31:59.526294: step: 120/469, loss: 0.7055705189704895
2023-01-24 03:32:00.131007: step: 122/469, loss: 0.015860218554735184
2023-01-24 03:32:00.740018: step: 124/469, loss: 0.08320516347885132
2023-01-24 03:32:01.345947: step: 126/469, loss: 0.05166981741786003
2023-01-24 03:32:01.958388: step: 128/469, loss: 0.15676382184028625
2023-01-24 03:32:02.546080: step: 130/469, loss: 0.014630008488893509
2023-01-24 03:32:03.218478: step: 132/469, loss: 0.1120273545384407
2023-01-24 03:32:03.838133: step: 134/469, loss: 0.029118932783603668
2023-01-24 03:32:04.505434: step: 136/469, loss: 0.07675378769636154
2023-01-24 03:32:05.077602: step: 138/469, loss: 0.028277577832341194
2023-01-24 03:32:05.705590: step: 140/469, loss: 0.022590328007936478
2023-01-24 03:32:06.377145: step: 142/469, loss: 0.020666001364588737
2023-01-24 03:32:07.124290: step: 144/469, loss: 0.069100521504879
2023-01-24 03:32:07.712749: step: 146/469, loss: 0.00901170913130045
2023-01-24 03:32:08.354439: step: 148/469, loss: 0.0521109439432621
2023-01-24 03:32:09.001657: step: 150/469, loss: 0.02426365204155445
2023-01-24 03:32:09.563199: step: 152/469, loss: 0.06741529703140259
2023-01-24 03:32:10.188208: step: 154/469, loss: 0.07119188457727432
2023-01-24 03:32:10.780926: step: 156/469, loss: 0.0225388091057539
2023-01-24 03:32:11.353466: step: 158/469, loss: 0.06181115657091141
2023-01-24 03:32:11.958636: step: 160/469, loss: 0.07040660083293915
2023-01-24 03:32:12.588765: step: 162/469, loss: 0.058279506862163544
2023-01-24 03:32:13.237534: step: 164/469, loss: 0.024268848821520805
2023-01-24 03:32:13.973369: step: 166/469, loss: 0.02673419937491417
2023-01-24 03:32:14.611865: step: 168/469, loss: 0.1298261433839798
2023-01-24 03:32:15.178167: step: 170/469, loss: 0.09414707124233246
2023-01-24 03:32:15.750439: step: 172/469, loss: 0.008704627864062786
2023-01-24 03:32:16.363130: step: 174/469, loss: 0.040511857718229294
2023-01-24 03:32:17.014033: step: 176/469, loss: 0.0404052659869194
2023-01-24 03:32:17.661052: step: 178/469, loss: 0.5321192741394043
2023-01-24 03:32:18.252101: step: 180/469, loss: 0.0034266209695488214
2023-01-24 03:32:18.826451: step: 182/469, loss: 0.018502982333302498
2023-01-24 03:32:19.508903: step: 184/469, loss: 0.05716400220990181
2023-01-24 03:32:20.152594: step: 186/469, loss: 0.03221050277352333
2023-01-24 03:32:20.734539: step: 188/469, loss: 0.06699027866125107
2023-01-24 03:32:21.323113: step: 190/469, loss: 0.08274269104003906
2023-01-24 03:32:21.838169: step: 192/469, loss: 0.005418492015451193
2023-01-24 03:32:22.452527: step: 194/469, loss: 0.010212346911430359
2023-01-24 03:32:23.137856: step: 196/469, loss: 0.07760020345449448
2023-01-24 03:32:23.766565: step: 198/469, loss: 0.30351677536964417
2023-01-24 03:32:24.400551: step: 200/469, loss: 0.012618208304047585
2023-01-24 03:32:25.117602: step: 202/469, loss: 0.49273350834846497
2023-01-24 03:32:25.755836: step: 204/469, loss: 0.04685742035508156
2023-01-24 03:32:26.395351: step: 206/469, loss: 0.04335838556289673
2023-01-24 03:32:26.980537: step: 208/469, loss: 0.01687638834118843
2023-01-24 03:32:27.595539: step: 210/469, loss: 0.0890517309308052
2023-01-24 03:32:28.225919: step: 212/469, loss: 0.1212993636727333
2023-01-24 03:32:28.832190: step: 214/469, loss: 0.036799754947423935
2023-01-24 03:32:29.458065: step: 216/469, loss: 0.03313329443335533
2023-01-24 03:32:30.045840: step: 218/469, loss: 0.11265157163143158
2023-01-24 03:32:30.621469: step: 220/469, loss: 0.011664781719446182
2023-01-24 03:32:31.264008: step: 222/469, loss: 0.0214131698012352
2023-01-24 03:32:31.856982: step: 224/469, loss: 0.004781034775078297
2023-01-24 03:32:32.537814: step: 226/469, loss: 0.002530965954065323
2023-01-24 03:32:33.124647: step: 228/469, loss: 0.024235527962446213
2023-01-24 03:32:33.833396: step: 230/469, loss: 0.039171766489744186
2023-01-24 03:32:34.479795: step: 232/469, loss: 0.05174962803721428
2023-01-24 03:32:35.114949: step: 234/469, loss: 0.05852152407169342
2023-01-24 03:32:35.683396: step: 236/469, loss: 0.018330590799450874
2023-01-24 03:32:36.306669: step: 238/469, loss: 0.0845969170331955
2023-01-24 03:32:36.868179: step: 240/469, loss: 0.04136737063527107
2023-01-24 03:32:37.505171: step: 242/469, loss: 0.013539737090468407
2023-01-24 03:32:38.108022: step: 244/469, loss: 0.07967480272054672
2023-01-24 03:32:38.699354: step: 246/469, loss: 0.008916055783629417
2023-01-24 03:32:39.293276: step: 248/469, loss: 0.012129005044698715
2023-01-24 03:32:39.840635: step: 250/469, loss: 0.014636692591011524
2023-01-24 03:32:40.551143: step: 252/469, loss: 0.024400966241955757
2023-01-24 03:32:41.120430: step: 254/469, loss: 0.03725671023130417
2023-01-24 03:32:41.690595: step: 256/469, loss: 0.00875252578407526
2023-01-24 03:32:42.255617: step: 258/469, loss: 0.18569916486740112
2023-01-24 03:32:42.933970: step: 260/469, loss: 0.02596977911889553
2023-01-24 03:32:43.572578: step: 262/469, loss: 0.8206031322479248
2023-01-24 03:32:44.170858: step: 264/469, loss: 0.09460817277431488
2023-01-24 03:32:44.762243: step: 266/469, loss: 0.032924480736255646
2023-01-24 03:32:45.371725: step: 268/469, loss: 0.0335528738796711
2023-01-24 03:32:45.940093: step: 270/469, loss: 0.060713693499565125
2023-01-24 03:32:46.571837: step: 272/469, loss: 0.07159701734781265
2023-01-24 03:32:47.179549: step: 274/469, loss: 0.013019309379160404
2023-01-24 03:32:47.818173: step: 276/469, loss: 0.07129477709531784
2023-01-24 03:32:48.505702: step: 278/469, loss: 0.07874827086925507
2023-01-24 03:32:49.101296: step: 280/469, loss: 0.029299231246113777
2023-01-24 03:32:49.784921: step: 282/469, loss: 0.05381292477250099
2023-01-24 03:32:50.429492: step: 284/469, loss: 0.13097001612186432
2023-01-24 03:32:51.105525: step: 286/469, loss: 0.06882507354021072
2023-01-24 03:32:51.699482: step: 288/469, loss: 0.12335500866174698
2023-01-24 03:32:52.316994: step: 290/469, loss: 0.04126376658678055
2023-01-24 03:32:52.948363: step: 292/469, loss: 0.039324551820755005
2023-01-24 03:32:53.635110: step: 294/469, loss: 0.05773017555475235
2023-01-24 03:32:54.256444: step: 296/469, loss: 0.03303098306059837
2023-01-24 03:32:54.842344: step: 298/469, loss: 0.05265083163976669
2023-01-24 03:32:55.422415: step: 300/469, loss: 0.08067907392978668
2023-01-24 03:32:56.078553: step: 302/469, loss: 0.0575513057410717
2023-01-24 03:32:56.682638: step: 304/469, loss: 0.9869254231452942
2023-01-24 03:32:57.274480: step: 306/469, loss: 0.011143622919917107
2023-01-24 03:32:57.924248: step: 308/469, loss: 0.049705423414707184
2023-01-24 03:32:58.529441: step: 310/469, loss: 0.02404535748064518
2023-01-24 03:32:59.211052: step: 312/469, loss: 0.05674991384148598
2023-01-24 03:32:59.857292: step: 314/469, loss: 0.10494145005941391
2023-01-24 03:33:00.465917: step: 316/469, loss: 0.06712942570447922
2023-01-24 03:33:01.020323: step: 318/469, loss: 0.04084033891558647
2023-01-24 03:33:01.647857: step: 320/469, loss: 0.03611866012215614
2023-01-24 03:33:02.172179: step: 322/469, loss: 0.008003677241504192
2023-01-24 03:33:02.821011: step: 324/469, loss: 0.034904543310403824
2023-01-24 03:33:03.444401: step: 326/469, loss: 0.03714032843708992
2023-01-24 03:33:04.093966: step: 328/469, loss: 0.012168901041150093
2023-01-24 03:33:04.735925: step: 330/469, loss: 0.014416170306503773
2023-01-24 03:33:05.365304: step: 332/469, loss: 0.07741773873567581
2023-01-24 03:33:06.022200: step: 334/469, loss: 0.0032909305300563574
2023-01-24 03:33:06.723059: step: 336/469, loss: 0.11048717796802521
2023-01-24 03:33:07.350359: step: 338/469, loss: 0.07588531076908112
2023-01-24 03:33:07.995644: step: 340/469, loss: 0.010511383414268494
2023-01-24 03:33:08.605973: step: 342/469, loss: 0.022397121414542198
2023-01-24 03:33:09.263025: step: 344/469, loss: 0.025274138897657394
2023-01-24 03:33:09.865489: step: 346/469, loss: 0.005095488857477903
2023-01-24 03:33:10.541964: step: 348/469, loss: 0.03323239088058472
2023-01-24 03:33:11.138762: step: 350/469, loss: 0.015544925816357136
2023-01-24 03:33:11.813689: step: 352/469, loss: 0.06461065262556076
2023-01-24 03:33:12.413164: step: 354/469, loss: 0.07638489454984665
2023-01-24 03:33:13.070095: step: 356/469, loss: 0.13434520363807678
2023-01-24 03:33:13.724601: step: 358/469, loss: 0.08030161261558533
2023-01-24 03:33:14.395993: step: 360/469, loss: 0.06590965390205383
2023-01-24 03:33:15.076155: step: 362/469, loss: 0.012448490597307682
2023-01-24 03:33:15.684456: step: 364/469, loss: 0.05046309903264046
2023-01-24 03:33:16.273473: step: 366/469, loss: 0.018466822803020477
2023-01-24 03:33:16.919457: step: 368/469, loss: 0.040025223046541214
2023-01-24 03:33:17.537932: step: 370/469, loss: 0.05510979890823364
2023-01-24 03:33:18.258710: step: 372/469, loss: 0.012401694431900978
2023-01-24 03:33:18.846194: step: 374/469, loss: 0.9642502069473267
2023-01-24 03:33:19.415144: step: 376/469, loss: 0.026485169306397438
2023-01-24 03:33:20.116889: step: 378/469, loss: 0.03587673231959343
2023-01-24 03:33:20.767202: step: 380/469, loss: 0.0007051278371363878
2023-01-24 03:33:21.379919: step: 382/469, loss: 0.3616332411766052
2023-01-24 03:33:21.948055: step: 384/469, loss: 0.044319137930870056
2023-01-24 03:33:22.499710: step: 386/469, loss: 0.08458127081394196
2023-01-24 03:33:23.188748: step: 388/469, loss: 0.10217348486185074
2023-01-24 03:33:23.830649: step: 390/469, loss: 0.26924359798431396
2023-01-24 03:33:24.381815: step: 392/469, loss: 0.012389730662107468
2023-01-24 03:33:25.000260: step: 394/469, loss: 0.013179104775190353
2023-01-24 03:33:25.669134: step: 396/469, loss: 0.09027823060750961
2023-01-24 03:33:26.343498: step: 398/469, loss: 0.03433922305703163
2023-01-24 03:33:26.950591: step: 400/469, loss: 0.06290686130523682
2023-01-24 03:33:27.590331: step: 402/469, loss: 0.02589227445423603
2023-01-24 03:33:28.180320: step: 404/469, loss: 0.0005919756949879229
2023-01-24 03:33:28.842379: step: 406/469, loss: 0.13433203101158142
2023-01-24 03:33:29.490090: step: 408/469, loss: 0.07053697109222412
2023-01-24 03:33:30.177600: step: 410/469, loss: 0.04509681835770607
2023-01-24 03:33:30.776301: step: 412/469, loss: 0.04402168467640877
2023-01-24 03:33:31.365466: step: 414/469, loss: 0.06334051489830017
2023-01-24 03:33:31.963799: step: 416/469, loss: 0.0007466504466719925
2023-01-24 03:33:32.523081: step: 418/469, loss: 0.43050992488861084
2023-01-24 03:33:33.161690: step: 420/469, loss: 0.10803550481796265
2023-01-24 03:33:33.708510: step: 422/469, loss: 0.05320751667022705
2023-01-24 03:33:34.346920: step: 424/469, loss: 0.0337304063141346
2023-01-24 03:33:34.966927: step: 426/469, loss: 0.0012051883386448026
2023-01-24 03:33:35.620424: step: 428/469, loss: 0.14188238978385925
2023-01-24 03:33:36.165597: step: 430/469, loss: 0.008196497336030006
2023-01-24 03:33:36.813136: step: 432/469, loss: 0.060212597250938416
2023-01-24 03:33:37.426396: step: 434/469, loss: 0.1244427040219307
2023-01-24 03:33:38.060846: step: 436/469, loss: 0.08918793499469757
2023-01-24 03:33:38.701608: step: 438/469, loss: 0.48906829953193665
2023-01-24 03:33:39.336572: step: 440/469, loss: 0.016950242221355438
2023-01-24 03:33:39.908471: step: 442/469, loss: 0.21700793504714966
2023-01-24 03:33:40.513751: step: 444/469, loss: 0.01460797619074583
2023-01-24 03:33:41.065166: step: 446/469, loss: 0.05856382101774216
2023-01-24 03:33:41.668601: step: 448/469, loss: 0.06313794106245041
2023-01-24 03:33:42.369120: step: 450/469, loss: 0.05432180315256119
2023-01-24 03:33:42.983177: step: 452/469, loss: 0.06948701292276382
2023-01-24 03:33:43.646916: step: 454/469, loss: 0.037344638258218765
2023-01-24 03:33:44.294813: step: 456/469, loss: 0.3675992786884308
2023-01-24 03:33:44.849102: step: 458/469, loss: 0.10851266235113144
2023-01-24 03:33:45.467969: step: 460/469, loss: 0.04810580983757973
2023-01-24 03:33:46.117931: step: 462/469, loss: 0.3988592028617859
2023-01-24 03:33:46.765873: step: 464/469, loss: 0.04201856255531311
2023-01-24 03:33:47.390350: step: 466/469, loss: 0.103286512196064
2023-01-24 03:33:47.975434: step: 468/469, loss: 0.032137639820575714
2023-01-24 03:33:48.591230: step: 470/469, loss: 0.048732005059719086
2023-01-24 03:33:49.144718: step: 472/469, loss: 0.043681900948286057
2023-01-24 03:33:49.695399: step: 474/469, loss: 0.061638057231903076
2023-01-24 03:33:50.283026: step: 476/469, loss: 0.009564572013914585
2023-01-24 03:33:50.872541: step: 478/469, loss: 0.020961610600352287
2023-01-24 03:33:51.492252: step: 480/469, loss: 0.08033375442028046
2023-01-24 03:33:52.158210: step: 482/469, loss: 0.4921906590461731
2023-01-24 03:33:52.839118: step: 484/469, loss: 0.039049189537763596
2023-01-24 03:33:53.446705: step: 486/469, loss: 0.45716163516044617
2023-01-24 03:33:54.067866: step: 488/469, loss: 0.3450915813446045
2023-01-24 03:33:54.757897: step: 490/469, loss: 0.00998485367745161
2023-01-24 03:33:55.347148: step: 492/469, loss: 0.03579733520746231
2023-01-24 03:33:56.023341: step: 494/469, loss: 0.05593695491552353
2023-01-24 03:33:56.737837: step: 496/469, loss: 0.048308905214071274
2023-01-24 03:33:57.376672: step: 498/469, loss: 0.014730180613696575
2023-01-24 03:33:58.010070: step: 500/469, loss: 0.021537592634558678
2023-01-24 03:33:58.647968: step: 502/469, loss: 0.007521749008446932
2023-01-24 03:33:59.267320: step: 504/469, loss: 0.048355430364608765
2023-01-24 03:33:59.915058: step: 506/469, loss: 3.7182867527008057
2023-01-24 03:34:00.481087: step: 508/469, loss: 0.04229341074824333
2023-01-24 03:34:01.063131: step: 510/469, loss: 0.032623041421175
2023-01-24 03:34:01.604034: step: 512/469, loss: 0.018214251846075058
2023-01-24 03:34:02.227657: step: 514/469, loss: 0.06210203468799591
2023-01-24 03:34:02.917029: step: 516/469, loss: 0.1362147480249405
2023-01-24 03:34:03.513164: step: 518/469, loss: 0.01085751224309206
2023-01-24 03:34:04.078268: step: 520/469, loss: 0.02598940208554268
2023-01-24 03:34:04.670223: step: 522/469, loss: 0.11556785553693771
2023-01-24 03:34:05.268041: step: 524/469, loss: 0.012101628817617893
2023-01-24 03:34:05.849101: step: 526/469, loss: 0.0612773634493351
2023-01-24 03:34:06.490412: step: 528/469, loss: 1.120747447013855
2023-01-24 03:34:07.130227: step: 530/469, loss: 0.0069404831156134605
2023-01-24 03:34:07.744996: step: 532/469, loss: 0.033291835337877274
2023-01-24 03:34:08.387109: step: 534/469, loss: 0.06330261379480362
2023-01-24 03:34:09.012536: step: 536/469, loss: 0.027323000133037567
2023-01-24 03:34:09.636047: step: 538/469, loss: 0.20305876433849335
2023-01-24 03:34:10.351006: step: 540/469, loss: 0.2994983196258545
2023-01-24 03:34:11.008542: step: 542/469, loss: 1.0734171867370605
2023-01-24 03:34:11.641082: step: 544/469, loss: 0.024813175201416016
2023-01-24 03:34:12.238181: step: 546/469, loss: 0.03625921159982681
2023-01-24 03:34:12.927202: step: 548/469, loss: 0.13224072754383087
2023-01-24 03:34:13.516194: step: 550/469, loss: 0.040598031133413315
2023-01-24 03:34:14.263890: step: 552/469, loss: 0.0528695173561573
2023-01-24 03:34:14.850382: step: 554/469, loss: 0.23352941870689392
2023-01-24 03:34:15.483050: step: 556/469, loss: 0.06219625845551491
2023-01-24 03:34:16.080921: step: 558/469, loss: 0.03036361373960972
2023-01-24 03:34:16.775966: step: 560/469, loss: 0.05718938261270523
2023-01-24 03:34:17.414738: step: 562/469, loss: 0.3490472137928009
2023-01-24 03:34:18.017768: step: 564/469, loss: 0.31674161553382874
2023-01-24 03:34:18.664047: step: 566/469, loss: 1.1303584575653076
2023-01-24 03:34:19.306934: step: 568/469, loss: 0.3321295976638794
2023-01-24 03:34:19.904203: step: 570/469, loss: 0.052285049110651016
2023-01-24 03:34:20.508688: step: 572/469, loss: 0.010169393382966518
2023-01-24 03:34:21.172645: step: 574/469, loss: 0.05551881715655327
2023-01-24 03:34:21.829812: step: 576/469, loss: 0.03533104434609413
2023-01-24 03:34:22.430431: step: 578/469, loss: 0.05030536651611328
2023-01-24 03:34:23.021098: step: 580/469, loss: 0.1418551802635193
2023-01-24 03:34:23.701478: step: 582/469, loss: 0.06159890070557594
2023-01-24 03:34:24.301863: step: 584/469, loss: 0.018290333449840546
2023-01-24 03:34:25.033108: step: 586/469, loss: 0.04992254823446274
2023-01-24 03:34:25.739977: step: 588/469, loss: 0.07574943453073502
2023-01-24 03:34:26.405567: step: 590/469, loss: 0.05323129519820213
2023-01-24 03:34:27.037416: step: 592/469, loss: 0.07767683267593384
2023-01-24 03:34:27.702687: step: 594/469, loss: 0.021485527977347374
2023-01-24 03:34:28.309030: step: 596/469, loss: 0.04382946342229843
2023-01-24 03:34:28.954199: step: 598/469, loss: 0.029458319768309593
2023-01-24 03:34:29.642681: step: 600/469, loss: 0.03222047537565231
2023-01-24 03:34:30.180236: step: 602/469, loss: 0.030031898990273476
2023-01-24 03:34:30.747570: step: 604/469, loss: 0.14416635036468506
2023-01-24 03:34:31.287477: step: 606/469, loss: 0.010015937499701977
2023-01-24 03:34:31.903676: step: 608/469, loss: 0.059417419135570526
2023-01-24 03:34:32.702180: step: 610/469, loss: 0.01093235332518816
2023-01-24 03:34:33.290459: step: 612/469, loss: 0.013218702748417854
2023-01-24 03:34:33.922425: step: 614/469, loss: 0.03595352917909622
2023-01-24 03:34:34.592302: step: 616/469, loss: 0.05864059180021286
2023-01-24 03:34:35.169231: step: 618/469, loss: 0.0648789331316948
2023-01-24 03:34:35.837958: step: 620/469, loss: 0.017844097688794136
2023-01-24 03:34:36.400177: step: 622/469, loss: 0.05244258791208267
2023-01-24 03:34:36.954655: step: 624/469, loss: 0.04297476261854172
2023-01-24 03:34:37.604447: step: 626/469, loss: 0.033403102308511734
2023-01-24 03:34:38.239872: step: 628/469, loss: 0.014146773144602776
2023-01-24 03:34:38.869615: step: 630/469, loss: 0.27720707654953003
2023-01-24 03:34:39.487007: step: 632/469, loss: 0.2061290740966797
2023-01-24 03:34:40.112830: step: 634/469, loss: 0.18586492538452148
2023-01-24 03:34:40.725062: step: 636/469, loss: 0.0966130793094635
2023-01-24 03:34:41.311338: step: 638/469, loss: 0.1111782118678093
2023-01-24 03:34:41.894486: step: 640/469, loss: 0.05226125568151474
2023-01-24 03:34:42.534912: step: 642/469, loss: 0.01457973476499319
2023-01-24 03:34:43.171848: step: 644/469, loss: 0.1761954128742218
2023-01-24 03:34:43.760221: step: 646/469, loss: 0.02660352550446987
2023-01-24 03:34:44.467717: step: 648/469, loss: 0.2710324823856354
2023-01-24 03:34:45.108109: step: 650/469, loss: 0.0830530896782875
2023-01-24 03:34:45.751237: step: 652/469, loss: 0.2343921959400177
2023-01-24 03:34:46.409697: step: 654/469, loss: 0.09646414965391159
2023-01-24 03:34:47.023406: step: 656/469, loss: 0.0021139108575880527
2023-01-24 03:34:47.696279: step: 658/469, loss: 0.03969826176762581
2023-01-24 03:34:48.344624: step: 660/469, loss: 0.025182340294122696
2023-01-24 03:34:49.004948: step: 662/469, loss: 0.02854195050895214
2023-01-24 03:34:49.642867: step: 664/469, loss: 0.007115752901881933
2023-01-24 03:34:50.250961: step: 666/469, loss: 0.01536788884550333
2023-01-24 03:34:50.874634: step: 668/469, loss: 0.04252452030777931
2023-01-24 03:34:51.517187: step: 670/469, loss: 0.03679046407341957
2023-01-24 03:34:52.125657: step: 672/469, loss: 0.0022139910142868757
2023-01-24 03:34:52.739197: step: 674/469, loss: 0.016556719318032265
2023-01-24 03:34:53.354521: step: 676/469, loss: 0.017600931227207184
2023-01-24 03:34:54.013320: step: 678/469, loss: 0.04440116137266159
2023-01-24 03:34:54.734705: step: 680/469, loss: 0.0637761726975441
2023-01-24 03:34:55.374510: step: 682/469, loss: 0.02740737795829773
2023-01-24 03:34:55.997331: step: 684/469, loss: 0.033616483211517334
2023-01-24 03:34:56.666995: step: 686/469, loss: 0.03198402374982834
2023-01-24 03:34:57.326127: step: 688/469, loss: 0.025264738127589226
2023-01-24 03:34:57.935258: step: 690/469, loss: 0.03330082446336746
2023-01-24 03:34:58.619020: step: 692/469, loss: 0.05013738200068474
2023-01-24 03:34:59.246080: step: 694/469, loss: 0.1575414389371872
2023-01-24 03:34:59.837776: step: 696/469, loss: 0.016313966363668442
2023-01-24 03:35:00.524723: step: 698/469, loss: 0.05271385610103607
2023-01-24 03:35:01.180655: step: 700/469, loss: 0.10756105184555054
2023-01-24 03:35:01.780923: step: 702/469, loss: 0.03324884548783302
2023-01-24 03:35:02.350178: step: 704/469, loss: 0.08443838357925415
2023-01-24 03:35:03.055370: step: 706/469, loss: 0.03254329413175583
2023-01-24 03:35:03.737602: step: 708/469, loss: 0.0392867811024189
2023-01-24 03:35:04.361871: step: 710/469, loss: 0.0397937186062336
2023-01-24 03:35:04.997967: step: 712/469, loss: 0.04455344378948212
2023-01-24 03:35:05.636172: step: 714/469, loss: 0.04998619481921196
2023-01-24 03:35:06.263862: step: 716/469, loss: 0.09658350050449371
2023-01-24 03:35:06.879132: step: 718/469, loss: 0.028297990560531616
2023-01-24 03:35:07.475524: step: 720/469, loss: 0.036358363926410675
2023-01-24 03:35:08.099495: step: 722/469, loss: 0.08025605231523514
2023-01-24 03:35:08.767636: step: 724/469, loss: 0.12209325283765793
2023-01-24 03:35:09.416187: step: 726/469, loss: 0.07784384489059448
2023-01-24 03:35:10.025145: step: 728/469, loss: 0.04587997868657112
2023-01-24 03:35:10.680214: step: 730/469, loss: 0.13514229655265808
2023-01-24 03:35:11.301981: step: 732/469, loss: 0.04976901039481163
2023-01-24 03:35:11.916785: step: 734/469, loss: 0.017125915735960007
2023-01-24 03:35:12.624549: step: 736/469, loss: 0.04468010738492012
2023-01-24 03:35:13.285696: step: 738/469, loss: 0.09711789339780807
2023-01-24 03:35:13.917837: step: 740/469, loss: 0.040078382939100266
2023-01-24 03:35:14.518965: step: 742/469, loss: 0.08487293869256973
2023-01-24 03:35:15.146653: step: 744/469, loss: 0.06645983457565308
2023-01-24 03:35:15.803904: step: 746/469, loss: 0.05511220172047615
2023-01-24 03:35:16.385236: step: 748/469, loss: 0.053987130522727966
2023-01-24 03:35:17.023573: step: 750/469, loss: 0.024653350934386253
2023-01-24 03:35:17.621150: step: 752/469, loss: 0.0641026571393013
2023-01-24 03:35:18.246633: step: 754/469, loss: 0.07033500075340271
2023-01-24 03:35:18.958832: step: 756/469, loss: 0.07802742719650269
2023-01-24 03:35:19.628528: step: 758/469, loss: 0.1480104774236679
2023-01-24 03:35:20.230919: step: 760/469, loss: 0.03959917649626732
2023-01-24 03:35:20.842079: step: 762/469, loss: 0.07692936807870865
2023-01-24 03:35:21.465581: step: 764/469, loss: 0.1016165241599083
2023-01-24 03:35:22.078079: step: 766/469, loss: 0.06488461792469025
2023-01-24 03:35:22.713554: step: 768/469, loss: 0.3187233507633209
2023-01-24 03:35:23.393611: step: 770/469, loss: 0.06554952263832092
2023-01-24 03:35:24.030597: step: 772/469, loss: 0.04240870475769043
2023-01-24 03:35:24.662903: step: 774/469, loss: 0.13569919764995575
2023-01-24 03:35:25.181748: step: 776/469, loss: 0.05393702909350395
2023-01-24 03:35:25.882293: step: 778/469, loss: 0.02817782759666443
2023-01-24 03:35:26.526385: step: 780/469, loss: 0.10576433688402176
2023-01-24 03:35:27.153050: step: 782/469, loss: 0.21694518625736237
2023-01-24 03:35:27.764855: step: 784/469, loss: 0.029813582077622414
2023-01-24 03:35:28.355295: step: 786/469, loss: 0.04769245162606239
2023-01-24 03:35:29.061161: step: 788/469, loss: 0.032447561621665955
2023-01-24 03:35:29.780413: step: 790/469, loss: 0.10353009402751923
2023-01-24 03:35:30.406985: step: 792/469, loss: 0.07201661169528961
2023-01-24 03:35:30.980579: step: 794/469, loss: 0.15413999557495117
2023-01-24 03:35:31.573522: step: 796/469, loss: 0.030728263780474663
2023-01-24 03:35:32.245638: step: 798/469, loss: 0.031079277396202087
2023-01-24 03:35:32.896557: step: 800/469, loss: 0.015821930021047592
2023-01-24 03:35:33.557103: step: 802/469, loss: 0.13217857480049133
2023-01-24 03:35:34.168114: step: 804/469, loss: 0.02876206487417221
2023-01-24 03:35:34.776906: step: 806/469, loss: 0.038718193769454956
2023-01-24 03:35:35.460811: step: 808/469, loss: 0.09459910541772842
2023-01-24 03:35:36.171997: step: 810/469, loss: 0.059684351086616516
2023-01-24 03:35:36.756544: step: 812/469, loss: 0.05107962340116501
2023-01-24 03:35:37.313228: step: 814/469, loss: 0.022224560379981995
2023-01-24 03:35:37.931565: step: 816/469, loss: 0.0248254407197237
2023-01-24 03:35:38.529616: step: 818/469, loss: 0.05781036987900734
2023-01-24 03:35:39.200890: step: 820/469, loss: 0.10669608414173126
2023-01-24 03:35:39.801167: step: 822/469, loss: 0.07365518063306808
2023-01-24 03:35:40.445600: step: 824/469, loss: 0.05389543995261192
2023-01-24 03:35:41.105376: step: 826/469, loss: 0.20074480772018433
2023-01-24 03:35:41.686156: step: 828/469, loss: 0.03945460543036461
2023-01-24 03:35:42.314068: step: 830/469, loss: 0.03820425644516945
2023-01-24 03:35:42.969958: step: 832/469, loss: 0.10944437980651855
2023-01-24 03:35:43.540064: step: 834/469, loss: 0.029513105750083923
2023-01-24 03:35:44.236772: step: 836/469, loss: 0.49039581418037415
2023-01-24 03:35:44.840999: step: 838/469, loss: 0.002449015388265252
2023-01-24 03:35:45.429575: step: 840/469, loss: 0.08510282635688782
2023-01-24 03:35:46.054352: step: 842/469, loss: 0.0468197725713253
2023-01-24 03:35:46.694464: step: 844/469, loss: 0.025860905647277832
2023-01-24 03:35:47.284456: step: 846/469, loss: 0.04489691182971001
2023-01-24 03:35:47.962334: step: 848/469, loss: 0.03902563452720642
2023-01-24 03:35:48.615138: step: 850/469, loss: 0.02157416380941868
2023-01-24 03:35:49.243895: step: 852/469, loss: 0.039949797093868256
2023-01-24 03:35:49.900244: step: 854/469, loss: 0.06636688858270645
2023-01-24 03:35:50.497531: step: 856/469, loss: 0.04155225306749344
2023-01-24 03:35:51.167850: step: 858/469, loss: 0.06414211541414261
2023-01-24 03:35:51.775438: step: 860/469, loss: 0.027421142905950546
2023-01-24 03:35:52.362917: step: 862/469, loss: 0.04800093546509743
2023-01-24 03:35:53.026679: step: 864/469, loss: 0.027248848229646683
2023-01-24 03:35:53.672666: step: 866/469, loss: 0.16070668399333954
2023-01-24 03:35:54.263544: step: 868/469, loss: 0.0034537664614617825
2023-01-24 03:35:54.917109: step: 870/469, loss: 0.059498563408851624
2023-01-24 03:35:55.649961: step: 872/469, loss: 0.0485636331140995
2023-01-24 03:35:56.316869: step: 874/469, loss: 0.029997479170560837
2023-01-24 03:35:57.008485: step: 876/469, loss: 0.034448787569999695
2023-01-24 03:35:57.749354: step: 878/469, loss: 0.1755153238773346
2023-01-24 03:35:58.381045: step: 880/469, loss: 0.04570706933736801
2023-01-24 03:35:59.002634: step: 882/469, loss: 0.02426147647202015
2023-01-24 03:35:59.661980: step: 884/469, loss: 0.03767477720975876
2023-01-24 03:36:00.332466: step: 886/469, loss: 0.07098328322172165
2023-01-24 03:36:00.956553: step: 888/469, loss: 0.09545578807592392
2023-01-24 03:36:01.533618: step: 890/469, loss: 0.02542886696755886
2023-01-24 03:36:02.159101: step: 892/469, loss: 0.05639605596661568
2023-01-24 03:36:02.829637: step: 894/469, loss: 0.006311480421572924
2023-01-24 03:36:03.392026: step: 896/469, loss: 0.02327331341803074
2023-01-24 03:36:04.041603: step: 898/469, loss: 0.0260337945073843
2023-01-24 03:36:04.666114: step: 900/469, loss: 0.03944583982229233
2023-01-24 03:36:05.269675: step: 902/469, loss: 0.04809301719069481
2023-01-24 03:36:05.842892: step: 904/469, loss: 0.02306533046066761
2023-01-24 03:36:06.524816: step: 906/469, loss: 0.0661945566534996
2023-01-24 03:36:07.239397: step: 908/469, loss: 0.0746571347117424
2023-01-24 03:36:08.057040: step: 910/469, loss: 0.38557612895965576
2023-01-24 03:36:08.699462: step: 912/469, loss: 0.052983105182647705
2023-01-24 03:36:09.322773: step: 914/469, loss: 0.8118378520011902
2023-01-24 03:36:09.982512: step: 916/469, loss: 0.02027197740972042
2023-01-24 03:36:10.624504: step: 918/469, loss: 0.041854795068502426
2023-01-24 03:36:11.363512: step: 920/469, loss: 0.04107408598065376
2023-01-24 03:36:12.039524: step: 922/469, loss: 0.035452499985694885
2023-01-24 03:36:12.720439: step: 924/469, loss: 0.035532962530851364
2023-01-24 03:36:13.333126: step: 926/469, loss: 0.4863441586494446
2023-01-24 03:36:13.958842: step: 928/469, loss: 0.059065476059913635
2023-01-24 03:36:14.603633: step: 930/469, loss: 0.0265822671353817
2023-01-24 03:36:15.278127: step: 932/469, loss: 0.08679469674825668
2023-01-24 03:36:16.011475: step: 934/469, loss: 0.1726817637681961
2023-01-24 03:36:16.659613: step: 936/469, loss: 0.007782823871821165
2023-01-24 03:36:17.326470: step: 938/469, loss: 0.08940225094556808
==================================================
Loss: 0.093
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33536772410180055, 'r': 0.2997309260947781, 'f1': 0.31654949509408425}, 'combined': 0.2332469963851147, 'epoch': 21}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.34273281699938385, 'r': 0.2787643863791878, 'f1': 0.30745658356453304}, 'combined': 0.16770359103519983, 'epoch': 21}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3461966685685305, 'r': 0.31400760450807885, 'f1': 0.3293174280114578}, 'combined': 0.242654946955811, 'epoch': 21}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33695054736135843, 'r': 0.27073083284335836, 'f1': 0.30023267220540706}, 'combined': 0.16376327574840382, 'epoch': 21}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3344100241213589, 'r': 0.2995095472206478, 'f1': 0.31599906183239523}, 'combined': 0.2328414139817649, 'epoch': 21}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32968780871745207, 'r': 0.26766434881261636, 'f1': 0.29545611083650697}, 'combined': 0.1611578786380947, 'epoch': 21}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33455882352941174, 'r': 0.325, 'f1': 0.32971014492753625}, 'combined': 0.21980676328502416, 'epoch': 21}
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': 21}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'epoch': 21}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:39:02.349284: step: 2/469, loss: 0.039380770176649094
2023-01-24 03:39:03.063858: step: 4/469, loss: 0.05055861920118332
2023-01-24 03:39:03.679627: step: 6/469, loss: 0.04295489937067032
2023-01-24 03:39:04.346671: step: 8/469, loss: 0.023237884044647217
2023-01-24 03:39:04.952713: step: 10/469, loss: 0.28028494119644165
2023-01-24 03:39:05.599385: step: 12/469, loss: 0.07559418678283691
2023-01-24 03:39:06.252091: step: 14/469, loss: 0.11430711299180984
2023-01-24 03:39:06.886957: step: 16/469, loss: 0.01595250517129898
2023-01-24 03:39:07.477170: step: 18/469, loss: 0.018117446452379227
2023-01-24 03:39:08.141802: step: 20/469, loss: 1.387865424156189
2023-01-24 03:39:08.728775: step: 22/469, loss: 0.024295097216963768
2023-01-24 03:39:09.445585: step: 24/469, loss: 1.1460556983947754
2023-01-24 03:39:10.134296: step: 26/469, loss: 0.13597992062568665
2023-01-24 03:39:10.756383: step: 28/469, loss: 0.01898580975830555
2023-01-24 03:39:11.352063: step: 30/469, loss: 0.015223619528114796
2023-01-24 03:39:11.962735: step: 32/469, loss: 0.0550190769135952
2023-01-24 03:39:12.628695: step: 34/469, loss: 0.005130401346832514
2023-01-24 03:39:13.311581: step: 36/469, loss: 0.02761279046535492
2023-01-24 03:39:13.913970: step: 38/469, loss: 0.0677400454878807
2023-01-24 03:39:14.624183: step: 40/469, loss: 0.048578161746263504
2023-01-24 03:39:15.362216: step: 42/469, loss: 0.07426793873310089
2023-01-24 03:39:16.023248: step: 44/469, loss: 0.04773702472448349
2023-01-24 03:39:16.737409: step: 46/469, loss: 0.3359375298023224
2023-01-24 03:39:17.367692: step: 48/469, loss: 0.08309541642665863
2023-01-24 03:39:17.949474: step: 50/469, loss: 0.17198117077350616
2023-01-24 03:39:18.600048: step: 52/469, loss: 0.06714746356010437
2023-01-24 03:39:19.203954: step: 54/469, loss: 0.0135366665199399
2023-01-24 03:39:19.864394: step: 56/469, loss: 0.5882316827774048
2023-01-24 03:39:20.438174: step: 58/469, loss: 0.008281073532998562
2023-01-24 03:39:21.045141: step: 60/469, loss: 0.0044734301045536995
2023-01-24 03:39:21.668036: step: 62/469, loss: 0.012628215365111828
2023-01-24 03:39:22.344564: step: 64/469, loss: 0.013408358208835125
2023-01-24 03:39:22.929551: step: 66/469, loss: 0.027022888883948326
2023-01-24 03:39:23.572076: step: 68/469, loss: 0.035244572907686234
2023-01-24 03:39:24.165923: step: 70/469, loss: 0.0042418683879077435
2023-01-24 03:39:24.819221: step: 72/469, loss: 0.03192221373319626
2023-01-24 03:39:25.441065: step: 74/469, loss: 0.05043495073914528
2023-01-24 03:39:25.979345: step: 76/469, loss: 0.03084174543619156
2023-01-24 03:39:26.561572: step: 78/469, loss: 0.05266093462705612
2023-01-24 03:39:27.198263: step: 80/469, loss: 0.04924841970205307
2023-01-24 03:39:27.842965: step: 82/469, loss: 0.014719842933118343
2023-01-24 03:39:28.502965: step: 84/469, loss: 0.0027282529044896364
2023-01-24 03:39:29.131568: step: 86/469, loss: 0.02334756590425968
2023-01-24 03:39:29.804481: step: 88/469, loss: 0.043558232486248016
2023-01-24 03:39:30.397341: step: 90/469, loss: 0.02834555320441723
2023-01-24 03:39:30.991135: step: 92/469, loss: 0.09036640077829361
2023-01-24 03:39:31.653915: step: 94/469, loss: 0.018504438921809196
2023-01-24 03:39:32.316877: step: 96/469, loss: 0.06946828961372375
2023-01-24 03:39:32.931593: step: 98/469, loss: 0.09055262058973312
2023-01-24 03:39:33.500785: step: 100/469, loss: 0.02907070517539978
2023-01-24 03:39:34.082746: step: 102/469, loss: 0.015320273116230965
2023-01-24 03:39:34.717214: step: 104/469, loss: 0.040162622928619385
2023-01-24 03:39:35.290999: step: 106/469, loss: 0.021767625585198402
2023-01-24 03:39:35.915958: step: 108/469, loss: 0.09671736508607864
2023-01-24 03:39:36.606780: step: 110/469, loss: 0.01166476495563984
2023-01-24 03:39:37.208886: step: 112/469, loss: 0.06064381077885628
2023-01-24 03:39:37.781037: step: 114/469, loss: 0.030871480703353882
2023-01-24 03:39:38.438963: step: 116/469, loss: 0.05562804266810417
2023-01-24 03:39:39.016459: step: 118/469, loss: 0.03468940407037735
2023-01-24 03:39:39.666029: step: 120/469, loss: 0.04261632263660431
2023-01-24 03:39:40.339864: step: 122/469, loss: 0.24910223484039307
2023-01-24 03:39:40.987331: step: 124/469, loss: 0.007574675139039755
2023-01-24 03:39:41.637521: step: 126/469, loss: 0.017516538500785828
2023-01-24 03:39:42.292375: step: 128/469, loss: 0.059154730290174484
2023-01-24 03:39:42.897677: step: 130/469, loss: 0.16113242506980896
2023-01-24 03:39:43.498680: step: 132/469, loss: 0.01714664325118065
2023-01-24 03:39:44.092049: step: 134/469, loss: 0.005969333928078413
2023-01-24 03:39:44.760274: step: 136/469, loss: 0.0019294844241812825
2023-01-24 03:39:45.387466: step: 138/469, loss: 0.06720604002475739
2023-01-24 03:39:45.990797: step: 140/469, loss: 0.14247657358646393
2023-01-24 03:39:46.613086: step: 142/469, loss: 0.020634878426790237
2023-01-24 03:39:47.283652: step: 144/469, loss: 0.020726803690195084
2023-01-24 03:39:47.903606: step: 146/469, loss: 0.0766528770327568
2023-01-24 03:39:48.472988: step: 148/469, loss: 0.04846583306789398
2023-01-24 03:39:49.096039: step: 150/469, loss: 0.07275208085775375
2023-01-24 03:39:49.719771: step: 152/469, loss: 0.06970221549272537
2023-01-24 03:39:50.329565: step: 154/469, loss: 0.2876651883125305
2023-01-24 03:39:50.955112: step: 156/469, loss: 0.018488343805074692
2023-01-24 03:39:51.566944: step: 158/469, loss: 0.04454474151134491
2023-01-24 03:39:52.130872: step: 160/469, loss: 0.03576549515128136
2023-01-24 03:39:52.770281: step: 162/469, loss: 0.05528002977371216
2023-01-24 03:39:53.363070: step: 164/469, loss: 0.03665146976709366
2023-01-24 03:39:53.939466: step: 166/469, loss: 0.005062991287559271
2023-01-24 03:39:54.491893: step: 168/469, loss: 0.0907004177570343
2023-01-24 03:39:55.059910: step: 170/469, loss: 0.1247393786907196
2023-01-24 03:39:55.684758: step: 172/469, loss: 0.034603241831064224
2023-01-24 03:39:56.315103: step: 174/469, loss: 0.018291473388671875
2023-01-24 03:39:56.969798: step: 176/469, loss: 0.010822205804288387
2023-01-24 03:39:57.613227: step: 178/469, loss: 0.041395403444767
2023-01-24 03:39:58.226175: step: 180/469, loss: 0.2562817931175232
2023-01-24 03:39:58.856077: step: 182/469, loss: 0.02315080165863037
2023-01-24 03:39:59.430913: step: 184/469, loss: 0.10349332541227341
2023-01-24 03:40:00.056349: step: 186/469, loss: 0.04429632052779198
2023-01-24 03:40:00.731028: step: 188/469, loss: 0.052627675235271454
2023-01-24 03:40:01.364228: step: 190/469, loss: 0.052082035690546036
2023-01-24 03:40:02.129157: step: 192/469, loss: 0.09045175462961197
2023-01-24 03:40:02.784256: step: 194/469, loss: 0.056290898472070694
2023-01-24 03:40:03.404611: step: 196/469, loss: 0.06224917992949486
2023-01-24 03:40:04.021446: step: 198/469, loss: 0.08666723966598511
2023-01-24 03:40:04.588210: step: 200/469, loss: 0.02088574692606926
2023-01-24 03:40:05.226838: step: 202/469, loss: 0.17314031720161438
2023-01-24 03:40:05.836382: step: 204/469, loss: 0.045591890811920166
2023-01-24 03:40:06.466879: step: 206/469, loss: 0.03817299008369446
2023-01-24 03:40:07.038201: step: 208/469, loss: 0.1506112813949585
2023-01-24 03:40:07.642896: step: 210/469, loss: 0.02801366150379181
2023-01-24 03:40:08.230552: step: 212/469, loss: 0.03334649279713631
2023-01-24 03:40:08.872750: step: 214/469, loss: 0.07692849636077881
2023-01-24 03:40:09.527146: step: 216/469, loss: 0.029438933357596397
2023-01-24 03:40:10.133285: step: 218/469, loss: 0.04559696093201637
2023-01-24 03:40:10.726462: step: 220/469, loss: 0.029989738017320633
2023-01-24 03:40:11.319753: step: 222/469, loss: 0.02871067449450493
2023-01-24 03:40:12.002802: step: 224/469, loss: 0.028774617239832878
2023-01-24 03:40:12.561735: step: 226/469, loss: 0.06132190674543381
2023-01-24 03:40:13.178669: step: 228/469, loss: 0.03399735689163208
2023-01-24 03:40:13.834872: step: 230/469, loss: 0.029686376452445984
2023-01-24 03:40:14.436195: step: 232/469, loss: 0.025587785989046097
2023-01-24 03:40:15.002535: step: 234/469, loss: 0.0662321075797081
2023-01-24 03:40:15.624621: step: 236/469, loss: 0.009135673753917217
2023-01-24 03:40:16.269005: step: 238/469, loss: 0.005674504209309816
2023-01-24 03:40:16.884033: step: 240/469, loss: 0.1720525622367859
2023-01-24 03:40:17.523080: step: 242/469, loss: 0.5190364122390747
2023-01-24 03:40:18.168279: step: 244/469, loss: 0.009142519906163216
2023-01-24 03:40:18.818177: step: 246/469, loss: 0.4977860748767853
2023-01-24 03:40:19.448506: step: 248/469, loss: 0.06799748539924622
2023-01-24 03:40:20.029457: step: 250/469, loss: 0.016992144286632538
2023-01-24 03:40:20.643969: step: 252/469, loss: 0.03562434762716293
2023-01-24 03:40:21.230878: step: 254/469, loss: 0.02499387413263321
2023-01-24 03:40:21.804489: step: 256/469, loss: 7.44908902561292e-05
2023-01-24 03:40:22.471329: step: 258/469, loss: 0.02635972946882248
2023-01-24 03:40:23.139092: step: 260/469, loss: 0.05244665965437889
2023-01-24 03:40:23.775081: step: 262/469, loss: 0.015961477532982826
2023-01-24 03:40:24.360218: step: 264/469, loss: 0.09574796259403229
2023-01-24 03:40:24.990084: step: 266/469, loss: 0.008326071314513683
2023-01-24 03:40:25.572620: step: 268/469, loss: 0.0605514831840992
2023-01-24 03:40:26.173148: step: 270/469, loss: 0.0383342020213604
2023-01-24 03:40:26.800581: step: 272/469, loss: 0.022514592856168747
2023-01-24 03:40:27.395930: step: 274/469, loss: 0.004070336930453777
2023-01-24 03:40:28.001487: step: 276/469, loss: 0.004935351200401783
2023-01-24 03:40:28.689642: step: 278/469, loss: 0.10180534422397614
2023-01-24 03:40:29.335974: step: 280/469, loss: 0.07068388909101486
2023-01-24 03:40:30.018704: step: 282/469, loss: 0.014246614649891853
2023-01-24 03:40:30.658404: step: 284/469, loss: 0.11330433934926987
2023-01-24 03:40:31.325757: step: 286/469, loss: 0.0123306754976511
2023-01-24 03:40:31.900354: step: 288/469, loss: 0.03695213422179222
2023-01-24 03:40:32.508521: step: 290/469, loss: 0.009263748303055763
2023-01-24 03:40:33.206569: step: 292/469, loss: 0.06397242099046707
2023-01-24 03:40:33.782934: step: 294/469, loss: 0.014196955598890781
2023-01-24 03:40:34.371403: step: 296/469, loss: 0.0032813590951263905
2023-01-24 03:40:34.967175: step: 298/469, loss: 0.009251163341104984
2023-01-24 03:40:35.582605: step: 300/469, loss: 0.040932126343250275
2023-01-24 03:40:36.203605: step: 302/469, loss: 0.003713840153068304
2023-01-24 03:40:36.918021: step: 304/469, loss: 0.10758811235427856
2023-01-24 03:40:37.568904: step: 306/469, loss: 0.024556109681725502
2023-01-24 03:40:38.211001: step: 308/469, loss: 0.08184278011322021
2023-01-24 03:40:38.736297: step: 310/469, loss: 0.012405350804328918
2023-01-24 03:40:39.355441: step: 312/469, loss: 1.9847286939620972
2023-01-24 03:40:40.020780: step: 314/469, loss: 0.15689538419246674
2023-01-24 03:40:40.618559: step: 316/469, loss: 0.025493750348687172
2023-01-24 03:40:41.228931: step: 318/469, loss: 0.08086427301168442
2023-01-24 03:40:41.854948: step: 320/469, loss: 0.031102390959858894
2023-01-24 03:40:42.644830: step: 322/469, loss: 0.040684446692466736
2023-01-24 03:40:43.231597: step: 324/469, loss: 0.018266992643475533
2023-01-24 03:40:43.843024: step: 326/469, loss: 0.032480835914611816
2023-01-24 03:40:44.439176: step: 328/469, loss: 0.054183073341846466
2023-01-24 03:40:45.026386: step: 330/469, loss: 0.03766085207462311
2023-01-24 03:40:45.811555: step: 332/469, loss: 0.06161145493388176
2023-01-24 03:40:46.452039: step: 334/469, loss: 0.01634340174496174
2023-01-24 03:40:47.043953: step: 336/469, loss: 0.06446312367916107
2023-01-24 03:40:47.674903: step: 338/469, loss: 0.002547625219449401
2023-01-24 03:40:48.270360: step: 340/469, loss: 0.015411713160574436
2023-01-24 03:40:48.917003: step: 342/469, loss: 0.4192122519016266
2023-01-24 03:40:49.564732: step: 344/469, loss: 0.08557723462581635
2023-01-24 03:40:50.134661: step: 346/469, loss: 0.04641762748360634
2023-01-24 03:40:50.732341: step: 348/469, loss: 0.04900040850043297
2023-01-24 03:40:51.403180: step: 350/469, loss: 0.02108554169535637
2023-01-24 03:40:51.992831: step: 352/469, loss: 0.5605222582817078
2023-01-24 03:40:52.626899: step: 354/469, loss: 0.008658409118652344
2023-01-24 03:40:53.262618: step: 356/469, loss: 0.050972625613212585
2023-01-24 03:40:53.918144: step: 358/469, loss: 0.1746513843536377
2023-01-24 03:40:54.490802: step: 360/469, loss: 0.022396810352802277
2023-01-24 03:40:55.123627: step: 362/469, loss: 0.07565449178218842
2023-01-24 03:40:55.799578: step: 364/469, loss: 0.034683264791965485
2023-01-24 03:40:56.381150: step: 366/469, loss: 0.190207377076149
2023-01-24 03:40:56.949843: step: 368/469, loss: 0.03791588172316551
2023-01-24 03:40:57.500921: step: 370/469, loss: 0.023350585252046585
2023-01-24 03:40:58.180786: step: 372/469, loss: 0.01141371950507164
2023-01-24 03:40:58.801448: step: 374/469, loss: 0.061606645584106445
2023-01-24 03:40:59.386964: step: 376/469, loss: 0.014597347006201744
2023-01-24 03:41:00.052104: step: 378/469, loss: 0.0035952257458120584
2023-01-24 03:41:00.755929: step: 380/469, loss: 0.08695082366466522
2023-01-24 03:41:01.293930: step: 382/469, loss: 0.25980886816978455
2023-01-24 03:41:01.886474: step: 384/469, loss: 0.014322969131171703
2023-01-24 03:41:02.468309: step: 386/469, loss: 0.02906735986471176
2023-01-24 03:41:03.110837: step: 388/469, loss: 0.016713572666049004
2023-01-24 03:41:03.699149: step: 390/469, loss: 0.026671504601836205
2023-01-24 03:41:04.266053: step: 392/469, loss: 0.027209313586354256
2023-01-24 03:41:04.945584: step: 394/469, loss: 0.08768302947282791
2023-01-24 03:41:05.543253: step: 396/469, loss: 0.05510547012090683
2023-01-24 03:41:06.128157: step: 398/469, loss: 0.018466763198375702
2023-01-24 03:41:06.739586: step: 400/469, loss: 0.01697220467031002
2023-01-24 03:41:07.343930: step: 402/469, loss: 0.03475261107087135
2023-01-24 03:41:07.915365: step: 404/469, loss: 0.04525039345026016
2023-01-24 03:41:08.490514: step: 406/469, loss: 0.02501925826072693
2023-01-24 03:41:09.091056: step: 408/469, loss: 0.006451896391808987
2023-01-24 03:41:09.726582: step: 410/469, loss: 0.04958367347717285
2023-01-24 03:41:10.313197: step: 412/469, loss: 0.015868689864873886
2023-01-24 03:41:10.986683: step: 414/469, loss: 0.011564032174646854
2023-01-24 03:41:11.635337: step: 416/469, loss: 0.16424602270126343
2023-01-24 03:41:12.352737: step: 418/469, loss: 0.050051528960466385
2023-01-24 03:41:12.944990: step: 420/469, loss: 0.05874348431825638
2023-01-24 03:41:13.591984: step: 422/469, loss: 0.26968201994895935
2023-01-24 03:41:14.101631: step: 424/469, loss: 0.0008949778275564313
2023-01-24 03:41:14.711155: step: 426/469, loss: 0.02027851715683937
2023-01-24 03:41:15.298806: step: 428/469, loss: 0.0919344499707222
2023-01-24 03:41:15.894302: step: 430/469, loss: 0.0019553264137357473
2023-01-24 03:41:16.552103: step: 432/469, loss: 0.09591136872768402
2023-01-24 03:41:17.233609: step: 434/469, loss: 0.023648599162697792
2023-01-24 03:41:17.915653: step: 436/469, loss: 0.0690121278166771
2023-01-24 03:41:18.531735: step: 438/469, loss: 0.009107696823775768
2023-01-24 03:41:19.138350: step: 440/469, loss: 0.07664472609758377
2023-01-24 03:41:19.816371: step: 442/469, loss: 0.058984462171792984
2023-01-24 03:41:20.427960: step: 444/469, loss: 0.1856195330619812
2023-01-24 03:41:21.063361: step: 446/469, loss: 0.025817250832915306
2023-01-24 03:41:21.679686: step: 448/469, loss: 0.008321426808834076
2023-01-24 03:41:22.293851: step: 450/469, loss: 0.10565192252397537
2023-01-24 03:41:22.910908: step: 452/469, loss: 0.026837600395083427
2023-01-24 03:41:23.471261: step: 454/469, loss: 0.04784046486020088
2023-01-24 03:41:24.012048: step: 456/469, loss: 0.002765099285170436
2023-01-24 03:41:24.594078: step: 458/469, loss: 0.05832146480679512
2023-01-24 03:41:25.210945: step: 460/469, loss: 0.0680270865559578
2023-01-24 03:41:25.789208: step: 462/469, loss: 0.06666941195726395
2023-01-24 03:41:26.416325: step: 464/469, loss: 0.13499917089939117
2023-01-24 03:41:27.088674: step: 466/469, loss: 0.02597840130329132
2023-01-24 03:41:27.722756: step: 468/469, loss: 0.07810312509536743
2023-01-24 03:41:28.300385: step: 470/469, loss: 0.04390675574541092
2023-01-24 03:41:28.959246: step: 472/469, loss: 0.01453032810240984
2023-01-24 03:41:29.585045: step: 474/469, loss: 0.025088896974921227
2023-01-24 03:41:30.278752: step: 476/469, loss: 0.09662743657827377
2023-01-24 03:41:30.921631: step: 478/469, loss: 0.035653889179229736
2023-01-24 03:41:31.535142: step: 480/469, loss: 0.02839694544672966
2023-01-24 03:41:32.162811: step: 482/469, loss: 0.036323752254247665
2023-01-24 03:41:32.908161: step: 484/469, loss: 0.0936509370803833
2023-01-24 03:41:33.489157: step: 486/469, loss: 0.07789144665002823
2023-01-24 03:41:34.129233: step: 488/469, loss: 0.045089107006788254
2023-01-24 03:41:34.731838: step: 490/469, loss: 0.006903240457177162
2023-01-24 03:41:35.421437: step: 492/469, loss: 0.023016300052404404
2023-01-24 03:41:36.109049: step: 494/469, loss: 0.08976443111896515
2023-01-24 03:41:36.738640: step: 496/469, loss: 0.38846355676651
2023-01-24 03:41:37.279783: step: 498/469, loss: 0.018937893211841583
2023-01-24 03:41:37.864045: step: 500/469, loss: 0.022624827921390533
2023-01-24 03:41:38.494317: step: 502/469, loss: 0.04228555038571358
2023-01-24 03:41:39.140021: step: 504/469, loss: 0.07831253111362457
2023-01-24 03:41:39.919918: step: 506/469, loss: 0.0061602178029716015
2023-01-24 03:41:40.576121: step: 508/469, loss: 0.009053698740899563
2023-01-24 03:41:41.184033: step: 510/469, loss: 0.028699707239866257
2023-01-24 03:41:41.875905: step: 512/469, loss: 0.05716666206717491
2023-01-24 03:41:42.452554: step: 514/469, loss: 0.05631757900118828
2023-01-24 03:41:43.157186: step: 516/469, loss: 0.01383176352828741
2023-01-24 03:41:43.806701: step: 518/469, loss: 0.07788243889808655
2023-01-24 03:41:44.466500: step: 520/469, loss: 0.11175289750099182
2023-01-24 03:41:45.080132: step: 522/469, loss: 0.12618686258792877
2023-01-24 03:41:45.713278: step: 524/469, loss: 0.0342743918299675
2023-01-24 03:41:46.335829: step: 526/469, loss: 0.0502798929810524
2023-01-24 03:41:46.995775: step: 528/469, loss: 0.030329961329698563
2023-01-24 03:41:47.641178: step: 530/469, loss: 0.03982508182525635
2023-01-24 03:41:48.185149: step: 532/469, loss: 0.2980542778968811
2023-01-24 03:41:48.811028: step: 534/469, loss: 0.03202463313937187
2023-01-24 03:41:49.502283: step: 536/469, loss: 0.03793339058756828
2023-01-24 03:41:50.084156: step: 538/469, loss: 0.12230332940816879
2023-01-24 03:41:50.733342: step: 540/469, loss: 0.13345609605312347
2023-01-24 03:41:51.384499: step: 542/469, loss: 0.012067705392837524
2023-01-24 03:41:51.979049: step: 544/469, loss: 0.029101772233843803
2023-01-24 03:41:52.620863: step: 546/469, loss: 0.033134300261735916
2023-01-24 03:41:53.272208: step: 548/469, loss: 0.027724526822566986
2023-01-24 03:41:53.937710: step: 550/469, loss: 0.03329896926879883
2023-01-24 03:41:54.539709: step: 552/469, loss: 0.40814974904060364
2023-01-24 03:41:55.144195: step: 554/469, loss: 0.16827653348445892
2023-01-24 03:41:55.810274: step: 556/469, loss: 0.037233296781778336
2023-01-24 03:41:56.381063: step: 558/469, loss: 0.025751609355211258
2023-01-24 03:41:57.031392: step: 560/469, loss: 0.030713330954313278
2023-01-24 03:41:57.639540: step: 562/469, loss: 0.10262533277273178
2023-01-24 03:41:58.242036: step: 564/469, loss: 0.07401344925165176
2023-01-24 03:41:58.855366: step: 566/469, loss: 0.0704004168510437
2023-01-24 03:41:59.497871: step: 568/469, loss: 0.13814091682434082
2023-01-24 03:42:00.112195: step: 570/469, loss: 0.06557688862085342
2023-01-24 03:42:00.740078: step: 572/469, loss: 0.02300243265926838
2023-01-24 03:42:01.355096: step: 574/469, loss: 0.0038402474019676447
2023-01-24 03:42:01.944939: step: 576/469, loss: 0.04973436892032623
2023-01-24 03:42:02.578748: step: 578/469, loss: 0.05711760371923447
2023-01-24 03:42:03.183262: step: 580/469, loss: 0.06349515914916992
2023-01-24 03:42:03.825994: step: 582/469, loss: 0.030135851353406906
2023-01-24 03:42:04.437772: step: 584/469, loss: 0.04700420796871185
2023-01-24 03:42:05.031910: step: 586/469, loss: 0.075089231133461
2023-01-24 03:42:05.692873: step: 588/469, loss: 0.08240267634391785
2023-01-24 03:42:06.358404: step: 590/469, loss: 0.15979255735874176
2023-01-24 03:42:06.952617: step: 592/469, loss: 0.011902032420039177
2023-01-24 03:42:07.560110: step: 594/469, loss: 0.04692215099930763
2023-01-24 03:42:08.170503: step: 596/469, loss: 0.056545473635196686
2023-01-24 03:42:08.855368: step: 598/469, loss: 0.04550258442759514
2023-01-24 03:42:09.507356: step: 600/469, loss: 0.07504047453403473
2023-01-24 03:42:10.146746: step: 602/469, loss: 0.006439357530325651
2023-01-24 03:42:10.947388: step: 604/469, loss: 0.175323486328125
2023-01-24 03:42:11.583623: step: 606/469, loss: 0.05155857652425766
2023-01-24 03:42:12.220292: step: 608/469, loss: 0.10046927630901337
2023-01-24 03:42:12.898557: step: 610/469, loss: 0.03589603677392006
2023-01-24 03:42:13.547596: step: 612/469, loss: 0.2100471705198288
2023-01-24 03:42:14.190641: step: 614/469, loss: 0.016872920095920563
2023-01-24 03:42:14.817693: step: 616/469, loss: 0.09207411110401154
2023-01-24 03:42:15.443418: step: 618/469, loss: 0.019891807809472084
2023-01-24 03:42:16.023938: step: 620/469, loss: 0.015381723642349243
2023-01-24 03:42:16.677391: step: 622/469, loss: 0.08633366227149963
2023-01-24 03:42:17.323799: step: 624/469, loss: 0.030681993812322617
2023-01-24 03:42:17.940989: step: 626/469, loss: 0.019833922386169434
2023-01-24 03:42:18.590616: step: 628/469, loss: 0.05075858160853386
2023-01-24 03:42:19.191797: step: 630/469, loss: 0.02489897422492504
2023-01-24 03:42:19.814447: step: 632/469, loss: 0.08151629567146301
2023-01-24 03:42:20.448200: step: 634/469, loss: 0.2602803409099579
2023-01-24 03:42:21.056558: step: 636/469, loss: 0.028771480545401573
2023-01-24 03:42:21.717284: step: 638/469, loss: 0.10833048075437546
2023-01-24 03:42:22.337667: step: 640/469, loss: 0.22582930326461792
2023-01-24 03:42:22.994468: step: 642/469, loss: 0.011523720808327198
2023-01-24 03:42:23.724952: step: 644/469, loss: 0.018657146021723747
2023-01-24 03:42:24.373426: step: 646/469, loss: 0.04349122568964958
2023-01-24 03:42:24.990901: step: 648/469, loss: 0.2706346809864044
2023-01-24 03:42:25.554748: step: 650/469, loss: 0.03992457315325737
2023-01-24 03:42:26.213871: step: 652/469, loss: 0.03795793280005455
2023-01-24 03:42:26.785270: step: 654/469, loss: 0.04529811441898346
2023-01-24 03:42:27.381443: step: 656/469, loss: 0.08681243658065796
2023-01-24 03:42:28.015704: step: 658/469, loss: 0.035051338374614716
2023-01-24 03:42:28.615905: step: 660/469, loss: 0.033167291432619095
2023-01-24 03:42:29.224620: step: 662/469, loss: 0.03456336259841919
2023-01-24 03:42:29.838216: step: 664/469, loss: 0.012135052122175694
2023-01-24 03:42:30.449474: step: 666/469, loss: 0.0567280538380146
2023-01-24 03:42:31.114012: step: 668/469, loss: 0.003694563638418913
2023-01-24 03:42:31.749724: step: 670/469, loss: 0.04029498249292374
2023-01-24 03:42:32.363135: step: 672/469, loss: 0.04340934008359909
2023-01-24 03:42:32.995948: step: 674/469, loss: 0.044494953006505966
2023-01-24 03:42:33.560052: step: 676/469, loss: 0.005487445276230574
2023-01-24 03:42:34.166156: step: 678/469, loss: 0.11133415997028351
2023-01-24 03:42:34.835945: step: 680/469, loss: 0.06047096475958824
2023-01-24 03:42:35.556976: step: 682/469, loss: 0.03617478907108307
2023-01-24 03:42:36.159170: step: 684/469, loss: 0.03409360349178314
2023-01-24 03:42:36.828468: step: 686/469, loss: 0.07524754852056503
2023-01-24 03:42:37.447020: step: 688/469, loss: 0.11170642077922821
2023-01-24 03:42:38.036173: step: 690/469, loss: 0.06437705457210541
2023-01-24 03:42:38.769290: step: 692/469, loss: 0.0658484622836113
2023-01-24 03:42:39.351459: step: 694/469, loss: 0.03594261035323143
2023-01-24 03:42:39.963792: step: 696/469, loss: 0.11162786185741425
2023-01-24 03:42:40.679559: step: 698/469, loss: 0.03382645919919014
2023-01-24 03:42:41.300977: step: 700/469, loss: 0.8750171065330505
2023-01-24 03:42:41.968886: step: 702/469, loss: 0.023832466453313828
2023-01-24 03:42:42.451523: step: 704/469, loss: 0.029626909643411636
2023-01-24 03:42:43.082992: step: 706/469, loss: 0.058364421129226685
2023-01-24 03:42:43.692064: step: 708/469, loss: 0.08198067545890808
2023-01-24 03:42:44.341970: step: 710/469, loss: 0.0586685948073864
2023-01-24 03:42:44.985877: step: 712/469, loss: 0.17847940325737
2023-01-24 03:42:45.557052: step: 714/469, loss: 0.040565043687820435
2023-01-24 03:42:46.183938: step: 716/469, loss: 0.11069989949464798
2023-01-24 03:42:46.834415: step: 718/469, loss: 0.29169994592666626
2023-01-24 03:42:47.506391: step: 720/469, loss: 0.034519705921411514
2023-01-24 03:42:48.218141: step: 722/469, loss: 0.008544232696294785
2023-01-24 03:42:48.855002: step: 724/469, loss: 0.02701670303940773
2023-01-24 03:42:49.513744: step: 726/469, loss: 0.07301875203847885
2023-01-24 03:42:50.171067: step: 728/469, loss: 0.07606630027294159
2023-01-24 03:42:50.740474: step: 730/469, loss: 0.041152600198984146
2023-01-24 03:42:51.327461: step: 732/469, loss: 0.05740166828036308
2023-01-24 03:42:51.965544: step: 734/469, loss: 0.08332406729459763
2023-01-24 03:42:52.563022: step: 736/469, loss: 0.2419954389333725
2023-01-24 03:42:53.181011: step: 738/469, loss: 0.03665747493505478
2023-01-24 03:42:53.815061: step: 740/469, loss: 0.025403790175914764
2023-01-24 03:42:54.407902: step: 742/469, loss: 0.008551633916795254
2023-01-24 03:42:54.955656: step: 744/469, loss: 0.002937992801889777
2023-01-24 03:42:55.570872: step: 746/469, loss: 0.11794460564851761
2023-01-24 03:42:56.260238: step: 748/469, loss: 0.0707455426454544
2023-01-24 03:42:56.877080: step: 750/469, loss: 0.029475955292582512
2023-01-24 03:42:57.451026: step: 752/469, loss: 0.19640345871448517
2023-01-24 03:42:58.120851: step: 754/469, loss: 0.012563933618366718
2023-01-24 03:42:58.794966: step: 756/469, loss: 0.05138123780488968
2023-01-24 03:42:59.383143: step: 758/469, loss: 0.27541208267211914
2023-01-24 03:42:59.985219: step: 760/469, loss: 0.016575973480939865
2023-01-24 03:43:00.707943: step: 762/469, loss: 0.056157324463129044
2023-01-24 03:43:01.340756: step: 764/469, loss: 0.19806243479251862
2023-01-24 03:43:01.948746: step: 766/469, loss: 0.03232935070991516
2023-01-24 03:43:02.576849: step: 768/469, loss: 0.01980048045516014
2023-01-24 03:43:03.245178: step: 770/469, loss: 0.4653545022010803
2023-01-24 03:43:03.854713: step: 772/469, loss: 0.07322318851947784
2023-01-24 03:43:04.475252: step: 774/469, loss: 0.0887472853064537
2023-01-24 03:43:05.134229: step: 776/469, loss: 0.012273302301764488
2023-01-24 03:43:05.758473: step: 778/469, loss: 0.02280343882739544
2023-01-24 03:43:06.391293: step: 780/469, loss: 0.012945477850735188
2023-01-24 03:43:06.971100: step: 782/469, loss: 0.09715475142002106
2023-01-24 03:43:07.615041: step: 784/469, loss: 0.13165117800235748
2023-01-24 03:43:08.202396: step: 786/469, loss: 0.02064213901758194
2023-01-24 03:43:08.886893: step: 788/469, loss: 0.018043173477053642
2023-01-24 03:43:09.515924: step: 790/469, loss: 0.05820675566792488
2023-01-24 03:43:10.120673: step: 792/469, loss: 0.012131190858781338
2023-01-24 03:43:10.745631: step: 794/469, loss: 0.035868994891643524
2023-01-24 03:43:11.321846: step: 796/469, loss: 0.01868510991334915
2023-01-24 03:43:11.953647: step: 798/469, loss: 0.4150649905204773
2023-01-24 03:43:12.548753: step: 800/469, loss: 0.028201915323734283
2023-01-24 03:43:13.104085: step: 802/469, loss: 0.016570623964071274
2023-01-24 03:43:13.745041: step: 804/469, loss: 0.06812107563018799
2023-01-24 03:43:14.369723: step: 806/469, loss: 0.06283491104841232
2023-01-24 03:43:15.011631: step: 808/469, loss: 0.0259453933686018
2023-01-24 03:43:15.652015: step: 810/469, loss: 0.05941562354564667
2023-01-24 03:43:16.236395: step: 812/469, loss: 0.023522358387708664
2023-01-24 03:43:16.861583: step: 814/469, loss: 0.044914744794368744
2023-01-24 03:43:17.467037: step: 816/469, loss: 0.013948260806500912
2023-01-24 03:43:18.061915: step: 818/469, loss: 0.06239095330238342
2023-01-24 03:43:18.708631: step: 820/469, loss: 0.09571448713541031
2023-01-24 03:43:19.406690: step: 822/469, loss: 0.06513001769781113
2023-01-24 03:43:20.106819: step: 824/469, loss: 0.029995225369930267
2023-01-24 03:43:20.720784: step: 826/469, loss: 0.007673286367207766
2023-01-24 03:43:21.356309: step: 828/469, loss: 0.029067866504192352
2023-01-24 03:43:21.984115: step: 830/469, loss: 0.04245278239250183
2023-01-24 03:43:22.629713: step: 832/469, loss: 0.021359845995903015
2023-01-24 03:43:23.286545: step: 834/469, loss: 0.030331697314977646
2023-01-24 03:43:23.893382: step: 836/469, loss: 0.02838105894625187
2023-01-24 03:43:24.530112: step: 838/469, loss: 0.10588711500167847
2023-01-24 03:43:25.207026: step: 840/469, loss: 0.044374190270900726
2023-01-24 03:43:25.913670: step: 842/469, loss: 0.5629298686981201
2023-01-24 03:43:26.557455: step: 844/469, loss: 0.05076729506254196
2023-01-24 03:43:27.159873: step: 846/469, loss: 0.02145289070904255
2023-01-24 03:43:27.816510: step: 848/469, loss: 0.035037655383348465
2023-01-24 03:43:28.439608: step: 850/469, loss: 0.029345309361815453
2023-01-24 03:43:29.059284: step: 852/469, loss: 0.04547927901148796
2023-01-24 03:43:29.723190: step: 854/469, loss: 0.019605614244937897
2023-01-24 03:43:30.436970: step: 856/469, loss: 0.061750419437885284
2023-01-24 03:43:31.071132: step: 858/469, loss: 0.00015733565669506788
2023-01-24 03:43:31.799684: step: 860/469, loss: 0.09106114506721497
2023-01-24 03:43:32.313483: step: 862/469, loss: 0.038240257650613785
2023-01-24 03:43:32.944190: step: 864/469, loss: 0.032368253916502
2023-01-24 03:43:33.613552: step: 866/469, loss: 0.02331375889480114
2023-01-24 03:43:34.306119: step: 868/469, loss: 0.0046402099542319775
2023-01-24 03:43:35.009514: step: 870/469, loss: 0.01011233776807785
2023-01-24 03:43:35.626506: step: 872/469, loss: 0.03311903774738312
2023-01-24 03:43:36.183706: step: 874/469, loss: 0.008461453020572662
2023-01-24 03:43:36.841492: step: 876/469, loss: 0.029028356075286865
2023-01-24 03:43:37.423841: step: 878/469, loss: 0.021870478987693787
2023-01-24 03:43:38.044237: step: 880/469, loss: 0.020664963871240616
2023-01-24 03:43:38.588533: step: 882/469, loss: 0.06315284967422485
2023-01-24 03:43:39.141710: step: 884/469, loss: 0.08060536533594131
2023-01-24 03:43:39.747818: step: 886/469, loss: 0.0008277355809696019
2023-01-24 03:43:40.395417: step: 888/469, loss: 0.08211325109004974
2023-01-24 03:43:40.995897: step: 890/469, loss: 0.12384329736232758
2023-01-24 03:43:41.657777: step: 892/469, loss: 0.02858704701066017
2023-01-24 03:43:42.285675: step: 894/469, loss: 0.06107771769165993
2023-01-24 03:43:42.936147: step: 896/469, loss: 0.017599692568182945
2023-01-24 03:43:43.580640: step: 898/469, loss: 0.016021881252527237
2023-01-24 03:43:44.214693: step: 900/469, loss: 0.12623955309391022
2023-01-24 03:43:44.881860: step: 902/469, loss: 0.01892252080142498
2023-01-24 03:43:45.530798: step: 904/469, loss: 0.04684660956263542
2023-01-24 03:43:46.165533: step: 906/469, loss: 0.027284299954771996
2023-01-24 03:43:46.774236: step: 908/469, loss: 0.05409190058708191
2023-01-24 03:43:47.436554: step: 910/469, loss: 0.038611020892858505
2023-01-24 03:43:48.046094: step: 912/469, loss: 0.008061953820288181
2023-01-24 03:43:48.646733: step: 914/469, loss: 0.14487463235855103
2023-01-24 03:43:49.329082: step: 916/469, loss: 0.2800885736942291
2023-01-24 03:43:50.000703: step: 918/469, loss: 0.037585340440273285
2023-01-24 03:43:50.615472: step: 920/469, loss: 0.2513177990913391
2023-01-24 03:43:51.228977: step: 922/469, loss: 0.05311236158013344
2023-01-24 03:43:51.916340: step: 924/469, loss: 0.3178267180919647
2023-01-24 03:43:52.586585: step: 926/469, loss: 0.08004887402057648
2023-01-24 03:43:53.193363: step: 928/469, loss: 0.06739316135644913
2023-01-24 03:43:53.839663: step: 930/469, loss: 0.04459620267152786
2023-01-24 03:43:54.494883: step: 932/469, loss: 0.055536992847919464
2023-01-24 03:43:55.121691: step: 934/469, loss: 0.04985564574599266
2023-01-24 03:43:55.706485: step: 936/469, loss: 0.22679363191127777
2023-01-24 03:43:56.324793: step: 938/469, loss: 0.10756853967905045
==================================================
Loss: 0.078
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3406569756001574, 'r': 0.2986404605830602, 'f1': 0.31826799338174466}, 'combined': 0.23451325828128552, 'epoch': 22}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3235632902925321, 'r': 0.25103537984269647, 'f1': 0.28272196823087814}, 'combined': 0.15421198267138805, 'epoch': 22}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3376277788805081, 'r': 0.2934222442642746, 'f1': 0.3139766958929396}, 'combined': 0.23135124960532388, 'epoch': 22}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33205101045371527, 'r': 0.2551901635691865, 'f1': 0.2885906350554794}, 'combined': 0.1574130736666251, 'epoch': 22}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32639529505582143, 'r': 0.2941893076878846, 'f1': 0.30945661706889255}, 'combined': 0.22802066520865766, 'epoch': 22}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3169314267288162, 'r': 0.2502395437026243, 'f1': 0.2796644389232805}, 'combined': 0.15254423941269846, 'epoch': 22}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.38839285714285715, 'r': 0.3107142857142857, 'f1': 0.34523809523809523}, 'combined': 0.23015873015873015, 'epoch': 22}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36363636363636365, 'r': 0.34782608695652173, 'f1': 0.3555555555555555}, 'combined': 0.17777777777777776, 'epoch': 22}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.475, 'r': 0.16379310344827586, 'f1': 0.24358974358974356}, 'combined': 0.16239316239316237, 'epoch': 22}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:46:41.476972: step: 2/469, loss: 1.2357395887374878
2023-01-24 03:46:42.098853: step: 4/469, loss: 0.024183563888072968
2023-01-24 03:46:42.685846: step: 6/469, loss: 0.0776687040925026
2023-01-24 03:46:43.311804: step: 8/469, loss: 0.0249489713460207
2023-01-24 03:46:43.936865: step: 10/469, loss: 0.0044220928102731705
2023-01-24 03:46:44.597061: step: 12/469, loss: 0.006003873888403177
2023-01-24 03:46:45.259766: step: 14/469, loss: 0.004591218661516905
2023-01-24 03:46:45.841690: step: 16/469, loss: 0.017270060256123543
2023-01-24 03:46:46.528715: step: 18/469, loss: 0.04863632470369339
2023-01-24 03:46:47.180298: step: 20/469, loss: 0.016850149258971214
2023-01-24 03:46:47.749414: step: 22/469, loss: 0.005202325060963631
2023-01-24 03:46:48.381901: step: 24/469, loss: 0.027514085173606873
2023-01-24 03:46:48.982095: step: 26/469, loss: 0.026645144447684288
2023-01-24 03:46:49.599352: step: 28/469, loss: 0.01198261883109808
2023-01-24 03:46:50.270623: step: 30/469, loss: 0.00844186544418335
2023-01-24 03:46:50.896646: step: 32/469, loss: 0.013920240104198456
2023-01-24 03:46:51.513786: step: 34/469, loss: 0.029003195464611053
2023-01-24 03:46:52.160646: step: 36/469, loss: 0.027369927614927292
2023-01-24 03:46:52.835817: step: 38/469, loss: 0.029376836493611336
2023-01-24 03:46:53.461716: step: 40/469, loss: 0.06202325597405434
2023-01-24 03:46:54.052031: step: 42/469, loss: 0.036938123404979706
2023-01-24 03:46:54.610909: step: 44/469, loss: 0.04467153921723366
2023-01-24 03:46:55.166320: step: 46/469, loss: 0.009959367103874683
2023-01-24 03:46:55.849613: step: 48/469, loss: 0.021179791539907455
2023-01-24 03:46:56.531801: step: 50/469, loss: 0.050611015409231186
2023-01-24 03:46:57.087974: step: 52/469, loss: 0.004724889528006315
2023-01-24 03:46:57.690835: step: 54/469, loss: 0.05585126578807831
2023-01-24 03:46:58.357312: step: 56/469, loss: 0.015907835215330124
2023-01-24 03:46:58.986493: step: 58/469, loss: 0.00852515920996666
2023-01-24 03:46:59.628189: step: 60/469, loss: 0.03204323351383209
2023-01-24 03:47:00.241301: step: 62/469, loss: 0.016114724799990654
2023-01-24 03:47:00.796096: step: 64/469, loss: 0.024006161838769913
2023-01-24 03:47:01.339472: step: 66/469, loss: 0.04767401143908501
2023-01-24 03:47:01.965791: step: 68/469, loss: 0.11314443498849869
2023-01-24 03:47:02.560866: step: 70/469, loss: 0.01779489405453205
2023-01-24 03:47:03.136711: step: 72/469, loss: 0.0358414426445961
2023-01-24 03:47:03.841763: step: 74/469, loss: 0.10481178015470505
2023-01-24 03:47:04.462276: step: 76/469, loss: 0.021338336169719696
2023-01-24 03:47:05.069999: step: 78/469, loss: 0.06205512583255768
2023-01-24 03:47:05.756793: step: 80/469, loss: 0.0201254952698946
2023-01-24 03:47:06.388759: step: 82/469, loss: 0.7630947828292847
2023-01-24 03:47:07.021836: step: 84/469, loss: 0.02397053875029087
2023-01-24 03:47:07.646266: step: 86/469, loss: 0.09846276789903641
2023-01-24 03:47:08.170800: step: 88/469, loss: 0.05467109754681587
2023-01-24 03:47:08.771028: step: 90/469, loss: 0.04410193860530853
2023-01-24 03:47:09.394445: step: 92/469, loss: 0.03433063253760338
2023-01-24 03:47:10.015332: step: 94/469, loss: 0.0014956542290747166
2023-01-24 03:47:10.648118: step: 96/469, loss: 0.017814695835113525
2023-01-24 03:47:11.303766: step: 98/469, loss: 0.061385128647089005
2023-01-24 03:47:11.977137: step: 100/469, loss: 0.07646140456199646
2023-01-24 03:47:12.554035: step: 102/469, loss: 0.05072186887264252
2023-01-24 03:47:13.171135: step: 104/469, loss: 0.011625583283603191
2023-01-24 03:47:13.806536: step: 106/469, loss: 0.006602386943995953
2023-01-24 03:47:14.414049: step: 108/469, loss: 0.05438736826181412
2023-01-24 03:47:15.011486: step: 110/469, loss: 0.0855780616402626
2023-01-24 03:47:15.641318: step: 112/469, loss: 0.047850873321294785
2023-01-24 03:47:16.370053: step: 114/469, loss: 0.04076141491532326
2023-01-24 03:47:16.976469: step: 116/469, loss: 0.019435521215200424
2023-01-24 03:47:17.624369: step: 118/469, loss: 0.028983084484934807
2023-01-24 03:47:18.179539: step: 120/469, loss: 0.016191082075238228
2023-01-24 03:47:18.822627: step: 122/469, loss: 0.04412242770195007
2023-01-24 03:47:19.420240: step: 124/469, loss: 0.08400098234415054
2023-01-24 03:47:20.003176: step: 126/469, loss: 0.029566580429673195
2023-01-24 03:47:20.635522: step: 128/469, loss: 0.3515491783618927
2023-01-24 03:47:21.279371: step: 130/469, loss: 0.11477603018283844
2023-01-24 03:47:21.861699: step: 132/469, loss: 0.03230782970786095
2023-01-24 03:47:22.487844: step: 134/469, loss: 0.010962975211441517
2023-01-24 03:47:23.073175: step: 136/469, loss: 0.01593821682035923
2023-01-24 03:47:23.667372: step: 138/469, loss: 0.01611877791583538
2023-01-24 03:47:24.268942: step: 140/469, loss: 0.04281977564096451
2023-01-24 03:47:24.891226: step: 142/469, loss: 0.005105625372380018
2023-01-24 03:47:25.510674: step: 144/469, loss: 0.06341095268726349
2023-01-24 03:47:26.175964: step: 146/469, loss: 0.04355448856949806
2023-01-24 03:47:26.865519: step: 148/469, loss: 0.0710495337843895
2023-01-24 03:47:27.454693: step: 150/469, loss: 0.5553318858146667
2023-01-24 03:47:28.088131: step: 152/469, loss: 0.0023809100966900587
2023-01-24 03:47:28.664472: step: 154/469, loss: 0.08436071127653122
2023-01-24 03:47:29.267632: step: 156/469, loss: 0.061742544174194336
2023-01-24 03:47:29.954328: step: 158/469, loss: 0.025910230353474617
2023-01-24 03:47:30.613298: step: 160/469, loss: 0.04920036345720291
2023-01-24 03:47:31.232506: step: 162/469, loss: 0.02608680911362171
2023-01-24 03:47:31.873724: step: 164/469, loss: 0.03181438520550728
2023-01-24 03:47:32.527036: step: 166/469, loss: 0.14423991739749908
2023-01-24 03:47:33.134296: step: 168/469, loss: 0.1029396802186966
2023-01-24 03:47:33.740961: step: 170/469, loss: 0.02797544188797474
2023-01-24 03:47:34.418734: step: 172/469, loss: 0.07917007803916931
2023-01-24 03:47:34.968663: step: 174/469, loss: 0.10432194918394089
2023-01-24 03:47:35.638916: step: 176/469, loss: 0.03921284154057503
2023-01-24 03:47:36.287083: step: 178/469, loss: 0.07324020564556122
2023-01-24 03:47:37.021598: step: 180/469, loss: 0.04576383903622627
2023-01-24 03:47:37.727880: step: 182/469, loss: 0.010903830640017986
2023-01-24 03:47:38.325870: step: 184/469, loss: 0.05258685722947121
2023-01-24 03:47:38.955706: step: 186/469, loss: 0.02395584061741829
2023-01-24 03:47:39.531639: step: 188/469, loss: 0.026599610224366188
2023-01-24 03:47:40.104790: step: 190/469, loss: 0.0020521513652056456
2023-01-24 03:47:40.723827: step: 192/469, loss: 0.011747482232749462
2023-01-24 03:47:41.323669: step: 194/469, loss: 0.01697644405066967
2023-01-24 03:47:41.936678: step: 196/469, loss: 0.03752192109823227
2023-01-24 03:47:42.518315: step: 198/469, loss: 0.031641364097595215
2023-01-24 03:47:43.288279: step: 200/469, loss: 0.01779523678123951
2023-01-24 03:47:43.942955: step: 202/469, loss: 0.22139151394367218
2023-01-24 03:47:44.627683: step: 204/469, loss: 0.013042815029621124
2023-01-24 03:47:45.180402: step: 206/469, loss: 0.017464587464928627
2023-01-24 03:47:45.789286: step: 208/469, loss: 0.006439428776502609
2023-01-24 03:47:46.538689: step: 210/469, loss: 0.018046630546450615
2023-01-24 03:47:47.217280: step: 212/469, loss: 0.13874879479408264
2023-01-24 03:47:47.817398: step: 214/469, loss: 0.032536838203668594
2023-01-24 03:47:48.499703: step: 216/469, loss: 0.03146125376224518
2023-01-24 03:47:49.139868: step: 218/469, loss: 0.02002551779150963
2023-01-24 03:47:49.741895: step: 220/469, loss: 0.020317958667874336
2023-01-24 03:47:50.327433: step: 222/469, loss: 0.35585200786590576
2023-01-24 03:47:51.059068: step: 224/469, loss: 0.026581084355711937
2023-01-24 03:47:51.638265: step: 226/469, loss: 0.001094404375180602
2023-01-24 03:47:52.292288: step: 228/469, loss: 0.018660511821508408
2023-01-24 03:47:52.901002: step: 230/469, loss: 0.023422103375196457
2023-01-24 03:47:53.543792: step: 232/469, loss: 0.05262136459350586
2023-01-24 03:47:54.175322: step: 234/469, loss: 0.015403765253722668
2023-01-24 03:47:54.891707: step: 236/469, loss: 0.013600052334368229
2023-01-24 03:47:55.480008: step: 238/469, loss: 0.05427788570523262
2023-01-24 03:47:56.051552: step: 240/469, loss: 0.08543679863214493
2023-01-24 03:47:56.701533: step: 242/469, loss: 0.0645485520362854
2023-01-24 03:47:57.442487: step: 244/469, loss: 0.00648009916767478
2023-01-24 03:47:58.086471: step: 246/469, loss: 0.03014432266354561
2023-01-24 03:47:58.610898: step: 248/469, loss: 0.004051559139043093
2023-01-24 03:47:59.204405: step: 250/469, loss: 0.010756065137684345
2023-01-24 03:47:59.776374: step: 252/469, loss: 0.012942900881171227
2023-01-24 03:48:00.401980: step: 254/469, loss: 0.3782583773136139
2023-01-24 03:48:00.984736: step: 256/469, loss: 0.006241234950721264
2023-01-24 03:48:01.678998: step: 258/469, loss: 0.03076982870697975
2023-01-24 03:48:02.255608: step: 260/469, loss: 0.04138808324933052
2023-01-24 03:48:02.837781: step: 262/469, loss: 0.018180401995778084
2023-01-24 03:48:03.540710: step: 264/469, loss: 0.023767195641994476
2023-01-24 03:48:04.216769: step: 266/469, loss: 0.0489799790084362
2023-01-24 03:48:04.881073: step: 268/469, loss: 0.006461685989052057
2023-01-24 03:48:05.553951: step: 270/469, loss: 0.0074934507720172405
2023-01-24 03:48:06.169741: step: 272/469, loss: 0.01630806177854538
2023-01-24 03:48:06.857336: step: 274/469, loss: 0.6623429656028748
2023-01-24 03:48:07.638894: step: 276/469, loss: 0.03137192502617836
2023-01-24 03:48:08.258095: step: 278/469, loss: 0.011359496042132378
2023-01-24 03:48:08.834372: step: 280/469, loss: 0.06348668038845062
2023-01-24 03:48:09.420794: step: 282/469, loss: 0.019177217036485672
2023-01-24 03:48:09.969092: step: 284/469, loss: 0.019112030044198036
2023-01-24 03:48:10.560760: step: 286/469, loss: 0.008358408696949482
2023-01-24 03:48:11.146702: step: 288/469, loss: 0.047255173325538635
2023-01-24 03:48:11.770316: step: 290/469, loss: 0.05162154510617256
2023-01-24 03:48:12.440788: step: 292/469, loss: 0.037955235689878464
2023-01-24 03:48:13.066995: step: 294/469, loss: 0.06755347549915314
2023-01-24 03:48:13.740851: step: 296/469, loss: 0.026413334533572197
2023-01-24 03:48:14.374414: step: 298/469, loss: 0.007649126462638378
2023-01-24 03:48:15.011458: step: 300/469, loss: 0.08559884130954742
2023-01-24 03:48:15.612238: step: 302/469, loss: 0.03458913415670395
2023-01-24 03:48:16.211607: step: 304/469, loss: 0.04814169183373451
2023-01-24 03:48:16.811310: step: 306/469, loss: 0.03001989610493183
2023-01-24 03:48:17.432253: step: 308/469, loss: 0.02405017614364624
2023-01-24 03:48:18.014638: step: 310/469, loss: 0.0034029295202344656
2023-01-24 03:48:18.643469: step: 312/469, loss: 0.006519317161291838
2023-01-24 03:48:19.284773: step: 314/469, loss: 0.13232645392417908
2023-01-24 03:48:19.918095: step: 316/469, loss: 0.029131615534424782
2023-01-24 03:48:20.548186: step: 318/469, loss: 0.056847065687179565
2023-01-24 03:48:21.196910: step: 320/469, loss: 0.02224601060152054
2023-01-24 03:48:21.796845: step: 322/469, loss: 0.03697815164923668
2023-01-24 03:48:22.430043: step: 324/469, loss: 0.001828978885896504
2023-01-24 03:48:23.114850: step: 326/469, loss: 0.020824763923883438
2023-01-24 03:48:23.723980: step: 328/469, loss: 0.03082248568534851
2023-01-24 03:48:24.357638: step: 330/469, loss: 0.03613508865237236
2023-01-24 03:48:24.968474: step: 332/469, loss: 2.1351606845855713
2023-01-24 03:48:25.604768: step: 334/469, loss: 0.07682400941848755
2023-01-24 03:48:26.254499: step: 336/469, loss: 0.006083210464566946
2023-01-24 03:48:26.864623: step: 338/469, loss: 0.04656771197915077
2023-01-24 03:48:27.444462: step: 340/469, loss: 0.7680062055587769
2023-01-24 03:48:28.070417: step: 342/469, loss: 0.02434537373483181
2023-01-24 03:48:28.754961: step: 344/469, loss: 0.0006408179178833961
2023-01-24 03:48:29.408936: step: 346/469, loss: 0.09377032518386841
2023-01-24 03:48:30.014603: step: 348/469, loss: 0.020529458299279213
2023-01-24 03:48:30.690790: step: 350/469, loss: 0.09350648522377014
2023-01-24 03:48:31.368645: step: 352/469, loss: 0.04236915335059166
2023-01-24 03:48:31.965406: step: 354/469, loss: 0.04024454951286316
2023-01-24 03:48:32.582772: step: 356/469, loss: 0.08462707698345184
2023-01-24 03:48:33.274939: step: 358/469, loss: 0.001549765351228416
2023-01-24 03:48:33.883451: step: 360/469, loss: 0.008456028997898102
2023-01-24 03:48:34.484187: step: 362/469, loss: 0.054597094655036926
2023-01-24 03:48:35.121286: step: 364/469, loss: 0.035022981464862823
2023-01-24 03:48:35.728925: step: 366/469, loss: 0.0033466024324297905
2023-01-24 03:48:36.304584: step: 368/469, loss: 0.05445101857185364
2023-01-24 03:48:36.916457: step: 370/469, loss: 0.01942160353064537
2023-01-24 03:48:37.552665: step: 372/469, loss: 0.038416557013988495
2023-01-24 03:48:38.187497: step: 374/469, loss: 0.002653640927746892
2023-01-24 03:48:38.827355: step: 376/469, loss: 0.045215360820293427
2023-01-24 03:48:39.456590: step: 378/469, loss: 0.05492890998721123
2023-01-24 03:48:40.062829: step: 380/469, loss: 0.005246720276772976
2023-01-24 03:48:40.673186: step: 382/469, loss: 0.013209211640059948
2023-01-24 03:48:41.294405: step: 384/469, loss: 0.0067526474595069885
2023-01-24 03:48:41.873065: step: 386/469, loss: 0.05400647222995758
2023-01-24 03:48:42.564068: step: 388/469, loss: 0.07380294054746628
2023-01-24 03:48:43.176049: step: 390/469, loss: 0.09125782549381256
2023-01-24 03:48:43.812304: step: 392/469, loss: 0.02457476034760475
2023-01-24 03:48:44.424908: step: 394/469, loss: 0.04653559625148773
2023-01-24 03:48:45.003214: step: 396/469, loss: 0.025619275867938995
2023-01-24 03:48:45.669033: step: 398/469, loss: 0.014898593537509441
2023-01-24 03:48:46.269699: step: 400/469, loss: 0.018561387434601784
2023-01-24 03:48:46.993300: step: 402/469, loss: 0.06717865914106369
2023-01-24 03:48:47.688578: step: 404/469, loss: 0.07287240773439407
2023-01-24 03:48:48.359722: step: 406/469, loss: 0.051496099680662155
2023-01-24 03:48:49.008718: step: 408/469, loss: 0.24909788370132446
2023-01-24 03:48:49.658646: step: 410/469, loss: 0.08912375569343567
2023-01-24 03:48:50.250306: step: 412/469, loss: 0.030857156962156296
2023-01-24 03:48:50.926527: step: 414/469, loss: 0.08198633044958115
2023-01-24 03:48:51.595830: step: 416/469, loss: 0.03507792949676514
2023-01-24 03:48:52.227463: step: 418/469, loss: 0.02260504849255085
2023-01-24 03:48:52.879887: step: 420/469, loss: 0.01254622358828783
2023-01-24 03:48:53.497329: step: 422/469, loss: 0.016889186576008797
2023-01-24 03:48:54.157994: step: 424/469, loss: 0.014178567565977573
2023-01-24 03:48:54.761574: step: 426/469, loss: 0.03221070393919945
2023-01-24 03:48:55.413495: step: 428/469, loss: 0.020412391051650047
2023-01-24 03:48:56.088378: step: 430/469, loss: 0.03339565172791481
2023-01-24 03:48:56.776525: step: 432/469, loss: 0.009506194852292538
2023-01-24 03:48:57.389193: step: 434/469, loss: 0.029422499239444733
2023-01-24 03:48:58.004718: step: 436/469, loss: 0.04744797199964523
2023-01-24 03:48:58.747169: step: 438/469, loss: 0.014477276243269444
2023-01-24 03:48:59.408025: step: 440/469, loss: 0.05468200519680977
2023-01-24 03:48:59.974044: step: 442/469, loss: 0.029213834553956985
2023-01-24 03:49:00.575297: step: 444/469, loss: 0.03252070024609566
2023-01-24 03:49:01.219556: step: 446/469, loss: 0.02223104238510132
2023-01-24 03:49:01.885963: step: 448/469, loss: 0.003474658355116844
2023-01-24 03:49:02.478786: step: 450/469, loss: 0.06686118990182877
2023-01-24 03:49:03.050371: step: 452/469, loss: 0.021839521825313568
2023-01-24 03:49:03.766858: step: 454/469, loss: 0.20771893858909607
2023-01-24 03:49:04.372721: step: 456/469, loss: 0.008947457186877728
2023-01-24 03:49:05.011237: step: 458/469, loss: 0.020264342427253723
2023-01-24 03:49:05.635968: step: 460/469, loss: 0.04001079499721527
2023-01-24 03:49:06.322922: step: 462/469, loss: 0.10093475133180618
2023-01-24 03:49:06.937148: step: 464/469, loss: 0.038687583059072495
2023-01-24 03:49:07.613535: step: 466/469, loss: 0.033658649772405624
2023-01-24 03:49:08.302514: step: 468/469, loss: 0.11991773545742035
2023-01-24 03:49:08.967656: step: 470/469, loss: 0.06612705439329147
2023-01-24 03:49:09.573836: step: 472/469, loss: 0.003712458536028862
2023-01-24 03:49:10.184432: step: 474/469, loss: 0.03467660769820213
2023-01-24 03:49:10.757129: step: 476/469, loss: 0.02436213009059429
2023-01-24 03:49:11.305784: step: 478/469, loss: 0.10271177440881729
2023-01-24 03:49:11.922536: step: 480/469, loss: 0.026616176590323448
2023-01-24 03:49:12.478565: step: 482/469, loss: 0.03505128622055054
2023-01-24 03:49:13.115359: step: 484/469, loss: 0.009781846776604652
2023-01-24 03:49:13.685706: step: 486/469, loss: 0.009833168238401413
2023-01-24 03:49:14.327628: step: 488/469, loss: 0.11808013170957565
2023-01-24 03:49:14.902074: step: 490/469, loss: 0.0261073037981987
2023-01-24 03:49:15.502121: step: 492/469, loss: 0.037615641951560974
2023-01-24 03:49:16.179799: step: 494/469, loss: 0.056649237871170044
2023-01-24 03:49:16.862087: step: 496/469, loss: 0.02912292256951332
2023-01-24 03:49:17.480250: step: 498/469, loss: 0.02152920514345169
2023-01-24 03:49:18.175582: step: 500/469, loss: 0.015567835420370102
2023-01-24 03:49:18.856468: step: 502/469, loss: 0.006007621064782143
2023-01-24 03:49:19.428708: step: 504/469, loss: 0.030542412772774696
2023-01-24 03:49:20.037284: step: 506/469, loss: 0.009135408326983452
2023-01-24 03:49:20.627557: step: 508/469, loss: 0.07108505070209503
2023-01-24 03:49:21.320985: step: 510/469, loss: 0.09674370288848877
2023-01-24 03:49:21.893083: step: 512/469, loss: 0.02525142952799797
2023-01-24 03:49:22.480099: step: 514/469, loss: 0.0644746795296669
2023-01-24 03:49:23.117127: step: 516/469, loss: 0.048930805176496506
2023-01-24 03:49:23.768958: step: 518/469, loss: 0.07319412380456924
2023-01-24 03:49:24.344680: step: 520/469, loss: 0.036929722875356674
2023-01-24 03:49:25.035077: step: 522/469, loss: 0.3169757127761841
2023-01-24 03:49:25.657687: step: 524/469, loss: 0.053899671882390976
2023-01-24 03:49:26.276873: step: 526/469, loss: 0.06712814420461655
2023-01-24 03:49:26.910026: step: 528/469, loss: 0.01026841625571251
2023-01-24 03:49:27.524361: step: 530/469, loss: 0.003544917330145836
2023-01-24 03:49:28.204227: step: 532/469, loss: 0.06460683792829514
2023-01-24 03:49:28.866885: step: 534/469, loss: 0.0171480905264616
2023-01-24 03:49:29.539916: step: 536/469, loss: 0.0022561487276107073
2023-01-24 03:49:30.180031: step: 538/469, loss: 0.06266505271196365
2023-01-24 03:49:30.777096: step: 540/469, loss: 0.014372874982655048
2023-01-24 03:49:31.434550: step: 542/469, loss: 0.03709370642900467
2023-01-24 03:49:32.078207: step: 544/469, loss: 0.0486343652009964
2023-01-24 03:49:32.654110: step: 546/469, loss: 0.08830500394105911
2023-01-24 03:49:33.347023: step: 548/469, loss: 0.0234213937073946
2023-01-24 03:49:33.973013: step: 550/469, loss: 0.02622537687420845
2023-01-24 03:49:34.603938: step: 552/469, loss: 0.011505834758281708
2023-01-24 03:49:35.303778: step: 554/469, loss: 0.10963188111782074
2023-01-24 03:49:35.946519: step: 556/469, loss: 0.3771672248840332
2023-01-24 03:49:36.594972: step: 558/469, loss: 0.23346242308616638
2023-01-24 03:49:37.254734: step: 560/469, loss: 0.038544341921806335
2023-01-24 03:49:37.874540: step: 562/469, loss: 0.0968988761305809
2023-01-24 03:49:38.498716: step: 564/469, loss: 0.02138388901948929
2023-01-24 03:49:39.090408: step: 566/469, loss: 0.20941877365112305
2023-01-24 03:49:39.726347: step: 568/469, loss: 0.04067647084593773
2023-01-24 03:49:40.423056: step: 570/469, loss: 0.04401589184999466
2023-01-24 03:49:41.080694: step: 572/469, loss: 0.005905947647988796
2023-01-24 03:49:41.709788: step: 574/469, loss: 0.02408822439610958
2023-01-24 03:49:42.385281: step: 576/469, loss: 0.08960024267435074
2023-01-24 03:49:42.964911: step: 578/469, loss: 0.0563046857714653
2023-01-24 03:49:43.589922: step: 580/469, loss: 0.1482042819261551
2023-01-24 03:49:44.260591: step: 582/469, loss: 0.030881470069289207
2023-01-24 03:49:44.924494: step: 584/469, loss: 0.016311822459101677
2023-01-24 03:49:45.557514: step: 586/469, loss: 0.023087259382009506
2023-01-24 03:49:46.215397: step: 588/469, loss: 0.36545512080192566
2023-01-24 03:49:46.876838: step: 590/469, loss: 0.010560513474047184
2023-01-24 03:49:47.464131: step: 592/469, loss: 0.20198041200637817
2023-01-24 03:49:48.204993: step: 594/469, loss: 0.049684807658195496
2023-01-24 03:49:48.846976: step: 596/469, loss: 0.03809770196676254
2023-01-24 03:49:49.438153: step: 598/469, loss: 0.008861164562404156
2023-01-24 03:49:50.033787: step: 600/469, loss: 0.03218526393175125
2023-01-24 03:49:50.684083: step: 602/469, loss: 0.022556880488991737
2023-01-24 03:49:51.308420: step: 604/469, loss: 0.011322306469082832
2023-01-24 03:49:51.859268: step: 606/469, loss: 0.030001727864146233
2023-01-24 03:49:52.474493: step: 608/469, loss: 0.045465029776096344
2023-01-24 03:49:53.125804: step: 610/469, loss: 0.057701513171195984
2023-01-24 03:49:53.766407: step: 612/469, loss: 0.02023312821984291
2023-01-24 03:49:54.397694: step: 614/469, loss: 0.016423925757408142
2023-01-24 03:49:55.027663: step: 616/469, loss: 0.02925160899758339
2023-01-24 03:49:55.607199: step: 618/469, loss: 0.028430957347154617
2023-01-24 03:49:56.244786: step: 620/469, loss: 0.05649249255657196
2023-01-24 03:49:56.842432: step: 622/469, loss: 0.03616967424750328
2023-01-24 03:49:57.454142: step: 624/469, loss: 0.02274082601070404
2023-01-24 03:49:58.116435: step: 626/469, loss: 0.037107981741428375
2023-01-24 03:49:58.793403: step: 628/469, loss: 0.03349355235695839
2023-01-24 03:49:59.449695: step: 630/469, loss: 0.06326816976070404
2023-01-24 03:50:00.051710: step: 632/469, loss: 0.02004053257405758
2023-01-24 03:50:00.668336: step: 634/469, loss: 0.05118941143155098
2023-01-24 03:50:01.330162: step: 636/469, loss: 0.03605641424655914
2023-01-24 03:50:01.973944: step: 638/469, loss: 0.008025464601814747
2023-01-24 03:50:02.650774: step: 640/469, loss: 0.03873804584145546
2023-01-24 03:50:03.256258: step: 642/469, loss: 0.003371611936017871
2023-01-24 03:50:03.864944: step: 644/469, loss: 0.005725967697799206
2023-01-24 03:50:04.474212: step: 646/469, loss: 0.11167502403259277
2023-01-24 03:50:05.126452: step: 648/469, loss: 0.05364027991890907
2023-01-24 03:50:05.725257: step: 650/469, loss: 0.03828307241201401
2023-01-24 03:50:06.376052: step: 652/469, loss: 0.027975894510746002
2023-01-24 03:50:06.991408: step: 654/469, loss: 0.015445971861481667
2023-01-24 03:50:07.604939: step: 656/469, loss: 0.01446506381034851
2023-01-24 03:50:08.175052: step: 658/469, loss: 0.0030841310508549213
2023-01-24 03:50:08.840579: step: 660/469, loss: 0.018016504123806953
2023-01-24 03:50:09.424458: step: 662/469, loss: 0.019011082127690315
2023-01-24 03:50:10.048272: step: 664/469, loss: 0.12268608808517456
2023-01-24 03:50:10.675724: step: 666/469, loss: 0.003342668293043971
2023-01-24 03:50:11.324124: step: 668/469, loss: 0.01909763738512993
2023-01-24 03:50:11.973249: step: 670/469, loss: 0.20439517498016357
2023-01-24 03:50:12.584094: step: 672/469, loss: 0.03834576532244682
2023-01-24 03:50:13.210703: step: 674/469, loss: 0.024597445502877235
2023-01-24 03:50:13.852357: step: 676/469, loss: 0.03728759288787842
2023-01-24 03:50:14.468420: step: 678/469, loss: 0.023696452379226685
2023-01-24 03:50:15.077713: step: 680/469, loss: 0.2461635023355484
2023-01-24 03:50:15.689070: step: 682/469, loss: 0.009932891465723515
2023-01-24 03:50:16.394726: step: 684/469, loss: 0.020177103579044342
2023-01-24 03:50:16.998458: step: 686/469, loss: 0.16025130450725555
2023-01-24 03:50:17.573294: step: 688/469, loss: 0.0043271807953715324
2023-01-24 03:50:18.190250: step: 690/469, loss: 0.023122074082493782
2023-01-24 03:50:18.820535: step: 692/469, loss: 0.42845121026039124
2023-01-24 03:50:19.488972: step: 694/469, loss: 0.023784488439559937
2023-01-24 03:50:20.185613: step: 696/469, loss: 0.045418478548526764
2023-01-24 03:50:20.927000: step: 698/469, loss: 0.0701347142457962
2023-01-24 03:50:21.552307: step: 700/469, loss: 0.029570408165454865
2023-01-24 03:50:22.129083: step: 702/469, loss: 0.04777064174413681
2023-01-24 03:50:22.704455: step: 704/469, loss: 0.08903773128986359
2023-01-24 03:50:23.353325: step: 706/469, loss: 0.07514233887195587
2023-01-24 03:50:24.000704: step: 708/469, loss: 0.0469592846930027
2023-01-24 03:50:24.625386: step: 710/469, loss: 0.02193559519946575
2023-01-24 03:50:25.285799: step: 712/469, loss: 0.11656536161899567
2023-01-24 03:50:25.910362: step: 714/469, loss: 0.04079541563987732
2023-01-24 03:50:26.605606: step: 716/469, loss: 0.03533748537302017
2023-01-24 03:50:27.240990: step: 718/469, loss: 0.03869449719786644
2023-01-24 03:50:27.849607: step: 720/469, loss: 0.04969077557325363
2023-01-24 03:50:28.424680: step: 722/469, loss: 0.01292459573596716
2023-01-24 03:50:29.062255: step: 724/469, loss: 0.004090246744453907
2023-01-24 03:50:29.686260: step: 726/469, loss: 0.023417063057422638
2023-01-24 03:50:30.316119: step: 728/469, loss: 0.0638405904173851
2023-01-24 03:50:30.980832: step: 730/469, loss: 0.10894934087991714
2023-01-24 03:50:31.612802: step: 732/469, loss: 0.035131413489580154
2023-01-24 03:50:32.183326: step: 734/469, loss: 0.04368053376674652
2023-01-24 03:50:32.769429: step: 736/469, loss: 0.8348058462142944
2023-01-24 03:50:33.409621: step: 738/469, loss: 0.003947824705392122
2023-01-24 03:50:34.037323: step: 740/469, loss: 0.0029385206289589405
2023-01-24 03:50:34.693663: step: 742/469, loss: 0.009950543753802776
2023-01-24 03:50:35.262296: step: 744/469, loss: 0.01953227072954178
2023-01-24 03:50:35.963248: step: 746/469, loss: 0.09103751927614212
2023-01-24 03:50:36.560690: step: 748/469, loss: 0.04214608296751976
2023-01-24 03:50:37.168016: step: 750/469, loss: 0.017283525317907333
2023-01-24 03:50:37.795415: step: 752/469, loss: 0.18202316761016846
2023-01-24 03:50:38.424787: step: 754/469, loss: 0.07312453538179398
2023-01-24 03:50:39.058858: step: 756/469, loss: 0.24903231859207153
2023-01-24 03:50:39.649155: step: 758/469, loss: 0.06482073664665222
2023-01-24 03:50:40.259623: step: 760/469, loss: 0.07405403256416321
2023-01-24 03:50:40.921373: step: 762/469, loss: 0.014474152587354183
2023-01-24 03:50:41.604943: step: 764/469, loss: 0.026526834815740585
2023-01-24 03:50:42.297096: step: 766/469, loss: 0.02918674424290657
2023-01-24 03:50:42.897111: step: 768/469, loss: 0.0171043761074543
2023-01-24 03:50:43.605888: step: 770/469, loss: 0.16759347915649414
2023-01-24 03:50:44.224684: step: 772/469, loss: 0.005510732065886259
2023-01-24 03:50:44.824158: step: 774/469, loss: 0.032438408583402634
2023-01-24 03:50:45.412188: step: 776/469, loss: 0.037898868322372437
2023-01-24 03:50:46.031492: step: 778/469, loss: 0.09436165541410446
2023-01-24 03:50:46.631815: step: 780/469, loss: 0.045958563685417175
2023-01-24 03:50:47.239442: step: 782/469, loss: 0.05432308465242386
2023-01-24 03:50:47.858928: step: 784/469, loss: 0.03569307550787926
2023-01-24 03:50:48.515208: step: 786/469, loss: 0.025533713400363922
2023-01-24 03:50:49.187643: step: 788/469, loss: 0.05924192816019058
2023-01-24 03:50:49.781812: step: 790/469, loss: 0.005669349804520607
2023-01-24 03:50:50.430220: step: 792/469, loss: 0.04133680835366249
2023-01-24 03:50:51.008559: step: 794/469, loss: 0.049105141311883926
2023-01-24 03:50:51.637256: step: 796/469, loss: 0.02192024327814579
2023-01-24 03:50:52.209829: step: 798/469, loss: 0.026449689641594887
2023-01-24 03:50:52.791828: step: 800/469, loss: 0.10335677117109299
2023-01-24 03:50:53.420896: step: 802/469, loss: 0.016659628599882126
2023-01-24 03:50:54.020653: step: 804/469, loss: 0.08267058432102203
2023-01-24 03:50:54.675246: step: 806/469, loss: 0.009828275069594383
2023-01-24 03:50:55.272742: step: 808/469, loss: 0.030231472104787827
2023-01-24 03:50:56.029523: step: 810/469, loss: 0.023600690066814423
2023-01-24 03:50:56.654732: step: 812/469, loss: 0.10526539385318756
2023-01-24 03:50:57.262337: step: 814/469, loss: 0.09193176031112671
2023-01-24 03:50:57.876167: step: 816/469, loss: 0.03997723013162613
2023-01-24 03:50:58.491634: step: 818/469, loss: 0.046001747250556946
2023-01-24 03:50:59.060949: step: 820/469, loss: 1.0909194946289062
2023-01-24 03:51:00.373255: step: 822/469, loss: 0.02829616330564022
2023-01-24 03:51:01.062560: step: 824/469, loss: 0.0725482627749443
2023-01-24 03:51:01.687211: step: 826/469, loss: 0.045401617884635925
2023-01-24 03:51:02.321021: step: 828/469, loss: 0.13206619024276733
2023-01-24 03:51:02.927220: step: 830/469, loss: 0.03091304562985897
2023-01-24 03:51:03.576035: step: 832/469, loss: 0.029082871973514557
2023-01-24 03:51:04.162254: step: 834/469, loss: 0.07198868691921234
2023-01-24 03:51:04.804755: step: 836/469, loss: 0.18165065348148346
2023-01-24 03:51:05.405381: step: 838/469, loss: 0.34014299511909485
2023-01-24 03:51:06.042346: step: 840/469, loss: 0.027846289798617363
2023-01-24 03:51:06.648798: step: 842/469, loss: 0.09241542220115662
2023-01-24 03:51:07.247418: step: 844/469, loss: 0.027130432426929474
2023-01-24 03:51:07.872103: step: 846/469, loss: 0.021871939301490784
2023-01-24 03:51:08.511422: step: 848/469, loss: 0.03874404728412628
2023-01-24 03:51:09.140396: step: 850/469, loss: 0.05512149631977081
2023-01-24 03:51:09.705998: step: 852/469, loss: 0.014337156899273396
2023-01-24 03:51:10.327685: step: 854/469, loss: 0.305141419172287
2023-01-24 03:51:11.019566: step: 856/469, loss: 0.07611072063446045
2023-01-24 03:51:11.610253: step: 858/469, loss: 0.029356474056839943
2023-01-24 03:51:12.232978: step: 860/469, loss: 0.04575691372156143
2023-01-24 03:51:12.871881: step: 862/469, loss: 0.09294658899307251
2023-01-24 03:51:13.530675: step: 864/469, loss: 0.06593305617570877
2023-01-24 03:51:14.149034: step: 866/469, loss: 0.035524748265743256
2023-01-24 03:51:14.716177: step: 868/469, loss: 0.10471679270267487
2023-01-24 03:51:15.391235: step: 870/469, loss: 0.03528767451643944
2023-01-24 03:51:15.991664: step: 872/469, loss: 0.03296990692615509
2023-01-24 03:51:16.655111: step: 874/469, loss: 0.026981398463249207
2023-01-24 03:51:17.346392: step: 876/469, loss: 0.02476923167705536
2023-01-24 03:51:18.004125: step: 878/469, loss: 0.029789147898554802
2023-01-24 03:51:18.648334: step: 880/469, loss: 0.27299654483795166
2023-01-24 03:51:19.317301: step: 882/469, loss: 0.026675784960389137
2023-01-24 03:51:19.987069: step: 884/469, loss: 0.2162950336933136
2023-01-24 03:51:20.563722: step: 886/469, loss: 0.001604490913450718
2023-01-24 03:51:21.111586: step: 888/469, loss: 0.0254694614559412
2023-01-24 03:51:21.747741: step: 890/469, loss: 0.008233447559177876
2023-01-24 03:51:22.407998: step: 892/469, loss: 0.03157993406057358
2023-01-24 03:51:23.054421: step: 894/469, loss: 0.13843785226345062
2023-01-24 03:51:23.687135: step: 896/469, loss: 0.013640285469591618
2023-01-24 03:51:24.277504: step: 898/469, loss: 0.0152322668582201
2023-01-24 03:51:24.913653: step: 900/469, loss: 0.055900149047374725
2023-01-24 03:51:25.586246: step: 902/469, loss: 0.028205275535583496
2023-01-24 03:51:26.161344: step: 904/469, loss: 0.03686301037669182
2023-01-24 03:51:26.898447: step: 906/469, loss: 0.04179917648434639
2023-01-24 03:51:27.495985: step: 908/469, loss: 0.040270671248435974
2023-01-24 03:51:28.120620: step: 910/469, loss: 0.007458284962922335
2023-01-24 03:51:28.769137: step: 912/469, loss: 0.5592674612998962
2023-01-24 03:51:29.407340: step: 914/469, loss: 0.007352380082011223
2023-01-24 03:51:30.014383: step: 916/469, loss: 0.05365872010588646
2023-01-24 03:51:30.638730: step: 918/469, loss: 0.11493711173534393
2023-01-24 03:51:31.421932: step: 920/469, loss: 0.02752826176583767
2023-01-24 03:51:32.073742: step: 922/469, loss: 0.0778980702161789
2023-01-24 03:51:32.648829: step: 924/469, loss: 0.18797804415225983
2023-01-24 03:51:33.177490: step: 926/469, loss: 0.02664988860487938
2023-01-24 03:51:33.722073: step: 928/469, loss: 0.11907251179218292
2023-01-24 03:51:34.397101: step: 930/469, loss: 0.024364197626709938
2023-01-24 03:51:34.988721: step: 932/469, loss: 0.0443686842918396
2023-01-24 03:51:35.537975: step: 934/469, loss: 0.0018686829134821892
2023-01-24 03:51:36.139963: step: 936/469, loss: 0.022116629406809807
2023-01-24 03:51:36.797164: step: 938/469, loss: 0.035270195454359055
==================================================
Loss: 0.068
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.320115154406662, 'r': 0.31829286700017245, 'f1': 0.3192014099126373}, 'combined': 0.23520103888299587, 'epoch': 23}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33318821667841847, 'r': 0.26100758838519617, 'f1': 0.2927137895370626}, 'combined': 0.15966206702021596, 'epoch': 23}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3160940545808967, 'r': 0.3076968690702087, 'f1': 0.31183894230769227}, 'combined': 0.2297760627530364, 'epoch': 23}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3335799507815052, 'r': 0.2576554464445812, 'f1': 0.29074271109888794}, 'combined': 0.15858693332666612, 'epoch': 23}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32074316298742683, 'r': 0.3183086797768961, 'f1': 0.31952128427128423}, 'combined': 0.235436735778841, 'epoch': 23}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32856753101822805, 'r': 0.25979059810856237, 'f1': 0.29015917746887926}, 'combined': 0.15826864225575232, 'epoch': 23}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2935606060606061, 'r': 0.2767857142857143, 'f1': 0.28492647058823534}, 'combined': 0.18995098039215688, 'epoch': 23}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3173076923076923, 'r': 0.358695652173913, 'f1': 0.33673469387755095}, 'combined': 0.16836734693877548, 'epoch': 23}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45454545454545453, 'r': 0.1724137931034483, 'f1': 0.25000000000000006}, 'combined': 0.16666666666666669, 'epoch': 23}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 03:54:22.699321: step: 2/469, loss: 0.016417326405644417
2023-01-24 03:54:23.436158: step: 4/469, loss: 0.047688115388154984
2023-01-24 03:54:24.078052: step: 6/469, loss: 0.0862254723906517
2023-01-24 03:54:24.702167: step: 8/469, loss: 0.23898805677890778
2023-01-24 03:54:25.305762: step: 10/469, loss: 0.030291911214590073
2023-01-24 03:54:25.956951: step: 12/469, loss: 0.01121998205780983
2023-01-24 03:54:26.585174: step: 14/469, loss: 0.034028246998786926
2023-01-24 03:54:27.140723: step: 16/469, loss: 0.01717783696949482
2023-01-24 03:54:27.889246: step: 18/469, loss: 0.0826980322599411
2023-01-24 03:54:28.555603: step: 20/469, loss: 0.05500301718711853
2023-01-24 03:54:29.208585: step: 22/469, loss: 0.04233062267303467
2023-01-24 03:54:29.877063: step: 24/469, loss: 0.0036251835990697145
2023-01-24 03:54:30.507836: step: 26/469, loss: 0.09086892753839493
2023-01-24 03:54:31.135261: step: 28/469, loss: 0.019768664613366127
2023-01-24 03:54:31.755376: step: 30/469, loss: 0.016958897933363914
2023-01-24 03:54:32.308704: step: 32/469, loss: 0.015197346918284893
2023-01-24 03:54:32.926440: step: 34/469, loss: 0.01870288886129856
2023-01-24 03:54:33.561632: step: 36/469, loss: 0.03923607990145683
2023-01-24 03:54:34.207681: step: 38/469, loss: 0.01410847157239914
2023-01-24 03:54:34.940367: step: 40/469, loss: 0.055641189217567444
2023-01-24 03:54:35.582308: step: 42/469, loss: 0.012252534739673138
2023-01-24 03:54:36.281942: step: 44/469, loss: 0.32044076919555664
2023-01-24 03:54:36.897908: step: 46/469, loss: 0.018998123705387115
2023-01-24 03:54:37.556564: step: 48/469, loss: 0.08631859719753265
2023-01-24 03:54:38.185232: step: 50/469, loss: 0.019391590729355812
2023-01-24 03:54:38.743932: step: 52/469, loss: 0.013424401171505451
2023-01-24 03:54:39.414598: step: 54/469, loss: 0.00611753948032856
2023-01-24 03:54:40.070358: step: 56/469, loss: 0.007324477192014456
2023-01-24 03:54:40.613786: step: 58/469, loss: 0.007927605882287025
2023-01-24 03:54:41.200440: step: 60/469, loss: 0.023863786831498146
2023-01-24 03:54:41.857010: step: 62/469, loss: 0.15221978724002838
2023-01-24 03:54:42.498822: step: 64/469, loss: 0.0205460824072361
2023-01-24 03:54:43.169514: step: 66/469, loss: 0.05236423760652542
2023-01-24 03:54:43.822867: step: 68/469, loss: 0.05775609612464905
2023-01-24 03:54:44.499320: step: 70/469, loss: 0.013726840727031231
2023-01-24 03:54:45.105732: step: 72/469, loss: 0.003370016347616911
2023-01-24 03:54:45.734413: step: 74/469, loss: 0.03200198709964752
2023-01-24 03:54:46.337202: step: 76/469, loss: 0.0227058008313179
2023-01-24 03:54:46.975000: step: 78/469, loss: 0.1415403038263321
2023-01-24 03:54:47.637214: step: 80/469, loss: 0.01559305377304554
2023-01-24 03:54:48.322720: step: 82/469, loss: 0.026849525049328804
2023-01-24 03:54:49.012354: step: 84/469, loss: 0.0059050279669463634
2023-01-24 03:54:49.613672: step: 86/469, loss: 0.01893472485244274
2023-01-24 03:54:50.269990: step: 88/469, loss: 0.021686840802431107
2023-01-24 03:54:50.930878: step: 90/469, loss: 0.01580534689128399
2023-01-24 03:54:51.617792: step: 92/469, loss: 0.02733035571873188
2023-01-24 03:54:52.255747: step: 94/469, loss: 0.04168585687875748
2023-01-24 03:54:52.878841: step: 96/469, loss: 0.030311888083815575
2023-01-24 03:54:53.548413: step: 98/469, loss: 0.05860369652509689
2023-01-24 03:54:54.154262: step: 100/469, loss: 0.021574096754193306
2023-01-24 03:54:54.810475: step: 102/469, loss: 0.04766014590859413
2023-01-24 03:54:55.365370: step: 104/469, loss: 0.003634591354057193
2023-01-24 03:54:55.976158: step: 106/469, loss: 0.29936927556991577
2023-01-24 03:54:56.591181: step: 108/469, loss: 0.029460735619068146
2023-01-24 03:54:57.151961: step: 110/469, loss: 0.024939091876149178
2023-01-24 03:54:57.754821: step: 112/469, loss: 0.010890143923461437
2023-01-24 03:54:58.387062: step: 114/469, loss: 0.11194773018360138
2023-01-24 03:54:59.054080: step: 116/469, loss: 0.02466609515249729
2023-01-24 03:54:59.609114: step: 118/469, loss: 0.03958394005894661
2023-01-24 03:55:00.334133: step: 120/469, loss: 0.14312510192394257
2023-01-24 03:55:00.957118: step: 122/469, loss: 0.012246928177773952
2023-01-24 03:55:01.540575: step: 124/469, loss: 0.017965009436011314
2023-01-24 03:55:02.176222: step: 126/469, loss: 0.04019022732973099
2023-01-24 03:55:02.779422: step: 128/469, loss: 0.01370336301624775
2023-01-24 03:55:03.361925: step: 130/469, loss: 0.010952872224152088
2023-01-24 03:55:03.984632: step: 132/469, loss: 0.030317997559905052
2023-01-24 03:55:04.624242: step: 134/469, loss: 0.05731196328997612
2023-01-24 03:55:05.232283: step: 136/469, loss: 0.029016038402915
2023-01-24 03:55:05.870278: step: 138/469, loss: 0.0025959822814911604
2023-01-24 03:55:06.550847: step: 140/469, loss: 0.012712554074823856
2023-01-24 03:55:07.192970: step: 142/469, loss: 0.0649077370762825
2023-01-24 03:55:07.830316: step: 144/469, loss: 0.013003380969166756
2023-01-24 03:55:08.436208: step: 146/469, loss: 0.008440962992608547
2023-01-24 03:55:09.025507: step: 148/469, loss: 0.01160487625747919
2023-01-24 03:55:09.649482: step: 150/469, loss: 0.0455317497253418
2023-01-24 03:55:10.259936: step: 152/469, loss: 0.03124481812119484
2023-01-24 03:55:10.822665: step: 154/469, loss: 0.05350888893008232
2023-01-24 03:55:11.457805: step: 156/469, loss: 0.03994572535157204
2023-01-24 03:55:12.071483: step: 158/469, loss: 0.010522032156586647
2023-01-24 03:55:12.691907: step: 160/469, loss: 0.03227447345852852
2023-01-24 03:55:13.279262: step: 162/469, loss: 0.008141381666064262
2023-01-24 03:55:13.859519: step: 164/469, loss: 0.004845090676099062
2023-01-24 03:55:14.500431: step: 166/469, loss: 0.013959623873233795
2023-01-24 03:55:15.112669: step: 168/469, loss: 0.0075279464945197105
2023-01-24 03:55:15.703686: step: 170/469, loss: 0.04734662547707558
2023-01-24 03:55:16.292606: step: 172/469, loss: 0.03917761892080307
2023-01-24 03:55:16.903537: step: 174/469, loss: 0.00599240604788065
2023-01-24 03:55:17.506903: step: 176/469, loss: 0.0036602281033992767
2023-01-24 03:55:18.171989: step: 178/469, loss: 0.013128047809004784
2023-01-24 03:55:18.789233: step: 180/469, loss: 0.029274987056851387
2023-01-24 03:55:19.371319: step: 182/469, loss: 0.021258031949400902
2023-01-24 03:55:20.021353: step: 184/469, loss: 0.006865369621664286
2023-01-24 03:55:20.590455: step: 186/469, loss: 0.027012838050723076
2023-01-24 03:55:21.256437: step: 188/469, loss: 0.10580946505069733
2023-01-24 03:55:21.892822: step: 190/469, loss: 0.11646991968154907
2023-01-24 03:55:22.454794: step: 192/469, loss: 0.02122093364596367
2023-01-24 03:55:23.064740: step: 194/469, loss: 0.007417526561766863
2023-01-24 03:55:23.645693: step: 196/469, loss: 0.00789575930684805
2023-01-24 03:55:24.288023: step: 198/469, loss: 0.004790593404322863
2023-01-24 03:55:24.925445: step: 200/469, loss: 0.6533937454223633
2023-01-24 03:55:25.533894: step: 202/469, loss: 0.29181212186813354
2023-01-24 03:55:26.198131: step: 204/469, loss: 0.023737413808703423
2023-01-24 03:55:26.856454: step: 206/469, loss: 0.07275974005460739
2023-01-24 03:55:27.474604: step: 208/469, loss: 0.05138004943728447
2023-01-24 03:55:28.114499: step: 210/469, loss: 0.05183066427707672
2023-01-24 03:55:28.748246: step: 212/469, loss: 0.01253726426512003
2023-01-24 03:55:29.344654: step: 214/469, loss: 0.021247226744890213
2023-01-24 03:55:30.058663: step: 216/469, loss: 0.022669294849038124
2023-01-24 03:55:30.673018: step: 218/469, loss: 0.020281096920371056
2023-01-24 03:55:31.252984: step: 220/469, loss: 0.005160744767636061
2023-01-24 03:55:31.867137: step: 222/469, loss: 0.11030631512403488
2023-01-24 03:55:32.614105: step: 224/469, loss: 0.02367747761309147
2023-01-24 03:55:33.347269: step: 226/469, loss: 0.012560294009745121
2023-01-24 03:55:34.012596: step: 228/469, loss: 0.007990298792719841
2023-01-24 03:55:34.560206: step: 230/469, loss: 0.06881830096244812
2023-01-24 03:55:35.293069: step: 232/469, loss: 0.010329904966056347
2023-01-24 03:55:35.934816: step: 234/469, loss: 0.006145569961518049
2023-01-24 03:55:36.488015: step: 236/469, loss: 0.0172202717512846
2023-01-24 03:55:37.122840: step: 238/469, loss: 0.0024612518027424812
2023-01-24 03:55:37.700414: step: 240/469, loss: 0.008188467472791672
2023-01-24 03:55:38.363211: step: 242/469, loss: 0.20481272041797638
2023-01-24 03:55:38.910144: step: 244/469, loss: 0.014653651043772697
2023-01-24 03:55:39.657948: step: 246/469, loss: 0.28711986541748047
2023-01-24 03:55:40.304635: step: 248/469, loss: 0.005164872854948044
2023-01-24 03:55:40.933655: step: 250/469, loss: 0.0071144504472613335
2023-01-24 03:55:41.508031: step: 252/469, loss: 0.0035280201118439436
2023-01-24 03:55:42.162036: step: 254/469, loss: 0.0887732207775116
2023-01-24 03:55:42.732045: step: 256/469, loss: 0.02170315757393837
2023-01-24 03:55:43.349854: step: 258/469, loss: 0.02189589850604534
2023-01-24 03:55:43.981685: step: 260/469, loss: 0.042867522686719894
2023-01-24 03:55:44.608618: step: 262/469, loss: 0.09971924126148224
2023-01-24 03:55:45.291918: step: 264/469, loss: 0.26245683431625366
2023-01-24 03:55:45.887212: step: 266/469, loss: 0.05709851160645485
2023-01-24 03:55:46.497120: step: 268/469, loss: 0.03264932334423065
2023-01-24 03:55:47.168921: step: 270/469, loss: 0.015331503935158253
2023-01-24 03:55:47.763597: step: 272/469, loss: 0.02993532083928585
2023-01-24 03:55:48.382859: step: 274/469, loss: 0.08994031697511673
2023-01-24 03:55:48.976438: step: 276/469, loss: 0.027369476854801178
2023-01-24 03:55:49.596156: step: 278/469, loss: 0.026092637330293655
2023-01-24 03:55:50.193283: step: 280/469, loss: 0.013567878864705563
2023-01-24 03:55:50.895778: step: 282/469, loss: 0.037978872656822205
2023-01-24 03:55:51.487262: step: 284/469, loss: 0.00607453566044569
2023-01-24 03:55:52.100035: step: 286/469, loss: 0.020827503874897957
2023-01-24 03:55:52.798965: step: 288/469, loss: 0.03754419833421707
2023-01-24 03:55:53.380050: step: 290/469, loss: 0.12021613866090775
2023-01-24 03:55:53.975321: step: 292/469, loss: 0.03460229933261871
2023-01-24 03:55:54.606204: step: 294/469, loss: 0.3516269624233246
2023-01-24 03:55:55.254233: step: 296/469, loss: 0.027158131822943687
2023-01-24 03:55:55.816772: step: 298/469, loss: 0.004540742374956608
2023-01-24 03:55:56.450163: step: 300/469, loss: 0.03442658856511116
2023-01-24 03:55:57.057356: step: 302/469, loss: 0.01600290648639202
2023-01-24 03:55:57.660062: step: 304/469, loss: 0.07805667072534561
2023-01-24 03:55:58.261971: step: 306/469, loss: 0.022994069382548332
2023-01-24 03:55:58.948712: step: 308/469, loss: 0.010473649017512798
2023-01-24 03:55:59.564489: step: 310/469, loss: 0.0978112742304802
2023-01-24 03:56:00.240555: step: 312/469, loss: 0.024772867560386658
2023-01-24 03:56:00.864221: step: 314/469, loss: 0.03395106643438339
2023-01-24 03:56:01.519759: step: 316/469, loss: 0.1460859328508377
2023-01-24 03:56:02.141288: step: 318/469, loss: 0.02039787359535694
2023-01-24 03:56:02.733874: step: 320/469, loss: 0.011497749015688896
2023-01-24 03:56:03.397372: step: 322/469, loss: 0.018590491265058517
2023-01-24 03:56:03.988162: step: 324/469, loss: 0.07504917681217194
2023-01-24 03:56:04.558886: step: 326/469, loss: 0.02037842757999897
2023-01-24 03:56:05.204335: step: 328/469, loss: 0.028747988864779472
2023-01-24 03:56:05.848071: step: 330/469, loss: 0.027681805193424225
2023-01-24 03:56:06.495265: step: 332/469, loss: 0.004579153377562761
2023-01-24 03:56:07.166855: step: 334/469, loss: 0.008732077665627003
2023-01-24 03:56:07.756022: step: 336/469, loss: 0.014567781239748001
2023-01-24 03:56:08.356622: step: 338/469, loss: 0.09077747166156769
2023-01-24 03:56:08.982869: step: 340/469, loss: 0.026898130774497986
2023-01-24 03:56:09.559575: step: 342/469, loss: 0.02545371651649475
2023-01-24 03:56:10.144650: step: 344/469, loss: 0.01812591962516308
2023-01-24 03:56:10.869302: step: 346/469, loss: 0.03316383808851242
2023-01-24 03:56:11.525783: step: 348/469, loss: 0.023934369906783104
2023-01-24 03:56:12.074420: step: 350/469, loss: 0.05916007608175278
2023-01-24 03:56:12.731643: step: 352/469, loss: 0.07270391285419464
2023-01-24 03:56:13.363418: step: 354/469, loss: 0.024173913523554802
2023-01-24 03:56:14.070319: step: 356/469, loss: 0.09916363656520844
2023-01-24 03:56:14.683495: step: 358/469, loss: 0.019212665036320686
2023-01-24 03:56:15.429420: step: 360/469, loss: 0.0030976892448961735
2023-01-24 03:56:16.102556: step: 362/469, loss: 0.0708962231874466
2023-01-24 03:56:16.748040: step: 364/469, loss: 0.09258852899074554
2023-01-24 03:56:17.327833: step: 366/469, loss: 0.012380612082779408
2023-01-24 03:56:17.967903: step: 368/469, loss: 0.04000595211982727
2023-01-24 03:56:18.614338: step: 370/469, loss: 0.03125681355595589
2023-01-24 03:56:19.208071: step: 372/469, loss: 0.029831333085894585
2023-01-24 03:56:19.821069: step: 374/469, loss: 0.02931158058345318
2023-01-24 03:56:20.418074: step: 376/469, loss: 0.12362349033355713
2023-01-24 03:56:21.085626: step: 378/469, loss: 0.1478091925382614
2023-01-24 03:56:21.688290: step: 380/469, loss: 0.011295045726001263
2023-01-24 03:56:22.305299: step: 382/469, loss: 0.00720637571066618
2023-01-24 03:56:22.902304: step: 384/469, loss: 7.650078296661377
2023-01-24 03:56:23.569783: step: 386/469, loss: 0.05155227705836296
2023-01-24 03:56:24.208024: step: 388/469, loss: 0.040322039276361465
2023-01-24 03:56:24.943836: step: 390/469, loss: 0.05368424952030182
2023-01-24 03:56:25.650668: step: 392/469, loss: 0.008382214233279228
2023-01-24 03:56:26.200978: step: 394/469, loss: 0.0029755679424852133
2023-01-24 03:56:26.816599: step: 396/469, loss: 0.09491639584302902
2023-01-24 03:56:27.417963: step: 398/469, loss: 0.0021750153973698616
2023-01-24 03:56:28.004553: step: 400/469, loss: 0.01303351204842329
2023-01-24 03:56:28.645679: step: 402/469, loss: 0.02852119877934456
2023-01-24 03:56:29.302823: step: 404/469, loss: 0.16635991632938385
2023-01-24 03:56:29.950626: step: 406/469, loss: 0.019529711455106735
2023-01-24 03:56:30.520424: step: 408/469, loss: 0.0358879417181015
2023-01-24 03:56:31.104886: step: 410/469, loss: 0.46126437187194824
2023-01-24 03:56:31.704427: step: 412/469, loss: 0.03125284984707832
2023-01-24 03:56:32.332584: step: 414/469, loss: 0.003533415962010622
2023-01-24 03:56:32.951919: step: 416/469, loss: 0.08269832283258438
2023-01-24 03:56:33.579239: step: 418/469, loss: 0.01909209042787552
2023-01-24 03:56:34.184862: step: 420/469, loss: 0.009479396045207977
2023-01-24 03:56:34.899335: step: 422/469, loss: 0.014674525707960129
2023-01-24 03:56:35.548943: step: 424/469, loss: 0.202433779835701
2023-01-24 03:56:36.219827: step: 426/469, loss: 0.03065209463238716
2023-01-24 03:56:36.830777: step: 428/469, loss: 0.007127057760953903
2023-01-24 03:56:37.402421: step: 430/469, loss: 0.004880867432802916
2023-01-24 03:56:38.037994: step: 432/469, loss: 0.030944108963012695
2023-01-24 03:56:38.683210: step: 434/469, loss: 0.7026104927062988
2023-01-24 03:56:39.325739: step: 436/469, loss: 0.036813121289014816
2023-01-24 03:56:40.013560: step: 438/469, loss: 0.05058964714407921
2023-01-24 03:56:40.588868: step: 440/469, loss: 0.025473378598690033
2023-01-24 03:56:41.124557: step: 442/469, loss: 0.02426227368414402
2023-01-24 03:56:41.763211: step: 444/469, loss: 0.02645028941333294
2023-01-24 03:56:42.350121: step: 446/469, loss: 0.4938548803329468
2023-01-24 03:56:43.010390: step: 448/469, loss: 0.022870637476444244
2023-01-24 03:56:43.585118: step: 450/469, loss: 0.0035457240883260965
2023-01-24 03:56:44.203263: step: 452/469, loss: 0.06122088059782982
2023-01-24 03:56:44.847731: step: 454/469, loss: 0.0231733750551939
2023-01-24 03:56:45.505455: step: 456/469, loss: 0.032441675662994385
2023-01-24 03:56:46.188824: step: 458/469, loss: 0.013426247052848339
2023-01-24 03:56:46.813612: step: 460/469, loss: 0.013612991198897362
2023-01-24 03:56:47.451324: step: 462/469, loss: 0.027152452617883682
2023-01-24 03:56:48.160036: step: 464/469, loss: 0.02933356910943985
2023-01-24 03:56:48.892512: step: 466/469, loss: 0.13497425615787506
2023-01-24 03:56:49.417939: step: 468/469, loss: 0.05727699398994446
2023-01-24 03:56:50.040278: step: 470/469, loss: 0.017669206485152245
2023-01-24 03:56:50.694036: step: 472/469, loss: 0.07330697774887085
2023-01-24 03:56:51.371044: step: 474/469, loss: 0.07063091546297073
2023-01-24 03:56:52.038914: step: 476/469, loss: 0.010941785760223866
2023-01-24 03:56:52.612415: step: 478/469, loss: 0.0388040654361248
2023-01-24 03:56:53.302333: step: 480/469, loss: 0.008385878056287766
2023-01-24 03:56:53.985836: step: 482/469, loss: 0.040492381900548935
2023-01-24 03:56:54.606200: step: 484/469, loss: 0.017449242994189262
2023-01-24 03:56:55.259824: step: 486/469, loss: 0.016774604097008705
2023-01-24 03:56:55.903652: step: 488/469, loss: 0.009150327183306217
2023-01-24 03:56:56.498182: step: 490/469, loss: 0.015866735950112343
2023-01-24 03:56:57.095603: step: 492/469, loss: 0.0018570665270090103
2023-01-24 03:56:57.745672: step: 494/469, loss: 0.03161801025271416
2023-01-24 03:56:58.416229: step: 496/469, loss: 0.14599068462848663
2023-01-24 03:56:59.047340: step: 498/469, loss: 0.061882343143224716
2023-01-24 03:56:59.720511: step: 500/469, loss: 0.016102727502584457
2023-01-24 03:57:00.280506: step: 502/469, loss: 0.09188220649957657
2023-01-24 03:57:00.937983: step: 504/469, loss: 0.04177233204245567
2023-01-24 03:57:01.515312: step: 506/469, loss: 0.02355528436601162
2023-01-24 03:57:02.115819: step: 508/469, loss: 0.052326660603284836
2023-01-24 03:57:02.803945: step: 510/469, loss: 0.03700276464223862
2023-01-24 03:57:03.497260: step: 512/469, loss: 0.022019846364855766
2023-01-24 03:57:04.060527: step: 514/469, loss: 0.07263131439685822
2023-01-24 03:57:04.768084: step: 516/469, loss: 0.01748010143637657
2023-01-24 03:57:05.388190: step: 518/469, loss: 0.062186408787965775
2023-01-24 03:57:05.981393: step: 520/469, loss: 0.004920444451272488
2023-01-24 03:57:06.630009: step: 522/469, loss: 0.0015854996163398027
2023-01-24 03:57:07.293337: step: 524/469, loss: 0.041216686367988586
2023-01-24 03:57:07.954771: step: 526/469, loss: 0.14086870849132538
2023-01-24 03:57:08.591820: step: 528/469, loss: 0.028211597353219986
2023-01-24 03:57:09.192112: step: 530/469, loss: 0.5521446466445923
2023-01-24 03:57:09.840173: step: 532/469, loss: 0.13783621788024902
2023-01-24 03:57:10.407954: step: 534/469, loss: 0.008081533946096897
2023-01-24 03:57:11.070449: step: 536/469, loss: 0.002966032363474369
2023-01-24 03:57:11.658879: step: 538/469, loss: 0.3086635172367096
2023-01-24 03:57:12.277980: step: 540/469, loss: 0.022557653486728668
2023-01-24 03:57:12.975414: step: 542/469, loss: 0.013709179125726223
2023-01-24 03:57:13.563495: step: 544/469, loss: 0.11992644518613815
2023-01-24 03:57:14.186457: step: 546/469, loss: 0.029493257403373718
2023-01-24 03:57:14.839177: step: 548/469, loss: 0.042251765727996826
2023-01-24 03:57:15.450675: step: 550/469, loss: 0.018960410729050636
2023-01-24 03:57:16.031665: step: 552/469, loss: 0.0232393816113472
2023-01-24 03:57:16.581711: step: 554/469, loss: 0.028066672384738922
2023-01-24 03:57:17.311270: step: 556/469, loss: 0.010841749608516693
2023-01-24 03:57:17.851960: step: 558/469, loss: 0.011582441627979279
2023-01-24 03:57:18.446138: step: 560/469, loss: 0.03709997981786728
2023-01-24 03:57:19.082880: step: 562/469, loss: 0.280786395072937
2023-01-24 03:57:19.699820: step: 564/469, loss: 0.02346476912498474
2023-01-24 03:57:20.322657: step: 566/469, loss: 0.12232447415590286
2023-01-24 03:57:21.034920: step: 568/469, loss: 0.020489519461989403
2023-01-24 03:57:21.698829: step: 570/469, loss: 0.2667163014411926
2023-01-24 03:57:22.287119: step: 572/469, loss: 0.012609031982719898
2023-01-24 03:57:22.850415: step: 574/469, loss: 0.02504895254969597
2023-01-24 03:57:23.497896: step: 576/469, loss: 0.04171283543109894
2023-01-24 03:57:24.044224: step: 578/469, loss: 0.022249821573495865
2023-01-24 03:57:24.635182: step: 580/469, loss: 0.023193230852484703
2023-01-24 03:57:25.220460: step: 582/469, loss: 0.010279330424964428
2023-01-24 03:57:25.807071: step: 584/469, loss: 0.03859834745526314
2023-01-24 03:57:26.499242: step: 586/469, loss: 0.020164670422673225
2023-01-24 03:57:27.221845: step: 588/469, loss: 0.12396000325679779
2023-01-24 03:57:27.945694: step: 590/469, loss: 0.778117835521698
2023-01-24 03:57:28.549388: step: 592/469, loss: 0.016898328438401222
2023-01-24 03:57:29.211316: step: 594/469, loss: 0.12879402935504913
2023-01-24 03:57:29.739046: step: 596/469, loss: 0.0073245819658041
2023-01-24 03:57:30.348878: step: 598/469, loss: 0.09994330257177353
2023-01-24 03:57:31.037207: step: 600/469, loss: 0.09125112742185593
2023-01-24 03:57:31.613372: step: 602/469, loss: 0.010347902774810791
2023-01-24 03:57:32.242118: step: 604/469, loss: 0.042560476809740067
2023-01-24 03:57:32.828838: step: 606/469, loss: 0.005342626478523016
2023-01-24 03:57:33.430424: step: 608/469, loss: 0.0492556095123291
2023-01-24 03:57:34.120119: step: 610/469, loss: 0.09419920295476913
2023-01-24 03:57:34.748508: step: 612/469, loss: 0.13855132460594177
2023-01-24 03:57:35.372250: step: 614/469, loss: 0.002914676209911704
2023-01-24 03:57:35.974749: step: 616/469, loss: 0.37900644540786743
2023-01-24 03:57:36.636405: step: 618/469, loss: 0.006001289002597332
2023-01-24 03:57:37.179364: step: 620/469, loss: 0.02134389989078045
2023-01-24 03:57:37.808114: step: 622/469, loss: 0.03038940764963627
2023-01-24 03:57:38.441983: step: 624/469, loss: 0.038485899567604065
2023-01-24 03:57:39.049204: step: 626/469, loss: 0.03308103606104851
2023-01-24 03:57:39.691643: step: 628/469, loss: 0.03451153263449669
2023-01-24 03:57:40.205942: step: 630/469, loss: 0.023783240467309952
2023-01-24 03:57:40.823186: step: 632/469, loss: 0.022690072655677795
2023-01-24 03:57:41.449906: step: 634/469, loss: 0.02024712786078453
2023-01-24 03:57:42.044696: step: 636/469, loss: 0.0010295177344232798
2023-01-24 03:57:42.766824: step: 638/469, loss: 0.0438709557056427
2023-01-24 03:57:43.406974: step: 640/469, loss: 0.055278677493333817
2023-01-24 03:57:43.996665: step: 642/469, loss: 0.01443219929933548
2023-01-24 03:57:44.668594: step: 644/469, loss: 0.023407230153679848
2023-01-24 03:57:45.231117: step: 646/469, loss: 0.00030136972782202065
2023-01-24 03:57:45.857094: step: 648/469, loss: 0.05775486305356026
2023-01-24 03:57:46.468171: step: 650/469, loss: 0.12905217707157135
2023-01-24 03:57:47.053097: step: 652/469, loss: 0.04188220947980881
2023-01-24 03:57:47.682438: step: 654/469, loss: 0.11069829016923904
2023-01-24 03:57:48.348950: step: 656/469, loss: 0.03923364728689194
2023-01-24 03:57:48.958812: step: 658/469, loss: 0.0034383300226181746
2023-01-24 03:57:49.648246: step: 660/469, loss: 0.04181593656539917
2023-01-24 03:57:50.296636: step: 662/469, loss: 0.04227343201637268
2023-01-24 03:57:50.898026: step: 664/469, loss: 0.007153121288865805
2023-01-24 03:57:51.530774: step: 666/469, loss: 0.023828310891985893
2023-01-24 03:57:52.163087: step: 668/469, loss: 0.03760472312569618
2023-01-24 03:57:52.866169: step: 670/469, loss: 0.07202967256307602
2023-01-24 03:57:53.514774: step: 672/469, loss: 0.0027448469772934914
2023-01-24 03:57:54.147187: step: 674/469, loss: 0.14921295642852783
2023-01-24 03:57:54.812492: step: 676/469, loss: 0.047992900013923645
2023-01-24 03:57:55.438664: step: 678/469, loss: 0.017281245440244675
2023-01-24 03:57:56.022947: step: 680/469, loss: 0.005759479012340307
2023-01-24 03:57:56.639098: step: 682/469, loss: 0.03225100040435791
2023-01-24 03:57:57.219783: step: 684/469, loss: 0.019822152331471443
2023-01-24 03:57:57.853737: step: 686/469, loss: 0.027294326573610306
2023-01-24 03:57:58.553128: step: 688/469, loss: 0.04073766991496086
2023-01-24 03:57:59.167707: step: 690/469, loss: 0.007256670854985714
2023-01-24 03:57:59.777559: step: 692/469, loss: 0.10709620267152786
2023-01-24 03:58:00.440611: step: 694/469, loss: 0.05638296529650688
2023-01-24 03:58:00.997627: step: 696/469, loss: 0.003282777965068817
2023-01-24 03:58:01.638804: step: 698/469, loss: 0.09598791599273682
2023-01-24 03:58:02.285220: step: 700/469, loss: 0.0482390932738781
2023-01-24 03:58:02.834413: step: 702/469, loss: 0.01908688433468342
2023-01-24 03:58:03.499805: step: 704/469, loss: 0.00163744087330997
2023-01-24 03:58:04.077969: step: 706/469, loss: 0.02473783679306507
2023-01-24 03:58:04.742480: step: 708/469, loss: 0.020040497183799744
2023-01-24 03:58:05.357164: step: 710/469, loss: 0.024155493825674057
2023-01-24 03:58:06.092343: step: 712/469, loss: 0.03475001081824303
2023-01-24 03:58:06.668973: step: 714/469, loss: 0.10461072623729706
2023-01-24 03:58:07.281335: step: 716/469, loss: 0.0498565211892128
2023-01-24 03:58:07.908127: step: 718/469, loss: 0.04575449228286743
2023-01-24 03:58:08.526597: step: 720/469, loss: 0.014970526099205017
2023-01-24 03:58:09.158242: step: 722/469, loss: 0.2002747803926468
2023-01-24 03:58:09.803556: step: 724/469, loss: 0.05371290445327759
2023-01-24 03:58:10.428914: step: 726/469, loss: 0.039565615355968475
2023-01-24 03:58:11.077336: step: 728/469, loss: 0.016365688294172287
2023-01-24 03:58:11.680690: step: 730/469, loss: 0.05834020674228668
2023-01-24 03:58:12.294841: step: 732/469, loss: 0.009845305234193802
2023-01-24 03:58:12.896903: step: 734/469, loss: 0.041016723960638046
2023-01-24 03:58:13.519005: step: 736/469, loss: 0.015585620887577534
2023-01-24 03:58:14.186527: step: 738/469, loss: 0.16015508770942688
2023-01-24 03:58:14.811793: step: 740/469, loss: 0.14360953867435455
2023-01-24 03:58:15.468600: step: 742/469, loss: 0.10342170298099518
2023-01-24 03:58:16.077305: step: 744/469, loss: 0.013389134779572487
2023-01-24 03:58:16.735482: step: 746/469, loss: 0.11928045749664307
2023-01-24 03:58:17.343329: step: 748/469, loss: 0.05421704798936844
2023-01-24 03:58:17.964942: step: 750/469, loss: 0.5256090760231018
2023-01-24 03:58:18.588917: step: 752/469, loss: 0.023640748113393784
2023-01-24 03:58:19.215113: step: 754/469, loss: 0.037213560193777084
2023-01-24 03:58:19.899225: step: 756/469, loss: 0.018608342856168747
2023-01-24 03:58:20.582624: step: 758/469, loss: 0.0015264227986335754
2023-01-24 03:58:21.173839: step: 760/469, loss: 0.04242260754108429
2023-01-24 03:58:21.768056: step: 762/469, loss: 0.7380765676498413
2023-01-24 03:58:22.505694: step: 764/469, loss: 0.0545666366815567
2023-01-24 03:58:23.201384: step: 766/469, loss: 0.1233232393860817
2023-01-24 03:58:23.841856: step: 768/469, loss: 0.7233437895774841
2023-01-24 03:58:24.462996: step: 770/469, loss: 0.00846213661134243
2023-01-24 03:58:25.108875: step: 772/469, loss: 0.025160931050777435
2023-01-24 03:58:25.739243: step: 774/469, loss: 0.023392528295516968
2023-01-24 03:58:26.377652: step: 776/469, loss: 0.09777527302503586
2023-01-24 03:58:26.939021: step: 778/469, loss: 0.03297801688313484
2023-01-24 03:58:27.557765: step: 780/469, loss: 0.03944766893982887
2023-01-24 03:58:28.162344: step: 782/469, loss: 0.05732549726963043
2023-01-24 03:58:28.774125: step: 784/469, loss: 0.015613374300301075
2023-01-24 03:58:29.411185: step: 786/469, loss: 0.04868251085281372
2023-01-24 03:58:30.024648: step: 788/469, loss: 0.03899196535348892
2023-01-24 03:58:30.605096: step: 790/469, loss: 0.036485206335783005
2023-01-24 03:58:31.235213: step: 792/469, loss: 0.03200719133019447
2023-01-24 03:58:31.891344: step: 794/469, loss: 0.01654466614127159
2023-01-24 03:58:32.519298: step: 796/469, loss: 0.05316543206572533
2023-01-24 03:58:33.102132: step: 798/469, loss: 0.0019444635836407542
2023-01-24 03:58:33.699247: step: 800/469, loss: 0.06956598162651062
2023-01-24 03:58:34.315899: step: 802/469, loss: 0.015713702887296677
2023-01-24 03:58:35.020222: step: 804/469, loss: 0.018174387514591217
2023-01-24 03:58:35.641080: step: 806/469, loss: 0.034022312611341476
2023-01-24 03:58:36.227619: step: 808/469, loss: 0.009265918284654617
2023-01-24 03:58:36.852289: step: 810/469, loss: 0.04342231526970863
2023-01-24 03:58:37.485078: step: 812/469, loss: 0.19386352598667145
2023-01-24 03:58:38.097601: step: 814/469, loss: 0.0654096007347107
2023-01-24 03:58:38.743462: step: 816/469, loss: 0.03987232968211174
2023-01-24 03:58:39.387217: step: 818/469, loss: 0.1549762338399887
2023-01-24 03:58:40.029362: step: 820/469, loss: 0.015902718529105186
2023-01-24 03:58:40.644890: step: 822/469, loss: 0.012863630428910255
2023-01-24 03:58:41.271283: step: 824/469, loss: 0.0011162246810272336
2023-01-24 03:58:41.860623: step: 826/469, loss: 0.022756634280085564
2023-01-24 03:58:42.478504: step: 828/469, loss: 0.04327286779880524
2023-01-24 03:58:43.062434: step: 830/469, loss: 0.006346752867102623
2023-01-24 03:58:43.730570: step: 832/469, loss: 0.029777828603982925
2023-01-24 03:58:44.385996: step: 834/469, loss: 0.05840518698096275
2023-01-24 03:58:45.043812: step: 836/469, loss: 0.03870542719960213
2023-01-24 03:58:45.735171: step: 838/469, loss: 0.07472429424524307
2023-01-24 03:58:46.338921: step: 840/469, loss: 0.02006162516772747
2023-01-24 03:58:47.022131: step: 842/469, loss: 0.030478358268737793
2023-01-24 03:58:47.641268: step: 844/469, loss: 0.04837769269943237
2023-01-24 03:58:48.277020: step: 846/469, loss: 0.022878864780068398
2023-01-24 03:58:48.861592: step: 848/469, loss: 0.007214287295937538
2023-01-24 03:58:49.444555: step: 850/469, loss: 0.025364549830555916
2023-01-24 03:58:50.053432: step: 852/469, loss: 0.053298626095056534
2023-01-24 03:58:50.688549: step: 854/469, loss: 0.07309738546609879
2023-01-24 03:58:51.304585: step: 856/469, loss: 0.025104938074946404
2023-01-24 03:58:51.910414: step: 858/469, loss: 0.03455242142081261
2023-01-24 03:58:52.529364: step: 860/469, loss: 0.008442571386694908
2023-01-24 03:58:53.176202: step: 862/469, loss: 0.04814957454800606
2023-01-24 03:58:53.865663: step: 864/469, loss: 0.008963426575064659
2023-01-24 03:58:54.445843: step: 866/469, loss: 0.09332709014415741
2023-01-24 03:58:55.079259: step: 868/469, loss: 0.019229233264923096
2023-01-24 03:58:55.660196: step: 870/469, loss: 0.07128330320119858
2023-01-24 03:58:56.220545: step: 872/469, loss: 0.035470034927129745
2023-01-24 03:58:56.872836: step: 874/469, loss: 0.0392182283103466
2023-01-24 03:58:57.472771: step: 876/469, loss: 0.0073399618268013
2023-01-24 03:58:58.089688: step: 878/469, loss: 0.035065118223428726
2023-01-24 03:58:58.690578: step: 880/469, loss: 0.005196990445256233
2023-01-24 03:58:59.345525: step: 882/469, loss: 0.0597517192363739
2023-01-24 03:59:00.009275: step: 884/469, loss: 0.0620705671608448
2023-01-24 03:59:00.692701: step: 886/469, loss: 0.028478804975748062
2023-01-24 03:59:01.267889: step: 888/469, loss: 0.06184910610318184
2023-01-24 03:59:01.899271: step: 890/469, loss: 0.04905041679739952
2023-01-24 03:59:02.586055: step: 892/469, loss: 0.007581349927932024
2023-01-24 03:59:03.222075: step: 894/469, loss: 0.017444944009184837
2023-01-24 03:59:03.839569: step: 896/469, loss: 0.011200396344065666
2023-01-24 03:59:04.497888: step: 898/469, loss: 0.04748990014195442
2023-01-24 03:59:05.103134: step: 900/469, loss: 0.04625925421714783
2023-01-24 03:59:05.717980: step: 902/469, loss: 0.07253258675336838
2023-01-24 03:59:06.312110: step: 904/469, loss: 0.00748829310759902
2023-01-24 03:59:06.956507: step: 906/469, loss: 0.22255004942417145
2023-01-24 03:59:07.586752: step: 908/469, loss: 0.043984923511743546
2023-01-24 03:59:08.191184: step: 910/469, loss: 0.02163475565612316
2023-01-24 03:59:08.777732: step: 912/469, loss: 0.2576966881752014
2023-01-24 03:59:09.478625: step: 914/469, loss: 0.07093063741922379
2023-01-24 03:59:10.132163: step: 916/469, loss: 0.2424660623073578
2023-01-24 03:59:10.713357: step: 918/469, loss: 0.067013680934906
2023-01-24 03:59:11.326093: step: 920/469, loss: 0.00853918306529522
2023-01-24 03:59:11.938024: step: 922/469, loss: 0.18369174003601074
2023-01-24 03:59:12.615931: step: 924/469, loss: 0.011981997638940811
2023-01-24 03:59:13.225646: step: 926/469, loss: 0.07305097579956055
2023-01-24 03:59:13.774093: step: 928/469, loss: 0.0101209981366992
2023-01-24 03:59:14.364358: step: 930/469, loss: 0.013684126548469067
2023-01-24 03:59:14.962527: step: 932/469, loss: 0.05986110866069794
2023-01-24 03:59:15.613331: step: 934/469, loss: 0.12811024487018585
2023-01-24 03:59:16.220656: step: 936/469, loss: 0.043509408831596375
2023-01-24 03:59:16.846498: step: 938/469, loss: 0.00022222570260055363
==================================================
Loss: 0.075
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31681169470293485, 'r': 0.30538964119372086, 'f1': 0.3109958278436539}, 'combined': 0.22915482051637656, 'epoch': 24}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31793264921353154, 'r': 0.25452064781504125, 'f1': 0.28271450006284565}, 'combined': 0.15420790912518853, 'epoch': 24}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3205836413703475, 'r': 0.30537568874367066, 'f1': 0.3127949231640708}, 'combined': 0.23048046969984165, 'epoch': 24}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.31859581200071363, 'r': 0.25213666731986945, 'f1': 0.28149681039899627}, 'combined': 0.15354371476308887, 'epoch': 24}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3175722871994802, 'r': 0.3091358317520557, 'f1': 0.31329727564102566}, 'combined': 0.23085062415654523, 'epoch': 24}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3172533354632746, 'r': 0.25252552777040155, 'f1': 0.2812128393816086}, 'combined': 0.15338882148087743, 'epoch': 24}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34244791666666663, 'r': 0.31309523809523804, 'f1': 0.3271144278606965}, 'combined': 0.21807628524046432, 'epoch': 24}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.20652173913043478, 'r': 0.20652173913043478, 'f1': 0.20652173913043478}, 'combined': 0.10326086956521739, 'epoch': 24}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'epoch': 24}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3367284695409696, 'r': 0.2836953329718985, 'f1': 0.30794529449266833}, 'combined': 0.22690705909986086, 'epoch': 5}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32194821687746217, 'r': 0.2185595397283412, 'f1': 0.2603657514147977}, 'combined': 0.14201768258988964, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.20689655172413793, 'f1': 0.2926829268292683}, 'combined': 0.19512195121951217, 'epoch': 5}
******************************
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
2023-01-24 04:02:02.547704: step: 2/469, loss: 0.04856976494193077
2023-01-24 04:02:03.217061: step: 4/469, loss: 0.02147574909031391
2023-01-24 04:02:03.862016: step: 6/469, loss: 0.042533762753009796
2023-01-24 04:02:04.414649: step: 8/469, loss: 0.026998911052942276
2023-01-24 04:02:04.978965: step: 10/469, loss: 0.34051206707954407
2023-01-24 04:02:05.649933: step: 12/469, loss: 0.01712040603160858
2023-01-24 04:02:06.248252: step: 14/469, loss: 0.015525841154158115
2023-01-24 04:02:06.867918: step: 16/469, loss: 0.03011523000895977
2023-01-24 04:02:07.497791: step: 18/469, loss: 0.05591309815645218
2023-01-24 04:02:08.147479: step: 20/469, loss: 0.04188614338636398
2023-01-24 04:02:08.763221: step: 22/469, loss: 0.0298788920044899
2023-01-24 04:02:09.388518: step: 24/469, loss: 0.06907416880130768
2023-01-24 04:02:10.041880: step: 26/469, loss: 0.03653291240334511
2023-01-24 04:02:10.645345: step: 28/469, loss: 0.5556086301803589
2023-01-24 04:02:11.264214: step: 30/469, loss: 0.00822235643863678
2023-01-24 04:02:11.908877: step: 32/469, loss: 0.06540173292160034
2023-01-24 04:02:12.554212: step: 34/469, loss: 0.011102447286248207
2023-01-24 04:02:13.183434: step: 36/469, loss: 0.013518033549189568
2023-01-24 04:02:13.811171: step: 38/469, loss: 0.006230557803064585
2023-01-24 04:02:14.505201: step: 40/469, loss: 0.10722088813781738
2023-01-24 04:02:15.126308: step: 42/469, loss: 0.0031198596116155386
2023-01-24 04:02:15.739093: step: 44/469, loss: 0.0341133289039135
2023-01-24 04:02:16.378646: step: 46/469, loss: 0.0076862904243171215
2023-01-24 04:02:16.974073: step: 48/469, loss: 0.016710253432393074
2023-01-24 04:02:17.634069: step: 50/469, loss: 0.021328141912817955
2023-01-24 04:02:18.215398: step: 52/469, loss: 0.009631364606320858
2023-01-24 04:02:18.863530: step: 54/469, loss: 0.01578831858932972
2023-01-24 04:02:19.521272: step: 56/469, loss: 0.0020905991550534964
2023-01-24 04:02:20.212359: step: 58/469, loss: 0.42499473690986633
2023-01-24 04:02:20.834065: step: 60/469, loss: 0.029958128929138184
2023-01-24 04:02:21.456040: step: 62/469, loss: 0.030102305114269257
2023-01-24 04:02:22.049804: step: 64/469, loss: 0.053664810955524445
2023-01-24 04:02:22.634400: step: 66/469, loss: 0.01745413988828659
2023-01-24 04:02:23.202020: step: 68/469, loss: 0.08032667636871338
2023-01-24 04:02:23.834653: step: 70/469, loss: 0.06182575970888138
2023-01-24 04:02:24.454445: step: 72/469, loss: 0.005048101767897606
2023-01-24 04:02:25.095004: step: 74/469, loss: 0.05123775824904442
2023-01-24 04:02:25.711029: step: 76/469, loss: 4.262962341308594
2023-01-24 04:02:26.374565: step: 78/469, loss: 0.01811578869819641
2023-01-24 04:02:26.942927: step: 80/469, loss: 0.020840588957071304
2023-01-24 04:02:27.613583: step: 82/469, loss: 0.007778041996061802
2023-01-24 04:02:28.188805: step: 84/469, loss: 0.09622455388307571
2023-01-24 04:02:28.830144: step: 86/469, loss: 0.04122927784919739
2023-01-24 04:02:29.407126: step: 88/469, loss: 0.051051631569862366
2023-01-24 04:02:30.045120: step: 90/469, loss: 0.017610173672437668
2023-01-24 04:02:30.648769: step: 92/469, loss: 0.03190859407186508
2023-01-24 04:02:31.290522: step: 94/469, loss: 0.005970291793346405
2023-01-24 04:02:31.847128: step: 96/469, loss: 0.05467331036925316
2023-01-24 04:02:32.453155: step: 98/469, loss: 0.12147871404886246
2023-01-24 04:02:33.075393: step: 100/469, loss: 0.01909748837351799
2023-01-24 04:02:33.595138: step: 102/469, loss: 0.04550115019083023
2023-01-24 04:02:34.240414: step: 104/469, loss: 0.034840092062950134
2023-01-24 04:02:34.849388: step: 106/469, loss: 0.005601534619927406
2023-01-24 04:02:35.581202: step: 108/469, loss: 0.0599069744348526
2023-01-24 04:02:36.170151: step: 110/469, loss: 0.0008288627723231912
2023-01-24 04:02:36.770051: step: 112/469, loss: 0.04758596792817116
2023-01-24 04:02:37.391845: step: 114/469, loss: 0.2026187628507614
2023-01-24 04:02:37.938133: step: 116/469, loss: 0.02390963025391102
2023-01-24 04:02:38.530030: step: 118/469, loss: 0.007931917905807495
2023-01-24 04:02:39.243133: step: 120/469, loss: 0.04644008353352547
2023-01-24 04:02:39.832869: step: 122/469, loss: 0.03678201138973236
2023-01-24 04:02:40.443537: step: 124/469, loss: 0.017658861353993416
2023-01-24 04:02:41.048633: step: 126/469, loss: 0.023343989625573158
2023-01-24 04:02:41.715998: step: 128/469, loss: 0.03157182037830353
2023-01-24 04:02:42.317562: step: 130/469, loss: 0.015042303130030632
2023-01-24 04:02:42.888201: step: 132/469, loss: 0.005432233680039644
2023-01-24 04:02:43.396040: step: 134/469, loss: 0.008275623433291912
2023-01-24 04:02:43.962791: step: 136/469, loss: 0.00010147449938813224
2023-01-24 04:02:44.660319: step: 138/469, loss: 0.018918149173259735
2023-01-24 04:02:45.320434: step: 140/469, loss: 0.016375940293073654
2023-01-24 04:02:45.961352: step: 142/469, loss: 0.041358571499586105
2023-01-24 04:02:46.574184: step: 144/469, loss: 0.01368478499352932
2023-01-24 04:02:47.178579: step: 146/469, loss: 0.004914687480777502
2023-01-24 04:02:47.787884: step: 148/469, loss: 0.0020167571492493153
2023-01-24 04:02:48.390064: step: 150/469, loss: 0.0745353177189827
2023-01-24 04:02:49.026649: step: 152/469, loss: 0.019189924001693726
2023-01-24 04:02:49.579151: step: 154/469, loss: 0.002326143207028508
2023-01-24 04:02:50.221341: step: 156/469, loss: 0.012304248288273811
2023-01-24 04:02:50.801637: step: 158/469, loss: 0.020376984030008316
2023-01-24 04:02:51.429124: step: 160/469, loss: 0.004673916380852461
2023-01-24 04:02:51.985060: step: 162/469, loss: 0.04110435023903847
2023-01-24 04:02:52.574073: step: 164/469, loss: 0.04092944413423538
2023-01-24 04:02:53.173584: step: 166/469, loss: 0.012793663889169693
2023-01-24 04:02:53.816047: step: 168/469, loss: 0.022109219804406166
2023-01-24 04:02:54.423780: step: 170/469, loss: 0.007726403884589672
2023-01-24 04:02:55.044869: step: 172/469, loss: 0.03344342112541199
2023-01-24 04:02:55.659991: step: 174/469, loss: 0.0014511216431856155
2023-01-24 04:02:56.283531: step: 176/469, loss: 0.006137159187346697
2023-01-24 04:02:56.925666: step: 178/469, loss: 0.10614075511693954
2023-01-24 04:02:57.496213: step: 180/469, loss: 0.014324543066322803
2023-01-24 04:02:58.136230: step: 182/469, loss: 0.08042246848344803
2023-01-24 04:02:58.718109: step: 184/469, loss: 0.032187726348638535
2023-01-24 04:02:59.286818: step: 186/469, loss: 0.04879891872406006
2023-01-24 04:02:59.914771: step: 188/469, loss: 0.139285147190094
2023-01-24 04:03:00.568589: step: 190/469, loss: 0.005954607855528593
2023-01-24 04:03:01.146744: step: 192/469, loss: 0.011356913484632969
2023-01-24 04:03:01.780668: step: 194/469, loss: 0.004321274347603321
2023-01-24 04:03:02.459295: step: 196/469, loss: 0.013530028983950615
2023-01-24 04:03:03.031373: step: 198/469, loss: 0.0008386899717152119
2023-01-24 04:03:03.576982: step: 200/469, loss: 0.01096635963767767
2023-01-24 04:03:04.140596: step: 202/469, loss: 0.009184669703245163
2023-01-24 04:03:04.771088: step: 204/469, loss: 0.03868536278605461
2023-01-24 04:03:05.437403: step: 206/469, loss: 0.04301360249519348
2023-01-24 04:03:06.042021: step: 208/469, loss: 0.0010095011675730348
2023-01-24 04:03:06.596881: step: 210/469, loss: 0.000283485947875306
2023-01-24 04:03:07.192971: step: 212/469, loss: 0.0070633552968502045
2023-01-24 04:03:07.821871: step: 214/469, loss: 0.030808549374341965
2023-01-24 04:03:08.454790: step: 216/469, loss: 0.0026243298780173063
2023-01-24 04:03:09.098290: step: 218/469, loss: 0.0005290028639137745
2023-01-24 04:03:09.736873: step: 220/469, loss: 0.015227171592414379
2023-01-24 04:03:10.476571: step: 222/469, loss: 0.024634400382637978
2023-01-24 04:03:11.109444: step: 224/469, loss: 0.03855723887681961
2023-01-24 04:03:11.660575: step: 226/469, loss: 0.00018793513299897313
2023-01-24 04:03:12.321921: step: 228/469, loss: 0.01885269209742546
2023-01-24 04:03:12.954706: step: 230/469, loss: 0.049848005175590515
2023-01-24 04:03:13.581366: step: 232/469, loss: 0.0272691510617733
2023-01-24 04:03:14.202585: step: 234/469, loss: 0.00755769619718194
2023-01-24 04:03:14.852309: step: 236/469, loss: 0.049853160977363586
2023-01-24 04:03:15.480928: step: 238/469, loss: 0.10203791409730911
2023-01-24 04:03:16.117950: step: 240/469, loss: 0.05088697001338005
2023-01-24 04:03:16.660756: step: 242/469, loss: 0.00043119274778291583
2023-01-24 04:03:17.251304: step: 244/469, loss: 0.11058246344327927
2023-01-24 04:03:17.882301: step: 246/469, loss: 0.03444642946124077
2023-01-24 04:03:18.550216: step: 248/469, loss: 0.013254709541797638
2023-01-24 04:03:19.143109: step: 250/469, loss: 0.05417263135313988
2023-01-24 04:03:19.738817: step: 252/469, loss: 0.013920310884714127
2023-01-24 04:03:20.346966: step: 254/469, loss: 0.04292064905166626
2023-01-24 04:03:20.906588: step: 256/469, loss: 0.030953271314501762
2023-01-24 04:03:21.493096: step: 258/469, loss: 0.00650059524923563
2023-01-24 04:03:22.128457: step: 260/469, loss: 0.020494060590863228
2023-01-24 04:03:22.713041: step: 262/469, loss: 0.05571705847978592
2023-01-24 04:03:23.299230: step: 264/469, loss: 0.03857578709721565
2023-01-24 04:03:23.895470: step: 266/469, loss: 0.0627986490726471
2023-01-24 04:03:24.489621: step: 268/469, loss: 0.01743331365287304
2023-01-24 04:03:25.127682: step: 270/469, loss: 0.003057928988710046
2023-01-24 04:03:25.748983: step: 272/469, loss: 0.0327683687210083
2023-01-24 04:03:26.377909: step: 274/469, loss: 0.036044642329216
2023-01-24 04:03:27.000238: step: 276/469, loss: 0.018472548574209213
2023-01-24 04:03:27.590278: step: 278/469, loss: 0.0030957930721342564
2023-01-24 04:03:28.195841: step: 280/469, loss: 0.06196119263768196
2023-01-24 04:03:28.907408: step: 282/469, loss: 0.012512745335698128
2023-01-24 04:03:29.507324: step: 284/469, loss: 0.026475517079234123
2023-01-24 04:03:30.129586: step: 286/469, loss: 0.015970377251505852
2023-01-24 04:03:30.738257: step: 288/469, loss: 0.004397625103592873
2023-01-24 04:03:31.322680: step: 290/469, loss: 0.010436036624014378
2023-01-24 04:03:32.072120: step: 292/469, loss: 0.015440810471773148
2023-01-24 04:03:32.608563: step: 294/469, loss: 0.0022039152681827545
2023-01-24 04:03:33.185494: step: 296/469, loss: 0.042669110000133514
2023-01-24 04:03:33.832835: step: 298/469, loss: 0.011528090573847294
2023-01-24 04:03:34.490437: step: 300/469, loss: 0.025446249172091484
2023-01-24 04:03:35.139845: step: 302/469, loss: 0.049084506928920746
2023-01-24 04:03:35.757722: step: 304/469, loss: 0.029263099655508995
2023-01-24 04:03:36.369939: step: 306/469, loss: 0.005450424738228321
2023-01-24 04:03:36.987614: step: 308/469, loss: 0.008434198796749115
2023-01-24 04:03:37.608476: step: 310/469, loss: 0.01223000418394804
2023-01-24 04:03:38.251256: step: 312/469, loss: 0.05077080428600311
2023-01-24 04:03:38.888913: step: 314/469, loss: 0.004749195650219917
2023-01-24 04:03:39.473754: step: 316/469, loss: 0.048470769077539444
2023-01-24 04:03:40.111809: step: 318/469, loss: 0.04480629786849022
2023-01-24 04:03:40.688577: step: 320/469, loss: 0.044698476791381836
2023-01-24 04:03:41.359871: step: 322/469, loss: 0.01952251046895981
2023-01-24 04:03:41.985240: step: 324/469, loss: 0.01769523322582245
2023-01-24 04:03:42.638939: step: 326/469, loss: 0.02703937515616417
2023-01-24 04:03:43.283762: step: 328/469, loss: 0.1337839663028717
2023-01-24 04:03:43.887251: step: 330/469, loss: 0.05273359268903732
2023-01-24 04:03:44.532384: step: 332/469, loss: 0.02908332273364067
2023-01-24 04:03:45.135355: step: 334/469, loss: 0.04517734795808792
2023-01-24 04:03:45.718772: step: 336/469, loss: 0.014714795164763927
2023-01-24 04:03:46.347536: step: 338/469, loss: 0.021900169551372528
2023-01-24 04:03:46.964844: step: 340/469, loss: 0.015135765075683594
2023-01-24 04:03:47.555940: step: 342/469, loss: 0.010647600516676903
2023-01-24 04:03:48.155387: step: 344/469, loss: 0.0033777577336877584
2023-01-24 04:03:48.747196: step: 346/469, loss: 0.02138627879321575
2023-01-24 04:03:49.351201: step: 348/469, loss: 0.03390428051352501
2023-01-24 04:03:50.044130: step: 350/469, loss: 0.00392957916483283
2023-01-24 04:03:50.637850: step: 352/469, loss: 0.0018901792354881763
2023-01-24 04:03:51.257855: step: 354/469, loss: 0.05929534509778023
2023-01-24 04:03:51.956821: step: 356/469, loss: 0.013390686362981796
2023-01-24 04:03:52.507164: step: 358/469, loss: 0.05661235377192497
2023-01-24 04:03:53.157517: step: 360/469, loss: 0.036856770515441895
2023-01-24 04:03:53.734968: step: 362/469, loss: 0.027632741257548332
2023-01-24 04:03:54.315188: step: 364/469, loss: 0.002649830188602209
2023-01-24 04:03:54.958787: step: 366/469, loss: 0.20955486595630646
2023-01-24 04:03:55.533721: step: 368/469, loss: 0.0019603234250098467
2023-01-24 04:03:56.235543: step: 370/469, loss: 0.015419835224747658
2023-01-24 04:03:56.846233: step: 372/469, loss: 0.04204192012548447
2023-01-24 04:03:57.434838: step: 374/469, loss: 0.10948891192674637
2023-01-24 04:03:58.097557: step: 376/469, loss: 0.045809097588062286
2023-01-24 04:03:58.678600: step: 378/469, loss: 0.007452741265296936
2023-01-24 04:03:59.457457: step: 380/469, loss: 0.013179030269384384
2023-01-24 04:04:00.085241: step: 382/469, loss: 0.11277803778648376
2023-01-24 04:04:00.795026: step: 384/469, loss: 0.0019561247900128365
2023-01-24 04:04:01.437357: step: 386/469, loss: 0.00523748341947794
2023-01-24 04:04:02.109669: step: 388/469, loss: 0.10067883133888245
2023-01-24 04:04:02.778533: step: 390/469, loss: 0.054992761462926865
2023-01-24 04:04:03.378742: step: 392/469, loss: 0.007033468224108219
2023-01-24 04:04:03.988702: step: 394/469, loss: 0.2416965365409851
2023-01-24 04:04:04.598425: step: 396/469, loss: 0.023505480960011482
2023-01-24 04:04:05.252388: step: 398/469, loss: 0.008563170209527016
2023-01-24 04:04:05.943932: step: 400/469, loss: 0.003997010178864002
2023-01-24 04:04:06.590689: step: 402/469, loss: 0.023158133029937744
2023-01-24 04:04:07.262696: step: 404/469, loss: 0.03962918743491173
2023-01-24 04:04:07.918454: step: 406/469, loss: 0.054418012499809265
2023-01-24 04:04:08.471389: step: 408/469, loss: 0.02258702740073204
2023-01-24 04:04:09.048119: step: 410/469, loss: 0.007732185069471598
2023-01-24 04:04:09.632204: step: 412/469, loss: 0.056680869311094284
2023-01-24 04:04:10.275275: step: 414/469, loss: 0.6087327003479004
2023-01-24 04:04:10.904342: step: 416/469, loss: 0.06544509530067444
2023-01-24 04:04:11.535731: step: 418/469, loss: 0.019155997782945633
2023-01-24 04:04:12.092690: step: 420/469, loss: 0.045098453760147095
2023-01-24 04:04:12.832795: step: 422/469, loss: 0.008726864121854305
2023-01-24 04:04:13.474359: step: 424/469, loss: 0.023709028959274292
2023-01-24 04:04:14.187315: step: 426/469, loss: 0.043676912784576416
2023-01-24 04:04:14.875413: step: 428/469, loss: 0.008577961474657059
2023-01-24 04:04:15.449955: step: 430/469, loss: 0.00293761701323092
2023-01-24 04:04:16.027977: step: 432/469, loss: 0.02273917943239212
2023-01-24 04:04:16.651165: step: 434/469, loss: 0.005073876585811377
2023-01-24 04:04:17.210440: step: 436/469, loss: 0.00121480249799788
2023-01-24 04:04:17.819329: step: 438/469, loss: 0.012796197086572647
2023-01-24 04:04:18.509650: step: 440/469, loss: 0.12014244496822357
2023-01-24 04:04:19.385885: step: 442/469, loss: 0.018803711980581284
2023-01-24 04:04:19.991077: step: 444/469, loss: 0.006569478195160627
2023-01-24 04:04:20.629781: step: 446/469, loss: 0.0064140004105865955
2023-01-24 04:04:21.241383: step: 448/469, loss: 0.034201301634311676
2023-01-24 04:04:21.842918: step: 450/469, loss: 0.0773974359035492
2023-01-24 04:04:22.417023: step: 452/469, loss: 0.006095223128795624
2023-01-24 04:04:22.990173: step: 454/469, loss: 0.024928433820605278
2023-01-24 04:04:23.623405: step: 456/469, loss: 0.008130456320941448
2023-01-24 04:04:24.206353: step: 458/469, loss: 0.010952129028737545
2023-01-24 04:04:24.854840: step: 460/469, loss: 0.034331656992435455
2023-01-24 04:04:25.515416: step: 462/469, loss: 0.024890027940273285
2023-01-24 04:04:26.185267: step: 464/469, loss: 0.013754414394497871
2023-01-24 04:04:26.824635: step: 466/469, loss: 0.21725188195705414
2023-01-24 04:04:27.437136: step: 468/469, loss: 0.03119678795337677
2023-01-24 04:04:28.111261: step: 470/469, loss: 0.010625576600432396
2023-01-24 04:04:28.822410: step: 472/469, loss: 0.38016849756240845
2023-01-24 04:04:29.501168: step: 474/469, loss: 0.012717713601887226
2023-01-24 04:04:30.179060: step: 476/469, loss: 0.07365652173757553
2023-01-24 04:04:30.827865: step: 478/469, loss: 0.0703604593873024
2023-01-24 04:04:31.414854: step: 480/469, loss: 0.027157843112945557
2023-01-24 04:04:32.029883: step: 482/469, loss: 0.008624759502708912
2023-01-24 04:04:32.659249: step: 484/469, loss: 0.20557545125484467
2023-01-24 04:04:33.269548: step: 486/469, loss: 0.02057848870754242
2023-01-24 04:04:33.878518: step: 488/469, loss: 0.010233267210423946
2023-01-24 04:04:34.562627: step: 490/469, loss: 0.006442150566726923
2023-01-24 04:04:35.211797: step: 492/469, loss: 0.02376784197986126
2023-01-24 04:04:35.837316: step: 494/469, loss: 0.03933355212211609
2023-01-24 04:04:36.492615: step: 496/469, loss: 0.03800881281495094
2023-01-24 04:04:37.123789: step: 498/469, loss: 0.10246901214122772
2023-01-24 04:04:37.744083: step: 500/469, loss: 0.0008079497492872179
2023-01-24 04:04:38.338045: step: 502/469, loss: 0.1171233206987381
2023-01-24 04:04:38.977772: step: 504/469, loss: 1.5556166172027588
2023-01-24 04:04:39.629635: step: 506/469, loss: 0.07243640720844269
2023-01-24 04:04:40.239719: step: 508/469, loss: 0.0018142522312700748
2023-01-24 04:04:40.810586: step: 510/469, loss: 0.01611032709479332
2023-01-24 04:04:41.404618: step: 512/469, loss: 1.1219016313552856
2023-01-24 04:04:42.017605: step: 514/469, loss: 0.0015680743381381035
2023-01-24 04:04:42.632525: step: 516/469, loss: 0.03115461766719818
2023-01-24 04:04:43.295987: step: 518/469, loss: 0.12085239589214325
2023-01-24 04:04:43.937246: step: 520/469, loss: 0.00013592492905445397
2023-01-24 04:04:44.566834: step: 522/469, loss: 0.022860264405608177
2023-01-24 04:04:45.237097: step: 524/469, loss: 0.24189890921115875
2023-01-24 04:04:45.879080: step: 526/469, loss: 0.6601332426071167
2023-01-24 04:04:46.488370: step: 528/469, loss: 0.0065761953592300415
2023-01-24 04:04:47.101944: step: 530/469, loss: 0.018679099157452583
2023-01-24 04:04:47.742395: step: 532/469, loss: 0.08067703992128372
2023-01-24 04:04:48.311680: step: 534/469, loss: 0.00792071782052517
2023-01-24 04:04:48.881558: step: 536/469, loss: 0.01419886201620102
2023-01-24 04:04:49.551561: step: 538/469, loss: 0.08376763761043549
2023-01-24 04:04:50.172330: step: 540/469, loss: 0.014224591664969921
2023-01-24 04:04:50.949018: step: 542/469, loss: 0.014264407567679882
2023-01-24 04:04:51.667813: step: 544/469, loss: 0.017167195677757263
2023-01-24 04:04:52.289336: step: 546/469, loss: 0.054914992302656174
2023-01-24 04:04:52.899580: step: 548/469, loss: 0.0004956695483997464
2023-01-24 04:04:53.513783: step: 550/469, loss: 0.017324771732091904
2023-01-24 04:04:54.110132: step: 552/469, loss: 0.008702096529304981
2023-01-24 04:04:54.705177: step: 554/469, loss: 0.006109388079494238
2023-01-24 04:04:55.340542: step: 556/469, loss: 0.13674870133399963
2023-01-24 04:04:55.996300: step: 558/469, loss: 0.09270133823156357
2023-01-24 04:04:56.615224: step: 560/469, loss: 0.11514364182949066
2023-01-24 04:04:57.285905: step: 562/469, loss: 0.007401920389384031
2023-01-24 04:04:57.926486: step: 564/469, loss: 0.009537674486637115
2023-01-24 04:04:58.595676: step: 566/469, loss: 0.015438495203852654
2023-01-24 04:04:59.184864: step: 568/469, loss: 0.014768391847610474
2023-01-24 04:04:59.869810: step: 570/469, loss: 0.03671162202954292
2023-01-24 04:05:00.482646: step: 572/469, loss: 0.007807845249772072
2023-01-24 04:05:01.035160: step: 574/469, loss: 0.07082484662532806
2023-01-24 04:05:01.677005: step: 576/469, loss: 0.03761536255478859
2023-01-24 04:05:02.275060: step: 578/469, loss: 0.009655756875872612
2023-01-24 04:05:02.880208: step: 580/469, loss: 0.002102601807564497
2023-01-24 04:05:03.495555: step: 582/469, loss: 0.05156554654240608
2023-01-24 04:05:04.189397: step: 584/469, loss: 0.1121736615896225
2023-01-24 04:05:04.787021: step: 586/469, loss: 0.2778625190258026
2023-01-24 04:05:05.384507: step: 588/469, loss: 0.009841597639024258
2023-01-24 04:05:06.088025: step: 590/469, loss: 0.028299439698457718
2023-01-24 04:05:06.760986: step: 592/469, loss: 0.05079028010368347
2023-01-24 04:05:07.365442: step: 594/469, loss: 0.01051055733114481
2023-01-24 04:05:08.013538: step: 596/469, loss: 0.015717197209596634
2023-01-24 04:05:08.679214: step: 598/469, loss: 0.046247448772192
2023-01-24 04:05:09.278870: step: 600/469, loss: 0.026593945920467377
2023-01-24 04:05:09.834060: step: 602/469, loss: 0.05360126122832298
2023-01-24 04:05:10.451293: step: 604/469, loss: 0.02141428180038929
2023-01-24 04:05:11.067995: step: 606/469, loss: 0.3677946925163269
2023-01-24 04:05:11.709837: step: 608/469, loss: 0.00097944017034024
2023-01-24 04:05:12.329002: step: 610/469, loss: 0.0052940682508051395
2023-01-24 04:05:12.973530: step: 612/469, loss: 0.006692413706332445
2023-01-24 04:05:13.581356: step: 614/469, loss: 0.0067467219196259975
2023-01-24 04:05:14.151013: step: 616/469, loss: 0.016620740294456482
2023-01-24 04:05:14.751888: step: 618/469, loss: 0.06428956240415573
2023-01-24 04:05:15.431996: step: 620/469, loss: 0.03241540119051933
2023-01-24 04:05:16.094001: step: 622/469, loss: 0.08981288969516754
2023-01-24 04:05:16.744651: step: 624/469, loss: 0.03582325950264931
2023-01-24 04:05:17.345115: step: 626/469, loss: 0.0794992595911026
2023-01-24 04:05:17.986769: step: 628/469, loss: 0.060099996626377106
2023-01-24 04:05:18.519097: step: 630/469, loss: 0.035620734095573425
2023-01-24 04:05:19.099464: step: 632/469, loss: 0.0037603736855089664
2023-01-24 04:05:19.740483: step: 634/469, loss: 0.001754170167259872
2023-01-24 04:05:20.429953: step: 636/469, loss: 0.04415275529026985
2023-01-24 04:05:20.999702: step: 638/469, loss: 0.022454949095845222
2023-01-24 04:05:21.619855: step: 640/469, loss: 0.012613899074494839
2023-01-24 04:05:22.240332: step: 642/469, loss: 0.005072041414678097
2023-01-24 04:05:22.900347: step: 644/469, loss: 0.04319910705089569
2023-01-24 04:05:23.539181: step: 646/469, loss: 0.18360324203968048
2023-01-24 04:05:24.208596: step: 648/469, loss: 0.046460311859846115
2023-01-24 04:05:24.779119: step: 650/469, loss: 0.009786998853087425
2023-01-24 04:05:25.411979: step: 652/469, loss: 0.1228475421667099
2023-01-24 04:05:26.090060: step: 654/469, loss: 0.020434217527508736
2023-01-24 04:05:26.764688: step: 656/469, loss: 0.0253992211073637
2023-01-24 04:05:27.363995: step: 658/469, loss: 0.027405569329857826
2023-01-24 04:05:27.992834: step: 660/469, loss: 0.01696774736046791
2023-01-24 04:05:28.633583: step: 662/469, loss: 0.017147373408079147
2023-01-24 04:05:29.234239: step: 664/469, loss: 0.025060776621103287
2023-01-24 04:05:29.911256: step: 666/469, loss: 0.009904792532324791
2023-01-24 04:05:30.539303: step: 668/469, loss: 0.002904832363128662
2023-01-24 04:05:31.198177: step: 670/469, loss: 0.027811652049422264
2023-01-24 04:05:31.807926: step: 672/469, loss: 0.013813911005854607
2023-01-24 04:05:32.469379: step: 674/469, loss: 0.010885735973715782
2023-01-24 04:05:33.109456: step: 676/469, loss: 0.27891072630882263
2023-01-24 04:05:33.725314: step: 678/469, loss: 0.01488383486866951
2023-01-24 04:05:34.383357: step: 680/469, loss: 0.030160052701830864
2023-01-24 04:05:35.025218: step: 682/469, loss: 0.03998572379350662
2023-01-24 04:05:35.637181: step: 684/469, loss: 0.03636665642261505
2023-01-24 04:05:36.247679: step: 686/469, loss: 0.07142338901758194
2023-01-24 04:05:36.963207: step: 688/469, loss: 0.0981699749827385
2023-01-24 04:05:37.580615: step: 690/469, loss: 0.0968250259757042
2023-01-24 04:05:38.166334: step: 692/469, loss: 0.014923705719411373
2023-01-24 04:05:38.799515: step: 694/469, loss: 0.03728951886296272
2023-01-24 04:05:39.475481: step: 696/469, loss: 0.038896434009075165
2023-01-24 04:05:40.136324: step: 698/469, loss: 0.07678399235010147
2023-01-24 04:05:40.746319: step: 700/469, loss: 0.01881502754986286
2023-01-24 04:05:41.367554: step: 702/469, loss: 0.008039776235818863
2023-01-24 04:05:42.106259: step: 704/469, loss: 0.013041947036981583
2023-01-24 04:05:42.642484: step: 706/469, loss: 0.00392870930954814
2023-01-24 04:05:43.361594: step: 708/469, loss: 0.08560433983802795
2023-01-24 04:05:43.954754: step: 710/469, loss: 0.0139212841168046
2023-01-24 04:05:44.586629: step: 712/469, loss: 0.09286808222532272
2023-01-24 04:05:45.259323: step: 714/469, loss: 0.03638756275177002
2023-01-24 04:05:45.917122: step: 716/469, loss: 0.01713269017636776
2023-01-24 04:05:46.553053: step: 718/469, loss: 0.13275638222694397
2023-01-24 04:05:47.193516: step: 720/469, loss: 0.05306063964962959
2023-01-24 04:05:47.781165: step: 722/469, loss: 0.02417629025876522
2023-01-24 04:05:48.437027: step: 724/469, loss: 0.013635202310979366
2023-01-24 04:05:49.029635: step: 726/469, loss: 0.12524113059043884
2023-01-24 04:05:49.644518: step: 728/469, loss: 0.1346540004014969
2023-01-24 04:05:50.259244: step: 730/469, loss: 0.01829395443201065
2023-01-24 04:05:50.929856: step: 732/469, loss: 0.3671169579029083
2023-01-24 04:05:51.553785: step: 734/469, loss: 0.004386854358017445
2023-01-24 04:05:52.135473: step: 736/469, loss: 0.039212267845869064
2023-01-24 04:05:52.797226: step: 738/469, loss: 0.0047495318576693535
2023-01-24 04:05:53.422358: step: 740/469, loss: 0.03000878542661667
2023-01-24 04:05:54.068154: step: 742/469, loss: 0.004853927996009588
2023-01-24 04:05:54.706542: step: 744/469, loss: 0.0021590818651020527
2023-01-24 04:05:55.361870: step: 746/469, loss: 0.02374895289540291
2023-01-24 04:05:55.990922: step: 748/469, loss: 0.009065737947821617
2023-01-24 04:05:56.560638: step: 750/469, loss: 0.008073159493505955
2023-01-24 04:05:57.124924: step: 752/469, loss: 0.11257588118314743
2023-01-24 04:05:57.767402: step: 754/469, loss: 0.04057428240776062
2023-01-24 04:05:58.421680: step: 756/469, loss: 0.10555069148540497
2023-01-24 04:05:59.109866: step: 758/469, loss: 0.023752979934215546
2023-01-24 04:05:59.765351: step: 760/469, loss: 0.048274967819452286
2023-01-24 04:06:00.438450: step: 762/469, loss: 1.2696187496185303
2023-01-24 04:06:01.075055: step: 764/469, loss: 0.012262381613254547
2023-01-24 04:06:01.698789: step: 766/469, loss: 0.03396160155534744
2023-01-24 04:06:02.323742: step: 768/469, loss: 0.1591954231262207
2023-01-24 04:06:02.983244: step: 770/469, loss: 0.05642412602901459
2023-01-24 04:06:03.635799: step: 772/469, loss: 0.3960493803024292
2023-01-24 04:06:04.291959: step: 774/469, loss: 0.026414884254336357
2023-01-24 04:06:04.869132: step: 776/469, loss: 0.026224391534924507
2023-01-24 04:06:05.486345: step: 778/469, loss: 0.03593488037586212
2023-01-24 04:06:06.128710: step: 780/469, loss: 0.0621548630297184
2023-01-24 04:06:06.847469: step: 782/469, loss: 0.0032862641382962465
2023-01-24 04:06:07.540592: step: 784/469, loss: 0.006173399742692709
2023-01-24 04:06:08.208963: step: 786/469, loss: 0.09690824151039124
2023-01-24 04:06:08.845461: step: 788/469, loss: 0.026896344497799873
2023-01-24 04:06:09.438055: step: 790/469, loss: 0.030217744410037994
2023-01-24 04:06:10.088303: step: 792/469, loss: 0.00029961648397147655
2023-01-24 04:06:10.794393: step: 794/469, loss: 0.025184880942106247
2023-01-24 04:06:11.389844: step: 796/469, loss: 0.1708069145679474
2023-01-24 04:06:11.994383: step: 798/469, loss: 0.013849414885044098
2023-01-24 04:06:12.574753: step: 800/469, loss: 0.03732619807124138
2023-01-24 04:06:13.212158: step: 802/469, loss: 0.018460582941770554
2023-01-24 04:06:13.866247: step: 804/469, loss: 0.003849827451631427
2023-01-24 04:06:14.483841: step: 806/469, loss: 0.03699662536382675
2023-01-24 04:06:15.052059: step: 808/469, loss: 0.04430724307894707
2023-01-24 04:06:15.653076: step: 810/469, loss: 0.0428469218313694
2023-01-24 04:06:16.263882: step: 812/469, loss: 0.028586532920598984
2023-01-24 04:06:16.879966: step: 814/469, loss: 0.05149797722697258
2023-01-24 04:06:17.458351: step: 816/469, loss: 0.013561070896685123
2023-01-24 04:06:18.089873: step: 818/469, loss: 0.10084158927202225
2023-01-24 04:06:18.785813: step: 820/469, loss: 0.014455013908445835
2023-01-24 04:06:19.417091: step: 822/469, loss: 0.01934192143380642
2023-01-24 04:06:20.017537: step: 824/469, loss: 0.03623116388916969
2023-01-24 04:06:20.649139: step: 826/469, loss: 0.0033513649832457304
2023-01-24 04:06:21.269987: step: 828/469, loss: 0.06103557348251343
2023-01-24 04:06:21.908797: step: 830/469, loss: 0.09281483292579651
2023-01-24 04:06:22.543226: step: 832/469, loss: 0.02423933893442154
2023-01-24 04:06:23.222775: step: 834/469, loss: 0.0684056505560875
2023-01-24 04:06:23.834863: step: 836/469, loss: 0.09093356877565384
2023-01-24 04:06:24.562141: step: 838/469, loss: 0.023410648107528687
2023-01-24 04:06:25.183849: step: 840/469, loss: 0.08767075836658478
2023-01-24 04:06:25.720204: step: 842/469, loss: 0.007343295030295849
2023-01-24 04:06:26.321690: step: 844/469, loss: 0.00962060783058405
2023-01-24 04:06:26.961189: step: 846/469, loss: 0.11975578963756561
2023-01-24 04:06:27.525818: step: 848/469, loss: 0.006536045111715794
2023-01-24 04:06:28.199094: step: 850/469, loss: 0.01408056914806366
2023-01-24 04:06:28.807366: step: 852/469, loss: 0.01377950794994831
2023-01-24 04:06:29.446448: step: 854/469, loss: 0.008818451315164566
2023-01-24 04:06:30.030752: step: 856/469, loss: 0.0555163249373436
2023-01-24 04:06:30.723914: step: 858/469, loss: 0.1449873000383377
2023-01-24 04:06:31.347646: step: 860/469, loss: 0.028125213459134102
2023-01-24 04:06:32.049417: step: 862/469, loss: 0.036477431654930115
2023-01-24 04:06:32.747106: step: 864/469, loss: 0.10478488355875015
2023-01-24 04:06:33.337882: step: 866/469, loss: 0.0466022826731205
2023-01-24 04:06:33.925734: step: 868/469, loss: 0.05031195282936096
2023-01-24 04:06:34.528510: step: 870/469, loss: 0.015532007440924644
2023-01-24 04:06:35.194279: step: 872/469, loss: 0.0006207653786987066
2023-01-24 04:06:35.857427: step: 874/469, loss: 0.05724656581878662
2023-01-24 04:06:36.451077: step: 876/469, loss: 0.09066110849380493
2023-01-24 04:06:37.117778: step: 878/469, loss: 0.01952778361737728
2023-01-24 04:06:37.811658: step: 880/469, loss: 0.020550131797790527
2023-01-24 04:06:38.412533: step: 882/469, loss: 0.02035904861986637
2023-01-24 04:06:39.027270: step: 884/469, loss: 0.0837024450302124
2023-01-24 04:06:39.618487: step: 886/469, loss: 0.02065715566277504
2023-01-24 04:06:40.202782: step: 888/469, loss: 0.061157356947660446
2023-01-24 04:06:40.843096: step: 890/469, loss: 0.0634181872010231
2023-01-24 04:06:41.444741: step: 892/469, loss: 0.07618377357721329
2023-01-24 04:06:42.140020: step: 894/469, loss: 0.006980047095566988
2023-01-24 04:06:42.803673: step: 896/469, loss: 0.07628069072961807
2023-01-24 04:06:43.553365: step: 898/469, loss: 0.03572295978665352
2023-01-24 04:06:44.248352: step: 900/469, loss: 0.0065027568489313126
2023-01-24 04:06:44.859475: step: 902/469, loss: 0.05485999584197998
2023-01-24 04:06:45.520106: step: 904/469, loss: 0.016958028078079224
2023-01-24 04:06:46.270828: step: 906/469, loss: 0.07176735252141953
2023-01-24 04:06:46.932123: step: 908/469, loss: 0.008512450382113457
2023-01-24 04:06:47.599198: step: 910/469, loss: 0.015240861102938652
2023-01-24 04:06:48.280314: step: 912/469, loss: 0.01660452038049698
2023-01-24 04:06:48.962336: step: 914/469, loss: 0.001401496701873839
2023-01-24 04:06:49.651414: step: 916/469, loss: 0.013293241150677204
2023-01-24 04:06:50.242059: step: 918/469, loss: 0.01657457835972309
2023-01-24 04:06:50.871613: step: 920/469, loss: 0.08381480723619461
2023-01-24 04:06:51.465867: step: 922/469, loss: 0.0026067576836794615
2023-01-24 04:06:52.129525: step: 924/469, loss: 0.008933331817388535
2023-01-24 04:06:52.697120: step: 926/469, loss: 0.011091455817222595
2023-01-24 04:06:53.415827: step: 928/469, loss: 0.01633446104824543
2023-01-24 04:06:54.018914: step: 930/469, loss: 0.027701539918780327
2023-01-24 04:06:54.661231: step: 932/469, loss: 0.08012156188488007
2023-01-24 04:06:55.311995: step: 934/469, loss: 0.01416864525526762
2023-01-24 04:06:55.945808: step: 936/469, loss: 0.009045025333762169
2023-01-24 04:06:56.574941: step: 938/469, loss: 0.03131178393959999
==================================================
Loss: 0.063
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32658863702220703, 'r': 0.305518402375613, 'f1': 0.3157023491214667}, 'combined': 0.232622783563186, 'epoch': 25}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3276759576781532, 'r': 0.2560249477192524, 'f1': 0.2874527661603933}, 'combined': 0.15679241790566906, 'epoch': 25}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3365515616950899, 'r': 0.3058979090169792, 'f1': 0.3204934354909504}, 'combined': 0.23615305773017395, 'epoch': 25}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33594009209246956, 'r': 0.2621746555854314, 'f1': 0.29450863160830065}, 'combined': 0.1606410717863458, 'epoch': 25}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33064516129032256, 'r': 0.29285714285714287, 'f1': 0.3106060606060606}, 'combined': 0.20707070707070707, 'epoch': 25}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.325, 'r': 0.2826086956521739, 'f1': 0.3023255813953488}, 'combined': 0.1511627906976744, 'epoch': 25}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 04:09:51.771118: step: 2/469, loss: 0.052119068801403046
2023-01-24 04:09:52.482780: step: 4/469, loss: 0.057875435799360275
2023-01-24 04:09:53.090016: step: 6/469, loss: 0.01828203722834587
2023-01-24 04:09:53.742173: step: 8/469, loss: 0.03723328188061714
2023-01-24 04:09:54.314741: step: 10/469, loss: 0.049895111471414566
2023-01-24 04:09:54.910151: step: 12/469, loss: 0.03184844180941582
2023-01-24 04:09:55.455275: step: 14/469, loss: 0.020090363919734955
2023-01-24 04:09:56.038810: step: 16/469, loss: 0.05181034654378891
2023-01-24 04:09:56.693905: step: 18/469, loss: 0.05390797555446625
2023-01-24 04:09:57.273810: step: 20/469, loss: 0.02640211582183838
2023-01-24 04:09:57.890868: step: 22/469, loss: 0.00038729762309230864
2023-01-24 04:09:58.490091: step: 24/469, loss: 0.017456218600273132
2023-01-24 04:09:59.100453: step: 26/469, loss: 0.018573587760329247
2023-01-24 04:09:59.668042: step: 28/469, loss: 0.03029969520866871
2023-01-24 04:10:00.332707: step: 30/469, loss: 0.07916606217622757
2023-01-24 04:10:00.974817: step: 32/469, loss: 0.02013191021978855
2023-01-24 04:10:01.583025: step: 34/469, loss: 0.03712153434753418
2023-01-24 04:10:02.258648: step: 36/469, loss: 0.021866630762815475
2023-01-24 04:10:02.964800: step: 38/469, loss: 0.0033951029181480408
2023-01-24 04:10:03.639962: step: 40/469, loss: 0.03701892867684364
2023-01-24 04:10:04.333568: step: 42/469, loss: 0.00207902560941875
2023-01-24 04:10:04.897892: step: 44/469, loss: 0.05544053018093109
2023-01-24 04:10:05.485343: step: 46/469, loss: 0.01703200861811638
2023-01-24 04:10:06.142959: step: 48/469, loss: 0.004666522610932589
2023-01-24 04:10:06.764204: step: 50/469, loss: 0.024404587224125862
2023-01-24 04:10:07.415618: step: 52/469, loss: 0.00701537961140275
2023-01-24 04:10:08.009061: step: 54/469, loss: 0.02445834130048752
2023-01-24 04:10:08.638335: step: 56/469, loss: 0.1930391788482666
2023-01-24 04:10:09.204172: step: 58/469, loss: 0.02732478454709053
2023-01-24 04:10:09.824281: step: 60/469, loss: 0.04507780447602272
2023-01-24 04:10:10.457695: step: 62/469, loss: 0.12123608589172363
2023-01-24 04:10:11.129978: step: 64/469, loss: 0.11656873673200607
2023-01-24 04:10:11.733951: step: 66/469, loss: 0.009603939950466156
2023-01-24 04:10:12.482262: step: 68/469, loss: 0.013164698146283627
2023-01-24 04:10:13.128191: step: 70/469, loss: 0.020418571308255196
2023-01-24 04:10:13.757756: step: 72/469, loss: 0.02749587595462799
2023-01-24 04:10:14.324320: step: 74/469, loss: 0.003771075513213873
2023-01-24 04:10:14.901844: step: 76/469, loss: 0.022811949253082275
2023-01-24 04:10:15.610876: step: 78/469, loss: 0.0032443255186080933
2023-01-24 04:10:16.180588: step: 80/469, loss: 0.061158884316682816
2023-01-24 04:10:16.814637: step: 82/469, loss: 0.033115629106760025
2023-01-24 04:10:17.410905: step: 84/469, loss: 0.008742800913751125
2023-01-24 04:10:18.060858: step: 86/469, loss: 0.07537149637937546
2023-01-24 04:10:18.713685: step: 88/469, loss: 0.2844546437263489
2023-01-24 04:10:19.259054: step: 90/469, loss: 0.02401832304894924
2023-01-24 04:10:19.910153: step: 92/469, loss: 0.01951124705374241
2023-01-24 04:10:20.550278: step: 94/469, loss: 0.027710849419236183
2023-01-24 04:10:21.247944: step: 96/469, loss: 0.04442556947469711
2023-01-24 04:10:21.897997: step: 98/469, loss: 0.019059425219893456
2023-01-24 04:10:22.473831: step: 100/469, loss: 0.09212709963321686
2023-01-24 04:10:23.087424: step: 102/469, loss: 0.01231745257973671
2023-01-24 04:10:23.800120: step: 104/469, loss: 0.0010406281799077988
2023-01-24 04:10:24.365844: step: 106/469, loss: 0.0013047197135165334
2023-01-24 04:10:25.030075: step: 108/469, loss: 0.08898918330669403
2023-01-24 04:10:25.661908: step: 110/469, loss: 0.013732579536736012
2023-01-24 04:10:26.270219: step: 112/469, loss: 0.03436555713415146
2023-01-24 04:10:26.916538: step: 114/469, loss: 0.003770434530451894
2023-01-24 04:10:27.507374: step: 116/469, loss: 0.019989464432001114
2023-01-24 04:10:28.122209: step: 118/469, loss: 0.04549114778637886
2023-01-24 04:10:28.724495: step: 120/469, loss: 0.02905629761517048
2023-01-24 04:10:29.402025: step: 122/469, loss: 0.015283535234630108
2023-01-24 04:10:30.014089: step: 124/469, loss: 0.030058445408940315
2023-01-24 04:10:30.623028: step: 126/469, loss: 0.012366805225610733
2023-01-24 04:10:31.253444: step: 128/469, loss: 0.01682085543870926
2023-01-24 04:10:31.841466: step: 130/469, loss: 0.5060863494873047
2023-01-24 04:10:32.449619: step: 132/469, loss: 0.050181202590465546
2023-01-24 04:10:33.095261: step: 134/469, loss: 0.005061844363808632
2023-01-24 04:10:33.704597: step: 136/469, loss: 0.023658951744437218
2023-01-24 04:10:34.312642: step: 138/469, loss: 0.029817741364240646
2023-01-24 04:10:34.893509: step: 140/469, loss: 0.006416229996830225
2023-01-24 04:10:35.484334: step: 142/469, loss: 2.4560458660125732
2023-01-24 04:10:36.087095: step: 144/469, loss: 0.05049045756459236
2023-01-24 04:10:36.753331: step: 146/469, loss: 2.2055299282073975
2023-01-24 04:10:37.351513: step: 148/469, loss: 0.0047340369783341885
2023-01-24 04:10:38.087474: step: 150/469, loss: 0.008636378683149815
2023-01-24 04:10:38.763185: step: 152/469, loss: 0.08580818772315979
2023-01-24 04:10:39.454018: step: 154/469, loss: 0.04944342374801636
2023-01-24 04:10:40.062205: step: 156/469, loss: 0.025038911029696465
2023-01-24 04:10:40.652407: step: 158/469, loss: 0.0020327784586697817
2023-01-24 04:10:41.270977: step: 160/469, loss: 0.03520830348134041
2023-01-24 04:10:41.884004: step: 162/469, loss: 0.007501641754060984
2023-01-24 04:10:42.554177: step: 164/469, loss: 0.6785876154899597
2023-01-24 04:10:43.198778: step: 166/469, loss: 0.03633784130215645
2023-01-24 04:10:43.817325: step: 168/469, loss: 0.018300127238035202
2023-01-24 04:10:44.379575: step: 170/469, loss: 0.011675868183374405
2023-01-24 04:10:44.986794: step: 172/469, loss: 0.06578411906957626
2023-01-24 04:10:45.653444: step: 174/469, loss: 0.05599719285964966
2023-01-24 04:10:46.281034: step: 176/469, loss: 0.06624706834554672
2023-01-24 04:10:46.919507: step: 178/469, loss: 0.23955385386943817
2023-01-24 04:10:47.522068: step: 180/469, loss: 0.2692038416862488
2023-01-24 04:10:48.176874: step: 182/469, loss: 0.011191947385668755
2023-01-24 04:10:48.779619: step: 184/469, loss: 0.0032901111990213394
2023-01-24 04:10:49.383493: step: 186/469, loss: 0.33437827229499817
2023-01-24 04:10:50.051625: step: 188/469, loss: 0.02446429431438446
2023-01-24 04:10:50.683452: step: 190/469, loss: 0.004033736884593964
2023-01-24 04:10:51.317504: step: 192/469, loss: 0.003232074435800314
2023-01-24 04:10:51.923336: step: 194/469, loss: 0.012413287535309792
2023-01-24 04:10:52.550774: step: 196/469, loss: 0.00035754716373048723
2023-01-24 04:10:53.132854: step: 198/469, loss: 0.0028858347795903683
2023-01-24 04:10:53.815308: step: 200/469, loss: 0.011671126820147038
2023-01-24 04:10:54.410321: step: 202/469, loss: 0.03840034082531929
2023-01-24 04:10:55.173610: step: 204/469, loss: 0.039894383400678635
2023-01-24 04:10:55.782436: step: 206/469, loss: 0.032491691410541534
2023-01-24 04:10:56.394213: step: 208/469, loss: 0.031528256833553314
2023-01-24 04:10:57.045752: step: 210/469, loss: 0.05007137358188629
2023-01-24 04:10:57.620867: step: 212/469, loss: 0.05403231456875801
2023-01-24 04:10:58.220975: step: 214/469, loss: 0.010872680693864822
2023-01-24 04:10:58.826019: step: 216/469, loss: 0.0020133310463279486
2023-01-24 04:10:59.512200: step: 218/469, loss: 0.1598788946866989
2023-01-24 04:11:00.078862: step: 220/469, loss: 0.0006900245207361877
2023-01-24 04:11:00.717148: step: 222/469, loss: 0.020223049446940422
2023-01-24 04:11:01.399848: step: 224/469, loss: 0.03611772507429123
2023-01-24 04:11:02.062448: step: 226/469, loss: 0.0020694381091743708
2023-01-24 04:11:02.665278: step: 228/469, loss: 0.019679654389619827
2023-01-24 04:11:03.279237: step: 230/469, loss: 1.0678807497024536
2023-01-24 04:11:03.883021: step: 232/469, loss: 0.017862658947706223
2023-01-24 04:11:04.514983: step: 234/469, loss: 0.007371433079242706
2023-01-24 04:11:05.067394: step: 236/469, loss: 0.0022500392515212297
2023-01-24 04:11:05.707315: step: 238/469, loss: 0.031100109219551086
2023-01-24 04:11:06.293051: step: 240/469, loss: 0.0032845602836459875
2023-01-24 04:11:07.001753: step: 242/469, loss: 0.2349967211484909
2023-01-24 04:11:07.649535: step: 244/469, loss: 0.006704397965222597
2023-01-24 04:11:08.244500: step: 246/469, loss: 0.002046919660642743
2023-01-24 04:11:08.850343: step: 248/469, loss: 0.048905618488788605
2023-01-24 04:11:09.467182: step: 250/469, loss: 0.02675948478281498
2023-01-24 04:11:10.119662: step: 252/469, loss: 0.013306604698300362
2023-01-24 04:11:10.765062: step: 254/469, loss: 0.04287441447377205
2023-01-24 04:11:11.369275: step: 256/469, loss: 0.0009932884713634849
2023-01-24 04:11:11.993609: step: 258/469, loss: 0.0010622227564454079
2023-01-24 04:11:12.638833: step: 260/469, loss: 0.006308846175670624
2023-01-24 04:11:13.309068: step: 262/469, loss: 0.039348725229501724
2023-01-24 04:11:13.953741: step: 264/469, loss: 0.00859423354268074
2023-01-24 04:11:14.608330: step: 266/469, loss: 0.0015562705229967833
2023-01-24 04:11:15.221557: step: 268/469, loss: 0.03566424921154976
2023-01-24 04:11:15.919740: step: 270/469, loss: 0.6679173707962036
2023-01-24 04:11:16.546427: step: 272/469, loss: 0.01110112201422453
2023-01-24 04:11:17.128105: step: 274/469, loss: 0.026794644072651863
2023-01-24 04:11:17.741669: step: 276/469, loss: 0.019411958754062653
2023-01-24 04:11:18.347265: step: 278/469, loss: 0.030573224648833275
2023-01-24 04:11:19.022061: step: 280/469, loss: 0.00015785006689839065
2023-01-24 04:11:19.643419: step: 282/469, loss: 0.02100604772567749
2023-01-24 04:11:20.298648: step: 284/469, loss: 0.004133254289627075
2023-01-24 04:11:20.948702: step: 286/469, loss: 0.05037087947130203
2023-01-24 04:11:21.539551: step: 288/469, loss: 0.029138660058379173
2023-01-24 04:11:22.176319: step: 290/469, loss: 0.02972107194364071
2023-01-24 04:11:22.770647: step: 292/469, loss: 0.1522054374217987
2023-01-24 04:11:23.339392: step: 294/469, loss: 0.5802236199378967
2023-01-24 04:11:23.948474: step: 296/469, loss: 0.003168710507452488
2023-01-24 04:11:24.558625: step: 298/469, loss: 0.003728737821802497
2023-01-24 04:11:25.111848: step: 300/469, loss: 0.135112926363945
2023-01-24 04:11:25.821993: step: 302/469, loss: 0.0040602353401482105
2023-01-24 04:11:26.499098: step: 304/469, loss: 0.014956161379814148
2023-01-24 04:11:27.117718: step: 306/469, loss: 0.06096882000565529
2023-01-24 04:11:27.650594: step: 308/469, loss: 0.004549896810203791
2023-01-24 04:11:28.242632: step: 310/469, loss: 0.012716942466795444
2023-01-24 04:11:28.850109: step: 312/469, loss: 0.01619807258248329
2023-01-24 04:11:29.447581: step: 314/469, loss: 0.011792403645813465
2023-01-24 04:11:30.004040: step: 316/469, loss: 0.012099232524633408
2023-01-24 04:11:30.610318: step: 318/469, loss: 0.1219257116317749
2023-01-24 04:11:31.255162: step: 320/469, loss: 0.0035128050949424505
2023-01-24 04:11:31.900785: step: 322/469, loss: 0.05700281262397766
2023-01-24 04:11:32.474231: step: 324/469, loss: 0.033953264355659485
2023-01-24 04:11:33.096266: step: 326/469, loss: 0.7913249135017395
2023-01-24 04:11:33.744510: step: 328/469, loss: 0.0027427980676293373
2023-01-24 04:11:34.441838: step: 330/469, loss: 0.014402883127331734
2023-01-24 04:11:35.039520: step: 332/469, loss: 0.0012608341639861465
2023-01-24 04:11:35.652351: step: 334/469, loss: 0.005000323057174683
2023-01-24 04:11:36.290035: step: 336/469, loss: 0.042454447597265244
2023-01-24 04:11:36.847369: step: 338/469, loss: 0.021152367815375328
2023-01-24 04:11:37.453752: step: 340/469, loss: 0.0006268061115406454
2023-01-24 04:11:37.989489: step: 342/469, loss: 0.01574760116636753
2023-01-24 04:11:38.603408: step: 344/469, loss: 0.7566384673118591
2023-01-24 04:11:39.361462: step: 346/469, loss: 0.06349111348390579
2023-01-24 04:11:39.907045: step: 348/469, loss: 0.0023796861059963703
2023-01-24 04:11:40.527049: step: 350/469, loss: 0.08010248094797134
2023-01-24 04:11:41.167298: step: 352/469, loss: 0.05025271326303482
2023-01-24 04:11:41.810473: step: 354/469, loss: 0.005450638476759195
2023-01-24 04:11:42.400066: step: 356/469, loss: 0.0031277972739189863
2023-01-24 04:11:43.087892: step: 358/469, loss: 0.01332804374396801
2023-01-24 04:11:43.796161: step: 360/469, loss: 0.0004827117663808167
2023-01-24 04:11:44.451637: step: 362/469, loss: 0.08021761476993561
2023-01-24 04:11:45.110189: step: 364/469, loss: 0.00970520917326212
2023-01-24 04:11:45.818954: step: 366/469, loss: 0.025385988876223564
2023-01-24 04:11:46.429457: step: 368/469, loss: 0.0004828694509342313
2023-01-24 04:11:47.003365: step: 370/469, loss: 0.021221010014414787
2023-01-24 04:11:47.638577: step: 372/469, loss: 0.014321565628051758
2023-01-24 04:11:48.302046: step: 374/469, loss: 0.010588493198156357
2023-01-24 04:11:48.922373: step: 376/469, loss: 0.04768862575292587
2023-01-24 04:11:49.466551: step: 378/469, loss: 0.0011960220290347934
2023-01-24 04:11:50.156786: step: 380/469, loss: 0.019489774480462074
2023-01-24 04:11:50.808144: step: 382/469, loss: 0.004130158107727766
2023-01-24 04:11:51.450192: step: 384/469, loss: 0.043059807270765305
2023-01-24 04:11:52.233930: step: 386/469, loss: 0.0044572739861905575
2023-01-24 04:11:52.851051: step: 388/469, loss: 0.01584039442241192
2023-01-24 04:11:53.488585: step: 390/469, loss: 0.0034310214687138796
2023-01-24 04:11:54.103452: step: 392/469, loss: 0.04041663184762001
2023-01-24 04:11:54.705315: step: 394/469, loss: 0.025866210460662842
2023-01-24 04:11:55.365900: step: 396/469, loss: 0.025049636140465736
2023-01-24 04:11:55.988737: step: 398/469, loss: 0.019481627270579338
2023-01-24 04:11:56.555953: step: 400/469, loss: 0.005536247044801712
2023-01-24 04:11:57.185520: step: 402/469, loss: 0.04828262701630592
2023-01-24 04:11:57.837883: step: 404/469, loss: 0.019890954717993736
2023-01-24 04:11:58.489203: step: 406/469, loss: 0.017756346613168716
2023-01-24 04:11:59.093780: step: 408/469, loss: 0.0208131093531847
2023-01-24 04:11:59.697944: step: 410/469, loss: 0.010058622807264328
2023-01-24 04:12:00.366894: step: 412/469, loss: 2.3890333977760747e-05
2023-01-24 04:12:01.011658: step: 414/469, loss: 0.027549250051379204
2023-01-24 04:12:01.705215: step: 416/469, loss: 0.01741381548345089
2023-01-24 04:12:02.303443: step: 418/469, loss: 0.03779299184679985
2023-01-24 04:12:02.948044: step: 420/469, loss: 0.02548857033252716
2023-01-24 04:12:03.646780: step: 422/469, loss: 0.04002354294061661
2023-01-24 04:12:04.292004: step: 424/469, loss: 0.052142735570669174
2023-01-24 04:12:04.865071: step: 426/469, loss: 0.01683874800801277
2023-01-24 04:12:05.503247: step: 428/469, loss: 0.015530227683484554
2023-01-24 04:12:06.099226: step: 430/469, loss: 0.004677011165767908
2023-01-24 04:12:06.714848: step: 432/469, loss: 0.024919092655181885
2023-01-24 04:12:07.324523: step: 434/469, loss: 0.028229011222720146
2023-01-24 04:12:07.943887: step: 436/469, loss: 0.07605470716953278
2023-01-24 04:12:08.593109: step: 438/469, loss: 0.053130775690078735
2023-01-24 04:12:09.235433: step: 440/469, loss: 1.0160630941390991
2023-01-24 04:12:09.868181: step: 442/469, loss: 0.029920082539319992
2023-01-24 04:12:10.507006: step: 444/469, loss: 0.014652331359684467
2023-01-24 04:12:11.167192: step: 446/469, loss: 0.0997944325208664
2023-01-24 04:12:11.820971: step: 448/469, loss: 0.0088579673320055
2023-01-24 04:12:12.541433: step: 450/469, loss: 0.05553983896970749
2023-01-24 04:12:13.237240: step: 452/469, loss: 0.05492016673088074
2023-01-24 04:12:13.964421: step: 454/469, loss: 0.05790337920188904
2023-01-24 04:12:14.608235: step: 456/469, loss: 0.010022619739174843
2023-01-24 04:12:15.261518: step: 458/469, loss: 0.0025393322575837374
2023-01-24 04:12:15.856979: step: 460/469, loss: 0.07157866656780243
2023-01-24 04:12:16.523221: step: 462/469, loss: 0.0258535984903574
2023-01-24 04:12:17.182616: step: 464/469, loss: 0.03282848000526428
2023-01-24 04:12:17.807886: step: 466/469, loss: 0.0360444150865078
2023-01-24 04:12:18.500464: step: 468/469, loss: 0.06956269592046738
2023-01-24 04:12:19.149602: step: 470/469, loss: 0.03313492611050606
2023-01-24 04:12:19.774923: step: 472/469, loss: 0.024751227349042892
2023-01-24 04:12:20.394092: step: 474/469, loss: 0.011004014872014523
2023-01-24 04:12:21.053605: step: 476/469, loss: 0.05356544628739357
2023-01-24 04:12:21.691764: step: 478/469, loss: 0.05753597989678383
2023-01-24 04:12:22.331312: step: 480/469, loss: 0.2702380120754242
2023-01-24 04:12:22.958056: step: 482/469, loss: 3.117340326309204
2023-01-24 04:12:23.541183: step: 484/469, loss: 0.018965883180499077
2023-01-24 04:12:24.163561: step: 486/469, loss: 0.14978134632110596
2023-01-24 04:12:24.800643: step: 488/469, loss: 0.0010173512855544686
2023-01-24 04:12:25.428894: step: 490/469, loss: 0.010677210055291653
2023-01-24 04:12:26.075243: step: 492/469, loss: 0.1280421018600464
2023-01-24 04:12:26.658161: step: 494/469, loss: 0.07581206411123276
2023-01-24 04:12:27.266783: step: 496/469, loss: 0.06245987489819527
2023-01-24 04:12:27.930568: step: 498/469, loss: 0.009609738364815712
2023-01-24 04:12:28.576023: step: 500/469, loss: 0.005049293395131826
2023-01-24 04:12:29.189517: step: 502/469, loss: 0.009780517779290676
2023-01-24 04:12:29.828071: step: 504/469, loss: 0.06654675304889679
2023-01-24 04:12:30.583054: step: 506/469, loss: 0.01880868338048458
2023-01-24 04:12:31.151717: step: 508/469, loss: 0.017586544156074524
2023-01-24 04:12:31.727276: step: 510/469, loss: 0.014270694926381111
2023-01-24 04:12:32.319797: step: 512/469, loss: 0.05923789367079735
2023-01-24 04:12:32.870486: step: 514/469, loss: 0.002917267382144928
2023-01-24 04:12:33.406358: step: 516/469, loss: 0.0029033832252025604
2023-01-24 04:12:34.030410: step: 518/469, loss: 0.03822728246450424
2023-01-24 04:12:34.699929: step: 520/469, loss: 6.42087984085083
2023-01-24 04:12:35.329275: step: 522/469, loss: 0.015480708330869675
2023-01-24 04:12:35.938502: step: 524/469, loss: 0.04548148065805435
2023-01-24 04:12:36.558076: step: 526/469, loss: 0.007104057818651199
2023-01-24 04:12:37.250949: step: 528/469, loss: 0.05192127078771591
2023-01-24 04:12:37.921497: step: 530/469, loss: 0.015678923577070236
2023-01-24 04:12:38.553690: step: 532/469, loss: 0.02728353999555111
2023-01-24 04:12:39.160971: step: 534/469, loss: 0.07811377942562103
2023-01-24 04:12:39.744287: step: 536/469, loss: 0.006859962362796068
2023-01-24 04:12:40.352984: step: 538/469, loss: 0.010269735008478165
2023-01-24 04:12:40.912778: step: 540/469, loss: 0.026836326345801353
2023-01-24 04:12:41.505110: step: 542/469, loss: 0.021811068058013916
2023-01-24 04:12:42.113226: step: 544/469, loss: 0.06388245522975922
2023-01-24 04:12:42.681805: step: 546/469, loss: 0.035730913281440735
2023-01-24 04:12:43.397023: step: 548/469, loss: 0.0647575780749321
2023-01-24 04:12:44.007098: step: 550/469, loss: 0.047171153128147125
2023-01-24 04:12:44.629338: step: 552/469, loss: 0.0014567658072337508
2023-01-24 04:12:45.214798: step: 554/469, loss: 0.06879657506942749
2023-01-24 04:12:45.859248: step: 556/469, loss: 0.08878390491008759
2023-01-24 04:12:46.460833: step: 558/469, loss: 0.02075077034533024
2023-01-24 04:12:47.052838: step: 560/469, loss: 0.0844666063785553
2023-01-24 04:12:47.654017: step: 562/469, loss: 0.006936375983059406
2023-01-24 04:12:48.346146: step: 564/469, loss: 0.03022335097193718
2023-01-24 04:12:48.982456: step: 566/469, loss: 0.018008532002568245
2023-01-24 04:12:49.634387: step: 568/469, loss: 0.057579126209020615
2023-01-24 04:12:50.244012: step: 570/469, loss: 0.0805489718914032
2023-01-24 04:12:50.855481: step: 572/469, loss: 0.07772126793861389
2023-01-24 04:12:51.493302: step: 574/469, loss: 0.031969670206308365
2023-01-24 04:12:52.106834: step: 576/469, loss: 0.009727970696985722
2023-01-24 04:12:52.722573: step: 578/469, loss: 0.09800968319177628
2023-01-24 04:12:53.315347: step: 580/469, loss: 0.014431802555918694
2023-01-24 04:12:53.925030: step: 582/469, loss: 0.011403510347008705
2023-01-24 04:12:54.537976: step: 584/469, loss: 0.02918725647032261
2023-01-24 04:12:55.174014: step: 586/469, loss: 0.009596250019967556
2023-01-24 04:12:55.771861: step: 588/469, loss: 0.020912984386086464
2023-01-24 04:12:56.414038: step: 590/469, loss: 0.037036627531051636
2023-01-24 04:12:57.092781: step: 592/469, loss: 0.022930650040507317
2023-01-24 04:12:57.629795: step: 594/469, loss: 0.020664162933826447
2023-01-24 04:12:58.213551: step: 596/469, loss: 0.04543563351035118
2023-01-24 04:12:58.888394: step: 598/469, loss: 0.0345572903752327
2023-01-24 04:12:59.467258: step: 600/469, loss: 0.0032024672254920006
2023-01-24 04:13:00.099869: step: 602/469, loss: 0.0560622401535511
2023-01-24 04:13:00.724990: step: 604/469, loss: 0.08288592100143433
2023-01-24 04:13:01.363730: step: 606/469, loss: 0.05112718790769577
2023-01-24 04:13:01.972241: step: 608/469, loss: 0.011430895887315273
2023-01-24 04:13:02.498878: step: 610/469, loss: 0.004481939598917961
2023-01-24 04:13:03.106713: step: 612/469, loss: 0.010696549899876118
2023-01-24 04:13:03.729737: step: 614/469, loss: 0.04353227838873863
2023-01-24 04:13:04.284010: step: 616/469, loss: 0.00513804005458951
2023-01-24 04:13:04.880823: step: 618/469, loss: 0.04890283942222595
2023-01-24 04:13:05.509819: step: 620/469, loss: 0.007950910367071629
2023-01-24 04:13:06.105502: step: 622/469, loss: 0.003297393675893545
2023-01-24 04:13:06.804303: step: 624/469, loss: 0.0445278026163578
2023-01-24 04:13:07.503254: step: 626/469, loss: 0.3941957950592041
2023-01-24 04:13:08.164510: step: 628/469, loss: 0.003935977350920439
2023-01-24 04:13:08.720751: step: 630/469, loss: 0.13316921889781952
2023-01-24 04:13:09.374720: step: 632/469, loss: 0.037868812680244446
2023-01-24 04:13:09.979391: step: 634/469, loss: 0.011567690409719944
2023-01-24 04:13:10.562564: step: 636/469, loss: 0.0038243380840867758
2023-01-24 04:13:11.133235: step: 638/469, loss: 0.011350546032190323
2023-01-24 04:13:11.708211: step: 640/469, loss: 0.053472843021154404
2023-01-24 04:13:12.277428: step: 642/469, loss: 0.04042840003967285
2023-01-24 04:13:13.044580: step: 644/469, loss: 0.025590164586901665
2023-01-24 04:13:13.652134: step: 646/469, loss: 0.4160204529762268
2023-01-24 04:13:14.236431: step: 648/469, loss: 0.016708774492144585
2023-01-24 04:13:14.858187: step: 650/469, loss: 0.0036376859061419964
2023-01-24 04:13:15.579202: step: 652/469, loss: 0.24705639481544495
2023-01-24 04:13:16.166128: step: 654/469, loss: 0.026834789663553238
2023-01-24 04:13:16.796099: step: 656/469, loss: 0.013414159417152405
2023-01-24 04:13:17.448988: step: 658/469, loss: 0.010435991920530796
2023-01-24 04:13:18.076675: step: 660/469, loss: 0.01883425936102867
2023-01-24 04:13:18.716125: step: 662/469, loss: 0.012636534869670868
2023-01-24 04:13:19.426765: step: 664/469, loss: 0.019053366035223007
2023-01-24 04:13:20.013542: step: 666/469, loss: 0.002981501864269376
2023-01-24 04:13:20.617102: step: 668/469, loss: 0.01738005504012108
2023-01-24 04:13:21.238456: step: 670/469, loss: 0.07976853847503662
2023-01-24 04:13:21.869825: step: 672/469, loss: 0.014995337463915348
2023-01-24 04:13:22.518666: step: 674/469, loss: 0.013884548097848892
2023-01-24 04:13:23.091565: step: 676/469, loss: 0.010399105958640575
2023-01-24 04:13:23.675957: step: 678/469, loss: 0.012271115556359291
2023-01-24 04:13:24.287152: step: 680/469, loss: 0.0009961036266759038
2023-01-24 04:13:24.927799: step: 682/469, loss: 0.023565329611301422
2023-01-24 04:13:25.556831: step: 684/469, loss: 0.035644806921482086
2023-01-24 04:13:26.210045: step: 686/469, loss: 1.081357479095459
2023-01-24 04:13:26.815077: step: 688/469, loss: 0.08901568502187729
2023-01-24 04:13:27.456777: step: 690/469, loss: 0.15900513529777527
2023-01-24 04:13:28.116635: step: 692/469, loss: 0.08483231067657471
2023-01-24 04:13:28.824133: step: 694/469, loss: 0.04530998691916466
2023-01-24 04:13:29.454269: step: 696/469, loss: 0.026291202753782272
2023-01-24 04:13:30.083895: step: 698/469, loss: 0.02551412396132946
2023-01-24 04:13:30.716981: step: 700/469, loss: 0.02575918473303318
2023-01-24 04:13:31.375072: step: 702/469, loss: 0.0030414615757763386
2023-01-24 04:13:31.990203: step: 704/469, loss: 0.06050509586930275
2023-01-24 04:13:32.566936: step: 706/469, loss: 0.007125751581043005
2023-01-24 04:13:33.193452: step: 708/469, loss: 0.053902920335531235
2023-01-24 04:13:33.797380: step: 710/469, loss: 0.009892820380628109
2023-01-24 04:13:34.362054: step: 712/469, loss: 0.026334915310144424
2023-01-24 04:13:34.978044: step: 714/469, loss: 0.007749361451715231
2023-01-24 04:13:35.643810: step: 716/469, loss: 0.1088370531797409
2023-01-24 04:13:36.269521: step: 718/469, loss: 0.29399850964546204
2023-01-24 04:13:36.933339: step: 720/469, loss: 0.004869928117841482
2023-01-24 04:13:37.621421: step: 722/469, loss: 0.000951407419051975
2023-01-24 04:13:38.308696: step: 724/469, loss: 0.05764957517385483
2023-01-24 04:13:38.937940: step: 726/469, loss: 0.035510048270225525
2023-01-24 04:13:39.533542: step: 728/469, loss: 0.022459859028458595
2023-01-24 04:13:40.123234: step: 730/469, loss: 0.1560434103012085
2023-01-24 04:13:40.741219: step: 732/469, loss: 0.020503107458353043
2023-01-24 04:13:41.364973: step: 734/469, loss: 0.020482506603002548
2023-01-24 04:13:42.007845: step: 736/469, loss: 0.0142503771930933
2023-01-24 04:13:42.623542: step: 738/469, loss: 0.8064932823181152
2023-01-24 04:13:43.169029: step: 740/469, loss: 0.026013199239969254
2023-01-24 04:13:43.704703: step: 742/469, loss: 0.1833120733499527
2023-01-24 04:13:44.328738: step: 744/469, loss: 0.014799002557992935
2023-01-24 04:13:44.927838: step: 746/469, loss: 0.011398497968912125
2023-01-24 04:13:45.528004: step: 748/469, loss: 0.053761355578899384
2023-01-24 04:13:46.152543: step: 750/469, loss: 0.03485002741217613
2023-01-24 04:13:46.865578: step: 752/469, loss: 0.014673682861030102
2023-01-24 04:13:47.418680: step: 754/469, loss: 0.10965120792388916
2023-01-24 04:13:47.989345: step: 756/469, loss: 0.05517612770199776
2023-01-24 04:13:48.614699: step: 758/469, loss: 0.09887915104627609
2023-01-24 04:13:49.295040: step: 760/469, loss: 0.01138286292552948
2023-01-24 04:13:49.898555: step: 762/469, loss: 0.03641868755221367
2023-01-24 04:13:50.553175: step: 764/469, loss: 0.003509464440867305
2023-01-24 04:13:51.189206: step: 766/469, loss: 0.014076833613216877
2023-01-24 04:13:51.816239: step: 768/469, loss: 0.00853697769343853
2023-01-24 04:13:52.478832: step: 770/469, loss: 0.03722076117992401
2023-01-24 04:13:53.155841: step: 772/469, loss: 0.002302593318745494
2023-01-24 04:13:53.719087: step: 774/469, loss: 0.029911432415246964
2023-01-24 04:13:54.330104: step: 776/469, loss: 0.06319554150104523
2023-01-24 04:13:54.950120: step: 778/469, loss: 0.03323550522327423
2023-01-24 04:13:55.637410: step: 780/469, loss: 0.006586946547031403
2023-01-24 04:13:56.241832: step: 782/469, loss: 0.013489141128957272
2023-01-24 04:13:56.838290: step: 784/469, loss: 0.030085476115345955
2023-01-24 04:13:57.470444: step: 786/469, loss: 0.04462684690952301
2023-01-24 04:13:58.133386: step: 788/469, loss: 0.02085179276764393
2023-01-24 04:13:58.781090: step: 790/469, loss: 0.010906665585935116
2023-01-24 04:13:59.399084: step: 792/469, loss: 0.02653900533914566
2023-01-24 04:14:00.007843: step: 794/469, loss: 0.1314384639263153
2023-01-24 04:14:00.579273: step: 796/469, loss: 0.15087509155273438
2023-01-24 04:14:01.188643: step: 798/469, loss: 0.000667657470330596
2023-01-24 04:14:01.903610: step: 800/469, loss: 0.5286304354667664
2023-01-24 04:14:02.512566: step: 802/469, loss: 0.01442254614084959
2023-01-24 04:14:03.246285: step: 804/469, loss: 0.006482763681560755
2023-01-24 04:14:03.853157: step: 806/469, loss: 0.007659719791263342
2023-01-24 04:14:04.424205: step: 808/469, loss: 0.05417191982269287
2023-01-24 04:14:05.080797: step: 810/469, loss: 0.06836564838886261
2023-01-24 04:14:05.674450: step: 812/469, loss: 0.041151028126478195
2023-01-24 04:14:06.285506: step: 814/469, loss: 0.03098500706255436
2023-01-24 04:14:06.883694: step: 816/469, loss: 0.002014571102336049
2023-01-24 04:14:07.541573: step: 818/469, loss: 0.4861396551132202
2023-01-24 04:14:08.210167: step: 820/469, loss: 0.07447970658540726
2023-01-24 04:14:08.785216: step: 822/469, loss: 0.011415109969675541
2023-01-24 04:14:09.305631: step: 824/469, loss: 0.0076906392350792885
2023-01-24 04:14:09.909735: step: 826/469, loss: 0.004792527295649052
2023-01-24 04:14:10.591363: step: 828/469, loss: 0.014225320890545845
2023-01-24 04:14:11.155793: step: 830/469, loss: 0.043766554445028305
2023-01-24 04:14:11.796688: step: 832/469, loss: 0.06967785209417343
2023-01-24 04:14:12.450764: step: 834/469, loss: 0.05522594973444939
2023-01-24 04:14:13.168289: step: 836/469, loss: 0.04994479939341545
2023-01-24 04:14:13.865927: step: 838/469, loss: 0.026540275663137436
2023-01-24 04:14:14.603004: step: 840/469, loss: 0.10919288545846939
2023-01-24 04:14:15.201393: step: 842/469, loss: 0.1099095568060875
2023-01-24 04:14:15.860815: step: 844/469, loss: 0.05464242398738861
2023-01-24 04:14:16.471899: step: 846/469, loss: 0.041132453829050064
2023-01-24 04:14:17.184944: step: 848/469, loss: 0.05038027837872505
2023-01-24 04:14:17.841226: step: 850/469, loss: 0.0027275551110506058
2023-01-24 04:14:18.490346: step: 852/469, loss: 0.018887832760810852
2023-01-24 04:14:19.120600: step: 854/469, loss: 0.0044850511476397514
2023-01-24 04:14:19.729417: step: 856/469, loss: 1.9406450986862183
2023-01-24 04:14:20.336186: step: 858/469, loss: 0.08518712967634201
2023-01-24 04:14:20.979250: step: 860/469, loss: 0.04969101771712303
2023-01-24 04:14:21.564221: step: 862/469, loss: 0.02239733561873436
2023-01-24 04:14:22.131369: step: 864/469, loss: 0.03769238665699959
2023-01-24 04:14:22.752505: step: 866/469, loss: 0.053547605872154236
2023-01-24 04:14:23.476709: step: 868/469, loss: 0.008203242905437946
2023-01-24 04:14:24.065427: step: 870/469, loss: 0.05329376831650734
2023-01-24 04:14:24.738430: step: 872/469, loss: 0.17371654510498047
2023-01-24 04:14:25.364418: step: 874/469, loss: 0.017412085086107254
2023-01-24 04:14:26.008543: step: 876/469, loss: 0.02849368192255497
2023-01-24 04:14:26.617597: step: 878/469, loss: 0.006044892594218254
2023-01-24 04:14:27.341021: step: 880/469, loss: 0.010606056079268456
2023-01-24 04:14:28.016629: step: 882/469, loss: 0.022346163168549538
2023-01-24 04:14:28.657766: step: 884/469, loss: 0.02221456728875637
2023-01-24 04:14:29.302264: step: 886/469, loss: 0.01554245874285698
2023-01-24 04:14:29.902891: step: 888/469, loss: 0.038454942405223846
2023-01-24 04:14:30.568849: step: 890/469, loss: 0.15954706072807312
2023-01-24 04:14:31.175115: step: 892/469, loss: 0.013759526424109936
2023-01-24 04:14:31.785096: step: 894/469, loss: 0.02033253014087677
2023-01-24 04:14:32.362077: step: 896/469, loss: 0.00540660135447979
2023-01-24 04:14:32.957477: step: 898/469, loss: 0.010812917724251747
2023-01-24 04:14:33.584775: step: 900/469, loss: 0.16664300858974457
2023-01-24 04:14:34.213061: step: 902/469, loss: 0.03643622249364853
2023-01-24 04:14:34.861425: step: 904/469, loss: 0.7900838851928711
2023-01-24 04:14:35.532839: step: 906/469, loss: 0.09270291775465012
2023-01-24 04:14:36.157610: step: 908/469, loss: 0.027008721604943275
2023-01-24 04:14:36.808456: step: 910/469, loss: 0.11897628754377365
2023-01-24 04:14:37.490048: step: 912/469, loss: 0.02917761169373989
2023-01-24 04:14:38.169472: step: 914/469, loss: 0.003338885260745883
2023-01-24 04:14:38.788318: step: 916/469, loss: 0.03401242569088936
2023-01-24 04:14:39.409082: step: 918/469, loss: 0.1241544559597969
2023-01-24 04:14:39.966910: step: 920/469, loss: 0.09011563658714294
2023-01-24 04:14:40.630238: step: 922/469, loss: 0.014786790125072002
2023-01-24 04:14:41.264997: step: 924/469, loss: 0.19662529230117798
2023-01-24 04:14:41.862296: step: 926/469, loss: 0.028263317421078682
2023-01-24 04:14:42.492632: step: 928/469, loss: 0.0006891288794577122
2023-01-24 04:14:43.176298: step: 930/469, loss: 0.021288258954882622
2023-01-24 04:14:43.809550: step: 932/469, loss: 0.02567538060247898
2023-01-24 04:14:44.505410: step: 934/469, loss: 0.031597234308719635
2023-01-24 04:14:45.162019: step: 936/469, loss: 0.04455246776342392
2023-01-24 04:14:45.766715: step: 938/469, loss: 0.029010459780693054
==================================================
Loss: 0.094
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32785641502746765, 'r': 0.3191467569432465, 'f1': 0.3234429632867133}, 'combined': 0.2383263940007361, 'epoch': 26}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33366586034193413, 'r': 0.2771899370452664, 'f1': 0.30281719259417905}, 'combined': 0.16517301414227947, 'epoch': 26}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3409605625118574, 'r': 0.3247859627722057, 'f1': 0.332676778194271}, 'combined': 0.24513025761683124, 'epoch': 26}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.330975685978962, 'r': 0.27525791267600774, 'f1': 0.3005563422126638}, 'combined': 0.16393982302508933, 'epoch': 26}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3212976421188631, 'r': 0.31459123972169517, 'f1': 0.31790907638223076}, 'combined': 0.23424879312374897, 'epoch': 26}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33278798542902527, 'r': 0.27524276196508585, 'f1': 0.3012922772437044}, 'combined': 0.16434124213292967, 'epoch': 26}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.33854166666666663, 'r': 0.3095238095238095, 'f1': 0.3233830845771144}, 'combined': 0.21558872305140958, 'epoch': 26}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.25, 'r': 0.21739130434782608, 'f1': 0.23255813953488372}, 'combined': 0.11627906976744186, 'epoch': 26}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45454545454545453, 'r': 0.1724137931034483, 'f1': 0.25000000000000006}, 'combined': 0.16666666666666669, 'epoch': 26}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 04:17:31.497013: step: 2/469, loss: 0.010263964533805847
2023-01-24 04:17:32.076978: step: 4/469, loss: 0.011231492273509502
2023-01-24 04:17:32.739495: step: 6/469, loss: 0.015762705355882645
2023-01-24 04:17:33.392125: step: 8/469, loss: 0.0012724900152534246
2023-01-24 04:17:34.003963: step: 10/469, loss: 0.053235072642564774
2023-01-24 04:17:34.716282: step: 12/469, loss: 0.010204012505710125
2023-01-24 04:17:35.313695: step: 14/469, loss: 0.030783262103796005
2023-01-24 04:17:35.965991: step: 16/469, loss: 0.005242544692009687
2023-01-24 04:17:36.590783: step: 18/469, loss: 0.08665913343429565
2023-01-24 04:17:37.248012: step: 20/469, loss: 0.011185991577804089
2023-01-24 04:17:37.853564: step: 22/469, loss: 0.009902694262564182
2023-01-24 04:17:38.396973: step: 24/469, loss: 0.017803888767957687
2023-01-24 04:17:39.051137: step: 26/469, loss: 0.003923527430742979
2023-01-24 04:17:39.668991: step: 28/469, loss: 0.029844868928194046
2023-01-24 04:17:40.290756: step: 30/469, loss: 0.03673786669969559
2023-01-24 04:17:40.869910: step: 32/469, loss: 0.01843520998954773
2023-01-24 04:17:41.501973: step: 34/469, loss: 0.006193936336785555
2023-01-24 04:17:42.190925: step: 36/469, loss: 0.014202727936208248
2023-01-24 04:17:42.891723: step: 38/469, loss: 0.05356700345873833
2023-01-24 04:17:43.529054: step: 40/469, loss: 0.008297438733279705
2023-01-24 04:17:44.174561: step: 42/469, loss: 0.0147783812135458
2023-01-24 04:17:44.838545: step: 44/469, loss: 0.010029271245002747
2023-01-24 04:17:45.448006: step: 46/469, loss: 0.011169832199811935
2023-01-24 04:17:46.100749: step: 48/469, loss: 0.041271597146987915
2023-01-24 04:17:46.771334: step: 50/469, loss: 0.0684984028339386
2023-01-24 04:17:47.370135: step: 52/469, loss: 0.013210831210017204
2023-01-24 04:17:48.001475: step: 54/469, loss: 0.026933982968330383
2023-01-24 04:17:48.624699: step: 56/469, loss: 0.001984068425372243
2023-01-24 04:17:49.260523: step: 58/469, loss: 0.026761960238218307
2023-01-24 04:17:49.908293: step: 60/469, loss: 0.12014544755220413
2023-01-24 04:17:50.482254: step: 62/469, loss: 0.02620898000895977
2023-01-24 04:17:50.995820: step: 64/469, loss: 0.0016914040315896273
2023-01-24 04:17:51.633332: step: 66/469, loss: 0.04991891607642174
2023-01-24 04:17:52.349737: step: 68/469, loss: 0.025870252400636673
2023-01-24 04:17:52.896436: step: 70/469, loss: 0.02388407662510872
2023-01-24 04:17:53.677984: step: 72/469, loss: 0.001007211278192699
2023-01-24 04:17:54.275821: step: 74/469, loss: 0.15625114738941193
2023-01-24 04:17:54.830201: step: 76/469, loss: 0.001346201985143125
2023-01-24 04:17:55.469740: step: 78/469, loss: 0.05820954218506813
2023-01-24 04:17:56.010281: step: 80/469, loss: 0.01771903596818447
2023-01-24 04:17:56.569582: step: 82/469, loss: 0.02378823608160019
2023-01-24 04:17:57.153346: step: 84/469, loss: 0.00656943628564477
2023-01-24 04:17:57.713918: step: 86/469, loss: 0.005551417823880911
2023-01-24 04:17:58.363552: step: 88/469, loss: 0.03339490294456482
2023-01-24 04:17:59.036978: step: 90/469, loss: 0.08753277361392975
2023-01-24 04:17:59.622500: step: 92/469, loss: 0.009791675955057144
2023-01-24 04:18:00.241192: step: 94/469, loss: 0.48874059319496155
2023-01-24 04:18:00.856079: step: 96/469, loss: 0.007072238251566887
2023-01-24 04:18:01.461738: step: 98/469, loss: 0.015402862802147865
2023-01-24 04:18:02.181444: step: 100/469, loss: 0.1414964199066162
2023-01-24 04:18:02.852088: step: 102/469, loss: 0.017023388296365738
2023-01-24 04:18:03.461713: step: 104/469, loss: 0.00987032800912857
2023-01-24 04:18:04.063923: step: 106/469, loss: 0.08945617079734802
2023-01-24 04:18:04.602903: step: 108/469, loss: 0.004312312696129084
2023-01-24 04:18:05.212219: step: 110/469, loss: 0.02816644497215748
2023-01-24 04:18:05.784937: step: 112/469, loss: 0.015106548555195332
2023-01-24 04:18:06.418006: step: 114/469, loss: 0.2121334969997406
2023-01-24 04:18:06.993904: step: 116/469, loss: 0.01742878556251526
2023-01-24 04:18:07.620533: step: 118/469, loss: 0.009169898927211761
2023-01-24 04:18:08.222752: step: 120/469, loss: 0.012686403468251228
2023-01-24 04:18:08.906689: step: 122/469, loss: 0.0169672854244709
2023-01-24 04:18:09.516684: step: 124/469, loss: 0.010977535508573055
2023-01-24 04:18:10.137029: step: 126/469, loss: 0.04842076823115349
2023-01-24 04:18:10.743137: step: 128/469, loss: 0.03538428992033005
2023-01-24 04:18:11.441377: step: 130/469, loss: 0.02807338535785675
2023-01-24 04:18:12.100146: step: 132/469, loss: 0.015565113164484501
2023-01-24 04:18:12.790911: step: 134/469, loss: 0.005185325630009174
2023-01-24 04:18:13.341664: step: 136/469, loss: 0.011364608071744442
2023-01-24 04:18:13.957028: step: 138/469, loss: 0.039853207767009735
2023-01-24 04:18:14.574366: step: 140/469, loss: 0.005194418597966433
2023-01-24 04:18:15.152865: step: 142/469, loss: 0.012483472935855389
2023-01-24 04:18:15.806364: step: 144/469, loss: 0.022440873086452484
2023-01-24 04:18:16.421774: step: 146/469, loss: 0.0964784175157547
2023-01-24 04:18:17.105111: step: 148/469, loss: 0.036113470792770386
2023-01-24 04:18:17.660778: step: 150/469, loss: 0.00023906411661300808
2023-01-24 04:18:18.238375: step: 152/469, loss: 0.003979787230491638
2023-01-24 04:18:18.817115: step: 154/469, loss: 0.052820540964603424
2023-01-24 04:18:19.493655: step: 156/469, loss: 0.012995469383895397
2023-01-24 04:18:20.056531: step: 158/469, loss: 0.00227616960182786
2023-01-24 04:18:20.649499: step: 160/469, loss: 0.043756499886512756
2023-01-24 04:18:21.300268: step: 162/469, loss: 0.08687310665845871
2023-01-24 04:18:21.903632: step: 164/469, loss: 0.011782361194491386
2023-01-24 04:18:22.517900: step: 166/469, loss: 0.05526575446128845
2023-01-24 04:18:23.110365: step: 168/469, loss: 0.0008925764705054462
2023-01-24 04:18:23.779840: step: 170/469, loss: 0.18294069170951843
2023-01-24 04:18:24.360954: step: 172/469, loss: 0.03835257142782211
2023-01-24 04:18:24.947661: step: 174/469, loss: 0.16800366342067719
2023-01-24 04:18:25.582537: step: 176/469, loss: 0.03162071853876114
2023-01-24 04:18:26.204340: step: 178/469, loss: 0.027066271752119064
2023-01-24 04:18:26.868117: step: 180/469, loss: 0.13620692491531372
2023-01-24 04:18:27.555808: step: 182/469, loss: 0.010903574526309967
2023-01-24 04:18:28.125291: step: 184/469, loss: 0.049468494951725006
2023-01-24 04:18:28.772427: step: 186/469, loss: 0.004295628517866135
2023-01-24 04:18:29.417569: step: 188/469, loss: 0.005311970598995686
2023-01-24 04:18:30.019238: step: 190/469, loss: 0.0048162611201405525
2023-01-24 04:18:30.604065: step: 192/469, loss: 0.01803344301879406
2023-01-24 04:18:31.180211: step: 194/469, loss: 0.011363444849848747
2023-01-24 04:18:31.770408: step: 196/469, loss: 0.0033321427181363106
2023-01-24 04:18:32.412465: step: 198/469, loss: 0.012740414589643478
2023-01-24 04:18:32.991056: step: 200/469, loss: 0.018664730712771416
2023-01-24 04:18:33.653584: step: 202/469, loss: 0.0025006842333823442
2023-01-24 04:18:34.228274: step: 204/469, loss: 0.00245764316059649
2023-01-24 04:18:34.855013: step: 206/469, loss: 0.2508716583251953
2023-01-24 04:18:35.453149: step: 208/469, loss: 0.022152552381157875
2023-01-24 04:18:36.092176: step: 210/469, loss: 0.027070006355643272
2023-01-24 04:18:36.765291: step: 212/469, loss: 0.1623942106962204
2023-01-24 04:18:37.461998: step: 214/469, loss: 0.32966285943984985
2023-01-24 04:18:38.068865: step: 216/469, loss: 0.005950678139925003
2023-01-24 04:18:38.678717: step: 218/469, loss: 0.003281219396740198
2023-01-24 04:18:39.264366: step: 220/469, loss: 0.019649382680654526
2023-01-24 04:18:39.890671: step: 222/469, loss: 0.040834516286849976
2023-01-24 04:18:40.447198: step: 224/469, loss: 0.025422558188438416
2023-01-24 04:18:41.057186: step: 226/469, loss: 0.00022721791174262762
2023-01-24 04:18:41.595816: step: 228/469, loss: 0.04407082125544548
2023-01-24 04:18:42.165517: step: 230/469, loss: 0.017822694033384323
2023-01-24 04:18:42.780715: step: 232/469, loss: 0.04084165394306183
2023-01-24 04:18:43.430994: step: 234/469, loss: 0.005138130858540535
2023-01-24 04:18:44.050749: step: 236/469, loss: 0.008525789715349674
2023-01-24 04:18:44.688793: step: 238/469, loss: 0.031569741666316986
2023-01-24 04:18:45.332476: step: 240/469, loss: 0.006945348810404539
2023-01-24 04:18:46.002238: step: 242/469, loss: 0.21676471829414368
2023-01-24 04:18:46.643450: step: 244/469, loss: 0.0058443257585167885
2023-01-24 04:18:47.283433: step: 246/469, loss: 0.021715538576245308
2023-01-24 04:18:47.921274: step: 248/469, loss: 0.01268727146089077
2023-01-24 04:18:48.538132: step: 250/469, loss: 0.0061350250616669655
2023-01-24 04:18:49.147181: step: 252/469, loss: 0.039857491850852966
2023-01-24 04:18:49.772976: step: 254/469, loss: 0.009696245193481445
2023-01-24 04:18:50.481820: step: 256/469, loss: 0.0034504346549510956
2023-01-24 04:18:51.112110: step: 258/469, loss: 0.030834296718239784
2023-01-24 04:18:51.692984: step: 260/469, loss: 1.4202287197113037
2023-01-24 04:18:52.434485: step: 262/469, loss: 0.011240133084356785
2023-01-24 04:18:52.980151: step: 264/469, loss: 0.0023286775685846806
2023-01-24 04:18:53.640781: step: 266/469, loss: 0.006101185455918312
2023-01-24 04:18:54.233630: step: 268/469, loss: 0.02342948503792286
2023-01-24 04:18:54.834689: step: 270/469, loss: 0.005187559872865677
2023-01-24 04:18:55.467751: step: 272/469, loss: 0.24962659180164337
2023-01-24 04:18:56.123061: step: 274/469, loss: 1.4215294122695923
2023-01-24 04:18:56.720256: step: 276/469, loss: 0.0015044870087876916
2023-01-24 04:18:57.345245: step: 278/469, loss: 0.040224362164735794
2023-01-24 04:18:57.941984: step: 280/469, loss: 0.0005229779053479433
2023-01-24 04:18:58.494787: step: 282/469, loss: 0.04526732861995697
2023-01-24 04:18:59.169942: step: 284/469, loss: 0.010339884087443352
2023-01-24 04:18:59.760886: step: 286/469, loss: 0.02542593516409397
2023-01-24 04:19:00.362886: step: 288/469, loss: 0.014497010968625546
2023-01-24 04:19:00.950889: step: 290/469, loss: 0.4429609179496765
2023-01-24 04:19:01.540066: step: 292/469, loss: 0.0052616591565310955
2023-01-24 04:19:02.130078: step: 294/469, loss: 0.04630669206380844
2023-01-24 04:19:02.846508: step: 296/469, loss: 0.01808157004415989
2023-01-24 04:19:03.425830: step: 298/469, loss: 0.15663926303386688
2023-01-24 04:19:04.112589: step: 300/469, loss: 0.017160143703222275
2023-01-24 04:19:04.812393: step: 302/469, loss: 0.0031339225824922323
2023-01-24 04:19:05.459586: step: 304/469, loss: 0.005071716848760843
2023-01-24 04:19:06.041389: step: 306/469, loss: 0.0012592441635206342
2023-01-24 04:19:06.672529: step: 308/469, loss: 0.15066708624362946
2023-01-24 04:19:07.321766: step: 310/469, loss: 0.027801720425486565
2023-01-24 04:19:07.953170: step: 312/469, loss: 0.03207564353942871
2023-01-24 04:19:08.565842: step: 314/469, loss: 0.015848476439714432
2023-01-24 04:19:09.164384: step: 316/469, loss: 0.0015576331643387675
2023-01-24 04:19:09.821263: step: 318/469, loss: 0.024646896868944168
2023-01-24 04:19:10.438816: step: 320/469, loss: 0.017506342381238937
2023-01-24 04:19:11.085113: step: 322/469, loss: 0.0037719248794019222
2023-01-24 04:19:11.782255: step: 324/469, loss: 0.43416082859039307
2023-01-24 04:19:12.438637: step: 326/469, loss: 0.04574159160256386
2023-01-24 04:19:13.130073: step: 328/469, loss: 0.013402159325778484
2023-01-24 04:19:13.702201: step: 330/469, loss: 0.009678997099399567
2023-01-24 04:19:14.308848: step: 332/469, loss: 0.01342147309333086
2023-01-24 04:19:14.923880: step: 334/469, loss: 0.03259721025824547
2023-01-24 04:19:15.504502: step: 336/469, loss: 0.01209324225783348
2023-01-24 04:19:16.169347: step: 338/469, loss: 0.0022710200864821672
2023-01-24 04:19:16.746833: step: 340/469, loss: 0.022515149787068367
2023-01-24 04:19:17.338705: step: 342/469, loss: 0.04635896533727646
2023-01-24 04:19:17.990213: step: 344/469, loss: 0.0037869280204176903
2023-01-24 04:19:18.639834: step: 346/469, loss: 0.021152865141630173
2023-01-24 04:19:19.244280: step: 348/469, loss: 0.01859697513282299
2023-01-24 04:19:19.822582: step: 350/469, loss: 0.02358274720609188
2023-01-24 04:19:20.474013: step: 352/469, loss: 0.008010893128812313
2023-01-24 04:19:21.173197: step: 354/469, loss: 0.009056910872459412
2023-01-24 04:19:21.821645: step: 356/469, loss: 0.32193630933761597
2023-01-24 04:19:22.481130: step: 358/469, loss: 0.07568494975566864
2023-01-24 04:19:23.087822: step: 360/469, loss: 0.09271309524774551
2023-01-24 04:19:23.676394: step: 362/469, loss: 0.10162200778722763
2023-01-24 04:19:24.311590: step: 364/469, loss: 0.03486338630318642
2023-01-24 04:19:24.958901: step: 366/469, loss: 0.030468272045254707
2023-01-24 04:19:25.589557: step: 368/469, loss: 0.009875318966805935
2023-01-24 04:19:26.316115: step: 370/469, loss: 0.008483083918690681
2023-01-24 04:19:26.916042: step: 372/469, loss: 0.046357907354831696
2023-01-24 04:19:27.566843: step: 374/469, loss: 0.01245014276355505
2023-01-24 04:19:28.140133: step: 376/469, loss: 0.04683561623096466
2023-01-24 04:19:28.830845: step: 378/469, loss: 0.0032857325859367847
2023-01-24 04:19:29.495103: step: 380/469, loss: 0.4295358657836914
2023-01-24 04:19:30.115501: step: 382/469, loss: 0.03776291757822037
2023-01-24 04:19:30.720136: step: 384/469, loss: 0.0042632948607206345
2023-01-24 04:19:31.510298: step: 386/469, loss: 0.06727524846792221
2023-01-24 04:19:32.187040: step: 388/469, loss: 0.0033810532186180353
2023-01-24 04:19:32.816179: step: 390/469, loss: 0.00856588501483202
2023-01-24 04:19:33.454535: step: 392/469, loss: 0.0437612310051918
2023-01-24 04:19:34.083273: step: 394/469, loss: 0.022761067375540733
2023-01-24 04:19:34.661960: step: 396/469, loss: 0.0060792299918830395
2023-01-24 04:19:35.184665: step: 398/469, loss: 0.008533630520105362
2023-01-24 04:19:35.703986: step: 400/469, loss: 0.002531493781134486
2023-01-24 04:19:36.355834: step: 402/469, loss: 0.01378880999982357
2023-01-24 04:19:37.015103: step: 404/469, loss: 0.012417015619575977
2023-01-24 04:19:37.609188: step: 406/469, loss: 0.007826639339327812
2023-01-24 04:19:38.173076: step: 408/469, loss: 0.05615496262907982
2023-01-24 04:19:38.751081: step: 410/469, loss: 0.015419812873005867
2023-01-24 04:19:39.393376: step: 412/469, loss: 0.01269865408539772
2023-01-24 04:19:40.060033: step: 414/469, loss: 0.006402693688869476
2023-01-24 04:19:40.644670: step: 416/469, loss: 0.007301743142306805
2023-01-24 04:19:41.294981: step: 418/469, loss: 0.08711107075214386
2023-01-24 04:19:41.869479: step: 420/469, loss: 0.3633323013782501
2023-01-24 04:19:42.504139: step: 422/469, loss: 0.03807739168405533
2023-01-24 04:19:43.125376: step: 424/469, loss: 0.04179481044411659
2023-01-24 04:19:43.749318: step: 426/469, loss: 0.10723355412483215
2023-01-24 04:19:44.437230: step: 428/469, loss: 0.3118813931941986
2023-01-24 04:19:45.083918: step: 430/469, loss: 0.021025799214839935
2023-01-24 04:19:45.703880: step: 432/469, loss: 0.017781071364879608
2023-01-24 04:19:46.339927: step: 434/469, loss: 0.0011829964350908995
2023-01-24 04:19:46.915694: step: 436/469, loss: 0.002774057677015662
2023-01-24 04:19:47.547048: step: 438/469, loss: 0.029620174318552017
2023-01-24 04:19:48.222899: step: 440/469, loss: 0.022168945521116257
2023-01-24 04:19:48.815308: step: 442/469, loss: 0.006440779659897089
2023-01-24 04:19:49.422422: step: 444/469, loss: 0.0011556058889254928
2023-01-24 04:19:50.047848: step: 446/469, loss: 0.2666653096675873
2023-01-24 04:19:50.641135: step: 448/469, loss: 0.0335611067712307
2023-01-24 04:19:51.289168: step: 450/469, loss: 0.06425870209932327
2023-01-24 04:19:51.944298: step: 452/469, loss: 0.011099952273070812
2023-01-24 04:19:52.578999: step: 454/469, loss: 0.0860430896282196
2023-01-24 04:19:53.203662: step: 456/469, loss: 0.6219310164451599
2023-01-24 04:19:53.784173: step: 458/469, loss: 0.0025105306413024664
2023-01-24 04:19:54.403724: step: 460/469, loss: 0.004365452565252781
2023-01-24 04:19:55.072371: step: 462/469, loss: 0.00031475472496822476
2023-01-24 04:19:55.697950: step: 464/469, loss: 0.07625474035739899
2023-01-24 04:19:56.262787: step: 466/469, loss: 0.0357365645468235
2023-01-24 04:19:56.855519: step: 468/469, loss: 0.04635073244571686
2023-01-24 04:19:57.463961: step: 470/469, loss: 0.010422706604003906
2023-01-24 04:19:58.083547: step: 472/469, loss: 0.015965810045599937
2023-01-24 04:19:58.692395: step: 474/469, loss: 0.05657362565398216
2023-01-24 04:19:59.292750: step: 476/469, loss: 0.01111332606524229
2023-01-24 04:19:59.982226: step: 478/469, loss: 2.8216209411621094
2023-01-24 04:20:00.573725: step: 480/469, loss: 0.03001786395907402
2023-01-24 04:20:01.219885: step: 482/469, loss: 0.009279635734856129
2023-01-24 04:20:01.927609: step: 484/469, loss: 0.011910689994692802
2023-01-24 04:20:02.584265: step: 486/469, loss: 0.07531367242336273
2023-01-24 04:20:03.199291: step: 488/469, loss: 0.04005114734172821
2023-01-24 04:20:03.860189: step: 490/469, loss: 0.029068103060126305
2023-01-24 04:20:04.478653: step: 492/469, loss: 0.007307740859687328
2023-01-24 04:20:05.157246: step: 494/469, loss: 0.013578913174569607
2023-01-24 04:20:05.706459: step: 496/469, loss: 0.014166039414703846
2023-01-24 04:20:06.308814: step: 498/469, loss: 0.005432970356196165
2023-01-24 04:20:06.909170: step: 500/469, loss: 0.438414603471756
2023-01-24 04:20:07.505406: step: 502/469, loss: 0.009488563053309917
2023-01-24 04:20:08.130298: step: 504/469, loss: 0.026535330340266228
2023-01-24 04:20:08.728071: step: 506/469, loss: 0.0009407024481333792
2023-01-24 04:20:09.282492: step: 508/469, loss: 0.021527405828237534
2023-01-24 04:20:09.900295: step: 510/469, loss: 0.0013636683579534292
2023-01-24 04:20:10.579479: step: 512/469, loss: 0.00748690078034997
2023-01-24 04:20:11.242585: step: 514/469, loss: 0.06145711988210678
2023-01-24 04:20:11.912905: step: 516/469, loss: 0.0016967600677162409
2023-01-24 04:20:12.540234: step: 518/469, loss: 0.01326613500714302
2023-01-24 04:20:13.190682: step: 520/469, loss: 0.017016036435961723
2023-01-24 04:20:13.756357: step: 522/469, loss: 0.2631334364414215
2023-01-24 04:20:14.411318: step: 524/469, loss: 0.0008613273384980857
2023-01-24 04:20:15.091643: step: 526/469, loss: 0.008722303435206413
2023-01-24 04:20:15.676638: step: 528/469, loss: 0.0010988791473209858
2023-01-24 04:20:16.298785: step: 530/469, loss: 0.025261837989091873
2023-01-24 04:20:16.961518: step: 532/469, loss: 0.108428455889225
2023-01-24 04:20:17.583400: step: 534/469, loss: 0.04474363103508949
2023-01-24 04:20:18.178751: step: 536/469, loss: 0.022395450621843338
2023-01-24 04:20:18.753358: step: 538/469, loss: 0.0051158517599105835
2023-01-24 04:20:19.377800: step: 540/469, loss: 0.07086169719696045
2023-01-24 04:20:20.017982: step: 542/469, loss: 0.1461431086063385
2023-01-24 04:20:20.664929: step: 544/469, loss: 0.02447369508445263
2023-01-24 04:20:21.265930: step: 546/469, loss: 0.003372251521795988
2023-01-24 04:20:21.957682: step: 548/469, loss: 0.022394711151719093
2023-01-24 04:20:22.603741: step: 550/469, loss: 0.05098595470190048
2023-01-24 04:20:23.228890: step: 552/469, loss: 0.03485753759741783
2023-01-24 04:20:23.835558: step: 554/469, loss: 0.01913411170244217
2023-01-24 04:20:24.548069: step: 556/469, loss: 0.0005106988828629255
2023-01-24 04:20:25.247073: step: 558/469, loss: 0.024273579940199852
2023-01-24 04:20:25.940124: step: 560/469, loss: 0.06003189459443092
2023-01-24 04:20:26.570732: step: 562/469, loss: 0.015975648537278175
2023-01-24 04:20:27.222638: step: 564/469, loss: 0.04889070242643356
2023-01-24 04:20:27.889547: step: 566/469, loss: 0.004329674877226353
2023-01-24 04:20:28.572285: step: 568/469, loss: 0.20665863156318665
2023-01-24 04:20:29.315005: step: 570/469, loss: 0.046717625111341476
2023-01-24 04:20:29.939098: step: 572/469, loss: 0.005358706694096327
2023-01-24 04:20:30.574602: step: 574/469, loss: 0.05420185253024101
2023-01-24 04:20:31.142908: step: 576/469, loss: 0.045543890446424484
2023-01-24 04:20:31.773455: step: 578/469, loss: 0.051338620483875275
2023-01-24 04:20:32.355897: step: 580/469, loss: 0.09271926432847977
2023-01-24 04:20:32.986068: step: 582/469, loss: 0.07600134611129761
2023-01-24 04:20:33.598466: step: 584/469, loss: 0.0850319117307663
2023-01-24 04:20:34.287588: step: 586/469, loss: 0.047790274024009705
2023-01-24 04:20:34.941462: step: 588/469, loss: 0.01662716642022133
2023-01-24 04:20:35.603606: step: 590/469, loss: 0.01776893064379692
2023-01-24 04:20:36.186146: step: 592/469, loss: 0.010264355689287186
2023-01-24 04:20:36.794545: step: 594/469, loss: 0.03647656738758087
2023-01-24 04:20:37.381380: step: 596/469, loss: 0.0029565831646323204
2023-01-24 04:20:38.049158: step: 598/469, loss: 0.005822004284709692
2023-01-24 04:20:38.665921: step: 600/469, loss: 0.07133756577968597
2023-01-24 04:20:39.225161: step: 602/469, loss: 0.05447622016072273
2023-01-24 04:20:39.796781: step: 604/469, loss: 0.0001856352319009602
2023-01-24 04:20:40.454772: step: 606/469, loss: 0.0003206977271474898
2023-01-24 04:20:40.958317: step: 608/469, loss: 0.007646747399121523
2023-01-24 04:20:41.622442: step: 610/469, loss: 0.015947137027978897
2023-01-24 04:20:42.249657: step: 612/469, loss: 0.031069105491042137
2023-01-24 04:20:42.876459: step: 614/469, loss: 0.09184547513723373
2023-01-24 04:20:43.694608: step: 616/469, loss: 0.020485946908593178
2023-01-24 04:20:44.328974: step: 618/469, loss: 0.2241358458995819
2023-01-24 04:20:44.958660: step: 620/469, loss: 0.005171081516891718
2023-01-24 04:20:45.623295: step: 622/469, loss: 0.034143850207328796
2023-01-24 04:20:46.265217: step: 624/469, loss: 0.02039930410683155
2023-01-24 04:20:47.058501: step: 626/469, loss: 0.061198413372039795
2023-01-24 04:20:47.658862: step: 628/469, loss: 0.0069563682191073895
2023-01-24 04:20:48.280767: step: 630/469, loss: 0.0026992070488631725
2023-01-24 04:20:48.944764: step: 632/469, loss: 0.01687643676996231
2023-01-24 04:20:49.570463: step: 634/469, loss: 0.023891648277640343
2023-01-24 04:20:50.132272: step: 636/469, loss: 0.04390119016170502
2023-01-24 04:20:50.775165: step: 638/469, loss: 0.2554837167263031
2023-01-24 04:20:51.435858: step: 640/469, loss: 0.04864421859383583
2023-01-24 04:20:52.083653: step: 642/469, loss: 0.004678256344050169
2023-01-24 04:20:52.684890: step: 644/469, loss: 0.0076864478178322315
2023-01-24 04:20:53.305952: step: 646/469, loss: 0.015554619953036308
2023-01-24 04:20:53.880183: step: 648/469, loss: 0.0730988010764122
2023-01-24 04:20:54.421565: step: 650/469, loss: 0.04674271121621132
2023-01-24 04:20:55.103736: step: 652/469, loss: 0.013844741508364677
2023-01-24 04:20:55.646834: step: 654/469, loss: 0.01298499759286642
2023-01-24 04:20:56.297218: step: 656/469, loss: 0.010526896454393864
2023-01-24 04:20:57.006976: step: 658/469, loss: 0.0166607778519392
2023-01-24 04:20:57.645957: step: 660/469, loss: 0.013099784031510353
2023-01-24 04:20:58.259893: step: 662/469, loss: 0.023929951712489128
2023-01-24 04:20:58.935453: step: 664/469, loss: 0.029083797708153725
2023-01-24 04:20:59.532856: step: 666/469, loss: 0.031284451484680176
2023-01-24 04:21:00.220165: step: 668/469, loss: 0.23350965976715088
2023-01-24 04:21:00.911802: step: 670/469, loss: 0.04141067713499069
2023-01-24 04:21:01.584692: step: 672/469, loss: 0.04890824109315872
2023-01-24 04:21:02.214744: step: 674/469, loss: 0.2251994013786316
2023-01-24 04:21:02.816081: step: 676/469, loss: 0.01100002322345972
2023-01-24 04:21:03.417224: step: 678/469, loss: 0.02639543078839779
2023-01-24 04:21:04.010596: step: 680/469, loss: 0.026796657592058182
2023-01-24 04:21:04.636196: step: 682/469, loss: 0.020167997106909752
2023-01-24 04:21:05.248661: step: 684/469, loss: 0.004455122631043196
2023-01-24 04:21:05.848251: step: 686/469, loss: 0.012984787113964558
2023-01-24 04:21:06.496414: step: 688/469, loss: 0.28461185097694397
2023-01-24 04:21:07.149734: step: 690/469, loss: 0.004374017007648945
2023-01-24 04:21:07.783786: step: 692/469, loss: 0.015682077035307884
2023-01-24 04:21:08.384873: step: 694/469, loss: 0.016279974952340126
2023-01-24 04:21:09.051764: step: 696/469, loss: 0.059418100863695145
2023-01-24 04:21:09.642812: step: 698/469, loss: 0.008805235847830772
2023-01-24 04:21:10.306031: step: 700/469, loss: 0.037468321621418
2023-01-24 04:21:10.893598: step: 702/469, loss: 0.03351537883281708
2023-01-24 04:21:11.520116: step: 704/469, loss: 0.2406420260667801
2023-01-24 04:21:12.195606: step: 706/469, loss: 0.0076634762808680534
2023-01-24 04:21:12.858870: step: 708/469, loss: 0.12576699256896973
2023-01-24 04:21:13.449790: step: 710/469, loss: 0.0019828625954687595
2023-01-24 04:21:14.058015: step: 712/469, loss: 0.015728894621133804
2023-01-24 04:21:14.608077: step: 714/469, loss: 0.009912285022437572
2023-01-24 04:21:15.255010: step: 716/469, loss: 0.02390599250793457
2023-01-24 04:21:15.927406: step: 718/469, loss: 0.6465012431144714
2023-01-24 04:21:16.549566: step: 720/469, loss: 0.0433785654604435
2023-01-24 04:21:17.145688: step: 722/469, loss: 0.0016821925528347492
2023-01-24 04:21:17.777862: step: 724/469, loss: 0.015557276085019112
2023-01-24 04:21:18.417999: step: 726/469, loss: 0.006185324862599373
2023-01-24 04:21:19.039799: step: 728/469, loss: 0.007912787608802319
2023-01-24 04:21:19.637773: step: 730/469, loss: 1.372776985168457
2023-01-24 04:21:20.270835: step: 732/469, loss: 0.10331526398658752
2023-01-24 04:21:20.846505: step: 734/469, loss: 0.08862237632274628
2023-01-24 04:21:21.459334: step: 736/469, loss: 0.05291207879781723
2023-01-24 04:21:22.049157: step: 738/469, loss: 0.014255165122449398
2023-01-24 04:21:22.683845: step: 740/469, loss: 0.03309673070907593
2023-01-24 04:21:23.251263: step: 742/469, loss: 0.003737740684300661
2023-01-24 04:21:23.902328: step: 744/469, loss: 0.10176929831504822
2023-01-24 04:21:24.558893: step: 746/469, loss: 0.0867793932557106
2023-01-24 04:21:25.147332: step: 748/469, loss: 0.050306957215070724
2023-01-24 04:21:25.823562: step: 750/469, loss: 0.02482243999838829
2023-01-24 04:21:26.450011: step: 752/469, loss: 0.03686288744211197
2023-01-24 04:21:27.110137: step: 754/469, loss: 0.019275685772299767
2023-01-24 04:21:27.707856: step: 756/469, loss: 0.0424811951816082
2023-01-24 04:21:28.232106: step: 758/469, loss: 0.015101857483386993
2023-01-24 04:21:28.948831: step: 760/469, loss: 0.0010853593703359365
2023-01-24 04:21:29.540228: step: 762/469, loss: 0.07512016594409943
2023-01-24 04:21:30.178380: step: 764/469, loss: 0.2834002375602722
2023-01-24 04:21:30.781761: step: 766/469, loss: 0.03509870544075966
2023-01-24 04:21:31.413456: step: 768/469, loss: 0.030473843216896057
2023-01-24 04:21:32.086238: step: 770/469, loss: 0.0468730665743351
2023-01-24 04:21:32.736310: step: 772/469, loss: 0.6759230494499207
2023-01-24 04:21:33.305612: step: 774/469, loss: 0.011631988920271397
2023-01-24 04:21:33.901300: step: 776/469, loss: 0.0067085642367601395
2023-01-24 04:21:34.538556: step: 778/469, loss: 0.025166219100356102
2023-01-24 04:21:35.236614: step: 780/469, loss: 0.03705146163702011
2023-01-24 04:21:35.864911: step: 782/469, loss: 0.044877778738737106
2023-01-24 04:21:36.510499: step: 784/469, loss: 0.05136854574084282
2023-01-24 04:21:37.098814: step: 786/469, loss: 0.16610364615917206
2023-01-24 04:21:37.789969: step: 788/469, loss: 0.04840927943587303
2023-01-24 04:21:38.487765: step: 790/469, loss: 0.19635668396949768
2023-01-24 04:21:39.045606: step: 792/469, loss: 0.01864774152636528
2023-01-24 04:21:39.741432: step: 794/469, loss: 0.002800745191052556
2023-01-24 04:21:40.367280: step: 796/469, loss: 0.012739913538098335
2023-01-24 04:21:41.010531: step: 798/469, loss: 0.012379863299429417
2023-01-24 04:21:41.661065: step: 800/469, loss: 0.0013234555954113603
2023-01-24 04:21:42.315921: step: 802/469, loss: 0.14927874505519867
2023-01-24 04:21:42.950907: step: 804/469, loss: 0.03492793068289757
2023-01-24 04:21:43.627450: step: 806/469, loss: 0.05809061974287033
2023-01-24 04:21:44.228331: step: 808/469, loss: 0.004753398708999157
2023-01-24 04:21:44.809428: step: 810/469, loss: 0.006861999165266752
2023-01-24 04:21:45.479625: step: 812/469, loss: 0.014548441395163536
2023-01-24 04:21:46.124687: step: 814/469, loss: 0.07043583691120148
2023-01-24 04:21:46.736868: step: 816/469, loss: 0.02126930095255375
2023-01-24 04:21:47.352947: step: 818/469, loss: 0.02161935158073902
2023-01-24 04:21:48.052356: step: 820/469, loss: 0.003955075982958078
2023-01-24 04:21:48.689139: step: 822/469, loss: 0.03301957994699478
2023-01-24 04:21:49.381041: step: 824/469, loss: 0.012437576428055763
2023-01-24 04:21:50.038676: step: 826/469, loss: 0.007403786759823561
2023-01-24 04:21:50.658102: step: 828/469, loss: 0.019394539296627045
2023-01-24 04:21:51.247766: step: 830/469, loss: 0.03379194810986519
2023-01-24 04:21:51.912536: step: 832/469, loss: 0.03000115603208542
2023-01-24 04:21:52.589748: step: 834/469, loss: 0.010721656493842602
2023-01-24 04:21:53.170747: step: 836/469, loss: 0.05591261014342308
2023-01-24 04:21:53.772161: step: 838/469, loss: 0.0024415398947894573
2023-01-24 04:21:54.382068: step: 840/469, loss: 0.04237809777259827
2023-01-24 04:21:55.024513: step: 842/469, loss: 0.004956814460456371
2023-01-24 04:21:55.645312: step: 844/469, loss: 0.021096479147672653
2023-01-24 04:21:56.299539: step: 846/469, loss: 0.0444808229804039
2023-01-24 04:21:56.837097: step: 848/469, loss: 0.0549582801759243
2023-01-24 04:21:57.466390: step: 850/469, loss: 0.049095068126916885
2023-01-24 04:21:58.077518: step: 852/469, loss: 0.0007168870070017874
2023-01-24 04:21:58.704737: step: 854/469, loss: 0.007447755895555019
2023-01-24 04:21:59.302206: step: 856/469, loss: 0.013007380068302155
2023-01-24 04:21:59.956056: step: 858/469, loss: 0.07912391424179077
2023-01-24 04:22:00.590709: step: 860/469, loss: 0.007616672199219465
2023-01-24 04:22:01.209878: step: 862/469, loss: 0.06354168802499771
2023-01-24 04:22:01.824651: step: 864/469, loss: 0.01765485294163227
2023-01-24 04:22:02.425434: step: 866/469, loss: 0.08060652017593384
2023-01-24 04:22:03.008986: step: 868/469, loss: 0.04794704541563988
2023-01-24 04:22:03.618691: step: 870/469, loss: 0.03857680410146713
2023-01-24 04:22:04.281997: step: 872/469, loss: 0.06660234928131104
2023-01-24 04:22:04.939354: step: 874/469, loss: 0.04524796083569527
2023-01-24 04:22:05.564314: step: 876/469, loss: 0.0294257253408432
2023-01-24 04:22:06.202416: step: 878/469, loss: 0.048293184489011765
2023-01-24 04:22:06.837035: step: 880/469, loss: 0.022815581411123276
2023-01-24 04:22:07.452633: step: 882/469, loss: 0.012829248793423176
2023-01-24 04:22:08.096549: step: 884/469, loss: 0.14886873960494995
2023-01-24 04:22:08.775094: step: 886/469, loss: 0.025759056210517883
2023-01-24 04:22:09.347751: step: 888/469, loss: 0.412566602230072
2023-01-24 04:22:09.982250: step: 890/469, loss: 0.033732280135154724
2023-01-24 04:22:10.656186: step: 892/469, loss: 0.011866229586303234
2023-01-24 04:22:11.237125: step: 894/469, loss: 0.003136869752779603
2023-01-24 04:22:11.822652: step: 896/469, loss: 0.028152301907539368
2023-01-24 04:22:12.558782: step: 898/469, loss: 0.07520636916160583
2023-01-24 04:22:13.185660: step: 900/469, loss: 0.055856283754110336
2023-01-24 04:22:13.845111: step: 902/469, loss: 0.01485371496528387
2023-01-24 04:22:14.438057: step: 904/469, loss: 0.06036660075187683
2023-01-24 04:22:15.104259: step: 906/469, loss: 0.11419340968132019
2023-01-24 04:22:15.694042: step: 908/469, loss: 0.02651139162480831
2023-01-24 04:22:16.340519: step: 910/469, loss: 0.0018147239461541176
2023-01-24 04:22:16.919033: step: 912/469, loss: 0.0162180345505476
2023-01-24 04:22:17.594582: step: 914/469, loss: 0.009250929579138756
2023-01-24 04:22:18.191861: step: 916/469, loss: 0.07815077155828476
2023-01-24 04:22:18.849684: step: 918/469, loss: 0.0694354996085167
2023-01-24 04:22:19.472954: step: 920/469, loss: 0.009638773277401924
2023-01-24 04:22:20.116767: step: 922/469, loss: 0.015771687030792236
2023-01-24 04:22:20.653894: step: 924/469, loss: 0.13897131383419037
2023-01-24 04:22:21.360986: step: 926/469, loss: 0.0017463566036894917
2023-01-24 04:22:21.997194: step: 928/469, loss: 0.04525983706116676
2023-01-24 04:22:22.703028: step: 930/469, loss: 0.011975876986980438
2023-01-24 04:22:23.302184: step: 932/469, loss: 0.006134568713605404
2023-01-24 04:22:23.882573: step: 934/469, loss: 0.0049422550946474075
2023-01-24 04:22:24.482155: step: 936/469, loss: 0.08714479207992554
2023-01-24 04:22:25.101137: step: 938/469, loss: 0.10087117552757263
==================================================
Loss: 0.064
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3299572743207712, 'r': 0.3061652886961236, 'f1': 0.3176163526434196}, 'combined': 0.23403310194778285, 'epoch': 27}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3280240928813593, 'r': 0.2601984341520023, 'f1': 0.29020090666136583}, 'combined': 0.15829140363347227, 'epoch': 27}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3371907933255269, 'r': 0.3122373949579832, 'f1': 0.32423469387755105}, 'combined': 0.23890977443609024, 'epoch': 27}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33705448698520457, 'r': 0.26427785484567273, 'f1': 0.29626225163725156}, 'combined': 0.1615975918021372, 'epoch': 27}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32770821234998065, 'r': 0.3059439098219933, 'f1': 0.31645228749006965}, 'combined': 0.233175369729525, 'epoch': 27}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3306802281274896, 'r': 0.2656333397035095, 'f1': 0.2946090718375808}, 'combined': 0.16069585736595315, 'epoch': 27}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3922413793103448, 'r': 0.325, 'f1': 0.35546875000000006}, 'combined': 0.23697916666666669, 'epoch': 27}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3409090909090909, 'r': 0.32608695652173914, 'f1': 0.3333333333333333}, 'combined': 0.16666666666666666, 'epoch': 27}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.1724137931034483, 'f1': 0.25641025641025644}, 'combined': 0.17094017094017094, 'epoch': 27}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 04:25:11.493546: step: 2/469, loss: 0.046117667108774185
2023-01-24 04:25:12.094336: step: 4/469, loss: 0.021690616384148598
2023-01-24 04:25:12.660906: step: 6/469, loss: 0.001044116448611021
2023-01-24 04:25:13.345486: step: 8/469, loss: 0.023402441293001175
2023-01-24 04:25:13.956207: step: 10/469, loss: 0.00445956876501441
2023-01-24 04:25:14.537348: step: 12/469, loss: 0.09092497825622559
2023-01-24 04:25:15.088792: step: 14/469, loss: 0.0051290481351315975
2023-01-24 04:25:15.708721: step: 16/469, loss: 0.0009732205071486533
2023-01-24 04:25:16.258097: step: 18/469, loss: 0.004005457740277052
2023-01-24 04:25:16.875235: step: 20/469, loss: 0.003026357153430581
2023-01-24 04:25:17.458248: step: 22/469, loss: 0.005434069782495499
2023-01-24 04:25:18.103041: step: 24/469, loss: 0.012082789093255997
2023-01-24 04:25:18.675934: step: 26/469, loss: 0.11068152636289597
2023-01-24 04:25:19.286684: step: 28/469, loss: 0.014834997244179249
2023-01-24 04:25:19.912462: step: 30/469, loss: 0.0019150963053107262
2023-01-24 04:25:20.487072: step: 32/469, loss: 0.0034351758658885956
2023-01-24 04:25:21.255973: step: 34/469, loss: 0.044433578848838806
2023-01-24 04:25:21.912608: step: 36/469, loss: 0.0034827005583792925
2023-01-24 04:25:22.512272: step: 38/469, loss: 0.03252704441547394
2023-01-24 04:25:23.116461: step: 40/469, loss: 0.0008543062140233815
2023-01-24 04:25:23.765632: step: 42/469, loss: 0.036822181195020676
2023-01-24 04:25:24.454974: step: 44/469, loss: 0.4671904742717743
2023-01-24 04:25:25.067663: step: 46/469, loss: 0.01179991103708744
2023-01-24 04:25:25.688975: step: 48/469, loss: 0.0029738720040768385
2023-01-24 04:25:26.286950: step: 50/469, loss: 0.025945907458662987
2023-01-24 04:25:26.910043: step: 52/469, loss: 0.24279694259166718
2023-01-24 04:25:27.553158: step: 54/469, loss: 0.04112083464860916
2023-01-24 04:25:28.186524: step: 56/469, loss: 0.0020899134688079357
2023-01-24 04:25:28.827044: step: 58/469, loss: 0.016317013651132584
2023-01-24 04:25:29.445090: step: 60/469, loss: 0.026673637330532074
2023-01-24 04:25:30.126765: step: 62/469, loss: 0.0037051585968583822
2023-01-24 04:25:30.747004: step: 64/469, loss: 0.000197053566807881
2023-01-24 04:25:31.453541: step: 66/469, loss: 0.003966174554079771
2023-01-24 04:25:32.049230: step: 68/469, loss: 0.014426983892917633
2023-01-24 04:25:32.694281: step: 70/469, loss: 0.015052501112222672
2023-01-24 04:25:33.320636: step: 72/469, loss: 0.029321715235710144
2023-01-24 04:25:33.906787: step: 74/469, loss: 0.010223906487226486
2023-01-24 04:25:34.646503: step: 76/469, loss: 0.020182477310299873
2023-01-24 04:25:35.328603: step: 78/469, loss: 0.0006092899711802602
2023-01-24 04:25:35.976956: step: 80/469, loss: 0.08710543066263199
2023-01-24 04:25:36.627749: step: 82/469, loss: 0.5180069804191589
2023-01-24 04:25:37.238267: step: 84/469, loss: 0.0765908807516098
2023-01-24 04:25:37.822822: step: 86/469, loss: 0.04816500097513199
2023-01-24 04:25:38.461373: step: 88/469, loss: 0.009879494085907936
2023-01-24 04:25:39.123395: step: 90/469, loss: 0.009175695478916168
2023-01-24 04:25:39.726562: step: 92/469, loss: 0.0030323462560772896
2023-01-24 04:25:40.339838: step: 94/469, loss: 0.016966333612799644
2023-01-24 04:25:40.995991: step: 96/469, loss: 1.4426153898239136
2023-01-24 04:25:41.594210: step: 98/469, loss: 0.019680799916386604
2023-01-24 04:25:42.191707: step: 100/469, loss: 0.007532022427767515
2023-01-24 04:25:42.865214: step: 102/469, loss: 0.003947995137423277
2023-01-24 04:25:43.514851: step: 104/469, loss: 0.02941165491938591
2023-01-24 04:25:44.121934: step: 106/469, loss: 0.04238269105553627
2023-01-24 04:25:44.688981: step: 108/469, loss: 0.00334938894957304
2023-01-24 04:25:45.486696: step: 110/469, loss: 0.04745030403137207
2023-01-24 04:25:46.122848: step: 112/469, loss: 0.005659888032823801
2023-01-24 04:25:46.770183: step: 114/469, loss: 0.004309596959501505
2023-01-24 04:25:47.427964: step: 116/469, loss: 0.013013780117034912
2023-01-24 04:25:48.060037: step: 118/469, loss: 0.0148171903565526
2023-01-24 04:25:48.661391: step: 120/469, loss: 0.0932435691356659
2023-01-24 04:25:49.259362: step: 122/469, loss: 0.03964155539870262
2023-01-24 04:25:49.879628: step: 124/469, loss: 0.03424255922436714
2023-01-24 04:25:50.491919: step: 126/469, loss: 0.35389021039009094
2023-01-24 04:25:51.047726: step: 128/469, loss: 0.008723670616745949
2023-01-24 04:25:51.693221: step: 130/469, loss: 0.14223450422286987
2023-01-24 04:25:52.318285: step: 132/469, loss: 0.0004380336031317711
2023-01-24 04:25:52.903853: step: 134/469, loss: 0.03252764046192169
2023-01-24 04:25:53.517163: step: 136/469, loss: 0.050242744386196136
2023-01-24 04:25:54.096179: step: 138/469, loss: 0.023888027295470238
2023-01-24 04:25:54.667947: step: 140/469, loss: 0.007920670323073864
2023-01-24 04:25:55.287258: step: 142/469, loss: 0.0038254917599260807
2023-01-24 04:25:55.865471: step: 144/469, loss: 0.0032616383396089077
2023-01-24 04:25:56.529877: step: 146/469, loss: 0.007968848571181297
2023-01-24 04:25:57.164463: step: 148/469, loss: 0.002290271455422044
2023-01-24 04:25:57.793419: step: 150/469, loss: 0.03925652429461479
2023-01-24 04:25:58.394368: step: 152/469, loss: 0.0185690987855196
2023-01-24 04:25:58.993842: step: 154/469, loss: 0.0018010850762948394
2023-01-24 04:25:59.703511: step: 156/469, loss: 0.009231813251972198
2023-01-24 04:26:00.305859: step: 158/469, loss: 0.011754135601222515
2023-01-24 04:26:00.918350: step: 160/469, loss: 0.06417781859636307
2023-01-24 04:26:01.538247: step: 162/469, loss: 0.032035015523433685
2023-01-24 04:26:02.131939: step: 164/469, loss: 0.14094367623329163
2023-01-24 04:26:02.734767: step: 166/469, loss: 0.03806191310286522
2023-01-24 04:26:03.422071: step: 168/469, loss: 0.028705600649118423
2023-01-24 04:26:04.000906: step: 170/469, loss: 0.012910599820315838
2023-01-24 04:26:04.540722: step: 172/469, loss: 0.002661576960235834
2023-01-24 04:26:05.170286: step: 174/469, loss: 0.011819063685834408
2023-01-24 04:26:05.872925: step: 176/469, loss: 0.029520921409130096
2023-01-24 04:26:06.495836: step: 178/469, loss: 0.05733266845345497
2023-01-24 04:26:07.094463: step: 180/469, loss: 0.011158952489495277
2023-01-24 04:26:07.744428: step: 182/469, loss: 0.021350566297769547
2023-01-24 04:26:08.421444: step: 184/469, loss: 0.052336230874061584
2023-01-24 04:26:09.051803: step: 186/469, loss: 0.026848940178751945
2023-01-24 04:26:09.624458: step: 188/469, loss: 0.0014062923146411777
2023-01-24 04:26:10.184452: step: 190/469, loss: 0.03976031020283699
2023-01-24 04:26:10.829099: step: 192/469, loss: 0.04806031659245491
2023-01-24 04:26:11.471142: step: 194/469, loss: 0.03805208206176758
2023-01-24 04:26:12.126481: step: 196/469, loss: 0.012083997018635273
2023-01-24 04:26:12.745586: step: 198/469, loss: 0.0216117724776268
2023-01-24 04:26:13.342338: step: 200/469, loss: 0.0507252961397171
2023-01-24 04:26:13.990591: step: 202/469, loss: 0.00042968595516867936
2023-01-24 04:26:14.589976: step: 204/469, loss: 0.06810729950666428
2023-01-24 04:26:15.231233: step: 206/469, loss: 0.013265375979244709
2023-01-24 04:26:15.956712: step: 208/469, loss: 0.02576095052063465
2023-01-24 04:26:16.602297: step: 210/469, loss: 0.023638907819986343
2023-01-24 04:26:17.215846: step: 212/469, loss: 0.11431443691253662
2023-01-24 04:26:17.823136: step: 214/469, loss: 0.00093061663210392
2023-01-24 04:26:18.522680: step: 216/469, loss: 0.11402209103107452
2023-01-24 04:26:19.135392: step: 218/469, loss: 0.3777497410774231
2023-01-24 04:26:19.714736: step: 220/469, loss: 0.0003449449432082474
2023-01-24 04:26:20.277292: step: 222/469, loss: 0.007000977173447609
2023-01-24 04:26:20.870769: step: 224/469, loss: 0.003302902216091752
2023-01-24 04:26:21.458081: step: 226/469, loss: 0.025939274579286575
2023-01-24 04:26:22.016315: step: 228/469, loss: 0.019885417073965073
2023-01-24 04:26:22.670035: step: 230/469, loss: 0.018146274611353874
2023-01-24 04:26:23.331292: step: 232/469, loss: 0.002075487282127142
2023-01-24 04:26:23.949413: step: 234/469, loss: 0.06297841668128967
2023-01-24 04:26:24.597723: step: 236/469, loss: 0.006929186638444662
2023-01-24 04:26:25.174323: step: 238/469, loss: 0.011928737163543701
2023-01-24 04:26:25.763475: step: 240/469, loss: 0.006712186615914106
2023-01-24 04:26:26.390104: step: 242/469, loss: 0.005772011820226908
2023-01-24 04:26:27.053817: step: 244/469, loss: 0.05793805792927742
2023-01-24 04:26:27.654722: step: 246/469, loss: 0.004826302640140057
2023-01-24 04:26:28.293766: step: 248/469, loss: 0.008750352077186108
2023-01-24 04:26:28.902025: step: 250/469, loss: 0.003474102122709155
2023-01-24 04:26:29.557306: step: 252/469, loss: 0.010111937299370766
2023-01-24 04:26:30.180567: step: 254/469, loss: 0.0006807201425544918
2023-01-24 04:26:30.804401: step: 256/469, loss: 0.005595608148723841
2023-01-24 04:26:31.360286: step: 258/469, loss: 0.013326623477041721
2023-01-24 04:26:31.951214: step: 260/469, loss: 0.7546446323394775
2023-01-24 04:26:32.610680: step: 262/469, loss: 0.019674133509397507
2023-01-24 04:26:33.291713: step: 264/469, loss: 0.024653123691678047
2023-01-24 04:26:33.840019: step: 266/469, loss: 0.030251184478402138
2023-01-24 04:26:34.457780: step: 268/469, loss: 0.021238503977656364
2023-01-24 04:26:35.078156: step: 270/469, loss: 0.06220995634794235
2023-01-24 04:26:35.697329: step: 272/469, loss: 0.18594741821289062
2023-01-24 04:26:36.360506: step: 274/469, loss: 0.006447215564548969
2023-01-24 04:26:36.948055: step: 276/469, loss: 0.020789941772818565
2023-01-24 04:26:37.508875: step: 278/469, loss: 3.72604736185167e-05
2023-01-24 04:26:38.221482: step: 280/469, loss: 0.006562444381415844
2023-01-24 04:26:38.824680: step: 282/469, loss: 0.007398547139018774
2023-01-24 04:26:39.383294: step: 284/469, loss: 0.026809178292751312
2023-01-24 04:26:40.017760: step: 286/469, loss: 0.061946723610162735
2023-01-24 04:26:40.601718: step: 288/469, loss: 0.0020723463967442513
2023-01-24 04:26:41.225687: step: 290/469, loss: 0.027895238250494003
2023-01-24 04:26:41.861046: step: 292/469, loss: 0.23240278661251068
2023-01-24 04:26:42.488846: step: 294/469, loss: 0.02472991682589054
2023-01-24 04:26:43.106700: step: 296/469, loss: 1.0509834289550781
2023-01-24 04:26:43.687899: step: 298/469, loss: 0.0015113805420696735
2023-01-24 04:26:44.310261: step: 300/469, loss: 0.017315786331892014
2023-01-24 04:26:44.907760: step: 302/469, loss: 0.021042747423052788
2023-01-24 04:26:45.479548: step: 304/469, loss: 0.011752031743526459
2023-01-24 04:26:46.175739: step: 306/469, loss: 0.513655424118042
2023-01-24 04:26:46.814766: step: 308/469, loss: 0.004860830493271351
2023-01-24 04:26:47.477860: step: 310/469, loss: 0.005903632380068302
2023-01-24 04:26:48.095127: step: 312/469, loss: 0.014028006233274937
2023-01-24 04:26:48.706509: step: 314/469, loss: 0.0006413854425773025
2023-01-24 04:26:49.293201: step: 316/469, loss: 0.03341635316610336
2023-01-24 04:26:49.905994: step: 318/469, loss: 0.004747896920889616
2023-01-24 04:26:50.627094: step: 320/469, loss: 0.015307956375181675
2023-01-24 04:26:51.176104: step: 322/469, loss: 0.0030243617948144674
2023-01-24 04:26:51.820088: step: 324/469, loss: 0.0326656699180603
2023-01-24 04:26:52.431352: step: 326/469, loss: 0.00802603829652071
2023-01-24 04:26:53.023570: step: 328/469, loss: 0.03192810341715813
2023-01-24 04:26:53.612225: step: 330/469, loss: 0.06231268122792244
2023-01-24 04:26:54.328479: step: 332/469, loss: 0.00647707236930728
2023-01-24 04:26:54.903053: step: 334/469, loss: 0.003140086540952325
2023-01-24 04:26:55.503698: step: 336/469, loss: 0.004049165640026331
2023-01-24 04:26:56.162139: step: 338/469, loss: 0.7120697498321533
2023-01-24 04:26:56.797218: step: 340/469, loss: 0.024741338565945625
2023-01-24 04:26:57.499920: step: 342/469, loss: 0.015725327655673027
2023-01-24 04:26:58.137056: step: 344/469, loss: 0.0012354745995253325
2023-01-24 04:26:58.785844: step: 346/469, loss: 0.013057139702141285
2023-01-24 04:26:59.274272: step: 348/469, loss: 0.008503837510943413
2023-01-24 04:26:59.969411: step: 350/469, loss: 0.03578595072031021
2023-01-24 04:27:00.583723: step: 352/469, loss: 0.014671429991722107
2023-01-24 04:27:01.184261: step: 354/469, loss: 0.020837299525737762
2023-01-24 04:27:01.799209: step: 356/469, loss: 0.012281851842999458
2023-01-24 04:27:02.378285: step: 358/469, loss: 0.5292306542396545
2023-01-24 04:27:02.978932: step: 360/469, loss: 0.021828878670930862
2023-01-24 04:27:03.670788: step: 362/469, loss: 0.004975995514541864
2023-01-24 04:27:04.280324: step: 364/469, loss: 0.01794261671602726
2023-01-24 04:27:04.926126: step: 366/469, loss: 0.007526268716901541
2023-01-24 04:27:05.566222: step: 368/469, loss: 0.6245337724685669
2023-01-24 04:27:06.231025: step: 370/469, loss: 0.017351172864437103
2023-01-24 04:27:06.867665: step: 372/469, loss: 0.009775765240192413
2023-01-24 04:27:07.461337: step: 374/469, loss: 0.013930571265518665
2023-01-24 04:27:08.118184: step: 376/469, loss: 0.102723628282547
2023-01-24 04:27:08.789295: step: 378/469, loss: 0.05071789026260376
2023-01-24 04:27:09.342398: step: 380/469, loss: 0.009899248369038105
2023-01-24 04:27:10.016503: step: 382/469, loss: 0.005348144564777613
2023-01-24 04:27:10.569996: step: 384/469, loss: 0.0845874771475792
2023-01-24 04:27:11.266994: step: 386/469, loss: 0.005308009684085846
2023-01-24 04:27:11.958430: step: 388/469, loss: 0.08498001098632812
2023-01-24 04:27:12.582701: step: 390/469, loss: 0.03851882740855217
2023-01-24 04:27:13.231495: step: 392/469, loss: 0.00036290474236011505
2023-01-24 04:27:13.840558: step: 394/469, loss: 0.03963419795036316
2023-01-24 04:27:14.481731: step: 396/469, loss: 0.03450312465429306
2023-01-24 04:27:15.090514: step: 398/469, loss: 0.0025501695927232504
2023-01-24 04:27:15.723246: step: 400/469, loss: 0.04440242052078247
2023-01-24 04:27:16.337593: step: 402/469, loss: 0.004292868077754974
2023-01-24 04:27:16.878301: step: 404/469, loss: 0.03436756879091263
2023-01-24 04:27:17.451041: step: 406/469, loss: 0.0028362928424030542
2023-01-24 04:27:18.134820: step: 408/469, loss: 0.0009868261404335499
2023-01-24 04:27:18.827388: step: 410/469, loss: 0.03605183959007263
2023-01-24 04:27:19.397293: step: 412/469, loss: 0.024166947230696678
2023-01-24 04:27:19.991780: step: 414/469, loss: 0.01576944626867771
2023-01-24 04:27:20.637328: step: 416/469, loss: 0.028224492445588112
2023-01-24 04:27:21.259390: step: 418/469, loss: 0.05126165971159935
2023-01-24 04:27:21.833356: step: 420/469, loss: 0.15945526957511902
2023-01-24 04:27:22.430696: step: 422/469, loss: 0.001844732672907412
2023-01-24 04:27:23.092473: step: 424/469, loss: 0.00355209456756711
2023-01-24 04:27:23.710003: step: 426/469, loss: 0.03788159415125847
2023-01-24 04:27:24.309694: step: 428/469, loss: 0.0040191118605434895
2023-01-24 04:27:24.992500: step: 430/469, loss: 0.018151845782995224
2023-01-24 04:27:25.587278: step: 432/469, loss: 0.03129963204264641
2023-01-24 04:27:26.166769: step: 434/469, loss: 0.010316013358533382
2023-01-24 04:27:26.782438: step: 436/469, loss: 0.07308047264814377
2023-01-24 04:27:27.447108: step: 438/469, loss: 0.0064715552143752575
2023-01-24 04:27:28.066082: step: 440/469, loss: 0.03209478035569191
2023-01-24 04:27:28.663261: step: 442/469, loss: 0.004542089533060789
2023-01-24 04:27:29.354798: step: 444/469, loss: 0.0011712894774973392
2023-01-24 04:27:29.965920: step: 446/469, loss: 0.1002793163061142
2023-01-24 04:27:30.641919: step: 448/469, loss: 0.07509500533342361
2023-01-24 04:27:31.265622: step: 450/469, loss: 0.04948216304183006
2023-01-24 04:27:31.854233: step: 452/469, loss: 0.12339958548545837
2023-01-24 04:27:32.490951: step: 454/469, loss: 0.001356293330900371
2023-01-24 04:27:33.178187: step: 456/469, loss: 0.001529977540485561
2023-01-24 04:27:33.742657: step: 458/469, loss: 0.0015764759154990315
2023-01-24 04:27:34.392003: step: 460/469, loss: 0.008430872112512589
2023-01-24 04:27:35.037296: step: 462/469, loss: 0.015910552814602852
2023-01-24 04:27:35.667529: step: 464/469, loss: 0.206633061170578
2023-01-24 04:27:36.248176: step: 466/469, loss: 0.050532370805740356
2023-01-24 04:27:36.877622: step: 468/469, loss: 0.0410938486456871
2023-01-24 04:27:37.490178: step: 470/469, loss: 0.01015803124755621
2023-01-24 04:27:38.106239: step: 472/469, loss: 0.10376623272895813
2023-01-24 04:27:38.843605: step: 474/469, loss: 0.010095294564962387
2023-01-24 04:27:39.458443: step: 476/469, loss: 0.047576677054166794
2023-01-24 04:27:40.182568: step: 478/469, loss: 0.008052426390349865
2023-01-24 04:27:40.813199: step: 480/469, loss: 2.4106077034957707e-05
2023-01-24 04:27:41.443858: step: 482/469, loss: 0.005809403490275145
2023-01-24 04:27:42.045274: step: 484/469, loss: 0.025287888944149017
2023-01-24 04:27:42.619389: step: 486/469, loss: 0.005380943417549133
2023-01-24 04:27:43.235108: step: 488/469, loss: 0.009135490283370018
2023-01-24 04:27:43.810840: step: 490/469, loss: 0.023876287043094635
2023-01-24 04:27:44.410754: step: 492/469, loss: 0.0030396936926990747
2023-01-24 04:27:45.031079: step: 494/469, loss: 0.015187445096671581
2023-01-24 04:27:45.701983: step: 496/469, loss: 0.01837237924337387
2023-01-24 04:27:46.368588: step: 498/469, loss: 0.0049912696704268456
2023-01-24 04:27:47.011838: step: 500/469, loss: 0.009158773347735405
2023-01-24 04:27:47.711415: step: 502/469, loss: 0.043934985995292664
2023-01-24 04:27:48.330087: step: 504/469, loss: 0.062133997678756714
2023-01-24 04:27:49.017093: step: 506/469, loss: 0.007055279333144426
2023-01-24 04:27:49.703888: step: 508/469, loss: 0.01807880960404873
2023-01-24 04:27:50.290088: step: 510/469, loss: 0.008635953068733215
2023-01-24 04:27:50.882638: step: 512/469, loss: 0.00672085490077734
2023-01-24 04:27:51.467157: step: 514/469, loss: 0.007145282346755266
2023-01-24 04:27:52.069583: step: 516/469, loss: 0.010456304997205734
2023-01-24 04:27:52.662915: step: 518/469, loss: 0.004864528309553862
2023-01-24 04:27:53.261331: step: 520/469, loss: 0.6717926263809204
2023-01-24 04:27:53.865590: step: 522/469, loss: 0.02913685329258442
2023-01-24 04:27:54.392197: step: 524/469, loss: 0.0020940680988132954
2023-01-24 04:27:55.053274: step: 526/469, loss: 0.004378907382488251
2023-01-24 04:27:55.694764: step: 528/469, loss: 0.1069122850894928
2023-01-24 04:27:56.318149: step: 530/469, loss: 0.07529553771018982
2023-01-24 04:27:56.950039: step: 532/469, loss: 0.015649432316422462
2023-01-24 04:27:57.700120: step: 534/469, loss: 0.00882435217499733
2023-01-24 04:27:58.288869: step: 536/469, loss: 0.030467107892036438
2023-01-24 04:27:58.952320: step: 538/469, loss: 0.013383789919316769
2023-01-24 04:27:59.669238: step: 540/469, loss: 0.2872244417667389
2023-01-24 04:28:00.332040: step: 542/469, loss: 0.0003488498041406274
2023-01-24 04:28:00.906035: step: 544/469, loss: 0.047618526965379715
2023-01-24 04:28:01.545676: step: 546/469, loss: 0.05529698356986046
2023-01-24 04:28:02.226543: step: 548/469, loss: 0.01042431965470314
2023-01-24 04:28:02.872203: step: 550/469, loss: 0.001183462212793529
2023-01-24 04:28:03.484975: step: 552/469, loss: 0.0013073893496766686
2023-01-24 04:28:04.062007: step: 554/469, loss: 0.0003614505403675139
2023-01-24 04:28:04.826289: step: 556/469, loss: 0.01786225475370884
2023-01-24 04:28:05.434951: step: 558/469, loss: 0.06564614921808243
2023-01-24 04:28:06.057207: step: 560/469, loss: 0.0533469133079052
2023-01-24 04:28:06.691574: step: 562/469, loss: 0.009879239834845066
2023-01-24 04:28:07.326642: step: 564/469, loss: 0.033112458884716034
2023-01-24 04:28:07.914883: step: 566/469, loss: 0.024811945855617523
2023-01-24 04:28:08.518355: step: 568/469, loss: 0.009929421357810497
2023-01-24 04:28:09.209818: step: 570/469, loss: 1.0463825464248657
2023-01-24 04:28:09.829970: step: 572/469, loss: 0.045280393213033676
2023-01-24 04:28:10.416118: step: 574/469, loss: 0.08431726694107056
2023-01-24 04:28:11.065347: step: 576/469, loss: 0.014226955361664295
2023-01-24 04:28:11.633098: step: 578/469, loss: 0.00147697061765939
2023-01-24 04:28:12.256165: step: 580/469, loss: 0.0017435989575460553
2023-01-24 04:28:12.957998: step: 582/469, loss: 0.015671757981181145
2023-01-24 04:28:13.559819: step: 584/469, loss: 0.05729326233267784
2023-01-24 04:28:14.125631: step: 586/469, loss: 0.005357309710234404
2023-01-24 04:28:14.810372: step: 588/469, loss: 0.08900397270917892
2023-01-24 04:28:15.410421: step: 590/469, loss: 0.007743714842945337
2023-01-24 04:28:16.034505: step: 592/469, loss: 0.0074604833498597145
2023-01-24 04:28:16.668856: step: 594/469, loss: 0.02177645079791546
2023-01-24 04:28:17.298156: step: 596/469, loss: 0.04581688717007637
2023-01-24 04:28:17.915552: step: 598/469, loss: 0.020270923152565956
2023-01-24 04:28:18.608144: step: 600/469, loss: 0.026205964386463165
2023-01-24 04:28:19.257081: step: 602/469, loss: 0.09614122658967972
2023-01-24 04:28:19.821854: step: 604/469, loss: 0.006960897706449032
2023-01-24 04:28:20.463741: step: 606/469, loss: 0.002453114604577422
2023-01-24 04:28:21.086926: step: 608/469, loss: 0.0012141662882640958
2023-01-24 04:28:21.666012: step: 610/469, loss: 0.9516305923461914
2023-01-24 04:28:22.333886: step: 612/469, loss: 0.0357881635427475
2023-01-24 04:28:22.897292: step: 614/469, loss: 0.014198594726622105
2023-01-24 04:28:23.556513: step: 616/469, loss: 0.21801839768886566
2023-01-24 04:28:24.197046: step: 618/469, loss: 0.004060262348502874
2023-01-24 04:28:24.930369: step: 620/469, loss: 0.045317068696022034
2023-01-24 04:28:25.457813: step: 622/469, loss: 0.22143952548503876
2023-01-24 04:28:26.127047: step: 624/469, loss: 0.01167630311101675
2023-01-24 04:28:26.764177: step: 626/469, loss: 0.05861573666334152
2023-01-24 04:28:27.394430: step: 628/469, loss: 0.016020627692341805
2023-01-24 04:28:27.993688: step: 630/469, loss: 0.02167559415102005
2023-01-24 04:28:28.538523: step: 632/469, loss: 0.001943980692885816
2023-01-24 04:28:29.161397: step: 634/469, loss: 0.006525107193738222
2023-01-24 04:28:29.744762: step: 636/469, loss: 0.029377026483416557
2023-01-24 04:28:30.358074: step: 638/469, loss: 0.024579958990216255
2023-01-24 04:28:30.949505: step: 640/469, loss: 0.09940575808286667
2023-01-24 04:28:31.570705: step: 642/469, loss: 0.015262838453054428
2023-01-24 04:28:32.231705: step: 644/469, loss: 0.020658176392316818
2023-01-24 04:28:32.874330: step: 646/469, loss: 0.12778401374816895
2023-01-24 04:28:33.425534: step: 648/469, loss: 0.007055656518787146
2023-01-24 04:28:34.007601: step: 650/469, loss: 0.03938606008887291
2023-01-24 04:28:34.571394: step: 652/469, loss: 0.00116272596642375
2023-01-24 04:28:35.141266: step: 654/469, loss: 0.03565958887338638
2023-01-24 04:28:35.706105: step: 656/469, loss: 0.02677679993212223
2023-01-24 04:28:36.242821: step: 658/469, loss: 0.00022557307966053486
2023-01-24 04:28:36.868665: step: 660/469, loss: 0.04465703293681145
2023-01-24 04:28:37.541346: step: 662/469, loss: 1.6279860734939575
2023-01-24 04:28:38.174965: step: 664/469, loss: 0.009028756059706211
2023-01-24 04:28:38.742264: step: 666/469, loss: 0.020242320373654366
2023-01-24 04:28:39.350770: step: 668/469, loss: 0.005034836940467358
2023-01-24 04:28:39.913050: step: 670/469, loss: 0.012029912322759628
2023-01-24 04:28:40.483532: step: 672/469, loss: 0.03289627283811569
2023-01-24 04:28:41.107616: step: 674/469, loss: 0.013846637681126595
2023-01-24 04:28:41.719892: step: 676/469, loss: 0.02020134963095188
2023-01-24 04:28:42.379876: step: 678/469, loss: 0.05965556204319
2023-01-24 04:28:42.987892: step: 680/469, loss: 0.025320544838905334
2023-01-24 04:28:43.643396: step: 682/469, loss: 0.03602776303887367
2023-01-24 04:28:44.258145: step: 684/469, loss: 0.008313469588756561
2023-01-24 04:28:44.876319: step: 686/469, loss: 0.01549284253269434
2023-01-24 04:28:45.541445: step: 688/469, loss: 0.04114497825503349
2023-01-24 04:28:46.243015: step: 690/469, loss: 0.03416604921221733
2023-01-24 04:28:46.998626: step: 692/469, loss: 0.04226415976881981
2023-01-24 04:28:47.704625: step: 694/469, loss: 0.06959113478660583
2023-01-24 04:28:48.284466: step: 696/469, loss: 0.0008838659268803895
2023-01-24 04:28:48.992901: step: 698/469, loss: 0.0439516082406044
2023-01-24 04:28:49.568038: step: 700/469, loss: 0.0051228865049779415
2023-01-24 04:28:50.117601: step: 702/469, loss: 0.022063951939344406
2023-01-24 04:28:50.722216: step: 704/469, loss: 0.006934995297342539
2023-01-24 04:28:51.402434: step: 706/469, loss: 0.05567527562379837
2023-01-24 04:28:51.991055: step: 708/469, loss: 0.014823506586253643
2023-01-24 04:28:52.638331: step: 710/469, loss: 0.010614674538373947
2023-01-24 04:28:53.207207: step: 712/469, loss: 0.030289940536022186
2023-01-24 04:28:53.829839: step: 714/469, loss: 0.00467514805495739
2023-01-24 04:28:54.420060: step: 716/469, loss: 0.009180083870887756
2023-01-24 04:28:55.082982: step: 718/469, loss: 0.05070386454463005
2023-01-24 04:28:55.740135: step: 720/469, loss: 0.02567620389163494
2023-01-24 04:28:56.349866: step: 722/469, loss: 0.032591812312603
2023-01-24 04:28:56.999327: step: 724/469, loss: 0.015123724937438965
2023-01-24 04:28:57.637773: step: 726/469, loss: 0.0711151584982872
2023-01-24 04:28:58.319191: step: 728/469, loss: 0.02317347377538681
2023-01-24 04:28:58.969882: step: 730/469, loss: 0.019069934263825417
2023-01-24 04:28:59.610686: step: 732/469, loss: 0.014179736375808716
2023-01-24 04:29:00.201242: step: 734/469, loss: 0.04434696584939957
2023-01-24 04:29:00.802790: step: 736/469, loss: 0.013942303135991096
2023-01-24 04:29:01.409057: step: 738/469, loss: 0.12939247488975525
2023-01-24 04:29:02.046147: step: 740/469, loss: 0.15470831096172333
2023-01-24 04:29:02.678095: step: 742/469, loss: 0.044453032314777374
2023-01-24 04:29:03.330369: step: 744/469, loss: 0.02451922744512558
2023-01-24 04:29:04.004820: step: 746/469, loss: 0.30026310682296753
2023-01-24 04:29:04.683668: step: 748/469, loss: 0.04077666997909546
2023-01-24 04:29:05.354494: step: 750/469, loss: 0.1663493514060974
2023-01-24 04:29:05.927121: step: 752/469, loss: 0.002196589717641473
2023-01-24 04:29:06.564792: step: 754/469, loss: 0.04906152933835983
2023-01-24 04:29:07.225230: step: 756/469, loss: 0.0015373738715425134
2023-01-24 04:29:07.839464: step: 758/469, loss: 0.005340177100151777
2023-01-24 04:29:08.469271: step: 760/469, loss: 0.005104701966047287
2023-01-24 04:29:09.116387: step: 762/469, loss: 0.015469688922166824
2023-01-24 04:29:09.713286: step: 764/469, loss: 0.007918402552604675
2023-01-24 04:29:10.311790: step: 766/469, loss: 0.024146132171154022
2023-01-24 04:29:10.918865: step: 768/469, loss: 0.05916436389088631
2023-01-24 04:29:11.570420: step: 770/469, loss: 0.006385270971804857
2023-01-24 04:29:12.176717: step: 772/469, loss: 0.06721234321594238
2023-01-24 04:29:12.896296: step: 774/469, loss: 0.050477322190999985
2023-01-24 04:29:13.571308: step: 776/469, loss: 0.008046678267419338
2023-01-24 04:29:14.151553: step: 778/469, loss: 0.09385431557893753
2023-01-24 04:29:14.779780: step: 780/469, loss: 0.03446837142109871
2023-01-24 04:29:15.403770: step: 782/469, loss: 0.02484111115336418
2023-01-24 04:29:16.027414: step: 784/469, loss: 0.05750124529004097
2023-01-24 04:29:16.662380: step: 786/469, loss: 0.002741179894655943
2023-01-24 04:29:17.321610: step: 788/469, loss: 0.015425169840455055
2023-01-24 04:29:17.991043: step: 790/469, loss: 0.04131796956062317
2023-01-24 04:29:18.649821: step: 792/469, loss: 0.006841577589511871
2023-01-24 04:29:19.362269: step: 794/469, loss: 0.003700926434248686
2023-01-24 04:29:19.938281: step: 796/469, loss: 0.00742322439327836
2023-01-24 04:29:20.539013: step: 798/469, loss: 0.061236098408699036
2023-01-24 04:29:21.092534: step: 800/469, loss: 0.0407230518758297
2023-01-24 04:29:21.774130: step: 802/469, loss: 0.003105613635852933
2023-01-24 04:29:22.387646: step: 804/469, loss: 0.02933841198682785
2023-01-24 04:29:23.011510: step: 806/469, loss: 0.02100670151412487
2023-01-24 04:29:23.717832: step: 808/469, loss: 0.01120324619114399
2023-01-24 04:29:24.289401: step: 810/469, loss: 0.0010781317250803113
2023-01-24 04:29:24.954773: step: 812/469, loss: 0.03038143739104271
2023-01-24 04:29:25.551810: step: 814/469, loss: 0.012821342796087265
2023-01-24 04:29:26.269295: step: 816/469, loss: 0.023509899154305458
2023-01-24 04:29:26.875531: step: 818/469, loss: 0.02559499256312847
2023-01-24 04:29:27.507862: step: 820/469, loss: 0.041714951395988464
2023-01-24 04:29:28.090174: step: 822/469, loss: 0.0006077050347812474
2023-01-24 04:29:28.710721: step: 824/469, loss: 0.03724521026015282
2023-01-24 04:29:29.394661: step: 826/469, loss: 0.005431410390883684
2023-01-24 04:29:30.001410: step: 828/469, loss: 0.02351495437324047
2023-01-24 04:29:30.727340: step: 830/469, loss: 0.009260783903300762
2023-01-24 04:29:31.347776: step: 832/469, loss: 0.0022510855924338102
2023-01-24 04:29:31.994602: step: 834/469, loss: 0.04596267640590668
2023-01-24 04:29:32.659183: step: 836/469, loss: 0.03593933954834938
2023-01-24 04:29:33.273222: step: 838/469, loss: 0.042275525629520416
2023-01-24 04:29:33.922897: step: 840/469, loss: 0.0019201339455321431
2023-01-24 04:29:34.543609: step: 842/469, loss: 0.03970102220773697
2023-01-24 04:29:35.247932: step: 844/469, loss: 0.01932855136692524
2023-01-24 04:29:35.894197: step: 846/469, loss: 0.022237861528992653
2023-01-24 04:29:36.535958: step: 848/469, loss: 0.05673278123140335
2023-01-24 04:29:37.126309: step: 850/469, loss: 0.0016504751984030008
2023-01-24 04:29:37.788351: step: 852/469, loss: 0.028248030692338943
2023-01-24 04:29:38.402642: step: 854/469, loss: 0.13463911414146423
2023-01-24 04:29:39.128578: step: 856/469, loss: 0.0360083132982254
2023-01-24 04:29:39.744113: step: 858/469, loss: 0.004419809672981501
2023-01-24 04:29:40.450425: step: 860/469, loss: 0.10130942612886429
2023-01-24 04:29:41.131336: step: 862/469, loss: 0.006401387508958578
2023-01-24 04:29:41.701683: step: 864/469, loss: 0.023610521107912064
2023-01-24 04:29:42.305901: step: 866/469, loss: 0.01691424660384655
2023-01-24 04:29:42.896860: step: 868/469, loss: 0.012129467912018299
2023-01-24 04:29:43.550810: step: 870/469, loss: 0.026763200759887695
2023-01-24 04:29:44.179636: step: 872/469, loss: 0.005129052326083183
2023-01-24 04:29:44.795208: step: 874/469, loss: 0.17912110686302185
2023-01-24 04:29:45.401598: step: 876/469, loss: 0.035643480718135834
2023-01-24 04:29:46.010598: step: 878/469, loss: 0.035767074674367905
2023-01-24 04:29:46.675815: step: 880/469, loss: 0.0043825372122228146
2023-01-24 04:29:47.280242: step: 882/469, loss: 0.011669031344354153
2023-01-24 04:29:47.901876: step: 884/469, loss: 0.055026717483997345
2023-01-24 04:29:48.548375: step: 886/469, loss: 0.0007716281106695533
2023-01-24 04:29:49.238320: step: 888/469, loss: 0.04984692856669426
2023-01-24 04:29:49.862462: step: 890/469, loss: 0.008310409262776375
2023-01-24 04:29:50.446466: step: 892/469, loss: 0.02318243868649006
2023-01-24 04:29:51.058763: step: 894/469, loss: 0.0009560533799231052
2023-01-24 04:29:51.792889: step: 896/469, loss: 0.031211044639348984
2023-01-24 04:29:52.392105: step: 898/469, loss: 0.038294319063425064
2023-01-24 04:29:53.023438: step: 900/469, loss: 0.04682275652885437
2023-01-24 04:29:53.642921: step: 902/469, loss: 0.006399987731128931
2023-01-24 04:29:54.247234: step: 904/469, loss: 0.004942836239933968
2023-01-24 04:29:54.831744: step: 906/469, loss: 0.0034050687681883574
2023-01-24 04:29:55.408787: step: 908/469, loss: 0.011395362205803394
2023-01-24 04:29:56.037503: step: 910/469, loss: 0.10199712961912155
2023-01-24 04:29:56.668221: step: 912/469, loss: 0.015820639207959175
2023-01-24 04:29:57.300334: step: 914/469, loss: 0.016284726560115814
2023-01-24 04:29:57.994065: step: 916/469, loss: 0.0012991942930966616
2023-01-24 04:29:58.660425: step: 918/469, loss: 0.0005135639803484082
2023-01-24 04:29:59.242043: step: 920/469, loss: 0.0022157044149935246
2023-01-24 04:29:59.895989: step: 922/469, loss: 0.0037811293732374907
2023-01-24 04:30:00.494606: step: 924/469, loss: 0.017572833225131035
2023-01-24 04:30:01.141979: step: 926/469, loss: 0.013367361389100552
2023-01-24 04:30:01.801715: step: 928/469, loss: 0.031215744093060493
2023-01-24 04:30:02.409140: step: 930/469, loss: 0.010102222673594952
2023-01-24 04:30:03.039166: step: 932/469, loss: 0.03398963436484337
2023-01-24 04:30:03.635803: step: 934/469, loss: 0.03642801567912102
2023-01-24 04:30:04.238078: step: 936/469, loss: 0.05083474516868591
2023-01-24 04:30:04.898503: step: 938/469, loss: 0.010094666853547096
==================================================
Loss: 0.054
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3226172328687572, 'r': 0.301191040932502, 'f1': 0.31153616991448196}, 'combined': 0.22955296730540775, 'epoch': 28}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.34310103676638115, 'r': 0.26242677652030616, 'f1': 0.29738980480735583}, 'combined': 0.16221262080401225, 'epoch': 28}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32937621477162293, 'r': 0.3062511294840517, 'f1': 0.31739300931778813}, 'combined': 0.2338685331815281, 'epoch': 28}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3517148485687144, 'r': 0.26869341130363816, 'f1': 0.30464927235983036}, 'combined': 0.16617233037808926, 'epoch': 28}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32522962591850374, 'r': 0.30794987349778624, 'f1': 0.31635396361273554}, 'combined': 0.2331029205567525, 'epoch': 28}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.34421300753434675, 'r': 0.2664265364812967, 'f1': 0.30036534747195187}, 'combined': 0.1638356440756101, 'epoch': 28}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.26727642276422764, 'r': 0.31309523809523804, 'f1': 0.2883771929824561}, 'combined': 0.19225146198830406, 'epoch': 28}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2717391304347826, 'r': 0.2717391304347826, 'f1': 0.2717391304347826}, 'combined': 0.1358695652173913, 'epoch': 28}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.1724137931034483, 'f1': 0.25641025641025644}, 'combined': 0.17094017094017094, 'epoch': 28}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 04:32:50.356235: step: 2/469, loss: 0.011397200636565685
2023-01-24 04:32:50.953685: step: 4/469, loss: 0.09441093355417252
2023-01-24 04:32:51.576189: step: 6/469, loss: 0.009555439464747906
2023-01-24 04:32:52.144399: step: 8/469, loss: 0.035223279148340225
2023-01-24 04:32:52.753922: step: 10/469, loss: 0.0031088590621948242
2023-01-24 04:32:53.350259: step: 12/469, loss: 0.0036763264797627926
2023-01-24 04:32:53.939789: step: 14/469, loss: 0.010613823309540749
2023-01-24 04:32:54.624828: step: 16/469, loss: 0.003453663783147931
2023-01-24 04:32:55.243813: step: 18/469, loss: 0.004090846516191959
2023-01-24 04:32:55.854285: step: 20/469, loss: 0.016755182296037674
2023-01-24 04:32:56.468613: step: 22/469, loss: 0.01178661361336708
2023-01-24 04:32:57.054663: step: 24/469, loss: 0.0036587894428521395
2023-01-24 04:32:57.759228: step: 26/469, loss: 0.034375809133052826
2023-01-24 04:32:58.444328: step: 28/469, loss: 0.09999600052833557
2023-01-24 04:32:59.127679: step: 30/469, loss: 0.004642448853701353
2023-01-24 04:32:59.749583: step: 32/469, loss: 0.04244396463036537
2023-01-24 04:33:00.391716: step: 34/469, loss: 0.003256869036704302
2023-01-24 04:33:00.982944: step: 36/469, loss: 0.004867095500230789
2023-01-24 04:33:01.563691: step: 38/469, loss: 0.05503746494650841
2023-01-24 04:33:02.188996: step: 40/469, loss: 0.0006913591641932726
2023-01-24 04:33:02.849655: step: 42/469, loss: 0.0014958296669647098
2023-01-24 04:33:03.457500: step: 44/469, loss: 0.0031275958754122257
2023-01-24 04:33:04.094103: step: 46/469, loss: 0.024859173223376274
2023-01-24 04:33:04.704357: step: 48/469, loss: 0.08497133105993271
2023-01-24 04:33:05.262896: step: 50/469, loss: 0.03626275435090065
2023-01-24 04:33:05.813393: step: 52/469, loss: 0.032655492424964905
2023-01-24 04:33:06.515508: step: 54/469, loss: 0.009692434221506119
2023-01-24 04:33:07.206794: step: 56/469, loss: 0.005447814706712961
2023-01-24 04:33:07.840983: step: 58/469, loss: 0.0020807625260204077
2023-01-24 04:33:08.522537: step: 60/469, loss: 0.029967639595270157
2023-01-24 04:33:09.146130: step: 62/469, loss: 0.004841005429625511
2023-01-24 04:33:09.806522: step: 64/469, loss: 0.013195697218179703
2023-01-24 04:33:10.370067: step: 66/469, loss: 0.0005663955816999078
2023-01-24 04:33:10.982396: step: 68/469, loss: 0.01343944575637579
2023-01-24 04:33:11.603352: step: 70/469, loss: 0.08714127540588379
2023-01-24 04:33:12.144872: step: 72/469, loss: 0.002277157036587596
2023-01-24 04:33:12.714973: step: 74/469, loss: 0.022743044421076775
2023-01-24 04:33:13.423379: step: 76/469, loss: 0.007360660005360842
2023-01-24 04:33:14.037953: step: 78/469, loss: 0.011254142969846725
2023-01-24 04:33:14.641218: step: 80/469, loss: 0.028145454823970795
2023-01-24 04:33:15.258266: step: 82/469, loss: 0.016802730038762093
2023-01-24 04:33:15.929700: step: 84/469, loss: 0.04198892042040825
2023-01-24 04:33:16.667884: step: 86/469, loss: 0.1045631393790245
2023-01-24 04:33:17.297799: step: 88/469, loss: 0.01818367838859558
2023-01-24 04:33:17.897105: step: 90/469, loss: 0.009146373718976974
2023-01-24 04:33:18.579067: step: 92/469, loss: 0.040817372500896454
2023-01-24 04:33:19.162290: step: 94/469, loss: 0.04876149818301201
2023-01-24 04:33:19.763455: step: 96/469, loss: 0.06437990069389343
2023-01-24 04:33:20.323886: step: 98/469, loss: 0.014572279527783394
2023-01-24 04:33:20.955921: step: 100/469, loss: 0.01077072974294424
2023-01-24 04:33:21.570651: step: 102/469, loss: 0.236786887049675
2023-01-24 04:33:22.155646: step: 104/469, loss: 0.006526426877826452
2023-01-24 04:33:22.738476: step: 106/469, loss: 0.01405851449817419
2023-01-24 04:33:23.405671: step: 108/469, loss: 0.010559209622442722
2023-01-24 04:33:24.016005: step: 110/469, loss: 0.002049786504358053
2023-01-24 04:33:24.654759: step: 112/469, loss: 0.011228427290916443
2023-01-24 04:33:25.258624: step: 114/469, loss: 0.05261453241109848
2023-01-24 04:33:25.837170: step: 116/469, loss: 0.0029814711306244135
2023-01-24 04:33:26.473156: step: 118/469, loss: 0.04157707095146179
2023-01-24 04:33:27.108027: step: 120/469, loss: 0.005800592713057995
2023-01-24 04:33:27.645476: step: 122/469, loss: 0.0075937239453196526
2023-01-24 04:33:28.349119: step: 124/469, loss: 0.003897598246112466
2023-01-24 04:33:29.020741: step: 126/469, loss: 0.001507570850662887
2023-01-24 04:33:29.769755: step: 128/469, loss: 0.004470352549105883
2023-01-24 04:33:30.427641: step: 130/469, loss: 0.020746994763612747
2023-01-24 04:33:31.045247: step: 132/469, loss: 0.06914812326431274
2023-01-24 04:33:31.649767: step: 134/469, loss: 0.05455198138952255
2023-01-24 04:33:32.311987: step: 136/469, loss: 0.002455746755003929
2023-01-24 04:33:32.948272: step: 138/469, loss: 0.050567299127578735
2023-01-24 04:33:33.525645: step: 140/469, loss: 0.0071621243841946125
2023-01-24 04:33:34.177633: step: 142/469, loss: 0.029519788920879364
2023-01-24 04:33:34.838569: step: 144/469, loss: 0.046111345291137695
2023-01-24 04:33:35.516438: step: 146/469, loss: 0.03253140673041344
2023-01-24 04:33:36.112549: step: 148/469, loss: 0.01767793670296669
2023-01-24 04:33:36.793993: step: 150/469, loss: 0.0021391334012150764
2023-01-24 04:33:37.442038: step: 152/469, loss: 0.005098097492009401
2023-01-24 04:33:38.027918: step: 154/469, loss: 0.033101294189691544
2023-01-24 04:33:38.617743: step: 156/469, loss: 0.05333928018808365
2023-01-24 04:33:39.164564: step: 158/469, loss: 0.02332524210214615
2023-01-24 04:33:39.824975: step: 160/469, loss: 0.006876158528029919
2023-01-24 04:33:40.407036: step: 162/469, loss: 0.012489285320043564
2023-01-24 04:33:41.049933: step: 164/469, loss: 0.02170495130121708
2023-01-24 04:33:41.634918: step: 166/469, loss: 0.0003414927050471306
2023-01-24 04:33:42.271871: step: 168/469, loss: 2.6231969968648627e-05
2023-01-24 04:33:42.829146: step: 170/469, loss: 0.08443411439657211
2023-01-24 04:33:43.439690: step: 172/469, loss: 0.1412838250398636
2023-01-24 04:33:43.973219: step: 174/469, loss: 0.0012679558712989092
2023-01-24 04:33:44.536958: step: 176/469, loss: 0.00448417104780674
2023-01-24 04:33:45.107394: step: 178/469, loss: 0.0009893211536109447
2023-01-24 04:33:45.734491: step: 180/469, loss: 0.028251152485609055
2023-01-24 04:33:46.359448: step: 182/469, loss: 0.0014473890187218785
2023-01-24 04:33:46.992382: step: 184/469, loss: 0.03571750223636627
2023-01-24 04:33:47.697329: step: 186/469, loss: 0.012102787382900715
2023-01-24 04:33:48.292850: step: 188/469, loss: 0.21775077283382416
2023-01-24 04:33:48.946348: step: 190/469, loss: 0.07623061537742615
2023-01-24 04:33:49.650698: step: 192/469, loss: 0.5434526205062866
2023-01-24 04:33:50.282525: step: 194/469, loss: 0.021269680932164192
2023-01-24 04:33:50.935520: step: 196/469, loss: 0.2258983701467514
2023-01-24 04:33:51.549312: step: 198/469, loss: 0.017458146438002586
2023-01-24 04:33:52.183031: step: 200/469, loss: 0.0072042066603899
2023-01-24 04:33:52.761409: step: 202/469, loss: 0.000873247510753572
2023-01-24 04:33:53.333960: step: 204/469, loss: 0.00014553866640198976
2023-01-24 04:33:53.980561: step: 206/469, loss: 0.01660745218396187
2023-01-24 04:33:54.587006: step: 208/469, loss: 0.015552261844277382
2023-01-24 04:33:55.193170: step: 210/469, loss: 0.004793266765773296
2023-01-24 04:33:55.826647: step: 212/469, loss: 0.0006335374200716615
2023-01-24 04:33:56.489661: step: 214/469, loss: 0.027401519939303398
2023-01-24 04:33:57.108261: step: 216/469, loss: 0.043808966875076294
2023-01-24 04:33:57.749783: step: 218/469, loss: 2.8400772862369195e-05
2023-01-24 04:33:58.362708: step: 220/469, loss: 0.023992571979761124
2023-01-24 04:33:58.990628: step: 222/469, loss: 0.002939148573204875
2023-01-24 04:33:59.709827: step: 224/469, loss: 0.00699267303571105
2023-01-24 04:34:00.303392: step: 226/469, loss: 0.02978898026049137
2023-01-24 04:34:00.918871: step: 228/469, loss: 0.013289243914186954
2023-01-24 04:34:01.548788: step: 230/469, loss: 0.02610580436885357
2023-01-24 04:34:02.171689: step: 232/469, loss: 0.007343559060245752
2023-01-24 04:34:02.825919: step: 234/469, loss: 0.001022710232064128
2023-01-24 04:34:03.463000: step: 236/469, loss: 0.01243559829890728
2023-01-24 04:34:04.110404: step: 238/469, loss: 0.06458567827939987
2023-01-24 04:34:04.751625: step: 240/469, loss: 0.045231886208057404
2023-01-24 04:34:05.358177: step: 242/469, loss: 0.032268546521663666
2023-01-24 04:34:05.928679: step: 244/469, loss: 0.011744252406060696
2023-01-24 04:34:06.611068: step: 246/469, loss: 0.00015904102474451065
2023-01-24 04:34:07.254400: step: 248/469, loss: 0.16161437332630157
2023-01-24 04:34:07.905838: step: 250/469, loss: 0.20700424909591675
2023-01-24 04:34:08.536167: step: 252/469, loss: 0.014303024858236313
2023-01-24 04:34:09.184674: step: 254/469, loss: 0.012318290770053864
2023-01-24 04:34:09.752915: step: 256/469, loss: 0.002054626354947686
2023-01-24 04:34:10.353724: step: 258/469, loss: 0.20263001322746277
2023-01-24 04:34:10.972128: step: 260/469, loss: 0.0022341187577694654
2023-01-24 04:34:11.581252: step: 262/469, loss: 0.014170438051223755
2023-01-24 04:34:12.183584: step: 264/469, loss: 0.018478937447071075
2023-01-24 04:34:12.761118: step: 266/469, loss: 0.022423433139920235
2023-01-24 04:34:13.403398: step: 268/469, loss: 0.0031005688942968845
2023-01-24 04:34:13.983907: step: 270/469, loss: 0.004753394518047571
2023-01-24 04:34:14.656424: step: 272/469, loss: 0.005259358789771795
2023-01-24 04:34:15.272768: step: 274/469, loss: 0.15629994869232178
2023-01-24 04:34:15.912426: step: 276/469, loss: 0.07923565059900284
2023-01-24 04:34:16.563597: step: 278/469, loss: 0.008050136268138885
2023-01-24 04:34:17.198667: step: 280/469, loss: 0.0004991943133063614
2023-01-24 04:34:17.875709: step: 282/469, loss: 0.22852376103401184
2023-01-24 04:34:18.478654: step: 284/469, loss: 0.016664106398820877
2023-01-24 04:34:19.103354: step: 286/469, loss: 0.02770352177321911
2023-01-24 04:34:19.763228: step: 288/469, loss: 0.04874853044748306
2023-01-24 04:34:20.393959: step: 290/469, loss: 0.01245155930519104
2023-01-24 04:34:21.043713: step: 292/469, loss: 0.024859843775629997
2023-01-24 04:34:21.694398: step: 294/469, loss: 0.00643170066177845
2023-01-24 04:34:22.378007: step: 296/469, loss: 0.08221544325351715
2023-01-24 04:34:22.916911: step: 298/469, loss: 0.00019639221136458218
2023-01-24 04:34:23.552346: step: 300/469, loss: 0.0065299165435135365
2023-01-24 04:34:24.146985: step: 302/469, loss: 0.002853293204680085
2023-01-24 04:34:24.761461: step: 304/469, loss: 0.014048060402274132
2023-01-24 04:34:25.309165: step: 306/469, loss: 0.0005820858059450984
2023-01-24 04:34:25.928795: step: 308/469, loss: 0.002236904576420784
2023-01-24 04:34:26.560788: step: 310/469, loss: 0.009890853427350521
2023-01-24 04:34:27.201498: step: 312/469, loss: 0.03145544230937958
2023-01-24 04:34:27.937157: step: 314/469, loss: 0.010448926128447056
2023-01-24 04:34:28.599951: step: 316/469, loss: 0.001130950404331088
2023-01-24 04:34:29.270305: step: 318/469, loss: 0.013824332505464554
2023-01-24 04:34:29.892662: step: 320/469, loss: 0.004797209519892931
2023-01-24 04:34:30.494139: step: 322/469, loss: 0.05765450373291969
2023-01-24 04:34:31.079625: step: 324/469, loss: 0.0034388245549052954
2023-01-24 04:34:31.642180: step: 326/469, loss: 0.000766948563978076
2023-01-24 04:34:32.252726: step: 328/469, loss: 0.022361118346452713
2023-01-24 04:34:32.870448: step: 330/469, loss: 0.005188967566937208
2023-01-24 04:34:33.485742: step: 332/469, loss: 0.00784236192703247
2023-01-24 04:34:34.027677: step: 334/469, loss: 0.012940814718604088
2023-01-24 04:34:34.670276: step: 336/469, loss: 0.0010617084335535765
2023-01-24 04:34:35.283712: step: 338/469, loss: 0.040706247091293335
2023-01-24 04:34:35.959754: step: 340/469, loss: 0.02976055070757866
2023-01-24 04:34:36.621305: step: 342/469, loss: 0.06347508728504181
2023-01-24 04:34:37.242995: step: 344/469, loss: 0.017345333471894264
2023-01-24 04:34:37.860867: step: 346/469, loss: 0.003586218459531665
2023-01-24 04:34:38.511079: step: 348/469, loss: 0.13524411618709564
2023-01-24 04:34:39.177357: step: 350/469, loss: 0.004465170670300722
2023-01-24 04:34:39.870272: step: 352/469, loss: 0.0479794479906559
2023-01-24 04:34:40.459143: step: 354/469, loss: 0.0004911953583359718
2023-01-24 04:34:41.061889: step: 356/469, loss: 0.01962626911699772
2023-01-24 04:34:41.679853: step: 358/469, loss: 0.01667158678174019
2023-01-24 04:34:42.320229: step: 360/469, loss: 0.005676074884831905
2023-01-24 04:34:42.977099: step: 362/469, loss: 0.05340810865163803
2023-01-24 04:34:43.610366: step: 364/469, loss: 0.017531901597976685
2023-01-24 04:34:44.171692: step: 366/469, loss: 0.07758454233407974
2023-01-24 04:34:44.896282: step: 368/469, loss: 0.4954358637332916
2023-01-24 04:34:45.535423: step: 370/469, loss: 0.004969179630279541
2023-01-24 04:34:46.186883: step: 372/469, loss: 0.004571582190692425
2023-01-24 04:34:46.826107: step: 374/469, loss: 0.024722153320908546
2023-01-24 04:34:47.416348: step: 376/469, loss: 0.02770611271262169
2023-01-24 04:34:48.034766: step: 378/469, loss: 0.0033734701573848724
2023-01-24 04:34:48.677140: step: 380/469, loss: 0.025060933083295822
2023-01-24 04:34:49.300409: step: 382/469, loss: 0.0038945425767451525
2023-01-24 04:34:49.942252: step: 384/469, loss: 0.05608239024877548
2023-01-24 04:34:50.525450: step: 386/469, loss: 0.20016659796237946
2023-01-24 04:34:51.177249: step: 388/469, loss: 0.0029896865598857403
2023-01-24 04:34:51.907251: step: 390/469, loss: 0.019879590719938278
2023-01-24 04:34:52.541541: step: 392/469, loss: 0.041897982358932495
2023-01-24 04:34:53.152706: step: 394/469, loss: 0.014243301004171371
2023-01-24 04:34:53.837071: step: 396/469, loss: 0.014828565530478954
2023-01-24 04:34:54.455464: step: 398/469, loss: 0.016474423930048943
2023-01-24 04:34:55.058066: step: 400/469, loss: 0.006784925237298012
2023-01-24 04:34:55.678440: step: 402/469, loss: 0.08661936223506927
2023-01-24 04:34:56.341612: step: 404/469, loss: 0.0553220696747303
2023-01-24 04:34:56.907991: step: 406/469, loss: 0.03310636803507805
2023-01-24 04:34:57.509009: step: 408/469, loss: 0.008349345996975899
2023-01-24 04:34:58.066965: step: 410/469, loss: 0.017226219177246094
2023-01-24 04:34:58.731438: step: 412/469, loss: 0.03554794192314148
2023-01-24 04:34:59.357338: step: 414/469, loss: 0.04668092727661133
2023-01-24 04:34:59.946209: step: 416/469, loss: 0.0037377693224698305
2023-01-24 04:35:00.511753: step: 418/469, loss: 0.013941371813416481
2023-01-24 04:35:01.109189: step: 420/469, loss: 0.0028607724234461784
2023-01-24 04:35:01.795433: step: 422/469, loss: 0.04367578402161598
2023-01-24 04:35:02.423786: step: 424/469, loss: 0.08808927983045578
2023-01-24 04:35:03.069771: step: 426/469, loss: 0.1437286138534546
2023-01-24 04:35:03.699691: step: 428/469, loss: 0.01248926855623722
2023-01-24 04:35:04.302199: step: 430/469, loss: 0.02520914562046528
2023-01-24 04:35:04.877159: step: 432/469, loss: 0.009373209439218044
2023-01-24 04:35:05.470686: step: 434/469, loss: 0.037377070635557175
2023-01-24 04:35:06.095181: step: 436/469, loss: 0.0019492616411298513
2023-01-24 04:35:06.867202: step: 438/469, loss: 0.01320639718323946
2023-01-24 04:35:07.522570: step: 440/469, loss: 0.020629139617085457
2023-01-24 04:35:08.124097: step: 442/469, loss: 0.04263303801417351
2023-01-24 04:35:08.805276: step: 444/469, loss: 0.017304904758930206
2023-01-24 04:35:09.420711: step: 446/469, loss: 0.0016037187306210399
2023-01-24 04:35:10.054206: step: 448/469, loss: 0.0705556645989418
2023-01-24 04:35:10.668158: step: 450/469, loss: 1.679777979850769
2023-01-24 04:35:11.284660: step: 452/469, loss: 0.021190904080867767
2023-01-24 04:35:11.907001: step: 454/469, loss: 0.005444503854960203
2023-01-24 04:35:12.488244: step: 456/469, loss: 0.007108920253813267
2023-01-24 04:35:13.161934: step: 458/469, loss: 0.045692723244428635
2023-01-24 04:35:13.717761: step: 460/469, loss: 0.023028597235679626
2023-01-24 04:35:14.365976: step: 462/469, loss: 0.049323033541440964
2023-01-24 04:35:14.930704: step: 464/469, loss: 0.0716588944196701
2023-01-24 04:35:15.512092: step: 466/469, loss: 0.3417256474494934
2023-01-24 04:35:16.117013: step: 468/469, loss: 0.14080263674259186
2023-01-24 04:35:16.768476: step: 470/469, loss: 0.08692007511854172
2023-01-24 04:35:17.385360: step: 472/469, loss: 0.10216516256332397
2023-01-24 04:35:17.944569: step: 474/469, loss: 0.00489381980150938
2023-01-24 04:35:18.615949: step: 476/469, loss: 0.07432972639799118
2023-01-24 04:35:19.293415: step: 478/469, loss: 0.03337600454688072
2023-01-24 04:35:19.955064: step: 480/469, loss: 0.005669097416102886
2023-01-24 04:35:20.543311: step: 482/469, loss: 0.271613210439682
2023-01-24 04:35:21.150226: step: 484/469, loss: 0.015623623505234718
2023-01-24 04:35:21.775299: step: 486/469, loss: 0.01844528317451477
2023-01-24 04:35:22.369815: step: 488/469, loss: 0.006291560363024473
2023-01-24 04:35:22.937535: step: 490/469, loss: 0.01965421251952648
2023-01-24 04:35:23.594377: step: 492/469, loss: 0.005876512266695499
2023-01-24 04:35:24.234760: step: 494/469, loss: 0.0049910470843315125
2023-01-24 04:35:24.880280: step: 496/469, loss: 1.1827524900436401
2023-01-24 04:35:25.487676: step: 498/469, loss: 0.020476648584008217
2023-01-24 04:35:26.064099: step: 500/469, loss: 0.01108358334749937
2023-01-24 04:35:26.767430: step: 502/469, loss: 0.02751188538968563
2023-01-24 04:35:27.444429: step: 504/469, loss: 0.15873494744300842
2023-01-24 04:35:27.992413: step: 506/469, loss: 0.0060341982170939445
2023-01-24 04:35:28.653010: step: 508/469, loss: 0.027051256969571114
2023-01-24 04:35:29.185940: step: 510/469, loss: 0.012410561554133892
2023-01-24 04:35:29.843282: step: 512/469, loss: 0.4625912308692932
2023-01-24 04:35:30.537378: step: 514/469, loss: 0.036333683878183365
2023-01-24 04:35:31.166256: step: 516/469, loss: 0.009291158989071846
2023-01-24 04:35:31.808566: step: 518/469, loss: 0.013837597332894802
2023-01-24 04:35:32.385926: step: 520/469, loss: 0.02988453023135662
2023-01-24 04:35:33.006775: step: 522/469, loss: 0.022480791434645653
2023-01-24 04:35:33.594325: step: 524/469, loss: 0.03669856861233711
2023-01-24 04:35:34.211360: step: 526/469, loss: 0.011793060228228569
2023-01-24 04:35:34.852524: step: 528/469, loss: 0.008280466310679913
2023-01-24 04:35:35.486169: step: 530/469, loss: 0.00646325433626771
2023-01-24 04:35:36.079480: step: 532/469, loss: 0.05213792249560356
2023-01-24 04:35:36.673325: step: 534/469, loss: 0.0025119639467447996
2023-01-24 04:35:37.251059: step: 536/469, loss: 0.0056335278786718845
2023-01-24 04:35:37.813596: step: 538/469, loss: 0.0007014645962044597
2023-01-24 04:35:38.484691: step: 540/469, loss: 0.01949908398091793
2023-01-24 04:35:39.057190: step: 542/469, loss: 0.006616770289838314
2023-01-24 04:35:39.622953: step: 544/469, loss: 0.0036147721111774445
2023-01-24 04:35:40.222153: step: 546/469, loss: 2.7988462448120117
2023-01-24 04:35:40.816722: step: 548/469, loss: 0.2557152509689331
2023-01-24 04:35:41.482585: step: 550/469, loss: 0.07260492444038391
2023-01-24 04:35:42.097975: step: 552/469, loss: 0.0028305102605372667
2023-01-24 04:35:42.688746: step: 554/469, loss: 0.001115532242693007
2023-01-24 04:35:43.294076: step: 556/469, loss: 0.010525760240852833
2023-01-24 04:35:43.878915: step: 558/469, loss: 0.0026127370074391365
2023-01-24 04:35:44.525979: step: 560/469, loss: 0.08996759355068207
2023-01-24 04:35:45.120484: step: 562/469, loss: 0.007148308679461479
2023-01-24 04:35:45.745017: step: 564/469, loss: 0.025730041787028313
2023-01-24 04:35:46.439301: step: 566/469, loss: 0.07166583836078644
2023-01-24 04:35:47.246291: step: 568/469, loss: 0.019982781261205673
2023-01-24 04:35:47.847980: step: 570/469, loss: 0.025221683084964752
2023-01-24 04:35:48.546368: step: 572/469, loss: 0.020528538152575493
2023-01-24 04:35:49.166949: step: 574/469, loss: 0.02145366370677948
2023-01-24 04:35:49.754783: step: 576/469, loss: 0.012887056916952133
2023-01-24 04:35:50.372730: step: 578/469, loss: 0.018775420263409615
2023-01-24 04:35:50.961379: step: 580/469, loss: 1.0892153978347778
2023-01-24 04:35:51.602050: step: 582/469, loss: 0.002186531899496913
2023-01-24 04:35:52.155366: step: 584/469, loss: 0.00845075398683548
2023-01-24 04:35:52.725357: step: 586/469, loss: 0.0008586874464526772
2023-01-24 04:35:53.353348: step: 588/469, loss: 0.0210244283080101
2023-01-24 04:35:53.923983: step: 590/469, loss: 0.0013312355149537325
2023-01-24 04:35:54.564213: step: 592/469, loss: 0.0015349240275099874
2023-01-24 04:35:55.169185: step: 594/469, loss: 0.04331725090742111
2023-01-24 04:35:55.814750: step: 596/469, loss: 0.07671844214200974
2023-01-24 04:35:56.464437: step: 598/469, loss: 0.03747640177607536
2023-01-24 04:35:57.045399: step: 600/469, loss: 0.0502481535077095
2023-01-24 04:35:57.702203: step: 602/469, loss: 0.02473577857017517
2023-01-24 04:35:58.402506: step: 604/469, loss: 0.019558290019631386
2023-01-24 04:35:59.059760: step: 606/469, loss: 0.03300067037343979
2023-01-24 04:35:59.728527: step: 608/469, loss: 0.007178252562880516
2023-01-24 04:36:00.354100: step: 610/469, loss: 0.016332488507032394
2023-01-24 04:36:00.925610: step: 612/469, loss: 7.859564902901184e-06
2023-01-24 04:36:01.530626: step: 614/469, loss: 0.004172973334789276
2023-01-24 04:36:02.190358: step: 616/469, loss: 0.013322818093001842
2023-01-24 04:36:02.742956: step: 618/469, loss: 0.09358158707618713
2023-01-24 04:36:03.325504: step: 620/469, loss: 0.0145272146910429
2023-01-24 04:36:03.994165: step: 622/469, loss: 0.004783676005899906
2023-01-24 04:36:04.606307: step: 624/469, loss: 0.01821512170135975
2023-01-24 04:36:05.219842: step: 626/469, loss: 0.01578216254711151
2023-01-24 04:36:05.956130: step: 628/469, loss: 0.002338086487725377
2023-01-24 04:36:06.658089: step: 630/469, loss: 0.06430988758802414
2023-01-24 04:36:07.242361: step: 632/469, loss: 0.019697776064276695
2023-01-24 04:36:07.852823: step: 634/469, loss: 0.0008986774482764304
2023-01-24 04:36:08.466514: step: 636/469, loss: 0.002800026908516884
2023-01-24 04:36:09.162645: step: 638/469, loss: 0.013280363753437996
2023-01-24 04:36:09.816080: step: 640/469, loss: 0.023753050714731216
2023-01-24 04:36:10.456972: step: 642/469, loss: 0.013031180016696453
2023-01-24 04:36:11.049573: step: 644/469, loss: 0.0015544953057542443
2023-01-24 04:36:11.622985: step: 646/469, loss: 0.007948714308440685
2023-01-24 04:36:12.264111: step: 648/469, loss: 0.029600001871585846
2023-01-24 04:36:12.872988: step: 650/469, loss: 0.05922909826040268
2023-01-24 04:36:13.498282: step: 652/469, loss: 0.013812258839607239
2023-01-24 04:36:14.116702: step: 654/469, loss: 0.15025420486927032
2023-01-24 04:36:14.683620: step: 656/469, loss: 0.585685670375824
2023-01-24 04:36:15.359442: step: 658/469, loss: 1.0335520505905151
2023-01-24 04:36:15.974534: step: 660/469, loss: 0.0057723610661923885
2023-01-24 04:36:16.671578: step: 662/469, loss: 0.07760661095380783
2023-01-24 04:36:17.296734: step: 664/469, loss: 0.006530494894832373
2023-01-24 04:36:17.965850: step: 666/469, loss: 0.0018100393936038017
2023-01-24 04:36:18.639267: step: 668/469, loss: 0.023965319618582726
2023-01-24 04:36:19.254026: step: 670/469, loss: 0.018816273659467697
2023-01-24 04:36:19.982377: step: 672/469, loss: 0.07420765608549118
2023-01-24 04:36:20.657343: step: 674/469, loss: 0.002655893098562956
2023-01-24 04:36:21.340954: step: 676/469, loss: 0.020108599215745926
2023-01-24 04:36:21.935916: step: 678/469, loss: 0.02379756048321724
2023-01-24 04:36:22.590483: step: 680/469, loss: 0.0020835783798247576
2023-01-24 04:36:23.228784: step: 682/469, loss: 0.039586957544088364
2023-01-24 04:36:23.889218: step: 684/469, loss: 0.04710690677165985
2023-01-24 04:36:24.508231: step: 686/469, loss: 0.003648559795692563
2023-01-24 04:36:25.128056: step: 688/469, loss: 0.023693419992923737
2023-01-24 04:36:25.851973: step: 690/469, loss: 0.04521752521395683
2023-01-24 04:36:26.469080: step: 692/469, loss: 0.005997614003717899
2023-01-24 04:36:27.102646: step: 694/469, loss: 0.038455672562122345
2023-01-24 04:36:27.692781: step: 696/469, loss: 0.01075368095189333
2023-01-24 04:36:28.292214: step: 698/469, loss: 0.01868843100965023
2023-01-24 04:36:28.916954: step: 700/469, loss: 0.0031358441337943077
2023-01-24 04:36:29.562396: step: 702/469, loss: 0.10962771624326706
2023-01-24 04:36:30.121609: step: 704/469, loss: 0.001154505298472941
2023-01-24 04:36:30.723696: step: 706/469, loss: 6.791084289550781
2023-01-24 04:36:31.252877: step: 708/469, loss: 0.0009272179449908435
2023-01-24 04:36:31.781465: step: 710/469, loss: 0.0019114745082333684
2023-01-24 04:36:32.377839: step: 712/469, loss: 0.04137321561574936
2023-01-24 04:36:33.000253: step: 714/469, loss: 0.006473363842815161
2023-01-24 04:36:33.598577: step: 716/469, loss: 0.004562808200716972
2023-01-24 04:36:34.306824: step: 718/469, loss: 0.04581043869256973
2023-01-24 04:36:34.907108: step: 720/469, loss: 0.008559256792068481
2023-01-24 04:36:35.551997: step: 722/469, loss: 0.010527494363486767
2023-01-24 04:36:36.186591: step: 724/469, loss: 0.004464718513190746
2023-01-24 04:36:36.766591: step: 726/469, loss: 0.04944245144724846
2023-01-24 04:36:37.382321: step: 728/469, loss: 0.005690377205610275
2023-01-24 04:36:38.065610: step: 730/469, loss: 0.2028210610151291
2023-01-24 04:36:38.721839: step: 732/469, loss: 0.012636340223252773
2023-01-24 04:36:39.431198: step: 734/469, loss: 0.047626569867134094
2023-01-24 04:36:40.071547: step: 736/469, loss: 0.05612828582525253
2023-01-24 04:36:40.694398: step: 738/469, loss: 0.04176720604300499
2023-01-24 04:36:41.370374: step: 740/469, loss: 0.00456358352676034
2023-01-24 04:36:42.033670: step: 742/469, loss: 0.03201710805296898
2023-01-24 04:36:42.609613: step: 744/469, loss: 0.007990165613591671
2023-01-24 04:36:43.327694: step: 746/469, loss: 0.1465800553560257
2023-01-24 04:36:43.991371: step: 748/469, loss: 0.06553951650857925
2023-01-24 04:36:44.602988: step: 750/469, loss: 0.006729306187480688
2023-01-24 04:36:45.245584: step: 752/469, loss: 0.00826718844473362
2023-01-24 04:36:45.888282: step: 754/469, loss: 0.002610917203128338
2023-01-24 04:36:46.570777: step: 756/469, loss: 0.03906663507223129
2023-01-24 04:36:47.161372: step: 758/469, loss: 0.005207396112382412
2023-01-24 04:36:47.844273: step: 760/469, loss: 0.006388232111930847
2023-01-24 04:36:48.504637: step: 762/469, loss: 0.013333003968000412
2023-01-24 04:36:49.107388: step: 764/469, loss: 0.005317576229572296
2023-01-24 04:36:49.698976: step: 766/469, loss: 0.02116086333990097
2023-01-24 04:36:50.319795: step: 768/469, loss: 0.008979404345154762
2023-01-24 04:36:50.956491: step: 770/469, loss: 0.02597903087735176
2023-01-24 04:36:51.551906: step: 772/469, loss: 0.6848384141921997
2023-01-24 04:36:52.213035: step: 774/469, loss: 0.0012179943732917309
2023-01-24 04:36:52.865190: step: 776/469, loss: 0.0016474841395393014
2023-01-24 04:36:53.456738: step: 778/469, loss: 0.0005874739727005363
2023-01-24 04:36:54.037773: step: 780/469, loss: 0.052955713123083115
2023-01-24 04:36:54.599928: step: 782/469, loss: 0.04274573177099228
2023-01-24 04:36:55.251812: step: 784/469, loss: 0.012886938638985157
2023-01-24 04:36:55.885389: step: 786/469, loss: 0.009848181158304214
2023-01-24 04:36:56.459089: step: 788/469, loss: 0.05092054232954979
2023-01-24 04:36:57.085888: step: 790/469, loss: 0.00875928346067667
2023-01-24 04:36:57.705586: step: 792/469, loss: 0.022496996447443962
2023-01-24 04:36:58.353389: step: 794/469, loss: 0.02337433211505413
2023-01-24 04:36:58.962546: step: 796/469, loss: 0.03319117799401283
2023-01-24 04:36:59.573548: step: 798/469, loss: 0.0005383278476074338
2023-01-24 04:37:00.256502: step: 800/469, loss: 0.031798552721738815
2023-01-24 04:37:00.934952: step: 802/469, loss: 0.08176372200250626
2023-01-24 04:37:01.499575: step: 804/469, loss: 0.0004847792733926326
2023-01-24 04:37:02.056466: step: 806/469, loss: 0.015916161239147186
2023-01-24 04:37:02.701751: step: 808/469, loss: 0.029505586251616478
2023-01-24 04:37:03.352876: step: 810/469, loss: 0.5855922698974609
2023-01-24 04:37:03.937074: step: 812/469, loss: 0.006037293933331966
2023-01-24 04:37:04.489676: step: 814/469, loss: 0.028843944892287254
2023-01-24 04:37:05.123888: step: 816/469, loss: 0.07339662313461304
2023-01-24 04:37:05.768924: step: 818/469, loss: 0.011284264735877514
2023-01-24 04:37:06.359619: step: 820/469, loss: 0.01086319237947464
2023-01-24 04:37:06.938111: step: 822/469, loss: 0.002898276085034013
2023-01-24 04:37:07.551191: step: 824/469, loss: 0.0077510373666882515
2023-01-24 04:37:08.186334: step: 826/469, loss: 0.025537706911563873
2023-01-24 04:37:08.801049: step: 828/469, loss: 0.003802065970376134
2023-01-24 04:37:09.389413: step: 830/469, loss: 0.07798043638467789
2023-01-24 04:37:10.039525: step: 832/469, loss: 0.0394209548830986
2023-01-24 04:37:10.693919: step: 834/469, loss: 0.2973405718803406
2023-01-24 04:37:11.292958: step: 836/469, loss: 0.0050156936049461365
2023-01-24 04:37:11.938203: step: 838/469, loss: 0.003936249762773514
2023-01-24 04:37:12.597044: step: 840/469, loss: 0.004344089888036251
2023-01-24 04:37:13.352428: step: 842/469, loss: 0.031523656100034714
2023-01-24 04:37:14.068757: step: 844/469, loss: 0.0013185730203986168
2023-01-24 04:37:14.683324: step: 846/469, loss: 0.009157379157841206
2023-01-24 04:37:15.354638: step: 848/469, loss: 0.1362275928258896
2023-01-24 04:37:15.918917: step: 850/469, loss: 0.002761450130492449
2023-01-24 04:37:16.510782: step: 852/469, loss: 0.012748624198138714
2023-01-24 04:37:17.151592: step: 854/469, loss: 0.3057138919830322
2023-01-24 04:37:17.812635: step: 856/469, loss: 0.03490421175956726
2023-01-24 04:37:18.391645: step: 858/469, loss: 0.013592280447483063
2023-01-24 04:37:18.999901: step: 860/469, loss: 0.013455227017402649
2023-01-24 04:37:19.576053: step: 862/469, loss: 6.178225885378197e-05
2023-01-24 04:37:20.262535: step: 864/469, loss: 0.1289229542016983
2023-01-24 04:37:20.908788: step: 866/469, loss: 0.014098123647272587
2023-01-24 04:37:21.503966: step: 868/469, loss: 0.015085606835782528
2023-01-24 04:37:22.114224: step: 870/469, loss: 0.0155626917257905
2023-01-24 04:37:22.759081: step: 872/469, loss: 0.9027851223945618
2023-01-24 04:37:23.351491: step: 874/469, loss: 0.04441506788134575
2023-01-24 04:37:23.993748: step: 876/469, loss: 0.004249469377100468
2023-01-24 04:37:24.605986: step: 878/469, loss: 0.002969399094581604
2023-01-24 04:37:25.182948: step: 880/469, loss: 0.015422014519572258
2023-01-24 04:37:25.815490: step: 882/469, loss: 0.010858754627406597
2023-01-24 04:37:26.508173: step: 884/469, loss: 0.0024042685981839895
2023-01-24 04:37:27.096846: step: 886/469, loss: 0.010281093418598175
2023-01-24 04:37:27.723087: step: 888/469, loss: 0.011785667389631271
2023-01-24 04:37:28.334442: step: 890/469, loss: 0.4762597978115082
2023-01-24 04:37:28.926537: step: 892/469, loss: 0.011760367080569267
2023-01-24 04:37:29.539222: step: 894/469, loss: 0.1458122581243515
2023-01-24 04:37:30.316890: step: 896/469, loss: 0.08357082307338715
2023-01-24 04:37:30.982096: step: 898/469, loss: 0.01763766258955002
2023-01-24 04:37:31.647719: step: 900/469, loss: 0.017989760264754295
2023-01-24 04:37:32.322642: step: 902/469, loss: 0.055756352841854095
2023-01-24 04:37:33.010557: step: 904/469, loss: 0.009300785139203072
2023-01-24 04:37:33.657821: step: 906/469, loss: 0.1509122997522354
2023-01-24 04:37:34.357571: step: 908/469, loss: 0.008779053576290607
2023-01-24 04:37:35.031181: step: 910/469, loss: 0.005239448044449091
2023-01-24 04:37:35.648531: step: 912/469, loss: 0.15467186272144318
2023-01-24 04:37:36.288806: step: 914/469, loss: 0.007002062164247036
2023-01-24 04:37:36.943158: step: 916/469, loss: 0.0002871248871088028
2023-01-24 04:37:37.582471: step: 918/469, loss: 0.009084869176149368
2023-01-24 04:37:38.203958: step: 920/469, loss: 0.008464104495942593
2023-01-24 04:37:38.779406: step: 922/469, loss: 0.08195966482162476
2023-01-24 04:37:39.393963: step: 924/469, loss: 0.028196517378091812
2023-01-24 04:37:40.049926: step: 926/469, loss: 0.0013524334644898772
2023-01-24 04:37:40.679267: step: 928/469, loss: 0.004344878252595663
2023-01-24 04:37:41.314035: step: 930/469, loss: 0.015616672113537788
2023-01-24 04:37:41.907875: step: 932/469, loss: 0.01837651990354061
2023-01-24 04:37:42.443446: step: 934/469, loss: 0.0018815413350239396
2023-01-24 04:37:43.067831: step: 936/469, loss: 0.003958356566727161
2023-01-24 04:37:43.704817: step: 938/469, loss: 0.0240335613489151
==================================================
Loss: 0.072
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32109375, 'r': 0.30708017077798866, 'f1': 0.31393064985451025}, 'combined': 0.2313173209454286, 'epoch': 29}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3531430266126457, 'r': 0.26719970998047393, 'f1': 0.30421800313401876}, 'combined': 0.16593709261855566, 'epoch': 29}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33372995991983967, 'r': 0.31599857685009486, 'f1': 0.3246223196881091}, 'combined': 0.23919539345439617, 'epoch': 29}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3565072864094151, 'r': 0.27431164489507603, 'f1': 0.3100544238576195}, 'combined': 0.1691205948314288, 'epoch': 29}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32198937908496733, 'r': 0.3116026249209361, 'f1': 0.3167108646737384}, 'combined': 0.23336590028591248, 'epoch': 29}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3520103910463079, 'r': 0.27407213429131566, 'f1': 0.3081901674695556}, 'combined': 0.16810372771066667, 'epoch': 29}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2881944444444444, 'r': 0.29642857142857143, 'f1': 0.2922535211267605}, 'combined': 0.19483568075117366, 'epoch': 29}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.29, 'r': 0.31521739130434784, 'f1': 0.3020833333333333}, 'combined': 0.15104166666666666, 'epoch': 29}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'epoch': 29}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 04:40:29.506020: step: 2/469, loss: 0.030204234644770622
2023-01-24 04:40:30.110285: step: 4/469, loss: 0.000214090890949592
2023-01-24 04:40:30.659117: step: 6/469, loss: 0.02446596510708332
2023-01-24 04:40:31.246171: step: 8/469, loss: 0.016314657405018806
2023-01-24 04:40:31.880050: step: 10/469, loss: 0.02458830736577511
2023-01-24 04:40:32.487510: step: 12/469, loss: 0.12970979511737823
2023-01-24 04:40:33.026142: step: 14/469, loss: 0.0018961385358124971
2023-01-24 04:40:33.626837: step: 16/469, loss: 0.01764444075524807
2023-01-24 04:40:34.241143: step: 18/469, loss: 1.2081280829079333e-06
2023-01-24 04:40:34.808675: step: 20/469, loss: 0.020217763260006905
2023-01-24 04:40:35.412499: step: 22/469, loss: 0.0008690494578331709
2023-01-24 04:40:36.048997: step: 24/469, loss: 0.04564937949180603
2023-01-24 04:40:36.670914: step: 26/469, loss: 0.01216245535761118
2023-01-24 04:40:37.241564: step: 28/469, loss: 0.040008775889873505
2023-01-24 04:40:37.852467: step: 30/469, loss: 0.011112927459180355
2023-01-24 04:40:38.516581: step: 32/469, loss: 0.011521357111632824
2023-01-24 04:40:39.082841: step: 34/469, loss: 0.004028141498565674
2023-01-24 04:40:39.735641: step: 36/469, loss: 0.0675557479262352
2023-01-24 04:40:40.333333: step: 38/469, loss: 0.0011803836096078157
2023-01-24 04:40:40.952346: step: 40/469, loss: 0.023845933377742767
2023-01-24 04:40:41.581870: step: 42/469, loss: 0.02379044145345688
2023-01-24 04:40:42.199059: step: 44/469, loss: 0.005500413477420807
2023-01-24 04:40:42.793141: step: 46/469, loss: 0.027780411764979362
2023-01-24 04:40:43.458200: step: 48/469, loss: 0.005657805595546961
2023-01-24 04:40:44.115616: step: 50/469, loss: 0.004490879364311695
2023-01-24 04:40:44.704715: step: 52/469, loss: 0.00833278987556696
2023-01-24 04:40:45.311006: step: 54/469, loss: 0.024658534675836563
2023-01-24 04:40:45.916731: step: 56/469, loss: 0.03944602236151695
2023-01-24 04:40:46.508856: step: 58/469, loss: 0.009471878409385681
2023-01-24 04:40:47.109916: step: 60/469, loss: 0.021279895678162575
2023-01-24 04:40:47.748141: step: 62/469, loss: 0.0003297892981208861
2023-01-24 04:40:48.451626: step: 64/469, loss: 0.25596874952316284
2023-01-24 04:40:49.034013: step: 66/469, loss: 0.0013570016017183661
2023-01-24 04:40:49.647472: step: 68/469, loss: 0.005010408349335194
2023-01-24 04:40:50.283755: step: 70/469, loss: 0.00613814452663064
2023-01-24 04:40:50.898445: step: 72/469, loss: 0.04745108261704445
2023-01-24 04:40:51.580031: step: 74/469, loss: 0.07794447988271713
2023-01-24 04:40:52.231126: step: 76/469, loss: 0.0014230242231860757
2023-01-24 04:40:52.822536: step: 78/469, loss: 0.01976405270397663
2023-01-24 04:40:53.378805: step: 80/469, loss: 0.007515359669923782
2023-01-24 04:40:53.998028: step: 82/469, loss: 0.20509494841098785
2023-01-24 04:40:54.712654: step: 84/469, loss: 0.02520422264933586
2023-01-24 04:40:55.292577: step: 86/469, loss: 0.002537622582167387
2023-01-24 04:40:55.867323: step: 88/469, loss: 0.017039865255355835
2023-01-24 04:40:56.587749: step: 90/469, loss: 0.012986699119210243
2023-01-24 04:40:57.219677: step: 92/469, loss: 0.022357499226927757
2023-01-24 04:40:57.857174: step: 94/469, loss: 0.004211435094475746
2023-01-24 04:40:58.501620: step: 96/469, loss: 0.041084833443164825
2023-01-24 04:40:59.129235: step: 98/469, loss: 0.07905570417642593
2023-01-24 04:40:59.780690: step: 100/469, loss: 0.01296793483197689
2023-01-24 04:41:00.350301: step: 102/469, loss: 0.015302873216569424
2023-01-24 04:41:01.088461: step: 104/469, loss: 0.4981491267681122
2023-01-24 04:41:01.836297: step: 106/469, loss: 0.006403472274541855
2023-01-24 04:41:02.448009: step: 108/469, loss: 0.00457416009157896
2023-01-24 04:41:03.026178: step: 110/469, loss: 0.35185667872428894
2023-01-24 04:41:03.748087: step: 112/469, loss: 0.029439128935337067
2023-01-24 04:41:04.359356: step: 114/469, loss: 0.002741925185546279
2023-01-24 04:41:04.992745: step: 116/469, loss: 0.0441625602543354
2023-01-24 04:41:05.786625: step: 118/469, loss: 0.16306741535663605
2023-01-24 04:41:06.373943: step: 120/469, loss: 0.003895440837368369
2023-01-24 04:41:06.995745: step: 122/469, loss: 0.006960265804082155
2023-01-24 04:41:07.634281: step: 124/469, loss: 0.003254164708778262
2023-01-24 04:41:08.234248: step: 126/469, loss: 0.08026694506406784
2023-01-24 04:41:08.928156: step: 128/469, loss: 0.00878845900297165
2023-01-24 04:41:09.505236: step: 130/469, loss: 0.01168108731508255
2023-01-24 04:41:10.149946: step: 132/469, loss: 0.04680744558572769
2023-01-24 04:41:10.709719: step: 134/469, loss: 0.00019920070189982653
2023-01-24 04:41:11.337208: step: 136/469, loss: 0.0009741685353219509
2023-01-24 04:41:11.897107: step: 138/469, loss: 0.004376692231744528
2023-01-24 04:41:12.479100: step: 140/469, loss: 0.0072433315217494965
2023-01-24 04:41:13.145818: step: 142/469, loss: 0.00038019128260202706
2023-01-24 04:41:13.776001: step: 144/469, loss: 0.0019010391552001238
2023-01-24 04:41:14.462998: step: 146/469, loss: 0.0016824081540107727
2023-01-24 04:41:15.082258: step: 148/469, loss: 0.008423411287367344
2023-01-24 04:41:15.716193: step: 150/469, loss: 0.017467912286520004
2023-01-24 04:41:16.338812: step: 152/469, loss: 0.005334971472620964
2023-01-24 04:41:16.958447: step: 154/469, loss: 0.008914156816899776
2023-01-24 04:41:17.555534: step: 156/469, loss: 0.0430353507399559
2023-01-24 04:41:18.174665: step: 158/469, loss: 0.012414567172527313
2023-01-24 04:41:18.776575: step: 160/469, loss: 0.00021787987498100847
2023-01-24 04:41:19.416920: step: 162/469, loss: 0.057112645357847214
2023-01-24 04:41:20.109075: step: 164/469, loss: 0.02861364744603634
2023-01-24 04:41:20.725762: step: 166/469, loss: 0.008333291858434677
2023-01-24 04:41:21.427346: step: 168/469, loss: 0.06528560817241669
2023-01-24 04:41:22.022687: step: 170/469, loss: 0.00824511144310236
2023-01-24 04:41:22.584655: step: 172/469, loss: 0.07460235059261322
2023-01-24 04:41:23.180582: step: 174/469, loss: 0.005715370178222656
2023-01-24 04:41:23.740055: step: 176/469, loss: 0.026749148964881897
2023-01-24 04:41:24.341031: step: 178/469, loss: 0.0014731278643012047
2023-01-24 04:41:24.991519: step: 180/469, loss: 0.047200821340084076
2023-01-24 04:41:25.603355: step: 182/469, loss: 0.01909456215798855
2023-01-24 04:41:26.214145: step: 184/469, loss: 0.00663789501413703
2023-01-24 04:41:26.868085: step: 186/469, loss: 0.04863253980875015
2023-01-24 04:41:27.468355: step: 188/469, loss: 0.010813768953084946
2023-01-24 04:41:28.168880: step: 190/469, loss: 0.012834246270358562
2023-01-24 04:41:28.805365: step: 192/469, loss: 0.01888222061097622
2023-01-24 04:41:29.444227: step: 194/469, loss: 0.024609556421637535
2023-01-24 04:41:30.035661: step: 196/469, loss: 0.003927430137991905
2023-01-24 04:41:30.669873: step: 198/469, loss: 0.001142520341090858
2023-01-24 04:41:31.339989: step: 200/469, loss: 0.05040375888347626
2023-01-24 04:41:31.922438: step: 202/469, loss: 6.32699957350269e-05
2023-01-24 04:41:32.529912: step: 204/469, loss: 0.018740428611636162
2023-01-24 04:41:33.114807: step: 206/469, loss: 0.010919380933046341
2023-01-24 04:41:33.693814: step: 208/469, loss: 0.015744278207421303
2023-01-24 04:41:34.285974: step: 210/469, loss: 0.04160604253411293
2023-01-24 04:41:34.914234: step: 212/469, loss: 0.32554858922958374
2023-01-24 04:41:35.523987: step: 214/469, loss: 0.02820652909576893
2023-01-24 04:41:36.174923: step: 216/469, loss: 0.007355737499892712
2023-01-24 04:41:36.706051: step: 218/469, loss: 0.014366361312568188
2023-01-24 04:41:37.320013: step: 220/469, loss: 0.05089385434985161
2023-01-24 04:41:37.908135: step: 222/469, loss: 0.0067719887010753155
2023-01-24 04:41:38.557847: step: 224/469, loss: 0.02073615975677967
2023-01-24 04:41:39.216313: step: 226/469, loss: 0.001756730256602168
2023-01-24 04:41:39.830766: step: 228/469, loss: 0.02269658073782921
2023-01-24 04:41:40.471506: step: 230/469, loss: 0.004856404848396778
2023-01-24 04:41:41.112079: step: 232/469, loss: 0.034278079867362976
2023-01-24 04:41:41.731284: step: 234/469, loss: 0.012941844761371613
2023-01-24 04:41:42.260588: step: 236/469, loss: 0.004036817234009504
2023-01-24 04:41:42.897317: step: 238/469, loss: 0.5611745715141296
2023-01-24 04:41:43.584691: step: 240/469, loss: 0.0008843239047564566
2023-01-24 04:41:44.192552: step: 242/469, loss: 0.004814642481505871
2023-01-24 04:41:44.828771: step: 244/469, loss: 0.012764296494424343
2023-01-24 04:41:45.416647: step: 246/469, loss: 0.4942607879638672
2023-01-24 04:41:46.124115: step: 248/469, loss: 0.09036976099014282
2023-01-24 04:41:46.708664: step: 250/469, loss: 0.0005032708868384361
2023-01-24 04:41:47.298167: step: 252/469, loss: 0.013998867943882942
2023-01-24 04:41:47.985935: step: 254/469, loss: 0.0005572093068622053
2023-01-24 04:41:48.586504: step: 256/469, loss: 0.16987258195877075
2023-01-24 04:41:49.226799: step: 258/469, loss: 0.0029405662789940834
2023-01-24 04:41:49.822154: step: 260/469, loss: 1.712666630744934
2023-01-24 04:41:50.487323: step: 262/469, loss: 0.022773411124944687
2023-01-24 04:41:51.056842: step: 264/469, loss: 0.010688270442187786
2023-01-24 04:41:51.686998: step: 266/469, loss: 0.008014222607016563
2023-01-24 04:41:52.281128: step: 268/469, loss: 0.00755898654460907
2023-01-24 04:41:52.895203: step: 270/469, loss: 0.002323312219232321
2023-01-24 04:41:53.569462: step: 272/469, loss: 0.016693051904439926
2023-01-24 04:41:54.175995: step: 274/469, loss: 0.02540774643421173
2023-01-24 04:41:54.751848: step: 276/469, loss: 0.03135130926966667
2023-01-24 04:41:55.380767: step: 278/469, loss: 0.061762865632772446
2023-01-24 04:41:56.055760: step: 280/469, loss: 0.005214679054915905
2023-01-24 04:41:56.650735: step: 282/469, loss: 0.0032812608405947685
2023-01-24 04:41:57.270513: step: 284/469, loss: 0.017116745933890343
2023-01-24 04:41:57.806835: step: 286/469, loss: 0.0011244808556511998
2023-01-24 04:41:58.446923: step: 288/469, loss: 0.01831858418881893
2023-01-24 04:41:59.035907: step: 290/469, loss: 0.010637855157256126
2023-01-24 04:41:59.698408: step: 292/469, loss: 0.0061506847850978374
2023-01-24 04:42:00.369854: step: 294/469, loss: 0.013292726129293442
2023-01-24 04:42:01.039523: step: 296/469, loss: 0.003598094917833805
2023-01-24 04:42:01.714792: step: 298/469, loss: 0.008599359542131424
2023-01-24 04:42:02.323394: step: 300/469, loss: 0.003592181019484997
2023-01-24 04:42:03.005305: step: 302/469, loss: 0.01342946756631136
2023-01-24 04:42:03.630630: step: 304/469, loss: 0.2819414436817169
2023-01-24 04:42:04.321956: step: 306/469, loss: 0.11808431893587112
2023-01-24 04:42:04.939203: step: 308/469, loss: 0.013801461085677147
2023-01-24 04:42:05.567077: step: 310/469, loss: 0.021975615993142128
2023-01-24 04:42:06.201751: step: 312/469, loss: 0.003579105716198683
2023-01-24 04:42:06.841919: step: 314/469, loss: 0.006908521521836519
2023-01-24 04:42:07.455988: step: 316/469, loss: 0.017278479412198067
2023-01-24 04:42:08.062258: step: 318/469, loss: 0.01671069860458374
2023-01-24 04:42:08.786692: step: 320/469, loss: 0.11681130528450012
2023-01-24 04:42:09.331138: step: 322/469, loss: 0.03637412562966347
2023-01-24 04:42:09.984928: step: 324/469, loss: 0.037795957177877426
2023-01-24 04:42:10.631407: step: 326/469, loss: 0.0647817924618721
2023-01-24 04:42:11.272097: step: 328/469, loss: 0.07110146433115005
2023-01-24 04:42:11.897057: step: 330/469, loss: 0.002806697739288211
2023-01-24 04:42:12.555821: step: 332/469, loss: 0.017226919531822205
2023-01-24 04:42:13.201533: step: 334/469, loss: 0.0007886120001785457
2023-01-24 04:42:13.826583: step: 336/469, loss: 0.40470314025878906
2023-01-24 04:42:14.398560: step: 338/469, loss: 0.0025602150708436966
2023-01-24 04:42:15.037509: step: 340/469, loss: 0.0430583655834198
2023-01-24 04:42:15.650472: step: 342/469, loss: 0.004851692821830511
2023-01-24 04:42:16.270287: step: 344/469, loss: 0.021595578640699387
2023-01-24 04:42:16.853707: step: 346/469, loss: 0.012612909078598022
2023-01-24 04:42:17.433309: step: 348/469, loss: 0.4985911250114441
2023-01-24 04:42:18.035759: step: 350/469, loss: 0.02535969950258732
2023-01-24 04:42:18.655217: step: 352/469, loss: 0.0025849139783531427
2023-01-24 04:42:19.325231: step: 354/469, loss: 0.006168850697577
2023-01-24 04:42:20.003927: step: 356/469, loss: 0.023574557155370712
2023-01-24 04:42:20.555936: step: 358/469, loss: 0.0024570091627538204
2023-01-24 04:42:21.171911: step: 360/469, loss: 0.014448233880102634
2023-01-24 04:42:21.874502: step: 362/469, loss: 0.027336303144693375
2023-01-24 04:42:22.501521: step: 364/469, loss: 0.04359082505106926
2023-01-24 04:42:23.149410: step: 366/469, loss: 0.5205985903739929
2023-01-24 04:42:23.767237: step: 368/469, loss: 0.015982870012521744
2023-01-24 04:42:24.382701: step: 370/469, loss: 0.011232663877308369
2023-01-24 04:42:24.943436: step: 372/469, loss: 0.033528730273246765
2023-01-24 04:42:25.626125: step: 374/469, loss: 0.002884415676817298
2023-01-24 04:42:26.237042: step: 376/469, loss: 0.04277842864394188
2023-01-24 04:42:26.834337: step: 378/469, loss: 0.0007292425725609064
2023-01-24 04:42:27.483628: step: 380/469, loss: 0.025297727435827255
2023-01-24 04:42:28.146743: step: 382/469, loss: 0.009050133638083935
2023-01-24 04:42:28.762041: step: 384/469, loss: 0.07818689197301865
2023-01-24 04:42:29.328690: step: 386/469, loss: 0.012338213622570038
2023-01-24 04:42:29.949060: step: 388/469, loss: 0.01873023808002472
2023-01-24 04:42:30.516457: step: 390/469, loss: 0.08117516338825226
2023-01-24 04:42:31.179520: step: 392/469, loss: 0.012470938265323639
2023-01-24 04:42:31.770189: step: 394/469, loss: 0.01541326753795147
2023-01-24 04:42:32.416501: step: 396/469, loss: 0.0018816686933860183
2023-01-24 04:42:33.011425: step: 398/469, loss: 0.0008937534876167774
2023-01-24 04:42:33.637028: step: 400/469, loss: 0.04712964966893196
2023-01-24 04:42:34.274039: step: 402/469, loss: 0.0015105074271559715
2023-01-24 04:42:34.897935: step: 404/469, loss: 0.00022589498257730156
2023-01-24 04:42:35.633023: step: 406/469, loss: 0.03625385835766792
2023-01-24 04:42:36.235228: step: 408/469, loss: 0.1721838265657425
2023-01-24 04:42:36.961415: step: 410/469, loss: 0.015009745955467224
2023-01-24 04:42:37.601335: step: 412/469, loss: 0.018819235265254974
2023-01-24 04:42:38.318401: step: 414/469, loss: 0.004143711645156145
2023-01-24 04:42:38.895402: step: 416/469, loss: 0.005448823794722557
2023-01-24 04:42:39.628057: step: 418/469, loss: 0.0025705129373818636
2023-01-24 04:42:40.259505: step: 420/469, loss: 0.01444432232528925
2023-01-24 04:42:40.880107: step: 422/469, loss: 0.001175693585537374
2023-01-24 04:42:41.592119: step: 424/469, loss: 0.009207737632095814
2023-01-24 04:42:42.279310: step: 426/469, loss: 0.022723522037267685
2023-01-24 04:42:42.897290: step: 428/469, loss: 0.008806123398244381
2023-01-24 04:42:43.551685: step: 430/469, loss: 0.11665830761194229
2023-01-24 04:42:44.180280: step: 432/469, loss: 0.005949435289949179
2023-01-24 04:42:44.803848: step: 434/469, loss: 0.016641709953546524
2023-01-24 04:42:45.324663: step: 436/469, loss: 0.004267572425305843
2023-01-24 04:42:45.941913: step: 438/469, loss: 0.0026941681280732155
2023-01-24 04:42:46.555942: step: 440/469, loss: 0.2649521827697754
2023-01-24 04:42:47.260647: step: 442/469, loss: 0.0063835857436060905
2023-01-24 04:42:47.880368: step: 444/469, loss: 0.006116997450590134
2023-01-24 04:42:48.525877: step: 446/469, loss: 0.006502763833850622
2023-01-24 04:42:49.159430: step: 448/469, loss: 0.027114741504192352
2023-01-24 04:42:49.765690: step: 450/469, loss: 0.0666317492723465
2023-01-24 04:42:50.409316: step: 452/469, loss: 0.04511849582195282
2023-01-24 04:42:51.073872: step: 454/469, loss: 0.0022478022146970034
2023-01-24 04:42:51.762723: step: 456/469, loss: 0.011447342112660408
2023-01-24 04:42:52.349357: step: 458/469, loss: 0.055655594915151596
2023-01-24 04:42:53.037760: step: 460/469, loss: 0.026209073141217232
2023-01-24 04:42:53.787854: step: 462/469, loss: 0.005066557787358761
2023-01-24 04:42:54.439034: step: 464/469, loss: 0.0262867771089077
2023-01-24 04:42:55.049708: step: 466/469, loss: 3.727868170244619e-05
2023-01-24 04:42:55.692581: step: 468/469, loss: 0.011682676151394844
2023-01-24 04:42:56.314291: step: 470/469, loss: 0.013487524352967739
2023-01-24 04:42:56.916891: step: 472/469, loss: 0.0008283891365863383
2023-01-24 04:42:57.570051: step: 474/469, loss: 5.688061355613172e-05
2023-01-24 04:42:58.149707: step: 476/469, loss: 0.003044802462682128
2023-01-24 04:42:58.779149: step: 478/469, loss: 0.07766813039779663
2023-01-24 04:42:59.428651: step: 480/469, loss: 0.2414858639240265
2023-01-24 04:43:00.053814: step: 482/469, loss: 0.0015074929688125849
2023-01-24 04:43:00.659656: step: 484/469, loss: 0.010486260987818241
2023-01-24 04:43:01.300450: step: 486/469, loss: 0.011371143162250519
2023-01-24 04:43:01.877124: step: 488/469, loss: 0.0038459154311567545
2023-01-24 04:43:02.520311: step: 490/469, loss: 0.0009269219590350986
2023-01-24 04:43:03.163325: step: 492/469, loss: 0.00967847928404808
2023-01-24 04:43:03.812103: step: 494/469, loss: 0.003559316508471966
2023-01-24 04:43:04.438946: step: 496/469, loss: 0.048895612359046936
2023-01-24 04:43:05.009248: step: 498/469, loss: 0.05181241035461426
2023-01-24 04:43:05.691733: step: 500/469, loss: 0.007987109944224358
2023-01-24 04:43:06.321300: step: 502/469, loss: 0.16030405461788177
2023-01-24 04:43:06.963927: step: 504/469, loss: 0.0008819969370961189
2023-01-24 04:43:07.580677: step: 506/469, loss: 0.28211885690689087
2023-01-24 04:43:08.206953: step: 508/469, loss: 0.001571113127283752
2023-01-24 04:43:08.765423: step: 510/469, loss: 0.00629191379994154
2023-01-24 04:43:09.371669: step: 512/469, loss: 0.02589668706059456
2023-01-24 04:43:10.001454: step: 514/469, loss: 0.0009901889134198427
2023-01-24 04:43:10.661662: step: 516/469, loss: 0.07391221076250076
2023-01-24 04:43:11.318133: step: 518/469, loss: 0.04188664257526398
2023-01-24 04:43:11.941358: step: 520/469, loss: 0.010917184874415398
2023-01-24 04:43:12.571761: step: 522/469, loss: 0.012965405359864235
2023-01-24 04:43:13.144768: step: 524/469, loss: 0.32013627886772156
2023-01-24 04:43:13.858562: step: 526/469, loss: 0.024639640003442764
2023-01-24 04:43:14.496730: step: 528/469, loss: 0.00801227055490017
2023-01-24 04:43:15.077138: step: 530/469, loss: 0.020771576091647148
2023-01-24 04:43:15.730527: step: 532/469, loss: 0.0076049817726016045
2023-01-24 04:43:16.416267: step: 534/469, loss: 0.007345182821154594
2023-01-24 04:43:17.060307: step: 536/469, loss: 0.20593872666358948
2023-01-24 04:43:17.697579: step: 538/469, loss: 0.23821468651294708
2023-01-24 04:43:18.354357: step: 540/469, loss: 0.0007799813756719232
2023-01-24 04:43:18.958688: step: 542/469, loss: 0.025101082399487495
2023-01-24 04:43:19.498017: step: 544/469, loss: 0.0236770361661911
2023-01-24 04:43:20.136929: step: 546/469, loss: 0.02644025720655918
2023-01-24 04:43:20.740089: step: 548/469, loss: 0.02457072027027607
2023-01-24 04:43:21.363555: step: 550/469, loss: 0.0788365826010704
2023-01-24 04:43:21.990544: step: 552/469, loss: 0.010176182724535465
2023-01-24 04:43:22.561089: step: 554/469, loss: 0.005486792419105768
2023-01-24 04:43:23.227000: step: 556/469, loss: 0.026093045249581337
2023-01-24 04:43:24.042718: step: 558/469, loss: 0.0605422779917717
2023-01-24 04:43:24.648137: step: 560/469, loss: 0.025924276560544968
2023-01-24 04:43:25.293927: step: 562/469, loss: 0.06749466806650162
2023-01-24 04:43:25.924687: step: 564/469, loss: 0.042776819318532944
2023-01-24 04:43:26.513587: step: 566/469, loss: 0.010451863519847393
2023-01-24 04:43:27.123968: step: 568/469, loss: 0.01529045682400465
2023-01-24 04:43:27.720390: step: 570/469, loss: 0.011241276748478413
2023-01-24 04:43:28.324237: step: 572/469, loss: 0.3424895405769348
2023-01-24 04:43:28.931834: step: 574/469, loss: 0.019531693309545517
2023-01-24 04:43:29.568841: step: 576/469, loss: 0.0014761670026928186
2023-01-24 04:43:30.145715: step: 578/469, loss: 0.048141270875930786
2023-01-24 04:43:30.800152: step: 580/469, loss: 0.004486797843128443
2023-01-24 04:43:31.434195: step: 582/469, loss: 0.0013610408641397953
2023-01-24 04:43:32.003018: step: 584/469, loss: 0.0013765976764261723
2023-01-24 04:43:32.623358: step: 586/469, loss: 0.02723407931625843
2023-01-24 04:43:33.283167: step: 588/469, loss: 0.0032612651120871305
2023-01-24 04:43:33.896205: step: 590/469, loss: 0.03588743880391121
2023-01-24 04:43:34.592095: step: 592/469, loss: 0.0017066128784790635
2023-01-24 04:43:35.193231: step: 594/469, loss: 0.007653994485735893
2023-01-24 04:43:35.808798: step: 596/469, loss: 0.023221269249916077
2023-01-24 04:43:36.427788: step: 598/469, loss: 0.000273090903647244
2023-01-24 04:43:37.099210: step: 600/469, loss: 0.003898853901773691
2023-01-24 04:43:37.663575: step: 602/469, loss: 0.054680511355400085
2023-01-24 04:43:38.279975: step: 604/469, loss: 0.6385080814361572
2023-01-24 04:43:38.890430: step: 606/469, loss: 0.0015598267782479525
2023-01-24 04:43:39.552138: step: 608/469, loss: 0.01506998110562563
2023-01-24 04:43:40.159837: step: 610/469, loss: 0.0008091532508842647
2023-01-24 04:43:40.872659: step: 612/469, loss: 0.014290979132056236
2023-01-24 04:43:41.476220: step: 614/469, loss: 0.029819728806614876
2023-01-24 04:43:42.031083: step: 616/469, loss: 0.013888353481888771
2023-01-24 04:43:42.646086: step: 618/469, loss: 0.007446426432579756
2023-01-24 04:43:43.294733: step: 620/469, loss: 0.0053463405929505825
2023-01-24 04:43:43.890328: step: 622/469, loss: 0.015953373163938522
2023-01-24 04:43:44.504313: step: 624/469, loss: 0.005202372092753649
2023-01-24 04:43:45.101042: step: 626/469, loss: 0.338346004486084
2023-01-24 04:43:45.738750: step: 628/469, loss: 0.06557228416204453
2023-01-24 04:43:46.306482: step: 630/469, loss: 0.13257935643196106
2023-01-24 04:43:46.910193: step: 632/469, loss: 0.0065249791368842125
2023-01-24 04:43:47.567388: step: 634/469, loss: 0.04262690991163254
2023-01-24 04:43:48.182915: step: 636/469, loss: 0.00965095590800047
2023-01-24 04:43:48.791675: step: 638/469, loss: 0.8289828896522522
2023-01-24 04:43:49.435980: step: 640/469, loss: 0.030092066153883934
2023-01-24 04:43:50.063536: step: 642/469, loss: 0.032380178570747375
2023-01-24 04:43:50.635372: step: 644/469, loss: 0.008327679708600044
2023-01-24 04:43:51.253449: step: 646/469, loss: 0.016449350863695145
2023-01-24 04:43:51.838277: step: 648/469, loss: 0.0007658099639229476
2023-01-24 04:43:52.524827: step: 650/469, loss: 0.009851734153926373
2023-01-24 04:43:53.146841: step: 652/469, loss: 0.05094342306256294
2023-01-24 04:43:53.750707: step: 654/469, loss: 0.0020685922354459763
2023-01-24 04:43:54.467437: step: 656/469, loss: 0.05595378950238228
2023-01-24 04:43:55.091772: step: 658/469, loss: 0.009969577193260193
2023-01-24 04:43:55.815772: step: 660/469, loss: 0.07338903099298477
2023-01-24 04:43:56.554831: step: 662/469, loss: 0.28325212001800537
2023-01-24 04:43:57.109195: step: 664/469, loss: 0.011265905573964119
2023-01-24 04:43:57.738793: step: 666/469, loss: 0.0010473066940903664
2023-01-24 04:43:58.393067: step: 668/469, loss: 0.03323003277182579
2023-01-24 04:43:58.910166: step: 670/469, loss: 0.001536346971988678
2023-01-24 04:43:59.510075: step: 672/469, loss: 0.06809452176094055
2023-01-24 04:44:00.168441: step: 674/469, loss: 0.6119838953018188
2023-01-24 04:44:00.865366: step: 676/469, loss: 0.06336773931980133
2023-01-24 04:44:01.469479: step: 678/469, loss: 0.0024896988179534674
2023-01-24 04:44:02.091633: step: 680/469, loss: 0.0852007046341896
2023-01-24 04:44:02.741268: step: 682/469, loss: 0.006763627752661705
2023-01-24 04:44:03.301586: step: 684/469, loss: 0.007324565201997757
2023-01-24 04:44:04.090069: step: 686/469, loss: 0.0406450591981411
2023-01-24 04:44:04.665096: step: 688/469, loss: 0.045363061130046844
2023-01-24 04:44:05.265293: step: 690/469, loss: 0.040597084909677505
2023-01-24 04:44:05.833956: step: 692/469, loss: 0.05471392348408699
2023-01-24 04:44:06.461153: step: 694/469, loss: 0.02417490817606449
2023-01-24 04:44:07.102819: step: 696/469, loss: 0.038300611078739166
2023-01-24 04:44:07.740256: step: 698/469, loss: 0.03155882656574249
2023-01-24 04:44:08.334321: step: 700/469, loss: 0.010796644724905491
2023-01-24 04:44:08.974273: step: 702/469, loss: 0.02432398311793804
2023-01-24 04:44:09.672678: step: 704/469, loss: 0.5379462838172913
2023-01-24 04:44:10.347740: step: 706/469, loss: 0.005173343233764172
2023-01-24 04:44:10.948237: step: 708/469, loss: 0.028695274144411087
2023-01-24 04:44:11.498926: step: 710/469, loss: 0.08584290742874146
2023-01-24 04:44:12.201163: step: 712/469, loss: 0.0008699421887286007
2023-01-24 04:44:12.896080: step: 714/469, loss: 0.009589890018105507
2023-01-24 04:44:13.485046: step: 716/469, loss: 0.0009711757302284241
2023-01-24 04:44:14.123556: step: 718/469, loss: 0.013375996612012386
2023-01-24 04:44:14.660772: step: 720/469, loss: 0.022644609212875366
2023-01-24 04:44:15.247568: step: 722/469, loss: 0.5862990617752075
2023-01-24 04:44:15.900248: step: 724/469, loss: 0.009702946059405804
2023-01-24 04:44:16.508657: step: 726/469, loss: 0.061791542917490005
2023-01-24 04:44:17.143676: step: 728/469, loss: 0.01918252743780613
2023-01-24 04:44:17.774025: step: 730/469, loss: 0.010699711740016937
2023-01-24 04:44:18.474110: step: 732/469, loss: 0.043368566781282425
2023-01-24 04:44:19.098308: step: 734/469, loss: 0.0138897355645895
2023-01-24 04:44:19.729452: step: 736/469, loss: 0.021746980026364326
2023-01-24 04:44:20.367460: step: 738/469, loss: 0.07260733097791672
2023-01-24 04:44:21.024457: step: 740/469, loss: 0.0003846806939691305
2023-01-24 04:44:21.630172: step: 742/469, loss: 0.1339012086391449
2023-01-24 04:44:22.347675: step: 744/469, loss: 0.00799509510397911
2023-01-24 04:44:22.988707: step: 746/469, loss: 0.001403206493705511
2023-01-24 04:44:23.667920: step: 748/469, loss: 0.019522899761795998
2023-01-24 04:44:24.375632: step: 750/469, loss: 0.0902690514922142
2023-01-24 04:44:24.973325: step: 752/469, loss: 0.011594656854867935
2023-01-24 04:44:25.590851: step: 754/469, loss: 0.013745458796620369
2023-01-24 04:44:26.225282: step: 756/469, loss: 0.012667307630181313
2023-01-24 04:44:26.849549: step: 758/469, loss: 0.0009552580304443836
2023-01-24 04:44:27.496642: step: 760/469, loss: 0.0006107121589593589
2023-01-24 04:44:28.063373: step: 762/469, loss: 0.027866194024682045
2023-01-24 04:44:28.684850: step: 764/469, loss: 0.0951715037226677
2023-01-24 04:44:29.327893: step: 766/469, loss: 0.016138773411512375
2023-01-24 04:44:30.037487: step: 768/469, loss: 0.005201226100325584
2023-01-24 04:44:30.638336: step: 770/469, loss: 0.00589489471167326
2023-01-24 04:44:31.209969: step: 772/469, loss: 0.02527569979429245
2023-01-24 04:44:31.822518: step: 774/469, loss: 0.0347880944609642
2023-01-24 04:44:32.447621: step: 776/469, loss: 0.013205569237470627
2023-01-24 04:44:33.081816: step: 778/469, loss: 0.011248763650655746
2023-01-24 04:44:33.774710: step: 780/469, loss: 0.00997249223291874
2023-01-24 04:44:34.313054: step: 782/469, loss: 0.0025223700795322657
2023-01-24 04:44:34.861004: step: 784/469, loss: 0.009769073687493801
2023-01-24 04:44:35.515450: step: 786/469, loss: 0.003616972593590617
2023-01-24 04:44:36.239146: step: 788/469, loss: 0.022250380367040634
2023-01-24 04:44:36.908473: step: 790/469, loss: 0.012565650045871735
2023-01-24 04:44:37.513783: step: 792/469, loss: 0.046210065484046936
2023-01-24 04:44:38.127290: step: 794/469, loss: 0.023500768467783928
2023-01-24 04:44:38.724594: step: 796/469, loss: 0.0485650934278965
2023-01-24 04:44:39.314800: step: 798/469, loss: 0.00012500408047344536
2023-01-24 04:44:39.922760: step: 800/469, loss: 0.007613717578351498
2023-01-24 04:44:40.494089: step: 802/469, loss: 0.003843215061351657
2023-01-24 04:44:41.096565: step: 804/469, loss: 0.00727503839880228
2023-01-24 04:44:41.739842: step: 806/469, loss: 0.017243437469005585
2023-01-24 04:44:42.337672: step: 808/469, loss: 0.01734367199242115
2023-01-24 04:44:42.979772: step: 810/469, loss: 0.012736249715089798
2023-01-24 04:44:43.607308: step: 812/469, loss: 0.057649098336696625
2023-01-24 04:44:44.231513: step: 814/469, loss: 0.019087396562099457
2023-01-24 04:44:44.886485: step: 816/469, loss: 0.04761027917265892
2023-01-24 04:44:45.532249: step: 818/469, loss: 0.03003348782658577
2023-01-24 04:44:46.155865: step: 820/469, loss: 0.005879759788513184
2023-01-24 04:44:46.790256: step: 822/469, loss: 0.0019286437891423702
2023-01-24 04:44:47.483669: step: 824/469, loss: 0.012159345671534538
2023-01-24 04:44:48.153007: step: 826/469, loss: 0.07695124298334122
2023-01-24 04:44:48.781034: step: 828/469, loss: 0.011008651927113533
2023-01-24 04:44:49.486167: step: 830/469, loss: 0.027759000658988953
2023-01-24 04:44:50.069035: step: 832/469, loss: 0.0030974114779382944
2023-01-24 04:44:50.698825: step: 834/469, loss: 0.07664292305707932
2023-01-24 04:44:51.264290: step: 836/469, loss: 0.09113086014986038
2023-01-24 04:44:51.903521: step: 838/469, loss: 0.0007742611924186349
2023-01-24 04:44:52.579102: step: 840/469, loss: 0.01921161636710167
2023-01-24 04:44:53.204772: step: 842/469, loss: 0.006564127281308174
2023-01-24 04:44:53.893799: step: 844/469, loss: 0.015580904670059681
2023-01-24 04:44:54.537713: step: 846/469, loss: 0.00860374141484499
2023-01-24 04:44:55.213290: step: 848/469, loss: 0.005637663416564465
2023-01-24 04:44:55.874176: step: 850/469, loss: 0.03962088003754616
2023-01-24 04:44:56.476102: step: 852/469, loss: 0.005060709081590176
2023-01-24 04:44:57.103578: step: 854/469, loss: 0.00484490767121315
2023-01-24 04:44:57.734175: step: 856/469, loss: 0.0007542431703768671
2023-01-24 04:44:58.348852: step: 858/469, loss: 0.02857186645269394
2023-01-24 04:44:58.976208: step: 860/469, loss: 0.020907428115606308
2023-01-24 04:44:59.566447: step: 862/469, loss: 0.02676711417734623
2023-01-24 04:45:00.104059: step: 864/469, loss: 0.0011087771272286773
2023-01-24 04:45:00.743211: step: 866/469, loss: 0.025923844426870346
2023-01-24 04:45:01.338368: step: 868/469, loss: 0.06489332020282745
2023-01-24 04:45:01.969761: step: 870/469, loss: 0.02352488972246647
2023-01-24 04:45:02.581110: step: 872/469, loss: 0.030912941321730614
2023-01-24 04:45:03.172094: step: 874/469, loss: 0.004885273054242134
2023-01-24 04:45:03.748664: step: 876/469, loss: 0.07296209037303925
2023-01-24 04:45:04.391985: step: 878/469, loss: 0.02735503576695919
2023-01-24 04:45:04.943354: step: 880/469, loss: 0.0836150050163269
2023-01-24 04:45:05.519882: step: 882/469, loss: 0.018567459657788277
2023-01-24 04:45:06.092648: step: 884/469, loss: 0.0021437390241771936
2023-01-24 04:45:06.641803: step: 886/469, loss: 0.017340516671538353
2023-01-24 04:45:07.243447: step: 888/469, loss: 0.009366720914840698
2023-01-24 04:45:07.833302: step: 890/469, loss: 0.01768156886100769
2023-01-24 04:45:08.427108: step: 892/469, loss: 0.029670976102352142
2023-01-24 04:45:09.062604: step: 894/469, loss: 0.0538417287170887
2023-01-24 04:45:09.732673: step: 896/469, loss: 0.021779846400022507
2023-01-24 04:45:10.375799: step: 898/469, loss: 0.013282307423651218
2023-01-24 04:45:10.931805: step: 900/469, loss: 0.0017287018708884716
2023-01-24 04:45:11.536670: step: 902/469, loss: 0.012488807551562786
2023-01-24 04:45:12.182450: step: 904/469, loss: 1.4560414552688599
2023-01-24 04:45:12.886215: step: 906/469, loss: 6.52432645438239e-05
2023-01-24 04:45:13.482593: step: 908/469, loss: 0.004614822566509247
2023-01-24 04:45:14.159981: step: 910/469, loss: 0.011488398537039757
2023-01-24 04:45:14.817558: step: 912/469, loss: 0.0010576223721727729
2023-01-24 04:45:15.397708: step: 914/469, loss: 0.053319886326789856
2023-01-24 04:45:16.010155: step: 916/469, loss: 0.012150132097303867
2023-01-24 04:45:16.706153: step: 918/469, loss: 0.11468244343996048
2023-01-24 04:45:17.344917: step: 920/469, loss: 0.0085227582603693
2023-01-24 04:45:17.905884: step: 922/469, loss: 0.026661816984415054
2023-01-24 04:45:18.487908: step: 924/469, loss: 0.039426226168870926
2023-01-24 04:45:19.075820: step: 926/469, loss: 0.013353646732866764
2023-01-24 04:45:19.834107: step: 928/469, loss: 0.04049745202064514
2023-01-24 04:45:20.433684: step: 930/469, loss: 0.02001982554793358
2023-01-24 04:45:21.058454: step: 932/469, loss: 0.00044286841875873506
2023-01-24 04:45:21.676526: step: 934/469, loss: 0.00044436060125008225
2023-01-24 04:45:22.230847: step: 936/469, loss: 1.128492832183838
2023-01-24 04:45:22.922717: step: 938/469, loss: 0.0041632517240941525
==================================================
Loss: 0.053
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3140649920255183, 'r': 0.3057217095049163, 'f1': 0.309837194055944}, 'combined': 0.22830109035701135, 'epoch': 30}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3319349872163209, 'r': 0.26026375484390396, 'f1': 0.29176234260962775}, 'combined': 0.15914309596888784, 'epoch': 30}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3244918608788472, 'r': 0.3146401155770226, 'f1': 0.31949005955508847}, 'combined': 0.23541372809322306, 'epoch': 30}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.344444337174535, 'r': 0.2676212857388983, 'f1': 0.30121161172670236}, 'combined': 0.16429724276001945, 'epoch': 30}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3138170330948642, 'r': 0.31024416364786384, 'f1': 0.3120203706916493}, 'combined': 0.22990974682542578, 'epoch': 30}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3354300437120743, 'r': 0.2626972711962814, 'f1': 0.29464147503082155}, 'combined': 0.16071353183499357, 'epoch': 30}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2785714285714286, 'r': 0.2785714285714286, 'f1': 0.2785714285714286}, 'combined': 0.18571428571428572, 'epoch': 30}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3020833333333333, 'r': 0.31521739130434784, 'f1': 0.30851063829787234}, 'combined': 0.15425531914893617, 'epoch': 30}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4444444444444444, 'r': 0.13793103448275862, 'f1': 0.21052631578947367}, 'combined': 0.14035087719298245, 'epoch': 30}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 04:48:08.228179: step: 2/469, loss: 0.0005729378899559379
2023-01-24 04:48:08.838003: step: 4/469, loss: 0.021582650020718575
2023-01-24 04:48:09.588375: step: 6/469, loss: 0.019079118967056274
2023-01-24 04:48:10.275392: step: 8/469, loss: 0.0162974800914526
2023-01-24 04:48:10.910213: step: 10/469, loss: 0.01126583106815815
2023-01-24 04:48:11.520114: step: 12/469, loss: 0.007237909361720085
2023-01-24 04:48:12.167543: step: 14/469, loss: 0.025096124038100243
2023-01-24 04:48:12.780077: step: 16/469, loss: 0.003229469293728471
2023-01-24 04:48:13.412715: step: 18/469, loss: 0.012669836170971394
2023-01-24 04:48:13.990537: step: 20/469, loss: 0.07041142880916595
2023-01-24 04:48:14.607671: step: 22/469, loss: 0.028156736865639687
2023-01-24 04:48:15.334092: step: 24/469, loss: 0.010577772743999958
2023-01-24 04:48:15.990756: step: 26/469, loss: 0.019591083750128746
2023-01-24 04:48:16.712829: step: 28/469, loss: 0.003482040949165821
2023-01-24 04:48:17.338547: step: 30/469, loss: 0.0009129349491558969
2023-01-24 04:48:17.961026: step: 32/469, loss: 0.024413228034973145
2023-01-24 04:48:18.621858: step: 34/469, loss: 0.01993262954056263
2023-01-24 04:48:19.213707: step: 36/469, loss: 0.01959720440208912
2023-01-24 04:48:19.818435: step: 38/469, loss: 0.0008238955633714795
2023-01-24 04:48:20.378695: step: 40/469, loss: 0.002699420787394047
2023-01-24 04:48:21.076170: step: 42/469, loss: 0.7757253050804138
2023-01-24 04:48:21.731513: step: 44/469, loss: 0.0028708865866065025
2023-01-24 04:48:22.344803: step: 46/469, loss: 0.018478717654943466
2023-01-24 04:48:22.994857: step: 48/469, loss: 0.055832114070653915
2023-01-24 04:48:23.649984: step: 50/469, loss: 0.0019766055047512054
2023-01-24 04:48:24.334180: step: 52/469, loss: 0.016218986362218857
2023-01-24 04:48:24.935963: step: 54/469, loss: 0.03432663530111313
2023-01-24 04:48:25.511963: step: 56/469, loss: 0.001772875664755702
2023-01-24 04:48:26.111224: step: 58/469, loss: 0.02379467710852623
2023-01-24 04:48:26.763970: step: 60/469, loss: 0.015501943416893482
2023-01-24 04:48:27.397246: step: 62/469, loss: 0.0018933971878141165
2023-01-24 04:48:28.058069: step: 64/469, loss: 0.005271086934953928
2023-01-24 04:48:28.732078: step: 66/469, loss: 0.026647893711924553
2023-01-24 04:48:29.367432: step: 68/469, loss: 0.009883650578558445
2023-01-24 04:48:30.012333: step: 70/469, loss: 0.01539866253733635
2023-01-24 04:48:30.608062: step: 72/469, loss: 0.0025817533023655415
2023-01-24 04:48:31.250491: step: 74/469, loss: 0.004883921705186367
2023-01-24 04:48:31.895447: step: 76/469, loss: 0.0011225785128772259
2023-01-24 04:48:32.516177: step: 78/469, loss: 0.04822733998298645
2023-01-24 04:48:33.178112: step: 80/469, loss: 0.03262604400515556
2023-01-24 04:48:33.816320: step: 82/469, loss: 0.015143095515668392
2023-01-24 04:48:34.370116: step: 84/469, loss: 0.10950957983732224
2023-01-24 04:48:34.955412: step: 86/469, loss: 0.0032710139639675617
2023-01-24 04:48:35.613647: step: 88/469, loss: 0.05682629719376564
2023-01-24 04:48:36.245886: step: 90/469, loss: 0.07679912447929382
2023-01-24 04:48:36.873663: step: 92/469, loss: 0.0005978215485811234
2023-01-24 04:48:37.526150: step: 94/469, loss: 0.0337165929377079
2023-01-24 04:48:38.205360: step: 96/469, loss: 0.006347418297082186
2023-01-24 04:48:38.839621: step: 98/469, loss: 0.06465981900691986
2023-01-24 04:48:39.464947: step: 100/469, loss: 0.00465664267539978
2023-01-24 04:48:40.120372: step: 102/469, loss: 0.024802401661872864
2023-01-24 04:48:40.760873: step: 104/469, loss: 0.011391839943826199
2023-01-24 04:48:41.381030: step: 106/469, loss: 0.0023167754989117384
2023-01-24 04:48:42.020114: step: 108/469, loss: 0.047045741230249405
2023-01-24 04:48:42.636404: step: 110/469, loss: 0.0008440035162493587
2023-01-24 04:48:43.306951: step: 112/469, loss: 0.010709509253501892
2023-01-24 04:48:43.883662: step: 114/469, loss: 0.016167698428034782
2023-01-24 04:48:44.498759: step: 116/469, loss: 0.0020748646929860115
2023-01-24 04:48:45.104468: step: 118/469, loss: 0.002652397146448493
2023-01-24 04:48:45.748107: step: 120/469, loss: 0.004655083175748587
2023-01-24 04:48:46.364643: step: 122/469, loss: 0.02868480049073696
2023-01-24 04:48:47.011219: step: 124/469, loss: 0.04327602684497833
2023-01-24 04:48:47.659538: step: 126/469, loss: 0.05765855684876442
2023-01-24 04:48:48.254770: step: 128/469, loss: 0.01431294996291399
2023-01-24 04:48:48.821746: step: 130/469, loss: 0.05785543471574783
2023-01-24 04:48:49.435420: step: 132/469, loss: 0.003356471424922347
2023-01-24 04:48:50.075349: step: 134/469, loss: 0.0007477797335013747
2023-01-24 04:48:50.769356: step: 136/469, loss: 0.007177515886723995
2023-01-24 04:48:51.331857: step: 138/469, loss: 0.01197109092026949
2023-01-24 04:48:51.976805: step: 140/469, loss: 0.0010844813659787178
2023-01-24 04:48:52.603546: step: 142/469, loss: 0.018617521971464157
2023-01-24 04:48:53.267606: step: 144/469, loss: 0.031321339309215546
2023-01-24 04:48:53.859907: step: 146/469, loss: 0.010097871534526348
2023-01-24 04:48:54.454177: step: 148/469, loss: 0.0375542975962162
2023-01-24 04:48:55.165103: step: 150/469, loss: 0.0012660510838031769
2023-01-24 04:48:55.736101: step: 152/469, loss: 0.00766314473003149
2023-01-24 04:48:56.362889: step: 154/469, loss: 0.040173135697841644
2023-01-24 04:48:56.941888: step: 156/469, loss: 0.01005063857883215
2023-01-24 04:48:57.537319: step: 158/469, loss: 0.012250649742782116
2023-01-24 04:48:58.177064: step: 160/469, loss: 0.0040445332415401936
2023-01-24 04:48:58.831048: step: 162/469, loss: 0.002032180316746235
2023-01-24 04:48:59.449891: step: 164/469, loss: 0.07697049528360367
2023-01-24 04:49:00.016197: step: 166/469, loss: 0.00881399679929018
2023-01-24 04:49:00.631255: step: 168/469, loss: 0.0013901349157094955
2023-01-24 04:49:01.289645: step: 170/469, loss: 0.0011047078296542168
2023-01-24 04:49:01.946788: step: 172/469, loss: 0.04833559691905975
2023-01-24 04:49:02.624881: step: 174/469, loss: 0.06360644847154617
2023-01-24 04:49:03.378044: step: 176/469, loss: 0.023506218567490578
2023-01-24 04:49:03.983760: step: 178/469, loss: 0.0009571845876052976
2023-01-24 04:49:04.558432: step: 180/469, loss: 0.019779067486524582
2023-01-24 04:49:05.197033: step: 182/469, loss: 0.011791273951530457
2023-01-24 04:49:05.839554: step: 184/469, loss: 0.004171493463218212
2023-01-24 04:49:06.461577: step: 186/469, loss: 0.05008388310670853
2023-01-24 04:49:07.155953: step: 188/469, loss: 0.007591721601784229
2023-01-24 04:49:07.814610: step: 190/469, loss: 0.00032156784436665475
2023-01-24 04:49:08.441513: step: 192/469, loss: 0.0032910103909671307
2023-01-24 04:49:09.021334: step: 194/469, loss: 0.01623852550983429
2023-01-24 04:49:09.673217: step: 196/469, loss: 0.006585577968508005
2023-01-24 04:49:10.321748: step: 198/469, loss: 0.008083397522568703
2023-01-24 04:49:10.880816: step: 200/469, loss: 0.00017901387764140964
2023-01-24 04:49:11.520903: step: 202/469, loss: 0.0354151576757431
2023-01-24 04:49:12.129591: step: 204/469, loss: 0.004744931124150753
2023-01-24 04:49:12.780234: step: 206/469, loss: 0.01003217976540327
2023-01-24 04:49:13.437038: step: 208/469, loss: 8.596295811003074e-05
2023-01-24 04:49:14.037107: step: 210/469, loss: 0.012387464754283428
2023-01-24 04:49:14.652308: step: 212/469, loss: 0.14620867371559143
2023-01-24 04:49:15.340028: step: 214/469, loss: 0.007369412574917078
2023-01-24 04:49:15.860159: step: 216/469, loss: 0.024283574894070625
2023-01-24 04:49:16.503269: step: 218/469, loss: 0.004432167857885361
2023-01-24 04:49:17.055094: step: 220/469, loss: 0.005264786072075367
2023-01-24 04:49:17.705490: step: 222/469, loss: 0.003752398304641247
2023-01-24 04:49:18.340179: step: 224/469, loss: 0.021850887686014175
2023-01-24 04:49:19.017869: step: 226/469, loss: 0.0037360461428761482
2023-01-24 04:49:19.656610: step: 228/469, loss: 0.20684556663036346
2023-01-24 04:49:20.281134: step: 230/469, loss: 0.017796510830521584
2023-01-24 04:49:20.923353: step: 232/469, loss: 0.019183460623025894
2023-01-24 04:49:21.483899: step: 234/469, loss: 0.011985360644757748
2023-01-24 04:49:22.178281: step: 236/469, loss: 0.0029038565699011087
2023-01-24 04:49:22.808743: step: 238/469, loss: 0.03439052030444145
2023-01-24 04:49:23.468292: step: 240/469, loss: 0.0347650982439518
2023-01-24 04:49:24.061868: step: 242/469, loss: 0.025752931833267212
2023-01-24 04:49:24.687637: step: 244/469, loss: 0.00030208344105631113
2023-01-24 04:49:25.283182: step: 246/469, loss: 0.00015331061149481684
2023-01-24 04:49:25.921343: step: 248/469, loss: 0.0011783675290644169
2023-01-24 04:49:26.544712: step: 250/469, loss: 0.04272384196519852
2023-01-24 04:49:27.181965: step: 252/469, loss: 0.0030883518047630787
2023-01-24 04:49:27.850144: step: 254/469, loss: 0.00023785419762134552
2023-01-24 04:49:28.513853: step: 256/469, loss: 0.0015512205427512527
2023-01-24 04:49:29.118907: step: 258/469, loss: 0.005846394691616297
2023-01-24 04:49:29.702537: step: 260/469, loss: 0.016543468460440636
2023-01-24 04:49:30.278242: step: 262/469, loss: 0.024850815534591675
2023-01-24 04:49:30.984247: step: 264/469, loss: 0.002375295152887702
2023-01-24 04:49:31.614566: step: 266/469, loss: 0.004793278872966766
2023-01-24 04:49:32.195145: step: 268/469, loss: 0.009141725488007069
2023-01-24 04:49:32.790072: step: 270/469, loss: 0.01785050705075264
2023-01-24 04:49:33.411187: step: 272/469, loss: 0.004698670469224453
2023-01-24 04:49:34.041477: step: 274/469, loss: 0.002224231604486704
2023-01-24 04:49:34.674925: step: 276/469, loss: 0.006143860053271055
2023-01-24 04:49:35.370088: step: 278/469, loss: 1.6983529329299927
2023-01-24 04:49:35.982907: step: 280/469, loss: 2.326651883777231e-05
2023-01-24 04:49:36.649316: step: 282/469, loss: 0.0031944005750119686
2023-01-24 04:49:37.293512: step: 284/469, loss: 0.00045949631021358073
2023-01-24 04:49:37.851708: step: 286/469, loss: 0.025172626599669456
2023-01-24 04:49:38.467800: step: 288/469, loss: 0.005660675000399351
2023-01-24 04:49:39.088806: step: 290/469, loss: 0.02098415233194828
2023-01-24 04:49:39.799799: step: 292/469, loss: 0.013500221073627472
2023-01-24 04:49:40.515670: step: 294/469, loss: 0.001041474286466837
2023-01-24 04:49:41.196077: step: 296/469, loss: 0.009058577008545399
2023-01-24 04:49:41.794080: step: 298/469, loss: 0.0028848727233707905
2023-01-24 04:49:42.413518: step: 300/469, loss: 0.006596582476049662
2023-01-24 04:49:43.100151: step: 302/469, loss: 0.002710898406803608
2023-01-24 04:49:43.734277: step: 304/469, loss: 0.026905842125415802
2023-01-24 04:49:44.404884: step: 306/469, loss: 0.037932656705379486
2023-01-24 04:49:45.023917: step: 308/469, loss: 0.05146189033985138
2023-01-24 04:49:45.650819: step: 310/469, loss: 0.00023282418260350823
2023-01-24 04:49:46.243740: step: 312/469, loss: 0.004080084152519703
2023-01-24 04:49:46.834881: step: 314/469, loss: 0.01171773113310337
2023-01-24 04:49:47.462128: step: 316/469, loss: 0.0002971935027744621
2023-01-24 04:49:48.063586: step: 318/469, loss: 0.015443394891917706
2023-01-24 04:49:48.689403: step: 320/469, loss: 0.033965498208999634
2023-01-24 04:49:49.340503: step: 322/469, loss: 0.0036953482776880264
2023-01-24 04:49:49.935242: step: 324/469, loss: 0.021460488438606262
2023-01-24 04:49:50.644636: step: 326/469, loss: 0.008619173429906368
2023-01-24 04:49:51.309378: step: 328/469, loss: 0.009122327901422977
2023-01-24 04:49:51.896494: step: 330/469, loss: 0.013629604130983353
2023-01-24 04:49:52.481509: step: 332/469, loss: 0.008984750136733055
2023-01-24 04:49:53.095708: step: 334/469, loss: 0.057154733687639236
2023-01-24 04:49:53.764651: step: 336/469, loss: 0.45392361283302307
2023-01-24 04:49:54.452535: step: 338/469, loss: 0.010387986898422241
2023-01-24 04:49:55.025964: step: 340/469, loss: 0.00038042268715798855
2023-01-24 04:49:55.681341: step: 342/469, loss: 0.029774561524391174
2023-01-24 04:49:56.303386: step: 344/469, loss: 0.0258974377065897
2023-01-24 04:49:56.879496: step: 346/469, loss: 0.04096565395593643
2023-01-24 04:49:57.509243: step: 348/469, loss: 0.010139081627130508
2023-01-24 04:49:58.133223: step: 350/469, loss: 0.05517276003956795
2023-01-24 04:49:58.790312: step: 352/469, loss: 0.02398163639008999
2023-01-24 04:49:59.401251: step: 354/469, loss: 0.03484689071774483
2023-01-24 04:49:59.999955: step: 356/469, loss: 0.07194016873836517
2023-01-24 04:50:00.741537: step: 358/469, loss: 0.02317383699119091
2023-01-24 04:50:01.319993: step: 360/469, loss: 0.001363103510811925
2023-01-24 04:50:01.945136: step: 362/469, loss: 0.008959420025348663
2023-01-24 04:50:02.623088: step: 364/469, loss: 0.0260955560952425
2023-01-24 04:50:03.226964: step: 366/469, loss: 0.011731689795851707
2023-01-24 04:50:03.905463: step: 368/469, loss: 0.00877874344587326
2023-01-24 04:50:04.525828: step: 370/469, loss: 0.010402548126876354
2023-01-24 04:50:05.122217: step: 372/469, loss: 0.0006272983155213296
2023-01-24 04:50:05.676653: step: 374/469, loss: 0.01702445186674595
2023-01-24 04:50:06.300762: step: 376/469, loss: 0.00828280858695507
2023-01-24 04:50:06.891048: step: 378/469, loss: 0.040847986936569214
2023-01-24 04:50:07.475456: step: 380/469, loss: 0.009576273150742054
2023-01-24 04:50:08.138046: step: 382/469, loss: 0.015475092455744743
2023-01-24 04:50:08.749342: step: 384/469, loss: 0.0035011260770261288
2023-01-24 04:50:09.315403: step: 386/469, loss: 0.001737115322612226
2023-01-24 04:50:09.988778: step: 388/469, loss: 0.009717884473502636
2023-01-24 04:50:10.599490: step: 390/469, loss: 0.011555822566151619
2023-01-24 04:50:11.202633: step: 392/469, loss: 0.003415114479139447
2023-01-24 04:50:11.897295: step: 394/469, loss: 0.0021645131055265665
2023-01-24 04:50:12.556982: step: 396/469, loss: 0.0073388307355344296
2023-01-24 04:50:13.201477: step: 398/469, loss: 0.030330680310726166
2023-01-24 04:50:13.793775: step: 400/469, loss: 0.007304188329726458
2023-01-24 04:50:14.418173: step: 402/469, loss: 0.03339911997318268
2023-01-24 04:50:15.045279: step: 404/469, loss: 0.005928943865001202
2023-01-24 04:50:15.777982: step: 406/469, loss: 0.011872672475874424
2023-01-24 04:50:16.391270: step: 408/469, loss: 0.006231411825865507
2023-01-24 04:50:16.992822: step: 410/469, loss: 0.00125815998762846
2023-01-24 04:50:17.606528: step: 412/469, loss: 0.007493156939744949
2023-01-24 04:50:18.255008: step: 414/469, loss: 0.014170171692967415
2023-01-24 04:50:18.875625: step: 416/469, loss: 0.03449777141213417
2023-01-24 04:50:19.499063: step: 418/469, loss: 0.0023047924041748047
2023-01-24 04:50:20.090888: step: 420/469, loss: 0.023593971505761147
2023-01-24 04:50:20.813534: step: 422/469, loss: 0.10681014508008957
2023-01-24 04:50:21.434201: step: 424/469, loss: 0.020520251244306564
2023-01-24 04:50:22.000696: step: 426/469, loss: 0.0009596815798431635
2023-01-24 04:50:22.637219: step: 428/469, loss: 0.026223665103316307
2023-01-24 04:50:23.232886: step: 430/469, loss: 0.013746678829193115
2023-01-24 04:50:23.910710: step: 432/469, loss: 0.004561530891805887
2023-01-24 04:50:24.621238: step: 434/469, loss: 0.01142672449350357
2023-01-24 04:50:25.184371: step: 436/469, loss: 0.0047954595647752285
2023-01-24 04:50:25.745138: step: 438/469, loss: 0.0055572581477463245
2023-01-24 04:50:26.463754: step: 440/469, loss: 0.033278938382864
2023-01-24 04:50:27.073297: step: 442/469, loss: 0.04738524928689003
2023-01-24 04:50:27.686060: step: 444/469, loss: 0.024530841037631035
2023-01-24 04:50:28.262015: step: 446/469, loss: 0.007115528918802738
2023-01-24 04:50:28.907965: step: 448/469, loss: 0.15645791590213776
2023-01-24 04:50:29.601625: step: 450/469, loss: 0.06723763048648834
2023-01-24 04:50:30.185500: step: 452/469, loss: 0.006464261561632156
2023-01-24 04:50:30.792062: step: 454/469, loss: 0.0035614504013210535
2023-01-24 04:50:31.445539: step: 456/469, loss: 0.05196283385157585
2023-01-24 04:50:32.088828: step: 458/469, loss: 0.04066628962755203
2023-01-24 04:50:32.691112: step: 460/469, loss: 0.011683044955134392
2023-01-24 04:50:33.328861: step: 462/469, loss: 0.0032291521783918142
2023-01-24 04:50:33.853016: step: 464/469, loss: 0.0010921609355136752
2023-01-24 04:50:34.413609: step: 466/469, loss: 0.0028939854819327593
2023-01-24 04:50:35.060928: step: 468/469, loss: 0.02308109775185585
2023-01-24 04:50:35.675829: step: 470/469, loss: 0.001572037348523736
2023-01-24 04:50:36.296490: step: 472/469, loss: 0.002705646213144064
2023-01-24 04:50:36.877079: step: 474/469, loss: 0.0002364056126680225
2023-01-24 04:50:37.464279: step: 476/469, loss: 0.04919661581516266
2023-01-24 04:50:38.031618: step: 478/469, loss: 0.015851834788918495
2023-01-24 04:50:38.640491: step: 480/469, loss: 0.0008903385605663061
2023-01-24 04:50:39.180524: step: 482/469, loss: 0.0006177516188472509
2023-01-24 04:50:39.762775: step: 484/469, loss: 0.009375235997140408
2023-01-24 04:50:40.389405: step: 486/469, loss: 0.004601579159498215
2023-01-24 04:50:41.014107: step: 488/469, loss: 0.015804223716259003
2023-01-24 04:50:41.703311: step: 490/469, loss: 0.018202630802989006
2023-01-24 04:50:42.377512: step: 492/469, loss: 0.00025559458299539983
2023-01-24 04:50:43.081293: step: 494/469, loss: 0.004796760622411966
2023-01-24 04:50:43.778880: step: 496/469, loss: 0.012133373878896236
2023-01-24 04:50:44.391504: step: 498/469, loss: 0.19531692564487457
2023-01-24 04:50:45.006038: step: 500/469, loss: 0.007474957499653101
2023-01-24 04:50:45.591024: step: 502/469, loss: 0.0008940544212237
2023-01-24 04:50:46.402999: step: 504/469, loss: 0.0025691776536405087
2023-01-24 04:50:47.001252: step: 506/469, loss: 0.050084542483091354
2023-01-24 04:50:47.617244: step: 508/469, loss: 0.005334364250302315
2023-01-24 04:50:48.212684: step: 510/469, loss: 0.0012737170327454805
2023-01-24 04:50:48.825511: step: 512/469, loss: 0.02926657348871231
2023-01-24 04:50:49.457851: step: 514/469, loss: 0.005524573847651482
2023-01-24 04:50:50.003022: step: 516/469, loss: 0.022212618961930275
2023-01-24 04:50:50.651267: step: 518/469, loss: 0.02893757075071335
2023-01-24 04:50:51.282201: step: 520/469, loss: 0.005629885010421276
2023-01-24 04:50:51.927293: step: 522/469, loss: 0.024496033787727356
2023-01-24 04:50:52.608969: step: 524/469, loss: 0.010469109751284122
2023-01-24 04:50:53.287436: step: 526/469, loss: 0.001399482600390911
2023-01-24 04:50:53.935535: step: 528/469, loss: 0.008184348233044147
2023-01-24 04:50:54.550371: step: 530/469, loss: 0.0072659580036997795
2023-01-24 04:50:55.181598: step: 532/469, loss: 0.004504271317273378
2023-01-24 04:50:55.732954: step: 534/469, loss: 0.0009724801639094949
2023-01-24 04:50:56.366455: step: 536/469, loss: 0.06959446519613266
2023-01-24 04:50:56.970547: step: 538/469, loss: 0.00033104713656939566
2023-01-24 04:50:57.567180: step: 540/469, loss: 0.009299339726567268
2023-01-24 04:50:58.138634: step: 542/469, loss: 0.008532840758562088
2023-01-24 04:50:58.762050: step: 544/469, loss: 0.00047709012869745493
2023-01-24 04:50:59.348047: step: 546/469, loss: 0.0034982587676495314
2023-01-24 04:50:59.992856: step: 548/469, loss: 0.013692804612219334
2023-01-24 04:51:00.585675: step: 550/469, loss: 0.006670364178717136
2023-01-24 04:51:01.224416: step: 552/469, loss: 0.0017971234628930688
2023-01-24 04:51:01.914427: step: 554/469, loss: 0.0021280001383274794
2023-01-24 04:51:02.533629: step: 556/469, loss: 0.05228687450289726
2023-01-24 04:51:03.207439: step: 558/469, loss: 0.03364037722349167
2023-01-24 04:51:03.807528: step: 560/469, loss: 0.04131297022104263
2023-01-24 04:51:04.404692: step: 562/469, loss: 0.019409582018852234
2023-01-24 04:51:05.136420: step: 564/469, loss: 0.004515229724347591
2023-01-24 04:51:05.809649: step: 566/469, loss: 0.001105062779970467
2023-01-24 04:51:06.425497: step: 568/469, loss: 0.00010040286724688485
2023-01-24 04:51:07.070662: step: 570/469, loss: 0.02487722598016262
2023-01-24 04:51:07.732012: step: 572/469, loss: 0.0003732540353666991
2023-01-24 04:51:08.334894: step: 574/469, loss: 0.021247070282697678
2023-01-24 04:51:08.955353: step: 576/469, loss: 0.043238986283540726
2023-01-24 04:51:09.578808: step: 578/469, loss: 0.0455329567193985
2023-01-24 04:51:10.248051: step: 580/469, loss: 0.043944958597421646
2023-01-24 04:51:10.791337: step: 582/469, loss: 0.021928537636995316
2023-01-24 04:51:11.362166: step: 584/469, loss: 0.019972575828433037
2023-01-24 04:51:11.924974: step: 586/469, loss: 0.05875847488641739
2023-01-24 04:51:12.601614: step: 588/469, loss: 0.020967772230505943
2023-01-24 04:51:13.249078: step: 590/469, loss: 0.03154616057872772
2023-01-24 04:51:13.991788: step: 592/469, loss: 0.049560993909835815
2023-01-24 04:51:14.638320: step: 594/469, loss: 0.004503656178712845
2023-01-24 04:51:15.240938: step: 596/469, loss: 0.026225287467241287
2023-01-24 04:51:15.830674: step: 598/469, loss: 0.012035707011818886
2023-01-24 04:51:16.449792: step: 600/469, loss: 0.052976544946432114
2023-01-24 04:51:17.115362: step: 602/469, loss: 0.004996637813746929
2023-01-24 04:51:17.704950: step: 604/469, loss: 0.004497432615607977
2023-01-24 04:51:18.335065: step: 606/469, loss: 0.0003385764721315354
2023-01-24 04:51:18.962012: step: 608/469, loss: 0.007032254710793495
2023-01-24 04:51:19.581364: step: 610/469, loss: 0.00252163247205317
2023-01-24 04:51:20.198910: step: 612/469, loss: 0.035394471138715744
2023-01-24 04:51:20.832190: step: 614/469, loss: 0.0033063183072954416
2023-01-24 04:51:21.547796: step: 616/469, loss: 0.0018908550264313817
2023-01-24 04:51:22.205440: step: 618/469, loss: 0.01915391907095909
2023-01-24 04:51:22.787110: step: 620/469, loss: 0.010002137161791325
2023-01-24 04:51:23.343370: step: 622/469, loss: 0.013907020911574364
2023-01-24 04:51:23.964700: step: 624/469, loss: 0.15572293102741241
2023-01-24 04:51:24.630567: step: 626/469, loss: 0.03410392627120018
2023-01-24 04:51:25.232083: step: 628/469, loss: 0.012967683374881744
2023-01-24 04:51:25.821937: step: 630/469, loss: 0.06055464968085289
2023-01-24 04:51:26.469322: step: 632/469, loss: 0.03310849890112877
2023-01-24 04:51:27.060993: step: 634/469, loss: 0.0019108057022094727
2023-01-24 04:51:27.807739: step: 636/469, loss: 0.004113891627639532
2023-01-24 04:51:28.453280: step: 638/469, loss: 0.07549567520618439
2023-01-24 04:51:29.077193: step: 640/469, loss: 0.016415109857916832
2023-01-24 04:51:29.684439: step: 642/469, loss: 0.04454901069402695
2023-01-24 04:51:30.305250: step: 644/469, loss: 7.959224603837356e-05
2023-01-24 04:51:30.943577: step: 646/469, loss: 0.21042108535766602
2023-01-24 04:51:31.653840: step: 648/469, loss: 0.02510662004351616
2023-01-24 04:51:32.240525: step: 650/469, loss: 0.002376752905547619
2023-01-24 04:51:32.898509: step: 652/469, loss: 0.040509264916181564
2023-01-24 04:51:33.512389: step: 654/469, loss: 0.019773663952946663
2023-01-24 04:51:34.070123: step: 656/469, loss: 0.0060656084679067135
2023-01-24 04:51:34.723654: step: 658/469, loss: 0.004794066771864891
2023-01-24 04:51:35.337831: step: 660/469, loss: 0.3114969730377197
2023-01-24 04:51:35.955239: step: 662/469, loss: 0.011619108729064465
2023-01-24 04:51:36.639310: step: 664/469, loss: 0.0051984163001179695
2023-01-24 04:51:37.190134: step: 666/469, loss: 0.034609321504831314
2023-01-24 04:51:37.811017: step: 668/469, loss: 0.011906139552593231
2023-01-24 04:51:38.429709: step: 670/469, loss: 0.007531465031206608
2023-01-24 04:51:39.083029: step: 672/469, loss: 0.008113306947052479
2023-01-24 04:51:39.684181: step: 674/469, loss: 0.009066373109817505
2023-01-24 04:51:40.265246: step: 676/469, loss: 0.020657051354646683
2023-01-24 04:51:40.813546: step: 678/469, loss: 0.007757657673209906
2023-01-24 04:51:41.465550: step: 680/469, loss: 0.0023668238427489996
2023-01-24 04:51:42.193715: step: 682/469, loss: 0.01625860668718815
2023-01-24 04:51:42.780337: step: 684/469, loss: 0.05641509220004082
2023-01-24 04:51:43.353945: step: 686/469, loss: 0.0011308124521747231
2023-01-24 04:51:43.960453: step: 688/469, loss: 0.004692739807069302
2023-01-24 04:51:44.629747: step: 690/469, loss: 0.006711769849061966
2023-01-24 04:51:45.321194: step: 692/469, loss: 0.028482874855399132
2023-01-24 04:51:45.945941: step: 694/469, loss: 0.0388733334839344
2023-01-24 04:51:46.514715: step: 696/469, loss: 0.0009056212147697806
2023-01-24 04:51:47.172432: step: 698/469, loss: 0.05017658323049545
2023-01-24 04:51:47.759456: step: 700/469, loss: 0.04181431978940964
2023-01-24 04:51:48.414353: step: 702/469, loss: 0.005831209011375904
2023-01-24 04:51:49.009029: step: 704/469, loss: 0.00044027509284205735
2023-01-24 04:51:49.605403: step: 706/469, loss: 0.008657765574753284
2023-01-24 04:51:50.207446: step: 708/469, loss: 0.011135912500321865
2023-01-24 04:51:50.811089: step: 710/469, loss: 0.001807711785659194
2023-01-24 04:51:51.385127: step: 712/469, loss: 0.8846816420555115
2023-01-24 04:51:51.999086: step: 714/469, loss: 0.0006951538962312043
2023-01-24 04:51:52.536372: step: 716/469, loss: 0.014210399240255356
2023-01-24 04:51:53.280924: step: 718/469, loss: 0.018556321039795876
2023-01-24 04:51:53.908994: step: 720/469, loss: 0.014850894920527935
2023-01-24 04:51:54.530524: step: 722/469, loss: 0.001306203892454505
2023-01-24 04:51:55.143337: step: 724/469, loss: 0.01426657848060131
2023-01-24 04:51:55.716033: step: 726/469, loss: 0.0008523244177922606
2023-01-24 04:51:56.410641: step: 728/469, loss: 0.047879546880722046
2023-01-24 04:51:57.049907: step: 730/469, loss: 0.11118033528327942
2023-01-24 04:51:57.683990: step: 732/469, loss: 0.022916695103049278
2023-01-24 04:51:58.309661: step: 734/469, loss: 0.0035462328232824802
2023-01-24 04:51:58.934583: step: 736/469, loss: 0.036676790565252304
2023-01-24 04:51:59.610124: step: 738/469, loss: 0.08634741604328156
2023-01-24 04:52:00.292207: step: 740/469, loss: 0.02391703985631466
2023-01-24 04:52:00.869408: step: 742/469, loss: 0.0008842243114486337
2023-01-24 04:52:01.463803: step: 744/469, loss: 0.0008636997663415968
2023-01-24 04:52:02.079928: step: 746/469, loss: 0.0009479793952777982
2023-01-24 04:52:02.690825: step: 748/469, loss: 0.0065277642570436
2023-01-24 04:52:03.268501: step: 750/469, loss: 0.0010879590408876538
2023-01-24 04:52:03.901044: step: 752/469, loss: 0.04227452352643013
2023-01-24 04:52:04.528731: step: 754/469, loss: 0.027240905910730362
2023-01-24 04:52:05.195083: step: 756/469, loss: 0.026949815452098846
2023-01-24 04:52:05.789469: step: 758/469, loss: 0.010922363959252834
2023-01-24 04:52:06.387019: step: 760/469, loss: 0.4779205322265625
2023-01-24 04:52:06.955573: step: 762/469, loss: 0.02142428234219551
2023-01-24 04:52:07.624736: step: 764/469, loss: 0.007394219283014536
2023-01-24 04:52:08.203992: step: 766/469, loss: 0.004700392950326204
2023-01-24 04:52:08.803722: step: 768/469, loss: 0.02452561818063259
2023-01-24 04:52:09.410255: step: 770/469, loss: 0.09465805441141129
2023-01-24 04:52:10.046806: step: 772/469, loss: 0.04306073486804962
2023-01-24 04:52:10.659816: step: 774/469, loss: 0.013418346643447876
2023-01-24 04:52:11.266615: step: 776/469, loss: 0.01829378493130207
2023-01-24 04:52:11.884799: step: 778/469, loss: 0.0048456392250955105
2023-01-24 04:52:12.524529: step: 780/469, loss: 0.07697334885597229
2023-01-24 04:52:13.144937: step: 782/469, loss: 0.01613239385187626
2023-01-24 04:52:13.846109: step: 784/469, loss: 0.007246014196425676
2023-01-24 04:52:14.456927: step: 786/469, loss: 0.06801823526620865
2023-01-24 04:52:15.053197: step: 788/469, loss: 0.011144820600748062
2023-01-24 04:52:15.656054: step: 790/469, loss: 0.012843788601458073
2023-01-24 04:52:16.301334: step: 792/469, loss: 0.01382353063672781
2023-01-24 04:52:16.873290: step: 794/469, loss: 0.001624260563403368
2023-01-24 04:52:17.604920: step: 796/469, loss: 0.0030050971545279026
2023-01-24 04:52:18.173327: step: 798/469, loss: 0.001356614171527326
2023-01-24 04:52:18.776210: step: 800/469, loss: 0.07368076592683792
2023-01-24 04:52:19.457147: step: 802/469, loss: 0.01569214276969433
2023-01-24 04:52:20.071647: step: 804/469, loss: 0.024293113499879837
2023-01-24 04:52:20.716188: step: 806/469, loss: 0.013290208764374256
2023-01-24 04:52:21.304541: step: 808/469, loss: 0.04374516382813454
2023-01-24 04:52:21.989035: step: 810/469, loss: 0.04349565505981445
2023-01-24 04:52:22.660523: step: 812/469, loss: 0.022485224530100822
2023-01-24 04:52:23.291132: step: 814/469, loss: 0.030861996114253998
2023-01-24 04:52:23.847707: step: 816/469, loss: 3.837492840830237e-05
2023-01-24 04:52:24.457563: step: 818/469, loss: 0.026942269876599312
2023-01-24 04:52:25.064188: step: 820/469, loss: 0.029813630506396294
2023-01-24 04:52:25.681996: step: 822/469, loss: 0.04226364195346832
2023-01-24 04:52:26.405218: step: 824/469, loss: 0.00019053473079111427
2023-01-24 04:52:27.017843: step: 826/469, loss: 0.6574000120162964
2023-01-24 04:52:27.651804: step: 828/469, loss: 0.010332663543522358
2023-01-24 04:52:28.258822: step: 830/469, loss: 0.04169304668903351
2023-01-24 04:52:28.896224: step: 832/469, loss: 0.0004893785226158798
2023-01-24 04:52:29.505677: step: 834/469, loss: 0.005573753267526627
2023-01-24 04:52:30.197039: step: 836/469, loss: 0.3874082565307617
2023-01-24 04:52:30.890001: step: 838/469, loss: 0.02727372571825981
2023-01-24 04:52:31.574848: step: 840/469, loss: 0.018294041976332664
2023-01-24 04:52:32.231772: step: 842/469, loss: 0.025934560224413872
2023-01-24 04:52:32.860907: step: 844/469, loss: 0.47449129819869995
2023-01-24 04:52:33.428037: step: 846/469, loss: 0.0019088794942945242
2023-01-24 04:52:34.092258: step: 848/469, loss: 0.0978962630033493
2023-01-24 04:52:34.668089: step: 850/469, loss: 0.0023534628562629223
2023-01-24 04:52:35.296653: step: 852/469, loss: 0.024740392342209816
2023-01-24 04:52:35.920117: step: 854/469, loss: 0.0012690417934209108
2023-01-24 04:52:36.505518: step: 856/469, loss: 0.014940101653337479
2023-01-24 04:52:37.160552: step: 858/469, loss: 0.053182702511548996
2023-01-24 04:52:37.786071: step: 860/469, loss: 0.04499712586402893
2023-01-24 04:52:38.329774: step: 862/469, loss: 0.0002868360315915197
2023-01-24 04:52:39.030735: step: 864/469, loss: 0.015457911416888237
2023-01-24 04:52:39.660084: step: 866/469, loss: 0.07289420068264008
2023-01-24 04:52:40.335322: step: 868/469, loss: 0.38829493522644043
2023-01-24 04:52:40.897944: step: 870/469, loss: 0.001543375663459301
2023-01-24 04:52:41.536777: step: 872/469, loss: 0.001180908177047968
2023-01-24 04:52:42.210390: step: 874/469, loss: 0.011447690427303314
2023-01-24 04:52:42.889370: step: 876/469, loss: 0.0020356171298772097
2023-01-24 04:52:43.548193: step: 878/469, loss: 0.0011502087581902742
2023-01-24 04:52:44.180350: step: 880/469, loss: 0.001193191739730537
2023-01-24 04:52:44.812208: step: 882/469, loss: 0.01965019293129444
2023-01-24 04:52:45.347704: step: 884/469, loss: 0.0037854595575481653
2023-01-24 04:52:45.948455: step: 886/469, loss: 0.021804021671414375
2023-01-24 04:52:46.591348: step: 888/469, loss: 0.04215393215417862
2023-01-24 04:52:47.210061: step: 890/469, loss: 0.016078893095254898
2023-01-24 04:52:47.886973: step: 892/469, loss: 0.0015113918343558908
2023-01-24 04:52:48.502986: step: 894/469, loss: 0.005867231171578169
2023-01-24 04:52:49.132493: step: 896/469, loss: 0.005106255877763033
2023-01-24 04:52:49.738588: step: 898/469, loss: 0.008018449880182743
2023-01-24 04:52:50.445211: step: 900/469, loss: 0.03355848044157028
2023-01-24 04:52:51.063060: step: 902/469, loss: 0.015441610477864742
2023-01-24 04:52:51.658086: step: 904/469, loss: 0.011782408691942692
2023-01-24 04:52:52.311864: step: 906/469, loss: 0.001954123843461275
2023-01-24 04:52:52.966649: step: 908/469, loss: 0.04112967476248741
2023-01-24 04:52:53.599399: step: 910/469, loss: 0.04850506782531738
2023-01-24 04:52:54.206914: step: 912/469, loss: 0.0682452842593193
2023-01-24 04:52:54.789346: step: 914/469, loss: 0.01938783936202526
2023-01-24 04:52:55.425612: step: 916/469, loss: 0.012103945016860962
2023-01-24 04:52:56.069827: step: 918/469, loss: 0.06571812927722931
2023-01-24 04:52:56.702222: step: 920/469, loss: 0.005671871360391378
2023-01-24 04:52:57.300416: step: 922/469, loss: 0.006516584195196629
2023-01-24 04:52:57.850091: step: 924/469, loss: 0.0010232835775241256
2023-01-24 04:52:58.390882: step: 926/469, loss: 0.0010701266583055258
2023-01-24 04:52:58.963958: step: 928/469, loss: 0.0016947818221524358
2023-01-24 04:52:59.557485: step: 930/469, loss: 0.0014523242134600878
2023-01-24 04:53:00.273795: step: 932/469, loss: 0.00045429577585309744
2023-01-24 04:53:00.854794: step: 934/469, loss: 0.023384835571050644
2023-01-24 04:53:01.459776: step: 936/469, loss: 0.0554439052939415
2023-01-24 04:53:02.095933: step: 938/469, loss: 0.0295626912266016
==================================================
Loss: 0.034
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31021728515625, 'r': 0.30138757115749526, 'f1': 0.3057386910490857}, 'combined': 0.22528114077301048, 'epoch': 31}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3437021693669004, 'r': 0.2572263262050545, 'f1': 0.29424215022723654}, 'combined': 0.16049571830576537, 'epoch': 31}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3181532949981745, 'r': 0.3006458081766431, 'f1': 0.3091518847006652}, 'combined': 0.22779612556891118, 'epoch': 31}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3461852666366555, 'r': 0.2565508380381436, 'f1': 0.294703169706454}, 'combined': 0.1607471834762476, 'epoch': 31}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30710190568475454, 'r': 0.3006918089816572, 'f1': 0.3038630552892298}, 'combined': 0.2238990933710114, 'epoch': 31}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3414380034433991, 'r': 0.26053000445726887, 'f1': 0.29554675129402685}, 'combined': 0.161207318887651, 'epoch': 31}
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': 31}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.34523809523809523, 'r': 0.31521739130434784, 'f1': 0.3295454545454546}, 'combined': 0.1647727272727273, 'epoch': 31}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.625, 'r': 0.1724137931034483, 'f1': 0.2702702702702703}, 'combined': 0.18018018018018017, 'epoch': 31}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 04:55:48.217965: step: 2/469, loss: 0.03749991953372955
2023-01-24 04:55:48.838134: step: 4/469, loss: 0.017268238589167595
2023-01-24 04:55:49.433019: step: 6/469, loss: 0.001208505011163652
2023-01-24 04:55:50.049260: step: 8/469, loss: 0.01648283377289772
2023-01-24 04:55:50.717665: step: 10/469, loss: 0.00220747129060328
2023-01-24 04:55:51.368376: step: 12/469, loss: 0.00031065926305018365
2023-01-24 04:55:52.026060: step: 14/469, loss: 0.1470402330160141
2023-01-24 04:55:52.583707: step: 16/469, loss: 0.020634595304727554
2023-01-24 04:55:53.241017: step: 18/469, loss: 0.0004752243112307042
2023-01-24 04:55:53.881737: step: 20/469, loss: 0.016507146880030632
2023-01-24 04:55:54.460568: step: 22/469, loss: 0.07745123654603958
2023-01-24 04:55:55.048262: step: 24/469, loss: 0.04096395522356033
2023-01-24 04:55:55.695047: step: 26/469, loss: 2.915346522058826e-05
2023-01-24 04:55:56.313856: step: 28/469, loss: 0.006948579102754593
2023-01-24 04:55:56.916829: step: 30/469, loss: 0.030988536775112152
2023-01-24 04:55:57.578364: step: 32/469, loss: 0.001262485166080296
2023-01-24 04:55:58.181363: step: 34/469, loss: 0.02379172295331955
2023-01-24 04:55:58.767285: step: 36/469, loss: 0.006459326948970556
2023-01-24 04:55:59.414067: step: 38/469, loss: 0.00017157568072434515
2023-01-24 04:56:00.074761: step: 40/469, loss: 0.0030621082987636328
2023-01-24 04:56:00.765190: step: 42/469, loss: 8.642600732855499e-05
2023-01-24 04:56:01.402244: step: 44/469, loss: 0.08777878433465958
2023-01-24 04:56:01.956602: step: 46/469, loss: 0.0026939958333969116
2023-01-24 04:56:02.562968: step: 48/469, loss: 0.4211970269680023
2023-01-24 04:56:03.184917: step: 50/469, loss: 3.9609494706382975e-05
2023-01-24 04:56:03.778186: step: 52/469, loss: 0.02289861999452114
2023-01-24 04:56:04.413741: step: 54/469, loss: 0.006645299959927797
2023-01-24 04:56:05.030751: step: 56/469, loss: 0.026295255869627
2023-01-24 04:56:05.671216: step: 58/469, loss: 0.0011924994178116322
2023-01-24 04:56:06.259868: step: 60/469, loss: 0.08294352889060974
2023-01-24 04:56:06.872799: step: 62/469, loss: 0.004066620022058487
2023-01-24 04:56:07.450212: step: 64/469, loss: 0.22339172661304474
2023-01-24 04:56:08.038846: step: 66/469, loss: 0.007126346230506897
2023-01-24 04:56:08.657704: step: 68/469, loss: 0.01773212105035782
2023-01-24 04:56:09.260689: step: 70/469, loss: 0.0011778019834309816
2023-01-24 04:56:09.906526: step: 72/469, loss: 0.1522241234779358
2023-01-24 04:56:10.484270: step: 74/469, loss: 0.0004932772717438638
2023-01-24 04:56:11.069571: step: 76/469, loss: 0.011974997818470001
2023-01-24 04:56:11.663175: step: 78/469, loss: 0.03133000060915947
2023-01-24 04:56:12.407616: step: 80/469, loss: 0.023759806528687477
2023-01-24 04:56:13.102096: step: 82/469, loss: 0.017190126702189445
2023-01-24 04:56:13.671187: step: 84/469, loss: 0.044721778482198715
2023-01-24 04:56:14.369401: step: 86/469, loss: 0.019774969667196274
2023-01-24 04:56:15.011218: step: 88/469, loss: 0.012061896733939648
2023-01-24 04:56:15.592139: step: 90/469, loss: 0.004765648394823074
2023-01-24 04:56:16.261313: step: 92/469, loss: 0.08470029383897781
2023-01-24 04:56:16.890203: step: 94/469, loss: 0.4178975224494934
2023-01-24 04:56:17.472059: step: 96/469, loss: 0.005485690664499998
2023-01-24 04:56:18.047732: step: 98/469, loss: 0.0009674173779785633
2023-01-24 04:56:18.659090: step: 100/469, loss: 0.004112924449145794
2023-01-24 04:56:19.217618: step: 102/469, loss: 0.00045645286445505917
2023-01-24 04:56:19.828500: step: 104/469, loss: 0.0058275870978832245
2023-01-24 04:56:20.406770: step: 106/469, loss: 0.004125871229916811
2023-01-24 04:56:21.028996: step: 108/469, loss: 0.03037143498659134
2023-01-24 04:56:21.641983: step: 110/469, loss: 0.06216638907790184
2023-01-24 04:56:22.231293: step: 112/469, loss: 0.005116002634167671
2023-01-24 04:56:22.841995: step: 114/469, loss: 0.0014115545200183988
2023-01-24 04:56:23.402389: step: 116/469, loss: 0.0010772172827273607
2023-01-24 04:56:24.010724: step: 118/469, loss: 0.00050545041449368
2023-01-24 04:56:24.747448: step: 120/469, loss: 0.000938965764362365
2023-01-24 04:56:25.403064: step: 122/469, loss: 0.007019012235105038
2023-01-24 04:56:25.968604: step: 124/469, loss: 0.0028248117305338383
2023-01-24 04:56:26.498773: step: 126/469, loss: 0.03765726834535599
2023-01-24 04:56:27.185459: step: 128/469, loss: 0.002961465623229742
2023-01-24 04:56:27.858213: step: 130/469, loss: 0.023719433695077896
2023-01-24 04:56:28.487224: step: 132/469, loss: 0.027861934155225754
2023-01-24 04:56:29.084836: step: 134/469, loss: 0.0019629402086138725
2023-01-24 04:56:29.665251: step: 136/469, loss: 0.018162770196795464
2023-01-24 04:56:30.264635: step: 138/469, loss: 0.008055283688008785
2023-01-24 04:56:30.916931: step: 140/469, loss: 0.007368750870227814
2023-01-24 04:56:31.560766: step: 142/469, loss: 0.041566379368305206
2023-01-24 04:56:32.161293: step: 144/469, loss: 0.016668105497956276
2023-01-24 04:56:32.755769: step: 146/469, loss: 0.0253001619130373
2023-01-24 04:56:33.343915: step: 148/469, loss: 0.005218131933361292
2023-01-24 04:56:34.004396: step: 150/469, loss: 0.0009144657524302602
2023-01-24 04:56:34.648360: step: 152/469, loss: 0.017045224085450172
2023-01-24 04:56:35.377200: step: 154/469, loss: 0.03626452386379242
2023-01-24 04:56:35.933949: step: 156/469, loss: 0.00015720822557341307
2023-01-24 04:56:36.521532: step: 158/469, loss: 0.013244305737316608
2023-01-24 04:56:37.143344: step: 160/469, loss: 0.002182579832151532
2023-01-24 04:56:37.763681: step: 162/469, loss: 0.005379943177103996
2023-01-24 04:56:38.388088: step: 164/469, loss: 0.00024298630887642503
2023-01-24 04:56:38.987832: step: 166/469, loss: 0.002628966700285673
2023-01-24 04:56:39.598819: step: 168/469, loss: 0.18549330532550812
2023-01-24 04:56:40.184850: step: 170/469, loss: 0.009937564842402935
2023-01-24 04:56:40.897305: step: 172/469, loss: 0.0010264319134876132
2023-01-24 04:56:41.634495: step: 174/469, loss: 0.005788552109152079
2023-01-24 04:56:42.307400: step: 176/469, loss: 0.0041469489224255085
2023-01-24 04:56:42.950552: step: 178/469, loss: 0.003415116108953953
2023-01-24 04:56:43.656559: step: 180/469, loss: 0.007839956320822239
2023-01-24 04:56:44.302690: step: 182/469, loss: 0.0027799762319773436
2023-01-24 04:56:44.955060: step: 184/469, loss: 0.016197774559259415
2023-01-24 04:56:45.482471: step: 186/469, loss: 0.25818222761154175
2023-01-24 04:56:46.169549: step: 188/469, loss: 0.025767633691430092
2023-01-24 04:56:46.753439: step: 190/469, loss: 0.005767365917563438
2023-01-24 04:56:47.346707: step: 192/469, loss: 0.010001887567341328
2023-01-24 04:56:47.978323: step: 194/469, loss: 0.014682997018098831
2023-01-24 04:56:48.611158: step: 196/469, loss: 0.0005096681998111308
2023-01-24 04:56:49.308548: step: 198/469, loss: 0.00389700080268085
2023-01-24 04:56:49.996684: step: 200/469, loss: 0.01446735579520464
2023-01-24 04:56:50.612670: step: 202/469, loss: 0.005991010461002588
2023-01-24 04:56:51.241056: step: 204/469, loss: 0.0007895565358921885
2023-01-24 04:56:51.912332: step: 206/469, loss: 0.02897719107568264
2023-01-24 04:56:52.640755: step: 208/469, loss: 0.004441920667886734
2023-01-24 04:56:53.237486: step: 210/469, loss: 0.012744102627038956
2023-01-24 04:56:53.875887: step: 212/469, loss: 0.0015204461524263024
2023-01-24 04:56:54.486461: step: 214/469, loss: 0.005202990025281906
2023-01-24 04:56:55.056536: step: 216/469, loss: 0.036313001066446304
2023-01-24 04:56:55.687908: step: 218/469, loss: 0.04497510567307472
2023-01-24 04:56:56.317495: step: 220/469, loss: 0.004818841814994812
2023-01-24 04:56:56.954593: step: 222/469, loss: 0.0025633235927671194
2023-01-24 04:56:57.510637: step: 224/469, loss: 0.0008717576856724918
2023-01-24 04:56:58.216135: step: 226/469, loss: 0.013081683777272701
2023-01-24 04:56:58.796877: step: 228/469, loss: 0.03065168298780918
2023-01-24 04:56:59.412342: step: 230/469, loss: 0.0028354807291179895
2023-01-24 04:57:00.005889: step: 232/469, loss: 0.0025457723531872034
2023-01-24 04:57:00.712154: step: 234/469, loss: 0.002082462888211012
2023-01-24 04:57:01.298422: step: 236/469, loss: 0.001847420004196465
2023-01-24 04:57:01.875501: step: 238/469, loss: 5.1690582040464506e-05
2023-01-24 04:57:02.462571: step: 240/469, loss: 0.006741645745933056
2023-01-24 04:57:03.038687: step: 242/469, loss: 0.013064516708254814
2023-01-24 04:57:03.735305: step: 244/469, loss: 0.018380461260676384
2023-01-24 04:57:04.394021: step: 246/469, loss: 0.004879888147115707
2023-01-24 04:57:04.990079: step: 248/469, loss: 0.017948638647794724
2023-01-24 04:57:05.557550: step: 250/469, loss: 0.018873173743486404
2023-01-24 04:57:06.238434: step: 252/469, loss: 0.0069093527272343636
2023-01-24 04:57:06.893177: step: 254/469, loss: 0.1195477694272995
2023-01-24 04:57:07.464551: step: 256/469, loss: 0.010812277905642986
2023-01-24 04:57:08.144366: step: 258/469, loss: 0.018889935687184334
2023-01-24 04:57:08.811837: step: 260/469, loss: 0.017336001619696617
2023-01-24 04:57:09.467039: step: 262/469, loss: 0.0010860683396458626
2023-01-24 04:57:10.093177: step: 264/469, loss: 0.0021146717481315136
2023-01-24 04:57:10.752249: step: 266/469, loss: 0.02262805961072445
2023-01-24 04:57:11.382615: step: 268/469, loss: 0.002259948058053851
2023-01-24 04:57:12.004694: step: 270/469, loss: 0.0009311236790381372
2023-01-24 04:57:12.668391: step: 272/469, loss: 0.01470889151096344
2023-01-24 04:57:13.357725: step: 274/469, loss: 0.01056294422596693
2023-01-24 04:57:13.903472: step: 276/469, loss: 0.06171771138906479
2023-01-24 04:57:14.546467: step: 278/469, loss: 0.008005499839782715
2023-01-24 04:57:15.160935: step: 280/469, loss: 0.017640594393014908
2023-01-24 04:57:15.758037: step: 282/469, loss: 0.014186647720634937
2023-01-24 04:57:16.307554: step: 284/469, loss: 0.008060427382588387
2023-01-24 04:57:16.900283: step: 286/469, loss: 0.01983780786395073
2023-01-24 04:57:17.452345: step: 288/469, loss: 0.015098470263183117
2023-01-24 04:57:18.012975: step: 290/469, loss: 0.0008657456492073834
2023-01-24 04:57:18.618864: step: 292/469, loss: 0.0006265053525567055
2023-01-24 04:57:19.228487: step: 294/469, loss: 0.024693096056580544
2023-01-24 04:57:19.860946: step: 296/469, loss: 0.2753787636756897
2023-01-24 04:57:20.481051: step: 298/469, loss: 0.003063612151890993
2023-01-24 04:57:21.064740: step: 300/469, loss: 0.0044922903180122375
2023-01-24 04:57:21.792282: step: 302/469, loss: 0.05268428847193718
2023-01-24 04:57:22.393407: step: 304/469, loss: 0.0007777509745210409
2023-01-24 04:57:23.012381: step: 306/469, loss: 0.08876866847276688
2023-01-24 04:57:23.631091: step: 308/469, loss: 0.01490736287087202
2023-01-24 04:57:24.368097: step: 310/469, loss: 0.005947615019977093
2023-01-24 04:57:25.018534: step: 312/469, loss: 0.019858727231621742
2023-01-24 04:57:25.655519: step: 314/469, loss: 0.004382960963994265
2023-01-24 04:57:26.257658: step: 316/469, loss: 0.01166087668389082
2023-01-24 04:57:26.823022: step: 318/469, loss: 0.0028572576120495796
2023-01-24 04:57:27.382704: step: 320/469, loss: 0.11967552453279495
2023-01-24 04:57:28.037305: step: 322/469, loss: 0.007672153413295746
2023-01-24 04:57:28.685676: step: 324/469, loss: 0.023025119677186012
2023-01-24 04:57:29.296798: step: 326/469, loss: 0.012373638339340687
2023-01-24 04:57:29.958307: step: 328/469, loss: 0.9530372023582458
2023-01-24 04:57:30.616401: step: 330/469, loss: 0.6637327075004578
2023-01-24 04:57:31.194583: step: 332/469, loss: 0.009954139590263367
2023-01-24 04:57:31.807799: step: 334/469, loss: 8.420260564889759e-05
2023-01-24 04:57:32.375929: step: 336/469, loss: 0.00999933946877718
2023-01-24 04:57:32.975043: step: 338/469, loss: 0.01693165861070156
2023-01-24 04:57:33.627736: step: 340/469, loss: 0.010749445296823978
2023-01-24 04:57:34.358647: step: 342/469, loss: 2.6861298084259033
2023-01-24 04:57:34.994739: step: 344/469, loss: 0.03646576404571533
2023-01-24 04:57:35.603262: step: 346/469, loss: 9.060656157089397e-05
2023-01-24 04:57:36.244518: step: 348/469, loss: 0.020453309640288353
2023-01-24 04:57:36.857277: step: 350/469, loss: 0.0018417125102132559
2023-01-24 04:57:37.465102: step: 352/469, loss: 0.00860718172043562
2023-01-24 04:57:38.118358: step: 354/469, loss: 0.025369614362716675
2023-01-24 04:57:38.700338: step: 356/469, loss: 0.0002613769320305437
2023-01-24 04:57:39.366310: step: 358/469, loss: 0.007920288480818272
2023-01-24 04:57:40.030755: step: 360/469, loss: 0.02583874575793743
2023-01-24 04:57:40.656078: step: 362/469, loss: 0.0003160881169606
2023-01-24 04:57:41.267795: step: 364/469, loss: 0.007488342467695475
2023-01-24 04:57:41.927702: step: 366/469, loss: 0.009340872056782246
2023-01-24 04:57:42.585980: step: 368/469, loss: 0.04050293192267418
2023-01-24 04:57:43.230585: step: 370/469, loss: 0.0694957748055458
2023-01-24 04:57:43.818807: step: 372/469, loss: 0.0023636994883418083
2023-01-24 04:57:44.393109: step: 374/469, loss: 0.007173544727265835
2023-01-24 04:57:44.998077: step: 376/469, loss: 0.010378501377999783
2023-01-24 04:57:45.643306: step: 378/469, loss: 0.002246354939416051
2023-01-24 04:57:46.269351: step: 380/469, loss: 0.03717915341258049
2023-01-24 04:57:46.886239: step: 382/469, loss: 0.006874177139252424
2023-01-24 04:57:47.451182: step: 384/469, loss: 0.009456251747906208
2023-01-24 04:57:48.053436: step: 386/469, loss: 0.01630944013595581
2023-01-24 04:57:48.676503: step: 388/469, loss: 0.015650790184736252
2023-01-24 04:57:49.317369: step: 390/469, loss: 0.04911442846059799
2023-01-24 04:57:49.945822: step: 392/469, loss: 0.0035679202992469072
2023-01-24 04:57:50.557944: step: 394/469, loss: 0.0008459281525574625
2023-01-24 04:57:51.177235: step: 396/469, loss: 0.03436840698122978
2023-01-24 04:57:51.721950: step: 398/469, loss: 0.009653203189373016
2023-01-24 04:57:52.405789: step: 400/469, loss: 0.002274241531267762
2023-01-24 04:57:53.011261: step: 402/469, loss: 0.006488419137895107
2023-01-24 04:57:53.590330: step: 404/469, loss: 0.0010931938886642456
2023-01-24 04:57:54.259215: step: 406/469, loss: 0.00029615702806040645
2023-01-24 04:57:54.890494: step: 408/469, loss: 0.013120145536959171
2023-01-24 04:57:55.615916: step: 410/469, loss: 0.008972086012363434
2023-01-24 04:57:56.270142: step: 412/469, loss: 0.09995332360267639
2023-01-24 04:57:56.854814: step: 414/469, loss: 0.01970064640045166
2023-01-24 04:57:57.474877: step: 416/469, loss: 0.00018883164739236236
2023-01-24 04:57:58.031684: step: 418/469, loss: 0.0018334169872105122
2023-01-24 04:57:58.686306: step: 420/469, loss: 0.011028261855244637
2023-01-24 04:57:59.299481: step: 422/469, loss: 0.03585797920823097
2023-01-24 04:57:59.962569: step: 424/469, loss: 0.007904846221208572
2023-01-24 04:58:00.558745: step: 426/469, loss: 0.00872550718486309
2023-01-24 04:58:01.200197: step: 428/469, loss: 0.023253824561834335
2023-01-24 04:58:01.889951: step: 430/469, loss: 0.00245981034822762
2023-01-24 04:58:02.457866: step: 432/469, loss: 0.01047658734023571
2023-01-24 04:58:03.033843: step: 434/469, loss: 3.3655032893875614e-07
2023-01-24 04:58:03.722669: step: 436/469, loss: 0.04564597085118294
2023-01-24 04:58:04.358274: step: 438/469, loss: 0.30991101264953613
2023-01-24 04:58:05.021749: step: 440/469, loss: 0.007484719157218933
2023-01-24 04:58:05.620810: step: 442/469, loss: 0.022249378263950348
2023-01-24 04:58:06.222909: step: 444/469, loss: 0.018054088577628136
2023-01-24 04:58:06.819161: step: 446/469, loss: 0.0015145221259444952
2023-01-24 04:58:07.457571: step: 448/469, loss: 0.0004005207447335124
2023-01-24 04:58:08.095140: step: 450/469, loss: 0.0007542406092397869
2023-01-24 04:58:08.761596: step: 452/469, loss: 0.009223207831382751
2023-01-24 04:58:09.378530: step: 454/469, loss: 0.01755375787615776
2023-01-24 04:58:09.970576: step: 456/469, loss: 0.004072573967278004
2023-01-24 04:58:10.562849: step: 458/469, loss: 0.05217577517032623
2023-01-24 04:58:11.165946: step: 460/469, loss: 0.012858073227107525
2023-01-24 04:58:11.814348: step: 462/469, loss: 0.001152542419731617
2023-01-24 04:58:12.435364: step: 464/469, loss: 0.0006960227619856596
2023-01-24 04:58:13.094216: step: 466/469, loss: 0.031560566276311874
2023-01-24 04:58:13.713017: step: 468/469, loss: 0.0060020796954631805
2023-01-24 04:58:14.363467: step: 470/469, loss: 0.049895279109478
2023-01-24 04:58:14.952603: step: 472/469, loss: 0.03689471632242203
2023-01-24 04:58:15.651867: step: 474/469, loss: 0.06906048953533173
2023-01-24 04:58:16.218995: step: 476/469, loss: 0.015291198156774044
2023-01-24 04:58:16.776269: step: 478/469, loss: 0.004548948258161545
2023-01-24 04:58:17.459142: step: 480/469, loss: 0.03188430890440941
2023-01-24 04:58:18.040023: step: 482/469, loss: 0.05921867862343788
2023-01-24 04:58:18.675078: step: 484/469, loss: 0.002240013564005494
2023-01-24 04:58:19.326547: step: 486/469, loss: 0.01722046174108982
2023-01-24 04:58:19.952118: step: 488/469, loss: 0.00045966083416715264
2023-01-24 04:58:20.573612: step: 490/469, loss: 0.004585472866892815
2023-01-24 04:58:21.193889: step: 492/469, loss: 0.005104638170450926
2023-01-24 04:58:21.795689: step: 494/469, loss: 0.012179567478597164
2023-01-24 04:58:22.404949: step: 496/469, loss: 0.0025584574323147535
2023-01-24 04:58:23.023947: step: 498/469, loss: 0.02211659587919712
2023-01-24 04:58:23.693260: step: 500/469, loss: 0.4852209687232971
2023-01-24 04:58:24.247699: step: 502/469, loss: 0.00184117432218045
2023-01-24 04:58:24.854643: step: 504/469, loss: 0.0005285548395477235
2023-01-24 04:58:25.454310: step: 506/469, loss: 0.029422659426927567
2023-01-24 04:58:26.102025: step: 508/469, loss: 0.025827063247561455
2023-01-24 04:58:26.701302: step: 510/469, loss: 0.0012686802074313164
2023-01-24 04:58:27.295687: step: 512/469, loss: 0.05435323715209961
2023-01-24 04:58:27.902238: step: 514/469, loss: 0.03335980325937271
2023-01-24 04:58:28.513304: step: 516/469, loss: 0.0006537021836265922
2023-01-24 04:58:29.151063: step: 518/469, loss: 0.006101388018578291
2023-01-24 04:58:29.767215: step: 520/469, loss: 0.004528559744358063
2023-01-24 04:58:30.390224: step: 522/469, loss: 0.6522846817970276
2023-01-24 04:58:31.089546: step: 524/469, loss: 0.05915721505880356
2023-01-24 04:58:31.761393: step: 526/469, loss: 0.018689153715968132
2023-01-24 04:58:32.419206: step: 528/469, loss: 0.03787685185670853
2023-01-24 04:58:33.050503: step: 530/469, loss: 1.9913724827347323e-05
2023-01-24 04:58:33.730907: step: 532/469, loss: 0.013306287117302418
2023-01-24 04:58:34.317911: step: 534/469, loss: 0.02387900836765766
2023-01-24 04:58:35.036327: step: 536/469, loss: 0.07774024456739426
2023-01-24 04:58:35.580127: step: 538/469, loss: 0.005904316436499357
2023-01-24 04:58:36.186520: step: 540/469, loss: 0.04864424094557762
2023-01-24 04:58:36.900522: step: 542/469, loss: 0.01240241527557373
2023-01-24 04:58:37.522458: step: 544/469, loss: 0.03410211578011513
2023-01-24 04:58:38.139360: step: 546/469, loss: 0.03649758920073509
2023-01-24 04:58:38.740915: step: 548/469, loss: 0.03038223646581173
2023-01-24 04:58:39.407738: step: 550/469, loss: 0.09271855652332306
2023-01-24 04:58:40.083078: step: 552/469, loss: 0.0013210264733061194
2023-01-24 04:58:40.742711: step: 554/469, loss: 0.05411539226770401
2023-01-24 04:58:41.383718: step: 556/469, loss: 0.035361193120479584
2023-01-24 04:58:42.134862: step: 558/469, loss: 0.03385433554649353
2023-01-24 04:58:42.680857: step: 560/469, loss: 8.091592462733388e-05
2023-01-24 04:58:43.422300: step: 562/469, loss: 0.019768020138144493
2023-01-24 04:58:44.107596: step: 564/469, loss: 0.0021043112501502037
2023-01-24 04:58:44.697614: step: 566/469, loss: 0.0042312839068472385
2023-01-24 04:58:45.311667: step: 568/469, loss: 0.0024475210811942816
2023-01-24 04:58:45.902246: step: 570/469, loss: 0.0007352540269494057
2023-01-24 04:58:46.508965: step: 572/469, loss: 0.12982802093029022
2023-01-24 04:58:47.071330: step: 574/469, loss: 0.020285388454794884
2023-01-24 04:58:47.735834: step: 576/469, loss: 0.00894717313349247
2023-01-24 04:58:48.317452: step: 578/469, loss: 0.017607485875487328
2023-01-24 04:58:48.946085: step: 580/469, loss: 0.017055517062544823
2023-01-24 04:58:49.536907: step: 582/469, loss: 0.000573902390897274
2023-01-24 04:58:50.153743: step: 584/469, loss: 0.14255721867084503
2023-01-24 04:58:50.835161: step: 586/469, loss: 0.0030318961944431067
2023-01-24 04:58:51.496707: step: 588/469, loss: 0.004560540895909071
2023-01-24 04:58:52.137156: step: 590/469, loss: 0.032422054558992386
2023-01-24 04:58:52.785060: step: 592/469, loss: 0.2888505458831787
2023-01-24 04:58:53.427207: step: 594/469, loss: 0.09623157232999802
2023-01-24 04:58:54.020448: step: 596/469, loss: 0.008272957056760788
2023-01-24 04:58:54.726796: step: 598/469, loss: 0.07348811626434326
2023-01-24 04:58:55.289918: step: 600/469, loss: 0.005834984127432108
2023-01-24 04:58:55.927275: step: 602/469, loss: 0.01735871471464634
2023-01-24 04:58:56.615396: step: 604/469, loss: 0.0485711395740509
2023-01-24 04:58:57.200770: step: 606/469, loss: 0.059332795441150665
2023-01-24 04:58:57.788899: step: 608/469, loss: 0.005800224840641022
2023-01-24 04:58:58.434255: step: 610/469, loss: 0.019524747505784035
2023-01-24 04:58:59.045339: step: 612/469, loss: 0.76934415102005
2023-01-24 04:58:59.613133: step: 614/469, loss: 0.007277317810803652
2023-01-24 04:59:00.225720: step: 616/469, loss: 0.004504975862801075
2023-01-24 04:59:00.809377: step: 618/469, loss: 0.0012157695600762963
2023-01-24 04:59:01.372846: step: 620/469, loss: 0.10344929993152618
2023-01-24 04:59:01.944408: step: 622/469, loss: 0.10154633224010468
2023-01-24 04:59:02.555119: step: 624/469, loss: 0.00018853195069823414
2023-01-24 04:59:03.153185: step: 626/469, loss: 0.048401981592178345
2023-01-24 04:59:03.736976: step: 628/469, loss: 0.002542890375480056
2023-01-24 04:59:04.446715: step: 630/469, loss: 0.005759979598224163
2023-01-24 04:59:05.103172: step: 632/469, loss: 0.01339081022888422
2023-01-24 04:59:05.767623: step: 634/469, loss: 0.029422728344798088
2023-01-24 04:59:06.525562: step: 636/469, loss: 0.014681156724691391
2023-01-24 04:59:07.165182: step: 638/469, loss: 0.001315159723162651
2023-01-24 04:59:07.748541: step: 640/469, loss: 0.017636211588978767
2023-01-24 04:59:08.386670: step: 642/469, loss: 0.0009735087514854968
2023-01-24 04:59:09.088004: step: 644/469, loss: 0.05150126293301582
2023-01-24 04:59:09.748812: step: 646/469, loss: 0.009876486845314503
2023-01-24 04:59:10.358121: step: 648/469, loss: 0.017833251506090164
2023-01-24 04:59:11.023539: step: 650/469, loss: 0.20279279351234436
2023-01-24 04:59:11.640289: step: 652/469, loss: 0.005821316037327051
2023-01-24 04:59:12.264725: step: 654/469, loss: 0.002447586040943861
2023-01-24 04:59:12.876336: step: 656/469, loss: 0.0080407140776515
2023-01-24 04:59:13.543782: step: 658/469, loss: 0.03799927979707718
2023-01-24 04:59:14.218263: step: 660/469, loss: 0.021526480093598366
2023-01-24 04:59:14.858395: step: 662/469, loss: 0.0017205958720296621
2023-01-24 04:59:15.508581: step: 664/469, loss: 0.05159081146121025
2023-01-24 04:59:16.105079: step: 666/469, loss: 0.019654128700494766
2023-01-24 04:59:16.733318: step: 668/469, loss: 0.0027194879949092865
2023-01-24 04:59:17.341057: step: 670/469, loss: 0.005255649797618389
2023-01-24 04:59:17.974621: step: 672/469, loss: 0.01566912792623043
2023-01-24 04:59:18.604098: step: 674/469, loss: 0.14635688066482544
2023-01-24 04:59:19.279694: step: 676/469, loss: 0.006894399411976337
2023-01-24 04:59:19.890825: step: 678/469, loss: 0.0023598771076649427
2023-01-24 04:59:20.452038: step: 680/469, loss: 0.050585679709911346
2023-01-24 04:59:21.036618: step: 682/469, loss: 0.0012097225990146399
2023-01-24 04:59:21.636734: step: 684/469, loss: 0.019620677456259727
2023-01-24 04:59:22.288432: step: 686/469, loss: 0.0015850631752982736
2023-01-24 04:59:22.941461: step: 688/469, loss: 0.0761529803276062
2023-01-24 04:59:23.575031: step: 690/469, loss: 0.00974776316434145
2023-01-24 04:59:24.170394: step: 692/469, loss: 0.44478705525398254
2023-01-24 04:59:24.828974: step: 694/469, loss: 0.001052939216606319
2023-01-24 04:59:25.464683: step: 696/469, loss: 0.011028924025595188
2023-01-24 04:59:26.086081: step: 698/469, loss: 0.004014064557850361
2023-01-24 04:59:26.764438: step: 700/469, loss: 0.007433253340423107
2023-01-24 04:59:27.404859: step: 702/469, loss: 0.018054557964205742
2023-01-24 04:59:28.042937: step: 704/469, loss: 0.0019376386189833283
2023-01-24 04:59:28.665922: step: 706/469, loss: 0.01151854544878006
2023-01-24 04:59:29.285534: step: 708/469, loss: 0.0018493456300348043
2023-01-24 04:59:29.876590: step: 710/469, loss: 0.057258240878582
2023-01-24 04:59:30.526903: step: 712/469, loss: 0.00707352114841342
2023-01-24 04:59:31.200494: step: 714/469, loss: 0.2225046455860138
2023-01-24 04:59:31.792989: step: 716/469, loss: 0.0035385992377996445
2023-01-24 04:59:32.348187: step: 718/469, loss: 0.0035661403089761734
2023-01-24 04:59:32.922796: step: 720/469, loss: 0.5725209712982178
2023-01-24 04:59:33.514550: step: 722/469, loss: 0.04594719037413597
2023-01-24 04:59:34.191588: step: 724/469, loss: 0.01260649785399437
2023-01-24 04:59:34.797438: step: 726/469, loss: 0.03628157079219818
2023-01-24 04:59:35.453468: step: 728/469, loss: 0.01140190102159977
2023-01-24 04:59:36.099173: step: 730/469, loss: 0.005689607001841068
2023-01-24 04:59:36.720459: step: 732/469, loss: 0.04229084029793739
2023-01-24 04:59:37.282258: step: 734/469, loss: 0.04005708917975426
2023-01-24 04:59:37.995760: step: 736/469, loss: 0.0002078147226711735
2023-01-24 04:59:38.649262: step: 738/469, loss: 0.006827342323958874
2023-01-24 04:59:39.231103: step: 740/469, loss: 0.02837841771543026
2023-01-24 04:59:39.954990: step: 742/469, loss: 0.03563904017210007
2023-01-24 04:59:40.621241: step: 744/469, loss: 0.048966579139232635
2023-01-24 04:59:41.193915: step: 746/469, loss: 0.0012211324647068977
2023-01-24 04:59:41.817504: step: 748/469, loss: 0.0002296100283274427
2023-01-24 04:59:42.436857: step: 750/469, loss: 0.002885879948735237
2023-01-24 04:59:43.084382: step: 752/469, loss: 0.03161158412694931
2023-01-24 04:59:43.715480: step: 754/469, loss: 0.021520603448152542
2023-01-24 04:59:44.343918: step: 756/469, loss: 0.025058690458536148
2023-01-24 04:59:45.022881: step: 758/469, loss: 0.0621785968542099
2023-01-24 04:59:45.629217: step: 760/469, loss: 0.009903007186949253
2023-01-24 04:59:46.303635: step: 762/469, loss: 0.014340068213641644
2023-01-24 04:59:46.965462: step: 764/469, loss: 0.035435933619737625
2023-01-24 04:59:47.569200: step: 766/469, loss: 0.08457788079977036
2023-01-24 04:59:48.178045: step: 768/469, loss: 0.022854575887322426
2023-01-24 04:59:48.806703: step: 770/469, loss: 0.009248269721865654
2023-01-24 04:59:49.355351: step: 772/469, loss: 0.0012875997927039862
2023-01-24 04:59:49.942768: step: 774/469, loss: 0.03336193412542343
2023-01-24 04:59:50.578504: step: 776/469, loss: 0.0009478839347139001
2023-01-24 04:59:51.208143: step: 778/469, loss: 0.10989048331975937
2023-01-24 04:59:51.829940: step: 780/469, loss: 0.18429778516292572
2023-01-24 04:59:52.447399: step: 782/469, loss: 0.01059026550501585
2023-01-24 04:59:53.003407: step: 784/469, loss: 0.15679648518562317
2023-01-24 04:59:53.602368: step: 786/469, loss: 0.001708191935904324
2023-01-24 04:59:54.172326: step: 788/469, loss: 0.006603969726711512
2023-01-24 04:59:54.803298: step: 790/469, loss: 0.03528481721878052
2023-01-24 04:59:55.377565: step: 792/469, loss: 0.005352017469704151
2023-01-24 04:59:56.042600: step: 794/469, loss: 0.01346633117645979
2023-01-24 04:59:56.608123: step: 796/469, loss: 0.03727249801158905
2023-01-24 04:59:57.193386: step: 798/469, loss: 1.8572876453399658
2023-01-24 04:59:57.809177: step: 800/469, loss: 0.03379129245877266
2023-01-24 04:59:58.461485: step: 802/469, loss: 0.0027329474687576294
2023-01-24 04:59:59.070220: step: 804/469, loss: 0.018761103972792625
2023-01-24 04:59:59.659585: step: 806/469, loss: 0.026164662092924118
2023-01-24 05:00:00.272115: step: 808/469, loss: 0.39833980798721313
2023-01-24 05:00:00.902020: step: 810/469, loss: 1.3219311237335205
2023-01-24 05:00:01.560683: step: 812/469, loss: 0.04336877167224884
2023-01-24 05:00:02.143891: step: 814/469, loss: 0.13728487491607666
2023-01-24 05:00:02.800687: step: 816/469, loss: 0.004919958300888538
2023-01-24 05:00:03.466391: step: 818/469, loss: 0.025538092479109764
2023-01-24 05:00:04.130447: step: 820/469, loss: 0.028856776654720306
2023-01-24 05:00:04.744404: step: 822/469, loss: 0.021210791543126106
2023-01-24 05:00:05.368669: step: 824/469, loss: 0.005643091630190611
2023-01-24 05:00:05.999431: step: 826/469, loss: 0.0005824893596582115
2023-01-24 05:00:06.620222: step: 828/469, loss: 0.048885468393564224
2023-01-24 05:00:07.298315: step: 830/469, loss: 0.004670221824198961
2023-01-24 05:00:07.889225: step: 832/469, loss: 0.0495980940759182
2023-01-24 05:00:08.504481: step: 834/469, loss: 0.05524533987045288
2023-01-24 05:00:09.132231: step: 836/469, loss: 0.013411085121333599
2023-01-24 05:00:09.752916: step: 838/469, loss: 0.020150167867541313
2023-01-24 05:00:10.380946: step: 840/469, loss: 0.0058477455750107765
2023-01-24 05:00:11.012403: step: 842/469, loss: 0.04638752341270447
2023-01-24 05:00:11.594643: step: 844/469, loss: 0.00031704845605418086
2023-01-24 05:00:12.245066: step: 846/469, loss: 0.039171431213617325
2023-01-24 05:00:12.882198: step: 848/469, loss: 0.023008722811937332
2023-01-24 05:00:13.442708: step: 850/469, loss: 0.0039032783824950457
2023-01-24 05:00:14.087042: step: 852/469, loss: 0.007801303174346685
2023-01-24 05:00:14.778372: step: 854/469, loss: 0.03950684145092964
2023-01-24 05:00:15.398962: step: 856/469, loss: 0.01630246639251709
2023-01-24 05:00:16.031537: step: 858/469, loss: 0.0004967916756868362
2023-01-24 05:00:16.572234: step: 860/469, loss: 0.003600027645006776
2023-01-24 05:00:17.297686: step: 862/469, loss: 0.005115168169140816
2023-01-24 05:00:17.939471: step: 864/469, loss: 0.008133250288665295
2023-01-24 05:00:18.502228: step: 866/469, loss: 0.02947641722857952
2023-01-24 05:00:19.184700: step: 868/469, loss: 0.07142122089862823
2023-01-24 05:00:19.796272: step: 870/469, loss: 0.00017969335021916777
2023-01-24 05:00:20.432186: step: 872/469, loss: 0.03394768387079239
2023-01-24 05:00:21.226928: step: 874/469, loss: 0.10148341208696365
2023-01-24 05:00:21.821498: step: 876/469, loss: 0.0012569662649184465
2023-01-24 05:00:22.462992: step: 878/469, loss: 0.04769293963909149
2023-01-24 05:00:23.101784: step: 880/469, loss: 0.0037581499200314283
2023-01-24 05:00:23.670196: step: 882/469, loss: 0.007814634591341019
2023-01-24 05:00:24.344221: step: 884/469, loss: 0.061906807124614716
2023-01-24 05:00:25.028636: step: 886/469, loss: 0.0010234395740553737
2023-01-24 05:00:25.590916: step: 888/469, loss: 0.010987556539475918
2023-01-24 05:00:26.169082: step: 890/469, loss: 0.03246670588850975
2023-01-24 05:00:26.770410: step: 892/469, loss: 0.03887225687503815
2023-01-24 05:00:27.367495: step: 894/469, loss: 0.03355664387345314
2023-01-24 05:00:27.975860: step: 896/469, loss: 0.015674414113163948
2023-01-24 05:00:28.628411: step: 898/469, loss: 0.020127814263105392
2023-01-24 05:00:29.235862: step: 900/469, loss: 0.010915447026491165
2023-01-24 05:00:29.868256: step: 902/469, loss: 0.032397475093603134
2023-01-24 05:00:30.451015: step: 904/469, loss: 0.0015398976393043995
2023-01-24 05:00:31.044948: step: 906/469, loss: 0.029909886419773102
2023-01-24 05:00:31.665364: step: 908/469, loss: 0.0016637513181194663
2023-01-24 05:00:32.272397: step: 910/469, loss: 0.002773152431473136
2023-01-24 05:00:32.843874: step: 912/469, loss: 0.025767548009753227
2023-01-24 05:00:33.460216: step: 914/469, loss: 0.021626248955726624
2023-01-24 05:00:34.025516: step: 916/469, loss: 0.012449540197849274
2023-01-24 05:00:34.625066: step: 918/469, loss: 0.05381845310330391
2023-01-24 05:00:35.199095: step: 920/469, loss: 0.14493398368358612
2023-01-24 05:00:35.849149: step: 922/469, loss: 0.3225865066051483
2023-01-24 05:00:36.535222: step: 924/469, loss: 0.013396164402365685
2023-01-24 05:00:37.108106: step: 926/469, loss: 0.03985230252146721
2023-01-24 05:00:37.743883: step: 928/469, loss: 0.01934659294784069
2023-01-24 05:00:38.381560: step: 930/469, loss: 0.016271311789751053
2023-01-24 05:00:39.019189: step: 932/469, loss: 0.0010511681903153658
2023-01-24 05:00:39.608159: step: 934/469, loss: 0.03172919526696205
2023-01-24 05:00:40.245068: step: 936/469, loss: 0.0014140321873128414
2023-01-24 05:00:40.901409: step: 938/469, loss: 0.010791617445647717
==================================================
Loss: 0.050
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3118487763892789, 'r': 0.3142157500241121, 'f1': 0.3130277887763839}, 'combined': 0.23065205488786178, 'epoch': 32}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33238949618757313, 'r': 0.2609242339697509, 'f1': 0.2923528321157742}, 'combined': 0.15946518115405864, 'epoch': 32}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32065574986312745, 'r': 0.31396274559653464, 'f1': 0.31727395384347795}, 'combined': 0.23378080809519428, 'epoch': 32}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3365956199151719, 'r': 0.2596066858083165, 'f1': 0.2931302764343904}, 'combined': 0.15988924169148566, 'epoch': 32}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30512180123010035, 'r': 0.3074377162299493, 'f1': 0.306275380818872}, 'combined': 0.22567659639285303, 'epoch': 32}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33385007099169944, 'r': 0.26634699167864767, 'f1': 0.2963025566460681}, 'combined': 0.16161957635240076, 'epoch': 32}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2530487804878049, 'r': 0.29642857142857143, 'f1': 0.27302631578947373}, 'combined': 0.18201754385964913, 'epoch': 32}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2708333333333333, 'r': 0.2826086956521739, 'f1': 0.2765957446808511}, 'combined': 0.13829787234042554, 'epoch': 32}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45454545454545453, 'r': 0.1724137931034483, 'f1': 0.25000000000000006}, 'combined': 0.16666666666666669, 'epoch': 32}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 05:03:27.082228: step: 2/469, loss: 0.013351435773074627
2023-01-24 05:03:27.643495: step: 4/469, loss: 0.005639699287712574
2023-01-24 05:03:28.225915: step: 6/469, loss: 0.006113546900451183
2023-01-24 05:03:28.853477: step: 8/469, loss: 0.0021835421212017536
2023-01-24 05:03:29.478682: step: 10/469, loss: 0.033465608954429626
2023-01-24 05:03:30.109215: step: 12/469, loss: 0.007830152288079262
2023-01-24 05:03:30.737898: step: 14/469, loss: 0.004056346137076616
2023-01-24 05:03:31.367125: step: 16/469, loss: 0.00999542698264122
2023-01-24 05:03:32.007725: step: 18/469, loss: 0.004410950932651758
2023-01-24 05:03:32.656522: step: 20/469, loss: 0.04339294135570526
2023-01-24 05:03:33.299477: step: 22/469, loss: 0.03698296472430229
2023-01-24 05:03:33.948650: step: 24/469, loss: 0.040439456701278687
2023-01-24 05:03:34.540562: step: 26/469, loss: 0.04639560729265213
2023-01-24 05:03:35.149375: step: 28/469, loss: 0.0019108380656689405
2023-01-24 05:03:35.755874: step: 30/469, loss: 0.011149045079946518
2023-01-24 05:03:36.340467: step: 32/469, loss: 0.0009831722127273679
2023-01-24 05:03:36.988480: step: 34/469, loss: 0.0006967243971303105
2023-01-24 05:03:37.677933: step: 36/469, loss: 0.039589859545230865
2023-01-24 05:03:38.304425: step: 38/469, loss: 0.00748983770608902
2023-01-24 05:03:38.919910: step: 40/469, loss: 0.24827691912651062
2023-01-24 05:03:39.503884: step: 42/469, loss: 0.04059219732880592
2023-01-24 05:03:40.161222: step: 44/469, loss: 0.0077805048786103725
2023-01-24 05:03:40.695508: step: 46/469, loss: 0.00036753417225554585
2023-01-24 05:03:41.276002: step: 48/469, loss: 2.3846070766448975
2023-01-24 05:03:41.889090: step: 50/469, loss: 0.012917861342430115
2023-01-24 05:03:42.568501: step: 52/469, loss: 0.0037191000301390886
2023-01-24 05:03:43.205094: step: 54/469, loss: 0.021560192108154297
2023-01-24 05:03:43.847264: step: 56/469, loss: 0.5750148892402649
2023-01-24 05:03:44.431351: step: 58/469, loss: 0.0033462175633758307
2023-01-24 05:03:45.068284: step: 60/469, loss: 0.12610109150409698
2023-01-24 05:03:45.683214: step: 62/469, loss: 0.004488074220716953
2023-01-24 05:03:46.197682: step: 64/469, loss: 0.002650371752679348
2023-01-24 05:03:46.869875: step: 66/469, loss: 0.0027625400107353926
2023-01-24 05:03:47.518573: step: 68/469, loss: 0.10583145171403885
2023-01-24 05:03:48.166403: step: 70/469, loss: 0.019448785111308098
2023-01-24 05:03:48.837702: step: 72/469, loss: 0.11890777945518494
2023-01-24 05:03:49.578277: step: 74/469, loss: 0.0055470094084739685
2023-01-24 05:03:50.246295: step: 76/469, loss: 0.040658287703990936
2023-01-24 05:03:50.871310: step: 78/469, loss: 0.007026447914540768
2023-01-24 05:03:51.480061: step: 80/469, loss: 0.0038187941536307335
2023-01-24 05:03:52.087486: step: 82/469, loss: 0.005367457401007414
2023-01-24 05:03:52.705373: step: 84/469, loss: 0.016662539914250374
2023-01-24 05:03:53.305079: step: 86/469, loss: 0.0029779854230582714
2023-01-24 05:03:53.908918: step: 88/469, loss: 0.06508389860391617
2023-01-24 05:03:54.621484: step: 90/469, loss: 0.0022850006353110075
2023-01-24 05:03:55.196079: step: 92/469, loss: 0.005730548873543739
2023-01-24 05:03:55.794111: step: 94/469, loss: 0.0008074180223047733
2023-01-24 05:03:56.347005: step: 96/469, loss: 0.0062136054039001465
2023-01-24 05:03:56.952774: step: 98/469, loss: 0.000551339122466743
2023-01-24 05:03:57.509856: step: 100/469, loss: 0.019677409902215004
2023-01-24 05:03:58.126264: step: 102/469, loss: 0.0033649744000285864
2023-01-24 05:03:58.745273: step: 104/469, loss: 0.008814056403934956
2023-01-24 05:03:59.366828: step: 106/469, loss: 0.03335726633667946
2023-01-24 05:04:00.079042: step: 108/469, loss: 0.06300927698612213
2023-01-24 05:04:00.685929: step: 110/469, loss: 0.0029953571502119303
2023-01-24 05:04:01.346272: step: 112/469, loss: 0.0060960473492741585
2023-01-24 05:04:02.001311: step: 114/469, loss: 0.011273249052464962
2023-01-24 05:04:02.611695: step: 116/469, loss: 0.004299314226955175
2023-01-24 05:04:03.250798: step: 118/469, loss: 0.12154749035835266
2023-01-24 05:04:03.869846: step: 120/469, loss: 0.018587274476885796
2023-01-24 05:04:04.625974: step: 122/469, loss: 0.016417136415839195
2023-01-24 05:04:05.210898: step: 124/469, loss: 0.012194930575788021
2023-01-24 05:04:05.883493: step: 126/469, loss: 0.04684147238731384
2023-01-24 05:04:06.462476: step: 128/469, loss: 0.005757268518209457
2023-01-24 05:04:07.123797: step: 130/469, loss: 0.003936708439141512
2023-01-24 05:04:07.739318: step: 132/469, loss: 0.004670368507504463
2023-01-24 05:04:08.382333: step: 134/469, loss: 0.03482309728860855
2023-01-24 05:04:09.032235: step: 136/469, loss: 0.00046595456660725176
2023-01-24 05:04:09.614403: step: 138/469, loss: 0.00020312923879828304
2023-01-24 05:04:10.209556: step: 140/469, loss: 0.0028754393570125103
2023-01-24 05:04:10.852925: step: 142/469, loss: 0.005672778934240341
2023-01-24 05:04:11.477479: step: 144/469, loss: 0.0037217920180410147
2023-01-24 05:04:12.023182: step: 146/469, loss: 0.003972527105361223
2023-01-24 05:04:12.635277: step: 148/469, loss: 0.00446277717128396
2023-01-24 05:04:13.210009: step: 150/469, loss: 0.001574783120304346
2023-01-24 05:04:13.821569: step: 152/469, loss: 0.0018017555121332407
2023-01-24 05:04:14.445108: step: 154/469, loss: 0.034334566444158554
2023-01-24 05:04:15.074834: step: 156/469, loss: 0.0006047360948286951
2023-01-24 05:04:15.724359: step: 158/469, loss: 0.0045813340693712234
2023-01-24 05:04:16.334175: step: 160/469, loss: 0.0003530083631630987
2023-01-24 05:04:16.972817: step: 162/469, loss: 1.590933788975235e-05
2023-01-24 05:04:17.554633: step: 164/469, loss: 0.010642945766448975
2023-01-24 05:04:18.143825: step: 166/469, loss: 0.011005950160324574
2023-01-24 05:04:18.767362: step: 168/469, loss: 0.0013642124831676483
2023-01-24 05:04:19.431605: step: 170/469, loss: 0.022932417690753937
2023-01-24 05:04:20.016965: step: 172/469, loss: 0.005808479152619839
2023-01-24 05:04:20.703186: step: 174/469, loss: 0.003486677072942257
2023-01-24 05:04:21.302687: step: 176/469, loss: 0.03442490100860596
2023-01-24 05:04:21.911912: step: 178/469, loss: 0.0015917201526463032
2023-01-24 05:04:22.560838: step: 180/469, loss: 0.0567733459174633
2023-01-24 05:04:23.116405: step: 182/469, loss: 0.007270394824445248
2023-01-24 05:04:23.696984: step: 184/469, loss: 0.00015969171363394707
2023-01-24 05:04:24.334352: step: 186/469, loss: 0.00758505892008543
2023-01-24 05:04:24.978005: step: 188/469, loss: 0.004748107399791479
2023-01-24 05:04:25.553170: step: 190/469, loss: 0.009574953466653824
2023-01-24 05:04:26.167736: step: 192/469, loss: 0.00833309069275856
2023-01-24 05:04:26.777031: step: 194/469, loss: 0.00844356045126915
2023-01-24 05:04:27.363987: step: 196/469, loss: 0.0020320776384323835
2023-01-24 05:04:27.951182: step: 198/469, loss: 0.013346420601010323
2023-01-24 05:04:28.519123: step: 200/469, loss: 0.014664324931800365
2023-01-24 05:04:29.135911: step: 202/469, loss: 0.01814393512904644
2023-01-24 05:04:29.744299: step: 204/469, loss: 0.0004453635192476213
2023-01-24 05:04:30.341971: step: 206/469, loss: 0.039727482944726944
2023-01-24 05:04:30.974021: step: 208/469, loss: 0.0053256177343428135
2023-01-24 05:04:31.689832: step: 210/469, loss: 0.0034098029136657715
2023-01-24 05:04:32.279368: step: 212/469, loss: 0.004800884984433651
2023-01-24 05:04:32.895489: step: 214/469, loss: 0.0006688708672299981
2023-01-24 05:04:33.541977: step: 216/469, loss: 0.00014004700642544776
2023-01-24 05:04:34.161338: step: 218/469, loss: 0.0251908116042614
2023-01-24 05:04:34.755172: step: 220/469, loss: 0.009037350304424763
2023-01-24 05:04:35.343627: step: 222/469, loss: 0.01472912821918726
2023-01-24 05:04:36.019743: step: 224/469, loss: 0.5599769949913025
2023-01-24 05:04:36.622557: step: 226/469, loss: 0.0030028442852199078
2023-01-24 05:04:37.184936: step: 228/469, loss: 0.00796330813318491
2023-01-24 05:04:37.839916: step: 230/469, loss: 0.0050033507868647575
2023-01-24 05:04:38.482901: step: 232/469, loss: 0.01153347548097372
2023-01-24 05:04:39.129952: step: 234/469, loss: 0.12970635294914246
2023-01-24 05:04:39.691540: step: 236/469, loss: 0.0012679616920650005
2023-01-24 05:04:40.244820: step: 238/469, loss: 0.0248167272657156
2023-01-24 05:04:40.888531: step: 240/469, loss: 0.00013923125516157597
2023-01-24 05:04:41.565044: step: 242/469, loss: 0.002921437146142125
2023-01-24 05:04:42.140854: step: 244/469, loss: 0.015390458516776562
2023-01-24 05:04:42.846861: step: 246/469, loss: 0.035339586436748505
2023-01-24 05:04:43.453202: step: 248/469, loss: 0.0014699893072247505
2023-01-24 05:04:44.027442: step: 250/469, loss: 0.023447921499609947
2023-01-24 05:04:44.650221: step: 252/469, loss: 0.002986697945743799
2023-01-24 05:04:45.309792: step: 254/469, loss: 0.003254184266552329
2023-01-24 05:04:46.125115: step: 256/469, loss: 0.02767689898610115
2023-01-24 05:04:46.740421: step: 258/469, loss: 0.00126143719535321
2023-01-24 05:04:47.375354: step: 260/469, loss: 0.005399410612881184
2023-01-24 05:04:47.956498: step: 262/469, loss: 0.0018525384366512299
2023-01-24 05:04:48.643251: step: 264/469, loss: 0.01274352241307497
2023-01-24 05:04:49.249316: step: 266/469, loss: 0.08559960871934891
2023-01-24 05:04:49.825715: step: 268/469, loss: 0.0021140091121196747
2023-01-24 05:04:50.416160: step: 270/469, loss: 0.0023341989144682884
2023-01-24 05:04:51.017424: step: 272/469, loss: 0.0004674943338613957
2023-01-24 05:04:51.625935: step: 274/469, loss: 0.32528895139694214
2023-01-24 05:04:52.282287: step: 276/469, loss: 0.001879091956652701
2023-01-24 05:04:52.891887: step: 278/469, loss: 0.017344696447253227
2023-01-24 05:04:53.592576: step: 280/469, loss: 0.011400858871638775
2023-01-24 05:04:54.256899: step: 282/469, loss: 0.01149826031178236
2023-01-24 05:04:54.868692: step: 284/469, loss: 0.039661381393671036
2023-01-24 05:04:55.491656: step: 286/469, loss: 0.01687077060341835
2023-01-24 05:04:56.154022: step: 288/469, loss: 0.004539964254945517
2023-01-24 05:04:56.733688: step: 290/469, loss: 0.00014690875832457095
2023-01-24 05:04:57.315485: step: 292/469, loss: 0.002088255016133189
2023-01-24 05:04:57.947333: step: 294/469, loss: 0.04087628051638603
2023-01-24 05:04:58.528086: step: 296/469, loss: 0.00926870759576559
2023-01-24 05:04:59.243771: step: 298/469, loss: 0.004287716932594776
2023-01-24 05:04:59.832521: step: 300/469, loss: 0.0011729313991963863
2023-01-24 05:05:00.410895: step: 302/469, loss: 0.04164522886276245
2023-01-24 05:05:01.106378: step: 304/469, loss: 0.02392064593732357
2023-01-24 05:05:01.766882: step: 306/469, loss: 0.0016163551481440663
2023-01-24 05:05:02.484241: step: 308/469, loss: 0.000714242400135845
2023-01-24 05:05:03.111931: step: 310/469, loss: 0.03168698027729988
2023-01-24 05:05:03.731114: step: 312/469, loss: 0.004886186681687832
2023-01-24 05:05:04.372995: step: 314/469, loss: 0.05792257934808731
2023-01-24 05:05:05.034482: step: 316/469, loss: 0.0011326250387355685
2023-01-24 05:05:05.601647: step: 318/469, loss: 0.00026391472783870995
2023-01-24 05:05:06.195374: step: 320/469, loss: 0.03720565885305405
2023-01-24 05:05:06.782372: step: 322/469, loss: 0.0004022291686851531
2023-01-24 05:05:07.356013: step: 324/469, loss: 0.0037682843394577503
2023-01-24 05:05:07.923598: step: 326/469, loss: 0.00714307464659214
2023-01-24 05:05:08.531059: step: 328/469, loss: 0.002341343555599451
2023-01-24 05:05:09.168130: step: 330/469, loss: 0.00014244038902688771
2023-01-24 05:05:09.825564: step: 332/469, loss: 0.006061086896806955
2023-01-24 05:05:10.439341: step: 334/469, loss: 0.03425901010632515
2023-01-24 05:05:11.047908: step: 336/469, loss: 0.007496016565710306
2023-01-24 05:05:11.696717: step: 338/469, loss: 0.03554781898856163
2023-01-24 05:05:12.292236: step: 340/469, loss: 0.006188980303704739
2023-01-24 05:05:12.950440: step: 342/469, loss: 0.009236977435648441
2023-01-24 05:05:13.591121: step: 344/469, loss: 0.010148722678422928
2023-01-24 05:05:14.306028: step: 346/469, loss: 0.007321231998503208
2023-01-24 05:05:14.940355: step: 348/469, loss: 0.10858845710754395
2023-01-24 05:05:15.526877: step: 350/469, loss: 0.000323133310303092
2023-01-24 05:05:16.201046: step: 352/469, loss: 0.00132815632969141
2023-01-24 05:05:16.769668: step: 354/469, loss: 0.0009524194174446166
2023-01-24 05:05:17.406957: step: 356/469, loss: 0.03454100340604782
2023-01-24 05:05:18.021606: step: 358/469, loss: 0.006098690442740917
2023-01-24 05:05:18.629822: step: 360/469, loss: 0.04598555341362953
2023-01-24 05:05:19.233456: step: 362/469, loss: 0.004837253130972385
2023-01-24 05:05:19.855984: step: 364/469, loss: 0.041017018258571625
2023-01-24 05:05:20.432231: step: 366/469, loss: 0.004117204807698727
2023-01-24 05:05:20.988274: step: 368/469, loss: 0.032427240163087845
2023-01-24 05:05:21.659491: step: 370/469, loss: 0.00023781275376677513
2023-01-24 05:05:22.275741: step: 372/469, loss: 0.05958930775523186
2023-01-24 05:05:22.855851: step: 374/469, loss: 0.01593131013214588
2023-01-24 05:05:23.544931: step: 376/469, loss: 0.015888068825006485
2023-01-24 05:05:24.191318: step: 378/469, loss: 0.01922130398452282
2023-01-24 05:05:24.793872: step: 380/469, loss: 0.19295734167099
2023-01-24 05:05:25.424651: step: 382/469, loss: 0.00452197901904583
2023-01-24 05:05:26.068144: step: 384/469, loss: 0.0188754890114069
2023-01-24 05:05:26.753138: step: 386/469, loss: 0.0028828668873757124
2023-01-24 05:05:27.407563: step: 388/469, loss: 0.002730908105149865
2023-01-24 05:05:27.976651: step: 390/469, loss: 0.037013109773397446
2023-01-24 05:05:28.654920: step: 392/469, loss: 0.00012813137436751276
2023-01-24 05:05:29.298566: step: 394/469, loss: 0.00018990701937582344
2023-01-24 05:05:29.945958: step: 396/469, loss: 0.00619854312390089
2023-01-24 05:05:30.612912: step: 398/469, loss: 0.018023747950792313
2023-01-24 05:05:31.275520: step: 400/469, loss: 0.003330582519993186
2023-01-24 05:05:31.968332: step: 402/469, loss: 0.019715260714292526
2023-01-24 05:05:32.592905: step: 404/469, loss: 0.00561181316152215
2023-01-24 05:05:33.196469: step: 406/469, loss: 0.006778828799724579
2023-01-24 05:05:33.893730: step: 408/469, loss: 0.01337337028235197
2023-01-24 05:05:34.530652: step: 410/469, loss: 0.0035241665318608284
2023-01-24 05:05:35.187117: step: 412/469, loss: 0.004474778193980455
2023-01-24 05:05:35.796896: step: 414/469, loss: 0.07631265372037888
2023-01-24 05:05:36.402700: step: 416/469, loss: 0.00584753230214119
2023-01-24 05:05:37.072673: step: 418/469, loss: 0.002276880666613579
2023-01-24 05:05:37.694312: step: 420/469, loss: 0.03101464733481407
2023-01-24 05:05:38.245397: step: 422/469, loss: 0.012025087140500546
2023-01-24 05:05:38.872200: step: 424/469, loss: 0.0015342243714258075
2023-01-24 05:05:39.497892: step: 426/469, loss: 0.015713496133685112
2023-01-24 05:05:40.124971: step: 428/469, loss: 0.0010290158679708838
2023-01-24 05:05:40.758585: step: 430/469, loss: 0.005436266772449017
2023-01-24 05:05:41.406919: step: 432/469, loss: 0.039580777287483215
2023-01-24 05:05:42.042367: step: 434/469, loss: 0.005971907638013363
2023-01-24 05:05:42.760517: step: 436/469, loss: 0.08663719892501831
2023-01-24 05:05:43.401566: step: 438/469, loss: 0.003683008486405015
2023-01-24 05:05:44.043446: step: 440/469, loss: 0.002901983680203557
2023-01-24 05:05:44.655159: step: 442/469, loss: 0.007728767581284046
2023-01-24 05:05:45.277339: step: 444/469, loss: 0.02300255000591278
2023-01-24 05:05:45.925237: step: 446/469, loss: 0.0006015023100189865
2023-01-24 05:05:46.558604: step: 448/469, loss: 0.03230655938386917
2023-01-24 05:05:47.152126: step: 450/469, loss: 0.0007482889341190457
2023-01-24 05:05:47.789780: step: 452/469, loss: 0.008743666112422943
2023-01-24 05:05:48.408840: step: 454/469, loss: 0.02133469097316265
2023-01-24 05:05:49.021205: step: 456/469, loss: 0.0022225086577236652
2023-01-24 05:05:49.701275: step: 458/469, loss: 0.0029493970796465874
2023-01-24 05:05:50.392104: step: 460/469, loss: 0.01647314988076687
2023-01-24 05:05:50.984080: step: 462/469, loss: 0.0008527342579327524
2023-01-24 05:05:51.637627: step: 464/469, loss: 0.005008402280509472
2023-01-24 05:05:52.237912: step: 466/469, loss: 0.0014473085757344961
2023-01-24 05:05:52.844581: step: 468/469, loss: 0.03902801126241684
2023-01-24 05:05:53.504132: step: 470/469, loss: 0.10863203555345535
2023-01-24 05:05:54.111373: step: 472/469, loss: 0.03507671505212784
2023-01-24 05:05:54.752820: step: 474/469, loss: 2.4033501148223877
2023-01-24 05:05:55.398626: step: 476/469, loss: 0.0023762674536556005
2023-01-24 05:05:56.040957: step: 478/469, loss: 0.006410107482224703
2023-01-24 05:05:56.667260: step: 480/469, loss: 0.010130060836672783
2023-01-24 05:05:57.255985: step: 482/469, loss: 0.0028522307984530926
2023-01-24 05:05:57.893687: step: 484/469, loss: 0.0016838125884532928
2023-01-24 05:05:58.515358: step: 486/469, loss: 0.18121619522571564
2023-01-24 05:05:59.094263: step: 488/469, loss: 0.0028508505783975124
2023-01-24 05:05:59.670109: step: 490/469, loss: 0.006383610889315605
2023-01-24 05:06:00.266702: step: 492/469, loss: 0.012291405349969864
2023-01-24 05:06:00.873507: step: 494/469, loss: 0.021269096061587334
2023-01-24 05:06:01.484567: step: 496/469, loss: 0.000360461650416255
2023-01-24 05:06:02.071595: step: 498/469, loss: 0.01742173545062542
2023-01-24 05:06:02.653745: step: 500/469, loss: 0.029842935502529144
2023-01-24 05:06:03.348694: step: 502/469, loss: 0.09552260488271713
2023-01-24 05:06:03.946008: step: 504/469, loss: 0.03839993476867676
2023-01-24 05:06:04.583328: step: 506/469, loss: 0.0005510871997103095
2023-01-24 05:06:05.251805: step: 508/469, loss: 0.007790790870785713
2023-01-24 05:06:05.823447: step: 510/469, loss: 0.003291425062343478
2023-01-24 05:06:06.480539: step: 512/469, loss: 0.0027130248490720987
2023-01-24 05:06:07.189221: step: 514/469, loss: 0.03849266842007637
2023-01-24 05:06:07.758813: step: 516/469, loss: 0.015371840447187424
2023-01-24 05:06:08.382573: step: 518/469, loss: 0.00024459429550915956
2023-01-24 05:06:08.943251: step: 520/469, loss: 0.011851261369884014
2023-01-24 05:06:09.474789: step: 522/469, loss: 0.0003780556144192815
2023-01-24 05:06:10.194792: step: 524/469, loss: 1.996565333683975e-05
2023-01-24 05:06:10.809396: step: 526/469, loss: 0.33478713035583496
2023-01-24 05:06:11.347514: step: 528/469, loss: 0.0013824690831825137
2023-01-24 05:06:11.921935: step: 530/469, loss: 0.013079002499580383
2023-01-24 05:06:12.495034: step: 532/469, loss: 0.0014266233192756772
2023-01-24 05:06:13.139571: step: 534/469, loss: 0.012344690039753914
2023-01-24 05:06:13.790125: step: 536/469, loss: 0.0005016499781049788
2023-01-24 05:06:14.452599: step: 538/469, loss: 0.0035884634125977755
2023-01-24 05:06:15.025449: step: 540/469, loss: 0.0975341945886612
2023-01-24 05:06:15.619322: step: 542/469, loss: 0.0015002776635810733
2023-01-24 05:06:16.270368: step: 544/469, loss: 0.017281167209148407
2023-01-24 05:06:16.771127: step: 546/469, loss: 0.0033554481342434883
2023-01-24 05:06:17.366974: step: 548/469, loss: 0.0021954441908746958
2023-01-24 05:06:18.023794: step: 550/469, loss: 0.02514529973268509
2023-01-24 05:06:18.728810: step: 552/469, loss: 0.011842131614685059
2023-01-24 05:06:19.352574: step: 554/469, loss: 0.002635958604514599
2023-01-24 05:06:19.962730: step: 556/469, loss: 0.0016326900804415345
2023-01-24 05:06:20.564128: step: 558/469, loss: 0.025699403136968613
2023-01-24 05:06:21.246953: step: 560/469, loss: 0.0009642823715694249
2023-01-24 05:06:21.825771: step: 562/469, loss: 0.04040439799427986
2023-01-24 05:06:22.586842: step: 564/469, loss: 0.00034277039230801165
2023-01-24 05:06:23.276234: step: 566/469, loss: 0.012492691166698933
2023-01-24 05:06:23.899906: step: 568/469, loss: 0.024846741929650307
2023-01-24 05:06:24.520590: step: 570/469, loss: 0.0007408543024212122
2023-01-24 05:06:25.130513: step: 572/469, loss: 8.127120236167684e-05
2023-01-24 05:06:25.782912: step: 574/469, loss: 0.16272634267807007
2023-01-24 05:06:26.397949: step: 576/469, loss: 0.0019044807413592935
2023-01-24 05:06:27.004565: step: 578/469, loss: 0.00011966226156800985
2023-01-24 05:06:27.571063: step: 580/469, loss: 0.0273868590593338
2023-01-24 05:06:28.137927: step: 582/469, loss: 0.00020728286472149193
2023-01-24 05:06:28.762254: step: 584/469, loss: 0.39482250809669495
2023-01-24 05:06:29.382082: step: 586/469, loss: 0.002915006596595049
2023-01-24 05:06:30.045259: step: 588/469, loss: 0.004416953772306442
2023-01-24 05:06:30.685026: step: 590/469, loss: 0.0629315972328186
2023-01-24 05:06:31.324071: step: 592/469, loss: 0.003230934264138341
2023-01-24 05:06:31.951457: step: 594/469, loss: 0.09500297158956528
2023-01-24 05:06:32.562580: step: 596/469, loss: 0.002657938050106168
2023-01-24 05:06:33.163534: step: 598/469, loss: 0.06940101087093353
2023-01-24 05:06:33.773531: step: 600/469, loss: 0.014296120032668114
2023-01-24 05:06:34.389711: step: 602/469, loss: 0.36395740509033203
2023-01-24 05:06:34.997089: step: 604/469, loss: 0.02228420600295067
2023-01-24 05:06:35.634967: step: 606/469, loss: 0.000938447832595557
2023-01-24 05:06:36.279001: step: 608/469, loss: 0.016886886209249496
2023-01-24 05:06:36.888327: step: 610/469, loss: 0.024989686906337738
2023-01-24 05:06:37.483629: step: 612/469, loss: 0.03809540346264839
2023-01-24 05:06:38.016382: step: 614/469, loss: 0.0003656471089925617
2023-01-24 05:06:38.608846: step: 616/469, loss: 0.11770421266555786
2023-01-24 05:06:39.278807: step: 618/469, loss: 0.03488276153802872
2023-01-24 05:06:39.821300: step: 620/469, loss: 4.1198763938155025e-05
2023-01-24 05:06:40.456324: step: 622/469, loss: 0.08880746364593506
2023-01-24 05:06:41.110308: step: 624/469, loss: 0.034829068928956985
2023-01-24 05:06:41.740839: step: 626/469, loss: 0.0013449967373162508
2023-01-24 05:06:42.359026: step: 628/469, loss: 0.03821936994791031
2023-01-24 05:06:42.960608: step: 630/469, loss: 0.019052352756261826
2023-01-24 05:06:43.546254: step: 632/469, loss: 0.0005967976176179945
2023-01-24 05:06:44.138461: step: 634/469, loss: 0.08901707082986832
2023-01-24 05:06:44.746455: step: 636/469, loss: 0.0010007378878071904
2023-01-24 05:06:45.350770: step: 638/469, loss: 0.014912023209035397
2023-01-24 05:06:45.962458: step: 640/469, loss: 0.17074042558670044
2023-01-24 05:06:46.619472: step: 642/469, loss: 0.01104023028165102
2023-01-24 05:06:47.300080: step: 644/469, loss: 0.04529206454753876
2023-01-24 05:06:47.979605: step: 646/469, loss: 0.02859463356435299
2023-01-24 05:06:48.624200: step: 648/469, loss: 0.031995393335819244
2023-01-24 05:06:49.379701: step: 650/469, loss: 2.4087648391723633
2023-01-24 05:06:50.074152: step: 652/469, loss: 0.009420580230653286
2023-01-24 05:06:50.718421: step: 654/469, loss: 0.02887788787484169
2023-01-24 05:06:51.377105: step: 656/469, loss: 0.12417895346879959
2023-01-24 05:06:51.970930: step: 658/469, loss: 0.0006238478235900402
2023-01-24 05:06:52.546989: step: 660/469, loss: 0.005185308866202831
2023-01-24 05:06:53.112599: step: 662/469, loss: 0.0008076611557044089
2023-01-24 05:06:53.736578: step: 664/469, loss: 0.046926502138376236
2023-01-24 05:06:54.383962: step: 666/469, loss: 0.019344089552760124
2023-01-24 05:06:54.983538: step: 668/469, loss: 0.0002813950413838029
2023-01-24 05:06:55.652057: step: 670/469, loss: 0.07090133428573608
2023-01-24 05:06:56.278811: step: 672/469, loss: 0.02977340668439865
2023-01-24 05:06:56.891208: step: 674/469, loss: 0.0018980741733685136
2023-01-24 05:06:57.515047: step: 676/469, loss: 0.04407316818833351
2023-01-24 05:06:58.138541: step: 678/469, loss: 0.02806190773844719
2023-01-24 05:06:58.690799: step: 680/469, loss: 0.01468958705663681
2023-01-24 05:06:59.502151: step: 682/469, loss: 0.008281126618385315
2023-01-24 05:07:00.098111: step: 684/469, loss: 0.002183744451031089
2023-01-24 05:07:00.695261: step: 686/469, loss: 0.0006071201642043889
2023-01-24 05:07:01.256571: step: 688/469, loss: 0.022162703797221184
2023-01-24 05:07:01.929387: step: 690/469, loss: 0.006789313163608313
2023-01-24 05:07:02.551638: step: 692/469, loss: 0.014217977412045002
2023-01-24 05:07:03.217124: step: 694/469, loss: 0.015008599497377872
2023-01-24 05:07:03.789065: step: 696/469, loss: 0.03592699393630028
2023-01-24 05:07:04.382139: step: 698/469, loss: 0.3247458040714264
2023-01-24 05:07:04.938361: step: 700/469, loss: 0.01957259327173233
2023-01-24 05:07:05.703225: step: 702/469, loss: 0.0026686498895287514
2023-01-24 05:07:06.356585: step: 704/469, loss: 0.02792477421462536
2023-01-24 05:07:06.953925: step: 706/469, loss: 0.0254361554980278
2023-01-24 05:07:07.552409: step: 708/469, loss: 0.0011668233200907707
2023-01-24 05:07:08.286641: step: 710/469, loss: 0.06137216463685036
2023-01-24 05:07:08.887109: step: 712/469, loss: 0.05560300126671791
2023-01-24 05:07:09.544885: step: 714/469, loss: 0.0025397774297744036
2023-01-24 05:07:10.198297: step: 716/469, loss: 0.001246861182153225
2023-01-24 05:07:10.783934: step: 718/469, loss: 0.0632171556353569
2023-01-24 05:07:11.411334: step: 720/469, loss: 0.000753260450437665
2023-01-24 05:07:12.038342: step: 722/469, loss: 0.03895358741283417
2023-01-24 05:07:12.718020: step: 724/469, loss: 0.013898639008402824
2023-01-24 05:07:13.344064: step: 726/469, loss: 0.04265652224421501
2023-01-24 05:07:13.886735: step: 728/469, loss: 0.004402386024594307
2023-01-24 05:07:14.484470: step: 730/469, loss: 0.004465318284928799
2023-01-24 05:07:15.051609: step: 732/469, loss: 0.01439233310520649
2023-01-24 05:07:15.684739: step: 734/469, loss: 0.014482861384749413
2023-01-24 05:07:16.285761: step: 736/469, loss: 0.059373173862695694
2023-01-24 05:07:16.971178: step: 738/469, loss: 0.02686934918165207
2023-01-24 05:07:17.583136: step: 740/469, loss: 0.001371812541037798
2023-01-24 05:07:18.204125: step: 742/469, loss: 0.023025471717119217
2023-01-24 05:07:18.841949: step: 744/469, loss: 0.00024758256040513515
2023-01-24 05:07:19.445467: step: 746/469, loss: 0.0034194202162325382
2023-01-24 05:07:20.040490: step: 748/469, loss: 0.001260263379663229
2023-01-24 05:07:20.739037: step: 750/469, loss: 0.020660411566495895
2023-01-24 05:07:21.520433: step: 752/469, loss: 0.03583719581365585
2023-01-24 05:07:22.193394: step: 754/469, loss: 0.021274235099554062
2023-01-24 05:07:22.852680: step: 756/469, loss: 0.011315690353512764
2023-01-24 05:07:23.454050: step: 758/469, loss: 0.027749918401241302
2023-01-24 05:07:24.082269: step: 760/469, loss: 0.023145675659179688
2023-01-24 05:07:24.732224: step: 762/469, loss: 0.0783037319779396
2023-01-24 05:07:25.333704: step: 764/469, loss: 0.00954751018434763
2023-01-24 05:07:25.965348: step: 766/469, loss: 0.0516485720872879
2023-01-24 05:07:26.614747: step: 768/469, loss: 0.03406033292412758
2023-01-24 05:07:27.345746: step: 770/469, loss: 0.0791030302643776
2023-01-24 05:07:28.012690: step: 772/469, loss: 0.0046530370600521564
2023-01-24 05:07:28.624660: step: 774/469, loss: 0.012602507136762142
2023-01-24 05:07:29.191037: step: 776/469, loss: 0.00102899968624115
2023-01-24 05:07:29.849203: step: 778/469, loss: 0.040264785289764404
2023-01-24 05:07:30.418580: step: 780/469, loss: 0.0050149839371442795
2023-01-24 05:07:30.960320: step: 782/469, loss: 0.07066849619150162
2023-01-24 05:07:31.593947: step: 784/469, loss: 0.017565440386533737
2023-01-24 05:07:32.302480: step: 786/469, loss: 0.013721856288611889
2023-01-24 05:07:32.907493: step: 788/469, loss: 0.03092535398900509
2023-01-24 05:07:33.517367: step: 790/469, loss: 0.04674604907631874
2023-01-24 05:07:34.134983: step: 792/469, loss: 0.02690579555928707
2023-01-24 05:07:34.757241: step: 794/469, loss: 0.07567117363214493
2023-01-24 05:07:35.381117: step: 796/469, loss: 0.08812756836414337
2023-01-24 05:07:36.058393: step: 798/469, loss: 0.10162734240293503
2023-01-24 05:07:36.697151: step: 800/469, loss: 0.13834482431411743
2023-01-24 05:07:37.464242: step: 802/469, loss: 0.010010241530835629
2023-01-24 05:07:38.079505: step: 804/469, loss: 0.01298542320728302
2023-01-24 05:07:38.744111: step: 806/469, loss: 0.017113426700234413
2023-01-24 05:07:39.392864: step: 808/469, loss: 0.013750889338552952
2023-01-24 05:07:39.985583: step: 810/469, loss: 0.006098391953855753
2023-01-24 05:07:40.590461: step: 812/469, loss: 0.03663692995905876
2023-01-24 05:07:41.208340: step: 814/469, loss: 0.017231501638889313
2023-01-24 05:07:41.847484: step: 816/469, loss: 0.010893937200307846
2023-01-24 05:07:42.472411: step: 818/469, loss: 0.00018118097796104848
2023-01-24 05:07:43.165551: step: 820/469, loss: 0.023833217099308968
2023-01-24 05:07:43.779823: step: 822/469, loss: 0.009173400700092316
2023-01-24 05:07:44.452768: step: 824/469, loss: 0.02096126414835453
2023-01-24 05:07:45.049064: step: 826/469, loss: 0.005791542120277882
2023-01-24 05:07:45.693078: step: 828/469, loss: 0.00048988894559443
2023-01-24 05:07:46.363768: step: 830/469, loss: 0.011068285442888737
2023-01-24 05:07:46.947740: step: 832/469, loss: 0.00469591747969389
2023-01-24 05:07:47.603480: step: 834/469, loss: 0.00930104125291109
2023-01-24 05:07:48.265784: step: 836/469, loss: 0.00478220684453845
2023-01-24 05:07:48.882762: step: 838/469, loss: 0.02467329427599907
2023-01-24 05:07:49.531639: step: 840/469, loss: 0.006275024730712175
2023-01-24 05:07:50.189181: step: 842/469, loss: 0.014605286531150341
2023-01-24 05:07:50.802770: step: 844/469, loss: 0.0015325166750699282
2023-01-24 05:07:51.447085: step: 846/469, loss: 0.0023205613251775503
2023-01-24 05:07:52.108931: step: 848/469, loss: 0.005115923937410116
2023-01-24 05:07:52.699807: step: 850/469, loss: 0.02142981067299843
2023-01-24 05:07:53.381458: step: 852/469, loss: 0.016367793083190918
2023-01-24 05:07:54.072640: step: 854/469, loss: 0.005425679963082075
2023-01-24 05:07:54.683967: step: 856/469, loss: 0.02080382965505123
2023-01-24 05:07:55.260404: step: 858/469, loss: 0.01139050628989935
2023-01-24 05:07:55.839813: step: 860/469, loss: 0.026312697678804398
2023-01-24 05:07:56.476523: step: 862/469, loss: 0.01092403382062912
2023-01-24 05:07:57.185526: step: 864/469, loss: 0.006747534964233637
2023-01-24 05:07:57.818180: step: 866/469, loss: 0.15142342448234558
2023-01-24 05:07:58.418916: step: 868/469, loss: 0.0016730048228055239
2023-01-24 05:07:59.088376: step: 870/469, loss: 0.05006123334169388
2023-01-24 05:07:59.656156: step: 872/469, loss: 0.014254732057452202
2023-01-24 05:08:00.243838: step: 874/469, loss: 0.04299959912896156
2023-01-24 05:08:00.838641: step: 876/469, loss: 0.027509279549121857
2023-01-24 05:08:01.482438: step: 878/469, loss: 0.01997573859989643
2023-01-24 05:08:02.074678: step: 880/469, loss: 0.00031374391983263195
2023-01-24 05:08:02.709347: step: 882/469, loss: 0.016268735751509666
2023-01-24 05:08:03.322503: step: 884/469, loss: 0.0013883366482332349
2023-01-24 05:08:03.910095: step: 886/469, loss: 0.025057921186089516
2023-01-24 05:08:04.498115: step: 888/469, loss: 0.2622474431991577
2023-01-24 05:08:05.103114: step: 890/469, loss: 0.0010785538470372558
2023-01-24 05:08:05.700766: step: 892/469, loss: 0.012118016369640827
2023-01-24 05:08:06.364709: step: 894/469, loss: 0.09365305304527283
2023-01-24 05:08:06.965055: step: 896/469, loss: 2.3522001356468536e-05
2023-01-24 05:08:07.589285: step: 898/469, loss: 0.0015640523051843047
2023-01-24 05:08:08.292895: step: 900/469, loss: 0.7320762276649475
2023-01-24 05:08:08.987864: step: 902/469, loss: 0.06162048131227493
2023-01-24 05:08:09.574352: step: 904/469, loss: 0.0066713797859847546
2023-01-24 05:08:10.270927: step: 906/469, loss: 0.016309410333633423
2023-01-24 05:08:10.973300: step: 908/469, loss: 0.21170613169670105
2023-01-24 05:08:11.585023: step: 910/469, loss: 0.033934880048036575
2023-01-24 05:08:12.186051: step: 912/469, loss: 0.01726914942264557
2023-01-24 05:08:12.850302: step: 914/469, loss: 0.0049497890286147594
2023-01-24 05:08:13.485126: step: 916/469, loss: 0.016548756510019302
2023-01-24 05:08:14.131143: step: 918/469, loss: 0.0022880916949361563
2023-01-24 05:08:14.802284: step: 920/469, loss: 0.000545771443285048
2023-01-24 05:08:15.399536: step: 922/469, loss: 0.02944769337773323
2023-01-24 05:08:16.046962: step: 924/469, loss: 0.0009377841488458216
2023-01-24 05:08:16.604386: step: 926/469, loss: 0.17907419800758362
2023-01-24 05:08:17.231198: step: 928/469, loss: 0.014677022583782673
2023-01-24 05:08:17.838533: step: 930/469, loss: 0.036170970648527145
2023-01-24 05:08:18.445881: step: 932/469, loss: 0.03944196552038193
2023-01-24 05:08:19.071747: step: 934/469, loss: 0.005004808772355318
2023-01-24 05:08:19.662825: step: 936/469, loss: 0.003991291392594576
2023-01-24 05:08:20.352082: step: 938/469, loss: 0.004129363689571619
==================================================
Loss: 0.045
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33154855582299575, 'r': 0.30890007762635846, 'f1': 0.319823852473656}, 'combined': 0.23565968077006233, 'epoch': 33}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3408934887295102, 'r': 0.2608115631321755, 'f1': 0.2955234076298291}, 'combined': 0.16119458597990677, 'epoch': 33}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3359369154508043, 'r': 0.3098014058996032, 'f1': 0.32234025845822484}, 'combined': 0.23751387465342882, 'epoch': 33}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3488997537260173, 'r': 0.26502348751948845, 'f1': 0.30123189126890426}, 'combined': 0.16430830432849322, 'epoch': 33}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32463644173695716, 'r': 0.29876408774653557, 'f1': 0.3111633878308779}, 'combined': 0.22927828577012052, 'epoch': 33}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3393100521726701, 'r': 0.2630118137499307, 'f1': 0.2963284492712916}, 'combined': 0.16163369960252266, 'epoch': 33}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32708333333333334, 'r': 0.28035714285714286, 'f1': 0.30192307692307696}, 'combined': 0.2012820512820513, 'epoch': 33}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3020833333333333, 'r': 0.31521739130434784, 'f1': 0.30851063829787234}, 'combined': 0.15425531914893617, 'epoch': 33}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.1724137931034483, 'f1': 0.25641025641025644}, 'combined': 0.17094017094017094, 'epoch': 33}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 05:11:06.737701: step: 2/469, loss: 0.006031720899045467
2023-01-24 05:11:07.369858: step: 4/469, loss: 0.0019197453511878848
2023-01-24 05:11:08.016764: step: 6/469, loss: 0.004195861984044313
2023-01-24 05:11:08.586790: step: 8/469, loss: 0.006084569729864597
2023-01-24 05:11:09.283800: step: 10/469, loss: 0.03573630005121231
2023-01-24 05:11:10.065511: step: 12/469, loss: 0.005998925771564245
2023-01-24 05:11:10.650159: step: 14/469, loss: 0.02235507406294346
2023-01-24 05:11:11.248622: step: 16/469, loss: 0.004785803612321615
2023-01-24 05:11:11.902428: step: 18/469, loss: 0.013863739557564259
2023-01-24 05:11:12.534589: step: 20/469, loss: 0.017171066254377365
2023-01-24 05:11:13.164356: step: 22/469, loss: 0.005527122877538204
2023-01-24 05:11:13.768308: step: 24/469, loss: 0.0009547692025080323
2023-01-24 05:11:14.391239: step: 26/469, loss: 0.02117086946964264
2023-01-24 05:11:15.117708: step: 28/469, loss: 0.00163931492716074
2023-01-24 05:11:15.741616: step: 30/469, loss: 0.025652950629591942
2023-01-24 05:11:16.427106: step: 32/469, loss: 0.00017634050163906068
2023-01-24 05:11:16.984628: step: 34/469, loss: 0.000924905703868717
2023-01-24 05:11:17.573822: step: 36/469, loss: 0.05202510952949524
2023-01-24 05:11:18.226270: step: 38/469, loss: 0.008343975991010666
2023-01-24 05:11:18.789301: step: 40/469, loss: 0.0006487302598543465
2023-01-24 05:11:19.389947: step: 42/469, loss: 0.07102520018815994
2023-01-24 05:11:20.032831: step: 44/469, loss: 0.01853327825665474
2023-01-24 05:11:20.665198: step: 46/469, loss: 0.0006005986942909658
2023-01-24 05:11:21.285868: step: 48/469, loss: 0.00398049782961607
2023-01-24 05:11:21.887807: step: 50/469, loss: 0.012305492535233498
2023-01-24 05:11:22.496845: step: 52/469, loss: 0.0011470906902104616
2023-01-24 05:11:23.206340: step: 54/469, loss: 0.0023668729700148106
2023-01-24 05:11:23.802780: step: 56/469, loss: 0.0054066115990281105
2023-01-24 05:11:24.382707: step: 58/469, loss: 0.012622066773474216
2023-01-24 05:11:25.060353: step: 60/469, loss: 0.00028697348898276687
2023-01-24 05:11:25.683622: step: 62/469, loss: 0.04201425984501839
2023-01-24 05:11:26.369636: step: 64/469, loss: 0.012655284255743027
2023-01-24 05:11:27.006373: step: 66/469, loss: 0.13666579127311707
2023-01-24 05:11:27.669485: step: 68/469, loss: 0.00934639759361744
2023-01-24 05:11:28.359269: step: 70/469, loss: 0.0013036837335675955
2023-01-24 05:11:29.014166: step: 72/469, loss: 0.00669926218688488
2023-01-24 05:11:29.614155: step: 74/469, loss: 0.0067839352414011955
2023-01-24 05:11:30.208224: step: 76/469, loss: 0.0014320772606879473
2023-01-24 05:11:30.867557: step: 78/469, loss: 0.010338111780583858
2023-01-24 05:11:31.463918: step: 80/469, loss: 0.0016123708337545395
2023-01-24 05:11:32.101774: step: 82/469, loss: 0.0005422577378340065
2023-01-24 05:11:32.676437: step: 84/469, loss: 0.008865961804986
2023-01-24 05:11:33.293244: step: 86/469, loss: 0.20689965784549713
2023-01-24 05:11:33.931509: step: 88/469, loss: 0.05947402864694595
2023-01-24 05:11:34.586182: step: 90/469, loss: 0.008328648284077644
2023-01-24 05:11:35.254072: step: 92/469, loss: 0.059641528874635696
2023-01-24 05:11:35.925300: step: 94/469, loss: 0.007071740925312042
2023-01-24 05:11:36.529243: step: 96/469, loss: 0.00270385411567986
2023-01-24 05:11:37.170622: step: 98/469, loss: 0.2607606053352356
2023-01-24 05:11:37.849028: step: 100/469, loss: 0.05911825969815254
2023-01-24 05:11:38.491910: step: 102/469, loss: 0.16916383802890778
2023-01-24 05:11:39.052980: step: 104/469, loss: 0.002343447646126151
2023-01-24 05:11:39.658976: step: 106/469, loss: 0.011622349731624126
2023-01-24 05:11:40.313229: step: 108/469, loss: 0.000993871595710516
2023-01-24 05:11:40.917906: step: 110/469, loss: 0.004134451039135456
2023-01-24 05:11:41.551172: step: 112/469, loss: 0.011134440079331398
2023-01-24 05:11:42.155686: step: 114/469, loss: 0.00017363010556437075
2023-01-24 05:11:42.740620: step: 116/469, loss: 0.0010013064602389932
2023-01-24 05:11:43.373479: step: 118/469, loss: 0.0020272599067538977
2023-01-24 05:11:44.047092: step: 120/469, loss: 0.009724320843815804
2023-01-24 05:11:44.660198: step: 122/469, loss: 0.000933723000343889
2023-01-24 05:11:45.282813: step: 124/469, loss: 0.0011233205441385508
2023-01-24 05:11:45.946884: step: 126/469, loss: 0.0980379581451416
2023-01-24 05:11:46.509449: step: 128/469, loss: 0.0008008508011698723
2023-01-24 05:11:47.126735: step: 130/469, loss: 0.4928361475467682
2023-01-24 05:11:47.762001: step: 132/469, loss: 0.00046625922550447285
2023-01-24 05:11:48.344411: step: 134/469, loss: 0.018281705677509308
2023-01-24 05:11:48.940958: step: 136/469, loss: 17.673542022705078
2023-01-24 05:11:49.520696: step: 138/469, loss: 0.0004628832102753222
2023-01-24 05:11:50.093229: step: 140/469, loss: 0.029018081724643707
2023-01-24 05:11:50.719905: step: 142/469, loss: 0.03466082364320755
2023-01-24 05:11:51.312312: step: 144/469, loss: 0.006776665803045034
2023-01-24 05:11:51.903577: step: 146/469, loss: 0.0028881519101560116
2023-01-24 05:11:52.564509: step: 148/469, loss: 0.10274806618690491
2023-01-24 05:11:53.197219: step: 150/469, loss: 0.0005523923900909722
2023-01-24 05:11:53.833681: step: 152/469, loss: 0.0441497340798378
2023-01-24 05:11:54.464176: step: 154/469, loss: 0.036486443132162094
2023-01-24 05:11:55.131213: step: 156/469, loss: 0.0028733036015182734
2023-01-24 05:11:55.709240: step: 158/469, loss: 6.04199267399963e-05
2023-01-24 05:11:56.283816: step: 160/469, loss: 0.022768253460526466
2023-01-24 05:11:56.917428: step: 162/469, loss: 6.1829574406147e-05
2023-01-24 05:11:57.555438: step: 164/469, loss: 0.0013987660640850663
2023-01-24 05:11:58.178204: step: 166/469, loss: 0.0006711300811730325
2023-01-24 05:11:58.800420: step: 168/469, loss: 0.002706859027966857
2023-01-24 05:11:59.395647: step: 170/469, loss: 0.032152675092220306
2023-01-24 05:12:00.050004: step: 172/469, loss: 7.145424751797691e-05
2023-01-24 05:12:00.679214: step: 174/469, loss: 0.01663138158619404
2023-01-24 05:12:01.267342: step: 176/469, loss: 0.007105072028934956
2023-01-24 05:12:01.974158: step: 178/469, loss: 0.004928879905492067
2023-01-24 05:12:02.572238: step: 180/469, loss: 0.010595102794468403
2023-01-24 05:12:03.208703: step: 182/469, loss: 0.08913377672433853
2023-01-24 05:12:04.008755: step: 184/469, loss: 0.012893940322101116
2023-01-24 05:12:04.635519: step: 186/469, loss: 0.0009624919039197266
2023-01-24 05:12:05.179833: step: 188/469, loss: 0.0019938363693654537
2023-01-24 05:12:05.792580: step: 190/469, loss: 0.02950909361243248
2023-01-24 05:12:06.403594: step: 192/469, loss: 0.009299580939114094
2023-01-24 05:12:07.035466: step: 194/469, loss: 4.469795021577738e-05
2023-01-24 05:12:07.713829: step: 196/469, loss: 0.017768926918506622
2023-01-24 05:12:08.310158: step: 198/469, loss: 0.0019421406323090196
2023-01-24 05:12:08.942345: step: 200/469, loss: 0.003053602995350957
2023-01-24 05:12:09.661234: step: 202/469, loss: 0.020354555919766426
2023-01-24 05:12:10.254609: step: 204/469, loss: 0.012567868456244469
2023-01-24 05:12:10.942306: step: 206/469, loss: 0.007447153329849243
2023-01-24 05:12:11.567929: step: 208/469, loss: 0.34254640340805054
2023-01-24 05:12:12.227478: step: 210/469, loss: 0.012624618597328663
2023-01-24 05:12:12.854738: step: 212/469, loss: 0.05136948823928833
2023-01-24 05:12:13.486519: step: 214/469, loss: 0.6681893467903137
2023-01-24 05:12:14.106435: step: 216/469, loss: 0.024027040228247643
2023-01-24 05:12:14.742352: step: 218/469, loss: 0.00382420071400702
2023-01-24 05:12:15.421690: step: 220/469, loss: 0.0004367214278317988
2023-01-24 05:12:16.049570: step: 222/469, loss: 0.00037103978684172034
2023-01-24 05:12:16.685406: step: 224/469, loss: 0.0037761121056973934
2023-01-24 05:12:17.311216: step: 226/469, loss: 0.029214244335889816
2023-01-24 05:12:17.915051: step: 228/469, loss: 0.002395816845819354
2023-01-24 05:12:18.588154: step: 230/469, loss: 0.17381082475185394
2023-01-24 05:12:19.220561: step: 232/469, loss: 0.030532490462064743
2023-01-24 05:12:19.859375: step: 234/469, loss: 0.012518075294792652
2023-01-24 05:12:20.474579: step: 236/469, loss: 0.004888856317847967
2023-01-24 05:12:21.050691: step: 238/469, loss: 0.013113731518387794
2023-01-24 05:12:21.642777: step: 240/469, loss: 0.008494261652231216
2023-01-24 05:12:22.237097: step: 242/469, loss: 0.016662968322634697
2023-01-24 05:12:22.870557: step: 244/469, loss: 0.008665439672768116
2023-01-24 05:12:23.416603: step: 246/469, loss: 0.001021687057800591
2023-01-24 05:12:24.095540: step: 248/469, loss: 0.0008591831428930163
2023-01-24 05:12:24.728077: step: 250/469, loss: 0.023028653115034103
2023-01-24 05:12:25.318427: step: 252/469, loss: 0.001024438999593258
2023-01-24 05:12:25.945168: step: 254/469, loss: 0.010340651497244835
2023-01-24 05:12:26.536439: step: 256/469, loss: 0.0374983474612236
2023-01-24 05:12:27.170862: step: 258/469, loss: 0.02440524473786354
2023-01-24 05:12:27.795436: step: 260/469, loss: 0.03594852238893509
2023-01-24 05:12:28.454863: step: 262/469, loss: 0.0031431352254003286
2023-01-24 05:12:29.127473: step: 264/469, loss: 0.3929257392883301
2023-01-24 05:12:29.713759: step: 266/469, loss: 0.005691472440958023
2023-01-24 05:12:30.258760: step: 268/469, loss: 0.001135129015892744
2023-01-24 05:12:30.903121: step: 270/469, loss: 0.005055820103734732
2023-01-24 05:12:31.525915: step: 272/469, loss: 0.001676631742157042
2023-01-24 05:12:32.176893: step: 274/469, loss: 0.0556795559823513
2023-01-24 05:12:32.770362: step: 276/469, loss: 0.009158093482255936
2023-01-24 05:12:33.413551: step: 278/469, loss: 0.0013554584002122283
2023-01-24 05:12:34.023604: step: 280/469, loss: 0.013460691086947918
2023-01-24 05:12:34.609864: step: 282/469, loss: 0.0020840729121118784
2023-01-24 05:12:35.216330: step: 284/469, loss: 0.00486515648663044
2023-01-24 05:12:35.896264: step: 286/469, loss: 0.0008479985990561545
2023-01-24 05:12:36.533065: step: 288/469, loss: 0.002161717973649502
2023-01-24 05:12:37.198921: step: 290/469, loss: 0.011881375685334206
2023-01-24 05:12:37.792202: step: 292/469, loss: 0.00757069606333971
2023-01-24 05:12:38.408644: step: 294/469, loss: 0.01817019283771515
2023-01-24 05:12:39.006750: step: 296/469, loss: 0.0027619285974651575
2023-01-24 05:12:39.681924: step: 298/469, loss: 0.001362512819468975
2023-01-24 05:12:40.298577: step: 300/469, loss: 0.006482349708676338
2023-01-24 05:12:40.971710: step: 302/469, loss: 0.0038111312314867973
2023-01-24 05:12:41.661832: step: 304/469, loss: 0.13215026259422302
2023-01-24 05:12:42.297657: step: 306/469, loss: 0.004076431971043348
2023-01-24 05:12:43.033888: step: 308/469, loss: 0.01719863899052143
2023-01-24 05:12:43.708549: step: 310/469, loss: 0.0044835517182946205
2023-01-24 05:12:44.308217: step: 312/469, loss: 0.0033766133710741997
2023-01-24 05:12:44.846631: step: 314/469, loss: 0.020229041576385498
2023-01-24 05:12:45.477062: step: 316/469, loss: 0.029720574617385864
2023-01-24 05:12:46.055366: step: 318/469, loss: 0.012220481410622597
2023-01-24 05:12:46.687529: step: 320/469, loss: 0.001467244466766715
2023-01-24 05:12:47.276240: step: 322/469, loss: 0.009732890874147415
2023-01-24 05:12:47.868391: step: 324/469, loss: 0.003811521688476205
2023-01-24 05:12:48.441868: step: 326/469, loss: 9.424789459444582e-05
2023-01-24 05:12:49.055063: step: 328/469, loss: 1.0046617984771729
2023-01-24 05:12:49.717181: step: 330/469, loss: 0.0038575257640331984
2023-01-24 05:12:50.338013: step: 332/469, loss: 0.09175248444080353
2023-01-24 05:12:50.884924: step: 334/469, loss: 2.0372726917266846
2023-01-24 05:12:51.485068: step: 336/469, loss: 0.17822694778442383
2023-01-24 05:12:52.042513: step: 338/469, loss: 0.0017835474573075771
2023-01-24 05:12:52.673170: step: 340/469, loss: 0.021845972165465355
2023-01-24 05:12:53.282231: step: 342/469, loss: 0.0038313264958560467
2023-01-24 05:12:53.853630: step: 344/469, loss: 0.002929736627265811
2023-01-24 05:12:54.448463: step: 346/469, loss: 0.0031008594669401646
2023-01-24 05:12:55.081387: step: 348/469, loss: 0.03419598937034607
2023-01-24 05:12:55.688507: step: 350/469, loss: 0.08123939484357834
2023-01-24 05:12:56.284550: step: 352/469, loss: 0.00441707344725728
2023-01-24 05:12:56.887615: step: 354/469, loss: 0.00400394294410944
2023-01-24 05:12:57.509026: step: 356/469, loss: 0.017485061660408974
2023-01-24 05:12:58.163352: step: 358/469, loss: 0.0006666892440989614
2023-01-24 05:12:58.751937: step: 360/469, loss: 0.021029051393270493
2023-01-24 05:12:59.347653: step: 362/469, loss: 0.2805744409561157
2023-01-24 05:12:59.983358: step: 364/469, loss: 0.004257042892277241
2023-01-24 05:13:00.626450: step: 366/469, loss: 0.00023133697686716914
2023-01-24 05:13:01.243767: step: 368/469, loss: 0.07727959007024765
2023-01-24 05:13:01.919133: step: 370/469, loss: 0.006901529151946306
2023-01-24 05:13:02.500726: step: 372/469, loss: 0.017377611249685287
2023-01-24 05:13:03.091794: step: 374/469, loss: 0.001473445212468505
2023-01-24 05:13:03.697749: step: 376/469, loss: 0.0023926731664687395
2023-01-24 05:13:04.363893: step: 378/469, loss: 0.003412291407585144
2023-01-24 05:13:05.016006: step: 380/469, loss: 0.00804143212735653
2023-01-24 05:13:05.633155: step: 382/469, loss: 0.0014265509089455009
2023-01-24 05:13:06.266981: step: 384/469, loss: 0.042633287608623505
2023-01-24 05:13:06.848904: step: 386/469, loss: 0.022622903808951378
2023-01-24 05:13:07.528907: step: 388/469, loss: 0.021721651777625084
2023-01-24 05:13:08.148955: step: 390/469, loss: 0.0018895902903750539
2023-01-24 05:13:08.767253: step: 392/469, loss: 0.0019854996353387833
2023-01-24 05:13:09.382769: step: 394/469, loss: 0.01369100995361805
2023-01-24 05:13:09.994243: step: 396/469, loss: 0.00621099304407835
2023-01-24 05:13:10.692711: step: 398/469, loss: 0.01120622456073761
2023-01-24 05:13:11.425133: step: 400/469, loss: 0.0005261891055852175
2023-01-24 05:13:12.081432: step: 402/469, loss: 0.00047795631689950824
2023-01-24 05:13:12.707042: step: 404/469, loss: 0.02254605107009411
2023-01-24 05:13:13.349910: step: 406/469, loss: 0.04985782504081726
2023-01-24 05:13:13.986396: step: 408/469, loss: 0.0027778656221926212
2023-01-24 05:13:14.567786: step: 410/469, loss: 0.059414394199848175
2023-01-24 05:13:15.137770: step: 412/469, loss: 0.024252986535429955
2023-01-24 05:13:15.772839: step: 414/469, loss: 0.019016612321138382
2023-01-24 05:13:16.448960: step: 416/469, loss: 0.004256725311279297
2023-01-24 05:13:17.097886: step: 418/469, loss: 0.0007422525086440146
2023-01-24 05:13:17.668601: step: 420/469, loss: 0.05341136455535889
2023-01-24 05:13:18.340538: step: 422/469, loss: 0.007369490340352058
2023-01-24 05:13:18.923868: step: 424/469, loss: 0.06091062352061272
2023-01-24 05:13:19.602913: step: 426/469, loss: 0.007739037275314331
2023-01-24 05:13:20.201149: step: 428/469, loss: 0.0036941147409379482
2023-01-24 05:13:20.816071: step: 430/469, loss: 0.027182970196008682
2023-01-24 05:13:21.410253: step: 432/469, loss: 0.002020519459620118
2023-01-24 05:13:22.004127: step: 434/469, loss: 0.12288780510425568
2023-01-24 05:13:22.624927: step: 436/469, loss: 0.014308992773294449
2023-01-24 05:13:23.256388: step: 438/469, loss: 0.03507082536816597
2023-01-24 05:13:23.863122: step: 440/469, loss: 0.001033384003676474
2023-01-24 05:13:24.464412: step: 442/469, loss: 0.9164943099021912
2023-01-24 05:13:25.111886: step: 444/469, loss: 0.004102073609828949
2023-01-24 05:13:25.739440: step: 446/469, loss: 0.0014659215230494738
2023-01-24 05:13:26.403903: step: 448/469, loss: 0.016013145446777344
2023-01-24 05:13:27.014201: step: 450/469, loss: 0.0547676607966423
2023-01-24 05:13:27.617103: step: 452/469, loss: 0.02253960631787777
2023-01-24 05:13:28.178789: step: 454/469, loss: 0.0020860759541392326
2023-01-24 05:13:28.738704: step: 456/469, loss: 0.0037214504554867744
2023-01-24 05:13:29.304877: step: 458/469, loss: 0.0073936269618570805
2023-01-24 05:13:29.880087: step: 460/469, loss: 0.010454141534864902
2023-01-24 05:13:30.444181: step: 462/469, loss: 0.006855126470327377
2023-01-24 05:13:31.087344: step: 464/469, loss: 0.022780634462833405
2023-01-24 05:13:31.753044: step: 466/469, loss: 0.03849603235721588
2023-01-24 05:13:32.398619: step: 468/469, loss: 0.012857901863753796
2023-01-24 05:13:33.088305: step: 470/469, loss: 0.0005129786441102624
2023-01-24 05:13:33.762648: step: 472/469, loss: 0.0010221077827736735
2023-01-24 05:13:34.361062: step: 474/469, loss: 0.017566831782460213
2023-01-24 05:13:34.965825: step: 476/469, loss: 0.008294445462524891
2023-01-24 05:13:35.652629: step: 478/469, loss: 0.025740107521414757
2023-01-24 05:13:36.310563: step: 480/469, loss: 0.005647765938192606
2023-01-24 05:13:36.876091: step: 482/469, loss: 0.00023753277491778135
2023-01-24 05:13:37.490899: step: 484/469, loss: 0.036121148616075516
2023-01-24 05:13:38.142514: step: 486/469, loss: 0.11313173919916153
2023-01-24 05:13:38.769815: step: 488/469, loss: 0.009546004235744476
2023-01-24 05:13:39.399120: step: 490/469, loss: 0.012960994616150856
2023-01-24 05:13:40.046955: step: 492/469, loss: 0.022116269916296005
2023-01-24 05:13:40.659176: step: 494/469, loss: 0.002578374929726124
2023-01-24 05:13:41.210386: step: 496/469, loss: 0.001413803081959486
2023-01-24 05:13:41.787150: step: 498/469, loss: 3.757523518288508e-05
2023-01-24 05:13:42.487407: step: 500/469, loss: 0.005428260657936335
2023-01-24 05:13:43.051734: step: 502/469, loss: 0.010336990468204021
2023-01-24 05:13:43.663240: step: 504/469, loss: 0.013869226910173893
2023-01-24 05:13:44.313817: step: 506/469, loss: 0.017277058213949203
2023-01-24 05:13:44.975078: step: 508/469, loss: 0.0038197608664631844
2023-01-24 05:13:45.545185: step: 510/469, loss: 0.025294004008173943
2023-01-24 05:13:46.173533: step: 512/469, loss: 0.485908567905426
2023-01-24 05:13:46.790455: step: 514/469, loss: 0.01573188789188862
2023-01-24 05:13:47.347115: step: 516/469, loss: 0.0028253868222236633
2023-01-24 05:13:48.031745: step: 518/469, loss: 0.007987121120095253
2023-01-24 05:13:48.704143: step: 520/469, loss: 0.010225597769021988
2023-01-24 05:13:49.295803: step: 522/469, loss: 0.0044867186807096004
2023-01-24 05:13:50.000777: step: 524/469, loss: 0.004424052778631449
2023-01-24 05:13:50.568401: step: 526/469, loss: 1.942397102538962e-05
2023-01-24 05:13:51.254825: step: 528/469, loss: 0.007998321205377579
2023-01-24 05:13:51.902539: step: 530/469, loss: 0.01795625314116478
2023-01-24 05:13:52.563451: step: 532/469, loss: 0.09316721558570862
2023-01-24 05:13:53.135637: step: 534/469, loss: 0.001042116666212678
2023-01-24 05:13:53.824163: step: 536/469, loss: 0.00992762204259634
2023-01-24 05:13:54.415824: step: 538/469, loss: 0.029562314972281456
2023-01-24 05:13:55.041432: step: 540/469, loss: 0.0009023420279845595
2023-01-24 05:13:55.616269: step: 542/469, loss: 0.028390206396579742
2023-01-24 05:13:56.155326: step: 544/469, loss: 6.388746260199696e-05
2023-01-24 05:13:56.773952: step: 546/469, loss: 0.0031936070881783962
2023-01-24 05:13:57.416361: step: 548/469, loss: 0.008089176379144192
2023-01-24 05:13:58.085887: step: 550/469, loss: 0.029060736298561096
2023-01-24 05:13:58.694066: step: 552/469, loss: 0.01640424132347107
2023-01-24 05:13:59.402842: step: 554/469, loss: 0.0007548629655502737
2023-01-24 05:14:00.108824: step: 556/469, loss: 0.0028010231908410788
2023-01-24 05:14:00.730519: step: 558/469, loss: 0.0002140920259989798
2023-01-24 05:14:01.374747: step: 560/469, loss: 0.005593898706138134
2023-01-24 05:14:01.979240: step: 562/469, loss: 0.00156761787366122
2023-01-24 05:14:02.600797: step: 564/469, loss: 0.00020123986178077757
2023-01-24 05:14:03.199719: step: 566/469, loss: 0.009417970664799213
2023-01-24 05:14:03.870538: step: 568/469, loss: 0.00011312395508866757
2023-01-24 05:14:04.463187: step: 570/469, loss: 0.006780230440199375
2023-01-24 05:14:05.083446: step: 572/469, loss: 0.011906866915524006
2023-01-24 05:14:05.675569: step: 574/469, loss: 0.018123114481568336
2023-01-24 05:14:06.451609: step: 576/469, loss: 0.017633073031902313
2023-01-24 05:14:07.124331: step: 578/469, loss: 0.0015887359622865915
2023-01-24 05:14:07.727476: step: 580/469, loss: 0.00014775626186747104
2023-01-24 05:14:08.288202: step: 582/469, loss: 0.044115468859672546
2023-01-24 05:14:08.929456: step: 584/469, loss: 0.002225038595497608
2023-01-24 05:14:09.520090: step: 586/469, loss: 0.006928933784365654
2023-01-24 05:14:10.164696: step: 588/469, loss: 0.0031385808251798153
2023-01-24 05:14:10.788396: step: 590/469, loss: 0.0014847946586087346
2023-01-24 05:14:11.365503: step: 592/469, loss: 0.004237988963723183
2023-01-24 05:14:12.118496: step: 594/469, loss: 0.003485941793769598
2023-01-24 05:14:12.747040: step: 596/469, loss: 0.0012962986947968602
2023-01-24 05:14:13.392575: step: 598/469, loss: 0.008641515858471394
2023-01-24 05:14:13.951544: step: 600/469, loss: 0.01856308989226818
2023-01-24 05:14:14.595532: step: 602/469, loss: 0.12201689928770065
2023-01-24 05:14:15.241913: step: 604/469, loss: 0.00418493989855051
2023-01-24 05:14:15.820530: step: 606/469, loss: 0.008976966142654419
2023-01-24 05:14:16.425918: step: 608/469, loss: 0.010338297113776207
2023-01-24 05:14:17.044338: step: 610/469, loss: 0.004966519307345152
2023-01-24 05:14:17.679692: step: 612/469, loss: 0.006739511154592037
2023-01-24 05:14:18.324771: step: 614/469, loss: 0.00052741909166798
2023-01-24 05:14:18.878343: step: 616/469, loss: 0.0007422165363095701
2023-01-24 05:14:19.508177: step: 618/469, loss: 0.0005756103782914579
2023-01-24 05:14:20.123674: step: 620/469, loss: 0.002179077360779047
2023-01-24 05:14:20.812472: step: 622/469, loss: 0.000697400770150125
2023-01-24 05:14:21.400625: step: 624/469, loss: 0.005185157526284456
2023-01-24 05:14:22.014543: step: 626/469, loss: 0.0017763691721484065
2023-01-24 05:14:22.629659: step: 628/469, loss: 0.0018852520734071732
2023-01-24 05:14:23.213338: step: 630/469, loss: 0.03680843114852905
2023-01-24 05:14:23.842030: step: 632/469, loss: 0.02520536445081234
2023-01-24 05:14:24.526354: step: 634/469, loss: 0.008047816343605518
2023-01-24 05:14:25.152356: step: 636/469, loss: 0.05942419543862343
2023-01-24 05:14:25.748509: step: 638/469, loss: 0.03507499769330025
2023-01-24 05:14:26.288905: step: 640/469, loss: 0.00015529656957369298
2023-01-24 05:14:26.859200: step: 642/469, loss: 0.010113165713846684
2023-01-24 05:14:27.559024: step: 644/469, loss: 0.0006901027518324554
2023-01-24 05:14:28.124910: step: 646/469, loss: 0.015838168561458588
2023-01-24 05:14:28.764201: step: 648/469, loss: 0.010356945917010307
2023-01-24 05:14:29.408985: step: 650/469, loss: 0.00045444778515957296
2023-01-24 05:14:30.020700: step: 652/469, loss: 0.04789530485868454
2023-01-24 05:14:30.668169: step: 654/469, loss: 0.00017765616939868778
2023-01-24 05:14:31.284557: step: 656/469, loss: 0.0028024199418723583
2023-01-24 05:14:31.903294: step: 658/469, loss: 0.046418748795986176
2023-01-24 05:14:32.553513: step: 660/469, loss: 0.01530068926513195
2023-01-24 05:14:33.233061: step: 662/469, loss: 0.028189966455101967
2023-01-24 05:14:33.856388: step: 664/469, loss: 0.012885896489024162
2023-01-24 05:14:34.474496: step: 666/469, loss: 0.004930654540657997
2023-01-24 05:14:35.129849: step: 668/469, loss: 0.004085281863808632
2023-01-24 05:14:35.743633: step: 670/469, loss: 0.03574523702263832
2023-01-24 05:14:36.465858: step: 672/469, loss: 0.0017322733765468001
2023-01-24 05:14:37.094527: step: 674/469, loss: 0.00633661774918437
2023-01-24 05:14:37.728379: step: 676/469, loss: 0.006138347554951906
2023-01-24 05:14:38.308622: step: 678/469, loss: 0.05056126415729523
2023-01-24 05:14:38.931809: step: 680/469, loss: 0.07599984109401703
2023-01-24 05:14:39.647598: step: 682/469, loss: 0.0013540622312575579
2023-01-24 05:14:40.252514: step: 684/469, loss: 0.005420427769422531
2023-01-24 05:14:40.902868: step: 686/469, loss: 0.17848405241966248
2023-01-24 05:14:41.661858: step: 688/469, loss: 0.025562219321727753
2023-01-24 05:14:42.267144: step: 690/469, loss: 0.08172006160020828
2023-01-24 05:14:42.937306: step: 692/469, loss: 0.003798913676291704
2023-01-24 05:14:43.588387: step: 694/469, loss: 0.007975392043590546
2023-01-24 05:14:44.215841: step: 696/469, loss: 0.015071935951709747
2023-01-24 05:14:44.788812: step: 698/469, loss: 0.0039918553084135056
2023-01-24 05:14:45.481393: step: 700/469, loss: 0.009902305901050568
2023-01-24 05:14:46.132943: step: 702/469, loss: 0.6302534937858582
2023-01-24 05:14:46.716306: step: 704/469, loss: 8.2736587501131e-05
2023-01-24 05:14:47.393776: step: 706/469, loss: 0.056186988949775696
2023-01-24 05:14:48.038761: step: 708/469, loss: 0.0038653018418699503
2023-01-24 05:14:48.675545: step: 710/469, loss: 0.004778795875608921
2023-01-24 05:14:49.309620: step: 712/469, loss: 0.008922592736780643
2023-01-24 05:14:50.007164: step: 714/469, loss: 0.0406455434858799
2023-01-24 05:14:50.634573: step: 716/469, loss: 0.35129010677337646
2023-01-24 05:14:51.202136: step: 718/469, loss: 0.00021591174299828708
2023-01-24 05:14:51.895153: step: 720/469, loss: 0.14848856627941132
2023-01-24 05:14:52.522898: step: 722/469, loss: 0.015957769006490707
2023-01-24 05:14:53.109982: step: 724/469, loss: 0.6531515717506409
2023-01-24 05:14:53.692131: step: 726/469, loss: 0.006518089212477207
2023-01-24 05:14:54.288639: step: 728/469, loss: 0.0049733794294297695
2023-01-24 05:14:54.890322: step: 730/469, loss: 0.002887943759560585
2023-01-24 05:14:55.605820: step: 732/469, loss: 0.0022062307689338923
2023-01-24 05:14:56.161071: step: 734/469, loss: 0.0024291295558214188
2023-01-24 05:14:56.759969: step: 736/469, loss: 0.054791562259197235
2023-01-24 05:14:57.400725: step: 738/469, loss: 0.028176110237836838
2023-01-24 05:14:58.039510: step: 740/469, loss: 0.026619803160429
2023-01-24 05:14:58.774220: step: 742/469, loss: 0.004758811555802822
2023-01-24 05:14:59.343970: step: 744/469, loss: 0.00128581328317523
2023-01-24 05:15:00.032395: step: 746/469, loss: 0.04105202481150627
2023-01-24 05:15:00.717180: step: 748/469, loss: 0.0015457069966942072
2023-01-24 05:15:01.346659: step: 750/469, loss: 0.04305998608469963
2023-01-24 05:15:02.007494: step: 752/469, loss: 0.009557138197124004
2023-01-24 05:15:02.613371: step: 754/469, loss: 0.001405681949108839
2023-01-24 05:15:03.270552: step: 756/469, loss: 0.02468080446124077
2023-01-24 05:15:03.932447: step: 758/469, loss: 0.011018931865692139
2023-01-24 05:15:04.729749: step: 760/469, loss: 0.019617140293121338
2023-01-24 05:15:05.333663: step: 762/469, loss: 0.005259671714156866
2023-01-24 05:15:05.965677: step: 764/469, loss: 0.0014008820289745927
2023-01-24 05:15:06.571591: step: 766/469, loss: 0.004322248511016369
2023-01-24 05:15:07.183872: step: 768/469, loss: 0.0024822531268000603
2023-01-24 05:15:07.801960: step: 770/469, loss: 0.0076635791920125484
2023-01-24 05:15:08.423466: step: 772/469, loss: 0.0390038900077343
2023-01-24 05:15:09.060541: step: 774/469, loss: 0.02912021242082119
2023-01-24 05:15:09.667976: step: 776/469, loss: 0.0012746142456308007
2023-01-24 05:15:10.290530: step: 778/469, loss: 3.890005350112915
2023-01-24 05:15:10.899861: step: 780/469, loss: 0.033169832080602646
2023-01-24 05:15:11.509520: step: 782/469, loss: 0.0016558844363316894
2023-01-24 05:15:12.190453: step: 784/469, loss: 0.22162684798240662
2023-01-24 05:15:12.857894: step: 786/469, loss: 0.012074566446244717
2023-01-24 05:15:13.446473: step: 788/469, loss: 0.023014012724161148
2023-01-24 05:15:14.040611: step: 790/469, loss: 0.0008739625918678939
2023-01-24 05:15:14.628601: step: 792/469, loss: 0.00013586315617430955
2023-01-24 05:15:15.184552: step: 794/469, loss: 0.011108554899692535
2023-01-24 05:15:15.821749: step: 796/469, loss: 0.0015684902900829911
2023-01-24 05:15:16.428750: step: 798/469, loss: 0.03064385987818241
2023-01-24 05:15:17.030725: step: 800/469, loss: 0.00010309765639249235
2023-01-24 05:15:17.708665: step: 802/469, loss: 0.0014354257145896554
2023-01-24 05:15:18.317630: step: 804/469, loss: 2.1678266525268555
2023-01-24 05:15:18.975027: step: 806/469, loss: 0.017343001440167427
2023-01-24 05:15:19.593128: step: 808/469, loss: 0.04927444830536842
2023-01-24 05:15:20.235976: step: 810/469, loss: 0.0027439019177109003
2023-01-24 05:15:20.882167: step: 812/469, loss: 6.236750050447881e-05
2023-01-24 05:15:21.470734: step: 814/469, loss: 0.0031373342499136925
2023-01-24 05:15:22.126766: step: 816/469, loss: 0.008151421323418617
2023-01-24 05:15:22.752518: step: 818/469, loss: 0.00015864340821281075
2023-01-24 05:15:23.378755: step: 820/469, loss: 0.02975013665854931
2023-01-24 05:15:24.031541: step: 822/469, loss: 0.005652218125760555
2023-01-24 05:15:24.662846: step: 824/469, loss: 0.0030411549378186464
2023-01-24 05:15:25.269561: step: 826/469, loss: 0.03713679686188698
2023-01-24 05:15:25.856228: step: 828/469, loss: 0.0015378013486042619
2023-01-24 05:15:26.454512: step: 830/469, loss: 0.0037213508039712906
2023-01-24 05:15:26.994014: step: 832/469, loss: 0.0023648878559470177
2023-01-24 05:15:27.536913: step: 834/469, loss: 4.139569227845641e-06
2023-01-24 05:15:28.155314: step: 836/469, loss: 0.004509124904870987
2023-01-24 05:15:28.703301: step: 838/469, loss: 0.13292941451072693
2023-01-24 05:15:29.343133: step: 840/469, loss: 0.0561220645904541
2023-01-24 05:15:29.981407: step: 842/469, loss: 0.0004946504486724734
2023-01-24 05:15:30.654530: step: 844/469, loss: 0.027973726391792297
2023-01-24 05:15:31.327008: step: 846/469, loss: 0.20878294110298157
2023-01-24 05:15:31.913569: step: 848/469, loss: 0.009020388126373291
2023-01-24 05:15:32.511659: step: 850/469, loss: 0.0171761903911829
2023-01-24 05:15:33.195028: step: 852/469, loss: 0.02266085147857666
2023-01-24 05:15:33.795390: step: 854/469, loss: 0.005098353605717421
2023-01-24 05:15:34.380888: step: 856/469, loss: 1.4842417840554845e-05
2023-01-24 05:15:35.038681: step: 858/469, loss: 0.04865461215376854
2023-01-24 05:15:35.736006: step: 860/469, loss: 0.003949211910367012
2023-01-24 05:15:36.340962: step: 862/469, loss: 1.0983926057815552
2023-01-24 05:15:36.943509: step: 864/469, loss: 0.037031140178442
2023-01-24 05:15:37.584650: step: 866/469, loss: 0.222388356924057
2023-01-24 05:15:38.217910: step: 868/469, loss: 0.006978880148380995
2023-01-24 05:15:38.846175: step: 870/469, loss: 0.0023100259713828564
2023-01-24 05:15:39.480958: step: 872/469, loss: 0.008067827671766281
2023-01-24 05:15:40.093663: step: 874/469, loss: 0.0067926631309092045
2023-01-24 05:15:40.718569: step: 876/469, loss: 0.04275653511285782
2023-01-24 05:15:41.373692: step: 878/469, loss: 0.002950613386929035
2023-01-24 05:15:42.014045: step: 880/469, loss: 0.004311679862439632
2023-01-24 05:15:42.617909: step: 882/469, loss: 0.017032163217663765
2023-01-24 05:15:43.226780: step: 884/469, loss: 0.0003411119687370956
2023-01-24 05:15:43.888825: step: 886/469, loss: 0.052657030522823334
2023-01-24 05:15:44.512195: step: 888/469, loss: 0.019283462315797806
2023-01-24 05:15:45.189091: step: 890/469, loss: 0.048589691519737244
2023-01-24 05:15:45.855833: step: 892/469, loss: 0.0272402074187994
2023-01-24 05:15:46.483766: step: 894/469, loss: 0.578173816204071
2023-01-24 05:15:47.101011: step: 896/469, loss: 0.0022126534022390842
2023-01-24 05:15:47.675619: step: 898/469, loss: 0.015187570825219154
2023-01-24 05:15:48.278232: step: 900/469, loss: 0.007477788254618645
2023-01-24 05:15:48.914269: step: 902/469, loss: 0.00683231744915247
2023-01-24 05:15:49.518713: step: 904/469, loss: 0.0017801914364099503
2023-01-24 05:15:50.061011: step: 906/469, loss: 0.004318722523748875
2023-01-24 05:15:50.684934: step: 908/469, loss: 0.0005664682830683887
2023-01-24 05:15:51.240278: step: 910/469, loss: 0.040004484355449677
2023-01-24 05:15:51.878272: step: 912/469, loss: 0.013206937350332737
2023-01-24 05:15:52.495152: step: 914/469, loss: 0.009563728235661983
2023-01-24 05:15:53.063511: step: 916/469, loss: 0.003190231043845415
2023-01-24 05:15:53.627769: step: 918/469, loss: 0.0006425548926927149
2023-01-24 05:15:54.232216: step: 920/469, loss: 0.025662649422883987
2023-01-24 05:15:54.991722: step: 922/469, loss: 0.013986133970320225
2023-01-24 05:15:55.578935: step: 924/469, loss: 0.11339568346738815
2023-01-24 05:15:56.174217: step: 926/469, loss: 0.0007033753208816051
2023-01-24 05:15:56.778406: step: 928/469, loss: 0.006073335651308298
2023-01-24 05:15:57.442189: step: 930/469, loss: 0.03721383213996887
2023-01-24 05:15:57.995817: step: 932/469, loss: 0.04197828844189644
2023-01-24 05:15:58.558276: step: 934/469, loss: 0.0018439313862472773
2023-01-24 05:15:59.183830: step: 936/469, loss: 0.001097707194276154
2023-01-24 05:15:59.762356: step: 938/469, loss: 0.03952580317854881
==================================================
Loss: 0.091
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31014948593073594, 'r': 0.296613550112127, 'f1': 0.30323053522617055}, 'combined': 0.22343302595612566, 'epoch': 34}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32257092186212294, 'r': 0.2641362992375115, 'f1': 0.29044363688792757}, 'combined': 0.15842380193886957, 'epoch': 34}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32493040343190943, 'r': 0.30704998274969814, 'f1': 0.3157372505543237}, 'combined': 0.23264850040844903, 'epoch': 34}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33141891932973394, 'r': 0.2698653597469929, 'f1': 0.2974915160902302}, 'combined': 0.16226809968558012, 'epoch': 34}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31003712573046566, 'r': 0.29591778793628887, 'f1': 0.3028129596940276}, 'combined': 0.22312533872191506, 'epoch': 34}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32367147743118885, 'r': 0.26681427371043104, 'f1': 0.2925055177186571}, 'combined': 0.1595484642101766, 'epoch': 34}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.32291666666666663, 'r': 0.2952380952380952, 'f1': 0.308457711442786}, 'combined': 0.20563847429519067, 'epoch': 34}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.2826086956521739, 'r': 0.2826086956521739, 'f1': 0.2826086956521739}, 'combined': 0.14130434782608695, 'epoch': 34}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4444444444444444, 'r': 0.13793103448275862, 'f1': 0.21052631578947367}, 'combined': 0.14035087719298245, 'epoch': 34}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 05:18:45.434837: step: 2/469, loss: 0.06223827227950096
2023-01-24 05:18:46.069196: step: 4/469, loss: 0.00801390316337347
2023-01-24 05:18:46.843459: step: 6/469, loss: 0.007537577301263809
2023-01-24 05:18:47.502848: step: 8/469, loss: 0.00014759607438463718
2023-01-24 05:18:48.053923: step: 10/469, loss: 0.007370145991444588
2023-01-24 05:18:48.629289: step: 12/469, loss: 0.0005001530516892672
2023-01-24 05:18:49.270870: step: 14/469, loss: 0.01761670596897602
2023-01-24 05:18:49.907768: step: 16/469, loss: 0.12962032854557037
2023-01-24 05:18:50.518792: step: 18/469, loss: 0.0010319643188267946
2023-01-24 05:18:51.201163: step: 20/469, loss: 0.016550837084650993
2023-01-24 05:18:51.784740: step: 22/469, loss: 0.30565378069877625
2023-01-24 05:18:52.514938: step: 24/469, loss: 0.00024738864158280194
2023-01-24 05:18:53.229165: step: 26/469, loss: 0.001660690875723958
2023-01-24 05:18:53.871832: step: 28/469, loss: 0.036150235682725906
2023-01-24 05:18:54.510157: step: 30/469, loss: 0.0013579098740592599
2023-01-24 05:18:55.086708: step: 32/469, loss: 0.005291574168950319
2023-01-24 05:18:55.681673: step: 34/469, loss: 0.010724920779466629
2023-01-24 05:18:56.360446: step: 36/469, loss: 0.003547102678567171
2023-01-24 05:18:56.945989: step: 38/469, loss: 0.00706341490149498
2023-01-24 05:18:57.596793: step: 40/469, loss: 0.0016088581178337336
2023-01-24 05:18:58.214464: step: 42/469, loss: 0.0027645586524158716
2023-01-24 05:18:58.770553: step: 44/469, loss: 0.0011111802887171507
2023-01-24 05:18:59.353424: step: 46/469, loss: 0.0009060550946742296
2023-01-24 05:18:59.939154: step: 48/469, loss: 0.0012177587486803532
2023-01-24 05:19:00.601393: step: 50/469, loss: 0.002270347438752651
2023-01-24 05:19:01.244758: step: 52/469, loss: 0.013230101205408573
2023-01-24 05:19:01.944232: step: 54/469, loss: 0.0015403461875393987
2023-01-24 05:19:02.530585: step: 56/469, loss: 0.035884175449609756
2023-01-24 05:19:03.144915: step: 58/469, loss: 1.0156863927841187
2023-01-24 05:19:03.800162: step: 60/469, loss: 0.01794080063700676
2023-01-24 05:19:04.395900: step: 62/469, loss: 0.012344960123300552
2023-01-24 05:19:05.005456: step: 64/469, loss: 0.029343632981181145
2023-01-24 05:19:05.628282: step: 66/469, loss: 0.0009511752869002521
2023-01-24 05:19:06.217680: step: 68/469, loss: 0.003018788993358612
2023-01-24 05:19:06.853732: step: 70/469, loss: 0.01511884294450283
2023-01-24 05:19:07.473583: step: 72/469, loss: 0.025081027299165726
2023-01-24 05:19:08.108978: step: 74/469, loss: 0.0034823277965188026
2023-01-24 05:19:08.788391: step: 76/469, loss: 0.00952210370451212
2023-01-24 05:19:09.440401: step: 78/469, loss: 0.028778832405805588
2023-01-24 05:19:10.058995: step: 80/469, loss: 0.02010970562696457
2023-01-24 05:19:10.830022: step: 82/469, loss: 0.3724760115146637
2023-01-24 05:19:11.433796: step: 84/469, loss: 0.001976816216483712
2023-01-24 05:19:12.018156: step: 86/469, loss: 0.01593942940235138
2023-01-24 05:19:12.713662: step: 88/469, loss: 0.0011511326301842928
2023-01-24 05:19:13.409563: step: 90/469, loss: 0.012217110954225063
2023-01-24 05:19:14.096966: step: 92/469, loss: 0.007778637111186981
2023-01-24 05:19:14.767853: step: 94/469, loss: 0.0013589736772701144
2023-01-24 05:19:15.426414: step: 96/469, loss: 0.011407505720853806
2023-01-24 05:19:16.102355: step: 98/469, loss: 0.01613622158765793
2023-01-24 05:19:16.748084: step: 100/469, loss: 0.010910450480878353
2023-01-24 05:19:17.366622: step: 102/469, loss: 0.033466242253780365
2023-01-24 05:19:17.996156: step: 104/469, loss: 0.03147251531481743
2023-01-24 05:19:18.676367: step: 106/469, loss: 0.003176672151312232
2023-01-24 05:19:19.277232: step: 108/469, loss: 0.1680041402578354
2023-01-24 05:19:19.902625: step: 110/469, loss: 0.09557179361581802
2023-01-24 05:19:20.481349: step: 112/469, loss: 0.001714197569526732
2023-01-24 05:19:21.117370: step: 114/469, loss: 0.026560502126812935
2023-01-24 05:19:21.722346: step: 116/469, loss: 0.00048767152475193143
2023-01-24 05:19:22.469150: step: 118/469, loss: 0.0006235787877812982
2023-01-24 05:19:23.000677: step: 120/469, loss: 0.0025874904822558165
2023-01-24 05:19:23.680475: step: 122/469, loss: 0.004461661912500858
2023-01-24 05:19:24.396507: step: 124/469, loss: 0.013387758284807205
2023-01-24 05:19:24.989899: step: 126/469, loss: 0.03437449410557747
2023-01-24 05:19:25.620296: step: 128/469, loss: 0.01547978539019823
2023-01-24 05:19:26.225858: step: 130/469, loss: 0.027353087440133095
2023-01-24 05:19:26.861603: step: 132/469, loss: 0.10551943629980087
2023-01-24 05:19:27.471894: step: 134/469, loss: 0.0008355679456144571
2023-01-24 05:19:28.121490: step: 136/469, loss: 5.5443837482016534e-05
2023-01-24 05:19:28.753236: step: 138/469, loss: 0.01803562231361866
2023-01-24 05:19:29.372149: step: 140/469, loss: 0.0072751473635435104
2023-01-24 05:19:30.025784: step: 142/469, loss: 0.0002711582346819341
2023-01-24 05:19:30.650557: step: 144/469, loss: 0.010057334788143635
2023-01-24 05:19:31.297076: step: 146/469, loss: 0.0020914659835398197
2023-01-24 05:19:31.876300: step: 148/469, loss: 0.027402479201555252
2023-01-24 05:19:32.532249: step: 150/469, loss: 0.07805662602186203
2023-01-24 05:19:33.200230: step: 152/469, loss: 0.05145958438515663
2023-01-24 05:19:33.842311: step: 154/469, loss: 0.0231634508818388
2023-01-24 05:19:34.402182: step: 156/469, loss: 7.571755850221962e-05
2023-01-24 05:19:34.975482: step: 158/469, loss: 0.0025138002820312977
2023-01-24 05:19:35.628741: step: 160/469, loss: 0.02510700188577175
2023-01-24 05:19:36.288120: step: 162/469, loss: 0.0085305105894804
2023-01-24 05:19:36.965031: step: 164/469, loss: 0.0009671675506979227
2023-01-24 05:19:37.641828: step: 166/469, loss: 0.03375331312417984
2023-01-24 05:19:38.231488: step: 168/469, loss: 0.004886567126959562
2023-01-24 05:19:38.814560: step: 170/469, loss: 0.04269058629870415
2023-01-24 05:19:39.359454: step: 172/469, loss: 0.016756601631641388
2023-01-24 05:19:39.968453: step: 174/469, loss: 0.002597453538328409
2023-01-24 05:19:40.538607: step: 176/469, loss: 0.010407566092908382
2023-01-24 05:19:41.172030: step: 178/469, loss: 0.022121120244264603
2023-01-24 05:19:41.791091: step: 180/469, loss: 0.5732991099357605
2023-01-24 05:19:42.413110: step: 182/469, loss: 0.036545529961586
2023-01-24 05:19:43.049546: step: 184/469, loss: 0.004315868951380253
2023-01-24 05:19:43.674740: step: 186/469, loss: 0.020468683913350105
2023-01-24 05:19:44.351023: step: 188/469, loss: 0.006902128458023071
2023-01-24 05:19:44.973754: step: 190/469, loss: 0.04524805769324303
2023-01-24 05:19:45.588841: step: 192/469, loss: 0.00020645791664719582
2023-01-24 05:19:46.229388: step: 194/469, loss: 0.002660428173840046
2023-01-24 05:19:46.828369: step: 196/469, loss: 0.06269151717424393
2023-01-24 05:19:47.442973: step: 198/469, loss: 0.0013125533005222678
2023-01-24 05:19:48.050824: step: 200/469, loss: 0.0731223076581955
2023-01-24 05:19:48.720403: step: 202/469, loss: 0.010240744799375534
2023-01-24 05:19:49.363694: step: 204/469, loss: 0.003099207766354084
2023-01-24 05:19:49.942597: step: 206/469, loss: 0.0004563714028336108
2023-01-24 05:19:50.560501: step: 208/469, loss: 0.004949130583554506
2023-01-24 05:19:51.280285: step: 210/469, loss: 0.013902345672249794
2023-01-24 05:19:52.039178: step: 212/469, loss: 0.0035656061954796314
2023-01-24 05:19:52.702297: step: 214/469, loss: 0.025212017819285393
2023-01-24 05:19:53.281575: step: 216/469, loss: 0.003123203292489052
2023-01-24 05:19:53.982953: step: 218/469, loss: 0.06892810761928558
2023-01-24 05:19:54.628293: step: 220/469, loss: 0.011356232687830925
2023-01-24 05:19:55.240389: step: 222/469, loss: 0.005522533785551786
2023-01-24 05:19:55.908523: step: 224/469, loss: 0.0005612036329694092
2023-01-24 05:19:56.554176: step: 226/469, loss: 0.010729297995567322
2023-01-24 05:19:57.203761: step: 228/469, loss: 0.010812995955348015
2023-01-24 05:19:57.771177: step: 230/469, loss: 0.00023187536862678826
2023-01-24 05:19:58.311082: step: 232/469, loss: 0.0005325591191649437
2023-01-24 05:19:58.997217: step: 234/469, loss: 0.0056231459602713585
2023-01-24 05:19:59.621092: step: 236/469, loss: 0.002099360106512904
2023-01-24 05:20:00.246333: step: 238/469, loss: 0.035660479217767715
2023-01-24 05:20:00.811394: step: 240/469, loss: 0.017806263640522957
2023-01-24 05:20:01.403335: step: 242/469, loss: 0.00563768669962883
2023-01-24 05:20:02.046314: step: 244/469, loss: 0.010401152074337006
2023-01-24 05:20:02.692970: step: 246/469, loss: 0.01913202367722988
2023-01-24 05:20:03.389955: step: 248/469, loss: 4.502174851950258e-05
2023-01-24 05:20:03.985334: step: 250/469, loss: 7.243495929287747e-05
2023-01-24 05:20:04.660891: step: 252/469, loss: 0.0009222208173014224
2023-01-24 05:20:05.370977: step: 254/469, loss: 0.07658590376377106
2023-01-24 05:20:05.982668: step: 256/469, loss: 0.004743319004774094
2023-01-24 05:20:06.624198: step: 258/469, loss: 0.0024721897207200527
2023-01-24 05:20:07.206308: step: 260/469, loss: 0.0011867209104821086
2023-01-24 05:20:07.932873: step: 262/469, loss: 0.0561700165271759
2023-01-24 05:20:08.521339: step: 264/469, loss: 0.014542055316269398
2023-01-24 05:20:09.154429: step: 266/469, loss: 0.418611615896225
2023-01-24 05:20:09.757330: step: 268/469, loss: 0.0036808205768465996
2023-01-24 05:20:10.417288: step: 270/469, loss: 0.01344411913305521
2023-01-24 05:20:11.035738: step: 272/469, loss: 0.010014382191002369
2023-01-24 05:20:11.675234: step: 274/469, loss: 0.0018394882790744305
2023-01-24 05:20:12.454295: step: 276/469, loss: 0.06465846300125122
2023-01-24 05:20:13.131423: step: 278/469, loss: 0.007905179634690285
2023-01-24 05:20:13.734365: step: 280/469, loss: 0.0169659536331892
2023-01-24 05:20:14.333024: step: 282/469, loss: 0.0152912437915802
2023-01-24 05:20:14.981010: step: 284/469, loss: 0.04542376101016998
2023-01-24 05:20:15.619908: step: 286/469, loss: 0.004321933723986149
2023-01-24 05:20:16.288497: step: 288/469, loss: 0.044069863855838776
2023-01-24 05:20:16.882207: step: 290/469, loss: 0.0033424466382712126
2023-01-24 05:20:17.572231: step: 292/469, loss: 0.01769493706524372
2023-01-24 05:20:18.181799: step: 294/469, loss: 0.00044977504876442254
2023-01-24 05:20:18.761833: step: 296/469, loss: 0.0023002258967608213
2023-01-24 05:20:19.419093: step: 298/469, loss: 0.0354275219142437
2023-01-24 05:20:19.983434: step: 300/469, loss: 0.0009577972814440727
2023-01-24 05:20:20.590891: step: 302/469, loss: 0.010117345489561558
2023-01-24 05:20:21.261223: step: 304/469, loss: 0.029526468366384506
2023-01-24 05:20:22.008713: step: 306/469, loss: 0.037232935428619385
2023-01-24 05:20:22.653768: step: 308/469, loss: 0.0014969746116548777
2023-01-24 05:20:23.249060: step: 310/469, loss: 0.001418725703842938
2023-01-24 05:20:23.855036: step: 312/469, loss: 0.039661943912506104
2023-01-24 05:20:24.475990: step: 314/469, loss: 0.03849601745605469
2023-01-24 05:20:25.152835: step: 316/469, loss: 0.004174413625150919
2023-01-24 05:20:25.775721: step: 318/469, loss: 0.0023285315837711096
2023-01-24 05:20:26.433581: step: 320/469, loss: 0.0018768302397802472
2023-01-24 05:20:27.032702: step: 322/469, loss: 0.0007896666647866368
2023-01-24 05:20:27.638640: step: 324/469, loss: 0.21864452958106995
2023-01-24 05:20:28.300437: step: 326/469, loss: 0.013234913349151611
2023-01-24 05:20:28.941496: step: 328/469, loss: 0.0040725478902459145
2023-01-24 05:20:29.615566: step: 330/469, loss: 0.12069471180438995
2023-01-24 05:20:30.258321: step: 332/469, loss: 0.006533664185553789
2023-01-24 05:20:30.930014: step: 334/469, loss: 0.0002847716095857322
2023-01-24 05:20:31.549472: step: 336/469, loss: 0.0018084668554365635
2023-01-24 05:20:32.188617: step: 338/469, loss: 0.11005932092666626
2023-01-24 05:20:32.782549: step: 340/469, loss: 0.019758908078074455
2023-01-24 05:20:33.427176: step: 342/469, loss: 0.018155261874198914
2023-01-24 05:20:34.162210: step: 344/469, loss: 0.006524763535708189
2023-01-24 05:20:34.771806: step: 346/469, loss: 0.07354401797056198
2023-01-24 05:20:35.355175: step: 348/469, loss: 0.009025816805660725
2023-01-24 05:20:35.976625: step: 350/469, loss: 0.002713108202442527
2023-01-24 05:20:36.637359: step: 352/469, loss: 0.03147520497441292
2023-01-24 05:20:37.317889: step: 354/469, loss: 0.0009897833224385977
2023-01-24 05:20:37.955311: step: 356/469, loss: 0.0012717392528429627
2023-01-24 05:20:38.621410: step: 358/469, loss: 0.032479457557201385
2023-01-24 05:20:39.263893: step: 360/469, loss: 0.0005192225216887891
2023-01-24 05:20:39.831929: step: 362/469, loss: 0.005973644554615021
2023-01-24 05:20:40.444231: step: 364/469, loss: 0.009888162836432457
2023-01-24 05:20:41.091312: step: 366/469, loss: 0.011599777266383171
2023-01-24 05:20:41.665283: step: 368/469, loss: 0.01079634577035904
2023-01-24 05:20:42.292037: step: 370/469, loss: 0.001837767194956541
2023-01-24 05:20:42.947256: step: 372/469, loss: 0.008005251176655293
2023-01-24 05:20:43.532457: step: 374/469, loss: 0.010463404469192028
2023-01-24 05:20:44.175408: step: 376/469, loss: 0.019618261605501175
2023-01-24 05:20:44.805797: step: 378/469, loss: 0.005425151903182268
2023-01-24 05:20:45.424619: step: 380/469, loss: 0.0055457246489822865
2023-01-24 05:20:46.044433: step: 382/469, loss: 0.0004786673525813967
2023-01-24 05:20:46.662485: step: 384/469, loss: 0.007368323393166065
2023-01-24 05:20:47.352466: step: 386/469, loss: 0.05301499366760254
2023-01-24 05:20:47.966183: step: 388/469, loss: 0.001236757030710578
2023-01-24 05:20:48.588729: step: 390/469, loss: 0.02682354487478733
2023-01-24 05:20:49.286132: step: 392/469, loss: 0.013161814771592617
2023-01-24 05:20:49.922079: step: 394/469, loss: 0.034417010843753815
2023-01-24 05:20:50.572953: step: 396/469, loss: 0.021855738013982773
2023-01-24 05:20:51.206627: step: 398/469, loss: 0.11348588764667511
2023-01-24 05:20:51.759582: step: 400/469, loss: 0.05384557694196701
2023-01-24 05:20:52.417222: step: 402/469, loss: 0.0439118817448616
2023-01-24 05:20:53.055189: step: 404/469, loss: 0.022635243833065033
2023-01-24 05:20:53.636541: step: 406/469, loss: 0.0011401812080293894
2023-01-24 05:20:54.243536: step: 408/469, loss: 0.02124967612326145
2023-01-24 05:20:54.850202: step: 410/469, loss: 0.005235178861767054
2023-01-24 05:20:55.477970: step: 412/469, loss: 0.06608827412128448
2023-01-24 05:20:56.098075: step: 414/469, loss: 0.009553633630275726
2023-01-24 05:20:56.738819: step: 416/469, loss: 0.1105639860033989
2023-01-24 05:20:57.331942: step: 418/469, loss: 0.004002057481557131
2023-01-24 05:20:57.989968: step: 420/469, loss: 0.0009886876214295626
2023-01-24 05:20:58.600009: step: 422/469, loss: 0.0018955428386107087
2023-01-24 05:20:59.231508: step: 424/469, loss: 0.014699460938572884
2023-01-24 05:20:59.892426: step: 426/469, loss: 0.0007934740860946476
2023-01-24 05:21:00.477946: step: 428/469, loss: 0.0005282569909468293
2023-01-24 05:21:01.110948: step: 430/469, loss: 0.002740419702604413
2023-01-24 05:21:01.707998: step: 432/469, loss: 0.06098758429288864
2023-01-24 05:21:02.280002: step: 434/469, loss: 0.0027008354663848877
2023-01-24 05:21:02.897934: step: 436/469, loss: 0.020581193268299103
2023-01-24 05:21:03.532463: step: 438/469, loss: 0.0008362382650375366
2023-01-24 05:21:04.128520: step: 440/469, loss: 0.009131846949458122
2023-01-24 05:21:04.771479: step: 442/469, loss: 0.0007631309563294053
2023-01-24 05:21:05.322529: step: 444/469, loss: 0.006298655178397894
2023-01-24 05:21:05.944938: step: 446/469, loss: 0.00956434290856123
2023-01-24 05:21:06.584205: step: 448/469, loss: 0.0022332214284688234
2023-01-24 05:21:07.188179: step: 450/469, loss: 0.03460382670164108
2023-01-24 05:21:07.814038: step: 452/469, loss: 0.010300195775926113
2023-01-24 05:21:08.432597: step: 454/469, loss: 0.05888713151216507
2023-01-24 05:21:09.024111: step: 456/469, loss: 5.7322900829603896e-05
2023-01-24 05:21:09.676443: step: 458/469, loss: 0.00104769435711205
2023-01-24 05:21:10.281465: step: 460/469, loss: 0.018517985939979553
2023-01-24 05:21:10.876829: step: 462/469, loss: 0.0035709377843886614
2023-01-24 05:21:11.473325: step: 464/469, loss: 0.0015351761830970645
2023-01-24 05:21:12.173179: step: 466/469, loss: 0.04311732202768326
2023-01-24 05:21:12.736488: step: 468/469, loss: 0.0011024208506569266
2023-01-24 05:21:13.411399: step: 470/469, loss: 0.01289608795195818
2023-01-24 05:21:13.996156: step: 472/469, loss: 0.003955214750021696
2023-01-24 05:21:14.643303: step: 474/469, loss: 0.002936768811196089
2023-01-24 05:21:15.281812: step: 476/469, loss: 0.038597188889980316
2023-01-24 05:21:15.869275: step: 478/469, loss: 0.0023800497874617577
2023-01-24 05:21:16.481926: step: 480/469, loss: 0.005549492314457893
2023-01-24 05:21:17.086375: step: 482/469, loss: 0.011222630739212036
2023-01-24 05:21:17.673021: step: 484/469, loss: 0.04048134759068489
2023-01-24 05:21:18.325692: step: 486/469, loss: 0.019612450152635574
2023-01-24 05:21:18.927392: step: 488/469, loss: 0.003918325528502464
2023-01-24 05:21:19.503916: step: 490/469, loss: 0.0009998517343774438
2023-01-24 05:21:20.105897: step: 492/469, loss: 0.0001641609414946288
2023-01-24 05:21:20.742308: step: 494/469, loss: 0.0014647396747022867
2023-01-24 05:21:21.310009: step: 496/469, loss: 0.0015139882452785969
2023-01-24 05:21:21.854131: step: 498/469, loss: 0.017345961183309555
2023-01-24 05:21:22.510380: step: 500/469, loss: 0.007861591875553131
2023-01-24 05:21:23.159080: step: 502/469, loss: 8.483230340061709e-05
2023-01-24 05:21:23.781955: step: 504/469, loss: 0.03512251004576683
2023-01-24 05:21:24.367552: step: 506/469, loss: 0.019959785044193268
2023-01-24 05:21:25.056705: step: 508/469, loss: 0.01568104699254036
2023-01-24 05:21:25.650173: step: 510/469, loss: 0.03988457843661308
2023-01-24 05:21:26.268882: step: 512/469, loss: 0.008457482792437077
2023-01-24 05:21:26.845096: step: 514/469, loss: 0.00017965841107070446
2023-01-24 05:21:27.510685: step: 516/469, loss: 4.432436253409833e-05
2023-01-24 05:21:28.113352: step: 518/469, loss: 0.037693727761507034
2023-01-24 05:21:28.702953: step: 520/469, loss: 0.00730451475828886
2023-01-24 05:21:29.341304: step: 522/469, loss: 0.009752505458891392
2023-01-24 05:21:30.014874: step: 524/469, loss: 0.01299829687923193
2023-01-24 05:21:30.620270: step: 526/469, loss: 0.0004542673414107412
2023-01-24 05:21:31.208438: step: 528/469, loss: 0.0005608549690805376
2023-01-24 05:21:31.781246: step: 530/469, loss: 3.6528388591250405e-05
2023-01-24 05:21:32.406123: step: 532/469, loss: 0.020629290491342545
2023-01-24 05:21:33.074594: step: 534/469, loss: 0.03824291378259659
2023-01-24 05:21:33.629997: step: 536/469, loss: 0.0007615429349243641
2023-01-24 05:21:34.201380: step: 538/469, loss: 0.0003051344829145819
2023-01-24 05:21:34.837633: step: 540/469, loss: 0.07173144817352295
2023-01-24 05:21:35.430285: step: 542/469, loss: 0.004043711815029383
2023-01-24 05:21:36.124146: step: 544/469, loss: 0.004293826408684254
2023-01-24 05:21:36.743624: step: 546/469, loss: 0.0028995154425501823
2023-01-24 05:21:37.343953: step: 548/469, loss: 0.02083742432296276
2023-01-24 05:21:37.945142: step: 550/469, loss: 0.019430281594395638
2023-01-24 05:21:38.518233: step: 552/469, loss: 0.014926875941455364
2023-01-24 05:21:39.163884: step: 554/469, loss: 0.002948716515675187
2023-01-24 05:21:39.761346: step: 556/469, loss: 0.020838819444179535
2023-01-24 05:21:40.357336: step: 558/469, loss: 0.0014127717586234212
2023-01-24 05:21:41.007204: step: 560/469, loss: 0.0012188029941171408
2023-01-24 05:21:41.611300: step: 562/469, loss: 0.004385044332593679
2023-01-24 05:21:42.180265: step: 564/469, loss: 0.002608982613310218
2023-01-24 05:21:42.779292: step: 566/469, loss: 0.003080811118707061
2023-01-24 05:21:43.396377: step: 568/469, loss: 0.005462948698550463
2023-01-24 05:21:43.988310: step: 570/469, loss: 0.0015820726985111833
2023-01-24 05:21:44.570424: step: 572/469, loss: 0.2151658535003662
2023-01-24 05:21:45.144502: step: 574/469, loss: 0.023377683013677597
2023-01-24 05:21:45.734822: step: 576/469, loss: 0.013376289047300816
2023-01-24 05:21:46.353162: step: 578/469, loss: 0.0034325220622122288
2023-01-24 05:21:46.979256: step: 580/469, loss: 0.038481228053569794
2023-01-24 05:21:47.575174: step: 582/469, loss: 0.003627503290772438
2023-01-24 05:21:48.179446: step: 584/469, loss: 0.092597596347332
2023-01-24 05:21:48.854904: step: 586/469, loss: 0.006897504907101393
2023-01-24 05:21:49.419315: step: 588/469, loss: 0.008465752005577087
2023-01-24 05:21:50.014172: step: 590/469, loss: 0.001693866797722876
2023-01-24 05:21:50.710551: step: 592/469, loss: 0.007011231034994125
2023-01-24 05:21:51.298075: step: 594/469, loss: 0.0005285179358907044
2023-01-24 05:21:51.928677: step: 596/469, loss: 0.0416235513985157
2023-01-24 05:21:52.520281: step: 598/469, loss: 0.0005588795174844563
2023-01-24 05:21:53.174953: step: 600/469, loss: 0.038418516516685486
2023-01-24 05:21:53.813160: step: 602/469, loss: 0.003238404169678688
2023-01-24 05:21:54.457053: step: 604/469, loss: 5.870701716048643e-05
2023-01-24 05:21:55.017433: step: 606/469, loss: 0.004645701963454485
2023-01-24 05:21:55.679621: step: 608/469, loss: 0.010543636046350002
2023-01-24 05:21:56.358440: step: 610/469, loss: 0.0011761996429413557
2023-01-24 05:21:56.977505: step: 612/469, loss: 0.005731097888201475
2023-01-24 05:21:57.622251: step: 614/469, loss: 0.022229019552469254
2023-01-24 05:21:58.263284: step: 616/469, loss: 0.0005212425021454692
2023-01-24 05:21:58.917980: step: 618/469, loss: 0.001753071672283113
2023-01-24 05:21:59.647421: step: 620/469, loss: 0.0012778625823557377
2023-01-24 05:22:00.191808: step: 622/469, loss: 0.020835336297750473
2023-01-24 05:22:00.812700: step: 624/469, loss: 0.0034977321047335863
2023-01-24 05:22:01.424852: step: 626/469, loss: 0.024047844111919403
2023-01-24 05:22:02.044956: step: 628/469, loss: 0.006701468024402857
2023-01-24 05:22:02.681516: step: 630/469, loss: 0.000508688623085618
2023-01-24 05:22:03.341011: step: 632/469, loss: 0.0008328788680955768
2023-01-24 05:22:04.038584: step: 634/469, loss: 0.0007181655382737517
2023-01-24 05:22:04.659624: step: 636/469, loss: 0.0021388118620961905
2023-01-24 05:22:05.247011: step: 638/469, loss: 0.029636982828378677
2023-01-24 05:22:05.886441: step: 640/469, loss: 0.05095604434609413
2023-01-24 05:22:06.511008: step: 642/469, loss: 0.004727157298475504
2023-01-24 05:22:07.096943: step: 644/469, loss: 1.4363168478012085
2023-01-24 05:22:07.726609: step: 646/469, loss: 0.0017516098450869322
2023-01-24 05:22:08.319380: step: 648/469, loss: 0.07704787701368332
2023-01-24 05:22:08.885638: step: 650/469, loss: 0.015268268994987011
2023-01-24 05:22:09.573189: step: 652/469, loss: 0.006294921040534973
2023-01-24 05:22:10.172927: step: 654/469, loss: 0.029882969334721565
2023-01-24 05:22:10.833371: step: 656/469, loss: 0.02858980931341648
2023-01-24 05:22:11.505556: step: 658/469, loss: 0.04057031497359276
2023-01-24 05:22:12.169786: step: 660/469, loss: 0.003819218371063471
2023-01-24 05:22:12.850774: step: 662/469, loss: 0.04323418438434601
2023-01-24 05:22:13.433626: step: 664/469, loss: 0.0002988446212839335
2023-01-24 05:22:14.098057: step: 666/469, loss: 0.18204519152641296
2023-01-24 05:22:14.736319: step: 668/469, loss: 0.0025522124487906694
2023-01-24 05:22:15.311743: step: 670/469, loss: 0.00962864700704813
2023-01-24 05:22:15.892355: step: 672/469, loss: 0.004951891489326954
2023-01-24 05:22:16.468326: step: 674/469, loss: 0.0006246576085686684
2023-01-24 05:22:17.085605: step: 676/469, loss: 0.0008598135318607092
2023-01-24 05:22:17.761011: step: 678/469, loss: 2.0176716134301387e-05
2023-01-24 05:22:18.371592: step: 680/469, loss: 0.024525316432118416
2023-01-24 05:22:18.951088: step: 682/469, loss: 0.0039021417032927275
2023-01-24 05:22:19.581237: step: 684/469, loss: 0.001621451461687684
2023-01-24 05:22:20.165078: step: 686/469, loss: 0.001344478689134121
2023-01-24 05:22:20.743352: step: 688/469, loss: 0.03194309026002884
2023-01-24 05:22:21.365369: step: 690/469, loss: 0.017155833542346954
2023-01-24 05:22:22.045560: step: 692/469, loss: 0.0018762206891551614
2023-01-24 05:22:22.739317: step: 694/469, loss: 0.00497461436316371
2023-01-24 05:22:23.431493: step: 696/469, loss: 0.01276924554258585
2023-01-24 05:22:24.075176: step: 698/469, loss: 0.0005737309111282229
2023-01-24 05:22:24.643619: step: 700/469, loss: 0.0007732072845101357
2023-01-24 05:22:25.278882: step: 702/469, loss: 0.0014760341728106141
2023-01-24 05:22:25.885298: step: 704/469, loss: 0.003231868613511324
2023-01-24 05:22:26.552924: step: 706/469, loss: 0.003730586264282465
2023-01-24 05:22:27.148730: step: 708/469, loss: 0.03210756555199623
2023-01-24 05:22:27.712291: step: 710/469, loss: 0.015252848155796528
2023-01-24 05:22:28.370816: step: 712/469, loss: 0.06766407936811447
2023-01-24 05:22:29.036055: step: 714/469, loss: 0.007349667139351368
2023-01-24 05:22:29.884067: step: 716/469, loss: 0.009399761445820332
2023-01-24 05:22:30.538552: step: 718/469, loss: 0.10491109639406204
2023-01-24 05:22:31.192051: step: 720/469, loss: 0.002760874340310693
2023-01-24 05:22:31.952077: step: 722/469, loss: 0.02332591637969017
2023-01-24 05:22:32.538631: step: 724/469, loss: 0.004359787795692682
2023-01-24 05:22:33.161540: step: 726/469, loss: 0.008645017631351948
2023-01-24 05:22:33.798625: step: 728/469, loss: 0.0009867568733170629
2023-01-24 05:22:34.473108: step: 730/469, loss: 0.0003513229312375188
2023-01-24 05:22:35.045078: step: 732/469, loss: 2.46677303314209
2023-01-24 05:22:35.660397: step: 734/469, loss: 0.02201024256646633
2023-01-24 05:22:36.234537: step: 736/469, loss: 0.016579758375883102
2023-01-24 05:22:36.868436: step: 738/469, loss: 0.038843315094709396
2023-01-24 05:22:37.560927: step: 740/469, loss: 0.00020381015201564878
2023-01-24 05:22:38.169771: step: 742/469, loss: 0.012041660025715828
2023-01-24 05:22:38.874691: step: 744/469, loss: 0.20232078433036804
2023-01-24 05:22:39.478704: step: 746/469, loss: 0.003205152228474617
2023-01-24 05:22:40.069838: step: 748/469, loss: 0.004757591988891363
2023-01-24 05:22:40.695079: step: 750/469, loss: 6.730795576004311e-05
2023-01-24 05:22:41.261866: step: 752/469, loss: 0.004922729916870594
2023-01-24 05:22:41.884572: step: 754/469, loss: 8.53805904625915e-05
2023-01-24 05:22:42.439201: step: 756/469, loss: 0.012571812607347965
2023-01-24 05:22:43.135341: step: 758/469, loss: 0.002861930988729
2023-01-24 05:22:43.779401: step: 760/469, loss: 0.0002941860584542155
2023-01-24 05:22:44.359484: step: 762/469, loss: 0.005963773466646671
2023-01-24 05:22:44.997331: step: 764/469, loss: 0.13207204639911652
2023-01-24 05:22:45.554474: step: 766/469, loss: 0.009327885694801807
2023-01-24 05:22:46.199078: step: 768/469, loss: 0.0031073433347046375
2023-01-24 05:22:46.827944: step: 770/469, loss: 0.02418460138142109
2023-01-24 05:22:47.564825: step: 772/469, loss: 0.01933264173567295
2023-01-24 05:22:48.213618: step: 774/469, loss: 0.007950271479785442
2023-01-24 05:22:48.810581: step: 776/469, loss: 0.0024820449762046337
2023-01-24 05:22:49.416307: step: 778/469, loss: 0.030494293197989464
2023-01-24 05:22:50.147675: step: 780/469, loss: 0.00631794473156333
2023-01-24 05:22:50.810920: step: 782/469, loss: 0.002698679454624653
2023-01-24 05:22:51.392157: step: 784/469, loss: 2.5327946787001565e-05
2023-01-24 05:22:52.030670: step: 786/469, loss: 0.04262625426054001
2023-01-24 05:22:52.655026: step: 788/469, loss: 0.0002699931210372597
2023-01-24 05:22:53.268419: step: 790/469, loss: 0.0003126077353954315
2023-01-24 05:22:53.856434: step: 792/469, loss: 0.00014261103933677077
2023-01-24 05:22:54.462097: step: 794/469, loss: 0.10336020588874817
2023-01-24 05:22:55.090465: step: 796/469, loss: 0.003584097372367978
2023-01-24 05:22:55.712817: step: 798/469, loss: 0.011599306017160416
2023-01-24 05:22:56.318460: step: 800/469, loss: 0.018106209114193916
2023-01-24 05:22:56.985447: step: 802/469, loss: 0.013742119073867798
2023-01-24 05:22:57.696762: step: 804/469, loss: 0.009712567552924156
2023-01-24 05:22:58.375889: step: 806/469, loss: 0.018879614770412445
2023-01-24 05:22:58.977401: step: 808/469, loss: 0.004268000368028879
2023-01-24 05:22:59.511599: step: 810/469, loss: 0.0032297568395733833
2023-01-24 05:23:00.217264: step: 812/469, loss: 0.0032134992070496082
2023-01-24 05:23:00.840502: step: 814/469, loss: 0.0198863185942173
2023-01-24 05:23:01.475840: step: 816/469, loss: 0.0004367715446278453
2023-01-24 05:23:02.123396: step: 818/469, loss: 0.00891380850225687
2023-01-24 05:23:02.732582: step: 820/469, loss: 0.025122186169028282
2023-01-24 05:23:03.362969: step: 822/469, loss: 0.0024353195913136005
2023-01-24 05:23:03.995596: step: 824/469, loss: 0.003031976753845811
2023-01-24 05:23:04.659001: step: 826/469, loss: 0.014371187426149845
2023-01-24 05:23:05.348247: step: 828/469, loss: 0.0011106326710432768
2023-01-24 05:23:06.038739: step: 830/469, loss: 0.008817785419523716
2023-01-24 05:23:06.675422: step: 832/469, loss: 0.024798348546028137
2023-01-24 05:23:07.234501: step: 834/469, loss: 0.011286124587059021
2023-01-24 05:23:07.839491: step: 836/469, loss: 0.029052378609776497
2023-01-24 05:23:08.499623: step: 838/469, loss: 0.10058391094207764
2023-01-24 05:23:09.129047: step: 840/469, loss: 0.006272433791309595
2023-01-24 05:23:09.731613: step: 842/469, loss: 0.0011993744410574436
2023-01-24 05:23:10.371034: step: 844/469, loss: 0.009213746525347233
2023-01-24 05:23:10.937003: step: 846/469, loss: 0.016731230542063713
2023-01-24 05:23:11.544470: step: 848/469, loss: 0.0027808707673102617
2023-01-24 05:23:12.179818: step: 850/469, loss: 0.0035659456625580788
2023-01-24 05:23:12.737275: step: 852/469, loss: 0.0008063454879447818
2023-01-24 05:23:13.357212: step: 854/469, loss: 0.00021601474145427346
2023-01-24 05:23:14.002610: step: 856/469, loss: 0.013462109491229057
2023-01-24 05:23:14.621546: step: 858/469, loss: 0.17038434743881226
2023-01-24 05:23:15.223656: step: 860/469, loss: 0.0026259678415954113
2023-01-24 05:23:15.822146: step: 862/469, loss: 0.14731523394584656
2023-01-24 05:23:16.418620: step: 864/469, loss: 0.006066069006919861
2023-01-24 05:23:17.090721: step: 866/469, loss: 0.0005654181586578488
2023-01-24 05:23:17.696339: step: 868/469, loss: 0.003503442509099841
2023-01-24 05:23:18.319173: step: 870/469, loss: 0.0025665946304798126
2023-01-24 05:23:18.914144: step: 872/469, loss: 0.011841288767755032
2023-01-24 05:23:19.516538: step: 874/469, loss: 0.00535447197034955
2023-01-24 05:23:20.141172: step: 876/469, loss: 0.000537946994882077
2023-01-24 05:23:20.743321: step: 878/469, loss: 0.0285461638122797
2023-01-24 05:23:21.335901: step: 880/469, loss: 0.0005378602654673159
2023-01-24 05:23:21.950624: step: 882/469, loss: 0.013773929327726364
2023-01-24 05:23:22.707868: step: 884/469, loss: 0.0024970925878733397
2023-01-24 05:23:23.297941: step: 886/469, loss: 0.0207919180393219
2023-01-24 05:23:23.965037: step: 888/469, loss: 0.0146642429754138
2023-01-24 05:23:24.619935: step: 890/469, loss: 0.0031988827977329493
2023-01-24 05:23:25.208141: step: 892/469, loss: 0.02267240174114704
2023-01-24 05:23:25.884066: step: 894/469, loss: 0.004538672976195812
2023-01-24 05:23:26.488006: step: 896/469, loss: 0.015491476282477379
2023-01-24 05:23:27.101741: step: 898/469, loss: 7.6398289820645e-05
2023-01-24 05:23:27.707422: step: 900/469, loss: 0.0008502332493662834
2023-01-24 05:23:28.304307: step: 902/469, loss: 0.010820634663105011
2023-01-24 05:23:28.947014: step: 904/469, loss: 0.14744719862937927
2023-01-24 05:23:29.668985: step: 906/469, loss: 0.21440817415714264
2023-01-24 05:23:30.364395: step: 908/469, loss: 0.014432581141591072
2023-01-24 05:23:31.010931: step: 910/469, loss: 0.005767323076725006
2023-01-24 05:23:31.631265: step: 912/469, loss: 0.0068262433633208275
2023-01-24 05:23:32.194566: step: 914/469, loss: 0.0001664624287514016
2023-01-24 05:23:32.786492: step: 916/469, loss: 0.19408603012561798
2023-01-24 05:23:33.372187: step: 918/469, loss: 0.005819531623274088
2023-01-24 05:23:33.988030: step: 920/469, loss: 0.010460923425853252
2023-01-24 05:23:34.611020: step: 922/469, loss: 0.010691720061004162
2023-01-24 05:23:35.170909: step: 924/469, loss: 0.0006093971896916628
2023-01-24 05:23:35.779277: step: 926/469, loss: 0.02577994391322136
2023-01-24 05:23:36.344780: step: 928/469, loss: 0.042842525988817215
2023-01-24 05:23:36.979273: step: 930/469, loss: 0.03465908020734787
2023-01-24 05:23:37.655365: step: 932/469, loss: 0.002047451911494136
2023-01-24 05:23:38.264790: step: 934/469, loss: 0.01731567084789276
2023-01-24 05:23:38.867208: step: 936/469, loss: 0.12593920528888702
2023-01-24 05:23:39.459343: step: 938/469, loss: 0.041484981775283813
==================================================
Loss: 0.033
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3146369448452782, 'r': 0.2901585487567461, 'f1': 0.30190237945667364}, 'combined': 0.22245438486281213, 'epoch': 35}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3446207175584883, 'r': 0.2654809187413057, 'f1': 0.29991797848500995}, 'combined': 0.16359162462818724, 'epoch': 35}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3346049783549784, 'r': 0.30158892735980025, 'f1': 0.31724024893935077}, 'combined': 0.2337559729026795, 'epoch': 35}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.356008514363439, 'r': 0.26806496552709086, 'f1': 0.30584029991765166}, 'combined': 0.16682198177326452, 'epoch': 35}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3147817460317461, 'r': 0.28850015812776725, 'f1': 0.30106848184818485}, 'combined': 0.22183993399339935, 'epoch': 35}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.34894459540275613, 'r': 0.2720043872672902, 'f1': 0.30570775864591077}, 'combined': 0.16674968653413313, 'epoch': 35}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.344551282051282, 'r': 0.25595238095238093, 'f1': 0.2937158469945355}, 'combined': 0.19581056466302366, 'epoch': 35}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.358695652173913, 'f1': 0.3666666666666666}, 'combined': 0.1833333333333333, 'epoch': 35}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.1724137931034483, 'f1': 0.25641025641025644}, 'combined': 0.17094017094017094, 'epoch': 35}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887178057632604, 'r': 0.2995095472206478, 'f1': 0.3088875369574979}, 'combined': 0.2276013430213142, 'epoch': 25}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3226430513120057, 'r': 0.25268293863044544, 'f1': 0.28340939140387567}, 'combined': 0.15458694076575036, 'epoch': 25}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'epoch': 25}
******************************
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
2023-01-24 05:26:25.575941: step: 2/469, loss: 0.004019667394459248
2023-01-24 05:26:26.182031: step: 4/469, loss: 0.0004227577883284539
2023-01-24 05:26:26.813716: step: 6/469, loss: 0.027020292356610298
2023-01-24 05:26:27.448000: step: 8/469, loss: 0.06948929280042648
2023-01-24 05:26:28.106343: step: 10/469, loss: 0.0002911464835051447
2023-01-24 05:26:28.756716: step: 12/469, loss: 0.10993222147226334
2023-01-24 05:26:29.388571: step: 14/469, loss: 0.000966193329077214
2023-01-24 05:26:29.995432: step: 16/469, loss: 0.0005814554169774055
2023-01-24 05:26:30.602740: step: 18/469, loss: 0.04141689091920853
2023-01-24 05:26:31.364852: step: 20/469, loss: 0.042358919978141785
2023-01-24 05:26:32.057879: step: 22/469, loss: 0.2076289802789688
2023-01-24 05:26:32.651926: step: 24/469, loss: 0.006613573059439659
2023-01-24 05:26:33.210566: step: 26/469, loss: 2.0684610717580654e-05
2023-01-24 05:26:33.728101: step: 28/469, loss: 0.004543894436210394
2023-01-24 05:26:34.330821: step: 30/469, loss: 0.08396077156066895
2023-01-24 05:26:34.901573: step: 32/469, loss: 0.012454559095203876
2023-01-24 05:26:35.593524: step: 34/469, loss: 0.006128770299255848
2023-01-24 05:26:36.169200: step: 36/469, loss: 0.006237713620066643
2023-01-24 05:26:36.783557: step: 38/469, loss: 0.00046029267832636833
2023-01-24 05:26:37.360494: step: 40/469, loss: 0.00116886873729527
2023-01-24 05:26:38.055510: step: 42/469, loss: 0.001049504615366459
2023-01-24 05:26:38.694846: step: 44/469, loss: 0.0021261069923639297
2023-01-24 05:26:39.291172: step: 46/469, loss: 0.03951739892363548
2023-01-24 05:26:39.865706: step: 48/469, loss: 0.00025101398932747543
2023-01-24 05:26:40.488795: step: 50/469, loss: 0.019808761775493622
2023-01-24 05:26:41.102428: step: 52/469, loss: 0.000916816818062216
2023-01-24 05:26:41.751492: step: 54/469, loss: 0.006958385929465294
2023-01-24 05:26:42.381643: step: 56/469, loss: 0.004789789207279682
2023-01-24 05:26:43.025527: step: 58/469, loss: 0.0009373460779897869
2023-01-24 05:26:43.678782: step: 60/469, loss: 0.017457688227295876
2023-01-24 05:26:44.270509: step: 62/469, loss: 0.000646613712888211
2023-01-24 05:26:44.972305: step: 64/469, loss: 0.032429322600364685
2023-01-24 05:26:45.592038: step: 66/469, loss: 0.011531285010278225
2023-01-24 05:26:46.264187: step: 68/469, loss: 0.0032940825913101435
2023-01-24 05:26:46.829501: step: 70/469, loss: 0.05203739181160927
2023-01-24 05:26:47.437744: step: 72/469, loss: 0.022996407002210617
2023-01-24 05:26:48.011495: step: 74/469, loss: 0.009048468433320522
2023-01-24 05:26:48.643563: step: 76/469, loss: 0.03836231678724289
2023-01-24 05:26:49.287701: step: 78/469, loss: 0.0057999067939817905
2023-01-24 05:26:49.887670: step: 80/469, loss: 0.0004627261951100081
2023-01-24 05:26:50.549860: step: 82/469, loss: 8.897064253687859e-05
2023-01-24 05:26:51.152391: step: 84/469, loss: 0.0003895910340361297
2023-01-24 05:26:51.757026: step: 86/469, loss: 8.814774628262967e-05
2023-01-24 05:26:52.405962: step: 88/469, loss: 0.00035210661008022726
2023-01-24 05:26:53.011131: step: 90/469, loss: 0.004196563735604286
2023-01-24 05:26:53.698180: step: 92/469, loss: 0.00043823086889460683
2023-01-24 05:26:54.312390: step: 94/469, loss: 0.013972615823149681
2023-01-24 05:26:54.864201: step: 96/469, loss: 0.012797524221241474
2023-01-24 05:26:55.422323: step: 98/469, loss: 0.09215812385082245
2023-01-24 05:26:56.034574: step: 100/469, loss: 0.01694154553115368
2023-01-24 05:26:56.664333: step: 102/469, loss: 0.00024399500398430973
2023-01-24 05:26:57.297980: step: 104/469, loss: 0.001303322147578001
2023-01-24 05:26:57.863445: step: 106/469, loss: 0.017214186489582062
2023-01-24 05:26:58.524271: step: 108/469, loss: 0.005354368593543768
2023-01-24 05:26:59.089250: step: 110/469, loss: 0.11762009561061859
2023-01-24 05:26:59.678604: step: 112/469, loss: 9.76502924459055e-05
2023-01-24 05:27:00.300319: step: 114/469, loss: 0.0015003300504758954
2023-01-24 05:27:00.897612: step: 116/469, loss: 0.0009911570232361555
2023-01-24 05:27:01.531784: step: 118/469, loss: 0.05354335531592369
2023-01-24 05:27:02.196349: step: 120/469, loss: 0.010274798609316349
2023-01-24 05:27:02.796669: step: 122/469, loss: 0.003682586131617427
2023-01-24 05:27:03.387424: step: 124/469, loss: 0.0016012543346732855
2023-01-24 05:27:03.930955: step: 126/469, loss: 0.008140754885971546
2023-01-24 05:27:04.619939: step: 128/469, loss: 0.11502741277217865
2023-01-24 05:27:05.269648: step: 130/469, loss: 0.014009936712682247
2023-01-24 05:27:06.053193: step: 132/469, loss: 0.003206227906048298
2023-01-24 05:27:06.676905: step: 134/469, loss: 0.10316529124975204
2023-01-24 05:27:07.279064: step: 136/469, loss: 0.0004017339670099318
2023-01-24 05:27:07.875757: step: 138/469, loss: 0.0013377888826653361
2023-01-24 05:27:08.490929: step: 140/469, loss: 0.9314048290252686
2023-01-24 05:27:09.128131: step: 142/469, loss: 0.0010301253059878945
2023-01-24 05:27:09.740230: step: 144/469, loss: 0.04562880098819733
2023-01-24 05:27:10.388912: step: 146/469, loss: 0.035739898681640625
2023-01-24 05:27:11.118969: step: 148/469, loss: 0.0039064460434019566
2023-01-24 05:27:11.824915: step: 150/469, loss: 0.012470165267586708
2023-01-24 05:27:12.431264: step: 152/469, loss: 0.005693660117685795
2023-01-24 05:27:13.026443: step: 154/469, loss: 0.00013863515050616115
2023-01-24 05:27:13.706911: step: 156/469, loss: 0.007109920494258404
2023-01-24 05:27:14.268714: step: 158/469, loss: 0.005907388404011726
2023-01-24 05:27:14.843169: step: 160/469, loss: 0.0011227307841181755
2023-01-24 05:27:15.506454: step: 162/469, loss: 0.0019335340475663543
2023-01-24 05:27:16.112371: step: 164/469, loss: 0.0009818810503929853
2023-01-24 05:27:16.757457: step: 166/469, loss: 0.0016895406879484653
2023-01-24 05:27:17.368646: step: 168/469, loss: 0.022339507937431335
2023-01-24 05:27:18.036378: step: 170/469, loss: 0.009019142016768456
2023-01-24 05:27:18.666846: step: 172/469, loss: 0.002969138091430068
2023-01-24 05:27:19.291822: step: 174/469, loss: 0.002767864614725113
2023-01-24 05:27:19.936872: step: 176/469, loss: 0.005112234968692064
2023-01-24 05:27:20.530575: step: 178/469, loss: 0.0011714731808751822
2023-01-24 05:27:21.083110: step: 180/469, loss: 0.21712468564510345
2023-01-24 05:27:21.709622: step: 182/469, loss: 0.0027430085465312004
2023-01-24 05:27:22.362400: step: 184/469, loss: 0.00548455910757184
2023-01-24 05:27:23.011553: step: 186/469, loss: 0.019656404852867126
2023-01-24 05:27:23.619568: step: 188/469, loss: 0.0007380904862657189
2023-01-24 05:27:24.223697: step: 190/469, loss: 0.00356236076913774
2023-01-24 05:27:24.844671: step: 192/469, loss: 0.008898664265871048
2023-01-24 05:27:25.460374: step: 194/469, loss: 0.010636312887072563
2023-01-24 05:27:26.174913: step: 196/469, loss: 0.001877523260191083
2023-01-24 05:27:26.797904: step: 198/469, loss: 0.017142169177532196
2023-01-24 05:27:27.373119: step: 200/469, loss: 0.0031895486172288656
2023-01-24 05:27:27.959665: step: 202/469, loss: 0.008416732773184776
2023-01-24 05:27:28.606628: step: 204/469, loss: 0.001715382793918252
2023-01-24 05:27:29.219992: step: 206/469, loss: 0.004539210349321365
2023-01-24 05:27:29.951750: step: 208/469, loss: 0.024577531963586807
2023-01-24 05:27:30.529796: step: 210/469, loss: 0.009009582921862602
2023-01-24 05:27:31.149548: step: 212/469, loss: 0.011423132382333279
2023-01-24 05:27:31.752855: step: 214/469, loss: 0.08204792439937592
2023-01-24 05:27:32.464120: step: 216/469, loss: 0.002255804371088743
2023-01-24 05:27:33.134393: step: 218/469, loss: 0.002182943746447563
2023-01-24 05:27:33.755029: step: 220/469, loss: 0.0008874643826857209
2023-01-24 05:27:34.326788: step: 222/469, loss: 0.00824873335659504
2023-01-24 05:27:34.908784: step: 224/469, loss: 0.000958276039455086
2023-01-24 05:27:35.504239: step: 226/469, loss: 0.0070266565307974815
2023-01-24 05:27:36.202115: step: 228/469, loss: 0.17838431894779205
2023-01-24 05:27:36.873627: step: 230/469, loss: 0.11022572219371796
2023-01-24 05:27:37.477770: step: 232/469, loss: 0.04407728835940361
2023-01-24 05:27:38.156202: step: 234/469, loss: 0.0008073513163253665
2023-01-24 05:27:38.857434: step: 236/469, loss: 0.01689794845879078
2023-01-24 05:27:39.451231: step: 238/469, loss: 0.004012030549347401
2023-01-24 05:27:40.067461: step: 240/469, loss: 0.014662004075944424
2023-01-24 05:27:40.698360: step: 242/469, loss: 0.0031540084164589643
2023-01-24 05:27:41.354468: step: 244/469, loss: 0.06471965461969376
2023-01-24 05:27:41.985690: step: 246/469, loss: 0.004902043845504522
2023-01-24 05:27:42.630173: step: 248/469, loss: 0.02574852854013443
2023-01-24 05:27:43.218402: step: 250/469, loss: 0.0011984813027083874
2023-01-24 05:27:43.832343: step: 252/469, loss: 0.0012043439783155918
2023-01-24 05:27:44.506897: step: 254/469, loss: 0.018357571214437485
2023-01-24 05:27:45.151277: step: 256/469, loss: 0.0015557422302663326
2023-01-24 05:27:45.832997: step: 258/469, loss: 0.049370232969522476
2023-01-24 05:27:46.428094: step: 260/469, loss: 0.005529611371457577
2023-01-24 05:27:47.004329: step: 262/469, loss: 0.0017110251355916262
2023-01-24 05:27:47.636685: step: 264/469, loss: 0.004286629147827625
2023-01-24 05:27:48.246163: step: 266/469, loss: 0.000177061214344576
2023-01-24 05:27:48.852601: step: 268/469, loss: 0.0700095072388649
2023-01-24 05:27:49.479085: step: 270/469, loss: 0.00356339942663908
2023-01-24 05:27:50.109065: step: 272/469, loss: 0.03956741467118263
2023-01-24 05:27:50.684020: step: 274/469, loss: 0.010773099958896637
2023-01-24 05:27:51.289490: step: 276/469, loss: 0.005284388083964586
2023-01-24 05:27:51.928440: step: 278/469, loss: 0.00043513590935617685
2023-01-24 05:27:52.750108: step: 280/469, loss: 0.01611909084022045
2023-01-24 05:27:53.298024: step: 282/469, loss: 0.0007956814370118082
2023-01-24 05:27:53.887807: step: 284/469, loss: 0.0034125293605029583
2023-01-24 05:27:54.556479: step: 286/469, loss: 0.000292459677439183
2023-01-24 05:27:55.209163: step: 288/469, loss: 0.004325747489929199
2023-01-24 05:27:55.906477: step: 290/469, loss: 0.08130623400211334
2023-01-24 05:27:56.497885: step: 292/469, loss: 8.02692084107548e-05
2023-01-24 05:27:57.101894: step: 294/469, loss: 0.0011682234471663833
2023-01-24 05:27:57.706834: step: 296/469, loss: 0.3660926818847656
2023-01-24 05:27:58.338666: step: 298/469, loss: 0.00048090022755786777
2023-01-24 05:27:58.925477: step: 300/469, loss: 0.08668415248394012
2023-01-24 05:27:59.558622: step: 302/469, loss: 0.08002693951129913
2023-01-24 05:28:00.218007: step: 304/469, loss: 0.0442228727042675
2023-01-24 05:28:00.824790: step: 306/469, loss: 0.0017019023653119802
2023-01-24 05:28:01.444083: step: 308/469, loss: 0.024139491841197014
2023-01-24 05:28:02.068800: step: 310/469, loss: 0.0019354281248524785
2023-01-24 05:28:02.717327: step: 312/469, loss: 0.006996998563408852
2023-01-24 05:28:03.338770: step: 314/469, loss: 0.00355371437035501
2023-01-24 05:28:04.019484: step: 316/469, loss: 0.01877163164317608
2023-01-24 05:28:04.676735: step: 318/469, loss: 0.0008296903106383979
2023-01-24 05:28:05.261913: step: 320/469, loss: 9.87905150395818e-05
2023-01-24 05:28:05.846634: step: 322/469, loss: 0.025181597098708153
2023-01-24 05:28:06.489654: step: 324/469, loss: 0.01067360583692789
2023-01-24 05:28:07.133438: step: 326/469, loss: 0.0005482613923959434
2023-01-24 05:28:07.689455: step: 328/469, loss: 0.005046092439442873
2023-01-24 05:28:08.304794: step: 330/469, loss: 0.02470463700592518
2023-01-24 05:28:08.986124: step: 332/469, loss: 0.009912683628499508
2023-01-24 05:28:09.631278: step: 334/469, loss: 0.005101479589939117
2023-01-24 05:28:10.221185: step: 336/469, loss: 0.0015234098536893725
2023-01-24 05:28:10.870654: step: 338/469, loss: 0.015306186862289906
2023-01-24 05:28:11.529612: step: 340/469, loss: 0.00023860990768298507
2023-01-24 05:28:12.110960: step: 342/469, loss: 0.0034003914333879948
2023-01-24 05:28:12.700411: step: 344/469, loss: 0.00551243033260107
2023-01-24 05:28:13.338054: step: 346/469, loss: 0.0004621801199391484
2023-01-24 05:28:13.974445: step: 348/469, loss: 0.0009943271288648248
2023-01-24 05:28:14.613926: step: 350/469, loss: 0.3635597229003906
2023-01-24 05:28:15.295979: step: 352/469, loss: 0.003187666879966855
2023-01-24 05:28:15.903567: step: 354/469, loss: 0.0033788057044148445
2023-01-24 05:28:16.599180: step: 356/469, loss: 0.006172339431941509
2023-01-24 05:28:17.195313: step: 358/469, loss: 0.01572144590318203
2023-01-24 05:28:17.748598: step: 360/469, loss: 0.005256704054772854
2023-01-24 05:28:18.363117: step: 362/469, loss: 0.012815205380320549
2023-01-24 05:28:19.033730: step: 364/469, loss: 0.0021572893019765615
2023-01-24 05:28:19.603270: step: 366/469, loss: 0.0014868644066154957
2023-01-24 05:28:20.295503: step: 368/469, loss: 0.014277968555688858
2023-01-24 05:28:20.909890: step: 370/469, loss: 0.00176100037060678
2023-01-24 05:28:21.513995: step: 372/469, loss: 0.00022385075862985104
2023-01-24 05:28:22.101580: step: 374/469, loss: 0.004147999454289675
2023-01-24 05:28:22.720060: step: 376/469, loss: 0.0004994391347281635
2023-01-24 05:28:23.464214: step: 378/469, loss: 0.006284559611231089
2023-01-24 05:28:24.123781: step: 380/469, loss: 0.0011346520623192191
2023-01-24 05:28:24.747979: step: 382/469, loss: 0.00012142006744397804
2023-01-24 05:28:25.338486: step: 384/469, loss: 0.0016428964445367455
2023-01-24 05:28:25.929311: step: 386/469, loss: 0.01398802176117897
2023-01-24 05:28:26.517365: step: 388/469, loss: 0.0004344326152931899
2023-01-24 05:28:27.148169: step: 390/469, loss: 0.0009233256569132209
2023-01-24 05:28:27.740117: step: 392/469, loss: 0.0014322545612230897
2023-01-24 05:28:28.271359: step: 394/469, loss: 5.282333222567104e-05
2023-01-24 05:28:28.990818: step: 396/469, loss: 0.0038123372942209244
2023-01-24 05:28:29.641311: step: 398/469, loss: 0.04511203616857529
2023-01-24 05:28:30.272612: step: 400/469, loss: 0.0031361912842839956
2023-01-24 05:28:30.847973: step: 402/469, loss: 0.0008506365120410919
2023-01-24 05:28:31.431878: step: 404/469, loss: 0.38688597083091736
2023-01-24 05:28:32.054419: step: 406/469, loss: 0.023370549082756042
2023-01-24 05:28:32.691423: step: 408/469, loss: 0.010454434901475906
2023-01-24 05:28:33.327225: step: 410/469, loss: 0.0018446693429723382
2023-01-24 05:28:33.916945: step: 412/469, loss: 0.0007001546327956021
2023-01-24 05:28:34.562072: step: 414/469, loss: 0.00025169330183416605
2023-01-24 05:28:35.267952: step: 416/469, loss: 0.0010023503564298153
2023-01-24 05:28:35.844696: step: 418/469, loss: 0.00013269903138279915
2023-01-24 05:28:36.443899: step: 420/469, loss: 0.013020424172282219
2023-01-24 05:28:37.055203: step: 422/469, loss: 0.019305003806948662
2023-01-24 05:28:37.759199: step: 424/469, loss: 0.07851661741733551
2023-01-24 05:28:38.392936: step: 426/469, loss: 0.020300403237342834
2023-01-24 05:28:39.004685: step: 428/469, loss: 0.03077412024140358
2023-01-24 05:28:39.647640: step: 430/469, loss: 0.010809487663209438
2023-01-24 05:28:40.256361: step: 432/469, loss: 0.026068199425935745
2023-01-24 05:28:40.849338: step: 434/469, loss: 0.0007637391099706292
2023-01-24 05:28:41.492863: step: 436/469, loss: 0.0024585032369941473
2023-01-24 05:28:42.046850: step: 438/469, loss: 0.0008235553978011012
2023-01-24 05:28:42.658513: step: 440/469, loss: 0.02056199684739113
2023-01-24 05:28:43.360152: step: 442/469, loss: 0.02932426705956459
2023-01-24 05:28:43.942777: step: 444/469, loss: 0.0018069082871079445
2023-01-24 05:28:44.504796: step: 446/469, loss: 0.007590556051582098
2023-01-24 05:28:45.119672: step: 448/469, loss: 0.007134605664759874
2023-01-24 05:28:45.875567: step: 450/469, loss: 0.018807299435138702
2023-01-24 05:28:46.470448: step: 452/469, loss: 0.020430870354175568
2023-01-24 05:28:47.148837: step: 454/469, loss: 0.004038804676383734
2023-01-24 05:28:47.777451: step: 456/469, loss: 0.0058199018239974976
2023-01-24 05:28:48.374731: step: 458/469, loss: 0.005377876106649637
2023-01-24 05:28:49.027603: step: 460/469, loss: 0.007059148512780666
2023-01-24 05:28:49.645930: step: 462/469, loss: 0.006550138350576162
2023-01-24 05:28:50.229030: step: 464/469, loss: 0.00034577693440951407
2023-01-24 05:28:50.846640: step: 466/469, loss: 0.0036921261344105005
2023-01-24 05:28:51.455953: step: 468/469, loss: 0.022593403235077858
2023-01-24 05:28:52.082248: step: 470/469, loss: 0.0671863704919815
2023-01-24 05:28:52.687304: step: 472/469, loss: 0.0019509991398081183
2023-01-24 05:28:53.367313: step: 474/469, loss: 0.001830831984989345
2023-01-24 05:28:53.988858: step: 476/469, loss: 0.0001018723487504758
2023-01-24 05:28:54.561848: step: 478/469, loss: 0.010821687057614326
2023-01-24 05:28:55.205356: step: 480/469, loss: 0.05585511028766632
2023-01-24 05:28:55.838246: step: 482/469, loss: 0.003776567755267024
2023-01-24 05:28:56.442339: step: 484/469, loss: 0.04578500613570213
2023-01-24 05:28:57.212946: step: 486/469, loss: 0.02981276996433735
2023-01-24 05:28:57.776593: step: 488/469, loss: 0.0014807283878326416
2023-01-24 05:28:58.432310: step: 490/469, loss: 0.0056166574358940125
2023-01-24 05:28:59.046460: step: 492/469, loss: 0.11408372223377228
2023-01-24 05:28:59.640732: step: 494/469, loss: 0.005550468806177378
2023-01-24 05:29:00.227593: step: 496/469, loss: 0.002481278032064438
2023-01-24 05:29:00.876507: step: 498/469, loss: 0.005701960064470768
2023-01-24 05:29:01.482773: step: 500/469, loss: 0.00721729127690196
2023-01-24 05:29:02.059624: step: 502/469, loss: 0.004936212673783302
2023-01-24 05:29:02.729961: step: 504/469, loss: 0.045986518263816833
2023-01-24 05:29:03.301275: step: 506/469, loss: 0.0019094212912023067
2023-01-24 05:29:03.918799: step: 508/469, loss: 0.049983784556388855
2023-01-24 05:29:04.477024: step: 510/469, loss: 0.018032558262348175
2023-01-24 05:29:05.092020: step: 512/469, loss: 1.561031058372464e-05
2023-01-24 05:29:05.822322: step: 514/469, loss: 0.07706205546855927
2023-01-24 05:29:06.508546: step: 516/469, loss: 0.007279384881258011
2023-01-24 05:29:07.123307: step: 518/469, loss: 0.0040094079449772835
2023-01-24 05:29:07.693517: step: 520/469, loss: 0.027229076251387596
2023-01-24 05:29:08.317628: step: 522/469, loss: 0.0019564018584787846
2023-01-24 05:29:09.027571: step: 524/469, loss: 0.0011849193833768368
2023-01-24 05:29:09.715536: step: 526/469, loss: 0.01664084754884243
2023-01-24 05:29:10.304343: step: 528/469, loss: 0.00618576118722558
2023-01-24 05:29:10.941896: step: 530/469, loss: 0.013897284865379333
2023-01-24 05:29:11.565431: step: 532/469, loss: 0.0008726078667677939
2023-01-24 05:29:12.201761: step: 534/469, loss: 0.0031327398028224707
2023-01-24 05:29:12.850789: step: 536/469, loss: 0.02323629893362522
2023-01-24 05:29:13.511431: step: 538/469, loss: 0.044767554849386215
2023-01-24 05:29:14.094774: step: 540/469, loss: 0.00033543503377586603
2023-01-24 05:29:14.710976: step: 542/469, loss: 0.0008319690823554993
2023-01-24 05:29:15.332403: step: 544/469, loss: 0.06147266924381256
2023-01-24 05:29:15.997134: step: 546/469, loss: 0.010405710898339748
2023-01-24 05:29:16.605516: step: 548/469, loss: 0.02598422020673752
2023-01-24 05:29:17.204287: step: 550/469, loss: 2.1834668586961925e-05
2023-01-24 05:29:17.795958: step: 552/469, loss: 0.0034023048356175423
2023-01-24 05:29:18.432141: step: 554/469, loss: 0.03261549025774002
2023-01-24 05:29:18.997495: step: 556/469, loss: 0.002278990810737014
2023-01-24 05:29:19.627349: step: 558/469, loss: 0.03563765808939934
2023-01-24 05:29:20.225995: step: 560/469, loss: 0.028120949864387512
2023-01-24 05:29:20.818833: step: 562/469, loss: 0.007851927541196346
2023-01-24 05:29:21.416095: step: 564/469, loss: 1.195573804579908e-05
2023-01-24 05:29:22.075453: step: 566/469, loss: 0.00018038078269455582
2023-01-24 05:29:22.679905: step: 568/469, loss: 0.03586490824818611
2023-01-24 05:29:23.228478: step: 570/469, loss: 0.009922190569341183
2023-01-24 05:29:23.823122: step: 572/469, loss: 0.08011331409215927
2023-01-24 05:29:24.522671: step: 574/469, loss: 0.023162007331848145
2023-01-24 05:29:25.206426: step: 576/469, loss: 0.0010554376058280468
2023-01-24 05:29:25.830893: step: 578/469, loss: 0.0033900949638336897
2023-01-24 05:29:26.458511: step: 580/469, loss: 0.036971576511859894
2023-01-24 05:29:27.060002: step: 582/469, loss: 0.025155462324619293
2023-01-24 05:29:27.664318: step: 584/469, loss: 9.353594577987678e-06
2023-01-24 05:29:28.219809: step: 586/469, loss: 0.001067722332663834
2023-01-24 05:29:28.872708: step: 588/469, loss: 0.0021462542936205864
2023-01-24 05:29:29.514477: step: 590/469, loss: 0.022367671132087708
2023-01-24 05:29:30.117571: step: 592/469, loss: 0.0014849365688860416
2023-01-24 05:29:30.666877: step: 594/469, loss: 3.283873593318276e-05
2023-01-24 05:29:31.289576: step: 596/469, loss: 0.0026768064126372337
2023-01-24 05:29:31.955182: step: 598/469, loss: 0.00786451157182455
2023-01-24 05:29:32.577457: step: 600/469, loss: 0.005423974711447954
2023-01-24 05:29:33.154851: step: 602/469, loss: 0.005975480657070875
2023-01-24 05:29:33.710394: step: 604/469, loss: 0.02671235427260399
2023-01-24 05:29:34.226933: step: 606/469, loss: 0.001727751805447042
2023-01-24 05:29:34.846028: step: 608/469, loss: 0.15199093520641327
2023-01-24 05:29:35.524390: step: 610/469, loss: 0.0003186521935276687
2023-01-24 05:29:36.197176: step: 612/469, loss: 0.009734037332236767
2023-01-24 05:29:36.777052: step: 614/469, loss: 0.001794076873920858
2023-01-24 05:29:37.468403: step: 616/469, loss: 0.00023365308879874647
2023-01-24 05:29:38.105569: step: 618/469, loss: 0.08687198162078857
2023-01-24 05:29:38.723676: step: 620/469, loss: 0.011066783219575882
2023-01-24 05:29:39.390766: step: 622/469, loss: 0.004672329872846603
2023-01-24 05:29:39.993058: step: 624/469, loss: 0.003951750695705414
2023-01-24 05:29:40.598735: step: 626/469, loss: 0.0007730473298579454
2023-01-24 05:29:41.210143: step: 628/469, loss: 0.00032559860846959054
2023-01-24 05:29:41.808857: step: 630/469, loss: 7.381993782473728e-05
2023-01-24 05:29:42.404942: step: 632/469, loss: 0.0011772344587370753
2023-01-24 05:29:43.022809: step: 634/469, loss: 0.03232504427433014
2023-01-24 05:29:43.678892: step: 636/469, loss: 0.0838412195444107
2023-01-24 05:29:44.236799: step: 638/469, loss: 0.4180150628089905
2023-01-24 05:29:44.840582: step: 640/469, loss: 0.0005095831584185362
2023-01-24 05:29:45.473914: step: 642/469, loss: 0.36279064416885376
2023-01-24 05:29:46.159652: step: 644/469, loss: 0.0027092904783785343
2023-01-24 05:29:46.763790: step: 646/469, loss: 0.005490084178745747
2023-01-24 05:29:47.398499: step: 648/469, loss: 0.0017521940171718597
2023-01-24 05:29:48.030213: step: 650/469, loss: 0.036064352840185165
2023-01-24 05:29:48.659463: step: 652/469, loss: 0.09220781177282333
2023-01-24 05:29:49.288710: step: 654/469, loss: 0.04325910657644272
2023-01-24 05:29:49.924279: step: 656/469, loss: 0.012073627673089504
2023-01-24 05:29:50.707135: step: 658/469, loss: 0.036337390542030334
2023-01-24 05:29:51.287707: step: 660/469, loss: 0.0017401073127985
2023-01-24 05:29:51.909684: step: 662/469, loss: 0.0011992332292720675
2023-01-24 05:29:52.505386: step: 664/469, loss: 0.02882547304034233
2023-01-24 05:29:53.132323: step: 666/469, loss: 0.026680851355195045
2023-01-24 05:29:53.789089: step: 668/469, loss: 0.004989529959857464
2023-01-24 05:29:54.394119: step: 670/469, loss: 0.01681157574057579
2023-01-24 05:29:54.969630: step: 672/469, loss: 6.639528146479279e-05
2023-01-24 05:29:55.514408: step: 674/469, loss: 0.008588061667978764
2023-01-24 05:29:56.150644: step: 676/469, loss: 6.242917152121663e-05
2023-01-24 05:29:56.779486: step: 678/469, loss: 6.337384547805414e-05
2023-01-24 05:29:57.436864: step: 680/469, loss: 0.0051832362078130245
2023-01-24 05:29:58.088753: step: 682/469, loss: 0.02174840122461319
2023-01-24 05:29:58.760591: step: 684/469, loss: 0.002919914200901985
2023-01-24 05:29:59.291274: step: 686/469, loss: 0.0022616484202444553
2023-01-24 05:29:59.865984: step: 688/469, loss: 0.007699252106249332
2023-01-24 05:30:00.420383: step: 690/469, loss: 0.0007571104797534645
2023-01-24 05:30:01.001924: step: 692/469, loss: 0.0009577810415066779
2023-01-24 05:30:01.614392: step: 694/469, loss: 0.0014563316944986582
2023-01-24 05:30:02.227962: step: 696/469, loss: 0.007509433664381504
2023-01-24 05:30:02.865128: step: 698/469, loss: 0.018059106543660164
2023-01-24 05:30:03.481072: step: 700/469, loss: 0.0019540274515748024
2023-01-24 05:30:04.089298: step: 702/469, loss: 0.18619872629642487
2023-01-24 05:30:04.715036: step: 704/469, loss: 0.0012100540334358811
2023-01-24 05:30:05.328734: step: 706/469, loss: 0.007862688042223454
2023-01-24 05:30:05.884401: step: 708/469, loss: 0.0008311189012601972
2023-01-24 05:30:06.468603: step: 710/469, loss: 0.063021220266819
2023-01-24 05:30:07.080159: step: 712/469, loss: 0.2638273239135742
2023-01-24 05:30:07.622549: step: 714/469, loss: 0.0015841509448364377
2023-01-24 05:30:08.249872: step: 716/469, loss: 0.00010814674897119403
2023-01-24 05:30:08.808207: step: 718/469, loss: 0.016875075176358223
2023-01-24 05:30:09.413054: step: 720/469, loss: 0.0034369411878287792
2023-01-24 05:30:09.951495: step: 722/469, loss: 0.0003486261412035674
2023-01-24 05:30:10.600501: step: 724/469, loss: 0.014958810061216354
2023-01-24 05:30:11.219861: step: 726/469, loss: 0.0028847274370491505
2023-01-24 05:30:11.828686: step: 728/469, loss: 0.010769457556307316
2023-01-24 05:30:12.419686: step: 730/469, loss: 0.19564558565616608
2023-01-24 05:30:13.140888: step: 732/469, loss: 0.0037767256144434214
2023-01-24 05:30:13.824181: step: 734/469, loss: 0.010133241303265095
2023-01-24 05:30:14.416008: step: 736/469, loss: 0.0005434389458969235
2023-01-24 05:30:15.042960: step: 738/469, loss: 0.000599593564402312
2023-01-24 05:30:15.660384: step: 740/469, loss: 0.00011581474245758727
2023-01-24 05:30:16.222415: step: 742/469, loss: 0.054639704525470734
2023-01-24 05:30:16.863482: step: 744/469, loss: 0.0030861583072692156
2023-01-24 05:30:17.484379: step: 746/469, loss: 0.0017878111684694886
2023-01-24 05:30:18.123039: step: 748/469, loss: 0.0074324156157672405
2023-01-24 05:30:18.766154: step: 750/469, loss: 0.12366275489330292
2023-01-24 05:30:19.378888: step: 752/469, loss: 0.021732477471232414
2023-01-24 05:30:20.014619: step: 754/469, loss: 0.0007377371075563133
2023-01-24 05:30:20.615501: step: 756/469, loss: 0.0034300272818654776
2023-01-24 05:30:21.234052: step: 758/469, loss: 0.004186233971267939
2023-01-24 05:30:21.877058: step: 760/469, loss: 0.06287708878517151
2023-01-24 05:30:22.516055: step: 762/469, loss: 0.007598173804581165
2023-01-24 05:30:23.148048: step: 764/469, loss: 0.15563441812992096
2023-01-24 05:30:23.768973: step: 766/469, loss: 0.11742037534713745
2023-01-24 05:30:24.495159: step: 768/469, loss: 0.022891785949468613
2023-01-24 05:30:25.069278: step: 770/469, loss: 0.00043143340735696256
2023-01-24 05:30:25.858182: step: 772/469, loss: 0.0017112481873482466
2023-01-24 05:30:26.461467: step: 774/469, loss: 0.00031356822000816464
2023-01-24 05:30:27.012922: step: 776/469, loss: 0.005490230396389961
2023-01-24 05:30:27.616956: step: 778/469, loss: 0.01457175798714161
2023-01-24 05:30:28.272903: step: 780/469, loss: 0.025646094232797623
2023-01-24 05:30:28.881087: step: 782/469, loss: 0.007112429942935705
2023-01-24 05:30:29.490862: step: 784/469, loss: 0.01074180193245411
2023-01-24 05:30:30.072869: step: 786/469, loss: 0.0004196114023216069
2023-01-24 05:30:30.676791: step: 788/469, loss: 0.00041283125756308436
2023-01-24 05:30:31.275825: step: 790/469, loss: 0.008841020986437798
2023-01-24 05:30:31.913526: step: 792/469, loss: 0.008139640092849731
2023-01-24 05:30:32.471470: step: 794/469, loss: 0.03408011049032211
2023-01-24 05:30:33.035701: step: 796/469, loss: 0.02207968197762966
2023-01-24 05:30:33.672868: step: 798/469, loss: 0.005294452887028456
2023-01-24 05:30:34.306430: step: 800/469, loss: 0.047961167991161346
2023-01-24 05:30:34.973854: step: 802/469, loss: 0.0017440533265471458
2023-01-24 05:30:35.609431: step: 804/469, loss: 0.013308239169418812
2023-01-24 05:30:36.210830: step: 806/469, loss: 0.005262637510895729
2023-01-24 05:30:36.837053: step: 808/469, loss: 0.001996168866753578
2023-01-24 05:30:37.535885: step: 810/469, loss: 0.027486082166433334
2023-01-24 05:30:38.139182: step: 812/469, loss: 0.0007017867756076157
2023-01-24 05:30:38.753937: step: 814/469, loss: 0.0018342012772336602
2023-01-24 05:30:39.361648: step: 816/469, loss: 9.853844676399603e-05
2023-01-24 05:30:39.929368: step: 818/469, loss: 0.0020896398928016424
2023-01-24 05:30:40.485035: step: 820/469, loss: 0.0050257109105587006
2023-01-24 05:30:41.145274: step: 822/469, loss: 0.030479149892926216
2023-01-24 05:30:41.826817: step: 824/469, loss: 0.0023915020283311605
2023-01-24 05:30:42.457674: step: 826/469, loss: 0.005647624377161264
2023-01-24 05:30:43.117012: step: 828/469, loss: 0.0007674493826925755
2023-01-24 05:30:43.674471: step: 830/469, loss: 0.004160327836871147
2023-01-24 05:30:44.316309: step: 832/469, loss: 0.021543780341744423
2023-01-24 05:30:44.918322: step: 834/469, loss: 0.019983643665909767
2023-01-24 05:30:45.524573: step: 836/469, loss: 0.0033185044303536415
2023-01-24 05:30:46.203933: step: 838/469, loss: 0.00011398903734516352
2023-01-24 05:30:46.818117: step: 840/469, loss: 0.0050304424948990345
2023-01-24 05:30:47.506547: step: 842/469, loss: 0.07564875483512878
2023-01-24 05:30:48.162651: step: 844/469, loss: 0.00016987166600301862
2023-01-24 05:30:48.800485: step: 846/469, loss: 0.022639740258455276
2023-01-24 05:30:49.472868: step: 848/469, loss: 0.010631454177200794
2023-01-24 05:30:50.080644: step: 850/469, loss: 0.0017994737718254328
2023-01-24 05:30:50.754270: step: 852/469, loss: 0.002849370939657092
2023-01-24 05:30:51.368910: step: 854/469, loss: 0.01692868396639824
2023-01-24 05:30:51.957303: step: 856/469, loss: 0.028368575498461723
2023-01-24 05:30:52.563798: step: 858/469, loss: 0.02622413821518421
2023-01-24 05:30:53.177164: step: 860/469, loss: 0.08661984652280807
2023-01-24 05:30:53.838534: step: 862/469, loss: 0.0007552942261099815
2023-01-24 05:30:54.506845: step: 864/469, loss: 0.1911463439464569
2023-01-24 05:30:55.103963: step: 866/469, loss: 0.002511322032660246
2023-01-24 05:30:55.685626: step: 868/469, loss: 0.0032366435043513775
2023-01-24 05:30:56.423662: step: 870/469, loss: 0.0002490816987119615
2023-01-24 05:30:57.002016: step: 872/469, loss: 0.0011198052670806646
2023-01-24 05:30:57.557910: step: 874/469, loss: 0.001496673095971346
2023-01-24 05:30:58.167292: step: 876/469, loss: 0.005319307558238506
2023-01-24 05:30:58.804439: step: 878/469, loss: 0.015571960248053074
2023-01-24 05:30:59.366956: step: 880/469, loss: 6.340535037452355e-05
2023-01-24 05:30:59.961257: step: 882/469, loss: 0.0018311298917979002
2023-01-24 05:31:00.643738: step: 884/469, loss: 7.11813336238265e-05
2023-01-24 05:31:01.282430: step: 886/469, loss: 0.009444230236113071
2023-01-24 05:31:01.856266: step: 888/469, loss: 0.01700914278626442
2023-01-24 05:31:02.409171: step: 890/469, loss: 0.006454721093177795
2023-01-24 05:31:02.988038: step: 892/469, loss: 0.056100994348526
2023-01-24 05:31:03.583645: step: 894/469, loss: 0.8182767629623413
2023-01-24 05:31:04.216077: step: 896/469, loss: 0.018168237060308456
2023-01-24 05:31:04.901956: step: 898/469, loss: 0.04914424940943718
2023-01-24 05:31:05.611120: step: 900/469, loss: 0.001316792331635952
2023-01-24 05:31:06.283536: step: 902/469, loss: 0.008519035764038563
2023-01-24 05:31:06.861552: step: 904/469, loss: 0.003834921633824706
2023-01-24 05:31:07.492462: step: 906/469, loss: 0.015359274111688137
2023-01-24 05:31:08.145803: step: 908/469, loss: 0.018616918474435806
2023-01-24 05:31:08.799197: step: 910/469, loss: 0.000498221896123141
2023-01-24 05:31:09.446618: step: 912/469, loss: 0.03173353523015976
2023-01-24 05:31:10.165617: step: 914/469, loss: 0.023717835545539856
2023-01-24 05:31:10.844145: step: 916/469, loss: 0.01838405802845955
2023-01-24 05:31:11.410682: step: 918/469, loss: 0.07607328146696091
2023-01-24 05:31:12.039324: step: 920/469, loss: 0.015997862443327904
2023-01-24 05:31:12.630599: step: 922/469, loss: 0.005880296695977449
2023-01-24 05:31:13.390282: step: 924/469, loss: 0.0033639695029705763
2023-01-24 05:31:14.004751: step: 926/469, loss: 0.0015219607157632709
2023-01-24 05:31:14.644491: step: 928/469, loss: 0.0019990154542028904
2023-01-24 05:31:15.271284: step: 930/469, loss: 0.01711413264274597
2023-01-24 05:31:15.850444: step: 932/469, loss: 0.006104788277298212
2023-01-24 05:31:16.522700: step: 934/469, loss: 0.004206092096865177
2023-01-24 05:31:17.124566: step: 936/469, loss: 0.0012522918405011296
2023-01-24 05:31:17.699472: step: 938/469, loss: 0.003964857663959265
==================================================
Loss: 0.026
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3296719192213082, 'r': 0.3071516363143498, 'f1': 0.3180135802311637}, 'combined': 0.23432579595980482, 'epoch': 36}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3274250154607297, 'r': 0.2621197516268422, 'f1': 0.2911553745204659}, 'combined': 0.15881202246570866, 'epoch': 36}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33730944175360156, 'r': 0.31234726295210163, 'f1': 0.3243487834005075}, 'combined': 0.2389938404003739, 'epoch': 36}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.34235788565215647, 'r': 0.27062874035083545, 'f1': 0.30229658988601243}, 'combined': 0.16488904902873405, 'epoch': 36}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32293679254488683, 'r': 0.2990382443299901, 'f1': 0.3105283837673001}, 'combined': 0.2288103880390632, 'epoch': 36}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3313143781893782, 'r': 0.269173987037665, 'f1': 0.2970289427886601}, 'combined': 0.16201578697563276, 'epoch': 36}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.31644144144144143, 'r': 0.3345238095238095, 'f1': 0.32523148148148145}, 'combined': 0.21682098765432095, 'epoch': 36}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.34523809523809523, 'r': 0.31521739130434784, 'f1': 0.3295454545454546}, 'combined': 0.1647727272727273, 'epoch': 36}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'epoch': 36}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32293679254488683, 'r': 0.2990382443299901, 'f1': 0.3105283837673001}, 'combined': 0.2288103880390632, 'epoch': 36}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3313143781893782, 'r': 0.269173987037665, 'f1': 0.2970289427886601}, 'combined': 0.16201578697563276, 'epoch': 36}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'epoch': 36}
******************************
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
2023-01-24 05:34:13.731358: step: 2/469, loss: 0.02334951050579548
2023-01-24 05:34:14.310420: step: 4/469, loss: 0.013603771105408669
2023-01-24 05:34:14.870791: step: 6/469, loss: 0.05895049870014191
2023-01-24 05:34:15.512412: step: 8/469, loss: 0.009032522328197956
2023-01-24 05:34:16.144706: step: 10/469, loss: 0.002515010302886367
2023-01-24 05:34:16.818373: step: 12/469, loss: 0.0003157924802508205
2023-01-24 05:34:17.469909: step: 14/469, loss: 0.00029328028904274106
2023-01-24 05:34:18.020018: step: 16/469, loss: 3.104509960394353e-05
2023-01-24 05:34:18.618743: step: 18/469, loss: 0.0002855995553545654
2023-01-24 05:34:19.197345: step: 20/469, loss: 0.001551100634969771
2023-01-24 05:34:19.864962: step: 22/469, loss: 0.006941393483430147
2023-01-24 05:34:20.515097: step: 24/469, loss: 0.006952290423214436
2023-01-24 05:34:21.103188: step: 26/469, loss: 7.099486538209021e-05
2023-01-24 05:34:21.716663: step: 28/469, loss: 0.007216090802103281
2023-01-24 05:34:22.306856: step: 30/469, loss: 0.003178994171321392
2023-01-24 05:34:22.935833: step: 32/469, loss: 0.0009747220319695771
2023-01-24 05:34:23.520697: step: 34/469, loss: 0.0005233795964159071
2023-01-24 05:34:24.191017: step: 36/469, loss: 0.008877452462911606
2023-01-24 05:34:24.792700: step: 38/469, loss: 0.019093405455350876
2023-01-24 05:34:25.344318: step: 40/469, loss: 5.362175215850584e-05
2023-01-24 05:34:26.001772: step: 42/469, loss: 0.0002662398910615593
2023-01-24 05:34:26.611869: step: 44/469, loss: 0.0019493541913107038
2023-01-24 05:34:27.242440: step: 46/469, loss: 0.015421044081449509
2023-01-24 05:34:27.879328: step: 48/469, loss: 0.0008357454207725823
2023-01-24 05:34:28.499201: step: 50/469, loss: 0.008192282170057297
2023-01-24 05:34:29.177339: step: 52/469, loss: 0.00021694099996238947
2023-01-24 05:34:29.799160: step: 54/469, loss: 0.0005123814335092902
2023-01-24 05:34:30.433083: step: 56/469, loss: 0.005808388814330101
2023-01-24 05:34:31.085178: step: 58/469, loss: 0.005942604038864374
2023-01-24 05:34:31.666456: step: 60/469, loss: 0.00048650658573023975
2023-01-24 05:34:32.268076: step: 62/469, loss: 0.028779789805412292
2023-01-24 05:34:32.973603: step: 64/469, loss: 0.001439630868844688
2023-01-24 05:34:33.641295: step: 66/469, loss: 0.00027584107010625303
2023-01-24 05:34:34.332184: step: 68/469, loss: 0.0037879787851125
2023-01-24 05:34:34.988703: step: 70/469, loss: 0.018322013318538666
2023-01-24 05:34:35.643125: step: 72/469, loss: 0.0068619451485574245
2023-01-24 05:34:36.310187: step: 74/469, loss: 0.00015405187150463462
2023-01-24 05:34:36.912147: step: 76/469, loss: 0.0002149700012523681
2023-01-24 05:34:37.447410: step: 78/469, loss: 0.0016966273542493582
2023-01-24 05:34:38.135381: step: 80/469, loss: 0.011040701530873775
2023-01-24 05:34:38.854461: step: 82/469, loss: 0.004825273063033819
2023-01-24 05:34:39.558457: step: 84/469, loss: 0.000932644703425467
2023-01-24 05:34:40.215363: step: 86/469, loss: 0.015768012031912804
2023-01-24 05:34:40.843794: step: 88/469, loss: 0.0015958852600306273
2023-01-24 05:34:41.597851: step: 90/469, loss: 0.00022211599571164697
2023-01-24 05:34:42.158388: step: 92/469, loss: 0.003766988404095173
2023-01-24 05:34:42.842778: step: 94/469, loss: 0.00632568821310997
2023-01-24 05:34:43.472608: step: 96/469, loss: 3.9818834920879453e-05
2023-01-24 05:34:44.146519: step: 98/469, loss: 0.00012792499910574406
2023-01-24 05:34:44.786145: step: 100/469, loss: 0.0056974878534674644
2023-01-24 05:34:45.388381: step: 102/469, loss: 0.0001498083584010601
2023-01-24 05:34:46.036654: step: 104/469, loss: 0.004224066622555256
2023-01-24 05:34:46.678973: step: 106/469, loss: 0.001001994707621634
2023-01-24 05:34:47.296872: step: 108/469, loss: 0.0001033278604154475
2023-01-24 05:34:47.919939: step: 110/469, loss: 0.008249464444816113
2023-01-24 05:34:48.506913: step: 112/469, loss: 2.1856059902347624e-05
2023-01-24 05:34:49.151719: step: 114/469, loss: 2.4825678337947465e-05
2023-01-24 05:34:49.752042: step: 116/469, loss: 0.0014028786681592464
2023-01-24 05:34:50.424659: step: 118/469, loss: 6.449964712373912e-05
2023-01-24 05:34:51.019647: step: 120/469, loss: 0.021299973130226135
2023-01-24 05:34:51.605853: step: 122/469, loss: 0.01827310584485531
2023-01-24 05:34:52.320240: step: 124/469, loss: 0.01773155853152275
2023-01-24 05:34:52.937649: step: 126/469, loss: 0.0010096313199028373
2023-01-24 05:34:53.590542: step: 128/469, loss: 0.0034883213229477406
2023-01-24 05:34:54.270928: step: 130/469, loss: 0.031068120151758194
2023-01-24 05:34:54.837534: step: 132/469, loss: 0.17981663346290588
2023-01-24 05:34:55.472107: step: 134/469, loss: 0.011230730451643467
2023-01-24 05:34:56.186221: step: 136/469, loss: 0.11118075251579285
2023-01-24 05:34:56.882953: step: 138/469, loss: 0.00017911367467604578
2023-01-24 05:34:57.558275: step: 140/469, loss: 0.07104042172431946
2023-01-24 05:34:58.213599: step: 142/469, loss: 0.012461545877158642
2023-01-24 05:34:58.810719: step: 144/469, loss: 0.00015260098734870553
2023-01-24 05:34:59.429530: step: 146/469, loss: 0.003665447235107422
2023-01-24 05:35:00.140418: step: 148/469, loss: 0.007120559923350811
2023-01-24 05:35:00.778554: step: 150/469, loss: 0.0008562491275370121
2023-01-24 05:35:01.417109: step: 152/469, loss: 0.03952468931674957
2023-01-24 05:35:02.029746: step: 154/469, loss: 0.00041526317363604903
2023-01-24 05:35:02.674605: step: 156/469, loss: 0.00015986785001587123
2023-01-24 05:35:03.244822: step: 158/469, loss: 0.00011045135033782572
2023-01-24 05:35:03.822504: step: 160/469, loss: 0.0034824644681066275
2023-01-24 05:35:04.411230: step: 162/469, loss: 0.0001812041155062616
2023-01-24 05:35:05.032959: step: 164/469, loss: 0.005615279544144869
2023-01-24 05:35:05.665716: step: 166/469, loss: 0.02610810473561287
2023-01-24 05:35:06.286441: step: 168/469, loss: 0.035773828625679016
2023-01-24 05:35:06.895739: step: 170/469, loss: 0.3308396339416504
2023-01-24 05:35:07.502572: step: 172/469, loss: 7.553344767075032e-05
2023-01-24 05:35:08.117909: step: 174/469, loss: 0.09016861766576767
2023-01-24 05:35:08.707905: step: 176/469, loss: 0.0012278578942641616
2023-01-24 05:35:09.333385: step: 178/469, loss: 0.0007366069476120174
2023-01-24 05:35:09.939831: step: 180/469, loss: 0.00018095181440003216
2023-01-24 05:35:10.529699: step: 182/469, loss: 8.926808732212521e-06
2023-01-24 05:35:11.205515: step: 184/469, loss: 0.0029862928204238415
2023-01-24 05:35:11.800836: step: 186/469, loss: 0.1733856350183487
2023-01-24 05:35:12.422170: step: 188/469, loss: 0.020981404930353165
2023-01-24 05:35:13.083375: step: 190/469, loss: 0.00013106894039083272
2023-01-24 05:35:13.751008: step: 192/469, loss: 0.015181186608970165
2023-01-24 05:35:14.294784: step: 194/469, loss: 3.205590837751515e-05
2023-01-24 05:35:14.960550: step: 196/469, loss: 0.0026021336670964956
2023-01-24 05:35:15.529106: step: 198/469, loss: 0.00040086277294903994
2023-01-24 05:35:16.155161: step: 200/469, loss: 0.0012865004828199744
2023-01-24 05:35:16.760748: step: 202/469, loss: 0.0005586662446148694
2023-01-24 05:35:17.386030: step: 204/469, loss: 0.012114351615309715
2023-01-24 05:35:17.980165: step: 206/469, loss: 0.050020214170217514
2023-01-24 05:35:18.554195: step: 208/469, loss: 0.01910516247153282
2023-01-24 05:35:19.141927: step: 210/469, loss: 0.00251079467125237
2023-01-24 05:35:19.735418: step: 212/469, loss: 0.011612393893301487
2023-01-24 05:35:20.327258: step: 214/469, loss: 0.004886446986347437
2023-01-24 05:35:20.979742: step: 216/469, loss: 0.005088290199637413
2023-01-24 05:35:21.571202: step: 218/469, loss: 0.017661696299910545
2023-01-24 05:35:22.236750: step: 220/469, loss: 0.0006772956112399697
2023-01-24 05:35:22.977713: step: 222/469, loss: 0.00578831322491169
2023-01-24 05:35:23.791922: step: 224/469, loss: 0.0015098800649866462
2023-01-24 05:35:24.395465: step: 226/469, loss: 0.0048980871215462685
2023-01-24 05:35:25.061700: step: 228/469, loss: 0.05263599008321762
2023-01-24 05:35:25.646105: step: 230/469, loss: 0.0008351249853149056
2023-01-24 05:35:26.276070: step: 232/469, loss: 0.0065918113104999065
2023-01-24 05:35:26.904112: step: 234/469, loss: 0.00393585255369544
2023-01-24 05:35:27.513164: step: 236/469, loss: 0.004989714361727238
2023-01-24 05:35:28.064522: step: 238/469, loss: 0.00044002989307045937
2023-01-24 05:35:28.646495: step: 240/469, loss: 0.0006200528587214649
2023-01-24 05:35:29.319340: step: 242/469, loss: 0.004732328932732344
2023-01-24 05:35:29.920346: step: 244/469, loss: 0.06446399539709091
2023-01-24 05:35:30.544784: step: 246/469, loss: 0.018771782517433167
2023-01-24 05:35:31.129934: step: 248/469, loss: 0.0024162803310900927
2023-01-24 05:35:31.771459: step: 250/469, loss: 0.0005391480517573655
2023-01-24 05:35:32.358625: step: 252/469, loss: 0.0045122853480279446
2023-01-24 05:35:33.085073: step: 254/469, loss: 0.00261093582957983
2023-01-24 05:35:33.657404: step: 256/469, loss: 0.000743781216442585
2023-01-24 05:35:34.313256: step: 258/469, loss: 0.00010305748583050445
2023-01-24 05:35:34.991441: step: 260/469, loss: 5.486128884513164e-07
2023-01-24 05:35:35.627121: step: 262/469, loss: 0.014851206913590431
2023-01-24 05:35:36.206913: step: 264/469, loss: 0.007517075631767511
2023-01-24 05:35:36.810040: step: 266/469, loss: 0.0023233280517160892
2023-01-24 05:35:37.459239: step: 268/469, loss: 0.009786678478121758
2023-01-24 05:35:38.051904: step: 270/469, loss: 0.0003873548412229866
2023-01-24 05:35:38.684668: step: 272/469, loss: 0.006946471985429525
2023-01-24 05:35:39.277094: step: 274/469, loss: 0.003758813254535198
2023-01-24 05:35:39.981869: step: 276/469, loss: 0.003824097802862525
2023-01-24 05:35:40.579433: step: 278/469, loss: 0.0009378312970511615
2023-01-24 05:35:41.122297: step: 280/469, loss: 0.0016444976208731532
2023-01-24 05:35:41.868865: step: 282/469, loss: 6.573781865881756e-05
2023-01-24 05:35:42.557429: step: 284/469, loss: 0.012586846947669983
2023-01-24 05:35:43.211749: step: 286/469, loss: 0.0011832331074401736
2023-01-24 05:35:43.787381: step: 288/469, loss: 0.017640678212046623
2023-01-24 05:35:44.396039: step: 290/469, loss: 0.0009549250244162977
2023-01-24 05:35:45.048103: step: 292/469, loss: 0.05993243679404259
2023-01-24 05:35:45.659250: step: 294/469, loss: 0.00037836923729628325
2023-01-24 05:35:46.300934: step: 296/469, loss: 0.000849375850521028
2023-01-24 05:35:47.010840: step: 298/469, loss: 0.5837039351463318
2023-01-24 05:35:47.586115: step: 300/469, loss: 0.00045387932914309204
2023-01-24 05:35:48.170270: step: 302/469, loss: 1.7525017028674483e-05
2023-01-24 05:35:48.799765: step: 304/469, loss: 0.010772112756967545
2023-01-24 05:35:49.414136: step: 306/469, loss: 0.0204091165214777
2023-01-24 05:35:50.046579: step: 308/469, loss: 0.0002220183814642951
2023-01-24 05:35:50.617361: step: 310/469, loss: 0.0054563977755606174
2023-01-24 05:35:51.259773: step: 312/469, loss: 0.005815763492137194
2023-01-24 05:35:51.872744: step: 314/469, loss: 0.0002758143236860633
2023-01-24 05:35:52.517801: step: 316/469, loss: 0.07313418388366699
2023-01-24 05:35:53.145676: step: 318/469, loss: 0.007582417689263821
2023-01-24 05:35:53.825219: step: 320/469, loss: 0.03991956263780594
2023-01-24 05:35:54.451205: step: 322/469, loss: 0.03166396915912628
2023-01-24 05:35:55.049318: step: 324/469, loss: 0.011305739171802998
2023-01-24 05:35:55.652648: step: 326/469, loss: 0.01131292525678873
2023-01-24 05:35:56.282334: step: 328/469, loss: 0.001254220143891871
2023-01-24 05:35:56.943776: step: 330/469, loss: 0.00580606609582901
2023-01-24 05:35:57.628694: step: 332/469, loss: 0.0020498523954302073
2023-01-24 05:35:58.316937: step: 334/469, loss: 7.834314601495862e-05
2023-01-24 05:35:58.878410: step: 336/469, loss: 0.008076257072389126
2023-01-24 05:35:59.429014: step: 338/469, loss: 0.0029463532846421003
2023-01-24 05:36:00.068568: step: 340/469, loss: 0.02310442179441452
2023-01-24 05:36:00.757931: step: 342/469, loss: 0.16581524908542633
2023-01-24 05:36:01.381979: step: 344/469, loss: 0.003446395741775632
2023-01-24 05:36:01.961519: step: 346/469, loss: 9.655807389208348e-07
2023-01-24 05:36:02.746514: step: 348/469, loss: 0.02838398888707161
2023-01-24 05:36:03.381247: step: 350/469, loss: 0.013428416103124619
2023-01-24 05:36:04.043978: step: 352/469, loss: 0.0110907768830657
2023-01-24 05:36:04.657810: step: 354/469, loss: 0.0035205520689487457
2023-01-24 05:36:05.254916: step: 356/469, loss: 0.011168516241014004
2023-01-24 05:36:05.866667: step: 358/469, loss: 0.02038724534213543
2023-01-24 05:36:06.478281: step: 360/469, loss: 1.6953126760199666e-05
2023-01-24 05:36:07.063942: step: 362/469, loss: 0.0064309025183320045
2023-01-24 05:36:07.662169: step: 364/469, loss: 0.00035900474176742136
2023-01-24 05:36:08.272524: step: 366/469, loss: 0.0017374753952026367
2023-01-24 05:36:08.910132: step: 368/469, loss: 0.035388797521591187
2023-01-24 05:36:09.597058: step: 370/469, loss: 0.0004407311789691448
2023-01-24 05:36:10.219971: step: 372/469, loss: 0.000823917449451983
2023-01-24 05:36:10.946110: step: 374/469, loss: 0.00952114351093769
2023-01-24 05:36:11.566348: step: 376/469, loss: 0.00024248902627732605
2023-01-24 05:36:12.179975: step: 378/469, loss: 0.07362029701471329
2023-01-24 05:36:12.832235: step: 380/469, loss: 0.5559163093566895
2023-01-24 05:36:13.469699: step: 382/469, loss: 0.0021526487544178963
2023-01-24 05:36:14.017304: step: 384/469, loss: 0.0008400852675549686
2023-01-24 05:36:14.604264: step: 386/469, loss: 0.0013083710800856352
2023-01-24 05:36:15.229351: step: 388/469, loss: 4.7370594984386116e-05
2023-01-24 05:36:15.880254: step: 390/469, loss: 9.946803402272053e-06
2023-01-24 05:36:16.495051: step: 392/469, loss: 0.025393834337592125
2023-01-24 05:36:17.106826: step: 394/469, loss: 0.0015814976068213582
2023-01-24 05:36:17.647703: step: 396/469, loss: 0.017286112532019615
2023-01-24 05:36:18.304872: step: 398/469, loss: 0.4820334017276764
2023-01-24 05:36:18.904269: step: 400/469, loss: 0.0005268231616355479
2023-01-24 05:36:19.477427: step: 402/469, loss: 0.000354180607246235
2023-01-24 05:36:20.097812: step: 404/469, loss: 0.0019696198869496584
2023-01-24 05:36:20.696881: step: 406/469, loss: 0.014124004170298576
2023-01-24 05:36:21.291816: step: 408/469, loss: 0.0011038167867809534
2023-01-24 05:36:21.911145: step: 410/469, loss: 0.03709586709737778
2023-01-24 05:36:22.546576: step: 412/469, loss: 0.007256742566823959
2023-01-24 05:36:23.173416: step: 414/469, loss: 0.0031886377837508917
2023-01-24 05:36:23.896983: step: 416/469, loss: 0.0014762443024665117
2023-01-24 05:36:24.574732: step: 418/469, loss: 0.017940755933523178
2023-01-24 05:36:25.139749: step: 420/469, loss: 0.005015256814658642
2023-01-24 05:36:25.808866: step: 422/469, loss: 0.002521911868825555
2023-01-24 05:36:26.391356: step: 424/469, loss: 0.0002531056525185704
2023-01-24 05:36:27.032742: step: 426/469, loss: 0.00305581814609468
2023-01-24 05:36:27.664114: step: 428/469, loss: 0.01845567487180233
2023-01-24 05:36:28.316456: step: 430/469, loss: 0.010437524877488613
2023-01-24 05:36:29.024748: step: 432/469, loss: 0.01325505506247282
2023-01-24 05:36:29.649328: step: 434/469, loss: 0.002705496968701482
2023-01-24 05:36:30.251510: step: 436/469, loss: 0.027814706787467003
2023-01-24 05:36:30.816440: step: 438/469, loss: 0.0008967772591859102
2023-01-24 05:36:31.441730: step: 440/469, loss: 0.036574140191078186
2023-01-24 05:36:32.044741: step: 442/469, loss: 0.0014592144871130586
2023-01-24 05:36:32.698654: step: 444/469, loss: 0.006886797957122326
2023-01-24 05:36:33.333870: step: 446/469, loss: 0.004467473365366459
2023-01-24 05:36:33.963154: step: 448/469, loss: 0.0009431479265913367
2023-01-24 05:36:34.608695: step: 450/469, loss: 0.0025406964123249054
2023-01-24 05:36:35.228833: step: 452/469, loss: 0.018055371940135956
2023-01-24 05:36:35.833372: step: 454/469, loss: 0.010064304806292057
2023-01-24 05:36:36.414599: step: 456/469, loss: 0.0036551090888679028
2023-01-24 05:36:37.094959: step: 458/469, loss: 0.004080642480403185
2023-01-24 05:36:37.692362: step: 460/469, loss: 0.019044430926442146
2023-01-24 05:36:38.282064: step: 462/469, loss: 0.0016572517342865467
2023-01-24 05:36:38.902021: step: 464/469, loss: 0.0060867383144795895
2023-01-24 05:36:39.495195: step: 466/469, loss: 0.000536244479008019
2023-01-24 05:36:40.156544: step: 468/469, loss: 0.012677637860178947
2023-01-24 05:36:40.730627: step: 470/469, loss: 1.4633342289016582e-05
2023-01-24 05:36:41.366660: step: 472/469, loss: 0.0130271315574646
2023-01-24 05:36:41.970642: step: 474/469, loss: 0.01142079383134842
2023-01-24 05:36:42.562626: step: 476/469, loss: 0.0062408470548689365
2023-01-24 05:36:43.182520: step: 478/469, loss: 0.06313908100128174
2023-01-24 05:36:43.767413: step: 480/469, loss: 0.001148531213402748
2023-01-24 05:36:44.417572: step: 482/469, loss: 0.006836864165961742
2023-01-24 05:36:45.015148: step: 484/469, loss: 0.014268173836171627
2023-01-24 05:36:45.679420: step: 486/469, loss: 0.0007623200654052198
2023-01-24 05:36:46.286740: step: 488/469, loss: 0.43366900086402893
2023-01-24 05:36:46.933494: step: 490/469, loss: 0.016756707802414894
2023-01-24 05:36:47.605337: step: 492/469, loss: 0.0017298609018325806
2023-01-24 05:36:48.212052: step: 494/469, loss: 0.007773790508508682
2023-01-24 05:36:48.882164: step: 496/469, loss: 0.14746889472007751
2023-01-24 05:36:49.470914: step: 498/469, loss: 0.00592234218493104
2023-01-24 05:36:50.051291: step: 500/469, loss: 0.008632895536720753
2023-01-24 05:36:50.643744: step: 502/469, loss: 0.020562294870615005
2023-01-24 05:36:51.327453: step: 504/469, loss: 0.00138269760645926
2023-01-24 05:36:51.903639: step: 506/469, loss: 0.039450839161872864
2023-01-24 05:36:52.527760: step: 508/469, loss: 0.12444482743740082
2023-01-24 05:36:53.114042: step: 510/469, loss: 0.003615305759012699
2023-01-24 05:36:53.718592: step: 512/469, loss: 0.010039028711616993
2023-01-24 05:36:54.248010: step: 514/469, loss: 0.0007576293428428471
2023-01-24 05:36:54.786486: step: 516/469, loss: 6.50722358841449e-05
2023-01-24 05:36:55.406492: step: 518/469, loss: 0.0018354099011048675
2023-01-24 05:36:56.045032: step: 520/469, loss: 0.0002575975959189236
2023-01-24 05:36:56.641952: step: 522/469, loss: 0.0008082690183073282
2023-01-24 05:36:57.228843: step: 524/469, loss: 0.00040417019044980407
2023-01-24 05:36:57.795097: step: 526/469, loss: 0.0014887795550748706
2023-01-24 05:36:58.388196: step: 528/469, loss: 0.4752001166343689
2023-01-24 05:36:59.031496: step: 530/469, loss: 0.0003663224051706493
2023-01-24 05:36:59.690228: step: 532/469, loss: 0.05763047933578491
2023-01-24 05:37:00.362826: step: 534/469, loss: 0.02389954961836338
2023-01-24 05:37:00.978515: step: 536/469, loss: 0.0033645592629909515
2023-01-24 05:37:01.623811: step: 538/469, loss: 3.387061042303685e-06
2023-01-24 05:37:02.285875: step: 540/469, loss: 0.01993384398519993
2023-01-24 05:37:02.843936: step: 542/469, loss: 0.009130529128015041
2023-01-24 05:37:03.414116: step: 544/469, loss: 0.03648785874247551
2023-01-24 05:37:04.000477: step: 546/469, loss: 0.011563469655811787
2023-01-24 05:37:04.536951: step: 548/469, loss: 0.0023125088773667812
2023-01-24 05:37:05.109031: step: 550/469, loss: 0.0007673653890378773
2023-01-24 05:37:05.688567: step: 552/469, loss: 0.003212862415239215
2023-01-24 05:37:06.264246: step: 554/469, loss: 0.015062791295349598
2023-01-24 05:37:06.830398: step: 556/469, loss: 0.004490231163799763
2023-01-24 05:37:07.522474: step: 558/469, loss: 0.009565253742039204
2023-01-24 05:37:08.158643: step: 560/469, loss: 0.00046789570478722453
2023-01-24 05:37:08.793894: step: 562/469, loss: 0.0007870469125919044
2023-01-24 05:37:09.421029: step: 564/469, loss: 2.5715095034684055e-05
2023-01-24 05:37:10.058941: step: 566/469, loss: 0.004579667001962662
2023-01-24 05:37:10.709785: step: 568/469, loss: 0.0014246586943045259
2023-01-24 05:37:11.341886: step: 570/469, loss: 0.0003634264867287129
2023-01-24 05:37:11.914872: step: 572/469, loss: 0.0011543008731678128
2023-01-24 05:37:12.532528: step: 574/469, loss: 0.008317421190440655
2023-01-24 05:37:13.140839: step: 576/469, loss: 0.008216132409870625
2023-01-24 05:37:13.722862: step: 578/469, loss: 0.011049808003008366
2023-01-24 05:37:14.366444: step: 580/469, loss: 0.4795406460762024
2023-01-24 05:37:14.997980: step: 582/469, loss: 0.02651878446340561
2023-01-24 05:37:15.560379: step: 584/469, loss: 0.016705136746168137
2023-01-24 05:37:16.185859: step: 586/469, loss: 0.07096443325281143
2023-01-24 05:37:16.726683: step: 588/469, loss: 0.00020236516138538718
2023-01-24 05:37:17.362125: step: 590/469, loss: 0.011545329354703426
2023-01-24 05:37:18.000117: step: 592/469, loss: 0.0005384701071307063
2023-01-24 05:37:18.597303: step: 594/469, loss: 0.007825718261301517
2023-01-24 05:37:19.183244: step: 596/469, loss: 0.01749524660408497
2023-01-24 05:37:19.820023: step: 598/469, loss: 0.0029937727376818657
2023-01-24 05:37:20.407354: step: 600/469, loss: 0.0022448524832725525
2023-01-24 05:37:20.968714: step: 602/469, loss: 0.000597543315961957
2023-01-24 05:37:21.675773: step: 604/469, loss: 0.09895917028188705
2023-01-24 05:37:22.294363: step: 606/469, loss: 0.019120363518595695
2023-01-24 05:37:22.917240: step: 608/469, loss: 0.006476159673184156
2023-01-24 05:37:23.481913: step: 610/469, loss: 0.0002013736084336415
2023-01-24 05:37:24.055121: step: 612/469, loss: 0.04919161647558212
2023-01-24 05:37:24.666463: step: 614/469, loss: 0.0032582608982920647
2023-01-24 05:37:25.374864: step: 616/469, loss: 0.025594206526875496
2023-01-24 05:37:25.962359: step: 618/469, loss: 0.0001824445789679885
2023-01-24 05:37:26.620888: step: 620/469, loss: 0.0008693342097103596
2023-01-24 05:37:27.212335: step: 622/469, loss: 0.008048921823501587
2023-01-24 05:37:27.831483: step: 624/469, loss: 0.0008903730195015669
2023-01-24 05:37:28.461948: step: 626/469, loss: 0.0020310492254793644
2023-01-24 05:37:29.193356: step: 628/469, loss: 0.0005097966059111059
2023-01-24 05:37:29.823463: step: 630/469, loss: 0.00037166595575399697
2023-01-24 05:37:30.398227: step: 632/469, loss: 0.0008686490473337471
2023-01-24 05:37:30.996928: step: 634/469, loss: 0.0005579735152423382
2023-01-24 05:37:31.603334: step: 636/469, loss: 0.005188541021198034
2023-01-24 05:37:32.160463: step: 638/469, loss: 0.002648049732670188
2023-01-24 05:37:32.820253: step: 640/469, loss: 0.03972799703478813
2023-01-24 05:37:33.383672: step: 642/469, loss: 0.07975295186042786
2023-01-24 05:37:34.020942: step: 644/469, loss: 0.004514096304774284
2023-01-24 05:37:34.684331: step: 646/469, loss: 0.006104631349444389
2023-01-24 05:37:35.297027: step: 648/469, loss: 0.002300059190019965
2023-01-24 05:37:35.888482: step: 650/469, loss: 0.03398158773779869
2023-01-24 05:37:36.480847: step: 652/469, loss: 0.003969356417655945
2023-01-24 05:37:37.176264: step: 654/469, loss: 0.0026101006660610437
2023-01-24 05:37:37.783602: step: 656/469, loss: 0.0012079097796231508
2023-01-24 05:37:38.428219: step: 658/469, loss: 0.0003898576833307743
2023-01-24 05:37:39.051425: step: 660/469, loss: 0.012895661406219006
2023-01-24 05:37:39.724075: step: 662/469, loss: 0.011776790954172611
2023-01-24 05:37:40.401975: step: 664/469, loss: 0.028253180906176567
2023-01-24 05:37:41.083568: step: 666/469, loss: 0.005696744192391634
2023-01-24 05:37:41.647428: step: 668/469, loss: 0.004100794438272715
2023-01-24 05:37:42.220099: step: 670/469, loss: 0.004053592216223478
2023-01-24 05:37:42.930947: step: 672/469, loss: 0.0008256476721726358
2023-01-24 05:37:43.552581: step: 674/469, loss: 0.014969659969210625
2023-01-24 05:37:44.203655: step: 676/469, loss: 0.019797423854470253
2023-01-24 05:37:44.819689: step: 678/469, loss: 0.003951985388994217
2023-01-24 05:37:45.343575: step: 680/469, loss: 0.0038019197527319193
2023-01-24 05:37:45.936576: step: 682/469, loss: 0.47740209102630615
2023-01-24 05:37:46.503812: step: 684/469, loss: 0.0016613781917840242
2023-01-24 05:37:47.139525: step: 686/469, loss: 0.01725945807993412
2023-01-24 05:37:47.793575: step: 688/469, loss: 0.05918346717953682
2023-01-24 05:37:48.342257: step: 690/469, loss: 0.002689868677407503
2023-01-24 05:37:48.911471: step: 692/469, loss: 0.0017075049690902233
2023-01-24 05:37:49.548851: step: 694/469, loss: 0.005542844533920288
2023-01-24 05:37:50.207327: step: 696/469, loss: 0.020259235054254532
2023-01-24 05:37:50.979881: step: 698/469, loss: 0.0008228069636970758
2023-01-24 05:37:51.620021: step: 700/469, loss: 0.00013446218508761376
2023-01-24 05:37:52.229747: step: 702/469, loss: 0.02992377057671547
2023-01-24 05:37:52.845432: step: 704/469, loss: 0.00042253901483491063
2023-01-24 05:37:53.512747: step: 706/469, loss: 0.0281726885586977
2023-01-24 05:37:54.157587: step: 708/469, loss: 0.0012305629206821322
2023-01-24 05:37:54.762953: step: 710/469, loss: 0.001158147701062262
2023-01-24 05:37:55.384339: step: 712/469, loss: 0.0007472842116840184
2023-01-24 05:37:56.003976: step: 714/469, loss: 0.013940438628196716
2023-01-24 05:37:56.614309: step: 716/469, loss: 0.0005880473181605339
2023-01-24 05:37:57.173028: step: 718/469, loss: 0.0005283617065288126
2023-01-24 05:37:57.743541: step: 720/469, loss: 0.06430403143167496
2023-01-24 05:37:58.319660: step: 722/469, loss: 0.005483551416546106
2023-01-24 05:37:58.987192: step: 724/469, loss: 0.0002046038134722039
2023-01-24 05:37:59.696967: step: 726/469, loss: 0.018971361219882965
2023-01-24 05:38:00.312244: step: 728/469, loss: 0.0009785378351807594
2023-01-24 05:38:00.929510: step: 730/469, loss: 0.0009495049598626792
2023-01-24 05:38:01.597697: step: 732/469, loss: 0.024526935070753098
2023-01-24 05:38:02.244218: step: 734/469, loss: 0.004857623018324375
2023-01-24 05:38:02.873251: step: 736/469, loss: 0.0015608284156769514
2023-01-24 05:38:03.513288: step: 738/469, loss: 0.01461784914135933
2023-01-24 05:38:04.131510: step: 740/469, loss: 0.02820703573524952
2023-01-24 05:38:04.734445: step: 742/469, loss: 0.0005968028563074768
2023-01-24 05:38:05.333979: step: 744/469, loss: 0.000444865960162133
2023-01-24 05:38:05.957203: step: 746/469, loss: 0.028595704585313797
2023-01-24 05:38:06.560922: step: 748/469, loss: 0.8248428702354431
2023-01-24 05:38:07.125249: step: 750/469, loss: 0.00023765770311001688
2023-01-24 05:38:07.735387: step: 752/469, loss: 0.0004923766828142107
2023-01-24 05:38:08.334511: step: 754/469, loss: 0.000211478240089491
2023-01-24 05:38:08.920997: step: 756/469, loss: 6.25285247224383e-05
2023-01-24 05:38:09.519392: step: 758/469, loss: 0.003036908805370331
2023-01-24 05:38:10.170357: step: 760/469, loss: 0.06792990118265152
2023-01-24 05:38:10.785486: step: 762/469, loss: 0.05790035054087639
2023-01-24 05:38:11.357561: step: 764/469, loss: 0.009418771602213383
2023-01-24 05:38:11.997215: step: 766/469, loss: 0.008413447998464108
2023-01-24 05:38:12.651930: step: 768/469, loss: 0.0005410366575233638
2023-01-24 05:38:13.271991: step: 770/469, loss: 0.003446622285991907
2023-01-24 05:38:13.928855: step: 772/469, loss: 0.0041089304722845554
2023-01-24 05:38:14.518250: step: 774/469, loss: 0.0015499526634812355
2023-01-24 05:38:15.170430: step: 776/469, loss: 0.003994627855718136
2023-01-24 05:38:15.805863: step: 778/469, loss: 0.007136105094105005
2023-01-24 05:38:16.419311: step: 780/469, loss: 0.038794975727796555
2023-01-24 05:38:17.015128: step: 782/469, loss: 7.773537618049886e-06
2023-01-24 05:38:17.554850: step: 784/469, loss: 0.02531854249536991
2023-01-24 05:38:18.125830: step: 786/469, loss: 0.014359182678163052
2023-01-24 05:38:18.700990: step: 788/469, loss: 0.002040768973529339
2023-01-24 05:38:19.350002: step: 790/469, loss: 0.003035011002793908
2023-01-24 05:38:19.918188: step: 792/469, loss: 8.428594446741045e-05
2023-01-24 05:38:20.523922: step: 794/469, loss: 0.0001258325792150572
2023-01-24 05:38:21.184316: step: 796/469, loss: 0.024884812533855438
2023-01-24 05:38:21.806359: step: 798/469, loss: 0.0002696172159630805
2023-01-24 05:38:22.461056: step: 800/469, loss: 0.0005056412192061543
2023-01-24 05:38:23.070200: step: 802/469, loss: 0.0027451585046947002
2023-01-24 05:38:23.692297: step: 804/469, loss: 0.003099893219769001
2023-01-24 05:38:24.304738: step: 806/469, loss: 0.0025701054837554693
2023-01-24 05:38:24.968636: step: 808/469, loss: 0.003196586621925235
2023-01-24 05:38:25.637352: step: 810/469, loss: 0.01178525947034359
2023-01-24 05:38:26.303895: step: 812/469, loss: 0.040642641484737396
2023-01-24 05:38:26.968509: step: 814/469, loss: 7.571535110473633
2023-01-24 05:38:27.560577: step: 816/469, loss: 0.005943898111581802
2023-01-24 05:38:28.205576: step: 818/469, loss: 0.022087549790740013
2023-01-24 05:38:28.813790: step: 820/469, loss: 0.01484906766563654
2023-01-24 05:38:29.447475: step: 822/469, loss: 0.070688396692276
2023-01-24 05:38:30.052812: step: 824/469, loss: 0.002011804608628154
2023-01-24 05:38:30.719449: step: 826/469, loss: 0.002348933834582567
2023-01-24 05:38:31.410530: step: 828/469, loss: 0.002215781481936574
2023-01-24 05:38:32.093887: step: 830/469, loss: 0.0008301714551635087
2023-01-24 05:38:32.643557: step: 832/469, loss: 0.0051965718157589436
2023-01-24 05:38:33.329559: step: 834/469, loss: 0.06248040497303009
2023-01-24 05:38:33.891582: step: 836/469, loss: 0.0007692843209952116
2023-01-24 05:38:34.497903: step: 838/469, loss: 0.0013292405055835843
2023-01-24 05:38:35.089033: step: 840/469, loss: 0.0032913689501583576
2023-01-24 05:38:35.673801: step: 842/469, loss: 0.0073381816036999226
2023-01-24 05:38:36.353247: step: 844/469, loss: 0.02456783689558506
2023-01-24 05:38:36.944391: step: 846/469, loss: 0.05738891288638115
2023-01-24 05:38:37.546764: step: 848/469, loss: 0.0019288643961772323
2023-01-24 05:38:38.181204: step: 850/469, loss: 0.003935445565730333
2023-01-24 05:38:38.820640: step: 852/469, loss: 0.014951786957681179
2023-01-24 05:38:39.413439: step: 854/469, loss: 0.0013995375484228134
2023-01-24 05:38:40.040358: step: 856/469, loss: 0.0019490347476676106
2023-01-24 05:38:40.627243: step: 858/469, loss: 0.02062826231122017
2023-01-24 05:38:41.222677: step: 860/469, loss: 0.0016663874266669154
2023-01-24 05:38:41.805205: step: 862/469, loss: 0.470892995595932
2023-01-24 05:38:42.435467: step: 864/469, loss: 0.004955326206982136
2023-01-24 05:38:42.992849: step: 866/469, loss: 0.0010713455267250538
2023-01-24 05:38:43.612181: step: 868/469, loss: 0.006135144736617804
2023-01-24 05:38:44.272814: step: 870/469, loss: 0.017733190208673477
2023-01-24 05:38:44.842783: step: 872/469, loss: 0.017774365842342377
2023-01-24 05:38:45.441359: step: 874/469, loss: 0.0013761044247075915
2023-01-24 05:38:45.976193: step: 876/469, loss: 0.00018988788360729814
2023-01-24 05:38:46.552245: step: 878/469, loss: 0.0005332918372005224
2023-01-24 05:38:47.187029: step: 880/469, loss: 0.10966512560844421
2023-01-24 05:38:47.790822: step: 882/469, loss: 0.009215809404850006
2023-01-24 05:38:48.401896: step: 884/469, loss: 0.021503997966647148
2023-01-24 05:38:49.037270: step: 886/469, loss: 0.03035183809697628
2023-01-24 05:38:49.644543: step: 888/469, loss: 0.0015832387143746018
2023-01-24 05:38:50.370067: step: 890/469, loss: 0.0521547831594944
2023-01-24 05:38:50.943112: step: 892/469, loss: 0.004446502309292555
2023-01-24 05:38:51.539649: step: 894/469, loss: 0.0028156894259154797
2023-01-24 05:38:52.162560: step: 896/469, loss: 0.007497936021536589
2023-01-24 05:38:52.807882: step: 898/469, loss: 0.013218437321484089
2023-01-24 05:38:53.419718: step: 900/469, loss: 0.026874646544456482
2023-01-24 05:38:54.105715: step: 902/469, loss: 0.01914488524198532
2023-01-24 05:38:54.717435: step: 904/469, loss: 0.00360128958709538
2023-01-24 05:38:55.471069: step: 906/469, loss: 0.011574283242225647
2023-01-24 05:38:56.087645: step: 908/469, loss: 0.0013154788175597787
2023-01-24 05:38:56.684056: step: 910/469, loss: 0.003331080311909318
2023-01-24 05:38:57.320101: step: 912/469, loss: 0.00806096289306879
2023-01-24 05:38:57.928631: step: 914/469, loss: 0.00961526483297348
2023-01-24 05:38:58.560803: step: 916/469, loss: 0.02750217728316784
2023-01-24 05:38:59.165194: step: 918/469, loss: 0.009093781001865864
2023-01-24 05:38:59.772704: step: 920/469, loss: 0.0008323579095304012
2023-01-24 05:39:00.412624: step: 922/469, loss: 0.0016904020449146628
2023-01-24 05:39:01.009754: step: 924/469, loss: 0.010574395768344402
2023-01-24 05:39:01.610850: step: 926/469, loss: 0.060014065355062485
2023-01-24 05:39:02.202936: step: 928/469, loss: 0.260230153799057
2023-01-24 05:39:02.818088: step: 930/469, loss: 0.010599013417959213
2023-01-24 05:39:03.468742: step: 932/469, loss: 0.17041371762752533
2023-01-24 05:39:04.045251: step: 934/469, loss: 0.0018142808694392443
2023-01-24 05:39:04.677242: step: 936/469, loss: 0.01914832927286625
2023-01-24 05:39:05.269638: step: 938/469, loss: 0.48395004868507385
==================================================
Loss: 0.041
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32835448038668896, 'r': 0.30467806624115923, 'f1': 0.3160735057265569}, 'combined': 0.23289626737746297, 'epoch': 37}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3305144661649764, 'r': 0.26670975220266163, 'f1': 0.2952038067417815}, 'combined': 0.1610202582227899, 'epoch': 37}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33953789900795445, 'r': 0.31183366815910807, 'f1': 0.32509662338249246}, 'combined': 0.2395448803870997, 'epoch': 37}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3341866897254541, 'r': 0.26967306526793283, 'f1': 0.2984837066712411}, 'combined': 0.16280929454794968, 'epoch': 37}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32999933151484145, 'r': 0.3030733898542377, 'f1': 0.3159637516383447}, 'combined': 0.23281539594404346, 'epoch': 37}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3253300631319278, 'r': 0.26531483687380053, 'f1': 0.2922733866969935}, 'combined': 0.15942184728926917, 'epoch': 37}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3919753086419753, 'r': 0.30238095238095236, 'f1': 0.3413978494623655}, 'combined': 0.22759856630824365, 'epoch': 37}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.31521739130434784, 'r': 0.31521739130434784, 'f1': 0.31521739130434784}, 'combined': 0.15760869565217392, 'epoch': 37}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.1724137931034483, 'f1': 0.25641025641025644}, 'combined': 0.17094017094017094, 'epoch': 37}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32293679254488683, 'r': 0.2990382443299901, 'f1': 0.3105283837673001}, 'combined': 0.2288103880390632, 'epoch': 36}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3313143781893782, 'r': 0.269173987037665, 'f1': 0.2970289427886601}, 'combined': 0.16201578697563276, 'epoch': 36}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'epoch': 36}
******************************
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
2023-01-24 05:41:51.358139: step: 2/469, loss: 0.00012753703049384058
2023-01-24 05:41:51.949047: step: 4/469, loss: 0.0003398454573471099
2023-01-24 05:41:52.608297: step: 6/469, loss: 0.0039046138990670443
2023-01-24 05:41:53.241834: step: 8/469, loss: 0.0031364429742097855
2023-01-24 05:41:53.834682: step: 10/469, loss: 0.0007567218272015452
2023-01-24 05:41:54.513340: step: 12/469, loss: 0.0025369087234139442
2023-01-24 05:41:55.138026: step: 14/469, loss: 0.016507478430867195
2023-01-24 05:41:55.682082: step: 16/469, loss: 0.051569197326898575
2023-01-24 05:41:56.300336: step: 18/469, loss: 0.0052370913326740265
2023-01-24 05:41:56.905666: step: 20/469, loss: 4.446284583536908e-05
2023-01-24 05:41:57.506797: step: 22/469, loss: 0.00018782868573907763
2023-01-24 05:41:58.200435: step: 24/469, loss: 0.0011781727662310004
2023-01-24 05:41:58.797942: step: 26/469, loss: 0.0026432471349835396
2023-01-24 05:41:59.357915: step: 28/469, loss: 0.00699997553601861
2023-01-24 05:41:59.977535: step: 30/469, loss: 0.011381281539797783
2023-01-24 05:42:00.584947: step: 32/469, loss: 0.00010784477490233257
2023-01-24 05:42:01.254824: step: 34/469, loss: 0.0006362306303344667
2023-01-24 05:42:01.903284: step: 36/469, loss: 0.05683068186044693
2023-01-24 05:42:02.542584: step: 38/469, loss: 0.5970094203948975
2023-01-24 05:42:03.158525: step: 40/469, loss: 0.01271666307002306
2023-01-24 05:42:03.801166: step: 42/469, loss: 0.012536873109638691
2023-01-24 05:42:04.406977: step: 44/469, loss: 0.5063958168029785
2023-01-24 05:42:05.042168: step: 46/469, loss: 0.011953196488320827
2023-01-24 05:42:05.609615: step: 48/469, loss: 0.010440017096698284
2023-01-24 05:42:06.253435: step: 50/469, loss: 0.0017809176351875067
2023-01-24 05:42:06.860004: step: 52/469, loss: 0.00205801404081285
2023-01-24 05:42:07.472841: step: 54/469, loss: 0.0007887992542237043
2023-01-24 05:42:08.090591: step: 56/469, loss: 0.0034836807753890753
2023-01-24 05:42:08.679592: step: 58/469, loss: 0.0007971806917339563
2023-01-24 05:42:09.369991: step: 60/469, loss: 0.004591221455484629
2023-01-24 05:42:09.960550: step: 62/469, loss: 0.008477076888084412
2023-01-24 05:42:10.560980: step: 64/469, loss: 0.03826672211289406
2023-01-24 05:42:11.191517: step: 66/469, loss: 0.06503720581531525
2023-01-24 05:42:11.781135: step: 68/469, loss: 0.003739919513463974
2023-01-24 05:42:12.473765: step: 70/469, loss: 0.0002656341530382633
2023-01-24 05:42:13.091650: step: 72/469, loss: 0.0011306344531476498
2023-01-24 05:42:13.719339: step: 74/469, loss: 0.006940985564142466
2023-01-24 05:42:14.256086: step: 76/469, loss: 0.00018072024977300316
2023-01-24 05:42:14.916896: step: 78/469, loss: 0.0032506794668734074
2023-01-24 05:42:15.533261: step: 80/469, loss: 0.02015191689133644
2023-01-24 05:42:16.168023: step: 82/469, loss: 0.30333465337753296
2023-01-24 05:42:16.831219: step: 84/469, loss: 0.03256223350763321
2023-01-24 05:42:17.414165: step: 86/469, loss: 0.000770751794334501
2023-01-24 05:42:18.097658: step: 88/469, loss: 0.00010630900214891881
2023-01-24 05:42:18.684279: step: 90/469, loss: 0.0025739348493516445
2023-01-24 05:42:19.217199: step: 92/469, loss: 0.0006421981379389763
2023-01-24 05:42:19.881252: step: 94/469, loss: 0.0023326845839619637
2023-01-24 05:42:20.565650: step: 96/469, loss: 0.0004707353364210576
2023-01-24 05:42:21.217332: step: 98/469, loss: 0.003543284721672535
2023-01-24 05:42:21.800483: step: 100/469, loss: 0.006560937501490116
2023-01-24 05:42:22.407061: step: 102/469, loss: 0.0035761953331530094
2023-01-24 05:42:22.990820: step: 104/469, loss: 0.005540677346289158
2023-01-24 05:42:23.728041: step: 106/469, loss: 0.015196459367871284
2023-01-24 05:42:24.325725: step: 108/469, loss: 0.003005946520715952
2023-01-24 05:42:24.940304: step: 110/469, loss: 0.0031792670488357544
2023-01-24 05:42:25.508465: step: 112/469, loss: 0.008570600301027298
2023-01-24 05:42:26.122598: step: 114/469, loss: 0.002000159118324518
2023-01-24 05:42:26.745619: step: 116/469, loss: 0.06860151886940002
2023-01-24 05:42:27.398043: step: 118/469, loss: 0.007608199026435614
2023-01-24 05:42:27.991203: step: 120/469, loss: 0.08729299902915955
2023-01-24 05:42:28.546320: step: 122/469, loss: 0.00823879987001419
2023-01-24 05:42:29.137911: step: 124/469, loss: 0.017600657418370247
2023-01-24 05:42:29.675792: step: 126/469, loss: 0.017034798860549927
2023-01-24 05:42:30.315486: step: 128/469, loss: 0.044462304562330246
2023-01-24 05:42:30.946147: step: 130/469, loss: 0.18946333229541779
2023-01-24 05:42:31.511416: step: 132/469, loss: 0.0031678848899900913
2023-01-24 05:42:32.056919: step: 134/469, loss: 0.0029597370885312557
2023-01-24 05:42:32.641466: step: 136/469, loss: 0.011893881484866142
2023-01-24 05:42:33.244111: step: 138/469, loss: 0.054351650178432465
2023-01-24 05:42:33.822643: step: 140/469, loss: 1.7306028894381598e-05
2023-01-24 05:42:34.500643: step: 142/469, loss: 0.04485905170440674
2023-01-24 05:42:35.132610: step: 144/469, loss: 0.002444647019729018
2023-01-24 05:42:35.750593: step: 146/469, loss: 4.622690200805664
2023-01-24 05:42:36.406450: step: 148/469, loss: 0.05602993816137314
2023-01-24 05:42:37.101021: step: 150/469, loss: 0.07476110756397247
2023-01-24 05:42:37.723972: step: 152/469, loss: 0.0045829168520867825
2023-01-24 05:42:38.295539: step: 154/469, loss: 0.016624649986624718
2023-01-24 05:42:38.955658: step: 156/469, loss: 0.007370179984718561
2023-01-24 05:42:39.622418: step: 158/469, loss: 0.01567571982741356
2023-01-24 05:42:40.293711: step: 160/469, loss: 0.0013074036687612534
2023-01-24 05:42:40.932791: step: 162/469, loss: 0.0014897125074639916
2023-01-24 05:42:41.542405: step: 164/469, loss: 0.006558215711265802
2023-01-24 05:42:42.125285: step: 166/469, loss: 0.0064345537684857845
2023-01-24 05:42:42.717798: step: 168/469, loss: 0.0007995741325430572
2023-01-24 05:42:43.383386: step: 170/469, loss: 0.014650707133114338
2023-01-24 05:42:44.084306: step: 172/469, loss: 0.04634474590420723
2023-01-24 05:42:44.781206: step: 174/469, loss: 0.0007460745400749147
2023-01-24 05:42:45.393053: step: 176/469, loss: 0.0076140668243169785
2023-01-24 05:42:46.008117: step: 178/469, loss: 3.6223441384208854e-06
2023-01-24 05:42:46.622766: step: 180/469, loss: 0.0013359755976125598
2023-01-24 05:42:47.268672: step: 182/469, loss: 0.0037875857669860125
2023-01-24 05:42:47.971851: step: 184/469, loss: 0.005390759091824293
2023-01-24 05:42:48.544669: step: 186/469, loss: 0.005834782030433416
2023-01-24 05:42:49.260353: step: 188/469, loss: 6.37365592410788e-05
2023-01-24 05:42:49.912847: step: 190/469, loss: 0.026993609964847565
2023-01-24 05:42:50.485082: step: 192/469, loss: 0.000593524076975882
2023-01-24 05:42:51.049458: step: 194/469, loss: 0.0006906589260324836
2023-01-24 05:42:51.720833: step: 196/469, loss: 0.0038057200144976377
2023-01-24 05:42:52.439802: step: 198/469, loss: 0.033612195402383804
2023-01-24 05:42:53.139916: step: 200/469, loss: 0.005429660901427269
2023-01-24 05:42:53.794478: step: 202/469, loss: 0.031010059639811516
2023-01-24 05:42:54.456981: step: 204/469, loss: 8.553740917705e-05
2023-01-24 05:42:55.097266: step: 206/469, loss: 0.009626995772123337
2023-01-24 05:42:55.756719: step: 208/469, loss: 0.05773867294192314
2023-01-24 05:42:56.344942: step: 210/469, loss: 0.003889423096552491
2023-01-24 05:42:56.979954: step: 212/469, loss: 0.03576301038265228
2023-01-24 05:42:57.634418: step: 214/469, loss: 0.008747031912207603
2023-01-24 05:42:58.313670: step: 216/469, loss: 0.00959421880543232
2023-01-24 05:42:58.966334: step: 218/469, loss: 0.0017345475498586893
2023-01-24 05:42:59.582963: step: 220/469, loss: 0.019519519060850143
2023-01-24 05:43:00.184720: step: 222/469, loss: 0.016517382115125656
2023-01-24 05:43:00.803317: step: 224/469, loss: 0.007057040464133024
2023-01-24 05:43:01.431642: step: 226/469, loss: 0.00028294912772253156
2023-01-24 05:43:02.142943: step: 228/469, loss: 0.0016824085032567382
2023-01-24 05:43:02.751432: step: 230/469, loss: 0.005338934250175953
2023-01-24 05:43:03.318629: step: 232/469, loss: 0.005753990728408098
2023-01-24 05:43:04.017470: step: 234/469, loss: 0.04637658968567848
2023-01-24 05:43:04.679103: step: 236/469, loss: 0.003527577966451645
2023-01-24 05:43:05.229096: step: 238/469, loss: 0.0018008939223363996
2023-01-24 05:43:05.840688: step: 240/469, loss: 0.0035127070732414722
2023-01-24 05:43:06.450891: step: 242/469, loss: 0.0016487244283780456
2023-01-24 05:43:07.036520: step: 244/469, loss: 0.0003422746667638421
2023-01-24 05:43:07.599951: step: 246/469, loss: 0.004949332680553198
2023-01-24 05:43:08.243144: step: 248/469, loss: 0.0001981878449441865
2023-01-24 05:43:08.881132: step: 250/469, loss: 0.024412959814071655
2023-01-24 05:43:09.512606: step: 252/469, loss: 0.009894313290715218
2023-01-24 05:43:10.056439: step: 254/469, loss: 0.005194500088691711
2023-01-24 05:43:10.702378: step: 256/469, loss: 0.0006939319428056479
2023-01-24 05:43:11.305761: step: 258/469, loss: 0.01006841380149126
2023-01-24 05:43:11.982306: step: 260/469, loss: 0.0022171945311129093
2023-01-24 05:43:12.593268: step: 262/469, loss: 0.0011323319049552083
2023-01-24 05:43:13.210124: step: 264/469, loss: 0.028261585161089897
2023-01-24 05:43:13.925832: step: 266/469, loss: 0.003775307908654213
2023-01-24 05:43:14.639802: step: 268/469, loss: 0.007662794087082148
2023-01-24 05:43:15.185282: step: 270/469, loss: 4.843069473281503e-05
2023-01-24 05:43:15.834202: step: 272/469, loss: 0.00922419410198927
2023-01-24 05:43:16.469532: step: 274/469, loss: 0.025499649345874786
2023-01-24 05:43:17.096354: step: 276/469, loss: 0.00046690506860613823
2023-01-24 05:43:17.762146: step: 278/469, loss: 0.015777206048369408
2023-01-24 05:43:18.345161: step: 280/469, loss: 0.00016869693354237825
2023-01-24 05:43:18.972923: step: 282/469, loss: 0.03249003365635872
2023-01-24 05:43:19.595621: step: 284/469, loss: 0.00014499310054816306
2023-01-24 05:43:20.205656: step: 286/469, loss: 9.50759495026432e-05
2023-01-24 05:43:20.905851: step: 288/469, loss: 0.01701691746711731
2023-01-24 05:43:21.563451: step: 290/469, loss: 0.012654634192585945
2023-01-24 05:43:22.133198: step: 292/469, loss: 0.0005531099741347134
2023-01-24 05:43:22.764594: step: 294/469, loss: 0.012154090218245983
2023-01-24 05:43:23.375954: step: 296/469, loss: 0.7882398366928101
2023-01-24 05:43:24.119853: step: 298/469, loss: 0.0001749203074723482
2023-01-24 05:43:24.751966: step: 300/469, loss: 0.017260221764445305
2023-01-24 05:43:25.413097: step: 302/469, loss: 0.002861148677766323
2023-01-24 05:43:26.050877: step: 304/469, loss: 0.012813948094844818
2023-01-24 05:43:26.744068: step: 306/469, loss: 0.03126691281795502
2023-01-24 05:43:27.415437: step: 308/469, loss: 0.0042886883020401
2023-01-24 05:43:28.015641: step: 310/469, loss: 0.0005286370287649333
2023-01-24 05:43:28.681899: step: 312/469, loss: 0.0025916260201483965
2023-01-24 05:43:29.383407: step: 314/469, loss: 0.00874342955648899
2023-01-24 05:43:29.995305: step: 316/469, loss: 0.001825582468882203
2023-01-24 05:43:30.662495: step: 318/469, loss: 0.0037278085947036743
2023-01-24 05:43:31.337987: step: 320/469, loss: 0.00016280909767374396
2023-01-24 05:43:31.934042: step: 322/469, loss: 0.04597877711057663
2023-01-24 05:43:32.534025: step: 324/469, loss: 0.0024294147733598948
2023-01-24 05:43:33.159915: step: 326/469, loss: 0.022655285894870758
2023-01-24 05:43:33.774097: step: 328/469, loss: 0.019259842112660408
2023-01-24 05:43:34.415977: step: 330/469, loss: 0.003929068800061941
2023-01-24 05:43:35.107375: step: 332/469, loss: 0.0030545189511030912
2023-01-24 05:43:35.702326: step: 334/469, loss: 0.03086966834962368
2023-01-24 05:43:36.360508: step: 336/469, loss: 0.010108484886586666
2023-01-24 05:43:36.971279: step: 338/469, loss: 0.004394331015646458
2023-01-24 05:43:37.538126: step: 340/469, loss: 0.0010387523798272014
2023-01-24 05:43:38.137549: step: 342/469, loss: 0.0018661613576114178
2023-01-24 05:43:38.742415: step: 344/469, loss: 0.00034492459963075817
2023-01-24 05:43:39.398953: step: 346/469, loss: 0.014092102646827698
2023-01-24 05:43:40.026146: step: 348/469, loss: 0.00043628690764307976
2023-01-24 05:43:40.685769: step: 350/469, loss: 0.04604126140475273
2023-01-24 05:43:41.370408: step: 352/469, loss: 0.016869962215423584
2023-01-24 05:43:42.011439: step: 354/469, loss: 0.00908180233091116
2023-01-24 05:43:42.601955: step: 356/469, loss: 0.008587555028498173
2023-01-24 05:43:43.181100: step: 358/469, loss: 0.00016373336256947368
2023-01-24 05:43:43.784765: step: 360/469, loss: 0.003951522056013346
2023-01-24 05:43:44.409778: step: 362/469, loss: 0.000977140269242227
2023-01-24 05:43:45.023475: step: 364/469, loss: 0.00026099587557837367
2023-01-24 05:43:45.585384: step: 366/469, loss: 0.01923340931534767
2023-01-24 05:43:46.201980: step: 368/469, loss: 0.28835055232048035
2023-01-24 05:43:46.819672: step: 370/469, loss: 0.0004068380512762815
2023-01-24 05:43:47.466246: step: 372/469, loss: 0.0068396651186048985
2023-01-24 05:43:48.120473: step: 374/469, loss: 0.03188212215900421
2023-01-24 05:43:48.744237: step: 376/469, loss: 0.011523513123393059
2023-01-24 05:43:49.347465: step: 378/469, loss: 0.0038248023483902216
2023-01-24 05:43:49.994107: step: 380/469, loss: 0.0013167018769308925
2023-01-24 05:43:50.650375: step: 382/469, loss: 0.004772607237100601
2023-01-24 05:43:51.329075: step: 384/469, loss: 0.0043232315219938755
2023-01-24 05:43:51.958763: step: 386/469, loss: 0.001649960526265204
2023-01-24 05:43:52.614296: step: 388/469, loss: 0.0001340229791821912
2023-01-24 05:43:53.265392: step: 390/469, loss: 0.0026363946963101625
2023-01-24 05:43:53.925006: step: 392/469, loss: 0.0008659258601255715
2023-01-24 05:43:54.572410: step: 394/469, loss: 0.0011113679502159357
2023-01-24 05:43:55.338814: step: 396/469, loss: 0.01586460880935192
2023-01-24 05:43:55.940737: step: 398/469, loss: 0.6813976168632507
2023-01-24 05:43:56.601181: step: 400/469, loss: 0.006336328107863665
2023-01-24 05:43:57.353385: step: 402/469, loss: 0.027061088010668755
2023-01-24 05:43:57.970243: step: 404/469, loss: 0.006307321134954691
2023-01-24 05:43:58.620082: step: 406/469, loss: 0.06695932894945145
2023-01-24 05:43:59.243208: step: 408/469, loss: 0.012269905768334866
2023-01-24 05:43:59.938699: step: 410/469, loss: 0.005150848068296909
2023-01-24 05:44:00.521623: step: 412/469, loss: 0.005380583461374044
2023-01-24 05:44:01.140059: step: 414/469, loss: 0.011634535156190395
2023-01-24 05:44:01.703032: step: 416/469, loss: 0.03634500131011009
2023-01-24 05:44:02.292071: step: 418/469, loss: 0.02824183739721775
2023-01-24 05:44:02.838870: step: 420/469, loss: 0.015918325632810593
2023-01-24 05:44:03.396261: step: 422/469, loss: 0.23165559768676758
2023-01-24 05:44:04.001514: step: 424/469, loss: 0.006573736201971769
2023-01-24 05:44:04.581679: step: 426/469, loss: 0.0016460868064314127
2023-01-24 05:44:05.217125: step: 428/469, loss: 0.20384475588798523
2023-01-24 05:44:05.860026: step: 430/469, loss: 0.0012258534552529454
2023-01-24 05:44:06.492502: step: 432/469, loss: 0.013706815429031849
2023-01-24 05:44:07.115217: step: 434/469, loss: 0.042897991836071014
2023-01-24 05:44:07.748789: step: 436/469, loss: 0.02255186066031456
2023-01-24 05:44:08.346678: step: 438/469, loss: 0.0777776837348938
2023-01-24 05:44:08.918628: step: 440/469, loss: 0.007089119870215654
2023-01-24 05:44:09.606141: step: 442/469, loss: 0.007612396962940693
2023-01-24 05:44:10.291351: step: 444/469, loss: 0.04386671259999275
2023-01-24 05:44:10.925757: step: 446/469, loss: 0.00020659025176428258
2023-01-24 05:44:11.532629: step: 448/469, loss: 0.000501752074342221
2023-01-24 05:44:12.159683: step: 450/469, loss: 0.003374500432983041
2023-01-24 05:44:12.794740: step: 452/469, loss: 0.08201678842306137
2023-01-24 05:44:13.435769: step: 454/469, loss: 0.01573663018643856
2023-01-24 05:44:14.059823: step: 456/469, loss: 0.00046490647946484387
2023-01-24 05:44:14.684565: step: 458/469, loss: 0.0004637721576727927
2023-01-24 05:44:15.353594: step: 460/469, loss: 0.07756218314170837
2023-01-24 05:44:15.955433: step: 462/469, loss: 0.002419006312265992
2023-01-24 05:44:16.496908: step: 464/469, loss: 1.2328708180575632e-05
2023-01-24 05:44:17.160548: step: 466/469, loss: 0.005360405892133713
2023-01-24 05:44:17.797212: step: 468/469, loss: 0.0007136064814403653
2023-01-24 05:44:18.393166: step: 470/469, loss: 0.0019342441810294986
2023-01-24 05:44:19.025691: step: 472/469, loss: 0.0008165700710378587
2023-01-24 05:44:19.678172: step: 474/469, loss: 0.002735595451667905
2023-01-24 05:44:20.332760: step: 476/469, loss: 0.023120015859603882
2023-01-24 05:44:20.953223: step: 478/469, loss: 0.00038176102680154145
2023-01-24 05:44:21.590863: step: 480/469, loss: 0.023487141355872154
2023-01-24 05:44:22.280545: step: 482/469, loss: 0.8848490715026855
2023-01-24 05:44:22.890839: step: 484/469, loss: 0.0044706896878778934
2023-01-24 05:44:23.447027: step: 486/469, loss: 0.014502924866974354
2023-01-24 05:44:24.013155: step: 488/469, loss: 0.007735269609838724
2023-01-24 05:44:24.594763: step: 490/469, loss: 0.01634342409670353
2023-01-24 05:44:25.303411: step: 492/469, loss: 0.004997485317289829
2023-01-24 05:44:25.916572: step: 494/469, loss: 0.2246975153684616
2023-01-24 05:44:26.538862: step: 496/469, loss: 0.014086057431995869
2023-01-24 05:44:27.158273: step: 498/469, loss: 0.00013090622087474912
2023-01-24 05:44:27.703614: step: 500/469, loss: 0.12599119544029236
2023-01-24 05:44:28.357427: step: 502/469, loss: 0.004129430279135704
2023-01-24 05:44:29.013664: step: 504/469, loss: 0.029582533985376358
2023-01-24 05:44:29.639314: step: 506/469, loss: 0.009352168999612331
2023-01-24 05:44:30.260076: step: 508/469, loss: 0.007790922187268734
2023-01-24 05:44:30.857678: step: 510/469, loss: 1.2287652492523193
2023-01-24 05:44:31.539302: step: 512/469, loss: 0.0032730766106396914
2023-01-24 05:44:32.182696: step: 514/469, loss: 0.0025268718600273132
2023-01-24 05:44:32.892782: step: 516/469, loss: 0.009384892880916595
2023-01-24 05:44:33.429014: step: 518/469, loss: 0.0007026235107332468
2023-01-24 05:44:34.021869: step: 520/469, loss: 0.0014882617397233844
2023-01-24 05:44:34.680062: step: 522/469, loss: 0.03958877548575401
2023-01-24 05:44:35.269563: step: 524/469, loss: 0.007507308851927519
2023-01-24 05:44:35.996320: step: 526/469, loss: 0.007090691011399031
2023-01-24 05:44:36.623162: step: 528/469, loss: 0.027186617255210876
2023-01-24 05:44:37.263594: step: 530/469, loss: 0.012380541302263737
2023-01-24 05:44:37.878991: step: 532/469, loss: 0.015014434233307838
2023-01-24 05:44:38.493785: step: 534/469, loss: 0.0004832313279621303
2023-01-24 05:44:39.131491: step: 536/469, loss: 0.012977574951946735
2023-01-24 05:44:39.774618: step: 538/469, loss: 0.01994369551539421
2023-01-24 05:44:40.348418: step: 540/469, loss: 0.0012370588956400752
2023-01-24 05:44:41.015534: step: 542/469, loss: 0.002112650079652667
2023-01-24 05:44:41.616244: step: 544/469, loss: 0.00645564217120409
2023-01-24 05:44:42.175924: step: 546/469, loss: 0.012297061271965504
2023-01-24 05:44:42.777517: step: 548/469, loss: 0.0006454386166296899
2023-01-24 05:44:43.398912: step: 550/469, loss: 0.0014267746591940522
2023-01-24 05:44:43.994906: step: 552/469, loss: 0.009479164145886898
2023-01-24 05:44:44.578009: step: 554/469, loss: 0.07529570907354355
2023-01-24 05:44:45.215388: step: 556/469, loss: 0.053799357265233994
2023-01-24 05:44:45.858893: step: 558/469, loss: 0.002171176951378584
2023-01-24 05:44:46.489670: step: 560/469, loss: 0.0010962956584990025
2023-01-24 05:44:47.127851: step: 562/469, loss: 0.012753731571137905
2023-01-24 05:44:47.722734: step: 564/469, loss: 0.08210617303848267
2023-01-24 05:44:48.316798: step: 566/469, loss: 0.07643083482980728
2023-01-24 05:44:49.074664: step: 568/469, loss: 0.0483868233859539
2023-01-24 05:44:49.660302: step: 570/469, loss: 2.3927494112285785e-05
2023-01-24 05:44:50.251198: step: 572/469, loss: 0.23457857966423035
2023-01-24 05:44:50.904951: step: 574/469, loss: 0.002064449479803443
2023-01-24 05:44:51.558612: step: 576/469, loss: 0.003332695923745632
2023-01-24 05:44:52.194626: step: 578/469, loss: 0.006315347272902727
2023-01-24 05:44:52.822312: step: 580/469, loss: 0.17449022829532623
2023-01-24 05:44:53.429325: step: 582/469, loss: 0.0014316319720819592
2023-01-24 05:44:54.057416: step: 584/469, loss: 0.1128283143043518
2023-01-24 05:44:54.680859: step: 586/469, loss: 0.011270860210061073
2023-01-24 05:44:55.294606: step: 588/469, loss: 1.1858852303703316e-05
2023-01-24 05:44:55.978482: step: 590/469, loss: 0.027867184951901436
2023-01-24 05:44:56.641539: step: 592/469, loss: 0.15390801429748535
2023-01-24 05:44:57.258171: step: 594/469, loss: 0.0001531842863187194
2023-01-24 05:44:57.860461: step: 596/469, loss: 0.0030719523783773184
2023-01-24 05:44:58.491384: step: 598/469, loss: 0.01468351949006319
2023-01-24 05:44:59.052281: step: 600/469, loss: 0.002717547584325075
2023-01-24 05:44:59.650592: step: 602/469, loss: 0.0015363650163635612
2023-01-24 05:45:00.292664: step: 604/469, loss: 0.06810019165277481
2023-01-24 05:45:01.032714: step: 606/469, loss: 0.007474309764802456
2023-01-24 05:45:01.646327: step: 608/469, loss: 0.010088734328746796
2023-01-24 05:45:02.260548: step: 610/469, loss: 0.05422927066683769
2023-01-24 05:45:02.902910: step: 612/469, loss: 0.011467122472822666
2023-01-24 05:45:03.536131: step: 614/469, loss: 0.040612462908029556
2023-01-24 05:45:04.139335: step: 616/469, loss: 0.000156102076289244
2023-01-24 05:45:04.768541: step: 618/469, loss: 0.024036496877670288
2023-01-24 05:45:05.448430: step: 620/469, loss: 0.06760215014219284
2023-01-24 05:45:06.042080: step: 622/469, loss: 0.052559491246938705
2023-01-24 05:45:06.650092: step: 624/469, loss: 0.002878944156691432
2023-01-24 05:45:07.276746: step: 626/469, loss: 0.030936047434806824
2023-01-24 05:45:07.780023: step: 628/469, loss: 0.04616130515933037
2023-01-24 05:45:08.410192: step: 630/469, loss: 0.0014087165473029017
2023-01-24 05:45:09.068548: step: 632/469, loss: 0.0077975899912416935
2023-01-24 05:45:09.691637: step: 634/469, loss: 0.023471761494874954
2023-01-24 05:45:10.300657: step: 636/469, loss: 0.00047905463725328445
2023-01-24 05:45:10.898747: step: 638/469, loss: 0.00016119459178298712
2023-01-24 05:45:11.602439: step: 640/469, loss: 0.003902548924088478
2023-01-24 05:45:12.195270: step: 642/469, loss: 0.001081079593859613
2023-01-24 05:45:12.797277: step: 644/469, loss: 0.009610828012228012
2023-01-24 05:45:13.563596: step: 646/469, loss: 0.005661234725266695
2023-01-24 05:45:14.226600: step: 648/469, loss: 0.0032922604586929083
2023-01-24 05:45:14.894863: step: 650/469, loss: 0.018884431570768356
2023-01-24 05:45:15.568255: step: 652/469, loss: 0.023012464866042137
2023-01-24 05:45:16.208954: step: 654/469, loss: 0.03778444975614548
2023-01-24 05:45:16.887490: step: 656/469, loss: 0.33450689911842346
2023-01-24 05:45:17.546397: step: 658/469, loss: 0.0032547968439757824
2023-01-24 05:45:18.096239: step: 660/469, loss: 0.002117619151249528
2023-01-24 05:45:18.766761: step: 662/469, loss: 0.015873834490776062
2023-01-24 05:45:19.467506: step: 664/469, loss: 0.001754995551891625
2023-01-24 05:45:20.027582: step: 666/469, loss: 0.0003140690387226641
2023-01-24 05:45:20.667260: step: 668/469, loss: 0.00021501169248949736
2023-01-24 05:45:21.324674: step: 670/469, loss: 0.07802244275808334
2023-01-24 05:45:21.950025: step: 672/469, loss: 0.017197560518980026
2023-01-24 05:45:22.632073: step: 674/469, loss: 0.004624032415449619
2023-01-24 05:45:23.287457: step: 676/469, loss: 0.001015166286379099
2023-01-24 05:45:23.948653: step: 678/469, loss: 0.0028869023080915213
2023-01-24 05:45:24.499329: step: 680/469, loss: 0.0017006745329126716
2023-01-24 05:45:25.108652: step: 682/469, loss: 0.014343960210680962
2023-01-24 05:45:25.764134: step: 684/469, loss: 0.05828974395990372
2023-01-24 05:45:26.367750: step: 686/469, loss: 0.0001194150245282799
2023-01-24 05:45:26.956122: step: 688/469, loss: 4.410809924593195e-05
2023-01-24 05:45:27.565856: step: 690/469, loss: 0.0006212394800968468
2023-01-24 05:45:28.135060: step: 692/469, loss: 0.0012261979281902313
2023-01-24 05:45:28.771884: step: 694/469, loss: 0.005106035619974136
2023-01-24 05:45:29.423531: step: 696/469, loss: 0.024821607396006584
2023-01-24 05:45:30.050531: step: 698/469, loss: 0.2126006931066513
2023-01-24 05:45:30.685755: step: 700/469, loss: 0.0022250772453844547
2023-01-24 05:45:31.310779: step: 702/469, loss: 0.00044866380630992353
2023-01-24 05:45:31.994875: step: 704/469, loss: 0.027074845507740974
2023-01-24 05:45:32.632319: step: 706/469, loss: 0.04755845293402672
2023-01-24 05:45:33.241221: step: 708/469, loss: 0.018422473222017288
2023-01-24 05:45:33.878913: step: 710/469, loss: 0.00020046424469910562
2023-01-24 05:45:34.510545: step: 712/469, loss: 0.00556178530678153
2023-01-24 05:45:35.269546: step: 714/469, loss: 0.013901887461543083
2023-01-24 05:45:35.813815: step: 716/469, loss: 0.010391877964138985
2023-01-24 05:45:36.453105: step: 718/469, loss: 0.007928375154733658
2023-01-24 05:45:37.099717: step: 720/469, loss: 0.010893300175666809
2023-01-24 05:45:37.735312: step: 722/469, loss: 0.008237047120928764
2023-01-24 05:45:38.314345: step: 724/469, loss: 0.0003001186123583466
2023-01-24 05:45:38.976846: step: 726/469, loss: 0.4318578243255615
2023-01-24 05:45:39.517305: step: 728/469, loss: 0.00014769600238651037
2023-01-24 05:45:40.117540: step: 730/469, loss: 0.07802700996398926
2023-01-24 05:45:40.657022: step: 732/469, loss: 0.000807570933829993
2023-01-24 05:45:41.270414: step: 734/469, loss: 0.0030142159666866064
2023-01-24 05:45:41.814400: step: 736/469, loss: 0.0005414392799139023
2023-01-24 05:45:42.432034: step: 738/469, loss: 0.018303856253623962
2023-01-24 05:45:43.077382: step: 740/469, loss: 0.11187437921762466
2023-01-24 05:45:43.673134: step: 742/469, loss: 0.007149531971663237
2023-01-24 05:45:44.264392: step: 744/469, loss: 0.003846829291433096
2023-01-24 05:45:44.798064: step: 746/469, loss: 0.004802349954843521
2023-01-24 05:45:45.376584: step: 748/469, loss: 0.001068518846295774
2023-01-24 05:45:46.024991: step: 750/469, loss: 0.0032422940712422132
2023-01-24 05:45:46.672732: step: 752/469, loss: 0.0010948532726615667
2023-01-24 05:45:47.346983: step: 754/469, loss: 0.0011246935464441776
2023-01-24 05:45:47.996617: step: 756/469, loss: 0.0019724294543266296
2023-01-24 05:45:48.578713: step: 758/469, loss: 0.006466195918619633
2023-01-24 05:45:49.198760: step: 760/469, loss: 0.03887542709708214
2023-01-24 05:45:49.894902: step: 762/469, loss: 0.004948553163558245
2023-01-24 05:45:50.622622: step: 764/469, loss: 0.004445853643119335
2023-01-24 05:45:51.215609: step: 766/469, loss: 0.01145121268928051
2023-01-24 05:45:51.808791: step: 768/469, loss: 0.009653294458985329
2023-01-24 05:45:52.380991: step: 770/469, loss: 0.0009770940523594618
2023-01-24 05:45:53.016612: step: 772/469, loss: 0.03544906899333
2023-01-24 05:45:53.627709: step: 774/469, loss: 0.00742124579846859
2023-01-24 05:45:54.276955: step: 776/469, loss: 0.016965607181191444
2023-01-24 05:45:54.814099: step: 778/469, loss: 0.012413175776600838
2023-01-24 05:45:55.598460: step: 780/469, loss: 0.000973120448179543
2023-01-24 05:45:56.261567: step: 782/469, loss: 0.00030484615126624703
2023-01-24 05:45:56.918145: step: 784/469, loss: 0.015686696395277977
2023-01-24 05:45:57.487307: step: 786/469, loss: 0.0005647270008921623
2023-01-24 05:45:58.140781: step: 788/469, loss: 3.056981222471222e-05
2023-01-24 05:45:58.783588: step: 790/469, loss: 0.05142643675208092
2023-01-24 05:45:59.454817: step: 792/469, loss: 0.0009963170159608126
2023-01-24 05:46:00.044873: step: 794/469, loss: 0.01668229140341282
2023-01-24 05:46:00.767305: step: 796/469, loss: 0.6107051968574524
2023-01-24 05:46:01.396122: step: 798/469, loss: 0.02283414453268051
2023-01-24 05:46:02.011916: step: 800/469, loss: 0.0021810675971210003
2023-01-24 05:46:02.687233: step: 802/469, loss: 0.024435829371213913
2023-01-24 05:46:03.242971: step: 804/469, loss: 0.27842965722084045
2023-01-24 05:46:03.882865: step: 806/469, loss: 0.007593396585434675
2023-01-24 05:46:04.478327: step: 808/469, loss: 0.00018909874779637903
2023-01-24 05:46:05.107130: step: 810/469, loss: 0.0016665005823597312
2023-01-24 05:46:05.774172: step: 812/469, loss: 0.009211063385009766
2023-01-24 05:46:06.472509: step: 814/469, loss: 0.004168577026575804
2023-01-24 05:46:07.070210: step: 816/469, loss: 0.044412530958652496
2023-01-24 05:46:07.792723: step: 818/469, loss: 2.7484076023101807
2023-01-24 05:46:08.372821: step: 820/469, loss: 0.059764403849840164
2023-01-24 05:46:09.014371: step: 822/469, loss: 0.0003559777105692774
2023-01-24 05:46:09.674743: step: 824/469, loss: 0.0015374531503766775
2023-01-24 05:46:10.381496: step: 826/469, loss: 0.02299226075410843
2023-01-24 05:46:11.066110: step: 828/469, loss: 0.001887224498204887
2023-01-24 05:46:11.717448: step: 830/469, loss: 0.001413281774148345
2023-01-24 05:46:12.282895: step: 832/469, loss: 0.01570207253098488
2023-01-24 05:46:12.931217: step: 834/469, loss: 0.0008477639057673514
2023-01-24 05:46:13.527175: step: 836/469, loss: 0.018604883924126625
2023-01-24 05:46:14.126095: step: 838/469, loss: 0.02100706286728382
2023-01-24 05:46:14.752825: step: 840/469, loss: 0.0008020714740268886
2023-01-24 05:46:15.375783: step: 842/469, loss: 0.21190530061721802
2023-01-24 05:46:16.023899: step: 844/469, loss: 0.00027793191839009523
2023-01-24 05:46:16.582426: step: 846/469, loss: 0.0073113772086799145
2023-01-24 05:46:17.176849: step: 848/469, loss: 0.002676371717825532
2023-01-24 05:46:17.829466: step: 850/469, loss: 0.004364520311355591
2023-01-24 05:46:18.426987: step: 852/469, loss: 0.041826117783784866
2023-01-24 05:46:19.031418: step: 854/469, loss: 0.025660106912255287
2023-01-24 05:46:19.627867: step: 856/469, loss: 0.0005329117411747575
2023-01-24 05:46:20.290270: step: 858/469, loss: 0.01842450723052025
2023-01-24 05:46:20.919278: step: 860/469, loss: 0.11757441610097885
2023-01-24 05:46:21.492157: step: 862/469, loss: 0.04275765269994736
2023-01-24 05:46:22.083905: step: 864/469, loss: 0.010624093934893608
2023-01-24 05:46:22.668085: step: 866/469, loss: 0.01629812642931938
2023-01-24 05:46:23.248890: step: 868/469, loss: 0.19480657577514648
2023-01-24 05:46:23.842856: step: 870/469, loss: 0.19016137719154358
2023-01-24 05:46:24.502977: step: 872/469, loss: 0.0025323720183223486
2023-01-24 05:46:25.124482: step: 874/469, loss: 0.007500536274164915
2023-01-24 05:46:25.716405: step: 876/469, loss: 0.04277237877249718
2023-01-24 05:46:26.330993: step: 878/469, loss: 0.0017568464390933514
2023-01-24 05:46:26.956702: step: 880/469, loss: 0.002035855781286955
2023-01-24 05:46:27.564941: step: 882/469, loss: 0.0010857965098693967
2023-01-24 05:46:28.140410: step: 884/469, loss: 0.020509520545601845
2023-01-24 05:46:28.755014: step: 886/469, loss: 0.01151403971016407
2023-01-24 05:46:29.378917: step: 888/469, loss: 0.006275097373872995
2023-01-24 05:46:30.014269: step: 890/469, loss: 0.0022157912608236074
2023-01-24 05:46:30.573592: step: 892/469, loss: 0.003706187242642045
2023-01-24 05:46:31.163812: step: 894/469, loss: 0.01411911379545927
2023-01-24 05:46:31.774956: step: 896/469, loss: 0.01766563020646572
2023-01-24 05:46:32.381647: step: 898/469, loss: 0.00021050726354587823
2023-01-24 05:46:32.981354: step: 900/469, loss: 0.0180773064494133
2023-01-24 05:46:33.690892: step: 902/469, loss: 0.005115542560815811
2023-01-24 05:46:34.264106: step: 904/469, loss: 0.0007388739613816142
2023-01-24 05:46:34.881815: step: 906/469, loss: 0.00018669040582608432
2023-01-24 05:46:35.551707: step: 908/469, loss: 0.0010879577603191137
2023-01-24 05:46:36.213052: step: 910/469, loss: 0.014332884922623634
2023-01-24 05:46:36.841683: step: 912/469, loss: 0.0029448089189827442
2023-01-24 05:46:37.470520: step: 914/469, loss: 0.0010465006344020367
2023-01-24 05:46:38.072565: step: 916/469, loss: 0.004090795759111643
2023-01-24 05:46:38.636688: step: 918/469, loss: 0.11881612241268158
2023-01-24 05:46:39.307313: step: 920/469, loss: 0.35682061314582825
2023-01-24 05:46:39.945125: step: 922/469, loss: 0.056122783571481705
2023-01-24 05:46:40.590805: step: 924/469, loss: 0.0008888035663403571
2023-01-24 05:46:41.150240: step: 926/469, loss: 0.004167707171291113
2023-01-24 05:46:41.771220: step: 928/469, loss: 0.0038449056446552277
2023-01-24 05:46:42.411630: step: 930/469, loss: 0.0010881380876526237
2023-01-24 05:46:43.069121: step: 932/469, loss: 0.01623956300318241
2023-01-24 05:46:43.733203: step: 934/469, loss: 0.019334888085722923
2023-01-24 05:46:44.320548: step: 936/469, loss: 0.0003507888759486377
2023-01-24 05:46:44.893165: step: 938/469, loss: 0.0006681834347546101
==================================================
Loss: 0.049
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33730606967882415, 'r': 0.32066478350871136, 'f1': 0.32877498231340646}, 'combined': 0.2422552501256679, 'epoch': 38}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33417656738630247, 'r': 0.26783044193083344, 'f1': 0.2973475602137135}, 'combined': 0.16218957829838918, 'epoch': 38}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34305568413256804, 'r': 0.3196211402449543, 'f1': 0.33092404893731026}, 'combined': 0.24383877290117598, 'epoch': 38}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33732284927324807, 'r': 0.273129662952264, 'f1': 0.30185108352560625}, 'combined': 0.16464604555942158, 'epoch': 38}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3308171543368912, 'r': 0.3101018486573515, 'f1': 0.32012472917223167}, 'combined': 0.23588137939006543, 'epoch': 38}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3327536501331047, 'r': 0.2713689585103767, 'f1': 0.29894266556223587}, 'combined': 0.16305963576121954, 'epoch': 38}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.34244791666666663, 'r': 0.31309523809523804, 'f1': 0.3271144278606965}, 'combined': 0.21807628524046432, 'epoch': 38}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.27380952380952384, 'r': 0.25, 'f1': 0.26136363636363635}, 'combined': 0.13068181818181818, 'epoch': 38}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'epoch': 38}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3308171543368912, 'r': 0.3101018486573515, 'f1': 0.32012472917223167}, 'combined': 0.23588137939006543, 'epoch': 38}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3327536501331047, 'r': 0.2713689585103767, 'f1': 0.29894266556223587}, 'combined': 0.16305963576121954, 'epoch': 38}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'epoch': 38}
******************************
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
2023-01-24 05:49:39.917447: step: 2/469, loss: 0.0030119754374027252
2023-01-24 05:49:40.453402: step: 4/469, loss: 0.002477311994880438
2023-01-24 05:49:41.002849: step: 6/469, loss: 0.013294542208313942
2023-01-24 05:49:41.618777: step: 8/469, loss: 0.000540114298928529
2023-01-24 05:49:42.201402: step: 10/469, loss: 0.0003245100087951869
2023-01-24 05:49:42.857999: step: 12/469, loss: 0.0332648903131485
2023-01-24 05:49:43.522827: step: 14/469, loss: 0.0003781408304348588
2023-01-24 05:49:44.185449: step: 16/469, loss: 0.011412395164370537
2023-01-24 05:49:44.807638: step: 18/469, loss: 0.07069984078407288
2023-01-24 05:49:45.445636: step: 20/469, loss: 0.017332054674625397
2023-01-24 05:49:46.080611: step: 22/469, loss: 0.001704319496639073
2023-01-24 05:49:46.694564: step: 24/469, loss: 0.004425748251378536
2023-01-24 05:49:47.296120: step: 26/469, loss: 0.0450458750128746
2023-01-24 05:49:47.884697: step: 28/469, loss: 0.003014008281752467
2023-01-24 05:49:48.469013: step: 30/469, loss: 0.008909519761800766
2023-01-24 05:49:49.084046: step: 32/469, loss: 0.014741238206624985
2023-01-24 05:49:49.716573: step: 34/469, loss: 0.005667850840836763
2023-01-24 05:49:50.356493: step: 36/469, loss: 0.02003190480172634
2023-01-24 05:49:50.985023: step: 38/469, loss: 0.03284147009253502
2023-01-24 05:49:51.572798: step: 40/469, loss: 0.000386177736800164
2023-01-24 05:49:52.209562: step: 42/469, loss: 0.00019314800738357008
2023-01-24 05:49:52.856804: step: 44/469, loss: 0.0005215840646997094
2023-01-24 05:49:53.558912: step: 46/469, loss: 0.0014168774941936135
2023-01-24 05:49:54.204481: step: 48/469, loss: 0.0005476261139847338
2023-01-24 05:49:54.805847: step: 50/469, loss: 0.04120873659849167
2023-01-24 05:49:55.416505: step: 52/469, loss: 0.00021077453857287765
2023-01-24 05:49:56.052265: step: 54/469, loss: 0.06059630587697029
2023-01-24 05:49:56.787302: step: 56/469, loss: 0.0011616606498137116
2023-01-24 05:49:57.408671: step: 58/469, loss: 0.027168288826942444
2023-01-24 05:49:58.107930: step: 60/469, loss: 0.010715505108237267
2023-01-24 05:49:58.737591: step: 62/469, loss: 0.006376428063958883
2023-01-24 05:49:59.290275: step: 64/469, loss: 0.006124431733042002
2023-01-24 05:49:59.876696: step: 66/469, loss: 0.020459473133087158
2023-01-24 05:50:00.491094: step: 68/469, loss: 0.0039391596801579
2023-01-24 05:50:01.138260: step: 70/469, loss: 0.08821238577365875
2023-01-24 05:50:01.797787: step: 72/469, loss: 0.010975842364132404
2023-01-24 05:50:02.368317: step: 74/469, loss: 0.00035055732587352395
2023-01-24 05:50:03.054122: step: 76/469, loss: 0.006269215140491724
2023-01-24 05:50:03.708217: step: 78/469, loss: 0.09885379672050476
2023-01-24 05:50:04.357504: step: 80/469, loss: 0.0010260924464091659
2023-01-24 05:50:05.016632: step: 82/469, loss: 0.0006054006516933441
2023-01-24 05:50:05.557814: step: 84/469, loss: 0.02720540389418602
2023-01-24 05:50:06.126355: step: 86/469, loss: 0.014896119013428688
2023-01-24 05:50:06.703572: step: 88/469, loss: 0.011236756108701229
2023-01-24 05:50:07.339997: step: 90/469, loss: 0.0060309115797281265
2023-01-24 05:50:07.920218: step: 92/469, loss: 0.006958479061722755
2023-01-24 05:50:08.551917: step: 94/469, loss: 0.0016738763079047203
2023-01-24 05:50:09.134629: step: 96/469, loss: 0.05706104636192322
2023-01-24 05:50:09.707044: step: 98/469, loss: 0.0050797052681446075
2023-01-24 05:50:10.282900: step: 100/469, loss: 0.00014971641940064728
2023-01-24 05:50:10.903902: step: 102/469, loss: 0.028395086526870728
2023-01-24 05:50:11.678923: step: 104/469, loss: 0.009888138622045517
2023-01-24 05:50:12.293561: step: 106/469, loss: 0.00012206560495542362
2023-01-24 05:50:12.965518: step: 108/469, loss: 0.0033363548573106527
2023-01-24 05:50:13.618935: step: 110/469, loss: 0.03384239599108696
2023-01-24 05:50:14.195165: step: 112/469, loss: 0.0065839351154863834
2023-01-24 05:50:14.801871: step: 114/469, loss: 0.0011425679549574852
2023-01-24 05:50:15.407885: step: 116/469, loss: 0.003612453117966652
2023-01-24 05:50:16.024231: step: 118/469, loss: 0.49945658445358276
2023-01-24 05:50:16.613886: step: 120/469, loss: 0.0940798670053482
2023-01-24 05:50:17.245898: step: 122/469, loss: 0.0006863982416689396
2023-01-24 05:50:17.847956: step: 124/469, loss: 0.0466776005923748
2023-01-24 05:50:18.474161: step: 126/469, loss: 0.004530573263764381
2023-01-24 05:50:19.039949: step: 128/469, loss: 0.030442632734775543
2023-01-24 05:50:19.640222: step: 130/469, loss: 0.0047458927147090435
2023-01-24 05:50:20.294021: step: 132/469, loss: 0.010832609608769417
2023-01-24 05:50:20.932863: step: 134/469, loss: 0.015890762209892273
2023-01-24 05:50:21.654633: step: 136/469, loss: 0.005582538899034262
2023-01-24 05:50:22.266575: step: 138/469, loss: 0.0020973137579858303
2023-01-24 05:50:22.831233: step: 140/469, loss: 0.023380955681204796
2023-01-24 05:50:23.524243: step: 142/469, loss: 0.01180985663086176
2023-01-24 05:50:24.172375: step: 144/469, loss: 0.0029723222833126783
2023-01-24 05:50:24.836804: step: 146/469, loss: 0.017057470977306366
2023-01-24 05:50:25.450525: step: 148/469, loss: 0.0005902117700316012
2023-01-24 05:50:26.135334: step: 150/469, loss: 0.0032326197251677513
2023-01-24 05:50:26.753013: step: 152/469, loss: 0.07234001904726028
2023-01-24 05:50:27.353027: step: 154/469, loss: 0.002089154440909624
2023-01-24 05:50:27.985894: step: 156/469, loss: 0.0006694797775708139
2023-01-24 05:50:28.663536: step: 158/469, loss: 6.99316369718872e-05
2023-01-24 05:50:29.299524: step: 160/469, loss: 0.00043517854646779597
2023-01-24 05:50:29.918116: step: 162/469, loss: 0.03860674053430557
2023-01-24 05:50:30.531319: step: 164/469, loss: 0.0001615319197298959
2023-01-24 05:50:31.216046: step: 166/469, loss: 0.17923331260681152
2023-01-24 05:50:31.818004: step: 168/469, loss: 0.011622265912592411
2023-01-24 05:50:32.412560: step: 170/469, loss: 0.006952633615583181
2023-01-24 05:50:33.047130: step: 172/469, loss: 0.039613474160432816
2023-01-24 05:50:33.684176: step: 174/469, loss: 0.03972364589571953
2023-01-24 05:50:34.230815: step: 176/469, loss: 0.0008014689665287733
2023-01-24 05:50:34.876109: step: 178/469, loss: 0.03004515916109085
2023-01-24 05:50:35.483021: step: 180/469, loss: 0.013035529293119907
2023-01-24 05:50:36.179994: step: 182/469, loss: 0.011972688138484955
2023-01-24 05:50:36.970076: step: 184/469, loss: 0.009005329571664333
2023-01-24 05:50:37.579137: step: 186/469, loss: 0.0024666080716997385
2023-01-24 05:50:38.170058: step: 188/469, loss: 8.075930963968858e-05
2023-01-24 05:50:38.848626: step: 190/469, loss: 0.0006661887746304274
2023-01-24 05:50:39.510153: step: 192/469, loss: 0.023676201701164246
2023-01-24 05:50:40.221143: step: 194/469, loss: 0.004343714565038681
2023-01-24 05:50:40.883763: step: 196/469, loss: 0.006186078302562237
2023-01-24 05:50:41.536171: step: 198/469, loss: 0.00859355740249157
2023-01-24 05:50:42.206276: step: 200/469, loss: 0.0005010629538446665
2023-01-24 05:50:42.861840: step: 202/469, loss: 0.007475322112441063
2023-01-24 05:50:43.497174: step: 204/469, loss: 0.004866512026637793
2023-01-24 05:50:44.069867: step: 206/469, loss: 0.001928465673699975
2023-01-24 05:50:44.705229: step: 208/469, loss: 0.007554308976978064
2023-01-24 05:50:45.317218: step: 210/469, loss: 0.02795448526740074
2023-01-24 05:50:45.948750: step: 212/469, loss: 0.019564524292945862
2023-01-24 05:50:46.545533: step: 214/469, loss: 0.003723745234310627
2023-01-24 05:50:47.162506: step: 216/469, loss: 0.016949478536844254
2023-01-24 05:50:47.780101: step: 218/469, loss: 0.0032471558079123497
2023-01-24 05:50:48.383563: step: 220/469, loss: 0.010439512319862843
2023-01-24 05:50:49.052956: step: 222/469, loss: 0.0035251828376203775
2023-01-24 05:50:49.666287: step: 224/469, loss: 0.011053825728595257
2023-01-24 05:50:50.338130: step: 226/469, loss: 0.0009576024021953344
2023-01-24 05:50:50.984238: step: 228/469, loss: 0.056902024894952774
2023-01-24 05:50:51.668452: step: 230/469, loss: 0.002920982427895069
2023-01-24 05:50:52.249717: step: 232/469, loss: 0.6969336271286011
2023-01-24 05:50:52.915697: step: 234/469, loss: 0.008771332912147045
2023-01-24 05:50:53.565545: step: 236/469, loss: 0.0016970186261460185
2023-01-24 05:50:54.155264: step: 238/469, loss: 0.0005713562131859362
2023-01-24 05:50:54.735075: step: 240/469, loss: 0.005612066015601158
2023-01-24 05:50:55.381279: step: 242/469, loss: 0.001563920290209353
2023-01-24 05:50:56.017721: step: 244/469, loss: 0.02681146189570427
2023-01-24 05:50:56.642164: step: 246/469, loss: 3.165794987580739e-05
2023-01-24 05:50:57.203637: step: 248/469, loss: 0.0004317841667216271
2023-01-24 05:50:57.829249: step: 250/469, loss: 0.00024566068896092474
2023-01-24 05:50:58.502003: step: 252/469, loss: 0.051570042967796326
2023-01-24 05:50:59.071005: step: 254/469, loss: 2.16726530197775e-05
2023-01-24 05:50:59.717398: step: 256/469, loss: 0.00011379853822290897
2023-01-24 05:51:00.353860: step: 258/469, loss: 0.0030371742323040962
2023-01-24 05:51:00.986276: step: 260/469, loss: 0.0005059054819867015
2023-01-24 05:51:01.657154: step: 262/469, loss: 0.0034952748101204634
2023-01-24 05:51:02.244268: step: 264/469, loss: 0.0011962997959926724
2023-01-24 05:51:02.831826: step: 266/469, loss: 9.325591963715851e-05
2023-01-24 05:51:03.411208: step: 268/469, loss: 0.0006678030476905406
2023-01-24 05:51:04.087491: step: 270/469, loss: 0.0006335260113701224
2023-01-24 05:51:04.642121: step: 272/469, loss: 0.002706658560782671
2023-01-24 05:51:05.234669: step: 274/469, loss: 0.008834761567413807
2023-01-24 05:51:05.843451: step: 276/469, loss: 0.003155779791995883
2023-01-24 05:51:06.484054: step: 278/469, loss: 0.002005981747061014
2023-01-24 05:51:07.060820: step: 280/469, loss: 0.9146357774734497
2023-01-24 05:51:07.753697: step: 282/469, loss: 0.03377266228199005
2023-01-24 05:51:08.314820: step: 284/469, loss: 0.008990660309791565
2023-01-24 05:51:08.945995: step: 286/469, loss: 0.02674446813762188
2023-01-24 05:51:09.584550: step: 288/469, loss: 0.00018079759320244193
2023-01-24 05:51:10.188551: step: 290/469, loss: 0.0032577719539403915
2023-01-24 05:51:10.836711: step: 292/469, loss: 0.00022912300482857972
2023-01-24 05:51:11.506622: step: 294/469, loss: 0.04188700392842293
2023-01-24 05:51:12.054784: step: 296/469, loss: 0.0006541315233334899
2023-01-24 05:51:12.744470: step: 298/469, loss: 0.00455709733068943
2023-01-24 05:51:13.484356: step: 300/469, loss: 0.04880499839782715
2023-01-24 05:51:14.096682: step: 302/469, loss: 0.016444897279143333
2023-01-24 05:51:14.738390: step: 304/469, loss: 0.021372556686401367
2023-01-24 05:51:15.368545: step: 306/469, loss: 0.00823103729635477
2023-01-24 05:51:16.028421: step: 308/469, loss: 0.002552240388467908
2023-01-24 05:51:16.694543: step: 310/469, loss: 0.0269322469830513
2023-01-24 05:51:17.268777: step: 312/469, loss: 0.002857362385839224
2023-01-24 05:51:17.960659: step: 314/469, loss: 0.04465809836983681
2023-01-24 05:51:18.593791: step: 316/469, loss: 0.0011126541066914797
2023-01-24 05:51:19.231410: step: 318/469, loss: 0.003672410501167178
2023-01-24 05:51:19.912267: step: 320/469, loss: 0.006917336490005255
2023-01-24 05:51:20.518804: step: 322/469, loss: 0.0008404464460909367
2023-01-24 05:51:21.092772: step: 324/469, loss: 0.025422999635338783
2023-01-24 05:51:21.739707: step: 326/469, loss: 0.0834602490067482
2023-01-24 05:51:22.351986: step: 328/469, loss: 0.0010484386002644897
2023-01-24 05:51:23.130632: step: 330/469, loss: 0.20623639225959778
2023-01-24 05:51:23.810579: step: 332/469, loss: 0.07975319772958755
2023-01-24 05:51:24.455631: step: 334/469, loss: 0.00032162253046408296
2023-01-24 05:51:24.994999: step: 336/469, loss: 0.03202521428465843
2023-01-24 05:51:25.618287: step: 338/469, loss: 0.018832555040717125
2023-01-24 05:51:26.205863: step: 340/469, loss: 0.0001598072558408603
2023-01-24 05:51:26.824449: step: 342/469, loss: 0.03233061358332634
2023-01-24 05:51:27.459716: step: 344/469, loss: 0.003593015717342496
2023-01-24 05:51:28.082259: step: 346/469, loss: 0.030679835006594658
2023-01-24 05:51:28.714657: step: 348/469, loss: 0.003391830250620842
2023-01-24 05:51:29.387264: step: 350/469, loss: 0.018660377711057663
2023-01-24 05:51:30.050870: step: 352/469, loss: 0.0004935087054036558
2023-01-24 05:51:30.637458: step: 354/469, loss: 5.612889435724355e-05
2023-01-24 05:51:31.215249: step: 356/469, loss: 7.583058322779834e-05
2023-01-24 05:51:31.766680: step: 358/469, loss: 0.0029486180283129215
2023-01-24 05:51:32.412655: step: 360/469, loss: 0.0005886894068680704
2023-01-24 05:51:33.044850: step: 362/469, loss: 0.016660086810588837
2023-01-24 05:51:33.664872: step: 364/469, loss: 0.0030485393945127726
2023-01-24 05:51:34.295201: step: 366/469, loss: 2.1959168910980225
2023-01-24 05:51:34.949629: step: 368/469, loss: 0.006272064987570047
2023-01-24 05:51:35.553119: step: 370/469, loss: 0.0006402720464393497
2023-01-24 05:51:36.111308: step: 372/469, loss: 0.0006316850194707513
2023-01-24 05:51:36.810660: step: 374/469, loss: 0.007134428713470697
2023-01-24 05:51:37.445646: step: 376/469, loss: 0.0076501937583088875
2023-01-24 05:51:38.068789: step: 378/469, loss: 0.003553960006684065
2023-01-24 05:51:38.677896: step: 380/469, loss: 0.02285035513341427
2023-01-24 05:51:39.356923: step: 382/469, loss: 0.003922155126929283
2023-01-24 05:51:39.997642: step: 384/469, loss: 0.7899556756019592
2023-01-24 05:51:40.588095: step: 386/469, loss: 0.0021147632505744696
2023-01-24 05:51:41.229043: step: 388/469, loss: 0.00772074144333601
2023-01-24 05:51:41.865169: step: 390/469, loss: 0.003524455474689603
2023-01-24 05:51:42.483590: step: 392/469, loss: 0.12726449966430664
2023-01-24 05:51:43.110739: step: 394/469, loss: 0.0011023666011169553
2023-01-24 05:51:43.729761: step: 396/469, loss: 0.043037544935941696
2023-01-24 05:51:44.340592: step: 398/469, loss: 0.029298389330506325
2023-01-24 05:51:44.915271: step: 400/469, loss: 0.002133794827386737
2023-01-24 05:51:45.539926: step: 402/469, loss: 0.010272110812366009
2023-01-24 05:51:46.135429: step: 404/469, loss: 0.00018153723794966936
2023-01-24 05:51:46.711023: step: 406/469, loss: 0.009023654274642467
2023-01-24 05:51:47.254803: step: 408/469, loss: 0.00046717398799955845
2023-01-24 05:51:47.874722: step: 410/469, loss: 0.017269618809223175
2023-01-24 05:51:48.515743: step: 412/469, loss: 0.004932466894388199
2023-01-24 05:51:49.146058: step: 414/469, loss: 0.3704630434513092
2023-01-24 05:51:49.767611: step: 416/469, loss: 0.06960838288068771
2023-01-24 05:51:50.476210: step: 418/469, loss: 0.03317670524120331
2023-01-24 05:51:51.079152: step: 420/469, loss: 0.014792066998779774
2023-01-24 05:51:51.647142: step: 422/469, loss: 0.012164157815277576
2023-01-24 05:51:52.220939: step: 424/469, loss: 0.0005053103668615222
2023-01-24 05:51:52.857296: step: 426/469, loss: 4.545390765997581e-05
2023-01-24 05:51:53.501594: step: 428/469, loss: 0.39047083258628845
2023-01-24 05:51:54.097444: step: 430/469, loss: 0.1179732158780098
2023-01-24 05:51:54.672413: step: 432/469, loss: 0.002892301417887211
2023-01-24 05:51:55.376223: step: 434/469, loss: 0.011080923490226269
2023-01-24 05:51:56.000060: step: 436/469, loss: 0.004454146604984999
2023-01-24 05:51:56.558547: step: 438/469, loss: 0.00016548072744626552
2023-01-24 05:51:57.196391: step: 440/469, loss: 0.0068971929140388966
2023-01-24 05:51:57.830177: step: 442/469, loss: 0.16627870500087738
2023-01-24 05:51:58.412270: step: 444/469, loss: 0.0004422983038239181
2023-01-24 05:51:59.006233: step: 446/469, loss: 0.0016291597858071327
2023-01-24 05:51:59.629029: step: 448/469, loss: 0.008061086758971214
2023-01-24 05:52:00.192014: step: 450/469, loss: 0.0023519310634583235
2023-01-24 05:52:00.843451: step: 452/469, loss: 0.883834183216095
2023-01-24 05:52:01.480003: step: 454/469, loss: 0.01137097179889679
2023-01-24 05:52:02.131190: step: 456/469, loss: 0.06367877125740051
2023-01-24 05:52:02.738267: step: 458/469, loss: 0.002710080938413739
2023-01-24 05:52:03.364550: step: 460/469, loss: 0.040760233998298645
2023-01-24 05:52:03.904573: step: 462/469, loss: 0.0007366880308836699
2023-01-24 05:52:04.515998: step: 464/469, loss: 0.005463487934321165
2023-01-24 05:52:05.111169: step: 466/469, loss: 0.05713071674108505
2023-01-24 05:52:05.706919: step: 468/469, loss: 0.02852305769920349
2023-01-24 05:52:06.368652: step: 470/469, loss: 0.021332694217562675
2023-01-24 05:52:06.970263: step: 472/469, loss: 0.06143294274806976
2023-01-24 05:52:07.616573: step: 474/469, loss: 0.003490180941298604
2023-01-24 05:52:08.203352: step: 476/469, loss: 0.007113657426089048
2023-01-24 05:52:08.815413: step: 478/469, loss: 0.029517650604248047
2023-01-24 05:52:09.526785: step: 480/469, loss: 0.19607967138290405
2023-01-24 05:52:10.125072: step: 482/469, loss: 0.004462911281734705
2023-01-24 05:52:10.698322: step: 484/469, loss: 0.0014543115394189954
2023-01-24 05:52:11.316322: step: 486/469, loss: 5.302381396177225e-05
2023-01-24 05:52:11.960907: step: 488/469, loss: 0.04611814022064209
2023-01-24 05:52:12.527723: step: 490/469, loss: 0.0006607295363210142
2023-01-24 05:52:13.225099: step: 492/469, loss: 0.017223069444298744
2023-01-24 05:52:13.818618: step: 494/469, loss: 0.008610890246927738
2023-01-24 05:52:14.503806: step: 496/469, loss: 0.002424276201054454
2023-01-24 05:52:15.105055: step: 498/469, loss: 0.0024730777367949486
2023-01-24 05:52:15.768685: step: 500/469, loss: 0.0046568987891077995
2023-01-24 05:52:16.383077: step: 502/469, loss: 0.025810427963733673
2023-01-24 05:52:17.022296: step: 504/469, loss: 3.631127765402198e-05
2023-01-24 05:52:17.723984: step: 506/469, loss: 0.001211229944601655
2023-01-24 05:52:18.358188: step: 508/469, loss: 0.0042308964766561985
2023-01-24 05:52:18.975265: step: 510/469, loss: 2.4700466383364983e-05
2023-01-24 05:52:19.618255: step: 512/469, loss: 0.007518894970417023
2023-01-24 05:52:20.211168: step: 514/469, loss: 0.001220062025822699
2023-01-24 05:52:20.862195: step: 516/469, loss: 0.16600191593170166
2023-01-24 05:52:21.551188: step: 518/469, loss: 0.001965184463188052
2023-01-24 05:52:22.111634: step: 520/469, loss: 0.09088757634162903
2023-01-24 05:52:22.719076: step: 522/469, loss: 0.038489799946546555
2023-01-24 05:52:23.315652: step: 524/469, loss: 0.0004704766906797886
2023-01-24 05:52:24.001606: step: 526/469, loss: 0.019209854304790497
2023-01-24 05:52:24.552725: step: 528/469, loss: 0.0010908718686550856
2023-01-24 05:52:25.186167: step: 530/469, loss: 0.02724377065896988
2023-01-24 05:52:25.850873: step: 532/469, loss: 0.012407144531607628
2023-01-24 05:52:26.520291: step: 534/469, loss: 0.010673681274056435
2023-01-24 05:52:27.066603: step: 536/469, loss: 0.0015231132274493575
2023-01-24 05:52:27.715531: step: 538/469, loss: 0.6964307427406311
2023-01-24 05:52:28.274994: step: 540/469, loss: 0.0008318874170072377
2023-01-24 05:52:28.877367: step: 542/469, loss: 0.03426213562488556
2023-01-24 05:52:29.484531: step: 544/469, loss: 0.005462720058858395
2023-01-24 05:52:30.094264: step: 546/469, loss: 0.0018660806817933917
2023-01-24 05:52:30.744532: step: 548/469, loss: 0.015423593111336231
2023-01-24 05:52:31.361658: step: 550/469, loss: 0.007194102741777897
2023-01-24 05:52:31.960818: step: 552/469, loss: 0.00035338601446710527
2023-01-24 05:52:32.612070: step: 554/469, loss: 0.002550520235672593
2023-01-24 05:52:33.190699: step: 556/469, loss: 0.07456482201814651
2023-01-24 05:52:33.828929: step: 558/469, loss: 0.01086405199021101
2023-01-24 05:52:34.500113: step: 560/469, loss: 0.0004567425057757646
2023-01-24 05:52:35.123218: step: 562/469, loss: 0.06614360958337784
2023-01-24 05:52:35.762632: step: 564/469, loss: 0.00047429444384761155
2023-01-24 05:52:36.370967: step: 566/469, loss: 0.024727847427129745
2023-01-24 05:52:36.970739: step: 568/469, loss: 0.0026039599906653166
2023-01-24 05:52:37.541075: step: 570/469, loss: 0.0047595687210559845
2023-01-24 05:52:38.173410: step: 572/469, loss: 0.0011343127116560936
2023-01-24 05:52:38.848994: step: 574/469, loss: 0.02800801768898964
2023-01-24 05:52:39.495336: step: 576/469, loss: 0.001546868123114109
2023-01-24 05:52:40.125444: step: 578/469, loss: 0.0015743788098916411
2023-01-24 05:52:40.764508: step: 580/469, loss: 0.0419471301138401
2023-01-24 05:52:41.313265: step: 582/469, loss: 0.014405900612473488
2023-01-24 05:52:41.970355: step: 584/469, loss: 0.00592692568898201
2023-01-24 05:52:42.586832: step: 586/469, loss: 0.004139040131121874
2023-01-24 05:52:43.144685: step: 588/469, loss: 0.02994312159717083
2023-01-24 05:52:43.747257: step: 590/469, loss: 0.0006825344171375036
2023-01-24 05:52:44.336397: step: 592/469, loss: 0.017383169382810593
2023-01-24 05:52:45.067860: step: 594/469, loss: 0.2890271246433258
2023-01-24 05:52:45.786334: step: 596/469, loss: 3.8460842915810645e-05
2023-01-24 05:52:46.405717: step: 598/469, loss: 0.02232646755874157
2023-01-24 05:52:47.018572: step: 600/469, loss: 0.00019514025188982487
2023-01-24 05:52:47.662008: step: 602/469, loss: 0.0007909578853286803
2023-01-24 05:52:48.206322: step: 604/469, loss: 0.014241098426282406
2023-01-24 05:52:48.795169: step: 606/469, loss: 0.001265901722945273
2023-01-24 05:52:49.443657: step: 608/469, loss: 0.004157170653343201
2023-01-24 05:52:50.125562: step: 610/469, loss: 0.02941458858549595
2023-01-24 05:52:50.766950: step: 612/469, loss: 0.22352951765060425
2023-01-24 05:52:51.372386: step: 614/469, loss: 0.01254553347826004
2023-01-24 05:52:51.954030: step: 616/469, loss: 0.0010224079014733434
2023-01-24 05:52:52.558188: step: 618/469, loss: 0.005898221395909786
2023-01-24 05:52:53.177314: step: 620/469, loss: 0.00041182778659276664
2023-01-24 05:52:53.777929: step: 622/469, loss: 0.01132738683372736
2023-01-24 05:52:54.398023: step: 624/469, loss: 0.02262009121477604
2023-01-24 05:52:55.036474: step: 626/469, loss: 0.002695016795769334
2023-01-24 05:52:55.724660: step: 628/469, loss: 0.04061281308531761
2023-01-24 05:52:56.337765: step: 630/469, loss: 0.014679528772830963
2023-01-24 05:52:56.926612: step: 632/469, loss: 0.0009139236062765121
2023-01-24 05:52:57.547838: step: 634/469, loss: 0.03422641009092331
2023-01-24 05:52:58.169324: step: 636/469, loss: 0.00804446917027235
2023-01-24 05:52:58.792345: step: 638/469, loss: 0.006519542541354895
2023-01-24 05:52:59.403155: step: 640/469, loss: 0.026553060859441757
2023-01-24 05:52:59.977479: step: 642/469, loss: 0.019603505730628967
2023-01-24 05:53:00.739267: step: 644/469, loss: 0.038403891026973724
2023-01-24 05:53:01.300021: step: 646/469, loss: 0.0019963104277849197
2023-01-24 05:53:01.936665: step: 648/469, loss: 0.006005199626088142
2023-01-24 05:53:02.573848: step: 650/469, loss: 0.0007043545483611524
2023-01-24 05:53:03.234966: step: 652/469, loss: 0.001996937906369567
2023-01-24 05:53:03.818564: step: 654/469, loss: 0.00488081993535161
2023-01-24 05:53:04.461907: step: 656/469, loss: 0.0031579190399497747
2023-01-24 05:53:05.051307: step: 658/469, loss: 4.6396431571338326e-05
2023-01-24 05:53:05.783077: step: 660/469, loss: 0.022864099591970444
2023-01-24 05:53:06.367643: step: 662/469, loss: 0.00975657906383276
2023-01-24 05:53:06.946416: step: 664/469, loss: 5.5786069424357265e-05
2023-01-24 05:53:07.612879: step: 666/469, loss: 0.0014591752551496029
2023-01-24 05:53:08.205327: step: 668/469, loss: 0.029773162677884102
2023-01-24 05:53:08.797005: step: 670/469, loss: 0.0008616966078989208
2023-01-24 05:53:09.400083: step: 672/469, loss: 0.00490968581289053
2023-01-24 05:53:10.021550: step: 674/469, loss: 0.00019307725597172976
2023-01-24 05:53:10.617497: step: 676/469, loss: 0.0011322894133627415
2023-01-24 05:53:11.246609: step: 678/469, loss: 0.00022908096434548497
2023-01-24 05:53:11.888580: step: 680/469, loss: 0.000859872146975249
2023-01-24 05:53:12.475346: step: 682/469, loss: 0.011646516621112823
2023-01-24 05:53:13.088395: step: 684/469, loss: 7.980142981978133e-05
2023-01-24 05:53:13.644480: step: 686/469, loss: 0.0006243081297725439
2023-01-24 05:53:14.232495: step: 688/469, loss: 0.002105759922415018
2023-01-24 05:53:14.854185: step: 690/469, loss: 0.5540243983268738
2023-01-24 05:53:15.430849: step: 692/469, loss: 0.0010243217693641782
2023-01-24 05:53:16.070251: step: 694/469, loss: 0.03987590968608856
2023-01-24 05:53:16.719733: step: 696/469, loss: 0.03170924633741379
2023-01-24 05:53:17.368983: step: 698/469, loss: 4.712785448646173e-05
2023-01-24 05:53:17.964612: step: 700/469, loss: 0.0008510553743690252
2023-01-24 05:53:18.661875: step: 702/469, loss: 0.00013377561117522418
2023-01-24 05:53:19.254367: step: 704/469, loss: 0.0004218009707983583
2023-01-24 05:53:19.849859: step: 706/469, loss: 0.012497241608798504
2023-01-24 05:53:20.405454: step: 708/469, loss: 0.00014099344843998551
2023-01-24 05:53:20.998135: step: 710/469, loss: 0.001278732088394463
2023-01-24 05:53:21.585387: step: 712/469, loss: 0.002304119523614645
2023-01-24 05:53:22.186406: step: 714/469, loss: 0.0002952862996608019
2023-01-24 05:53:22.865823: step: 716/469, loss: 0.0002496714296285063
2023-01-24 05:53:23.472824: step: 718/469, loss: 0.0008478966192342341
2023-01-24 05:53:24.142741: step: 720/469, loss: 0.002209728816524148
2023-01-24 05:53:24.797568: step: 722/469, loss: 0.009437385946512222
2023-01-24 05:53:25.418822: step: 724/469, loss: 0.0032731054816395044
2023-01-24 05:53:26.034444: step: 726/469, loss: 0.005128795281052589
2023-01-24 05:53:26.704340: step: 728/469, loss: 0.0031885921489447355
2023-01-24 05:53:27.296347: step: 730/469, loss: 0.07506471127271652
2023-01-24 05:53:27.867114: step: 732/469, loss: 0.0030589159578084946
2023-01-24 05:53:28.512603: step: 734/469, loss: 0.0003622500516939908
2023-01-24 05:53:29.046113: step: 736/469, loss: 0.00045982073061168194
2023-01-24 05:53:29.716188: step: 738/469, loss: 0.0006731986650265753
2023-01-24 05:53:30.339639: step: 740/469, loss: 0.0002361301303608343
2023-01-24 05:53:31.018918: step: 742/469, loss: 6.249495345400646e-05
2023-01-24 05:53:31.568616: step: 744/469, loss: 0.0003132132114842534
2023-01-24 05:53:32.195385: step: 746/469, loss: 0.1405199021100998
2023-01-24 05:53:32.762244: step: 748/469, loss: 6.839424167992547e-05
2023-01-24 05:53:33.320650: step: 750/469, loss: 0.002533519407734275
2023-01-24 05:53:33.977974: step: 752/469, loss: 0.001349869417026639
2023-01-24 05:53:34.600551: step: 754/469, loss: 0.01379681471735239
2023-01-24 05:53:35.193391: step: 756/469, loss: 0.00016496462922077626
2023-01-24 05:53:35.862903: step: 758/469, loss: 0.001254603615961969
2023-01-24 05:53:36.539996: step: 760/469, loss: 0.0010512936860322952
2023-01-24 05:53:37.213633: step: 762/469, loss: 0.024918323382735252
2023-01-24 05:53:37.952083: step: 764/469, loss: 0.06979934871196747
2023-01-24 05:53:38.570324: step: 766/469, loss: 0.003951192833483219
2023-01-24 05:53:39.238334: step: 768/469, loss: 0.0005764127126894891
2023-01-24 05:53:39.916305: step: 770/469, loss: 0.10904546082019806
2023-01-24 05:53:40.589819: step: 772/469, loss: 0.0023626761976629496
2023-01-24 05:53:41.229004: step: 774/469, loss: 0.0029543868731707335
2023-01-24 05:53:41.865944: step: 776/469, loss: 0.06157940998673439
2023-01-24 05:53:42.452536: step: 778/469, loss: 0.0031244659330695868
2023-01-24 05:53:43.113966: step: 780/469, loss: 0.00601613987237215
2023-01-24 05:53:43.722780: step: 782/469, loss: 0.026845060288906097
2023-01-24 05:53:44.366250: step: 784/469, loss: 0.0007251825300045311
2023-01-24 05:53:45.070548: step: 786/469, loss: 0.02268672175705433
2023-01-24 05:53:45.710653: step: 788/469, loss: 0.0004044454835820943
2023-01-24 05:53:46.315607: step: 790/469, loss: 0.008996649645268917
2023-01-24 05:53:46.909706: step: 792/469, loss: 0.00010959096107399091
2023-01-24 05:53:47.519428: step: 794/469, loss: 0.0003383233561180532
2023-01-24 05:53:48.153649: step: 796/469, loss: 0.00963415578007698
2023-01-24 05:53:48.718550: step: 798/469, loss: 0.005896236281841993
2023-01-24 05:53:49.311518: step: 800/469, loss: 0.0011253239354118705
2023-01-24 05:53:49.933325: step: 802/469, loss: 0.0005202133324928582
2023-01-24 05:53:50.513945: step: 804/469, loss: 0.03894947096705437
2023-01-24 05:53:51.102652: step: 806/469, loss: 0.0006364258006215096
2023-01-24 05:53:51.651665: step: 808/469, loss: 0.0010266718454658985
2023-01-24 05:53:52.253834: step: 810/469, loss: 0.0001264224702026695
2023-01-24 05:53:52.837029: step: 812/469, loss: 0.008374189957976341
2023-01-24 05:53:53.433482: step: 814/469, loss: 0.0027772036846727133
2023-01-24 05:53:53.978907: step: 816/469, loss: 0.001290840096771717
2023-01-24 05:53:54.682151: step: 818/469, loss: 0.0027226342353969812
2023-01-24 05:53:55.271315: step: 820/469, loss: 0.003282391233369708
2023-01-24 05:53:55.841504: step: 822/469, loss: 0.005161920562386513
2023-01-24 05:53:56.551823: step: 824/469, loss: 0.052473343908786774
2023-01-24 05:53:57.166754: step: 826/469, loss: 0.005467752460390329
2023-01-24 05:53:57.788649: step: 828/469, loss: 0.00017220845620613545
2023-01-24 05:53:58.431227: step: 830/469, loss: 0.021755851805210114
2023-01-24 05:53:59.069896: step: 832/469, loss: 0.021843472495675087
2023-01-24 05:53:59.769095: step: 834/469, loss: 0.06006266549229622
2023-01-24 05:54:00.389795: step: 836/469, loss: 0.09590421617031097
2023-01-24 05:54:01.100646: step: 838/469, loss: 0.013243522495031357
2023-01-24 05:54:01.745258: step: 840/469, loss: 0.020998096093535423
2023-01-24 05:54:02.371916: step: 842/469, loss: 0.01351924054324627
2023-01-24 05:54:03.041140: step: 844/469, loss: 0.0011390522122383118
2023-01-24 05:54:03.658477: step: 846/469, loss: 0.0002918808604590595
2023-01-24 05:54:04.227218: step: 848/469, loss: 0.005110482685267925
2023-01-24 05:54:04.794199: step: 850/469, loss: 0.002068703528493643
2023-01-24 05:54:05.419983: step: 852/469, loss: 0.0002787143748719245
2023-01-24 05:54:05.995035: step: 854/469, loss: 0.030446400865912437
2023-01-24 05:54:06.575629: step: 856/469, loss: 0.02337447553873062
2023-01-24 05:54:07.167175: step: 858/469, loss: 0.004919606260955334
2023-01-24 05:54:07.855571: step: 860/469, loss: 0.11173321306705475
2023-01-24 05:54:08.487482: step: 862/469, loss: 0.0001346757635474205
2023-01-24 05:54:09.131684: step: 864/469, loss: 0.061282794922590256
2023-01-24 05:54:09.765325: step: 866/469, loss: 0.00018122194160241634
2023-01-24 05:54:10.344550: step: 868/469, loss: 0.003808876732364297
2023-01-24 05:54:10.892873: step: 870/469, loss: 0.003564674872905016
2023-01-24 05:54:11.516574: step: 872/469, loss: 0.0012337930966168642
2023-01-24 05:54:12.105950: step: 874/469, loss: 0.003552865469828248
2023-01-24 05:54:12.680948: step: 876/469, loss: 0.009105992503464222
2023-01-24 05:54:13.325496: step: 878/469, loss: 0.024139082059264183
2023-01-24 05:54:13.952055: step: 880/469, loss: 0.0015041761798784137
2023-01-24 05:54:14.511371: step: 882/469, loss: 0.0035050634760409594
2023-01-24 05:54:15.127415: step: 884/469, loss: 0.0010745482286438346
2023-01-24 05:54:15.749231: step: 886/469, loss: 4.355171768111177e-05
2023-01-24 05:54:16.398052: step: 888/469, loss: 0.38475853204727173
2023-01-24 05:54:17.024670: step: 890/469, loss: 0.00010159765224670991
2023-01-24 05:54:17.684897: step: 892/469, loss: 0.0024965463671833277
2023-01-24 05:54:18.297280: step: 894/469, loss: 0.002298385603353381
2023-01-24 05:54:18.941712: step: 896/469, loss: 0.004638176877051592
2023-01-24 05:54:19.497295: step: 898/469, loss: 0.0022129861172288656
2023-01-24 05:54:20.136239: step: 900/469, loss: 0.01527074258774519
2023-01-24 05:54:20.817769: step: 902/469, loss: 0.45652323961257935
2023-01-24 05:54:21.500653: step: 904/469, loss: 0.004197975154966116
2023-01-24 05:54:22.127468: step: 906/469, loss: 0.007649663835763931
2023-01-24 05:54:22.727933: step: 908/469, loss: 0.00026691131643019617
2023-01-24 05:54:23.353122: step: 910/469, loss: 0.055212393403053284
2023-01-24 05:54:23.963825: step: 912/469, loss: 0.007090070750564337
2023-01-24 05:54:24.596448: step: 914/469, loss: 0.28060656785964966
2023-01-24 05:54:25.211529: step: 916/469, loss: 0.022623805329203606
2023-01-24 05:54:25.897249: step: 918/469, loss: 0.007064515259116888
2023-01-24 05:54:26.541594: step: 920/469, loss: 0.010560913942754269
2023-01-24 05:54:27.200735: step: 922/469, loss: 0.005171039141714573
2023-01-24 05:54:27.841708: step: 924/469, loss: 9.960651368601248e-05
2023-01-24 05:54:28.525012: step: 926/469, loss: 0.0042560952715575695
2023-01-24 05:54:29.074590: step: 928/469, loss: 0.0013860042672604322
2023-01-24 05:54:29.704314: step: 930/469, loss: 0.03449440747499466
2023-01-24 05:54:30.321132: step: 932/469, loss: 0.0010424494976177812
2023-01-24 05:54:30.923065: step: 934/469, loss: 0.00033884294680319726
2023-01-24 05:54:31.519144: step: 936/469, loss: 0.007781301159411669
2023-01-24 05:54:32.105404: step: 938/469, loss: 0.004696676507592201
==================================================
Loss: 0.036
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34541190046156933, 'r': 0.2969100396756943, 'f1': 0.3193297773654916}, 'combined': 0.23529562542720434, 'epoch': 39}
Test Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3430918257364211, 'r': 0.24829426729872747, 'f1': 0.2880951530334492}, 'combined': 0.15714281074551772, 'epoch': 39}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34704402636104503, 'r': 0.2989715141706156, 'f1': 0.3212191395880009}, 'combined': 0.23668778706484275, 'epoch': 39}
Test Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.35184067342831715, 'r': 0.2520505464724358, 'f1': 0.29370069007928823}, 'combined': 0.16020037640688448, 'epoch': 39}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3339276241628539, 'r': 0.2895729112759473, 'f1': 0.3101726102488297}, 'combined': 0.2285482391307166, 'epoch': 39}
Test Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.33481466514532027, 'r': 0.24781799094470638, 'f1': 0.28482130820458895}, 'combined': 0.15535707720250305, 'epoch': 39}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3517156862745098, 'r': 0.3416666666666666, 'f1': 0.34661835748792263}, 'combined': 0.23107890499194841, 'epoch': 39}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.31521739130434784, 'r': 0.31521739130434784, 'f1': 0.31521739130434784}, 'combined': 0.15760869565217392, 'epoch': 39}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5555555555555556, 'r': 0.1724137931034483, 'f1': 0.26315789473684215}, 'combined': 0.1754385964912281, 'epoch': 39}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361027497559388, 'r': 0.27997933044185414, 'f1': 0.305484693877551}, 'combined': 0.22509398496240599, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.32787725334367124, 'r': 0.22108466213566852, 'f1': 0.26409348165495705}, 'combined': 0.14405098999361293, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4111111111111111, 'r': 0.35238095238095235, 'f1': 0.3794871794871794}, 'combined': 0.2529914529914529, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3163678353215013, 'r': 0.2947563702900515, 'f1': 0.30517997474038727}, 'combined': 0.2248694550718643, 'epoch': 10}
Test for Korean: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3382611423427968, 'r': 0.26522396979668517, 'f1': 0.2973228707566942}, 'combined': 0.1621761113218332, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3854166666666667, 'r': 0.40217391304347827, 'f1': 0.39361702127659576}, 'combined': 0.19680851063829788, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3308171543368912, 'r': 0.3101018486573515, 'f1': 0.32012472917223167}, 'combined': 0.23588137939006543, 'epoch': 38}
Test for Russian: {'template': {'p': 0.8059701492537313, 'r': 0.4122137404580153, 'f1': 0.5454545454545454}, 'slot': {'p': 0.3327536501331047, 'r': 0.2713689585103767, 'f1': 0.29894266556223587}, 'combined': 0.16305963576121954, 'epoch': 38}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6666666666666666, 'r': 0.20689655172413793, 'f1': 0.31578947368421056}, 'combined': 0.2105263157894737, 'epoch': 38}