Command that produces this log: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
----------------------------------------------------------------------------------------------------
> trainable params:
>>> xlmr.embeddings.word_embeddings.weight: torch.Size([250002, 1024])
>>> xlmr.embeddings.position_embeddings.weight: torch.Size([514, 1024])
>>> xlmr.embeddings.token_type_embeddings.weight: torch.Size([1, 1024])
>>> xlmr.embeddings.LayerNorm.weight: torch.Size([1024])
>>> xlmr.embeddings.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.0.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.0.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.0.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.1.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.1.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.1.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.2.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.2.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.2.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.3.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.3.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.3.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.4.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.4.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.4.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.5.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.5.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.5.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.6.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.6.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.6.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.7.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.7.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.7.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.8.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.8.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.8.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.9.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.9.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.9.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.10.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.10.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.10.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.11.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.11.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.11.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.12.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.12.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.12.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.13.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.13.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.13.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.14.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.14.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.14.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.15.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.15.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.15.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.16.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.16.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.16.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.17.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.17.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.17.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.18.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.18.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.18.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.19.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.19.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.19.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.20.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.20.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.20.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.21.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.21.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.21.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.22.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.22.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.22.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.23.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.23.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.23.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.pooler.dense.weight: torch.Size([1024, 1024])
>>> xlmr.pooler.dense.bias: torch.Size([1024])
>>> type_embedding.weight: torch.Size([123, 100])
>>> trans_rep.weight: torch.Size([1024, 1124])
>>> trans_rep.bias: torch.Size([1024])
>>> coref_type_ffn.weight: torch.Size([3, 4096])
>>> coref_type_ffn.bias: torch.Size([3])
n_trainable_params: 561067023, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:20:42.905813: step: 4/531, loss: 0.018170563504099846
2023-01-24 05:20:43.948661: step: 8/531, loss: 0.011322838254272938
2023-01-24 05:20:45.005851: step: 12/531, loss: 0.04829345643520355
2023-01-24 05:20:46.047310: step: 16/531, loss: 0.009348283521831036
2023-01-24 05:20:47.099180: step: 20/531, loss: 0.017068643122911453
2023-01-24 05:20:48.147734: step: 24/531, loss: 0.018864022567868233
2023-01-24 05:20:49.203821: step: 28/531, loss: 0.017118431627750397
2023-01-24 05:20:50.262593: step: 32/531, loss: 0.01312822476029396
2023-01-24 05:20:51.312795: step: 36/531, loss: 0.016625747084617615
2023-01-24 05:20:52.368268: step: 40/531, loss: 0.01186138391494751
2023-01-24 05:20:53.414295: step: 44/531, loss: 0.018956823274493217
2023-01-24 05:20:54.469702: step: 48/531, loss: 0.014355204999446869
2023-01-24 05:20:55.529959: step: 52/531, loss: 0.013917816802859306
2023-01-24 05:20:56.591972: step: 56/531, loss: 0.02647165022790432
2023-01-24 05:20:57.644588: step: 60/531, loss: 0.061029136180877686
2023-01-24 05:20:58.691770: step: 64/531, loss: 0.0702832043170929
2023-01-24 05:20:59.756253: step: 68/531, loss: 0.023450976237654686
2023-01-24 05:21:00.802914: step: 72/531, loss: 0.049824126064777374
2023-01-24 05:21:01.859828: step: 76/531, loss: 0.03386794403195381
2023-01-24 05:21:02.918574: step: 80/531, loss: 0.020017804577946663
2023-01-24 05:21:03.976200: step: 84/531, loss: 0.019348086789250374
2023-01-24 05:21:05.015480: step: 88/531, loss: 0.05341392382979393
2023-01-24 05:21:06.086771: step: 92/531, loss: 0.058558326214551926
2023-01-24 05:21:07.140480: step: 96/531, loss: 0.010691803880035877
2023-01-24 05:21:08.213869: step: 100/531, loss: 0.01755356788635254
2023-01-24 05:21:09.276295: step: 104/531, loss: 0.015221161767840385
2023-01-24 05:21:10.327514: step: 108/531, loss: 0.060155000537633896
2023-01-24 05:21:11.372337: step: 112/531, loss: 0.07014718651771545
2023-01-24 05:21:12.432455: step: 116/531, loss: 0.01248928252607584
2023-01-24 05:21:13.491228: step: 120/531, loss: 0.012406772002577782
2023-01-24 05:21:14.547357: step: 124/531, loss: 0.02380838617682457
2023-01-24 05:21:15.609653: step: 128/531, loss: 0.015290040522813797
2023-01-24 05:21:16.664342: step: 132/531, loss: 0.008468336425721645
2023-01-24 05:21:17.714470: step: 136/531, loss: 0.007525733672082424
2023-01-24 05:21:18.772018: step: 140/531, loss: 0.04454159736633301
2023-01-24 05:21:19.826237: step: 144/531, loss: 0.02104450948536396
2023-01-24 05:21:20.860489: step: 148/531, loss: 0.03128483146429062
2023-01-24 05:21:21.926358: step: 152/531, loss: 0.01681424491107464
2023-01-24 05:21:22.997057: step: 156/531, loss: 0.05191762372851372
2023-01-24 05:21:24.062169: step: 160/531, loss: 0.02295805886387825
2023-01-24 05:21:25.119355: step: 164/531, loss: 0.010234040208160877
2023-01-24 05:21:26.190972: step: 168/531, loss: 0.04013200104236603
2023-01-24 05:21:27.250985: step: 172/531, loss: 0.021994352340698242
2023-01-24 05:21:28.318448: step: 176/531, loss: 0.0261736661195755
2023-01-24 05:21:29.391479: step: 180/531, loss: 0.054567862302064896
2023-01-24 05:21:30.454777: step: 184/531, loss: 0.05303144082427025
2023-01-24 05:21:31.521825: step: 188/531, loss: 0.015433679334819317
2023-01-24 05:21:32.570905: step: 192/531, loss: 0.01450360007584095
2023-01-24 05:21:33.629139: step: 196/531, loss: 0.009794311597943306
2023-01-24 05:21:34.698086: step: 200/531, loss: 0.016226863488554955
2023-01-24 05:21:35.764381: step: 204/531, loss: 0.020626744255423546
2023-01-24 05:21:36.836394: step: 208/531, loss: 0.012945247814059258
2023-01-24 05:21:37.899442: step: 212/531, loss: 0.055919088423252106
2023-01-24 05:21:38.969962: step: 216/531, loss: 0.03969443589448929
2023-01-24 05:21:40.019542: step: 220/531, loss: 0.00956704281270504
2023-01-24 05:21:41.076803: step: 224/531, loss: 0.019948000088334084
2023-01-24 05:21:42.152417: step: 228/531, loss: 0.07200264930725098
2023-01-24 05:21:43.220957: step: 232/531, loss: 0.0961732566356659
2023-01-24 05:21:44.284264: step: 236/531, loss: 0.0125066377222538
2023-01-24 05:21:45.363996: step: 240/531, loss: 0.01298561692237854
2023-01-24 05:21:46.429399: step: 244/531, loss: 0.021817568689584732
2023-01-24 05:21:47.495717: step: 248/531, loss: 0.008433319628238678
2023-01-24 05:21:48.561353: step: 252/531, loss: 0.018323224037885666
2023-01-24 05:21:49.634700: step: 256/531, loss: 0.04815671965479851
2023-01-24 05:21:50.706365: step: 260/531, loss: 0.04839369282126427
2023-01-24 05:21:51.763762: step: 264/531, loss: 0.04580888897180557
2023-01-24 05:21:52.820505: step: 268/531, loss: 0.06339695304632187
2023-01-24 05:21:53.887965: step: 272/531, loss: 0.009873722679913044
2023-01-24 05:21:54.941833: step: 276/531, loss: 0.01474162470549345
2023-01-24 05:21:56.015538: step: 280/531, loss: 0.041152819991111755
2023-01-24 05:21:57.067190: step: 284/531, loss: 0.05454022437334061
2023-01-24 05:21:58.133495: step: 288/531, loss: 0.01857876218855381
2023-01-24 05:21:59.197255: step: 292/531, loss: 0.05805511772632599
2023-01-24 05:22:00.279118: step: 296/531, loss: 0.0394238606095314
2023-01-24 05:22:01.342546: step: 300/531, loss: 0.0279531329870224
2023-01-24 05:22:02.409931: step: 304/531, loss: 0.023521119728684425
2023-01-24 05:22:03.466985: step: 308/531, loss: 0.016286799684166908
2023-01-24 05:22:04.525669: step: 312/531, loss: 0.018223265185952187
2023-01-24 05:22:05.585551: step: 316/531, loss: 0.006818976253271103
2023-01-24 05:22:06.656958: step: 320/531, loss: 0.013323552906513214
2023-01-24 05:22:07.711784: step: 324/531, loss: 0.026609499007463455
2023-01-24 05:22:08.775980: step: 328/531, loss: 0.04978005960583687
2023-01-24 05:22:09.843208: step: 332/531, loss: 0.07152272015810013
2023-01-24 05:22:10.908970: step: 336/531, loss: 0.0075768763199448586
2023-01-24 05:22:11.971466: step: 340/531, loss: 0.003764066379517317
2023-01-24 05:22:13.054615: step: 344/531, loss: 0.008797116577625275
2023-01-24 05:22:14.118088: step: 348/531, loss: 0.0457511767745018
2023-01-24 05:22:15.187237: step: 352/531, loss: 0.05321735143661499
2023-01-24 05:22:16.259857: step: 356/531, loss: 0.012059643864631653
2023-01-24 05:22:17.329583: step: 360/531, loss: 0.01047996524721384
2023-01-24 05:22:18.391798: step: 364/531, loss: 0.013448943383991718
2023-01-24 05:22:19.438606: step: 368/531, loss: 0.024902738630771637
2023-01-24 05:22:20.499620: step: 372/531, loss: 0.011134122498333454
2023-01-24 05:22:21.561186: step: 376/531, loss: 0.01941181905567646
2023-01-24 05:22:22.631692: step: 380/531, loss: 0.01484807301312685
2023-01-24 05:22:23.717605: step: 384/531, loss: 0.010247286409139633
2023-01-24 05:22:24.785090: step: 388/531, loss: 0.045143526047468185
2023-01-24 05:22:25.846654: step: 392/531, loss: 0.017212165519595146
2023-01-24 05:22:26.925086: step: 396/531, loss: 0.045472994446754456
2023-01-24 05:22:28.026907: step: 400/531, loss: 0.010158528573811054
2023-01-24 05:22:29.106881: step: 404/531, loss: 0.00854258332401514
2023-01-24 05:22:30.169506: step: 408/531, loss: 0.05470995604991913
2023-01-24 05:22:31.245245: step: 412/531, loss: 0.01939086616039276
2023-01-24 05:22:32.298566: step: 416/531, loss: 0.014499673619866371
2023-01-24 05:22:33.352773: step: 420/531, loss: 0.03453696519136429
2023-01-24 05:22:34.418862: step: 424/531, loss: 0.0500594787299633
2023-01-24 05:22:35.501399: step: 428/531, loss: 0.029794123023748398
2023-01-24 05:22:36.590823: step: 432/531, loss: 0.005801026243716478
2023-01-24 05:22:37.653161: step: 436/531, loss: 0.013934549875557423
2023-01-24 05:22:38.733394: step: 440/531, loss: 0.01165790669620037
2023-01-24 05:22:39.798376: step: 444/531, loss: 0.014572062529623508
2023-01-24 05:22:40.881631: step: 448/531, loss: 0.008337599225342274
2023-01-24 05:22:41.956542: step: 452/531, loss: 0.04914865270256996
2023-01-24 05:22:43.032406: step: 456/531, loss: 0.048679422587156296
2023-01-24 05:22:44.105842: step: 460/531, loss: 0.01309958379715681
2023-01-24 05:22:45.170530: step: 464/531, loss: 0.039141640067100525
2023-01-24 05:22:46.215481: step: 468/531, loss: 0.0
2023-01-24 05:22:47.275074: step: 472/531, loss: 0.008508128114044666
2023-01-24 05:22:48.334371: step: 476/531, loss: 0.0803237333893776
2023-01-24 05:22:49.393042: step: 480/531, loss: 0.011697777546942234
2023-01-24 05:22:50.445126: step: 484/531, loss: 0.011993582360446453
2023-01-24 05:22:51.503201: step: 488/531, loss: 0.013080984354019165
2023-01-24 05:22:52.566066: step: 492/531, loss: 0.010660339146852493
2023-01-24 05:22:53.635402: step: 496/531, loss: 0.01299708615988493
2023-01-24 05:22:54.686973: step: 500/531, loss: 0.009807550348341465
2023-01-24 05:22:55.749448: step: 504/531, loss: 0.04132939875125885
2023-01-24 05:22:56.815602: step: 508/531, loss: 0.07086385786533356
2023-01-24 05:22:57.883675: step: 512/531, loss: 0.02512393519282341
2023-01-24 05:22:58.943601: step: 516/531, loss: 0.008981358259916306
2023-01-24 05:22:59.988825: step: 520/531, loss: 0.00837255734950304
2023-01-24 05:23:01.058302: step: 524/531, loss: 0.04507027193903923
2023-01-24 05:23:02.115409: step: 528/531, loss: 0.009422453120350838
2023-01-24 05:23:03.189471: step: 532/531, loss: 0.012063867412507534
2023-01-24 05:23:04.252245: step: 536/531, loss: 0.00793278869241476
2023-01-24 05:23:05.325669: step: 540/531, loss: 0.026150500401854515
2023-01-24 05:23:06.400459: step: 544/531, loss: 0.031051211059093475
2023-01-24 05:23:07.457937: step: 548/531, loss: 0.04840414226055145
2023-01-24 05:23:08.527173: step: 552/531, loss: 0.013596313074231148
2023-01-24 05:23:09.584465: step: 556/531, loss: 0.03785036876797676
2023-01-24 05:23:10.642746: step: 560/531, loss: 0.029163893312215805
2023-01-24 05:23:11.692620: step: 564/531, loss: 0.01968100108206272
2023-01-24 05:23:12.756252: step: 568/531, loss: 0.07464582473039627
2023-01-24 05:23:13.811550: step: 572/531, loss: 0.011769238859415054
2023-01-24 05:23:14.888624: step: 576/531, loss: 0.015067631378769875
2023-01-24 05:23:15.938893: step: 580/531, loss: 0.01259372103959322
2023-01-24 05:23:16.992999: step: 584/531, loss: 0.04508479684591293
2023-01-24 05:23:18.070881: step: 588/531, loss: 0.033124689012765884
2023-01-24 05:23:19.155137: step: 592/531, loss: 0.006049429532140493
2023-01-24 05:23:20.205882: step: 596/531, loss: 0.0
2023-01-24 05:23:21.265261: step: 600/531, loss: 0.04306354746222496
2023-01-24 05:23:22.332496: step: 604/531, loss: 0.019644686952233315
2023-01-24 05:23:23.400980: step: 608/531, loss: 0.03895169869065285
2023-01-24 05:23:24.465946: step: 612/531, loss: 0.050115134567022324
2023-01-24 05:23:25.519046: step: 616/531, loss: 0.010712578892707825
2023-01-24 05:23:26.592588: step: 620/531, loss: 0.033733267337083817
2023-01-24 05:23:27.663242: step: 624/531, loss: 0.06120038032531738
2023-01-24 05:23:28.723544: step: 628/531, loss: 0.012908191420137882
2023-01-24 05:23:29.779763: step: 632/531, loss: 0.017876828089356422
2023-01-24 05:23:30.847492: step: 636/531, loss: 0.05685174837708473
2023-01-24 05:23:31.902962: step: 640/531, loss: 0.012657851912081242
2023-01-24 05:23:32.965278: step: 644/531, loss: 0.039190035313367844
2023-01-24 05:23:34.043131: step: 648/531, loss: 0.016411198303103447
2023-01-24 05:23:35.111636: step: 652/531, loss: 0.028136972337961197
2023-01-24 05:23:36.178609: step: 656/531, loss: 0.02555316872894764
2023-01-24 05:23:37.261338: step: 660/531, loss: 0.018969589844346046
2023-01-24 05:23:38.317630: step: 664/531, loss: 0.018380412831902504
2023-01-24 05:23:39.360604: step: 668/531, loss: 0.013217329978942871
2023-01-24 05:23:40.425091: step: 672/531, loss: 0.00837804563343525
2023-01-24 05:23:41.472326: step: 676/531, loss: 0.008425845764577389
2023-01-24 05:23:42.533113: step: 680/531, loss: 0.01829485408961773
2023-01-24 05:23:43.594866: step: 684/531, loss: 0.01057519018650055
2023-01-24 05:23:44.652352: step: 688/531, loss: 0.06050803139805794
2023-01-24 05:23:45.716108: step: 692/531, loss: 0.011691092513501644
2023-01-24 05:23:46.792180: step: 696/531, loss: 0.009698997251689434
2023-01-24 05:23:47.851624: step: 700/531, loss: 0.05816865712404251
2023-01-24 05:23:48.912027: step: 704/531, loss: 0.01664169318974018
2023-01-24 05:23:49.963848: step: 708/531, loss: 0.023120898753404617
2023-01-24 05:23:51.017259: step: 712/531, loss: 0.00801254715770483
2023-01-24 05:23:52.084936: step: 716/531, loss: 0.0381682813167572
2023-01-24 05:23:53.143299: step: 720/531, loss: 0.0072555020451545715
2023-01-24 05:23:54.213111: step: 724/531, loss: 0.018962437286973
2023-01-24 05:23:55.266177: step: 728/531, loss: 0.03683837875723839
2023-01-24 05:23:56.345160: step: 732/531, loss: 0.038544539362192154
2023-01-24 05:23:57.411292: step: 736/531, loss: 0.04627222940325737
2023-01-24 05:23:58.457190: step: 740/531, loss: 0.03517960384488106
2023-01-24 05:23:59.505454: step: 744/531, loss: 0.007916511967778206
2023-01-24 05:24:00.566355: step: 748/531, loss: 0.009745625779032707
2023-01-24 05:24:01.657963: step: 752/531, loss: 0.006276762578636408
2023-01-24 05:24:02.735295: step: 756/531, loss: 0.009843764826655388
2023-01-24 05:24:03.782755: step: 760/531, loss: 0.028286047279834747
2023-01-24 05:24:04.834641: step: 764/531, loss: 0.06176306679844856
2023-01-24 05:24:05.908372: step: 768/531, loss: 0.016211532056331635
2023-01-24 05:24:06.963586: step: 772/531, loss: 0.007534511387348175
2023-01-24 05:24:08.023265: step: 776/531, loss: 0.007740554865449667
2023-01-24 05:24:09.083251: step: 780/531, loss: 0.02157668210566044
2023-01-24 05:24:10.151080: step: 784/531, loss: 0.007612189278006554
2023-01-24 05:24:11.213883: step: 788/531, loss: 0.04780685901641846
2023-01-24 05:24:12.275317: step: 792/531, loss: 0.046151190996170044
2023-01-24 05:24:13.330094: step: 796/531, loss: 0.03277471661567688
2023-01-24 05:24:14.379436: step: 800/531, loss: 0.01489497534930706
2023-01-24 05:24:15.438166: step: 804/531, loss: 0.010438865050673485
2023-01-24 05:24:16.512927: step: 808/531, loss: 0.0464506521821022
2023-01-24 05:24:17.582679: step: 812/531, loss: 0.018300771713256836
2023-01-24 05:24:18.661597: step: 816/531, loss: 0.00840457621961832
2023-01-24 05:24:19.715040: step: 820/531, loss: 0.023203309625387192
2023-01-24 05:24:20.768646: step: 824/531, loss: 0.013294472359120846
2023-01-24 05:24:21.827197: step: 828/531, loss: 0.01593204215168953
2023-01-24 05:24:22.908298: step: 832/531, loss: 0.014876758679747581
2023-01-24 05:24:23.970657: step: 836/531, loss: 0.07697822898626328
2023-01-24 05:24:25.047208: step: 840/531, loss: 0.03857125714421272
2023-01-24 05:24:26.116060: step: 844/531, loss: 0.029041605070233345
2023-01-24 05:24:27.176898: step: 848/531, loss: 0.009344058111310005
2023-01-24 05:24:28.231285: step: 852/531, loss: 0.02397291362285614
2023-01-24 05:24:29.277145: step: 856/531, loss: 0.004911182913929224
2023-01-24 05:24:30.323044: step: 860/531, loss: 0.04191805049777031
2023-01-24 05:24:31.403490: step: 864/531, loss: 0.011695814318954945
2023-01-24 05:24:32.492813: step: 868/531, loss: 0.020490050315856934
2023-01-24 05:24:33.540476: step: 872/531, loss: 0.012526093982160091
2023-01-24 05:24:34.598796: step: 876/531, loss: 0.02372817136347294
2023-01-24 05:24:35.647914: step: 880/531, loss: 0.023975122720003128
2023-01-24 05:24:36.705906: step: 884/531, loss: 0.05118924006819725
2023-01-24 05:24:37.762463: step: 888/531, loss: 0.06693841516971588
2023-01-24 05:24:38.820734: step: 892/531, loss: 0.010523651726543903
2023-01-24 05:24:39.885617: step: 896/531, loss: 0.006021940149366856
2023-01-24 05:24:40.941048: step: 900/531, loss: 0.01172979548573494
2023-01-24 05:24:41.998110: step: 904/531, loss: 0.04168125241994858
2023-01-24 05:24:43.061003: step: 908/531, loss: 0.012182427570223808
2023-01-24 05:24:44.129829: step: 912/531, loss: 0.05263920873403549
2023-01-24 05:24:45.183698: step: 916/531, loss: 0.011832731775939465
2023-01-24 05:24:46.254042: step: 920/531, loss: 0.018344487994909286
2023-01-24 05:24:47.324289: step: 924/531, loss: 0.017274517565965652
2023-01-24 05:24:48.377302: step: 928/531, loss: 0.03351505100727081
2023-01-24 05:24:49.432586: step: 932/531, loss: 0.04269670322537422
2023-01-24 05:24:50.491552: step: 936/531, loss: 0.012370468117296696
2023-01-24 05:24:51.553887: step: 940/531, loss: 0.014154774136841297
2023-01-24 05:24:52.627445: step: 944/531, loss: 0.006835263222455978
2023-01-24 05:24:53.687869: step: 948/531, loss: 0.06959729641675949
2023-01-24 05:24:54.758206: step: 952/531, loss: 0.0188874714076519
2023-01-24 05:24:55.810865: step: 956/531, loss: 0.0070149400271475315
2023-01-24 05:24:56.881094: step: 960/531, loss: 0.0069689759984612465
2023-01-24 05:24:57.941256: step: 964/531, loss: 0.008546366356313229
2023-01-24 05:24:59.006869: step: 968/531, loss: 0.008212319575250149
2023-01-24 05:25:00.077723: step: 972/531, loss: 0.006533846724778414
2023-01-24 05:25:01.156826: step: 976/531, loss: 0.01114641409367323
2023-01-24 05:25:02.226107: step: 980/531, loss: 0.012465793639421463
2023-01-24 05:25:03.291102: step: 984/531, loss: 0.018711285665631294
2023-01-24 05:25:04.345374: step: 988/531, loss: 0.010686461813747883
2023-01-24 05:25:05.397885: step: 992/531, loss: 0.009988091886043549
2023-01-24 05:25:06.432693: step: 996/531, loss: 0.011504275724291801
2023-01-24 05:25:07.477123: step: 1000/531, loss: 0.03524003177881241
2023-01-24 05:25:08.550347: step: 1004/531, loss: 0.002620745450258255
2023-01-24 05:25:09.615778: step: 1008/531, loss: 0.020677056163549423
2023-01-24 05:25:10.661182: step: 1012/531, loss: 0.010407635010778904
2023-01-24 05:25:11.735449: step: 1016/531, loss: 0.054459091275930405
2023-01-24 05:25:12.791414: step: 1020/531, loss: 0.004039744380861521
2023-01-24 05:25:13.850779: step: 1024/531, loss: 0.008886104449629784
2023-01-24 05:25:14.918792: step: 1028/531, loss: 0.04599504545331001
2023-01-24 05:25:15.985717: step: 1032/531, loss: 0.013574999757111073
2023-01-24 05:25:17.045259: step: 1036/531, loss: 0.008643172681331635
2023-01-24 05:25:18.129804: step: 1040/531, loss: 0.012747419998049736
2023-01-24 05:25:19.203875: step: 1044/531, loss: 0.017689671367406845
2023-01-24 05:25:20.253533: step: 1048/531, loss: 0.012442556209862232
2023-01-24 05:25:21.315983: step: 1052/531, loss: 0.01307733729481697
2023-01-24 05:25:22.397638: step: 1056/531, loss: 0.02727523446083069
2023-01-24 05:25:23.461789: step: 1060/531, loss: 0.07458508014678955
2023-01-24 05:25:24.540958: step: 1064/531, loss: 0.006109400186687708
2023-01-24 05:25:25.596779: step: 1068/531, loss: 0.012386331334710121
2023-01-24 05:25:26.672843: step: 1072/531, loss: 0.009489276446402073
2023-01-24 05:25:27.723064: step: 1076/531, loss: 0.01200362853705883
2023-01-24 05:25:28.779722: step: 1080/531, loss: 0.025578133761882782
2023-01-24 05:25:29.838654: step: 1084/531, loss: 0.038195353001356125
2023-01-24 05:25:30.902970: step: 1088/531, loss: 0.020360831171274185
2023-01-24 05:25:31.973695: step: 1092/531, loss: 0.019183607771992683
2023-01-24 05:25:33.040949: step: 1096/531, loss: 0.05920606106519699
2023-01-24 05:25:34.096290: step: 1100/531, loss: 0.018724963068962097
2023-01-24 05:25:35.151262: step: 1104/531, loss: 0.043291497975587845
2023-01-24 05:25:36.220528: step: 1108/531, loss: 0.01643366925418377
2023-01-24 05:25:37.302351: step: 1112/531, loss: 0.033016398549079895
2023-01-24 05:25:38.370500: step: 1116/531, loss: 0.015161125920712948
2023-01-24 05:25:39.451387: step: 1120/531, loss: 0.007837921380996704
2023-01-24 05:25:40.503828: step: 1124/531, loss: 0.015348638407886028
2023-01-24 05:25:41.571380: step: 1128/531, loss: 0.0284282099455595
2023-01-24 05:25:42.641034: step: 1132/531, loss: 0.03275051712989807
2023-01-24 05:25:43.707471: step: 1136/531, loss: 0.016015522181987762
2023-01-24 05:25:44.753616: step: 1140/531, loss: 0.005391702521592379
2023-01-24 05:25:45.821360: step: 1144/531, loss: 0.006712976843118668
2023-01-24 05:25:46.873156: step: 1148/531, loss: 0.0070574008859694
2023-01-24 05:25:47.927129: step: 1152/531, loss: 0.005472483579069376
2023-01-24 05:25:48.985340: step: 1156/531, loss: 0.04423312470316887
2023-01-24 05:25:50.048245: step: 1160/531, loss: 0.0072450158186256886
2023-01-24 05:25:51.117375: step: 1164/531, loss: 0.01512818317860365
2023-01-24 05:25:52.182298: step: 1168/531, loss: 0.009336884133517742
2023-01-24 05:25:53.254503: step: 1172/531, loss: 0.018048180267214775
2023-01-24 05:25:54.312481: step: 1176/531, loss: 0.03046495094895363
2023-01-24 05:25:55.367905: step: 1180/531, loss: 0.01297029945999384
2023-01-24 05:25:56.441430: step: 1184/531, loss: 0.0062399026937782764
2023-01-24 05:25:57.504068: step: 1188/531, loss: 0.010551639832556248
2023-01-24 05:25:58.574351: step: 1192/531, loss: 0.010108751244843006
2023-01-24 05:25:59.651329: step: 1196/531, loss: 0.015173581428825855
2023-01-24 05:26:00.731234: step: 1200/531, loss: 0.008416966535151005
2023-01-24 05:26:01.791318: step: 1204/531, loss: 0.04106985405087471
2023-01-24 05:26:02.874759: step: 1208/531, loss: 0.007257617078721523
2023-01-24 05:26:03.951402: step: 1212/531, loss: 0.010450026951730251
2023-01-24 05:26:05.022580: step: 1216/531, loss: 0.04543720930814743
2023-01-24 05:26:06.093850: step: 1220/531, loss: 0.010831048712134361
2023-01-24 05:26:07.163244: step: 1224/531, loss: 0.05159803107380867
2023-01-24 05:26:08.233916: step: 1228/531, loss: 0.016074061393737793
2023-01-24 05:26:09.300105: step: 1232/531, loss: 0.0320110097527504
2023-01-24 05:26:10.355673: step: 1236/531, loss: 0.025435796007514
2023-01-24 05:26:11.405129: step: 1240/531, loss: 0.007534940727055073
2023-01-24 05:26:12.464943: step: 1244/531, loss: 0.012176496908068657
2023-01-24 05:26:13.520153: step: 1248/531, loss: 0.05254765599966049
2023-01-24 05:26:14.585587: step: 1252/531, loss: 0.010222867131233215
2023-01-24 05:26:15.657988: step: 1256/531, loss: 0.028361370787024498
2023-01-24 05:26:16.723085: step: 1260/531, loss: 0.0041364035569131374
2023-01-24 05:26:17.815946: step: 1264/531, loss: 0.04036647826433182
2023-01-24 05:26:18.891669: step: 1268/531, loss: 0.04490387439727783
2023-01-24 05:26:19.960778: step: 1272/531, loss: 0.031922683119773865
2023-01-24 05:26:21.015910: step: 1276/531, loss: 0.013720821589231491
2023-01-24 05:26:22.073956: step: 1280/531, loss: 0.015734847635030746
2023-01-24 05:26:23.129811: step: 1284/531, loss: 0.010630029253661633
2023-01-24 05:26:24.217959: step: 1288/531, loss: 0.011186394840478897
2023-01-24 05:26:25.279820: step: 1292/531, loss: 0.04478336125612259
2023-01-24 05:26:26.366293: step: 1296/531, loss: 0.011511689983308315
2023-01-24 05:26:27.442209: step: 1300/531, loss: 0.024349957704544067
2023-01-24 05:26:28.492217: step: 1304/531, loss: 0.027117760851979256
2023-01-24 05:26:29.568055: step: 1308/531, loss: 0.002493282314389944
2023-01-24 05:26:30.635251: step: 1312/531, loss: 0.02797669731080532
2023-01-24 05:26:31.694980: step: 1316/531, loss: 0.01398746483027935
2023-01-24 05:26:32.753224: step: 1320/531, loss: 0.01459596399217844
2023-01-24 05:26:33.825349: step: 1324/531, loss: 0.0104651665315032
2023-01-24 05:26:34.882072: step: 1328/531, loss: 0.01089832466095686
2023-01-24 05:26:35.940008: step: 1332/531, loss: 0.011678804643452168
2023-01-24 05:26:37.009285: step: 1336/531, loss: 0.020437197759747505
2023-01-24 05:26:38.082495: step: 1340/531, loss: 0.006575725506991148
2023-01-24 05:26:39.158695: step: 1344/531, loss: 0.012712560594081879
2023-01-24 05:26:40.238133: step: 1348/531, loss: 0.00724458135664463
2023-01-24 05:26:41.306883: step: 1352/531, loss: 0.058703940361738205
2023-01-24 05:26:42.393163: step: 1356/531, loss: 0.006272586528211832
2023-01-24 05:26:43.454802: step: 1360/531, loss: 0.0061026751063764095
2023-01-24 05:26:44.505451: step: 1364/531, loss: 0.007148159202188253
2023-01-24 05:26:45.588955: step: 1368/531, loss: 0.040638335049152374
2023-01-24 05:26:46.646642: step: 1372/531, loss: 0.03636328503489494
2023-01-24 05:26:47.708639: step: 1376/531, loss: 0.007570963818579912
2023-01-24 05:26:48.791785: step: 1380/531, loss: 0.016862431541085243
2023-01-24 05:26:49.880060: step: 1384/531, loss: 0.009899328462779522
2023-01-24 05:26:50.946805: step: 1388/531, loss: 0.012377752922475338
2023-01-24 05:26:51.992370: step: 1392/531, loss: 0.049109891057014465
2023-01-24 05:26:53.057385: step: 1396/531, loss: 0.005925807170569897
2023-01-24 05:26:54.114898: step: 1400/531, loss: 0.009235509671270847
2023-01-24 05:26:55.183940: step: 1404/531, loss: 0.011829568073153496
2023-01-24 05:26:56.259281: step: 1408/531, loss: 0.006862274371087551
2023-01-24 05:26:57.309775: step: 1412/531, loss: 0.05027484893798828
2023-01-24 05:26:58.383122: step: 1416/531, loss: 0.033290036022663116
2023-01-24 05:26:59.461578: step: 1420/531, loss: 0.006521621719002724
2023-01-24 05:27:00.526641: step: 1424/531, loss: 0.03325602412223816
2023-01-24 05:27:01.587000: step: 1428/531, loss: 0.010387971065938473
2023-01-24 05:27:02.643218: step: 1432/531, loss: 0.0127054862678051
2023-01-24 05:27:03.702259: step: 1436/531, loss: 0.011370796710252762
2023-01-24 05:27:04.767384: step: 1440/531, loss: 0.03601215407252312
2023-01-24 05:27:05.819595: step: 1444/531, loss: 0.03154682368040085
2023-01-24 05:27:06.908705: step: 1448/531, loss: 0.005829459987580776
2023-01-24 05:27:07.961777: step: 1452/531, loss: 0.07624151557683945
2023-01-24 05:27:09.038203: step: 1456/531, loss: 0.01008535921573639
2023-01-24 05:27:10.108012: step: 1460/531, loss: 0.007337359711527824
2023-01-24 05:27:11.166822: step: 1464/531, loss: 0.0547441802918911
2023-01-24 05:27:12.231794: step: 1468/531, loss: 0.008347827941179276
2023-01-24 05:27:13.299943: step: 1472/531, loss: 0.005240162368863821
2023-01-24 05:27:14.369683: step: 1476/531, loss: 0.02310614287853241
2023-01-24 05:27:15.437534: step: 1480/531, loss: 0.004760191310197115
2023-01-24 05:27:16.513481: step: 1484/531, loss: 0.008953658863902092
2023-01-24 05:27:17.588980: step: 1488/531, loss: 0.025950385257601738
2023-01-24 05:27:18.650685: step: 1492/531, loss: 0.007313200272619724
2023-01-24 05:27:19.728678: step: 1496/531, loss: 0.007858707569539547
2023-01-24 05:27:20.799898: step: 1500/531, loss: 0.037678711116313934
2023-01-24 05:27:21.854508: step: 1504/531, loss: 0.008985237218439579
2023-01-24 05:27:22.938963: step: 1508/531, loss: 0.034513480961322784
2023-01-24 05:27:24.014963: step: 1512/531, loss: 0.008745499886572361
2023-01-24 05:27:25.087606: step: 1516/531, loss: 0.010591990314424038
2023-01-24 05:27:26.156649: step: 1520/531, loss: 0.008706007152795792
2023-01-24 05:27:27.221855: step: 1524/531, loss: 0.018371237441897392
2023-01-24 05:27:28.284478: step: 1528/531, loss: 0.012669135816395283
2023-01-24 05:27:29.349054: step: 1532/531, loss: 0.0063010770827531815
2023-01-24 05:27:30.426795: step: 1536/531, loss: 0.043510716408491135
2023-01-24 05:27:31.501648: step: 1540/531, loss: 0.08390334248542786
2023-01-24 05:27:32.561002: step: 1544/531, loss: 0.01373217161744833
2023-01-24 05:27:33.605083: step: 1548/531, loss: 7.701742288190871e-05
2023-01-24 05:27:34.661820: step: 1552/531, loss: 0.008855289779603481
2023-01-24 05:27:35.724293: step: 1556/531, loss: 0.009088132530450821
2023-01-24 05:27:36.808823: step: 1560/531, loss: 0.010419655591249466
2023-01-24 05:27:37.894784: step: 1564/531, loss: 0.012826536782085896
2023-01-24 05:27:38.938170: step: 1568/531, loss: 0.01423854473978281
2023-01-24 05:27:39.987961: step: 1572/531, loss: 0.011211882345378399
2023-01-24 05:27:41.058178: step: 1576/531, loss: 0.024514595046639442
2023-01-24 05:27:42.126351: step: 1580/531, loss: 0.004648515954613686
2023-01-24 05:27:43.176181: step: 1584/531, loss: 0.03818988427519798
2023-01-24 05:27:44.250267: step: 1588/531, loss: 0.03093668259680271
2023-01-24 05:27:45.329674: step: 1592/531, loss: 0.009916197508573532
2023-01-24 05:27:46.407882: step: 1596/531, loss: 0.04565809667110443
2023-01-24 05:27:47.466178: step: 1600/531, loss: 0.009167956188321114
2023-01-24 05:27:48.526086: step: 1604/531, loss: 0.013539629988372326
2023-01-24 05:27:49.593199: step: 1608/531, loss: 0.02205510064959526
2023-01-24 05:27:50.680513: step: 1612/531, loss: 0.007033591158688068
2023-01-24 05:27:51.730930: step: 1616/531, loss: 0.005123315379023552
2023-01-24 05:27:52.809349: step: 1620/531, loss: 0.03132849931716919
2023-01-24 05:27:53.883062: step: 1624/531, loss: 0.007058056071400642
2023-01-24 05:27:54.959584: step: 1628/531, loss: 0.012796028517186642
2023-01-24 05:27:56.026743: step: 1632/531, loss: 0.009384261444211006
2023-01-24 05:27:57.096952: step: 1636/531, loss: 0.04952043294906616
2023-01-24 05:27:58.168309: step: 1640/531, loss: 0.05762968584895134
2023-01-24 05:27:59.237496: step: 1644/531, loss: 0.04548857361078262
2023-01-24 05:28:00.291731: step: 1648/531, loss: 0.010962730273604393
2023-01-24 05:28:01.363430: step: 1652/531, loss: 0.006005888804793358
2023-01-24 05:28:02.429135: step: 1656/531, loss: 0.0018209691625088453
2023-01-24 05:28:03.505909: step: 1660/531, loss: 0.013071589171886444
2023-01-24 05:28:04.563061: step: 1664/531, loss: 0.015822121873497963
2023-01-24 05:28:05.628147: step: 1668/531, loss: 0.006638388615101576
2023-01-24 05:28:06.700740: step: 1672/531, loss: 0.01161070354282856
2023-01-24 05:28:07.754123: step: 1676/531, loss: 0.0159497931599617
2023-01-24 05:28:08.827076: step: 1680/531, loss: 0.012878895737230778
2023-01-24 05:28:09.896089: step: 1684/531, loss: 0.014363139867782593
2023-01-24 05:28:10.974881: step: 1688/531, loss: 0.007820959202945232
2023-01-24 05:28:12.099891: step: 1692/531, loss: 0.012973114848136902
2023-01-24 05:28:13.195797: step: 1696/531, loss: 0.041471242904663086
2023-01-24 05:28:14.265697: step: 1700/531, loss: 0.023479929193854332
2023-01-24 05:28:15.336400: step: 1704/531, loss: 0.007520216982811689
2023-01-24 05:28:16.413949: step: 1708/531, loss: 0.001234938157722354
2023-01-24 05:28:17.473102: step: 1712/531, loss: 0.0073923030868172646
2023-01-24 05:28:18.525912: step: 1716/531, loss: 0.006445819977670908
2023-01-24 05:28:19.600574: step: 1720/531, loss: 0.01131470873951912
2023-01-24 05:28:20.676639: step: 1724/531, loss: 0.028294507414102554
2023-01-24 05:28:21.731119: step: 1728/531, loss: 0.006392807699739933
2023-01-24 05:28:22.799338: step: 1732/531, loss: 0.003950975835323334
2023-01-24 05:28:23.873159: step: 1736/531, loss: 0.008274729363620281
2023-01-24 05:28:24.950689: step: 1740/531, loss: 0.07794395089149475
2023-01-24 05:28:26.023284: step: 1744/531, loss: 0.005518303252756596
2023-01-24 05:28:27.089402: step: 1748/531, loss: 0.031895626336336136
2023-01-24 05:28:28.198906: step: 1752/531, loss: 0.006316723767668009
2023-01-24 05:28:29.263206: step: 1756/531, loss: 0.007330481894314289
2023-01-24 05:28:30.338207: step: 1760/531, loss: 0.034529659897089005
2023-01-24 05:28:31.417732: step: 1764/531, loss: 0.0036982884630560875
2023-01-24 05:28:32.489598: step: 1768/531, loss: 0.0050541311502456665
2023-01-24 05:28:33.542512: step: 1772/531, loss: 0.007315453141927719
2023-01-24 05:28:34.610023: step: 1776/531, loss: 0.023043112829327583
2023-01-24 05:28:35.670851: step: 1780/531, loss: 0.014776111580431461
2023-01-24 05:28:36.753428: step: 1784/531, loss: 0.012547774240374565
2023-01-24 05:28:37.828977: step: 1788/531, loss: 0.04544464498758316
2023-01-24 05:28:38.888118: step: 1792/531, loss: 0.008483555167913437
2023-01-24 05:28:39.959353: step: 1796/531, loss: 0.01034250296652317
2023-01-24 05:28:41.034107: step: 1800/531, loss: 0.0055771032348275185
2023-01-24 05:28:42.116193: step: 1804/531, loss: 0.033846691250801086
2023-01-24 05:28:43.175445: step: 1808/531, loss: 0.007275803480297327
2023-01-24 05:28:44.247589: step: 1812/531, loss: 0.013520680367946625
2023-01-24 05:28:45.327271: step: 1816/531, loss: 0.016886606812477112
2023-01-24 05:28:46.397103: step: 1820/531, loss: 0.041414789855480194
2023-01-24 05:28:47.455565: step: 1824/531, loss: 0.046005189418792725
2023-01-24 05:28:48.518662: step: 1828/531, loss: 0.00952172838151455
2023-01-24 05:28:49.586756: step: 1832/531, loss: 0.035623155534267426
2023-01-24 05:28:50.673512: step: 1836/531, loss: 0.0112422164529562
2023-01-24 05:28:51.761405: step: 1840/531, loss: 0.006985026877373457
2023-01-24 05:28:52.827105: step: 1844/531, loss: 0.04322997108101845
2023-01-24 05:28:53.881921: step: 1848/531, loss: 0.009377659298479557
2023-01-24 05:28:54.942697: step: 1852/531, loss: 0.011422567069530487
2023-01-24 05:28:56.016564: step: 1856/531, loss: 0.043231479823589325
2023-01-24 05:28:57.075145: step: 1860/531, loss: 0.01586301252245903
2023-01-24 05:28:58.150111: step: 1864/531, loss: 0.009389316663146019
2023-01-24 05:28:59.227035: step: 1868/531, loss: 0.008753849193453789
2023-01-24 05:29:00.293380: step: 1872/531, loss: 0.009196775034070015
2023-01-24 05:29:01.358949: step: 1876/531, loss: 0.020064661279320717
2023-01-24 05:29:02.412630: step: 1880/531, loss: 0.01364896260201931
2023-01-24 05:29:03.472521: step: 1884/531, loss: 0.009153665974736214
2023-01-24 05:29:04.537991: step: 1888/531, loss: 0.005034239497035742
2023-01-24 05:29:05.601280: step: 1892/531, loss: 0.005006608087569475
2023-01-24 05:29:06.677214: step: 1896/531, loss: 0.008844244293868542
2023-01-24 05:29:07.745199: step: 1900/531, loss: 0.011331385001540184
2023-01-24 05:29:08.821007: step: 1904/531, loss: 0.038331806659698486
2023-01-24 05:29:09.901936: step: 1908/531, loss: 0.005373641848564148
2023-01-24 05:29:10.968409: step: 1912/531, loss: 0.007340161595493555
2023-01-24 05:29:12.034199: step: 1916/531, loss: 0.03102702647447586
2023-01-24 05:29:13.092897: step: 1920/531, loss: 0.05088759586215019
2023-01-24 05:29:14.157219: step: 1924/531, loss: 0.006846578326076269
2023-01-24 05:29:15.223213: step: 1928/531, loss: 0.011807342059910297
2023-01-24 05:29:16.297192: step: 1932/531, loss: 0.030191076919436455
2023-01-24 05:29:17.366249: step: 1936/531, loss: 0.007880610413849354
2023-01-24 05:29:18.433688: step: 1940/531, loss: 0.007350956555455923
2023-01-24 05:29:19.511858: step: 1944/531, loss: 0.031131573021411896
2023-01-24 05:29:20.581307: step: 1948/531, loss: 0.07715418934822083
2023-01-24 05:29:21.640413: step: 1952/531, loss: 0.03203938901424408
2023-01-24 05:29:22.719142: step: 1956/531, loss: 0.007324943318963051
2023-01-24 05:29:23.784798: step: 1960/531, loss: 0.010838370770215988
2023-01-24 05:29:24.859292: step: 1964/531, loss: 0.03717128932476044
2023-01-24 05:29:25.931183: step: 1968/531, loss: 0.0065204789862036705
2023-01-24 05:29:27.000743: step: 1972/531, loss: 0.012113319709897041
2023-01-24 05:29:28.065907: step: 1976/531, loss: 0.02180514857172966
2023-01-24 05:29:29.130524: step: 1980/531, loss: 0.005178001243621111
2023-01-24 05:29:30.187754: step: 1984/531, loss: 0.010195231065154076
2023-01-24 05:29:31.243848: step: 1988/531, loss: 0.007839050143957138
2023-01-24 05:29:32.332298: step: 1992/531, loss: 0.009247769601643085
2023-01-24 05:29:33.398316: step: 1996/531, loss: 0.012342852540314198
2023-01-24 05:29:34.452343: step: 2000/531, loss: 0.009161161258816719
2023-01-24 05:29:35.538681: step: 2004/531, loss: 0.0052819461561739445
2023-01-24 05:29:36.612390: step: 2008/531, loss: 0.007459281012415886
2023-01-24 05:29:37.673263: step: 2012/531, loss: 0.011270435526967049
2023-01-24 05:29:38.728128: step: 2016/531, loss: 0.030428921803832054
2023-01-24 05:29:39.797223: step: 2020/531, loss: 0.014814364723861217
2023-01-24 05:29:40.866604: step: 2024/531, loss: 0.027404872700572014
2023-01-24 05:29:41.937865: step: 2028/531, loss: 0.01005913782864809
2023-01-24 05:29:43.008192: step: 2032/531, loss: 0.03193280100822449
2023-01-24 05:29:44.071008: step: 2036/531, loss: 0.018321385607123375
2023-01-24 05:29:45.126152: step: 2040/531, loss: 0.019345005974173546
2023-01-24 05:29:46.184196: step: 2044/531, loss: 5.868716471013613e-05
2023-01-24 05:29:47.232921: step: 2048/531, loss: 0.00970078818500042
2023-01-24 05:29:48.305876: step: 2052/531, loss: 0.011111809872090816
2023-01-24 05:29:49.363926: step: 2056/531, loss: 0.03218020871281624
2023-01-24 05:29:50.412724: step: 2060/531, loss: 0.021760791540145874
2023-01-24 05:29:51.461098: step: 2064/531, loss: 0.04120469093322754
2023-01-24 05:29:52.524582: step: 2068/531, loss: 0.010430751368403435
2023-01-24 05:29:53.568459: step: 2072/531, loss: 0.026210544630885124
2023-01-24 05:29:54.643972: step: 2076/531, loss: 0.007317809853702784
2023-01-24 05:29:55.713381: step: 2080/531, loss: 0.015261203050613403
2023-01-24 05:29:56.778979: step: 2084/531, loss: 0.013149858452379704
2023-01-24 05:29:57.829650: step: 2088/531, loss: 0.0021271780133247375
2023-01-24 05:29:58.901904: step: 2092/531, loss: 0.009499236941337585
2023-01-24 05:29:59.947320: step: 2096/531, loss: 0.007625204510986805
2023-01-24 05:30:01.030041: step: 2100/531, loss: 0.013872173614799976
2023-01-24 05:30:02.081923: step: 2104/531, loss: 0.006319490727037191
2023-01-24 05:30:03.168806: step: 2108/531, loss: 0.005811006762087345
2023-01-24 05:30:04.247914: step: 2112/531, loss: 0.019926337525248528
2023-01-24 05:30:05.296180: step: 2116/531, loss: 0.007904676720499992
2023-01-24 05:30:06.345248: step: 2120/531, loss: 0.008954621851444244
2023-01-24 05:30:07.417679: step: 2124/531, loss: 0.034259598702192307
==================================================
Loss: 0.022
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831259775426596, 'r': 0.32278545356535265, 'f1': 0.350376795116253}, 'combined': 0.258172375348818, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.37707474114617634, 'r': 0.275750780044679, 'f1': 0.31854959903078023}, 'combined': 0.19946563677628296, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3649282870896924, 'r': 0.3399995995465635, 'f1': 0.3520231610236522}, 'combined': 0.25938548707005954, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3724664793460567, 'r': 0.2848075513845411, 'f1': 0.3227915937511049}, 'combined': 0.20003986091617768, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34422553947655926, 'r': 0.32463015772267545, 'f1': 0.33414080687470693}, 'combined': 0.2462090155918893, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.39597560386952446, 'r': 0.28804723530580933, 'f1': 0.3334966945860363}, 'combined': 0.22123048056697459, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.43478260869565216, 'f1': 0.425531914893617}, 'combined': 0.2127659574468085, 'stategy': 1, 'epoch': 0}
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, 'stategy': 1, 'epoch': 0}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3831259775426596, 'r': 0.32278545356535265, 'f1': 0.350376795116253}, 'combined': 0.258172375348818, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.37707474114617634, 'r': 0.275750780044679, 'f1': 0.31854959903078023}, 'combined': 0.19946563677628296, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3649282870896924, 'r': 0.3399995995465635, 'f1': 0.3520231610236522}, 'combined': 0.25938548707005954, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3724664793460567, 'r': 0.2848075513845411, 'f1': 0.3227915937511049}, 'combined': 0.20003986091617768, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4166666666666667, 'r': 0.43478260869565216, 'f1': 0.425531914893617}, 'combined': 0.2127659574468085, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34422553947655926, 'r': 0.32463015772267545, 'f1': 0.33414080687470693}, 'combined': 0.2462090155918893, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.39597560386952446, 'r': 0.28804723530580933, 'f1': 0.3334966945860363}, 'combined': 0.22123048056697459, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:33:05.235511: step: 4/531, loss: 0.09178076684474945
2023-01-24 05:33:06.290265: step: 8/531, loss: 0.009556343778967857
2023-01-24 05:33:07.334567: step: 12/531, loss: 0.0329352468252182
2023-01-24 05:33:08.403672: step: 16/531, loss: 0.019852932542562485
2023-01-24 05:33:09.456231: step: 20/531, loss: 0.023449081927537918
2023-01-24 05:33:10.510946: step: 24/531, loss: 0.018652426078915596
2023-01-24 05:33:11.579887: step: 28/531, loss: 0.014825774356722832
2023-01-24 05:33:12.660589: step: 32/531, loss: 0.013731390237808228
2023-01-24 05:33:13.721118: step: 36/531, loss: 0.023465080186724663
2023-01-24 05:33:14.768818: step: 40/531, loss: 0.0033914686646312475
2023-01-24 05:33:15.813232: step: 44/531, loss: 0.03890390321612358
2023-01-24 05:33:16.864716: step: 48/531, loss: 0.012838237918913364
2023-01-24 05:33:17.924718: step: 52/531, loss: 0.026646077632904053
2023-01-24 05:33:18.973501: step: 56/531, loss: 0.012675140984356403
2023-01-24 05:33:20.047663: step: 60/531, loss: 0.007770244963467121
2023-01-24 05:33:21.106528: step: 64/531, loss: 0.017953475937247276
2023-01-24 05:33:22.147484: step: 68/531, loss: 0.011134296655654907
2023-01-24 05:33:23.199345: step: 72/531, loss: 0.00889762956649065
2023-01-24 05:33:24.278021: step: 76/531, loss: 0.0445646308362484
2023-01-24 05:33:25.319899: step: 80/531, loss: 0.00789334811270237
2023-01-24 05:33:26.387563: step: 84/531, loss: 0.005396140739321709
2023-01-24 05:33:27.437818: step: 88/531, loss: 0.009716407395899296
2023-01-24 05:33:28.493260: step: 92/531, loss: 0.010318266227841377
2023-01-24 05:33:29.557092: step: 96/531, loss: 0.05564114451408386
2023-01-24 05:33:30.622441: step: 100/531, loss: 0.014927938580513
2023-01-24 05:33:31.690557: step: 104/531, loss: 0.03708529844880104
2023-01-24 05:33:32.751977: step: 108/531, loss: 0.015157019719481468
2023-01-24 05:33:33.814872: step: 112/531, loss: 0.01258289534598589
2023-01-24 05:33:34.878998: step: 116/531, loss: 0.018509941175580025
2023-01-24 05:33:35.947690: step: 120/531, loss: 0.07344067841768265
2023-01-24 05:33:36.993788: step: 124/531, loss: 0.005568209104239941
2023-01-24 05:33:38.078133: step: 128/531, loss: 0.026432767510414124
2023-01-24 05:33:39.158898: step: 132/531, loss: 0.02401437796652317
2023-01-24 05:33:40.231281: step: 136/531, loss: 0.009684343822300434
2023-01-24 05:33:41.292565: step: 140/531, loss: 0.012389306910336018
2023-01-24 05:33:42.351294: step: 144/531, loss: 0.010250166058540344
2023-01-24 05:33:43.412488: step: 148/531, loss: 0.04310257360339165
2023-01-24 05:33:44.483037: step: 152/531, loss: 0.021831609308719635
2023-01-24 05:33:45.532352: step: 156/531, loss: 0.009862443432211876
2023-01-24 05:33:46.605991: step: 160/531, loss: 0.027956031262874603
2023-01-24 05:33:47.666216: step: 164/531, loss: 0.048135023564100266
2023-01-24 05:33:48.724325: step: 168/531, loss: 0.019551318138837814
2023-01-24 05:33:49.790186: step: 172/531, loss: 0.01896512135863304
2023-01-24 05:33:50.852775: step: 176/531, loss: 0.013906910084187984
2023-01-24 05:33:51.899677: step: 180/531, loss: 0.022282781079411507
2023-01-24 05:33:52.965361: step: 184/531, loss: 0.008715187199413776
2023-01-24 05:33:54.024150: step: 188/531, loss: 0.0077690239995718
2023-01-24 05:33:55.073683: step: 192/531, loss: 0.004787336103618145
2023-01-24 05:33:56.138479: step: 196/531, loss: 0.041909441351890564
2023-01-24 05:33:57.203010: step: 200/531, loss: 0.009868372231721878
2023-01-24 05:33:58.276071: step: 204/531, loss: 0.011924352496862411
2023-01-24 05:33:59.341470: step: 208/531, loss: 0.003855706425383687
2023-01-24 05:34:00.406404: step: 212/531, loss: 0.009761754423379898
2023-01-24 05:34:01.486263: step: 216/531, loss: 0.0067886305041611195
2023-01-24 05:34:02.559406: step: 220/531, loss: 0.007311253808438778
2023-01-24 05:34:03.633721: step: 224/531, loss: 0.0353132002055645
2023-01-24 05:34:04.711407: step: 228/531, loss: 0.0034550772979855537
2023-01-24 05:34:05.790650: step: 232/531, loss: 0.032790686935186386
2023-01-24 05:34:06.855392: step: 236/531, loss: 0.005856727249920368
2023-01-24 05:34:07.921633: step: 240/531, loss: 0.0110018290579319
2023-01-24 05:34:08.992949: step: 244/531, loss: 0.024778563529253006
2023-01-24 05:34:10.079747: step: 248/531, loss: 0.008650518953800201
2023-01-24 05:34:11.142487: step: 252/531, loss: 0.004926738329231739
2023-01-24 05:34:12.210018: step: 256/531, loss: 0.012716108001768589
2023-01-24 05:34:13.281928: step: 260/531, loss: 0.006069564260542393
2023-01-24 05:34:14.350582: step: 264/531, loss: 0.005527488887310028
2023-01-24 05:34:15.433955: step: 268/531, loss: 0.008695040829479694
2023-01-24 05:34:16.493891: step: 272/531, loss: 0.0069482941180467606
2023-01-24 05:34:17.574924: step: 276/531, loss: 0.011258721351623535
2023-01-24 05:34:18.656963: step: 280/531, loss: 0.0829072967171669
2023-01-24 05:34:19.745042: step: 284/531, loss: 0.008146488107740879
2023-01-24 05:34:20.811290: step: 288/531, loss: 0.007282691076397896
2023-01-24 05:34:21.890044: step: 292/531, loss: 0.016103364527225494
2023-01-24 05:34:22.988927: step: 296/531, loss: 0.005875722970813513
2023-01-24 05:34:24.050049: step: 300/531, loss: 0.0035357805900275707
2023-01-24 05:34:25.109000: step: 304/531, loss: 0.0034886773210018873
2023-01-24 05:34:26.171610: step: 308/531, loss: 0.016442179679870605
2023-01-24 05:34:27.230986: step: 312/531, loss: 0.019149813801050186
2023-01-24 05:34:28.306865: step: 316/531, loss: 0.022424906492233276
2023-01-24 05:34:29.373221: step: 320/531, loss: 0.010963410139083862
2023-01-24 05:34:30.446332: step: 324/531, loss: 0.006567399483174086
2023-01-24 05:34:31.512225: step: 328/531, loss: 0.0008040042594075203
2023-01-24 05:34:32.577030: step: 332/531, loss: 0.01717044971883297
2023-01-24 05:34:33.656129: step: 336/531, loss: 0.012676534242928028
2023-01-24 05:34:34.712260: step: 340/531, loss: 0.006378055550158024
2023-01-24 05:34:35.765166: step: 344/531, loss: 0.012150856666266918
2023-01-24 05:34:36.822850: step: 348/531, loss: 0.06427229940891266
2023-01-24 05:34:37.898638: step: 352/531, loss: 0.01812794804573059
2023-01-24 05:34:38.967492: step: 356/531, loss: 0.012500600889325142
2023-01-24 05:34:40.013963: step: 360/531, loss: 0.0054733785800635815
2023-01-24 05:34:41.082981: step: 364/531, loss: 0.0012258852366358042
2023-01-24 05:34:42.181461: step: 368/531, loss: 0.0026976759545505047
2023-01-24 05:34:43.261763: step: 372/531, loss: 0.020970840007066727
2023-01-24 05:34:44.325173: step: 376/531, loss: 0.02774849906563759
2023-01-24 05:34:45.391368: step: 380/531, loss: 0.03277068957686424
2023-01-24 05:34:46.459273: step: 384/531, loss: 0.01633204147219658
2023-01-24 05:34:47.520209: step: 388/531, loss: 0.007651320658624172
2023-01-24 05:34:48.604740: step: 392/531, loss: 0.009806823916733265
2023-01-24 05:34:49.676904: step: 396/531, loss: 0.006372191943228245
2023-01-24 05:34:50.736536: step: 400/531, loss: 0.015485931187868118
2023-01-24 05:34:51.812435: step: 404/531, loss: 0.005884003359824419
2023-01-24 05:34:52.894313: step: 408/531, loss: 0.004996773321181536
2023-01-24 05:34:53.967511: step: 412/531, loss: 0.03665619716048241
2023-01-24 05:34:55.031882: step: 416/531, loss: 0.0
2023-01-24 05:34:56.082181: step: 420/531, loss: 0.01944882422685623
2023-01-24 05:34:57.154155: step: 424/531, loss: 0.0429818257689476
2023-01-24 05:34:58.211522: step: 428/531, loss: 0.02300003357231617
2023-01-24 05:34:59.289633: step: 432/531, loss: 0.007280625402927399
2023-01-24 05:35:00.346671: step: 436/531, loss: 0.007473290432244539
2023-01-24 05:35:01.409036: step: 440/531, loss: 0.007171986158937216
2023-01-24 05:35:02.476457: step: 444/531, loss: 0.04028509929776192
2023-01-24 05:35:03.552066: step: 448/531, loss: 0.011428830213844776
2023-01-24 05:35:04.609190: step: 452/531, loss: 0.01570049859583378
2023-01-24 05:35:05.673724: step: 456/531, loss: 0.012460127472877502
2023-01-24 05:35:06.731286: step: 460/531, loss: 0.0266293715685606
2023-01-24 05:35:07.811311: step: 464/531, loss: 0.008816512301564217
2023-01-24 05:35:08.869055: step: 468/531, loss: 0.006196875590831041
2023-01-24 05:35:09.934399: step: 472/531, loss: 0.006693840026855469
2023-01-24 05:35:11.035438: step: 476/531, loss: 0.006907900795340538
2023-01-24 05:35:12.112636: step: 480/531, loss: 0.013373376801609993
2023-01-24 05:35:13.186434: step: 484/531, loss: 0.009013530798256397
2023-01-24 05:35:14.239999: step: 488/531, loss: 0.00850666407495737
2023-01-24 05:35:15.294180: step: 492/531, loss: 0.001762406900525093
2023-01-24 05:35:16.377882: step: 496/531, loss: 0.03610870614647865
2023-01-24 05:35:17.447742: step: 500/531, loss: 0.007061814423650503
2023-01-24 05:35:18.528881: step: 504/531, loss: 0.006155211012810469
2023-01-24 05:35:19.607703: step: 508/531, loss: 0.01041685976088047
2023-01-24 05:35:20.665345: step: 512/531, loss: 0.011248735710978508
2023-01-24 05:35:21.737462: step: 516/531, loss: 0.02531476691365242
2023-01-24 05:35:22.814848: step: 520/531, loss: 0.01878204382956028
2023-01-24 05:35:23.899725: step: 524/531, loss: 0.007710628677159548
2023-01-24 05:35:24.967840: step: 528/531, loss: 0.014674684964120388
2023-01-24 05:35:26.039058: step: 532/531, loss: 0.02699761837720871
2023-01-24 05:35:27.094947: step: 536/531, loss: 0.0042434511706233025
2023-01-24 05:35:28.162559: step: 540/531, loss: 0.02224177122116089
2023-01-24 05:35:29.237545: step: 544/531, loss: 0.005734087899327278
2023-01-24 05:35:30.309070: step: 548/531, loss: 0.049987345933914185
2023-01-24 05:35:31.372228: step: 552/531, loss: 0.013814532198011875
2023-01-24 05:35:32.449570: step: 556/531, loss: 0.009399447590112686
2023-01-24 05:35:33.516358: step: 560/531, loss: 0.05782898887991905
2023-01-24 05:35:34.577319: step: 564/531, loss: 0.005294196307659149
2023-01-24 05:35:35.641149: step: 568/531, loss: 0.010895602405071259
2023-01-24 05:35:36.692176: step: 572/531, loss: 0.012185837142169476
2023-01-24 05:35:37.748424: step: 576/531, loss: 0.010583250783383846
2023-01-24 05:35:38.832933: step: 580/531, loss: 0.014942733570933342
2023-01-24 05:35:39.899091: step: 584/531, loss: 0.0027758022770285606
2023-01-24 05:35:40.955191: step: 588/531, loss: 0.012569941580295563
2023-01-24 05:35:42.032592: step: 592/531, loss: 0.03456798195838928
2023-01-24 05:35:43.104212: step: 596/531, loss: 0.02051612176001072
2023-01-24 05:35:44.175224: step: 600/531, loss: 0.009913983754813671
2023-01-24 05:35:45.244714: step: 604/531, loss: 0.011612809263169765
2023-01-24 05:35:46.321567: step: 608/531, loss: 0.005555942188948393
2023-01-24 05:35:47.402149: step: 612/531, loss: 0.010517431423068047
2023-01-24 05:35:48.474528: step: 616/531, loss: 0.0173844862729311
2023-01-24 05:35:49.536095: step: 620/531, loss: 0.0014835285255685449
2023-01-24 05:35:50.610208: step: 624/531, loss: 0.058384351432323456
2023-01-24 05:35:51.691984: step: 628/531, loss: 0.010259066708385944
2023-01-24 05:35:52.756548: step: 632/531, loss: 0.010645410977303982
2023-01-24 05:35:53.826175: step: 636/531, loss: 0.008815240114927292
2023-01-24 05:35:54.925643: step: 640/531, loss: 0.007068410515785217
2023-01-24 05:35:55.999380: step: 644/531, loss: 0.03986091539263725
2023-01-24 05:35:57.058288: step: 648/531, loss: 0.013599403202533722
2023-01-24 05:35:58.137951: step: 652/531, loss: 0.0025150806177407503
2023-01-24 05:35:59.217588: step: 656/531, loss: 0.010195252485573292
2023-01-24 05:36:00.288537: step: 660/531, loss: 0.016416076570749283
2023-01-24 05:36:01.366888: step: 664/531, loss: 0.006640026345849037
2023-01-24 05:36:02.430451: step: 668/531, loss: 0.050393760204315186
2023-01-24 05:36:03.492175: step: 672/531, loss: 0.009499446488916874
2023-01-24 05:36:04.573026: step: 676/531, loss: 0.051284126937389374
2023-01-24 05:36:05.625858: step: 680/531, loss: 0.023495344445109367
2023-01-24 05:36:06.707040: step: 684/531, loss: 0.0166424959897995
2023-01-24 05:36:07.761962: step: 688/531, loss: 0.002596989506855607
2023-01-24 05:36:08.834957: step: 692/531, loss: 0.03550850600004196
2023-01-24 05:36:09.919574: step: 696/531, loss: 0.004854866769164801
2023-01-24 05:36:10.986880: step: 700/531, loss: 0.021808704361319542
2023-01-24 05:36:12.049203: step: 704/531, loss: 0.013941183686256409
2023-01-24 05:36:13.113500: step: 708/531, loss: 0.09654286503791809
2023-01-24 05:36:14.181749: step: 712/531, loss: 0.009889055974781513
2023-01-24 05:36:15.224544: step: 716/531, loss: 0.0017241982277482748
2023-01-24 05:36:16.299253: step: 720/531, loss: 0.026191428303718567
2023-01-24 05:36:17.360637: step: 724/531, loss: 0.010890468955039978
2023-01-24 05:36:18.450702: step: 728/531, loss: 0.009511811658740044
2023-01-24 05:36:19.522076: step: 732/531, loss: 0.012885295785963535
2023-01-24 05:36:20.574009: step: 736/531, loss: 0.012562588788568974
2023-01-24 05:36:21.670216: step: 740/531, loss: 0.07264727354049683
2023-01-24 05:36:22.743105: step: 744/531, loss: 0.00932356994599104
2023-01-24 05:36:23.806115: step: 748/531, loss: 0.03984125331044197
2023-01-24 05:36:24.875041: step: 752/531, loss: 0.004348627291619778
2023-01-24 05:36:25.937704: step: 756/531, loss: 0.014298013411462307
2023-01-24 05:36:26.996515: step: 760/531, loss: 0.006649958435446024
2023-01-24 05:36:28.064014: step: 764/531, loss: 0.008323272690176964
2023-01-24 05:36:29.133574: step: 768/531, loss: 0.07428687810897827
2023-01-24 05:36:30.207032: step: 772/531, loss: 0.01691368781030178
2023-01-24 05:36:31.268204: step: 776/531, loss: 0.006733793765306473
2023-01-24 05:36:32.310977: step: 780/531, loss: 0.026237420737743378
2023-01-24 05:36:33.400999: step: 784/531, loss: 0.014186098240315914
2023-01-24 05:36:34.475760: step: 788/531, loss: 0.0085311159491539
2023-01-24 05:36:35.558089: step: 792/531, loss: 0.0057366034016013145
2023-01-24 05:36:36.616030: step: 796/531, loss: 0.0037600744981318712
2023-01-24 05:36:37.683310: step: 800/531, loss: 0.0023868680000305176
2023-01-24 05:36:38.735832: step: 804/531, loss: 0.047112684696912766
2023-01-24 05:36:39.801535: step: 808/531, loss: 0.00708191841840744
2023-01-24 05:36:40.864913: step: 812/531, loss: 0.013263104483485222
2023-01-24 05:36:41.940217: step: 816/531, loss: 0.030224021524190903
2023-01-24 05:36:42.987047: step: 820/531, loss: 0.00970078818500042
2023-01-24 05:36:44.044708: step: 824/531, loss: 0.009935368783771992
2023-01-24 05:36:45.117681: step: 828/531, loss: 0.01689828559756279
2023-01-24 05:36:46.187882: step: 832/531, loss: 0.014442265033721924
2023-01-24 05:36:47.253316: step: 836/531, loss: 0.011026089079678059
2023-01-24 05:36:48.322243: step: 840/531, loss: 0.014645881950855255
2023-01-24 05:36:49.373844: step: 844/531, loss: 0.006513155531138182
2023-01-24 05:36:50.433976: step: 848/531, loss: 0.010485423728823662
2023-01-24 05:36:51.496351: step: 852/531, loss: 0.007206744514405727
2023-01-24 05:36:52.557986: step: 856/531, loss: 0.005383828654885292
2023-01-24 05:36:53.634342: step: 860/531, loss: 0.051911529153585434
2023-01-24 05:36:54.697823: step: 864/531, loss: 0.005123678129166365
2023-01-24 05:36:55.748147: step: 868/531, loss: 0.010245547629892826
2023-01-24 05:36:56.806130: step: 872/531, loss: 0.006416060961782932
2023-01-24 05:36:57.871680: step: 876/531, loss: 0.01878443732857704
2023-01-24 05:36:58.921344: step: 880/531, loss: 0.012331430800259113
2023-01-24 05:36:59.989664: step: 884/531, loss: 0.0038081659004092216
2023-01-24 05:37:01.049523: step: 888/531, loss: 0.014018531888723373
2023-01-24 05:37:02.106554: step: 892/531, loss: 0.009234867990016937
2023-01-24 05:37:03.148137: step: 896/531, loss: 0.015506122261285782
2023-01-24 05:37:04.211834: step: 900/531, loss: 0.002232337836176157
2023-01-24 05:37:05.257076: step: 904/531, loss: 0.018577953800559044
2023-01-24 05:37:06.328481: step: 908/531, loss: 0.007903103716671467
2023-01-24 05:37:07.376987: step: 912/531, loss: 0.019865937530994415
2023-01-24 05:37:08.432337: step: 916/531, loss: 0.005732994992285967
2023-01-24 05:37:09.489444: step: 920/531, loss: 0.010244255885481834
2023-01-24 05:37:10.538208: step: 924/531, loss: 0.008030731230974197
2023-01-24 05:37:11.630545: step: 928/531, loss: 0.009935649111866951
2023-01-24 05:37:12.692466: step: 932/531, loss: 0.010212778113782406
2023-01-24 05:37:13.742578: step: 936/531, loss: 0.04242117702960968
2023-01-24 05:37:14.808245: step: 940/531, loss: 0.0030285066459327936
2023-01-24 05:37:15.883537: step: 944/531, loss: 0.03561278432607651
2023-01-24 05:37:16.953620: step: 948/531, loss: 0.02422773838043213
2023-01-24 05:37:18.018977: step: 952/531, loss: 0.005665940698236227
2023-01-24 05:37:19.075324: step: 956/531, loss: 0.02517211064696312
2023-01-24 05:37:20.143461: step: 960/531, loss: 0.012842093594372272
2023-01-24 05:37:21.191282: step: 964/531, loss: 0.07806464284658432
2023-01-24 05:37:22.250965: step: 968/531, loss: 0.00721712177619338
2023-01-24 05:37:23.303348: step: 972/531, loss: 0.00022359513968694955
2023-01-24 05:37:24.374715: step: 976/531, loss: 0.005565779749304056
2023-01-24 05:37:25.445046: step: 980/531, loss: 0.0502593107521534
2023-01-24 05:37:26.502227: step: 984/531, loss: 0.006101043429225683
2023-01-24 05:37:27.548402: step: 988/531, loss: 0.028726443648338318
2023-01-24 05:37:28.613412: step: 992/531, loss: 0.010455455631017685
2023-01-24 05:37:29.673168: step: 996/531, loss: 0.0028423184994608164
2023-01-24 05:37:30.728328: step: 1000/531, loss: 0.005535279866307974
2023-01-24 05:37:31.772092: step: 1004/531, loss: 0.007476668804883957
2023-01-24 05:37:32.818799: step: 1008/531, loss: 0.03956976160407066
2023-01-24 05:37:33.907345: step: 1012/531, loss: 0.01567956618964672
2023-01-24 05:37:34.966675: step: 1016/531, loss: 0.03967675939202309
2023-01-24 05:37:36.018250: step: 1020/531, loss: 0.006127448752522469
2023-01-24 05:37:37.095465: step: 1024/531, loss: 0.017828097566962242
2023-01-24 05:37:38.156962: step: 1028/531, loss: 0.006519016344100237
2023-01-24 05:37:39.215474: step: 1032/531, loss: 0.005050727631896734
2023-01-24 05:37:40.281284: step: 1036/531, loss: 0.005482138134539127
2023-01-24 05:37:41.338286: step: 1040/531, loss: 0.01060046162456274
2023-01-24 05:37:42.409448: step: 1044/531, loss: 0.003469890682026744
2023-01-24 05:37:43.476722: step: 1048/531, loss: 0.0057162027806043625
2023-01-24 05:37:44.532120: step: 1052/531, loss: 0.005085076671093702
2023-01-24 05:37:45.600391: step: 1056/531, loss: 0.010341119021177292
2023-01-24 05:37:46.654654: step: 1060/531, loss: 0.04512256011366844
2023-01-24 05:37:47.704321: step: 1064/531, loss: 0.027469689026474953
2023-01-24 05:37:48.792240: step: 1068/531, loss: 0.010330287739634514
2023-01-24 05:37:49.861425: step: 1072/531, loss: 0.004143772181123495
2023-01-24 05:37:50.922132: step: 1076/531, loss: 0.06753170490264893
2023-01-24 05:37:51.995466: step: 1080/531, loss: 0.0033784378319978714
2023-01-24 05:37:53.057919: step: 1084/531, loss: 0.004873470403254032
2023-01-24 05:37:54.120758: step: 1088/531, loss: 0.005720699671655893
2023-01-24 05:37:55.180502: step: 1092/531, loss: 0.0030614014249294996
2023-01-24 05:37:56.236940: step: 1096/531, loss: 0.028639938682317734
2023-01-24 05:37:57.298240: step: 1100/531, loss: 0.0073258415795862675
2023-01-24 05:37:58.375049: step: 1104/531, loss: 0.027203531935811043
2023-01-24 05:37:59.427073: step: 1108/531, loss: 0.014489049091935158
2023-01-24 05:38:00.497951: step: 1112/531, loss: 0.00576788792386651
2023-01-24 05:38:01.565393: step: 1116/531, loss: 0.009144771844148636
2023-01-24 05:38:02.627941: step: 1120/531, loss: 0.03240538015961647
2023-01-24 05:38:03.686154: step: 1124/531, loss: 0.023965157568454742
2023-01-24 05:38:04.754627: step: 1128/531, loss: 0.005787264090031385
2023-01-24 05:38:05.828222: step: 1132/531, loss: 0.008953070268034935
2023-01-24 05:38:06.904548: step: 1136/531, loss: 0.01851697452366352
2023-01-24 05:38:07.959784: step: 1140/531, loss: 0.013876278884708881
2023-01-24 05:38:09.043524: step: 1144/531, loss: 0.0022372829262167215
2023-01-24 05:38:10.114641: step: 1148/531, loss: 0.0014857390196993947
2023-01-24 05:38:11.174164: step: 1152/531, loss: 0.007147029507905245
2023-01-24 05:38:12.236714: step: 1156/531, loss: 0.0025060686748474836
2023-01-24 05:38:13.297875: step: 1160/531, loss: 0.013159961439669132
2023-01-24 05:38:14.357501: step: 1164/531, loss: 0.006286369636654854
2023-01-24 05:38:15.430714: step: 1168/531, loss: 0.016939081251621246
2023-01-24 05:38:16.490412: step: 1172/531, loss: 0.0035575907677412033
2023-01-24 05:38:17.553526: step: 1176/531, loss: 0.00465867156162858
2023-01-24 05:38:18.616972: step: 1180/531, loss: 0.005843263119459152
2023-01-24 05:38:19.677061: step: 1184/531, loss: 0.003680992405861616
2023-01-24 05:38:20.734133: step: 1188/531, loss: 0.0006899041472934186
2023-01-24 05:38:21.804799: step: 1192/531, loss: 0.0076921251602470875
2023-01-24 05:38:22.856386: step: 1196/531, loss: 0.0034816963598132133
2023-01-24 05:38:23.927419: step: 1200/531, loss: 0.01774633675813675
2023-01-24 05:38:24.982008: step: 1204/531, loss: 0.00540650449693203
2023-01-24 05:38:26.046919: step: 1208/531, loss: 0.012637587264180183
2023-01-24 05:38:27.091777: step: 1212/531, loss: 0.0011300697224214673
2023-01-24 05:38:28.143122: step: 1216/531, loss: 0.0027908890042454004
2023-01-24 05:38:29.218560: step: 1220/531, loss: 0.009684571996331215
2023-01-24 05:38:30.293029: step: 1224/531, loss: 0.02658742293715477
2023-01-24 05:38:31.341913: step: 1228/531, loss: 0.007562708109617233
2023-01-24 05:38:32.416919: step: 1232/531, loss: 0.012605461291968822
2023-01-24 05:38:33.469061: step: 1236/531, loss: 0.006218646187335253
2023-01-24 05:38:34.530868: step: 1240/531, loss: 0.0062874602153897285
2023-01-24 05:38:35.602325: step: 1244/531, loss: 0.0032117431983351707
2023-01-24 05:38:36.663466: step: 1248/531, loss: 0.017528463155031204
2023-01-24 05:38:37.734548: step: 1252/531, loss: 0.015302884392440319
2023-01-24 05:38:38.795801: step: 1256/531, loss: 0.014818764291703701
2023-01-24 05:38:39.860103: step: 1260/531, loss: 0.007478457409888506
2023-01-24 05:38:40.902863: step: 1264/531, loss: 0.007360471412539482
2023-01-24 05:38:41.956067: step: 1268/531, loss: 0.031239191070199013
2023-01-24 05:38:43.015437: step: 1272/531, loss: 0.005239270161837339
2023-01-24 05:38:44.077576: step: 1276/531, loss: 0.014330082572996616
2023-01-24 05:38:45.155289: step: 1280/531, loss: 0.03908878192305565
2023-01-24 05:38:46.211406: step: 1284/531, loss: 0.01593167893588543
2023-01-24 05:38:47.279277: step: 1288/531, loss: 0.0050966511480510235
2023-01-24 05:38:48.342813: step: 1292/531, loss: 0.011381132528185844
2023-01-24 05:38:49.405791: step: 1296/531, loss: 0.005269972607493401
2023-01-24 05:38:50.474565: step: 1300/531, loss: 0.0067209466360509396
2023-01-24 05:38:51.521862: step: 1304/531, loss: 0.008411402814090252
2023-01-24 05:38:52.578864: step: 1308/531, loss: 0.010598246939480305
2023-01-24 05:38:53.641597: step: 1312/531, loss: 0.0056084562093019485
2023-01-24 05:38:54.710221: step: 1316/531, loss: 0.002204101299867034
2023-01-24 05:38:55.792033: step: 1320/531, loss: 0.006579904817044735
2023-01-24 05:38:56.856941: step: 1324/531, loss: 0.010172891430556774
2023-01-24 05:38:57.926209: step: 1328/531, loss: 0.023190589621663094
2023-01-24 05:38:58.983387: step: 1332/531, loss: 0.01168964896351099
2023-01-24 05:39:00.054924: step: 1336/531, loss: 0.010293787345290184
2023-01-24 05:39:01.117373: step: 1340/531, loss: 0.008583199232816696
2023-01-24 05:39:02.176236: step: 1344/531, loss: 0.0009360854746773839
2023-01-24 05:39:03.256293: step: 1348/531, loss: 0.009190468117594719
2023-01-24 05:39:04.320179: step: 1352/531, loss: 0.034403879195451736
2023-01-24 05:39:05.381763: step: 1356/531, loss: 0.009490725584328175
2023-01-24 05:39:06.451046: step: 1360/531, loss: 0.004836771637201309
2023-01-24 05:39:07.523530: step: 1364/531, loss: 0.006449365522712469
2023-01-24 05:39:08.586742: step: 1368/531, loss: 0.002050477545708418
2023-01-24 05:39:09.637714: step: 1372/531, loss: 0.024750513955950737
2023-01-24 05:39:10.684479: step: 1376/531, loss: 0.0036240650806576014
2023-01-24 05:39:11.758353: step: 1380/531, loss: 0.0056877294555306435
2023-01-24 05:39:12.834834: step: 1384/531, loss: 0.008128160610795021
2023-01-24 05:39:13.903052: step: 1388/531, loss: 0.007719332817941904
2023-01-24 05:39:14.980461: step: 1392/531, loss: 0.0063159409910440445
2023-01-24 05:39:16.029438: step: 1396/531, loss: 0.020592328161001205
2023-01-24 05:39:17.088570: step: 1400/531, loss: 0.003002229379490018
2023-01-24 05:39:18.158590: step: 1404/531, loss: 0.018590757623314857
2023-01-24 05:39:19.223200: step: 1408/531, loss: 0.019040344282984734
2023-01-24 05:39:20.299918: step: 1412/531, loss: 0.023021532222628593
2023-01-24 05:39:21.360311: step: 1416/531, loss: 0.003237620461732149
2023-01-24 05:39:22.402109: step: 1420/531, loss: 0.017588037997484207
2023-01-24 05:39:23.494783: step: 1424/531, loss: 0.012304337695240974
2023-01-24 05:39:24.581613: step: 1428/531, loss: 0.003331138053908944
2023-01-24 05:39:25.649957: step: 1432/531, loss: 0.02969825640320778
2023-01-24 05:39:26.714737: step: 1436/531, loss: 0.006468979641795158
2023-01-24 05:39:27.781138: step: 1440/531, loss: 0.008388368412852287
2023-01-24 05:39:28.850681: step: 1444/531, loss: 0.019970454275608063
2023-01-24 05:39:29.925084: step: 1448/531, loss: 0.00469807768240571
2023-01-24 05:39:30.995782: step: 1452/531, loss: 0.002759417751803994
2023-01-24 05:39:32.065782: step: 1456/531, loss: 0.019516875967383385
2023-01-24 05:39:33.124752: step: 1460/531, loss: 0.005682252813130617
2023-01-24 05:39:34.172867: step: 1464/531, loss: 0.001431136392056942
2023-01-24 05:39:35.228430: step: 1468/531, loss: 0.0031800181604921818
2023-01-24 05:39:36.291380: step: 1472/531, loss: 0.023356551304459572
2023-01-24 05:39:37.363830: step: 1476/531, loss: 0.004850280005484819
2023-01-24 05:39:38.417152: step: 1480/531, loss: 0.011429929174482822
2023-01-24 05:39:39.466677: step: 1484/531, loss: 0.003373160259798169
2023-01-24 05:39:40.521284: step: 1488/531, loss: 0.0005578648997470737
2023-01-24 05:39:41.583800: step: 1492/531, loss: 0.005483557935804129
2023-01-24 05:39:42.679810: step: 1496/531, loss: 0.005559155717492104
2023-01-24 05:39:43.729637: step: 1500/531, loss: 0.006850066129118204
2023-01-24 05:39:44.822171: step: 1504/531, loss: 0.0032734123524278402
2023-01-24 05:39:45.905498: step: 1508/531, loss: 0.013615076430141926
2023-01-24 05:39:46.966938: step: 1512/531, loss: 0.004723368678241968
2023-01-24 05:39:48.057772: step: 1516/531, loss: 0.013113846071064472
2023-01-24 05:39:49.125116: step: 1520/531, loss: 0.005154415033757687
2023-01-24 05:39:50.181633: step: 1524/531, loss: 0.007819097489118576
2023-01-24 05:39:51.243213: step: 1528/531, loss: 0.007447626441717148
2023-01-24 05:39:52.288980: step: 1532/531, loss: 0.0016658528475090861
2023-01-24 05:39:53.356398: step: 1536/531, loss: 0.008843150921165943
2023-01-24 05:39:54.423040: step: 1540/531, loss: 0.0042173066176474094
2023-01-24 05:39:55.483747: step: 1544/531, loss: 0.0062405942007899284
2023-01-24 05:39:56.537861: step: 1548/531, loss: 0.005881103221327066
2023-01-24 05:39:57.613786: step: 1552/531, loss: 0.0062689525075256824
2023-01-24 05:39:58.680270: step: 1556/531, loss: 0.006860203109681606
2023-01-24 05:39:59.741967: step: 1560/531, loss: 0.005478202365338802
2023-01-24 05:40:00.792081: step: 1564/531, loss: 0.03872603923082352
2023-01-24 05:40:01.865032: step: 1568/531, loss: 0.00893507618457079
2023-01-24 05:40:02.925716: step: 1572/531, loss: 0.025152452290058136
2023-01-24 05:40:04.004484: step: 1576/531, loss: 0.013910738751292229
2023-01-24 05:40:05.082333: step: 1580/531, loss: 0.026610050350427628
2023-01-24 05:40:06.156851: step: 1584/531, loss: 0.006829569116234779
2023-01-24 05:40:07.223681: step: 1588/531, loss: 0.01031615398824215
2023-01-24 05:40:08.296701: step: 1592/531, loss: 0.0015475634718313813
2023-01-24 05:40:09.380430: step: 1596/531, loss: 0.019924283027648926
2023-01-24 05:40:10.450706: step: 1600/531, loss: 0.012449763715267181
2023-01-24 05:40:11.523933: step: 1604/531, loss: 0.009813033975660801
2023-01-24 05:40:12.590012: step: 1608/531, loss: 0.013363712467253208
2023-01-24 05:40:13.654812: step: 1612/531, loss: 0.0031043514609336853
2023-01-24 05:40:14.732775: step: 1616/531, loss: 0.009060146287083626
2023-01-24 05:40:15.787389: step: 1620/531, loss: 0.055927474051713943
2023-01-24 05:40:16.858831: step: 1624/531, loss: 0.008789319545030594
2023-01-24 05:40:17.922269: step: 1628/531, loss: 0.00854311604052782
2023-01-24 05:40:18.984584: step: 1632/531, loss: 0.01279479917138815
2023-01-24 05:40:20.053132: step: 1636/531, loss: 0.026169409975409508
2023-01-24 05:40:21.118171: step: 1640/531, loss: 0.01975897140800953
2023-01-24 05:40:22.221261: step: 1644/531, loss: 0.013997703790664673
2023-01-24 05:40:23.290961: step: 1648/531, loss: 0.038259588181972504
2023-01-24 05:40:24.372527: step: 1652/531, loss: 0.004551553633064032
2023-01-24 05:40:25.446307: step: 1656/531, loss: 0.005316711030900478
2023-01-24 05:40:26.516363: step: 1660/531, loss: 0.014941259287297726
2023-01-24 05:40:27.599643: step: 1664/531, loss: 0.0044372365809977055
2023-01-24 05:40:28.662303: step: 1668/531, loss: 0.031872279942035675
2023-01-24 05:40:29.739724: step: 1672/531, loss: 0.033701952546834946
2023-01-24 05:40:30.799626: step: 1676/531, loss: 0.024039575830101967
2023-01-24 05:40:31.853518: step: 1680/531, loss: 0.008942786604166031
2023-01-24 05:40:32.932256: step: 1684/531, loss: 0.009668517857789993
2023-01-24 05:40:33.996249: step: 1688/531, loss: 0.006605146918445826
2023-01-24 05:40:35.055596: step: 1692/531, loss: 0.004481645300984383
2023-01-24 05:40:36.114856: step: 1696/531, loss: 0.014689686708152294
2023-01-24 05:40:37.186768: step: 1700/531, loss: 0.011518360115587711
2023-01-24 05:40:38.243742: step: 1704/531, loss: 0.011369490064680576
2023-01-24 05:40:39.319833: step: 1708/531, loss: 0.009161842986941338
2023-01-24 05:40:40.392583: step: 1712/531, loss: 0.00941532664000988
2023-01-24 05:40:41.446461: step: 1716/531, loss: 0.027204032987356186
2023-01-24 05:40:42.509057: step: 1720/531, loss: 0.020403021946549416
2023-01-24 05:40:43.591378: step: 1724/531, loss: 0.026714880019426346
2023-01-24 05:40:44.669941: step: 1728/531, loss: 0.005099593661725521
2023-01-24 05:40:45.735177: step: 1732/531, loss: 0.010438046418130398
2023-01-24 05:40:46.802502: step: 1736/531, loss: 0.0015087584033608437
2023-01-24 05:40:47.869531: step: 1740/531, loss: 0.0062045142985880375
2023-01-24 05:40:48.923022: step: 1744/531, loss: 0.021082807332277298
2023-01-24 05:40:49.981838: step: 1748/531, loss: 0.02364220656454563
2023-01-24 05:40:51.038346: step: 1752/531, loss: 0.006717804353684187
2023-01-24 05:40:52.101555: step: 1756/531, loss: 0.006931005045771599
2023-01-24 05:40:53.173894: step: 1760/531, loss: 0.0064237043261528015
2023-01-24 05:40:54.258408: step: 1764/531, loss: 0.010398545302450657
2023-01-24 05:40:55.330707: step: 1768/531, loss: 0.01305343583226204
2023-01-24 05:40:56.384558: step: 1772/531, loss: 0.04983716085553169
2023-01-24 05:40:57.440722: step: 1776/531, loss: 0.014482763595879078
2023-01-24 05:40:58.505424: step: 1780/531, loss: 0.0020984080620110035
2023-01-24 05:40:59.564154: step: 1784/531, loss: 0.0026128175668418407
2023-01-24 05:41:00.619961: step: 1788/531, loss: 0.004091400187462568
2023-01-24 05:41:01.681113: step: 1792/531, loss: 0.0024972951505333185
2023-01-24 05:41:02.764088: step: 1796/531, loss: 0.014961661770939827
2023-01-24 05:41:03.825388: step: 1800/531, loss: 0.005145871080458164
2023-01-24 05:41:04.886815: step: 1804/531, loss: 0.008562278002500534
2023-01-24 05:41:05.936364: step: 1808/531, loss: 0.0042311218567192554
2023-01-24 05:41:07.004941: step: 1812/531, loss: 0.006016520783305168
2023-01-24 05:41:08.060471: step: 1816/531, loss: 0.006790841463953257
2023-01-24 05:41:09.124872: step: 1820/531, loss: 0.019874434918165207
2023-01-24 05:41:10.192535: step: 1824/531, loss: 0.007352512329816818
2023-01-24 05:41:11.255275: step: 1828/531, loss: 0.01314636506140232
2023-01-24 05:41:12.358231: step: 1832/531, loss: 0.002267833100631833
2023-01-24 05:41:13.439485: step: 1836/531, loss: 0.013022135011851788
2023-01-24 05:41:14.523867: step: 1840/531, loss: 0.024273375049233437
2023-01-24 05:41:15.591582: step: 1844/531, loss: 0.007241162937134504
2023-01-24 05:41:16.656220: step: 1848/531, loss: 0.016550511121749878
2023-01-24 05:41:17.708025: step: 1852/531, loss: 0.005948533769696951
2023-01-24 05:41:18.775630: step: 1856/531, loss: 0.028029173612594604
2023-01-24 05:41:19.830737: step: 1860/531, loss: 0.0076446011662483215
2023-01-24 05:41:20.894909: step: 1864/531, loss: 0.0064603546634316444
2023-01-24 05:41:21.968745: step: 1868/531, loss: 0.010256613604724407
2023-01-24 05:41:23.036487: step: 1872/531, loss: 0.013309633359313011
2023-01-24 05:41:24.127866: step: 1876/531, loss: 0.009671253152191639
2023-01-24 05:41:25.205696: step: 1880/531, loss: 0.005127544980496168
2023-01-24 05:41:26.263899: step: 1884/531, loss: 0.010823805816471577
2023-01-24 05:41:27.348677: step: 1888/531, loss: 0.07204632461071014
2023-01-24 05:41:28.423137: step: 1892/531, loss: 0.040515247732400894
2023-01-24 05:41:29.476065: step: 1896/531, loss: 0.004581084940582514
2023-01-24 05:41:30.526331: step: 1900/531, loss: 0.0043451376259326935
2023-01-24 05:41:31.588857: step: 1904/531, loss: 0.007818354293704033
2023-01-24 05:41:32.658858: step: 1908/531, loss: 0.02696968801319599
2023-01-24 05:41:33.731174: step: 1912/531, loss: 0.005032163579016924
2023-01-24 05:41:34.789114: step: 1916/531, loss: 0.034199975430965424
2023-01-24 05:41:35.853409: step: 1920/531, loss: 0.039390791207551956
2023-01-24 05:41:36.919025: step: 1924/531, loss: 0.04767834395170212
2023-01-24 05:41:37.979910: step: 1928/531, loss: 0.003919246606528759
2023-01-24 05:41:39.054028: step: 1932/531, loss: 0.013910716399550438
2023-01-24 05:41:40.107046: step: 1936/531, loss: 0.007001328747719526
2023-01-24 05:41:41.177254: step: 1940/531, loss: 0.025540199130773544
2023-01-24 05:41:42.231625: step: 1944/531, loss: 0.008113562129437923
2023-01-24 05:41:43.320629: step: 1948/531, loss: 0.01224514003843069
2023-01-24 05:41:44.376153: step: 1952/531, loss: 0.0009273162577301264
2023-01-24 05:41:45.428691: step: 1956/531, loss: 0.015027081593871117
2023-01-24 05:41:46.484842: step: 1960/531, loss: 0.011257095262408257
2023-01-24 05:41:47.552381: step: 1964/531, loss: 0.03339969739317894
2023-01-24 05:41:48.618909: step: 1968/531, loss: 0.0031417880672961473
2023-01-24 05:41:49.687871: step: 1972/531, loss: 4.752674431074411e-05
2023-01-24 05:41:50.779265: step: 1976/531, loss: 0.004710976500064135
2023-01-24 05:41:51.843969: step: 1980/531, loss: 0.030392993241548538
2023-01-24 05:41:52.915505: step: 1984/531, loss: 0.008365673013031483
2023-01-24 05:41:53.975310: step: 1988/531, loss: 0.011345232836902142
2023-01-24 05:41:55.037068: step: 1992/531, loss: 0.011520115658640862
2023-01-24 05:41:56.119866: step: 1996/531, loss: 0.023927411064505577
2023-01-24 05:41:57.182997: step: 2000/531, loss: 0.015948159620165825
2023-01-24 05:41:58.264149: step: 2004/531, loss: 0.008474358357489109
2023-01-24 05:41:59.338335: step: 2008/531, loss: 0.002990583423525095
2023-01-24 05:42:00.416752: step: 2012/531, loss: 0.005668531637638807
2023-01-24 05:42:01.494547: step: 2016/531, loss: 0.006443630438297987
2023-01-24 05:42:02.565282: step: 2020/531, loss: 0.00948173739016056
2023-01-24 05:42:03.638756: step: 2024/531, loss: 0.011518003419041634
2023-01-24 05:42:04.703991: step: 2028/531, loss: 0.0038602864369750023
2023-01-24 05:42:05.770501: step: 2032/531, loss: 0.002907469402998686
2023-01-24 05:42:06.839611: step: 2036/531, loss: 0.00720258941873908
2023-01-24 05:42:07.903020: step: 2040/531, loss: 0.004965411499142647
2023-01-24 05:42:08.977652: step: 2044/531, loss: 0.015387766994535923
2023-01-24 05:42:10.026592: step: 2048/531, loss: 0.004561169072985649
2023-01-24 05:42:11.093129: step: 2052/531, loss: 0.008874557912349701
2023-01-24 05:42:12.186897: step: 2056/531, loss: 0.023467542603611946
2023-01-24 05:42:13.258635: step: 2060/531, loss: 0.0
2023-01-24 05:42:14.331163: step: 2064/531, loss: 0.009165942668914795
2023-01-24 05:42:15.410498: step: 2068/531, loss: 0.022655600681900978
2023-01-24 05:42:16.479926: step: 2072/531, loss: 0.0127024557441473
2023-01-24 05:42:17.557509: step: 2076/531, loss: 0.03347679600119591
2023-01-24 05:42:18.630592: step: 2080/531, loss: 0.005705432966351509
2023-01-24 05:42:19.690182: step: 2084/531, loss: 0.009377938695251942
2023-01-24 05:42:20.750397: step: 2088/531, loss: 0.0043668863363564014
2023-01-24 05:42:21.826178: step: 2092/531, loss: 0.049331605434417725
2023-01-24 05:42:22.890482: step: 2096/531, loss: 0.005443839356303215
2023-01-24 05:42:23.960713: step: 2100/531, loss: 0.028085576370358467
2023-01-24 05:42:25.037006: step: 2104/531, loss: 0.005784222856163979
2023-01-24 05:42:26.099348: step: 2108/531, loss: 0.02353052981197834
2023-01-24 05:42:27.164449: step: 2112/531, loss: 0.009859143756330013
2023-01-24 05:42:28.253310: step: 2116/531, loss: 0.008600117638707161
2023-01-24 05:42:29.342671: step: 2120/531, loss: 0.04422273114323616
2023-01-24 05:42:30.416288: step: 2124/531, loss: 0.013776259496808052
==================================================
Loss: 0.015
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3930320171215678, 'r': 0.3206902606494766, 'f1': 0.35319491611760534}, 'combined': 0.26024888556034076, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38920916781391235, 'r': 0.27620163667227143, 'f1': 0.3231092985965707}, 'combined': 0.2023207757567312, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3756416609706083, 'r': 0.3385764496414401, 'f1': 0.3561472833553671}, 'combined': 0.2624243140513231, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3873793804968824, 'r': 0.2850329796983373, 'f1': 0.3284172202446297}, 'combined': 0.20352616465864376, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36311859010539105, 'r': 0.32591099263728646, 'f1': 0.34351018623969987}, 'combined': 0.2531127688081999, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41048945312511204, 'r': 0.28674985263432917, 'f1': 0.3376395714334078}, 'combined': 0.22397872560433982, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41, 'r': 0.44565217391304346, 'f1': 0.4270833333333333}, 'combined': 0.21354166666666666, 'stategy': 1, 'epoch': 1}
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, 'stategy': 1, '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': 0.3930320171215678, 'r': 0.3206902606494766, 'f1': 0.35319491611760534}, 'combined': 0.26024888556034076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38920916781391235, 'r': 0.27620163667227143, 'f1': 0.3231092985965707}, 'combined': 0.2023207757567312, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3756416609706083, 'r': 0.3385764496414401, 'f1': 0.3561472833553671}, 'combined': 0.2624243140513231, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3873793804968824, 'r': 0.2850329796983373, 'f1': 0.3284172202446297}, 'combined': 0.20352616465864376, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41, 'r': 0.44565217391304346, 'f1': 0.4270833333333333}, 'combined': 0.21354166666666666, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36311859010539105, 'r': 0.32591099263728646, 'f1': 0.34351018623969987}, 'combined': 0.2531127688081999, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41048945312511204, 'r': 0.28674985263432917, 'f1': 0.3376395714334078}, 'combined': 0.22397872560433982, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:45:17.432302: step: 4/531, loss: 0.004352105315774679
2023-01-24 05:45:18.491158: step: 8/531, loss: 0.020459897816181183
2023-01-24 05:45:19.533833: step: 12/531, loss: 0.021195387467741966
2023-01-24 05:45:20.587122: step: 16/531, loss: 0.009708487428724766
2023-01-24 05:45:21.628806: step: 20/531, loss: 0.004925751127302647
2023-01-24 05:45:22.679097: step: 24/531, loss: 0.012010580860078335
2023-01-24 05:45:23.728538: step: 28/531, loss: 0.004298270680010319
2023-01-24 05:45:24.775546: step: 32/531, loss: 0.008473596535623074
2023-01-24 05:45:25.830914: step: 36/531, loss: 0.007687244098633528
2023-01-24 05:45:26.892497: step: 40/531, loss: 0.04451196640729904
2023-01-24 05:45:27.950879: step: 44/531, loss: 0.005121026653796434
2023-01-24 05:45:28.986379: step: 48/531, loss: 0.006576779764145613
2023-01-24 05:45:30.046634: step: 52/531, loss: 0.017142634838819504
2023-01-24 05:45:31.109219: step: 56/531, loss: 0.011228079907596111
2023-01-24 05:45:32.169812: step: 60/531, loss: 0.029795169830322266
2023-01-24 05:45:33.249204: step: 64/531, loss: 0.010979712940752506
2023-01-24 05:45:34.320965: step: 68/531, loss: 0.03241435065865517
2023-01-24 05:45:35.375787: step: 72/531, loss: 0.00888033863157034
2023-01-24 05:45:36.432992: step: 76/531, loss: 0.007152865175157785
2023-01-24 05:45:37.479183: step: 80/531, loss: 0.0
2023-01-24 05:45:38.538556: step: 84/531, loss: 0.004070541355758905
2023-01-24 05:45:39.586585: step: 88/531, loss: 0.014607944525778294
2023-01-24 05:45:40.647645: step: 92/531, loss: 0.006742457393556833
2023-01-24 05:45:41.705493: step: 96/531, loss: 0.026470575481653214
2023-01-24 05:45:42.759308: step: 100/531, loss: 0.005333580542355776
2023-01-24 05:45:43.817071: step: 104/531, loss: 0.018963797017931938
2023-01-24 05:45:44.871930: step: 108/531, loss: 0.008935569785535336
2023-01-24 05:45:45.942761: step: 112/531, loss: 0.03659486025571823
2023-01-24 05:45:47.005335: step: 116/531, loss: 0.014554736204445362
2023-01-24 05:45:48.059124: step: 120/531, loss: 0.022502126172184944
2023-01-24 05:45:49.163160: step: 124/531, loss: 0.02685648202896118
2023-01-24 05:45:50.209731: step: 128/531, loss: 0.001173300319351256
2023-01-24 05:45:51.268217: step: 132/531, loss: 0.0037559354677796364
2023-01-24 05:45:52.330080: step: 136/531, loss: 0.0026571196503937244
2023-01-24 05:45:53.390702: step: 140/531, loss: 0.009270715527236462
2023-01-24 05:45:54.475331: step: 144/531, loss: 0.02681458368897438
2023-01-24 05:45:55.521209: step: 148/531, loss: 0.008141659200191498
2023-01-24 05:45:56.579978: step: 152/531, loss: 0.015150204300880432
2023-01-24 05:45:57.646977: step: 156/531, loss: 0.0036456130910664797
2023-01-24 05:45:58.725788: step: 160/531, loss: 0.008028483018279076
2023-01-24 05:45:59.807970: step: 164/531, loss: 0.0028695957735180855
2023-01-24 05:46:00.848138: step: 168/531, loss: 0.0019893269054591656
2023-01-24 05:46:01.914553: step: 172/531, loss: 0.025172429159283638
2023-01-24 05:46:02.963237: step: 176/531, loss: 0.003383524715900421
2023-01-24 05:46:04.041276: step: 180/531, loss: 0.037243448197841644
2023-01-24 05:46:05.106798: step: 184/531, loss: 0.011588050983846188
2023-01-24 05:46:06.178770: step: 188/531, loss: 0.01626310497522354
2023-01-24 05:46:07.244074: step: 192/531, loss: 0.00913391262292862
2023-01-24 05:46:08.301740: step: 196/531, loss: 0.003052431158721447
2023-01-24 05:46:09.382352: step: 200/531, loss: 0.00968985352665186
2023-01-24 05:46:10.447348: step: 204/531, loss: 0.00568684097379446
2023-01-24 05:46:11.497633: step: 208/531, loss: 0.007495521102100611
2023-01-24 05:46:12.584902: step: 212/531, loss: 0.017931997776031494
2023-01-24 05:46:13.660399: step: 216/531, loss: 0.023087874054908752
2023-01-24 05:46:14.723251: step: 220/531, loss: 0.006206677295267582
2023-01-24 05:46:15.784029: step: 224/531, loss: 0.006671375595033169
2023-01-24 05:46:16.857606: step: 228/531, loss: 0.022651249542832375
2023-01-24 05:46:17.956363: step: 232/531, loss: 0.008202160708606243
2023-01-24 05:46:19.030578: step: 236/531, loss: 0.0020127848256379366
2023-01-24 05:46:20.090322: step: 240/531, loss: 0.01109483651816845
2023-01-24 05:46:21.145239: step: 244/531, loss: 0.013756894506514072
2023-01-24 05:46:22.221481: step: 248/531, loss: 0.027989234775304794
2023-01-24 05:46:23.278959: step: 252/531, loss: 0.0030352952890098095
2023-01-24 05:46:24.338480: step: 256/531, loss: 0.02312830090522766
2023-01-24 05:46:25.381238: step: 260/531, loss: 0.023030975833535194
2023-01-24 05:46:26.442452: step: 264/531, loss: 0.007313702255487442
2023-01-24 05:46:27.493000: step: 268/531, loss: 0.005014278460294008
2023-01-24 05:46:28.550223: step: 272/531, loss: 0.0010467886459082365
2023-01-24 05:46:29.606820: step: 276/531, loss: 0.001209757407195866
2023-01-24 05:46:30.668739: step: 280/531, loss: 0.004092218354344368
2023-01-24 05:46:31.738011: step: 284/531, loss: 0.00844376441091299
2023-01-24 05:46:32.808848: step: 288/531, loss: 0.023990551009774208
2023-01-24 05:46:33.866028: step: 292/531, loss: 0.029529767110943794
2023-01-24 05:46:34.931111: step: 296/531, loss: 0.018035391345620155
2023-01-24 05:46:35.986841: step: 300/531, loss: 0.0033457730896770954
2023-01-24 05:46:37.057671: step: 304/531, loss: 0.005013692192733288
2023-01-24 05:46:38.118301: step: 308/531, loss: 0.02712704800069332
2023-01-24 05:46:39.188167: step: 312/531, loss: 0.01133128721266985
2023-01-24 05:46:40.245923: step: 316/531, loss: 0.026250425726175308
2023-01-24 05:46:41.315323: step: 320/531, loss: 0.01038841437548399
2023-01-24 05:46:42.384486: step: 324/531, loss: 0.0007836610311642289
2023-01-24 05:46:43.448839: step: 328/531, loss: 0.007466156501322985
2023-01-24 05:46:44.523210: step: 332/531, loss: 0.004719925113022327
2023-01-24 05:46:45.593369: step: 336/531, loss: 0.016059324145317078
2023-01-24 05:46:46.645899: step: 340/531, loss: 0.010760081000626087
2023-01-24 05:46:47.685952: step: 344/531, loss: 0.03876057639718056
2023-01-24 05:46:48.734367: step: 348/531, loss: 0.0002530314086470753
2023-01-24 05:46:49.787822: step: 352/531, loss: 0.0013005572836846113
2023-01-24 05:46:50.852795: step: 356/531, loss: 0.003125865710899234
2023-01-24 05:46:51.895243: step: 360/531, loss: 0.003142973640933633
2023-01-24 05:46:52.975423: step: 364/531, loss: 0.007031532004475594
2023-01-24 05:46:54.042130: step: 368/531, loss: 0.003911362960934639
2023-01-24 05:46:55.109050: step: 372/531, loss: 0.004267843905836344
2023-01-24 05:46:56.187789: step: 376/531, loss: 0.04243801161646843
2023-01-24 05:46:57.259241: step: 380/531, loss: 0.001584008801728487
2023-01-24 05:46:58.332664: step: 384/531, loss: 0.010753756389021873
2023-01-24 05:46:59.391528: step: 388/531, loss: 0.005048241000622511
2023-01-24 05:47:00.458287: step: 392/531, loss: 0.0042828405275940895
2023-01-24 05:47:01.517368: step: 396/531, loss: 0.046355344355106354
2023-01-24 05:47:02.576363: step: 400/531, loss: 0.020720630884170532
2023-01-24 05:47:03.636385: step: 404/531, loss: 0.00245657074265182
2023-01-24 05:47:04.729910: step: 408/531, loss: 0.020238470286130905
2023-01-24 05:47:05.792685: step: 412/531, loss: 0.00804706010967493
2023-01-24 05:47:06.851274: step: 416/531, loss: 0.004534791223704815
2023-01-24 05:47:07.928957: step: 420/531, loss: 0.015211626887321472
2023-01-24 05:47:08.993264: step: 424/531, loss: 0.0082132238894701
2023-01-24 05:47:10.046156: step: 428/531, loss: 0.009714786894619465
2023-01-24 05:47:11.113223: step: 432/531, loss: 0.004712847527116537
2023-01-24 05:47:12.179104: step: 436/531, loss: 0.006697678007185459
2023-01-24 05:47:13.248789: step: 440/531, loss: 0.036334652453660965
2023-01-24 05:47:14.303227: step: 444/531, loss: 0.005509565118700266
2023-01-24 05:47:15.371540: step: 448/531, loss: 0.006770780775696039
2023-01-24 05:47:16.454711: step: 452/531, loss: 0.009797475300729275
2023-01-24 05:47:17.524249: step: 456/531, loss: 0.0005074595101177692
2023-01-24 05:47:18.585945: step: 460/531, loss: 0.019728800281882286
2023-01-24 05:47:19.653414: step: 464/531, loss: 0.005373081658035517
2023-01-24 05:47:20.718888: step: 468/531, loss: 0.01225414127111435
2023-01-24 05:47:21.784410: step: 472/531, loss: 0.007407640106976032
2023-01-24 05:47:22.844222: step: 476/531, loss: 0.012558969669044018
2023-01-24 05:47:23.925396: step: 480/531, loss: 0.014754174277186394
2023-01-24 05:47:25.012788: step: 484/531, loss: 0.042245738208293915
2023-01-24 05:47:26.078041: step: 488/531, loss: 0.0210590697824955
2023-01-24 05:47:27.125393: step: 492/531, loss: 0.008470935747027397
2023-01-24 05:47:28.191196: step: 496/531, loss: 0.008551366627216339
2023-01-24 05:47:29.259722: step: 500/531, loss: 0.044560711830854416
2023-01-24 05:47:30.317599: step: 504/531, loss: 0.014161897823214531
2023-01-24 05:47:31.384833: step: 508/531, loss: 0.0011446214048191905
2023-01-24 05:47:32.454739: step: 512/531, loss: 0.08650229871273041
2023-01-24 05:47:33.509288: step: 516/531, loss: 0.007837348617613316
2023-01-24 05:47:34.576179: step: 520/531, loss: 0.026229260489344597
2023-01-24 05:47:35.639471: step: 524/531, loss: 0.03698166459798813
2023-01-24 05:47:36.704540: step: 528/531, loss: 0.038229942321777344
2023-01-24 05:47:37.762783: step: 532/531, loss: 0.005690035875886679
2023-01-24 05:47:38.847966: step: 536/531, loss: 0.013920952565968037
2023-01-24 05:47:39.908505: step: 540/531, loss: 0.0009368452592752874
2023-01-24 05:47:40.981532: step: 544/531, loss: 0.013223019428551197
2023-01-24 05:47:42.039464: step: 548/531, loss: 0.009844765067100525
2023-01-24 05:47:43.099091: step: 552/531, loss: 0.013350303284823895
2023-01-24 05:47:44.163682: step: 556/531, loss: 0.01223684847354889
2023-01-24 05:47:45.231654: step: 560/531, loss: 0.00041542091639712453
2023-01-24 05:47:46.298857: step: 564/531, loss: 0.0035067263524979353
2023-01-24 05:47:47.361158: step: 568/531, loss: 0.021740669384598732
2023-01-24 05:47:48.442637: step: 572/531, loss: 0.012412325479090214
2023-01-24 05:47:49.517074: step: 576/531, loss: 0.03687620908021927
2023-01-24 05:47:50.588349: step: 580/531, loss: 0.002590457210317254
2023-01-24 05:47:51.645624: step: 584/531, loss: 0.0006319463718682528
2023-01-24 05:47:52.705281: step: 588/531, loss: 0.007740527391433716
2023-01-24 05:47:53.768180: step: 592/531, loss: 0.008442549034953117
2023-01-24 05:47:54.837289: step: 596/531, loss: 0.0035422963555902243
2023-01-24 05:47:55.892151: step: 600/531, loss: 0.0006683246465399861
2023-01-24 05:47:56.956319: step: 604/531, loss: 0.0024830906186252832
2023-01-24 05:47:58.020084: step: 608/531, loss: 0.015179877169430256
2023-01-24 05:47:59.100041: step: 612/531, loss: 0.0008795327157713473
2023-01-24 05:48:00.164189: step: 616/531, loss: 0.002481618197634816
2023-01-24 05:48:01.228170: step: 620/531, loss: 0.008597446605563164
2023-01-24 05:48:02.298196: step: 624/531, loss: 0.041076984256505966
2023-01-24 05:48:03.351928: step: 628/531, loss: 0.015597502700984478
2023-01-24 05:48:04.419210: step: 632/531, loss: 0.01000105682760477
2023-01-24 05:48:05.478482: step: 636/531, loss: 0.0031480668112635612
2023-01-24 05:48:06.541471: step: 640/531, loss: 0.010408508591353893
2023-01-24 05:48:07.609447: step: 644/531, loss: 0.016908518970012665
2023-01-24 05:48:08.669144: step: 648/531, loss: 0.015883702784776688
2023-01-24 05:48:09.724057: step: 652/531, loss: 0.001235972042195499
2023-01-24 05:48:10.789558: step: 656/531, loss: 0.019087497144937515
2023-01-24 05:48:11.889251: step: 660/531, loss: 0.006723023485392332
2023-01-24 05:48:12.935877: step: 664/531, loss: 0.01384618878364563
2023-01-24 05:48:13.984363: step: 668/531, loss: 0.005318854469805956
2023-01-24 05:48:15.042235: step: 672/531, loss: 0.0025831512175500393
2023-01-24 05:48:16.110495: step: 676/531, loss: 0.029259277507662773
2023-01-24 05:48:17.177241: step: 680/531, loss: 0.004867771174758673
2023-01-24 05:48:18.235292: step: 684/531, loss: 0.016316745430231094
2023-01-24 05:48:19.294026: step: 688/531, loss: 0.00856808666139841
2023-01-24 05:48:20.356365: step: 692/531, loss: 0.002886097179725766
2023-01-24 05:48:21.408293: step: 696/531, loss: 0.0007334217661991715
2023-01-24 05:48:22.468305: step: 700/531, loss: 0.03867122158408165
2023-01-24 05:48:23.543957: step: 704/531, loss: 0.015843059867620468
2023-01-24 05:48:24.612653: step: 708/531, loss: 0.02910970151424408
2023-01-24 05:48:25.664784: step: 712/531, loss: 0.002809828845784068
2023-01-24 05:48:26.733589: step: 716/531, loss: 0.013181174173951149
2023-01-24 05:48:27.794225: step: 720/531, loss: 0.03666000813245773
2023-01-24 05:48:28.852076: step: 724/531, loss: 0.010472246445715427
2023-01-24 05:48:29.920827: step: 728/531, loss: 0.0021222438663244247
2023-01-24 05:48:31.000302: step: 732/531, loss: 0.036330971866846085
2023-01-24 05:48:32.079072: step: 736/531, loss: 0.00701176980510354
2023-01-24 05:48:33.137553: step: 740/531, loss: 0.006832615938037634
2023-01-24 05:48:34.200818: step: 744/531, loss: 0.09322182089090347
2023-01-24 05:48:35.243651: step: 748/531, loss: 0.004076693672686815
2023-01-24 05:48:36.304166: step: 752/531, loss: 0.014712278731167316
2023-01-24 05:48:37.359217: step: 756/531, loss: 0.00699743814766407
2023-01-24 05:48:38.432280: step: 760/531, loss: 0.056770358234643936
2023-01-24 05:48:39.496755: step: 764/531, loss: 0.019629813730716705
2023-01-24 05:48:40.569210: step: 768/531, loss: 0.04331810027360916
2023-01-24 05:48:41.625760: step: 772/531, loss: 0.007678089197725058
2023-01-24 05:48:42.677648: step: 776/531, loss: 0.007802879437804222
2023-01-24 05:48:43.731073: step: 780/531, loss: 0.0015147406375035644
2023-01-24 05:48:44.798109: step: 784/531, loss: 0.00765644945204258
2023-01-24 05:48:45.862665: step: 788/531, loss: 0.004759211093187332
2023-01-24 05:48:46.935633: step: 792/531, loss: 0.0031675910577178
2023-01-24 05:48:48.012952: step: 796/531, loss: 0.025086427107453346
2023-01-24 05:48:49.074109: step: 800/531, loss: 0.13266576826572418
2023-01-24 05:48:50.147888: step: 804/531, loss: 0.001716657541692257
2023-01-24 05:48:51.207768: step: 808/531, loss: 0.0027550519444048405
2023-01-24 05:48:52.303912: step: 812/531, loss: 0.00742874201387167
2023-01-24 05:48:53.359681: step: 816/531, loss: 0.006402923259884119
2023-01-24 05:48:54.431116: step: 820/531, loss: 0.013202822767198086
2023-01-24 05:48:55.499619: step: 824/531, loss: 0.011958223767578602
2023-01-24 05:48:56.562122: step: 828/531, loss: 0.006566676776856184
2023-01-24 05:48:57.629357: step: 832/531, loss: 0.009989522397518158
2023-01-24 05:48:58.721536: step: 836/531, loss: 0.036954306066036224
2023-01-24 05:48:59.786768: step: 840/531, loss: 0.0322166383266449
2023-01-24 05:49:00.867103: step: 844/531, loss: 0.006569726392626762
2023-01-24 05:49:01.934138: step: 848/531, loss: 0.0056249904446303844
2023-01-24 05:49:03.003281: step: 852/531, loss: 0.018429214134812355
2023-01-24 05:49:04.075250: step: 856/531, loss: 0.03290853649377823
2023-01-24 05:49:05.132410: step: 860/531, loss: 0.009376497007906437
2023-01-24 05:49:06.208028: step: 864/531, loss: 0.016479624435305595
2023-01-24 05:49:07.280965: step: 868/531, loss: 0.0211174376308918
2023-01-24 05:49:08.348460: step: 872/531, loss: 0.010659064166247845
2023-01-24 05:49:09.400368: step: 876/531, loss: 0.005403154995292425
2023-01-24 05:49:10.456160: step: 880/531, loss: 0.0004183748096693307
2023-01-24 05:49:11.531832: step: 884/531, loss: 0.003261387115344405
2023-01-24 05:49:12.590646: step: 888/531, loss: 0.0
2023-01-24 05:49:13.651214: step: 892/531, loss: 0.03475382179021835
2023-01-24 05:49:14.730432: step: 896/531, loss: 0.005472506862133741
2023-01-24 05:49:15.814750: step: 900/531, loss: 0.01338645163923502
2023-01-24 05:49:16.878380: step: 904/531, loss: 0.003423280082643032
2023-01-24 05:49:17.937837: step: 908/531, loss: 0.010540076531469822
2023-01-24 05:49:19.011787: step: 912/531, loss: 0.02655048854649067
2023-01-24 05:49:20.058378: step: 916/531, loss: 0.00658982340246439
2023-01-24 05:49:21.139734: step: 920/531, loss: 0.002910940907895565
2023-01-24 05:49:22.223835: step: 924/531, loss: 0.01712654158473015
2023-01-24 05:49:23.288256: step: 928/531, loss: 0.0039005933795124292
2023-01-24 05:49:24.337136: step: 932/531, loss: 0.007449942175298929
2023-01-24 05:49:25.409421: step: 936/531, loss: 0.014374330639839172
2023-01-24 05:49:26.463948: step: 940/531, loss: 0.007312045432627201
2023-01-24 05:49:27.517199: step: 944/531, loss: 0.01999361254274845
2023-01-24 05:49:28.575519: step: 948/531, loss: 0.015330715104937553
2023-01-24 05:49:29.655874: step: 952/531, loss: 0.012714835815131664
2023-01-24 05:49:30.739503: step: 956/531, loss: 0.005335532128810883
2023-01-24 05:49:31.803640: step: 960/531, loss: 0.00808714609593153
2023-01-24 05:49:32.864699: step: 964/531, loss: 0.0012076643761247396
2023-01-24 05:49:33.936677: step: 968/531, loss: 0.009486301802098751
2023-01-24 05:49:35.016936: step: 972/531, loss: 0.005028801504522562
2023-01-24 05:49:36.085565: step: 976/531, loss: 0.0016789609799161553
2023-01-24 05:49:37.143530: step: 980/531, loss: 0.007988802157342434
2023-01-24 05:49:38.230073: step: 984/531, loss: 0.0043768612667918205
2023-01-24 05:49:39.311468: step: 988/531, loss: 0.0677265077829361
2023-01-24 05:49:40.382186: step: 992/531, loss: 0.016451023519039154
2023-01-24 05:49:41.457594: step: 996/531, loss: 0.0394602008163929
2023-01-24 05:49:42.540359: step: 1000/531, loss: 0.003941897302865982
2023-01-24 05:49:43.605359: step: 1004/531, loss: 0.013630902394652367
2023-01-24 05:49:44.670067: step: 1008/531, loss: 0.007742106914520264
2023-01-24 05:49:45.723271: step: 1012/531, loss: 0.015339868143200874
2023-01-24 05:49:46.795831: step: 1016/531, loss: 0.005221690982580185
2023-01-24 05:49:47.873033: step: 1020/531, loss: 0.026504477486014366
2023-01-24 05:49:48.936554: step: 1024/531, loss: 0.029230261221528053
2023-01-24 05:49:49.989698: step: 1028/531, loss: 0.012360453605651855
2023-01-24 05:49:51.041500: step: 1032/531, loss: 0.0041351765394210815
2023-01-24 05:49:52.108192: step: 1036/531, loss: 0.014223077334463596
2023-01-24 05:49:53.169081: step: 1040/531, loss: 0.012814600951969624
2023-01-24 05:49:54.224525: step: 1044/531, loss: 0.001860265270806849
2023-01-24 05:49:55.300380: step: 1048/531, loss: 0.0050408197566866875
2023-01-24 05:49:56.359057: step: 1052/531, loss: 0.008755365386605263
2023-01-24 05:49:57.438210: step: 1056/531, loss: 0.005666117649525404
2023-01-24 05:49:58.487282: step: 1060/531, loss: 0.01227036863565445
2023-01-24 05:49:59.575988: step: 1064/531, loss: 0.013285154476761818
2023-01-24 05:50:00.673829: step: 1068/531, loss: 0.007334236986935139
2023-01-24 05:50:01.724439: step: 1072/531, loss: 0.0016570896841585636
2023-01-24 05:50:02.794534: step: 1076/531, loss: 0.002204014454036951
2023-01-24 05:50:03.862950: step: 1080/531, loss: 0.008553000167012215
2023-01-24 05:50:04.924938: step: 1084/531, loss: 0.01245174277573824
2023-01-24 05:50:05.992966: step: 1088/531, loss: 0.02858390472829342
2023-01-24 05:50:07.048826: step: 1092/531, loss: 0.0021017941180616617
2023-01-24 05:50:08.114623: step: 1096/531, loss: 0.010990865528583527
2023-01-24 05:50:09.169458: step: 1100/531, loss: 0.009551011957228184
2023-01-24 05:50:10.227464: step: 1104/531, loss: 0.0021572967525571585
2023-01-24 05:50:11.291133: step: 1108/531, loss: 0.0015618226025253534
2023-01-24 05:50:12.353340: step: 1112/531, loss: 0.03426532447338104
2023-01-24 05:50:13.418847: step: 1116/531, loss: 0.015635645017027855
2023-01-24 05:50:14.472692: step: 1120/531, loss: 0.005257135722786188
2023-01-24 05:50:15.535013: step: 1124/531, loss: 0.03241654112935066
2023-01-24 05:50:16.623650: step: 1128/531, loss: 0.03126508370041847
2023-01-24 05:50:17.675902: step: 1132/531, loss: 0.009504013694822788
2023-01-24 05:50:18.728290: step: 1136/531, loss: 0.007109604775905609
2023-01-24 05:50:19.799971: step: 1140/531, loss: 0.008919750340282917
2023-01-24 05:50:20.863196: step: 1144/531, loss: 0.00458704587072134
2023-01-24 05:50:21.924471: step: 1148/531, loss: 0.011064345017075539
2023-01-24 05:50:23.000167: step: 1152/531, loss: 0.011693078093230724
2023-01-24 05:50:24.073750: step: 1156/531, loss: 0.06505129486322403
2023-01-24 05:50:25.135688: step: 1160/531, loss: 0.020284447818994522
2023-01-24 05:50:26.197241: step: 1164/531, loss: 0.005057459231466055
2023-01-24 05:50:27.271273: step: 1168/531, loss: 0.003141334280371666
2023-01-24 05:50:28.358463: step: 1172/531, loss: 0.0020014727488160133
2023-01-24 05:50:29.437447: step: 1176/531, loss: 0.015610367991030216
2023-01-24 05:50:30.512061: step: 1180/531, loss: 0.009590407833456993
2023-01-24 05:50:31.572455: step: 1184/531, loss: 0.003493065247312188
2023-01-24 05:50:32.633486: step: 1188/531, loss: 0.03922054171562195
2023-01-24 05:50:33.692817: step: 1192/531, loss: 0.001920498558320105
2023-01-24 05:50:34.765145: step: 1196/531, loss: 0.009542138315737247
2023-01-24 05:50:35.852095: step: 1200/531, loss: 0.015098577365279198
2023-01-24 05:50:36.908311: step: 1204/531, loss: 0.015390695072710514
2023-01-24 05:50:37.987719: step: 1208/531, loss: 0.009725487791001797
2023-01-24 05:50:39.072293: step: 1212/531, loss: 0.01185739878565073
2023-01-24 05:50:40.149770: step: 1216/531, loss: 0.005489910487085581
2023-01-24 05:50:41.189362: step: 1220/531, loss: 0.006963996682316065
2023-01-24 05:50:42.262476: step: 1224/531, loss: 0.003871776396408677
2023-01-24 05:50:43.314059: step: 1228/531, loss: 0.02884555049240589
2023-01-24 05:50:44.373187: step: 1232/531, loss: 0.000818113679997623
2023-01-24 05:50:45.450845: step: 1236/531, loss: 0.027231259271502495
2023-01-24 05:50:46.527141: step: 1240/531, loss: 0.005196020472794771
2023-01-24 05:50:47.590289: step: 1244/531, loss: 0.008681959472596645
2023-01-24 05:50:48.656602: step: 1248/531, loss: 0.08371572196483612
2023-01-24 05:50:49.721024: step: 1252/531, loss: 0.006729732733219862
2023-01-24 05:50:50.779015: step: 1256/531, loss: 0.0025454936549067497
2023-01-24 05:50:51.856283: step: 1260/531, loss: 0.010033482685685158
2023-01-24 05:50:52.910570: step: 1264/531, loss: 0.0065170456655323505
2023-01-24 05:50:53.991946: step: 1268/531, loss: 0.01327525731176138
2023-01-24 05:50:55.069109: step: 1272/531, loss: 0.01201469823718071
2023-01-24 05:50:56.125435: step: 1276/531, loss: 0.005637824535369873
2023-01-24 05:50:57.183851: step: 1280/531, loss: 0.04774932190775871
2023-01-24 05:50:58.257337: step: 1284/531, loss: 0.005011477507650852
2023-01-24 05:50:59.320980: step: 1288/531, loss: 0.030396079644560814
2023-01-24 05:51:00.393286: step: 1292/531, loss: 0.008106202818453312
2023-01-24 05:51:01.459303: step: 1296/531, loss: 0.006353373173624277
2023-01-24 05:51:02.532051: step: 1300/531, loss: 0.002120911842212081
2023-01-24 05:51:03.609519: step: 1304/531, loss: 0.03550753369927406
2023-01-24 05:51:04.671939: step: 1308/531, loss: 0.014169967733323574
2023-01-24 05:51:05.734414: step: 1312/531, loss: 0.01643649861216545
2023-01-24 05:51:06.796477: step: 1316/531, loss: 0.006041550077497959
2023-01-24 05:51:07.874678: step: 1320/531, loss: 0.009202200919389725
2023-01-24 05:51:08.925857: step: 1324/531, loss: 0.01462903618812561
2023-01-24 05:51:09.989071: step: 1328/531, loss: 0.01487416960299015
2023-01-24 05:51:11.059474: step: 1332/531, loss: 0.005591053050011396
2023-01-24 05:51:12.118093: step: 1336/531, loss: 0.010400021448731422
2023-01-24 05:51:13.179147: step: 1340/531, loss: 0.0030778103973716497
2023-01-24 05:51:14.226103: step: 1344/531, loss: 0.006464879959821701
2023-01-24 05:51:15.303599: step: 1348/531, loss: 0.06205100938677788
2023-01-24 05:51:16.385823: step: 1352/531, loss: 0.003671812592074275
2023-01-24 05:51:17.450925: step: 1356/531, loss: 0.01701735332608223
2023-01-24 05:51:18.527603: step: 1360/531, loss: 0.04350874572992325
2023-01-24 05:51:19.582615: step: 1364/531, loss: 0.0027278142515569925
2023-01-24 05:51:20.635766: step: 1368/531, loss: 0.004778644070029259
2023-01-24 05:51:21.689105: step: 1372/531, loss: 0.004517232533544302
2023-01-24 05:51:22.760127: step: 1376/531, loss: 0.006217169109731913
2023-01-24 05:51:23.830374: step: 1380/531, loss: 0.015240363776683807
2023-01-24 05:51:24.897373: step: 1384/531, loss: 0.007383220829069614
2023-01-24 05:51:25.954459: step: 1388/531, loss: 0.022683104500174522
2023-01-24 05:51:27.025836: step: 1392/531, loss: 0.022249735891819
2023-01-24 05:51:28.086108: step: 1396/531, loss: 0.00836427416652441
2023-01-24 05:51:29.149364: step: 1400/531, loss: 0.01059095561504364
2023-01-24 05:51:30.195395: step: 1404/531, loss: 0.006974156480282545
2023-01-24 05:51:31.259320: step: 1408/531, loss: 0.007008974906057119
2023-01-24 05:51:32.300792: step: 1412/531, loss: 0.0055645788088440895
2023-01-24 05:51:33.365200: step: 1416/531, loss: 0.019400261342525482
2023-01-24 05:51:34.443837: step: 1420/531, loss: 0.0061435881070792675
2023-01-24 05:51:35.518723: step: 1424/531, loss: 0.006364084780216217
2023-01-24 05:51:36.581214: step: 1428/531, loss: 0.001846448052674532
2023-01-24 05:51:37.627634: step: 1432/531, loss: 0.008257667534053326
2023-01-24 05:51:38.703606: step: 1436/531, loss: 0.002634771866723895
2023-01-24 05:51:39.765596: step: 1440/531, loss: 0.01020835805684328
2023-01-24 05:51:40.837086: step: 1444/531, loss: 0.009831872768700123
2023-01-24 05:51:41.934987: step: 1448/531, loss: 0.016211209818720818
2023-01-24 05:51:42.984134: step: 1452/531, loss: 0.004206764977425337
2023-01-24 05:51:44.047838: step: 1456/531, loss: 0.010705050081014633
2023-01-24 05:51:45.119985: step: 1460/531, loss: 0.0038526919670403004
2023-01-24 05:51:46.181538: step: 1464/531, loss: 0.0077238441444933414
2023-01-24 05:51:47.239080: step: 1468/531, loss: 0.027157988399267197
2023-01-24 05:51:48.294116: step: 1472/531, loss: 0.0005434079794213176
2023-01-24 05:51:49.365963: step: 1476/531, loss: 0.0026184748858213425
2023-01-24 05:51:50.423197: step: 1480/531, loss: 0.0012519037118181586
2023-01-24 05:51:51.484796: step: 1484/531, loss: 0.0050787245854735374
2023-01-24 05:51:52.548885: step: 1488/531, loss: 0.004459341522306204
2023-01-24 05:51:53.622575: step: 1492/531, loss: 0.011001690290868282
2023-01-24 05:51:54.695234: step: 1496/531, loss: 0.005979818757623434
2023-01-24 05:51:55.761344: step: 1500/531, loss: 0.009303625673055649
2023-01-24 05:51:56.824863: step: 1504/531, loss: 0.00011039365926990286
2023-01-24 05:51:57.888225: step: 1508/531, loss: 0.006546668708324432
2023-01-24 05:51:58.952006: step: 1512/531, loss: 0.0367443710565567
2023-01-24 05:52:00.020712: step: 1516/531, loss: 0.003502284875139594
2023-01-24 05:52:01.084876: step: 1520/531, loss: 0.017570864409208298
2023-01-24 05:52:02.153268: step: 1524/531, loss: 0.017676059156656265
2023-01-24 05:52:03.224258: step: 1528/531, loss: 0.005596524570137262
2023-01-24 05:52:04.283008: step: 1532/531, loss: 0.004737562034279108
2023-01-24 05:52:05.346445: step: 1536/531, loss: 0.009755619801580906
2023-01-24 05:52:06.402867: step: 1540/531, loss: 0.0008651097887195647
2023-01-24 05:52:07.470317: step: 1544/531, loss: 0.015758806839585304
2023-01-24 05:52:08.540913: step: 1548/531, loss: 0.004234983120113611
2023-01-24 05:52:09.609591: step: 1552/531, loss: 0.030790746212005615
2023-01-24 05:52:10.674289: step: 1556/531, loss: 0.017823224887251854
2023-01-24 05:52:11.736841: step: 1560/531, loss: 0.020318850874900818
2023-01-24 05:52:12.826005: step: 1564/531, loss: 0.01772797480225563
2023-01-24 05:52:13.899446: step: 1568/531, loss: 0.039910510182380676
2023-01-24 05:52:14.956339: step: 1572/531, loss: 0.002660271944478154
2023-01-24 05:52:16.023840: step: 1576/531, loss: 0.0031544482335448265
2023-01-24 05:52:17.086256: step: 1580/531, loss: 0.023564768955111504
2023-01-24 05:52:18.149228: step: 1584/531, loss: 0.009568865410983562
2023-01-24 05:52:19.226159: step: 1588/531, loss: 0.0046332525089383125
2023-01-24 05:52:20.296492: step: 1592/531, loss: 0.04241786152124405
2023-01-24 05:52:21.359933: step: 1596/531, loss: 0.025244561955332756
2023-01-24 05:52:22.446338: step: 1600/531, loss: 0.026974640786647797
2023-01-24 05:52:23.506949: step: 1604/531, loss: 0.017429644241929054
2023-01-24 05:52:24.567903: step: 1608/531, loss: 0.006756743881851435
2023-01-24 05:52:25.635388: step: 1612/531, loss: 0.016141850501298904
2023-01-24 05:52:26.690817: step: 1616/531, loss: 0.012421050108969212
2023-01-24 05:52:27.746026: step: 1620/531, loss: 0.014212023466825485
2023-01-24 05:52:28.809371: step: 1624/531, loss: 0.014323304407298565
2023-01-24 05:52:29.872624: step: 1628/531, loss: 0.0065786573104560375
2023-01-24 05:52:30.952001: step: 1632/531, loss: 0.003649013116955757
2023-01-24 05:52:32.013341: step: 1636/531, loss: 0.016441455110907555
2023-01-24 05:52:33.066066: step: 1640/531, loss: 0.018609926104545593
2023-01-24 05:52:34.136862: step: 1644/531, loss: 0.0028549593407660723
2023-01-24 05:52:35.216620: step: 1648/531, loss: 0.023130150511860847
2023-01-24 05:52:36.284113: step: 1652/531, loss: 0.009245655499398708
2023-01-24 05:52:37.349654: step: 1656/531, loss: 0.03684879466891289
2023-01-24 05:52:38.407020: step: 1660/531, loss: 0.003761161118745804
2023-01-24 05:52:39.491469: step: 1664/531, loss: 0.005097277462482452
2023-01-24 05:52:40.548056: step: 1668/531, loss: 0.016136791557073593
2023-01-24 05:52:41.612661: step: 1672/531, loss: 0.030105091631412506
2023-01-24 05:52:42.684048: step: 1676/531, loss: 0.012599162757396698
2023-01-24 05:52:43.750199: step: 1680/531, loss: 0.014272150583565235
2023-01-24 05:52:44.797777: step: 1684/531, loss: 0.0019857652951031923
2023-01-24 05:52:45.871642: step: 1688/531, loss: 0.0028475599829107523
2023-01-24 05:52:46.945066: step: 1692/531, loss: 0.01421818695962429
2023-01-24 05:52:48.003088: step: 1696/531, loss: 0.011855151504278183
2023-01-24 05:52:49.058734: step: 1700/531, loss: 0.003681303234770894
2023-01-24 05:52:50.125531: step: 1704/531, loss: 0.004155156668275595
2023-01-24 05:52:51.181877: step: 1708/531, loss: 0.025328440591692924
2023-01-24 05:52:52.273139: step: 1712/531, loss: 0.005948621779680252
2023-01-24 05:52:53.364596: step: 1716/531, loss: 0.001444079214707017
2023-01-24 05:52:54.453683: step: 1720/531, loss: 0.0019061742350459099
2023-01-24 05:52:55.511665: step: 1724/531, loss: 0.007866954430937767
2023-01-24 05:52:56.583785: step: 1728/531, loss: 0.016262635588645935
2023-01-24 05:52:57.655132: step: 1732/531, loss: 0.01545544620603323
2023-01-24 05:52:58.716194: step: 1736/531, loss: 0.033637918531894684
2023-01-24 05:52:59.782848: step: 1740/531, loss: 0.006914136465638876
2023-01-24 05:53:00.844625: step: 1744/531, loss: 0.040340542793273926
2023-01-24 05:53:01.911501: step: 1748/531, loss: 0.025750571861863136
2023-01-24 05:53:02.973229: step: 1752/531, loss: 0.010608994401991367
2023-01-24 05:53:04.047754: step: 1756/531, loss: 0.007926186546683311
2023-01-24 05:53:05.111056: step: 1760/531, loss: 0.005685245618224144
2023-01-24 05:53:06.190515: step: 1764/531, loss: 0.018118424341082573
2023-01-24 05:53:07.268150: step: 1768/531, loss: 0.011907443404197693
2023-01-24 05:53:08.323908: step: 1772/531, loss: 0.002592187374830246
2023-01-24 05:53:09.379585: step: 1776/531, loss: 0.00498719047755003
2023-01-24 05:53:10.451096: step: 1780/531, loss: 0.007208333350718021
2023-01-24 05:53:11.505000: step: 1784/531, loss: 0.04381411522626877
2023-01-24 05:53:12.592825: step: 1788/531, loss: 0.004342720843851566
2023-01-24 05:53:13.658092: step: 1792/531, loss: 0.006631031166762114
2023-01-24 05:53:14.715886: step: 1796/531, loss: 0.001173530239611864
2023-01-24 05:53:15.787353: step: 1800/531, loss: 0.001868226332589984
2023-01-24 05:53:16.864683: step: 1804/531, loss: 0.00784171000123024
2023-01-24 05:53:17.936155: step: 1808/531, loss: 0.0069846780970692635
2023-01-24 05:53:18.998085: step: 1812/531, loss: 0.0037238539662212133
2023-01-24 05:53:20.052719: step: 1816/531, loss: 0.0016817169962450862
2023-01-24 05:53:21.109941: step: 1820/531, loss: 0.0042967661283910275
2023-01-24 05:53:22.173351: step: 1824/531, loss: 0.005480621941387653
2023-01-24 05:53:23.224619: step: 1828/531, loss: 0.02603236399590969
2023-01-24 05:53:24.287544: step: 1832/531, loss: 0.020367998629808426
2023-01-24 05:53:25.337101: step: 1836/531, loss: 0.007561712525784969
2023-01-24 05:53:26.406649: step: 1840/531, loss: 0.010053700767457485
2023-01-24 05:53:27.480151: step: 1844/531, loss: 0.012591834180057049
2023-01-24 05:53:28.532027: step: 1848/531, loss: 0.005055839661508799
2023-01-24 05:53:29.589348: step: 1852/531, loss: 0.0024400800466537476
2023-01-24 05:53:30.639572: step: 1856/531, loss: 0.010241357609629631
2023-01-24 05:53:31.692973: step: 1860/531, loss: 0.08464954793453217
2023-01-24 05:53:32.769922: step: 1864/531, loss: 0.006787307560443878
2023-01-24 05:53:33.827295: step: 1868/531, loss: 0.010291000828146935
2023-01-24 05:53:34.905970: step: 1872/531, loss: 0.008114447817206383
2023-01-24 05:53:35.972844: step: 1876/531, loss: 0.0033625962678343058
2023-01-24 05:53:37.042135: step: 1880/531, loss: 0.007749938406050205
2023-01-24 05:53:38.106624: step: 1884/531, loss: 0.00843559019267559
2023-01-24 05:53:39.165969: step: 1888/531, loss: 0.008046545088291168
2023-01-24 05:53:40.212217: step: 1892/531, loss: 0.023566262796521187
2023-01-24 05:53:41.285914: step: 1896/531, loss: 0.012293393723666668
2023-01-24 05:53:42.364650: step: 1900/531, loss: 0.05550937354564667
2023-01-24 05:53:43.429669: step: 1904/531, loss: 0.025415586307644844
2023-01-24 05:53:44.502299: step: 1908/531, loss: 0.016372740268707275
2023-01-24 05:53:45.575027: step: 1912/531, loss: 0.04654484987258911
2023-01-24 05:53:46.634715: step: 1916/531, loss: 0.010204870253801346
2023-01-24 05:53:47.683176: step: 1920/531, loss: 0.016956163570284843
2023-01-24 05:53:48.765718: step: 1924/531, loss: 0.003951470833271742
2023-01-24 05:53:49.819568: step: 1928/531, loss: 0.00043705650023184717
2023-01-24 05:53:50.868389: step: 1932/531, loss: 0.0102516645565629
2023-01-24 05:53:51.919943: step: 1936/531, loss: 0.004810890648514032
2023-01-24 05:53:52.979347: step: 1940/531, loss: 0.01888265833258629
2023-01-24 05:53:54.043779: step: 1944/531, loss: 0.035354502499103546
2023-01-24 05:53:55.113875: step: 1948/531, loss: 0.004907671827822924
2023-01-24 05:53:56.161599: step: 1952/531, loss: 0.0027734641917049885
2023-01-24 05:53:57.247760: step: 1956/531, loss: 0.0067260474897921085
2023-01-24 05:53:58.313010: step: 1960/531, loss: 0.008661641739308834
2023-01-24 05:53:59.391653: step: 1964/531, loss: 0.00519506074488163
2023-01-24 05:54:00.474995: step: 1968/531, loss: 0.005057011265307665
2023-01-24 05:54:01.552602: step: 1972/531, loss: 0.012670012190937996
2023-01-24 05:54:02.610089: step: 1976/531, loss: 0.005739648826420307
2023-01-24 05:54:03.676018: step: 1980/531, loss: 0.00497743533924222
2023-01-24 05:54:04.743975: step: 1984/531, loss: 0.016153978183865547
2023-01-24 05:54:05.798689: step: 1988/531, loss: 0.005767592694610357
2023-01-24 05:54:06.870209: step: 1992/531, loss: 0.006481880787760019
2023-01-24 05:54:07.932153: step: 1996/531, loss: 0.005682860501110554
2023-01-24 05:54:08.973754: step: 2000/531, loss: 0.004004604183137417
2023-01-24 05:54:10.040105: step: 2004/531, loss: 0.013545628637075424
2023-01-24 05:54:11.099859: step: 2008/531, loss: 0.014110635034739971
2023-01-24 05:54:12.184944: step: 2012/531, loss: 0.010650896467268467
2023-01-24 05:54:13.241754: step: 2016/531, loss: 0.006431364454329014
2023-01-24 05:54:14.297323: step: 2020/531, loss: 0.0027899337001144886
2023-01-24 05:54:15.367330: step: 2024/531, loss: 0.01540421787649393
2023-01-24 05:54:16.414781: step: 2028/531, loss: 0.004104196093976498
2023-01-24 05:54:17.473372: step: 2032/531, loss: 0.015195207670331001
2023-01-24 05:54:18.535219: step: 2036/531, loss: 0.016384121030569077
2023-01-24 05:54:19.577696: step: 2040/531, loss: 0.012861286289989948
2023-01-24 05:54:20.642092: step: 2044/531, loss: 0.004025546833872795
2023-01-24 05:54:21.707057: step: 2048/531, loss: 0.0530475378036499
2023-01-24 05:54:22.756987: step: 2052/531, loss: 0.0006397791439667344
2023-01-24 05:54:23.834716: step: 2056/531, loss: 0.015077264979481697
2023-01-24 05:54:24.907896: step: 2060/531, loss: 0.026661042124032974
2023-01-24 05:54:25.969099: step: 2064/531, loss: 0.005175887607038021
2023-01-24 05:54:27.024775: step: 2068/531, loss: 0.008792277425527573
2023-01-24 05:54:28.076163: step: 2072/531, loss: 0.028944917023181915
2023-01-24 05:54:29.139521: step: 2076/531, loss: 0.0038539026863873005
2023-01-24 05:54:30.213489: step: 2080/531, loss: 0.015821902081370354
2023-01-24 05:54:31.259218: step: 2084/531, loss: 0.013511608354747295
2023-01-24 05:54:32.333855: step: 2088/531, loss: 0.012183400802314281
2023-01-24 05:54:33.408632: step: 2092/531, loss: 0.010933508165180683
2023-01-24 05:54:34.481665: step: 2096/531, loss: 0.00789438746869564
2023-01-24 05:54:35.555449: step: 2100/531, loss: 0.01371679361909628
2023-01-24 05:54:36.618259: step: 2104/531, loss: 0.007995257154107094
2023-01-24 05:54:37.687976: step: 2108/531, loss: 0.0035291395615786314
2023-01-24 05:54:38.746631: step: 2112/531, loss: 0.0014713897835463285
2023-01-24 05:54:39.816435: step: 2116/531, loss: 0.0042847092263400555
2023-01-24 05:54:40.890055: step: 2120/531, loss: 0.015639590099453926
2023-01-24 05:54:41.952012: step: 2124/531, loss: 0.004624858032912016
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3864025950319013, 'r': 0.3204135370568138, 'f1': 0.3503276639604582}, 'combined': 0.25813617344454814, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.37838286894016265, 'r': 0.2705659288273661, 'f1': 0.3155179969185583}, 'combined': 0.19756734386489166, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.369667611952363, 'r': 0.33810206633973233, 'f1': 0.3531809493776788}, 'combined': 0.2602385942782896, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3835975478032156, 'r': 0.28570926463972596, 'f1': 0.327495167426828}, 'combined': 0.2029547516447948, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35989667312598334, 'r': 0.329848374041461, 'f1': 0.3442180061779207}, 'combined': 0.25363432034162575, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4048585708891052, 'r': 0.2872011161722353, 'f1': 0.3360283386682542}, 'combined': 0.2229098880274558, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4322916666666667, 'r': 0.29642857142857143, 'f1': 0.35169491525423724}, 'combined': 0.23446327683615814, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41, 'r': 0.44565217391304346, 'f1': 0.4270833333333333}, 'combined': 0.21354166666666666, 'stategy': 1, 'epoch': 2}
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, 'stategy': 1, 'epoch': 2}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3930320171215678, 'r': 0.3206902606494766, 'f1': 0.35319491611760534}, 'combined': 0.26024888556034076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38920916781391235, 'r': 0.27620163667227143, 'f1': 0.3231092985965707}, 'combined': 0.2023207757567312, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3756416609706083, 'r': 0.3385764496414401, 'f1': 0.3561472833553671}, 'combined': 0.2624243140513231, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3873793804968824, 'r': 0.2850329796983373, 'f1': 0.3284172202446297}, 'combined': 0.20352616465864376, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41, 'r': 0.44565217391304346, 'f1': 0.4270833333333333}, 'combined': 0.21354166666666666, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35989667312598334, 'r': 0.329848374041461, 'f1': 0.3442180061779207}, 'combined': 0.25363432034162575, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4048585708891052, 'r': 0.2872011161722353, 'f1': 0.3360283386682542}, 'combined': 0.2229098880274558, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 3
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 05:57:14.793205: step: 4/531, loss: 0.00825596135109663
2023-01-24 05:57:15.861024: step: 8/531, loss: 0.00016586575657129288
2023-01-24 05:57:16.911521: step: 12/531, loss: 0.0028286681044846773
2023-01-24 05:57:17.979029: step: 16/531, loss: 0.006053767167031765
2023-01-24 05:57:19.064535: step: 20/531, loss: 0.004816325847059488
2023-01-24 05:57:20.136391: step: 24/531, loss: 0.018235409632325172
2023-01-24 05:57:21.196487: step: 28/531, loss: 0.008318692445755005
2023-01-24 05:57:22.266567: step: 32/531, loss: 0.012458117678761482
2023-01-24 05:57:23.337005: step: 36/531, loss: 0.042028073221445084
2023-01-24 05:57:24.407546: step: 40/531, loss: 0.007052010390907526
2023-01-24 05:57:25.466235: step: 44/531, loss: 0.013949177227914333
2023-01-24 05:57:26.536741: step: 48/531, loss: 0.00538051500916481
2023-01-24 05:57:27.609693: step: 52/531, loss: 0.001497541437856853
2023-01-24 05:57:28.664659: step: 56/531, loss: 0.014978907071053982
2023-01-24 05:57:29.730196: step: 60/531, loss: 0.0023460162337869406
2023-01-24 05:57:30.794428: step: 64/531, loss: 0.04558098316192627
2023-01-24 05:57:31.863017: step: 68/531, loss: 0.007001228164881468
2023-01-24 05:57:32.921578: step: 72/531, loss: 0.028760366141796112
2023-01-24 05:57:33.990559: step: 76/531, loss: 0.005202973261475563
2023-01-24 05:57:35.059427: step: 80/531, loss: 0.019886594265699387
2023-01-24 05:57:36.136165: step: 84/531, loss: 0.0015385076403617859
2023-01-24 05:57:37.211785: step: 88/531, loss: 0.013544277288019657
2023-01-24 05:57:38.276056: step: 92/531, loss: 0.020996497943997383
2023-01-24 05:57:39.346390: step: 96/531, loss: 0.002939745783805847
2023-01-24 05:57:40.405270: step: 100/531, loss: 0.0149089265614748
2023-01-24 05:57:41.480570: step: 104/531, loss: 0.013207102194428444
2023-01-24 05:57:42.570389: step: 108/531, loss: 0.005114658270031214
2023-01-24 05:57:43.624697: step: 112/531, loss: 0.003013624344021082
2023-01-24 05:57:44.709281: step: 116/531, loss: 0.008817988447844982
2023-01-24 05:57:45.786405: step: 120/531, loss: 0.008939876221120358
2023-01-24 05:57:46.852814: step: 124/531, loss: 0.07155707478523254
2023-01-24 05:57:47.921362: step: 128/531, loss: 0.013058925047516823
2023-01-24 05:57:48.979319: step: 132/531, loss: 0.007229271810501814
2023-01-24 05:57:50.026770: step: 136/531, loss: 0.0019203925039619207
2023-01-24 05:57:51.092816: step: 140/531, loss: 0.005608052015304565
2023-01-24 05:57:52.159767: step: 144/531, loss: 0.016013264656066895
2023-01-24 05:57:53.220028: step: 148/531, loss: 0.0034265010617673397
2023-01-24 05:57:54.292350: step: 152/531, loss: 0.021052032709121704
2023-01-24 05:57:55.365178: step: 156/531, loss: 0.008227755315601826
2023-01-24 05:57:56.438807: step: 160/531, loss: 0.003688282798975706
2023-01-24 05:57:57.507513: step: 164/531, loss: 0.012636126950383186
2023-01-24 05:57:58.566779: step: 168/531, loss: 0.005776895675808191
2023-01-24 05:57:59.644700: step: 172/531, loss: 0.003211360424757004
2023-01-24 05:58:00.704827: step: 176/531, loss: 0.004356752149760723
2023-01-24 05:58:01.748967: step: 180/531, loss: 0.02256453037261963
2023-01-24 05:58:02.819995: step: 184/531, loss: 0.009278696961700916
2023-01-24 05:58:03.879365: step: 188/531, loss: 0.02773536741733551
2023-01-24 05:58:04.950725: step: 192/531, loss: 0.017448367550969124
2023-01-24 05:58:06.012778: step: 196/531, loss: 0.007279939018189907
2023-01-24 05:58:07.083426: step: 200/531, loss: 0.011650837026536465
2023-01-24 05:58:08.134964: step: 204/531, loss: 0.010631701909005642
2023-01-24 05:58:09.203152: step: 208/531, loss: 0.004068745765835047
2023-01-24 05:58:10.269713: step: 212/531, loss: 0.00975571945309639
2023-01-24 05:58:11.344799: step: 216/531, loss: 0.005036220885813236
2023-01-24 05:58:12.435374: step: 220/531, loss: 0.003934045787900686
2023-01-24 05:58:13.509732: step: 224/531, loss: 0.05864235386252403
2023-01-24 05:58:14.571467: step: 228/531, loss: 0.004538682289421558
2023-01-24 05:58:15.630961: step: 232/531, loss: 0.0034913637209683657
2023-01-24 05:58:16.691330: step: 236/531, loss: 0.019596682861447334
2023-01-24 05:58:17.751100: step: 240/531, loss: 0.0006120089092291892
2023-01-24 05:58:18.828044: step: 244/531, loss: 0.007744806818664074
2023-01-24 05:58:19.915827: step: 248/531, loss: 0.002766442485153675
2023-01-24 05:58:20.971469: step: 252/531, loss: 0.029749469831585884
2023-01-24 05:58:22.022262: step: 256/531, loss: 0.009306740947067738
2023-01-24 05:58:23.073077: step: 260/531, loss: 0.01456803735345602
2023-01-24 05:58:24.137864: step: 264/531, loss: 0.0026536439545452595
2023-01-24 05:58:25.194026: step: 268/531, loss: 0.008977441117167473
2023-01-24 05:58:26.271966: step: 272/531, loss: 0.03587059676647186
2023-01-24 05:58:27.347262: step: 276/531, loss: 0.0036901943385601044
2023-01-24 05:58:28.420591: step: 280/531, loss: 0.0026352743152529
2023-01-24 05:58:29.489377: step: 284/531, loss: 0.011832822114229202
2023-01-24 05:58:30.563326: step: 288/531, loss: 0.011179967783391476
2023-01-24 05:58:31.626660: step: 292/531, loss: 0.00022906227968633175
2023-01-24 05:58:32.690236: step: 296/531, loss: 0.003962282091379166
2023-01-24 05:58:33.764216: step: 300/531, loss: 0.006789751350879669
2023-01-24 05:58:34.830625: step: 304/531, loss: 0.006102881394326687
2023-01-24 05:58:35.896945: step: 308/531, loss: 0.008739740587770939
2023-01-24 05:58:36.964057: step: 312/531, loss: 0.00865511316806078
2023-01-24 05:58:38.043399: step: 316/531, loss: 0.010070760734379292
2023-01-24 05:58:39.118285: step: 320/531, loss: 0.004473298322409391
2023-01-24 05:58:40.173809: step: 324/531, loss: 0.009891677647829056
2023-01-24 05:58:41.248498: step: 328/531, loss: 0.004360807593911886
2023-01-24 05:58:42.338456: step: 332/531, loss: 0.00655454583466053
2023-01-24 05:58:43.400157: step: 336/531, loss: 0.0032483020331710577
2023-01-24 05:58:44.470150: step: 340/531, loss: 0.005746086128056049
2023-01-24 05:58:45.553173: step: 344/531, loss: 0.012817678041756153
2023-01-24 05:58:46.628828: step: 348/531, loss: 0.011524232104420662
2023-01-24 05:58:47.725609: step: 352/531, loss: 0.013928496278822422
2023-01-24 05:58:48.802986: step: 356/531, loss: 0.07018346339464188
2023-01-24 05:58:49.875777: step: 360/531, loss: 0.00577493105083704
2023-01-24 05:58:50.957636: step: 364/531, loss: 0.0031595155596733093
2023-01-24 05:58:52.029686: step: 368/531, loss: 0.012158900499343872
2023-01-24 05:58:53.106180: step: 372/531, loss: 0.005312105640769005
2023-01-24 05:58:54.190019: step: 376/531, loss: 0.02854202874004841
2023-01-24 05:58:55.257380: step: 380/531, loss: 0.009361553005874157
2023-01-24 05:58:56.332316: step: 384/531, loss: 0.004679825156927109
2023-01-24 05:58:57.394142: step: 388/531, loss: 0.004918469116091728
2023-01-24 05:58:58.458024: step: 392/531, loss: 0.01258725393563509
2023-01-24 05:58:59.524214: step: 396/531, loss: 0.0035387177485972643
2023-01-24 05:59:00.582513: step: 400/531, loss: 0.003993109799921513
2023-01-24 05:59:01.647399: step: 404/531, loss: 0.0033950379583984613
2023-01-24 05:59:02.705169: step: 408/531, loss: 0.00237878761254251
2023-01-24 05:59:03.772005: step: 412/531, loss: 0.0074381413869559765
2023-01-24 05:59:04.825159: step: 416/531, loss: 0.005622901953756809
2023-01-24 05:59:05.869222: step: 420/531, loss: 0.011522011831402779
2023-01-24 05:59:06.927134: step: 424/531, loss: 0.006392822600901127
2023-01-24 05:59:07.989135: step: 428/531, loss: 0.0032358590979129076
2023-01-24 05:59:09.052973: step: 432/531, loss: 0.007227728608995676
2023-01-24 05:59:10.112198: step: 436/531, loss: 0.013248465023934841
2023-01-24 05:59:11.166067: step: 440/531, loss: 0.03283291310071945
2023-01-24 05:59:12.217478: step: 444/531, loss: 0.0037193107418715954
2023-01-24 05:59:13.299834: step: 448/531, loss: 0.0038427719846367836
2023-01-24 05:59:14.372959: step: 452/531, loss: 0.013870516791939735
2023-01-24 05:59:15.435828: step: 456/531, loss: 0.0075324522331357
2023-01-24 05:59:16.510757: step: 460/531, loss: 0.014308858662843704
2023-01-24 05:59:17.573607: step: 464/531, loss: 0.009213636629283428
2023-01-24 05:59:18.634192: step: 468/531, loss: 0.010558145120739937
2023-01-24 05:59:19.689790: step: 472/531, loss: 0.0036829900927841663
2023-01-24 05:59:20.773175: step: 476/531, loss: 0.02445288933813572
2023-01-24 05:59:21.831392: step: 480/531, loss: 0.008990545757114887
2023-01-24 05:59:22.897907: step: 484/531, loss: 0.018219618126749992
2023-01-24 05:59:23.980897: step: 488/531, loss: 0.013771738857030869
2023-01-24 05:59:25.026368: step: 492/531, loss: 0.018816614523530006
2023-01-24 05:59:26.088816: step: 496/531, loss: 0.0018912581726908684
2023-01-24 05:59:27.160892: step: 500/531, loss: 0.011184596456587315
2023-01-24 05:59:28.219910: step: 504/531, loss: 0.004793441854417324
2023-01-24 05:59:29.277278: step: 508/531, loss: 0.0027120495215058327
2023-01-24 05:59:30.344161: step: 512/531, loss: 0.002141448436304927
2023-01-24 05:59:31.413541: step: 516/531, loss: 0.008437187410891056
2023-01-24 05:59:32.484382: step: 520/531, loss: 0.010813063010573387
2023-01-24 05:59:33.570936: step: 524/531, loss: 0.03009651042521
2023-01-24 05:59:34.649976: step: 528/531, loss: 0.0066567291505634785
2023-01-24 05:59:35.714596: step: 532/531, loss: 0.005642846692353487
2023-01-24 05:59:36.770775: step: 536/531, loss: 0.002437244402244687
2023-01-24 05:59:37.832323: step: 540/531, loss: 0.00498404074460268
2023-01-24 05:59:38.906584: step: 544/531, loss: 0.006974169984459877
2023-01-24 05:59:39.965579: step: 548/531, loss: 0.0032037836499512196
2023-01-24 05:59:41.010876: step: 552/531, loss: 0.0017853636527433991
2023-01-24 05:59:42.100561: step: 556/531, loss: 0.0012945530470460653
2023-01-24 05:59:43.155854: step: 560/531, loss: 0.040665559470653534
2023-01-24 05:59:44.235561: step: 564/531, loss: 0.0016492478316649795
2023-01-24 05:59:45.285477: step: 568/531, loss: 0.004183882847428322
2023-01-24 05:59:46.354565: step: 572/531, loss: 0.005279974080622196
2023-01-24 05:59:47.414612: step: 576/531, loss: 0.0058014593087136745
2023-01-24 05:59:48.493017: step: 580/531, loss: 0.004608124028891325
2023-01-24 05:59:49.571565: step: 584/531, loss: 0.006839042529463768
2023-01-24 05:59:50.642395: step: 588/531, loss: 0.00027707641129381955
2023-01-24 05:59:51.722780: step: 592/531, loss: 0.005235550459474325
2023-01-24 05:59:52.780092: step: 596/531, loss: 0.005289706401526928
2023-01-24 05:59:53.859875: step: 600/531, loss: 0.011757896281778812
2023-01-24 05:59:54.926339: step: 604/531, loss: 0.006067200098186731
2023-01-24 05:59:55.972062: step: 608/531, loss: 0.005957695655524731
2023-01-24 05:59:57.036623: step: 612/531, loss: 0.013614512048661709
2023-01-24 05:59:58.100589: step: 616/531, loss: 0.008196470327675343
2023-01-24 05:59:59.164774: step: 620/531, loss: 0.010286089964210987
2023-01-24 06:00:00.242579: step: 624/531, loss: 0.005689904093742371
2023-01-24 06:00:01.316538: step: 628/531, loss: 0.0031526912935078144
2023-01-24 06:00:02.390766: step: 632/531, loss: 0.0054020872339606285
2023-01-24 06:00:03.449163: step: 636/531, loss: 0.009811890311539173
2023-01-24 06:00:04.508342: step: 640/531, loss: 0.011979300528764725
2023-01-24 06:00:05.577176: step: 644/531, loss: 0.011244582012295723
2023-01-24 06:00:06.625802: step: 648/531, loss: 0.008071884512901306
2023-01-24 06:00:07.693525: step: 652/531, loss: 0.0025572855956852436
2023-01-24 06:00:08.748671: step: 656/531, loss: 0.0036156997084617615
2023-01-24 06:00:09.802248: step: 660/531, loss: 0.003823567647486925
2023-01-24 06:00:10.851125: step: 664/531, loss: 0.019515687599778175
2023-01-24 06:00:11.942557: step: 668/531, loss: 0.012334228493273258
2023-01-24 06:00:13.010760: step: 672/531, loss: 0.006226486060768366
2023-01-24 06:00:14.066538: step: 676/531, loss: 0.000510255282279104
2023-01-24 06:00:15.129889: step: 680/531, loss: 0.01388457790017128
2023-01-24 06:00:16.182574: step: 684/531, loss: 0.009974336251616478
2023-01-24 06:00:17.257685: step: 688/531, loss: 0.008342131972312927
2023-01-24 06:00:18.326472: step: 692/531, loss: 0.0007959392969496548
2023-01-24 06:00:19.392068: step: 696/531, loss: 0.0037402233574539423
2023-01-24 06:00:20.447703: step: 700/531, loss: 0.009263568557798862
2023-01-24 06:00:21.514532: step: 704/531, loss: 0.010787513107061386
2023-01-24 06:00:22.591525: step: 708/531, loss: 0.014701229520142078
2023-01-24 06:00:23.667721: step: 712/531, loss: 0.04599161818623543
2023-01-24 06:00:24.734330: step: 716/531, loss: 0.006098523736000061
2023-01-24 06:00:25.804781: step: 720/531, loss: 0.07113492488861084
2023-01-24 06:00:26.850713: step: 724/531, loss: 0.008178084157407284
2023-01-24 06:00:27.914131: step: 728/531, loss: 0.007214087061583996
2023-01-24 06:00:28.960779: step: 732/531, loss: 6.0081314586568624e-05
2023-01-24 06:00:30.045493: step: 736/531, loss: 0.021966680884361267
2023-01-24 06:00:31.106398: step: 740/531, loss: 0.006906636990606785
2023-01-24 06:00:32.171068: step: 744/531, loss: 0.005075166001915932
2023-01-24 06:00:33.227549: step: 748/531, loss: 0.003017052076756954
2023-01-24 06:00:34.282333: step: 752/531, loss: 0.0024422996211797
2023-01-24 06:00:35.343988: step: 756/531, loss: 0.004597730003297329
2023-01-24 06:00:36.404374: step: 760/531, loss: 0.026027733460068703
2023-01-24 06:00:37.497109: step: 764/531, loss: 0.0026450571604073048
2023-01-24 06:00:38.570168: step: 768/531, loss: 0.0023178867995738983
2023-01-24 06:00:39.648968: step: 772/531, loss: 0.009700399823486805
2023-01-24 06:00:40.698123: step: 776/531, loss: 0.01435423269867897
2023-01-24 06:00:41.768872: step: 780/531, loss: 0.006480752024799585
2023-01-24 06:00:42.843807: step: 784/531, loss: 0.031863827258348465
2023-01-24 06:00:43.906049: step: 788/531, loss: 0.01961096003651619
2023-01-24 06:00:44.966695: step: 792/531, loss: 0.003960778936743736
2023-01-24 06:00:46.028350: step: 796/531, loss: 0.006863596383482218
2023-01-24 06:00:47.101126: step: 800/531, loss: 0.03473423048853874
2023-01-24 06:00:48.170829: step: 804/531, loss: 0.005358964204788208
2023-01-24 06:00:49.244101: step: 808/531, loss: 0.04858779534697533
2023-01-24 06:00:50.312440: step: 812/531, loss: 0.02484353445470333
2023-01-24 06:00:51.370901: step: 816/531, loss: 0.0008629474905319512
2023-01-24 06:00:52.437484: step: 820/531, loss: 0.005493585020303726
2023-01-24 06:00:53.499189: step: 824/531, loss: 0.005706422496587038
2023-01-24 06:00:54.558806: step: 828/531, loss: 0.003967179451137781
2023-01-24 06:00:55.612405: step: 832/531, loss: 0.0035745592322200537
2023-01-24 06:00:56.674878: step: 836/531, loss: 0.03399597853422165
2023-01-24 06:00:57.723916: step: 840/531, loss: 0.0048324232921004295
2023-01-24 06:00:58.785185: step: 844/531, loss: 0.015490568242967129
2023-01-24 06:00:59.839968: step: 848/531, loss: 0.009137268178164959
2023-01-24 06:01:00.915681: step: 852/531, loss: 0.008090930059552193
2023-01-24 06:01:01.975087: step: 856/531, loss: 0.03114093653857708
2023-01-24 06:01:03.032219: step: 860/531, loss: 0.004642469808459282
2023-01-24 06:01:04.123833: step: 864/531, loss: 0.06422934681177139
2023-01-24 06:01:05.168526: step: 868/531, loss: 0.021638648584485054
2023-01-24 06:01:06.233804: step: 872/531, loss: 0.03170209378004074
2023-01-24 06:01:07.304135: step: 876/531, loss: 0.006259063258767128
2023-01-24 06:01:08.374193: step: 880/531, loss: 0.02374625764787197
2023-01-24 06:01:09.440966: step: 884/531, loss: 0.08532796055078506
2023-01-24 06:01:10.489117: step: 888/531, loss: 0.00865882821381092
2023-01-24 06:01:11.557867: step: 892/531, loss: 0.010816564783453941
2023-01-24 06:01:12.629090: step: 896/531, loss: 0.007841667160391808
2023-01-24 06:01:13.685751: step: 900/531, loss: 0.049881499260663986
2023-01-24 06:01:14.745913: step: 904/531, loss: 0.0368400476872921
2023-01-24 06:01:15.810983: step: 908/531, loss: 0.0008017414365895092
2023-01-24 06:01:16.877661: step: 912/531, loss: 0.00277475593611598
2023-01-24 06:01:17.939037: step: 916/531, loss: 0.018239369615912437
2023-01-24 06:01:19.002476: step: 920/531, loss: 0.023079991340637207
2023-01-24 06:01:20.051575: step: 924/531, loss: 0.004089293535798788
2023-01-24 06:01:21.115865: step: 928/531, loss: 0.007062810938805342
2023-01-24 06:01:22.164332: step: 932/531, loss: 0.0007188616436906159
2023-01-24 06:01:23.223853: step: 936/531, loss: 0.007054132409393787
2023-01-24 06:01:24.288834: step: 940/531, loss: 0.0025027741212397814
2023-01-24 06:01:25.372888: step: 944/531, loss: 0.008826656267046928
2023-01-24 06:01:26.462189: step: 948/531, loss: 0.04039265215396881
2023-01-24 06:01:27.517830: step: 952/531, loss: 0.01714899018406868
2023-01-24 06:01:28.574264: step: 956/531, loss: 0.011195934377610683
2023-01-24 06:01:29.650250: step: 960/531, loss: 0.026175515726208687
2023-01-24 06:01:30.707157: step: 964/531, loss: 0.005881982855498791
2023-01-24 06:01:31.750563: step: 968/531, loss: 0.0
2023-01-24 06:01:32.800600: step: 972/531, loss: 0.009446099400520325
2023-01-24 06:01:33.847311: step: 976/531, loss: 0.014840062707662582
2023-01-24 06:01:34.917092: step: 980/531, loss: 0.013021034188568592
2023-01-24 06:01:35.982550: step: 984/531, loss: 0.0033347129356116056
2023-01-24 06:01:37.038830: step: 988/531, loss: 0.043203387409448624
2023-01-24 06:01:38.103966: step: 992/531, loss: 0.008585507981479168
2023-01-24 06:01:39.164910: step: 996/531, loss: 0.005980364978313446
2023-01-24 06:01:40.213757: step: 1000/531, loss: 0.011566465720534325
2023-01-24 06:01:41.282715: step: 1004/531, loss: 0.015538278967142105
2023-01-24 06:01:42.354496: step: 1008/531, loss: 0.012091074138879776
2023-01-24 06:01:43.409190: step: 1012/531, loss: 0.0037062913179397583
2023-01-24 06:01:44.459356: step: 1016/531, loss: 0.02916717156767845
2023-01-24 06:01:45.519251: step: 1020/531, loss: 0.011735990643501282
2023-01-24 06:01:46.565011: step: 1024/531, loss: 0.010441160760819912
2023-01-24 06:01:47.631444: step: 1028/531, loss: 0.005095531232655048
2023-01-24 06:01:48.686380: step: 1032/531, loss: 0.00971211213618517
2023-01-24 06:01:49.754746: step: 1036/531, loss: 0.061905305832624435
2023-01-24 06:01:50.804409: step: 1040/531, loss: 0.0012857085093855858
2023-01-24 06:01:51.851797: step: 1044/531, loss: 0.0010416122386232018
2023-01-24 06:01:52.918841: step: 1048/531, loss: 0.002953298855572939
2023-01-24 06:01:53.981363: step: 1052/531, loss: 0.00984971597790718
2023-01-24 06:01:55.053729: step: 1056/531, loss: 0.021457791328430176
2023-01-24 06:01:56.122563: step: 1060/531, loss: 0.005005578976124525
2023-01-24 06:01:57.193366: step: 1064/531, loss: 0.011042384430766106
2023-01-24 06:01:58.252722: step: 1068/531, loss: 0.025549301877617836
2023-01-24 06:01:59.312204: step: 1072/531, loss: 0.005598848219960928
2023-01-24 06:02:00.375838: step: 1076/531, loss: 0.0011638473952189088
2023-01-24 06:02:01.442593: step: 1080/531, loss: 0.003443461610004306
2023-01-24 06:02:02.519280: step: 1084/531, loss: 0.028383811935782433
2023-01-24 06:02:03.604206: step: 1088/531, loss: 0.01226129475980997
2023-01-24 06:02:04.650912: step: 1092/531, loss: 0.003556832205504179
2023-01-24 06:02:05.702190: step: 1096/531, loss: 0.004501263611018658
2023-01-24 06:02:06.763641: step: 1100/531, loss: 0.020327776670455933
2023-01-24 06:02:07.815832: step: 1104/531, loss: 0.09774454683065414
2023-01-24 06:02:08.872539: step: 1108/531, loss: 0.03078611008822918
2023-01-24 06:02:09.910130: step: 1112/531, loss: 0.010324189439415932
2023-01-24 06:02:10.985335: step: 1116/531, loss: 0.022571392357349396
2023-01-24 06:02:12.090124: step: 1120/531, loss: 0.005407420452684164
2023-01-24 06:02:13.134375: step: 1124/531, loss: 0.013136330991983414
2023-01-24 06:02:14.192459: step: 1128/531, loss: 0.012684522196650505
2023-01-24 06:02:15.256702: step: 1132/531, loss: 0.0024550834205001593
2023-01-24 06:02:16.324651: step: 1136/531, loss: 0.010017668828368187
2023-01-24 06:02:17.393678: step: 1140/531, loss: 0.011186819523572922
2023-01-24 06:02:18.456161: step: 1144/531, loss: 0.007019475102424622
2023-01-24 06:02:19.534919: step: 1148/531, loss: 0.013907302170991898
2023-01-24 06:02:20.596137: step: 1152/531, loss: 0.00404173880815506
2023-01-24 06:02:21.670069: step: 1156/531, loss: 0.006247961428016424
2023-01-24 06:02:22.723269: step: 1160/531, loss: 0.003992138896137476
2023-01-24 06:02:23.784075: step: 1164/531, loss: 0.008561491966247559
2023-01-24 06:02:24.838686: step: 1168/531, loss: 0.006891845725476742
2023-01-24 06:02:25.886253: step: 1172/531, loss: 0.020960526540875435
2023-01-24 06:02:26.947633: step: 1176/531, loss: 0.008791033178567886
2023-01-24 06:02:28.000534: step: 1180/531, loss: 0.0019249562174081802
2023-01-24 06:02:29.055932: step: 1184/531, loss: 0.003304139245301485
2023-01-24 06:02:30.105419: step: 1188/531, loss: 0.005203144624829292
2023-01-24 06:02:31.166062: step: 1192/531, loss: 0.0030283795204013586
2023-01-24 06:02:32.219264: step: 1196/531, loss: 0.059227969497442245
2023-01-24 06:02:33.280268: step: 1200/531, loss: 0.011674697510898113
2023-01-24 06:02:34.342876: step: 1204/531, loss: 0.007917428389191628
2023-01-24 06:02:35.426377: step: 1208/531, loss: 0.010782918892800808
2023-01-24 06:02:36.472825: step: 1212/531, loss: 0.014027918688952923
2023-01-24 06:02:37.529892: step: 1216/531, loss: 0.011139859445393085
2023-01-24 06:02:38.587845: step: 1220/531, loss: 0.006109717767685652
2023-01-24 06:02:39.640938: step: 1224/531, loss: 0.011085920967161655
2023-01-24 06:02:40.713879: step: 1228/531, loss: 0.11575441807508469
2023-01-24 06:02:41.764928: step: 1232/531, loss: 0.028393127024173737
2023-01-24 06:02:42.849512: step: 1236/531, loss: 0.005467280279844999
2023-01-24 06:02:43.901989: step: 1240/531, loss: 0.006713276728987694
2023-01-24 06:02:44.974500: step: 1244/531, loss: 0.004648793023079634
2023-01-24 06:02:46.026141: step: 1248/531, loss: 0.00685318885371089
2023-01-24 06:02:47.090257: step: 1252/531, loss: 0.03564877063035965
2023-01-24 06:02:48.149020: step: 1256/531, loss: 0.041564859449863434
2023-01-24 06:02:49.212254: step: 1260/531, loss: 0.013147922232747078
2023-01-24 06:02:50.264759: step: 1264/531, loss: 0.0014401249354705215
2023-01-24 06:02:51.308637: step: 1268/531, loss: 0.0027441091369837523
2023-01-24 06:02:52.367905: step: 1272/531, loss: 0.011722305789589882
2023-01-24 06:02:53.430299: step: 1276/531, loss: 0.08332924544811249
2023-01-24 06:02:54.485624: step: 1280/531, loss: 0.002597358077764511
2023-01-24 06:02:55.548564: step: 1284/531, loss: 0.01555523369461298
2023-01-24 06:02:56.612500: step: 1288/531, loss: 0.13061170279979706
2023-01-24 06:02:57.687476: step: 1292/531, loss: 0.005295668262988329
2023-01-24 06:02:58.742245: step: 1296/531, loss: 0.017770804464817047
2023-01-24 06:02:59.792737: step: 1300/531, loss: 0.007504474371671677
2023-01-24 06:03:00.832746: step: 1304/531, loss: 0.02351203002035618
2023-01-24 06:03:01.892989: step: 1308/531, loss: 0.010521844029426575
2023-01-24 06:03:02.954105: step: 1312/531, loss: 0.027280917391180992
2023-01-24 06:03:04.032856: step: 1316/531, loss: 0.006498619448393583
2023-01-24 06:03:05.077078: step: 1320/531, loss: 0.003986257128417492
2023-01-24 06:03:06.163224: step: 1324/531, loss: 0.0130449328571558
2023-01-24 06:03:07.220428: step: 1328/531, loss: 0.011105556041002274
2023-01-24 06:03:08.276208: step: 1332/531, loss: 0.0
2023-01-24 06:03:09.347852: step: 1336/531, loss: 0.008886473253369331
2023-01-24 06:03:10.398337: step: 1340/531, loss: 0.01760837994515896
2023-01-24 06:03:11.457848: step: 1344/531, loss: 0.005355107598006725
2023-01-24 06:03:12.514845: step: 1348/531, loss: 0.02342238463461399
2023-01-24 06:03:13.568867: step: 1352/531, loss: 0.015532005578279495
2023-01-24 06:03:14.642334: step: 1356/531, loss: 0.004329567309468985
2023-01-24 06:03:15.701578: step: 1360/531, loss: 0.0007388498052023351
2023-01-24 06:03:16.756731: step: 1364/531, loss: 0.001713779172860086
2023-01-24 06:03:17.811547: step: 1368/531, loss: 0.014009689912199974
2023-01-24 06:03:18.876275: step: 1372/531, loss: 0.06963585317134857
2023-01-24 06:03:19.930857: step: 1376/531, loss: 0.011355608701705933
2023-01-24 06:03:20.994011: step: 1380/531, loss: 0.05988581106066704
2023-01-24 06:03:22.044544: step: 1384/531, loss: 0.0018392998026683927
2023-01-24 06:03:23.107848: step: 1388/531, loss: 0.0037168115377426147
2023-01-24 06:03:24.185712: step: 1392/531, loss: 0.0038279080763459206
2023-01-24 06:03:25.243133: step: 1396/531, loss: 0.009530803188681602
2023-01-24 06:03:26.295785: step: 1400/531, loss: 0.012957570143043995
2023-01-24 06:03:27.377594: step: 1404/531, loss: 0.0163667444139719
2023-01-24 06:03:28.449042: step: 1408/531, loss: 0.006851600483059883
2023-01-24 06:03:29.514115: step: 1412/531, loss: 0.005970964208245277
2023-01-24 06:03:30.573446: step: 1416/531, loss: 0.0053473771549761295
2023-01-24 06:03:31.624871: step: 1420/531, loss: 0.0025720957200974226
2023-01-24 06:03:32.675897: step: 1424/531, loss: 0.004987241700291634
2023-01-24 06:03:33.734086: step: 1428/531, loss: 0.024758026003837585
2023-01-24 06:03:34.795419: step: 1432/531, loss: 0.0020685719791799784
2023-01-24 06:03:35.853799: step: 1436/531, loss: 0.008989634923636913
2023-01-24 06:03:36.906700: step: 1440/531, loss: 0.006896218750625849
2023-01-24 06:03:37.992082: step: 1444/531, loss: 0.02935216762125492
2023-01-24 06:03:39.052895: step: 1448/531, loss: 0.011283285915851593
2023-01-24 06:03:40.104988: step: 1452/531, loss: 0.02889883704483509
2023-01-24 06:03:41.181716: step: 1456/531, loss: 0.005969729274511337
2023-01-24 06:03:42.239033: step: 1460/531, loss: 0.002971237525343895
2023-01-24 06:03:43.297901: step: 1464/531, loss: 0.025799859315156937
2023-01-24 06:03:44.345490: step: 1468/531, loss: 0.03327492997050285
2023-01-24 06:03:45.409580: step: 1472/531, loss: 0.061219293624162674
2023-01-24 06:03:46.479800: step: 1476/531, loss: 0.00037485663779079914
2023-01-24 06:03:47.546381: step: 1480/531, loss: 0.004634445998817682
2023-01-24 06:03:48.601955: step: 1484/531, loss: 0.04018624126911163
2023-01-24 06:03:49.662667: step: 1488/531, loss: 0.027372492477297783
2023-01-24 06:03:50.723488: step: 1492/531, loss: 0.013875926844775677
2023-01-24 06:03:51.798033: step: 1496/531, loss: 0.00806163065135479
2023-01-24 06:03:52.878093: step: 1500/531, loss: 0.02455878257751465
2023-01-24 06:03:53.937666: step: 1504/531, loss: 0.010958276689052582
2023-01-24 06:03:55.001770: step: 1508/531, loss: 0.014744852669537067
2023-01-24 06:03:56.053925: step: 1512/531, loss: 0.013093473389744759
2023-01-24 06:03:57.103452: step: 1516/531, loss: 0.00933352392166853
2023-01-24 06:03:58.165442: step: 1520/531, loss: 0.01852133683860302
2023-01-24 06:03:59.225247: step: 1524/531, loss: 0.015952784568071365
2023-01-24 06:04:00.296358: step: 1528/531, loss: 0.007352899760007858
2023-01-24 06:04:01.353129: step: 1532/531, loss: 0.02387125976383686
2023-01-24 06:04:02.405594: step: 1536/531, loss: 0.01753857173025608
2023-01-24 06:04:03.469238: step: 1540/531, loss: 0.010952083393931389
2023-01-24 06:04:04.526761: step: 1544/531, loss: 0.04563755542039871
2023-01-24 06:04:05.583162: step: 1548/531, loss: 0.002622702158987522
2023-01-24 06:04:06.673051: step: 1552/531, loss: 0.010987264104187489
2023-01-24 06:04:07.751010: step: 1556/531, loss: 0.02206575870513916
2023-01-24 06:04:08.807543: step: 1560/531, loss: 0.02936229109764099
2023-01-24 06:04:09.875106: step: 1564/531, loss: 0.005610931199043989
2023-01-24 06:04:10.936611: step: 1568/531, loss: 0.004258530680090189
2023-01-24 06:04:12.008050: step: 1572/531, loss: 0.007061867509037256
2023-01-24 06:04:13.091917: step: 1576/531, loss: 0.0035791262052953243
2023-01-24 06:04:14.157688: step: 1580/531, loss: 0.009710179641842842
2023-01-24 06:04:15.193635: step: 1584/531, loss: 0.001007150742225349
2023-01-24 06:04:16.286227: step: 1588/531, loss: 0.010055597871541977
2023-01-24 06:04:17.343740: step: 1592/531, loss: 0.003203935921192169
2023-01-24 06:04:18.413893: step: 1596/531, loss: 0.033856719732284546
2023-01-24 06:04:19.468937: step: 1600/531, loss: 0.026200085878372192
2023-01-24 06:04:20.528010: step: 1604/531, loss: 0.008753352798521519
2023-01-24 06:04:21.614883: step: 1608/531, loss: 0.0017513601342216134
2023-01-24 06:04:22.652886: step: 1612/531, loss: 0.006941612344235182
2023-01-24 06:04:23.717043: step: 1616/531, loss: 0.01039678230881691
2023-01-24 06:04:24.752084: step: 1620/531, loss: 0.008160735480487347
2023-01-24 06:04:25.813783: step: 1624/531, loss: 0.0023922729305922985
2023-01-24 06:04:26.866552: step: 1628/531, loss: 0.001966872252523899
2023-01-24 06:04:27.915984: step: 1632/531, loss: 0.010224957019090652
2023-01-24 06:04:28.971007: step: 1636/531, loss: 0.002609137911349535
2023-01-24 06:04:30.025468: step: 1640/531, loss: 0.03572692349553108
2023-01-24 06:04:31.107534: step: 1644/531, loss: 0.006409843917936087
2023-01-24 06:04:32.170348: step: 1648/531, loss: 0.0025181996170431376
2023-01-24 06:04:33.234151: step: 1652/531, loss: 0.03474220633506775
2023-01-24 06:04:34.297247: step: 1656/531, loss: 0.00776472594588995
2023-01-24 06:04:35.366359: step: 1660/531, loss: 0.006455665919929743
2023-01-24 06:04:36.432741: step: 1664/531, loss: 0.03143719583749771
2023-01-24 06:04:37.490279: step: 1668/531, loss: 0.011104064993560314
2023-01-24 06:04:38.545137: step: 1672/531, loss: 0.02775968797504902
2023-01-24 06:04:39.598292: step: 1676/531, loss: 0.008741592988371849
2023-01-24 06:04:40.662967: step: 1680/531, loss: 0.01810801774263382
2023-01-24 06:04:41.725942: step: 1684/531, loss: 0.004843638278543949
2023-01-24 06:04:42.786518: step: 1688/531, loss: 0.004471385385841131
2023-01-24 06:04:43.842066: step: 1692/531, loss: 0.0061780172400176525
2023-01-24 06:04:44.906296: step: 1696/531, loss: 0.010288001969456673
2023-01-24 06:04:45.985061: step: 1700/531, loss: 0.005826051812618971
2023-01-24 06:04:47.064716: step: 1704/531, loss: 0.0075319078750908375
2023-01-24 06:04:48.124126: step: 1708/531, loss: 0.0026481272652745247
2023-01-24 06:04:49.181751: step: 1712/531, loss: 0.04316351190209389
2023-01-24 06:04:50.232566: step: 1716/531, loss: 0.002765804994851351
2023-01-24 06:04:51.275577: step: 1720/531, loss: 0.0032780934125185013
2023-01-24 06:04:52.328110: step: 1724/531, loss: 0.014150029979646206
2023-01-24 06:04:53.389300: step: 1728/531, loss: 0.06964344531297684
2023-01-24 06:04:54.442519: step: 1732/531, loss: 0.00605577789247036
2023-01-24 06:04:55.494121: step: 1736/531, loss: 0.0044052437879145145
2023-01-24 06:04:56.566019: step: 1740/531, loss: 0.07521738111972809
2023-01-24 06:04:57.632378: step: 1744/531, loss: 0.012526576407253742
2023-01-24 06:04:58.694874: step: 1748/531, loss: 0.0169774629175663
2023-01-24 06:04:59.743433: step: 1752/531, loss: 0.014141344465315342
2023-01-24 06:05:00.817444: step: 1756/531, loss: 0.008866876363754272
2023-01-24 06:05:01.869789: step: 1760/531, loss: 0.013693507760763168
2023-01-24 06:05:02.951920: step: 1764/531, loss: 0.025218477472662926
2023-01-24 06:05:04.013271: step: 1768/531, loss: 0.009164059534668922
2023-01-24 06:05:05.068487: step: 1772/531, loss: 0.032739702612161636
2023-01-24 06:05:06.128842: step: 1776/531, loss: 0.01979782059788704
2023-01-24 06:05:07.178274: step: 1780/531, loss: 0.005625186022371054
2023-01-24 06:05:08.242147: step: 1784/531, loss: 0.006696365773677826
2023-01-24 06:05:09.311846: step: 1788/531, loss: 0.004048663657158613
2023-01-24 06:05:10.379716: step: 1792/531, loss: 0.02188773639500141
2023-01-24 06:05:11.433120: step: 1796/531, loss: 0.0060102916322648525
2023-01-24 06:05:12.499348: step: 1800/531, loss: 0.030482010915875435
2023-01-24 06:05:13.560824: step: 1804/531, loss: 0.007428075652569532
2023-01-24 06:05:14.610113: step: 1808/531, loss: 0.005936458706855774
2023-01-24 06:05:15.673347: step: 1812/531, loss: 0.01320312637835741
2023-01-24 06:05:16.727293: step: 1816/531, loss: 0.0038099256344139576
2023-01-24 06:05:17.776668: step: 1820/531, loss: 0.002713568275794387
2023-01-24 06:05:18.846068: step: 1824/531, loss: 0.04737890884280205
2023-01-24 06:05:19.905683: step: 1828/531, loss: 0.0026436031330376863
2023-01-24 06:05:20.991185: step: 1832/531, loss: 0.012270888313651085
2023-01-24 06:05:22.054097: step: 1836/531, loss: 0.009706312790513039
2023-01-24 06:05:23.112061: step: 1840/531, loss: 0.0022018705494701862
2023-01-24 06:05:24.181653: step: 1844/531, loss: 0.0074734459631145
2023-01-24 06:05:25.243594: step: 1848/531, loss: 0.009813284501433372
2023-01-24 06:05:26.292919: step: 1852/531, loss: 0.05924934148788452
2023-01-24 06:05:27.354293: step: 1856/531, loss: 0.007057646289467812
2023-01-24 06:05:28.412869: step: 1860/531, loss: 0.005799010396003723
2023-01-24 06:05:29.470232: step: 1864/531, loss: 0.0604633167386055
2023-01-24 06:05:30.527870: step: 1868/531, loss: 0.029298024252057076
2023-01-24 06:05:31.585086: step: 1872/531, loss: 0.020175062119960785
2023-01-24 06:05:32.659709: step: 1876/531, loss: 0.03403453156352043
2023-01-24 06:05:33.725716: step: 1880/531, loss: 0.007818075828254223
2023-01-24 06:05:34.786706: step: 1884/531, loss: 0.003131083445623517
2023-01-24 06:05:35.852753: step: 1888/531, loss: 0.02331097237765789
2023-01-24 06:05:36.906773: step: 1892/531, loss: 0.0286044180393219
2023-01-24 06:05:37.946430: step: 1896/531, loss: 0.005853778682649136
2023-01-24 06:05:39.010166: step: 1900/531, loss: 0.0035308748483657837
2023-01-24 06:05:40.086850: step: 1904/531, loss: 0.064869225025177
2023-01-24 06:05:41.140989: step: 1908/531, loss: 0.0072122192941606045
2023-01-24 06:05:42.193083: step: 1912/531, loss: 0.004317569546401501
2023-01-24 06:05:43.245214: step: 1916/531, loss: 0.005695443134754896
2023-01-24 06:05:44.303607: step: 1920/531, loss: 0.010903386399149895
2023-01-24 06:05:45.353458: step: 1924/531, loss: 0.007791449781507254
2023-01-24 06:05:46.411043: step: 1928/531, loss: 0.011957583948969841
2023-01-24 06:05:47.465859: step: 1932/531, loss: 0.008363187313079834
2023-01-24 06:05:48.536190: step: 1936/531, loss: 0.01102373655885458
2023-01-24 06:05:49.591645: step: 1940/531, loss: 0.00917668454349041
2023-01-24 06:05:50.638192: step: 1944/531, loss: 0.0030903760343790054
2023-01-24 06:05:51.702952: step: 1948/531, loss: 0.00785362534224987
2023-01-24 06:05:52.781581: step: 1952/531, loss: 0.006935576908290386
2023-01-24 06:05:53.845360: step: 1956/531, loss: 0.004695732146501541
2023-01-24 06:05:54.899517: step: 1960/531, loss: 0.004890380892902613
2023-01-24 06:05:55.958454: step: 1964/531, loss: 0.008526074700057507
2023-01-24 06:05:57.027026: step: 1968/531, loss: 0.002123031532391906
2023-01-24 06:05:58.089767: step: 1972/531, loss: 0.005248913075774908
2023-01-24 06:05:59.141103: step: 1976/531, loss: 0.008927969262003899
2023-01-24 06:06:00.187707: step: 1980/531, loss: 0.0113055519759655
2023-01-24 06:06:01.249894: step: 1984/531, loss: 0.0013906665844842792
2023-01-24 06:06:02.304795: step: 1988/531, loss: 0.00942879356443882
2023-01-24 06:06:03.364898: step: 1992/531, loss: 0.005479065235704184
2023-01-24 06:06:04.420378: step: 1996/531, loss: 0.007529011927545071
2023-01-24 06:06:05.481553: step: 2000/531, loss: 0.00459635816514492
2023-01-24 06:06:06.533374: step: 2004/531, loss: 0.03991734981536865
2023-01-24 06:06:07.595414: step: 2008/531, loss: 0.004686987493187189
2023-01-24 06:06:08.648267: step: 2012/531, loss: 0.013272380456328392
2023-01-24 06:06:09.701432: step: 2016/531, loss: 0.020952170714735985
2023-01-24 06:06:10.773730: step: 2020/531, loss: 0.013088252395391464
2023-01-24 06:06:11.835683: step: 2024/531, loss: 0.013740804977715015
2023-01-24 06:06:12.902739: step: 2028/531, loss: 0.003718385472893715
2023-01-24 06:06:13.944797: step: 2032/531, loss: 0.011931989341974258
2023-01-24 06:06:15.006725: step: 2036/531, loss: 0.02632828615605831
2023-01-24 06:06:16.059931: step: 2040/531, loss: 0.010957547463476658
2023-01-24 06:06:17.105158: step: 2044/531, loss: 0.013814541511237621
2023-01-24 06:06:18.164299: step: 2048/531, loss: 0.0016523165395483375
2023-01-24 06:06:19.215411: step: 2052/531, loss: 0.011547659523785114
2023-01-24 06:06:20.268279: step: 2056/531, loss: 0.007431823294609785
2023-01-24 06:06:21.320339: step: 2060/531, loss: 0.0039128796197474
2023-01-24 06:06:22.399483: step: 2064/531, loss: 0.00915682502090931
2023-01-24 06:06:23.476490: step: 2068/531, loss: 0.0029002767987549305
2023-01-24 06:06:24.533012: step: 2072/531, loss: 0.0037574335001409054
2023-01-24 06:06:25.568500: step: 2076/531, loss: 0.006329825613647699
2023-01-24 06:06:26.632171: step: 2080/531, loss: 0.03108215145766735
2023-01-24 06:06:27.685209: step: 2084/531, loss: 0.0042252857238054276
2023-01-24 06:06:28.736466: step: 2088/531, loss: 0.00210560648702085
2023-01-24 06:06:29.789536: step: 2092/531, loss: 0.009277300909161568
2023-01-24 06:06:30.841872: step: 2096/531, loss: 0.02244584821164608
2023-01-24 06:06:31.917143: step: 2100/531, loss: 0.018372735008597374
2023-01-24 06:06:32.968963: step: 2104/531, loss: 0.008814483880996704
2023-01-24 06:06:34.033009: step: 2108/531, loss: 0.03223353624343872
2023-01-24 06:06:35.092682: step: 2112/531, loss: 0.009882899932563305
2023-01-24 06:06:36.152843: step: 2116/531, loss: 0.013947169296443462
2023-01-24 06:06:37.212431: step: 2120/531, loss: 0.003022989258170128
2023-01-24 06:06:38.284345: step: 2124/531, loss: 0.013685203157365322
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38433621370213833, 'r': 0.32088792035852154, 'f1': 0.3497578780329697}, 'combined': 0.2577163311821882, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38185071257194075, 'r': 0.2730456402791244, 'f1': 0.3184096898733428}, 'combined': 0.19937803010760718, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3688769001269001, 'r': 0.336678916434609, 'f1': 0.35204323206555344}, 'combined': 0.25940027625882883, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3847394071861491, 'r': 0.28413126644315245, 'f1': 0.32686885320068054}, 'combined': 0.20256661325112596, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3534712667765495, 'r': 0.32463015772267545, 'f1': 0.33843737511345195}, 'combined': 0.249374907978333, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.40358630625806197, 'r': 0.28604042986369405, 'f1': 0.3347956060357115}, 'combined': 0.22209213469695716, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.4322916666666667, 'r': 0.29642857142857143, 'f1': 0.35169491525423724}, 'combined': 0.23446327683615814, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41, 'r': 0.44565217391304346, 'f1': 0.4270833333333333}, 'combined': 0.21354166666666666, 'stategy': 1, 'epoch': 3}
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, 'stategy': 1, 'epoch': 3}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3930320171215678, 'r': 0.3206902606494766, 'f1': 0.35319491611760534}, 'combined': 0.26024888556034076, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38920916781391235, 'r': 0.27620163667227143, 'f1': 0.3231092985965707}, 'combined': 0.2023207757567312, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3756416609706083, 'r': 0.3385764496414401, 'f1': 0.3561472833553671}, 'combined': 0.2624243140513231, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3873793804968824, 'r': 0.2850329796983373, 'f1': 0.3284172202446297}, 'combined': 0.20352616465864376, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.41, 'r': 0.44565217391304346, 'f1': 0.4270833333333333}, 'combined': 0.21354166666666666, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35989667312598334, 'r': 0.329848374041461, 'f1': 0.3442180061779207}, 'combined': 0.25363432034162575, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4048585708891052, 'r': 0.2872011161722353, 'f1': 0.3360283386682542}, 'combined': 0.2229098880274558, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 4
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:09:01.544246: step: 4/531, loss: 0.014120172709226608
2023-01-24 06:09:02.610710: step: 8/531, loss: 0.006682697683572769
2023-01-24 06:09:03.671838: step: 12/531, loss: 0.03515120968222618
2023-01-24 06:09:04.720635: step: 16/531, loss: 0.010853380896151066
2023-01-24 06:09:05.782394: step: 20/531, loss: 0.006817764136940241
2023-01-24 06:09:06.838327: step: 24/531, loss: 0.0014552063075825572
2023-01-24 06:09:07.899423: step: 28/531, loss: 0.004277610685676336
2023-01-24 06:09:08.946799: step: 32/531, loss: 0.01216868031769991
2023-01-24 06:09:09.985509: step: 36/531, loss: 0.019867248833179474
2023-01-24 06:09:11.038763: step: 40/531, loss: 0.029024865478277206
2023-01-24 06:09:12.108079: step: 44/531, loss: 0.006300168111920357
2023-01-24 06:09:13.157035: step: 48/531, loss: 0.02416304126381874
2023-01-24 06:09:14.195271: step: 52/531, loss: 0.0017094590002670884
2023-01-24 06:09:15.240313: step: 56/531, loss: 0.0013462232891470194
2023-01-24 06:09:16.301582: step: 60/531, loss: 0.0010470687411725521
2023-01-24 06:09:17.358076: step: 64/531, loss: 0.0035332604311406612
2023-01-24 06:09:18.420145: step: 68/531, loss: 0.021271180361509323
2023-01-24 06:09:19.484656: step: 72/531, loss: 1.2698243153863586e-05
2023-01-24 06:09:20.576086: step: 76/531, loss: 0.0031765408348292112
2023-01-24 06:09:21.628923: step: 80/531, loss: 0.006587965413928032
2023-01-24 06:09:22.690281: step: 84/531, loss: 0.02233354188501835
2023-01-24 06:09:23.743520: step: 88/531, loss: 0.006880105473101139
2023-01-24 06:09:24.800320: step: 92/531, loss: 0.012796667404472828
2023-01-24 06:09:25.861261: step: 96/531, loss: 0.00949548464268446
2023-01-24 06:09:26.916734: step: 100/531, loss: 0.02511078305542469
2023-01-24 06:09:27.984829: step: 104/531, loss: 0.004062130115926266
2023-01-24 06:09:29.047508: step: 108/531, loss: 0.0035931048914790154
2023-01-24 06:09:30.098829: step: 112/531, loss: 0.004986644256860018
2023-01-24 06:09:31.162732: step: 116/531, loss: 0.003980125300586224
2023-01-24 06:09:32.211388: step: 120/531, loss: 0.0037292789202183485
2023-01-24 06:09:33.270818: step: 124/531, loss: 0.04006205126643181
2023-01-24 06:09:34.318456: step: 128/531, loss: 0.010462186299264431
2023-01-24 06:09:35.368041: step: 132/531, loss: 0.0034327919129282236
2023-01-24 06:09:36.448266: step: 136/531, loss: 0.005827185697853565
2023-01-24 06:09:37.491291: step: 140/531, loss: 0.0007558600045740604
2023-01-24 06:09:38.525003: step: 144/531, loss: 0.00017142956494353712
2023-01-24 06:09:39.585066: step: 148/531, loss: 0.013463253155350685
2023-01-24 06:09:40.646861: step: 152/531, loss: 0.007346061989665031
2023-01-24 06:09:41.694599: step: 156/531, loss: 0.013847418129444122
2023-01-24 06:09:42.767906: step: 160/531, loss: 0.061364609748125076
2023-01-24 06:09:43.817703: step: 164/531, loss: 0.003914410714060068
2023-01-24 06:09:44.881647: step: 168/531, loss: 0.006762303877621889
2023-01-24 06:09:45.948493: step: 172/531, loss: 0.012773388996720314
2023-01-24 06:09:47.011226: step: 176/531, loss: 0.007753476966172457
2023-01-24 06:09:48.060836: step: 180/531, loss: 0.014776489697396755
2023-01-24 06:09:49.132610: step: 184/531, loss: 0.02107352949678898
2023-01-24 06:09:50.196353: step: 188/531, loss: 0.02246982231736183
2023-01-24 06:09:51.240450: step: 192/531, loss: 0.001362648094072938
2023-01-24 06:09:52.307626: step: 196/531, loss: 0.027102597057819366
2023-01-24 06:09:53.370716: step: 200/531, loss: 0.011291301809251308
2023-01-24 06:09:54.423677: step: 204/531, loss: 0.004192367196083069
2023-01-24 06:09:55.497723: step: 208/531, loss: 0.005737635772675276
2023-01-24 06:09:56.557666: step: 212/531, loss: 0.005328624043613672
2023-01-24 06:09:57.611045: step: 216/531, loss: 0.004522640723735094
2023-01-24 06:09:58.656495: step: 220/531, loss: 0.007462525740265846
2023-01-24 06:09:59.712387: step: 224/531, loss: 0.018044428899884224
2023-01-24 06:10:00.785874: step: 228/531, loss: 0.00784721877425909
2023-01-24 06:10:01.845472: step: 232/531, loss: 0.0
2023-01-24 06:10:02.908321: step: 236/531, loss: 0.013877315446734428
2023-01-24 06:10:03.960989: step: 240/531, loss: 0.00955837219953537
2023-01-24 06:10:05.033851: step: 244/531, loss: 0.004485964775085449
2023-01-24 06:10:06.085752: step: 248/531, loss: 0.006767854560166597
2023-01-24 06:10:07.147382: step: 252/531, loss: 0.003219024511054158
2023-01-24 06:10:08.195169: step: 256/531, loss: 0.003234386444091797
2023-01-24 06:10:09.271835: step: 260/531, loss: 0.011280063539743423
2023-01-24 06:10:10.317706: step: 264/531, loss: 0.0037553971633315086
2023-01-24 06:10:11.381766: step: 268/531, loss: 0.003862376557663083
2023-01-24 06:10:12.437167: step: 272/531, loss: 0.0017365460516884923
2023-01-24 06:10:13.513352: step: 276/531, loss: 0.007787508424371481
2023-01-24 06:10:14.575974: step: 280/531, loss: 0.005531442351639271
2023-01-24 06:10:15.639244: step: 284/531, loss: 0.0012803171994164586
2023-01-24 06:10:16.692100: step: 288/531, loss: 0.006415815558284521
2023-01-24 06:10:17.762235: step: 292/531, loss: 0.0071218619123101234
2023-01-24 06:10:18.855117: step: 296/531, loss: 0.00494378712028265
2023-01-24 06:10:19.910580: step: 300/531, loss: 0.005453706718981266
2023-01-24 06:10:20.966615: step: 304/531, loss: 0.0021511497907340527
2023-01-24 06:10:22.034371: step: 308/531, loss: 0.0004934875178150833
2023-01-24 06:10:23.105188: step: 312/531, loss: 0.00821372028440237
2023-01-24 06:10:24.153127: step: 316/531, loss: 0.0048161339946091175
2023-01-24 06:10:25.201752: step: 320/531, loss: 0.00028853537514805794
2023-01-24 06:10:26.260721: step: 324/531, loss: 0.0336274728178978
2023-01-24 06:10:27.322079: step: 328/531, loss: 0.0052524167113006115
2023-01-24 06:10:28.378758: step: 332/531, loss: 0.0100155770778656
2023-01-24 06:10:29.435891: step: 336/531, loss: 0.0189670417457819
2023-01-24 06:10:30.497161: step: 340/531, loss: 0.009143245406448841
2023-01-24 06:10:31.552592: step: 344/531, loss: 0.00248920195735991
2023-01-24 06:10:32.640064: step: 348/531, loss: 0.011447952128946781
2023-01-24 06:10:33.704748: step: 352/531, loss: 0.06651657074689865
2023-01-24 06:10:34.757767: step: 356/531, loss: 0.000792564416769892
2023-01-24 06:10:35.829845: step: 360/531, loss: 0.024494869634509087
2023-01-24 06:10:36.900300: step: 364/531, loss: 0.020984619855880737
2023-01-24 06:10:37.958457: step: 368/531, loss: 0.0056723980233073235
2023-01-24 06:10:39.031645: step: 372/531, loss: 0.03303275629878044
2023-01-24 06:10:40.084542: step: 376/531, loss: 0.005866799037903547
2023-01-24 06:10:41.136267: step: 380/531, loss: 0.00024266091350000352
2023-01-24 06:10:42.199336: step: 384/531, loss: 0.022709475830197334
2023-01-24 06:10:43.276880: step: 388/531, loss: 0.006276153493672609
2023-01-24 06:10:44.342726: step: 392/531, loss: 0.007548362948000431
2023-01-24 06:10:45.387576: step: 396/531, loss: 0.0013162402901798487
2023-01-24 06:10:46.450954: step: 400/531, loss: 0.0038812006823718548
2023-01-24 06:10:47.526250: step: 404/531, loss: 0.0014815202448517084
2023-01-24 06:10:48.581995: step: 408/531, loss: 0.008196880109608173
2023-01-24 06:10:49.651092: step: 412/531, loss: 0.008656901307404041
2023-01-24 06:10:50.711700: step: 416/531, loss: 0.003748697927221656
2023-01-24 06:10:51.771217: step: 420/531, loss: 0.04771991819143295
2023-01-24 06:10:52.842908: step: 424/531, loss: 0.004933672491461039
2023-01-24 06:10:53.912483: step: 428/531, loss: 0.008803177624940872
2023-01-24 06:10:54.989790: step: 432/531, loss: 0.020003728568553925
2023-01-24 06:10:56.081353: step: 436/531, loss: 0.026127735152840614
2023-01-24 06:10:57.146511: step: 440/531, loss: 0.00811250600963831
2023-01-24 06:10:58.234541: step: 444/531, loss: 0.005144232884049416
2023-01-24 06:10:59.314210: step: 448/531, loss: 0.006486075464636087
2023-01-24 06:11:00.380753: step: 452/531, loss: 0.008398662321269512
2023-01-24 06:11:01.456818: step: 456/531, loss: 0.02692290022969246
2023-01-24 06:11:02.530165: step: 460/531, loss: 0.007317574229091406
2023-01-24 06:11:03.611477: step: 464/531, loss: 0.007980293594300747
2023-01-24 06:11:04.704040: step: 468/531, loss: 0.008779807016253471
2023-01-24 06:11:05.779882: step: 472/531, loss: 0.010540878400206566
2023-01-24 06:11:06.860571: step: 476/531, loss: 0.006640647072345018
2023-01-24 06:11:07.929703: step: 480/531, loss: 0.00310403760522604
2023-01-24 06:11:09.011328: step: 484/531, loss: 0.004137186799198389
2023-01-24 06:11:10.082746: step: 488/531, loss: 0.011220235377550125
2023-01-24 06:11:11.145955: step: 492/531, loss: 0.01986110955476761
2023-01-24 06:11:12.199419: step: 496/531, loss: 0.010194278322160244
2023-01-24 06:11:13.273362: step: 500/531, loss: 0.005563562270253897
2023-01-24 06:11:14.340174: step: 504/531, loss: 0.008323823101818562
2023-01-24 06:11:15.399786: step: 508/531, loss: 0.005014132708311081
2023-01-24 06:11:16.461923: step: 512/531, loss: 0.024302873760461807
2023-01-24 06:11:17.537688: step: 516/531, loss: 0.024076519533991814
2023-01-24 06:11:18.594272: step: 520/531, loss: 0.004532541148364544
2023-01-24 06:11:19.670387: step: 524/531, loss: 0.0010067735565826297
2023-01-24 06:11:20.731379: step: 528/531, loss: 0.004437810275703669
2023-01-24 06:11:21.803872: step: 532/531, loss: 0.04998788982629776
2023-01-24 06:11:22.851950: step: 536/531, loss: 0.029736055061221123
2023-01-24 06:11:23.922751: step: 540/531, loss: 0.012387125752866268
2023-01-24 06:11:24.979593: step: 544/531, loss: 0.0019971667788922787
2023-01-24 06:11:26.047168: step: 548/531, loss: 0.013324547559022903
2023-01-24 06:11:27.105623: step: 552/531, loss: 0.025667695328593254
2023-01-24 06:11:28.163826: step: 556/531, loss: 0.004306916147470474
2023-01-24 06:11:29.225686: step: 560/531, loss: 0.010714216157793999
2023-01-24 06:11:30.296993: step: 564/531, loss: 0.021912487223744392
2023-01-24 06:11:31.356156: step: 568/531, loss: 0.05018653720617294
2023-01-24 06:11:32.422820: step: 572/531, loss: 0.024516025558114052
2023-01-24 06:11:33.486602: step: 576/531, loss: 0.009168602526187897
2023-01-24 06:11:34.542951: step: 580/531, loss: 0.007532237563282251
2023-01-24 06:11:35.600502: step: 584/531, loss: 0.0003346972807776183
2023-01-24 06:11:36.668028: step: 588/531, loss: 0.0348026379942894
2023-01-24 06:11:37.740299: step: 592/531, loss: 0.03567736968398094
2023-01-24 06:11:38.796912: step: 596/531, loss: 0.002214094391092658
2023-01-24 06:11:39.864949: step: 600/531, loss: 0.007236414588987827
2023-01-24 06:11:40.936999: step: 604/531, loss: 0.02221815660595894
2023-01-24 06:11:42.000609: step: 608/531, loss: 0.003051872132346034
2023-01-24 06:11:43.058201: step: 612/531, loss: 0.02217867225408554
2023-01-24 06:11:44.118587: step: 616/531, loss: 0.0036869077011942863
2023-01-24 06:11:45.187203: step: 620/531, loss: 0.013273851945996284
2023-01-24 06:11:46.267744: step: 624/531, loss: 0.009029224514961243
2023-01-24 06:11:47.315301: step: 628/531, loss: 0.0034077484160661697
2023-01-24 06:11:48.402612: step: 632/531, loss: 0.021823812276124954
2023-01-24 06:11:49.475914: step: 636/531, loss: 0.006052076350897551
2023-01-24 06:11:50.553632: step: 640/531, loss: 0.004911745898425579
2023-01-24 06:11:51.620744: step: 644/531, loss: 0.05342480167746544
2023-01-24 06:11:52.717325: step: 648/531, loss: 0.005484255030751228
2023-01-24 06:11:53.782417: step: 652/531, loss: 0.012694372795522213
2023-01-24 06:11:54.848002: step: 656/531, loss: 0.006429442670196295
2023-01-24 06:11:55.928570: step: 660/531, loss: 0.0031178209464997053
2023-01-24 06:11:57.005931: step: 664/531, loss: 0.0016089307609945536
2023-01-24 06:11:58.064369: step: 668/531, loss: 0.011093459092080593
2023-01-24 06:11:59.125062: step: 672/531, loss: 0.0052119772881269455
2023-01-24 06:12:00.199736: step: 676/531, loss: 0.027570489794015884
2023-01-24 06:12:01.268141: step: 680/531, loss: 0.001186838955618441
2023-01-24 06:12:02.335701: step: 684/531, loss: 0.006844093091785908
2023-01-24 06:12:03.382775: step: 688/531, loss: 0.004935556091368198
2023-01-24 06:12:04.437360: step: 692/531, loss: 0.007439350243657827
2023-01-24 06:12:05.501707: step: 696/531, loss: 0.0049890936352312565
2023-01-24 06:12:06.562436: step: 700/531, loss: 0.0013611697359010577
2023-01-24 06:12:07.637940: step: 704/531, loss: 0.004644644912332296
2023-01-24 06:12:08.688666: step: 708/531, loss: 0.003395052859559655
2023-01-24 06:12:09.743528: step: 712/531, loss: 0.009862705133855343
2023-01-24 06:12:10.809741: step: 716/531, loss: 0.009629306383430958
2023-01-24 06:12:11.893062: step: 720/531, loss: 0.006141656078398228
2023-01-24 06:12:12.943919: step: 724/531, loss: 0.00485787820070982
2023-01-24 06:12:14.001464: step: 728/531, loss: 0.020004672929644585
2023-01-24 06:12:15.065513: step: 732/531, loss: 0.011888944543898106
2023-01-24 06:12:16.124327: step: 736/531, loss: 0.0018903245218098164
2023-01-24 06:12:17.184053: step: 740/531, loss: 0.002657040487974882
2023-01-24 06:12:18.251199: step: 744/531, loss: 0.0006607944378629327
2023-01-24 06:12:19.325968: step: 748/531, loss: 0.0035916180349886417
2023-01-24 06:12:20.381929: step: 752/531, loss: 0.007719813380390406
2023-01-24 06:12:21.441857: step: 756/531, loss: 0.007262494880706072
2023-01-24 06:12:22.518663: step: 760/531, loss: 0.019486352801322937
2023-01-24 06:12:23.559203: step: 764/531, loss: 0.01112589705735445
2023-01-24 06:12:24.619190: step: 768/531, loss: 0.014657550491392612
2023-01-24 06:12:25.677646: step: 772/531, loss: 0.02967098169028759
2023-01-24 06:12:26.761626: step: 776/531, loss: 0.008942109532654285
2023-01-24 06:12:27.838282: step: 780/531, loss: 0.015748485922813416
2023-01-24 06:12:28.904943: step: 784/531, loss: 0.0030344678089022636
2023-01-24 06:12:29.952163: step: 788/531, loss: 0.008891900070011616
2023-01-24 06:12:31.019243: step: 792/531, loss: 0.040598366409540176
2023-01-24 06:12:32.073833: step: 796/531, loss: 0.0029410021379590034
2023-01-24 06:12:33.135029: step: 800/531, loss: 0.017152665182948112
2023-01-24 06:12:34.196025: step: 804/531, loss: 0.0126335509121418
2023-01-24 06:12:35.250108: step: 808/531, loss: 0.010139510966837406
2023-01-24 06:12:36.301718: step: 812/531, loss: 0.0028377585113048553
2023-01-24 06:12:37.368154: step: 816/531, loss: 0.003249727189540863
2023-01-24 06:12:38.434176: step: 820/531, loss: 0.017950786277651787
2023-01-24 06:12:39.491290: step: 824/531, loss: 0.005333798937499523
2023-01-24 06:12:40.559641: step: 828/531, loss: 0.0035397931933403015
2023-01-24 06:12:41.621416: step: 832/531, loss: 0.0462794229388237
2023-01-24 06:12:42.683680: step: 836/531, loss: 0.007998448796570301
2023-01-24 06:12:43.768617: step: 840/531, loss: 0.02705160714685917
2023-01-24 06:12:44.841044: step: 844/531, loss: 0.005735460203140974
2023-01-24 06:12:45.911198: step: 848/531, loss: 0.0031818770803511143
2023-01-24 06:12:46.955984: step: 852/531, loss: 0.005705671384930611
2023-01-24 06:12:48.013972: step: 856/531, loss: 0.008555103093385696
2023-01-24 06:12:49.071133: step: 860/531, loss: 0.0024066423065960407
2023-01-24 06:12:50.117866: step: 864/531, loss: 0.004721895791590214
2023-01-24 06:12:51.199086: step: 868/531, loss: 0.005090405698865652
2023-01-24 06:12:52.247294: step: 872/531, loss: 0.0061364793218672276
2023-01-24 06:12:53.316077: step: 876/531, loss: 0.04104631394147873
2023-01-24 06:12:54.379388: step: 880/531, loss: 0.007381265051662922
2023-01-24 06:12:55.427943: step: 884/531, loss: 0.0043432763777673244
2023-01-24 06:12:56.498032: step: 888/531, loss: 0.005296186078339815
2023-01-24 06:12:57.573496: step: 892/531, loss: 0.002196338027715683
2023-01-24 06:12:58.642208: step: 896/531, loss: 0.006520502734929323
2023-01-24 06:12:59.686422: step: 900/531, loss: 0.011645560152828693
2023-01-24 06:13:00.762223: step: 904/531, loss: 0.009051233530044556
2023-01-24 06:13:01.831901: step: 908/531, loss: 0.016671858727931976
2023-01-24 06:13:02.895013: step: 912/531, loss: 0.005036613438278437
2023-01-24 06:13:03.966276: step: 916/531, loss: 0.014427910558879375
2023-01-24 06:13:05.034130: step: 920/531, loss: 0.00046623675734736025
2023-01-24 06:13:06.104380: step: 924/531, loss: 0.013886132277548313
2023-01-24 06:13:07.165120: step: 928/531, loss: 0.01004299707710743
2023-01-24 06:13:08.218375: step: 932/531, loss: 0.009398017078638077
2023-01-24 06:13:09.277502: step: 936/531, loss: 0.0025876956060528755
2023-01-24 06:13:10.355184: step: 940/531, loss: 0.041548389941453934
2023-01-24 06:13:11.419284: step: 944/531, loss: 0.004219766240566969
2023-01-24 06:13:12.497745: step: 948/531, loss: 0.0017521681729704142
2023-01-24 06:13:13.562962: step: 952/531, loss: 0.014079599641263485
2023-01-24 06:13:14.617294: step: 956/531, loss: 0.011452076025307178
2023-01-24 06:13:15.680475: step: 960/531, loss: 0.0038475249893963337
2023-01-24 06:13:16.734746: step: 964/531, loss: 0.0054289293475449085
2023-01-24 06:13:17.807381: step: 968/531, loss: 0.004413502290844917
2023-01-24 06:13:18.889438: step: 972/531, loss: 0.0005040338728576899
2023-01-24 06:13:19.959723: step: 976/531, loss: 0.005536057520657778
2023-01-24 06:13:21.030313: step: 980/531, loss: 0.0059566805139184
2023-01-24 06:13:22.088430: step: 984/531, loss: 0.004091221839189529
2023-01-24 06:13:23.149289: step: 988/531, loss: 0.004754670429974794
2023-01-24 06:13:24.200786: step: 992/531, loss: 0.021801957860589027
2023-01-24 06:13:25.260719: step: 996/531, loss: 0.04336067661643028
2023-01-24 06:13:26.358434: step: 1000/531, loss: 0.020230498164892197
2023-01-24 06:13:27.415393: step: 1004/531, loss: 0.005798004567623138
2023-01-24 06:13:28.469257: step: 1008/531, loss: 0.005172763951122761
2023-01-24 06:13:29.547558: step: 1012/531, loss: 0.00398161681368947
2023-01-24 06:13:30.604896: step: 1016/531, loss: 0.020105313509702682
2023-01-24 06:13:31.672441: step: 1020/531, loss: 0.0057420809753239155
2023-01-24 06:13:32.736494: step: 1024/531, loss: 0.006394962780177593
2023-01-24 06:13:33.823037: step: 1028/531, loss: 0.001249514752998948
2023-01-24 06:13:34.886016: step: 1032/531, loss: 0.008573153987526894
2023-01-24 06:13:35.934224: step: 1036/531, loss: 0.0055114817805588245
2023-01-24 06:13:36.997640: step: 1040/531, loss: 0.02221653051674366
2023-01-24 06:13:38.055519: step: 1044/531, loss: 0.0014722991036251187
2023-01-24 06:13:39.106083: step: 1048/531, loss: 0.0003363671712577343
2023-01-24 06:13:40.156532: step: 1052/531, loss: 0.004248330835253
2023-01-24 06:13:41.227321: step: 1056/531, loss: 0.009905761107802391
2023-01-24 06:13:42.295094: step: 1060/531, loss: 0.0020095587242394686
2023-01-24 06:13:43.351661: step: 1064/531, loss: 0.0077373310923576355
2023-01-24 06:13:44.423583: step: 1068/531, loss: 0.025465836748480797
2023-01-24 06:13:45.488518: step: 1072/531, loss: 0.01543425302952528
2023-01-24 06:13:46.534772: step: 1076/531, loss: 0.009915855713188648
2023-01-24 06:13:47.585636: step: 1080/531, loss: 0.013025938533246517
2023-01-24 06:13:48.634637: step: 1084/531, loss: 0.0030364685226231813
2023-01-24 06:13:49.683605: step: 1088/531, loss: 0.030855901539325714
2023-01-24 06:13:50.746586: step: 1092/531, loss: 0.05402104929089546
2023-01-24 06:13:51.797602: step: 1096/531, loss: 0.006830158643424511
2023-01-24 06:13:52.859409: step: 1100/531, loss: 0.011064563877880573
2023-01-24 06:13:53.914584: step: 1104/531, loss: 0.021480709314346313
2023-01-24 06:13:54.968004: step: 1108/531, loss: 0.01907600276172161
2023-01-24 06:13:56.035751: step: 1112/531, loss: 0.004825084004551172
2023-01-24 06:13:57.095458: step: 1116/531, loss: 0.03258570656180382
2023-01-24 06:13:58.138489: step: 1120/531, loss: 0.022793063893914223
2023-01-24 06:13:59.196485: step: 1124/531, loss: 0.005661248695105314
2023-01-24 06:14:00.247690: step: 1128/531, loss: 0.0022720012348145247
2023-01-24 06:14:01.301986: step: 1132/531, loss: 0.004178924486041069
2023-01-24 06:14:02.374251: step: 1136/531, loss: 0.07149509340524673
2023-01-24 06:14:03.408743: step: 1140/531, loss: 0.017420422285795212
2023-01-24 06:14:04.471529: step: 1144/531, loss: 0.010559949092566967
2023-01-24 06:14:05.528480: step: 1148/531, loss: 0.011860010214149952
2023-01-24 06:14:06.603674: step: 1152/531, loss: 0.06689035147428513
2023-01-24 06:14:07.648144: step: 1156/531, loss: 0.046632975339889526
2023-01-24 06:14:08.709207: step: 1160/531, loss: 0.004091491922736168
2023-01-24 06:14:09.756502: step: 1164/531, loss: 0.0022138371132314205
2023-01-24 06:14:10.820833: step: 1168/531, loss: 0.01418247353285551
2023-01-24 06:14:11.893146: step: 1172/531, loss: 0.007050564978271723
2023-01-24 06:14:12.954093: step: 1176/531, loss: 0.07845360040664673
2023-01-24 06:14:14.016888: step: 1180/531, loss: 0.008402055129408836
2023-01-24 06:14:15.081614: step: 1184/531, loss: 0.005471793003380299
2023-01-24 06:14:16.126935: step: 1188/531, loss: 0.00032339635072275996
2023-01-24 06:14:17.194691: step: 1192/531, loss: 0.008736653253436089
2023-01-24 06:14:18.257617: step: 1196/531, loss: 0.0049553243443369865
2023-01-24 06:14:19.322040: step: 1200/531, loss: 0.007759691681712866
2023-01-24 06:14:20.384795: step: 1204/531, loss: 0.015211337246000767
2023-01-24 06:14:21.436051: step: 1208/531, loss: 0.01538966316729784
2023-01-24 06:14:22.494356: step: 1212/531, loss: 0.021568182855844498
2023-01-24 06:14:23.526620: step: 1216/531, loss: 0.0006008119089528918
2023-01-24 06:14:24.576348: step: 1220/531, loss: 0.012032121419906616
2023-01-24 06:14:25.646498: step: 1224/531, loss: 0.036595966666936874
2023-01-24 06:14:26.702096: step: 1228/531, loss: 0.007924004457890987
2023-01-24 06:14:27.786587: step: 1232/531, loss: 0.04528406634926796
2023-01-24 06:14:28.839254: step: 1236/531, loss: 0.013258915394544601
2023-01-24 06:14:29.895516: step: 1240/531, loss: 0.0007331136730499566
2023-01-24 06:14:30.963135: step: 1244/531, loss: 0.019347058609128
2023-01-24 06:14:32.020294: step: 1248/531, loss: 0.0061698839999735355
2023-01-24 06:14:33.079150: step: 1252/531, loss: 0.03367088362574577
2023-01-24 06:14:34.137604: step: 1256/531, loss: 0.0052800364792346954
2023-01-24 06:14:35.200003: step: 1260/531, loss: 0.0017504931893199682
2023-01-24 06:14:36.248868: step: 1264/531, loss: 0.02444339171051979
2023-01-24 06:14:37.331990: step: 1268/531, loss: 0.034685395658016205
2023-01-24 06:14:38.391487: step: 1272/531, loss: 0.005013342946767807
2023-01-24 06:14:39.441238: step: 1276/531, loss: 0.0036082046572118998
2023-01-24 06:14:40.493020: step: 1280/531, loss: 0.017291255295276642
2023-01-24 06:14:41.566255: step: 1284/531, loss: 0.004581100307404995
2023-01-24 06:14:42.611033: step: 1288/531, loss: 0.000507197342813015
2023-01-24 06:14:43.686573: step: 1292/531, loss: 0.012628301978111267
2023-01-24 06:14:44.754899: step: 1296/531, loss: 0.002073760610073805
2023-01-24 06:14:45.810557: step: 1300/531, loss: 0.0270913727581501
2023-01-24 06:14:46.894310: step: 1304/531, loss: 0.015117453411221504
2023-01-24 06:14:47.964787: step: 1308/531, loss: 0.022538896650075912
2023-01-24 06:14:49.051765: step: 1312/531, loss: 0.03624674305319786
2023-01-24 06:14:50.123116: step: 1316/531, loss: 0.004522361326962709
2023-01-24 06:14:51.185862: step: 1320/531, loss: 0.010240288451313972
2023-01-24 06:14:52.264408: step: 1324/531, loss: 0.009906929917633533
2023-01-24 06:14:53.327499: step: 1328/531, loss: 0.025363946333527565
2023-01-24 06:14:54.395486: step: 1332/531, loss: 0.0018918426940217614
2023-01-24 06:14:55.443709: step: 1336/531, loss: 0.0035500042140483856
2023-01-24 06:14:56.503749: step: 1340/531, loss: 0.019974039867520332
2023-01-24 06:14:57.556863: step: 1344/531, loss: 0.0022247035522013903
2023-01-24 06:14:58.630301: step: 1348/531, loss: 0.0040542082861065865
2023-01-24 06:14:59.677064: step: 1352/531, loss: 0.006103890016674995
2023-01-24 06:15:00.731940: step: 1356/531, loss: 0.013787849806249142
2023-01-24 06:15:01.781186: step: 1360/531, loss: 0.021495060995221138
2023-01-24 06:15:02.837373: step: 1364/531, loss: 0.009032532572746277
2023-01-24 06:15:03.904771: step: 1368/531, loss: 0.012110460549592972
2023-01-24 06:15:04.954952: step: 1372/531, loss: 0.005954327993094921
2023-01-24 06:15:06.004348: step: 1376/531, loss: 0.014109624549746513
2023-01-24 06:15:07.073893: step: 1380/531, loss: 0.04883275181055069
2023-01-24 06:15:08.132125: step: 1384/531, loss: 0.01282959058880806
2023-01-24 06:15:09.201912: step: 1388/531, loss: 0.012233157642185688
2023-01-24 06:15:10.291915: step: 1392/531, loss: 0.022701958194375038
2023-01-24 06:15:11.355162: step: 1396/531, loss: 0.006441434845328331
2023-01-24 06:15:12.447190: step: 1400/531, loss: 0.012959196232259274
2023-01-24 06:15:13.503771: step: 1404/531, loss: 0.007666775956749916
2023-01-24 06:15:14.552691: step: 1408/531, loss: 0.0009315578499808908
2023-01-24 06:15:15.620379: step: 1412/531, loss: 0.0037649234291166067
2023-01-24 06:15:16.676532: step: 1416/531, loss: 0.014111046679317951
2023-01-24 06:15:17.732609: step: 1420/531, loss: 0.0038568233139812946
2023-01-24 06:15:18.793300: step: 1424/531, loss: 0.009174461476504803
2023-01-24 06:15:19.859968: step: 1428/531, loss: 0.0057424819096922874
2023-01-24 06:15:20.913376: step: 1432/531, loss: 0.005351158324629068
2023-01-24 06:15:21.991837: step: 1436/531, loss: 0.02396395057439804
2023-01-24 06:15:23.057462: step: 1440/531, loss: 0.009414681233465672
2023-01-24 06:15:24.116034: step: 1444/531, loss: 0.01584302820265293
2023-01-24 06:15:25.178434: step: 1448/531, loss: 0.004913279786705971
2023-01-24 06:15:26.237942: step: 1452/531, loss: 0.007930240593850613
2023-01-24 06:15:27.298935: step: 1456/531, loss: 0.006487489677965641
2023-01-24 06:15:28.380035: step: 1460/531, loss: 0.012037992477416992
2023-01-24 06:15:29.438497: step: 1464/531, loss: 0.006566865835338831
2023-01-24 06:15:30.485151: step: 1468/531, loss: 0.005106267519295216
2023-01-24 06:15:31.533432: step: 1472/531, loss: 0.003189919050782919
2023-01-24 06:15:32.591059: step: 1476/531, loss: 0.013816825114190578
2023-01-24 06:15:33.644320: step: 1480/531, loss: 0.015051505528390408
2023-01-24 06:15:34.703091: step: 1484/531, loss: 0.016562610864639282
2023-01-24 06:15:35.758083: step: 1488/531, loss: 0.03791069984436035
2023-01-24 06:15:36.816076: step: 1492/531, loss: 0.004593304358422756
2023-01-24 06:15:37.886555: step: 1496/531, loss: 0.0009665197576396167
2023-01-24 06:15:38.955521: step: 1500/531, loss: 0.043097857385873795
2023-01-24 06:15:40.014750: step: 1504/531, loss: 0.013915913179516792
2023-01-24 06:15:41.072240: step: 1508/531, loss: 0.039936330169439316
2023-01-24 06:15:42.136482: step: 1512/531, loss: 0.005395339801907539
2023-01-24 06:15:43.218539: step: 1516/531, loss: 0.04015607386827469
2023-01-24 06:15:44.275046: step: 1520/531, loss: 0.00961624551564455
2023-01-24 06:15:45.354462: step: 1524/531, loss: 0.005523694679141045
2023-01-24 06:15:46.404814: step: 1528/531, loss: 0.016392536461353302
2023-01-24 06:15:47.474410: step: 1532/531, loss: 0.017963485792279243
2023-01-24 06:15:48.533440: step: 1536/531, loss: 0.004716671071946621
2023-01-24 06:15:49.600411: step: 1540/531, loss: 0.009314429946243763
2023-01-24 06:15:50.664088: step: 1544/531, loss: 0.014859539456665516
2023-01-24 06:15:51.731846: step: 1548/531, loss: 0.00373009592294693
2023-01-24 06:15:52.801919: step: 1552/531, loss: 0.01349884457886219
2023-01-24 06:15:53.872170: step: 1556/531, loss: 0.0012248989660292864
2023-01-24 06:15:54.952603: step: 1560/531, loss: 0.0167396143078804
2023-01-24 06:15:56.032235: step: 1564/531, loss: 0.005124368704855442
2023-01-24 06:15:57.098494: step: 1568/531, loss: 0.00532143609598279
2023-01-24 06:15:58.159443: step: 1572/531, loss: 0.002435114234685898
2023-01-24 06:15:59.220607: step: 1576/531, loss: 0.007091684732586145
2023-01-24 06:16:00.268731: step: 1580/531, loss: 0.04177471250295639
2023-01-24 06:16:01.332456: step: 1584/531, loss: 0.009794454090297222
2023-01-24 06:16:02.401211: step: 1588/531, loss: 0.01756526343524456
2023-01-24 06:16:03.455144: step: 1592/531, loss: 0.008132767863571644
2023-01-24 06:16:04.518858: step: 1596/531, loss: 0.0005605625919997692
2023-01-24 06:16:05.579320: step: 1600/531, loss: 0.014891646802425385
2023-01-24 06:16:06.643110: step: 1604/531, loss: 0.017712175846099854
2023-01-24 06:16:07.704273: step: 1608/531, loss: 0.00015844375593587756
2023-01-24 06:16:08.752558: step: 1612/531, loss: 0.008950797840952873
2023-01-24 06:16:09.823793: step: 1616/531, loss: 0.0005535169038921595
2023-01-24 06:16:10.876084: step: 1620/531, loss: 0.00734550878405571
2023-01-24 06:16:11.940972: step: 1624/531, loss: 0.013187505304813385
2023-01-24 06:16:13.003774: step: 1628/531, loss: 0.01382160373032093
2023-01-24 06:16:14.068435: step: 1632/531, loss: 0.0131465969607234
2023-01-24 06:16:15.137127: step: 1636/531, loss: 0.10788968950510025
2023-01-24 06:16:16.195286: step: 1640/531, loss: 0.009063305333256721
2023-01-24 06:16:17.269115: step: 1644/531, loss: 0.008790520951151848
2023-01-24 06:16:18.334867: step: 1648/531, loss: 0.021610645577311516
2023-01-24 06:16:19.398253: step: 1652/531, loss: 0.008326945826411247
2023-01-24 06:16:20.453016: step: 1656/531, loss: 0.03982025384902954
2023-01-24 06:16:21.524158: step: 1660/531, loss: 0.004880597349256277
2023-01-24 06:16:22.570675: step: 1664/531, loss: 0.004995083436369896
2023-01-24 06:16:23.632771: step: 1668/531, loss: 0.00897503923624754
2023-01-24 06:16:24.685105: step: 1672/531, loss: 0.0036237251479178667
2023-01-24 06:16:25.754000: step: 1676/531, loss: 0.005051128100603819
2023-01-24 06:16:26.828896: step: 1680/531, loss: 0.15174442529678345
2023-01-24 06:16:27.903292: step: 1684/531, loss: 0.0
2023-01-24 06:16:28.977382: step: 1688/531, loss: 0.033902134746313095
2023-01-24 06:16:30.042236: step: 1692/531, loss: 0.07192021608352661
2023-01-24 06:16:31.105032: step: 1696/531, loss: 0.007757317740470171
2023-01-24 06:16:32.173018: step: 1700/531, loss: 0.029810024425387383
2023-01-24 06:16:33.242162: step: 1704/531, loss: 0.0022699744440615177
2023-01-24 06:16:34.301342: step: 1708/531, loss: 0.004880097229033709
2023-01-24 06:16:35.364643: step: 1712/531, loss: 0.0071748364716768265
2023-01-24 06:16:36.428400: step: 1716/531, loss: 0.009971429593861103
2023-01-24 06:16:37.483579: step: 1720/531, loss: 0.004291251301765442
2023-01-24 06:16:38.535639: step: 1724/531, loss: 0.013477936387062073
2023-01-24 06:16:39.598717: step: 1728/531, loss: 0.009166092611849308
2023-01-24 06:16:40.657188: step: 1732/531, loss: 0.02056244947016239
2023-01-24 06:16:41.706637: step: 1736/531, loss: 0.029907966032624245
2023-01-24 06:16:42.764661: step: 1740/531, loss: 0.0038931923918426037
2023-01-24 06:16:43.822020: step: 1744/531, loss: 0.00536212557926774
2023-01-24 06:16:44.869611: step: 1748/531, loss: 0.004581668879836798
2023-01-24 06:16:45.948531: step: 1752/531, loss: 0.005966234020888805
2023-01-24 06:16:47.003350: step: 1756/531, loss: 0.010447864420711994
2023-01-24 06:16:48.070573: step: 1760/531, loss: 0.003937452100217342
2023-01-24 06:16:49.130860: step: 1764/531, loss: 0.005030252505093813
2023-01-24 06:16:50.182661: step: 1768/531, loss: 0.014101854525506496
2023-01-24 06:16:51.243522: step: 1772/531, loss: 0.0017251266399398446
2023-01-24 06:16:52.296462: step: 1776/531, loss: 0.004788325168192387
2023-01-24 06:16:53.357232: step: 1780/531, loss: 0.012858579866588116
2023-01-24 06:16:54.412676: step: 1784/531, loss: 0.009258554317057133
2023-01-24 06:16:55.456881: step: 1788/531, loss: 0.005546551663428545
2023-01-24 06:16:56.511166: step: 1792/531, loss: 0.004637312144041061
2023-01-24 06:16:57.572477: step: 1796/531, loss: 0.011219508945941925
2023-01-24 06:16:58.651234: step: 1800/531, loss: 0.003312710439786315
2023-01-24 06:16:59.708678: step: 1804/531, loss: 0.025780469179153442
2023-01-24 06:17:00.768450: step: 1808/531, loss: 0.010041517205536366
2023-01-24 06:17:01.828968: step: 1812/531, loss: 0.01294084545224905
2023-01-24 06:17:02.893500: step: 1816/531, loss: 0.0037586225662380457
2023-01-24 06:17:03.965224: step: 1820/531, loss: 0.003309978637844324
2023-01-24 06:17:05.027004: step: 1824/531, loss: 0.01272408664226532
2023-01-24 06:17:06.103387: step: 1828/531, loss: 0.01631883718073368
2023-01-24 06:17:07.175654: step: 1832/531, loss: 0.003025906393304467
2023-01-24 06:17:08.246990: step: 1836/531, loss: 0.026338353753089905
2023-01-24 06:17:09.326331: step: 1840/531, loss: 0.008698285557329655
2023-01-24 06:17:10.397371: step: 1844/531, loss: 0.013285747729241848
2023-01-24 06:17:11.469265: step: 1848/531, loss: 0.007151308935135603
2023-01-24 06:17:12.544572: step: 1852/531, loss: 0.003446970833465457
2023-01-24 06:17:13.596300: step: 1856/531, loss: 0.016193140298128128
2023-01-24 06:17:14.667153: step: 1860/531, loss: 0.03714349865913391
2023-01-24 06:17:15.728007: step: 1864/531, loss: 0.008802087977528572
2023-01-24 06:17:16.811359: step: 1868/531, loss: 0.00472974730655551
2023-01-24 06:17:17.884236: step: 1872/531, loss: 0.004969058092683554
2023-01-24 06:17:18.955616: step: 1876/531, loss: 0.01655971072614193
2023-01-24 06:17:20.011149: step: 1880/531, loss: 0.005845074076205492
2023-01-24 06:17:21.080413: step: 1884/531, loss: 0.0037426832132041454
2023-01-24 06:17:22.143576: step: 1888/531, loss: 0.021836236119270325
2023-01-24 06:17:23.205001: step: 1892/531, loss: 0.028230121359229088
2023-01-24 06:17:24.249195: step: 1896/531, loss: 0.0045180413872003555
2023-01-24 06:17:25.315867: step: 1900/531, loss: 0.029489697888493538
2023-01-24 06:17:26.382571: step: 1904/531, loss: 0.01240628957748413
2023-01-24 06:17:27.448796: step: 1908/531, loss: 0.004909764509648085
2023-01-24 06:17:28.516369: step: 1912/531, loss: 0.002719014184549451
2023-01-24 06:17:29.598077: step: 1916/531, loss: 0.005891120061278343
2023-01-24 06:17:30.655469: step: 1920/531, loss: 0.0052268970757722855
2023-01-24 06:17:31.740009: step: 1924/531, loss: 0.004456925205886364
2023-01-24 06:17:32.820809: step: 1928/531, loss: 0.045633673667907715
2023-01-24 06:17:33.883326: step: 1932/531, loss: 0.0038677516859024763
2023-01-24 06:17:34.950510: step: 1936/531, loss: 0.017424726858735085
2023-01-24 06:17:36.012996: step: 1940/531, loss: 0.002469978528097272
2023-01-24 06:17:37.075375: step: 1944/531, loss: 0.006199637893587351
2023-01-24 06:17:38.131649: step: 1948/531, loss: 0.013204146176576614
2023-01-24 06:17:39.210270: step: 1952/531, loss: 0.0021460703574121
2023-01-24 06:17:40.270404: step: 1956/531, loss: 0.008032361045479774
2023-01-24 06:17:41.326167: step: 1960/531, loss: 0.003598395036533475
2023-01-24 06:17:42.423761: step: 1964/531, loss: 0.008926734328269958
2023-01-24 06:17:43.476572: step: 1968/531, loss: 0.005528079811483622
2023-01-24 06:17:44.541120: step: 1972/531, loss: 0.003637881251052022
2023-01-24 06:17:45.608187: step: 1976/531, loss: 0.008379240520298481
2023-01-24 06:17:46.675007: step: 1980/531, loss: 0.009176112711429596
2023-01-24 06:17:47.730560: step: 1984/531, loss: 0.0045841108076274395
2023-01-24 06:17:48.792138: step: 1988/531, loss: 0.0014704858185723424
2023-01-24 06:17:49.859685: step: 1992/531, loss: 0.03910716995596886
2023-01-24 06:17:50.930696: step: 1996/531, loss: 0.0025522089563310146
2023-01-24 06:17:52.004598: step: 2000/531, loss: 0.0012237310875207186
2023-01-24 06:17:53.071077: step: 2004/531, loss: 0.006343057844787836
2023-01-24 06:17:54.143352: step: 2008/531, loss: 0.04061000794172287
2023-01-24 06:17:55.192743: step: 2012/531, loss: 0.0002299383922945708
2023-01-24 06:17:56.269516: step: 2016/531, loss: 0.009326566942036152
2023-01-24 06:17:57.338185: step: 2020/531, loss: 0.0038306904025375843
2023-01-24 06:17:58.403697: step: 2024/531, loss: 0.002030216855928302
2023-01-24 06:17:59.464837: step: 2028/531, loss: 0.00933896191418171
2023-01-24 06:18:00.537212: step: 2032/531, loss: 0.003491660114377737
2023-01-24 06:18:01.600677: step: 2036/531, loss: 0.0031041449401527643
2023-01-24 06:18:02.666553: step: 2040/531, loss: 0.006671515293419361
2023-01-24 06:18:03.728435: step: 2044/531, loss: 0.00508086895570159
2023-01-24 06:18:04.785091: step: 2048/531, loss: 0.015601389110088348
2023-01-24 06:18:05.849994: step: 2052/531, loss: 0.008544765412807465
2023-01-24 06:18:06.922041: step: 2056/531, loss: 0.02071394957602024
2023-01-24 06:18:07.986587: step: 2060/531, loss: 0.003219618694856763
2023-01-24 06:18:09.043687: step: 2064/531, loss: 0.007551091257482767
2023-01-24 06:18:10.107933: step: 2068/531, loss: 0.00708481902256608
2023-01-24 06:18:11.163204: step: 2072/531, loss: 0.009560951963067055
2023-01-24 06:18:12.229067: step: 2076/531, loss: 0.010458333417773247
2023-01-24 06:18:13.293178: step: 2080/531, loss: 0.037046853452920914
2023-01-24 06:18:14.364704: step: 2084/531, loss: 0.07459976524114609
2023-01-24 06:18:15.439312: step: 2088/531, loss: 0.007718859240412712
2023-01-24 06:18:16.493354: step: 2092/531, loss: 0.008536077104508877
2023-01-24 06:18:17.561460: step: 2096/531, loss: 0.013174931518733501
2023-01-24 06:18:18.642430: step: 2100/531, loss: 0.04114936292171478
2023-01-24 06:18:19.704861: step: 2104/531, loss: 0.003819637931883335
2023-01-24 06:18:20.783786: step: 2108/531, loss: 0.019232796505093575
2023-01-24 06:18:21.849142: step: 2112/531, loss: 0.004383544437587261
2023-01-24 06:18:22.906861: step: 2116/531, loss: 0.02925959974527359
2023-01-24 06:18:23.983245: step: 2120/531, loss: 0.006749176885932684
2023-01-24 06:18:25.045353: step: 2124/531, loss: 0.0028425422497093678
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3933515724803238, 'r': 0.3246829867721838, 'f1': 0.3557337505799186}, 'combined': 0.26211960569046633, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38738335236054167, 'r': 0.27665249329986386, 'f1': 0.3227854971799569}, 'combined': 0.20211802159866463, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36058352733302074, 'r': 0.3284252241363377, 'f1': 0.343753908877557}, 'combined': 0.25329235390977883, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.40572927784466245, 'r': 0.28536414492230544, 'f1': 0.33506494094106587}, 'combined': 0.22227080240644964, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
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, 'stategy': 1, 'epoch': 4}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3933515724803238, 'r': 0.3246829867721838, 'f1': 0.3557337505799186}, 'combined': 0.26211960569046633, 'stategy': 1, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38738335236054167, 'r': 0.27665249329986386, 'f1': 0.3227854971799569}, 'combined': 0.20211802159866463, 'stategy': 1, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35989667312598334, 'r': 0.329848374041461, 'f1': 0.3442180061779207}, 'combined': 0.25363432034162575, 'stategy': 1, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4048585708891052, 'r': 0.2872011161722353, 'f1': 0.3360283386682542}, 'combined': 0.2229098880274558, 'stategy': 1, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 2}
******************************
Epoch: 5
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:21:03.075747: step: 4/531, loss: 0.005807214882224798
2023-01-24 06:21:04.134949: step: 8/531, loss: 0.0022022947669029236
2023-01-24 06:21:05.190115: step: 12/531, loss: 0.02152836136519909
2023-01-24 06:21:06.238165: step: 16/531, loss: 0.006170021835714579
2023-01-24 06:21:07.285678: step: 20/531, loss: 0.01623407192528248
2023-01-24 06:21:08.346944: step: 24/531, loss: 0.003679434070363641
2023-01-24 06:21:09.404082: step: 28/531, loss: 0.0026208723429590464
2023-01-24 06:21:10.447124: step: 32/531, loss: 0.0031494239810854197
2023-01-24 06:21:11.485819: step: 36/531, loss: 0.0015068423235788941
2023-01-24 06:21:12.572927: step: 40/531, loss: 0.0038974073249846697
2023-01-24 06:21:13.607842: step: 44/531, loss: 0.003259575692936778
2023-01-24 06:21:14.648044: step: 48/531, loss: 0.002108826534822583
2023-01-24 06:21:15.703704: step: 52/531, loss: 0.0013047748943790793
2023-01-24 06:21:16.753691: step: 56/531, loss: 0.0007550541777163744
2023-01-24 06:21:17.805412: step: 60/531, loss: 0.002022378146648407
2023-01-24 06:21:18.873143: step: 64/531, loss: 0.005456749815493822
2023-01-24 06:21:19.946259: step: 68/531, loss: 0.007847040891647339
2023-01-24 06:21:21.021030: step: 72/531, loss: 0.004182835575193167
2023-01-24 06:21:22.068409: step: 76/531, loss: 0.0049982499331235886
2023-01-24 06:21:23.143255: step: 80/531, loss: 0.044010329991579056
2023-01-24 06:21:24.197811: step: 84/531, loss: 0.004086959175765514
2023-01-24 06:21:25.258099: step: 88/531, loss: 0.002345503307878971
2023-01-24 06:21:26.326405: step: 92/531, loss: 0.0042015486396849155
2023-01-24 06:21:27.383360: step: 96/531, loss: 0.00812936294823885
2023-01-24 06:21:28.446271: step: 100/531, loss: 0.0044873724691569805
2023-01-24 06:21:29.502774: step: 104/531, loss: 0.015516269020736217
2023-01-24 06:21:30.555625: step: 108/531, loss: 0.004173475783318281
2023-01-24 06:21:31.612546: step: 112/531, loss: 0.016641296446323395
2023-01-24 06:21:32.663244: step: 116/531, loss: 0.0057066092267632484
2023-01-24 06:21:33.726320: step: 120/531, loss: 0.007502554450184107
2023-01-24 06:21:34.808064: step: 124/531, loss: 0.0028000548481941223
2023-01-24 06:21:35.861182: step: 128/531, loss: 0.005122318398207426
2023-01-24 06:21:36.910404: step: 132/531, loss: 0.007589933928102255
2023-01-24 06:21:37.966437: step: 136/531, loss: 0.0038941216189414263
2023-01-24 06:21:39.042602: step: 140/531, loss: 0.02303730510175228
2023-01-24 06:21:40.084650: step: 144/531, loss: 0.02759641967713833
2023-01-24 06:21:41.157488: step: 148/531, loss: 0.004355369135737419
2023-01-24 06:21:42.215500: step: 152/531, loss: 0.0025970609858632088
2023-01-24 06:21:43.282703: step: 156/531, loss: 0.014739280566573143
2023-01-24 06:21:44.336372: step: 160/531, loss: 0.0026813806034624577
2023-01-24 06:21:45.401596: step: 164/531, loss: 0.004748336039483547
2023-01-24 06:21:46.460426: step: 168/531, loss: 0.005711060017347336
2023-01-24 06:21:47.532552: step: 172/531, loss: 0.018474796786904335
2023-01-24 06:21:48.587103: step: 176/531, loss: 0.002739003859460354
2023-01-24 06:21:49.670286: step: 180/531, loss: 0.011312433518469334
2023-01-24 06:21:50.739138: step: 184/531, loss: 0.023797253146767616
2023-01-24 06:21:51.795153: step: 188/531, loss: 0.011803213506937027
2023-01-24 06:21:52.850811: step: 192/531, loss: 0.012820323929190636
2023-01-24 06:21:53.907182: step: 196/531, loss: 3.698200453072786e-05
2023-01-24 06:21:54.969370: step: 200/531, loss: 0.003794708289206028
2023-01-24 06:21:56.047060: step: 204/531, loss: 0.03602186590433121
2023-01-24 06:21:57.125370: step: 208/531, loss: 0.0006447615451179445
2023-01-24 06:21:58.186505: step: 212/531, loss: 0.002043553162366152
2023-01-24 06:21:59.248562: step: 216/531, loss: 0.0020245842169970274
2023-01-24 06:22:00.329950: step: 220/531, loss: 0.013785269111394882
2023-01-24 06:22:01.405309: step: 224/531, loss: 0.04330361634492874
2023-01-24 06:22:02.469988: step: 228/531, loss: 0.009757502004504204
2023-01-24 06:22:03.546316: step: 232/531, loss: 0.01938987523317337
2023-01-24 06:22:04.610461: step: 236/531, loss: 0.0051905191503465176
2023-01-24 06:22:05.665940: step: 240/531, loss: 0.017227424308657646
2023-01-24 06:22:06.733332: step: 244/531, loss: 0.004427309613674879
2023-01-24 06:22:07.794534: step: 248/531, loss: 0.007141686510294676
2023-01-24 06:22:08.852918: step: 252/531, loss: 0.0038854489102959633
2023-01-24 06:22:09.916526: step: 256/531, loss: 0.0016804260667413473
2023-01-24 06:22:10.984420: step: 260/531, loss: 0.008154327981173992
2023-01-24 06:22:12.033882: step: 264/531, loss: 0.0
2023-01-24 06:22:13.101608: step: 268/531, loss: 0.0018283461686223745
2023-01-24 06:22:14.158900: step: 272/531, loss: 0.010594193823635578
2023-01-24 06:22:15.227118: step: 276/531, loss: 0.00935339368879795
2023-01-24 06:22:16.276538: step: 280/531, loss: 0.009318103082478046
2023-01-24 06:22:17.345982: step: 284/531, loss: 0.009640650823712349
2023-01-24 06:22:18.408764: step: 288/531, loss: 0.004278747830539942
2023-01-24 06:22:19.486100: step: 292/531, loss: 0.007965181954205036
2023-01-24 06:22:20.547683: step: 296/531, loss: 0.02535293437540531
2023-01-24 06:22:21.609942: step: 300/531, loss: 0.013964627869427204
2023-01-24 06:22:22.674833: step: 304/531, loss: 0.005327991209924221
2023-01-24 06:22:23.735342: step: 308/531, loss: 0.00338742695748806
2023-01-24 06:22:24.788550: step: 312/531, loss: 0.011840930208563805
2023-01-24 06:22:25.857520: step: 316/531, loss: 0.0028024010825902224
2023-01-24 06:22:26.917029: step: 320/531, loss: 0.004474756307899952
2023-01-24 06:22:27.982565: step: 324/531, loss: 0.00753122428432107
2023-01-24 06:22:29.065575: step: 328/531, loss: 0.0027843203861266375
2023-01-24 06:22:30.120197: step: 332/531, loss: 0.006605905015021563
2023-01-24 06:22:31.186090: step: 336/531, loss: 0.00018224156519863755
2023-01-24 06:22:32.253436: step: 340/531, loss: 0.0032902921084314585
2023-01-24 06:22:33.329033: step: 344/531, loss: 0.0013544083340093493
2023-01-24 06:22:34.389004: step: 348/531, loss: 6.108375964686275e-05
2023-01-24 06:22:35.452561: step: 352/531, loss: 0.0034663656260818243
2023-01-24 06:22:36.507215: step: 356/531, loss: 0.0003987389791291207
2023-01-24 06:22:37.558831: step: 360/531, loss: 0.06145963445305824
2023-01-24 06:22:38.631095: step: 364/531, loss: 0.000662085774820298
2023-01-24 06:22:39.694222: step: 368/531, loss: 0.04449881613254547
2023-01-24 06:22:40.767815: step: 372/531, loss: 0.0163415614515543
2023-01-24 06:22:41.833529: step: 376/531, loss: 0.0033831375185400248
2023-01-24 06:22:42.911680: step: 380/531, loss: 0.0019204376731067896
2023-01-24 06:22:43.973525: step: 384/531, loss: 0.028147753328084946
2023-01-24 06:22:45.037433: step: 388/531, loss: 0.016038352623581886
2023-01-24 06:22:46.088555: step: 392/531, loss: 0.005063127260655165
2023-01-24 06:22:47.145421: step: 396/531, loss: 0.004314687568694353
2023-01-24 06:22:48.215144: step: 400/531, loss: 0.007408762816339731
2023-01-24 06:22:49.293289: step: 404/531, loss: 0.013506321236491203
2023-01-24 06:22:50.348780: step: 408/531, loss: 0.0043339235708117485
2023-01-24 06:22:51.411203: step: 412/531, loss: 0.00619980925694108
2023-01-24 06:22:52.481326: step: 416/531, loss: 0.014608023688197136
2023-01-24 06:22:53.548004: step: 420/531, loss: 0.002072980161756277
2023-01-24 06:22:54.621786: step: 424/531, loss: 0.010320314206182957
2023-01-24 06:22:55.709432: step: 428/531, loss: 0.011293102987110615
2023-01-24 06:22:56.790305: step: 432/531, loss: 0.007146671414375305
2023-01-24 06:22:57.858462: step: 436/531, loss: 0.004076071549206972
2023-01-24 06:22:58.916577: step: 440/531, loss: 0.01607760228216648
2023-01-24 06:22:59.968190: step: 444/531, loss: 0.0052183824591338634
2023-01-24 06:23:01.020793: step: 448/531, loss: 0.015845775604248047
2023-01-24 06:23:02.079465: step: 452/531, loss: 0.004702863749116659
2023-01-24 06:23:03.141992: step: 456/531, loss: 0.009268103167414665
2023-01-24 06:23:04.197603: step: 460/531, loss: 0.0185063686221838
2023-01-24 06:23:05.273433: step: 464/531, loss: 0.0049374946393072605
2023-01-24 06:23:06.340182: step: 468/531, loss: 0.008612715639173985
2023-01-24 06:23:07.393971: step: 472/531, loss: 0.002266595372930169
2023-01-24 06:23:08.451645: step: 476/531, loss: 0.006317255087196827
2023-01-24 06:23:09.507961: step: 480/531, loss: 0.029082240536808968
2023-01-24 06:23:10.561070: step: 484/531, loss: 0.013400383293628693
2023-01-24 06:23:11.652428: step: 488/531, loss: 0.003226094413548708
2023-01-24 06:23:12.708317: step: 492/531, loss: 0.001526180887594819
2023-01-24 06:23:13.797149: step: 496/531, loss: 0.003652245504781604
2023-01-24 06:23:14.867330: step: 500/531, loss: 0.010590340942144394
2023-01-24 06:23:15.935804: step: 504/531, loss: 0.014829112216830254
2023-01-24 06:23:17.012369: step: 508/531, loss: 0.0018887472106143832
2023-01-24 06:23:18.072206: step: 512/531, loss: 0.0031903600320219994
2023-01-24 06:23:19.131055: step: 516/531, loss: 0.0077584185637533665
2023-01-24 06:23:20.195634: step: 520/531, loss: 0.010188636370003223
2023-01-24 06:23:21.278353: step: 524/531, loss: 0.019377458840608597
2023-01-24 06:23:22.333382: step: 528/531, loss: 0.0036466431338340044
2023-01-24 06:23:23.392554: step: 532/531, loss: 0.004038535058498383
2023-01-24 06:23:24.451386: step: 536/531, loss: 0.010000564157962799
2023-01-24 06:23:25.523252: step: 540/531, loss: 0.01448139175772667
2023-01-24 06:23:26.603450: step: 544/531, loss: 0.004286718089133501
2023-01-24 06:23:27.666283: step: 548/531, loss: 0.013287190347909927
2023-01-24 06:23:28.739564: step: 552/531, loss: 0.0548272468149662
2023-01-24 06:23:29.807199: step: 556/531, loss: 0.03567224740982056
2023-01-24 06:23:30.882397: step: 560/531, loss: 0.007338162511587143
2023-01-24 06:23:31.964124: step: 564/531, loss: 0.0010257135145366192
2023-01-24 06:23:33.032131: step: 568/531, loss: 0.0068540871143341064
2023-01-24 06:23:34.091324: step: 572/531, loss: 0.004826688207685947
2023-01-24 06:23:35.145901: step: 576/531, loss: 0.0063118766993284225
2023-01-24 06:23:36.233697: step: 580/531, loss: 0.04523809626698494
2023-01-24 06:23:37.302462: step: 584/531, loss: 0.008123817853629589
2023-01-24 06:23:38.371668: step: 588/531, loss: 0.004273754078894854
2023-01-24 06:23:39.463927: step: 592/531, loss: 0.040251363068819046
2023-01-24 06:23:40.524573: step: 596/531, loss: 0.009955678135156631
2023-01-24 06:23:41.585274: step: 600/531, loss: 0.004804521799087524
2023-01-24 06:23:42.670619: step: 604/531, loss: 0.028351513668894768
2023-01-24 06:23:43.718515: step: 608/531, loss: 0.15413495898246765
2023-01-24 06:23:44.791709: step: 612/531, loss: 0.006048975978046656
2023-01-24 06:23:45.844490: step: 616/531, loss: 0.021297432482242584
2023-01-24 06:23:46.888406: step: 620/531, loss: 0.011791897006332874
2023-01-24 06:23:47.953022: step: 624/531, loss: 0.016374753788113594
2023-01-24 06:23:49.011000: step: 628/531, loss: 0.0036152920220047235
2023-01-24 06:23:50.065410: step: 632/531, loss: 0.002369828289374709
2023-01-24 06:23:51.116761: step: 636/531, loss: 0.0028354148380458355
2023-01-24 06:23:52.163534: step: 640/531, loss: 0.0034248242154717445
2023-01-24 06:23:53.225543: step: 644/531, loss: 0.014805841259658337
2023-01-24 06:23:54.273308: step: 648/531, loss: 0.00849098339676857
2023-01-24 06:23:55.333506: step: 652/531, loss: 0.008847140707075596
2023-01-24 06:23:56.410471: step: 656/531, loss: 0.008732152171432972
2023-01-24 06:23:57.466965: step: 660/531, loss: 0.008818008005619049
2023-01-24 06:23:58.527676: step: 664/531, loss: 0.00877432618290186
2023-01-24 06:23:59.577313: step: 668/531, loss: 0.013980763033032417
2023-01-24 06:24:00.637694: step: 672/531, loss: 0.011354943737387657
2023-01-24 06:24:01.695464: step: 676/531, loss: 0.0053780353628098965
2023-01-24 06:24:02.760221: step: 680/531, loss: 0.0056334990076720715
2023-01-24 06:24:03.821752: step: 684/531, loss: 0.0019074814626947045
2023-01-24 06:24:04.879312: step: 688/531, loss: 0.0024077247362583876
2023-01-24 06:24:05.937310: step: 692/531, loss: 0.0013195687206462026
2023-01-24 06:24:06.996590: step: 696/531, loss: 0.025060025975108147
2023-01-24 06:24:08.043078: step: 700/531, loss: 0.009929392486810684
2023-01-24 06:24:09.117265: step: 704/531, loss: 0.00851244106888771
2023-01-24 06:24:10.178748: step: 708/531, loss: 0.01609143242239952
2023-01-24 06:24:11.245585: step: 712/531, loss: 0.02244430035352707
2023-01-24 06:24:12.310051: step: 716/531, loss: 0.007732793223112822
2023-01-24 06:24:13.371973: step: 720/531, loss: 0.00012667883129324764
2023-01-24 06:24:14.435862: step: 724/531, loss: 0.028393354266881943
2023-01-24 06:24:15.520075: step: 728/531, loss: 0.003548459615558386
2023-01-24 06:24:16.571150: step: 732/531, loss: 0.01752273552119732
2023-01-24 06:24:17.633983: step: 736/531, loss: 0.003290896536782384
2023-01-24 06:24:18.694072: step: 740/531, loss: 0.024473173543810844
2023-01-24 06:24:19.745087: step: 744/531, loss: 0.0007964319665916264
2023-01-24 06:24:20.816789: step: 748/531, loss: 0.004943354520946741
2023-01-24 06:24:21.874066: step: 752/531, loss: 0.027291763573884964
2023-01-24 06:24:22.949862: step: 756/531, loss: 0.03941899538040161
2023-01-24 06:24:24.006809: step: 760/531, loss: 0.00375573942437768
2023-01-24 06:24:25.073631: step: 764/531, loss: 0.008461283519864082
2023-01-24 06:24:26.140877: step: 768/531, loss: 0.0088475551456213
2023-01-24 06:24:27.198338: step: 772/531, loss: 0.0025104815140366554
2023-01-24 06:24:28.266309: step: 776/531, loss: 0.004422907251864672
2023-01-24 06:24:29.330803: step: 780/531, loss: 0.009042094461619854
2023-01-24 06:24:30.393537: step: 784/531, loss: 0.00742373988032341
2023-01-24 06:24:31.457246: step: 788/531, loss: 0.003960083704441786
2023-01-24 06:24:32.504129: step: 792/531, loss: 0.005032602231949568
2023-01-24 06:24:33.569462: step: 796/531, loss: 0.005871370434761047
2023-01-24 06:24:34.629518: step: 800/531, loss: 0.006120866630226374
2023-01-24 06:24:35.692015: step: 804/531, loss: 0.022875437512993813
2023-01-24 06:24:36.734607: step: 808/531, loss: 0.00894143432378769
2023-01-24 06:24:37.801907: step: 812/531, loss: 0.02909945510327816
2023-01-24 06:24:38.855637: step: 816/531, loss: 0.007247535511851311
2023-01-24 06:24:39.915565: step: 820/531, loss: 0.07022277265787125
2023-01-24 06:24:40.990095: step: 824/531, loss: 0.011695099994540215
2023-01-24 06:24:42.054349: step: 828/531, loss: 0.006673064548522234
2023-01-24 06:24:43.122508: step: 832/531, loss: 0.0058763278648257256
2023-01-24 06:24:44.168645: step: 836/531, loss: 0.004524358082562685
2023-01-24 06:24:45.215837: step: 840/531, loss: 0.01430712454020977
2023-01-24 06:24:46.270029: step: 844/531, loss: 0.004708596970885992
2023-01-24 06:24:47.331552: step: 848/531, loss: 0.001690601697191596
2023-01-24 06:24:48.385400: step: 852/531, loss: 0.015059088356792927
2023-01-24 06:24:49.453637: step: 856/531, loss: 0.006663259584456682
2023-01-24 06:24:50.509826: step: 860/531, loss: 0.003261934733018279
2023-01-24 06:24:51.558081: step: 864/531, loss: 0.009079797193408012
2023-01-24 06:24:52.626590: step: 868/531, loss: 0.008918702602386475
2023-01-24 06:24:53.677744: step: 872/531, loss: 0.0006527914083562791
2023-01-24 06:24:54.709844: step: 876/531, loss: 0.0022630339954048395
2023-01-24 06:24:55.785027: step: 880/531, loss: 0.03832429647445679
2023-01-24 06:24:56.864213: step: 884/531, loss: 0.012818587943911552
2023-01-24 06:24:57.915799: step: 888/531, loss: 0.011210795491933823
2023-01-24 06:24:58.975133: step: 892/531, loss: 0.0023321902845054865
2023-01-24 06:25:00.031275: step: 896/531, loss: 0.0075229620561003685
2023-01-24 06:25:01.092930: step: 900/531, loss: 0.016809718683362007
2023-01-24 06:25:02.157343: step: 904/531, loss: 0.008349324576556683
2023-01-24 06:25:03.222957: step: 908/531, loss: 0.008199167437851429
2023-01-24 06:25:04.282345: step: 912/531, loss: 0.003793461015447974
2023-01-24 06:25:05.343045: step: 916/531, loss: 0.04661436751484871
2023-01-24 06:25:06.392928: step: 920/531, loss: 0.006356748752295971
2023-01-24 06:25:07.485598: step: 924/531, loss: 0.007706102915108204
2023-01-24 06:25:08.546553: step: 928/531, loss: 0.008557467721402645
2023-01-24 06:25:09.615845: step: 932/531, loss: 0.009810470044612885
2023-01-24 06:25:10.684373: step: 936/531, loss: 0.005701807793229818
2023-01-24 06:25:11.739858: step: 940/531, loss: 0.0023188721388578415
2023-01-24 06:25:12.831851: step: 944/531, loss: 0.016089465469121933
2023-01-24 06:25:13.876331: step: 948/531, loss: 0.008515138179063797
2023-01-24 06:25:14.939648: step: 952/531, loss: 0.01171775534749031
2023-01-24 06:25:15.997916: step: 956/531, loss: 0.020042473450303078
2023-01-24 06:25:17.044164: step: 960/531, loss: 0.009194825775921345
2023-01-24 06:25:18.085522: step: 964/531, loss: 0.02214464731514454
2023-01-24 06:25:19.138004: step: 968/531, loss: 0.0253550224006176
2023-01-24 06:25:20.198636: step: 972/531, loss: 0.027331119403243065
2023-01-24 06:25:21.250785: step: 976/531, loss: 0.0048026093281805515
2023-01-24 06:25:22.307818: step: 980/531, loss: 0.012424202635884285
2023-01-24 06:25:23.377857: step: 984/531, loss: 0.006939048878848553
2023-01-24 06:25:24.438964: step: 988/531, loss: 0.0032061359379440546
2023-01-24 06:25:25.487994: step: 992/531, loss: 0.006910219322890043
2023-01-24 06:25:26.546773: step: 996/531, loss: 0.0018666409887373447
2023-01-24 06:25:27.614236: step: 1000/531, loss: 0.0029800981283187866
2023-01-24 06:25:28.680876: step: 1004/531, loss: 0.0013396149734035134
2023-01-24 06:25:29.737079: step: 1008/531, loss: 0.003700954606756568
2023-01-24 06:25:30.800780: step: 1012/531, loss: 0.0013811460230499506
2023-01-24 06:25:31.859231: step: 1016/531, loss: 0.0015336914220824838
2023-01-24 06:25:32.926192: step: 1020/531, loss: 0.0021230322308838367
2023-01-24 06:25:34.014114: step: 1024/531, loss: 0.012486407533288002
2023-01-24 06:25:35.077284: step: 1028/531, loss: 0.015820514410734177
2023-01-24 06:25:36.134181: step: 1032/531, loss: 0.017405198886990547
2023-01-24 06:25:37.193179: step: 1036/531, loss: 0.0032268869690597057
2023-01-24 06:25:38.259430: step: 1040/531, loss: 0.00020192879310343415
2023-01-24 06:25:39.343333: step: 1044/531, loss: 0.003607572056353092
2023-01-24 06:25:40.411912: step: 1048/531, loss: 0.0029978856910020113
2023-01-24 06:25:41.473554: step: 1052/531, loss: 0.0069878557696938515
2023-01-24 06:25:42.536346: step: 1056/531, loss: 0.004222525283694267
2023-01-24 06:25:43.604191: step: 1060/531, loss: 0.006350035313516855
2023-01-24 06:25:44.662676: step: 1064/531, loss: 0.036838605999946594
2023-01-24 06:25:45.705672: step: 1068/531, loss: 0.0007744743488729
2023-01-24 06:25:46.762913: step: 1072/531, loss: 0.004105206113308668
2023-01-24 06:25:47.816984: step: 1076/531, loss: 0.0029686882626265287
2023-01-24 06:25:48.886472: step: 1080/531, loss: 0.005077075678855181
2023-01-24 06:25:49.943966: step: 1084/531, loss: 0.011331991292536259
2023-01-24 06:25:51.001673: step: 1088/531, loss: 0.003255445510149002
2023-01-24 06:25:52.062240: step: 1092/531, loss: 0.002899549901485443
2023-01-24 06:25:53.120631: step: 1096/531, loss: 0.0
2023-01-24 06:25:54.194125: step: 1100/531, loss: 0.036151282489299774
2023-01-24 06:25:55.252315: step: 1104/531, loss: 0.018611082807183266
2023-01-24 06:25:56.308790: step: 1108/531, loss: 0.0024892115034163
2023-01-24 06:25:57.373081: step: 1112/531, loss: 0.00424707867205143
2023-01-24 06:25:58.424232: step: 1116/531, loss: 0.0056391311809420586
2023-01-24 06:25:59.482979: step: 1120/531, loss: 0.005849056877195835
2023-01-24 06:26:00.562231: step: 1124/531, loss: 0.012019841000437737
2023-01-24 06:26:01.626882: step: 1128/531, loss: 0.004478851333260536
2023-01-24 06:26:02.683391: step: 1132/531, loss: 0.011968092992901802
2023-01-24 06:26:03.736187: step: 1136/531, loss: 0.007573192939162254
2023-01-24 06:26:04.792334: step: 1140/531, loss: 0.007035081274807453
2023-01-24 06:26:05.861882: step: 1144/531, loss: 0.0040196990594267845
2023-01-24 06:26:06.919801: step: 1148/531, loss: 0.004365410190075636
2023-01-24 06:26:07.986202: step: 1152/531, loss: 0.007847755216062069
2023-01-24 06:26:09.031551: step: 1156/531, loss: 0.009195538237690926
2023-01-24 06:26:10.094251: step: 1160/531, loss: 0.008788717910647392
2023-01-24 06:26:11.160285: step: 1164/531, loss: 0.03694355860352516
2023-01-24 06:26:12.204836: step: 1168/531, loss: 0.0006039888830855489
2023-01-24 06:26:13.274825: step: 1172/531, loss: 0.0034986878745257854
2023-01-24 06:26:14.325476: step: 1176/531, loss: 0.009941834956407547
2023-01-24 06:26:15.365665: step: 1180/531, loss: 0.006046846974641085
2023-01-24 06:26:16.446742: step: 1184/531, loss: 0.00839924719184637
2023-01-24 06:26:17.503522: step: 1188/531, loss: 0.0026115509681403637
2023-01-24 06:26:18.569934: step: 1192/531, loss: 0.030738770961761475
2023-01-24 06:26:19.626774: step: 1196/531, loss: 0.004127085208892822
2023-01-24 06:26:20.687256: step: 1200/531, loss: 0.0032245481852442026
2023-01-24 06:26:21.743963: step: 1204/531, loss: 0.0173778235912323
2023-01-24 06:26:22.812926: step: 1208/531, loss: 0.0036086291074752808
2023-01-24 06:26:23.886160: step: 1212/531, loss: 0.011766073293983936
2023-01-24 06:26:24.967185: step: 1216/531, loss: 0.0042497157119214535
2023-01-24 06:26:26.029468: step: 1220/531, loss: 0.007871869951486588
2023-01-24 06:26:27.084502: step: 1224/531, loss: 0.005298707168549299
2023-01-24 06:26:28.140961: step: 1228/531, loss: 0.0012293810723349452
2023-01-24 06:26:29.198554: step: 1232/531, loss: 0.014326884411275387
2023-01-24 06:26:30.245487: step: 1236/531, loss: 0.0021404060535132885
2023-01-24 06:26:31.307415: step: 1240/531, loss: 0.0051089320331811905
2023-01-24 06:26:32.369311: step: 1244/531, loss: 0.003313001012429595
2023-01-24 06:26:33.457814: step: 1248/531, loss: 0.005388742778450251
2023-01-24 06:26:34.525667: step: 1252/531, loss: 0.020495640113949776
2023-01-24 06:26:35.590500: step: 1256/531, loss: 0.005792425014078617
2023-01-24 06:26:36.660202: step: 1260/531, loss: 0.004559899214655161
2023-01-24 06:26:37.728008: step: 1264/531, loss: 0.007380574010312557
2023-01-24 06:26:38.789998: step: 1268/531, loss: 0.00351132033392787
2023-01-24 06:26:39.859221: step: 1272/531, loss: 0.009252430871129036
2023-01-24 06:26:40.928893: step: 1276/531, loss: 0.0005795079632662237
2023-01-24 06:26:41.988594: step: 1280/531, loss: 0.0027042715810239315
2023-01-24 06:26:43.054229: step: 1284/531, loss: 0.005632023327052593
2023-01-24 06:26:44.112632: step: 1288/531, loss: 0.008819757960736752
2023-01-24 06:26:45.176056: step: 1292/531, loss: 0.0069810510613024235
2023-01-24 06:26:46.250164: step: 1296/531, loss: 0.011823880486190319
2023-01-24 06:26:47.309062: step: 1300/531, loss: 0.003263703780248761
2023-01-24 06:26:48.368804: step: 1304/531, loss: 0.002039700048044324
2023-01-24 06:26:49.435692: step: 1308/531, loss: 0.004265934694558382
2023-01-24 06:26:50.493571: step: 1312/531, loss: 0.015694238245487213
2023-01-24 06:26:51.547898: step: 1316/531, loss: 0.00418870011344552
2023-01-24 06:26:52.607555: step: 1320/531, loss: 0.00011992788495263085
2023-01-24 06:26:53.706449: step: 1324/531, loss: 0.007078006863594055
2023-01-24 06:26:54.770694: step: 1328/531, loss: 0.05498579889535904
2023-01-24 06:26:55.823877: step: 1332/531, loss: 0.015058860182762146
2023-01-24 06:26:56.884514: step: 1336/531, loss: 0.029800251126289368
2023-01-24 06:26:57.949281: step: 1340/531, loss: 0.010312286205589771
2023-01-24 06:26:59.014731: step: 1344/531, loss: 0.004535887856036425
2023-01-24 06:27:00.078580: step: 1348/531, loss: 0.025628194212913513
2023-01-24 06:27:01.148325: step: 1352/531, loss: 0.01830103062093258
2023-01-24 06:27:02.212526: step: 1356/531, loss: 0.02631601318717003
2023-01-24 06:27:03.292983: step: 1360/531, loss: 0.004949101246893406
2023-01-24 06:27:04.362246: step: 1364/531, loss: 0.02413923293352127
2023-01-24 06:27:05.426907: step: 1368/531, loss: 0.0020132192876189947
2023-01-24 06:27:06.501552: step: 1372/531, loss: 0.004399430006742477
2023-01-24 06:27:07.561916: step: 1376/531, loss: 0.004157388582825661
2023-01-24 06:27:08.634620: step: 1380/531, loss: 0.013954339548945427
2023-01-24 06:27:09.698211: step: 1384/531, loss: 0.020859219133853912
2023-01-24 06:27:10.759644: step: 1388/531, loss: 0.007197873666882515
2023-01-24 06:27:11.817074: step: 1392/531, loss: 0.00767285143956542
2023-01-24 06:27:12.886606: step: 1396/531, loss: 0.000982769881375134
2023-01-24 06:27:13.948644: step: 1400/531, loss: 0.015042808838188648
2023-01-24 06:27:15.010451: step: 1404/531, loss: 0.006504209712147713
2023-01-24 06:27:16.057138: step: 1408/531, loss: 0.0017136555397883058
2023-01-24 06:27:17.123833: step: 1412/531, loss: 0.010274010710418224
2023-01-24 06:27:18.182996: step: 1416/531, loss: 0.003196256933733821
2023-01-24 06:27:19.259340: step: 1420/531, loss: 0.017529016360640526
2023-01-24 06:27:20.309710: step: 1424/531, loss: 0.004103458486497402
2023-01-24 06:27:21.377282: step: 1428/531, loss: 0.006388582289218903
2023-01-24 06:27:22.438475: step: 1432/531, loss: 0.014448893256485462
2023-01-24 06:27:23.496797: step: 1436/531, loss: 0.009344315156340599
2023-01-24 06:27:24.570071: step: 1440/531, loss: 0.014278499409556389
2023-01-24 06:27:25.628805: step: 1444/531, loss: 0.0011535405647009611
2023-01-24 06:27:26.693645: step: 1448/531, loss: 0.0016149998409673572
2023-01-24 06:27:27.762939: step: 1452/531, loss: 0.011326124891638756
2023-01-24 06:27:28.829280: step: 1456/531, loss: 0.0021855556406080723
2023-01-24 06:27:29.892734: step: 1460/531, loss: 0.018211137503385544
2023-01-24 06:27:30.970964: step: 1464/531, loss: 0.005283666774630547
2023-01-24 06:27:32.034710: step: 1468/531, loss: 0.026966135948896408
2023-01-24 06:27:33.094006: step: 1472/531, loss: 0.003373767016455531
2023-01-24 06:27:34.157152: step: 1476/531, loss: 0.00674789072945714
2023-01-24 06:27:35.225558: step: 1480/531, loss: 0.040469296276569366
2023-01-24 06:27:36.293793: step: 1484/531, loss: 0.03187422454357147
2023-01-24 06:27:37.352844: step: 1488/531, loss: 0.00416473438963294
2023-01-24 06:27:38.420277: step: 1492/531, loss: 0.012027925811707973
2023-01-24 06:27:39.482496: step: 1496/531, loss: 0.030837608501315117
2023-01-24 06:27:40.534193: step: 1500/531, loss: 0.007405830081552267
2023-01-24 06:27:41.574458: step: 1504/531, loss: 0.004102893639355898
2023-01-24 06:27:42.683935: step: 1508/531, loss: 0.021001551300287247
2023-01-24 06:27:43.752117: step: 1512/531, loss: 0.015309328213334084
2023-01-24 06:27:44.827098: step: 1516/531, loss: 0.03283904865384102
2023-01-24 06:27:45.884757: step: 1520/531, loss: 0.019317546859383583
2023-01-24 06:27:46.933534: step: 1524/531, loss: 0.008958989754319191
2023-01-24 06:27:47.997698: step: 1528/531, loss: 0.0031436244025826454
2023-01-24 06:27:49.053309: step: 1532/531, loss: 0.0053840335458517075
2023-01-24 06:27:50.115206: step: 1536/531, loss: 0.010995203629136086
2023-01-24 06:27:51.190586: step: 1540/531, loss: 0.0065671843476593494
2023-01-24 06:27:52.255656: step: 1544/531, loss: 0.002719355747103691
2023-01-24 06:27:53.311261: step: 1548/531, loss: 0.01125891599804163
2023-01-24 06:27:54.366096: step: 1552/531, loss: 0.016793832182884216
2023-01-24 06:27:55.420445: step: 1556/531, loss: 0.004078240599483252
2023-01-24 06:27:56.500792: step: 1560/531, loss: 0.0009361952543258667
2023-01-24 06:27:57.563070: step: 1564/531, loss: 0.0048470571637153625
2023-01-24 06:27:58.620233: step: 1568/531, loss: 0.0046816421672701836
2023-01-24 06:27:59.709213: step: 1572/531, loss: 0.004210076294839382
2023-01-24 06:28:00.775197: step: 1576/531, loss: 0.002407207153737545
2023-01-24 06:28:01.848901: step: 1580/531, loss: 0.004963562358170748
2023-01-24 06:28:02.911757: step: 1584/531, loss: 0.015713829547166824
2023-01-24 06:28:03.984347: step: 1588/531, loss: 0.007654715795069933
2023-01-24 06:28:05.039512: step: 1592/531, loss: 0.005019447300583124
2023-01-24 06:28:06.089274: step: 1596/531, loss: 0.003619999159127474
2023-01-24 06:28:07.158916: step: 1600/531, loss: 0.0058888718485832214
2023-01-24 06:28:08.222475: step: 1604/531, loss: 0.006739064119756222
2023-01-24 06:28:09.282706: step: 1608/531, loss: 0.01315231528133154
2023-01-24 06:28:10.344382: step: 1612/531, loss: 0.004951538518071175
2023-01-24 06:28:11.403917: step: 1616/531, loss: 0.0008648558869026601
2023-01-24 06:28:12.461837: step: 1620/531, loss: 0.01770302839577198
2023-01-24 06:28:13.518752: step: 1624/531, loss: 0.0030953509267419577
2023-01-24 06:28:14.600796: step: 1628/531, loss: 0.01373161282390356
2023-01-24 06:28:15.667382: step: 1632/531, loss: 0.01755007915198803
2023-01-24 06:28:16.736929: step: 1636/531, loss: 0.010792574845254421
2023-01-24 06:28:17.796000: step: 1640/531, loss: 0.0038749745581299067
2023-01-24 06:28:18.859075: step: 1644/531, loss: 0.006427703890949488
2023-01-24 06:28:19.920053: step: 1648/531, loss: 0.005678446032106876
2023-01-24 06:28:21.005180: step: 1652/531, loss: 0.009267380461096764
2023-01-24 06:28:22.065223: step: 1656/531, loss: 0.006418990902602673
2023-01-24 06:28:23.127391: step: 1660/531, loss: 0.006146763917058706
2023-01-24 06:28:24.186003: step: 1664/531, loss: 0.00021611290867440403
2023-01-24 06:28:25.240231: step: 1668/531, loss: 0.013222035951912403
2023-01-24 06:28:26.308346: step: 1672/531, loss: 0.026508115231990814
2023-01-24 06:28:27.373272: step: 1676/531, loss: 0.001554515096358955
2023-01-24 06:28:28.449131: step: 1680/531, loss: 0.006360173225402832
2023-01-24 06:28:29.518447: step: 1684/531, loss: 0.0021642367355525494
2023-01-24 06:28:30.584058: step: 1688/531, loss: 0.0018947167554870248
2023-01-24 06:28:31.645770: step: 1692/531, loss: 0.002895057899877429
2023-01-24 06:28:32.702056: step: 1696/531, loss: 0.0023906559217721224
2023-01-24 06:28:33.768659: step: 1700/531, loss: 0.004442200995981693
2023-01-24 06:28:34.815142: step: 1704/531, loss: 0.0034768462646752596
2023-01-24 06:28:35.871643: step: 1708/531, loss: 0.0036459180992096663
2023-01-24 06:28:36.932514: step: 1712/531, loss: 0.003067202167585492
2023-01-24 06:28:37.990176: step: 1716/531, loss: 0.00449244724586606
2023-01-24 06:28:39.041888: step: 1720/531, loss: 0.019509945064783096
2023-01-24 06:28:40.094060: step: 1724/531, loss: 0.0059991031885147095
2023-01-24 06:28:41.149821: step: 1728/531, loss: 0.007486745715141296
2023-01-24 06:28:42.189473: step: 1732/531, loss: 0.005369197111576796
2023-01-24 06:28:43.264178: step: 1736/531, loss: 0.003810570575296879
2023-01-24 06:28:44.312257: step: 1740/531, loss: 0.004245352931320667
2023-01-24 06:28:45.375903: step: 1744/531, loss: 0.009846829809248447
2023-01-24 06:28:46.453831: step: 1748/531, loss: 0.0033084116876125336
2023-01-24 06:28:47.520267: step: 1752/531, loss: 0.0009926391066983342
2023-01-24 06:28:48.592303: step: 1756/531, loss: 0.0061272066086530685
2023-01-24 06:28:49.659428: step: 1760/531, loss: 0.0005276908632367849
2023-01-24 06:28:50.721685: step: 1764/531, loss: 0.004491967614740133
2023-01-24 06:28:51.766439: step: 1768/531, loss: 0.00498414458706975
2023-01-24 06:28:52.827880: step: 1772/531, loss: 0.005609001498669386
2023-01-24 06:28:53.883215: step: 1776/531, loss: 0.005922937300056219
2023-01-24 06:28:54.952193: step: 1780/531, loss: 0.010900807566940784
2023-01-24 06:28:56.002833: step: 1784/531, loss: 0.03198820725083351
2023-01-24 06:28:57.062869: step: 1788/531, loss: 0.014963364228606224
2023-01-24 06:28:58.122861: step: 1792/531, loss: 0.009051097556948662
2023-01-24 06:28:59.195382: step: 1796/531, loss: 0.09195971488952637
2023-01-24 06:29:00.260545: step: 1800/531, loss: 0.011376633308827877
2023-01-24 06:29:01.312044: step: 1804/531, loss: 0.029947912320494652
2023-01-24 06:29:02.370408: step: 1808/531, loss: 0.022808456793427467
2023-01-24 06:29:03.433900: step: 1812/531, loss: 0.0034042480401694775
2023-01-24 06:29:04.491894: step: 1816/531, loss: 0.003545522689819336
2023-01-24 06:29:05.539942: step: 1820/531, loss: 0.01330691296607256
2023-01-24 06:29:06.583768: step: 1824/531, loss: 0.004876063670963049
2023-01-24 06:29:07.632106: step: 1828/531, loss: 0.0007383336196653545
2023-01-24 06:29:08.686583: step: 1832/531, loss: 0.06327845901250839
2023-01-24 06:29:09.745062: step: 1836/531, loss: 0.10722129791975021
2023-01-24 06:29:10.805230: step: 1840/531, loss: 0.038653433322906494
2023-01-24 06:29:11.882693: step: 1844/531, loss: 0.007030686363577843
2023-01-24 06:29:12.937975: step: 1848/531, loss: 0.008413450792431831
2023-01-24 06:29:14.009475: step: 1852/531, loss: 0.019486885517835617
2023-01-24 06:29:15.053427: step: 1856/531, loss: 0.013278994709253311
2023-01-24 06:29:16.095876: step: 1860/531, loss: 0.01258185226470232
2023-01-24 06:29:17.152308: step: 1864/531, loss: 0.0066006239503622055
2023-01-24 06:29:18.214085: step: 1868/531, loss: 0.0067676883190870285
2023-01-24 06:29:19.262967: step: 1872/531, loss: 0.00558567326515913
2023-01-24 06:29:20.332928: step: 1876/531, loss: 0.032826460897922516
2023-01-24 06:29:21.402820: step: 1880/531, loss: 0.007169494871050119
2023-01-24 06:29:22.470210: step: 1884/531, loss: 0.005921301431953907
2023-01-24 06:29:23.541527: step: 1888/531, loss: 0.0006818806868977845
2023-01-24 06:29:24.613032: step: 1892/531, loss: 0.00084651232464239
2023-01-24 06:29:25.665225: step: 1896/531, loss: 0.03537513688206673
2023-01-24 06:29:26.722970: step: 1900/531, loss: 0.007354011293500662
2023-01-24 06:29:27.769051: step: 1904/531, loss: 0.013846050947904587
2023-01-24 06:29:28.840173: step: 1908/531, loss: 0.0018523391336202621
2023-01-24 06:29:29.904846: step: 1912/531, loss: 0.01390829123556614
2023-01-24 06:29:30.992424: step: 1916/531, loss: 0.01004581619054079
2023-01-24 06:29:32.056065: step: 1920/531, loss: 0.0026891790330410004
2023-01-24 06:29:33.128472: step: 1924/531, loss: 0.023877356201410294
2023-01-24 06:29:34.172053: step: 1928/531, loss: 0.017211874946951866
2023-01-24 06:29:35.229168: step: 1932/531, loss: 0.007620025891810656
2023-01-24 06:29:36.316110: step: 1936/531, loss: 0.005514797288924456
2023-01-24 06:29:37.375660: step: 1940/531, loss: 0.0031915786676108837
2023-01-24 06:29:38.435683: step: 1944/531, loss: 0.0018358406377956271
2023-01-24 06:29:39.490756: step: 1948/531, loss: 0.006972788833081722
2023-01-24 06:29:40.544464: step: 1952/531, loss: 0.00932492595165968
2023-01-24 06:29:41.605820: step: 1956/531, loss: 0.002349860966205597
2023-01-24 06:29:42.665011: step: 1960/531, loss: 0.02525022253394127
2023-01-24 06:29:43.726698: step: 1964/531, loss: 0.029251618310809135
2023-01-24 06:29:44.764177: step: 1968/531, loss: 0.006897643208503723
2023-01-24 06:29:45.818297: step: 1972/531, loss: 0.023039130493998528
2023-01-24 06:29:46.884027: step: 1976/531, loss: 0.008329298347234726
2023-01-24 06:29:47.952692: step: 1980/531, loss: 0.004423499573022127
2023-01-24 06:29:49.007412: step: 1984/531, loss: 0.007672346197068691
2023-01-24 06:29:50.078078: step: 1988/531, loss: 0.007056684233248234
2023-01-24 06:29:51.134089: step: 1992/531, loss: 0.015146947465837002
2023-01-24 06:29:52.182873: step: 1996/531, loss: 0.0074618845246732235
2023-01-24 06:29:53.229604: step: 2000/531, loss: 0.007594224065542221
2023-01-24 06:29:54.276184: step: 2004/531, loss: 0.014378862455487251
2023-01-24 06:29:55.336707: step: 2008/531, loss: 0.01346305850893259
2023-01-24 06:29:56.392070: step: 2012/531, loss: 0.0124990688636899
2023-01-24 06:29:57.439629: step: 2016/531, loss: 0.002079632366076112
2023-01-24 06:29:58.499685: step: 2020/531, loss: 0.003100641770288348
2023-01-24 06:29:59.569617: step: 2024/531, loss: 0.0057336376048624516
2023-01-24 06:30:00.621995: step: 2028/531, loss: 0.0375279076397419
2023-01-24 06:30:01.716595: step: 2032/531, loss: 0.04547116532921791
2023-01-24 06:30:02.770765: step: 2036/531, loss: 0.0145768653601408
2023-01-24 06:30:03.829374: step: 2040/531, loss: 0.0009005660540424287
2023-01-24 06:30:04.883513: step: 2044/531, loss: 0.004415468312799931
2023-01-24 06:30:05.929196: step: 2048/531, loss: 0.0009496543207205832
2023-01-24 06:30:06.969351: step: 2052/531, loss: 0.0001494246971560642
2023-01-24 06:30:08.038702: step: 2056/531, loss: 0.008947949856519699
2023-01-24 06:30:09.108560: step: 2060/531, loss: 0.005062913987785578
2023-01-24 06:30:10.177776: step: 2064/531, loss: 0.011062598787248135
2023-01-24 06:30:11.225704: step: 2068/531, loss: 0.0024848771281540394
2023-01-24 06:30:12.316095: step: 2072/531, loss: 0.002251523081213236
2023-01-24 06:30:13.373051: step: 2076/531, loss: 0.010579647496342659
2023-01-24 06:30:14.437142: step: 2080/531, loss: 0.009761269204318523
2023-01-24 06:30:15.489084: step: 2084/531, loss: 0.008730175904929638
2023-01-24 06:30:16.545041: step: 2088/531, loss: 0.004113091621547937
2023-01-24 06:30:17.612636: step: 2092/531, loss: 0.013936447910964489
2023-01-24 06:30:18.660260: step: 2096/531, loss: 0.0006778360111638904
2023-01-24 06:30:19.712897: step: 2100/531, loss: 0.0076556517742574215
2023-01-24 06:30:20.771663: step: 2104/531, loss: 0.009191824123263359
2023-01-24 06:30:21.820282: step: 2108/531, loss: 0.013487404212355614
2023-01-24 06:30:22.880004: step: 2112/531, loss: 0.008738575503230095
2023-01-24 06:30:23.949361: step: 2116/531, loss: 0.018730249255895615
2023-01-24 06:30:24.992486: step: 2120/531, loss: 0.004661012906581163
2023-01-24 06:30:26.040453: step: 2124/531, loss: 0.007966527715325356
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3928589700437433, 'r': 0.32278545356535265, 'f1': 0.3543915292269601}, 'combined': 0.2611306004830232, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3893497653166865, 'r': 0.27665249329986386, 'f1': 0.32346612026309857}, 'combined': 0.2025442061460524, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.377211297612241, 'r': 0.3414227494516868, 'f1': 0.35842587442438034}, 'combined': 0.26410327589164867, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.39053916298590485, 'r': 0.2884144044052805, 'f1': 0.33179623909279676}, 'combined': 0.20562020450821206, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36442367530366865, 'r': 0.329848374041461, 'f1': 0.34627508589611544}, 'combined': 0.2551500632918745, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4102575605166279, 'r': 0.2855895732361016, 'f1': 0.33675580725022514}, 'combined': 0.22339246619569392, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 5}
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, 'stategy': 1, 'epoch': 5}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3933515724803238, 'r': 0.3246829867721838, 'f1': 0.3557337505799186}, 'combined': 0.26211960569046633, 'stategy': 1, 'epoch': 4}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38738335236054167, 'r': 0.27665249329986386, 'f1': 0.3227854971799569}, 'combined': 0.20211802159866463, 'stategy': 1, 'epoch': 4}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36442367530366865, 'r': 0.329848374041461, 'f1': 0.34627508589611544}, 'combined': 0.2551500632918745, 'stategy': 1, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4102575605166279, 'r': 0.2855895732361016, 'f1': 0.33675580725022514}, 'combined': 0.22339246619569392, 'stategy': 1, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 5}
******************************
Epoch: 6
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:32:53.187146: step: 4/531, loss: 0.0029432920273393393
2023-01-24 06:32:54.250151: step: 8/531, loss: 0.012537912465631962
2023-01-24 06:32:55.298050: step: 12/531, loss: 0.006358463317155838
2023-01-24 06:32:56.340407: step: 16/531, loss: 0.01048597227782011
2023-01-24 06:32:57.389941: step: 20/531, loss: 0.03826751559972763
2023-01-24 06:32:58.442653: step: 24/531, loss: 0.007358907721936703
2023-01-24 06:32:59.509461: step: 28/531, loss: 0.0007023790967650712
2023-01-24 06:33:00.557577: step: 32/531, loss: 0.010311347432434559
2023-01-24 06:33:01.598908: step: 36/531, loss: 0.009779251180589199
2023-01-24 06:33:02.652306: step: 40/531, loss: 0.00765445688739419
2023-01-24 06:33:03.701981: step: 44/531, loss: 0.007590987719595432
2023-01-24 06:33:04.757409: step: 48/531, loss: 0.004070092923939228
2023-01-24 06:33:05.820664: step: 52/531, loss: 0.013553265482187271
2023-01-24 06:33:06.865223: step: 56/531, loss: 0.00460100919008255
2023-01-24 06:33:07.917136: step: 60/531, loss: 0.0018755365163087845
2023-01-24 06:33:08.977176: step: 64/531, loss: 0.006594268139451742
2023-01-24 06:33:10.036782: step: 68/531, loss: 0.021202603355050087
2023-01-24 06:33:11.087271: step: 72/531, loss: 0.0051115211099386215
2023-01-24 06:33:12.183486: step: 76/531, loss: 0.011831862851977348
2023-01-24 06:33:13.266629: step: 80/531, loss: 0.00372308655641973
2023-01-24 06:33:14.326571: step: 84/531, loss: 0.0059432159177958965
2023-01-24 06:33:15.388974: step: 88/531, loss: 0.002925391076132655
2023-01-24 06:33:16.450643: step: 92/531, loss: 0.007892461493611336
2023-01-24 06:33:17.517157: step: 96/531, loss: 0.004295353312045336
2023-01-24 06:33:18.569651: step: 100/531, loss: 0.003130609868094325
2023-01-24 06:33:19.629250: step: 104/531, loss: 0.003559037111699581
2023-01-24 06:33:20.689606: step: 108/531, loss: 0.03169618546962738
2023-01-24 06:33:21.760941: step: 112/531, loss: 0.0016914688749238849
2023-01-24 06:33:22.808807: step: 116/531, loss: 0.00453194510191679
2023-01-24 06:33:23.864766: step: 120/531, loss: 0.004311460070312023
2023-01-24 06:33:24.929976: step: 124/531, loss: 0.00015067994536366314
2023-01-24 06:33:25.995936: step: 128/531, loss: 0.01180365588515997
2023-01-24 06:33:27.056002: step: 132/531, loss: 0.0068669915199279785
2023-01-24 06:33:28.113974: step: 136/531, loss: 0.014179384335875511
2023-01-24 06:33:29.193476: step: 140/531, loss: 0.009227036498486996
2023-01-24 06:33:30.240598: step: 144/531, loss: 0.0031901486217975616
2023-01-24 06:33:31.293964: step: 148/531, loss: 0.010394065640866756
2023-01-24 06:33:32.343681: step: 152/531, loss: 0.005526988301426172
2023-01-24 06:33:33.402302: step: 156/531, loss: 0.007694893982261419
2023-01-24 06:33:34.466349: step: 160/531, loss: 0.018761100247502327
2023-01-24 06:33:35.516749: step: 164/531, loss: 0.003636488225311041
2023-01-24 06:33:36.566210: step: 168/531, loss: 0.007499323692172766
2023-01-24 06:33:37.623237: step: 172/531, loss: 0.0012549867387861013
2023-01-24 06:33:38.682408: step: 176/531, loss: 0.017907671630382538
2023-01-24 06:33:39.762625: step: 180/531, loss: 0.004827454686164856
2023-01-24 06:33:40.824662: step: 184/531, loss: 0.011534781195223331
2023-01-24 06:33:41.892719: step: 188/531, loss: 0.010364646092057228
2023-01-24 06:33:42.959945: step: 192/531, loss: 0.02631274238228798
2023-01-24 06:33:44.026947: step: 196/531, loss: 0.05170430988073349
2023-01-24 06:33:45.089762: step: 200/531, loss: 0.009858191013336182
2023-01-24 06:33:46.152430: step: 204/531, loss: 0.002230084501206875
2023-01-24 06:33:47.210572: step: 208/531, loss: 0.03495972976088524
2023-01-24 06:33:48.265798: step: 212/531, loss: 0.006210052873939276
2023-01-24 06:33:49.322170: step: 216/531, loss: 0.0016872802516445518
2023-01-24 06:33:50.378994: step: 220/531, loss: 0.006086660083383322
2023-01-24 06:33:51.448523: step: 224/531, loss: 0.006006134673953056
2023-01-24 06:33:52.519656: step: 228/531, loss: 0.011503309942781925
2023-01-24 06:33:53.588458: step: 232/531, loss: 0.004908869042992592
2023-01-24 06:33:54.651286: step: 236/531, loss: 0.030399464070796967
2023-01-24 06:33:55.709915: step: 240/531, loss: 0.01036855112761259
2023-01-24 06:33:56.785302: step: 244/531, loss: 0.005475116427987814
2023-01-24 06:33:57.858275: step: 248/531, loss: 0.005370229482650757
2023-01-24 06:33:58.918012: step: 252/531, loss: 0.08954307436943054
2023-01-24 06:33:59.966261: step: 256/531, loss: 0.0033486774191260338
2023-01-24 06:34:01.026082: step: 260/531, loss: 0.009520561434328556
2023-01-24 06:34:02.077559: step: 264/531, loss: 0.009070155210793018
2023-01-24 06:34:03.154480: step: 268/531, loss: 0.005462727043777704
2023-01-24 06:34:04.210040: step: 272/531, loss: 0.003876342670992017
2023-01-24 06:34:05.268915: step: 276/531, loss: 0.0036967338528484106
2023-01-24 06:34:06.317074: step: 280/531, loss: 0.016257284209132195
2023-01-24 06:34:07.372440: step: 284/531, loss: 0.015393643639981747
2023-01-24 06:34:08.431551: step: 288/531, loss: 0.017000624909996986
2023-01-24 06:34:09.490370: step: 292/531, loss: 0.0014995795208960772
2023-01-24 06:34:10.553922: step: 296/531, loss: 0.0019912030547857285
2023-01-24 06:34:11.613277: step: 300/531, loss: 0.018623339012265205
2023-01-24 06:34:12.679049: step: 304/531, loss: 0.0032100719399750233
2023-01-24 06:34:13.760951: step: 308/531, loss: 0.008174534887075424
2023-01-24 06:34:14.813749: step: 312/531, loss: 0.006355820689350367
2023-01-24 06:34:15.875076: step: 316/531, loss: 0.004291565623134375
2023-01-24 06:34:16.925980: step: 320/531, loss: 0.01585438847541809
2023-01-24 06:34:17.983121: step: 324/531, loss: 0.008459637872874737
2023-01-24 06:34:19.054076: step: 328/531, loss: 0.0025221228133887053
2023-01-24 06:34:20.130277: step: 332/531, loss: 0.006429034750908613
2023-01-24 06:34:21.196492: step: 336/531, loss: 0.01835118792951107
2023-01-24 06:34:22.257279: step: 340/531, loss: 0.0032088810112327337
2023-01-24 06:34:23.317995: step: 344/531, loss: 0.008852764032781124
2023-01-24 06:34:24.389618: step: 348/531, loss: 0.0006368711474351585
2023-01-24 06:34:25.473502: step: 352/531, loss: 0.0020705857314169407
2023-01-24 06:34:26.532001: step: 356/531, loss: 0.0012071322416886687
2023-01-24 06:34:27.610330: step: 360/531, loss: 0.06297539174556732
2023-01-24 06:34:28.679462: step: 364/531, loss: 0.0025182832032442093
2023-01-24 06:34:29.743853: step: 368/531, loss: 0.003892142791301012
2023-01-24 06:34:30.798093: step: 372/531, loss: 0.0023428681306540966
2023-01-24 06:34:31.844515: step: 376/531, loss: 0.011905311606824398
2023-01-24 06:34:32.897109: step: 380/531, loss: 0.00553668849170208
2023-01-24 06:34:33.953285: step: 384/531, loss: 0.0015418021939694881
2023-01-24 06:34:35.006098: step: 388/531, loss: 0.00022266483574640006
2023-01-24 06:34:36.062471: step: 392/531, loss: 0.07920946180820465
2023-01-24 06:34:37.125375: step: 396/531, loss: 0.039017874747514725
2023-01-24 06:34:38.180120: step: 400/531, loss: 0.036102745682001114
2023-01-24 06:34:39.244382: step: 404/531, loss: 0.005013606045395136
2023-01-24 06:34:40.281824: step: 408/531, loss: 0.0035922450479120016
2023-01-24 06:34:41.374343: step: 412/531, loss: 0.005755963735282421
2023-01-24 06:34:42.424290: step: 416/531, loss: 0.058614909648895264
2023-01-24 06:34:43.510861: step: 420/531, loss: 0.010722002945840359
2023-01-24 06:34:44.570041: step: 424/531, loss: 0.010336421430110931
2023-01-24 06:34:45.649381: step: 428/531, loss: 0.010240410454571247
2023-01-24 06:34:46.713098: step: 432/531, loss: 0.0035464453976601362
2023-01-24 06:34:47.768857: step: 436/531, loss: 0.004397819750010967
2023-01-24 06:34:48.821845: step: 440/531, loss: 0.0069640446454286575
2023-01-24 06:34:49.911038: step: 444/531, loss: 0.008963567204773426
2023-01-24 06:34:50.981814: step: 448/531, loss: 0.010772636160254478
2023-01-24 06:34:52.041043: step: 452/531, loss: 0.02769404649734497
2023-01-24 06:34:53.118979: step: 456/531, loss: 0.002520160283893347
2023-01-24 06:34:54.186878: step: 460/531, loss: 0.008938014507293701
2023-01-24 06:34:55.264655: step: 464/531, loss: 0.007377485744655132
2023-01-24 06:34:56.314947: step: 468/531, loss: 0.0018793304916471243
2023-01-24 06:34:57.377436: step: 472/531, loss: 0.005979171488434076
2023-01-24 06:34:58.457077: step: 476/531, loss: 0.008090565912425518
2023-01-24 06:34:59.500520: step: 480/531, loss: 0.00870831310749054
2023-01-24 06:35:00.560831: step: 484/531, loss: 0.0295771025121212
2023-01-24 06:35:01.625891: step: 488/531, loss: 0.010176768526434898
2023-01-24 06:35:02.669913: step: 492/531, loss: 0.005269124638289213
2023-01-24 06:35:03.739806: step: 496/531, loss: 0.012513717636466026
2023-01-24 06:35:04.803138: step: 500/531, loss: 0.017855126410722733
2023-01-24 06:35:05.865740: step: 504/531, loss: 0.003243731101974845
2023-01-24 06:35:06.939488: step: 508/531, loss: 0.0022735833190381527
2023-01-24 06:35:08.003143: step: 512/531, loss: 0.01889975368976593
2023-01-24 06:35:09.075159: step: 516/531, loss: 0.013020745478570461
2023-01-24 06:35:10.129525: step: 520/531, loss: 0.002150821965187788
2023-01-24 06:35:11.184101: step: 524/531, loss: 0.0028804310131818056
2023-01-24 06:35:12.227017: step: 528/531, loss: 0.003170869778841734
2023-01-24 06:35:13.292026: step: 532/531, loss: 0.0013524453388527036
2023-01-24 06:35:14.353447: step: 536/531, loss: 0.00864172913134098
2023-01-24 06:35:15.418738: step: 540/531, loss: 0.001284754485823214
2023-01-24 06:35:16.483802: step: 544/531, loss: 0.025572624057531357
2023-01-24 06:35:17.548279: step: 548/531, loss: 0.006978447083383799
2023-01-24 06:35:18.606187: step: 552/531, loss: 0.00270474492572248
2023-01-24 06:35:19.671547: step: 556/531, loss: 0.03037181869149208
2023-01-24 06:35:20.748913: step: 560/531, loss: 0.010270398110151291
2023-01-24 06:35:21.798803: step: 564/531, loss: 0.007949589751660824
2023-01-24 06:35:22.865625: step: 568/531, loss: 0.004779871553182602
2023-01-24 06:35:23.920350: step: 572/531, loss: 0.0014209687942638993
2023-01-24 06:35:24.983661: step: 576/531, loss: 0.002962718019261956
2023-01-24 06:35:26.027032: step: 580/531, loss: 0.015369495376944542
2023-01-24 06:35:27.100822: step: 584/531, loss: 0.01894855871796608
2023-01-24 06:35:28.150295: step: 588/531, loss: 0.006767974700778723
2023-01-24 06:35:29.212638: step: 592/531, loss: 0.003008423373103142
2023-01-24 06:35:30.284798: step: 596/531, loss: 0.01145913079380989
2023-01-24 06:35:31.338326: step: 600/531, loss: 0.0060500348918139935
2023-01-24 06:35:32.406630: step: 604/531, loss: 0.021979445591568947
2023-01-24 06:35:33.470968: step: 608/531, loss: 0.008840704336762428
2023-01-24 06:35:34.528747: step: 612/531, loss: 0.023319141939282417
2023-01-24 06:35:35.604366: step: 616/531, loss: 0.05718563497066498
2023-01-24 06:35:36.692467: step: 620/531, loss: 0.030173836275935173
2023-01-24 06:35:37.765336: step: 624/531, loss: 0.0003511547693051398
2023-01-24 06:35:38.836865: step: 628/531, loss: 0.006536046974360943
2023-01-24 06:35:39.887030: step: 632/531, loss: 0.0019321806030347943
2023-01-24 06:35:40.962466: step: 636/531, loss: 0.010432318784296513
2023-01-24 06:35:42.032751: step: 640/531, loss: 0.0026999544352293015
2023-01-24 06:35:43.107501: step: 644/531, loss: 0.0157073475420475
2023-01-24 06:35:44.174990: step: 648/531, loss: 0.05477079749107361
2023-01-24 06:35:45.226572: step: 652/531, loss: 0.00508402194827795
2023-01-24 06:35:46.286298: step: 656/531, loss: 0.0050207399763166904
2023-01-24 06:35:47.344512: step: 660/531, loss: 0.007853449322283268
2023-01-24 06:35:48.411562: step: 664/531, loss: 0.008380183018743992
2023-01-24 06:35:49.461488: step: 668/531, loss: 0.0026519836392253637
2023-01-24 06:35:50.533389: step: 672/531, loss: 0.005142910405993462
2023-01-24 06:35:51.596681: step: 676/531, loss: 0.024934709072113037
2023-01-24 06:35:52.664305: step: 680/531, loss: 0.0005833875620737672
2023-01-24 06:35:53.745007: step: 684/531, loss: 0.005784018896520138
2023-01-24 06:35:54.801159: step: 688/531, loss: 0.009918668307363987
2023-01-24 06:35:55.875833: step: 692/531, loss: 0.009790316224098206
2023-01-24 06:35:56.943640: step: 696/531, loss: 0.0015267275739461184
2023-01-24 06:35:58.040777: step: 700/531, loss: 0.004760469309985638
2023-01-24 06:35:59.105479: step: 704/531, loss: 0.011497597210109234
2023-01-24 06:36:00.182879: step: 708/531, loss: 0.0032411532010883093
2023-01-24 06:36:01.264317: step: 712/531, loss: 0.005637328140437603
2023-01-24 06:36:02.325403: step: 716/531, loss: 0.007290184032171965
2023-01-24 06:36:03.392094: step: 720/531, loss: 0.0424954816699028
2023-01-24 06:36:04.459596: step: 724/531, loss: 0.005525291431695223
2023-01-24 06:36:05.528815: step: 728/531, loss: 0.005197733640670776
2023-01-24 06:36:06.607629: step: 732/531, loss: 0.03285115957260132
2023-01-24 06:36:07.678221: step: 736/531, loss: 0.009032647125422955
2023-01-24 06:36:08.729118: step: 740/531, loss: 0.0115432720631361
2023-01-24 06:36:09.779516: step: 744/531, loss: 0.009898380376398563
2023-01-24 06:36:10.833732: step: 748/531, loss: 0.012690548785030842
2023-01-24 06:36:11.916275: step: 752/531, loss: 0.007415212690830231
2023-01-24 06:36:12.967819: step: 756/531, loss: 0.0053363386541605
2023-01-24 06:36:14.032545: step: 760/531, loss: 0.005677635315805674
2023-01-24 06:36:15.113936: step: 764/531, loss: 0.006649449467658997
2023-01-24 06:36:16.196427: step: 768/531, loss: 0.011402852833271027
2023-01-24 06:36:17.278485: step: 772/531, loss: 0.00688968924805522
2023-01-24 06:36:18.336441: step: 776/531, loss: 0.0009790461044758558
2023-01-24 06:36:19.383558: step: 780/531, loss: 0.0030372862238436937
2023-01-24 06:36:20.445714: step: 784/531, loss: 0.008241291157901287
2023-01-24 06:36:21.514017: step: 788/531, loss: 0.004959088284522295
2023-01-24 06:36:22.577122: step: 792/531, loss: 0.006605707574635744
2023-01-24 06:36:23.645432: step: 796/531, loss: 0.006869078613817692
2023-01-24 06:36:24.701554: step: 800/531, loss: 0.0013255409430712461
2023-01-24 06:36:25.762779: step: 804/531, loss: 0.0011628136271610856
2023-01-24 06:36:26.823720: step: 808/531, loss: 0.01237429492175579
2023-01-24 06:36:27.903458: step: 812/531, loss: 0.014288225211203098
2023-01-24 06:36:28.988088: step: 816/531, loss: 0.020358677953481674
2023-01-24 06:36:30.072325: step: 820/531, loss: 0.0016593632753938437
2023-01-24 06:36:31.143763: step: 824/531, loss: 0.0037502467166632414
2023-01-24 06:36:32.206943: step: 828/531, loss: 0.004868919961154461
2023-01-24 06:36:33.267230: step: 832/531, loss: 0.00874305795878172
2023-01-24 06:36:34.329232: step: 836/531, loss: 0.004308534786105156
2023-01-24 06:36:35.407867: step: 840/531, loss: 0.05860290303826332
2023-01-24 06:36:36.467042: step: 844/531, loss: 0.0038430599961429834
2023-01-24 06:36:37.525564: step: 848/531, loss: 0.03443102166056633
2023-01-24 06:36:38.604266: step: 852/531, loss: 0.0041647967882454395
2023-01-24 06:36:39.646259: step: 856/531, loss: 0.0
2023-01-24 06:36:40.705995: step: 860/531, loss: 0.005874386988580227
2023-01-24 06:36:41.770357: step: 864/531, loss: 0.00691419979557395
2023-01-24 06:36:42.869241: step: 868/531, loss: 0.018089568242430687
2023-01-24 06:36:43.939769: step: 872/531, loss: 0.002000002423301339
2023-01-24 06:36:45.003875: step: 876/531, loss: 0.0031377498526126146
2023-01-24 06:36:46.080940: step: 880/531, loss: 0.006632352247834206
2023-01-24 06:36:47.142238: step: 884/531, loss: 0.012486872263252735
2023-01-24 06:36:48.219097: step: 888/531, loss: 0.007046861108392477
2023-01-24 06:36:49.294103: step: 892/531, loss: 0.008797496557235718
2023-01-24 06:36:50.366497: step: 896/531, loss: 0.008230539038777351
2023-01-24 06:36:51.428058: step: 900/531, loss: 0.005878815893083811
2023-01-24 06:36:52.496214: step: 904/531, loss: 0.00798221305012703
2023-01-24 06:36:53.562839: step: 908/531, loss: 0.0037675644271075726
2023-01-24 06:36:54.644959: step: 912/531, loss: 0.007415076717734337
2023-01-24 06:36:55.706771: step: 916/531, loss: 0.00133984733838588
2023-01-24 06:36:56.764690: step: 920/531, loss: 0.002230678219348192
2023-01-24 06:36:57.831930: step: 924/531, loss: 0.0013091347645968199
2023-01-24 06:36:58.900803: step: 928/531, loss: 0.0016474085859954357
2023-01-24 06:36:59.964748: step: 932/531, loss: 0.008072270080447197
2023-01-24 06:37:01.040276: step: 936/531, loss: 0.004681349731981754
2023-01-24 06:37:02.089096: step: 940/531, loss: 0.0372842475771904
2023-01-24 06:37:03.139495: step: 944/531, loss: 0.015247981064021587
2023-01-24 06:37:04.207163: step: 948/531, loss: 0.011911117471754551
2023-01-24 06:37:05.288364: step: 952/531, loss: 0.007198999170213938
2023-01-24 06:37:06.360127: step: 956/531, loss: 0.0014013596810400486
2023-01-24 06:37:07.425866: step: 960/531, loss: 0.004519191104918718
2023-01-24 06:37:08.493776: step: 964/531, loss: 0.008875181898474693
2023-01-24 06:37:09.565053: step: 968/531, loss: 0.0036492496728897095
2023-01-24 06:37:10.642525: step: 972/531, loss: 0.02182733826339245
2023-01-24 06:37:11.703932: step: 976/531, loss: 0.04539189487695694
2023-01-24 06:37:12.768560: step: 980/531, loss: 0.0011102509452030063
2023-01-24 06:37:13.813443: step: 984/531, loss: 0.006845785304903984
2023-01-24 06:37:14.858737: step: 988/531, loss: 0.0005421403329819441
2023-01-24 06:37:15.935400: step: 992/531, loss: 0.010717685334384441
2023-01-24 06:37:17.008822: step: 996/531, loss: 0.02985331416130066
2023-01-24 06:37:18.072223: step: 1000/531, loss: 0.008929370902478695
2023-01-24 06:37:19.131135: step: 1004/531, loss: 0.015887390822172165
2023-01-24 06:37:20.193684: step: 1008/531, loss: 0.012111171148717403
2023-01-24 06:37:21.246278: step: 1012/531, loss: 0.004509125370532274
2023-01-24 06:37:22.310441: step: 1016/531, loss: 0.013637019321322441
2023-01-24 06:37:23.363694: step: 1020/531, loss: 6.853634840808809e-05
2023-01-24 06:37:24.419494: step: 1024/531, loss: 0.002534861909225583
2023-01-24 06:37:25.486347: step: 1028/531, loss: 0.004997155163437128
2023-01-24 06:37:26.538432: step: 1032/531, loss: 0.05634595453739166
2023-01-24 06:37:27.597325: step: 1036/531, loss: 0.0011073792120441794
2023-01-24 06:37:28.655148: step: 1040/531, loss: 0.010222180746495724
2023-01-24 06:37:29.702000: step: 1044/531, loss: 0.0005028155283071101
2023-01-24 06:37:30.762058: step: 1048/531, loss: 0.0023263171315193176
2023-01-24 06:37:31.819715: step: 1052/531, loss: 0.005292803514748812
2023-01-24 06:37:32.879040: step: 1056/531, loss: 0.005772221367806196
2023-01-24 06:37:33.930259: step: 1060/531, loss: 0.00011989741324214265
2023-01-24 06:37:34.979625: step: 1064/531, loss: 0.005717512220144272
2023-01-24 06:37:36.019740: step: 1068/531, loss: 0.010426831431686878
2023-01-24 06:37:37.079706: step: 1072/531, loss: 0.003298128955066204
2023-01-24 06:37:38.134141: step: 1076/531, loss: 0.0006716709467582405
2023-01-24 06:37:39.193164: step: 1080/531, loss: 0.0008013807237148285
2023-01-24 06:37:40.260138: step: 1084/531, loss: 0.009770435281097889
2023-01-24 06:37:41.320090: step: 1088/531, loss: 0.012029794976115227
2023-01-24 06:37:42.413119: step: 1092/531, loss: 0.0029329024255275726
2023-01-24 06:37:43.468074: step: 1096/531, loss: 0.015537690371274948
2023-01-24 06:37:44.524189: step: 1100/531, loss: 0.002954992698505521
2023-01-24 06:37:45.592344: step: 1104/531, loss: 0.03443381190299988
2023-01-24 06:37:46.649348: step: 1108/531, loss: 0.009190636686980724
2023-01-24 06:37:47.714919: step: 1112/531, loss: 0.020895270630717278
2023-01-24 06:37:48.780127: step: 1116/531, loss: 0.0015741956885904074
2023-01-24 06:37:49.848768: step: 1120/531, loss: 0.020179197192192078
2023-01-24 06:37:50.935410: step: 1124/531, loss: 0.0016432267148047686
2023-01-24 06:37:51.985171: step: 1128/531, loss: 0.0007776243728585541
2023-01-24 06:37:53.058089: step: 1132/531, loss: 0.04637470841407776
2023-01-24 06:37:54.114183: step: 1136/531, loss: 0.023987144231796265
2023-01-24 06:37:55.178500: step: 1140/531, loss: 0.005930606741458178
2023-01-24 06:37:56.231823: step: 1144/531, loss: 0.010379788465797901
2023-01-24 06:37:57.312635: step: 1148/531, loss: 0.020205894485116005
2023-01-24 06:37:58.384839: step: 1152/531, loss: 0.004121109377592802
2023-01-24 06:37:59.447435: step: 1156/531, loss: 0.013121345080435276
2023-01-24 06:38:00.523834: step: 1160/531, loss: 0.010387592017650604
2023-01-24 06:38:01.595344: step: 1164/531, loss: 0.03616507723927498
2023-01-24 06:38:02.647992: step: 1168/531, loss: 0.005236451979726553
2023-01-24 06:38:03.710609: step: 1172/531, loss: 0.01286311261355877
2023-01-24 06:38:04.754137: step: 1176/531, loss: 0.0005282892961986363
2023-01-24 06:38:05.805413: step: 1180/531, loss: 0.015461313538253307
2023-01-24 06:38:06.867087: step: 1184/531, loss: 0.011073824018239975
2023-01-24 06:38:07.915415: step: 1188/531, loss: 0.00697501003742218
2023-01-24 06:38:08.991167: step: 1192/531, loss: 0.03540768846869469
2023-01-24 06:38:10.057291: step: 1196/531, loss: 0.014474504627287388
2023-01-24 06:38:11.113834: step: 1200/531, loss: 0.005541430786252022
2023-01-24 06:38:12.177140: step: 1204/531, loss: 0.011974726803600788
2023-01-24 06:38:13.236612: step: 1208/531, loss: 0.022920407354831696
2023-01-24 06:38:14.317433: step: 1212/531, loss: 0.0017761550843715668
2023-01-24 06:38:15.380022: step: 1216/531, loss: 0.005945018958300352
2023-01-24 06:38:16.453193: step: 1220/531, loss: 0.0001790232490748167
2023-01-24 06:38:17.509352: step: 1224/531, loss: 0.015340182930231094
2023-01-24 06:38:18.575999: step: 1228/531, loss: 0.007377743721008301
2023-01-24 06:38:19.643793: step: 1232/531, loss: 0.005427806172519922
2023-01-24 06:38:20.687669: step: 1236/531, loss: 0.0010519563220441341
2023-01-24 06:38:21.753215: step: 1240/531, loss: 0.010295179672539234
2023-01-24 06:38:22.805367: step: 1244/531, loss: 0.008899634703993797
2023-01-24 06:38:23.862579: step: 1248/531, loss: 0.005573725793510675
2023-01-24 06:38:24.914585: step: 1252/531, loss: 0.036438584327697754
2023-01-24 06:38:25.993992: step: 1256/531, loss: 0.0173336174339056
2023-01-24 06:38:27.070745: step: 1260/531, loss: 0.009335625916719437
2023-01-24 06:38:28.127064: step: 1264/531, loss: 0.020228074863553047
2023-01-24 06:38:29.170847: step: 1268/531, loss: 0.0166328102350235
2023-01-24 06:38:30.239679: step: 1272/531, loss: 0.0017933398485183716
2023-01-24 06:38:31.286989: step: 1276/531, loss: 0.0047768172807991505
2023-01-24 06:38:32.342101: step: 1280/531, loss: 0.00873319711536169
2023-01-24 06:38:33.388478: step: 1284/531, loss: 0.00023820690694265068
2023-01-24 06:38:34.441454: step: 1288/531, loss: 0.00501972297206521
2023-01-24 06:38:35.504787: step: 1292/531, loss: 0.017059117555618286
2023-01-24 06:38:36.554367: step: 1296/531, loss: 0.0006950476672500372
2023-01-24 06:38:37.630040: step: 1300/531, loss: 0.004926077090203762
2023-01-24 06:38:38.684460: step: 1304/531, loss: 0.003382546827197075
2023-01-24 06:38:39.751539: step: 1308/531, loss: 0.007411657832562923
2023-01-24 06:38:40.804738: step: 1312/531, loss: 0.004177900031208992
2023-01-24 06:38:41.893372: step: 1316/531, loss: 0.018221421167254448
2023-01-24 06:38:42.930788: step: 1320/531, loss: 0.0035860363859683275
2023-01-24 06:38:43.982777: step: 1324/531, loss: 0.0016093968879431486
2023-01-24 06:38:45.056604: step: 1328/531, loss: 0.0009316093055531383
2023-01-24 06:38:46.120129: step: 1332/531, loss: 0.0011106191668659449
2023-01-24 06:38:47.181615: step: 1336/531, loss: 0.013964518904685974
2023-01-24 06:38:48.231956: step: 1340/531, loss: 0.005351893603801727
2023-01-24 06:38:49.301715: step: 1344/531, loss: 0.022416943684220314
2023-01-24 06:38:50.351286: step: 1348/531, loss: 0.06408470869064331
2023-01-24 06:38:51.418669: step: 1352/531, loss: 0.006485450081527233
2023-01-24 06:38:52.481732: step: 1356/531, loss: 0.0038483969401568174
2023-01-24 06:38:53.543310: step: 1360/531, loss: 0.006142089143395424
2023-01-24 06:38:54.611725: step: 1364/531, loss: 0.009657652117311954
2023-01-24 06:38:55.650454: step: 1368/531, loss: 0.015305178239941597
2023-01-24 06:38:56.705621: step: 1372/531, loss: 0.037024226039648056
2023-01-24 06:38:57.762389: step: 1376/531, loss: 0.0028578753117471933
2023-01-24 06:38:58.804071: step: 1380/531, loss: 4.95872154715471e-05
2023-01-24 06:38:59.869386: step: 1384/531, loss: 0.0007027056417427957
2023-01-24 06:39:00.941297: step: 1388/531, loss: 0.006710399873554707
2023-01-24 06:39:01.992843: step: 1392/531, loss: 0.016674794256687164
2023-01-24 06:39:03.034168: step: 1396/531, loss: 0.001589001971296966
2023-01-24 06:39:04.091765: step: 1400/531, loss: 0.0016361505258828402
2023-01-24 06:39:05.127129: step: 1404/531, loss: 0.00785883516073227
2023-01-24 06:39:06.179403: step: 1408/531, loss: 0.0003021680167876184
2023-01-24 06:39:07.236030: step: 1412/531, loss: 0.003640773007646203
2023-01-24 06:39:08.299832: step: 1416/531, loss: 0.01461334340274334
2023-01-24 06:39:09.372940: step: 1420/531, loss: 0.002424241742119193
2023-01-24 06:39:10.410443: step: 1424/531, loss: 0.002955395495519042
2023-01-24 06:39:11.490546: step: 1428/531, loss: 0.008063364773988724
2023-01-24 06:39:12.544886: step: 1432/531, loss: 0.006800973787903786
2023-01-24 06:39:13.600149: step: 1436/531, loss: 0.004543921444565058
2023-01-24 06:39:14.647440: step: 1440/531, loss: 0.00531755993142724
2023-01-24 06:39:15.701171: step: 1444/531, loss: 0.0048471237532794476
2023-01-24 06:39:16.757950: step: 1448/531, loss: 0.01994478330016136
2023-01-24 06:39:17.816086: step: 1452/531, loss: 0.044987574219703674
2023-01-24 06:39:18.881209: step: 1456/531, loss: 0.0003491649404168129
2023-01-24 06:39:19.941066: step: 1460/531, loss: 0.0002789389109238982
2023-01-24 06:39:20.994619: step: 1464/531, loss: 1.3910464986111037e-05
2023-01-24 06:39:22.047143: step: 1468/531, loss: 0.014729684218764305
2023-01-24 06:39:23.126522: step: 1472/531, loss: 0.00895836390554905
2023-01-24 06:39:24.181549: step: 1476/531, loss: 0.007623247802257538
2023-01-24 06:39:25.230493: step: 1480/531, loss: 0.007720944471657276
2023-01-24 06:39:26.306748: step: 1484/531, loss: 0.008904880844056606
2023-01-24 06:39:27.378976: step: 1488/531, loss: 0.009866662323474884
2023-01-24 06:39:28.429162: step: 1492/531, loss: 0.008230365812778473
2023-01-24 06:39:29.486757: step: 1496/531, loss: 0.0062467847019433975
2023-01-24 06:39:30.539645: step: 1500/531, loss: 0.0013609403977170587
2023-01-24 06:39:31.612063: step: 1504/531, loss: 0.003021181095391512
2023-01-24 06:39:32.680838: step: 1508/531, loss: 0.007688530720770359
2023-01-24 06:39:33.733449: step: 1512/531, loss: 0.006852554157376289
2023-01-24 06:39:34.783000: step: 1516/531, loss: 0.014278341084718704
2023-01-24 06:39:35.867635: step: 1520/531, loss: 0.007408963516354561
2023-01-24 06:39:36.919056: step: 1524/531, loss: 0.0034462958574295044
2023-01-24 06:39:37.968007: step: 1528/531, loss: 0.0025516273453831673
2023-01-24 06:39:39.028035: step: 1532/531, loss: 0.003779664635658264
2023-01-24 06:39:40.082017: step: 1536/531, loss: 0.0048885946162045
2023-01-24 06:39:41.123678: step: 1540/531, loss: 0.004900121130049229
2023-01-24 06:39:42.190386: step: 1544/531, loss: 0.005288383457809687
2023-01-24 06:39:43.249392: step: 1548/531, loss: 0.018736552447080612
2023-01-24 06:39:44.304784: step: 1552/531, loss: 1.226474250870524e-05
2023-01-24 06:39:45.353105: step: 1556/531, loss: 0.006348559632897377
2023-01-24 06:39:46.428740: step: 1560/531, loss: 0.03728722035884857
2023-01-24 06:39:47.475772: step: 1564/531, loss: 0.0047976309433579445
2023-01-24 06:39:48.526164: step: 1568/531, loss: 0.0014296979643404484
2023-01-24 06:39:49.592985: step: 1572/531, loss: 0.01720673032104969
2023-01-24 06:39:50.661798: step: 1576/531, loss: 0.0019312668591737747
2023-01-24 06:39:51.728799: step: 1580/531, loss: 0.002072556409984827
2023-01-24 06:39:52.792105: step: 1584/531, loss: 0.0003468520299065858
2023-01-24 06:39:53.840172: step: 1588/531, loss: 0.0031809844076633453
2023-01-24 06:39:54.922824: step: 1592/531, loss: 0.011697826907038689
2023-01-24 06:39:55.980414: step: 1596/531, loss: 0.004813006613403559
2023-01-24 06:39:57.043828: step: 1600/531, loss: 0.0033183274790644646
2023-01-24 06:39:58.094977: step: 1604/531, loss: 0.004599857144057751
2023-01-24 06:39:59.156373: step: 1608/531, loss: 0.01199669111520052
2023-01-24 06:40:00.214033: step: 1612/531, loss: 0.005202004685997963
2023-01-24 06:40:01.285685: step: 1616/531, loss: 0.003957950510084629
2023-01-24 06:40:02.350831: step: 1620/531, loss: 0.0011726460652425885
2023-01-24 06:40:03.398309: step: 1624/531, loss: 0.004059431608766317
2023-01-24 06:40:04.455963: step: 1628/531, loss: 0.003595364047214389
2023-01-24 06:40:05.518641: step: 1632/531, loss: 0.007409157231450081
2023-01-24 06:40:06.583256: step: 1636/531, loss: 0.0019780935253947973
2023-01-24 06:40:07.645498: step: 1640/531, loss: 0.022702112793922424
2023-01-24 06:40:08.689169: step: 1644/531, loss: 0.005747990682721138
2023-01-24 06:40:09.739228: step: 1648/531, loss: 0.005032900255173445
2023-01-24 06:40:10.809361: step: 1652/531, loss: 0.0028443720657378435
2023-01-24 06:40:11.889411: step: 1656/531, loss: 0.0035552673507481813
2023-01-24 06:40:12.937469: step: 1660/531, loss: 0.015025815926492214
2023-01-24 06:40:13.981613: step: 1664/531, loss: 0.00045435811625793576
2023-01-24 06:40:15.033610: step: 1668/531, loss: 0.005025635939091444
2023-01-24 06:40:16.085801: step: 1672/531, loss: 0.03417355194687843
2023-01-24 06:40:17.146374: step: 1676/531, loss: 0.011585216037929058
2023-01-24 06:40:18.200710: step: 1680/531, loss: 0.003591161919757724
2023-01-24 06:40:19.251597: step: 1684/531, loss: 0.01113806664943695
2023-01-24 06:40:20.304283: step: 1688/531, loss: 0.004196211230009794
2023-01-24 06:40:21.369252: step: 1692/531, loss: 0.00629101088270545
2023-01-24 06:40:22.420882: step: 1696/531, loss: 0.014905724674463272
2023-01-24 06:40:23.470150: step: 1700/531, loss: 0.0029332919511944056
2023-01-24 06:40:24.541713: step: 1704/531, loss: 0.004238472320139408
2023-01-24 06:40:25.595068: step: 1708/531, loss: 0.000372401176718995
2023-01-24 06:40:26.658833: step: 1712/531, loss: 0.01268011610955
2023-01-24 06:40:27.728527: step: 1716/531, loss: 0.011812311597168446
2023-01-24 06:40:28.779377: step: 1720/531, loss: 0.003110135206952691
2023-01-24 06:40:29.849476: step: 1724/531, loss: 0.008479684591293335
2023-01-24 06:40:30.912766: step: 1728/531, loss: 0.004277018364518881
2023-01-24 06:40:31.960614: step: 1732/531, loss: 0.006617109291255474
2023-01-24 06:40:33.015602: step: 1736/531, loss: 0.0044241719879209995
2023-01-24 06:40:34.068719: step: 1740/531, loss: 0.0026026498526334763
2023-01-24 06:40:35.120755: step: 1744/531, loss: 0.007485625799745321
2023-01-24 06:40:36.177929: step: 1748/531, loss: 0.007189452648162842
2023-01-24 06:40:37.233959: step: 1752/531, loss: 0.0045541455037891865
2023-01-24 06:40:38.287000: step: 1756/531, loss: 0.008894850499927998
2023-01-24 06:40:39.373037: step: 1760/531, loss: 0.005660593509674072
2023-01-24 06:40:40.422562: step: 1764/531, loss: 0.0019180066883563995
2023-01-24 06:40:41.483002: step: 1768/531, loss: 0.0009436768596060574
2023-01-24 06:40:42.580326: step: 1772/531, loss: 0.005720451939851046
2023-01-24 06:40:43.647426: step: 1776/531, loss: 0.0025520373601466417
2023-01-24 06:40:44.716799: step: 1780/531, loss: 0.0015464320313185453
2023-01-24 06:40:45.772254: step: 1784/531, loss: 0.004384071100503206
2023-01-24 06:40:46.833726: step: 1788/531, loss: 0.006013082806020975
2023-01-24 06:40:47.880166: step: 1792/531, loss: 0.006493647117167711
2023-01-24 06:40:48.942779: step: 1796/531, loss: 0.00790315866470337
2023-01-24 06:40:50.012304: step: 1800/531, loss: 0.0090031111612916
2023-01-24 06:40:51.066943: step: 1804/531, loss: 0.000918390229344368
2023-01-24 06:40:52.119008: step: 1808/531, loss: 0.0007245594169944525
2023-01-24 06:40:53.180148: step: 1812/531, loss: 0.00401635468006134
2023-01-24 06:40:54.241194: step: 1816/531, loss: 0.002673220820724964
2023-01-24 06:40:55.290561: step: 1820/531, loss: 0.005069272127002478
2023-01-24 06:40:56.353815: step: 1824/531, loss: 0.00564933568239212
2023-01-24 06:40:57.424336: step: 1828/531, loss: 0.0047026448883116245
2023-01-24 06:40:58.505984: step: 1832/531, loss: 0.005653322674334049
2023-01-24 06:40:59.552977: step: 1836/531, loss: 0.002209238475188613
2023-01-24 06:41:00.621664: step: 1840/531, loss: 0.0026490730233490467
2023-01-24 06:41:01.671581: step: 1844/531, loss: 0.011918609961867332
2023-01-24 06:41:02.736898: step: 1848/531, loss: 0.0036911170464009047
2023-01-24 06:41:03.793777: step: 1852/531, loss: 0.005991524085402489
2023-01-24 06:41:04.863050: step: 1856/531, loss: 0.003986523021012545
2023-01-24 06:41:05.910835: step: 1860/531, loss: 0.027299998328089714
2023-01-24 06:41:06.956213: step: 1864/531, loss: 0.01316267903894186
2023-01-24 06:41:08.002204: step: 1868/531, loss: 0.00766478106379509
2023-01-24 06:41:09.074781: step: 1872/531, loss: 0.008670568466186523
2023-01-24 06:41:10.133554: step: 1876/531, loss: 0.02351980097591877
2023-01-24 06:41:11.181170: step: 1880/531, loss: 0.02516782097518444
2023-01-24 06:41:12.243569: step: 1884/531, loss: 0.002396475290879607
2023-01-24 06:41:13.325416: step: 1888/531, loss: 0.0023003334645181894
2023-01-24 06:41:14.396857: step: 1892/531, loss: 0.008029518648982048
2023-01-24 06:41:15.461478: step: 1896/531, loss: 0.009424656629562378
2023-01-24 06:41:16.537213: step: 1900/531, loss: 0.0029585405718535185
2023-01-24 06:41:17.582897: step: 1904/531, loss: 0.008412801660597324
2023-01-24 06:41:18.642755: step: 1908/531, loss: 0.008342405781149864
2023-01-24 06:41:19.688094: step: 1912/531, loss: 0.01795872487127781
2023-01-24 06:41:20.742562: step: 1916/531, loss: 0.00738177727907896
2023-01-24 06:41:21.800249: step: 1920/531, loss: 0.011627256870269775
2023-01-24 06:41:22.857445: step: 1924/531, loss: 0.009259622544050217
2023-01-24 06:41:23.902647: step: 1928/531, loss: 0.007299355231225491
2023-01-24 06:41:24.947216: step: 1932/531, loss: 0.004032579716295004
2023-01-24 06:41:26.014278: step: 1936/531, loss: 0.0019013237906619906
2023-01-24 06:41:27.074037: step: 1940/531, loss: 0.01666168123483658
2023-01-24 06:41:28.141318: step: 1944/531, loss: 0.013499433174729347
2023-01-24 06:41:29.198133: step: 1948/531, loss: 0.022215723991394043
2023-01-24 06:41:30.259547: step: 1952/531, loss: 0.014236253686249256
2023-01-24 06:41:31.321475: step: 1956/531, loss: 0.004504339769482613
2023-01-24 06:41:32.386867: step: 1960/531, loss: 0.01728799007833004
2023-01-24 06:41:33.441762: step: 1964/531, loss: 0.002598227234557271
2023-01-24 06:41:34.510805: step: 1968/531, loss: 0.019606834277510643
2023-01-24 06:41:35.567148: step: 1972/531, loss: 0.0017232568934559822
2023-01-24 06:41:36.621043: step: 1976/531, loss: 0.003615857334807515
2023-01-24 06:41:37.686452: step: 1980/531, loss: 0.00292869727127254
2023-01-24 06:41:38.755079: step: 1984/531, loss: 0.0055353702045977116
2023-01-24 06:41:39.834849: step: 1988/531, loss: 0.008058445528149605
2023-01-24 06:41:40.897591: step: 1992/531, loss: 0.007985231466591358
2023-01-24 06:41:41.971029: step: 1996/531, loss: 0.02180594578385353
2023-01-24 06:41:43.015013: step: 2000/531, loss: 0.010600738227367401
2023-01-24 06:41:44.082062: step: 2004/531, loss: 0.04641266167163849
2023-01-24 06:41:45.141145: step: 2008/531, loss: 0.028026631101965904
2023-01-24 06:41:46.198885: step: 2012/531, loss: 0.00044320797314867377
2023-01-24 06:41:47.258296: step: 2016/531, loss: 0.011095143854618073
2023-01-24 06:41:48.318714: step: 2020/531, loss: 0.029895756393671036
2023-01-24 06:41:49.377535: step: 2024/531, loss: 0.0033620460890233517
2023-01-24 06:41:50.435902: step: 2028/531, loss: 0.01604628562927246
2023-01-24 06:41:51.495185: step: 2032/531, loss: 0.0037713171914219856
2023-01-24 06:41:52.547333: step: 2036/531, loss: 0.02835371159017086
2023-01-24 06:41:53.625974: step: 2040/531, loss: 0.004161869175732136
2023-01-24 06:41:54.675630: step: 2044/531, loss: 0.003946738317608833
2023-01-24 06:41:55.739120: step: 2048/531, loss: 0.008512686006724834
2023-01-24 06:41:56.794050: step: 2052/531, loss: 0.0004516572807915509
2023-01-24 06:41:57.859579: step: 2056/531, loss: 0.06959584355354309
2023-01-24 06:41:58.917405: step: 2060/531, loss: 0.0
2023-01-24 06:41:59.962659: step: 2064/531, loss: 0.020264845341444016
2023-01-24 06:42:01.001441: step: 2068/531, loss: 0.011989165097475052
2023-01-24 06:42:02.062340: step: 2072/531, loss: 0.0026472690515220165
2023-01-24 06:42:03.131944: step: 2076/531, loss: 0.025359176099300385
2023-01-24 06:42:04.191782: step: 2080/531, loss: 0.0020903984550386667
2023-01-24 06:42:05.247044: step: 2084/531, loss: 0.001333598862402141
2023-01-24 06:42:06.310737: step: 2088/531, loss: 0.02223386988043785
2023-01-24 06:42:07.370196: step: 2092/531, loss: 0.01397033128887415
2023-01-24 06:42:08.414860: step: 2096/531, loss: 0.013732771389186382
2023-01-24 06:42:09.486104: step: 2100/531, loss: 0.006502912845462561
2023-01-24 06:42:10.576289: step: 2104/531, loss: 0.005976259242743254
2023-01-24 06:42:11.631644: step: 2108/531, loss: 0.0008377428166568279
2023-01-24 06:42:12.675293: step: 2112/531, loss: 0.0009003969607874751
2023-01-24 06:42:13.711536: step: 2116/531, loss: 0.004043653141707182
2023-01-24 06:42:14.778474: step: 2120/531, loss: 0.01152876392006874
2023-01-24 06:42:15.854975: step: 2124/531, loss: 0.008723646402359009
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3756416609706083, 'r': 0.3385764496414401, 'f1': 0.3561472833553671}, 'combined': 0.2624243140513231, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892525485079313, 'r': 0.28570926463972596, 'f1': 0.32953881901763504}, 'combined': 0.2042212399545907, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3663754650743069, 'r': 0.32605330762779877, 'f1': 0.3450403476302208}, 'combined': 0.2542402561485837, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4128482340917574, 'r': 0.2873929997464713, 'f1': 0.338882335692543}, 'combined': 0.2248031335782216, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.40217391304347827, 'r': 0.40217391304347827, 'f1': 0.40217391304347827}, 'combined': 0.20108695652173914, 'stategy': 1, 'epoch': 6}
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, 'stategy': 1, 'epoch': 6}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36442367530366865, 'r': 0.329848374041461, 'f1': 0.34627508589611544}, 'combined': 0.2551500632918745, 'stategy': 1, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4102575605166279, 'r': 0.2855895732361016, 'f1': 0.33675580725022514}, 'combined': 0.22339246619569392, 'stategy': 1, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 5}
******************************
Epoch: 7
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:44:48.242782: step: 4/531, loss: 0.0006492187967523932
2023-01-24 06:44:49.284040: step: 8/531, loss: 0.004802904091775417
2023-01-24 06:44:50.338498: step: 12/531, loss: 0.015752611681818962
2023-01-24 06:44:51.393716: step: 16/531, loss: 0.012046156451106071
2023-01-24 06:44:52.443344: step: 20/531, loss: 0.002270354190841317
2023-01-24 06:44:53.477020: step: 24/531, loss: 0.021567337214946747
2023-01-24 06:44:54.536843: step: 28/531, loss: 0.0036491076461970806
2023-01-24 06:44:55.601870: step: 32/531, loss: 0.0017398595809936523
2023-01-24 06:44:56.658624: step: 36/531, loss: 0.0005531217902898788
2023-01-24 06:44:57.719974: step: 40/531, loss: 0.001784879365004599
2023-01-24 06:44:58.782234: step: 44/531, loss: 7.12331939212163e-06
2023-01-24 06:44:59.829482: step: 48/531, loss: 0.0028284811414778233
2023-01-24 06:45:00.874448: step: 52/531, loss: 0.0004425981314852834
2023-01-24 06:45:01.934006: step: 56/531, loss: 0.004374339245259762
2023-01-24 06:45:02.987849: step: 60/531, loss: 0.0028135827742516994
2023-01-24 06:45:04.035317: step: 64/531, loss: 0.012824036180973053
2023-01-24 06:45:05.107533: step: 68/531, loss: 0.0335075743496418
2023-01-24 06:45:06.162911: step: 72/531, loss: 0.0053871809504926205
2023-01-24 06:45:07.231538: step: 76/531, loss: 0.013369427993893623
2023-01-24 06:45:08.286855: step: 80/531, loss: 0.04436447098851204
2023-01-24 06:45:09.357426: step: 84/531, loss: 0.002875553211197257
2023-01-24 06:45:10.419259: step: 88/531, loss: 0.007801753934472799
2023-01-24 06:45:11.482312: step: 92/531, loss: 0.0037565003149211407
2023-01-24 06:45:12.561502: step: 96/531, loss: 0.004316174425184727
2023-01-24 06:45:13.617147: step: 100/531, loss: 0.005416641477495432
2023-01-24 06:45:14.672623: step: 104/531, loss: 0.0036287778057157993
2023-01-24 06:45:15.730169: step: 108/531, loss: 0.004348293412476778
2023-01-24 06:45:16.803171: step: 112/531, loss: 0.014397756196558475
2023-01-24 06:45:17.849541: step: 116/531, loss: 0.00114683888386935
2023-01-24 06:45:18.902367: step: 120/531, loss: 0.005130800884217024
2023-01-24 06:45:19.950124: step: 124/531, loss: 0.007498049642890692
2023-01-24 06:45:21.003543: step: 128/531, loss: 0.0005397589993663132
2023-01-24 06:45:22.083880: step: 132/531, loss: 0.06988916546106339
2023-01-24 06:45:23.140817: step: 136/531, loss: 0.002622071420773864
2023-01-24 06:45:24.198609: step: 140/531, loss: 0.005704334005713463
2023-01-24 06:45:25.264888: step: 144/531, loss: 0.0005702752387151122
2023-01-24 06:45:26.301516: step: 148/531, loss: 0.0010824378114193678
2023-01-24 06:45:27.355789: step: 152/531, loss: 0.00779822887852788
2023-01-24 06:45:28.414014: step: 156/531, loss: 0.014901806600391865
2023-01-24 06:45:29.483692: step: 160/531, loss: 0.004425419960170984
2023-01-24 06:45:30.539266: step: 164/531, loss: 0.0002514993539080024
2023-01-24 06:45:31.605782: step: 168/531, loss: 0.01510639488697052
2023-01-24 06:45:32.655839: step: 172/531, loss: 0.006646621040999889
2023-01-24 06:45:33.725672: step: 176/531, loss: 0.01198204793035984
2023-01-24 06:45:34.784434: step: 180/531, loss: 0.0022676994558423758
2023-01-24 06:45:35.852852: step: 184/531, loss: 0.0023348811082541943
2023-01-24 06:45:36.931544: step: 188/531, loss: 0.021751388907432556
2023-01-24 06:45:38.005711: step: 192/531, loss: 0.019914787262678146
2023-01-24 06:45:39.071862: step: 196/531, loss: 0.00429602200165391
2023-01-24 06:45:40.141162: step: 200/531, loss: 0.00019583826360758394
2023-01-24 06:45:41.199515: step: 204/531, loss: 0.0012761821271851659
2023-01-24 06:45:42.248279: step: 208/531, loss: 0.011430647224187851
2023-01-24 06:45:43.304811: step: 212/531, loss: 0.0006558317691087723
2023-01-24 06:45:44.364041: step: 216/531, loss: 0.009576068259775639
2023-01-24 06:45:45.425665: step: 220/531, loss: 0.0027853159699589014
2023-01-24 06:45:46.477355: step: 224/531, loss: 0.006347036920487881
2023-01-24 06:45:47.533064: step: 228/531, loss: 0.0005861844401806593
2023-01-24 06:45:48.599687: step: 232/531, loss: 0.06506709009408951
2023-01-24 06:45:49.651222: step: 236/531, loss: 0.0032848953269422054
2023-01-24 06:45:50.697794: step: 240/531, loss: 0.0025946497917175293
2023-01-24 06:45:51.750015: step: 244/531, loss: 0.003949759993702173
2023-01-24 06:45:52.804939: step: 248/531, loss: 0.010272135026752949
2023-01-24 06:45:53.866598: step: 252/531, loss: 0.006210848689079285
2023-01-24 06:45:54.956515: step: 256/531, loss: 0.007650288287550211
2023-01-24 06:45:56.019544: step: 260/531, loss: 0.007213053293526173
2023-01-24 06:45:57.077448: step: 264/531, loss: 0.00025169874425046146
2023-01-24 06:45:58.150689: step: 268/531, loss: 0.0022797819692641497
2023-01-24 06:45:59.200365: step: 272/531, loss: 0.004989979322999716
2023-01-24 06:46:00.269182: step: 276/531, loss: 0.002507602795958519
2023-01-24 06:46:01.326852: step: 280/531, loss: 0.0033433998469263315
2023-01-24 06:46:02.387181: step: 284/531, loss: 0.0029465025290846825
2023-01-24 06:46:03.446173: step: 288/531, loss: 0.006215470377355814
2023-01-24 06:46:04.505753: step: 292/531, loss: 0.0010657849488779902
2023-01-24 06:46:05.584773: step: 296/531, loss: 0.007482234388589859
2023-01-24 06:46:06.636239: step: 300/531, loss: 0.006049760617315769
2023-01-24 06:46:07.713659: step: 304/531, loss: 0.0049827806651592255
2023-01-24 06:46:08.765925: step: 308/531, loss: 0.0010435294825583696
2023-01-24 06:46:09.824232: step: 312/531, loss: 0.0007052760920487344
2023-01-24 06:46:10.887527: step: 316/531, loss: 0.014551017433404922
2023-01-24 06:46:11.961842: step: 320/531, loss: 0.044681794941425323
2023-01-24 06:46:13.013553: step: 324/531, loss: 0.009216065518558025
2023-01-24 06:46:14.069248: step: 328/531, loss: 0.013036536984145641
2023-01-24 06:46:15.133458: step: 332/531, loss: 0.00922372005879879
2023-01-24 06:46:16.182185: step: 336/531, loss: 0.008950003422796726
2023-01-24 06:46:17.243497: step: 340/531, loss: 0.00798529852181673
2023-01-24 06:46:18.320278: step: 344/531, loss: 0.006593076977878809
2023-01-24 06:46:19.373067: step: 348/531, loss: 0.002142342971637845
2023-01-24 06:46:20.442167: step: 352/531, loss: 0.0032343610655516386
2023-01-24 06:46:21.501815: step: 356/531, loss: 0.014155490323901176
2023-01-24 06:46:22.558557: step: 360/531, loss: 0.0016211258480325341
2023-01-24 06:46:23.624498: step: 364/531, loss: 0.0027973006945103407
2023-01-24 06:46:24.681076: step: 368/531, loss: 0.006330488715320826
2023-01-24 06:46:25.750135: step: 372/531, loss: 0.007343151606619358
2023-01-24 06:46:26.832044: step: 376/531, loss: 0.010084627196192741
2023-01-24 06:46:27.890941: step: 380/531, loss: 0.0008924533030949533
2023-01-24 06:46:28.947520: step: 384/531, loss: 0.01889900490641594
2023-01-24 06:46:30.012951: step: 388/531, loss: 0.004234483931213617
2023-01-24 06:46:31.101717: step: 392/531, loss: 0.0062158117070794106
2023-01-24 06:46:32.160996: step: 396/531, loss: 0.009244952350854874
2023-01-24 06:46:33.231942: step: 400/531, loss: 0.009495830163359642
2023-01-24 06:46:34.284377: step: 404/531, loss: 0.0019206582801416516
2023-01-24 06:46:35.357479: step: 408/531, loss: 0.002965971827507019
2023-01-24 06:46:36.422809: step: 412/531, loss: 0.0062917061150074005
2023-01-24 06:46:37.484784: step: 416/531, loss: 0.0047087762504816055
2023-01-24 06:46:38.541723: step: 420/531, loss: 0.0052788592875003815
2023-01-24 06:46:39.593577: step: 424/531, loss: 0.012063873000442982
2023-01-24 06:46:40.643951: step: 428/531, loss: 0.007540481630712748
2023-01-24 06:46:41.701278: step: 432/531, loss: 0.0027695889584720135
2023-01-24 06:46:42.764904: step: 436/531, loss: 0.021550847217440605
2023-01-24 06:46:43.815851: step: 440/531, loss: 0.005915469024330378
2023-01-24 06:46:44.887974: step: 444/531, loss: 0.004781430587172508
2023-01-24 06:46:45.948023: step: 448/531, loss: 0.006881205830723047
2023-01-24 06:46:47.006694: step: 452/531, loss: 0.007237443700432777
2023-01-24 06:46:48.069669: step: 456/531, loss: 0.007598720956593752
2023-01-24 06:46:49.132165: step: 460/531, loss: 0.0075926268473267555
2023-01-24 06:46:50.193891: step: 464/531, loss: 0.0001259603159269318
2023-01-24 06:46:51.279044: step: 468/531, loss: 0.007884755730628967
2023-01-24 06:46:52.333250: step: 472/531, loss: 0.0008542384603060782
2023-01-24 06:46:53.403979: step: 476/531, loss: 0.0012061416637152433
2023-01-24 06:46:54.466851: step: 480/531, loss: 0.0015838273102417588
2023-01-24 06:46:55.513642: step: 484/531, loss: 0.014944592490792274
2023-01-24 06:46:56.592536: step: 488/531, loss: 0.004819272551685572
2023-01-24 06:46:57.673238: step: 492/531, loss: 0.008972696959972382
2023-01-24 06:46:58.744228: step: 496/531, loss: 0.0012989470269531012
2023-01-24 06:46:59.799363: step: 500/531, loss: 0.007035675924271345
2023-01-24 06:47:00.870018: step: 504/531, loss: 0.004334037192165852
2023-01-24 06:47:01.938815: step: 508/531, loss: 0.02392931655049324
2023-01-24 06:47:03.008130: step: 512/531, loss: 0.015061544254422188
2023-01-24 06:47:04.067337: step: 516/531, loss: 0.008190691471099854
2023-01-24 06:47:05.142112: step: 520/531, loss: 0.005081430077552795
2023-01-24 06:47:06.197683: step: 524/531, loss: 0.017981668934226036
2023-01-24 06:47:07.251012: step: 528/531, loss: 0.0005370138096623123
2023-01-24 06:47:08.312834: step: 532/531, loss: 0.003851471468806267
2023-01-24 06:47:09.370163: step: 536/531, loss: 0.0025094801094383
2023-01-24 06:47:10.431093: step: 540/531, loss: 0.003738607745617628
2023-01-24 06:47:11.505562: step: 544/531, loss: 0.013799403794109821
2023-01-24 06:47:12.596326: step: 548/531, loss: 0.032146699726581573
2023-01-24 06:47:13.656050: step: 552/531, loss: 0.00934658758342266
2023-01-24 06:47:14.715267: step: 556/531, loss: 0.012887738645076752
2023-01-24 06:47:15.794206: step: 560/531, loss: 0.014045830816030502
2023-01-24 06:47:16.871331: step: 564/531, loss: 0.019588304683566093
2023-01-24 06:47:17.924038: step: 568/531, loss: 0.0014023719122633338
2023-01-24 06:47:18.987232: step: 572/531, loss: 0.061655573546886444
2023-01-24 06:47:20.032057: step: 576/531, loss: 0.011357041075825691
2023-01-24 06:47:21.089422: step: 580/531, loss: 0.008658317849040031
2023-01-24 06:47:22.159585: step: 584/531, loss: 0.005844382103532553
2023-01-24 06:47:23.218950: step: 588/531, loss: 0.0033900365233421326
2023-01-24 06:47:24.288274: step: 592/531, loss: 0.010819818824529648
2023-01-24 06:47:25.348715: step: 596/531, loss: 0.005710499361157417
2023-01-24 06:47:26.445254: step: 600/531, loss: 0.01022400613874197
2023-01-24 06:47:27.503474: step: 604/531, loss: 0.011874786578118801
2023-01-24 06:47:28.570596: step: 608/531, loss: 0.002632047748193145
2023-01-24 06:47:29.646248: step: 612/531, loss: 0.0004185358702670783
2023-01-24 06:47:30.715534: step: 616/531, loss: 0.0032836003229022026
2023-01-24 06:47:31.758900: step: 620/531, loss: 0.00014435005141422153
2023-01-24 06:47:32.821315: step: 624/531, loss: 0.00794036965817213
2023-01-24 06:47:33.900991: step: 628/531, loss: 0.003446119837462902
2023-01-24 06:47:34.945984: step: 632/531, loss: 0.0014714625431224704
2023-01-24 06:47:35.983767: step: 636/531, loss: 0.00029268290381878614
2023-01-24 06:47:37.058296: step: 640/531, loss: 0.018005361780524254
2023-01-24 06:47:38.123925: step: 644/531, loss: 0.005744707304984331
2023-01-24 06:47:39.199804: step: 648/531, loss: 0.03598678484559059
2023-01-24 06:47:40.278349: step: 652/531, loss: 0.020917510613799095
2023-01-24 06:47:41.351816: step: 656/531, loss: 0.000643776380456984
2023-01-24 06:47:42.437146: step: 660/531, loss: 0.003372986800968647
2023-01-24 06:47:43.501849: step: 664/531, loss: 0.004733528476208448
2023-01-24 06:47:44.576251: step: 668/531, loss: 0.006730652879923582
2023-01-24 06:47:45.651016: step: 672/531, loss: 0.007533761207014322
2023-01-24 06:47:46.715702: step: 676/531, loss: 0.012822278775274754
2023-01-24 06:47:47.786809: step: 680/531, loss: 0.00032225617906078696
2023-01-24 06:47:48.874879: step: 684/531, loss: 0.005407245829701424
2023-01-24 06:47:49.947965: step: 688/531, loss: 0.0015551522374153137
2023-01-24 06:47:51.024094: step: 692/531, loss: 0.009238948114216328
2023-01-24 06:47:52.091847: step: 696/531, loss: 0.002054974203929305
2023-01-24 06:47:53.190067: step: 700/531, loss: 0.0019452502019703388
2023-01-24 06:47:54.250648: step: 704/531, loss: 0.0022884036879986525
2023-01-24 06:47:55.311874: step: 708/531, loss: 0.004203475546091795
2023-01-24 06:47:56.403796: step: 712/531, loss: 0.005513494368642569
2023-01-24 06:47:57.463330: step: 716/531, loss: 0.001011253334581852
2023-01-24 06:47:58.533322: step: 720/531, loss: 0.009160853922367096
2023-01-24 06:47:59.599368: step: 724/531, loss: 0.003776432015001774
2023-01-24 06:48:00.679901: step: 728/531, loss: 0.006054773926734924
2023-01-24 06:48:01.751349: step: 732/531, loss: 0.004920446313917637
2023-01-24 06:48:02.809608: step: 736/531, loss: 0.0011047249427065253
2023-01-24 06:48:03.884713: step: 740/531, loss: 0.0015072107780724764
2023-01-24 06:48:04.943257: step: 744/531, loss: 0.0011187985073775053
2023-01-24 06:48:06.025436: step: 748/531, loss: 0.013454984873533249
2023-01-24 06:48:07.091147: step: 752/531, loss: 0.013698996044695377
2023-01-24 06:48:08.161312: step: 756/531, loss: 0.006787206511944532
2023-01-24 06:48:09.230472: step: 760/531, loss: 0.0010444317013025284
2023-01-24 06:48:10.300046: step: 764/531, loss: 0.011175837367773056
2023-01-24 06:48:11.369523: step: 768/531, loss: 8.234030974563211e-05
2023-01-24 06:48:12.445498: step: 772/531, loss: 0.005729043390601873
2023-01-24 06:48:13.489301: step: 776/531, loss: 0.003512623952701688
2023-01-24 06:48:14.560620: step: 780/531, loss: 0.011913996189832687
2023-01-24 06:48:15.624630: step: 784/531, loss: 0.0031369433272629976
2023-01-24 06:48:16.670881: step: 788/531, loss: 0.01617421954870224
2023-01-24 06:48:17.732414: step: 792/531, loss: 0.010591531172394753
2023-01-24 06:48:18.791590: step: 796/531, loss: 0.006628000643104315
2023-01-24 06:48:19.857865: step: 800/531, loss: 0.037484798580408096
2023-01-24 06:48:20.914969: step: 804/531, loss: 0.027918970212340355
2023-01-24 06:48:21.961038: step: 808/531, loss: 0.0006715216441079974
2023-01-24 06:48:23.021030: step: 812/531, loss: 0.025618532672524452
2023-01-24 06:48:24.084841: step: 816/531, loss: 0.034035008400678635
2023-01-24 06:48:25.134002: step: 820/531, loss: 0.011319356970489025
2023-01-24 06:48:26.213073: step: 824/531, loss: 0.021084044128656387
2023-01-24 06:48:27.251023: step: 828/531, loss: 0.000995192094705999
2023-01-24 06:48:28.310082: step: 832/531, loss: 0.0007222912972792983
2023-01-24 06:48:29.380675: step: 836/531, loss: 0.004113358911126852
2023-01-24 06:48:30.436374: step: 840/531, loss: 0.019447915256023407
2023-01-24 06:48:31.496354: step: 844/531, loss: 0.016118677332997322
2023-01-24 06:48:32.578199: step: 848/531, loss: 0.013019963167607784
2023-01-24 06:48:33.654245: step: 852/531, loss: 0.005787972826510668
2023-01-24 06:48:34.736112: step: 856/531, loss: 0.0003658224013634026
2023-01-24 06:48:35.812255: step: 860/531, loss: 0.007707090582698584
2023-01-24 06:48:36.890432: step: 864/531, loss: 0.0012676366604864597
2023-01-24 06:48:37.944812: step: 868/531, loss: 0.004137119743973017
2023-01-24 06:48:39.009750: step: 872/531, loss: 0.0014692473923787475
2023-01-24 06:48:40.070942: step: 876/531, loss: 0.0034385465551167727
2023-01-24 06:48:41.124893: step: 880/531, loss: 0.002908271737396717
2023-01-24 06:48:42.189947: step: 884/531, loss: 0.011820798739790916
2023-01-24 06:48:43.245415: step: 888/531, loss: 0.003473530290648341
2023-01-24 06:48:44.313108: step: 892/531, loss: 0.008599039167165756
2023-01-24 06:48:45.362010: step: 896/531, loss: 0.0031041253823786974
2023-01-24 06:48:46.428806: step: 900/531, loss: 0.008347421884536743
2023-01-24 06:48:47.505205: step: 904/531, loss: 0.007552129682153463
2023-01-24 06:48:48.570356: step: 908/531, loss: 0.002162358956411481
2023-01-24 06:48:49.656372: step: 912/531, loss: 0.0024050199426710606
2023-01-24 06:48:50.710020: step: 916/531, loss: 0.023277850821614265
2023-01-24 06:48:51.773628: step: 920/531, loss: 0.002533361315727234
2023-01-24 06:48:52.849649: step: 924/531, loss: 0.010061078704893589
2023-01-24 06:48:53.918557: step: 928/531, loss: 0.0019515901803970337
2023-01-24 06:48:54.979123: step: 932/531, loss: 0.007701380643993616
2023-01-24 06:48:56.052516: step: 936/531, loss: 0.01530991867184639
2023-01-24 06:48:57.112272: step: 940/531, loss: 0.0031159475911408663
2023-01-24 06:48:58.171935: step: 944/531, loss: 0.0007430640398524702
2023-01-24 06:48:59.244885: step: 948/531, loss: 0.005443783476948738
2023-01-24 06:49:00.319766: step: 952/531, loss: 0.006688730791211128
2023-01-24 06:49:01.373140: step: 956/531, loss: 0.00014675510465167463
2023-01-24 06:49:02.432103: step: 960/531, loss: 0.006066479254513979
2023-01-24 06:49:03.485396: step: 964/531, loss: 0.004118728917092085
2023-01-24 06:49:04.547924: step: 968/531, loss: 0.012234709225594997
2023-01-24 06:49:05.610744: step: 972/531, loss: 0.015265420079231262
2023-01-24 06:49:06.676600: step: 976/531, loss: 0.0037207254208624363
2023-01-24 06:49:07.739800: step: 980/531, loss: 0.006244618911296129
2023-01-24 06:49:08.801359: step: 984/531, loss: 0.005643168464303017
2023-01-24 06:49:09.878050: step: 988/531, loss: 0.0017455547349527478
2023-01-24 06:49:10.929166: step: 992/531, loss: 0.014706265181303024
2023-01-24 06:49:12.016804: step: 996/531, loss: 0.0038010096177458763
2023-01-24 06:49:13.092768: step: 1000/531, loss: 0.0011887227883562446
2023-01-24 06:49:14.180703: step: 1004/531, loss: 0.011953913606703281
2023-01-24 06:49:15.230131: step: 1008/531, loss: 0.000768556201364845
2023-01-24 06:49:16.301021: step: 1012/531, loss: 0.008452901616692543
2023-01-24 06:49:17.363603: step: 1016/531, loss: 0.008053474128246307
2023-01-24 06:49:18.428029: step: 1020/531, loss: 0.007288651540875435
2023-01-24 06:49:19.495581: step: 1024/531, loss: 0.004656703677028418
2023-01-24 06:49:20.556882: step: 1028/531, loss: 0.0014144114684313536
2023-01-24 06:49:21.622349: step: 1032/531, loss: 0.007407342549413443
2023-01-24 06:49:22.669015: step: 1036/531, loss: 0.003363720141351223
2023-01-24 06:49:23.734982: step: 1040/531, loss: 1.0100815416080877e-05
2023-01-24 06:49:24.796738: step: 1044/531, loss: 0.008445918560028076
2023-01-24 06:49:25.854620: step: 1048/531, loss: 0.00014292298874352127
2023-01-24 06:49:26.907510: step: 1052/531, loss: 0.007359790150076151
2023-01-24 06:49:27.982918: step: 1056/531, loss: 0.017630619928240776
2023-01-24 06:49:29.037677: step: 1060/531, loss: 0.0054226163774728775
2023-01-24 06:49:30.066497: step: 1064/531, loss: 0.005007212050259113
2023-01-24 06:49:31.124855: step: 1068/531, loss: 6.087717702030204e-05
2023-01-24 06:49:32.182917: step: 1072/531, loss: 0.0036626989021897316
2023-01-24 06:49:33.250568: step: 1076/531, loss: 0.007369166240096092
2023-01-24 06:49:34.321989: step: 1080/531, loss: 0.0074149626307189465
2023-01-24 06:49:35.386620: step: 1084/531, loss: 0.0033081865403801203
2023-01-24 06:49:36.444479: step: 1088/531, loss: 0.0065081436187028885
2023-01-24 06:49:37.518320: step: 1092/531, loss: 0.0027745591942220926
2023-01-24 06:49:38.578115: step: 1096/531, loss: 0.004033735487610102
2023-01-24 06:49:39.623161: step: 1100/531, loss: 0.004824902396649122
2023-01-24 06:49:40.687443: step: 1104/531, loss: 0.0027580666355788708
2023-01-24 06:49:41.735380: step: 1108/531, loss: 0.004225380718708038
2023-01-24 06:49:42.802735: step: 1112/531, loss: 0.0014375685714185238
2023-01-24 06:49:43.872991: step: 1116/531, loss: 0.0006143644568510354
2023-01-24 06:49:44.924851: step: 1120/531, loss: 0.015592087991535664
2023-01-24 06:49:45.989793: step: 1124/531, loss: 0.007434329017996788
2023-01-24 06:49:47.066495: step: 1128/531, loss: 0.002444205339998007
2023-01-24 06:49:48.111654: step: 1132/531, loss: 0.018612677231431007
2023-01-24 06:49:49.165665: step: 1136/531, loss: 0.007736400701105595
2023-01-24 06:49:50.215104: step: 1140/531, loss: 0.004145750775933266
2023-01-24 06:49:51.278772: step: 1144/531, loss: 0.012243203818798065
2023-01-24 06:49:52.345001: step: 1148/531, loss: 0.015129510313272476
2023-01-24 06:49:53.418952: step: 1152/531, loss: 0.020059751346707344
2023-01-24 06:49:54.451821: step: 1156/531, loss: 0.00022447883384302258
2023-01-24 06:49:55.525711: step: 1160/531, loss: 0.0020700094755738974
2023-01-24 06:49:56.577808: step: 1164/531, loss: 0.01687202975153923
2023-01-24 06:49:57.631443: step: 1168/531, loss: 0.006159815937280655
2023-01-24 06:49:58.682742: step: 1172/531, loss: 0.010063309222459793
2023-01-24 06:49:59.726456: step: 1176/531, loss: 0.002743379445746541
2023-01-24 06:50:00.797110: step: 1180/531, loss: 0.0033418331295251846
2023-01-24 06:50:01.876948: step: 1184/531, loss: 0.025549838319420815
2023-01-24 06:50:02.941643: step: 1188/531, loss: 0.003771526040509343
2023-01-24 06:50:04.008060: step: 1192/531, loss: 0.00991787388920784
2023-01-24 06:50:05.093871: step: 1196/531, loss: 0.015510828234255314
2023-01-24 06:50:06.158133: step: 1200/531, loss: 0.011565836146473885
2023-01-24 06:50:07.233950: step: 1204/531, loss: 0.04709074646234512
2023-01-24 06:50:08.284508: step: 1208/531, loss: 0.018286455422639847
2023-01-24 06:50:09.359224: step: 1212/531, loss: 0.0026013979222625494
2023-01-24 06:50:10.420065: step: 1216/531, loss: 0.0042064860463142395
2023-01-24 06:50:11.482814: step: 1220/531, loss: 0.006525625474750996
2023-01-24 06:50:12.575215: step: 1224/531, loss: 0.00807811040431261
2023-01-24 06:50:13.624749: step: 1228/531, loss: 0.004882653709501028
2023-01-24 06:50:14.693649: step: 1232/531, loss: 0.019261857494711876
2023-01-24 06:50:15.746366: step: 1236/531, loss: 0.004634142387658358
2023-01-24 06:50:16.811348: step: 1240/531, loss: 0.0034124834928661585
2023-01-24 06:50:17.862600: step: 1244/531, loss: 0.0036466929595917463
2023-01-24 06:50:18.923307: step: 1248/531, loss: 0.004509231075644493
2023-01-24 06:50:19.976405: step: 1252/531, loss: 0.000947600114159286
2023-01-24 06:50:21.032020: step: 1256/531, loss: 0.009373374283313751
2023-01-24 06:50:22.089645: step: 1260/531, loss: 0.021008070558309555
2023-01-24 06:50:23.149749: step: 1264/531, loss: 0.010760831646621227
2023-01-24 06:50:24.238950: step: 1268/531, loss: 0.004743773024529219
2023-01-24 06:50:25.286959: step: 1272/531, loss: 0.021553313359618187
2023-01-24 06:50:26.351626: step: 1276/531, loss: 0.003004447789862752
2023-01-24 06:50:27.392760: step: 1280/531, loss: 0.00231836992315948
2023-01-24 06:50:28.442599: step: 1284/531, loss: 0.029413830488920212
2023-01-24 06:50:29.509522: step: 1288/531, loss: 0.008015123195946217
2023-01-24 06:50:30.580235: step: 1292/531, loss: 0.006133352406322956
2023-01-24 06:50:31.639431: step: 1296/531, loss: 0.004206741228699684
2023-01-24 06:50:32.702619: step: 1300/531, loss: 0.0022905052173882723
2023-01-24 06:50:33.750824: step: 1304/531, loss: 0.004863007925450802
2023-01-24 06:50:34.799492: step: 1308/531, loss: 0.008591294288635254
2023-01-24 06:50:35.853585: step: 1312/531, loss: 0.008686983026564121
2023-01-24 06:50:36.905815: step: 1316/531, loss: 0.0014601402217522264
2023-01-24 06:50:37.967256: step: 1320/531, loss: 0.009601959027349949
2023-01-24 06:50:39.026807: step: 1324/531, loss: 0.016543062403798103
2023-01-24 06:50:40.078215: step: 1328/531, loss: 0.006538198329508305
2023-01-24 06:50:41.138363: step: 1332/531, loss: 0.010706229135394096
2023-01-24 06:50:42.188002: step: 1336/531, loss: 0.007833709940314293
2023-01-24 06:50:43.235030: step: 1340/531, loss: 0.014195882715284824
2023-01-24 06:50:44.291602: step: 1344/531, loss: 0.0029244590550661087
2023-01-24 06:50:45.345464: step: 1348/531, loss: 0.0006867393385618925
2023-01-24 06:50:46.413069: step: 1352/531, loss: 0.009999522008001804
2023-01-24 06:50:47.473990: step: 1356/531, loss: 0.006914444267749786
2023-01-24 06:50:48.537750: step: 1360/531, loss: 0.001022397424094379
2023-01-24 06:50:49.598814: step: 1364/531, loss: 0.011720074340701103
2023-01-24 06:50:50.638223: step: 1368/531, loss: 0.005520156119018793
2023-01-24 06:50:51.687690: step: 1372/531, loss: 0.0028696891386061907
2023-01-24 06:50:52.757813: step: 1376/531, loss: 0.016635971143841743
2023-01-24 06:50:53.797468: step: 1380/531, loss: 0.0003744933637790382
2023-01-24 06:50:54.859650: step: 1384/531, loss: 0.0008608332718722522
2023-01-24 06:50:55.916075: step: 1388/531, loss: 0.012566376477479935
2023-01-24 06:50:56.986423: step: 1392/531, loss: 0.020176827907562256
2023-01-24 06:50:58.045694: step: 1396/531, loss: 0.002106319647282362
2023-01-24 06:50:59.098815: step: 1400/531, loss: 0.033433765172958374
2023-01-24 06:51:00.170458: step: 1404/531, loss: 0.009769782423973083
2023-01-24 06:51:01.236047: step: 1408/531, loss: 0.0005209156661294401
2023-01-24 06:51:02.287834: step: 1412/531, loss: 0.0008644047193229198
2023-01-24 06:51:03.339556: step: 1416/531, loss: 0.004266010597348213
2023-01-24 06:51:04.393735: step: 1420/531, loss: 0.003032218897715211
2023-01-24 06:51:05.453671: step: 1424/531, loss: 0.0023113335482776165
2023-01-24 06:51:06.507279: step: 1428/531, loss: 0.0018706824630498886
2023-01-24 06:51:07.558434: step: 1432/531, loss: 0.008413641713559628
2023-01-24 06:51:08.603606: step: 1436/531, loss: 0.015643928200006485
2023-01-24 06:51:09.676304: step: 1440/531, loss: 0.01871102675795555
2023-01-24 06:51:10.738343: step: 1444/531, loss: 0.000810525962151587
2023-01-24 06:51:11.792855: step: 1448/531, loss: 0.026164840906858444
2023-01-24 06:51:12.847099: step: 1452/531, loss: 0.0009098420850932598
2023-01-24 06:51:13.905903: step: 1456/531, loss: 0.01916046440601349
2023-01-24 06:51:14.967085: step: 1460/531, loss: 0.0034798732958734035
2023-01-24 06:51:16.040624: step: 1464/531, loss: 0.0021816177759319544
2023-01-24 06:51:17.095495: step: 1468/531, loss: 0.007542390376329422
2023-01-24 06:51:18.163207: step: 1472/531, loss: 0.004269434604793787
2023-01-24 06:51:19.219325: step: 1476/531, loss: 0.008925436064600945
2023-01-24 06:51:20.263935: step: 1480/531, loss: 0.0013633263297379017
2023-01-24 06:51:21.313416: step: 1484/531, loss: 0.0023207608610391617
2023-01-24 06:51:22.388229: step: 1488/531, loss: 0.004495031666010618
2023-01-24 06:51:23.440301: step: 1492/531, loss: 0.0
2023-01-24 06:51:24.508655: step: 1496/531, loss: 0.016254903748631477
2023-01-24 06:51:25.581403: step: 1500/531, loss: 0.003299233503639698
2023-01-24 06:51:26.634874: step: 1504/531, loss: 0.0007362092728726566
2023-01-24 06:51:27.693920: step: 1508/531, loss: 0.0020259853918105364
2023-01-24 06:51:28.756245: step: 1512/531, loss: 0.0040224818512797356
2023-01-24 06:51:29.809539: step: 1516/531, loss: 0.003701281500980258
2023-01-24 06:51:30.872409: step: 1520/531, loss: 0.004383988678455353
2023-01-24 06:51:31.920060: step: 1524/531, loss: 9.619694901630282e-05
2023-01-24 06:51:32.965690: step: 1528/531, loss: 0.025479143485426903
2023-01-24 06:51:34.023713: step: 1532/531, loss: 0.0044145225547254086
2023-01-24 06:51:35.077671: step: 1536/531, loss: 0.01800454407930374
2023-01-24 06:51:36.137931: step: 1540/531, loss: 0.01497863419353962
2023-01-24 06:51:37.194463: step: 1544/531, loss: 0.0042779576033353806
2023-01-24 06:51:38.270212: step: 1548/531, loss: 0.008412308990955353
2023-01-24 06:51:39.318790: step: 1552/531, loss: 0.010228274390101433
2023-01-24 06:51:40.393473: step: 1556/531, loss: 0.0026888977736234665
2023-01-24 06:51:41.432941: step: 1560/531, loss: 0.016876718029379845
2023-01-24 06:51:42.481022: step: 1564/531, loss: 7.888342952355742e-05
2023-01-24 06:51:43.544010: step: 1568/531, loss: 0.07939287275075912
2023-01-24 06:51:44.603671: step: 1572/531, loss: 0.00013619325181934983
2023-01-24 06:51:45.659291: step: 1576/531, loss: 0.0012743815314024687
2023-01-24 06:51:46.698836: step: 1580/531, loss: 0.000544706650543958
2023-01-24 06:51:47.764471: step: 1584/531, loss: 0.02795686200261116
2023-01-24 06:51:48.825031: step: 1588/531, loss: 0.005173315294086933
2023-01-24 06:51:49.887754: step: 1592/531, loss: 0.0015534008853137493
2023-01-24 06:51:50.941439: step: 1596/531, loss: 0.00313403713516891
2023-01-24 06:51:51.999382: step: 1600/531, loss: 0.009784866124391556
2023-01-24 06:51:53.078780: step: 1604/531, loss: 0.0021912362426519394
2023-01-24 06:51:54.126946: step: 1608/531, loss: 0.006951576564460993
2023-01-24 06:51:55.178367: step: 1612/531, loss: 0.0006216104375198483
2023-01-24 06:51:56.244576: step: 1616/531, loss: 0.008630983531475067
2023-01-24 06:51:57.314194: step: 1620/531, loss: 0.0025050377007573843
2023-01-24 06:51:58.394607: step: 1624/531, loss: 0.001553927781060338
2023-01-24 06:51:59.438968: step: 1628/531, loss: 0.001910782535560429
2023-01-24 06:52:00.505963: step: 1632/531, loss: 0.0025655110366642475
2023-01-24 06:52:01.577025: step: 1636/531, loss: 0.004358029458671808
2023-01-24 06:52:02.642135: step: 1640/531, loss: 0.001964786322787404
2023-01-24 06:52:03.700188: step: 1644/531, loss: 0.002564901951700449
2023-01-24 06:52:04.751004: step: 1648/531, loss: 0.0026567408349364996
2023-01-24 06:52:05.808648: step: 1652/531, loss: 2.052164745691698e-05
2023-01-24 06:52:06.867186: step: 1656/531, loss: 0.008762887679040432
2023-01-24 06:52:07.934535: step: 1660/531, loss: 0.001838785712607205
2023-01-24 06:52:08.998446: step: 1664/531, loss: 0.02431187778711319
2023-01-24 06:52:10.061805: step: 1668/531, loss: 0.018949678167700768
2023-01-24 06:52:11.135553: step: 1672/531, loss: 0.006652952171862125
2023-01-24 06:52:12.181319: step: 1676/531, loss: 3.775200457312167e-05
2023-01-24 06:52:13.234525: step: 1680/531, loss: 0.004154319409281015
2023-01-24 06:52:14.294751: step: 1684/531, loss: 0.018371930345892906
2023-01-24 06:52:15.338299: step: 1688/531, loss: 0.006730475928634405
2023-01-24 06:52:16.404088: step: 1692/531, loss: 0.010968293994665146
2023-01-24 06:52:17.447982: step: 1696/531, loss: 0.0025148936547338963
2023-01-24 06:52:18.509334: step: 1700/531, loss: 0.005015175323933363
2023-01-24 06:52:19.556598: step: 1704/531, loss: 0.004874736536294222
2023-01-24 06:52:20.612047: step: 1708/531, loss: 0.009839463979005814
2023-01-24 06:52:21.658455: step: 1712/531, loss: 0.0034756127279251814
2023-01-24 06:52:22.722746: step: 1716/531, loss: 0.032976653426885605
2023-01-24 06:52:23.778142: step: 1720/531, loss: 0.0012503552716225386
2023-01-24 06:52:24.847204: step: 1724/531, loss: 0.003754228353500366
2023-01-24 06:52:25.908578: step: 1728/531, loss: 0.004127139691263437
2023-01-24 06:52:26.968548: step: 1732/531, loss: 0.03128005936741829
2023-01-24 06:52:28.017180: step: 1736/531, loss: 0.003958693705499172
2023-01-24 06:52:29.078760: step: 1740/531, loss: 0.001204545609652996
2023-01-24 06:52:30.138159: step: 1744/531, loss: 0.034654177725315094
2023-01-24 06:52:31.198102: step: 1748/531, loss: 0.013512332923710346
2023-01-24 06:52:32.264915: step: 1752/531, loss: 0.006131541449576616
2023-01-24 06:52:33.333267: step: 1756/531, loss: 0.0015703821554780006
2023-01-24 06:52:34.375898: step: 1760/531, loss: 0.00391714833676815
2023-01-24 06:52:35.407916: step: 1764/531, loss: 0.0015651213470846415
2023-01-24 06:52:36.459158: step: 1768/531, loss: 4.7727189667057246e-05
2023-01-24 06:52:37.556496: step: 1772/531, loss: 0.0055036842823028564
2023-01-24 06:52:38.611878: step: 1776/531, loss: 0.011021219193935394
2023-01-24 06:52:39.679919: step: 1780/531, loss: 0.0022489370312541723
2023-01-24 06:52:40.730094: step: 1784/531, loss: 0.00528279785066843
2023-01-24 06:52:41.782232: step: 1788/531, loss: 0.006164574529975653
2023-01-24 06:52:42.848269: step: 1792/531, loss: 0.019493382424116135
2023-01-24 06:52:43.889719: step: 1796/531, loss: 0.0005644686170853674
2023-01-24 06:52:44.959731: step: 1800/531, loss: 0.0072881258092820644
2023-01-24 06:52:46.029233: step: 1804/531, loss: 0.004288215655833483
2023-01-24 06:52:47.095474: step: 1808/531, loss: 0.010092239826917648
2023-01-24 06:52:48.149710: step: 1812/531, loss: 0.004266197327524424
2023-01-24 06:52:49.205050: step: 1816/531, loss: 0.0014405458932742476
2023-01-24 06:52:50.264412: step: 1820/531, loss: 0.003679243614897132
2023-01-24 06:52:51.327456: step: 1824/531, loss: 0.015139496885240078
2023-01-24 06:52:52.387021: step: 1828/531, loss: 0.024759916588664055
2023-01-24 06:52:53.449553: step: 1832/531, loss: 0.021077243611216545
2023-01-24 06:52:54.499651: step: 1836/531, loss: 0.026106897741556168
2023-01-24 06:52:55.561207: step: 1840/531, loss: 0.05264068394899368
2023-01-24 06:52:56.612933: step: 1844/531, loss: 0.005715729668736458
2023-01-24 06:52:57.671983: step: 1848/531, loss: 0.0052014864049851894
2023-01-24 06:52:58.741089: step: 1852/531, loss: 0.00589185394346714
2023-01-24 06:52:59.800431: step: 1856/531, loss: 0.003483076114207506
2023-01-24 06:53:00.866807: step: 1860/531, loss: 0.0023939392995089293
2023-01-24 06:53:01.927133: step: 1864/531, loss: 0.008688930422067642
2023-01-24 06:53:02.974656: step: 1868/531, loss: 0.0013840004103258252
2023-01-24 06:53:04.036431: step: 1872/531, loss: 0.001034295535646379
2023-01-24 06:53:05.086534: step: 1876/531, loss: 0.011744841001927853
2023-01-24 06:53:06.150438: step: 1880/531, loss: 0.0059185572899878025
2023-01-24 06:53:07.218715: step: 1884/531, loss: 0.025036606937646866
2023-01-24 06:53:08.266475: step: 1888/531, loss: 0.007557482458651066
2023-01-24 06:53:09.320308: step: 1892/531, loss: 0.0047930465079844
2023-01-24 06:53:10.377170: step: 1896/531, loss: 0.00020706787472590804
2023-01-24 06:53:11.428064: step: 1900/531, loss: 0.0030501841101795435
2023-01-24 06:53:12.499996: step: 1904/531, loss: 0.004785385448485613
2023-01-24 06:53:13.574122: step: 1908/531, loss: 0.03510251268744469
2023-01-24 06:53:14.651094: step: 1912/531, loss: 0.061462949961423874
2023-01-24 06:53:15.717978: step: 1916/531, loss: 0.0007456626044586301
2023-01-24 06:53:16.782636: step: 1920/531, loss: 0.001428638701327145
2023-01-24 06:53:17.832386: step: 1924/531, loss: 0.0060381353832781315
2023-01-24 06:53:18.912837: step: 1928/531, loss: 0.0038770250976085663
2023-01-24 06:53:19.954432: step: 1932/531, loss: 0.004950044676661491
2023-01-24 06:53:21.008301: step: 1936/531, loss: 0.008088234812021255
2023-01-24 06:53:22.069492: step: 1940/531, loss: 0.00382617418654263
2023-01-24 06:53:23.136948: step: 1944/531, loss: 0.002881772117689252
2023-01-24 06:53:24.186609: step: 1948/531, loss: 0.01000647060573101
2023-01-24 06:53:25.240171: step: 1952/531, loss: 0.007367494981735945
2023-01-24 06:53:26.295819: step: 1956/531, loss: 0.005698645021766424
2023-01-24 06:53:27.348208: step: 1960/531, loss: 0.00498863123357296
2023-01-24 06:53:28.403141: step: 1964/531, loss: 0.00729562621563673
2023-01-24 06:53:29.463261: step: 1968/531, loss: 0.004644978325814009
2023-01-24 06:53:30.524633: step: 1972/531, loss: 0.0009126242948696017
2023-01-24 06:53:31.592492: step: 1976/531, loss: 0.04344611242413521
2023-01-24 06:53:32.648326: step: 1980/531, loss: 0.008268143981695175
2023-01-24 06:53:33.687030: step: 1984/531, loss: 0.004788004327565432
2023-01-24 06:53:34.747044: step: 1988/531, loss: 0.0017148415790870786
2023-01-24 06:53:35.791089: step: 1992/531, loss: 0.00936845038086176
2023-01-24 06:53:36.846449: step: 1996/531, loss: 0.008106195367872715
2023-01-24 06:53:37.896337: step: 2000/531, loss: 0.0025294064544141293
2023-01-24 06:53:38.966764: step: 2004/531, loss: 0.005026867613196373
2023-01-24 06:53:40.026254: step: 2008/531, loss: 0.0017298514721915126
2023-01-24 06:53:41.083979: step: 2012/531, loss: 0.008364005014300346
2023-01-24 06:53:42.164368: step: 2016/531, loss: 0.002123839920386672
2023-01-24 06:53:43.218425: step: 2020/531, loss: 0.015202515758574009
2023-01-24 06:53:44.269863: step: 2024/531, loss: 1.3222117559053004e-05
2023-01-24 06:53:45.334145: step: 2028/531, loss: 0.004475335590541363
2023-01-24 06:53:46.398852: step: 2032/531, loss: 0.00017878945800475776
2023-01-24 06:53:47.460319: step: 2036/531, loss: 0.027553226798772812
2023-01-24 06:53:48.513468: step: 2040/531, loss: 0.002366541652008891
2023-01-24 06:53:49.562949: step: 2044/531, loss: 0.01303250901401043
2023-01-24 06:53:50.608856: step: 2048/531, loss: 0.004782837349921465
2023-01-24 06:53:51.667329: step: 2052/531, loss: 0.03559749200940132
2023-01-24 06:53:52.730253: step: 2056/531, loss: 0.02289102040231228
2023-01-24 06:53:53.794241: step: 2060/531, loss: 0.016103940084576607
2023-01-24 06:53:54.846011: step: 2064/531, loss: 0.005509399808943272
2023-01-24 06:53:55.908899: step: 2068/531, loss: 0.005110845435410738
2023-01-24 06:53:56.961168: step: 2072/531, loss: 0.0029792129062116146
2023-01-24 06:53:58.002115: step: 2076/531, loss: 0.0003720921231433749
2023-01-24 06:53:59.059035: step: 2080/531, loss: 0.020529035478830338
2023-01-24 06:54:00.123584: step: 2084/531, loss: 0.002365376567468047
2023-01-24 06:54:01.182439: step: 2088/531, loss: 0.007025447674095631
2023-01-24 06:54:02.230255: step: 2092/531, loss: 0.003251168876886368
2023-01-24 06:54:03.277112: step: 2096/531, loss: 0.0023603267036378384
2023-01-24 06:54:04.354792: step: 2100/531, loss: 0.007606369908899069
2023-01-24 06:54:05.393707: step: 2104/531, loss: 0.00882585160434246
2023-01-24 06:54:06.446336: step: 2108/531, loss: 0.0031348522752523422
2023-01-24 06:54:07.504558: step: 2112/531, loss: 0.0017807622207328677
2023-01-24 06:54:08.558198: step: 2116/531, loss: 0.030992040410637856
2023-01-24 06:54:09.623068: step: 2120/531, loss: 0.008543238043785095
2023-01-24 06:54:10.665853: step: 2124/531, loss: 0.0154934236779809
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3921914346470581, 'r': 0.31851600384998263, 'f1': 0.35153494037474525}, 'combined': 0.259025745539286, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3882899555026102, 'r': 0.27484906678949417, 'f1': 0.32186654178410673}, 'combined': 0.20154260093023507, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3780164324072552, 'r': 0.3399995995465635, 'f1': 0.3580015763457322}, 'combined': 0.26379063520211843, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.38952398834001967, 'r': 0.2866109778949108, 'f1': 0.3302354020628115}, 'combined': 0.204652925222024, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3653505161780254, 'r': 0.32652769092950656, 'f1': 0.34484988601172334}, 'combined': 0.25409991600863824, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41242743762123607, 'r': 0.2878438563740638, 'f1': 0.33905346438538153}, 'combined': 0.2249166545922828, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3695652173913043, 'r': 0.3695652173913043, 'f1': 0.36956521739130427}, 'combined': 0.18478260869565213, 'stategy': 1, 'epoch': 7}
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, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36442367530366865, 'r': 0.329848374041461, 'f1': 0.34627508589611544}, 'combined': 0.2551500632918745, 'stategy': 1, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4102575605166279, 'r': 0.2855895732361016, 'f1': 0.33675580725022514}, 'combined': 0.22339246619569392, 'stategy': 1, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 5}
******************************
Epoch: 8
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 06:56:36.150036: step: 4/531, loss: 0.009521507658064365
2023-01-24 06:56:37.225906: step: 8/531, loss: 0.0045917765237390995
2023-01-24 06:56:38.297170: step: 12/531, loss: 0.0001824085775297135
2023-01-24 06:56:39.343454: step: 16/531, loss: 0.001161676598712802
2023-01-24 06:56:40.399131: step: 20/531, loss: 0.00173962174449116
2023-01-24 06:56:41.454183: step: 24/531, loss: 0.004030345939099789
2023-01-24 06:56:42.496561: step: 28/531, loss: 0.005910784471780062
2023-01-24 06:56:43.555417: step: 32/531, loss: 0.0022268928587436676
2023-01-24 06:56:44.625969: step: 36/531, loss: 0.001641519833356142
2023-01-24 06:56:45.689835: step: 40/531, loss: 0.005174714606255293
2023-01-24 06:56:46.730855: step: 44/531, loss: 0.00026218785205855966
2023-01-24 06:56:47.791464: step: 48/531, loss: 0.005118938162922859
2023-01-24 06:56:48.853883: step: 52/531, loss: 0.0077238744124770164
2023-01-24 06:56:49.900970: step: 56/531, loss: 0.0056335655972361565
2023-01-24 06:56:50.954752: step: 60/531, loss: 0.01059556845575571
2023-01-24 06:56:52.025535: step: 64/531, loss: 0.01633615233004093
2023-01-24 06:56:53.069581: step: 68/531, loss: 0.00037927928497083485
2023-01-24 06:56:54.117096: step: 72/531, loss: 0.011826412752270699
2023-01-24 06:56:55.172633: step: 76/531, loss: 0.0026891108136624098
2023-01-24 06:56:56.226247: step: 80/531, loss: 0.02325444109737873
2023-01-24 06:56:57.273117: step: 84/531, loss: 0.0018955161795020103
2023-01-24 06:56:58.327428: step: 88/531, loss: 0.004414505325257778
2023-01-24 06:56:59.375724: step: 92/531, loss: 0.028098415583372116
2023-01-24 06:57:00.435808: step: 96/531, loss: 0.016535473987460136
2023-01-24 06:57:01.506097: step: 100/531, loss: 0.016983775421977043
2023-01-24 06:57:02.555452: step: 104/531, loss: 0.005316626280546188
2023-01-24 06:57:03.619467: step: 108/531, loss: 0.008518573828041553
2023-01-24 06:57:04.697723: step: 112/531, loss: 0.0006991970585659146
2023-01-24 06:57:05.762872: step: 116/531, loss: 0.012890145182609558
2023-01-24 06:57:06.823513: step: 120/531, loss: 0.008623485453426838
2023-01-24 06:57:07.881050: step: 124/531, loss: 0.002367323264479637
2023-01-24 06:57:08.925965: step: 128/531, loss: 0.00504923053085804
2023-01-24 06:57:10.004884: step: 132/531, loss: 0.003036619396880269
2023-01-24 06:57:11.052691: step: 136/531, loss: 0.00011985273158643395
2023-01-24 06:57:12.113500: step: 140/531, loss: 0.02278294786810875
2023-01-24 06:57:13.165076: step: 144/531, loss: 0.0015168596291914582
2023-01-24 06:57:14.223906: step: 148/531, loss: 0.004891501739621162
2023-01-24 06:57:15.267848: step: 152/531, loss: 0.0023071442265063524
2023-01-24 06:57:16.305237: step: 156/531, loss: 0.0030005318112671375
2023-01-24 06:57:17.362453: step: 160/531, loss: 0.0012034763349220157
2023-01-24 06:57:18.432037: step: 164/531, loss: 0.0049870070070028305
2023-01-24 06:57:19.496140: step: 168/531, loss: 0.018340349197387695
2023-01-24 06:57:20.567516: step: 172/531, loss: 0.009047003462910652
2023-01-24 06:57:21.609974: step: 176/531, loss: 0.006398437079042196
2023-01-24 06:57:22.663824: step: 180/531, loss: 0.017008837312459946
2023-01-24 06:57:23.716316: step: 184/531, loss: 0.002017815364524722
2023-01-24 06:57:24.766037: step: 188/531, loss: 0.004317536484450102
2023-01-24 06:57:25.838541: step: 192/531, loss: 0.0027937027625739574
2023-01-24 06:57:26.892689: step: 196/531, loss: 0.011573059484362602
2023-01-24 06:57:27.960152: step: 200/531, loss: 0.003688855329528451
2023-01-24 06:57:29.029520: step: 204/531, loss: 0.008166870102286339
2023-01-24 06:57:30.088747: step: 208/531, loss: 0.0034504185896366835
2023-01-24 06:57:31.149359: step: 212/531, loss: 0.009649948216974735
2023-01-24 06:57:32.202160: step: 216/531, loss: 0.003355876076966524
2023-01-24 06:57:33.300796: step: 220/531, loss: 0.0016142718959599733
2023-01-24 06:57:34.386915: step: 224/531, loss: 0.006700103171169758
2023-01-24 06:57:35.434187: step: 228/531, loss: 0.0058255912736058235
2023-01-24 06:57:36.478409: step: 232/531, loss: 0.004777774214744568
2023-01-24 06:57:37.543032: step: 236/531, loss: 0.003245204919949174
2023-01-24 06:57:38.610060: step: 240/531, loss: 0.0020778810139745474
2023-01-24 06:57:39.658328: step: 244/531, loss: 0.005692709237337112
2023-01-24 06:57:40.732763: step: 248/531, loss: 0.005422898568212986
2023-01-24 06:57:41.792369: step: 252/531, loss: 0.004670081194490194
2023-01-24 06:57:42.842705: step: 256/531, loss: 0.006144367158412933
2023-01-24 06:57:43.894280: step: 260/531, loss: 0.005465567111968994
2023-01-24 06:57:44.961992: step: 264/531, loss: 0.010556402616202831
2023-01-24 06:57:46.029962: step: 268/531, loss: 0.007777459919452667
2023-01-24 06:57:47.074262: step: 272/531, loss: 0.004604372661560774
2023-01-24 06:57:48.131152: step: 276/531, loss: 0.000592091353610158
2023-01-24 06:57:49.232325: step: 280/531, loss: 0.011012891307473183
2023-01-24 06:57:50.283468: step: 284/531, loss: 0.00016225418949034065
2023-01-24 06:57:51.329111: step: 288/531, loss: 0.006222032476216555
2023-01-24 06:57:52.387081: step: 292/531, loss: 0.0032932369504123926
2023-01-24 06:57:53.440329: step: 296/531, loss: 0.004250827711075544
2023-01-24 06:57:54.519607: step: 300/531, loss: 0.0007221480482257903
2023-01-24 06:57:55.577641: step: 304/531, loss: 0.003463632892817259
2023-01-24 06:57:56.636789: step: 308/531, loss: 0.00922374613583088
2023-01-24 06:57:57.681385: step: 312/531, loss: 0.0022472532000392675
2023-01-24 06:57:58.783369: step: 316/531, loss: 0.0005551144131459296
2023-01-24 06:57:59.827598: step: 320/531, loss: 0.0010310213547199965
2023-01-24 06:58:00.897049: step: 324/531, loss: 0.005658258683979511
2023-01-24 06:58:01.944179: step: 328/531, loss: 0.0003289622545707971
2023-01-24 06:58:02.991183: step: 332/531, loss: 0.00023402618535328656
2023-01-24 06:58:04.029666: step: 336/531, loss: 0.0010350487427785993
2023-01-24 06:58:05.100662: step: 340/531, loss: 0.010129990056157112
2023-01-24 06:58:06.152143: step: 344/531, loss: 0.0036504019517451525
2023-01-24 06:58:07.211533: step: 348/531, loss: 0.0005748554249294102
2023-01-24 06:58:08.268213: step: 352/531, loss: 0.009512398391962051
2023-01-24 06:58:09.329156: step: 356/531, loss: 0.0035774048883467913
2023-01-24 06:58:10.395485: step: 360/531, loss: 0.003359885886311531
2023-01-24 06:58:11.449619: step: 364/531, loss: 0.023506442084908485
2023-01-24 06:58:12.503284: step: 368/531, loss: 0.031302519142627716
2023-01-24 06:58:13.570606: step: 372/531, loss: 0.024131527170538902
2023-01-24 06:58:14.626946: step: 376/531, loss: 0.0021976816933602095
2023-01-24 06:58:15.695693: step: 380/531, loss: 0.01051371544599533
2023-01-24 06:58:16.760981: step: 384/531, loss: 0.004568392410874367
2023-01-24 06:58:17.814690: step: 388/531, loss: 0.0056373607367277145
2023-01-24 06:58:18.873172: step: 392/531, loss: 0.0024717007763683796
2023-01-24 06:58:19.943042: step: 396/531, loss: 0.004057064652442932
2023-01-24 06:58:21.006469: step: 400/531, loss: 0.0025357746053487062
2023-01-24 06:58:22.066774: step: 404/531, loss: 0.0021160433534532785
2023-01-24 06:58:23.133424: step: 408/531, loss: 0.0037641029339283705
2023-01-24 06:58:24.204962: step: 412/531, loss: 0.000673118163831532
2023-01-24 06:58:25.262772: step: 416/531, loss: 0.0012082151370123029
2023-01-24 06:58:26.323068: step: 420/531, loss: 0.01828766241669655
2023-01-24 06:58:27.391989: step: 424/531, loss: 0.018649084493517876
2023-01-24 06:58:28.462437: step: 428/531, loss: 0.005770507734268904
2023-01-24 06:58:29.528392: step: 432/531, loss: 0.003924884833395481
2023-01-24 06:58:30.582822: step: 436/531, loss: 0.012615293264389038
2023-01-24 06:58:31.658240: step: 440/531, loss: 0.001242022030055523
2023-01-24 06:58:32.707858: step: 444/531, loss: 0.004470647778362036
2023-01-24 06:58:33.776025: step: 448/531, loss: 0.012171771377325058
2023-01-24 06:58:34.848368: step: 452/531, loss: 0.013862748630344868
2023-01-24 06:58:35.891445: step: 456/531, loss: 0.004594526719301939
2023-01-24 06:58:36.959412: step: 460/531, loss: 0.009186458773911
2023-01-24 06:58:38.023725: step: 464/531, loss: 0.003315070876851678
2023-01-24 06:58:39.090106: step: 468/531, loss: 0.00016763914027251303
2023-01-24 06:58:40.146237: step: 472/531, loss: 0.00032415706664323807
2023-01-24 06:58:41.207875: step: 476/531, loss: 0.017326390370726585
2023-01-24 06:58:42.274711: step: 480/531, loss: 0.000792271108366549
2023-01-24 06:58:43.328496: step: 484/531, loss: 0.0032066642306745052
2023-01-24 06:58:44.400221: step: 488/531, loss: 0.021497756242752075
2023-01-24 06:58:45.445310: step: 492/531, loss: 0.01887635327875614
2023-01-24 06:58:46.518294: step: 496/531, loss: 0.0015345726860687137
2023-01-24 06:58:47.582561: step: 500/531, loss: 0.005101568531244993
2023-01-24 06:58:48.630924: step: 504/531, loss: 0.0013782402966171503
2023-01-24 06:58:49.690886: step: 508/531, loss: 0.0014437205391004682
2023-01-24 06:58:50.757165: step: 512/531, loss: 0.005455211736261845
2023-01-24 06:58:51.801894: step: 516/531, loss: 7.479720807168633e-05
2023-01-24 06:58:52.872108: step: 520/531, loss: 0.025287700816988945
2023-01-24 06:58:53.926260: step: 524/531, loss: 0.006370967254042625
2023-01-24 06:58:54.988285: step: 528/531, loss: 0.00978098250925541
2023-01-24 06:58:56.066090: step: 532/531, loss: 0.005064946133643389
2023-01-24 06:58:57.145531: step: 536/531, loss: 0.023861998692154884
2023-01-24 06:58:58.215672: step: 540/531, loss: 0.002950523514300585
2023-01-24 06:58:59.279137: step: 544/531, loss: 0.0010207381565123796
2023-01-24 06:59:00.342891: step: 548/531, loss: 0.002542046597227454
2023-01-24 06:59:01.396470: step: 552/531, loss: 0.002155070658773184
2023-01-24 06:59:02.476969: step: 556/531, loss: 0.005741284228861332
2023-01-24 06:59:03.530197: step: 560/531, loss: 0.0009831854840740561
2023-01-24 06:59:04.597108: step: 564/531, loss: 0.0025570113211870193
2023-01-24 06:59:05.656717: step: 568/531, loss: 0.016676031053066254
2023-01-24 06:59:06.716674: step: 572/531, loss: 3.8245536416070536e-05
2023-01-24 06:59:07.770773: step: 576/531, loss: 0.005851565394550562
2023-01-24 06:59:08.841046: step: 580/531, loss: 0.0
2023-01-24 06:59:09.901252: step: 584/531, loss: 0.0017882848624140024
2023-01-24 06:59:10.982343: step: 588/531, loss: 0.002803139155730605
2023-01-24 06:59:12.040495: step: 592/531, loss: 0.004985233768820763
2023-01-24 06:59:13.099128: step: 596/531, loss: 0.00047307752538472414
2023-01-24 06:59:14.146392: step: 600/531, loss: 0.0016902529168874025
2023-01-24 06:59:15.209378: step: 604/531, loss: 0.004461311735212803
2023-01-24 06:59:16.276027: step: 608/531, loss: 0.0012405706802383065
2023-01-24 06:59:17.331064: step: 612/531, loss: 0.0016074622981250286
2023-01-24 06:59:18.382337: step: 616/531, loss: 0.0021988446824252605
2023-01-24 06:59:19.445175: step: 620/531, loss: 0.005559419747442007
2023-01-24 06:59:20.507272: step: 624/531, loss: 0.040141861885786057
2023-01-24 06:59:21.559372: step: 628/531, loss: 0.004170118365436792
2023-01-24 06:59:22.605939: step: 632/531, loss: 0.015231350436806679
2023-01-24 06:59:23.672436: step: 636/531, loss: 0.02916671894490719
2023-01-24 06:59:24.730460: step: 640/531, loss: 0.0022286614403128624
2023-01-24 06:59:25.781617: step: 644/531, loss: 0.0061494517140090466
2023-01-24 06:59:26.849970: step: 648/531, loss: 0.025374583899974823
2023-01-24 06:59:27.938546: step: 652/531, loss: 0.020446576178073883
2023-01-24 06:59:28.995761: step: 656/531, loss: 0.002724332269281149
2023-01-24 06:59:30.074492: step: 660/531, loss: 0.012123017571866512
2023-01-24 06:59:31.154662: step: 664/531, loss: 0.0036326858680695295
2023-01-24 06:59:32.220454: step: 668/531, loss: 0.0161232091486454
2023-01-24 06:59:33.275982: step: 672/531, loss: 0.0040760040283203125
2023-01-24 06:59:34.348350: step: 676/531, loss: 0.01164824515581131
2023-01-24 06:59:35.409965: step: 680/531, loss: 0.002962257247418165
2023-01-24 06:59:36.485815: step: 684/531, loss: 0.00103163777384907
2023-01-24 06:59:37.540614: step: 688/531, loss: 0.01721273548901081
2023-01-24 06:59:38.611890: step: 692/531, loss: 0.0025461604818701744
2023-01-24 06:59:39.686978: step: 696/531, loss: 0.0033750180155038834
2023-01-24 06:59:40.748458: step: 700/531, loss: 0.02103145234286785
2023-01-24 06:59:41.805495: step: 704/531, loss: 0.03886880353093147
2023-01-24 06:59:42.867234: step: 708/531, loss: 0.01326089445501566
2023-01-24 06:59:43.926236: step: 712/531, loss: 0.009282470680773258
2023-01-24 06:59:44.986420: step: 716/531, loss: 0.0036380321253091097
2023-01-24 06:59:46.040803: step: 720/531, loss: 0.002317324047908187
2023-01-24 06:59:47.121507: step: 724/531, loss: 0.005068523343652487
2023-01-24 06:59:48.201669: step: 728/531, loss: 0.0076700844801962376
2023-01-24 06:59:49.260575: step: 732/531, loss: 0.0019287178292870522
2023-01-24 06:59:50.335482: step: 736/531, loss: 0.011293146759271622
2023-01-24 06:59:51.411389: step: 740/531, loss: 0.001963953720405698
2023-01-24 06:59:52.481693: step: 744/531, loss: 0.006708445493131876
2023-01-24 06:59:53.539831: step: 748/531, loss: 0.014490853995084763
2023-01-24 06:59:54.598272: step: 752/531, loss: 0.002180551178753376
2023-01-24 06:59:55.665289: step: 756/531, loss: 0.0038238507695496082
2023-01-24 06:59:56.717190: step: 760/531, loss: 0.006020710337907076
2023-01-24 06:59:57.772124: step: 764/531, loss: 0.006316723767668009
2023-01-24 06:59:58.841381: step: 768/531, loss: 0.0029893338214606047
2023-01-24 06:59:59.891145: step: 772/531, loss: 0.0025441646575927734
2023-01-24 07:00:00.958665: step: 776/531, loss: 0.0030968119390308857
2023-01-24 07:00:02.023358: step: 780/531, loss: 0.00013579557707998902
2023-01-24 07:00:03.090749: step: 784/531, loss: 0.00590282678604126
2023-01-24 07:00:04.136127: step: 788/531, loss: 0.001438887557014823
2023-01-24 07:00:05.210351: step: 792/531, loss: 0.011630845256149769
2023-01-24 07:00:06.278558: step: 796/531, loss: 0.0077319061383605
2023-01-24 07:00:07.351384: step: 800/531, loss: 0.0018211868591606617
2023-01-24 07:00:08.408281: step: 804/531, loss: 0.008590525016188622
2023-01-24 07:00:09.483615: step: 808/531, loss: 0.006511078681796789
2023-01-24 07:00:10.553108: step: 812/531, loss: 0.004509621299803257
2023-01-24 07:00:11.618925: step: 816/531, loss: 0.01483891811221838
2023-01-24 07:00:12.692318: step: 820/531, loss: 0.010829690843820572
2023-01-24 07:00:13.751228: step: 824/531, loss: 0.016312792897224426
2023-01-24 07:00:14.827173: step: 828/531, loss: 0.03890813887119293
2023-01-24 07:00:15.888890: step: 832/531, loss: 0.009767335839569569
2023-01-24 07:00:16.947605: step: 836/531, loss: 0.00046701834071427584
2023-01-24 07:00:18.017292: step: 840/531, loss: 0.0004780926101375371
2023-01-24 07:00:19.087917: step: 844/531, loss: 0.0051103741861879826
2023-01-24 07:00:20.151916: step: 848/531, loss: 0.02015470713376999
2023-01-24 07:00:21.217797: step: 852/531, loss: 0.007281284313648939
2023-01-24 07:00:22.299176: step: 856/531, loss: 0.0012055073166266084
2023-01-24 07:00:23.358319: step: 860/531, loss: 0.008240344934165478
2023-01-24 07:00:24.432040: step: 864/531, loss: 0.0038327702786773443
2023-01-24 07:00:25.512837: step: 868/531, loss: 0.006365139968693256
2023-01-24 07:00:26.589173: step: 872/531, loss: 0.0024804798886179924
2023-01-24 07:00:27.647585: step: 876/531, loss: 0.025120964273810387
2023-01-24 07:00:28.707538: step: 880/531, loss: 0.0003910895611625165
2023-01-24 07:00:29.778802: step: 884/531, loss: 0.0007088647107593715
2023-01-24 07:00:30.828848: step: 888/531, loss: 0.002923545427620411
2023-01-24 07:00:31.886775: step: 892/531, loss: 0.010894962586462498
2023-01-24 07:00:32.972046: step: 896/531, loss: 0.004530869424343109
2023-01-24 07:00:34.024627: step: 900/531, loss: 0.002915431745350361
2023-01-24 07:00:35.119394: step: 904/531, loss: 0.008574807085096836
2023-01-24 07:00:36.207080: step: 908/531, loss: 0.018006768077611923
2023-01-24 07:00:37.280387: step: 912/531, loss: 0.00028963852673768997
2023-01-24 07:00:38.337743: step: 916/531, loss: 0.0025813868269324303
2023-01-24 07:00:39.409330: step: 920/531, loss: 2.9397575417533517e-05
2023-01-24 07:00:40.466013: step: 924/531, loss: 0.0037239028606563807
2023-01-24 07:00:41.543970: step: 928/531, loss: 0.004326937720179558
2023-01-24 07:00:42.626175: step: 932/531, loss: 0.01605810597538948
2023-01-24 07:00:43.680939: step: 936/531, loss: 0.0006219294155016541
2023-01-24 07:00:44.747155: step: 940/531, loss: 0.000443142227595672
2023-01-24 07:00:45.814136: step: 944/531, loss: 0.007307771127671003
2023-01-24 07:00:46.873880: step: 948/531, loss: 0.0455024316906929
2023-01-24 07:00:47.942305: step: 952/531, loss: 0.008575189858675003
2023-01-24 07:00:49.003827: step: 956/531, loss: 0.002232529688626528
2023-01-24 07:00:50.066195: step: 960/531, loss: 0.002812477992847562
2023-01-24 07:00:51.124572: step: 964/531, loss: 0.004008966963738203
2023-01-24 07:00:52.201074: step: 968/531, loss: 0.0011554103111848235
2023-01-24 07:00:53.290411: step: 972/531, loss: 0.005167889408767223
2023-01-24 07:00:54.356518: step: 976/531, loss: 0.0034117435570806265
2023-01-24 07:00:55.428309: step: 980/531, loss: 0.00020782227511517704
2023-01-24 07:00:56.497505: step: 984/531, loss: 0.0015388152096420527
2023-01-24 07:00:57.573755: step: 988/531, loss: 0.00014759301848243922
2023-01-24 07:00:58.654041: step: 992/531, loss: 0.006717701908200979
2023-01-24 07:00:59.716368: step: 996/531, loss: 0.0024136644788086414
2023-01-24 07:01:00.773526: step: 1000/531, loss: 0.003548719920217991
2023-01-24 07:01:01.836886: step: 1004/531, loss: 0.0
2023-01-24 07:01:02.893334: step: 1008/531, loss: 0.0002607418573461473
2023-01-24 07:01:03.973464: step: 1012/531, loss: 0.004946514964103699
2023-01-24 07:01:05.052127: step: 1016/531, loss: 0.02123146876692772
2023-01-24 07:01:06.118628: step: 1020/531, loss: 0.008447559550404549
2023-01-24 07:01:07.184422: step: 1024/531, loss: 0.0013551246374845505
2023-01-24 07:01:08.235819: step: 1028/531, loss: 0.00220544938929379
2023-01-24 07:01:09.289797: step: 1032/531, loss: 0.012969838455319405
2023-01-24 07:01:10.357599: step: 1036/531, loss: 0.00014873032341711223
2023-01-24 07:01:11.405583: step: 1040/531, loss: 0.0033487624023109674
2023-01-24 07:01:12.473292: step: 1044/531, loss: 0.002069843700155616
2023-01-24 07:01:13.530642: step: 1048/531, loss: 0.01372519787400961
2023-01-24 07:01:14.592601: step: 1052/531, loss: 0.00833092164248228
2023-01-24 07:01:15.659767: step: 1056/531, loss: 0.0053888894617557526
2023-01-24 07:01:16.711063: step: 1060/531, loss: 0.0023009374272078276
2023-01-24 07:01:17.748221: step: 1064/531, loss: 0.002385929226875305
2023-01-24 07:01:18.798806: step: 1068/531, loss: 0.008888494223356247
2023-01-24 07:01:19.870723: step: 1072/531, loss: 0.007335087284445763
2023-01-24 07:01:20.931924: step: 1076/531, loss: 0.0067205182276666164
2023-01-24 07:01:21.990010: step: 1080/531, loss: 0.0003820423735305667
2023-01-24 07:01:23.065861: step: 1084/531, loss: 0.0018620449118316174
2023-01-24 07:01:24.110504: step: 1088/531, loss: 0.007995960302650928
2023-01-24 07:01:25.188204: step: 1092/531, loss: 0.004356453660875559
2023-01-24 07:01:26.235608: step: 1096/531, loss: 0.0026766823139041662
2023-01-24 07:01:27.308241: step: 1100/531, loss: 0.006368543487042189
2023-01-24 07:01:28.375554: step: 1104/531, loss: 0.010825267061591148
2023-01-24 07:01:29.446139: step: 1108/531, loss: 0.03677953779697418
2023-01-24 07:01:30.528088: step: 1112/531, loss: 0.001485364744439721
2023-01-24 07:01:31.595243: step: 1116/531, loss: 0.0058395215310156345
2023-01-24 07:01:32.659290: step: 1120/531, loss: 0.005955967120826244
2023-01-24 07:01:33.743143: step: 1124/531, loss: 0.001750392373651266
2023-01-24 07:01:34.804511: step: 1128/531, loss: 0.006681247614324093
2023-01-24 07:01:35.862840: step: 1132/531, loss: 0.017130382359027863
2023-01-24 07:01:36.928395: step: 1136/531, loss: 0.013268603011965752
2023-01-24 07:01:38.000867: step: 1140/531, loss: 0.004405970685184002
2023-01-24 07:01:39.052126: step: 1144/531, loss: 0.0038946911226958036
2023-01-24 07:01:40.121672: step: 1148/531, loss: 0.0018913538660854101
2023-01-24 07:01:41.181804: step: 1152/531, loss: 0.0033937504049390554
2023-01-24 07:01:42.240520: step: 1156/531, loss: 0.012840493582189083
2023-01-24 07:01:43.296002: step: 1160/531, loss: 0.0030658477917313576
2023-01-24 07:01:44.359338: step: 1164/531, loss: 0.0026989688631147146
2023-01-24 07:01:45.412374: step: 1168/531, loss: 0.00987061858177185
2023-01-24 07:01:46.477462: step: 1172/531, loss: 0.025835705921053886
2023-01-24 07:01:47.542084: step: 1176/531, loss: 0.009692615829408169
2023-01-24 07:01:48.609459: step: 1180/531, loss: 0.007611141540110111
2023-01-24 07:01:49.668742: step: 1184/531, loss: 0.0038731752429157495
2023-01-24 07:01:50.724032: step: 1188/531, loss: 0.01868722401559353
2023-01-24 07:01:51.784583: step: 1192/531, loss: 0.001892442349344492
2023-01-24 07:01:52.840364: step: 1196/531, loss: 0.0034807517658919096
2023-01-24 07:01:53.918833: step: 1200/531, loss: 0.003272327361628413
2023-01-24 07:01:54.978826: step: 1204/531, loss: 0.003184059401974082
2023-01-24 07:01:56.038210: step: 1208/531, loss: 0.003688983153551817
2023-01-24 07:01:57.083262: step: 1212/531, loss: 0.0048958249390125275
2023-01-24 07:01:58.150013: step: 1216/531, loss: 0.0030868016183376312
2023-01-24 07:01:59.252376: step: 1220/531, loss: 0.002337475074455142
2023-01-24 07:02:00.317239: step: 1224/531, loss: 0.0032325468491762877
2023-01-24 07:02:01.383611: step: 1228/531, loss: 0.014581906609237194
2023-01-24 07:02:02.438975: step: 1232/531, loss: 0.0040698787197470665
2023-01-24 07:02:03.482093: step: 1236/531, loss: 0.00026136069209314883
2023-01-24 07:02:04.543577: step: 1240/531, loss: 0.005507575813680887
2023-01-24 07:02:05.614845: step: 1244/531, loss: 0.0006998664466664195
2023-01-24 07:02:06.673399: step: 1248/531, loss: 0.0016541146906092763
2023-01-24 07:02:07.728425: step: 1252/531, loss: 0.005082534160465002
2023-01-24 07:02:08.808794: step: 1256/531, loss: 0.019193334504961967
2023-01-24 07:02:09.858388: step: 1260/531, loss: 0.0267738439142704
2023-01-24 07:02:10.920032: step: 1264/531, loss: 0.011469540186226368
2023-01-24 07:02:11.979598: step: 1268/531, loss: 0.0029621445573866367
2023-01-24 07:02:13.051478: step: 1272/531, loss: 0.011390729807317257
2023-01-24 07:02:14.107417: step: 1276/531, loss: 0.0069556450471282005
2023-01-24 07:02:15.146024: step: 1280/531, loss: 0.004577385261654854
2023-01-24 07:02:16.205909: step: 1284/531, loss: 0.007107224781066179
2023-01-24 07:02:17.256401: step: 1288/531, loss: 0.01946289837360382
2023-01-24 07:02:18.331900: step: 1292/531, loss: 0.03458670526742935
2023-01-24 07:02:19.387874: step: 1296/531, loss: 0.007475607097148895
2023-01-24 07:02:20.438516: step: 1300/531, loss: 0.005438089836388826
2023-01-24 07:02:21.499586: step: 1304/531, loss: 0.006899349391460419
2023-01-24 07:02:22.558178: step: 1308/531, loss: 0.00033680512569844723
2023-01-24 07:02:23.625539: step: 1312/531, loss: 0.0024557586293667555
2023-01-24 07:02:24.701052: step: 1316/531, loss: 0.011073829606175423
2023-01-24 07:02:25.766854: step: 1320/531, loss: 0.0035494016483426094
2023-01-24 07:02:26.857397: step: 1324/531, loss: 0.021071037277579308
2023-01-24 07:02:27.918679: step: 1328/531, loss: 0.0029742741025984287
2023-01-24 07:02:28.975535: step: 1332/531, loss: 0.009426775388419628
2023-01-24 07:02:30.041618: step: 1336/531, loss: 0.003817416960373521
2023-01-24 07:02:31.106286: step: 1340/531, loss: 0.015146479941904545
2023-01-24 07:02:32.149417: step: 1344/531, loss: 0.011023357510566711
2023-01-24 07:02:33.204939: step: 1348/531, loss: 0.007813742384314537
2023-01-24 07:02:34.266405: step: 1352/531, loss: 0.021830998361110687
2023-01-24 07:02:35.320930: step: 1356/531, loss: 0.003205236978828907
2023-01-24 07:02:36.373930: step: 1360/531, loss: 0.002000129083171487
2023-01-24 07:02:37.430228: step: 1364/531, loss: 0.014800283126533031
2023-01-24 07:02:38.485455: step: 1368/531, loss: 0.0016528251580893993
2023-01-24 07:02:39.540763: step: 1372/531, loss: 0.001199369435198605
2023-01-24 07:02:40.633157: step: 1376/531, loss: 0.005130136851221323
2023-01-24 07:02:41.694775: step: 1380/531, loss: 0.005333214066922665
2023-01-24 07:02:42.749177: step: 1384/531, loss: 0.005962173920124769
2023-01-24 07:02:43.790405: step: 1388/531, loss: 0.0022245629224926233
2023-01-24 07:02:44.852490: step: 1392/531, loss: 0.0001227810571435839
2023-01-24 07:02:45.930428: step: 1396/531, loss: 0.00589818274602294
2023-01-24 07:02:46.995555: step: 1400/531, loss: 0.03538191691040993
2023-01-24 07:02:48.035469: step: 1404/531, loss: 0.00947636365890503
2023-01-24 07:02:49.109941: step: 1408/531, loss: 0.0036297296173870564
2023-01-24 07:02:50.193517: step: 1412/531, loss: 0.08291570097208023
2023-01-24 07:02:51.242984: step: 1416/531, loss: 0.0008545141899958253
2023-01-24 07:02:52.294108: step: 1420/531, loss: 7.632618093111887e-08
2023-01-24 07:02:53.350154: step: 1424/531, loss: 0.024561110883951187
2023-01-24 07:02:54.418667: step: 1428/531, loss: 0.013079265132546425
2023-01-24 07:02:55.463715: step: 1432/531, loss: 0.006209118757396936
2023-01-24 07:02:56.517817: step: 1436/531, loss: 0.01702086441218853
2023-01-24 07:02:57.575340: step: 1440/531, loss: 0.008531196974217892
2023-01-24 07:02:58.644258: step: 1444/531, loss: 0.008175347000360489
2023-01-24 07:02:59.704880: step: 1448/531, loss: 0.004992689471691847
2023-01-24 07:03:00.768118: step: 1452/531, loss: 0.008593486621975899
2023-01-24 07:03:01.821022: step: 1456/531, loss: 0.010351836681365967
2023-01-24 07:03:02.882552: step: 1460/531, loss: 0.006545158103108406
2023-01-24 07:03:03.928455: step: 1464/531, loss: 0.008038087747991085
2023-01-24 07:03:04.992540: step: 1468/531, loss: 0.008359107188880444
2023-01-24 07:03:06.043011: step: 1472/531, loss: 0.007803000044077635
2023-01-24 07:03:07.117661: step: 1476/531, loss: 0.0004924036911688745
2023-01-24 07:03:08.162577: step: 1480/531, loss: 0.007833710871636868
2023-01-24 07:03:09.233313: step: 1484/531, loss: 0.007910453714430332
2023-01-24 07:03:10.299478: step: 1488/531, loss: 0.015578282997012138
2023-01-24 07:03:11.377105: step: 1492/531, loss: 0.008035898208618164
2023-01-24 07:03:12.442448: step: 1496/531, loss: 0.002181046176701784
2023-01-24 07:03:13.503292: step: 1500/531, loss: 0.015502078458666801
2023-01-24 07:03:14.545385: step: 1504/531, loss: 0.007511697243899107
2023-01-24 07:03:15.603647: step: 1508/531, loss: 0.008183242753148079
2023-01-24 07:03:16.678128: step: 1512/531, loss: 0.026776069775223732
2023-01-24 07:03:17.733943: step: 1516/531, loss: 0.0009291375172324479
2023-01-24 07:03:18.802077: step: 1520/531, loss: 0.0
2023-01-24 07:03:19.855280: step: 1524/531, loss: 0.0004272660880815238
2023-01-24 07:03:20.909333: step: 1528/531, loss: 0.007856117561459541
2023-01-24 07:03:21.962790: step: 1532/531, loss: 0.002330540679395199
2023-01-24 07:03:23.015606: step: 1536/531, loss: 0.0075758653692901134
2023-01-24 07:03:24.047215: step: 1540/531, loss: 0.00020464049885049462
2023-01-24 07:03:25.104140: step: 1544/531, loss: 0.00659991754218936
2023-01-24 07:03:26.153766: step: 1548/531, loss: 2.73139539785916e-05
2023-01-24 07:03:27.216320: step: 1552/531, loss: 0.022007448598742485
2023-01-24 07:03:28.280200: step: 1556/531, loss: 0.0026621902361512184
2023-01-24 07:03:29.341248: step: 1560/531, loss: 0.0071321697905659676
2023-01-24 07:03:30.395528: step: 1564/531, loss: 0.021041875705122948
2023-01-24 07:03:31.447442: step: 1568/531, loss: 0.005351006053388119
2023-01-24 07:03:32.509467: step: 1572/531, loss: 0.005273071583360434
2023-01-24 07:03:33.570439: step: 1576/531, loss: 0.009908037260174751
2023-01-24 07:03:34.623200: step: 1580/531, loss: 0.01015748456120491
2023-01-24 07:03:35.674747: step: 1584/531, loss: 0.0028091552667319775
2023-01-24 07:03:36.724336: step: 1588/531, loss: 0.00613460224121809
2023-01-24 07:03:37.776541: step: 1592/531, loss: 0.0069671026431024075
2023-01-24 07:03:38.845977: step: 1596/531, loss: 0.007132793311029673
2023-01-24 07:03:39.891297: step: 1600/531, loss: 0.006399608217179775
2023-01-24 07:03:40.951846: step: 1604/531, loss: 0.004066131543368101
2023-01-24 07:03:42.014543: step: 1608/531, loss: 0.010241586714982986
2023-01-24 07:03:43.076842: step: 1612/531, loss: 0.007992560043931007
2023-01-24 07:03:44.119555: step: 1616/531, loss: 0.005091615952551365
2023-01-24 07:03:45.165738: step: 1620/531, loss: 0.0009947161888703704
2023-01-24 07:03:46.237124: step: 1624/531, loss: 0.0016462111379951239
2023-01-24 07:03:47.293741: step: 1628/531, loss: 0.024003515020012856
2023-01-24 07:03:48.340735: step: 1632/531, loss: 0.027133911848068237
2023-01-24 07:03:49.389999: step: 1636/531, loss: 0.007679780479520559
2023-01-24 07:03:50.443668: step: 1640/531, loss: 0.013520422391593456
2023-01-24 07:03:51.489139: step: 1644/531, loss: 0.0014681483153253794
2023-01-24 07:03:52.550286: step: 1648/531, loss: 0.01458329614251852
2023-01-24 07:03:53.613909: step: 1652/531, loss: 0.007456892170011997
2023-01-24 07:03:54.676629: step: 1656/531, loss: 0.00390252354554832
2023-01-24 07:03:55.730493: step: 1660/531, loss: 0.002072854433208704
2023-01-24 07:03:56.792409: step: 1664/531, loss: 0.006439339369535446
2023-01-24 07:03:57.838431: step: 1668/531, loss: 0.0026333676651120186
2023-01-24 07:03:58.901514: step: 1672/531, loss: 0.006465183570981026
2023-01-24 07:03:59.992967: step: 1676/531, loss: 0.01602604240179062
2023-01-24 07:04:01.051237: step: 1680/531, loss: 0.003123921575024724
2023-01-24 07:04:02.105316: step: 1684/531, loss: 0.0013871487462893128
2023-01-24 07:04:03.172986: step: 1688/531, loss: 0.0002768167178146541
2023-01-24 07:04:04.214517: step: 1692/531, loss: 0.00234323856420815
2023-01-24 07:04:05.275843: step: 1696/531, loss: 0.00960514321923256
2023-01-24 07:04:06.329986: step: 1700/531, loss: 0.0038568656891584396
2023-01-24 07:04:07.380426: step: 1704/531, loss: 0.0007602032856084406
2023-01-24 07:04:08.446243: step: 1708/531, loss: 5.5687709391349927e-05
2023-01-24 07:04:09.509355: step: 1712/531, loss: 0.005803669802844524
2023-01-24 07:04:10.580656: step: 1716/531, loss: 0.005684552248567343
2023-01-24 07:04:11.646005: step: 1720/531, loss: 0.01094534620642662
2023-01-24 07:04:12.697692: step: 1724/531, loss: 0.012037607841193676
2023-01-24 07:04:13.752212: step: 1728/531, loss: 0.003143709385767579
2023-01-24 07:04:14.814254: step: 1732/531, loss: 0.014864440076053143
2023-01-24 07:04:15.887724: step: 1736/531, loss: 0.05536574870347977
2023-01-24 07:04:16.949795: step: 1740/531, loss: 0.021446529775857925
2023-01-24 07:04:18.003020: step: 1744/531, loss: 0.005113128572702408
2023-01-24 07:04:19.065374: step: 1748/531, loss: 0.00308169680647552
2023-01-24 07:04:20.120968: step: 1752/531, loss: 0.00468352809548378
2023-01-24 07:04:21.170455: step: 1756/531, loss: 0.007143042050302029
2023-01-24 07:04:22.221341: step: 1760/531, loss: 0.005902677774429321
2023-01-24 07:04:23.281597: step: 1764/531, loss: 0.0017894305055961013
2023-01-24 07:04:24.348171: step: 1768/531, loss: 0.008010032586753368
2023-01-24 07:04:25.407473: step: 1772/531, loss: 0.007526349276304245
2023-01-24 07:04:26.465169: step: 1776/531, loss: 0.016422927379608154
2023-01-24 07:04:27.508036: step: 1780/531, loss: 0.00418756902217865
2023-01-24 07:04:28.573874: step: 1784/531, loss: 2.3179160280051292e-07
2023-01-24 07:04:29.644718: step: 1788/531, loss: 0.005281936842948198
2023-01-24 07:04:30.708293: step: 1792/531, loss: 0.007767172995954752
2023-01-24 07:04:31.770829: step: 1796/531, loss: 0.0027408848982304335
2023-01-24 07:04:32.823682: step: 1800/531, loss: 0.005599344149231911
2023-01-24 07:04:33.887200: step: 1804/531, loss: 0.001434585195966065
2023-01-24 07:04:34.952811: step: 1808/531, loss: 0.0006198306800797582
2023-01-24 07:04:36.008899: step: 1812/531, loss: 0.0013011071132496
2023-01-24 07:04:37.060927: step: 1816/531, loss: 0.027643442153930664
2023-01-24 07:04:38.103930: step: 1820/531, loss: 0.00298634497448802
2023-01-24 07:04:39.164351: step: 1824/531, loss: 0.0025018230080604553
2023-01-24 07:04:40.243108: step: 1828/531, loss: 0.006105093751102686
2023-01-24 07:04:41.301208: step: 1832/531, loss: 0.0026465593837201595
2023-01-24 07:04:42.399448: step: 1836/531, loss: 0.005341792479157448
2023-01-24 07:04:43.472313: step: 1840/531, loss: 0.003560730954632163
2023-01-24 07:04:44.538168: step: 1844/531, loss: 0.02786068059504032
2023-01-24 07:04:45.599282: step: 1848/531, loss: 0.0012372505152598023
2023-01-24 07:04:46.661548: step: 1852/531, loss: 0.021328700706362724
2023-01-24 07:04:47.741164: step: 1856/531, loss: 0.01656363159418106
2023-01-24 07:04:48.804069: step: 1860/531, loss: 2.979422060889192e-05
2023-01-24 07:04:49.885170: step: 1864/531, loss: 0.011781489476561546
2023-01-24 07:04:50.965743: step: 1868/531, loss: 0.0005675645661540329
2023-01-24 07:04:52.034611: step: 1872/531, loss: 0.005878841038793325
2023-01-24 07:04:53.093230: step: 1876/531, loss: 0.004570318385958672
2023-01-24 07:04:54.147184: step: 1880/531, loss: 0.002639268757775426
2023-01-24 07:04:55.206354: step: 1884/531, loss: 0.0026401374489068985
2023-01-24 07:04:56.271094: step: 1888/531, loss: 0.05612551420927048
2023-01-24 07:04:57.333199: step: 1892/531, loss: 0.0007068126578815281
2023-01-24 07:04:58.400350: step: 1896/531, loss: 0.02459676004946232
2023-01-24 07:04:59.460779: step: 1900/531, loss: 0.00029960571555420756
2023-01-24 07:05:00.535615: step: 1904/531, loss: 0.0004264643357601017
2023-01-24 07:05:01.599447: step: 1908/531, loss: 0.004157466348260641
2023-01-24 07:05:02.661792: step: 1912/531, loss: 0.013789691962301731
2023-01-24 07:05:03.724144: step: 1916/531, loss: 0.012317962013185024
2023-01-24 07:05:04.785454: step: 1920/531, loss: 0.0021516093984246254
2023-01-24 07:05:05.840481: step: 1924/531, loss: 0.0036408354062587023
2023-01-24 07:05:06.897344: step: 1928/531, loss: 0.0025644563138484955
2023-01-24 07:05:07.961123: step: 1932/531, loss: 0.0035383193753659725
2023-01-24 07:05:09.023181: step: 1936/531, loss: 0.02960287220776081
2023-01-24 07:05:10.084349: step: 1940/531, loss: 0.0026895683258771896
2023-01-24 07:05:11.149956: step: 1944/531, loss: 0.0009147656382992864
2023-01-24 07:05:12.260468: step: 1948/531, loss: 0.006670397240668535
2023-01-24 07:05:13.328823: step: 1952/531, loss: 0.0013399462914094329
2023-01-24 07:05:14.386614: step: 1956/531, loss: 0.007294829934835434
2023-01-24 07:05:15.456253: step: 1960/531, loss: 0.004420367069542408
2023-01-24 07:05:16.525656: step: 1964/531, loss: 0.006349206902086735
2023-01-24 07:05:17.574919: step: 1968/531, loss: 0.003116267267614603
2023-01-24 07:05:18.642365: step: 1972/531, loss: 0.013571003451943398
2023-01-24 07:05:19.701311: step: 1976/531, loss: 0.03366992622613907
2023-01-24 07:05:20.769192: step: 1980/531, loss: 0.01436995156109333
2023-01-24 07:05:21.851751: step: 1984/531, loss: 0.007501256186515093
2023-01-24 07:05:22.916991: step: 1988/531, loss: 0.020963972434401512
2023-01-24 07:05:23.977155: step: 1992/531, loss: 0.0036808261647820473
2023-01-24 07:05:25.034807: step: 1996/531, loss: 0.001825462793931365
2023-01-24 07:05:26.102310: step: 2000/531, loss: 0.00017323480278719217
2023-01-24 07:05:27.167802: step: 2004/531, loss: 0.010004017502069473
2023-01-24 07:05:28.214360: step: 2008/531, loss: 0.011605517007410526
2023-01-24 07:05:29.283710: step: 2012/531, loss: 0.017539387568831444
2023-01-24 07:05:30.342011: step: 2016/531, loss: 0.002200875896960497
2023-01-24 07:05:31.401795: step: 2020/531, loss: 0.005723350681364536
2023-01-24 07:05:32.470075: step: 2024/531, loss: 0.009227910079061985
2023-01-24 07:05:33.529135: step: 2028/531, loss: 0.0007814702694304287
2023-01-24 07:05:34.588028: step: 2032/531, loss: 0.004175608512014151
2023-01-24 07:05:35.653833: step: 2036/531, loss: 0.0009639888303354383
2023-01-24 07:05:36.712836: step: 2040/531, loss: 0.02446260116994381
2023-01-24 07:05:37.787430: step: 2044/531, loss: 0.01093518827110529
2023-01-24 07:05:38.848591: step: 2048/531, loss: 0.0005230515380389988
2023-01-24 07:05:39.910205: step: 2052/531, loss: 0.006759479641914368
2023-01-24 07:05:40.978927: step: 2056/531, loss: 0.0037046505603939295
2023-01-24 07:05:42.042580: step: 2060/531, loss: 0.004195843357592821
2023-01-24 07:05:43.106734: step: 2064/531, loss: 0.0038369738031178713
2023-01-24 07:05:44.174324: step: 2068/531, loss: 0.000492674414999783
2023-01-24 07:05:45.222950: step: 2072/531, loss: 0.008961460553109646
2023-01-24 07:05:46.282280: step: 2076/531, loss: 0.02713868021965027
2023-01-24 07:05:47.346065: step: 2080/531, loss: 0.015142214484512806
2023-01-24 07:05:48.407253: step: 2084/531, loss: 0.020338667556643486
2023-01-24 07:05:49.482131: step: 2088/531, loss: 0.008478760719299316
2023-01-24 07:05:50.534159: step: 2092/531, loss: 0.012183763086795807
2023-01-24 07:05:51.574991: step: 2096/531, loss: 0.0
2023-01-24 07:05:52.651738: step: 2100/531, loss: 0.021184327080845833
2023-01-24 07:05:53.707431: step: 2104/531, loss: 0.012286979705095291
2023-01-24 07:05:54.755559: step: 2108/531, loss: 0.008115244098007679
2023-01-24 07:05:55.821072: step: 2112/531, loss: 0.0009436632390134037
2023-01-24 07:05:56.894495: step: 2116/531, loss: 0.004173213616013527
2023-01-24 07:05:57.967656: step: 2120/531, loss: 0.0041024102829396725
2023-01-24 07:05:59.027433: step: 2124/531, loss: 0.013826792128384113
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39127723549869664, 'r': 0.31851600384998263, 'f1': 0.3511672260019683}, 'combined': 0.2587547981067135, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.39229287636422067, 'r': 0.27732877824125246, 'f1': 0.3249420127517686}, 'combined': 0.20346836312493924, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37696989186660795, 'r': 0.3376276830380246, 'f1': 0.3562157937157937}, 'combined': 0.26247479536953217, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3934213708308193, 'r': 0.2884144044052805, 'f1': 0.3328320233979772}, 'combined': 0.2062620990071971, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 8}
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, 'stategy': 1, 'epoch': 8}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:08:28.764671: step: 4/531, loss: 0.0045977430418133736
2023-01-24 07:08:29.812731: step: 8/531, loss: 0.0019700611010193825
2023-01-24 07:08:30.866023: step: 12/531, loss: 0.004937261343002319
2023-01-24 07:08:31.926730: step: 16/531, loss: 0.009785373695194721
2023-01-24 07:08:32.979434: step: 20/531, loss: 0.0010665488662198186
2023-01-24 07:08:34.041588: step: 24/531, loss: 0.0018849570769816637
2023-01-24 07:08:35.091018: step: 28/531, loss: 0.0027515084948390722
2023-01-24 07:08:36.151811: step: 32/531, loss: 0.0047698556445539
2023-01-24 07:08:37.197586: step: 36/531, loss: 0.005599712487310171
2023-01-24 07:08:38.249815: step: 40/531, loss: 0.003969782497733831
2023-01-24 07:08:39.304420: step: 44/531, loss: 0.0006599472835659981
2023-01-24 07:08:40.361061: step: 48/531, loss: 0.005097010172903538
2023-01-24 07:08:41.410862: step: 52/531, loss: 0.014123380184173584
2023-01-24 07:08:42.468139: step: 56/531, loss: 0.005724338814616203
2023-01-24 07:08:43.506007: step: 60/531, loss: 0.00408971169963479
2023-01-24 07:08:44.562862: step: 64/531, loss: 0.045634925365448
2023-01-24 07:08:45.627316: step: 68/531, loss: 0.007729522883892059
2023-01-24 07:08:46.687064: step: 72/531, loss: 0.006360651925206184
2023-01-24 07:08:47.732945: step: 76/531, loss: 0.0007551007438451052
2023-01-24 07:08:48.785560: step: 80/531, loss: 0.004799914080649614
2023-01-24 07:08:49.845721: step: 84/531, loss: 0.0015599695034325123
2023-01-24 07:08:50.903938: step: 88/531, loss: 0.011800430715084076
2023-01-24 07:08:51.953116: step: 92/531, loss: 0.004497630521655083
2023-01-24 07:08:53.005193: step: 96/531, loss: 0.003674152074381709
2023-01-24 07:08:54.059606: step: 100/531, loss: 0.0010398485464975238
2023-01-24 07:08:55.107622: step: 104/531, loss: 0.017408128827810287
2023-01-24 07:08:56.156589: step: 108/531, loss: 0.0031853914260864258
2023-01-24 07:08:57.198446: step: 112/531, loss: 0.007440201472491026
2023-01-24 07:08:58.248296: step: 116/531, loss: 0.0024703936651349068
2023-01-24 07:08:59.301439: step: 120/531, loss: 0.0033811787143349648
2023-01-24 07:09:00.364508: step: 124/531, loss: 0.006839707959443331
2023-01-24 07:09:01.426679: step: 128/531, loss: 0.00014722137711942196
2023-01-24 07:09:02.476544: step: 132/531, loss: 0.004453862085938454
2023-01-24 07:09:03.520376: step: 136/531, loss: 0.018303485587239265
2023-01-24 07:09:04.573705: step: 140/531, loss: 0.010282585397362709
2023-01-24 07:09:05.626311: step: 144/531, loss: 0.006527125369757414
2023-01-24 07:09:06.680707: step: 148/531, loss: 0.0034645788837224245
2023-01-24 07:09:07.737681: step: 152/531, loss: 0.007936164736747742
2023-01-24 07:09:08.801967: step: 156/531, loss: 0.005556902848184109
2023-01-24 07:09:09.847145: step: 160/531, loss: 0.0
2023-01-24 07:09:10.899865: step: 164/531, loss: 0.001379739143885672
2023-01-24 07:09:11.962871: step: 168/531, loss: 0.016546497121453285
2023-01-24 07:09:13.016072: step: 172/531, loss: 0.006233325693756342
2023-01-24 07:09:14.068517: step: 176/531, loss: 0.008840410970151424
2023-01-24 07:09:15.144193: step: 180/531, loss: 0.002961039077490568
2023-01-24 07:09:16.217736: step: 184/531, loss: 0.007977454923093319
2023-01-24 07:09:17.270781: step: 188/531, loss: 0.00157838873565197
2023-01-24 07:09:18.327009: step: 192/531, loss: 0.004022036213427782
2023-01-24 07:09:19.390078: step: 196/531, loss: 0.005652822088450193
2023-01-24 07:09:20.445086: step: 200/531, loss: 0.000407386920414865
2023-01-24 07:09:21.494951: step: 204/531, loss: 0.0012129707029089332
2023-01-24 07:09:22.550216: step: 208/531, loss: 0.0182546004652977
2023-01-24 07:09:23.613901: step: 212/531, loss: 0.005494026001542807
2023-01-24 07:09:24.685205: step: 216/531, loss: 0.004386740271002054
2023-01-24 07:09:25.748090: step: 220/531, loss: 0.003960524220019579
2023-01-24 07:09:26.809834: step: 224/531, loss: 0.004750370979309082
2023-01-24 07:09:27.858542: step: 228/531, loss: 0.013265627436339855
2023-01-24 07:09:28.909020: step: 232/531, loss: 0.03604407608509064
2023-01-24 07:09:29.971637: step: 236/531, loss: 0.01644900068640709
2023-01-24 07:09:31.020912: step: 240/531, loss: 0.012413191609084606
2023-01-24 07:09:32.071573: step: 244/531, loss: 0.0004996042116545141
2023-01-24 07:09:33.133915: step: 248/531, loss: 0.006077242083847523
2023-01-24 07:09:34.192369: step: 252/531, loss: 0.016008995473384857
2023-01-24 07:09:35.243136: step: 256/531, loss: 9.779685933608562e-05
2023-01-24 07:09:36.309167: step: 260/531, loss: 0.015536663122475147
2023-01-24 07:09:37.365330: step: 264/531, loss: 0.003452009754255414
2023-01-24 07:09:38.425281: step: 268/531, loss: 0.0022483840584754944
2023-01-24 07:09:39.474675: step: 272/531, loss: 0.0020265274215489626
2023-01-24 07:09:40.521453: step: 276/531, loss: 0.006405857857316732
2023-01-24 07:09:41.588266: step: 280/531, loss: 0.008755036629736423
2023-01-24 07:09:42.649084: step: 284/531, loss: 0.004601696971803904
2023-01-24 07:09:43.719051: step: 288/531, loss: 0.008911800570786
2023-01-24 07:09:44.778694: step: 292/531, loss: 0.003905730089172721
2023-01-24 07:09:45.851143: step: 296/531, loss: 0.006910170894116163
2023-01-24 07:09:46.920828: step: 300/531, loss: 0.001313588465563953
2023-01-24 07:09:47.963799: step: 304/531, loss: 0.0063367681577801704
2023-01-24 07:09:49.015659: step: 308/531, loss: 0.0018200651975348592
2023-01-24 07:09:50.080140: step: 312/531, loss: 0.004841177258640528
2023-01-24 07:09:51.136254: step: 316/531, loss: 0.014197521843016148
2023-01-24 07:09:52.198547: step: 320/531, loss: 0.0008779449854046106
2023-01-24 07:09:53.255742: step: 324/531, loss: 0.007762029767036438
2023-01-24 07:09:54.310916: step: 328/531, loss: 0.001322629046626389
2023-01-24 07:09:55.359446: step: 332/531, loss: 0.001630575628951192
2023-01-24 07:09:56.415601: step: 336/531, loss: 0.0014119212282821536
2023-01-24 07:09:57.474937: step: 340/531, loss: 0.0012350730830803514
2023-01-24 07:09:58.538247: step: 344/531, loss: 4.487645492190495e-05
2023-01-24 07:09:59.593020: step: 348/531, loss: 0.003320972668007016
2023-01-24 07:10:00.667335: step: 352/531, loss: 0.0013794652186334133
2023-01-24 07:10:01.720094: step: 356/531, loss: 4.466444079298526e-05
2023-01-24 07:10:02.772563: step: 360/531, loss: 0.007342898286879063
2023-01-24 07:10:03.836958: step: 364/531, loss: 0.0064662303775548935
2023-01-24 07:10:04.897375: step: 368/531, loss: 0.0018413165817037225
2023-01-24 07:10:05.948276: step: 372/531, loss: 0.007778462953865528
2023-01-24 07:10:07.011957: step: 376/531, loss: 0.01393235195428133
2023-01-24 07:10:08.070039: step: 380/531, loss: 0.0008352399454452097
2023-01-24 07:10:09.143350: step: 384/531, loss: 0.0014705639332532883
2023-01-24 07:10:10.195170: step: 388/531, loss: 0.005661927629262209
2023-01-24 07:10:11.266042: step: 392/531, loss: 0.008845703676342964
2023-01-24 07:10:12.341221: step: 396/531, loss: 0.0009504136396571994
2023-01-24 07:10:13.389246: step: 400/531, loss: 0.0010107960551977158
2023-01-24 07:10:14.446049: step: 404/531, loss: 0.00014433078467845917
2023-01-24 07:10:15.512262: step: 408/531, loss: 0.016325997188687325
2023-01-24 07:10:16.582092: step: 412/531, loss: 0.0003459411673247814
2023-01-24 07:10:17.637868: step: 416/531, loss: 0.015770798549056053
2023-01-24 07:10:18.714196: step: 420/531, loss: 0.004629632458090782
2023-01-24 07:10:19.771028: step: 424/531, loss: 0.007492108270525932
2023-01-24 07:10:20.820622: step: 428/531, loss: 0.008259224705398083
2023-01-24 07:10:21.871977: step: 432/531, loss: 0.01000315323472023
2023-01-24 07:10:22.938673: step: 436/531, loss: 0.005067561287432909
2023-01-24 07:10:23.998599: step: 440/531, loss: 0.001194012351334095
2023-01-24 07:10:25.046997: step: 444/531, loss: 0.00036043146974407136
2023-01-24 07:10:26.103308: step: 448/531, loss: 0.0033841647673398256
2023-01-24 07:10:27.152776: step: 452/531, loss: 0.0037216609343886375
2023-01-24 07:10:28.213541: step: 456/531, loss: 0.00327302236109972
2023-01-24 07:10:29.276255: step: 460/531, loss: 0.020945213735103607
2023-01-24 07:10:30.341551: step: 464/531, loss: 0.006891566328704357
2023-01-24 07:10:31.383688: step: 468/531, loss: 0.0023995935916900635
2023-01-24 07:10:32.451062: step: 472/531, loss: 0.00436417106539011
2023-01-24 07:10:33.521414: step: 476/531, loss: 0.002857574727386236
2023-01-24 07:10:34.575946: step: 480/531, loss: 0.00039393914630636573
2023-01-24 07:10:35.633153: step: 484/531, loss: 0.00477828923612833
2023-01-24 07:10:36.685344: step: 488/531, loss: 0.005784063134342432
2023-01-24 07:10:37.731192: step: 492/531, loss: 0.00048021567636169493
2023-01-24 07:10:38.798898: step: 496/531, loss: 0.001890623476356268
2023-01-24 07:10:39.862756: step: 500/531, loss: 0.018695522099733353
2023-01-24 07:10:40.930223: step: 504/531, loss: 0.01640419103205204
2023-01-24 07:10:42.021364: step: 508/531, loss: 0.00582819664850831
2023-01-24 07:10:43.079715: step: 512/531, loss: 0.02799372561275959
2023-01-24 07:10:44.134140: step: 516/531, loss: 0.008583822287619114
2023-01-24 07:10:45.173785: step: 520/531, loss: 0.003239756915718317
2023-01-24 07:10:46.213286: step: 524/531, loss: 0.0003791235794778913
2023-01-24 07:10:47.268382: step: 528/531, loss: 0.005838289391249418
2023-01-24 07:10:48.324985: step: 532/531, loss: 0.009548705071210861
2023-01-24 07:10:49.378994: step: 536/531, loss: 0.0013132026651874185
2023-01-24 07:10:50.446761: step: 540/531, loss: 0.008961766958236694
2023-01-24 07:10:51.506849: step: 544/531, loss: 0.00017841016233433038
2023-01-24 07:10:52.563627: step: 548/531, loss: 0.0027805950958281755
2023-01-24 07:10:53.637274: step: 552/531, loss: 0.0026308472733944654
2023-01-24 07:10:54.711235: step: 556/531, loss: 0.0038388827815651894
2023-01-24 07:10:55.781835: step: 560/531, loss: 0.002630452858284116
2023-01-24 07:10:56.839832: step: 564/531, loss: 0.05558782443404198
2023-01-24 07:10:57.896449: step: 568/531, loss: 0.0007264415617100894
2023-01-24 07:10:58.943381: step: 572/531, loss: 0.01898963749408722
2023-01-24 07:11:00.002261: step: 576/531, loss: 0.00010552137246122584
2023-01-24 07:11:01.056594: step: 580/531, loss: 0.0050046988762915134
2023-01-24 07:11:02.113983: step: 584/531, loss: 0.0026430857833474874
2023-01-24 07:11:03.156971: step: 588/531, loss: 0.001241020392626524
2023-01-24 07:11:04.218783: step: 592/531, loss: 0.0036607852671295404
2023-01-24 07:11:05.268394: step: 596/531, loss: 0.00029355636797845364
2023-01-24 07:11:06.335306: step: 600/531, loss: 0.006995843257755041
2023-01-24 07:11:07.401553: step: 604/531, loss: 0.002957818331196904
2023-01-24 07:11:08.457337: step: 608/531, loss: 0.0019812150858342648
2023-01-24 07:11:09.530741: step: 612/531, loss: 9.81592747848481e-05
2023-01-24 07:11:10.581091: step: 616/531, loss: 0.0014182009035721421
2023-01-24 07:11:11.656883: step: 620/531, loss: 0.0018387639429420233
2023-01-24 07:11:12.703969: step: 624/531, loss: 0.0020353938452899456
2023-01-24 07:11:13.769580: step: 628/531, loss: 0.01270974613726139
2023-01-24 07:11:14.840262: step: 632/531, loss: 0.005841148551553488
2023-01-24 07:11:15.889479: step: 636/531, loss: 0.03105478733778
2023-01-24 07:11:16.948892: step: 640/531, loss: 0.0036587135400623083
2023-01-24 07:11:18.016364: step: 644/531, loss: 0.0027956501580774784
2023-01-24 07:11:19.067969: step: 648/531, loss: 0.005313706584274769
2023-01-24 07:11:20.138002: step: 652/531, loss: 0.0005047524464316666
2023-01-24 07:11:21.206960: step: 656/531, loss: 0.00048412979231216013
2023-01-24 07:11:22.254422: step: 660/531, loss: 0.00015525547496508807
2023-01-24 07:11:23.330187: step: 664/531, loss: 0.007092516403645277
2023-01-24 07:11:24.399139: step: 668/531, loss: 0.0033150548115372658
2023-01-24 07:11:25.452351: step: 672/531, loss: 0.004298761487007141
2023-01-24 07:11:26.510786: step: 676/531, loss: 0.004011280369013548
2023-01-24 07:11:27.584283: step: 680/531, loss: 0.008520894683897495
2023-01-24 07:11:28.637168: step: 684/531, loss: 0.0005329372943378985
2023-01-24 07:11:29.706908: step: 688/531, loss: 0.005702773109078407
2023-01-24 07:11:30.779808: step: 692/531, loss: 0.005568182095885277
2023-01-24 07:11:31.832323: step: 696/531, loss: 0.00956930872052908
2023-01-24 07:11:32.898491: step: 700/531, loss: 0.007446709088981152
2023-01-24 07:11:33.973699: step: 704/531, loss: 0.0028796715196222067
2023-01-24 07:11:35.034324: step: 708/531, loss: 0.005106172524392605
2023-01-24 07:11:36.076854: step: 712/531, loss: 0.000268861826043576
2023-01-24 07:11:37.151100: step: 716/531, loss: 0.0019048639805987477
2023-01-24 07:11:38.221662: step: 720/531, loss: 0.00028441695030778646
2023-01-24 07:11:39.268584: step: 724/531, loss: 0.005149377975612879
2023-01-24 07:11:40.349662: step: 728/531, loss: 0.003986825235188007
2023-01-24 07:11:41.399087: step: 732/531, loss: 0.002429863205179572
2023-01-24 07:11:42.470973: step: 736/531, loss: 0.001819361699745059
2023-01-24 07:11:43.529473: step: 740/531, loss: 0.0029367515817284584
2023-01-24 07:11:44.603826: step: 744/531, loss: 0.003790078451856971
2023-01-24 07:11:45.673162: step: 748/531, loss: 0.0033502851147204638
2023-01-24 07:11:46.741875: step: 752/531, loss: 0.0004885253147222102
2023-01-24 07:11:47.814181: step: 756/531, loss: 0.004335005301982164
2023-01-24 07:11:48.865162: step: 760/531, loss: 0.0011945945443585515
2023-01-24 07:11:49.921107: step: 764/531, loss: 0.0023913851473480463
2023-01-24 07:11:50.989552: step: 768/531, loss: 0.003030638676136732
2023-01-24 07:11:52.049869: step: 772/531, loss: 0.0011016554199159145
2023-01-24 07:11:53.104083: step: 776/531, loss: 0.007391211111098528
2023-01-24 07:11:54.168312: step: 780/531, loss: 0.019452929496765137
2023-01-24 07:11:55.227711: step: 784/531, loss: 0.0054628984071314335
2023-01-24 07:11:56.296040: step: 788/531, loss: 0.012637363746762276
2023-01-24 07:11:57.364259: step: 792/531, loss: 0.0011910557514056563
2023-01-24 07:11:58.414213: step: 796/531, loss: 0.0026493645273149014
2023-01-24 07:11:59.471515: step: 800/531, loss: 0.011939937248826027
2023-01-24 07:12:00.527479: step: 804/531, loss: 0.007114273961633444
2023-01-24 07:12:01.587696: step: 808/531, loss: 0.014530682936310768
2023-01-24 07:12:02.647622: step: 812/531, loss: 0.002293882193043828
2023-01-24 07:12:03.704834: step: 816/531, loss: 0.03261454403400421
2023-01-24 07:12:04.779915: step: 820/531, loss: 0.0034278477542102337
2023-01-24 07:12:05.845607: step: 824/531, loss: 0.004947775974869728
2023-01-24 07:12:06.905233: step: 828/531, loss: 0.0030227298848330975
2023-01-24 07:12:07.955124: step: 832/531, loss: 0.0017091204645112157
2023-01-24 07:12:09.020437: step: 836/531, loss: 0.0064543127082288265
2023-01-24 07:12:10.070636: step: 840/531, loss: 0.004850310739129782
2023-01-24 07:12:11.128598: step: 844/531, loss: 2.369673347857315e-05
2023-01-24 07:12:12.185606: step: 848/531, loss: 0.03181464970111847
2023-01-24 07:12:13.268439: step: 852/531, loss: 0.0031605076510459185
2023-01-24 07:12:14.334180: step: 856/531, loss: 0.014925448223948479
2023-01-24 07:12:15.401167: step: 860/531, loss: 0.0030504364985972643
2023-01-24 07:12:16.452268: step: 864/531, loss: 0.004174187779426575
2023-01-24 07:12:17.526962: step: 868/531, loss: 0.0032774428837001324
2023-01-24 07:12:18.581833: step: 872/531, loss: 0.005438651889562607
2023-01-24 07:12:19.644662: step: 876/531, loss: 0.0029399788472801447
2023-01-24 07:12:20.712385: step: 880/531, loss: 0.0025096528697758913
2023-01-24 07:12:21.756722: step: 884/531, loss: 0.0014572727959603071
2023-01-24 07:12:22.839552: step: 888/531, loss: 0.004770008847117424
2023-01-24 07:12:23.904474: step: 892/531, loss: 0.0010061761131510139
2023-01-24 07:12:24.961672: step: 896/531, loss: 0.0014356044121086597
2023-01-24 07:12:26.014242: step: 900/531, loss: 0.0035231199581176043
2023-01-24 07:12:27.088608: step: 904/531, loss: 0.002293233759701252
2023-01-24 07:12:28.165561: step: 908/531, loss: 0.0072817932814359665
2023-01-24 07:12:29.235041: step: 912/531, loss: 0.01366877555847168
2023-01-24 07:12:30.316510: step: 916/531, loss: 0.005684357602149248
2023-01-24 07:12:31.374101: step: 920/531, loss: 0.013977249152958393
2023-01-24 07:12:32.454058: step: 924/531, loss: 0.005502911750227213
2023-01-24 07:12:33.526622: step: 928/531, loss: 0.0019891508854925632
2023-01-24 07:12:34.587889: step: 932/531, loss: 0.007536507211625576
2023-01-24 07:12:35.662341: step: 936/531, loss: 0.0005093825166113675
2023-01-24 07:12:36.724997: step: 940/531, loss: 0.0012100131716579199
2023-01-24 07:12:37.814009: step: 944/531, loss: 0.00581153342500329
2023-01-24 07:12:38.888208: step: 948/531, loss: 0.013841337524354458
2023-01-24 07:12:39.963533: step: 952/531, loss: 0.006892412900924683
2023-01-24 07:12:41.038776: step: 956/531, loss: 0.00490581663325429
2023-01-24 07:12:42.107564: step: 960/531, loss: 0.012574831023812294
2023-01-24 07:12:43.178794: step: 964/531, loss: 0.02010909467935562
2023-01-24 07:12:44.245893: step: 968/531, loss: 0.0024519346188753843
2023-01-24 07:12:45.306705: step: 972/531, loss: 0.0006077011348679662
2023-01-24 07:12:46.377978: step: 976/531, loss: 0.01896348036825657
2023-01-24 07:12:47.447732: step: 980/531, loss: 0.0003838891861960292
2023-01-24 07:12:48.520779: step: 984/531, loss: 0.001048270845785737
2023-01-24 07:12:49.569434: step: 988/531, loss: 0.004417904652655125
2023-01-24 07:12:50.635841: step: 992/531, loss: 0.0009408965706825256
2023-01-24 07:12:51.697984: step: 996/531, loss: 0.002442322438582778
2023-01-24 07:12:52.776182: step: 1000/531, loss: 0.0022212981712073088
2023-01-24 07:12:53.857930: step: 1004/531, loss: 0.0013069476699456573
2023-01-24 07:12:54.922323: step: 1008/531, loss: 0.009917059913277626
2023-01-24 07:12:55.988105: step: 1012/531, loss: 0.0041924575343728065
2023-01-24 07:12:57.041802: step: 1016/531, loss: 6.13931697444059e-05
2023-01-24 07:12:58.101312: step: 1020/531, loss: 0.002931284951046109
2023-01-24 07:12:59.166982: step: 1024/531, loss: 0.01705293543636799
2023-01-24 07:13:00.236819: step: 1028/531, loss: 0.003357037901878357
2023-01-24 07:13:01.317785: step: 1032/531, loss: 0.0018999928142875433
2023-01-24 07:13:02.387111: step: 1036/531, loss: 0.015623767860233784
2023-01-24 07:13:03.445381: step: 1040/531, loss: 0.0006367540336214006
2023-01-24 07:13:04.518456: step: 1044/531, loss: 0.0007088141865096986
2023-01-24 07:13:05.596242: step: 1048/531, loss: 0.00343990046530962
2023-01-24 07:13:06.690502: step: 1052/531, loss: 0.0006036301492713392
2023-01-24 07:13:07.742668: step: 1056/531, loss: 0.00012817702372558415
2023-01-24 07:13:08.807713: step: 1060/531, loss: 0.004272814840078354
2023-01-24 07:13:09.866115: step: 1064/531, loss: 0.0025128498673439026
2023-01-24 07:13:10.925596: step: 1068/531, loss: 0.0032080861274152994
2023-01-24 07:13:11.977312: step: 1072/531, loss: 0.0037822870071977377
2023-01-24 07:13:13.053696: step: 1076/531, loss: 0.0013688289327546954
2023-01-24 07:13:14.132282: step: 1080/531, loss: 0.009208443574607372
2023-01-24 07:13:15.197346: step: 1084/531, loss: 0.010907547548413277
2023-01-24 07:13:16.257604: step: 1088/531, loss: 0.006185346283018589
2023-01-24 07:13:17.330977: step: 1092/531, loss: 0.004072161391377449
2023-01-24 07:13:18.385185: step: 1096/531, loss: 0.007457377854734659
2023-01-24 07:13:19.457571: step: 1100/531, loss: 0.004470342304557562
2023-01-24 07:13:20.516958: step: 1104/531, loss: 0.007369750179350376
2023-01-24 07:13:21.567891: step: 1108/531, loss: 0.033470671623945236
2023-01-24 07:13:22.635202: step: 1112/531, loss: 0.03634115681052208
2023-01-24 07:13:23.691123: step: 1116/531, loss: 0.024756332859396935
2023-01-24 07:13:24.767230: step: 1120/531, loss: 0.0061282324604690075
2023-01-24 07:13:25.812007: step: 1124/531, loss: 0.003763258457183838
2023-01-24 07:13:26.861628: step: 1128/531, loss: 0.03824980929493904
2023-01-24 07:13:27.940284: step: 1132/531, loss: 0.005244008265435696
2023-01-24 07:13:28.991380: step: 1136/531, loss: 0.00044720651931129396
2023-01-24 07:13:30.053899: step: 1140/531, loss: 0.01317501813173294
2023-01-24 07:13:31.111473: step: 1144/531, loss: 0.004085793625563383
2023-01-24 07:13:32.176621: step: 1148/531, loss: 0.001619831658899784
2023-01-24 07:13:33.254999: step: 1152/531, loss: 0.014504484832286835
2023-01-24 07:13:34.314157: step: 1156/531, loss: 0.010084259323775768
2023-01-24 07:13:35.379938: step: 1160/531, loss: 0.0070733968168497086
2023-01-24 07:13:36.440265: step: 1164/531, loss: 0.01693405769765377
2023-01-24 07:13:37.504913: step: 1168/531, loss: 0.0057841334491968155
2023-01-24 07:13:38.556989: step: 1172/531, loss: 0.0027460299897938967
2023-01-24 07:13:39.621796: step: 1176/531, loss: 0.0005352850421331823
2023-01-24 07:13:40.675935: step: 1180/531, loss: 0.004516599699854851
2023-01-24 07:13:41.723052: step: 1184/531, loss: 0.00194433459546417
2023-01-24 07:13:42.782347: step: 1188/531, loss: 0.006917648948729038
2023-01-24 07:13:43.844471: step: 1192/531, loss: 0.0025990032590925694
2023-01-24 07:13:44.916283: step: 1196/531, loss: 0.0003694795595947653
2023-01-24 07:13:45.988149: step: 1200/531, loss: 0.0022541554644703865
2023-01-24 07:13:47.055637: step: 1204/531, loss: 0.005560600198805332
2023-01-24 07:13:48.117502: step: 1208/531, loss: 0.0009630077984184027
2023-01-24 07:13:49.178690: step: 1212/531, loss: 0.0018164411885663867
2023-01-24 07:13:50.245452: step: 1216/531, loss: 0.005099601577967405
2023-01-24 07:13:51.295575: step: 1220/531, loss: 0.0021063892636448145
2023-01-24 07:13:52.379260: step: 1224/531, loss: 0.009221532382071018
2023-01-24 07:13:53.442795: step: 1228/531, loss: 0.0001460358325857669
2023-01-24 07:13:54.510878: step: 1232/531, loss: 0.00019809798686765134
2023-01-24 07:13:55.586959: step: 1236/531, loss: 0.005001719109714031
2023-01-24 07:13:56.678112: step: 1240/531, loss: 0.005442372057586908
2023-01-24 07:13:57.744573: step: 1244/531, loss: 0.01572977565228939
2023-01-24 07:13:58.806039: step: 1248/531, loss: 0.009500561282038689
2023-01-24 07:13:59.885567: step: 1252/531, loss: 0.006423449609428644
2023-01-24 07:14:00.946646: step: 1256/531, loss: 0.0029891899321228266
2023-01-24 07:14:02.015027: step: 1260/531, loss: 0.006739405449479818
2023-01-24 07:14:03.080515: step: 1264/531, loss: 0.0031463869381695986
2023-01-24 07:14:04.123651: step: 1268/531, loss: 0.0010002534836530685
2023-01-24 07:14:05.180186: step: 1272/531, loss: 0.0011597184929996729
2023-01-24 07:14:06.246509: step: 1276/531, loss: 0.010666647925972939
2023-01-24 07:14:07.305089: step: 1280/531, loss: 0.0024663519579917192
2023-01-24 07:14:08.371264: step: 1284/531, loss: 0.0009161880007013679
2023-01-24 07:14:09.427495: step: 1288/531, loss: 0.004265964962542057
2023-01-24 07:14:10.493123: step: 1292/531, loss: 0.002798403613269329
2023-01-24 07:14:11.554138: step: 1296/531, loss: 0.007940325886011124
2023-01-24 07:14:12.658183: step: 1300/531, loss: 0.013691847212612629
2023-01-24 07:14:13.709144: step: 1304/531, loss: 0.044071342796087265
2023-01-24 07:14:14.773721: step: 1308/531, loss: 1.2964428606210276e-05
2023-01-24 07:14:15.847557: step: 1312/531, loss: 0.004941326100379229
2023-01-24 07:14:16.912162: step: 1316/531, loss: 0.007497509941458702
2023-01-24 07:14:17.962789: step: 1320/531, loss: 0.0141603359952569
2023-01-24 07:14:19.023192: step: 1324/531, loss: 0.0019523242954164743
2023-01-24 07:14:20.086756: step: 1328/531, loss: 0.008256577886641026
2023-01-24 07:14:21.160142: step: 1332/531, loss: 0.018632415682077408
2023-01-24 07:14:22.232742: step: 1336/531, loss: 0.0066160825081169605
2023-01-24 07:14:23.288095: step: 1340/531, loss: 0.004395787138491869
2023-01-24 07:14:24.358469: step: 1344/531, loss: 0.004893674980849028
2023-01-24 07:14:25.422482: step: 1348/531, loss: 0.0042001004330813885
2023-01-24 07:14:26.492154: step: 1352/531, loss: 0.007403684314340353
2023-01-24 07:14:27.535663: step: 1356/531, loss: 0.0024068010970950127
2023-01-24 07:14:28.608461: step: 1360/531, loss: 0.009022404439747334
2023-01-24 07:14:29.681189: step: 1364/531, loss: 0.010823088698089123
2023-01-24 07:14:30.746097: step: 1368/531, loss: 0.003000014927238226
2023-01-24 07:14:31.810020: step: 1372/531, loss: 0.007877732627093792
2023-01-24 07:14:32.868413: step: 1376/531, loss: 0.006350968964397907
2023-01-24 07:14:33.916869: step: 1380/531, loss: 0.001364083494991064
2023-01-24 07:14:34.992785: step: 1384/531, loss: 0.001567261409945786
2023-01-24 07:14:36.047836: step: 1388/531, loss: 0.0011952656786888838
2023-01-24 07:14:37.102673: step: 1392/531, loss: 0.004942044615745544
2023-01-24 07:14:38.168915: step: 1396/531, loss: 0.010176066309213638
2023-01-24 07:14:39.246954: step: 1400/531, loss: 0.009766532108187675
2023-01-24 07:14:40.301944: step: 1404/531, loss: 0.008324784226715565
2023-01-24 07:14:41.389081: step: 1408/531, loss: 0.004485917277634144
2023-01-24 07:14:42.442065: step: 1412/531, loss: 0.08397059887647629
2023-01-24 07:14:43.503330: step: 1416/531, loss: 0.004498843569308519
2023-01-24 07:14:44.568600: step: 1420/531, loss: 0.00676374789327383
2023-01-24 07:14:45.627479: step: 1424/531, loss: 0.002184188924729824
2023-01-24 07:14:46.689862: step: 1428/531, loss: 0.00883243978023529
2023-01-24 07:14:47.753839: step: 1432/531, loss: 0.004732491914182901
2023-01-24 07:14:48.816363: step: 1436/531, loss: 0.002859783126041293
2023-01-24 07:14:49.875420: step: 1440/531, loss: 0.009899810887873173
2023-01-24 07:14:50.930463: step: 1444/531, loss: 0.0027839664835482836
2023-01-24 07:14:51.993800: step: 1448/531, loss: 0.0035953286569565535
2023-01-24 07:14:53.070156: step: 1452/531, loss: 0.001807543565519154
2023-01-24 07:14:54.122703: step: 1456/531, loss: 0.003441819455474615
2023-01-24 07:14:55.177335: step: 1460/531, loss: 0.002082986058667302
2023-01-24 07:14:56.256270: step: 1464/531, loss: 0.014478602446615696
2023-01-24 07:14:57.303301: step: 1468/531, loss: 0.0002972553775180131
2023-01-24 07:14:58.357945: step: 1472/531, loss: 0.006524278782308102
2023-01-24 07:14:59.430797: step: 1476/531, loss: 0.0018274827161803842
2023-01-24 07:15:00.494883: step: 1480/531, loss: 0.0033217170275747776
2023-01-24 07:15:01.545999: step: 1484/531, loss: 0.004770943894982338
2023-01-24 07:15:02.629616: step: 1488/531, loss: 0.009360947646200657
2023-01-24 07:15:03.688207: step: 1492/531, loss: 0.004306859336793423
2023-01-24 07:15:04.744618: step: 1496/531, loss: 0.0028718560934066772
2023-01-24 07:15:05.822073: step: 1500/531, loss: 0.010401396080851555
2023-01-24 07:15:06.888140: step: 1504/531, loss: 0.008091055788099766
2023-01-24 07:15:07.929375: step: 1508/531, loss: 8.021388566703536e-06
2023-01-24 07:15:09.021244: step: 1512/531, loss: 0.012760911136865616
2023-01-24 07:15:10.079191: step: 1516/531, loss: 0.00579597894102335
2023-01-24 07:15:11.157876: step: 1520/531, loss: 0.004161902703344822
2023-01-24 07:15:12.220098: step: 1524/531, loss: 0.0007724956376478076
2023-01-24 07:15:13.271470: step: 1528/531, loss: 0.0061883945018053055
2023-01-24 07:15:14.336789: step: 1532/531, loss: 0.020957650616765022
2023-01-24 07:15:15.384921: step: 1536/531, loss: 0.003814868163317442
2023-01-24 07:15:16.439102: step: 1540/531, loss: 0.0034995765890926123
2023-01-24 07:15:17.497603: step: 1544/531, loss: 0.021796464920043945
2023-01-24 07:15:18.560763: step: 1548/531, loss: 0.01099161896854639
2023-01-24 07:15:19.624771: step: 1552/531, loss: 0.008265999145805836
2023-01-24 07:15:20.687834: step: 1556/531, loss: 0.0015358910895884037
2023-01-24 07:15:21.750177: step: 1560/531, loss: 0.01249379850924015
2023-01-24 07:15:22.794658: step: 1564/531, loss: 0.00026867687120102346
2023-01-24 07:15:23.858834: step: 1568/531, loss: 0.0012288582511246204
2023-01-24 07:15:24.910335: step: 1572/531, loss: 0.015754522755742073
2023-01-24 07:15:25.974816: step: 1576/531, loss: 0.0016865389188751578
2023-01-24 07:15:27.041407: step: 1580/531, loss: 0.006365284323692322
2023-01-24 07:15:28.102296: step: 1584/531, loss: 0.004033660050481558
2023-01-24 07:15:29.166674: step: 1588/531, loss: 0.009530124254524708
2023-01-24 07:15:30.245095: step: 1592/531, loss: 0.00394415482878685
2023-01-24 07:15:31.293200: step: 1596/531, loss: 0.0014219009317457676
2023-01-24 07:15:32.349374: step: 1600/531, loss: 0.0018334005726501346
2023-01-24 07:15:33.392799: step: 1604/531, loss: 0.0004036286554764956
2023-01-24 07:15:34.447400: step: 1608/531, loss: 0.0014138143742457032
2023-01-24 07:15:35.514585: step: 1612/531, loss: 0.003865512553602457
2023-01-24 07:15:36.562474: step: 1616/531, loss: 0.012560317292809486
2023-01-24 07:15:37.624332: step: 1620/531, loss: 0.00033325847471132874
2023-01-24 07:15:38.674805: step: 1624/531, loss: 0.018526321277022362
2023-01-24 07:15:39.754663: step: 1628/531, loss: 0.0010144388070330024
2023-01-24 07:15:40.817815: step: 1632/531, loss: 0.006329218856990337
2023-01-24 07:15:41.892667: step: 1636/531, loss: 0.0025783791206777096
2023-01-24 07:15:42.928076: step: 1640/531, loss: 0.0029158187098801136
2023-01-24 07:15:43.993520: step: 1644/531, loss: 0.05281605198979378
2023-01-24 07:15:45.045706: step: 1648/531, loss: 0.008556989952921867
2023-01-24 07:15:46.100505: step: 1652/531, loss: 0.0036575677804648876
2023-01-24 07:15:47.181623: step: 1656/531, loss: 0.0026574493385851383
2023-01-24 07:15:48.228631: step: 1660/531, loss: 0.0007102875388227403
2023-01-24 07:15:49.280173: step: 1664/531, loss: 0.005531547125428915
2023-01-24 07:15:50.335737: step: 1668/531, loss: 0.004560297355055809
2023-01-24 07:15:51.396561: step: 1672/531, loss: 0.004554799757897854
2023-01-24 07:15:52.446599: step: 1676/531, loss: 0.008683348074555397
2023-01-24 07:15:53.526447: step: 1680/531, loss: 0.008254681713879108
2023-01-24 07:15:54.577101: step: 1684/531, loss: 0.0007623700075782835
2023-01-24 07:15:55.632283: step: 1688/531, loss: 0.005907068960368633
2023-01-24 07:15:56.694671: step: 1692/531, loss: 0.005418321117758751
2023-01-24 07:15:57.764499: step: 1696/531, loss: 0.011914653703570366
2023-01-24 07:15:58.811762: step: 1700/531, loss: 0.0062050847336649895
2023-01-24 07:15:59.878756: step: 1704/531, loss: 0.015705464407801628
2023-01-24 07:16:00.939647: step: 1708/531, loss: 0.01217713300138712
2023-01-24 07:16:01.975761: step: 1712/531, loss: 0.007883260026574135
2023-01-24 07:16:03.021633: step: 1716/531, loss: 0.008228284306824207
2023-01-24 07:16:04.088882: step: 1720/531, loss: 0.0046814861707389355
2023-01-24 07:16:05.158412: step: 1724/531, loss: 0.0026429970748722553
2023-01-24 07:16:06.222152: step: 1728/531, loss: 0.007962407544255257
2023-01-24 07:16:07.287105: step: 1732/531, loss: 0.018482469022274017
2023-01-24 07:16:08.339957: step: 1736/531, loss: 0.00960539560765028
2023-01-24 07:16:09.393128: step: 1740/531, loss: 0.012688994407653809
2023-01-24 07:16:10.442586: step: 1744/531, loss: 0.0030719093047082424
2023-01-24 07:16:11.493786: step: 1748/531, loss: 0.003626542165875435
2023-01-24 07:16:12.572089: step: 1752/531, loss: 4.641379291570047e-06
2023-01-24 07:16:13.642055: step: 1756/531, loss: 0.007028732914477587
2023-01-24 07:16:14.705331: step: 1760/531, loss: 0.006028780713677406
2023-01-24 07:16:15.762453: step: 1764/531, loss: 0.005071580875664949
2023-01-24 07:16:16.817304: step: 1768/531, loss: 0.0031488838139921427
2023-01-24 07:16:17.860678: step: 1772/531, loss: 0.005551172886043787
2023-01-24 07:16:18.919122: step: 1776/531, loss: 0.009225967340171337
2023-01-24 07:16:19.986190: step: 1780/531, loss: 0.005321824923157692
2023-01-24 07:16:21.035592: step: 1784/531, loss: 0.002587475348263979
2023-01-24 07:16:22.089635: step: 1788/531, loss: 0.01316310465335846
2023-01-24 07:16:23.142520: step: 1792/531, loss: 0.006016949657350779
2023-01-24 07:16:24.203703: step: 1796/531, loss: 0.014933210797607899
2023-01-24 07:16:25.258945: step: 1800/531, loss: 0.0023555923253297806
2023-01-24 07:16:26.314275: step: 1804/531, loss: 0.002614242024719715
2023-01-24 07:16:27.355422: step: 1808/531, loss: 0.005970026832073927
2023-01-24 07:16:28.408364: step: 1812/531, loss: 8.773949230089784e-05
2023-01-24 07:16:29.465863: step: 1816/531, loss: 0.003064475255087018
2023-01-24 07:16:30.536708: step: 1820/531, loss: 0.0032090472523123026
2023-01-24 07:16:31.593318: step: 1824/531, loss: 0.00393712380900979
2023-01-24 07:16:32.651320: step: 1828/531, loss: 0.005815640091896057
2023-01-24 07:16:33.705626: step: 1832/531, loss: 0.003421928035095334
2023-01-24 07:16:34.762791: step: 1836/531, loss: 0.0014354335144162178
2023-01-24 07:16:35.824949: step: 1840/531, loss: 0.00011879876547027379
2023-01-24 07:16:36.893694: step: 1844/531, loss: 0.0009502311004325747
2023-01-24 07:16:37.965899: step: 1848/531, loss: 0.011249667964875698
2023-01-24 07:16:39.027124: step: 1852/531, loss: 0.0050295148976147175
2023-01-24 07:16:40.086025: step: 1856/531, loss: 0.0072916485369205475
2023-01-24 07:16:41.133399: step: 1860/531, loss: 0.004858419299125671
2023-01-24 07:16:42.206758: step: 1864/531, loss: 0.0014829982537776232
2023-01-24 07:16:43.284998: step: 1868/531, loss: 0.001284286379814148
2023-01-24 07:16:44.340732: step: 1872/531, loss: 0.002504470758140087
2023-01-24 07:16:45.393243: step: 1876/531, loss: 0.00563031667843461
2023-01-24 07:16:46.438196: step: 1880/531, loss: 0.0021439294796437025
2023-01-24 07:16:47.523061: step: 1884/531, loss: 0.004883362911641598
2023-01-24 07:16:48.594108: step: 1888/531, loss: 0.001417040009982884
2023-01-24 07:16:49.648417: step: 1892/531, loss: 0.0026358189061284065
2023-01-24 07:16:50.709167: step: 1896/531, loss: 0.009136012755334377
2023-01-24 07:16:51.748580: step: 1900/531, loss: 0.004267186392098665
2023-01-24 07:16:52.800269: step: 1904/531, loss: 0.004240268841385841
2023-01-24 07:16:53.846862: step: 1908/531, loss: 0.0009395118686370552
2023-01-24 07:16:54.902997: step: 1912/531, loss: 0.0044632768258452415
2023-01-24 07:16:55.973028: step: 1916/531, loss: 0.0037036878056824207
2023-01-24 07:16:57.036554: step: 1920/531, loss: 0.0024403089191764593
2023-01-24 07:16:58.094143: step: 1924/531, loss: 0.004854206927120686
2023-01-24 07:16:59.153751: step: 1928/531, loss: 0.009533275850117207
2023-01-24 07:17:00.224301: step: 1932/531, loss: 0.0066087255254387856
2023-01-24 07:17:01.276987: step: 1936/531, loss: 0.0033751921728253365
2023-01-24 07:17:02.325953: step: 1940/531, loss: 0.0025438310112804174
2023-01-24 07:17:03.373603: step: 1944/531, loss: 0.0038192011415958405
2023-01-24 07:17:04.451953: step: 1948/531, loss: 0.004002876114100218
2023-01-24 07:17:05.512824: step: 1952/531, loss: 0.0013789072399958968
2023-01-24 07:17:06.563922: step: 1956/531, loss: 0.0002060772239929065
2023-01-24 07:17:07.605290: step: 1960/531, loss: 1.8445278328727e-05
2023-01-24 07:17:08.661100: step: 1964/531, loss: 0.001845311839133501
2023-01-24 07:17:09.716583: step: 1968/531, loss: 0.01027022022753954
2023-01-24 07:17:10.770805: step: 1972/531, loss: 0.003569865133613348
2023-01-24 07:17:11.830816: step: 1976/531, loss: 0.011889354325830936
2023-01-24 07:17:12.915483: step: 1980/531, loss: 0.0036696013994514942
2023-01-24 07:17:13.977706: step: 1984/531, loss: 0.01345662958920002
2023-01-24 07:17:15.060769: step: 1988/531, loss: 0.03222336247563362
2023-01-24 07:17:16.099902: step: 1992/531, loss: 0.00046090842806734145
2023-01-24 07:17:17.177039: step: 1996/531, loss: 0.0018972171237692237
2023-01-24 07:17:18.234592: step: 2000/531, loss: 0.007250071503221989
2023-01-24 07:17:19.275762: step: 2004/531, loss: 0.0006911639939062297
2023-01-24 07:17:20.343040: step: 2008/531, loss: 0.0030516444239765406
2023-01-24 07:17:21.404212: step: 2012/531, loss: 0.005031300708651543
2023-01-24 07:17:22.462434: step: 2016/531, loss: 0.008610888384282589
2023-01-24 07:17:23.532779: step: 2020/531, loss: 0.008901862427592278
2023-01-24 07:17:24.603370: step: 2024/531, loss: 0.004255966283380985
2023-01-24 07:17:25.674178: step: 2028/531, loss: 0.007193244062364101
2023-01-24 07:17:26.738198: step: 2032/531, loss: 0.010513965040445328
2023-01-24 07:17:27.782277: step: 2036/531, loss: 0.0065001631155610085
2023-01-24 07:17:28.851181: step: 2040/531, loss: 0.002157973125576973
2023-01-24 07:17:29.930834: step: 2044/531, loss: 0.006816069129854441
2023-01-24 07:17:30.981565: step: 2048/531, loss: 0.0003723324625752866
2023-01-24 07:17:32.049983: step: 2052/531, loss: 0.0013117629569023848
2023-01-24 07:17:33.115361: step: 2056/531, loss: 0.007126954849809408
2023-01-24 07:17:34.181390: step: 2060/531, loss: 0.01046606432646513
2023-01-24 07:17:35.242370: step: 2064/531, loss: 0.0014329601544886827
2023-01-24 07:17:36.302227: step: 2068/531, loss: 0.0025488664396107197
2023-01-24 07:17:37.353855: step: 2072/531, loss: 0.0019703141879290342
2023-01-24 07:17:38.430429: step: 2076/531, loss: 0.001737391809001565
2023-01-24 07:17:39.502491: step: 2080/531, loss: 0.002448421437293291
2023-01-24 07:17:40.537239: step: 2084/531, loss: 0.004302576184272766
2023-01-24 07:17:41.608669: step: 2088/531, loss: 0.0016425788635388017
2023-01-24 07:17:42.668842: step: 2092/531, loss: 0.004586624912917614
2023-01-24 07:17:43.728746: step: 2096/531, loss: 0.010497825220227242
2023-01-24 07:17:44.791837: step: 2100/531, loss: 0.015880558639764786
2023-01-24 07:17:45.861842: step: 2104/531, loss: 0.02986776828765869
2023-01-24 07:17:46.930115: step: 2108/531, loss: 0.004116294905543327
2023-01-24 07:17:47.999825: step: 2112/531, loss: 0.02415524609386921
2023-01-24 07:17:49.052714: step: 2116/531, loss: 0.024909794330596924
2023-01-24 07:17:50.128443: step: 2120/531, loss: 0.005354198161512613
2023-01-24 07:17:51.190859: step: 2124/531, loss: 0.0008390581351704895
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39195376504364254, 'r': 0.32278545356535265, 'f1': 0.35402275552329004}, 'combined': 0.2608588724908453, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3880807297836916, 'r': 0.275750780044679, 'f1': 0.3224118240058503}, 'combined': 0.2018840393307661, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37459415584415584, 'r': 0.3418971327533946, 'f1': 0.3574995812719027}, 'combined': 0.26342074409508615, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3900019318839952, 'r': 0.2866109778949108, 'f1': 0.3304070420846737}, 'combined': 0.20475929368627663, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3588867502517856, 'r': 0.32415577442096766, 'f1': 0.34063827142542363}, 'combined': 0.2509966210503121, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41328439420289353, 'r': 0.28806928468785997, 'f1': 0.33949929513160115}, 'combined': 0.22521240370116116, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 9}
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, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 10
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:20:15.690946: step: 4/531, loss: 0.04511779546737671
2023-01-24 07:20:16.747960: step: 8/531, loss: 0.00462351692840457
2023-01-24 07:20:17.810428: step: 12/531, loss: 0.007168647833168507
2023-01-24 07:20:18.858567: step: 16/531, loss: 0.003161326050758362
2023-01-24 07:20:19.916553: step: 20/531, loss: 0.0013177969958633184
2023-01-24 07:20:20.976242: step: 24/531, loss: 0.002089598448947072
2023-01-24 07:20:22.027718: step: 28/531, loss: 0.0008811427978798747
2023-01-24 07:20:23.074982: step: 32/531, loss: 0.013425305485725403
2023-01-24 07:20:24.141514: step: 36/531, loss: 0.004978492856025696
2023-01-24 07:20:25.189078: step: 40/531, loss: 0.0021314946934580803
2023-01-24 07:20:26.241215: step: 44/531, loss: 0.007731348741799593
2023-01-24 07:20:27.298295: step: 48/531, loss: 0.008214164525270462
2023-01-24 07:20:28.346428: step: 52/531, loss: 0.006958740763366222
2023-01-24 07:20:29.405366: step: 56/531, loss: 0.004736525937914848
2023-01-24 07:20:30.460715: step: 60/531, loss: 0.001544374506920576
2023-01-24 07:20:31.509212: step: 64/531, loss: 0.0007114785257726908
2023-01-24 07:20:32.567695: step: 68/531, loss: 0.00037321209674701095
2023-01-24 07:20:33.636400: step: 72/531, loss: 5.124994004290784e-06
2023-01-24 07:20:34.713959: step: 76/531, loss: 0.0020870547741651535
2023-01-24 07:20:35.760664: step: 80/531, loss: 0.005033628083765507
2023-01-24 07:20:36.833541: step: 84/531, loss: 0.003659485839307308
2023-01-24 07:20:37.884306: step: 88/531, loss: 0.0016210979083552957
2023-01-24 07:20:38.931639: step: 92/531, loss: 0.001539427787065506
2023-01-24 07:20:39.977859: step: 96/531, loss: 0.00696446280926466
2023-01-24 07:20:41.037012: step: 100/531, loss: 0.007940429262816906
2023-01-24 07:20:42.109345: step: 104/531, loss: 0.002993629314005375
2023-01-24 07:20:43.151757: step: 108/531, loss: 0.0011190499644726515
2023-01-24 07:20:44.208378: step: 112/531, loss: 0.0016277168178930879
2023-01-24 07:20:45.260884: step: 116/531, loss: 0.009492279961705208
2023-01-24 07:20:46.326657: step: 120/531, loss: 0.005150929559022188
2023-01-24 07:20:47.395132: step: 124/531, loss: 0.02994631417095661
2023-01-24 07:20:48.452192: step: 128/531, loss: 0.00018145870126318187
2023-01-24 07:20:49.515461: step: 132/531, loss: 0.006231280975043774
2023-01-24 07:20:50.560308: step: 136/531, loss: 0.006994050461798906
2023-01-24 07:20:51.627321: step: 140/531, loss: 0.0008030076860450208
2023-01-24 07:20:52.684889: step: 144/531, loss: 0.01632116734981537
2023-01-24 07:20:53.747930: step: 148/531, loss: 0.006124191451817751
2023-01-24 07:20:54.804752: step: 152/531, loss: 0.001828584005124867
2023-01-24 07:20:55.851383: step: 156/531, loss: 0.0076834834180772305
2023-01-24 07:20:56.902416: step: 160/531, loss: 0.0002667790395207703
2023-01-24 07:20:57.974815: step: 164/531, loss: 0.0019487914396449924
2023-01-24 07:20:59.024087: step: 168/531, loss: 0.0012811741326004267
2023-01-24 07:21:00.075695: step: 172/531, loss: 0.006654617376625538
2023-01-24 07:21:01.167143: step: 176/531, loss: 5.1039300160482526e-05
2023-01-24 07:21:02.223082: step: 180/531, loss: 0.006273975595831871
2023-01-24 07:21:03.277937: step: 184/531, loss: 0.004562840797007084
2023-01-24 07:21:04.354878: step: 188/531, loss: 0.0028800014406442642
2023-01-24 07:21:05.439578: step: 192/531, loss: 0.008555044420063496
2023-01-24 07:21:06.505759: step: 196/531, loss: 0.021640609949827194
2023-01-24 07:21:07.571450: step: 200/531, loss: 0.01305987499654293
2023-01-24 07:21:08.635047: step: 204/531, loss: 0.004544206894934177
2023-01-24 07:21:09.692104: step: 208/531, loss: 0.0005355750909075141
2023-01-24 07:21:10.763484: step: 212/531, loss: 0.003395135747268796
2023-01-24 07:21:11.829719: step: 216/531, loss: 0.01401414256542921
2023-01-24 07:21:12.910309: step: 220/531, loss: 0.0013866559602320194
2023-01-24 07:21:13.985680: step: 224/531, loss: 0.0034855192061513662
2023-01-24 07:21:15.061917: step: 228/531, loss: 0.00919613242149353
2023-01-24 07:21:16.106960: step: 232/531, loss: 0.0018149090465158224
2023-01-24 07:21:17.172505: step: 236/531, loss: 0.005378360860049725
2023-01-24 07:21:18.223072: step: 240/531, loss: 0.010230228304862976
2023-01-24 07:21:19.289217: step: 244/531, loss: 0.006599671207368374
2023-01-24 07:21:20.329651: step: 248/531, loss: 0.0020888138096779585
2023-01-24 07:21:21.377910: step: 252/531, loss: 0.00295943277888
2023-01-24 07:21:22.445428: step: 256/531, loss: 0.014759765937924385
2023-01-24 07:21:23.512037: step: 260/531, loss: 0.0006802362040616572
2023-01-24 07:21:24.574869: step: 264/531, loss: 0.010016325861215591
2023-01-24 07:21:25.627731: step: 268/531, loss: 0.002727009356021881
2023-01-24 07:21:26.688698: step: 272/531, loss: 0.0032889549620449543
2023-01-24 07:21:27.750264: step: 276/531, loss: 0.009291118010878563
2023-01-24 07:21:28.806937: step: 280/531, loss: 0.00533568300306797
2023-01-24 07:21:29.863947: step: 284/531, loss: 0.005063887219876051
2023-01-24 07:21:30.933196: step: 288/531, loss: 0.018546774983406067
2023-01-24 07:21:32.004207: step: 292/531, loss: 0.00047081513912416995
2023-01-24 07:21:33.071097: step: 296/531, loss: 0.003874396439641714
2023-01-24 07:21:34.126280: step: 300/531, loss: 0.006063390057533979
2023-01-24 07:21:35.197805: step: 304/531, loss: 0.0004326277121435851
2023-01-24 07:21:36.264997: step: 308/531, loss: 0.00873729307204485
2023-01-24 07:21:37.321037: step: 312/531, loss: 0.0025322730652987957
2023-01-24 07:21:38.358837: step: 316/531, loss: 0.0004271742363926023
2023-01-24 07:21:39.423514: step: 320/531, loss: 0.0015197329921647906
2023-01-24 07:21:40.477318: step: 324/531, loss: 0.00015667501429561526
2023-01-24 07:21:41.543947: step: 328/531, loss: 0.002340910490602255
2023-01-24 07:21:42.601639: step: 332/531, loss: 0.0005036396323703229
2023-01-24 07:21:43.661338: step: 336/531, loss: 0.00492580933496356
2023-01-24 07:21:44.726278: step: 340/531, loss: 0.0008552538929507136
2023-01-24 07:21:45.798160: step: 344/531, loss: 0.000658549543004483
2023-01-24 07:21:46.864395: step: 348/531, loss: 0.00240096403285861
2023-01-24 07:21:47.914501: step: 352/531, loss: 0.004501339979469776
2023-01-24 07:21:48.962434: step: 356/531, loss: 0.006458848714828491
2023-01-24 07:21:50.013354: step: 360/531, loss: 0.0025434524286538363
2023-01-24 07:21:51.091716: step: 364/531, loss: 0.005225899629294872
2023-01-24 07:21:52.160092: step: 368/531, loss: 0.0015345087740570307
2023-01-24 07:21:53.215828: step: 372/531, loss: 4.23461060563568e-05
2023-01-24 07:21:54.274146: step: 376/531, loss: 0.004633399657905102
2023-01-24 07:21:55.330179: step: 380/531, loss: 0.00588305713608861
2023-01-24 07:21:56.391662: step: 384/531, loss: 0.0019457533489912748
2023-01-24 07:21:57.446057: step: 388/531, loss: 0.011172914877533913
2023-01-24 07:21:58.503928: step: 392/531, loss: 0.0016959008062258363
2023-01-24 07:21:59.562017: step: 396/531, loss: 0.009033746086061
2023-01-24 07:22:00.638086: step: 400/531, loss: 0.0021470552310347557
2023-01-24 07:22:01.707746: step: 404/531, loss: 0.008604781702160835
2023-01-24 07:22:02.765418: step: 408/531, loss: 0.00966779887676239
2023-01-24 07:22:03.840718: step: 412/531, loss: 0.004850557539612055
2023-01-24 07:22:04.910863: step: 416/531, loss: 0.0023350140545517206
2023-01-24 07:22:05.957864: step: 420/531, loss: 0.0017042026156559587
2023-01-24 07:22:07.008129: step: 424/531, loss: 0.015522753819823265
2023-01-24 07:22:08.083714: step: 428/531, loss: 6.732891779392958e-05
2023-01-24 07:22:09.147395: step: 432/531, loss: 0.002678492572158575
2023-01-24 07:22:10.205015: step: 436/531, loss: 0.0007440093904733658
2023-01-24 07:22:11.267942: step: 440/531, loss: 0.003997982479631901
2023-01-24 07:22:12.349624: step: 444/531, loss: 0.006845226977020502
2023-01-24 07:22:13.409219: step: 448/531, loss: 0.0161073449999094
2023-01-24 07:22:14.451870: step: 452/531, loss: 0.00021637490135617554
2023-01-24 07:22:15.498300: step: 456/531, loss: 0.0006897651473991573
2023-01-24 07:22:16.539059: step: 460/531, loss: 0.0058429124765098095
2023-01-24 07:22:17.597010: step: 464/531, loss: 0.0022120114881545305
2023-01-24 07:22:18.649919: step: 468/531, loss: 0.005331730004400015
2023-01-24 07:22:19.723088: step: 472/531, loss: 0.01432296447455883
2023-01-24 07:22:20.790741: step: 476/531, loss: 0.0017438482027500868
2023-01-24 07:22:21.854323: step: 480/531, loss: 0.0020928301382809877
2023-01-24 07:22:22.917259: step: 484/531, loss: 0.008921593427658081
2023-01-24 07:22:23.985485: step: 488/531, loss: 0.002374213421717286
2023-01-24 07:22:25.062152: step: 492/531, loss: 0.009918469935655594
2023-01-24 07:22:26.120529: step: 496/531, loss: 0.004704870283603668
2023-01-24 07:22:27.184957: step: 500/531, loss: 0.02259114384651184
2023-01-24 07:22:28.260742: step: 504/531, loss: 0.009441405534744263
2023-01-24 07:22:29.329196: step: 508/531, loss: 0.004769668448716402
2023-01-24 07:22:30.393723: step: 512/531, loss: 0.002169100334867835
2023-01-24 07:22:31.462916: step: 516/531, loss: 0.008042097091674805
2023-01-24 07:22:32.534748: step: 520/531, loss: 5.85186826356221e-05
2023-01-24 07:22:33.597150: step: 524/531, loss: 0.00021469821513164788
2023-01-24 07:22:34.660722: step: 528/531, loss: 0.001111433026380837
2023-01-24 07:22:35.710735: step: 532/531, loss: 0.002982824109494686
2023-01-24 07:22:36.754815: step: 536/531, loss: 0.00036540350993163884
2023-01-24 07:22:37.807293: step: 540/531, loss: 0.0024884394370019436
2023-01-24 07:22:38.860224: step: 544/531, loss: 0.0012482332531362772
2023-01-24 07:22:39.931868: step: 548/531, loss: 0.013080939650535583
2023-01-24 07:22:40.990071: step: 552/531, loss: 0.005708321928977966
2023-01-24 07:22:42.104312: step: 556/531, loss: 0.005130017176270485
2023-01-24 07:22:43.181733: step: 560/531, loss: 0.00036316082696430385
2023-01-24 07:22:44.259201: step: 564/531, loss: 0.0035906070843338966
2023-01-24 07:22:45.334778: step: 568/531, loss: 0.009966195560991764
2023-01-24 07:22:46.408809: step: 572/531, loss: 0.0015761046670377254
2023-01-24 07:22:47.455604: step: 576/531, loss: 0.0016983483219519258
2023-01-24 07:22:48.510325: step: 580/531, loss: 0.005861691664904356
2023-01-24 07:22:49.589194: step: 584/531, loss: 0.0020601532887667418
2023-01-24 07:22:50.648534: step: 588/531, loss: 0.005512963514775038
2023-01-24 07:22:51.713947: step: 592/531, loss: 0.002283709356561303
2023-01-24 07:22:52.792356: step: 596/531, loss: 0.010348460637032986
2023-01-24 07:22:53.869504: step: 600/531, loss: 0.002217413391917944
2023-01-24 07:22:54.940253: step: 604/531, loss: 0.017472414299845695
2023-01-24 07:22:55.997000: step: 608/531, loss: 0.0005667863879352808
2023-01-24 07:22:57.060658: step: 612/531, loss: 0.005727748386561871
2023-01-24 07:22:58.099604: step: 616/531, loss: 0.0021054695826023817
2023-01-24 07:22:59.151499: step: 620/531, loss: 0.005775059573352337
2023-01-24 07:23:00.211170: step: 624/531, loss: 0.0025534944143146276
2023-01-24 07:23:01.278906: step: 628/531, loss: 0.029104895889759064
2023-01-24 07:23:02.345117: step: 632/531, loss: 0.0024954474065452814
2023-01-24 07:23:03.414099: step: 636/531, loss: 0.008792751468718052
2023-01-24 07:23:04.485799: step: 640/531, loss: 0.007368545047938824
2023-01-24 07:23:05.538602: step: 644/531, loss: 0.004871091805398464
2023-01-24 07:23:06.614677: step: 648/531, loss: 0.006081071682274342
2023-01-24 07:23:07.686458: step: 652/531, loss: 0.0033418633975088596
2023-01-24 07:23:08.752269: step: 656/531, loss: 0.00267624668776989
2023-01-24 07:23:09.799721: step: 660/531, loss: 0.0
2023-01-24 07:23:10.857310: step: 664/531, loss: 0.006120113655924797
2023-01-24 07:23:11.937095: step: 668/531, loss: 0.008462866768240929
2023-01-24 07:23:12.995165: step: 672/531, loss: 0.0036988535430282354
2023-01-24 07:23:14.063404: step: 676/531, loss: 0.01724778302013874
2023-01-24 07:23:15.118755: step: 680/531, loss: 0.0038293784018605947
2023-01-24 07:23:16.180073: step: 684/531, loss: 0.00032143128919415176
2023-01-24 07:23:17.263674: step: 688/531, loss: 0.0030675882007926702
2023-01-24 07:23:18.303860: step: 692/531, loss: 0.006303122267127037
2023-01-24 07:23:19.362582: step: 696/531, loss: 0.00011737759632524103
2023-01-24 07:23:20.413965: step: 700/531, loss: 0.008816881105303764
2023-01-24 07:23:21.483132: step: 704/531, loss: 0.0017857117345556617
2023-01-24 07:23:22.549028: step: 708/531, loss: 0.0015491386875510216
2023-01-24 07:23:23.608703: step: 712/531, loss: 5.8598543546395376e-05
2023-01-24 07:23:24.681028: step: 716/531, loss: 0.002664199797436595
2023-01-24 07:23:25.733195: step: 720/531, loss: 0.0030972673557698727
2023-01-24 07:23:26.798314: step: 724/531, loss: 0.0014562207506969571
2023-01-24 07:23:27.869560: step: 728/531, loss: 0.009958475828170776
2023-01-24 07:23:28.939147: step: 732/531, loss: 0.005514010787010193
2023-01-24 07:23:30.009725: step: 736/531, loss: 0.00345690012909472
2023-01-24 07:23:31.079682: step: 740/531, loss: 0.0007793250260874629
2023-01-24 07:23:32.137361: step: 744/531, loss: 0.00010515483882045373
2023-01-24 07:23:33.207404: step: 748/531, loss: 0.003168870694935322
2023-01-24 07:23:34.269027: step: 752/531, loss: 0.005417739972472191
2023-01-24 07:23:35.326843: step: 756/531, loss: 1.2698379805442528e-06
2023-01-24 07:23:36.396063: step: 760/531, loss: 0.0014340360648930073
2023-01-24 07:23:37.470201: step: 764/531, loss: 0.05637550354003906
2023-01-24 07:23:38.550090: step: 768/531, loss: 0.003015951719135046
2023-01-24 07:23:39.613386: step: 772/531, loss: 0.004437098279595375
2023-01-24 07:23:40.688252: step: 776/531, loss: 0.00028024762286804616
2023-01-24 07:23:41.748793: step: 780/531, loss: 0.00016136518388520926
2023-01-24 07:23:42.833646: step: 784/531, loss: 0.025463992729783058
2023-01-24 07:23:43.907190: step: 788/531, loss: 0.003796741832047701
2023-01-24 07:23:44.964924: step: 792/531, loss: 0.0009928278159350157
2023-01-24 07:23:46.032283: step: 796/531, loss: 0.0020523546263575554
2023-01-24 07:23:47.106483: step: 800/531, loss: 0.0010502723744139075
2023-01-24 07:23:48.188206: step: 804/531, loss: 0.0008379457285627723
2023-01-24 07:23:49.268701: step: 808/531, loss: 0.058690670877695084
2023-01-24 07:23:50.323416: step: 812/531, loss: 0.0033038626424968243
2023-01-24 07:23:51.384262: step: 816/531, loss: 0.000611974741332233
2023-01-24 07:23:52.437204: step: 820/531, loss: 0.008932569995522499
2023-01-24 07:23:53.509337: step: 824/531, loss: 0.0007279608398675919
2023-01-24 07:23:54.563355: step: 828/531, loss: 3.9632912375964224e-05
2023-01-24 07:23:55.624010: step: 832/531, loss: 0.005446029826998711
2023-01-24 07:23:56.689484: step: 836/531, loss: 0.007040816824883223
2023-01-24 07:23:57.747059: step: 840/531, loss: 0.002783367410302162
2023-01-24 07:23:58.831816: step: 844/531, loss: 0.010686303488910198
2023-01-24 07:23:59.901361: step: 848/531, loss: 0.0016936537576839328
2023-01-24 07:24:00.981104: step: 852/531, loss: 0.005468764342367649
2023-01-24 07:24:02.038498: step: 856/531, loss: 0.0017886536661535501
2023-01-24 07:24:03.109018: step: 860/531, loss: 0.018694577738642693
2023-01-24 07:24:04.172431: step: 864/531, loss: 0.0005616036360152066
2023-01-24 07:24:05.225060: step: 868/531, loss: 0.0026409996207803488
2023-01-24 07:24:06.297191: step: 872/531, loss: 0.01968526467680931
2023-01-24 07:24:07.375356: step: 876/531, loss: 0.0026152569334954023
2023-01-24 07:24:08.430318: step: 880/531, loss: 0.008349597454071045
2023-01-24 07:24:09.524002: step: 884/531, loss: 0.004530239850282669
2023-01-24 07:24:10.592036: step: 888/531, loss: 0.002871243515983224
2023-01-24 07:24:11.668488: step: 892/531, loss: 0.00841600727289915
2023-01-24 07:24:12.742892: step: 896/531, loss: 0.0026405765675008297
2023-01-24 07:24:13.822613: step: 900/531, loss: 0.009743747301399708
2023-01-24 07:24:14.879947: step: 904/531, loss: 0.004232747945934534
2023-01-24 07:24:15.951124: step: 908/531, loss: 0.02207007445394993
2023-01-24 07:24:17.034153: step: 912/531, loss: 0.0035033232998102903
2023-01-24 07:24:18.091475: step: 916/531, loss: 0.005719034466892481
2023-01-24 07:24:19.148016: step: 920/531, loss: 0.001169433118775487
2023-01-24 07:24:20.190205: step: 924/531, loss: 0.009069438092410564
2023-01-24 07:24:21.249622: step: 928/531, loss: 0.008030245080590248
2023-01-24 07:24:22.313819: step: 932/531, loss: 0.0021121983882039785
2023-01-24 07:24:23.378008: step: 936/531, loss: 0.004578235559165478
2023-01-24 07:24:24.432768: step: 940/531, loss: 0.0004743619356304407
2023-01-24 07:24:25.489880: step: 944/531, loss: 0.004270483274012804
2023-01-24 07:24:26.558146: step: 948/531, loss: 0.01703280583024025
2023-01-24 07:24:27.619397: step: 952/531, loss: 0.006143835838884115
2023-01-24 07:24:28.695209: step: 956/531, loss: 0.00525349285453558
2023-01-24 07:24:29.739661: step: 960/531, loss: 0.004162059165537357
2023-01-24 07:24:30.824418: step: 964/531, loss: 0.003167388029396534
2023-01-24 07:24:31.901148: step: 968/531, loss: 0.047397419810295105
2023-01-24 07:24:32.966843: step: 972/531, loss: 0.004545622505247593
2023-01-24 07:24:34.038484: step: 976/531, loss: 0.004120222758501768
2023-01-24 07:24:35.094744: step: 980/531, loss: 0.0027510409709066153
2023-01-24 07:24:36.150044: step: 984/531, loss: 0.012611347250640392
2023-01-24 07:24:37.217123: step: 988/531, loss: 0.00018220402125734836
2023-01-24 07:24:38.281553: step: 992/531, loss: 0.005045078694820404
2023-01-24 07:24:39.350565: step: 996/531, loss: 0.00630967877805233
2023-01-24 07:24:40.423702: step: 1000/531, loss: 0.008546345867216587
2023-01-24 07:24:41.497633: step: 1004/531, loss: 7.393538544420153e-05
2023-01-24 07:24:42.613559: step: 1008/531, loss: 0.010151691734790802
2023-01-24 07:24:43.679839: step: 1012/531, loss: 0.0058904788456857204
2023-01-24 07:24:44.732162: step: 1016/531, loss: 0.0030716576147824526
2023-01-24 07:24:45.792690: step: 1020/531, loss: 0.00032007074332796037
2023-01-24 07:24:46.852192: step: 1024/531, loss: 0.0026038538198918104
2023-01-24 07:24:47.946210: step: 1028/531, loss: 0.0004469689156394452
2023-01-24 07:24:49.029381: step: 1032/531, loss: 0.005721640307456255
2023-01-24 07:24:50.088223: step: 1036/531, loss: 0.011646556667983532
2023-01-24 07:24:51.150133: step: 1040/531, loss: 0.0005736255552619696
2023-01-24 07:24:52.207600: step: 1044/531, loss: 0.00048291642451658845
2023-01-24 07:24:53.259892: step: 1048/531, loss: 0.006947695277631283
2023-01-24 07:24:54.320195: step: 1052/531, loss: 0.002741861157119274
2023-01-24 07:24:55.384035: step: 1056/531, loss: 0.002739276271313429
2023-01-24 07:24:56.438877: step: 1060/531, loss: 0.003842536825686693
2023-01-24 07:24:57.487046: step: 1064/531, loss: 0.009659718722105026
2023-01-24 07:24:58.546501: step: 1068/531, loss: 0.00011684564378811046
2023-01-24 07:24:59.607181: step: 1072/531, loss: 0.0014100978150963783
2023-01-24 07:25:00.675072: step: 1076/531, loss: 0.014100932516157627
2023-01-24 07:25:01.730859: step: 1080/531, loss: 0.018242180347442627
2023-01-24 07:25:02.814457: step: 1084/531, loss: 0.008263876661658287
2023-01-24 07:25:03.877334: step: 1088/531, loss: 0.004137961193919182
2023-01-24 07:25:04.935207: step: 1092/531, loss: 0.004951735492795706
2023-01-24 07:25:05.993549: step: 1096/531, loss: 0.008860207162797451
2023-01-24 07:25:07.048449: step: 1100/531, loss: 0.0010698740370571613
2023-01-24 07:25:08.100914: step: 1104/531, loss: 0.005388192366808653
2023-01-24 07:25:09.157991: step: 1108/531, loss: 0.00560379633679986
2023-01-24 07:25:10.207291: step: 1112/531, loss: 0.0033469530753791332
2023-01-24 07:25:11.276103: step: 1116/531, loss: 0.007595570757985115
2023-01-24 07:25:12.341968: step: 1120/531, loss: 0.00023423753737006336
2023-01-24 07:25:13.409491: step: 1124/531, loss: 0.004273217637091875
2023-01-24 07:25:14.471707: step: 1128/531, loss: 0.002667166292667389
2023-01-24 07:25:15.545078: step: 1132/531, loss: 0.0007323683821596205
2023-01-24 07:25:16.616843: step: 1136/531, loss: 0.0010395990684628487
2023-01-24 07:25:17.681292: step: 1140/531, loss: 0.0021878022234886885
2023-01-24 07:25:18.736971: step: 1144/531, loss: 0.0020483252592384815
2023-01-24 07:25:19.786670: step: 1148/531, loss: 0.0047643911093473434
2023-01-24 07:25:20.848810: step: 1152/531, loss: 0.0013432919513434172
2023-01-24 07:25:21.927363: step: 1156/531, loss: 6.042409222573042e-05
2023-01-24 07:25:22.981774: step: 1160/531, loss: 0.033806730061769485
2023-01-24 07:25:24.042049: step: 1164/531, loss: 0.007924630306661129
2023-01-24 07:25:25.084665: step: 1168/531, loss: 0.005530583672225475
2023-01-24 07:25:26.149652: step: 1172/531, loss: 0.004673686809837818
2023-01-24 07:25:27.222048: step: 1176/531, loss: 0.01001940667629242
2023-01-24 07:25:28.283881: step: 1180/531, loss: 0.004419660195708275
2023-01-24 07:25:29.339028: step: 1184/531, loss: 0.004453849513083696
2023-01-24 07:25:30.397159: step: 1188/531, loss: 0.00010570708400337026
2023-01-24 07:25:31.474642: step: 1192/531, loss: 0.015451865270733833
2023-01-24 07:25:32.542747: step: 1196/531, loss: 0.006219562143087387
2023-01-24 07:25:33.591481: step: 1200/531, loss: 0.006642982363700867
2023-01-24 07:25:34.686073: step: 1204/531, loss: 0.03245781734585762
2023-01-24 07:25:35.754138: step: 1208/531, loss: 0.012482921592891216
2023-01-24 07:25:36.828223: step: 1212/531, loss: 0.0158814899623394
2023-01-24 07:25:37.886732: step: 1216/531, loss: 0.00147052644751966
2023-01-24 07:25:38.931839: step: 1220/531, loss: 0.011913049034774303
2023-01-24 07:25:40.018088: step: 1224/531, loss: 0.0028967829421162605
2023-01-24 07:25:41.080838: step: 1228/531, loss: 0.016320789232850075
2023-01-24 07:25:42.185696: step: 1232/531, loss: 0.0002468716411385685
2023-01-24 07:25:43.257916: step: 1236/531, loss: 0.013635863550007343
2023-01-24 07:25:44.311539: step: 1240/531, loss: 0.00041916221380233765
2023-01-24 07:25:45.390033: step: 1244/531, loss: 0.0034596596378833055
2023-01-24 07:25:46.442312: step: 1248/531, loss: 0.004369057714939117
2023-01-24 07:25:47.499268: step: 1252/531, loss: 1.7405774997314438e-05
2023-01-24 07:25:48.573191: step: 1256/531, loss: 0.01018279604613781
2023-01-24 07:25:49.641523: step: 1260/531, loss: 0.0038037945050746202
2023-01-24 07:25:50.712191: step: 1264/531, loss: 0.022700605913996696
2023-01-24 07:25:51.768784: step: 1268/531, loss: 0.003217222634702921
2023-01-24 07:25:52.817451: step: 1272/531, loss: 0.0008606911869719625
2023-01-24 07:25:53.891209: step: 1276/531, loss: 0.0039140949957072735
2023-01-24 07:25:54.973713: step: 1280/531, loss: 0.031579140573740005
2023-01-24 07:25:56.021715: step: 1284/531, loss: 9.058567957254127e-05
2023-01-24 07:25:57.090051: step: 1288/531, loss: 0.007591401692479849
2023-01-24 07:25:58.153020: step: 1292/531, loss: 0.007560128811746836
2023-01-24 07:25:59.208684: step: 1296/531, loss: 0.0005940622068010271
2023-01-24 07:26:00.271996: step: 1300/531, loss: 0.006782899145036936
2023-01-24 07:26:01.339575: step: 1304/531, loss: 0.0010394651908427477
2023-01-24 07:26:02.438653: step: 1308/531, loss: 0.013745302334427834
2023-01-24 07:26:03.506578: step: 1312/531, loss: 0.004006646573543549
2023-01-24 07:26:04.578368: step: 1316/531, loss: 0.012290666811168194
2023-01-24 07:26:05.624434: step: 1320/531, loss: 0.002449002582579851
2023-01-24 07:26:06.667092: step: 1324/531, loss: 0.0008735805167816579
2023-01-24 07:26:07.727981: step: 1328/531, loss: 0.0008889613091014326
2023-01-24 07:26:08.789905: step: 1332/531, loss: 0.0036207358352839947
2023-01-24 07:26:09.833511: step: 1336/531, loss: 0.00499630207195878
2023-01-24 07:26:10.886050: step: 1340/531, loss: 0.0027833532076328993
2023-01-24 07:26:11.968860: step: 1344/531, loss: 0.0018036727560684085
2023-01-24 07:26:13.028806: step: 1348/531, loss: 0.0016338448040187359
2023-01-24 07:26:14.090006: step: 1352/531, loss: 0.005640815943479538
2023-01-24 07:26:15.160856: step: 1356/531, loss: 0.002958085620775819
2023-01-24 07:26:16.223910: step: 1360/531, loss: 0.025196939706802368
2023-01-24 07:26:17.282975: step: 1364/531, loss: 0.0037646417040377855
2023-01-24 07:26:18.354058: step: 1368/531, loss: 0.004507889039814472
2023-01-24 07:26:19.415331: step: 1372/531, loss: 0.00010726918844738975
2023-01-24 07:26:20.485268: step: 1376/531, loss: 0.0027078590355813503
2023-01-24 07:26:21.533898: step: 1380/531, loss: 0.0038744057528674603
2023-01-24 07:26:22.580640: step: 1384/531, loss: 0.0016367561183869839
2023-01-24 07:26:23.654212: step: 1388/531, loss: 0.0031484398059546947
2023-01-24 07:26:24.715018: step: 1392/531, loss: 0.0027061980217695236
2023-01-24 07:26:25.774658: step: 1396/531, loss: 0.007732085883617401
2023-01-24 07:26:26.836084: step: 1400/531, loss: 0.003513761330395937
2023-01-24 07:26:27.885941: step: 1404/531, loss: 0.03504456579685211
2023-01-24 07:26:28.957265: step: 1408/531, loss: 0.00013752601807937026
2023-01-24 07:26:30.014846: step: 1412/531, loss: 0.007317660842090845
2023-01-24 07:26:31.078644: step: 1416/531, loss: 0.0006424398743547499
2023-01-24 07:26:32.159507: step: 1420/531, loss: 0.0016001794720068574
2023-01-24 07:26:33.216545: step: 1424/531, loss: 0.1215495616197586
2023-01-24 07:26:34.270265: step: 1428/531, loss: 0.014077279716730118
2023-01-24 07:26:35.322336: step: 1432/531, loss: 0.0013367494102567434
2023-01-24 07:26:36.391115: step: 1436/531, loss: 0.009776687249541283
2023-01-24 07:26:37.450096: step: 1440/531, loss: 0.0032634963281452656
2023-01-24 07:26:38.510027: step: 1444/531, loss: 0.005308025516569614
2023-01-24 07:26:39.565799: step: 1448/531, loss: 0.050706665962934494
2023-01-24 07:26:40.615725: step: 1452/531, loss: 0.004951969254761934
2023-01-24 07:26:41.674801: step: 1456/531, loss: 0.002046182518824935
2023-01-24 07:26:42.732467: step: 1460/531, loss: 0.0020493913907557726
2023-01-24 07:26:43.779024: step: 1464/531, loss: 0.00031897457665763795
2023-01-24 07:26:44.844279: step: 1468/531, loss: 0.00032071577152237296
2023-01-24 07:26:45.917968: step: 1472/531, loss: 0.00449588056653738
2023-01-24 07:26:46.972905: step: 1476/531, loss: 0.015204568393528461
2023-01-24 07:26:48.022375: step: 1480/531, loss: 0.018791966140270233
2023-01-24 07:26:49.074610: step: 1484/531, loss: 0.0008019257802516222
2023-01-24 07:26:50.148057: step: 1488/531, loss: 0.004643011372536421
2023-01-24 07:26:51.204070: step: 1492/531, loss: 0.00012099656305508688
2023-01-24 07:26:52.253055: step: 1496/531, loss: 0.0012349931057542562
2023-01-24 07:26:53.305568: step: 1500/531, loss: 0.0036675555165857077
2023-01-24 07:26:54.354794: step: 1504/531, loss: 0.006605407223105431
2023-01-24 07:26:55.416813: step: 1508/531, loss: 0.007399989757686853
2023-01-24 07:26:56.473500: step: 1512/531, loss: 0.0051831589080393314
2023-01-24 07:26:57.550636: step: 1516/531, loss: 0.005010760389268398
2023-01-24 07:26:58.637867: step: 1520/531, loss: 0.0036288737319409847
2023-01-24 07:26:59.686026: step: 1524/531, loss: 0.008250990882515907
2023-01-24 07:27:00.745022: step: 1528/531, loss: 0.004854382947087288
2023-01-24 07:27:01.799134: step: 1532/531, loss: 0.0020668278448283672
2023-01-24 07:27:02.868911: step: 1536/531, loss: 0.00876717921346426
2023-01-24 07:27:03.918288: step: 1540/531, loss: 0.009252313524484634
2023-01-24 07:27:04.978623: step: 1544/531, loss: 0.0042928964830935
2023-01-24 07:27:06.042331: step: 1548/531, loss: 0.006253547966480255
2023-01-24 07:27:07.102914: step: 1552/531, loss: 0.005105405114591122
2023-01-24 07:27:08.174763: step: 1556/531, loss: 0.00194579700473696
2023-01-24 07:27:09.234301: step: 1560/531, loss: 0.013849948532879353
2023-01-24 07:27:10.302319: step: 1564/531, loss: 0.005193711258471012
2023-01-24 07:27:11.356163: step: 1568/531, loss: 0.004304729402065277
2023-01-24 07:27:12.435324: step: 1572/531, loss: 0.002057864563539624
2023-01-24 07:27:13.507232: step: 1576/531, loss: 0.004682786297053099
2023-01-24 07:27:14.562026: step: 1580/531, loss: 0.009445921517908573
2023-01-24 07:27:15.624683: step: 1584/531, loss: 0.0007583817932754755
2023-01-24 07:27:16.678936: step: 1588/531, loss: 0.0024650886189192533
2023-01-24 07:27:17.727322: step: 1592/531, loss: 0.004287093412131071
2023-01-24 07:27:18.788804: step: 1596/531, loss: 0.004548561293631792
2023-01-24 07:27:19.854924: step: 1600/531, loss: 0.00031103467335924506
2023-01-24 07:27:20.923167: step: 1604/531, loss: 0.004302352201193571
2023-01-24 07:27:21.977043: step: 1608/531, loss: 0.014272102154791355
2023-01-24 07:27:23.036321: step: 1612/531, loss: 0.0028163467068225145
2023-01-24 07:27:24.102922: step: 1616/531, loss: 0.005952394567430019
2023-01-24 07:27:25.156709: step: 1620/531, loss: 0.004385761916637421
2023-01-24 07:27:26.233733: step: 1624/531, loss: 0.030985429883003235
2023-01-24 07:27:27.299543: step: 1628/531, loss: 0.008499976247549057
2023-01-24 07:27:28.358277: step: 1632/531, loss: 0.006252588704228401
2023-01-24 07:27:29.424239: step: 1636/531, loss: 0.0013014872092753649
2023-01-24 07:27:30.503159: step: 1640/531, loss: 0.009132741019129753
2023-01-24 07:27:31.596862: step: 1644/531, loss: 8.013339538592845e-05
2023-01-24 07:27:32.661519: step: 1648/531, loss: 0.002650429494678974
2023-01-24 07:27:33.737747: step: 1652/531, loss: 0.0024341337848454714
2023-01-24 07:27:34.784973: step: 1656/531, loss: 0.003223975421860814
2023-01-24 07:27:35.836571: step: 1660/531, loss: 0.0006092719850130379
2023-01-24 07:27:36.892457: step: 1664/531, loss: 0.0014739006292074919
2023-01-24 07:27:37.942749: step: 1668/531, loss: 0.0009018494747579098
2023-01-24 07:27:38.993241: step: 1672/531, loss: 0.005439567845314741
2023-01-24 07:27:40.069267: step: 1676/531, loss: 0.003644815878942609
2023-01-24 07:27:41.135473: step: 1680/531, loss: 0.0072359307669103146
2023-01-24 07:27:42.199873: step: 1684/531, loss: 0.0013825768837705255
2023-01-24 07:27:43.240138: step: 1688/531, loss: 0.0012426445027813315
2023-01-24 07:27:44.302476: step: 1692/531, loss: 0.025410452857613564
2023-01-24 07:27:45.355547: step: 1696/531, loss: 0.011287734843790531
2023-01-24 07:27:46.410817: step: 1700/531, loss: 0.007642117794603109
2023-01-24 07:27:47.467147: step: 1704/531, loss: 0.0025312243960797787
2023-01-24 07:27:48.538432: step: 1708/531, loss: 0.009996318258345127
2023-01-24 07:27:49.579874: step: 1712/531, loss: 0.0017377582844346762
2023-01-24 07:27:50.653260: step: 1716/531, loss: 0.008395014330744743
2023-01-24 07:27:51.702168: step: 1720/531, loss: 3.8053538446547464e-05
2023-01-24 07:27:52.792706: step: 1724/531, loss: 0.006723566446453333
2023-01-24 07:27:53.847423: step: 1728/531, loss: 0.004380987025797367
2023-01-24 07:27:54.914846: step: 1732/531, loss: 0.0042249285615980625
2023-01-24 07:27:55.974989: step: 1736/531, loss: 0.002711418317630887
2023-01-24 07:27:57.039238: step: 1740/531, loss: 0.00038981231045909226
2023-01-24 07:27:58.084197: step: 1744/531, loss: 0.003361661918461323
2023-01-24 07:27:59.159181: step: 1748/531, loss: 0.002664417028427124
2023-01-24 07:28:00.216608: step: 1752/531, loss: 0.0004814085550606251
2023-01-24 07:28:01.279962: step: 1756/531, loss: 0.005907909013330936
2023-01-24 07:28:02.353805: step: 1760/531, loss: 0.00395190017297864
2023-01-24 07:28:03.410465: step: 1764/531, loss: 0.0037833317182958126
2023-01-24 07:28:04.467337: step: 1768/531, loss: 0.01780518889427185
2023-01-24 07:28:05.527214: step: 1772/531, loss: 0.0016816816059872508
2023-01-24 07:28:06.588123: step: 1776/531, loss: 0.0006575814331881702
2023-01-24 07:28:07.627004: step: 1780/531, loss: 9.967300229618559e-07
2023-01-24 07:28:08.683180: step: 1784/531, loss: 0.00028070222469978034
2023-01-24 07:28:09.775524: step: 1788/531, loss: 0.02735465206205845
2023-01-24 07:28:10.860610: step: 1792/531, loss: 0.0011749131372198462
2023-01-24 07:28:11.937626: step: 1796/531, loss: 0.012724286876618862
2023-01-24 07:28:12.995664: step: 1800/531, loss: 0.0013588605215772986
2023-01-24 07:28:14.063829: step: 1804/531, loss: 0.007292529102414846
2023-01-24 07:28:15.128157: step: 1808/531, loss: 0.004301643464714289
2023-01-24 07:28:16.187599: step: 1812/531, loss: 0.006009149830788374
2023-01-24 07:28:17.255020: step: 1816/531, loss: 0.0023827701807022095
2023-01-24 07:28:18.307265: step: 1820/531, loss: 0.002875205362215638
2023-01-24 07:28:19.361299: step: 1824/531, loss: 0.01805732026696205
2023-01-24 07:28:20.411592: step: 1828/531, loss: 0.0004128643777221441
2023-01-24 07:28:21.464202: step: 1832/531, loss: 0.0007312208763323724
2023-01-24 07:28:22.506058: step: 1836/531, loss: 0.0012952744727954268
2023-01-24 07:28:23.564587: step: 1840/531, loss: 0.0067427270114421844
2023-01-24 07:28:24.644900: step: 1844/531, loss: 0.009244879707694054
2023-01-24 07:28:25.706363: step: 1848/531, loss: 0.003126917639747262
2023-01-24 07:28:26.747565: step: 1852/531, loss: 0.003114111954346299
2023-01-24 07:28:27.814448: step: 1856/531, loss: 0.004199311137199402
2023-01-24 07:28:28.866706: step: 1860/531, loss: 0.006388251204043627
2023-01-24 07:28:29.937093: step: 1864/531, loss: 0.023254306986927986
2023-01-24 07:28:30.996785: step: 1868/531, loss: 0.0038735060952603817
2023-01-24 07:28:32.055796: step: 1872/531, loss: 0.0016032494604587555
2023-01-24 07:28:33.136315: step: 1876/531, loss: 0.027199311181902885
2023-01-24 07:28:34.195034: step: 1880/531, loss: 0.004051702097058296
2023-01-24 07:28:35.254206: step: 1884/531, loss: 0.020427949726581573
2023-01-24 07:28:36.315765: step: 1888/531, loss: 0.03202217444777489
2023-01-24 07:28:37.384349: step: 1892/531, loss: 0.003984553273767233
2023-01-24 07:28:38.461934: step: 1896/531, loss: 0.009155458770692348
2023-01-24 07:28:39.525977: step: 1900/531, loss: 0.025644440203905106
2023-01-24 07:28:40.576664: step: 1904/531, loss: 0.007649907376617193
2023-01-24 07:28:41.622223: step: 1908/531, loss: 0.00028209033189341426
2023-01-24 07:28:42.687733: step: 1912/531, loss: 0.0008907606243155897
2023-01-24 07:28:43.756393: step: 1916/531, loss: 0.01240821834653616
2023-01-24 07:28:44.833833: step: 1920/531, loss: 0.00012892595259472728
2023-01-24 07:28:45.897847: step: 1924/531, loss: 0.0014187126653268933
2023-01-24 07:28:46.951651: step: 1928/531, loss: 0.010740848258137703
2023-01-24 07:28:48.017123: step: 1932/531, loss: 0.0031338625121861696
2023-01-24 07:28:49.072474: step: 1936/531, loss: 0.0023126755841076374
2023-01-24 07:28:50.114342: step: 1940/531, loss: 0.0002548302581999451
2023-01-24 07:28:51.173245: step: 1944/531, loss: 0.0006706409621983767
2023-01-24 07:28:52.232312: step: 1948/531, loss: 0.00010857357119675726
2023-01-24 07:28:53.293163: step: 1952/531, loss: 0.002403313061222434
2023-01-24 07:28:54.347645: step: 1956/531, loss: 0.03757341951131821
2023-01-24 07:28:55.409352: step: 1960/531, loss: 0.005053660366684198
2023-01-24 07:28:56.485958: step: 1964/531, loss: 0.006158989388495684
2023-01-24 07:28:57.539242: step: 1968/531, loss: 0.00041146628791466355
2023-01-24 07:28:58.601561: step: 1972/531, loss: 0.0026964074932038784
2023-01-24 07:28:59.665473: step: 1976/531, loss: 0.003737696446478367
2023-01-24 07:29:00.738098: step: 1980/531, loss: 0.004402313847094774
2023-01-24 07:29:01.786675: step: 1984/531, loss: 0.016468999907374382
2023-01-24 07:29:02.832173: step: 1988/531, loss: 0.007842383347451687
2023-01-24 07:29:03.910307: step: 1992/531, loss: 0.011507249437272549
2023-01-24 07:29:04.970296: step: 1996/531, loss: 0.0001733368553686887
2023-01-24 07:29:06.018971: step: 2000/531, loss: 0.012670803815126419
2023-01-24 07:29:07.082418: step: 2004/531, loss: 0.006167001090943813
2023-01-24 07:29:08.142557: step: 2008/531, loss: 0.005690338090062141
2023-01-24 07:29:09.203516: step: 2012/531, loss: 0.004677900578826666
2023-01-24 07:29:10.269719: step: 2016/531, loss: 0.018740715458989143
2023-01-24 07:29:11.323039: step: 2020/531, loss: 0.0238112211227417
2023-01-24 07:29:12.396914: step: 2024/531, loss: 0.0008958554244600236
2023-01-24 07:29:13.450397: step: 2028/531, loss: 0.009894277900457382
2023-01-24 07:29:14.509031: step: 2032/531, loss: 0.002333128359168768
2023-01-24 07:29:15.570279: step: 2036/531, loss: 0.0021440156269818544
2023-01-24 07:29:16.622112: step: 2040/531, loss: 0.005679186899214983
2023-01-24 07:29:17.696076: step: 2044/531, loss: 0.00939517468214035
2023-01-24 07:29:18.751396: step: 2048/531, loss: 0.008401891216635704
2023-01-24 07:29:19.818556: step: 2052/531, loss: 0.0008273826097138226
2023-01-24 07:29:20.873777: step: 2056/531, loss: 0.03998059406876564
2023-01-24 07:29:21.937942: step: 2060/531, loss: 0.006508908700197935
2023-01-24 07:29:23.008663: step: 2064/531, loss: 0.0081448620185256
2023-01-24 07:29:24.075418: step: 2068/531, loss: 0.0030839676037430763
2023-01-24 07:29:25.148751: step: 2072/531, loss: 0.0016284179873764515
2023-01-24 07:29:26.206206: step: 2076/531, loss: 0.006517891772091389
2023-01-24 07:29:27.272607: step: 2080/531, loss: 0.0023467401042580605
2023-01-24 07:29:28.334038: step: 2084/531, loss: 0.0006494150729849935
2023-01-24 07:29:29.417247: step: 2088/531, loss: 0.006998279597610235
2023-01-24 07:29:30.486761: step: 2092/531, loss: 0.0007310719229280949
2023-01-24 07:29:31.527628: step: 2096/531, loss: 0.0005386866978369653
2023-01-24 07:29:32.586656: step: 2100/531, loss: 0.002123769372701645
2023-01-24 07:29:33.627375: step: 2104/531, loss: 0.002239992842078209
2023-01-24 07:29:34.693443: step: 2108/531, loss: 0.00496734119951725
2023-01-24 07:29:35.745582: step: 2112/531, loss: 0.03868440166115761
2023-01-24 07:29:36.812232: step: 2116/531, loss: 0.00293820071965456
2023-01-24 07:29:37.870965: step: 2120/531, loss: 0.001741659129038453
2023-01-24 07:29:38.928992: step: 2124/531, loss: 0.019097991287708282
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38946156387225256, 'r': 0.31851600384998263, 'f1': 0.3504341002691876}, 'combined': 0.25821460019834874, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3869855337605451, 'r': 0.27462363847569793, 'f1': 0.32126330703538925}, 'combined': 0.20116487449879517, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3745872916723868, 'r': 0.3362045331329012, 'f1': 0.3543595779220779}, 'combined': 0.2611070574162679, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3885716069504353, 'r': 0.2866109778949108, 'f1': 0.3298926564457251}, 'combined': 0.2044405194874916, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3661654515251058, 'r': 0.3279508408346299, 'f1': 0.34600619243213204}, 'combined': 0.2549519312657815, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41564952697765195, 'r': 0.2878438563740638, 'f1': 0.3401372794020636}, 'combined': 0.22563562098948775, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 10}
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, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 11
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:32:01.754769: step: 4/531, loss: 0.011861962266266346
2023-01-24 07:32:02.802570: step: 8/531, loss: 0.008071650750935078
2023-01-24 07:32:03.853683: step: 12/531, loss: 0.000208403987926431
2023-01-24 07:32:04.911106: step: 16/531, loss: 0.0010404442436993122
2023-01-24 07:32:05.971481: step: 20/531, loss: 0.001116069033741951
2023-01-24 07:32:07.015845: step: 24/531, loss: 0.003468763316050172
2023-01-24 07:32:08.073020: step: 28/531, loss: 0.004135690163820982
2023-01-24 07:32:09.137484: step: 32/531, loss: 0.0073848385363817215
2023-01-24 07:32:10.178739: step: 36/531, loss: 0.0020591611973941326
2023-01-24 07:32:11.238283: step: 40/531, loss: 0.0019269976764917374
2023-01-24 07:32:12.283577: step: 44/531, loss: 0.002490139799192548
2023-01-24 07:32:13.340695: step: 48/531, loss: 0.005024838726967573
2023-01-24 07:32:14.393948: step: 52/531, loss: 0.004694833420217037
2023-01-24 07:32:15.445927: step: 56/531, loss: 0.00994531624019146
2023-01-24 07:32:16.498063: step: 60/531, loss: 0.007700231857597828
2023-01-24 07:32:17.545002: step: 64/531, loss: 0.013530361466109753
2023-01-24 07:32:18.597165: step: 68/531, loss: 0.002030949341133237
2023-01-24 07:32:19.658789: step: 72/531, loss: 0.0021307142451405525
2023-01-24 07:32:20.722768: step: 76/531, loss: 0.0007005725055932999
2023-01-24 07:32:21.780050: step: 80/531, loss: 3.269667649874464e-05
2023-01-24 07:32:22.843449: step: 84/531, loss: 0.0011059649987146258
2023-01-24 07:32:23.893475: step: 88/531, loss: 0.0036076586693525314
2023-01-24 07:32:24.958336: step: 92/531, loss: 0.0035521909594535828
2023-01-24 07:32:26.021913: step: 96/531, loss: 0.03489205986261368
2023-01-24 07:32:27.081271: step: 100/531, loss: 0.014840464107692242
2023-01-24 07:32:28.141694: step: 104/531, loss: 0.0013690049527212977
2023-01-24 07:32:29.199870: step: 108/531, loss: 0.0031027987133711576
2023-01-24 07:32:30.253030: step: 112/531, loss: 0.00198413897305727
2023-01-24 07:32:31.306846: step: 116/531, loss: 0.004999811295419931
2023-01-24 07:32:32.362944: step: 120/531, loss: 0.0020942334085702896
2023-01-24 07:32:33.407494: step: 124/531, loss: 0.002167933154851198
2023-01-24 07:32:34.453913: step: 128/531, loss: 0.011389507912099361
2023-01-24 07:32:35.500409: step: 132/531, loss: 0.0023518609814345837
2023-01-24 07:32:36.562388: step: 136/531, loss: 0.0008302110363729298
2023-01-24 07:32:37.633291: step: 140/531, loss: 0.005180789157748222
2023-01-24 07:32:38.684646: step: 144/531, loss: 0.0030223741196095943
2023-01-24 07:32:39.727776: step: 148/531, loss: 0.0053098308853805065
2023-01-24 07:32:40.797095: step: 152/531, loss: 0.0034682273399084806
2023-01-24 07:32:41.891897: step: 156/531, loss: 0.0056068180128932
2023-01-24 07:32:42.944440: step: 160/531, loss: 0.000880257342942059
2023-01-24 07:32:44.021550: step: 164/531, loss: 0.006435590796172619
2023-01-24 07:32:45.097913: step: 168/531, loss: 0.004628789145499468
2023-01-24 07:32:46.166895: step: 172/531, loss: 0.0018600308103486896
2023-01-24 07:32:47.234563: step: 176/531, loss: 0.0026068449951708317
2023-01-24 07:32:48.293865: step: 180/531, loss: 0.008805465884506702
2023-01-24 07:32:49.364809: step: 184/531, loss: 0.005547242239117622
2023-01-24 07:32:50.411820: step: 188/531, loss: 6.172151915961877e-05
2023-01-24 07:32:51.467857: step: 192/531, loss: 0.0009066284401342273
2023-01-24 07:32:52.522480: step: 196/531, loss: 0.001958414213731885
2023-01-24 07:32:53.578695: step: 200/531, loss: 0.0004091927839908749
2023-01-24 07:32:54.639270: step: 204/531, loss: 0.0162381362169981
2023-01-24 07:32:55.714969: step: 208/531, loss: 0.006360786035656929
2023-01-24 07:32:56.767905: step: 212/531, loss: 0.00134243443608284
2023-01-24 07:32:57.817357: step: 216/531, loss: 0.004472144413739443
2023-01-24 07:32:58.878889: step: 220/531, loss: 0.0001199832622660324
2023-01-24 07:32:59.955030: step: 224/531, loss: 0.00017228329670615494
2023-01-24 07:33:01.034266: step: 228/531, loss: 0.001089850440621376
2023-01-24 07:33:02.108627: step: 232/531, loss: 0.005808225367218256
2023-01-24 07:33:03.155836: step: 236/531, loss: 0.006756265182048082
2023-01-24 07:33:04.223280: step: 240/531, loss: 0.00015489471843466163
2023-01-24 07:33:05.267194: step: 244/531, loss: 0.006117692217230797
2023-01-24 07:33:06.329603: step: 248/531, loss: 0.0012868092162534595
2023-01-24 07:33:07.377014: step: 252/531, loss: 0.0060088420286774635
2023-01-24 07:33:08.431031: step: 256/531, loss: 0.003042251104488969
2023-01-24 07:33:09.486768: step: 260/531, loss: 0.004750113468617201
2023-01-24 07:33:10.565019: step: 264/531, loss: 0.00598478876054287
2023-01-24 07:33:11.607296: step: 268/531, loss: 0.020888064056634903
2023-01-24 07:33:12.689743: step: 272/531, loss: 0.000384991493774578
2023-01-24 07:33:13.746971: step: 276/531, loss: 0.003254319541156292
2023-01-24 07:33:14.806573: step: 280/531, loss: 0.0015920934965834022
2023-01-24 07:33:15.846198: step: 284/531, loss: 0.0006789285107515752
2023-01-24 07:33:16.921042: step: 288/531, loss: 0.0016608184669166803
2023-01-24 07:33:17.989330: step: 292/531, loss: 0.001358446548692882
2023-01-24 07:33:19.045281: step: 296/531, loss: 0.0007131583988666534
2023-01-24 07:33:20.108353: step: 300/531, loss: 0.003415829036384821
2023-01-24 07:33:21.180571: step: 304/531, loss: 0.008375131525099277
2023-01-24 07:33:22.238665: step: 308/531, loss: 0.0009640548378229141
2023-01-24 07:33:23.303557: step: 312/531, loss: 0.0015861615538597107
2023-01-24 07:33:24.364468: step: 316/531, loss: 0.0004318073915783316
2023-01-24 07:33:25.417581: step: 320/531, loss: 0.00015259617066476494
2023-01-24 07:33:26.494883: step: 324/531, loss: 0.0024037668481469154
2023-01-24 07:33:27.573031: step: 328/531, loss: 0.009311018511652946
2023-01-24 07:33:28.661340: step: 332/531, loss: 4.776411515194923e-05
2023-01-24 07:33:29.723222: step: 336/531, loss: 0.023765331134200096
2023-01-24 07:33:30.781594: step: 340/531, loss: 0.0034515359438955784
2023-01-24 07:33:31.838272: step: 344/531, loss: 0.001172275166027248
2023-01-24 07:33:32.889799: step: 348/531, loss: 0.0033460904378443956
2023-01-24 07:33:33.952988: step: 352/531, loss: 0.007876559160649776
2023-01-24 07:33:35.007251: step: 356/531, loss: 0.002973369788378477
2023-01-24 07:33:36.059360: step: 360/531, loss: 0.003678396809846163
2023-01-24 07:33:37.110550: step: 364/531, loss: 0.006506223697215319
2023-01-24 07:33:38.167781: step: 368/531, loss: 0.0004361586179584265
2023-01-24 07:33:39.215359: step: 372/531, loss: 0.008504385128617287
2023-01-24 07:33:40.258089: step: 376/531, loss: 0.0019203261472284794
2023-01-24 07:33:41.299411: step: 380/531, loss: 0.00046843045856803656
2023-01-24 07:33:42.360350: step: 384/531, loss: 0.008011464960873127
2023-01-24 07:33:43.433374: step: 388/531, loss: 0.003691725432872772
2023-01-24 07:33:44.506449: step: 392/531, loss: 0.0017186313634738326
2023-01-24 07:33:45.571769: step: 396/531, loss: 0.00033388304291293025
2023-01-24 07:33:46.620886: step: 400/531, loss: 0.004575843922793865
2023-01-24 07:33:47.697123: step: 404/531, loss: 0.0027084494940936565
2023-01-24 07:33:48.745722: step: 408/531, loss: 0.0009295142372138798
2023-01-24 07:33:49.815805: step: 412/531, loss: 0.0016048046527430415
2023-01-24 07:33:50.870403: step: 416/531, loss: 0.0029492757748812437
2023-01-24 07:33:51.935966: step: 420/531, loss: 0.0004289450007490814
2023-01-24 07:33:53.001075: step: 424/531, loss: 0.001646324060857296
2023-01-24 07:33:54.065190: step: 428/531, loss: 0.010851244442164898
2023-01-24 07:33:55.139102: step: 432/531, loss: 0.010935558937489986
2023-01-24 07:33:56.203208: step: 436/531, loss: 0.005383491516113281
2023-01-24 07:33:57.251764: step: 440/531, loss: 0.0010768651263788342
2023-01-24 07:33:58.316974: step: 444/531, loss: 0.0045637465082108974
2023-01-24 07:33:59.376675: step: 448/531, loss: 0.00131141091696918
2023-01-24 07:34:00.436496: step: 452/531, loss: 0.0002298193285241723
2023-01-24 07:34:01.506681: step: 456/531, loss: 0.006291334982961416
2023-01-24 07:34:02.566879: step: 460/531, loss: 0.001991485944017768
2023-01-24 07:34:03.645242: step: 464/531, loss: 0.009577264077961445
2023-01-24 07:34:04.694580: step: 468/531, loss: 0.0003144587972201407
2023-01-24 07:34:05.762458: step: 472/531, loss: 0.024402670562267303
2023-01-24 07:34:06.825560: step: 476/531, loss: 0.005171215161681175
2023-01-24 07:34:07.887943: step: 480/531, loss: 0.0002673995040822774
2023-01-24 07:34:08.951828: step: 484/531, loss: 0.00021483120508491993
2023-01-24 07:34:10.005759: step: 488/531, loss: 0.0002423171536065638
2023-01-24 07:34:11.065482: step: 492/531, loss: 0.005877661518752575
2023-01-24 07:34:12.125782: step: 496/531, loss: 0.000291046395432204
2023-01-24 07:34:13.191567: step: 500/531, loss: 0.007739312946796417
2023-01-24 07:34:14.248450: step: 504/531, loss: 0.0016455594450235367
2023-01-24 07:34:15.311478: step: 508/531, loss: 0.011581001803278923
2023-01-24 07:34:16.356604: step: 512/531, loss: 0.0035536608193069696
2023-01-24 07:34:17.419430: step: 516/531, loss: 0.006567489821463823
2023-01-24 07:34:18.475735: step: 520/531, loss: 3.331424159114249e-05
2023-01-24 07:34:19.542968: step: 524/531, loss: 0.0029319655150175095
2023-01-24 07:34:20.592650: step: 528/531, loss: 0.00599403353407979
2023-01-24 07:34:21.644959: step: 532/531, loss: 0.005029898602515459
2023-01-24 07:34:22.703485: step: 536/531, loss: 0.00017079082317650318
2023-01-24 07:34:23.759654: step: 540/531, loss: 0.0016179722733795643
2023-01-24 07:34:24.825855: step: 544/531, loss: 0.003598906099796295
2023-01-24 07:34:25.883480: step: 548/531, loss: 0.002266326919198036
2023-01-24 07:34:26.944981: step: 552/531, loss: 0.0008765868842601776
2023-01-24 07:34:28.008385: step: 556/531, loss: 0.014094655402004719
2023-01-24 07:34:29.070351: step: 560/531, loss: 0.0075484528206288815
2023-01-24 07:34:30.128489: step: 564/531, loss: 0.0013430730905383825
2023-01-24 07:34:31.204392: step: 568/531, loss: 0.004203127231448889
2023-01-24 07:34:32.266013: step: 572/531, loss: 0.0026134364306926727
2023-01-24 07:34:33.349885: step: 576/531, loss: 0.0031323174480348825
2023-01-24 07:34:34.421248: step: 580/531, loss: 0.0009437850094400346
2023-01-24 07:34:35.490709: step: 584/531, loss: 0.0060317725874483585
2023-01-24 07:34:36.564322: step: 588/531, loss: 0.0018124451162293553
2023-01-24 07:34:37.610987: step: 592/531, loss: 0.002542851259931922
2023-01-24 07:34:38.672936: step: 596/531, loss: 0.00011189384531462565
2023-01-24 07:34:39.726219: step: 600/531, loss: 0.004575440660119057
2023-01-24 07:34:40.785001: step: 604/531, loss: 0.002222835086286068
2023-01-24 07:34:41.881453: step: 608/531, loss: 0.005140097811818123
2023-01-24 07:34:42.923046: step: 612/531, loss: 0.0018736954079940915
2023-01-24 07:34:43.974237: step: 616/531, loss: 0.0010442807106301188
2023-01-24 07:34:45.019313: step: 620/531, loss: 0.0028386476915329695
2023-01-24 07:34:46.091245: step: 624/531, loss: 0.00496304128319025
2023-01-24 07:34:47.162991: step: 628/531, loss: 0.006199537310749292
2023-01-24 07:34:48.224723: step: 632/531, loss: 0.01989562436938286
2023-01-24 07:34:49.270702: step: 636/531, loss: 0.0026654258836060762
2023-01-24 07:34:50.351641: step: 640/531, loss: 0.002410410437732935
2023-01-24 07:34:51.410408: step: 644/531, loss: 0.0010149793233722448
2023-01-24 07:34:52.478587: step: 648/531, loss: 0.0023655917029827833
2023-01-24 07:34:53.549392: step: 652/531, loss: 0.0022076650056988
2023-01-24 07:34:54.612849: step: 656/531, loss: 0.006200449541211128
2023-01-24 07:34:55.666624: step: 660/531, loss: 0.008652614429593086
2023-01-24 07:34:56.726422: step: 664/531, loss: 0.0015065692132338881
2023-01-24 07:34:57.784334: step: 668/531, loss: 0.007710055448114872
2023-01-24 07:34:58.829531: step: 672/531, loss: 0.0002910518378484994
2023-01-24 07:34:59.877385: step: 676/531, loss: 0.0032941356766968966
2023-01-24 07:35:00.934505: step: 680/531, loss: 0.002095744013786316
2023-01-24 07:35:02.010368: step: 684/531, loss: 0.0012469409266486764
2023-01-24 07:35:03.068921: step: 688/531, loss: 0.006371789611876011
2023-01-24 07:35:04.130031: step: 692/531, loss: 0.001873451634310186
2023-01-24 07:35:05.192594: step: 696/531, loss: 0.004255469888448715
2023-01-24 07:35:06.272508: step: 700/531, loss: 0.007635138928890228
2023-01-24 07:35:07.335179: step: 704/531, loss: 0.008111944422125816
2023-01-24 07:35:08.388260: step: 708/531, loss: 0.009344195015728474
2023-01-24 07:35:09.474126: step: 712/531, loss: 0.0024300895165652037
2023-01-24 07:35:10.526141: step: 716/531, loss: 0.0007058361079543829
2023-01-24 07:35:11.574944: step: 720/531, loss: 0.005931665189564228
2023-01-24 07:35:12.694884: step: 724/531, loss: 0.00538041302934289
2023-01-24 07:35:13.749700: step: 728/531, loss: 0.004413405433297157
2023-01-24 07:35:14.812430: step: 732/531, loss: 0.0033413004130125046
2023-01-24 07:35:15.893650: step: 736/531, loss: 0.004877195693552494
2023-01-24 07:35:16.945776: step: 740/531, loss: 0.006328440736979246
2023-01-24 07:35:18.005193: step: 744/531, loss: 0.006791654042899609
2023-01-24 07:35:19.062222: step: 748/531, loss: 0.0010770582593977451
2023-01-24 07:35:20.119979: step: 752/531, loss: 0.005755329038947821
2023-01-24 07:35:21.188017: step: 756/531, loss: 0.0015215236926451325
2023-01-24 07:35:22.248976: step: 760/531, loss: 0.001223857863806188
2023-01-24 07:35:23.303863: step: 764/531, loss: 0.0122085465118289
2023-01-24 07:35:24.372823: step: 768/531, loss: 0.0005444795824587345
2023-01-24 07:35:25.447340: step: 772/531, loss: 0.004318851046264172
2023-01-24 07:35:26.510109: step: 776/531, loss: 0.0014233270194381475
2023-01-24 07:35:27.565312: step: 780/531, loss: 0.0001222977152792737
2023-01-24 07:35:28.616687: step: 784/531, loss: 0.03975486382842064
2023-01-24 07:35:29.679863: step: 788/531, loss: 0.005028843879699707
2023-01-24 07:35:30.739169: step: 792/531, loss: 0.004637574311345816
2023-01-24 07:35:31.799818: step: 796/531, loss: 0.004428816493600607
2023-01-24 07:35:32.866280: step: 800/531, loss: 0.00016019698523450643
2023-01-24 07:35:33.929976: step: 804/531, loss: 0.003329712199047208
2023-01-24 07:35:34.986024: step: 808/531, loss: 0.02217811346054077
2023-01-24 07:35:36.043894: step: 812/531, loss: 0.0012782919220626354
2023-01-24 07:35:37.104216: step: 816/531, loss: 0.0018862895667552948
2023-01-24 07:35:38.170489: step: 820/531, loss: 0.0014390208525583148
2023-01-24 07:35:39.224950: step: 824/531, loss: 0.011796059086918831
2023-01-24 07:35:40.281973: step: 828/531, loss: 0.008138417266309261
2023-01-24 07:35:41.320652: step: 832/531, loss: 0.000262885179836303
2023-01-24 07:35:42.375562: step: 836/531, loss: 0.006853947415947914
2023-01-24 07:35:43.426695: step: 840/531, loss: 0.0007535576587542892
2023-01-24 07:35:44.484208: step: 844/531, loss: 0.0002806924458127469
2023-01-24 07:35:45.539866: step: 848/531, loss: 0.004743541125208139
2023-01-24 07:35:46.600147: step: 852/531, loss: 0.000423107179813087
2023-01-24 07:35:47.646207: step: 856/531, loss: 0.004514685831964016
2023-01-24 07:35:48.699080: step: 860/531, loss: 0.0019779985304921865
2023-01-24 07:35:49.758524: step: 864/531, loss: 0.0015256067272275686
2023-01-24 07:35:50.798927: step: 868/531, loss: 0.000194802982150577
2023-01-24 07:35:51.877294: step: 872/531, loss: 0.012310339137911797
2023-01-24 07:35:52.932310: step: 876/531, loss: 0.0005365722463466227
2023-01-24 07:35:53.992318: step: 880/531, loss: 0.0036379857920110226
2023-01-24 07:35:55.039354: step: 884/531, loss: 0.01085724774748087
2023-01-24 07:35:56.106803: step: 888/531, loss: 0.0005317054456099868
2023-01-24 07:35:57.149708: step: 892/531, loss: 0.00018345253192819655
2023-01-24 07:35:58.214868: step: 896/531, loss: 0.0030171286780387163
2023-01-24 07:35:59.282026: step: 900/531, loss: 0.003309423802420497
2023-01-24 07:36:00.343509: step: 904/531, loss: 0.001217101002112031
2023-01-24 07:36:01.422219: step: 908/531, loss: 0.03060407191514969
2023-01-24 07:36:02.478656: step: 912/531, loss: 0.0113700395449996
2023-01-24 07:36:03.544859: step: 916/531, loss: 0.004854146391153336
2023-01-24 07:36:04.598652: step: 920/531, loss: 0.006441024597734213
2023-01-24 07:36:05.661476: step: 924/531, loss: 0.004410286899656057
2023-01-24 07:36:06.715976: step: 928/531, loss: 0.006873035803437233
2023-01-24 07:36:07.772465: step: 932/531, loss: 0.0002730699779931456
2023-01-24 07:36:08.839162: step: 936/531, loss: 0.0018945703050121665
2023-01-24 07:36:09.903334: step: 940/531, loss: 0.006529218517243862
2023-01-24 07:36:10.973244: step: 944/531, loss: 0.0006231256993487477
2023-01-24 07:36:12.078003: step: 948/531, loss: 0.0005243791965767741
2023-01-24 07:36:13.137685: step: 952/531, loss: 0.0015809608157724142
2023-01-24 07:36:14.196742: step: 956/531, loss: 0.008266216143965721
2023-01-24 07:36:15.243581: step: 960/531, loss: 0.018888840451836586
2023-01-24 07:36:16.316466: step: 964/531, loss: 0.00015002106374595314
2023-01-24 07:36:17.380685: step: 968/531, loss: 0.0064233760349452496
2023-01-24 07:36:18.434413: step: 972/531, loss: 0.0033490073401480913
2023-01-24 07:36:19.491844: step: 976/531, loss: 0.0016718388069421053
2023-01-24 07:36:20.547911: step: 980/531, loss: 0.00017033734184224159
2023-01-24 07:36:21.601528: step: 984/531, loss: 0.006633893586695194
2023-01-24 07:36:22.655920: step: 988/531, loss: 0.004494899418205023
2023-01-24 07:36:23.714480: step: 992/531, loss: 0.0020726737566292286
2023-01-24 07:36:24.779713: step: 996/531, loss: 0.0019445770885795355
2023-01-24 07:36:25.846245: step: 1000/531, loss: 0.00526324100792408
2023-01-24 07:36:26.886983: step: 1004/531, loss: 0.0008864232804626226
2023-01-24 07:36:27.939296: step: 1008/531, loss: 0.004418803378939629
2023-01-24 07:36:28.997686: step: 1012/531, loss: 0.003179551102221012
2023-01-24 07:36:30.043230: step: 1016/531, loss: 0.0024454572703689337
2023-01-24 07:36:31.117550: step: 1020/531, loss: 0.04245481267571449
2023-01-24 07:36:32.174811: step: 1024/531, loss: 0.012318273074924946
2023-01-24 07:36:33.225027: step: 1028/531, loss: 0.0044145057909190655
2023-01-24 07:36:34.272784: step: 1032/531, loss: 6.116233271313831e-05
2023-01-24 07:36:35.322483: step: 1036/531, loss: 0.0011430742451921105
2023-01-24 07:36:36.372568: step: 1040/531, loss: 0.0008967426256276667
2023-01-24 07:36:37.422245: step: 1044/531, loss: 0.011159449815750122
2023-01-24 07:36:38.482888: step: 1048/531, loss: 0.006936488673090935
2023-01-24 07:36:39.548109: step: 1052/531, loss: 0.0007150927558541298
2023-01-24 07:36:40.616327: step: 1056/531, loss: 0.010731692425906658
2023-01-24 07:36:41.683097: step: 1060/531, loss: 0.0037799340207129717
2023-01-24 07:36:42.743713: step: 1064/531, loss: 0.011266198940575123
2023-01-24 07:36:43.797836: step: 1068/531, loss: 0.0002607348724268377
2023-01-24 07:36:44.867789: step: 1072/531, loss: 0.003033361630514264
2023-01-24 07:36:45.937556: step: 1076/531, loss: 0.005947592202574015
2023-01-24 07:36:46.987170: step: 1080/531, loss: 0.007470968645066023
2023-01-24 07:36:48.046057: step: 1084/531, loss: 0.0019138501957058907
2023-01-24 07:36:49.087992: step: 1088/531, loss: 0.0011556856334209442
2023-01-24 07:36:50.157884: step: 1092/531, loss: 0.0005223070620559156
2023-01-24 07:36:51.214383: step: 1096/531, loss: 0.011568109504878521
2023-01-24 07:36:52.266708: step: 1100/531, loss: 0.006213732063770294
2023-01-24 07:36:53.328009: step: 1104/531, loss: 0.0002279826730955392
2023-01-24 07:36:54.383053: step: 1108/531, loss: 0.00017191852384712547
2023-01-24 07:36:55.437333: step: 1112/531, loss: 0.0026087078731507063
2023-01-24 07:36:56.492837: step: 1116/531, loss: 0.002258676802739501
2023-01-24 07:36:57.560718: step: 1120/531, loss: 0.008678958751261234
2023-01-24 07:36:58.611064: step: 1124/531, loss: 0.004187881946563721
2023-01-24 07:36:59.669721: step: 1128/531, loss: 0.00678448798134923
2023-01-24 07:37:00.735479: step: 1132/531, loss: 0.003109800163656473
2023-01-24 07:37:01.767115: step: 1136/531, loss: 3.5098997614113614e-05
2023-01-24 07:37:02.827553: step: 1140/531, loss: 0.00300983595661819
2023-01-24 07:37:03.876967: step: 1144/531, loss: 0.002147710183635354
2023-01-24 07:37:04.921217: step: 1148/531, loss: 4.352720861788839e-05
2023-01-24 07:37:05.986575: step: 1152/531, loss: 0.005084862466901541
2023-01-24 07:37:07.058473: step: 1156/531, loss: 0.0027062869630753994
2023-01-24 07:37:08.112920: step: 1160/531, loss: 0.0027608387172222137
2023-01-24 07:37:09.166638: step: 1164/531, loss: 0.012221050448715687
2023-01-24 07:37:10.229769: step: 1168/531, loss: 0.008218341507017612
2023-01-24 07:37:11.280376: step: 1172/531, loss: 0.0064306179992854595
2023-01-24 07:37:12.353976: step: 1176/531, loss: 0.004282574634999037
2023-01-24 07:37:13.409070: step: 1180/531, loss: 0.0003131578559987247
2023-01-24 07:37:14.472188: step: 1184/531, loss: 0.0055084070190787315
2023-01-24 07:37:15.531710: step: 1188/531, loss: 0.005028588231652975
2023-01-24 07:37:16.592100: step: 1192/531, loss: 0.0023935751523822546
2023-01-24 07:37:17.654796: step: 1196/531, loss: 0.007222407963126898
2023-01-24 07:37:18.699816: step: 1200/531, loss: 0.0009791728807613254
2023-01-24 07:37:19.768639: step: 1204/531, loss: 0.0015960520831868052
2023-01-24 07:37:20.829835: step: 1208/531, loss: 0.0008987372275441885
2023-01-24 07:37:21.890226: step: 1212/531, loss: 0.0024682246148586273
2023-01-24 07:37:22.954839: step: 1216/531, loss: 8.78802893566899e-05
2023-01-24 07:37:24.015150: step: 1220/531, loss: 0.002148613566532731
2023-01-24 07:37:25.077652: step: 1224/531, loss: 0.0058380537666380405
2023-01-24 07:37:26.147574: step: 1228/531, loss: 0.0004793701518792659
2023-01-24 07:37:27.199126: step: 1232/531, loss: 0.011534301564097404
2023-01-24 07:37:28.276733: step: 1236/531, loss: 0.0043892525136470795
2023-01-24 07:37:29.344862: step: 1240/531, loss: 0.007320867385715246
2023-01-24 07:37:30.406566: step: 1244/531, loss: 0.009166529402136803
2023-01-24 07:37:31.480998: step: 1248/531, loss: 0.003661456750705838
2023-01-24 07:37:32.559978: step: 1252/531, loss: 0.013029376044869423
2023-01-24 07:37:33.638127: step: 1256/531, loss: 0.0006287398864515126
2023-01-24 07:37:34.685943: step: 1260/531, loss: 0.005346239078789949
2023-01-24 07:37:35.759169: step: 1264/531, loss: 0.000639710167888552
2023-01-24 07:37:36.822216: step: 1268/531, loss: 4.5079395931679755e-05
2023-01-24 07:37:37.886304: step: 1272/531, loss: 0.04524929076433182
2023-01-24 07:37:38.955510: step: 1276/531, loss: 0.005343164317309856
2023-01-24 07:37:40.031221: step: 1280/531, loss: 0.0042571756057441235
2023-01-24 07:37:41.104604: step: 1284/531, loss: 0.005458963569253683
2023-01-24 07:37:42.192476: step: 1288/531, loss: 0.0143412034958601
2023-01-24 07:37:43.244071: step: 1292/531, loss: 0.005807945504784584
2023-01-24 07:37:44.324319: step: 1296/531, loss: 0.005546705797314644
2023-01-24 07:37:45.370149: step: 1300/531, loss: 0.0067531997337937355
2023-01-24 07:37:46.419598: step: 1304/531, loss: 0.0008774721645750105
2023-01-24 07:37:47.481848: step: 1308/531, loss: 0.007062950171530247
2023-01-24 07:37:48.532866: step: 1312/531, loss: 0.0005221646279096603
2023-01-24 07:37:49.627841: step: 1316/531, loss: 0.0013187529984861612
2023-01-24 07:37:50.694402: step: 1320/531, loss: 0.0004419395700097084
2023-01-24 07:37:51.746599: step: 1324/531, loss: 0.00824517011642456
2023-01-24 07:37:52.798009: step: 1328/531, loss: 0.0015413709916174412
2023-01-24 07:37:53.858375: step: 1332/531, loss: 0.0033878982067108154
2023-01-24 07:37:54.917802: step: 1336/531, loss: 0.004665473010390997
2023-01-24 07:37:55.963286: step: 1340/531, loss: 0.0006703593535348773
2023-01-24 07:37:57.005511: step: 1344/531, loss: 0.0004064817912876606
2023-01-24 07:37:58.070492: step: 1348/531, loss: 0.0032921815291047096
2023-01-24 07:37:59.145049: step: 1352/531, loss: 0.015185847878456116
2023-01-24 07:38:00.199854: step: 1356/531, loss: 0.0003153661382384598
2023-01-24 07:38:01.262433: step: 1360/531, loss: 0.002001093467697501
2023-01-24 07:38:02.330078: step: 1364/531, loss: 0.012593758292496204
2023-01-24 07:38:03.392415: step: 1368/531, loss: 0.0006679664365947247
2023-01-24 07:38:04.433263: step: 1372/531, loss: 0.0009427554905414581
2023-01-24 07:38:05.490177: step: 1376/531, loss: 0.00018571940017864108
2023-01-24 07:38:06.548632: step: 1380/531, loss: 0.007450035307556391
2023-01-24 07:38:07.617469: step: 1384/531, loss: 0.003342832438647747
2023-01-24 07:38:08.673414: step: 1388/531, loss: 0.005212183576077223
2023-01-24 07:38:09.734066: step: 1392/531, loss: 0.005624871701002121
2023-01-24 07:38:10.792248: step: 1396/531, loss: 0.0007276016985997558
2023-01-24 07:38:11.890288: step: 1400/531, loss: 0.010481802746653557
2023-01-24 07:38:12.939325: step: 1404/531, loss: 0.000984206679277122
2023-01-24 07:38:14.002339: step: 1408/531, loss: 0.018762333318591118
2023-01-24 07:38:15.069152: step: 1412/531, loss: 0.0007749480428174138
2023-01-24 07:38:16.139032: step: 1416/531, loss: 0.0029891724698245525
2023-01-24 07:38:17.197531: step: 1420/531, loss: 3.6878678656648844e-05
2023-01-24 07:38:18.262121: step: 1424/531, loss: 0.004841763060539961
2023-01-24 07:38:19.324786: step: 1428/531, loss: 0.008448080159723759
2023-01-24 07:38:20.403142: step: 1432/531, loss: 0.0005592944798991084
2023-01-24 07:38:21.464889: step: 1436/531, loss: 0.017689159139990807
2023-01-24 07:38:22.522942: step: 1440/531, loss: 0.005695062223821878
2023-01-24 07:38:23.588398: step: 1444/531, loss: 0.004672298673540354
2023-01-24 07:38:24.648012: step: 1448/531, loss: 0.000152892607729882
2023-01-24 07:38:25.709650: step: 1452/531, loss: 0.002773034619167447
2023-01-24 07:38:26.770406: step: 1456/531, loss: 0.00044494381290860474
2023-01-24 07:38:27.835249: step: 1460/531, loss: 0.005455221980810165
2023-01-24 07:38:28.914048: step: 1464/531, loss: 0.0016655612271279097
2023-01-24 07:38:29.966682: step: 1468/531, loss: 0.001345763448625803
2023-01-24 07:38:31.033929: step: 1472/531, loss: 0.002285619266331196
2023-01-24 07:38:32.119906: step: 1476/531, loss: 0.005338137503713369
2023-01-24 07:38:33.187335: step: 1480/531, loss: 0.0026537994854152203
2023-01-24 07:38:34.233269: step: 1484/531, loss: 0.002621342660859227
2023-01-24 07:38:35.286218: step: 1488/531, loss: 0.0003916116838809103
2023-01-24 07:38:36.351067: step: 1492/531, loss: 0.0029015252366662025
2023-01-24 07:38:37.401373: step: 1496/531, loss: 0.0026797123719006777
2023-01-24 07:38:38.461528: step: 1500/531, loss: 0.008366267196834087
2023-01-24 07:38:39.540030: step: 1504/531, loss: 0.008602991700172424
2023-01-24 07:38:40.601067: step: 1508/531, loss: 0.015988850966095924
2023-01-24 07:38:41.663441: step: 1512/531, loss: 0.013631724752485752
2023-01-24 07:38:42.729008: step: 1516/531, loss: 0.0019024478970095515
2023-01-24 07:38:43.788893: step: 1520/531, loss: 0.0041855210438370705
2023-01-24 07:38:44.853277: step: 1524/531, loss: 0.004925829824060202
2023-01-24 07:38:45.948763: step: 1528/531, loss: 0.005109453573822975
2023-01-24 07:38:47.023095: step: 1532/531, loss: 0.0015046736225485802
2023-01-24 07:38:48.070632: step: 1536/531, loss: 0.0020050164312124252
2023-01-24 07:38:49.136420: step: 1540/531, loss: 0.006838127505034208
2023-01-24 07:38:50.222067: step: 1544/531, loss: 0.0013855180004611611
2023-01-24 07:38:51.281781: step: 1548/531, loss: 0.013926796615123749
2023-01-24 07:38:52.350913: step: 1552/531, loss: 0.016245339065790176
2023-01-24 07:38:53.436209: step: 1556/531, loss: 0.009078939445316792
2023-01-24 07:38:54.508913: step: 1560/531, loss: 0.011057503521442413
2023-01-24 07:38:55.575018: step: 1564/531, loss: 7.659125549253076e-05
2023-01-24 07:38:56.629699: step: 1568/531, loss: 0.0021128018852323294
2023-01-24 07:38:57.713913: step: 1572/531, loss: 0.01326420996338129
2023-01-24 07:38:58.770283: step: 1576/531, loss: 0.001199234277009964
2023-01-24 07:38:59.840221: step: 1580/531, loss: 0.008252283558249474
2023-01-24 07:39:00.919713: step: 1584/531, loss: 0.01246541179716587
2023-01-24 07:39:02.005007: step: 1588/531, loss: 0.011930056847631931
2023-01-24 07:39:03.064171: step: 1592/531, loss: 0.0006496492424048483
2023-01-24 07:39:04.136027: step: 1596/531, loss: 0.0011638659052550793
2023-01-24 07:39:05.190555: step: 1600/531, loss: 0.05825250223278999
2023-01-24 07:39:06.248193: step: 1604/531, loss: 0.008243819698691368
2023-01-24 07:39:07.307845: step: 1608/531, loss: 0.0035970723256468773
2023-01-24 07:39:08.355092: step: 1612/531, loss: 0.00021067557099740952
2023-01-24 07:39:09.419749: step: 1616/531, loss: 0.02393924444913864
2023-01-24 07:39:10.483457: step: 1620/531, loss: 0.020270323380827904
2023-01-24 07:39:11.552427: step: 1624/531, loss: 0.0032589409966021776
2023-01-24 07:39:12.611528: step: 1628/531, loss: 0.006127768196165562
2023-01-24 07:39:13.687446: step: 1632/531, loss: 0.0024526531342417
2023-01-24 07:39:14.756114: step: 1636/531, loss: 0.00407453766092658
2023-01-24 07:39:15.802587: step: 1640/531, loss: 0.00470855925232172
2023-01-24 07:39:16.864358: step: 1644/531, loss: 0.02908954583108425
2023-01-24 07:39:17.918977: step: 1648/531, loss: 0.007423473987728357
2023-01-24 07:39:18.984218: step: 1652/531, loss: 4.4258504203753546e-05
2023-01-24 07:39:20.048347: step: 1656/531, loss: 0.002961240243166685
2023-01-24 07:39:21.118614: step: 1660/531, loss: 0.0008582502487115562
2023-01-24 07:39:22.176131: step: 1664/531, loss: 0.003365323878824711
2023-01-24 07:39:23.249033: step: 1668/531, loss: 0.008368290960788727
2023-01-24 07:39:24.297298: step: 1672/531, loss: 0.005154167301952839
2023-01-24 07:39:25.349364: step: 1676/531, loss: 0.004117444157600403
2023-01-24 07:39:26.457344: step: 1680/531, loss: 0.0056172749027609825
2023-01-24 07:39:27.515390: step: 1684/531, loss: 0.00018345407443121076
2023-01-24 07:39:28.584055: step: 1688/531, loss: 0.001721491222269833
2023-01-24 07:39:29.649336: step: 1692/531, loss: 0.0002251827681902796
2023-01-24 07:39:30.700822: step: 1696/531, loss: 0.003302122699096799
2023-01-24 07:39:31.770331: step: 1700/531, loss: 0.002727292710915208
2023-01-24 07:39:32.835998: step: 1704/531, loss: 0.012648818083107471
2023-01-24 07:39:33.896677: step: 1708/531, loss: 0.004212263040244579
2023-01-24 07:39:34.948352: step: 1712/531, loss: 0.0012800705153495073
2023-01-24 07:39:36.033973: step: 1716/531, loss: 0.01647569239139557
2023-01-24 07:39:37.086290: step: 1720/531, loss: 0.0014455660711973906
2023-01-24 07:39:38.136083: step: 1724/531, loss: 0.0008796030306257308
2023-01-24 07:39:39.193815: step: 1728/531, loss: 0.005203488282859325
2023-01-24 07:39:40.256835: step: 1732/531, loss: 0.01926231011748314
2023-01-24 07:39:41.318590: step: 1736/531, loss: 0.00021135433053132147
2023-01-24 07:39:42.393418: step: 1740/531, loss: 0.006085301749408245
2023-01-24 07:39:43.447528: step: 1744/531, loss: 0.005453317426145077
2023-01-24 07:39:44.500221: step: 1748/531, loss: 0.0015991569962352514
2023-01-24 07:39:45.552982: step: 1752/531, loss: 9.101376053877175e-05
2023-01-24 07:39:46.612733: step: 1756/531, loss: 0.0008252952829934657
2023-01-24 07:39:47.683576: step: 1760/531, loss: 0.0009875706164166331
2023-01-24 07:39:48.755050: step: 1764/531, loss: 0.005662148352712393
2023-01-24 07:39:49.828279: step: 1768/531, loss: 0.00747600058093667
2023-01-24 07:39:50.879320: step: 1772/531, loss: 0.0009594178991392255
2023-01-24 07:39:51.949907: step: 1776/531, loss: 0.012910320423543453
2023-01-24 07:39:53.001843: step: 1780/531, loss: 0.0069103236310184
2023-01-24 07:39:54.069033: step: 1784/531, loss: 0.006927257403731346
2023-01-24 07:39:55.128310: step: 1788/531, loss: 0.0002609694784041494
2023-01-24 07:39:56.205087: step: 1792/531, loss: 0.04665395990014076
2023-01-24 07:39:57.267517: step: 1796/531, loss: 0.02080320194363594
2023-01-24 07:39:58.335791: step: 1800/531, loss: 0.0005638275179080665
2023-01-24 07:39:59.405016: step: 1804/531, loss: 0.0009399615810252726
2023-01-24 07:40:00.466522: step: 1808/531, loss: 0.010329034179449081
2023-01-24 07:40:01.543235: step: 1812/531, loss: 0.0024414118379354477
2023-01-24 07:40:02.602784: step: 1816/531, loss: 0.0004456086317077279
2023-01-24 07:40:03.686325: step: 1820/531, loss: 0.0027660930063575506
2023-01-24 07:40:04.753035: step: 1824/531, loss: 0.0038704487960785627
2023-01-24 07:40:05.818298: step: 1828/531, loss: 0.004264619667083025
2023-01-24 07:40:06.900220: step: 1832/531, loss: 0.013584275729954243
2023-01-24 07:40:07.957700: step: 1836/531, loss: 0.016197444871068
2023-01-24 07:40:09.010453: step: 1840/531, loss: 0.011844533495604992
2023-01-24 07:40:10.061266: step: 1844/531, loss: 0.002995867980644107
2023-01-24 07:40:11.142093: step: 1848/531, loss: 0.00017257625586353242
2023-01-24 07:40:12.194044: step: 1852/531, loss: 0.0005876217037439346
2023-01-24 07:40:13.247035: step: 1856/531, loss: 0.007146322168409824
2023-01-24 07:40:14.286822: step: 1860/531, loss: 0.00023343191423919052
2023-01-24 07:40:15.340804: step: 1864/531, loss: 0.0018423054134473205
2023-01-24 07:40:16.409992: step: 1868/531, loss: 0.014122666791081429
2023-01-24 07:40:17.472908: step: 1872/531, loss: 0.001166050205938518
2023-01-24 07:40:18.533636: step: 1876/531, loss: 0.008618973195552826
2023-01-24 07:40:19.604054: step: 1880/531, loss: 0.0017856524791568518
2023-01-24 07:40:20.688533: step: 1884/531, loss: 0.04140400514006615
2023-01-24 07:40:21.749622: step: 1888/531, loss: 0.007130743470042944
2023-01-24 07:40:22.818444: step: 1892/531, loss: 0.04196929559111595
2023-01-24 07:40:23.885411: step: 1896/531, loss: 0.0016301539726555347
2023-01-24 07:40:24.943547: step: 1900/531, loss: 0.009510564617812634
2023-01-24 07:40:26.004148: step: 1904/531, loss: 0.00044240913121029735
2023-01-24 07:40:27.070392: step: 1908/531, loss: 0.012046189978718758
2023-01-24 07:40:28.116682: step: 1912/531, loss: 0.00041518075158819556
2023-01-24 07:40:29.197092: step: 1916/531, loss: 0.027137255296111107
2023-01-24 07:40:30.236371: step: 1920/531, loss: 0.0004925797111354768
2023-01-24 07:40:31.290078: step: 1924/531, loss: 0.012253421358764172
2023-01-24 07:40:32.358751: step: 1928/531, loss: 0.02932673692703247
2023-01-24 07:40:33.407586: step: 1932/531, loss: 0.010897035710513592
2023-01-24 07:40:34.462535: step: 1936/531, loss: 0.0011757295578718185
2023-01-24 07:40:35.521484: step: 1940/531, loss: 0.0018360865069553256
2023-01-24 07:40:36.599978: step: 1944/531, loss: 0.007614095229655504
2023-01-24 07:40:37.672106: step: 1948/531, loss: 0.005120331887155771
2023-01-24 07:40:38.731258: step: 1952/531, loss: 0.0036779800429940224
2023-01-24 07:40:39.799956: step: 1956/531, loss: 0.003120720386505127
2023-01-24 07:40:40.850821: step: 1960/531, loss: 0.008584629744291306
2023-01-24 07:40:41.938098: step: 1964/531, loss: 0.005383949726819992
2023-01-24 07:40:43.002365: step: 1968/531, loss: 0.00524586858227849
2023-01-24 07:40:44.087337: step: 1972/531, loss: 0.015556536614894867
2023-01-24 07:40:45.143650: step: 1976/531, loss: 0.013057351112365723
2023-01-24 07:40:46.197285: step: 1980/531, loss: 0.021872470155358315
2023-01-24 07:40:47.267966: step: 1984/531, loss: 2.665207466634456e-05
2023-01-24 07:40:48.330030: step: 1988/531, loss: 0.000882698455825448
2023-01-24 07:40:49.394980: step: 1992/531, loss: 0.003634906839579344
2023-01-24 07:40:50.464085: step: 1996/531, loss: 0.004949311725795269
2023-01-24 07:40:51.524948: step: 2000/531, loss: 6.262212991714478e-05
2023-01-24 07:40:52.614850: step: 2004/531, loss: 0.09322883188724518
2023-01-24 07:40:53.693612: step: 2008/531, loss: 0.021210629492998123
2023-01-24 07:40:54.764508: step: 2012/531, loss: 0.006638068240135908
2023-01-24 07:40:55.822045: step: 2016/531, loss: 0.0001774926349753514
2023-01-24 07:40:56.873224: step: 2020/531, loss: 0.0022074251901358366
2023-01-24 07:40:57.939081: step: 2024/531, loss: 0.006805712357163429
2023-01-24 07:40:58.999249: step: 2028/531, loss: 0.005032597575336695
2023-01-24 07:41:00.059609: step: 2032/531, loss: 0.004065856337547302
2023-01-24 07:41:01.117843: step: 2036/531, loss: 0.0032912169117480516
2023-01-24 07:41:02.161667: step: 2040/531, loss: 0.002695470117032528
2023-01-24 07:41:03.225523: step: 2044/531, loss: 0.0031310562044382095
2023-01-24 07:41:04.279947: step: 2048/531, loss: 0.0027956843841820955
2023-01-24 07:41:05.343278: step: 2052/531, loss: 0.0020208486821502447
2023-01-24 07:41:06.397316: step: 2056/531, loss: 0.006803087890148163
2023-01-24 07:41:07.455420: step: 2060/531, loss: 0.005171677563339472
2023-01-24 07:41:08.502715: step: 2064/531, loss: 0.0025616742204874754
2023-01-24 07:41:09.559402: step: 2068/531, loss: 9.408283949596807e-05
2023-01-24 07:41:10.619844: step: 2072/531, loss: 0.0010668785544112325
2023-01-24 07:41:11.688459: step: 2076/531, loss: 0.022057106718420982
2023-01-24 07:41:12.760247: step: 2080/531, loss: 0.008383555337786674
2023-01-24 07:41:13.816189: step: 2084/531, loss: 0.0007936846814118326
2023-01-24 07:41:14.871638: step: 2088/531, loss: 1.5653886293875985e-05
2023-01-24 07:41:15.929417: step: 2092/531, loss: 0.009281976148486137
2023-01-24 07:41:17.002816: step: 2096/531, loss: 0.0028985398821532726
2023-01-24 07:41:18.057794: step: 2100/531, loss: 0.001012779655866325
2023-01-24 07:41:19.107791: step: 2104/531, loss: 0.013688012957572937
2023-01-24 07:41:20.153626: step: 2108/531, loss: 0.0008754542795941234
2023-01-24 07:41:21.211256: step: 2112/531, loss: 0.010695521719753742
2023-01-24 07:41:22.274880: step: 2116/531, loss: 0.005161258392035961
2023-01-24 07:41:23.334818: step: 2120/531, loss: 0.002305034315213561
2023-01-24 07:41:24.410474: step: 2124/531, loss: 0.03891216963529587
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39136394243522005, 'r': 0.31784396083922994, 'f1': 0.35079323007806107}, 'combined': 0.25847922216278185, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3898444918291601, 'r': 0.27665249329986386, 'f1': 0.32363672475690825}, 'combined': 0.20265103325899864, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3777820660150084, 'r': 0.3362045331329012, 'f1': 0.3557827087571063}, 'combined': 0.2621556801368152, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.38996520744853863, 'r': 0.2872872628362994, 'f1': 0.33084275647503225}, 'combined': 0.20502931387185094, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3768845677084582, 'r': 0.3339755087663187, 'f1': 0.35413499621700195}, 'combined': 0.26094157615989616, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4128482340917574, 'r': 0.2873929997464713, 'f1': 0.338882335692543}, 'combined': 0.2248031335782216, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 11}
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, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 12
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:43:47.416772: step: 4/531, loss: 0.0008389207650907338
2023-01-24 07:43:48.458940: step: 8/531, loss: 0.00010559849033597857
2023-01-24 07:43:49.495386: step: 12/531, loss: 0.0018369851168245077
2023-01-24 07:43:50.539544: step: 16/531, loss: 0.0007721724105067551
2023-01-24 07:43:51.615136: step: 20/531, loss: 0.0032571502961218357
2023-01-24 07:43:52.680722: step: 24/531, loss: 0.0036437639500945807
2023-01-24 07:43:53.724385: step: 28/531, loss: 2.4471442884532735e-05
2023-01-24 07:43:54.774573: step: 32/531, loss: 0.0033021809067577124
2023-01-24 07:43:55.839557: step: 36/531, loss: 0.004632710013538599
2023-01-24 07:43:56.887897: step: 40/531, loss: 0.005841181147843599
2023-01-24 07:43:57.947615: step: 44/531, loss: 5.735109152738005e-05
2023-01-24 07:43:59.011843: step: 48/531, loss: 0.024581611156463623
2023-01-24 07:44:00.061284: step: 52/531, loss: 0.0019269189797341824
2023-01-24 07:44:01.126230: step: 56/531, loss: 0.00784609466791153
2023-01-24 07:44:02.200922: step: 60/531, loss: 0.00300803454592824
2023-01-24 07:44:03.267716: step: 64/531, loss: 0.0009494698606431484
2023-01-24 07:44:04.315565: step: 68/531, loss: 9.220935316989198e-05
2023-01-24 07:44:05.389630: step: 72/531, loss: 0.003247142769396305
2023-01-24 07:44:06.435406: step: 76/531, loss: 2.4122944523696788e-05
2023-01-24 07:44:07.506456: step: 80/531, loss: 0.0016064064111560583
2023-01-24 07:44:08.568785: step: 84/531, loss: 0.0005471711046993732
2023-01-24 07:44:09.609013: step: 88/531, loss: 0.0022514851298183203
2023-01-24 07:44:10.661879: step: 92/531, loss: 0.009884671308100224
2023-01-24 07:44:11.715838: step: 96/531, loss: 0.00525251030921936
2023-01-24 07:44:12.772878: step: 100/531, loss: 0.0037255228962749243
2023-01-24 07:44:13.826335: step: 104/531, loss: 0.005992396734654903
2023-01-24 07:44:14.866721: step: 108/531, loss: 0.000234859500778839
2023-01-24 07:44:15.910795: step: 112/531, loss: 9.715954365674406e-05
2023-01-24 07:44:16.963394: step: 116/531, loss: 0.00032209724304266274
2023-01-24 07:44:18.015090: step: 120/531, loss: 0.008206389844417572
2023-01-24 07:44:19.069472: step: 124/531, loss: 0.0003823053266387433
2023-01-24 07:44:20.130706: step: 128/531, loss: 0.0051974281668663025
2023-01-24 07:44:21.191709: step: 132/531, loss: 0.004671670496463776
2023-01-24 07:44:22.260160: step: 136/531, loss: 0.004954180214554071
2023-01-24 07:44:23.315926: step: 140/531, loss: 0.004117222502827644
2023-01-24 07:44:24.379378: step: 144/531, loss: 0.005710092838853598
2023-01-24 07:44:25.433532: step: 148/531, loss: 0.007301541045308113
2023-01-24 07:44:26.496549: step: 152/531, loss: 0.007987217977643013
2023-01-24 07:44:27.557126: step: 156/531, loss: 0.0036173320841044188
2023-01-24 07:44:28.613485: step: 160/531, loss: 0.030461503192782402
2023-01-24 07:44:29.666143: step: 164/531, loss: 0.009336454793810844
2023-01-24 07:44:30.709869: step: 168/531, loss: 0.0008688546367920935
2023-01-24 07:44:31.752019: step: 172/531, loss: 0.00035778165329247713
2023-01-24 07:44:32.813998: step: 176/531, loss: 0.0039122882299125195
2023-01-24 07:44:33.869028: step: 180/531, loss: 0.010806133970618248
2023-01-24 07:44:34.901140: step: 184/531, loss: 0.00023036330821923912
2023-01-24 07:44:35.952925: step: 188/531, loss: 0.03970678895711899
2023-01-24 07:44:37.023119: step: 192/531, loss: 0.008071407675743103
2023-01-24 07:44:38.079228: step: 196/531, loss: 0.002907214453443885
2023-01-24 07:44:39.124635: step: 200/531, loss: 0.03283369168639183
2023-01-24 07:44:40.188341: step: 204/531, loss: 0.00859660841524601
2023-01-24 07:44:41.240787: step: 208/531, loss: 0.0019820162560790777
2023-01-24 07:44:42.294215: step: 212/531, loss: 0.004488769453018904
2023-01-24 07:44:43.347926: step: 216/531, loss: 0.003945598378777504
2023-01-24 07:44:44.381015: step: 220/531, loss: 0.0001054470703820698
2023-01-24 07:44:45.440914: step: 224/531, loss: 0.001361457398161292
2023-01-24 07:44:46.506984: step: 228/531, loss: 0.0018045916222035885
2023-01-24 07:44:47.572235: step: 232/531, loss: 3.198215927113779e-05
2023-01-24 07:44:48.634936: step: 236/531, loss: 0.0011877354700118303
2023-01-24 07:44:49.687642: step: 240/531, loss: 0.0027856742963194847
2023-01-24 07:44:50.736799: step: 244/531, loss: 0.001992375124245882
2023-01-24 07:44:51.786167: step: 248/531, loss: 0.007944031618535519
2023-01-24 07:44:52.843814: step: 252/531, loss: 0.006351663265377283
2023-01-24 07:44:53.898062: step: 256/531, loss: 0.015617218799889088
2023-01-24 07:44:54.983180: step: 260/531, loss: 6.317496445262805e-05
2023-01-24 07:44:56.035546: step: 264/531, loss: 0.001909082755446434
2023-01-24 07:44:57.081435: step: 268/531, loss: 0.0045850686728954315
2023-01-24 07:44:58.153247: step: 272/531, loss: 0.00044367933878675103
2023-01-24 07:44:59.201510: step: 276/531, loss: 0.008906870149075985
2023-01-24 07:45:00.261243: step: 280/531, loss: 0.003220190526917577
2023-01-24 07:45:01.326216: step: 284/531, loss: 0.0033500271383672953
2023-01-24 07:45:02.390701: step: 288/531, loss: 0.0001335518463747576
2023-01-24 07:45:03.451078: step: 292/531, loss: 0.004304062575101852
2023-01-24 07:45:04.502981: step: 296/531, loss: 0.008509303443133831
2023-01-24 07:45:05.562447: step: 300/531, loss: 0.016502907499670982
2023-01-24 07:45:06.629669: step: 304/531, loss: 0.0036851379554718733
2023-01-24 07:45:07.699974: step: 308/531, loss: 0.0066000730730593204
2023-01-24 07:45:08.773767: step: 312/531, loss: 0.006111239083111286
2023-01-24 07:45:09.839109: step: 316/531, loss: 0.03327450156211853
2023-01-24 07:45:10.885516: step: 320/531, loss: 0.006460524629801512
2023-01-24 07:45:11.972297: step: 324/531, loss: 0.0033953215461224318
2023-01-24 07:45:13.047470: step: 328/531, loss: 0.01261853240430355
2023-01-24 07:45:14.122898: step: 332/531, loss: 0.00012264428369235247
2023-01-24 07:45:15.184797: step: 336/531, loss: 0.002265886403620243
2023-01-24 07:45:16.241546: step: 340/531, loss: 0.007583374623209238
2023-01-24 07:45:17.304063: step: 344/531, loss: 0.006667454726994038
2023-01-24 07:45:18.372990: step: 348/531, loss: 0.004515505861490965
2023-01-24 07:45:19.428477: step: 352/531, loss: 0.005921052768826485
2023-01-24 07:45:20.492658: step: 356/531, loss: 0.002086668973788619
2023-01-24 07:45:21.546085: step: 360/531, loss: 0.00901003647595644
2023-01-24 07:45:22.604553: step: 364/531, loss: 0.004519919864833355
2023-01-24 07:45:23.658467: step: 368/531, loss: 0.004887619987130165
2023-01-24 07:45:24.713515: step: 372/531, loss: 0.002692396519705653
2023-01-24 07:45:25.764871: step: 376/531, loss: 0.0013424503849819303
2023-01-24 07:45:26.812552: step: 380/531, loss: 0.0012260869843885303
2023-01-24 07:45:27.874817: step: 384/531, loss: 0.008952656760811806
2023-01-24 07:45:28.948273: step: 388/531, loss: 0.006157420109957457
2023-01-24 07:45:30.005060: step: 392/531, loss: 0.00423513213172555
2023-01-24 07:45:31.061308: step: 396/531, loss: 0.003380093490704894
2023-01-24 07:45:32.115737: step: 400/531, loss: 0.004202052019536495
2023-01-24 07:45:33.159106: step: 404/531, loss: 0.0025893016718328
2023-01-24 07:45:34.197152: step: 408/531, loss: 0.0006840350106358528
2023-01-24 07:45:35.268688: step: 412/531, loss: 0.007730729412287474
2023-01-24 07:45:36.315829: step: 416/531, loss: 0.00012970188981853426
2023-01-24 07:45:37.376680: step: 420/531, loss: 0.00041116910870186985
2023-01-24 07:45:38.435817: step: 424/531, loss: 0.03476627543568611
2023-01-24 07:45:39.508371: step: 428/531, loss: 3.2617645047139376e-05
2023-01-24 07:45:40.570113: step: 432/531, loss: 0.0032686570193618536
2023-01-24 07:45:41.633417: step: 436/531, loss: 0.009400025941431522
2023-01-24 07:45:42.677141: step: 440/531, loss: 0.0042421636171638966
2023-01-24 07:45:43.744484: step: 444/531, loss: 0.004297575913369656
2023-01-24 07:45:44.803425: step: 448/531, loss: 0.001137967687100172
2023-01-24 07:45:45.864534: step: 452/531, loss: 0.004794553853571415
2023-01-24 07:45:46.921448: step: 456/531, loss: 0.005618246737867594
2023-01-24 07:45:47.977512: step: 460/531, loss: 0.010654338635504246
2023-01-24 07:45:49.042292: step: 464/531, loss: 4.0400300349574536e-05
2023-01-24 07:45:50.097215: step: 468/531, loss: 0.005780503153800964
2023-01-24 07:45:51.166492: step: 472/531, loss: 0.001814171439036727
2023-01-24 07:45:52.230867: step: 476/531, loss: 0.003135963575914502
2023-01-24 07:45:53.288096: step: 480/531, loss: 0.00317192985676229
2023-01-24 07:45:54.359912: step: 484/531, loss: 0.0002823463291861117
2023-01-24 07:45:55.404944: step: 488/531, loss: 0.0007620081305503845
2023-01-24 07:45:56.460687: step: 492/531, loss: 0.0005408728611655533
2023-01-24 07:45:57.513595: step: 496/531, loss: 0.001419361331500113
2023-01-24 07:45:58.593875: step: 500/531, loss: 0.018071437254548073
2023-01-24 07:45:59.661404: step: 504/531, loss: 0.0003890968509949744
2023-01-24 07:46:00.701668: step: 508/531, loss: 0.0028337924741208553
2023-01-24 07:46:01.762738: step: 512/531, loss: 0.0005585855687968433
2023-01-24 07:46:02.824144: step: 516/531, loss: 0.001072737155482173
2023-01-24 07:46:03.881652: step: 520/531, loss: 0.004423412028700113
2023-01-24 07:46:04.931851: step: 524/531, loss: 0.009205316193401814
2023-01-24 07:46:05.984095: step: 528/531, loss: 0.00017672343528829515
2023-01-24 07:46:07.050902: step: 532/531, loss: 0.025930123403668404
2023-01-24 07:46:08.101544: step: 536/531, loss: 0.02773277275264263
2023-01-24 07:46:09.159653: step: 540/531, loss: 0.0035834801383316517
2023-01-24 07:46:10.228676: step: 544/531, loss: 0.014484859071671963
2023-01-24 07:46:11.292421: step: 548/531, loss: 0.01031828485429287
2023-01-24 07:46:12.353857: step: 552/531, loss: 0.034110959619283676
2023-01-24 07:46:13.405930: step: 556/531, loss: 0.004532115533947945
2023-01-24 07:46:14.458360: step: 560/531, loss: 6.901539018144831e-05
2023-01-24 07:46:15.529854: step: 564/531, loss: 0.0022416478022933006
2023-01-24 07:46:16.587951: step: 568/531, loss: 0.00440360838547349
2023-01-24 07:46:17.645870: step: 572/531, loss: 0.012465021573007107
2023-01-24 07:46:18.699748: step: 576/531, loss: 0.0024797343648970127
2023-01-24 07:46:19.772911: step: 580/531, loss: 0.0025166908744722605
2023-01-24 07:46:20.845019: step: 584/531, loss: 0.0018173493444919586
2023-01-24 07:46:21.909238: step: 588/531, loss: 0.003276263130828738
2023-01-24 07:46:22.982027: step: 592/531, loss: 0.010924028232693672
2023-01-24 07:46:24.030833: step: 596/531, loss: 0.0006664815009571612
2023-01-24 07:46:25.087204: step: 600/531, loss: 0.0035071498714387417
2023-01-24 07:46:26.142118: step: 604/531, loss: 0.0025345301255583763
2023-01-24 07:46:27.205190: step: 608/531, loss: 0.006584506947547197
2023-01-24 07:46:28.266028: step: 612/531, loss: 0.002991733141243458
2023-01-24 07:46:29.329585: step: 616/531, loss: 0.0026069479063153267
2023-01-24 07:46:30.378600: step: 620/531, loss: 0.006710594519972801
2023-01-24 07:46:31.438637: step: 624/531, loss: 0.002223886549472809
2023-01-24 07:46:32.519377: step: 628/531, loss: 6.38153069303371e-05
2023-01-24 07:46:33.587986: step: 632/531, loss: 0.0061606005765497684
2023-01-24 07:46:34.647326: step: 636/531, loss: 0.007872034795582294
2023-01-24 07:46:35.713941: step: 640/531, loss: 0.002794067608192563
2023-01-24 07:46:36.775573: step: 644/531, loss: 0.0005641243769787252
2023-01-24 07:46:37.825442: step: 648/531, loss: 0.003788859350606799
2023-01-24 07:46:38.887784: step: 652/531, loss: 0.003150087548419833
2023-01-24 07:46:39.961733: step: 656/531, loss: 0.0016968734562397003
2023-01-24 07:46:41.013347: step: 660/531, loss: 0.003051474690437317
2023-01-24 07:46:42.100912: step: 664/531, loss: 0.0004801126488018781
2023-01-24 07:46:43.150909: step: 668/531, loss: 0.00017927706358022988
2023-01-24 07:46:44.217959: step: 672/531, loss: 0.0018251375295221806
2023-01-24 07:46:45.286222: step: 676/531, loss: 0.008766816928982735
2023-01-24 07:46:46.332477: step: 680/531, loss: 0.010923833586275578
2023-01-24 07:46:47.392794: step: 684/531, loss: 0.0032276224810630083
2023-01-24 07:46:48.445035: step: 688/531, loss: 0.0002460060059092939
2023-01-24 07:46:49.511413: step: 692/531, loss: 0.0022312605287879705
2023-01-24 07:46:50.582017: step: 696/531, loss: 0.0036463169381022453
2023-01-24 07:46:51.634364: step: 700/531, loss: 0.02077023684978485
2023-01-24 07:46:52.702841: step: 704/531, loss: 0.0012957289582118392
2023-01-24 07:46:53.770911: step: 708/531, loss: 0.00034273412893526256
2023-01-24 07:46:54.834779: step: 712/531, loss: 0.002293934812769294
2023-01-24 07:46:55.887168: step: 716/531, loss: 0.007038906216621399
2023-01-24 07:46:56.932088: step: 720/531, loss: 0.008487860672175884
2023-01-24 07:46:57.972314: step: 724/531, loss: 0.004350061994045973
2023-01-24 07:46:59.039570: step: 728/531, loss: 0.0016962428344413638
2023-01-24 07:47:00.107123: step: 732/531, loss: 0.0033008086029440165
2023-01-24 07:47:01.170250: step: 736/531, loss: 0.004522221628576517
2023-01-24 07:47:02.227132: step: 740/531, loss: 0.003127848030999303
2023-01-24 07:47:03.285655: step: 744/531, loss: 0.0016203239792957902
2023-01-24 07:47:04.347135: step: 748/531, loss: 0.006861977744847536
2023-01-24 07:47:05.403581: step: 752/531, loss: 0.0016648167511448264
2023-01-24 07:47:06.468258: step: 756/531, loss: 0.0
2023-01-24 07:47:07.535943: step: 760/531, loss: 0.0020345740485936403
2023-01-24 07:47:08.638290: step: 764/531, loss: 0.0018157161539420485
2023-01-24 07:47:09.695106: step: 768/531, loss: 0.0
2023-01-24 07:47:10.751021: step: 772/531, loss: 0.000396099901990965
2023-01-24 07:47:11.808907: step: 776/531, loss: 0.003001901088282466
2023-01-24 07:47:12.877354: step: 780/531, loss: 0.001074808300472796
2023-01-24 07:47:13.939874: step: 784/531, loss: 0.002999604679644108
2023-01-24 07:47:15.001110: step: 788/531, loss: 0.004084710497409105
2023-01-24 07:47:16.063424: step: 792/531, loss: 0.002436148002743721
2023-01-24 07:47:17.121192: step: 796/531, loss: 0.0019201913382858038
2023-01-24 07:47:18.183584: step: 800/531, loss: 0.0017997156828641891
2023-01-24 07:47:19.246935: step: 804/531, loss: 0.0024946166668087244
2023-01-24 07:47:20.312784: step: 808/531, loss: 0.0011476814979687333
2023-01-24 07:47:21.383785: step: 812/531, loss: 0.0011169894132763147
2023-01-24 07:47:22.436609: step: 816/531, loss: 0.006832829676568508
2023-01-24 07:47:23.488582: step: 820/531, loss: 0.013472024351358414
2023-01-24 07:47:24.542387: step: 824/531, loss: 0.0006732032052241266
2023-01-24 07:47:25.620348: step: 828/531, loss: 0.008710733614861965
2023-01-24 07:47:26.683437: step: 832/531, loss: 0.0006531117833219469
2023-01-24 07:47:27.751924: step: 836/531, loss: 0.0008852792088873684
2023-01-24 07:47:28.828301: step: 840/531, loss: 0.0002344071981497109
2023-01-24 07:47:29.877771: step: 844/531, loss: 0.004317728336900473
2023-01-24 07:47:30.946788: step: 848/531, loss: 0.0032241877634078264
2023-01-24 07:47:32.005952: step: 852/531, loss: 0.0013686273014172912
2023-01-24 07:47:33.074161: step: 856/531, loss: 0.002086965600028634
2023-01-24 07:47:34.129835: step: 860/531, loss: 0.0011500888504087925
2023-01-24 07:47:35.194972: step: 864/531, loss: 0.000752498337533325
2023-01-24 07:47:36.266793: step: 868/531, loss: 0.004230258986353874
2023-01-24 07:47:37.319948: step: 872/531, loss: 0.0018112084362655878
2023-01-24 07:47:38.388235: step: 876/531, loss: 0.001974749844521284
2023-01-24 07:47:39.445358: step: 880/531, loss: 0.0009569660178385675
2023-01-24 07:47:40.516091: step: 884/531, loss: 0.005202190019190311
2023-01-24 07:47:41.576752: step: 888/531, loss: 0.008720196783542633
2023-01-24 07:47:42.654427: step: 892/531, loss: 0.0006743905250914395
2023-01-24 07:47:43.718024: step: 896/531, loss: 0.0031865478958934546
2023-01-24 07:47:44.775128: step: 900/531, loss: 0.0004073894815519452
2023-01-24 07:47:45.826586: step: 904/531, loss: 0.003885938785970211
2023-01-24 07:47:46.866015: step: 908/531, loss: 0.004631747957319021
2023-01-24 07:47:47.919591: step: 912/531, loss: 0.004460339434444904
2023-01-24 07:47:48.986139: step: 916/531, loss: 0.0013200478861108422
2023-01-24 07:47:50.040335: step: 920/531, loss: 0.00246457033790648
2023-01-24 07:47:51.116275: step: 924/531, loss: 5.09754208906088e-05
2023-01-24 07:47:52.177224: step: 928/531, loss: 0.0022536313626915216
2023-01-24 07:47:53.239687: step: 932/531, loss: 0.007142882794141769
2023-01-24 07:47:54.294709: step: 936/531, loss: 0.0013322465820237994
2023-01-24 07:47:55.373542: step: 940/531, loss: 0.0016735511599108577
2023-01-24 07:47:56.436208: step: 944/531, loss: 0.00809379480779171
2023-01-24 07:47:57.502373: step: 948/531, loss: 0.002075192518532276
2023-01-24 07:47:58.559641: step: 952/531, loss: 1.3628292435896583e-05
2023-01-24 07:47:59.608590: step: 956/531, loss: 0.0
2023-01-24 07:48:00.666834: step: 960/531, loss: 0.0025110712740570307
2023-01-24 07:48:01.721776: step: 964/531, loss: 0.0028623335529118776
2023-01-24 07:48:02.789185: step: 968/531, loss: 0.0001212401402881369
2023-01-24 07:48:03.859310: step: 972/531, loss: 0.006787054240703583
2023-01-24 07:48:04.958759: step: 976/531, loss: 0.004579642787575722
2023-01-24 07:48:06.037136: step: 980/531, loss: 0.003262066747993231
2023-01-24 07:48:07.098536: step: 984/531, loss: 0.0024431669153273106
2023-01-24 07:48:08.167000: step: 988/531, loss: 3.8667440094286576e-05
2023-01-24 07:48:09.228782: step: 992/531, loss: 0.004330071620643139
2023-01-24 07:48:10.293864: step: 996/531, loss: 0.0027935367543250322
2023-01-24 07:48:11.368701: step: 1000/531, loss: 0.0020482842810451984
2023-01-24 07:48:12.436717: step: 1004/531, loss: 0.004700318910181522
2023-01-24 07:48:13.508227: step: 1008/531, loss: 0.016613643616437912
2023-01-24 07:48:14.571418: step: 1012/531, loss: 0.0017231876263394952
2023-01-24 07:48:15.637232: step: 1016/531, loss: 0.003956877160817385
2023-01-24 07:48:16.700827: step: 1020/531, loss: 0.0001247296022484079
2023-01-24 07:48:17.789308: step: 1024/531, loss: 0.009423875249922276
2023-01-24 07:48:18.860709: step: 1028/531, loss: 0.00022268889006227255
2023-01-24 07:48:19.922912: step: 1032/531, loss: 0.00044816909939981997
2023-01-24 07:48:21.021522: step: 1036/531, loss: 0.0003109208191744983
2023-01-24 07:48:22.085349: step: 1040/531, loss: 0.0025388181675225496
2023-01-24 07:48:23.164752: step: 1044/531, loss: 0.0005637683789245784
2023-01-24 07:48:24.244260: step: 1048/531, loss: 0.005272428505122662
2023-01-24 07:48:25.301129: step: 1052/531, loss: 0.005151810590177774
2023-01-24 07:48:26.371057: step: 1056/531, loss: 0.003676653141155839
2023-01-24 07:48:27.432162: step: 1060/531, loss: 0.001526866341009736
2023-01-24 07:48:28.491125: step: 1064/531, loss: 0.018764158710837364
2023-01-24 07:48:29.571080: step: 1068/531, loss: 0.0035187965258955956
2023-01-24 07:48:30.640452: step: 1072/531, loss: 0.0025187255814671516
2023-01-24 07:48:31.707288: step: 1076/531, loss: 0.0004637420061044395
2023-01-24 07:48:32.763775: step: 1080/531, loss: 0.009744417853653431
2023-01-24 07:48:33.855657: step: 1084/531, loss: 0.023237161338329315
2023-01-24 07:48:34.924549: step: 1088/531, loss: 0.0015469287754967809
2023-01-24 07:48:36.002240: step: 1092/531, loss: 0.002548233373090625
2023-01-24 07:48:37.063256: step: 1096/531, loss: 0.0011249580420553684
2023-01-24 07:48:38.119685: step: 1100/531, loss: 0.21845102310180664
2023-01-24 07:48:39.188438: step: 1104/531, loss: 0.00193855632096529
2023-01-24 07:48:40.249265: step: 1108/531, loss: 0.0017726629739627242
2023-01-24 07:48:41.311511: step: 1112/531, loss: 0.0059312013909220695
2023-01-24 07:48:42.370373: step: 1116/531, loss: 0.005972353741526604
2023-01-24 07:48:43.434397: step: 1120/531, loss: 0.008372385054826736
2023-01-24 07:48:44.509720: step: 1124/531, loss: 0.006263169925659895
2023-01-24 07:48:45.579202: step: 1128/531, loss: 0.006859087385237217
2023-01-24 07:48:46.628411: step: 1132/531, loss: 0.0002497813547961414
2023-01-24 07:48:47.692787: step: 1136/531, loss: 0.0027852808125317097
2023-01-24 07:48:48.752430: step: 1140/531, loss: 0.004294695798307657
2023-01-24 07:48:49.811201: step: 1144/531, loss: 0.008168441243469715
2023-01-24 07:48:50.872373: step: 1148/531, loss: 0.0003930634702555835
2023-01-24 07:48:51.952120: step: 1152/531, loss: 0.0011404338292777538
2023-01-24 07:48:53.014345: step: 1156/531, loss: 0.002245817333459854
2023-01-24 07:48:54.095676: step: 1160/531, loss: 0.007948026061058044
2023-01-24 07:48:55.169777: step: 1164/531, loss: 0.00342952786013484
2023-01-24 07:48:56.226083: step: 1168/531, loss: 0.0018263505771756172
2023-01-24 07:48:57.280840: step: 1172/531, loss: 0.002272512298077345
2023-01-24 07:48:58.339630: step: 1176/531, loss: 0.004708748310804367
2023-01-24 07:48:59.401166: step: 1180/531, loss: 0.0013651384506374598
2023-01-24 07:49:00.463071: step: 1184/531, loss: 0.014489850960671902
2023-01-24 07:49:01.521812: step: 1188/531, loss: 0.007809903007000685
2023-01-24 07:49:02.589070: step: 1192/531, loss: 0.006919751409441233
2023-01-24 07:49:03.657774: step: 1196/531, loss: 0.0029774876311421394
2023-01-24 07:49:04.735885: step: 1200/531, loss: 0.0022975176107138395
2023-01-24 07:49:05.807142: step: 1204/531, loss: 0.0176263228058815
2023-01-24 07:49:06.877989: step: 1208/531, loss: 0.005035478621721268
2023-01-24 07:49:07.941211: step: 1212/531, loss: 0.0012818221002817154
2023-01-24 07:49:09.009274: step: 1216/531, loss: 0.002564843511208892
2023-01-24 07:49:10.069457: step: 1220/531, loss: 0.0016376414569094777
2023-01-24 07:49:11.129107: step: 1224/531, loss: 0.003441035747528076
2023-01-24 07:49:12.198770: step: 1228/531, loss: 0.008165335282683372
2023-01-24 07:49:13.261372: step: 1232/531, loss: 0.004367683548480272
2023-01-24 07:49:14.324806: step: 1236/531, loss: 0.0035028522834181786
2023-01-24 07:49:15.375871: step: 1240/531, loss: 0.0060541522689163685
2023-01-24 07:49:16.434732: step: 1244/531, loss: 0.0040772161446511745
2023-01-24 07:49:17.493086: step: 1248/531, loss: 0.0019783724565058947
2023-01-24 07:49:18.545391: step: 1252/531, loss: 0.0003578769392333925
2023-01-24 07:49:19.602486: step: 1256/531, loss: 0.013649380765855312
2023-01-24 07:49:20.665946: step: 1260/531, loss: 0.0005524872685782611
2023-01-24 07:49:21.723159: step: 1264/531, loss: 0.003236167598515749
2023-01-24 07:49:22.796355: step: 1268/531, loss: 0.012535768561065197
2023-01-24 07:49:23.863053: step: 1272/531, loss: 0.003931407816708088
2023-01-24 07:49:24.924524: step: 1276/531, loss: 0.0002936648088507354
2023-01-24 07:49:25.986361: step: 1280/531, loss: 3.521692269714549e-05
2023-01-24 07:49:27.047924: step: 1284/531, loss: 0.0012437583645805717
2023-01-24 07:49:28.098867: step: 1288/531, loss: 0.001574097783304751
2023-01-24 07:49:29.157768: step: 1292/531, loss: 0.0031973973382264376
2023-01-24 07:49:30.223464: step: 1296/531, loss: 0.0008955801604315639
2023-01-24 07:49:31.270993: step: 1300/531, loss: 0.003448003903031349
2023-01-24 07:49:32.341441: step: 1304/531, loss: 0.0018009128980338573
2023-01-24 07:49:33.396494: step: 1308/531, loss: 0.0025702917482703924
2023-01-24 07:49:34.444013: step: 1312/531, loss: 0.0035841939970850945
2023-01-24 07:49:35.499223: step: 1316/531, loss: 0.000988248037174344
2023-01-24 07:49:36.551353: step: 1320/531, loss: 0.0007358400616794825
2023-01-24 07:49:37.614690: step: 1324/531, loss: 0.00043001319863833487
2023-01-24 07:49:38.682535: step: 1328/531, loss: 0.002343202941119671
2023-01-24 07:49:39.735011: step: 1332/531, loss: 0.003015042282640934
2023-01-24 07:49:40.804002: step: 1336/531, loss: 0.0067059556022286415
2023-01-24 07:49:41.893323: step: 1340/531, loss: 0.0016357195563614368
2023-01-24 07:49:42.942378: step: 1344/531, loss: 0.0002781250514090061
2023-01-24 07:49:44.000241: step: 1348/531, loss: 0.010305825620889664
2023-01-24 07:49:45.076869: step: 1352/531, loss: 0.008523844182491302
2023-01-24 07:49:46.164356: step: 1356/531, loss: 0.0016000947216525674
2023-01-24 07:49:47.223820: step: 1360/531, loss: 0.0007851168629713356
2023-01-24 07:49:48.294349: step: 1364/531, loss: 0.0037974438164383173
2023-01-24 07:49:49.347272: step: 1368/531, loss: 0.01731755957007408
2023-01-24 07:49:50.423152: step: 1372/531, loss: 0.004646297078579664
2023-01-24 07:49:51.487091: step: 1376/531, loss: 0.04282676428556442
2023-01-24 07:49:52.564083: step: 1380/531, loss: 0.002410672605037689
2023-01-24 07:49:53.628116: step: 1384/531, loss: 0.008816739544272423
2023-01-24 07:49:54.704237: step: 1388/531, loss: 0.006698832847177982
2023-01-24 07:49:55.776725: step: 1392/531, loss: 0.007065494079142809
2023-01-24 07:49:56.838629: step: 1396/531, loss: 0.0043277801014482975
2023-01-24 07:49:57.901193: step: 1400/531, loss: 0.009176273830235004
2023-01-24 07:49:58.949543: step: 1404/531, loss: 0.0016439496539533138
2023-01-24 07:50:00.000370: step: 1408/531, loss: 5.334922661859309e-06
2023-01-24 07:50:01.070769: step: 1412/531, loss: 0.0016743950545787811
2023-01-24 07:50:02.131458: step: 1416/531, loss: 0.009108916856348515
2023-01-24 07:50:03.200687: step: 1420/531, loss: 0.0007434654980897903
2023-01-24 07:50:04.260838: step: 1424/531, loss: 0.0014274800196290016
2023-01-24 07:50:05.318621: step: 1428/531, loss: 0.0015580813633278012
2023-01-24 07:50:06.377776: step: 1432/531, loss: 0.002763007767498493
2023-01-24 07:50:07.434663: step: 1436/531, loss: 0.0046341298148036
2023-01-24 07:50:08.487730: step: 1440/531, loss: 0.009754196740686893
2023-01-24 07:50:09.559090: step: 1444/531, loss: 0.005951341707259417
2023-01-24 07:50:10.608030: step: 1448/531, loss: 0.0016500568017363548
2023-01-24 07:50:11.689563: step: 1452/531, loss: 0.032500818371772766
2023-01-24 07:50:12.744104: step: 1456/531, loss: 0.0002141181903425604
2023-01-24 07:50:13.800250: step: 1460/531, loss: 0.003507954766973853
2023-01-24 07:50:14.860685: step: 1464/531, loss: 0.016222190111875534
2023-01-24 07:50:15.911760: step: 1468/531, loss: 0.0016991709126159549
2023-01-24 07:50:16.982585: step: 1472/531, loss: 0.0007061606738716364
2023-01-24 07:50:18.049162: step: 1476/531, loss: 0.010753964073956013
2023-01-24 07:50:19.107156: step: 1480/531, loss: 0.0027052199002355337
2023-01-24 07:50:20.163121: step: 1484/531, loss: 0.0032335391733795404
2023-01-24 07:50:21.212598: step: 1488/531, loss: 0.0012604587245732546
2023-01-24 07:50:22.285329: step: 1492/531, loss: 0.0024454377125948668
2023-01-24 07:50:23.345987: step: 1496/531, loss: 0.0001314998953603208
2023-01-24 07:50:24.417391: step: 1500/531, loss: 0.0002466514997649938
2023-01-24 07:50:25.490636: step: 1504/531, loss: 0.025304365903139114
2023-01-24 07:50:26.569216: step: 1508/531, loss: 0.007147661410272121
2023-01-24 07:50:27.634872: step: 1512/531, loss: 0.002998407930135727
2023-01-24 07:50:28.695046: step: 1516/531, loss: 0.0029829959385097027
2023-01-24 07:50:29.768225: step: 1520/531, loss: 0.0007618461386300623
2023-01-24 07:50:30.835365: step: 1524/531, loss: 0.0012937746942043304
2023-01-24 07:50:31.892210: step: 1528/531, loss: 0.010385893285274506
2023-01-24 07:50:32.953286: step: 1532/531, loss: 0.0027797003276646137
2023-01-24 07:50:34.034096: step: 1536/531, loss: 7.323131285374984e-05
2023-01-24 07:50:35.095481: step: 1540/531, loss: 0.013378430157899857
2023-01-24 07:50:36.158556: step: 1544/531, loss: 0.007806778885424137
2023-01-24 07:50:37.203696: step: 1548/531, loss: 0.0008553255465812981
2023-01-24 07:50:38.251678: step: 1552/531, loss: 0.0055023678578436375
2023-01-24 07:50:39.308486: step: 1556/531, loss: 0.0005368198035284877
2023-01-24 07:50:40.365680: step: 1560/531, loss: 0.0013809683732688427
2023-01-24 07:50:41.422477: step: 1564/531, loss: 0.036582279950380325
2023-01-24 07:50:42.489076: step: 1568/531, loss: 0.00589761883020401
2023-01-24 07:50:43.554145: step: 1572/531, loss: 0.00021944929903838784
2023-01-24 07:50:44.601738: step: 1576/531, loss: 0.00018480616563465446
2023-01-24 07:50:45.666562: step: 1580/531, loss: 0.003983218688517809
2023-01-24 07:50:46.708520: step: 1584/531, loss: 9.13636467885226e-05
2023-01-24 07:50:47.761999: step: 1588/531, loss: 0.0002771069994196296
2023-01-24 07:50:48.831227: step: 1592/531, loss: 0.005496619734913111
2023-01-24 07:50:49.895321: step: 1596/531, loss: 0.004821850918233395
2023-01-24 07:50:50.970355: step: 1600/531, loss: 0.0012605211231857538
2023-01-24 07:50:52.022527: step: 1604/531, loss: 0.002098711906000972
2023-01-24 07:50:53.076802: step: 1608/531, loss: 0.003607384394854307
2023-01-24 07:50:54.127817: step: 1612/531, loss: 0.001945766736753285
2023-01-24 07:50:55.186875: step: 1616/531, loss: 0.009840852580964565
2023-01-24 07:50:56.267127: step: 1620/531, loss: 0.006122017744928598
2023-01-24 07:50:57.336491: step: 1624/531, loss: 0.005689968355000019
2023-01-24 07:50:58.395098: step: 1628/531, loss: 0.017472121864557266
2023-01-24 07:50:59.483813: step: 1632/531, loss: 0.026586653664708138
2023-01-24 07:51:00.535072: step: 1636/531, loss: 0.0009049536311067641
2023-01-24 07:51:01.597174: step: 1640/531, loss: 0.004547577351331711
2023-01-24 07:51:02.654734: step: 1644/531, loss: 0.0004844518261961639
2023-01-24 07:51:03.715475: step: 1648/531, loss: 0.01065845601260662
2023-01-24 07:51:04.777094: step: 1652/531, loss: 0.0036239465698599815
2023-01-24 07:51:05.837213: step: 1656/531, loss: 0.0030450609046965837
2023-01-24 07:51:06.894210: step: 1660/531, loss: 0.001044715172611177
2023-01-24 07:51:07.969866: step: 1664/531, loss: 0.0013334108516573906
2023-01-24 07:51:09.022295: step: 1668/531, loss: 0.006684655789285898
2023-01-24 07:51:10.094094: step: 1672/531, loss: 0.004914723336696625
2023-01-24 07:51:11.146559: step: 1676/531, loss: 0.0013926565879955888
2023-01-24 07:51:12.203074: step: 1680/531, loss: 0.033084314316511154
2023-01-24 07:51:13.270708: step: 1684/531, loss: 0.009538733400404453
2023-01-24 07:51:14.320746: step: 1688/531, loss: 9.470694931223989e-05
2023-01-24 07:51:15.365450: step: 1692/531, loss: 0.003146019298583269
2023-01-24 07:51:16.435821: step: 1696/531, loss: 0.003303182777017355
2023-01-24 07:51:17.494126: step: 1700/531, loss: 0.001183894113637507
2023-01-24 07:51:18.565293: step: 1704/531, loss: 0.004848706070333719
2023-01-24 07:51:19.628177: step: 1708/531, loss: 0.07924825698137283
2023-01-24 07:51:20.702560: step: 1712/531, loss: 0.005933256819844246
2023-01-24 07:51:21.770050: step: 1716/531, loss: 0.003230552189052105
2023-01-24 07:51:22.852634: step: 1720/531, loss: 0.0013347519561648369
2023-01-24 07:51:23.894896: step: 1724/531, loss: 0.000424595782533288
2023-01-24 07:51:24.953156: step: 1728/531, loss: 0.0002757837646640837
2023-01-24 07:51:26.036207: step: 1732/531, loss: 0.018341783434152603
2023-01-24 07:51:27.092609: step: 1736/531, loss: 0.007935325615108013
2023-01-24 07:51:28.140835: step: 1740/531, loss: 0.009496736340224743
2023-01-24 07:51:29.190966: step: 1744/531, loss: 0.003631721716374159
2023-01-24 07:51:30.246961: step: 1748/531, loss: 0.004995123017579317
2023-01-24 07:51:31.309062: step: 1752/531, loss: 0.002949915360659361
2023-01-24 07:51:32.392044: step: 1756/531, loss: 0.002674936316907406
2023-01-24 07:51:33.459028: step: 1760/531, loss: 0.002306596841663122
2023-01-24 07:51:34.508055: step: 1764/531, loss: 0.0006740200333297253
2023-01-24 07:51:35.554995: step: 1768/531, loss: 0.000765511707868427
2023-01-24 07:51:36.605196: step: 1772/531, loss: 0.0007559226942248642
2023-01-24 07:51:37.658466: step: 1776/531, loss: 0.008602048270404339
2023-01-24 07:51:38.705885: step: 1780/531, loss: 0.0010769534856081009
2023-01-24 07:51:39.785107: step: 1784/531, loss: 0.013192391023039818
2023-01-24 07:51:40.852182: step: 1788/531, loss: 0.0029705294873565435
2023-01-24 07:51:41.937308: step: 1792/531, loss: 0.003922355826944113
2023-01-24 07:51:42.997997: step: 1796/531, loss: 0.00020109360048081726
2023-01-24 07:51:44.066583: step: 1800/531, loss: 0.009328101761639118
2023-01-24 07:51:45.133123: step: 1804/531, loss: 0.000808170938398689
2023-01-24 07:51:46.204449: step: 1808/531, loss: 0.006595465820282698
2023-01-24 07:51:47.260808: step: 1812/531, loss: 0.00468902662396431
2023-01-24 07:51:48.308739: step: 1816/531, loss: 0.00102903856895864
2023-01-24 07:51:49.377390: step: 1820/531, loss: 0.00034604378743097186
2023-01-24 07:51:50.439778: step: 1824/531, loss: 0.0037786783650517464
2023-01-24 07:51:51.516625: step: 1828/531, loss: 0.002887751441448927
2023-01-24 07:51:52.573975: step: 1832/531, loss: 0.0006598402396775782
2023-01-24 07:51:53.635484: step: 1836/531, loss: 0.027080411091446877
2023-01-24 07:51:54.706423: step: 1840/531, loss: 0.00883109588176012
2023-01-24 07:51:55.760442: step: 1844/531, loss: 0.0030366857536137104
2023-01-24 07:51:56.804965: step: 1848/531, loss: 4.7267636546166614e-05
2023-01-24 07:51:57.859241: step: 1852/531, loss: 0.00014116977399680763
2023-01-24 07:51:58.929615: step: 1856/531, loss: 0.003972511272877455
2023-01-24 07:51:59.985134: step: 1860/531, loss: 0.00021782699332106858
2023-01-24 07:52:01.055582: step: 1864/531, loss: 0.004587695002555847
2023-01-24 07:52:02.111944: step: 1868/531, loss: 0.0024384784046560526
2023-01-24 07:52:03.172923: step: 1872/531, loss: 0.0008537122630514205
2023-01-24 07:52:04.227326: step: 1876/531, loss: 0.0025096184108406305
2023-01-24 07:52:05.300586: step: 1880/531, loss: 0.0006997943273745477
2023-01-24 07:52:06.351569: step: 1884/531, loss: 0.0035982350818812847
2023-01-24 07:52:07.406461: step: 1888/531, loss: 0.03471110761165619
2023-01-24 07:52:08.469730: step: 1892/531, loss: 0.0034948561806231737
2023-01-24 07:52:09.529232: step: 1896/531, loss: 0.010049194097518921
2023-01-24 07:52:10.604763: step: 1900/531, loss: 0.00663770642131567
2023-01-24 07:52:11.663191: step: 1904/531, loss: 0.0009335716022178531
2023-01-24 07:52:12.729862: step: 1908/531, loss: 0.0035138465464115143
2023-01-24 07:52:13.791270: step: 1912/531, loss: 0.0020982068963348866
2023-01-24 07:52:14.868287: step: 1916/531, loss: 0.002704428741708398
2023-01-24 07:52:15.939710: step: 1920/531, loss: 0.0017310682451352477
2023-01-24 07:52:16.993995: step: 1924/531, loss: 0.006131255999207497
2023-01-24 07:52:18.061973: step: 1928/531, loss: 1.450459649277036e-06
2023-01-24 07:52:19.106313: step: 1932/531, loss: 0.0010957487393170595
2023-01-24 07:52:20.168413: step: 1936/531, loss: 0.0002672454575076699
2023-01-24 07:52:21.237383: step: 1940/531, loss: 0.002202295698225498
2023-01-24 07:52:22.306782: step: 1944/531, loss: 0.0030842034611850977
2023-01-24 07:52:23.388525: step: 1948/531, loss: 0.0033153227996081114
2023-01-24 07:52:24.470026: step: 1952/531, loss: 0.003676784224808216
2023-01-24 07:52:25.522583: step: 1956/531, loss: 0.0023453200701624155
2023-01-24 07:52:26.590492: step: 1960/531, loss: 0.013029161840677261
2023-01-24 07:52:27.648137: step: 1964/531, loss: 0.006316058337688446
2023-01-24 07:52:28.711363: step: 1968/531, loss: 0.01072138175368309
2023-01-24 07:52:29.781886: step: 1972/531, loss: 0.006450321059674025
2023-01-24 07:52:30.851825: step: 1976/531, loss: 0.005556017160415649
2023-01-24 07:52:31.918393: step: 1980/531, loss: 0.0004038731858599931
2023-01-24 07:52:32.985077: step: 1984/531, loss: 0.005801858380436897
2023-01-24 07:52:34.046572: step: 1988/531, loss: 0.024494579061865807
2023-01-24 07:52:35.102947: step: 1992/531, loss: 0.005121651571244001
2023-01-24 07:52:36.166821: step: 1996/531, loss: 0.000211178237805143
2023-01-24 07:52:37.210091: step: 2000/531, loss: 0.0012726139975711703
2023-01-24 07:52:38.283821: step: 2004/531, loss: 0.01274011842906475
2023-01-24 07:52:39.358708: step: 2008/531, loss: 0.0037234495393931866
2023-01-24 07:52:40.414517: step: 2012/531, loss: 0.0001431824202882126
2023-01-24 07:52:41.497387: step: 2016/531, loss: 0.006955960299819708
2023-01-24 07:52:42.576751: step: 2020/531, loss: 0.0070723253302276134
2023-01-24 07:52:43.633902: step: 2024/531, loss: 0.0011288494570180774
2023-01-24 07:52:44.694026: step: 2028/531, loss: 0.0011688803788274527
2023-01-24 07:52:45.762098: step: 2032/531, loss: 0.004531980957835913
2023-01-24 07:52:46.821530: step: 2036/531, loss: 0.0015466450713574886
2023-01-24 07:52:47.874316: step: 2040/531, loss: 0.0032513076439499855
2023-01-24 07:52:48.927773: step: 2044/531, loss: 0.004711893852800131
2023-01-24 07:52:49.976737: step: 2048/531, loss: 0.02056264318525791
2023-01-24 07:52:51.032131: step: 2052/531, loss: 0.019057223573327065
2023-01-24 07:52:52.079956: step: 2056/531, loss: 0.00039366702549159527
2023-01-24 07:52:53.139506: step: 2060/531, loss: 0.006560617592185736
2023-01-24 07:52:54.201075: step: 2064/531, loss: 0.000678473967127502
2023-01-24 07:52:55.249242: step: 2068/531, loss: 0.0009545246139168739
2023-01-24 07:52:56.317968: step: 2072/531, loss: 0.0034764143638312817
2023-01-24 07:52:57.387180: step: 2076/531, loss: 0.002918965183198452
2023-01-24 07:52:58.442855: step: 2080/531, loss: 0.0026115260552614927
2023-01-24 07:52:59.492560: step: 2084/531, loss: 0.004642174579203129
2023-01-24 07:53:00.566431: step: 2088/531, loss: 0.009831012226641178
2023-01-24 07:53:01.632015: step: 2092/531, loss: 0.004661223851144314
2023-01-24 07:53:02.716416: step: 2096/531, loss: 0.003432834055274725
2023-01-24 07:53:03.780376: step: 2100/531, loss: 0.00026433152379468083
2023-01-24 07:53:04.841056: step: 2104/531, loss: 0.011200176551938057
2023-01-24 07:53:05.890467: step: 2108/531, loss: 0.003517532255500555
2023-01-24 07:53:06.971686: step: 2112/531, loss: 0.00347131141461432
2023-01-24 07:53:08.030453: step: 2116/531, loss: 0.0021918402053415775
2023-01-24 07:53:09.103427: step: 2120/531, loss: 0.005421316716820002
2023-01-24 07:53:10.148150: step: 2124/531, loss: 0.0059256297536194324
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39236179589081405, 'r': 0.32088792035852154, 'f1': 0.3530437036094798}, 'combined': 0.2601374658175114, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38903250643343784, 'r': 0.2764270649860676, 'f1': 0.32320254619878647}, 'combined': 0.2023791644422308, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3793258714969241, 'r': 0.3418971327533946, 'f1': 0.3596402973274231}, 'combined': 0.2649981138202065, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.39118919765661697, 'r': 0.2881889760914843, 'f1': 0.33188117807420153}, 'combined': 0.2056728427502094, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36518927126018896, 'r': 0.329848374041461, 'f1': 0.3466203252639081}, 'combined': 0.2554044501944586, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4125243998948662, 'r': 0.2874267479411884, 'f1': 0.3387966348072731}, 'combined': 0.22474628249591386, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.40217391304347827, 'r': 0.40217391304347827, 'f1': 0.40217391304347827}, 'combined': 0.20108695652173914, 'stategy': 1, 'epoch': 12}
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, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 13
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 07:55:33.392702: step: 4/531, loss: 0.0015524713089689612
2023-01-24 07:55:34.444428: step: 8/531, loss: 0.01499737799167633
2023-01-24 07:55:35.496938: step: 12/531, loss: 0.009471848607063293
2023-01-24 07:55:36.541106: step: 16/531, loss: 0.0030436008237302303
2023-01-24 07:55:37.591220: step: 20/531, loss: 0.00910823792219162
2023-01-24 07:55:38.639618: step: 24/531, loss: 0.0075300512835383415
2023-01-24 07:55:39.683181: step: 28/531, loss: 4.1462368244538084e-05
2023-01-24 07:55:40.733149: step: 32/531, loss: 0.026324231177568436
2023-01-24 07:55:41.785636: step: 36/531, loss: 0.0018935796106234193
2023-01-24 07:55:42.828354: step: 40/531, loss: 8.813742169877514e-05
2023-01-24 07:55:43.889517: step: 44/531, loss: 0.00015770709433127195
2023-01-24 07:55:44.947566: step: 48/531, loss: 0.0022419379092752934
2023-01-24 07:55:46.020336: step: 52/531, loss: 0.0032461993396282196
2023-01-24 07:55:47.087589: step: 56/531, loss: 4.696365522249835e-06
2023-01-24 07:55:48.148269: step: 60/531, loss: 0.00043738234671764076
2023-01-24 07:55:49.185509: step: 64/531, loss: 0.0004448320541996509
2023-01-24 07:55:50.249507: step: 68/531, loss: 0.0012952450197190046
2023-01-24 07:55:51.314549: step: 72/531, loss: 0.003757863538339734
2023-01-24 07:55:52.375418: step: 76/531, loss: 0.001192079158499837
2023-01-24 07:55:53.427153: step: 80/531, loss: 0.0009926131460815668
2023-01-24 07:55:54.476859: step: 84/531, loss: 0.007381749805063009
2023-01-24 07:55:55.530995: step: 88/531, loss: 0.0005179202416911721
2023-01-24 07:55:56.586828: step: 92/531, loss: 0.0003311268810648471
2023-01-24 07:55:57.649398: step: 96/531, loss: 0.024976368993520737
2023-01-24 07:55:58.718590: step: 100/531, loss: 0.0017767202807590365
2023-01-24 07:55:59.770502: step: 104/531, loss: 0.003380588488653302
2023-01-24 07:56:00.821840: step: 108/531, loss: 0.00627892604097724
2023-01-24 07:56:01.884866: step: 112/531, loss: 0.0040617273189127445
2023-01-24 07:56:02.957228: step: 116/531, loss: 0.009586027823388577
2023-01-24 07:56:04.023690: step: 120/531, loss: 0.0023350792471319437
2023-01-24 07:56:05.069211: step: 124/531, loss: 0.0012568285455927253
2023-01-24 07:56:06.136780: step: 128/531, loss: 0.003740791231393814
2023-01-24 07:56:07.203992: step: 132/531, loss: 0.002929637674242258
2023-01-24 07:56:08.270044: step: 136/531, loss: 0.007804454304277897
2023-01-24 07:56:09.323887: step: 140/531, loss: 0.00035720583400689065
2023-01-24 07:56:10.395543: step: 144/531, loss: 0.0015390024054795504
2023-01-24 07:56:11.453258: step: 148/531, loss: 0.00013543761451728642
2023-01-24 07:56:12.514653: step: 152/531, loss: 0.005867954809218645
2023-01-24 07:56:13.598107: step: 156/531, loss: 0.0020808361005038023
2023-01-24 07:56:14.665943: step: 160/531, loss: 0.001825898652896285
2023-01-24 07:56:15.720851: step: 164/531, loss: 0.011046471074223518
2023-01-24 07:56:16.785943: step: 168/531, loss: 0.0024260778445750475
2023-01-24 07:56:17.853998: step: 172/531, loss: 0.0035714274272322655
2023-01-24 07:56:18.911015: step: 176/531, loss: 0.0005712392157875001
2023-01-24 07:56:19.976991: step: 180/531, loss: 0.00995740294456482
2023-01-24 07:56:21.021068: step: 184/531, loss: 0.002682530088350177
2023-01-24 07:56:22.063617: step: 188/531, loss: 0.001276618568226695
2023-01-24 07:56:23.114302: step: 192/531, loss: 0.0022227729205042124
2023-01-24 07:56:24.177190: step: 196/531, loss: 0.00020986668823752552
2023-01-24 07:56:25.238287: step: 200/531, loss: 0.005629145074635744
2023-01-24 07:56:26.287482: step: 204/531, loss: 0.00013388696243055165
2023-01-24 07:56:27.352383: step: 208/531, loss: 0.0024597765877842903
2023-01-24 07:56:28.409178: step: 212/531, loss: 0.0035304490011185408
2023-01-24 07:56:29.483087: step: 216/531, loss: 0.0005620679003186524
2023-01-24 07:56:30.540221: step: 220/531, loss: 0.0004899389459751546
2023-01-24 07:56:31.593781: step: 224/531, loss: 0.0001721788285067305
2023-01-24 07:56:32.656585: step: 228/531, loss: 1.9541201254469343e-05
2023-01-24 07:56:33.711699: step: 232/531, loss: 0.0029747115913778543
2023-01-24 07:56:34.776231: step: 236/531, loss: 0.0004925038083456457
2023-01-24 07:56:35.836237: step: 240/531, loss: 0.002626052824780345
2023-01-24 07:56:36.905325: step: 244/531, loss: 0.004584931768476963
2023-01-24 07:56:37.951556: step: 248/531, loss: 0.00014285094221122563
2023-01-24 07:56:39.012573: step: 252/531, loss: 0.0025896625593304634
2023-01-24 07:56:40.075047: step: 256/531, loss: 0.0011560394195839763
2023-01-24 07:56:41.123666: step: 260/531, loss: 0.0002148125640815124
2023-01-24 07:56:42.198349: step: 264/531, loss: 1.130525106418645e-05
2023-01-24 07:56:43.256638: step: 268/531, loss: 0.00018567038932815194
2023-01-24 07:56:44.325857: step: 272/531, loss: 0.005343783181160688
2023-01-24 07:56:45.378683: step: 276/531, loss: 2.7842357667395845e-05
2023-01-24 07:56:46.444906: step: 280/531, loss: 0.0005529717309400439
2023-01-24 07:56:47.511985: step: 284/531, loss: 0.015849506482481956
2023-01-24 07:56:48.562711: step: 288/531, loss: 3.4106898283425835e-07
2023-01-24 07:56:49.628229: step: 292/531, loss: 0.0022414561826735735
2023-01-24 07:56:50.692783: step: 296/531, loss: 0.0049082934856414795
2023-01-24 07:56:51.752899: step: 300/531, loss: 0.004191167186945677
2023-01-24 07:56:52.804429: step: 304/531, loss: 0.004176117479801178
2023-01-24 07:56:53.854939: step: 308/531, loss: 0.0010842847405001521
2023-01-24 07:56:54.899819: step: 312/531, loss: 0.002646995708346367
2023-01-24 07:56:55.954794: step: 316/531, loss: 0.0012743031838908792
2023-01-24 07:56:57.035174: step: 320/531, loss: 0.014964173547923565
2023-01-24 07:56:58.103830: step: 324/531, loss: 0.0018465067259967327
2023-01-24 07:56:59.162571: step: 328/531, loss: 0.00042861539986915886
2023-01-24 07:57:00.218333: step: 332/531, loss: 0.0006880436558276415
2023-01-24 07:57:01.275471: step: 336/531, loss: 0.010439034551382065
2023-01-24 07:57:02.330091: step: 340/531, loss: 0.0018505294574424624
2023-01-24 07:57:03.385405: step: 344/531, loss: 0.015337217599153519
2023-01-24 07:57:04.437100: step: 348/531, loss: 0.001650273334234953
2023-01-24 07:57:05.509171: step: 352/531, loss: 0.0044954800978302956
2023-01-24 07:57:06.576445: step: 356/531, loss: 0.0008822939125820994
2023-01-24 07:57:07.630614: step: 360/531, loss: 0.013922404497861862
2023-01-24 07:57:08.696389: step: 364/531, loss: 0.0009341145632788539
2023-01-24 07:57:09.746559: step: 368/531, loss: 0.005473637022078037
2023-01-24 07:57:10.806740: step: 372/531, loss: 0.00021152434055693448
2023-01-24 07:57:11.893538: step: 376/531, loss: 0.0008005455019883811
2023-01-24 07:57:12.938152: step: 380/531, loss: 0.016201358288526535
2023-01-24 07:57:14.031277: step: 384/531, loss: 0.0024131005629897118
2023-01-24 07:57:15.089110: step: 388/531, loss: 0.0035366006195545197
2023-01-24 07:57:16.136474: step: 392/531, loss: 0.0006364466971717775
2023-01-24 07:57:17.191989: step: 396/531, loss: 0.0036750156432390213
2023-01-24 07:57:18.244094: step: 400/531, loss: 0.010198943316936493
2023-01-24 07:57:19.302756: step: 404/531, loss: 0.0046410756185650826
2023-01-24 07:57:20.358477: step: 408/531, loss: 0.0012746219290420413
2023-01-24 07:57:21.432323: step: 412/531, loss: 0.004716424737125635
2023-01-24 07:57:22.491537: step: 416/531, loss: 0.0008412728784605861
2023-01-24 07:57:23.569771: step: 420/531, loss: 0.0016794379334896803
2023-01-24 07:57:24.645978: step: 424/531, loss: 0.00033171536051668227
2023-01-24 07:57:25.728003: step: 428/531, loss: 0.000693941256031394
2023-01-24 07:57:26.802135: step: 432/531, loss: 0.0008372759912163019
2023-01-24 07:57:27.868175: step: 436/531, loss: 0.002383533166721463
2023-01-24 07:57:28.926771: step: 440/531, loss: 0.00023720662284176797
2023-01-24 07:57:30.015130: step: 444/531, loss: 6.657603080384433e-06
2023-01-24 07:57:31.094835: step: 448/531, loss: 0.00045885637518949807
2023-01-24 07:57:32.175735: step: 452/531, loss: 0.0025257784873247147
2023-01-24 07:57:33.245005: step: 456/531, loss: 0.00575175741687417
2023-01-24 07:57:34.291725: step: 460/531, loss: 0.00470378901809454
2023-01-24 07:57:35.347821: step: 464/531, loss: 0.001136065344326198
2023-01-24 07:57:36.400588: step: 468/531, loss: 0.004996010102331638
2023-01-24 07:57:37.469361: step: 472/531, loss: 0.0033562418539077044
2023-01-24 07:57:38.540628: step: 476/531, loss: 0.00822437833994627
2023-01-24 07:57:39.613457: step: 480/531, loss: 0.02308301255106926
2023-01-24 07:57:40.665064: step: 484/531, loss: 0.007869339548051357
2023-01-24 07:57:41.724306: step: 488/531, loss: 0.00032674174872227013
2023-01-24 07:57:42.786612: step: 492/531, loss: 0.0028445899952203035
2023-01-24 07:57:43.853682: step: 496/531, loss: 0.00431124959141016
2023-01-24 07:57:44.914650: step: 500/531, loss: 0.0010724717285484076
2023-01-24 07:57:45.996073: step: 504/531, loss: 0.010192510671913624
2023-01-24 07:57:47.058997: step: 508/531, loss: 0.003565502353012562
2023-01-24 07:57:48.124005: step: 512/531, loss: 0.003772348864004016
2023-01-24 07:57:49.192915: step: 516/531, loss: 0.0031863315962255
2023-01-24 07:57:50.253575: step: 520/531, loss: 0.0030434601940214634
2023-01-24 07:57:51.309624: step: 524/531, loss: 0.00029302132315933704
2023-01-24 07:57:52.386421: step: 528/531, loss: 0.0015231528086587787
2023-01-24 07:57:53.447328: step: 532/531, loss: 0.0023154811933636665
2023-01-24 07:57:54.497703: step: 536/531, loss: 0.0013210881734266877
2023-01-24 07:57:55.552303: step: 540/531, loss: 0.0014938501408323646
2023-01-24 07:57:56.628837: step: 544/531, loss: 0.0035288657527416945
2023-01-24 07:57:57.700095: step: 548/531, loss: 0.0019634172786027193
2023-01-24 07:57:58.751093: step: 552/531, loss: 6.07566016697092e-06
2023-01-24 07:57:59.833444: step: 556/531, loss: 0.0037721225526183844
2023-01-24 07:58:00.899233: step: 560/531, loss: 0.0002379878278588876
2023-01-24 07:58:01.959853: step: 564/531, loss: 0.012581178918480873
2023-01-24 07:58:03.009201: step: 568/531, loss: 0.00033885397715494037
2023-01-24 07:58:04.065827: step: 572/531, loss: 0.0029925929848104715
2023-01-24 07:58:05.113006: step: 576/531, loss: 0.002095448086038232
2023-01-24 07:58:06.166280: step: 580/531, loss: 5.0195154472021386e-05
2023-01-24 07:58:07.225037: step: 584/531, loss: 0.00031893744016997516
2023-01-24 07:58:08.300449: step: 588/531, loss: 0.010178529657423496
2023-01-24 07:58:09.356701: step: 592/531, loss: 0.0002997489646077156
2023-01-24 07:58:10.419647: step: 596/531, loss: 0.00027759699150919914
2023-01-24 07:58:11.496646: step: 600/531, loss: 0.0005925332079641521
2023-01-24 07:58:12.599147: step: 604/531, loss: 0.0025195046328008175
2023-01-24 07:58:13.682981: step: 608/531, loss: 0.0005067794118076563
2023-01-24 07:58:14.756626: step: 612/531, loss: 0.001997646875679493
2023-01-24 07:58:15.836014: step: 616/531, loss: 0.0013828689698129892
2023-01-24 07:58:16.887608: step: 620/531, loss: 0.0013104738900437951
2023-01-24 07:58:17.952314: step: 624/531, loss: 0.0012215077877044678
2023-01-24 07:58:19.017489: step: 628/531, loss: 0.0014896633801981807
2023-01-24 07:58:20.082301: step: 632/531, loss: 0.0002536572574172169
2023-01-24 07:58:21.136630: step: 636/531, loss: 0.0032729008235037327
2023-01-24 07:58:22.188480: step: 640/531, loss: 0.005137813743203878
2023-01-24 07:58:23.247756: step: 644/531, loss: 0.005632741842418909
2023-01-24 07:58:24.319320: step: 648/531, loss: 0.0017411921871826053
2023-01-24 07:58:25.378125: step: 652/531, loss: 0.005432858597487211
2023-01-24 07:58:26.433237: step: 656/531, loss: 0.007814447395503521
2023-01-24 07:58:27.484854: step: 660/531, loss: 0.0018666234100237489
2023-01-24 07:58:28.548106: step: 664/531, loss: 0.004743272438645363
2023-01-24 07:58:29.626406: step: 668/531, loss: 0.0026119311805814505
2023-01-24 07:58:30.687810: step: 672/531, loss: 0.005119148641824722
2023-01-24 07:58:31.750058: step: 676/531, loss: 0.0009645094978623092
2023-01-24 07:58:32.810160: step: 680/531, loss: 0.002783802803605795
2023-01-24 07:58:33.872205: step: 684/531, loss: 0.0031408776994794607
2023-01-24 07:58:34.924905: step: 688/531, loss: 8.268315286841244e-05
2023-01-24 07:58:36.006818: step: 692/531, loss: 0.00182149198371917
2023-01-24 07:58:37.064649: step: 696/531, loss: 0.0017728491220623255
2023-01-24 07:58:38.132974: step: 700/531, loss: 0.005128629505634308
2023-01-24 07:58:39.185446: step: 704/531, loss: 0.02272040955722332
2023-01-24 07:58:40.237542: step: 708/531, loss: 0.0009333566995337605
2023-01-24 07:58:41.295161: step: 712/531, loss: 0.0015171220293268561
2023-01-24 07:58:42.362769: step: 716/531, loss: 0.005915905814617872
2023-01-24 07:58:43.412170: step: 720/531, loss: 8.707794768270105e-05
2023-01-24 07:58:44.480172: step: 724/531, loss: 0.0015791140031069517
2023-01-24 07:58:45.532594: step: 728/531, loss: 0.00224265456199646
2023-01-24 07:58:46.608069: step: 732/531, loss: 0.014692768454551697
2023-01-24 07:58:47.683094: step: 736/531, loss: 0.0011341115459799767
2023-01-24 07:58:48.724818: step: 740/531, loss: 0.00010615502105792984
2023-01-24 07:58:49.789256: step: 744/531, loss: 0.0009733618353493512
2023-01-24 07:58:50.844011: step: 748/531, loss: 0.000630239665042609
2023-01-24 07:58:51.895725: step: 752/531, loss: 6.670024595223367e-05
2023-01-24 07:58:52.952858: step: 756/531, loss: 0.002582815708592534
2023-01-24 07:58:54.021080: step: 760/531, loss: 0.0065236459486186504
2023-01-24 07:58:55.070011: step: 764/531, loss: 0.0005398447392508388
2023-01-24 07:58:56.152899: step: 768/531, loss: 0.002886428963392973
2023-01-24 07:58:57.206023: step: 772/531, loss: 1.2386779417283833e-05
2023-01-24 07:58:58.272159: step: 776/531, loss: 0.005482846405357122
2023-01-24 07:58:59.337031: step: 780/531, loss: 0.007490086369216442
2023-01-24 07:59:00.410614: step: 784/531, loss: 0.000914071686565876
2023-01-24 07:59:01.477397: step: 788/531, loss: 0.008129005320370197
2023-01-24 07:59:02.545713: step: 792/531, loss: 0.008872500620782375
2023-01-24 07:59:03.603836: step: 796/531, loss: 4.6977449528640136e-05
2023-01-24 07:59:04.666989: step: 800/531, loss: 0.009049315005540848
2023-01-24 07:59:05.730142: step: 804/531, loss: 0.007938825525343418
2023-01-24 07:59:06.797589: step: 808/531, loss: 0.004597396589815617
2023-01-24 07:59:07.864892: step: 812/531, loss: 2.0720905013149604e-05
2023-01-24 07:59:08.924980: step: 816/531, loss: 0.0005779388593509793
2023-01-24 07:59:09.988870: step: 820/531, loss: 0.0012223701924085617
2023-01-24 07:59:11.043386: step: 824/531, loss: 0.0022516080643981695
2023-01-24 07:59:12.110192: step: 828/531, loss: 0.00019816841813735664
2023-01-24 07:59:13.175540: step: 832/531, loss: 0.005344463977962732
2023-01-24 07:59:14.235452: step: 836/531, loss: 0.004119896795600653
2023-01-24 07:59:15.295036: step: 840/531, loss: 0.007639960385859013
2023-01-24 07:59:16.342225: step: 844/531, loss: 0.0061889891512691975
2023-01-24 07:59:17.398267: step: 848/531, loss: 0.014041555114090443
2023-01-24 07:59:18.475966: step: 852/531, loss: 0.01117026899009943
2023-01-24 07:59:19.531111: step: 856/531, loss: 0.0016999348299577832
2023-01-24 07:59:20.586521: step: 860/531, loss: 0.0023541594855487347
2023-01-24 07:59:21.651595: step: 864/531, loss: 0.006213717628270388
2023-01-24 07:59:22.706286: step: 868/531, loss: 0.025150950998067856
2023-01-24 07:59:23.791243: step: 872/531, loss: 0.0012401898857206106
2023-01-24 07:59:24.838649: step: 876/531, loss: 9.335210779681802e-05
2023-01-24 07:59:25.900828: step: 880/531, loss: 0.00022841035388410091
2023-01-24 07:59:26.966517: step: 884/531, loss: 0.017027227208018303
2023-01-24 07:59:28.032344: step: 888/531, loss: 0.00010077827755594626
2023-01-24 07:59:29.091173: step: 892/531, loss: 0.0006659696809947491
2023-01-24 07:59:30.137463: step: 896/531, loss: 0.0004178892995696515
2023-01-24 07:59:31.198766: step: 900/531, loss: 0.0016962476074695587
2023-01-24 07:59:32.248275: step: 904/531, loss: 0.008167213760316372
2023-01-24 07:59:33.330894: step: 908/531, loss: 0.002180703915655613
2023-01-24 07:59:34.381217: step: 912/531, loss: 0.007386069279164076
2023-01-24 07:59:35.462308: step: 916/531, loss: 0.009456770494580269
2023-01-24 07:59:36.525789: step: 920/531, loss: 0.005559196230024099
2023-01-24 07:59:37.607219: step: 924/531, loss: 0.006130869034677744
2023-01-24 07:59:38.673933: step: 928/531, loss: 0.0005443996051326394
2023-01-24 07:59:39.737045: step: 932/531, loss: 0.0017750472761690617
2023-01-24 07:59:40.812789: step: 936/531, loss: 0.0008147003827616572
2023-01-24 07:59:41.891319: step: 940/531, loss: 0.0028524252120405436
2023-01-24 07:59:42.938661: step: 944/531, loss: 0.005025567952543497
2023-01-24 07:59:44.012673: step: 948/531, loss: 0.011067330837249756
2023-01-24 07:59:45.067010: step: 952/531, loss: 0.005371290259063244
2023-01-24 07:59:46.132600: step: 956/531, loss: 0.008980665355920792
2023-01-24 07:59:47.204888: step: 960/531, loss: 0.0003326531150378287
2023-01-24 07:59:48.265634: step: 964/531, loss: 0.0022596947383135557
2023-01-24 07:59:49.326609: step: 968/531, loss: 4.021526183350943e-05
2023-01-24 07:59:50.390872: step: 972/531, loss: 0.011506552807986736
2023-01-24 07:59:51.471019: step: 976/531, loss: 0.014786058105528355
2023-01-24 07:59:52.548239: step: 980/531, loss: 0.063012033700943
2023-01-24 07:59:53.599585: step: 984/531, loss: 0.0027725694235414267
2023-01-24 07:59:54.664108: step: 988/531, loss: 0.0001401176123181358
2023-01-24 07:59:55.722407: step: 992/531, loss: 0.014190798625349998
2023-01-24 07:59:56.795103: step: 996/531, loss: 0.022968707606196404
2023-01-24 07:59:57.868114: step: 1000/531, loss: 0.011638056486845016
2023-01-24 07:59:58.921358: step: 1004/531, loss: 5.398088978836313e-05
2023-01-24 07:59:59.990858: step: 1008/531, loss: 0.0005842193495482206
2023-01-24 08:00:01.048043: step: 1012/531, loss: 0.006642464082688093
2023-01-24 08:00:02.120117: step: 1016/531, loss: 0.01608196832239628
2023-01-24 08:00:03.182192: step: 1020/531, loss: 0.007150702644139528
2023-01-24 08:00:04.226348: step: 1024/531, loss: 0.008679691702127457
2023-01-24 08:00:05.262363: step: 1028/531, loss: 0.05388197675347328
2023-01-24 08:00:06.334290: step: 1032/531, loss: 0.061284396797418594
2023-01-24 08:00:07.391058: step: 1036/531, loss: 0.0010705149034038186
2023-01-24 08:00:08.456733: step: 1040/531, loss: 0.0030790152959525585
2023-01-24 08:00:09.525037: step: 1044/531, loss: 0.004421367309987545
2023-01-24 08:00:10.600186: step: 1048/531, loss: 0.0009097373113036156
2023-01-24 08:00:11.643516: step: 1052/531, loss: 0.0060294982977211475
2023-01-24 08:00:12.690553: step: 1056/531, loss: 0.008174785412847996
2023-01-24 08:00:13.755242: step: 1060/531, loss: 0.012843639589846134
2023-01-24 08:00:14.813842: step: 1064/531, loss: 0.0005802420200780034
2023-01-24 08:00:15.908512: step: 1068/531, loss: 0.007690838538110256
2023-01-24 08:00:16.962312: step: 1072/531, loss: 0.0034123535733669996
2023-01-24 08:00:18.023997: step: 1076/531, loss: 0.05621039494872093
2023-01-24 08:00:19.085577: step: 1080/531, loss: 0.005726216826587915
2023-01-24 08:00:20.141106: step: 1084/531, loss: 0.0012716427445411682
2023-01-24 08:00:21.213262: step: 1088/531, loss: 0.028594590723514557
2023-01-24 08:00:22.256150: step: 1092/531, loss: 0.00024010120250750333
2023-01-24 08:00:23.317369: step: 1096/531, loss: 0.0016107282135635614
2023-01-24 08:00:24.363820: step: 1100/531, loss: 0.0010938129853457212
2023-01-24 08:00:25.407523: step: 1104/531, loss: 0.004322534892708063
2023-01-24 08:00:26.476171: step: 1108/531, loss: 0.0023237746208906174
2023-01-24 08:00:27.537603: step: 1112/531, loss: 0.00018691914738155901
2023-01-24 08:00:28.619019: step: 1116/531, loss: 0.0003504491178318858
2023-01-24 08:00:29.667448: step: 1120/531, loss: 0.0017954764189198613
2023-01-24 08:00:30.733023: step: 1124/531, loss: 0.0003262172103859484
2023-01-24 08:00:31.765953: step: 1128/531, loss: 0.0044793072156608105
2023-01-24 08:00:32.827422: step: 1132/531, loss: 0.004968823865056038
2023-01-24 08:00:33.863726: step: 1136/531, loss: 6.309113814495504e-05
2023-01-24 08:00:34.932631: step: 1140/531, loss: 0.0012590914266183972
2023-01-24 08:00:35.977519: step: 1144/531, loss: 8.805541438050568e-05
2023-01-24 08:00:37.039344: step: 1148/531, loss: 0.009042898193001747
2023-01-24 08:00:38.087355: step: 1152/531, loss: 0.001615240704268217
2023-01-24 08:00:39.160235: step: 1156/531, loss: 0.026992496103048325
2023-01-24 08:00:40.217653: step: 1160/531, loss: 0.0008137584081850946
2023-01-24 08:00:41.275562: step: 1164/531, loss: 0.011020206846296787
2023-01-24 08:00:42.355805: step: 1168/531, loss: 0.0008785320678725839
2023-01-24 08:00:43.392464: step: 1172/531, loss: 0.004559738095849752
2023-01-24 08:00:44.457006: step: 1176/531, loss: 0.013241405598819256
2023-01-24 08:00:45.498141: step: 1180/531, loss: 1.5530036762356758e-05
2023-01-24 08:00:46.547381: step: 1184/531, loss: 0.025860823690891266
2023-01-24 08:00:47.612838: step: 1188/531, loss: 0.005090369377285242
2023-01-24 08:00:48.671999: step: 1192/531, loss: 0.0032372602727264166
2023-01-24 08:00:49.731441: step: 1196/531, loss: 0.0011953068897128105
2023-01-24 08:00:50.787571: step: 1200/531, loss: 0.0022225056309252977
2023-01-24 08:00:51.842639: step: 1204/531, loss: 0.0013108529383316636
2023-01-24 08:00:52.897559: step: 1208/531, loss: 8.956688543548808e-05
2023-01-24 08:00:53.948796: step: 1212/531, loss: 0.001609743689186871
2023-01-24 08:00:54.999270: step: 1216/531, loss: 0.0003628864069469273
2023-01-24 08:00:56.065913: step: 1220/531, loss: 0.0010906127281486988
2023-01-24 08:00:57.110558: step: 1224/531, loss: 0.0004920852370560169
2023-01-24 08:00:58.152846: step: 1228/531, loss: 0.003378136781975627
2023-01-24 08:00:59.199362: step: 1232/531, loss: 0.002010734286159277
2023-01-24 08:01:00.258934: step: 1236/531, loss: 0.002170839812606573
2023-01-24 08:01:01.319722: step: 1240/531, loss: 0.0006582196219824255
2023-01-24 08:01:02.371101: step: 1244/531, loss: 0.04095841571688652
2023-01-24 08:01:03.431537: step: 1248/531, loss: 0.015030969865620136
2023-01-24 08:01:04.487565: step: 1252/531, loss: 0.00022219220409169793
2023-01-24 08:01:05.541503: step: 1256/531, loss: 7.857872697059065e-05
2023-01-24 08:01:06.607643: step: 1260/531, loss: 0.0014182198792696
2023-01-24 08:01:07.679632: step: 1264/531, loss: 0.004063778556883335
2023-01-24 08:01:08.726587: step: 1268/531, loss: 0.0011769463308155537
2023-01-24 08:01:09.773204: step: 1272/531, loss: 0.010867233388125896
2023-01-24 08:01:10.847710: step: 1276/531, loss: 0.0038230204954743385
2023-01-24 08:01:11.937454: step: 1280/531, loss: 0.000911044713575393
2023-01-24 08:01:12.998908: step: 1284/531, loss: 0.001992700854316354
2023-01-24 08:01:14.078090: step: 1288/531, loss: 0.005457703024148941
2023-01-24 08:01:15.139480: step: 1292/531, loss: 0.0018652963917702436
2023-01-24 08:01:16.207588: step: 1296/531, loss: 0.003989304415881634
2023-01-24 08:01:17.263299: step: 1300/531, loss: 0.01085844449698925
2023-01-24 08:01:18.321102: step: 1304/531, loss: 0.001219116966240108
2023-01-24 08:01:19.382160: step: 1308/531, loss: 0.006250276230275631
2023-01-24 08:01:20.443847: step: 1312/531, loss: 0.00668021384626627
2023-01-24 08:01:21.498522: step: 1316/531, loss: 0.004537404049187899
2023-01-24 08:01:22.559309: step: 1320/531, loss: 0.002917621284723282
2023-01-24 08:01:23.601235: step: 1324/531, loss: 3.054946500924416e-05
2023-01-24 08:01:24.653310: step: 1328/531, loss: 0.00030456160311587155
2023-01-24 08:01:25.705827: step: 1332/531, loss: 0.001132350880652666
2023-01-24 08:01:26.764783: step: 1336/531, loss: 0.00498964125290513
2023-01-24 08:01:27.818083: step: 1340/531, loss: 0.006298901978880167
2023-01-24 08:01:28.891411: step: 1344/531, loss: 0.0023895029444247484
2023-01-24 08:01:29.948994: step: 1348/531, loss: 0.0038918203208595514
2023-01-24 08:01:31.003947: step: 1352/531, loss: 3.296085196780041e-05
2023-01-24 08:01:32.057006: step: 1356/531, loss: 0.0006127421511337161
2023-01-24 08:01:33.141915: step: 1360/531, loss: 0.011149992235004902
2023-01-24 08:01:34.188982: step: 1364/531, loss: 0.0036587396170943975
2023-01-24 08:01:35.243259: step: 1368/531, loss: 0.0017438203794881701
2023-01-24 08:01:36.302797: step: 1372/531, loss: 0.02992326393723488
2023-01-24 08:01:37.356875: step: 1376/531, loss: 8.607034396845847e-05
2023-01-24 08:01:38.418607: step: 1380/531, loss: 0.0045074219815433025
2023-01-24 08:01:39.479096: step: 1384/531, loss: 0.0012903253082185984
2023-01-24 08:01:40.532717: step: 1388/531, loss: 5.810592119814828e-05
2023-01-24 08:01:41.619358: step: 1392/531, loss: 0.0022700822446495295
2023-01-24 08:01:42.690881: step: 1396/531, loss: 0.000807271571829915
2023-01-24 08:01:43.765168: step: 1400/531, loss: 1.979072840185836e-05
2023-01-24 08:01:44.809511: step: 1404/531, loss: 0.00010419355385238305
2023-01-24 08:01:45.858976: step: 1408/531, loss: 0.0023636610712856054
2023-01-24 08:01:46.916638: step: 1412/531, loss: 0.00010474493319634348
2023-01-24 08:01:47.963426: step: 1416/531, loss: 0.0027683116495609283
2023-01-24 08:01:49.024654: step: 1420/531, loss: 0.004748487379401922
2023-01-24 08:01:50.084426: step: 1424/531, loss: 0.00281822239048779
2023-01-24 08:01:51.123862: step: 1428/531, loss: 0.0010070235002785921
2023-01-24 08:01:52.184424: step: 1432/531, loss: 3.932854724553181e-06
2023-01-24 08:01:53.253538: step: 1436/531, loss: 0.0021961256861686707
2023-01-24 08:01:54.307153: step: 1440/531, loss: 0.0008509191102348268
2023-01-24 08:01:55.372758: step: 1444/531, loss: 0.0008358809282071888
2023-01-24 08:01:56.438353: step: 1448/531, loss: 2.6334613721701317e-05
2023-01-24 08:01:57.502692: step: 1452/531, loss: 0.004515047185122967
2023-01-24 08:01:58.573778: step: 1456/531, loss: 0.003837031312286854
2023-01-24 08:01:59.636531: step: 1460/531, loss: 5.697361848433502e-05
2023-01-24 08:02:00.736882: step: 1464/531, loss: 0.0019774767570197582
2023-01-24 08:02:01.793808: step: 1468/531, loss: 4.4358290324453264e-05
2023-01-24 08:02:02.856127: step: 1472/531, loss: 0.0006438334239646792
2023-01-24 08:02:03.915587: step: 1476/531, loss: 0.0032409466803073883
2023-01-24 08:02:04.982532: step: 1480/531, loss: 0.0015242878580465913
2023-01-24 08:02:06.045946: step: 1484/531, loss: 0.003153785364702344
2023-01-24 08:02:07.106035: step: 1488/531, loss: 1.4236917195376009e-05
2023-01-24 08:02:08.180970: step: 1492/531, loss: 0.0005675765569321811
2023-01-24 08:02:09.259390: step: 1496/531, loss: 2.7047299226978794e-05
2023-01-24 08:02:10.318601: step: 1500/531, loss: 8.26976029202342e-05
2023-01-24 08:02:11.362276: step: 1504/531, loss: 0.0006109775858931243
2023-01-24 08:02:12.433584: step: 1508/531, loss: 0.0001951136946445331
2023-01-24 08:02:13.504843: step: 1512/531, loss: 0.0008975151577033103
2023-01-24 08:02:14.552520: step: 1516/531, loss: 0.0005838876240886748
2023-01-24 08:02:15.605798: step: 1520/531, loss: 0.0011557629331946373
2023-01-24 08:02:16.673683: step: 1524/531, loss: 0.011381728574633598
2023-01-24 08:02:17.735042: step: 1528/531, loss: 0.005961467511951923
2023-01-24 08:02:18.795238: step: 1532/531, loss: 0.04712522029876709
2023-01-24 08:02:19.847754: step: 1536/531, loss: 0.0025206315331161022
2023-01-24 08:02:20.906695: step: 1540/531, loss: 0.0037165971007198095
2023-01-24 08:02:21.955149: step: 1544/531, loss: 0.008586629293859005
2023-01-24 08:02:23.017560: step: 1548/531, loss: 0.007212300319224596
2023-01-24 08:02:24.083086: step: 1552/531, loss: 0.004146702587604523
2023-01-24 08:02:25.144470: step: 1556/531, loss: 0.004820911213755608
2023-01-24 08:02:26.200504: step: 1560/531, loss: 0.004934458062052727
2023-01-24 08:02:27.259993: step: 1564/531, loss: 0.007060043513774872
2023-01-24 08:02:28.305244: step: 1568/531, loss: 0.0037182329688221216
2023-01-24 08:02:29.376061: step: 1572/531, loss: 0.00265847472473979
2023-01-24 08:02:30.418453: step: 1576/531, loss: 0.00320924399420619
2023-01-24 08:02:31.472363: step: 1580/531, loss: 0.005504476837813854
2023-01-24 08:02:32.551166: step: 1584/531, loss: 0.000665211642626673
2023-01-24 08:02:33.597008: step: 1588/531, loss: 0.006778986193239689
2023-01-24 08:02:34.646332: step: 1592/531, loss: 0.0018619614420458674
2023-01-24 08:02:35.711320: step: 1596/531, loss: 0.0029642395675182343
2023-01-24 08:02:36.775340: step: 1600/531, loss: 0.003254387527704239
2023-01-24 08:02:37.844657: step: 1604/531, loss: 0.003264126367866993
2023-01-24 08:02:38.887206: step: 1608/531, loss: 0.0033200099132955074
2023-01-24 08:02:39.945671: step: 1612/531, loss: 0.002769629703834653
2023-01-24 08:02:40.998412: step: 1616/531, loss: 0.0011690377723425627
2023-01-24 08:02:42.093434: step: 1620/531, loss: 0.001325818127952516
2023-01-24 08:02:43.141701: step: 1624/531, loss: 0.0032912404276430607
2023-01-24 08:02:44.191594: step: 1628/531, loss: 0.03286954015493393
2023-01-24 08:02:45.250110: step: 1632/531, loss: 0.0005078306421637535
2023-01-24 08:02:46.308125: step: 1636/531, loss: 6.243363895919174e-05
2023-01-24 08:02:47.350540: step: 1640/531, loss: 0.0021527670323848724
2023-01-24 08:02:48.400733: step: 1644/531, loss: 0.00846614595502615
2023-01-24 08:02:49.466274: step: 1648/531, loss: 0.01128337625414133
2023-01-24 08:02:50.536850: step: 1652/531, loss: 0.0024253749288618565
2023-01-24 08:02:51.593049: step: 1656/531, loss: 0.0011595949763432145
2023-01-24 08:02:52.644992: step: 1660/531, loss: 0.0006072914693504572
2023-01-24 08:02:53.706343: step: 1664/531, loss: 0.004316008649766445
2023-01-24 08:02:54.774512: step: 1668/531, loss: 0.061830636113882065
2023-01-24 08:02:55.823801: step: 1672/531, loss: 0.004680373705923557
2023-01-24 08:02:56.864071: step: 1676/531, loss: 0.002400621073320508
2023-01-24 08:02:57.906325: step: 1680/531, loss: 0.00011722392810042948
2023-01-24 08:02:58.971341: step: 1684/531, loss: 0.002592526376247406
2023-01-24 08:03:00.043516: step: 1688/531, loss: 0.0010730191133916378
2023-01-24 08:03:01.117225: step: 1692/531, loss: 0.002417347626760602
2023-01-24 08:03:02.174829: step: 1696/531, loss: 0.014336168766021729
2023-01-24 08:03:03.236464: step: 1700/531, loss: 0.0013070888817310333
2023-01-24 08:03:04.275440: step: 1704/531, loss: 0.027085356414318085
2023-01-24 08:03:05.317960: step: 1708/531, loss: 0.00013016282173339278
2023-01-24 08:03:06.362868: step: 1712/531, loss: 0.003856057533994317
2023-01-24 08:03:07.433269: step: 1716/531, loss: 0.009995688684284687
2023-01-24 08:03:08.499988: step: 1720/531, loss: 0.00039512524381279945
2023-01-24 08:03:09.563207: step: 1724/531, loss: 0.003914263565093279
2023-01-24 08:03:10.616468: step: 1728/531, loss: 0.005618093069642782
2023-01-24 08:03:11.673649: step: 1732/531, loss: 0.006893915589898825
2023-01-24 08:03:12.726136: step: 1736/531, loss: 0.014279298484325409
2023-01-24 08:03:13.794341: step: 1740/531, loss: 0.005142610520124435
2023-01-24 08:03:14.837619: step: 1744/531, loss: 7.414120773319155e-05
2023-01-24 08:03:15.891537: step: 1748/531, loss: 0.002108305459842086
2023-01-24 08:03:16.962048: step: 1752/531, loss: 0.0018001499120146036
2023-01-24 08:03:18.019454: step: 1756/531, loss: 0.00030126600177027285
2023-01-24 08:03:19.098722: step: 1760/531, loss: 0.0054490105248987675
2023-01-24 08:03:20.156661: step: 1764/531, loss: 0.004551001824438572
2023-01-24 08:03:21.215283: step: 1768/531, loss: 8.754232112551108e-05
2023-01-24 08:03:22.263988: step: 1772/531, loss: 0.010184419341385365
2023-01-24 08:03:23.335523: step: 1776/531, loss: 0.005537926685065031
2023-01-24 08:03:24.398868: step: 1780/531, loss: 0.002223237883299589
2023-01-24 08:03:25.449085: step: 1784/531, loss: 0.0013415184803307056
2023-01-24 08:03:26.508630: step: 1788/531, loss: 0.004140784032642841
2023-01-24 08:03:27.563324: step: 1792/531, loss: 0.0009523855405859649
2023-01-24 08:03:28.615131: step: 1796/531, loss: 0.004413597751408815
2023-01-24 08:03:29.660454: step: 1800/531, loss: 0.003502572188153863
2023-01-24 08:03:30.707447: step: 1804/531, loss: 0.00018110548262484372
2023-01-24 08:03:31.775154: step: 1808/531, loss: 0.0012267277343198657
2023-01-24 08:03:32.817045: step: 1812/531, loss: 0.0004821026523131877
2023-01-24 08:03:33.877620: step: 1816/531, loss: 0.0026140213012695312
2023-01-24 08:03:34.937191: step: 1820/531, loss: 0.019991111010313034
2023-01-24 08:03:35.997134: step: 1824/531, loss: 0.005648982711136341
2023-01-24 08:03:37.075010: step: 1828/531, loss: 0.0006146921659819782
2023-01-24 08:03:38.144374: step: 1832/531, loss: 0.0017123919678851962
2023-01-24 08:03:39.207271: step: 1836/531, loss: 0.0022584530524909496
2023-01-24 08:03:40.256771: step: 1840/531, loss: 0.0035019302740693092
2023-01-24 08:03:41.309338: step: 1844/531, loss: 0.0008214695262722671
2023-01-24 08:03:42.367829: step: 1848/531, loss: 0.0020750330295413733
2023-01-24 08:03:43.408086: step: 1852/531, loss: 0.001352264080196619
2023-01-24 08:03:44.485228: step: 1856/531, loss: 0.0014432482421398163
2023-01-24 08:03:45.534899: step: 1860/531, loss: 0.00410476652905345
2023-01-24 08:03:46.585822: step: 1864/531, loss: 5.1833023462677374e-05
2023-01-24 08:03:47.653193: step: 1868/531, loss: 0.00209336681291461
2023-01-24 08:03:48.712798: step: 1872/531, loss: 0.00021056714467704296
2023-01-24 08:03:49.794691: step: 1876/531, loss: 0.002319770399481058
2023-01-24 08:03:50.846480: step: 1880/531, loss: 7.407455268548802e-05
2023-01-24 08:03:51.888744: step: 1884/531, loss: 0.009329630061984062
2023-01-24 08:03:52.955175: step: 1888/531, loss: 0.00022655384964309633
2023-01-24 08:03:54.018157: step: 1892/531, loss: 0.0006434321985580027
2023-01-24 08:03:55.082391: step: 1896/531, loss: 0.008055443875491619
2023-01-24 08:03:56.143287: step: 1900/531, loss: 0.0006588028045371175
2023-01-24 08:03:57.194995: step: 1904/531, loss: 0.0009856290416792035
2023-01-24 08:03:58.251744: step: 1908/531, loss: 0.0006299313972704113
2023-01-24 08:03:59.300999: step: 1912/531, loss: 0.0004923464148305357
2023-01-24 08:04:00.343285: step: 1916/531, loss: 0.0007975624175742269
2023-01-24 08:04:01.397202: step: 1920/531, loss: 0.013214414939284325
2023-01-24 08:04:02.465406: step: 1924/531, loss: 0.003228053916245699
2023-01-24 08:04:03.527038: step: 1928/531, loss: 0.005804707296192646
2023-01-24 08:04:04.581465: step: 1932/531, loss: 0.0049368226900696754
2023-01-24 08:04:05.639020: step: 1936/531, loss: 0.004499434493482113
2023-01-24 08:04:06.694543: step: 1940/531, loss: 0.0029881522059440613
2023-01-24 08:04:07.755957: step: 1944/531, loss: 0.002854348160326481
2023-01-24 08:04:08.816134: step: 1948/531, loss: 0.002133850008249283
2023-01-24 08:04:09.875168: step: 1952/531, loss: 0.0019627660512924194
2023-01-24 08:04:10.946005: step: 1956/531, loss: 0.001569436746649444
2023-01-24 08:04:11.987854: step: 1960/531, loss: 0.011065283790230751
2023-01-24 08:04:13.042368: step: 1964/531, loss: 0.0012104656780138612
2023-01-24 08:04:14.093836: step: 1968/531, loss: 0.0035701077431440353
2023-01-24 08:04:15.149766: step: 1972/531, loss: 0.00444983784109354
2023-01-24 08:04:16.231373: step: 1976/531, loss: 0.0026652247179299593
2023-01-24 08:04:17.271503: step: 1980/531, loss: 0.0016057912725955248
2023-01-24 08:04:18.328078: step: 1984/531, loss: 0.0067677260376513
2023-01-24 08:04:19.383371: step: 1988/531, loss: 0.01013968512415886
2023-01-24 08:04:20.457494: step: 1992/531, loss: 0.0029363830108195543
2023-01-24 08:04:21.521234: step: 1996/531, loss: 0.010073035955429077
2023-01-24 08:04:22.584152: step: 2000/531, loss: 0.0294170044362545
2023-01-24 08:04:23.621171: step: 2004/531, loss: 2.329733433725778e-05
2023-01-24 08:04:24.676776: step: 2008/531, loss: 0.005676647182554007
2023-01-24 08:04:25.734632: step: 2012/531, loss: 0.00281923683360219
2023-01-24 08:04:26.801559: step: 2016/531, loss: 0.0018013858934864402
2023-01-24 08:04:27.872687: step: 2020/531, loss: 0.0018166168592870235
2023-01-24 08:04:28.934078: step: 2024/531, loss: 0.009231380186975002
2023-01-24 08:04:29.999652: step: 2028/531, loss: 0.007757980842143297
2023-01-24 08:04:31.057091: step: 2032/531, loss: 0.00017122748249676079
2023-01-24 08:04:32.119832: step: 2036/531, loss: 0.00026397412875667214
2023-01-24 08:04:33.169958: step: 2040/531, loss: 0.000343112536938861
2023-01-24 08:04:34.226371: step: 2044/531, loss: 0.0049992213025689125
2023-01-24 08:04:35.300602: step: 2048/531, loss: 0.014012685976922512
2023-01-24 08:04:36.362881: step: 2052/531, loss: 0.005404432769864798
2023-01-24 08:04:37.426874: step: 2056/531, loss: 0.000970169494394213
2023-01-24 08:04:38.500189: step: 2060/531, loss: 0.001486293156631291
2023-01-24 08:04:39.559097: step: 2064/531, loss: 0.0044876281172037125
2023-01-24 08:04:40.605666: step: 2068/531, loss: 0.004209108650684357
2023-01-24 08:04:41.664444: step: 2072/531, loss: 0.001256016199477017
2023-01-24 08:04:42.723656: step: 2076/531, loss: 0.002157731680199504
2023-01-24 08:04:43.795786: step: 2080/531, loss: 0.006548232864588499
2023-01-24 08:04:44.846227: step: 2084/531, loss: 5.276700539980084e-05
2023-01-24 08:04:45.891573: step: 2088/531, loss: 0.009501063264906406
2023-01-24 08:04:46.965215: step: 2092/531, loss: 0.007542643696069717
2023-01-24 08:04:48.017249: step: 2096/531, loss: 0.00042067599133588374
2023-01-24 08:04:49.074442: step: 2100/531, loss: 0.0009010783978737891
2023-01-24 08:04:50.137144: step: 2104/531, loss: 0.017282428219914436
2023-01-24 08:04:51.168904: step: 2108/531, loss: 0.00039278127951547503
2023-01-24 08:04:52.210599: step: 2112/531, loss: 0.0002482626005075872
2023-01-24 08:04:53.271235: step: 2116/531, loss: 0.0001620492694200948
2023-01-24 08:04:54.338473: step: 2120/531, loss: 0.004453693982213736
2023-01-24 08:04:55.413488: step: 2124/531, loss: 0.0007471845019608736
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3930320171215678, 'r': 0.3206902606494766, 'f1': 0.35319491611760534}, 'combined': 0.26024888556034076, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38903250643343784, 'r': 0.2764270649860676, 'f1': 0.32320254619878647}, 'combined': 0.2023791644422308, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3780164324072552, 'r': 0.3399995995465635, 'f1': 0.3580015763457322}, 'combined': 0.26379063520211843, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3894884773660832, 'r': 0.2872872628362994, 'f1': 0.3306710684851646}, 'combined': 0.20492291568094706, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36787546114133185, 'r': 0.3301804423526565, 'f1': 0.34801018623969987}, 'combined': 0.2564285582818841, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41155289730419264, 'r': 0.28649128649128647, 'f1': 0.33781907147138407}, 'combined': 0.22409779988695777, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.40217391304347827, 'r': 0.40217391304347827, 'f1': 0.40217391304347827}, 'combined': 0.20108695652173914, 'stategy': 1, 'epoch': 13}
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, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:07:18.940930: step: 4/531, loss: 0.0016820986056700349
2023-01-24 08:07:19.984283: step: 8/531, loss: 0.001272919587790966
2023-01-24 08:07:21.036851: step: 12/531, loss: 0.0018223518272861838
2023-01-24 08:07:22.083051: step: 16/531, loss: 0.0001720621803542599
2023-01-24 08:07:23.136138: step: 20/531, loss: 0.0011702225310727954
2023-01-24 08:07:24.201856: step: 24/531, loss: 0.0004568614240270108
2023-01-24 08:07:25.233327: step: 28/531, loss: 0.00287062325514853
2023-01-24 08:07:26.293712: step: 32/531, loss: 0.00017823060625232756
2023-01-24 08:07:27.327897: step: 36/531, loss: 0.0004975678748451173
2023-01-24 08:07:28.374635: step: 40/531, loss: 0.0011281631886959076
2023-01-24 08:07:29.429529: step: 44/531, loss: 0.021383967250585556
2023-01-24 08:07:30.487983: step: 48/531, loss: 0.0015692919259890914
2023-01-24 08:07:31.547688: step: 52/531, loss: 0.00544044841080904
2023-01-24 08:07:32.593606: step: 56/531, loss: 0.0009331905166618526
2023-01-24 08:07:33.642953: step: 60/531, loss: 0.003196435747668147
2023-01-24 08:07:34.716900: step: 64/531, loss: 0.009559637866914272
2023-01-24 08:07:35.797356: step: 68/531, loss: 0.00292372633703053
2023-01-24 08:07:36.837915: step: 72/531, loss: 1.689396049187053e-05
2023-01-24 08:07:37.900052: step: 76/531, loss: 0.000737437978386879
2023-01-24 08:07:38.958105: step: 80/531, loss: 0.0008886161958798766
2023-01-24 08:07:40.016032: step: 84/531, loss: 0.0014787687687203288
2023-01-24 08:07:41.077398: step: 88/531, loss: 0.001064131036400795
2023-01-24 08:07:42.149355: step: 92/531, loss: 0.011055948212742805
2023-01-24 08:07:43.223909: step: 96/531, loss: 0.004343170206993818
2023-01-24 08:07:44.273157: step: 100/531, loss: 0.0023446830455213785
2023-01-24 08:07:45.345555: step: 104/531, loss: 0.002073544543236494
2023-01-24 08:07:46.421167: step: 108/531, loss: 0.00457299267873168
2023-01-24 08:07:47.475873: step: 112/531, loss: 0.0011097511742264032
2023-01-24 08:07:48.525445: step: 116/531, loss: 0.0035200065467506647
2023-01-24 08:07:49.591056: step: 120/531, loss: 0.0012597950408235192
2023-01-24 08:07:50.642055: step: 124/531, loss: 0.004782854579389095
2023-01-24 08:07:51.695870: step: 128/531, loss: 0.00341703649610281
2023-01-24 08:07:52.749338: step: 132/531, loss: 0.0008929745526984334
2023-01-24 08:07:53.797542: step: 136/531, loss: 0.003075639484450221
2023-01-24 08:07:54.849160: step: 140/531, loss: 0.003302244935184717
2023-01-24 08:07:55.904997: step: 144/531, loss: 0.004704549442976713
2023-01-24 08:07:56.967312: step: 148/531, loss: 0.001426379894837737
2023-01-24 08:07:58.024538: step: 152/531, loss: 0.007419176399707794
2023-01-24 08:07:59.083408: step: 156/531, loss: 0.0029818553011864424
2023-01-24 08:08:00.134644: step: 160/531, loss: 0.00545874796807766
2023-01-24 08:08:01.201237: step: 164/531, loss: 0.006517227739095688
2023-01-24 08:08:02.257196: step: 168/531, loss: 0.0009801655542105436
2023-01-24 08:08:03.320307: step: 172/531, loss: 0.001989149022847414
2023-01-24 08:08:04.391286: step: 176/531, loss: 0.016178661957383156
2023-01-24 08:08:05.463580: step: 180/531, loss: 0.0005514121730811894
2023-01-24 08:08:06.512143: step: 184/531, loss: 0.001059800386428833
2023-01-24 08:08:07.566590: step: 188/531, loss: 0.0003515127464197576
2023-01-24 08:08:08.637359: step: 192/531, loss: 0.011831310577690601
2023-01-24 08:08:09.688484: step: 196/531, loss: 0.0006817436078563333
2023-01-24 08:08:10.754131: step: 200/531, loss: 0.004688303917646408
2023-01-24 08:08:11.816356: step: 204/531, loss: 0.0029748762026429176
2023-01-24 08:08:12.880745: step: 208/531, loss: 0.0007723732851445675
2023-01-24 08:08:13.951021: step: 212/531, loss: 0.0005731121054850519
2023-01-24 08:08:15.019227: step: 216/531, loss: 0.003231952665373683
2023-01-24 08:08:16.069870: step: 220/531, loss: 0.003479874227195978
2023-01-24 08:08:17.131806: step: 224/531, loss: 0.012836527079343796
2023-01-24 08:08:18.192642: step: 228/531, loss: 0.0012740707024931908
2023-01-24 08:08:19.244828: step: 232/531, loss: 0.003075475338846445
2023-01-24 08:08:20.305708: step: 236/531, loss: 7.526024273829535e-05
2023-01-24 08:08:21.351764: step: 240/531, loss: 0.0032913503237068653
2023-01-24 08:08:22.423270: step: 244/531, loss: 0.02079927735030651
2023-01-24 08:08:23.498914: step: 248/531, loss: 0.006989686284214258
2023-01-24 08:08:24.562358: step: 252/531, loss: 0.00024235071032308042
2023-01-24 08:08:25.615471: step: 256/531, loss: 0.0024690113496035337
2023-01-24 08:08:26.663891: step: 260/531, loss: 5.9587280702544376e-05
2023-01-24 08:08:27.713310: step: 264/531, loss: 0.0003184451488777995
2023-01-24 08:08:28.775735: step: 268/531, loss: 0.0011628486681729555
2023-01-24 08:08:29.827376: step: 272/531, loss: 1.5757747462430416e-07
2023-01-24 08:08:30.895019: step: 276/531, loss: 0.0033106112387031317
2023-01-24 08:08:31.950964: step: 280/531, loss: 9.4774310127832e-05
2023-01-24 08:08:33.008758: step: 284/531, loss: 0.012757186777889729
2023-01-24 08:08:34.071413: step: 288/531, loss: 0.0007110279984772205
2023-01-24 08:08:35.132993: step: 292/531, loss: 0.00045626662904396653
2023-01-24 08:08:36.183246: step: 296/531, loss: 0.0016196728684008121
2023-01-24 08:08:37.244545: step: 300/531, loss: 0.00012583131319843233
2023-01-24 08:08:38.299754: step: 304/531, loss: 0.0010653295321390033
2023-01-24 08:08:39.373706: step: 308/531, loss: 0.009608013555407524
2023-01-24 08:08:40.452442: step: 312/531, loss: 0.007180084008723497
2023-01-24 08:08:41.519040: step: 316/531, loss: 0.0002772776933852583
2023-01-24 08:08:42.588484: step: 320/531, loss: 0.0010277617257088423
2023-01-24 08:08:43.647503: step: 324/531, loss: 0.008284168317914009
2023-01-24 08:08:44.703974: step: 328/531, loss: 2.0305313228163868e-05
2023-01-24 08:08:45.757688: step: 332/531, loss: 0.0028432130347937346
2023-01-24 08:08:46.835345: step: 336/531, loss: 0.004729862324893475
2023-01-24 08:08:47.900493: step: 340/531, loss: 0.0015953927068039775
2023-01-24 08:08:48.964616: step: 344/531, loss: 0.004616578575223684
2023-01-24 08:08:50.037191: step: 348/531, loss: 9.849398338701576e-05
2023-01-24 08:08:51.082763: step: 352/531, loss: 0.00017300553736276925
2023-01-24 08:08:52.135340: step: 356/531, loss: 0.00025847461074590683
2023-01-24 08:08:53.180573: step: 360/531, loss: 0.0011382269440218806
2023-01-24 08:08:54.242064: step: 364/531, loss: 0.003926119767129421
2023-01-24 08:08:55.298750: step: 368/531, loss: 5.382801191444742e-07
2023-01-24 08:08:56.350917: step: 372/531, loss: 0.004052409902215004
2023-01-24 08:08:57.417887: step: 376/531, loss: 0.0041965399868786335
2023-01-24 08:08:58.483919: step: 380/531, loss: 0.00027606557705439627
2023-01-24 08:08:59.534594: step: 384/531, loss: 0.008244985714554787
2023-01-24 08:09:00.591505: step: 388/531, loss: 0.023369159549474716
2023-01-24 08:09:01.660496: step: 392/531, loss: 0.008395473472774029
2023-01-24 08:09:02.697574: step: 396/531, loss: 0.00015345678548328578
2023-01-24 08:09:03.744704: step: 400/531, loss: 0.0058576627634465694
2023-01-24 08:09:04.810955: step: 404/531, loss: 0.023645292967557907
2023-01-24 08:09:05.858078: step: 408/531, loss: 0.005871656816452742
2023-01-24 08:09:06.919385: step: 412/531, loss: 0.0
2023-01-24 08:09:07.985463: step: 416/531, loss: 0.009561366401612759
2023-01-24 08:09:09.042815: step: 420/531, loss: 0.003358026035130024
2023-01-24 08:09:10.101014: step: 424/531, loss: 2.7298731311020674e-06
2023-01-24 08:09:11.144745: step: 428/531, loss: 0.000304831366520375
2023-01-24 08:09:12.203654: step: 432/531, loss: 0.0005358936614356935
2023-01-24 08:09:13.270852: step: 436/531, loss: 0.004430905915796757
2023-01-24 08:09:14.323607: step: 440/531, loss: 0.009700379334390163
2023-01-24 08:09:15.402689: step: 444/531, loss: 0.01859997771680355
2023-01-24 08:09:16.473396: step: 448/531, loss: 0.005416507832705975
2023-01-24 08:09:17.529565: step: 452/531, loss: 0.001897883485071361
2023-01-24 08:09:18.580686: step: 456/531, loss: 0.005075945984572172
2023-01-24 08:09:19.643025: step: 460/531, loss: 0.002688433276489377
2023-01-24 08:09:20.702120: step: 464/531, loss: 0.0011071580229327083
2023-01-24 08:09:21.746726: step: 468/531, loss: 0.0009355830843560398
2023-01-24 08:09:22.816823: step: 472/531, loss: 0.022723183035850525
2023-01-24 08:09:23.874855: step: 476/531, loss: 0.0018428267212584615
2023-01-24 08:09:24.922933: step: 480/531, loss: 0.0005078070098534226
2023-01-24 08:09:25.972239: step: 484/531, loss: 0.011524239555001259
2023-01-24 08:09:27.038788: step: 488/531, loss: 0.022834865376353264
2023-01-24 08:09:28.101274: step: 492/531, loss: 0.0035942893009632826
2023-01-24 08:09:29.171145: step: 496/531, loss: 0.011420325376093388
2023-01-24 08:09:30.219256: step: 500/531, loss: 0.00018307343998458236
2023-01-24 08:09:31.272512: step: 504/531, loss: 0.005503448192030191
2023-01-24 08:09:32.340585: step: 508/531, loss: 0.0003262669197283685
2023-01-24 08:09:33.413060: step: 512/531, loss: 0.001203661086037755
2023-01-24 08:09:34.487330: step: 516/531, loss: 0.002987103769555688
2023-01-24 08:09:35.552869: step: 520/531, loss: 0.0018034788081422448
2023-01-24 08:09:36.619192: step: 524/531, loss: 0.00021906476467847824
2023-01-24 08:09:37.666849: step: 528/531, loss: 0.004053742159157991
2023-01-24 08:09:38.712383: step: 532/531, loss: 0.001761258696205914
2023-01-24 08:09:39.762574: step: 536/531, loss: 0.0007478193147107959
2023-01-24 08:09:40.826889: step: 540/531, loss: 0.0016021106857806444
2023-01-24 08:09:41.926632: step: 544/531, loss: 0.003069615922868252
2023-01-24 08:09:42.979473: step: 548/531, loss: 0.006721076089888811
2023-01-24 08:09:44.044168: step: 552/531, loss: 0.00018410134362056851
2023-01-24 08:09:45.107112: step: 556/531, loss: 0.005953546613454819
2023-01-24 08:09:46.165540: step: 560/531, loss: 0.00891153048723936
2023-01-24 08:09:47.221585: step: 564/531, loss: 0.0005984383169561625
2023-01-24 08:09:48.286749: step: 568/531, loss: 0.002336231991648674
2023-01-24 08:09:49.350920: step: 572/531, loss: 0.004336831625550985
2023-01-24 08:09:50.422535: step: 576/531, loss: 0.002549282740801573
2023-01-24 08:09:51.489649: step: 580/531, loss: 0.004837400745600462
2023-01-24 08:09:52.548121: step: 584/531, loss: 0.00420438963919878
2023-01-24 08:09:53.600935: step: 588/531, loss: 0.00033191306283697486
2023-01-24 08:09:54.658408: step: 592/531, loss: 0.006384607870131731
2023-01-24 08:09:55.724190: step: 596/531, loss: 0.04607657343149185
2023-01-24 08:09:56.778382: step: 600/531, loss: 0.0156918466091156
2023-01-24 08:09:57.825167: step: 604/531, loss: 0.004715701565146446
2023-01-24 08:09:58.911433: step: 608/531, loss: 0.0021382300183176994
2023-01-24 08:09:59.968341: step: 612/531, loss: 6.838714762125164e-05
2023-01-24 08:10:01.051404: step: 616/531, loss: 0.0020097082015126944
2023-01-24 08:10:02.103355: step: 620/531, loss: 0.001160504063591361
2023-01-24 08:10:03.164447: step: 624/531, loss: 0.01615995727479458
2023-01-24 08:10:04.228121: step: 628/531, loss: 0.0004716401163022965
2023-01-24 08:10:05.307182: step: 632/531, loss: 0.00023386311659123749
2023-01-24 08:10:06.379149: step: 636/531, loss: 0.0010904439259320498
2023-01-24 08:10:07.436827: step: 640/531, loss: 0.03402023762464523
2023-01-24 08:10:08.509632: step: 644/531, loss: 0.008198312483727932
2023-01-24 08:10:09.580298: step: 648/531, loss: 0.005444493610411882
2023-01-24 08:10:10.651852: step: 652/531, loss: 0.0010515376925468445
2023-01-24 08:10:11.706448: step: 656/531, loss: 0.001187400775961578
2023-01-24 08:10:12.782047: step: 660/531, loss: 0.0029704223852604628
2023-01-24 08:10:13.840684: step: 664/531, loss: 0.005244607571512461
2023-01-24 08:10:14.891643: step: 668/531, loss: 0.00024652108550071716
2023-01-24 08:10:15.929759: step: 672/531, loss: 4.3499308958416805e-05
2023-01-24 08:10:16.967941: step: 676/531, loss: 0.0010115631157532334
2023-01-24 08:10:18.024865: step: 680/531, loss: 6.89786538714543e-05
2023-01-24 08:10:19.082328: step: 684/531, loss: 0.011706339195370674
2023-01-24 08:10:20.127848: step: 688/531, loss: 0.00024610068066976964
2023-01-24 08:10:21.205424: step: 692/531, loss: 0.00041355937719345093
2023-01-24 08:10:22.263319: step: 696/531, loss: 0.003793865442276001
2023-01-24 08:10:23.323098: step: 700/531, loss: 0.0017515491927042603
2023-01-24 08:10:24.386069: step: 704/531, loss: 0.0004933085292577744
2023-01-24 08:10:25.449931: step: 708/531, loss: 0.003368173725903034
2023-01-24 08:10:26.503899: step: 712/531, loss: 0.0026110573671758175
2023-01-24 08:10:27.575962: step: 716/531, loss: 0.010060235857963562
2023-01-24 08:10:28.619690: step: 720/531, loss: 0.0033873047214001417
2023-01-24 08:10:29.681161: step: 724/531, loss: 0.006929227150976658
2023-01-24 08:10:30.738125: step: 728/531, loss: 0.0001884236407931894
2023-01-24 08:10:31.796836: step: 732/531, loss: 0.0020551488269120455
2023-01-24 08:10:32.863647: step: 736/531, loss: 0.0011208693031221628
2023-01-24 08:10:33.936838: step: 740/531, loss: 0.0025508366525173187
2023-01-24 08:10:35.015622: step: 744/531, loss: 0.003605595324188471
2023-01-24 08:10:36.089493: step: 748/531, loss: 0.0031855276320129633
2023-01-24 08:10:37.154953: step: 752/531, loss: 0.0013335483381524682
2023-01-24 08:10:38.210800: step: 756/531, loss: 0.004736605100333691
2023-01-24 08:10:39.282395: step: 760/531, loss: 0.002244482282549143
2023-01-24 08:10:40.340779: step: 764/531, loss: 0.006045165471732616
2023-01-24 08:10:41.397289: step: 768/531, loss: 0.0025767809711396694
2023-01-24 08:10:42.465211: step: 772/531, loss: 0.0023516854271292686
2023-01-24 08:10:43.529502: step: 776/531, loss: 0.025837058201432228
2023-01-24 08:10:44.603337: step: 780/531, loss: 0.0033677786123007536
2023-01-24 08:10:45.669752: step: 784/531, loss: 0.003299022326245904
2023-01-24 08:10:46.731174: step: 788/531, loss: 0.004824823699891567
2023-01-24 08:10:47.783650: step: 792/531, loss: 0.000424450496211648
2023-01-24 08:10:48.842052: step: 796/531, loss: 0.003976419102400541
2023-01-24 08:10:49.914452: step: 800/531, loss: 0.0009315311908721924
2023-01-24 08:10:50.964931: step: 804/531, loss: 0.001829913118854165
2023-01-24 08:10:52.036739: step: 808/531, loss: 0.0006813353975303471
2023-01-24 08:10:53.105029: step: 812/531, loss: 0.0003635450266301632
2023-01-24 08:10:54.161604: step: 816/531, loss: 0.0028247255831956863
2023-01-24 08:10:55.212422: step: 820/531, loss: 0.0003783183346968144
2023-01-24 08:10:56.278460: step: 824/531, loss: 0.02247655764222145
2023-01-24 08:10:57.329449: step: 828/531, loss: 0.006990055087953806
2023-01-24 08:10:58.382651: step: 832/531, loss: 0.003279736964032054
2023-01-24 08:10:59.451392: step: 836/531, loss: 0.00020956936350557953
2023-01-24 08:11:00.508216: step: 840/531, loss: 0.006325643975287676
2023-01-24 08:11:01.594353: step: 844/531, loss: 0.0015139882452785969
2023-01-24 08:11:02.670333: step: 848/531, loss: 0.003643469652161002
2023-01-24 08:11:03.740939: step: 852/531, loss: 0.0006772595806978643
2023-01-24 08:11:04.805826: step: 856/531, loss: 0.012736771255731583
2023-01-24 08:11:05.869165: step: 860/531, loss: 0.00013063388178125024
2023-01-24 08:11:06.937237: step: 864/531, loss: 0.016379380598664284
2023-01-24 08:11:07.999913: step: 868/531, loss: 0.0027588270604610443
2023-01-24 08:11:09.057007: step: 872/531, loss: 0.002072672825306654
2023-01-24 08:11:10.113328: step: 876/531, loss: 0.0073729208670556545
2023-01-24 08:11:11.195202: step: 880/531, loss: 0.004386465065181255
2023-01-24 08:11:12.240353: step: 884/531, loss: 0.00037287399754859507
2023-01-24 08:11:13.292411: step: 888/531, loss: 0.025077518075704575
2023-01-24 08:11:14.354273: step: 892/531, loss: 0.0010974209289997816
2023-01-24 08:11:15.407231: step: 896/531, loss: 0.00032600853592157364
2023-01-24 08:11:16.457694: step: 900/531, loss: 0.0027068040799349546
2023-01-24 08:11:17.511529: step: 904/531, loss: 0.008336818777024746
2023-01-24 08:11:18.573435: step: 908/531, loss: 0.023365305736660957
2023-01-24 08:11:19.625994: step: 912/531, loss: 0.02693640999495983
2023-01-24 08:11:20.674664: step: 916/531, loss: 0.001894272631034255
2023-01-24 08:11:21.740344: step: 920/531, loss: 0.0035084369592368603
2023-01-24 08:11:22.808581: step: 924/531, loss: 6.535274587804452e-05
2023-01-24 08:11:23.857821: step: 928/531, loss: 0.01578643172979355
2023-01-24 08:11:24.905520: step: 932/531, loss: 0.001120746717788279
2023-01-24 08:11:25.948612: step: 936/531, loss: 0.00036900717532262206
2023-01-24 08:11:27.028975: step: 940/531, loss: 0.003949716221541166
2023-01-24 08:11:28.080484: step: 944/531, loss: 0.013492215424776077
2023-01-24 08:11:29.126147: step: 948/531, loss: 0.0011108984472230077
2023-01-24 08:11:30.179185: step: 952/531, loss: 1.3997655514685903e-06
2023-01-24 08:11:31.218777: step: 956/531, loss: 0.006160073913633823
2023-01-24 08:11:32.276227: step: 960/531, loss: 0.0008319893968291581
2023-01-24 08:11:33.356497: step: 964/531, loss: 0.004093868657946587
2023-01-24 08:11:34.430287: step: 968/531, loss: 0.0016748070484027267
2023-01-24 08:11:35.487289: step: 972/531, loss: 0.014420202933251858
2023-01-24 08:11:36.553842: step: 976/531, loss: 0.044114142656326294
2023-01-24 08:11:37.613641: step: 980/531, loss: 0.002088951412588358
2023-01-24 08:11:38.668012: step: 984/531, loss: 0.0008230320527218282
2023-01-24 08:11:39.723343: step: 988/531, loss: 2.7117554054711945e-05
2023-01-24 08:11:40.795615: step: 992/531, loss: 0.005365328397601843
2023-01-24 08:11:41.891153: step: 996/531, loss: 0.00030452950159087777
2023-01-24 08:11:42.946891: step: 1000/531, loss: 0.008147473447024822
2023-01-24 08:11:44.020927: step: 1004/531, loss: 0.0017271735705435276
2023-01-24 08:11:45.087483: step: 1008/531, loss: 0.019129585474729538
2023-01-24 08:11:46.157124: step: 1012/531, loss: 0.00033819032250903547
2023-01-24 08:11:47.206576: step: 1016/531, loss: 0.0006485722842626274
2023-01-24 08:11:48.254276: step: 1020/531, loss: 0.005802926141768694
2023-01-24 08:11:49.305658: step: 1024/531, loss: 7.30617975932546e-05
2023-01-24 08:11:50.360826: step: 1028/531, loss: 0.002927525667473674
2023-01-24 08:11:51.418871: step: 1032/531, loss: 0.001537336385808885
2023-01-24 08:11:52.472048: step: 1036/531, loss: 0.003212809097021818
2023-01-24 08:11:53.519293: step: 1040/531, loss: 0.007474812678992748
2023-01-24 08:11:54.580208: step: 1044/531, loss: 0.004082385450601578
2023-01-24 08:11:55.635628: step: 1048/531, loss: 0.004068862646818161
2023-01-24 08:11:56.692967: step: 1052/531, loss: 0.002151491353288293
2023-01-24 08:11:57.755353: step: 1056/531, loss: 0.00022242763952817768
2023-01-24 08:11:58.825463: step: 1060/531, loss: 0.0005699098692275584
2023-01-24 08:11:59.883708: step: 1064/531, loss: 0.0054177348501980305
2023-01-24 08:12:00.954496: step: 1068/531, loss: 0.0013560166116803885
2023-01-24 08:12:02.004506: step: 1072/531, loss: 0.0010135923512279987
2023-01-24 08:12:03.081238: step: 1076/531, loss: 0.011238436214625835
2023-01-24 08:12:04.140173: step: 1080/531, loss: 0.009857100434601307
2023-01-24 08:12:05.191501: step: 1084/531, loss: 0.006238971371203661
2023-01-24 08:12:06.271139: step: 1088/531, loss: 0.0022449446842074394
2023-01-24 08:12:07.342615: step: 1092/531, loss: 0.004349490161985159
2023-01-24 08:12:08.408610: step: 1096/531, loss: 0.001649242709390819
2023-01-24 08:12:09.471666: step: 1100/531, loss: 0.004435345530509949
2023-01-24 08:12:10.539153: step: 1104/531, loss: 0.0015254599275067449
2023-01-24 08:12:11.597609: step: 1108/531, loss: 0.0020954047795385122
2023-01-24 08:12:12.672134: step: 1112/531, loss: 0.002117619151249528
2023-01-24 08:12:13.742534: step: 1116/531, loss: 0.007768052630126476
2023-01-24 08:12:14.807499: step: 1120/531, loss: 0.0008308215183205903
2023-01-24 08:12:15.863980: step: 1124/531, loss: 0.014101465232670307
2023-01-24 08:12:16.922581: step: 1128/531, loss: 0.000940972997341305
2023-01-24 08:12:17.976238: step: 1132/531, loss: 0.011788940988481045
2023-01-24 08:12:19.040991: step: 1136/531, loss: 0.01554956566542387
2023-01-24 08:12:20.114539: step: 1140/531, loss: 0.002533720573410392
2023-01-24 08:12:21.172470: step: 1144/531, loss: 0.0010297263506799936
2023-01-24 08:12:22.236844: step: 1148/531, loss: 0.0009417362161912024
2023-01-24 08:12:23.313753: step: 1152/531, loss: 0.0034285648725926876
2023-01-24 08:12:24.368474: step: 1156/531, loss: 0.015229434706270695
2023-01-24 08:12:25.433912: step: 1160/531, loss: 0.0016063969815149903
2023-01-24 08:12:26.492208: step: 1164/531, loss: 0.002477684523910284
2023-01-24 08:12:27.551387: step: 1168/531, loss: 0.00459054671227932
2023-01-24 08:12:28.624590: step: 1172/531, loss: 0.0009257200290448964
2023-01-24 08:12:29.690631: step: 1176/531, loss: 0.0042646173387765884
2023-01-24 08:12:30.751444: step: 1180/531, loss: 0.0031062662601470947
2023-01-24 08:12:31.830063: step: 1184/531, loss: 0.003644076641649008
2023-01-24 08:12:32.892676: step: 1188/531, loss: 0.014481316320598125
2023-01-24 08:12:33.973233: step: 1192/531, loss: 0.005696759559214115
2023-01-24 08:12:35.044375: step: 1196/531, loss: 0.018747806549072266
2023-01-24 08:12:36.117966: step: 1200/531, loss: 0.0006471088854596019
2023-01-24 08:12:37.182157: step: 1204/531, loss: 0.002548839198425412
2023-01-24 08:12:38.235366: step: 1208/531, loss: 0.002331779571250081
2023-01-24 08:12:39.302656: step: 1212/531, loss: 0.0007410774705931544
2023-01-24 08:12:40.361622: step: 1216/531, loss: 0.003397623309865594
2023-01-24 08:12:41.417112: step: 1220/531, loss: 0.004738804418593645
2023-01-24 08:12:42.478298: step: 1224/531, loss: 0.01094214990735054
2023-01-24 08:12:43.538184: step: 1228/531, loss: 0.004732155241072178
2023-01-24 08:12:44.603871: step: 1232/531, loss: 0.0016288203187286854
2023-01-24 08:12:45.648754: step: 1236/531, loss: 0.0003689306031446904
2023-01-24 08:12:46.690943: step: 1240/531, loss: 0.01876705326139927
2023-01-24 08:12:47.781357: step: 1244/531, loss: 0.0051356167532503605
2023-01-24 08:12:48.842795: step: 1248/531, loss: 0.000179226859472692
2023-01-24 08:12:49.913117: step: 1252/531, loss: 0.0016030054539442062
2023-01-24 08:12:50.963695: step: 1256/531, loss: 5.2526374361150374e-08
2023-01-24 08:12:52.016829: step: 1260/531, loss: 0.017035307362675667
2023-01-24 08:12:53.069950: step: 1264/531, loss: 0.0010174678172916174
2023-01-24 08:12:54.123084: step: 1268/531, loss: 0.005724236369132996
2023-01-24 08:12:55.180368: step: 1272/531, loss: 0.011316437274217606
2023-01-24 08:12:56.240476: step: 1276/531, loss: 6.072134510759497e-07
2023-01-24 08:12:57.287631: step: 1280/531, loss: 0.00015859492123126984
2023-01-24 08:12:58.340344: step: 1284/531, loss: 0.07415708154439926
2023-01-24 08:12:59.400428: step: 1288/531, loss: 9.049095388036221e-05
2023-01-24 08:13:00.475891: step: 1292/531, loss: 0.00020989171753171831
2023-01-24 08:13:01.545484: step: 1296/531, loss: 6.227486301213503e-05
2023-01-24 08:13:02.621074: step: 1300/531, loss: 0.009107462130486965
2023-01-24 08:13:03.708378: step: 1304/531, loss: 0.00450220936909318
2023-01-24 08:13:04.764268: step: 1308/531, loss: 0.004006167873740196
2023-01-24 08:13:05.811985: step: 1312/531, loss: 0.0016605237033218145
2023-01-24 08:13:06.867224: step: 1316/531, loss: 0.05278365686535835
2023-01-24 08:13:07.922921: step: 1320/531, loss: 0.0002809948055073619
2023-01-24 08:13:08.974868: step: 1324/531, loss: 1.4901159195446212e-09
2023-01-24 08:13:10.033932: step: 1328/531, loss: 0.026465419679880142
2023-01-24 08:13:11.083922: step: 1332/531, loss: 0.00578249990940094
2023-01-24 08:13:12.138842: step: 1336/531, loss: 0.003918411210179329
2023-01-24 08:13:13.189572: step: 1340/531, loss: 0.00020096925436519086
2023-01-24 08:13:14.265961: step: 1344/531, loss: 0.005762449465692043
2023-01-24 08:13:15.318535: step: 1348/531, loss: 5.289510227157734e-05
2023-01-24 08:13:16.402600: step: 1352/531, loss: 0.009238005615770817
2023-01-24 08:13:17.442371: step: 1356/531, loss: 0.05169999971985817
2023-01-24 08:13:18.501129: step: 1360/531, loss: 2.4488930648658425e-05
2023-01-24 08:13:19.570995: step: 1364/531, loss: 0.003602051641792059
2023-01-24 08:13:20.637329: step: 1368/531, loss: 0.009253833442926407
2023-01-24 08:13:21.697715: step: 1372/531, loss: 0.006664591375738382
2023-01-24 08:13:22.763048: step: 1376/531, loss: 0.0019129817374050617
2023-01-24 08:13:23.818803: step: 1380/531, loss: 0.005156231112778187
2023-01-24 08:13:24.868573: step: 1384/531, loss: 0.006752627901732922
2023-01-24 08:13:25.924065: step: 1388/531, loss: 0.010048375464975834
2023-01-24 08:13:26.992786: step: 1392/531, loss: 0.005329609848558903
2023-01-24 08:13:28.050855: step: 1396/531, loss: 0.0031355631072074175
2023-01-24 08:13:29.108937: step: 1400/531, loss: 0.008318467997014523
2023-01-24 08:13:30.164803: step: 1404/531, loss: 0.0032343617640435696
2023-01-24 08:13:31.207991: step: 1408/531, loss: 0.007278535980731249
2023-01-24 08:13:32.271587: step: 1412/531, loss: 0.0010737443808466196
2023-01-24 08:13:33.341779: step: 1416/531, loss: 0.007663228083401918
2023-01-24 08:13:34.397256: step: 1420/531, loss: 0.0006519157323054969
2023-01-24 08:13:35.452837: step: 1424/531, loss: 0.0005340309580788016
2023-01-24 08:13:36.517949: step: 1428/531, loss: 6.025416496413527e-06
2023-01-24 08:13:37.577199: step: 1432/531, loss: 0.012702541425824165
2023-01-24 08:13:38.645389: step: 1436/531, loss: 0.0022467621602118015
2023-01-24 08:13:39.696105: step: 1440/531, loss: 0.00802487600594759
2023-01-24 08:13:40.749614: step: 1444/531, loss: 0.002211732091382146
2023-01-24 08:13:41.823808: step: 1448/531, loss: 0.0014593214727938175
2023-01-24 08:13:42.887741: step: 1452/531, loss: 0.004380774684250355
2023-01-24 08:13:43.951429: step: 1456/531, loss: 0.011990535072982311
2023-01-24 08:13:45.010283: step: 1460/531, loss: 0.00494889821857214
2023-01-24 08:13:46.063151: step: 1464/531, loss: 0.0019130029249936342
2023-01-24 08:13:47.120023: step: 1468/531, loss: 0.0017892494797706604
2023-01-24 08:13:48.198174: step: 1472/531, loss: 0.00023916776990517974
2023-01-24 08:13:49.267419: step: 1476/531, loss: 0.006511999294161797
2023-01-24 08:13:50.317198: step: 1480/531, loss: 5.554518065764569e-05
2023-01-24 08:13:51.370762: step: 1484/531, loss: 0.0010838648304343224
2023-01-24 08:13:52.436924: step: 1488/531, loss: 0.0025906478986144066
2023-01-24 08:13:53.493438: step: 1492/531, loss: 0.005643096286803484
2023-01-24 08:13:54.566174: step: 1496/531, loss: 7.056837057461962e-05
2023-01-24 08:13:55.638055: step: 1500/531, loss: 0.005247182212769985
2023-01-24 08:13:56.679362: step: 1504/531, loss: 0.0010700220009312034
2023-01-24 08:13:57.745024: step: 1508/531, loss: 0.009434818290174007
2023-01-24 08:13:58.810705: step: 1512/531, loss: 0.008374935016036034
2023-01-24 08:13:59.878724: step: 1516/531, loss: 0.0043015568517148495
2023-01-24 08:14:00.953339: step: 1520/531, loss: 0.002789322752505541
2023-01-24 08:14:02.004562: step: 1524/531, loss: 0.009308841079473495
2023-01-24 08:14:03.077340: step: 1528/531, loss: 0.003999396227300167
2023-01-24 08:14:04.143637: step: 1532/531, loss: 0.005346197169274092
2023-01-24 08:14:05.205831: step: 1536/531, loss: 0.010844535194337368
2023-01-24 08:14:06.264450: step: 1540/531, loss: 0.0010235788067802787
2023-01-24 08:14:07.318667: step: 1544/531, loss: 0.015632014721632004
2023-01-24 08:14:08.361723: step: 1548/531, loss: 6.488789222203195e-05
2023-01-24 08:14:09.421861: step: 1552/531, loss: 0.003997104242444038
2023-01-24 08:14:10.489784: step: 1556/531, loss: 0.0002263225323986262
2023-01-24 08:14:11.527487: step: 1560/531, loss: 9.856142241915222e-06
2023-01-24 08:14:12.592724: step: 1564/531, loss: 0.004197990987449884
2023-01-24 08:14:13.649906: step: 1568/531, loss: 0.0035436716862022877
2023-01-24 08:14:14.699971: step: 1572/531, loss: 0.02010076493024826
2023-01-24 08:14:15.773648: step: 1576/531, loss: 0.0050505381077528
2023-01-24 08:14:16.825784: step: 1580/531, loss: 0.003970159683376551
2023-01-24 08:14:17.870818: step: 1584/531, loss: 3.6895977245876566e-05
2023-01-24 08:14:18.925240: step: 1588/531, loss: 0.0018596414010971785
2023-01-24 08:14:19.995333: step: 1592/531, loss: 0.0009473281679674983
2023-01-24 08:14:21.053329: step: 1596/531, loss: 0.006821515038609505
2023-01-24 08:14:22.126718: step: 1600/531, loss: 0.007906089536845684
2023-01-24 08:14:23.179739: step: 1604/531, loss: 0.0043446654453873634
2023-01-24 08:14:24.255926: step: 1608/531, loss: 0.0051284958608448505
2023-01-24 08:14:25.333596: step: 1612/531, loss: 0.0002567243645898998
2023-01-24 08:14:26.389763: step: 1616/531, loss: 0.003474753350019455
2023-01-24 08:14:27.439674: step: 1620/531, loss: 0.0014915207866579294
2023-01-24 08:14:28.493490: step: 1624/531, loss: 0.004405052401125431
2023-01-24 08:14:29.564701: step: 1628/531, loss: 0.0037583820521831512
2023-01-24 08:14:30.610837: step: 1632/531, loss: 3.7574278394458815e-05
2023-01-24 08:14:31.670285: step: 1636/531, loss: 0.0027674599550664425
2023-01-24 08:14:32.727632: step: 1640/531, loss: 0.007190498989075422
2023-01-24 08:14:33.793649: step: 1644/531, loss: 0.0006815463420934975
2023-01-24 08:14:34.853239: step: 1648/531, loss: 0.0009214354795403779
2023-01-24 08:14:35.921759: step: 1652/531, loss: 0.0030990124214440584
2023-01-24 08:14:36.974180: step: 1656/531, loss: 0.0011164223542436957
2023-01-24 08:14:38.064234: step: 1660/531, loss: 0.0017048048321157694
2023-01-24 08:14:39.118059: step: 1664/531, loss: 0.0002919072285294533
2023-01-24 08:14:40.177075: step: 1668/531, loss: 0.0024997543077915907
2023-01-24 08:14:41.261190: step: 1672/531, loss: 0.00972164049744606
2023-01-24 08:14:42.360485: step: 1676/531, loss: 0.0343078188598156
2023-01-24 08:14:43.429871: step: 1680/531, loss: 0.0010097825434058905
2023-01-24 08:14:44.485863: step: 1684/531, loss: 0.00311590195633471
2023-01-24 08:14:45.535686: step: 1688/531, loss: 0.0029082675464451313
2023-01-24 08:14:46.594761: step: 1692/531, loss: 0.008551392704248428
2023-01-24 08:14:47.664513: step: 1696/531, loss: 0.0001803740597097203
2023-01-24 08:14:48.737259: step: 1700/531, loss: 0.009989561513066292
2023-01-24 08:14:49.793458: step: 1704/531, loss: 0.002462916076183319
2023-01-24 08:14:50.857371: step: 1708/531, loss: 0.0035486482083797455
2023-01-24 08:14:51.920489: step: 1712/531, loss: 0.001967664808034897
2023-01-24 08:14:52.975283: step: 1716/531, loss: 0.002778839087113738
2023-01-24 08:14:54.032669: step: 1720/531, loss: 0.001200348138809204
2023-01-24 08:14:55.091592: step: 1724/531, loss: 0.0009527311194688082
2023-01-24 08:14:56.132896: step: 1728/531, loss: 0.0022733428049832582
2023-01-24 08:14:57.207308: step: 1732/531, loss: 0.004268552642315626
2023-01-24 08:14:58.263663: step: 1736/531, loss: 0.0017586820758879185
2023-01-24 08:14:59.318142: step: 1740/531, loss: 0.0017639162251725793
2023-01-24 08:15:00.390232: step: 1744/531, loss: 0.007432482670992613
2023-01-24 08:15:01.478839: step: 1748/531, loss: 0.0008550300844945014
2023-01-24 08:15:02.577024: step: 1752/531, loss: 0.00046894658589735627
2023-01-24 08:15:03.627616: step: 1756/531, loss: 0.0005495856166817248
2023-01-24 08:15:04.682433: step: 1760/531, loss: 0.00046782713616266847
2023-01-24 08:15:05.746703: step: 1764/531, loss: 0.0016932528233155608
2023-01-24 08:15:06.801804: step: 1768/531, loss: 0.002158620161935687
2023-01-24 08:15:07.850949: step: 1772/531, loss: 4.678270488511771e-05
2023-01-24 08:15:08.908606: step: 1776/531, loss: 0.005452624522149563
2023-01-24 08:15:09.969137: step: 1780/531, loss: 0.0002606469497550279
2023-01-24 08:15:11.049620: step: 1784/531, loss: 0.006427340675145388
2023-01-24 08:15:12.105108: step: 1788/531, loss: 0.00634990306571126
2023-01-24 08:15:13.177464: step: 1792/531, loss: 0.003668583231046796
2023-01-24 08:15:14.226426: step: 1796/531, loss: 0.0021028018090873957
2023-01-24 08:15:15.289928: step: 1800/531, loss: 0.002138777868822217
2023-01-24 08:15:16.344992: step: 1804/531, loss: 0.0001514388422947377
2023-01-24 08:15:17.407693: step: 1808/531, loss: 0.00022652155894320458
2023-01-24 08:15:18.449662: step: 1812/531, loss: 0.0002831830643117428
2023-01-24 08:15:19.504864: step: 1816/531, loss: 9.081160533241928e-05
2023-01-24 08:15:20.560150: step: 1820/531, loss: 0.0007973187603056431
2023-01-24 08:15:21.637619: step: 1824/531, loss: 0.00013473823491949588
2023-01-24 08:15:22.700121: step: 1828/531, loss: 0.0061875288374722
2023-01-24 08:15:23.771314: step: 1832/531, loss: 0.004659847356379032
2023-01-24 08:15:24.821156: step: 1836/531, loss: 0.00021924739121459424
2023-01-24 08:15:25.882487: step: 1840/531, loss: 0.0023256917484104633
2023-01-24 08:15:26.942923: step: 1844/531, loss: 0.006041111424565315
2023-01-24 08:15:27.997772: step: 1848/531, loss: 2.155197216779925e-05
2023-01-24 08:15:29.050642: step: 1852/531, loss: 0.0015061178710311651
2023-01-24 08:15:30.109118: step: 1856/531, loss: 0.003322010859847069
2023-01-24 08:15:31.179143: step: 1860/531, loss: 0.006429298315197229
2023-01-24 08:15:32.234916: step: 1864/531, loss: 0.001559158437885344
2023-01-24 08:15:33.292825: step: 1868/531, loss: 0.010159683413803577
2023-01-24 08:15:34.359725: step: 1872/531, loss: 0.004556985571980476
2023-01-24 08:15:35.409415: step: 1876/531, loss: 0.003635360626503825
2023-01-24 08:15:36.477637: step: 1880/531, loss: 0.004577002488076687
2023-01-24 08:15:37.534155: step: 1884/531, loss: 0.002632185583934188
2023-01-24 08:15:38.583608: step: 1888/531, loss: 0.010948077775537968
2023-01-24 08:15:39.654956: step: 1892/531, loss: 0.0030329760629683733
2023-01-24 08:15:40.709755: step: 1896/531, loss: 0.0044677406549453735
2023-01-24 08:15:41.774843: step: 1900/531, loss: 0.000990628032013774
2023-01-24 08:15:42.847935: step: 1904/531, loss: 0.0005836610216647387
2023-01-24 08:15:43.909618: step: 1908/531, loss: 0.0011377936461940408
2023-01-24 08:15:44.974271: step: 1912/531, loss: 0.00619694497436285
2023-01-24 08:15:46.031517: step: 1916/531, loss: 0.003997748252004385
2023-01-24 08:15:47.101382: step: 1920/531, loss: 0.003310997737571597
2023-01-24 08:15:48.167981: step: 1924/531, loss: 0.007806388661265373
2023-01-24 08:15:49.222867: step: 1928/531, loss: 4.578873631544411e-05
2023-01-24 08:15:50.286344: step: 1932/531, loss: 0.006815907079726458
2023-01-24 08:15:51.339686: step: 1936/531, loss: 4.5634459411303396e-07
2023-01-24 08:15:52.389209: step: 1940/531, loss: 0.001159795792773366
2023-01-24 08:15:53.450326: step: 1944/531, loss: 0.0026013364549726248
2023-01-24 08:15:54.519995: step: 1948/531, loss: 0.0038500570226460695
2023-01-24 08:15:55.613841: step: 1952/531, loss: 0.008455782197415829
2023-01-24 08:15:56.666141: step: 1956/531, loss: 0.0002958730619866401
2023-01-24 08:15:57.730867: step: 1960/531, loss: 0.005648695398122072
2023-01-24 08:15:58.796074: step: 1964/531, loss: 0.006919756531715393
2023-01-24 08:15:59.848761: step: 1968/531, loss: 0.0026051849126815796
2023-01-24 08:16:00.896833: step: 1972/531, loss: 0.0015414806548506021
2023-01-24 08:16:01.949627: step: 1976/531, loss: 0.005913617089390755
2023-01-24 08:16:03.037019: step: 1980/531, loss: 0.004916145000606775
2023-01-24 08:16:04.093132: step: 1984/531, loss: 0.0015078928554430604
2023-01-24 08:16:05.166971: step: 1988/531, loss: 0.0071089365519583225
2023-01-24 08:16:06.221110: step: 1992/531, loss: 0.008130467496812344
2023-01-24 08:16:07.278616: step: 1996/531, loss: 0.0010581787209957838
2023-01-24 08:16:08.347371: step: 2000/531, loss: 0.001217597397044301
2023-01-24 08:16:09.416643: step: 2004/531, loss: 0.0007773605175316334
2023-01-24 08:16:10.503280: step: 2008/531, loss: 0.0024157122243195772
2023-01-24 08:16:11.574550: step: 2012/531, loss: 0.004002046305686235
2023-01-24 08:16:12.632225: step: 2016/531, loss: 0.005973339080810547
2023-01-24 08:16:13.697040: step: 2020/531, loss: 0.0012962199980393052
2023-01-24 08:16:14.765712: step: 2024/531, loss: 0.00107801822014153
2023-01-24 08:16:15.834771: step: 2028/531, loss: 0.0035686420742422342
2023-01-24 08:16:16.910673: step: 2032/531, loss: 0.005178095772862434
2023-01-24 08:16:17.969114: step: 2036/531, loss: 0.004839688073843718
2023-01-24 08:16:19.037664: step: 2040/531, loss: 0.003223894629627466
2023-01-24 08:16:20.096363: step: 2044/531, loss: 0.0009847404435276985
2023-01-24 08:16:21.175521: step: 2048/531, loss: 0.003674639854580164
2023-01-24 08:16:22.255560: step: 2052/531, loss: 0.0009432816877961159
2023-01-24 08:16:23.312760: step: 2056/531, loss: 0.004605493508279324
2023-01-24 08:16:24.378373: step: 2060/531, loss: 0.003991587553173304
2023-01-24 08:16:25.449604: step: 2064/531, loss: 0.0018774409545585513
2023-01-24 08:16:26.512113: step: 2068/531, loss: 0.00480128126218915
2023-01-24 08:16:27.560923: step: 2072/531, loss: 0.024160893633961678
2023-01-24 08:16:28.632486: step: 2076/531, loss: 0.00102907489053905
2023-01-24 08:16:29.686380: step: 2080/531, loss: 0.00034973936271853745
2023-01-24 08:16:30.744637: step: 2084/531, loss: 0.006875805556774139
2023-01-24 08:16:31.806992: step: 2088/531, loss: 0.0020749513059854507
2023-01-24 08:16:32.865418: step: 2092/531, loss: 0.0017216912237927318
2023-01-24 08:16:33.934749: step: 2096/531, loss: 0.002929131733253598
2023-01-24 08:16:35.003937: step: 2100/531, loss: 0.016796234995126724
2023-01-24 08:16:36.054422: step: 2104/531, loss: 0.0022440662141889334
2023-01-24 08:16:37.121539: step: 2108/531, loss: 0.0030159587040543556
2023-01-24 08:16:38.180234: step: 2112/531, loss: 0.0002595247933641076
2023-01-24 08:16:39.240422: step: 2116/531, loss: 0.005056208930909634
2023-01-24 08:16:40.307818: step: 2120/531, loss: 0.011324580758810043
2023-01-24 08:16:41.365255: step: 2124/531, loss: 0.00010594310879241675
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.38979992427441806, 'r': 0.3187927274426455, 'f1': 0.35073855399222165}, 'combined': 0.25843893452058436, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38620561713683077, 'r': 0.2737219252205131, 'f1': 0.3203774301525583}, 'combined': 0.20061016654412533, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3780164324072552, 'r': 0.3399995995465635, 'f1': 0.3580015763457322}, 'combined': 0.26379063520211843, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.38996520744853863, 'r': 0.2872872628362994, 'f1': 0.33084275647503225}, 'combined': 0.20502931387185094, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36576129623646925, 'r': 0.32828290914582536, 'f1': 0.3460101862396999}, 'combined': 0.2549548740713578, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41153294761877335, 'r': 0.28536414492230544, 'f1': 0.33702751514253115}, 'combined': 0.22357270806484741, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 14}
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, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 15
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:19:05.675486: step: 4/531, loss: 0.0009297167416661978
2023-01-24 08:19:06.735077: step: 8/531, loss: 0.004007861949503422
2023-01-24 08:19:07.789321: step: 12/531, loss: 0.004778177477419376
2023-01-24 08:19:08.849113: step: 16/531, loss: 0.002197671914473176
2023-01-24 08:19:09.921681: step: 20/531, loss: 0.004840637091547251
2023-01-24 08:19:10.971708: step: 24/531, loss: 0.002825033850967884
2023-01-24 08:19:12.029502: step: 28/531, loss: 0.006522003095597029
2023-01-24 08:19:13.085912: step: 32/531, loss: 0.0005030282191000879
2023-01-24 08:19:14.132383: step: 36/531, loss: 3.879536234308034e-05
2023-01-24 08:19:15.181478: step: 40/531, loss: 0.0027950697112828493
2023-01-24 08:19:16.240122: step: 44/531, loss: 0.000885081070009619
2023-01-24 08:19:17.288632: step: 48/531, loss: 0.0019474371802061796
2023-01-24 08:19:18.337678: step: 52/531, loss: 0.0018467579502612352
2023-01-24 08:19:19.386084: step: 56/531, loss: 0.0018239349592477083
2023-01-24 08:19:20.434913: step: 60/531, loss: 0.0021507146302610636
2023-01-24 08:19:21.498546: step: 64/531, loss: 0.002219590824097395
2023-01-24 08:19:22.557750: step: 68/531, loss: 0.008323084563016891
2023-01-24 08:19:23.628957: step: 72/531, loss: 0.0005446018767543137
2023-01-24 08:19:24.668988: step: 76/531, loss: 0.0010872746352106333
2023-01-24 08:19:25.716939: step: 80/531, loss: 0.0016193060437217355
2023-01-24 08:19:26.771005: step: 84/531, loss: 8.282660564873368e-05
2023-01-24 08:19:27.811768: step: 88/531, loss: 0.0004665288724936545
2023-01-24 08:19:28.882190: step: 92/531, loss: 0.0012503565521910787
2023-01-24 08:19:29.928242: step: 96/531, loss: 0.000962749938480556
2023-01-24 08:19:30.979407: step: 100/531, loss: 0.0021599980536848307
2023-01-24 08:19:32.049472: step: 104/531, loss: 0.003258185926824808
2023-01-24 08:19:33.101683: step: 108/531, loss: 0.0023698259610682726
2023-01-24 08:19:34.159686: step: 112/531, loss: 0.0032050651498138905
2023-01-24 08:19:35.208005: step: 116/531, loss: 0.00022550602443516254
2023-01-24 08:19:36.274244: step: 120/531, loss: 0.007348128594458103
2023-01-24 08:19:37.345794: step: 124/531, loss: 0.005411579739302397
2023-01-24 08:19:38.398818: step: 128/531, loss: 9.814813529374078e-05
2023-01-24 08:19:39.450875: step: 132/531, loss: 0.005580283235758543
2023-01-24 08:19:40.510252: step: 136/531, loss: 0.004964708350598812
2023-01-24 08:19:41.555881: step: 140/531, loss: 0.0017173548694700003
2023-01-24 08:19:42.625989: step: 144/531, loss: 0.0005969404010102153
2023-01-24 08:19:43.681955: step: 148/531, loss: 0.000544672948308289
2023-01-24 08:19:44.729919: step: 152/531, loss: 6.936961290193722e-05
2023-01-24 08:19:45.790563: step: 156/531, loss: 0.0046898918226361275
2023-01-24 08:19:46.849512: step: 160/531, loss: 0.0001894142769742757
2023-01-24 08:19:47.897243: step: 164/531, loss: 0.0027475047390908003
2023-01-24 08:19:48.957429: step: 168/531, loss: 0.000921240309253335
2023-01-24 08:19:50.008271: step: 172/531, loss: 0.00041818353929556906
2023-01-24 08:19:51.079201: step: 176/531, loss: 0.003889592830091715
2023-01-24 08:19:52.127320: step: 180/531, loss: 0.0002383182873018086
2023-01-24 08:19:53.190083: step: 184/531, loss: 0.0033205451909452677
2023-01-24 08:19:54.259274: step: 188/531, loss: 0.002614720957353711
2023-01-24 08:19:55.324869: step: 192/531, loss: 0.0038635912351310253
2023-01-24 08:19:56.389773: step: 196/531, loss: 0.006494181230664253
2023-01-24 08:19:57.458267: step: 200/531, loss: 0.00048694873112253845
2023-01-24 08:19:58.528103: step: 204/531, loss: 0.010614367201924324
2023-01-24 08:19:59.581040: step: 208/531, loss: 0.010754323564469814
2023-01-24 08:20:00.642443: step: 212/531, loss: 0.0004258018161635846
2023-01-24 08:20:01.694037: step: 216/531, loss: 0.0008007609867490828
2023-01-24 08:20:02.752740: step: 220/531, loss: 0.0032074851915240288
2023-01-24 08:20:03.812750: step: 224/531, loss: 0.0036868557799607515
2023-01-24 08:20:04.869965: step: 228/531, loss: 0.0023249229416251183
2023-01-24 08:20:05.922318: step: 232/531, loss: 0.00012762272672262043
2023-01-24 08:20:06.980107: step: 236/531, loss: 0.00022608712606597692
2023-01-24 08:20:08.045691: step: 240/531, loss: 0.00021699524950236082
2023-01-24 08:20:09.120919: step: 244/531, loss: 9.294210758525878e-05
2023-01-24 08:20:10.175664: step: 248/531, loss: 0.004078640136867762
2023-01-24 08:20:11.231794: step: 252/531, loss: 0.0005958827678114176
2023-01-24 08:20:12.301138: step: 256/531, loss: 0.0031321807764470577
2023-01-24 08:20:13.366184: step: 260/531, loss: 0.0004113212926313281
2023-01-24 08:20:14.404916: step: 264/531, loss: 0.004436914809048176
2023-01-24 08:20:15.463137: step: 268/531, loss: 0.0007022920181043446
2023-01-24 08:20:16.516886: step: 272/531, loss: 0.0003805515298154205
2023-01-24 08:20:17.581958: step: 276/531, loss: 0.0008302227943204343
2023-01-24 08:20:18.646579: step: 280/531, loss: 0.0009930954547598958
2023-01-24 08:20:19.707771: step: 284/531, loss: 0.0004300784203223884
2023-01-24 08:20:20.784089: step: 288/531, loss: 1.254850303666899e-05
2023-01-24 08:20:21.837479: step: 292/531, loss: 0.00011757396714529023
2023-01-24 08:20:22.903767: step: 296/531, loss: 0.0046015409752726555
2023-01-24 08:20:23.960655: step: 300/531, loss: 0.000182485266122967
2023-01-24 08:20:25.026117: step: 304/531, loss: 0.002524326788261533
2023-01-24 08:20:26.075856: step: 308/531, loss: 0.0001551653112983331
2023-01-24 08:20:27.121677: step: 312/531, loss: 0.0005007855361327529
2023-01-24 08:20:28.189028: step: 316/531, loss: 0.001926211640238762
2023-01-24 08:20:29.241419: step: 320/531, loss: 0.0016906842356547713
2023-01-24 08:20:30.302422: step: 324/531, loss: 0.002724287798628211
2023-01-24 08:20:31.354660: step: 328/531, loss: 0.002014667959883809
2023-01-24 08:20:32.439638: step: 332/531, loss: 0.00012962426990270615
2023-01-24 08:20:33.491562: step: 336/531, loss: 0.001721011707559228
2023-01-24 08:20:34.558919: step: 340/531, loss: 0.002679077908396721
2023-01-24 08:20:35.614199: step: 344/531, loss: 0.002680771518498659
2023-01-24 08:20:36.673898: step: 348/531, loss: 0.0009493392426520586
2023-01-24 08:20:37.729559: step: 352/531, loss: 0.002221663948148489
2023-01-24 08:20:38.799937: step: 356/531, loss: 0.000615772558376193
2023-01-24 08:20:39.852168: step: 360/531, loss: 0.0007418880704790354
2023-01-24 08:20:40.906788: step: 364/531, loss: 1.619071190361865e-05
2023-01-24 08:20:41.948209: step: 368/531, loss: 0.000788150995504111
2023-01-24 08:20:43.008234: step: 372/531, loss: 0.0005295132868923247
2023-01-24 08:20:44.073627: step: 376/531, loss: 0.0009582198108546436
2023-01-24 08:20:45.142500: step: 380/531, loss: 0.0006560353212989867
2023-01-24 08:20:46.203214: step: 384/531, loss: 0.002854851307347417
2023-01-24 08:20:47.275997: step: 388/531, loss: 0.0036674593575298786
2023-01-24 08:20:48.345774: step: 392/531, loss: 1.1197299500054214e-05
2023-01-24 08:20:49.405770: step: 396/531, loss: 0.0025105879176408052
2023-01-24 08:20:50.465063: step: 400/531, loss: 0.0021822794806212187
2023-01-24 08:20:51.537926: step: 404/531, loss: 0.0012240527430549264
2023-01-24 08:20:52.596979: step: 408/531, loss: 0.00037952701677568257
2023-01-24 08:20:53.661879: step: 412/531, loss: 0.0005294446018524468
2023-01-24 08:20:54.716334: step: 416/531, loss: 0.00405338266864419
2023-01-24 08:20:55.781945: step: 420/531, loss: 0.00394094455987215
2023-01-24 08:20:56.869026: step: 424/531, loss: 0.01870819739997387
2023-01-24 08:20:57.924803: step: 428/531, loss: 0.004751021973788738
2023-01-24 08:20:58.990085: step: 432/531, loss: 0.0018602223135530949
2023-01-24 08:21:00.051013: step: 436/531, loss: 0.0002575826656538993
2023-01-24 08:21:01.122461: step: 440/531, loss: 0.005963757634162903
2023-01-24 08:21:02.175651: step: 444/531, loss: 0.021844692528247833
2023-01-24 08:21:03.245583: step: 448/531, loss: 0.01680346205830574
2023-01-24 08:21:04.306620: step: 452/531, loss: 0.0038715405389666557
2023-01-24 08:21:05.367403: step: 456/531, loss: 0.004481372889131308
2023-01-24 08:21:06.423603: step: 460/531, loss: 9.810111805563793e-06
2023-01-24 08:21:07.490543: step: 464/531, loss: 0.0007966441917233169
2023-01-24 08:21:08.562058: step: 468/531, loss: 0.013006845489144325
2023-01-24 08:21:09.617225: step: 472/531, loss: 0.0003879364812746644
2023-01-24 08:21:10.664311: step: 476/531, loss: 3.171792923239991e-05
2023-01-24 08:21:11.723945: step: 480/531, loss: 0.0013922168873250484
2023-01-24 08:21:12.781104: step: 484/531, loss: 0.0011973888613283634
2023-01-24 08:21:13.845293: step: 488/531, loss: 0.002654570620507002
2023-01-24 08:21:14.903873: step: 492/531, loss: 0.0008288152748718858
2023-01-24 08:21:15.961964: step: 496/531, loss: 0.0024223164655268192
2023-01-24 08:21:17.024461: step: 500/531, loss: 0.0008029621676541865
2023-01-24 08:21:18.081087: step: 504/531, loss: 0.0003220121143385768
2023-01-24 08:21:19.144339: step: 508/531, loss: 0.0008974025840871036
2023-01-24 08:21:20.220317: step: 512/531, loss: 0.014584644697606564
2023-01-24 08:21:21.281119: step: 516/531, loss: 0.0003352530184201896
2023-01-24 08:21:22.360982: step: 520/531, loss: 0.00376947782933712
2023-01-24 08:21:23.427805: step: 524/531, loss: 8.404223626712337e-05
2023-01-24 08:21:24.483165: step: 528/531, loss: 0.004354581236839294
2023-01-24 08:21:25.566261: step: 532/531, loss: 0.005631724372506142
2023-01-24 08:21:26.630498: step: 536/531, loss: 0.007826856337487698
2023-01-24 08:21:27.685965: step: 540/531, loss: 8.72770615387708e-05
2023-01-24 08:21:28.744047: step: 544/531, loss: 0.00010538606147747487
2023-01-24 08:21:29.819876: step: 548/531, loss: 0.0004370012029539794
2023-01-24 08:21:30.904715: step: 552/531, loss: 0.004729630891233683
2023-01-24 08:21:31.964696: step: 556/531, loss: 0.00027069816133007407
2023-01-24 08:21:33.017366: step: 560/531, loss: 0.003029781859368086
2023-01-24 08:21:34.092631: step: 564/531, loss: 0.009513920173048973
2023-01-24 08:21:35.172952: step: 568/531, loss: 0.003292496083304286
2023-01-24 08:21:36.221872: step: 572/531, loss: 0.0024838829413056374
2023-01-24 08:21:37.291931: step: 576/531, loss: 0.002788601443171501
2023-01-24 08:21:38.358648: step: 580/531, loss: 0.002021592576056719
2023-01-24 08:21:39.425897: step: 584/531, loss: 0.0010590646415948868
2023-01-24 08:21:40.484492: step: 588/531, loss: 0.0007489988929592073
2023-01-24 08:21:41.561953: step: 592/531, loss: 0.00048802714445628226
2023-01-24 08:21:42.636419: step: 596/531, loss: 0.005037723574787378
2023-01-24 08:21:43.720772: step: 600/531, loss: 0.00013229298929218203
2023-01-24 08:21:44.765764: step: 604/531, loss: 0.019517280161380768
2023-01-24 08:21:45.846914: step: 608/531, loss: 5.1459428505040705e-05
2023-01-24 08:21:46.906170: step: 612/531, loss: 0.004906481597572565
2023-01-24 08:21:47.978084: step: 616/531, loss: 0.002516153734177351
2023-01-24 08:21:49.034713: step: 620/531, loss: 0.0012465064646676183
2023-01-24 08:21:50.110730: step: 624/531, loss: 0.001101003959774971
2023-01-24 08:21:51.174227: step: 628/531, loss: 2.837063766492065e-05
2023-01-24 08:21:52.235800: step: 632/531, loss: 0.0006293684127740562
2023-01-24 08:21:53.312295: step: 636/531, loss: 0.012196602299809456
2023-01-24 08:21:54.371893: step: 640/531, loss: 2.4855626179487444e-05
2023-01-24 08:21:55.426452: step: 644/531, loss: 0.000763328280299902
2023-01-24 08:21:56.513322: step: 648/531, loss: 0.00030824964051134884
2023-01-24 08:21:57.570114: step: 652/531, loss: 0.0005002337857149541
2023-01-24 08:21:58.628042: step: 656/531, loss: 0.00023411422444041818
2023-01-24 08:21:59.690206: step: 660/531, loss: 0.0048622870817780495
2023-01-24 08:22:00.752923: step: 664/531, loss: 0.0003881608135998249
2023-01-24 08:22:01.825630: step: 668/531, loss: 0.00048383790999650955
2023-01-24 08:22:02.876288: step: 672/531, loss: 0.0025997376069426537
2023-01-24 08:22:03.942425: step: 676/531, loss: 5.2105431677773595e-05
2023-01-24 08:22:05.000898: step: 680/531, loss: 0.030486680567264557
2023-01-24 08:22:06.058210: step: 684/531, loss: 8.691824041306973e-05
2023-01-24 08:22:07.108603: step: 688/531, loss: 0.0
2023-01-24 08:22:08.164186: step: 692/531, loss: 0.001845174003392458
2023-01-24 08:22:09.223586: step: 696/531, loss: 0.002244679955765605
2023-01-24 08:22:10.287290: step: 700/531, loss: 0.0006919368170201778
2023-01-24 08:22:11.342838: step: 704/531, loss: 0.0034909069072455168
2023-01-24 08:22:12.429510: step: 708/531, loss: 0.001032219617627561
2023-01-24 08:22:13.490462: step: 712/531, loss: 0.00033255619928240776
2023-01-24 08:22:14.554368: step: 716/531, loss: 0.004948308225721121
2023-01-24 08:22:15.605135: step: 720/531, loss: 0.0004958026693202555
2023-01-24 08:22:16.679032: step: 724/531, loss: 0.0008576534455642104
2023-01-24 08:22:17.719641: step: 728/531, loss: 0.0032093883492052555
2023-01-24 08:22:18.787153: step: 732/531, loss: 0.008547630161046982
2023-01-24 08:22:19.843029: step: 736/531, loss: 0.007780618034303188
2023-01-24 08:22:20.886139: step: 740/531, loss: 0.000961107958573848
2023-01-24 08:22:21.969919: step: 744/531, loss: 0.004089743364602327
2023-01-24 08:22:23.030979: step: 748/531, loss: 2.2777938283979893e-05
2023-01-24 08:22:24.085679: step: 752/531, loss: 0.001483023981563747
2023-01-24 08:22:25.141309: step: 756/531, loss: 0.0013040174962952733
2023-01-24 08:22:26.216535: step: 760/531, loss: 0.0026340496260672808
2023-01-24 08:22:27.292595: step: 764/531, loss: 0.0024289642460644245
2023-01-24 08:22:28.344889: step: 768/531, loss: 0.00034977204632014036
2023-01-24 08:22:29.404707: step: 772/531, loss: 0.013295880518853664
2023-01-24 08:22:30.481821: step: 776/531, loss: 0.004345230292528868
2023-01-24 08:22:31.533038: step: 780/531, loss: 0.0022396044805645943
2023-01-24 08:22:32.605004: step: 784/531, loss: 3.582090585041442e-06
2023-01-24 08:22:33.655674: step: 788/531, loss: 0.005299786105751991
2023-01-24 08:22:34.743963: step: 792/531, loss: 0.0018520280718803406
2023-01-24 08:22:35.805442: step: 796/531, loss: 0.004250641446560621
2023-01-24 08:22:36.863625: step: 800/531, loss: 0.0013073586160317063
2023-01-24 08:22:37.939840: step: 804/531, loss: 0.0007779623265378177
2023-01-24 08:22:38.998860: step: 808/531, loss: 0.0021871502976864576
2023-01-24 08:22:40.059890: step: 812/531, loss: 3.1937543099047616e-05
2023-01-24 08:22:41.109778: step: 816/531, loss: 0.004651687573641539
2023-01-24 08:22:42.192798: step: 820/531, loss: 0.002168322214856744
2023-01-24 08:22:43.256426: step: 824/531, loss: 0.009237860329449177
2023-01-24 08:22:44.316282: step: 828/531, loss: 0.0015819964464753866
2023-01-24 08:22:45.382827: step: 832/531, loss: 0.00013506108371075243
2023-01-24 08:22:46.443821: step: 836/531, loss: 0.008326171897351742
2023-01-24 08:22:47.500887: step: 840/531, loss: 6.934761768206954e-05
2023-01-24 08:22:48.547483: step: 844/531, loss: 0.00123911676928401
2023-01-24 08:22:49.617320: step: 848/531, loss: 0.0034209522418677807
2023-01-24 08:22:50.672381: step: 852/531, loss: 0.009107130579650402
2023-01-24 08:22:51.740546: step: 856/531, loss: 0.00020019787189085037
2023-01-24 08:22:52.816564: step: 860/531, loss: 0.0019052329007536173
2023-01-24 08:22:53.873701: step: 864/531, loss: 0.0017082573613151908
2023-01-24 08:22:54.911894: step: 868/531, loss: 0.0
2023-01-24 08:22:55.985317: step: 872/531, loss: 0.004345685709267855
2023-01-24 08:22:57.048463: step: 876/531, loss: 3.483918044366874e-05
2023-01-24 08:22:58.110652: step: 880/531, loss: 0.002432444831356406
2023-01-24 08:22:59.160324: step: 884/531, loss: 0.0001277826086152345
2023-01-24 08:23:00.231888: step: 888/531, loss: 0.00638930406421423
2023-01-24 08:23:01.296495: step: 892/531, loss: 0.002860849956050515
2023-01-24 08:23:02.354041: step: 896/531, loss: 0.00019754651293624192
2023-01-24 08:23:03.421439: step: 900/531, loss: 0.0030481130816042423
2023-01-24 08:23:04.485878: step: 904/531, loss: 0.004139148164540529
2023-01-24 08:23:05.534140: step: 908/531, loss: 0.002282257191836834
2023-01-24 08:23:06.588612: step: 912/531, loss: 0.0007151679019443691
2023-01-24 08:23:07.665602: step: 916/531, loss: 0.0011508659226819873
2023-01-24 08:23:08.726117: step: 920/531, loss: 0.004929671995341778
2023-01-24 08:23:09.799465: step: 924/531, loss: 0.0008378620259463787
2023-01-24 08:23:10.846350: step: 928/531, loss: 0.0016921816859394312
2023-01-24 08:23:11.901987: step: 932/531, loss: 0.002038485137745738
2023-01-24 08:23:12.957330: step: 936/531, loss: 0.0005120376590639353
2023-01-24 08:23:14.007093: step: 940/531, loss: 0.0001441959320800379
2023-01-24 08:23:15.077342: step: 944/531, loss: 0.0030919346027076244
2023-01-24 08:23:16.141907: step: 948/531, loss: 0.00015885457105468959
2023-01-24 08:23:17.204872: step: 952/531, loss: 0.005923484917730093
2023-01-24 08:23:18.265269: step: 956/531, loss: 0.0008517189417034388
2023-01-24 08:23:19.349895: step: 960/531, loss: 0.00018739393271971494
2023-01-24 08:23:20.413227: step: 964/531, loss: 0.0008119182311929762
2023-01-24 08:23:21.466962: step: 968/531, loss: 1.7786125681595877e-05
2023-01-24 08:23:22.524703: step: 972/531, loss: 0.00018600131443236023
2023-01-24 08:23:23.568679: step: 976/531, loss: 0.0020022897515445948
2023-01-24 08:23:24.632827: step: 980/531, loss: 0.0031820288859307766
2023-01-24 08:23:25.694377: step: 984/531, loss: 0.004812317434698343
2023-01-24 08:23:26.758644: step: 988/531, loss: 3.905444827978499e-05
2023-01-24 08:23:27.816716: step: 992/531, loss: 0.00034579497878439724
2023-01-24 08:23:28.868589: step: 996/531, loss: 0.000839526648633182
2023-01-24 08:23:29.930857: step: 1000/531, loss: 0.0013043514918535948
2023-01-24 08:23:30.992307: step: 1004/531, loss: 0.00033112673554569483
2023-01-24 08:23:32.076059: step: 1008/531, loss: 0.007101436611264944
2023-01-24 08:23:33.141579: step: 1012/531, loss: 0.0014476361684501171
2023-01-24 08:23:34.201870: step: 1016/531, loss: 0.0008238592999987304
2023-01-24 08:23:35.285402: step: 1020/531, loss: 0.005778813734650612
2023-01-24 08:23:36.353868: step: 1024/531, loss: 0.00389322848059237
2023-01-24 08:23:37.412446: step: 1028/531, loss: 6.392520299414173e-05
2023-01-24 08:23:38.487024: step: 1032/531, loss: 0.0004985540872439742
2023-01-24 08:23:39.541183: step: 1036/531, loss: 0.001746293157339096
2023-01-24 08:23:40.600297: step: 1040/531, loss: 0.024079257622361183
2023-01-24 08:23:41.646269: step: 1044/531, loss: 1.2902031812700443e-05
2023-01-24 08:23:42.711003: step: 1048/531, loss: 6.419776764232665e-05
2023-01-24 08:23:43.783555: step: 1052/531, loss: 0.0012342811096459627
2023-01-24 08:23:44.861947: step: 1056/531, loss: 0.0042419228702783585
2023-01-24 08:23:45.911791: step: 1060/531, loss: 0.0031465382780879736
2023-01-24 08:23:46.970583: step: 1064/531, loss: 4.572844773065299e-05
2023-01-24 08:23:48.042496: step: 1068/531, loss: 0.006197073496878147
2023-01-24 08:23:49.087999: step: 1072/531, loss: 0.005649218335747719
2023-01-24 08:23:50.153925: step: 1076/531, loss: 0.0013822930632159114
2023-01-24 08:23:51.203461: step: 1080/531, loss: 0.001131804776377976
2023-01-24 08:23:52.273496: step: 1084/531, loss: 0.0023004761897027493
2023-01-24 08:23:53.328110: step: 1088/531, loss: 0.006593323778361082
2023-01-24 08:23:54.383530: step: 1092/531, loss: 0.0007122933166101575
2023-01-24 08:23:55.451212: step: 1096/531, loss: 0.00011971169442404062
2023-01-24 08:23:56.498192: step: 1100/531, loss: 0.01289062574505806
2023-01-24 08:23:57.545416: step: 1104/531, loss: 0.004245121031999588
2023-01-24 08:23:58.604365: step: 1108/531, loss: 0.0026767197996377945
2023-01-24 08:23:59.654237: step: 1112/531, loss: 0.002532575512304902
2023-01-24 08:24:00.727534: step: 1116/531, loss: 0.0016375520499423146
2023-01-24 08:24:01.797416: step: 1120/531, loss: 0.0037415369879454374
2023-01-24 08:24:02.850103: step: 1124/531, loss: 0.0019043168285861611
2023-01-24 08:24:03.910420: step: 1128/531, loss: 0.0016788356006145477
2023-01-24 08:24:04.972272: step: 1132/531, loss: 0.002324876841157675
2023-01-24 08:24:06.025870: step: 1136/531, loss: 0.0012641472276300192
2023-01-24 08:24:07.086829: step: 1140/531, loss: 0.0009165317169390619
2023-01-24 08:24:08.141863: step: 1144/531, loss: 0.0005250711692497134
2023-01-24 08:24:09.202664: step: 1148/531, loss: 0.0003882689052261412
2023-01-24 08:24:10.254869: step: 1152/531, loss: 3.588005347410217e-05
2023-01-24 08:24:11.319236: step: 1156/531, loss: 0.002411850495263934
2023-01-24 08:24:12.369226: step: 1160/531, loss: 0.0016653139609843493
2023-01-24 08:24:13.431816: step: 1164/531, loss: 1.6790027075330727e-06
2023-01-24 08:24:14.493691: step: 1168/531, loss: 0.010914490558207035
2023-01-24 08:24:15.592668: step: 1172/531, loss: 0.0013401506002992392
2023-01-24 08:24:16.643785: step: 1176/531, loss: 0.03709438443183899
2023-01-24 08:24:17.685307: step: 1180/531, loss: 0.0002670694375410676
2023-01-24 08:24:18.734222: step: 1184/531, loss: 0.0013875156873837113
2023-01-24 08:24:19.794479: step: 1188/531, loss: 0.0006196255562826991
2023-01-24 08:24:20.847512: step: 1192/531, loss: 2.9499486117856577e-05
2023-01-24 08:24:21.885586: step: 1196/531, loss: 0.0024369647726416588
2023-01-24 08:24:22.948673: step: 1200/531, loss: 0.0012887604534626007
2023-01-24 08:24:24.005528: step: 1204/531, loss: 0.0015059924917295575
2023-01-24 08:24:25.067914: step: 1208/531, loss: 0.004952121526002884
2023-01-24 08:24:26.113633: step: 1212/531, loss: 0.009264972060918808
2023-01-24 08:24:27.153120: step: 1216/531, loss: 6.048934665159322e-06
2023-01-24 08:24:28.218986: step: 1220/531, loss: 0.0032116060610860586
2023-01-24 08:24:29.281683: step: 1224/531, loss: 0.010375224985182285
2023-01-24 08:24:30.331383: step: 1228/531, loss: 0.0013669985346496105
2023-01-24 08:24:31.384770: step: 1232/531, loss: 0.0011358282063156366
2023-01-24 08:24:32.459956: step: 1236/531, loss: 0.018549779430031776
2023-01-24 08:24:33.525474: step: 1240/531, loss: 0.000828936230391264
2023-01-24 08:24:34.573794: step: 1244/531, loss: 0.0020182894077152014
2023-01-24 08:24:35.647916: step: 1248/531, loss: 0.0015858432743698359
2023-01-24 08:24:36.702601: step: 1252/531, loss: 0.0011689248494803905
2023-01-24 08:24:37.737797: step: 1256/531, loss: 0.0009232672746293247
2023-01-24 08:24:38.778057: step: 1260/531, loss: 0.00344842835329473
2023-01-24 08:24:39.840219: step: 1264/531, loss: 0.0015458631096407771
2023-01-24 08:24:40.898914: step: 1268/531, loss: 0.017227625474333763
2023-01-24 08:24:41.967448: step: 1272/531, loss: 0.00433390261605382
2023-01-24 08:24:43.037224: step: 1276/531, loss: 0.0013303110608831048
2023-01-24 08:24:44.093674: step: 1280/531, loss: 0.0010876747546717525
2023-01-24 08:24:45.152886: step: 1284/531, loss: 0.00026305578649044037
2023-01-24 08:24:46.211926: step: 1288/531, loss: 0.0013360129669308662
2023-01-24 08:24:47.270485: step: 1292/531, loss: 0.0021273477468639612
2023-01-24 08:24:48.352262: step: 1296/531, loss: 0.0028546222019940615
2023-01-24 08:24:49.425232: step: 1300/531, loss: 0.008761582896113396
2023-01-24 08:24:50.484576: step: 1304/531, loss: 0.003074493957683444
2023-01-24 08:24:51.538706: step: 1308/531, loss: 0.0020554193761199713
2023-01-24 08:24:52.587066: step: 1312/531, loss: 0.0032944732811301947
2023-01-24 08:24:53.636166: step: 1316/531, loss: 0.043767448514699936
2023-01-24 08:24:54.711478: step: 1320/531, loss: 0.0016127859707921743
2023-01-24 08:24:55.787611: step: 1324/531, loss: 0.0005246309447102249
2023-01-24 08:24:56.825997: step: 1328/531, loss: 0.003447155933827162
2023-01-24 08:24:57.886296: step: 1332/531, loss: 0.0014250022359192371
2023-01-24 08:24:58.943911: step: 1336/531, loss: 0.015000371262431145
2023-01-24 08:25:00.008922: step: 1340/531, loss: 0.004626358859241009
2023-01-24 08:25:01.071041: step: 1344/531, loss: 0.00035782423219643533
2023-01-24 08:25:02.145367: step: 1348/531, loss: 0.0028104258235543966
2023-01-24 08:25:03.198393: step: 1352/531, loss: 4.902098567072244e-07
2023-01-24 08:25:04.260056: step: 1356/531, loss: 0.02652476169168949
2023-01-24 08:25:05.339146: step: 1360/531, loss: 0.0018253581365570426
2023-01-24 08:25:06.374629: step: 1364/531, loss: 0.0028708456084132195
2023-01-24 08:25:07.410845: step: 1368/531, loss: 0.005636297166347504
2023-01-24 08:25:08.461845: step: 1372/531, loss: 2.0378316548885778e-05
2023-01-24 08:25:09.518298: step: 1376/531, loss: 9.27389701246284e-05
2023-01-24 08:25:10.595374: step: 1380/531, loss: 0.008336848579347134
2023-01-24 08:25:11.650521: step: 1384/531, loss: 0.00011499337415443733
2023-01-24 08:25:12.700200: step: 1388/531, loss: 0.006575698498636484
2023-01-24 08:25:13.753083: step: 1392/531, loss: 0.000831614772323519
2023-01-24 08:25:14.799212: step: 1396/531, loss: 0.007550542708486319
2023-01-24 08:25:15.860120: step: 1400/531, loss: 0.009045243263244629
2023-01-24 08:25:16.909806: step: 1404/531, loss: 0.0002583989698905498
2023-01-24 08:25:17.989440: step: 1408/531, loss: 0.001176288235001266
2023-01-24 08:25:19.041197: step: 1412/531, loss: 0.002563477959483862
2023-01-24 08:25:20.091960: step: 1416/531, loss: 0.02445443719625473
2023-01-24 08:25:21.153970: step: 1420/531, loss: 0.0010914438171312213
2023-01-24 08:25:22.209818: step: 1424/531, loss: 0.0022718708496540785
2023-01-24 08:25:23.272162: step: 1428/531, loss: 0.008199960924685001
2023-01-24 08:25:24.336831: step: 1432/531, loss: 0.002697072457522154
2023-01-24 08:25:25.380957: step: 1436/531, loss: 0.0013049154076725245
2023-01-24 08:25:26.444023: step: 1440/531, loss: 0.004307322204113007
2023-01-24 08:25:27.495642: step: 1444/531, loss: 0.004063761793076992
2023-01-24 08:25:28.550061: step: 1448/531, loss: 1.4264049241319299e-05
2023-01-24 08:25:29.617461: step: 1452/531, loss: 0.005914001259952784
2023-01-24 08:25:30.677599: step: 1456/531, loss: 0.0013912719441577792
2023-01-24 08:25:31.730266: step: 1460/531, loss: 0.004360991530120373
2023-01-24 08:25:32.788759: step: 1464/531, loss: 0.0030729311984032393
2023-01-24 08:25:33.857313: step: 1468/531, loss: 5.357481131795794e-05
2023-01-24 08:25:34.902575: step: 1472/531, loss: 0.0003682511451188475
2023-01-24 08:25:35.979897: step: 1476/531, loss: 0.004276358988136053
2023-01-24 08:25:37.049357: step: 1480/531, loss: 0.0024351440370082855
2023-01-24 08:25:38.105428: step: 1484/531, loss: 0.0012374743819236755
2023-01-24 08:25:39.181250: step: 1488/531, loss: 0.002166086109355092
2023-01-24 08:25:40.244975: step: 1492/531, loss: 0.002553847385570407
2023-01-24 08:25:41.322004: step: 1496/531, loss: 0.0008582479786127806
2023-01-24 08:25:42.384844: step: 1500/531, loss: 0.002674586372449994
2023-01-24 08:25:43.445670: step: 1504/531, loss: 0.005065123084932566
2023-01-24 08:25:44.487523: step: 1508/531, loss: 0.0002147833292838186
2023-01-24 08:25:45.546614: step: 1512/531, loss: 0.0048254686407744884
2023-01-24 08:25:46.606260: step: 1516/531, loss: 9.325707651441917e-05
2023-01-24 08:25:47.667864: step: 1520/531, loss: 0.0014961569104343653
2023-01-24 08:25:48.720171: step: 1524/531, loss: 0.0012830272316932678
2023-01-24 08:25:49.767741: step: 1528/531, loss: 0.0017140316776931286
2023-01-24 08:25:50.817799: step: 1532/531, loss: 0.0018837180687114596
2023-01-24 08:25:51.884096: step: 1536/531, loss: 0.003946154844015837
2023-01-24 08:25:52.930616: step: 1540/531, loss: 2.889134339056909e-05
2023-01-24 08:25:53.982112: step: 1544/531, loss: 0.0016391181852668524
2023-01-24 08:25:55.046521: step: 1548/531, loss: 0.003246506443247199
2023-01-24 08:25:56.096309: step: 1552/531, loss: 0.0006468216306529939
2023-01-24 08:25:57.153386: step: 1556/531, loss: 0.002711770124733448
2023-01-24 08:25:58.209378: step: 1560/531, loss: 0.00037209983565844595
2023-01-24 08:25:59.258430: step: 1564/531, loss: 0.0011038295924663544
2023-01-24 08:26:00.314010: step: 1568/531, loss: 0.0003347354067955166
2023-01-24 08:26:01.374464: step: 1572/531, loss: 0.008154347538948059
2023-01-24 08:26:02.430241: step: 1576/531, loss: 0.00012576636800076813
2023-01-24 08:26:03.492009: step: 1580/531, loss: 0.0009588545653969049
2023-01-24 08:26:04.542124: step: 1584/531, loss: 0.00022881808399688452
2023-01-24 08:26:05.586020: step: 1588/531, loss: 0.0004036377649754286
2023-01-24 08:26:06.647607: step: 1592/531, loss: 0.00029302609618753195
2023-01-24 08:26:07.675099: step: 1596/531, loss: 0.00017839540669228882
2023-01-24 08:26:08.727761: step: 1600/531, loss: 0.0002494643849786371
2023-01-24 08:26:09.788224: step: 1604/531, loss: 0.0016358079155907035
2023-01-24 08:26:10.862848: step: 1608/531, loss: 0.003934149164706469
2023-01-24 08:26:11.942368: step: 1612/531, loss: 0.00014277591253630817
2023-01-24 08:26:12.990975: step: 1616/531, loss: 0.00753205269575119
2023-01-24 08:26:14.041444: step: 1620/531, loss: 0.0015130650717765093
2023-01-24 08:26:15.089712: step: 1624/531, loss: 0.006078492850065231
2023-01-24 08:26:16.138532: step: 1628/531, loss: 0.0001622473355382681
2023-01-24 08:26:17.214539: step: 1632/531, loss: 0.008209086023271084
2023-01-24 08:26:18.288858: step: 1636/531, loss: 0.0006903487374074757
2023-01-24 08:26:19.346116: step: 1640/531, loss: 0.008148431777954102
2023-01-24 08:26:20.394311: step: 1644/531, loss: 0.0013487264513969421
2023-01-24 08:26:21.464877: step: 1648/531, loss: 0.0016750216018408537
2023-01-24 08:26:22.524963: step: 1652/531, loss: 0.0033348274882882833
2023-01-24 08:26:23.587966: step: 1656/531, loss: 0.0019874819554388523
2023-01-24 08:26:24.640080: step: 1660/531, loss: 0.0032966621220111847
2023-01-24 08:26:25.718409: step: 1664/531, loss: 0.00629988219588995
2023-01-24 08:26:26.766138: step: 1668/531, loss: 0.000295562349492684
2023-01-24 08:26:27.835718: step: 1672/531, loss: 0.0009927835781127214
2023-01-24 08:26:28.896848: step: 1676/531, loss: 0.004141892772167921
2023-01-24 08:26:29.960105: step: 1680/531, loss: 0.00021202464995440096
2023-01-24 08:26:31.024873: step: 1684/531, loss: 7.637318776687607e-05
2023-01-24 08:26:32.090706: step: 1688/531, loss: 0.008229069411754608
2023-01-24 08:26:33.157772: step: 1692/531, loss: 0.0006660353974439204
2023-01-24 08:26:34.207323: step: 1696/531, loss: 0.0034808157943189144
2023-01-24 08:26:35.261788: step: 1700/531, loss: 0.0025462347548455
2023-01-24 08:26:36.309128: step: 1704/531, loss: 0.00018691897275857627
2023-01-24 08:26:37.381583: step: 1708/531, loss: 0.0020961440168321133
2023-01-24 08:26:38.448863: step: 1712/531, loss: 0.019499309360980988
2023-01-24 08:26:39.528472: step: 1716/531, loss: 0.00430101016536355
2023-01-24 08:26:40.583712: step: 1720/531, loss: 0.016481703147292137
2023-01-24 08:26:41.637154: step: 1724/531, loss: 0.0006929804803803563
2023-01-24 08:26:42.695345: step: 1728/531, loss: 0.0023284987546503544
2023-01-24 08:26:43.739654: step: 1732/531, loss: 0.012157940305769444
2023-01-24 08:26:44.801088: step: 1736/531, loss: 0.002034611301496625
2023-01-24 08:26:45.850510: step: 1740/531, loss: 0.0021266622934490442
2023-01-24 08:26:46.907616: step: 1744/531, loss: 0.0005496070371009409
2023-01-24 08:26:47.956796: step: 1748/531, loss: 0.0015330406604334712
2023-01-24 08:26:49.008914: step: 1752/531, loss: 0.0012892597587779164
2023-01-24 08:26:50.057460: step: 1756/531, loss: 3.597663817345165e-05
2023-01-24 08:26:51.127376: step: 1760/531, loss: 0.00023635837715119123
2023-01-24 08:26:52.199701: step: 1764/531, loss: 0.0013389786472544074
2023-01-24 08:26:53.250271: step: 1768/531, loss: 0.001086128642782569
2023-01-24 08:26:54.304169: step: 1772/531, loss: 0.0038151314947754145
2023-01-24 08:26:55.374880: step: 1776/531, loss: 0.0001457268081139773
2023-01-24 08:26:56.432519: step: 1780/531, loss: 0.0012750650057569146
2023-01-24 08:26:57.491963: step: 1784/531, loss: 0.0002461817057337612
2023-01-24 08:26:58.580897: step: 1788/531, loss: 0.00013186557043809444
2023-01-24 08:26:59.649007: step: 1792/531, loss: 0.0011999428970739245
2023-01-24 08:27:00.703313: step: 1796/531, loss: 0.016539234668016434
2023-01-24 08:27:01.758197: step: 1800/531, loss: 0.0010777073912322521
2023-01-24 08:27:02.821895: step: 1804/531, loss: 0.002102690516039729
2023-01-24 08:27:03.898917: step: 1808/531, loss: 0.004626779817044735
2023-01-24 08:27:04.968287: step: 1812/531, loss: 8.001690730452538e-06
2023-01-24 08:27:06.020962: step: 1816/531, loss: 0.0020071801263839006
2023-01-24 08:27:07.083116: step: 1820/531, loss: 9.671814950706903e-06
2023-01-24 08:27:08.131450: step: 1824/531, loss: 0.002047412097454071
2023-01-24 08:27:09.191509: step: 1828/531, loss: 0.008023356087505817
2023-01-24 08:27:10.231041: step: 1832/531, loss: 0.0034277657978236675
2023-01-24 08:27:11.286670: step: 1836/531, loss: 0.0013587395660579205
2023-01-24 08:27:12.352779: step: 1840/531, loss: 0.02174326404929161
2023-01-24 08:27:13.413519: step: 1844/531, loss: 0.005105058662593365
2023-01-24 08:27:14.491865: step: 1848/531, loss: 0.007215899880975485
2023-01-24 08:27:15.542989: step: 1852/531, loss: 0.0003426890471018851
2023-01-24 08:27:16.609166: step: 1856/531, loss: 0.0002772504521999508
2023-01-24 08:27:17.657844: step: 1860/531, loss: 0.006160797085613012
2023-01-24 08:27:18.716209: step: 1864/531, loss: 0.0005491849151439965
2023-01-24 08:27:19.761108: step: 1868/531, loss: 6.927702634129673e-05
2023-01-24 08:27:20.813184: step: 1872/531, loss: 0.005631587002426386
2023-01-24 08:27:21.880367: step: 1876/531, loss: 0.0033361671958118677
2023-01-24 08:27:22.930861: step: 1880/531, loss: 0.0011379916686564684
2023-01-24 08:27:24.033792: step: 1884/531, loss: 0.0013854247517883778
2023-01-24 08:27:25.081285: step: 1888/531, loss: 0.002004228299483657
2023-01-24 08:27:26.140408: step: 1892/531, loss: 0.00758488941937685
2023-01-24 08:27:27.189015: step: 1896/531, loss: 0.1323963701725006
2023-01-24 08:27:28.257177: step: 1900/531, loss: 0.029628774151206017
2023-01-24 08:27:29.323194: step: 1904/531, loss: 0.005650073755532503
2023-01-24 08:27:30.371057: step: 1908/531, loss: 0.0007673946092836559
2023-01-24 08:27:31.418737: step: 1912/531, loss: 0.002863846020773053
2023-01-24 08:27:32.477589: step: 1916/531, loss: 0.00010875792213482782
2023-01-24 08:27:33.544792: step: 1920/531, loss: 0.002233806299045682
2023-01-24 08:27:34.599201: step: 1924/531, loss: 0.02473893202841282
2023-01-24 08:27:35.674099: step: 1928/531, loss: 0.002922331215813756
2023-01-24 08:27:36.737052: step: 1932/531, loss: 0.00017819192726165056
2023-01-24 08:27:37.786113: step: 1936/531, loss: 0.0016617338405922055
2023-01-24 08:27:38.839341: step: 1940/531, loss: 0.00122277089394629
2023-01-24 08:27:39.875786: step: 1944/531, loss: 0.0016748837660998106
2023-01-24 08:27:40.926261: step: 1948/531, loss: 0.0011753502767533064
2023-01-24 08:27:41.975011: step: 1952/531, loss: 0.00028088665567338467
2023-01-24 08:27:43.040690: step: 1956/531, loss: 0.0017002267995849252
2023-01-24 08:27:44.102837: step: 1960/531, loss: 0.0036748351994901896
2023-01-24 08:27:45.163207: step: 1964/531, loss: 0.0024912068620324135
2023-01-24 08:27:46.229199: step: 1968/531, loss: 0.0002578684943728149
2023-01-24 08:27:47.272558: step: 1972/531, loss: 0.0007715074461884797
2023-01-24 08:27:48.341034: step: 1976/531, loss: 0.00542663736268878
2023-01-24 08:27:49.398783: step: 1980/531, loss: 0.0023416990879923105
2023-01-24 08:27:50.444294: step: 1984/531, loss: 0.0020016503985971212
2023-01-24 08:27:51.517540: step: 1988/531, loss: 0.0010499984491616488
2023-01-24 08:27:52.576143: step: 1992/531, loss: 0.0030251534190028906
2023-01-24 08:27:53.632965: step: 1996/531, loss: 0.0028106558602303267
2023-01-24 08:27:54.692437: step: 2000/531, loss: 0.00534806540235877
2023-01-24 08:27:55.728698: step: 2004/531, loss: 0.002174492459744215
2023-01-24 08:27:56.791182: step: 2008/531, loss: 0.0005388790741562843
2023-01-24 08:27:57.863853: step: 2012/531, loss: 0.008345023728907108
2023-01-24 08:27:58.924864: step: 2016/531, loss: 0.00013704894809052348
2023-01-24 08:27:59.992557: step: 2020/531, loss: 0.008596867322921753
2023-01-24 08:28:01.056975: step: 2024/531, loss: 0.001306700985878706
2023-01-24 08:28:02.107401: step: 2028/531, loss: 0.005681769922375679
2023-01-24 08:28:03.176468: step: 2032/531, loss: 0.001276426948606968
2023-01-24 08:28:04.254365: step: 2036/531, loss: 0.014172968454658985
2023-01-24 08:28:05.314708: step: 2040/531, loss: 0.0029230588115751743
2023-01-24 08:28:06.384077: step: 2044/531, loss: 0.0062430864199995995
2023-01-24 08:28:07.450624: step: 2048/531, loss: 0.014193709008395672
2023-01-24 08:28:08.516471: step: 2052/531, loss: 0.001921636750921607
2023-01-24 08:28:09.562528: step: 2056/531, loss: 0.0035454973112791777
2023-01-24 08:28:10.607198: step: 2060/531, loss: 0.0003642788506112993
2023-01-24 08:28:11.657198: step: 2064/531, loss: 0.004448044579476118
2023-01-24 08:28:12.716380: step: 2068/531, loss: 0.0008169467910192907
2023-01-24 08:28:13.767524: step: 2072/531, loss: 0.010781528428196907
2023-01-24 08:28:14.824850: step: 2076/531, loss: 0.003003212623298168
2023-01-24 08:28:15.901288: step: 2080/531, loss: 3.2854015444172546e-05
2023-01-24 08:28:16.959036: step: 2084/531, loss: 0.00021568017837125808
2023-01-24 08:28:18.018935: step: 2088/531, loss: 0.0014874560292810202
2023-01-24 08:28:19.075232: step: 2092/531, loss: 0.005862790159881115
2023-01-24 08:28:20.122939: step: 2096/531, loss: 0.017239782959222794
2023-01-24 08:28:21.180827: step: 2100/531, loss: 0.005743935238569975
2023-01-24 08:28:22.223361: step: 2104/531, loss: 0.0008272667764686048
2023-01-24 08:28:23.290084: step: 2108/531, loss: 0.0052041723392903805
2023-01-24 08:28:24.340840: step: 2112/531, loss: 0.0012248418061062694
2023-01-24 08:28:25.396196: step: 2116/531, loss: 0.012106272391974926
2023-01-24 08:28:26.456582: step: 2120/531, loss: 0.0015891635557636619
2023-01-24 08:28:27.518567: step: 2124/531, loss: 0.002304482040926814
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3905616759499405, 'r': 0.3216390272528922, 'f1': 0.35276538472897856}, 'combined': 0.2599323887476684, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.386494435367448, 'r': 0.27462363847569793, 'f1': 0.32109395368428995}, 'combined': 0.2010588308116582, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3751148615535408, 'r': 0.3395252162448557, 'f1': 0.3564338425518704}, 'combined': 0.2626354629329571, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3882659834785527, 'r': 0.28638554958111456, 'f1': 0.3296331857659119}, 'combined': 0.20427972075633974, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3653146606286163, 'r': 0.33065482565436427, 'f1': 0.3471216994419322}, 'combined': 0.2557738837993185, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41164783989459314, 'r': 0.28581500154989786, 'f1': 0.33738034775820835}, 'combined': 0.22380676534455407, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 15}
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, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 16
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:30:52.082865: step: 4/531, loss: 0.0005486905574798584
2023-01-24 08:30:53.125498: step: 8/531, loss: 0.005638486705720425
2023-01-24 08:30:54.178637: step: 12/531, loss: 0.0019356182310730219
2023-01-24 08:30:55.236308: step: 16/531, loss: 0.003297555260360241
2023-01-24 08:30:56.287092: step: 20/531, loss: 0.0020506056025624275
2023-01-24 08:30:57.349247: step: 24/531, loss: 0.005351112224161625
2023-01-24 08:30:58.406552: step: 28/531, loss: 0.011799738742411137
2023-01-24 08:30:59.473683: step: 32/531, loss: 1.9336966943228617e-05
2023-01-24 08:31:00.544896: step: 36/531, loss: 0.007591160945594311
2023-01-24 08:31:01.589632: step: 40/531, loss: 0.003377538872882724
2023-01-24 08:31:02.657028: step: 44/531, loss: 0.0005813426105305552
2023-01-24 08:31:03.716286: step: 48/531, loss: 0.004989310633391142
2023-01-24 08:31:04.759041: step: 52/531, loss: 0.0014595228713005781
2023-01-24 08:31:05.821492: step: 56/531, loss: 0.00645263958722353
2023-01-24 08:31:06.875358: step: 60/531, loss: 0.004616355057805777
2023-01-24 08:31:07.928811: step: 64/531, loss: 0.0040242960676550865
2023-01-24 08:31:08.975067: step: 68/531, loss: 0.011794381774961948
2023-01-24 08:31:10.016864: step: 72/531, loss: 8.037840598262846e-05
2023-01-24 08:31:11.069800: step: 76/531, loss: 0.002860124222934246
2023-01-24 08:31:12.112326: step: 80/531, loss: 0.007969512604176998
2023-01-24 08:31:13.170406: step: 84/531, loss: 4.2295665480196476e-05
2023-01-24 08:31:14.232417: step: 88/531, loss: 0.0042200167663395405
2023-01-24 08:31:15.289846: step: 92/531, loss: 0.004397066310048103
2023-01-24 08:31:16.369182: step: 96/531, loss: 0.001455863704904914
2023-01-24 08:31:17.425032: step: 100/531, loss: 0.0003081799077335745
2023-01-24 08:31:18.522214: step: 104/531, loss: 0.0035187399480491877
2023-01-24 08:31:19.584022: step: 108/531, loss: 2.927088871729211e-06
2023-01-24 08:31:20.623075: step: 112/531, loss: 2.8914173526572995e-05
2023-01-24 08:31:21.664294: step: 116/531, loss: 0.008407571353018284
2023-01-24 08:31:22.744040: step: 120/531, loss: 0.004076279234141111
2023-01-24 08:31:23.803693: step: 124/531, loss: 0.0014197694836184382
2023-01-24 08:31:24.871130: step: 128/531, loss: 0.0036911575589329004
2023-01-24 08:31:25.923357: step: 132/531, loss: 0.0006807747413404286
2023-01-24 08:31:26.958351: step: 136/531, loss: 6.875905091874301e-05
2023-01-24 08:31:28.014246: step: 140/531, loss: 0.004404854960739613
2023-01-24 08:31:29.060144: step: 144/531, loss: 0.002807085169479251
2023-01-24 08:31:30.119191: step: 148/531, loss: 0.0030035311356186867
2023-01-24 08:31:31.182945: step: 152/531, loss: 0.0018101237947121263
2023-01-24 08:31:32.229997: step: 156/531, loss: 0.0006155849550850689
2023-01-24 08:31:33.273279: step: 160/531, loss: 0.0007294066599570215
2023-01-24 08:31:34.332305: step: 164/531, loss: 0.0005816432530991733
2023-01-24 08:31:35.385686: step: 168/531, loss: 0.0020621127914637327
2023-01-24 08:31:36.456773: step: 172/531, loss: 0.00011609279317781329
2023-01-24 08:31:37.531178: step: 176/531, loss: 0.0008085482404567301
2023-01-24 08:31:38.586077: step: 180/531, loss: 2.0397019397933036e-05
2023-01-24 08:31:39.646220: step: 184/531, loss: 0.007287472486495972
2023-01-24 08:31:40.687113: step: 188/531, loss: 0.0009562839986756444
2023-01-24 08:31:41.757291: step: 192/531, loss: 0.007725608069449663
2023-01-24 08:31:42.844780: step: 196/531, loss: 0.0031432481482625008
2023-01-24 08:31:43.901011: step: 200/531, loss: 0.004705763887614012
2023-01-24 08:31:44.967298: step: 204/531, loss: 0.0012705445988103747
2023-01-24 08:31:46.027200: step: 208/531, loss: 0.006196799222379923
2023-01-24 08:31:47.096007: step: 212/531, loss: 0.0006535562570206821
2023-01-24 08:31:48.173787: step: 216/531, loss: 0.002844964386895299
2023-01-24 08:31:49.236827: step: 220/531, loss: 0.00399673031643033
2023-01-24 08:31:50.304676: step: 224/531, loss: 0.0028555591125041246
2023-01-24 08:31:51.360919: step: 228/531, loss: 0.0039131478406488895
2023-01-24 08:31:52.425556: step: 232/531, loss: 0.007284544408321381
2023-01-24 08:31:53.475442: step: 236/531, loss: 0.00017736232257448137
2023-01-24 08:31:54.547089: step: 240/531, loss: 0.004970039241015911
2023-01-24 08:31:55.598599: step: 244/531, loss: 1.9991690351162106e-05
2023-01-24 08:31:56.661855: step: 248/531, loss: 0.0011893160408362746
2023-01-24 08:31:57.724741: step: 252/531, loss: 0.005878967698663473
2023-01-24 08:31:58.779302: step: 256/531, loss: 4.5313376176636666e-05
2023-01-24 08:31:59.829091: step: 260/531, loss: 0.002199020469561219
2023-01-24 08:32:00.885768: step: 264/531, loss: 0.00015328492736443877
2023-01-24 08:32:01.939971: step: 268/531, loss: 0.0014381208457052708
2023-01-24 08:32:02.980901: step: 272/531, loss: 0.0003298294323030859
2023-01-24 08:32:04.043509: step: 276/531, loss: 0.0010655870428308845
2023-01-24 08:32:05.110345: step: 280/531, loss: 0.00034697697265073657
2023-01-24 08:32:06.173723: step: 284/531, loss: 0.006925155874341726
2023-01-24 08:32:07.232266: step: 288/531, loss: 2.0201870938763022e-05
2023-01-24 08:32:08.268941: step: 292/531, loss: 0.0007099260110408068
2023-01-24 08:32:09.333897: step: 296/531, loss: 0.011019090190529823
2023-01-24 08:32:10.392336: step: 300/531, loss: 4.568853000819217e-06
2023-01-24 08:32:11.451914: step: 304/531, loss: 0.0041047679260373116
2023-01-24 08:32:12.533024: step: 308/531, loss: 0.0038848845288157463
2023-01-24 08:32:13.606710: step: 312/531, loss: 0.003538146847859025
2023-01-24 08:32:14.675563: step: 316/531, loss: 6.563659553648904e-05
2023-01-24 08:32:15.754919: step: 320/531, loss: 0.0021672204602509737
2023-01-24 08:32:16.815050: step: 324/531, loss: 0.0007981749949976802
2023-01-24 08:32:17.859043: step: 328/531, loss: 1.4987713257141877e-05
2023-01-24 08:32:18.934919: step: 332/531, loss: 0.006025921553373337
2023-01-24 08:32:19.999258: step: 336/531, loss: 0.003645022166892886
2023-01-24 08:32:21.064586: step: 340/531, loss: 0.00034223950933665037
2023-01-24 08:32:22.119316: step: 344/531, loss: 0.007994323968887329
2023-01-24 08:32:23.173436: step: 348/531, loss: 0.002756382804363966
2023-01-24 08:32:24.217245: step: 352/531, loss: 0.00021866396127734333
2023-01-24 08:32:25.281660: step: 356/531, loss: 0.0001236679236171767
2023-01-24 08:32:26.337041: step: 360/531, loss: 0.0001943993556778878
2023-01-24 08:32:27.422782: step: 364/531, loss: 0.00147626840043813
2023-01-24 08:32:28.485046: step: 368/531, loss: 0.018230203539133072
2023-01-24 08:32:29.539174: step: 372/531, loss: 0.00027743951068259776
2023-01-24 08:32:30.590036: step: 376/531, loss: 0.005304703023284674
2023-01-24 08:32:31.657753: step: 380/531, loss: 0.001575262169353664
2023-01-24 08:32:32.718901: step: 384/531, loss: 0.011680803261697292
2023-01-24 08:32:33.771450: step: 388/531, loss: 1.245699604623951e-05
2023-01-24 08:32:34.826919: step: 392/531, loss: 0.00036558666033670306
2023-01-24 08:32:35.891652: step: 396/531, loss: 0.007009987719357014
2023-01-24 08:32:36.948200: step: 400/531, loss: 7.078037356222922e-08
2023-01-24 08:32:37.998449: step: 404/531, loss: 0.002747965743765235
2023-01-24 08:32:39.059075: step: 408/531, loss: 0.00023298650921788067
2023-01-24 08:32:40.109185: step: 412/531, loss: 0.0026268947403877974
2023-01-24 08:32:41.164103: step: 416/531, loss: 0.006747996900230646
2023-01-24 08:32:42.211063: step: 420/531, loss: 0.0002006733266171068
2023-01-24 08:32:43.283404: step: 424/531, loss: 0.00010924031084869057
2023-01-24 08:32:44.353089: step: 428/531, loss: 0.005553253460675478
2023-01-24 08:32:45.424166: step: 432/531, loss: 0.03208472952246666
2023-01-24 08:32:46.482146: step: 436/531, loss: 0.004296464845538139
2023-01-24 08:32:47.537932: step: 440/531, loss: 0.0015038911951705813
2023-01-24 08:32:48.597584: step: 444/531, loss: 0.002741214819252491
2023-01-24 08:32:49.658901: step: 448/531, loss: 0.002793479012325406
2023-01-24 08:32:50.722993: step: 452/531, loss: 3.7675938074244186e-05
2023-01-24 08:32:51.794213: step: 456/531, loss: 0.0013523348607122898
2023-01-24 08:32:52.852820: step: 460/531, loss: 0.0007990815793164074
2023-01-24 08:32:53.921485: step: 464/531, loss: 0.002101711928844452
2023-01-24 08:32:54.972124: step: 468/531, loss: 0.0011780555360019207
2023-01-24 08:32:56.034198: step: 472/531, loss: 0.001475114026106894
2023-01-24 08:32:57.098020: step: 476/531, loss: 0.0001634666114114225
2023-01-24 08:32:58.138835: step: 480/531, loss: 0.002623925218358636
2023-01-24 08:32:59.209360: step: 484/531, loss: 0.0044868397526443005
2023-01-24 08:33:00.260117: step: 488/531, loss: 0.0016982014058157802
2023-01-24 08:33:01.308215: step: 492/531, loss: 0.0001340064191026613
2023-01-24 08:33:02.369309: step: 496/531, loss: 0.0022903243079781532
2023-01-24 08:33:03.428122: step: 500/531, loss: 0.001770670060068369
2023-01-24 08:33:04.491468: step: 504/531, loss: 0.003249990288168192
2023-01-24 08:33:05.539565: step: 508/531, loss: 0.0
2023-01-24 08:33:06.593418: step: 512/531, loss: 0.0007118220091797411
2023-01-24 08:33:07.665261: step: 516/531, loss: 0.0058363983407616615
2023-01-24 08:33:08.732323: step: 520/531, loss: 0.0025534082669764757
2023-01-24 08:33:09.772203: step: 524/531, loss: 0.003192349337041378
2023-01-24 08:33:10.836559: step: 528/531, loss: 7.978378562256694e-05
2023-01-24 08:33:11.934234: step: 532/531, loss: 0.0013387470971792936
2023-01-24 08:33:12.979950: step: 536/531, loss: 0.0005626198835670948
2023-01-24 08:33:14.058429: step: 540/531, loss: 0.0035505532287061214
2023-01-24 08:33:15.105408: step: 544/531, loss: 0.0013098145136609674
2023-01-24 08:33:16.163866: step: 548/531, loss: 0.007388577796518803
2023-01-24 08:33:17.219322: step: 552/531, loss: 0.00047912332229316235
2023-01-24 08:33:18.276708: step: 556/531, loss: 6.0840258811367676e-05
2023-01-24 08:33:19.341381: step: 560/531, loss: 0.001054595224559307
2023-01-24 08:33:20.393545: step: 564/531, loss: 0.0003234370960853994
2023-01-24 08:33:21.439614: step: 568/531, loss: 0.0013571546878665686
2023-01-24 08:33:22.488356: step: 572/531, loss: 2.2032678316463716e-05
2023-01-24 08:33:23.540438: step: 576/531, loss: 2.442975073790876e-06
2023-01-24 08:33:24.593010: step: 580/531, loss: 0.00010165247658733279
2023-01-24 08:33:25.655350: step: 584/531, loss: 1.2875897482444998e-05
2023-01-24 08:33:26.718831: step: 588/531, loss: 0.002972032641991973
2023-01-24 08:33:27.784790: step: 592/531, loss: 0.0001249411579919979
2023-01-24 08:33:28.845877: step: 596/531, loss: 0.00010246341116726398
2023-01-24 08:33:29.883783: step: 600/531, loss: 0.00042192815453745425
2023-01-24 08:33:30.936747: step: 604/531, loss: 0.00083645258564502
2023-01-24 08:33:31.993615: step: 608/531, loss: 0.0016103017842397094
2023-01-24 08:33:33.058568: step: 612/531, loss: 0.002996583469212055
2023-01-24 08:33:34.114388: step: 616/531, loss: 0.008293939754366875
2023-01-24 08:33:35.177436: step: 620/531, loss: 0.002016602549701929
2023-01-24 08:33:36.222419: step: 624/531, loss: 0.0004442233475856483
2023-01-24 08:33:37.296551: step: 628/531, loss: 0.000340130616677925
2023-01-24 08:33:38.374062: step: 632/531, loss: 0.0031298520043492317
2023-01-24 08:33:39.432809: step: 636/531, loss: 0.005849834531545639
2023-01-24 08:33:40.511274: step: 640/531, loss: 0.0013425523648038507
2023-01-24 08:33:41.567406: step: 644/531, loss: 0.0077392528764903545
2023-01-24 08:33:42.621075: step: 648/531, loss: 0.003035782603546977
2023-01-24 08:33:43.683838: step: 652/531, loss: 0.0012241639196872711
2023-01-24 08:33:44.730437: step: 656/531, loss: 0.004161634482443333
2023-01-24 08:33:45.820173: step: 660/531, loss: 0.011733267456293106
2023-01-24 08:33:46.883048: step: 664/531, loss: 0.008866648189723492
2023-01-24 08:33:47.939505: step: 668/531, loss: 5.774093096988508e-07
2023-01-24 08:33:49.008508: step: 672/531, loss: 0.0003667854762170464
2023-01-24 08:33:50.088311: step: 676/531, loss: 0.018139883875846863
2023-01-24 08:33:51.143461: step: 680/531, loss: 0.0014334052102640271
2023-01-24 08:33:52.201129: step: 684/531, loss: 0.0009828147012740374
2023-01-24 08:33:53.263881: step: 688/531, loss: 0.0482136495411396
2023-01-24 08:33:54.331264: step: 692/531, loss: 0.0044499170035123825
2023-01-24 08:33:55.402416: step: 696/531, loss: 0.006069484166800976
2023-01-24 08:33:56.468045: step: 700/531, loss: 0.00397529499605298
2023-01-24 08:33:57.523458: step: 704/531, loss: 0.0021991494577378035
2023-01-24 08:33:58.585120: step: 708/531, loss: 0.007443928625434637
2023-01-24 08:33:59.653647: step: 712/531, loss: 0.024295277893543243
2023-01-24 08:34:00.724498: step: 716/531, loss: 0.002493762644007802
2023-01-24 08:34:01.800320: step: 720/531, loss: 0.0006320299580693245
2023-01-24 08:34:02.856063: step: 724/531, loss: 0.00021273297898005694
2023-01-24 08:34:03.915156: step: 728/531, loss: 0.0007978095673024654
2023-01-24 08:34:04.982087: step: 732/531, loss: 0.000337799807311967
2023-01-24 08:34:06.052927: step: 736/531, loss: 0.0007277352269738913
2023-01-24 08:34:07.119132: step: 740/531, loss: 0.007081305608153343
2023-01-24 08:34:08.170493: step: 744/531, loss: 8.452231122646481e-05
2023-01-24 08:34:09.234712: step: 748/531, loss: 0.004326251335442066
2023-01-24 08:34:10.295316: step: 752/531, loss: 0.0015107349026948214
2023-01-24 08:34:11.362049: step: 756/531, loss: 0.0003000946016982198
2023-01-24 08:34:12.434700: step: 760/531, loss: 0.02435571886599064
2023-01-24 08:34:13.480165: step: 764/531, loss: 0.000554512080270797
2023-01-24 08:34:14.554671: step: 768/531, loss: 0.0031434923876076937
2023-01-24 08:34:15.623135: step: 772/531, loss: 0.03658808395266533
2023-01-24 08:34:16.681233: step: 776/531, loss: 0.009474306367337704
2023-01-24 08:34:17.755925: step: 780/531, loss: 0.0006337225786410272
2023-01-24 08:34:18.810567: step: 784/531, loss: 0.0006190314306877553
2023-01-24 08:34:19.866610: step: 788/531, loss: 0.00016941303329076618
2023-01-24 08:34:20.918909: step: 792/531, loss: 0.0034792874939739704
2023-01-24 08:34:22.003052: step: 796/531, loss: 0.0026638987474143505
2023-01-24 08:34:23.056001: step: 800/531, loss: 0.004257877357304096
2023-01-24 08:34:24.130978: step: 804/531, loss: 0.0016678273677825928
2023-01-24 08:34:25.191952: step: 808/531, loss: 0.0013899136101827025
2023-01-24 08:34:26.263145: step: 812/531, loss: 0.00044038414489477873
2023-01-24 08:34:27.341115: step: 816/531, loss: 0.004343985579907894
2023-01-24 08:34:28.410663: step: 820/531, loss: 0.004557658452540636
2023-01-24 08:34:29.476441: step: 824/531, loss: 0.000536191975697875
2023-01-24 08:34:30.555646: step: 828/531, loss: 0.001975310267880559
2023-01-24 08:34:31.605979: step: 832/531, loss: 0.002083404455333948
2023-01-24 08:34:32.675705: step: 836/531, loss: 3.190386632923037e-05
2023-01-24 08:34:33.719398: step: 840/531, loss: 1.8812079360941425e-05
2023-01-24 08:34:34.771691: step: 844/531, loss: 0.00013241350825410336
2023-01-24 08:34:35.847760: step: 848/531, loss: 0.000764001626521349
2023-01-24 08:34:36.898239: step: 852/531, loss: 0.005922616459429264
2023-01-24 08:34:37.954609: step: 856/531, loss: 0.00026294938288629055
2023-01-24 08:34:39.010395: step: 860/531, loss: 6.724869308527559e-05
2023-01-24 08:34:40.064292: step: 864/531, loss: 0.004805354867130518
2023-01-24 08:34:41.125263: step: 868/531, loss: 0.00019580681691877544
2023-01-24 08:34:42.203970: step: 872/531, loss: 0.0022269911132752895
2023-01-24 08:34:43.254965: step: 876/531, loss: 0.005511918570846319
2023-01-24 08:34:44.336465: step: 880/531, loss: 0.0003908055368810892
2023-01-24 08:34:45.411170: step: 884/531, loss: 0.0038577395025640726
2023-01-24 08:34:46.456207: step: 888/531, loss: 0.00012229409185238183
2023-01-24 08:34:47.512044: step: 892/531, loss: 0.022004032507538795
2023-01-24 08:34:48.559856: step: 896/531, loss: 0.0011355261085554957
2023-01-24 08:34:49.625778: step: 900/531, loss: 0.00016177931684069335
2023-01-24 08:34:50.677690: step: 904/531, loss: 9.462114576308522e-07
2023-01-24 08:34:51.730933: step: 908/531, loss: 0.0003072930558118969
2023-01-24 08:34:52.787557: step: 912/531, loss: 0.0010208121966570616
2023-01-24 08:34:53.847841: step: 916/531, loss: 0.005024034529924393
2023-01-24 08:34:54.911712: step: 920/531, loss: 2.779700707833399e-06
2023-01-24 08:34:55.964239: step: 924/531, loss: 0.0005459256353788078
2023-01-24 08:34:57.026260: step: 928/531, loss: 2.352625051571522e-05
2023-01-24 08:34:58.091997: step: 932/531, loss: 0.005092419683933258
2023-01-24 08:34:59.158769: step: 936/531, loss: 0.004188242368400097
2023-01-24 08:35:00.236316: step: 940/531, loss: 0.0005123792798258364
2023-01-24 08:35:01.306905: step: 944/531, loss: 0.002709169639274478
2023-01-24 08:35:02.372357: step: 948/531, loss: 0.004825504496693611
2023-01-24 08:35:03.424291: step: 952/531, loss: 0.003973186481744051
2023-01-24 08:35:04.496231: step: 956/531, loss: 0.0006743451813235879
2023-01-24 08:35:05.543707: step: 960/531, loss: 0.004166416823863983
2023-01-24 08:35:06.599751: step: 964/531, loss: 0.00047372953849844635
2023-01-24 08:35:07.680372: step: 968/531, loss: 0.004287892021238804
2023-01-24 08:35:08.769433: step: 972/531, loss: 0.007905044592916965
2023-01-24 08:35:09.828940: step: 976/531, loss: 0.004012254998087883
2023-01-24 08:35:10.882437: step: 980/531, loss: 0.0025107422843575478
2023-01-24 08:35:11.945724: step: 984/531, loss: 0.0005221758619882166
2023-01-24 08:35:13.009655: step: 988/531, loss: 0.0023451775778084993
2023-01-24 08:35:14.064573: step: 992/531, loss: 0.0024254019372165203
2023-01-24 08:35:15.119971: step: 996/531, loss: 0.0005585875478573143
2023-01-24 08:35:16.189835: step: 1000/531, loss: 0.007971425540745258
2023-01-24 08:35:17.255347: step: 1004/531, loss: 0.004571865312755108
2023-01-24 08:35:18.334689: step: 1008/531, loss: 0.00048525878810323775
2023-01-24 08:35:19.384214: step: 1012/531, loss: 0.0015203282237052917
2023-01-24 08:35:20.433106: step: 1016/531, loss: 0.010365449823439121
2023-01-24 08:35:21.486347: step: 1020/531, loss: 0.0049848249182105064
2023-01-24 08:35:22.549913: step: 1024/531, loss: 0.0037505249492824078
2023-01-24 08:35:23.606910: step: 1028/531, loss: 0.005364949814975262
2023-01-24 08:35:24.695313: step: 1032/531, loss: 0.004655045457184315
2023-01-24 08:35:25.744588: step: 1036/531, loss: 0.0004250466590747237
2023-01-24 08:35:26.805935: step: 1040/531, loss: 0.004402277525514364
2023-01-24 08:35:27.868065: step: 1044/531, loss: 0.008860880509018898
2023-01-24 08:35:28.925148: step: 1048/531, loss: 0.0011058483505621552
2023-01-24 08:35:29.997766: step: 1052/531, loss: 0.0010410579852759838
2023-01-24 08:35:31.042121: step: 1056/531, loss: 1.4615292457165197e-05
2023-01-24 08:35:32.098379: step: 1060/531, loss: 0.0011917271185666323
2023-01-24 08:35:33.171296: step: 1064/531, loss: 0.0007558545912615955
2023-01-24 08:35:34.235021: step: 1068/531, loss: 0.005323739722371101
2023-01-24 08:35:35.295013: step: 1072/531, loss: 0.00017955050861928612
2023-01-24 08:35:36.360682: step: 1076/531, loss: 0.0021870082709938288
2023-01-24 08:35:37.414013: step: 1080/531, loss: 4.3273194023640826e-05
2023-01-24 08:35:38.475453: step: 1084/531, loss: 0.0040289005264639854
2023-01-24 08:35:39.569056: step: 1088/531, loss: 0.00014256784925237298
2023-01-24 08:35:40.624600: step: 1092/531, loss: 0.00023438378411810845
2023-01-24 08:35:41.682522: step: 1096/531, loss: 1.7452583051635884e-05
2023-01-24 08:35:42.767692: step: 1100/531, loss: 0.002010050928220153
2023-01-24 08:35:43.834731: step: 1104/531, loss: 0.0023867525160312653
2023-01-24 08:35:44.886147: step: 1108/531, loss: 0.007288050372153521
2023-01-24 08:35:45.944860: step: 1112/531, loss: 0.0014383370289579034
2023-01-24 08:35:47.024075: step: 1116/531, loss: 0.003016107017174363
2023-01-24 08:35:48.084981: step: 1120/531, loss: 0.003575441427528858
2023-01-24 08:35:49.144383: step: 1124/531, loss: 0.00020924244017805904
2023-01-24 08:35:50.213429: step: 1128/531, loss: 0.0010998067446053028
2023-01-24 08:35:51.278802: step: 1132/531, loss: 0.0027836367953568697
2023-01-24 08:35:52.364523: step: 1136/531, loss: 0.000872039410751313
2023-01-24 08:35:53.424631: step: 1140/531, loss: 6.790413317503408e-05
2023-01-24 08:35:54.507926: step: 1144/531, loss: 0.0010864792857319117
2023-01-24 08:35:55.569757: step: 1148/531, loss: 2.113144319082494e-06
2023-01-24 08:35:56.639094: step: 1152/531, loss: 0.004047530237585306
2023-01-24 08:35:57.710997: step: 1156/531, loss: 0.04118496924638748
2023-01-24 08:35:58.763087: step: 1160/531, loss: 0.019365420565009117
2023-01-24 08:35:59.828988: step: 1164/531, loss: 0.0003123456845059991
2023-01-24 08:36:00.912024: step: 1168/531, loss: 0.0051879254169762135
2023-01-24 08:36:01.979801: step: 1172/531, loss: 0.0005348093691281974
2023-01-24 08:36:03.040970: step: 1176/531, loss: 0.0034417458809912205
2023-01-24 08:36:04.087704: step: 1180/531, loss: 0.0005080850096419454
2023-01-24 08:36:05.135818: step: 1184/531, loss: 7.316900882869959e-05
2023-01-24 08:36:06.198633: step: 1188/531, loss: 0.003836761461570859
2023-01-24 08:36:07.255370: step: 1192/531, loss: 0.016399923712015152
2023-01-24 08:36:08.316644: step: 1196/531, loss: 0.00011520372208906338
2023-01-24 08:36:09.386205: step: 1200/531, loss: 0.016874657943844795
2023-01-24 08:36:10.445040: step: 1204/531, loss: 0.006478848867118359
2023-01-24 08:36:11.521634: step: 1208/531, loss: 0.006651771254837513
2023-01-24 08:36:12.616417: step: 1212/531, loss: 0.005560880061239004
2023-01-24 08:36:13.679609: step: 1216/531, loss: 0.011105512268841267
2023-01-24 08:36:14.743664: step: 1220/531, loss: 0.004349041264504194
2023-01-24 08:36:15.811431: step: 1224/531, loss: 0.007353505585342646
2023-01-24 08:36:16.873061: step: 1228/531, loss: 0.0016315426910296082
2023-01-24 08:36:17.934759: step: 1232/531, loss: 0.0010192908812314272
2023-01-24 08:36:18.990725: step: 1236/531, loss: 0.00018461354193277657
2023-01-24 08:36:20.048684: step: 1240/531, loss: 0.0029581880662590265
2023-01-24 08:36:21.113884: step: 1244/531, loss: 0.005374578293412924
2023-01-24 08:36:22.194167: step: 1248/531, loss: 0.005349393002688885
2023-01-24 08:36:23.248523: step: 1252/531, loss: 0.0012194185983389616
2023-01-24 08:36:24.298703: step: 1256/531, loss: 0.0021546054631471634
2023-01-24 08:36:25.352567: step: 1260/531, loss: 0.0004597770457621664
2023-01-24 08:36:26.437953: step: 1264/531, loss: 0.00028122885851189494
2023-01-24 08:36:27.502986: step: 1268/531, loss: 0.0009860617574304342
2023-01-24 08:36:28.570551: step: 1272/531, loss: 0.00726823415607214
2023-01-24 08:36:29.627296: step: 1276/531, loss: 0.00618370296433568
2023-01-24 08:36:30.700784: step: 1280/531, loss: 0.0008198546129278839
2023-01-24 08:36:31.765971: step: 1284/531, loss: 0.0016563403187319636
2023-01-24 08:36:32.810930: step: 1288/531, loss: 0.003673788858577609
2023-01-24 08:36:33.870982: step: 1292/531, loss: 0.00038287806091830134
2023-01-24 08:36:34.918200: step: 1296/531, loss: 0.0017629192443564534
2023-01-24 08:36:35.978450: step: 1300/531, loss: 0.0026671725790947676
2023-01-24 08:36:37.031535: step: 1304/531, loss: 0.0030565953347831964
2023-01-24 08:36:38.090490: step: 1308/531, loss: 0.0050751385278999805
2023-01-24 08:36:39.142095: step: 1312/531, loss: 0.0004592680197674781
2023-01-24 08:36:40.212101: step: 1316/531, loss: 0.006077755708247423
2023-01-24 08:36:41.264395: step: 1320/531, loss: 0.002504387404769659
2023-01-24 08:36:42.352070: step: 1324/531, loss: 0.0016804387560114264
2023-01-24 08:36:43.400668: step: 1328/531, loss: 0.03159349039196968
2023-01-24 08:36:44.451389: step: 1332/531, loss: 0.002411656081676483
2023-01-24 08:36:45.499468: step: 1336/531, loss: 0.009108101017773151
2023-01-24 08:36:46.579696: step: 1340/531, loss: 0.030691813677549362
2023-01-24 08:36:47.635644: step: 1344/531, loss: 0.005158753599971533
2023-01-24 08:36:48.692411: step: 1348/531, loss: 2.4898179617593996e-05
2023-01-24 08:36:49.747820: step: 1352/531, loss: 0.013886045664548874
2023-01-24 08:36:50.814817: step: 1356/531, loss: 0.0026678945869207382
2023-01-24 08:36:51.871485: step: 1360/531, loss: 0.0014832192100584507
2023-01-24 08:36:52.929711: step: 1364/531, loss: 0.00021716530318371952
2023-01-24 08:36:53.985759: step: 1368/531, loss: 3.186364438079181e-06
2023-01-24 08:36:55.043920: step: 1372/531, loss: 0.0014044985873624682
2023-01-24 08:36:56.104053: step: 1376/531, loss: 0.0037600467912852764
2023-01-24 08:36:57.165178: step: 1380/531, loss: 0.002768822479993105
2023-01-24 08:36:58.209689: step: 1384/531, loss: 0.005670212674885988
2023-01-24 08:36:59.269937: step: 1388/531, loss: 0.023402299731969833
2023-01-24 08:37:00.324621: step: 1392/531, loss: 3.9808048313716426e-05
2023-01-24 08:37:01.368088: step: 1396/531, loss: 6.373807264026254e-05
2023-01-24 08:37:02.412910: step: 1400/531, loss: 0.004025139845907688
2023-01-24 08:37:03.475945: step: 1404/531, loss: 0.009786794893443584
2023-01-24 08:37:04.535147: step: 1408/531, loss: 0.0009095058194361627
2023-01-24 08:37:05.612263: step: 1412/531, loss: 0.011140435934066772
2023-01-24 08:37:06.679411: step: 1416/531, loss: 0.0006607322138734162
2023-01-24 08:37:07.741581: step: 1420/531, loss: 0.0004952255985699594
2023-01-24 08:37:08.798133: step: 1424/531, loss: 0.006792471744120121
2023-01-24 08:37:09.834237: step: 1428/531, loss: 0.002992016961798072
2023-01-24 08:37:10.904384: step: 1432/531, loss: 0.0036824692506343126
2023-01-24 08:37:11.947444: step: 1436/531, loss: 0.012425734661519527
2023-01-24 08:37:13.002598: step: 1440/531, loss: 0.00041032061562873423
2023-01-24 08:37:14.046211: step: 1444/531, loss: 0.011098210699856281
2023-01-24 08:37:15.106063: step: 1448/531, loss: 0.0030635774601250887
2023-01-24 08:37:16.155328: step: 1452/531, loss: 0.0018457588739693165
2023-01-24 08:37:17.217398: step: 1456/531, loss: 0.00670445803552866
2023-01-24 08:37:18.270956: step: 1460/531, loss: 0.004242204129695892
2023-01-24 08:37:19.338435: step: 1464/531, loss: 0.0001496480399509892
2023-01-24 08:37:20.409547: step: 1468/531, loss: 0.07136724889278412
2023-01-24 08:37:21.467730: step: 1472/531, loss: 2.9415205062832683e-05
2023-01-24 08:37:22.504812: step: 1476/531, loss: 0.0011069440515711904
2023-01-24 08:37:23.578926: step: 1480/531, loss: 0.0001400729815941304
2023-01-24 08:37:24.622586: step: 1484/531, loss: 0.0003343082789797336
2023-01-24 08:37:25.681379: step: 1488/531, loss: 8.178819552995265e-05
2023-01-24 08:37:26.718635: step: 1492/531, loss: 0.001840598531998694
2023-01-24 08:37:27.799763: step: 1496/531, loss: 0.01013681385666132
2023-01-24 08:37:28.853381: step: 1500/531, loss: 0.0025778785347938538
2023-01-24 08:37:29.909181: step: 1504/531, loss: 0.0002579967840574682
2023-01-24 08:37:30.975453: step: 1508/531, loss: 0.04207774996757507
2023-01-24 08:37:32.041557: step: 1512/531, loss: 2.6987532919520163e-07
2023-01-24 08:37:33.108221: step: 1516/531, loss: 2.7331512683304027e-05
2023-01-24 08:37:34.170218: step: 1520/531, loss: 0.0013419572496786714
2023-01-24 08:37:35.226331: step: 1524/531, loss: 0.0042828964069485664
2023-01-24 08:37:36.302609: step: 1528/531, loss: 0.08026225864887238
2023-01-24 08:37:37.363139: step: 1532/531, loss: 0.029859913513064384
2023-01-24 08:37:38.413470: step: 1536/531, loss: 0.0049073961563408375
2023-01-24 08:37:39.468987: step: 1540/531, loss: 0.0012522776378318667
2023-01-24 08:37:40.515783: step: 1544/531, loss: 0.006776969879865646
2023-01-24 08:37:41.583331: step: 1548/531, loss: 0.004690579604357481
2023-01-24 08:37:42.669509: step: 1552/531, loss: 0.00415599113330245
2023-01-24 08:37:43.733226: step: 1556/531, loss: 0.002957819029688835
2023-01-24 08:37:44.814941: step: 1560/531, loss: 0.000746549223549664
2023-01-24 08:37:45.876441: step: 1564/531, loss: 0.013988284394145012
2023-01-24 08:37:46.945070: step: 1568/531, loss: 0.0005988162592984736
2023-01-24 08:37:48.016829: step: 1572/531, loss: 0.004227219615131617
2023-01-24 08:37:49.091185: step: 1576/531, loss: 0.001184638123959303
2023-01-24 08:37:50.166787: step: 1580/531, loss: 0.00997968390583992
2023-01-24 08:37:51.225916: step: 1584/531, loss: 0.006052677053958178
2023-01-24 08:37:52.272918: step: 1588/531, loss: 2.45750488829799e-05
2023-01-24 08:37:53.328911: step: 1592/531, loss: 0.015461661852896214
2023-01-24 08:37:54.380590: step: 1596/531, loss: 0.006575525738298893
2023-01-24 08:37:55.431990: step: 1600/531, loss: 0.002303633140400052
2023-01-24 08:37:56.503158: step: 1604/531, loss: 0.001096038380637765
2023-01-24 08:37:57.554228: step: 1608/531, loss: 0.00010347751958761364
2023-01-24 08:37:58.599255: step: 1612/531, loss: 0.0005093302461318672
2023-01-24 08:37:59.666963: step: 1616/531, loss: 0.008888202719390392
2023-01-24 08:38:00.728518: step: 1620/531, loss: 0.005364787764847279
2023-01-24 08:38:01.792317: step: 1624/531, loss: 0.005350317806005478
2023-01-24 08:38:02.845094: step: 1628/531, loss: 0.0008648353395983577
2023-01-24 08:38:03.905076: step: 1632/531, loss: 0.0006377737736329436
2023-01-24 08:38:04.962079: step: 1636/531, loss: 0.0010672896169126034
2023-01-24 08:38:06.025259: step: 1640/531, loss: 0.004219456110149622
2023-01-24 08:38:07.080403: step: 1644/531, loss: 0.003980959299951792
2023-01-24 08:38:08.131415: step: 1648/531, loss: 0.0028800093568861485
2023-01-24 08:38:09.183786: step: 1652/531, loss: 5.2026498451596126e-05
2023-01-24 08:38:10.250921: step: 1656/531, loss: 0.005431903060525656
2023-01-24 08:38:11.313781: step: 1660/531, loss: 0.0066912793554365635
2023-01-24 08:38:12.391549: step: 1664/531, loss: 0.006996945012360811
2023-01-24 08:38:13.452916: step: 1668/531, loss: 0.004999788478016853
2023-01-24 08:38:14.510376: step: 1672/531, loss: 0.0009596017189323902
2023-01-24 08:38:15.557338: step: 1676/531, loss: 0.0007917137118056417
2023-01-24 08:38:16.599045: step: 1680/531, loss: 0.001373159233480692
2023-01-24 08:38:17.661593: step: 1684/531, loss: 0.00048797804629430175
2023-01-24 08:38:18.715814: step: 1688/531, loss: 0.000255568913416937
2023-01-24 08:38:19.768295: step: 1692/531, loss: 0.00018379483663011342
2023-01-24 08:38:20.841165: step: 1696/531, loss: 0.0030112704262137413
2023-01-24 08:38:21.904384: step: 1700/531, loss: 0.00014690367970615625
2023-01-24 08:38:22.967258: step: 1704/531, loss: 0.00441074138507247
2023-01-24 08:38:24.020967: step: 1708/531, loss: 0.0007090168655849993
2023-01-24 08:38:25.083935: step: 1712/531, loss: 0.005016597453504801
2023-01-24 08:38:26.132474: step: 1716/531, loss: 0.003971371799707413
2023-01-24 08:38:27.198946: step: 1720/531, loss: 0.0005290894187055528
2023-01-24 08:38:28.242632: step: 1724/531, loss: 0.003302742727100849
2023-01-24 08:38:29.306219: step: 1728/531, loss: 0.003913096617907286
2023-01-24 08:38:30.384272: step: 1732/531, loss: 0.0011660200543701649
2023-01-24 08:38:31.436771: step: 1736/531, loss: 0.0008671550313010812
2023-01-24 08:38:32.491406: step: 1740/531, loss: 0.00204609171487391
2023-01-24 08:38:33.569264: step: 1744/531, loss: 0.00020118526299484074
2023-01-24 08:38:34.609831: step: 1748/531, loss: 0.006373061332851648
2023-01-24 08:38:35.679818: step: 1752/531, loss: 0.0031337805557996035
2023-01-24 08:38:36.727340: step: 1756/531, loss: 5.2260995289543644e-05
2023-01-24 08:38:37.779647: step: 1760/531, loss: 0.0007659198599867523
2023-01-24 08:38:38.844352: step: 1764/531, loss: 4.83723524666857e-05
2023-01-24 08:38:39.902407: step: 1768/531, loss: 0.0017845489783212543
2023-01-24 08:38:40.968659: step: 1772/531, loss: 6.029046744515654e-06
2023-01-24 08:38:42.010842: step: 1776/531, loss: 0.008418998681008816
2023-01-24 08:38:43.073932: step: 1780/531, loss: 0.006016191560775042
2023-01-24 08:38:44.136480: step: 1784/531, loss: 8.963803338701837e-06
2023-01-24 08:38:45.185948: step: 1788/531, loss: 0.003902255091816187
2023-01-24 08:38:46.237238: step: 1792/531, loss: 0.00015019219426903874
2023-01-24 08:38:47.306014: step: 1796/531, loss: 0.00860699824988842
2023-01-24 08:38:48.395394: step: 1800/531, loss: 0.0018698297208175063
2023-01-24 08:38:49.448850: step: 1804/531, loss: 0.003223733976483345
2023-01-24 08:38:50.520237: step: 1808/531, loss: 0.01708688586950302
2023-01-24 08:38:51.583224: step: 1812/531, loss: 0.005929495207965374
2023-01-24 08:38:52.657917: step: 1816/531, loss: 0.00023376382887363434
2023-01-24 08:38:53.729273: step: 1820/531, loss: 0.020254552364349365
2023-01-24 08:38:54.819755: step: 1824/531, loss: 0.0026953064370900393
2023-01-24 08:38:55.876266: step: 1828/531, loss: 0.00672599533572793
2023-01-24 08:38:56.969327: step: 1832/531, loss: 0.006798403803259134
2023-01-24 08:38:58.028753: step: 1836/531, loss: 0.003984320443123579
2023-01-24 08:38:59.087094: step: 1840/531, loss: 0.003288338892161846
2023-01-24 08:39:00.138534: step: 1844/531, loss: 0.003636469366028905
2023-01-24 08:39:01.232717: step: 1848/531, loss: 0.00671724509447813
2023-01-24 08:39:02.291089: step: 1852/531, loss: 0.00036437358357943594
2023-01-24 08:39:03.339822: step: 1856/531, loss: 1.495458036515629e-05
2023-01-24 08:39:04.396949: step: 1860/531, loss: 0.00010102773376274854
2023-01-24 08:39:05.463067: step: 1864/531, loss: 0.0037178967613726854
2023-01-24 08:39:06.509218: step: 1868/531, loss: 0.005754513666033745
2023-01-24 08:39:07.551174: step: 1872/531, loss: 0.03755314275622368
2023-01-24 08:39:08.616802: step: 1876/531, loss: 0.0035454800818115473
2023-01-24 08:39:09.663662: step: 1880/531, loss: 0.005830982234328985
2023-01-24 08:39:10.710070: step: 1884/531, loss: 0.008748526684939861
2023-01-24 08:39:11.763919: step: 1888/531, loss: 0.002525359159335494
2023-01-24 08:39:12.831235: step: 1892/531, loss: 0.008077842183411121
2023-01-24 08:39:13.900901: step: 1896/531, loss: 6.24095082457643e-06
2023-01-24 08:39:14.966402: step: 1900/531, loss: 0.0019070765702053905
2023-01-24 08:39:16.020511: step: 1904/531, loss: 3.677227482512535e-07
2023-01-24 08:39:17.085850: step: 1908/531, loss: 0.0010879384353756905
2023-01-24 08:39:18.143400: step: 1912/531, loss: 0.007038034964352846
2023-01-24 08:39:19.196366: step: 1916/531, loss: 0.002885445486754179
2023-01-24 08:39:20.264579: step: 1920/531, loss: 0.0034756995737552643
2023-01-24 08:39:21.329002: step: 1924/531, loss: 0.00026293564587831497
2023-01-24 08:39:22.380758: step: 1928/531, loss: 0.002439383650198579
2023-01-24 08:39:23.443441: step: 1932/531, loss: 2.792055056488607e-05
2023-01-24 08:39:24.488832: step: 1936/531, loss: 7.744190224912018e-05
2023-01-24 08:39:25.565603: step: 1940/531, loss: 0.002347267000004649
2023-01-24 08:39:26.660100: step: 1944/531, loss: 0.002145696897059679
2023-01-24 08:39:27.751014: step: 1948/531, loss: 0.007006294559687376
2023-01-24 08:39:28.806435: step: 1952/531, loss: 0.0007536351913586259
2023-01-24 08:39:29.866605: step: 1956/531, loss: 0.0014195183757692575
2023-01-24 08:39:30.935847: step: 1960/531, loss: 0.0005646995850838721
2023-01-24 08:39:31.988743: step: 1964/531, loss: 0.0011817436898127198
2023-01-24 08:39:33.042440: step: 1968/531, loss: 0.0009935875423252583
2023-01-24 08:39:34.091073: step: 1972/531, loss: 0.0005446636932902038
2023-01-24 08:39:35.161818: step: 1976/531, loss: 0.0005326094687916338
2023-01-24 08:39:36.216393: step: 1980/531, loss: 6.404858140740544e-05
2023-01-24 08:39:37.312079: step: 1984/531, loss: 0.000803306931629777
2023-01-24 08:39:38.366864: step: 1988/531, loss: 0.004085606895387173
2023-01-24 08:39:39.433136: step: 1992/531, loss: 0.0005840605590492487
2023-01-24 08:39:40.500116: step: 1996/531, loss: 0.0078003243543207645
2023-01-24 08:39:41.540789: step: 2000/531, loss: 0.001434163423255086
2023-01-24 08:39:42.586859: step: 2004/531, loss: 0.0016677728854119778
2023-01-24 08:39:43.651345: step: 2008/531, loss: 0.0044198608957231045
2023-01-24 08:39:44.707941: step: 2012/531, loss: 0.003359207883477211
2023-01-24 08:39:45.755048: step: 2016/531, loss: 0.004193820990622044
2023-01-24 08:39:46.814748: step: 2020/531, loss: 0.0036032337229698896
2023-01-24 08:39:47.879959: step: 2024/531, loss: 0.0016510685672983527
2023-01-24 08:39:48.942709: step: 2028/531, loss: 0.003847442101687193
2023-01-24 08:39:49.990549: step: 2032/531, loss: 0.004811007529497147
2023-01-24 08:39:51.046894: step: 2036/531, loss: 0.00699926121160388
2023-01-24 08:39:52.113075: step: 2040/531, loss: 0.0004596064973156899
2023-01-24 08:39:53.157119: step: 2044/531, loss: 0.0027884547598659992
2023-01-24 08:39:54.201774: step: 2048/531, loss: 0.00021353489137254655
2023-01-24 08:39:55.246839: step: 2052/531, loss: 0.0006405066815204918
2023-01-24 08:39:56.309697: step: 2056/531, loss: 0.0036231086123734713
2023-01-24 08:39:57.365303: step: 2060/531, loss: 0.0025239442475140095
2023-01-24 08:39:58.434219: step: 2064/531, loss: 0.01017787680029869
2023-01-24 08:39:59.477579: step: 2068/531, loss: 0.0019906111992895603
2023-01-24 08:40:00.550900: step: 2072/531, loss: 0.000426443584728986
2023-01-24 08:40:01.618823: step: 2076/531, loss: 0.0021929400973021984
2023-01-24 08:40:02.666299: step: 2080/531, loss: 0.0
2023-01-24 08:40:03.746780: step: 2084/531, loss: 0.004055523779243231
2023-01-24 08:40:04.810327: step: 2088/531, loss: 0.0006808657199144363
2023-01-24 08:40:05.874205: step: 2092/531, loss: 0.0009017421980388463
2023-01-24 08:40:06.930593: step: 2096/531, loss: 1.2260234143468551e-05
2023-01-24 08:40:07.988588: step: 2100/531, loss: 1.0708765330491588e-05
2023-01-24 08:40:09.041477: step: 2104/531, loss: 0.0004936104523949325
2023-01-24 08:40:10.086540: step: 2108/531, loss: 0.012104598805308342
2023-01-24 08:40:11.150297: step: 2112/531, loss: 0.0006459844880737364
2023-01-24 08:40:12.213738: step: 2116/531, loss: 0.005747909191995859
2023-01-24 08:40:13.260643: step: 2120/531, loss: 0.004473009146749973
2023-01-24 08:40:14.320845: step: 2124/531, loss: 0.0013793382095173001
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.39468198150566325, 'r': 0.32278545356535265, 'f1': 0.35513138628171365}, 'combined': 0.2616757583128416, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3870160701522917, 'r': 0.27394735353430927, 'f1': 0.32081057557502535}, 'combined': 0.20088138844417477, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3780164324072552, 'r': 0.3399995995465635, 'f1': 0.3580015763457322}, 'combined': 0.26379063520211843, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3887412172404603, 'r': 0.28638554958111456, 'f1': 0.329804334875863}, 'combined': 0.20438578499349255, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36985126195712753, 'r': 0.329848374041461, 'f1': 0.3487063051551654}, 'combined': 0.2569414880090692, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41099848924524246, 'r': 0.28536414492230544, 'f1': 0.3368481497805606}, 'combined': 0.22345372312175804, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 16}
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, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 17
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:42:38.385877: step: 4/531, loss: 0.0010591301834210753
2023-01-24 08:42:39.431177: step: 8/531, loss: 0.014781218022108078
2023-01-24 08:42:40.473623: step: 12/531, loss: 0.0037061702460050583
2023-01-24 08:42:41.524218: step: 16/531, loss: 0.00033428677124902606
2023-01-24 08:42:42.590245: step: 20/531, loss: 8.860175148583949e-05
2023-01-24 08:42:43.645169: step: 24/531, loss: 0.006528640631586313
2023-01-24 08:42:44.704144: step: 28/531, loss: 0.005082056857645512
2023-01-24 08:42:45.755474: step: 32/531, loss: 0.0007815062417648733
2023-01-24 08:42:46.816545: step: 36/531, loss: 0.001364995026960969
2023-01-24 08:42:47.868027: step: 40/531, loss: 0.00395982526242733
2023-01-24 08:42:48.908319: step: 44/531, loss: 0.013364103622734547
2023-01-24 08:42:49.970561: step: 48/531, loss: 0.0017849599244073033
2023-01-24 08:42:51.028513: step: 52/531, loss: 0.0034796802792698145
2023-01-24 08:42:52.058953: step: 56/531, loss: 0.005245598498731852
2023-01-24 08:42:53.099194: step: 60/531, loss: 6.323427805909887e-05
2023-01-24 08:42:54.132789: step: 64/531, loss: 0.00051159190479666
2023-01-24 08:42:55.194783: step: 68/531, loss: 0.003531547263264656
2023-01-24 08:42:56.254330: step: 72/531, loss: 0.0010178668890148401
2023-01-24 08:42:57.297068: step: 76/531, loss: 0.002235204679891467
2023-01-24 08:42:58.363153: step: 80/531, loss: 0.0058624702505767345
2023-01-24 08:42:59.415646: step: 84/531, loss: 0.00028773743542842567
2023-01-24 08:43:00.458442: step: 88/531, loss: 0.00022078095935285091
2023-01-24 08:43:01.513183: step: 92/531, loss: 7.382411422440782e-05
2023-01-24 08:43:02.560364: step: 96/531, loss: 2.302437678736169e-05
2023-01-24 08:43:03.608573: step: 100/531, loss: 0.0005729347467422485
2023-01-24 08:43:04.664061: step: 104/531, loss: 0.0008002286776900291
2023-01-24 08:43:05.735691: step: 108/531, loss: 0.00018516951240599155
2023-01-24 08:43:06.791632: step: 112/531, loss: 2.2955859094508924e-05
2023-01-24 08:43:07.857138: step: 116/531, loss: 0.00016484715160913765
2023-01-24 08:43:08.917153: step: 120/531, loss: 0.005383912939578295
2023-01-24 08:43:09.989327: step: 124/531, loss: 0.007578098215162754
2023-01-24 08:43:11.042562: step: 128/531, loss: 0.005913260392844677
2023-01-24 08:43:12.107818: step: 132/531, loss: 0.0038971109315752983
2023-01-24 08:43:13.168197: step: 136/531, loss: 1.3455038242682349e-05
2023-01-24 08:43:14.218293: step: 140/531, loss: 0.005872782319784164
2023-01-24 08:43:15.269940: step: 144/531, loss: 0.0017661303281784058
2023-01-24 08:43:16.334375: step: 148/531, loss: 0.008567708544433117
2023-01-24 08:43:17.371645: step: 152/531, loss: 0.0009409493650309741
2023-01-24 08:43:18.435051: step: 156/531, loss: 0.00018545141210779548
2023-01-24 08:43:19.485355: step: 160/531, loss: 3.97282638004981e-05
2023-01-24 08:43:20.560866: step: 164/531, loss: 0.001125269802287221
2023-01-24 08:43:21.624075: step: 168/531, loss: 2.6217414870188804e-06
2023-01-24 08:43:22.667420: step: 172/531, loss: 0.0012865333119407296
2023-01-24 08:43:23.720485: step: 176/531, loss: 5.930763654760085e-05
2023-01-24 08:43:24.777846: step: 180/531, loss: 0.004098004661500454
2023-01-24 08:43:25.832669: step: 184/531, loss: 0.0023150916676968336
2023-01-24 08:43:26.875317: step: 188/531, loss: 0.002951332600787282
2023-01-24 08:43:27.939906: step: 192/531, loss: 0.002031816868111491
2023-01-24 08:43:28.993171: step: 196/531, loss: 0.0015997339505702257
2023-01-24 08:43:30.053879: step: 200/531, loss: 5.237978712102631e-06
2023-01-24 08:43:31.107034: step: 204/531, loss: 0.006756736896932125
2023-01-24 08:43:32.163122: step: 208/531, loss: 6.461319117079256e-06
2023-01-24 08:43:33.238028: step: 212/531, loss: 0.000697409559506923
2023-01-24 08:43:34.291618: step: 216/531, loss: 0.00254813302308321
2023-01-24 08:43:35.348897: step: 220/531, loss: 0.004089620895683765
2023-01-24 08:43:36.404655: step: 224/531, loss: 0.002317257924005389
2023-01-24 08:43:37.461939: step: 228/531, loss: 0.00019191388855688274
2023-01-24 08:43:38.514058: step: 232/531, loss: 0.00041288428474217653
2023-01-24 08:43:39.573703: step: 236/531, loss: 0.0018394957296550274
2023-01-24 08:43:40.624420: step: 240/531, loss: 0.00012980592146050185
2023-01-24 08:43:41.680998: step: 244/531, loss: 0.00034726655576378107
2023-01-24 08:43:42.731833: step: 248/531, loss: 5.330373460310511e-05
2023-01-24 08:43:43.779978: step: 252/531, loss: 4.238435394654516e-06
2023-01-24 08:43:44.837974: step: 256/531, loss: 0.00018782711413223296
2023-01-24 08:43:45.900186: step: 260/531, loss: 0.0013384897029027343
2023-01-24 08:43:46.951941: step: 264/531, loss: 0.0008462652913294733
2023-01-24 08:43:48.002554: step: 268/531, loss: 0.0019726683385670185
2023-01-24 08:43:49.057425: step: 272/531, loss: 0.001999210799112916
2023-01-24 08:43:50.118863: step: 276/531, loss: 0.00041788246016949415
2023-01-24 08:43:51.195509: step: 280/531, loss: 0.0046173399314284325
2023-01-24 08:43:52.257129: step: 284/531, loss: 0.0006525160279124975
2023-01-24 08:43:53.308744: step: 288/531, loss: 7.261510472744703e-05
2023-01-24 08:43:54.354374: step: 292/531, loss: 0.0013442516792565584
2023-01-24 08:43:55.414697: step: 296/531, loss: 0.008767567574977875
2023-01-24 08:43:56.466459: step: 300/531, loss: 0.005095435306429863
2023-01-24 08:43:57.522125: step: 304/531, loss: 0.0008047689334489405
2023-01-24 08:43:58.574986: step: 308/531, loss: 0.0030603145714849234
2023-01-24 08:43:59.626303: step: 312/531, loss: 0.0006080297753214836
2023-01-24 08:44:00.693513: step: 316/531, loss: 0.0040301172994077206
2023-01-24 08:44:01.769758: step: 320/531, loss: 2.628640459079179e-06
2023-01-24 08:44:02.839109: step: 324/531, loss: 0.012205506674945354
2023-01-24 08:44:03.908530: step: 328/531, loss: 0.003325662575662136
2023-01-24 08:44:04.967889: step: 332/531, loss: 0.004738849587738514
2023-01-24 08:44:06.012537: step: 336/531, loss: 0.0007261703722178936
2023-01-24 08:44:07.061298: step: 340/531, loss: 0.00019172353495378047
2023-01-24 08:44:08.119044: step: 344/531, loss: 0.0014166636392474174
2023-01-24 08:44:09.174416: step: 348/531, loss: 0.0003064592892769724
2023-01-24 08:44:10.227218: step: 352/531, loss: 0.0018100740853697062
2023-01-24 08:44:11.294412: step: 356/531, loss: 0.00027037030667997897
2023-01-24 08:44:12.366579: step: 360/531, loss: 0.00015691015869379044
2023-01-24 08:44:13.429913: step: 364/531, loss: 0.0006983047351241112
2023-01-24 08:44:14.482224: step: 368/531, loss: 0.0022426953073590994
2023-01-24 08:44:15.534997: step: 372/531, loss: 0.0006167655810713768
2023-01-24 08:44:16.588340: step: 376/531, loss: 0.0004734009853564203
2023-01-24 08:44:17.654822: step: 380/531, loss: 0.0001547702559037134
2023-01-24 08:44:18.721610: step: 384/531, loss: 0.00038646493339911103
2023-01-24 08:44:19.780237: step: 388/531, loss: 0.002265315502882004
2023-01-24 08:44:20.844164: step: 392/531, loss: 0.002514406805858016
2023-01-24 08:44:21.891082: step: 396/531, loss: 0.0005918876267969608
2023-01-24 08:44:22.944004: step: 400/531, loss: 0.006264612544327974
2023-01-24 08:44:24.008529: step: 404/531, loss: 0.00033855895162560046
2023-01-24 08:44:25.064779: step: 408/531, loss: 9.501646854914725e-05
2023-01-24 08:44:26.114009: step: 412/531, loss: 0.003078275825828314
2023-01-24 08:44:27.169189: step: 416/531, loss: 7.965124677866697e-05
2023-01-24 08:44:28.225131: step: 420/531, loss: 0.0005357344634830952
2023-01-24 08:44:29.287134: step: 424/531, loss: 0.0023287509102374315
2023-01-24 08:44:30.359941: step: 428/531, loss: 0.0021544082555919886
2023-01-24 08:44:31.427723: step: 432/531, loss: 0.004816059954464436
2023-01-24 08:44:32.485935: step: 436/531, loss: 0.00020005705300718546
2023-01-24 08:44:33.536479: step: 440/531, loss: 0.00018254034512210637
2023-01-24 08:44:34.611962: step: 444/531, loss: 0.000611867755651474
2023-01-24 08:44:35.678938: step: 448/531, loss: 7.335914415307343e-05
2023-01-24 08:44:36.744842: step: 452/531, loss: 0.004518484231084585
2023-01-24 08:44:37.813321: step: 456/531, loss: 0.005140627268701792
2023-01-24 08:44:38.869603: step: 460/531, loss: 0.0006301365210674703
2023-01-24 08:44:39.923415: step: 464/531, loss: 0.0021027002949267626
2023-01-24 08:44:40.985779: step: 468/531, loss: 5.8715468185255304e-05
2023-01-24 08:44:42.071002: step: 472/531, loss: 0.003164167981594801
2023-01-24 08:44:43.121777: step: 476/531, loss: 0.009007076732814312
2023-01-24 08:44:44.174058: step: 480/531, loss: 0.005488893948495388
2023-01-24 08:44:45.235535: step: 484/531, loss: 0.0013162342365831137
2023-01-24 08:44:46.281012: step: 488/531, loss: 0.004377539269626141
2023-01-24 08:44:47.350942: step: 492/531, loss: 0.0013336186530068517
2023-01-24 08:44:48.413389: step: 496/531, loss: 8.922337656258605e-06
2023-01-24 08:44:49.497919: step: 500/531, loss: 0.006440530996769667
2023-01-24 08:44:50.560055: step: 504/531, loss: 0.002337603596970439
2023-01-24 08:44:51.621138: step: 508/531, loss: 0.004704826977103949
2023-01-24 08:44:52.679445: step: 512/531, loss: 2.3259861336555332e-05
2023-01-24 08:44:53.740957: step: 516/531, loss: 0.0009793529752641916
2023-01-24 08:44:54.791284: step: 520/531, loss: 0.006845055613666773
2023-01-24 08:44:55.852945: step: 524/531, loss: 0.0041955867782235146
2023-01-24 08:44:56.905909: step: 528/531, loss: 0.0019427043152973056
2023-01-24 08:44:57.962244: step: 532/531, loss: 0.002804335905238986
2023-01-24 08:44:59.025974: step: 536/531, loss: 1.0511784239497501e-05
2023-01-24 08:45:00.089466: step: 540/531, loss: 0.001268138294108212
2023-01-24 08:45:01.151278: step: 544/531, loss: 0.001591818523593247
2023-01-24 08:45:02.218006: step: 548/531, loss: 0.00017964364087674767
2023-01-24 08:45:03.292363: step: 552/531, loss: 0.007876533083617687
2023-01-24 08:45:04.367909: step: 556/531, loss: 0.001596052898094058
2023-01-24 08:45:05.440154: step: 560/531, loss: 0.006762867793440819
2023-01-24 08:45:06.489948: step: 564/531, loss: 0.00028747261967509985
2023-01-24 08:45:07.552412: step: 568/531, loss: 0.003805815242230892
2023-01-24 08:45:08.603177: step: 572/531, loss: 2.2555337636731565e-05
2023-01-24 08:45:09.656457: step: 576/531, loss: 0.0032091541215777397
2023-01-24 08:45:10.732462: step: 580/531, loss: 0.0006547679658979177
2023-01-24 08:45:11.801281: step: 584/531, loss: 0.005057461094111204
2023-01-24 08:45:12.853589: step: 588/531, loss: 0.0010434415889903903
2023-01-24 08:45:13.911269: step: 592/531, loss: 1.3075495530756598e-07
2023-01-24 08:45:14.971711: step: 596/531, loss: 0.0004937549238093197
2023-01-24 08:45:16.027567: step: 600/531, loss: 0.007920471951365471
2023-01-24 08:45:17.074106: step: 604/531, loss: 0.0018424766603857279
2023-01-24 08:45:18.120998: step: 608/531, loss: 0.00020057539222761989
2023-01-24 08:45:19.209326: step: 612/531, loss: 0.006189912557601929
2023-01-24 08:45:20.274859: step: 616/531, loss: 0.000951491529121995
2023-01-24 08:45:21.346511: step: 620/531, loss: 0.00013815052807331085
2023-01-24 08:45:22.405699: step: 624/531, loss: 0.012013589963316917
2023-01-24 08:45:23.455489: step: 628/531, loss: 0.000238620035815984
2023-01-24 08:45:24.537470: step: 632/531, loss: 0.001472893520258367
2023-01-24 08:45:25.592944: step: 636/531, loss: 3.199533966835588e-05
2023-01-24 08:45:26.654987: step: 640/531, loss: 0.003311782842501998
2023-01-24 08:45:27.709411: step: 644/531, loss: 1.7413856767234392e-05
2023-01-24 08:45:28.757376: step: 648/531, loss: 0.0
2023-01-24 08:45:29.834910: step: 652/531, loss: 0.0005648055230267346
2023-01-24 08:45:30.908049: step: 656/531, loss: 0.00041577249066904187
2023-01-24 08:45:31.956683: step: 660/531, loss: 0.0005932781496085227
2023-01-24 08:45:33.009058: step: 664/531, loss: 3.1131337891565636e-05
2023-01-24 08:45:34.066753: step: 668/531, loss: 0.0016683556605130434
2023-01-24 08:45:35.134803: step: 672/531, loss: 0.0008324781083501875
2023-01-24 08:45:36.189394: step: 676/531, loss: 0.0015998296439647675
2023-01-24 08:45:37.263916: step: 680/531, loss: 0.0010401420295238495
2023-01-24 08:45:38.337079: step: 684/531, loss: 0.00021410842600744218
2023-01-24 08:45:39.412885: step: 688/531, loss: 0.00986777525395155
2023-01-24 08:45:40.468798: step: 692/531, loss: 0.005428651813417673
2023-01-24 08:45:41.525216: step: 696/531, loss: 0.0026745384093374014
2023-01-24 08:45:42.599444: step: 700/531, loss: 8.789300773059949e-05
2023-01-24 08:45:43.660082: step: 704/531, loss: 0.0013627734733745456
2023-01-24 08:45:44.735972: step: 708/531, loss: 0.006983757484704256
2023-01-24 08:45:45.790544: step: 712/531, loss: 0.00024586988729424775
2023-01-24 08:45:46.871536: step: 716/531, loss: 0.006869173143059015
2023-01-24 08:45:47.936564: step: 720/531, loss: 0.00016961278743110597
2023-01-24 08:45:48.991016: step: 724/531, loss: 0.007143969181925058
2023-01-24 08:45:50.056120: step: 728/531, loss: 0.011537830345332623
2023-01-24 08:45:51.121858: step: 732/531, loss: 0.0002902477281168103
2023-01-24 08:45:52.197358: step: 736/531, loss: 0.006546034477651119
2023-01-24 08:45:53.265178: step: 740/531, loss: 6.851474608993158e-05
2023-01-24 08:45:54.322964: step: 744/531, loss: 0.004820783622562885
2023-01-24 08:45:55.377022: step: 748/531, loss: 4.584113048622385e-05
2023-01-24 08:45:56.422085: step: 752/531, loss: 0.003378402441740036
2023-01-24 08:45:57.483343: step: 756/531, loss: 0.011286232620477676
2023-01-24 08:45:58.539128: step: 760/531, loss: 0.002090710448101163
2023-01-24 08:45:59.579405: step: 764/531, loss: 3.3444015571149066e-05
2023-01-24 08:46:00.662572: step: 768/531, loss: 0.0006884770118631423
2023-01-24 08:46:01.722948: step: 772/531, loss: 0.00045069732004776597
2023-01-24 08:46:02.764705: step: 776/531, loss: 0.0007072472362779081
2023-01-24 08:46:03.838236: step: 780/531, loss: 0.0020578026305884123
2023-01-24 08:46:04.896321: step: 784/531, loss: 0.0006573524442501366
2023-01-24 08:46:05.964978: step: 788/531, loss: 0.023261716589331627
2023-01-24 08:46:07.017533: step: 792/531, loss: 1.0141192433366086e-05
2023-01-24 08:46:08.083235: step: 796/531, loss: 0.002168754581362009
2023-01-24 08:46:09.151945: step: 800/531, loss: 0.001569385640323162
2023-01-24 08:46:10.221649: step: 804/531, loss: 3.9136025407060515e-06
2023-01-24 08:46:11.278304: step: 808/531, loss: 0.0002535523963160813
2023-01-24 08:46:12.358368: step: 812/531, loss: 2.527751712477766e-05
2023-01-24 08:46:13.429963: step: 816/531, loss: 0.0003287234576418996
2023-01-24 08:46:14.489822: step: 820/531, loss: 0.0002072100032819435
2023-01-24 08:46:15.549543: step: 824/531, loss: 0.00023947506269905716
2023-01-24 08:46:16.612611: step: 828/531, loss: 0.0010242847492918372
2023-01-24 08:46:17.680275: step: 832/531, loss: 0.0020955665968358517
2023-01-24 08:46:18.737626: step: 836/531, loss: 0.0007789822411723435
2023-01-24 08:46:19.814679: step: 840/531, loss: 0.0031239890959113836
2023-01-24 08:46:20.877383: step: 844/531, loss: 0.002139681950211525
2023-01-24 08:46:21.933753: step: 848/531, loss: 0.00010103691602125764
2023-01-24 08:46:22.992699: step: 852/531, loss: 0.0023629390634596348
2023-01-24 08:46:24.069444: step: 856/531, loss: 0.003942996263504028
2023-01-24 08:46:25.135868: step: 860/531, loss: 0.0017932187765836716
2023-01-24 08:46:26.209050: step: 864/531, loss: 0.010287689976394176
2023-01-24 08:46:27.268101: step: 868/531, loss: 0.00614097248762846
2023-01-24 08:46:28.342414: step: 872/531, loss: 0.0024153664708137512
2023-01-24 08:46:29.413462: step: 876/531, loss: 0.002685698913410306
2023-01-24 08:46:30.476866: step: 880/531, loss: 0.004279584623873234
2023-01-24 08:46:31.534975: step: 884/531, loss: 0.0036086956970393658
2023-01-24 08:46:32.613185: step: 888/531, loss: 0.0007581334211863577
2023-01-24 08:46:33.684380: step: 892/531, loss: 0.008575083687901497
2023-01-24 08:46:34.755032: step: 896/531, loss: 0.005085669457912445
2023-01-24 08:46:35.818916: step: 900/531, loss: 0.00022220025130081922
2023-01-24 08:46:36.897664: step: 904/531, loss: 0.00014551023195963353
2023-01-24 08:46:37.952549: step: 908/531, loss: 0.0007867612293921411
2023-01-24 08:46:39.027706: step: 912/531, loss: 0.0005422435933724046
2023-01-24 08:46:40.095707: step: 916/531, loss: 0.006346079055219889
2023-01-24 08:46:41.153084: step: 920/531, loss: 0.0014782777288928628
2023-01-24 08:46:42.222321: step: 924/531, loss: 0.0008234384004026651
2023-01-24 08:46:43.275367: step: 928/531, loss: 5.163700507182512e-07
2023-01-24 08:46:44.347841: step: 932/531, loss: 0.0005923594580963254
2023-01-24 08:46:45.415018: step: 936/531, loss: 0.0009426764445379376
2023-01-24 08:46:46.457693: step: 940/531, loss: 9.509312076261267e-05
2023-01-24 08:46:47.518481: step: 944/531, loss: 0.003369776299223304
2023-01-24 08:46:48.590501: step: 948/531, loss: 0.0003580296761356294
2023-01-24 08:46:49.636419: step: 952/531, loss: 6.050045703887008e-05
2023-01-24 08:46:50.709084: step: 956/531, loss: 0.004939751233905554
2023-01-24 08:46:51.771841: step: 960/531, loss: 0.00016296881949529052
2023-01-24 08:46:52.838497: step: 964/531, loss: 0.010895533487200737
2023-01-24 08:46:53.914438: step: 968/531, loss: 0.009111028164625168
2023-01-24 08:46:54.977329: step: 972/531, loss: 0.003915261011570692
2023-01-24 08:46:56.044758: step: 976/531, loss: 0.0006893750978633761
2023-01-24 08:46:57.105694: step: 980/531, loss: 0.0008727729436941445
2023-01-24 08:46:58.160279: step: 984/531, loss: 0.002139232587069273
2023-01-24 08:46:59.225233: step: 988/531, loss: 0.0003349109028931707
2023-01-24 08:47:00.284508: step: 992/531, loss: 0.0036862508859485388
2023-01-24 08:47:01.350766: step: 996/531, loss: 0.0015776100335642695
2023-01-24 08:47:02.408472: step: 1000/531, loss: 0.0007878416799940169
2023-01-24 08:47:03.456550: step: 1004/531, loss: 7.109108992153779e-05
2023-01-24 08:47:04.508909: step: 1008/531, loss: 0.0038698548451066017
2023-01-24 08:47:05.558514: step: 1012/531, loss: 0.014222804456949234
2023-01-24 08:47:06.627452: step: 1016/531, loss: 0.017534222453832626
2023-01-24 08:47:07.693617: step: 1020/531, loss: 0.0025508874095976353
2023-01-24 08:47:08.758650: step: 1024/531, loss: 0.004525311756879091
2023-01-24 08:47:09.832972: step: 1028/531, loss: 0.01276471372693777
2023-01-24 08:47:10.887918: step: 1032/531, loss: 0.00013596868666354567
2023-01-24 08:47:11.940609: step: 1036/531, loss: 0.0001314611581619829
2023-01-24 08:47:13.001823: step: 1040/531, loss: 0.0049752178601920605
2023-01-24 08:47:14.071392: step: 1044/531, loss: 0.0010042430367320776
2023-01-24 08:47:15.148776: step: 1048/531, loss: 0.011717608198523521
2023-01-24 08:47:16.210070: step: 1052/531, loss: 0.0063424925319850445
2023-01-24 08:47:17.272461: step: 1056/531, loss: 0.0028261584229767323
2023-01-24 08:47:18.334618: step: 1060/531, loss: 0.0006312905461527407
2023-01-24 08:47:19.394793: step: 1064/531, loss: 0.0006985447253100574
2023-01-24 08:47:20.453103: step: 1068/531, loss: 8.053990313783288e-06
2023-01-24 08:47:21.513642: step: 1072/531, loss: 0.00010158088116440922
2023-01-24 08:47:22.582517: step: 1076/531, loss: 0.0014032371109351516
2023-01-24 08:47:23.636254: step: 1080/531, loss: 0.0017378615448251367
2023-01-24 08:47:24.700838: step: 1084/531, loss: 0.001124097965657711
2023-01-24 08:47:25.749759: step: 1088/531, loss: 4.155989245191449e-06
2023-01-24 08:47:26.821854: step: 1092/531, loss: 0.004896112252026796
2023-01-24 08:47:27.889366: step: 1096/531, loss: 0.0030176760628819466
2023-01-24 08:47:28.980835: step: 1100/531, loss: 9.037006384460256e-05
2023-01-24 08:47:30.043998: step: 1104/531, loss: 0.0010507587576285005
2023-01-24 08:47:31.115277: step: 1108/531, loss: 0.0016560732619836926
2023-01-24 08:47:32.176545: step: 1112/531, loss: 4.4967466237721965e-05
2023-01-24 08:47:33.231142: step: 1116/531, loss: 0.015512155368924141
2023-01-24 08:47:34.297384: step: 1120/531, loss: 0.013124290853738785
2023-01-24 08:47:35.347154: step: 1124/531, loss: 0.0028140032663941383
2023-01-24 08:47:36.413709: step: 1128/531, loss: 0.003043188713490963
2023-01-24 08:47:37.489427: step: 1132/531, loss: 0.009081898257136345
2023-01-24 08:47:38.553803: step: 1136/531, loss: 3.626557008828968e-05
2023-01-24 08:47:39.614522: step: 1140/531, loss: 0.011086744256317616
2023-01-24 08:47:40.678222: step: 1144/531, loss: 0.002954406663775444
2023-01-24 08:47:41.732153: step: 1148/531, loss: 2.356210461584851e-05
2023-01-24 08:47:42.829828: step: 1152/531, loss: 0.004788017366081476
2023-01-24 08:47:43.892834: step: 1156/531, loss: 0.006939814891666174
2023-01-24 08:47:44.954954: step: 1160/531, loss: 0.001125428476370871
2023-01-24 08:47:46.029281: step: 1164/531, loss: 0.004942075349390507
2023-01-24 08:47:47.084251: step: 1168/531, loss: 0.0008772382861934602
2023-01-24 08:47:48.141520: step: 1172/531, loss: 0.0013258844846859574
2023-01-24 08:47:49.213737: step: 1176/531, loss: 0.00739274499937892
2023-01-24 08:47:50.280156: step: 1180/531, loss: 0.0014582430012524128
2023-01-24 08:47:51.331796: step: 1184/531, loss: 0.0005501639097929001
2023-01-24 08:47:52.388234: step: 1188/531, loss: 0.0016470944974571466
2023-01-24 08:47:53.447495: step: 1192/531, loss: 0.0017556428210809827
2023-01-24 08:47:54.507877: step: 1196/531, loss: 0.004391124937683344
2023-01-24 08:47:55.560764: step: 1200/531, loss: 0.0006489954539574683
2023-01-24 08:47:56.642347: step: 1204/531, loss: 0.0007281933794729412
2023-01-24 08:47:57.697279: step: 1208/531, loss: 0.0011890002060681581
2023-01-24 08:47:58.757196: step: 1212/531, loss: 0.0006047792849130929
2023-01-24 08:47:59.815330: step: 1216/531, loss: 0.004985279403626919
2023-01-24 08:48:00.889068: step: 1220/531, loss: 0.0004808290395885706
2023-01-24 08:48:01.970007: step: 1224/531, loss: 0.006486736703664064
2023-01-24 08:48:03.031398: step: 1228/531, loss: 0.001231358852237463
2023-01-24 08:48:04.116043: step: 1232/531, loss: 0.011270023882389069
2023-01-24 08:48:05.168279: step: 1236/531, loss: 0.0008208649232983589
2023-01-24 08:48:06.240866: step: 1240/531, loss: 0.004045217763632536
2023-01-24 08:48:07.290685: step: 1244/531, loss: 5.2749368478544056e-05
2023-01-24 08:48:08.369238: step: 1248/531, loss: 0.005218219477683306
2023-01-24 08:48:09.429132: step: 1252/531, loss: 0.002251754282042384
2023-01-24 08:48:10.480547: step: 1256/531, loss: 9.591809794073924e-05
2023-01-24 08:48:11.525847: step: 1260/531, loss: 7.123234809114365e-06
2023-01-24 08:48:12.592693: step: 1264/531, loss: 0.004032783675938845
2023-01-24 08:48:13.661370: step: 1268/531, loss: 0.000742900709155947
2023-01-24 08:48:14.713843: step: 1272/531, loss: 0.0011782868532463908
2023-01-24 08:48:15.760119: step: 1276/531, loss: 6.809475507907337e-07
2023-01-24 08:48:16.811329: step: 1280/531, loss: 7.996735803317279e-05
2023-01-24 08:48:17.851399: step: 1284/531, loss: 0.0011381471995264292
2023-01-24 08:48:18.916463: step: 1288/531, loss: 0.00548606738448143
2023-01-24 08:48:19.976914: step: 1292/531, loss: 0.0008059622487053275
2023-01-24 08:48:21.019721: step: 1296/531, loss: 0.00030760097433812916
2023-01-24 08:48:22.075189: step: 1300/531, loss: 0.004079130478203297
2023-01-24 08:48:23.123457: step: 1304/531, loss: 0.006860645953565836
2023-01-24 08:48:24.184268: step: 1308/531, loss: 9.480576181886136e-07
2023-01-24 08:48:25.246662: step: 1312/531, loss: 0.0019376041600480676
2023-01-24 08:48:26.306579: step: 1316/531, loss: 0.003845769912004471
2023-01-24 08:48:27.358408: step: 1320/531, loss: 5.221631727181375e-05
2023-01-24 08:48:28.421124: step: 1324/531, loss: 0.003528336761519313
2023-01-24 08:48:29.476457: step: 1328/531, loss: 0.00637925835326314
2023-01-24 08:48:30.538493: step: 1332/531, loss: 0.00010631334589561448
2023-01-24 08:48:31.608863: step: 1336/531, loss: 0.006522983778268099
2023-01-24 08:48:32.695380: step: 1340/531, loss: 0.00011496706429170445
2023-01-24 08:48:33.780358: step: 1344/531, loss: 0.0033556539565324783
2023-01-24 08:48:34.831228: step: 1348/531, loss: 0.00019041269843000919
2023-01-24 08:48:35.887697: step: 1352/531, loss: 0.0016024350188672543
2023-01-24 08:48:36.942576: step: 1356/531, loss: 0.0007284569437615573
2023-01-24 08:48:37.993707: step: 1360/531, loss: 0.0043895915150642395
2023-01-24 08:48:39.045020: step: 1364/531, loss: 0.0031304971780627966
2023-01-24 08:48:40.098310: step: 1368/531, loss: 0.0016167134745046496
2023-01-24 08:48:41.144943: step: 1372/531, loss: 0.0015101308235898614
2023-01-24 08:48:42.205433: step: 1376/531, loss: 0.007826688699424267
2023-01-24 08:48:43.253766: step: 1380/531, loss: 0.0007461021887138486
2023-01-24 08:48:44.320361: step: 1384/531, loss: 0.0014523325953632593
2023-01-24 08:48:45.356327: step: 1388/531, loss: 4.959692159900442e-05
2023-01-24 08:48:46.420111: step: 1392/531, loss: 0.0001512253365945071
2023-01-24 08:48:47.474785: step: 1396/531, loss: 0.0012374120997264981
2023-01-24 08:48:48.524703: step: 1400/531, loss: 0.01050270814448595
2023-01-24 08:48:49.579632: step: 1404/531, loss: 0.0031221939716488123
2023-01-24 08:48:50.636074: step: 1408/531, loss: 0.0016900835325941443
2023-01-24 08:48:51.691752: step: 1412/531, loss: 0.003941865637898445
2023-01-24 08:48:52.769801: step: 1416/531, loss: 0.00013313518138602376
2023-01-24 08:48:53.843269: step: 1420/531, loss: 0.005387207958847284
2023-01-24 08:48:54.909829: step: 1424/531, loss: 0.00913289189338684
2023-01-24 08:48:55.954667: step: 1428/531, loss: 0.060010168701410294
2023-01-24 08:48:57.036905: step: 1432/531, loss: 0.002390248468145728
2023-01-24 08:48:58.106577: step: 1436/531, loss: 4.347315552877262e-05
2023-01-24 08:48:59.168379: step: 1440/531, loss: 0.0025861372705549
2023-01-24 08:49:00.240158: step: 1444/531, loss: 0.003920883871614933
2023-01-24 08:49:01.299637: step: 1448/531, loss: 1.5943909659199562e-07
2023-01-24 08:49:02.362120: step: 1452/531, loss: 0.0035977144725620747
2023-01-24 08:49:03.433763: step: 1456/531, loss: 4.213129432173446e-05
2023-01-24 08:49:04.502043: step: 1460/531, loss: 0.0005724129732698202
2023-01-24 08:49:05.553277: step: 1464/531, loss: 0.00028577656485140324
2023-01-24 08:49:06.630984: step: 1468/531, loss: 0.0008289706311188638
2023-01-24 08:49:07.689066: step: 1472/531, loss: 0.0010570675367489457
2023-01-24 08:49:08.750839: step: 1476/531, loss: 0.0035019528586417437
2023-01-24 08:49:09.812272: step: 1480/531, loss: 0.00019357156998012215
2023-01-24 08:49:10.867202: step: 1484/531, loss: 4.4373598939273506e-05
2023-01-24 08:49:11.942522: step: 1488/531, loss: 0.0016001868061721325
2023-01-24 08:49:13.009358: step: 1492/531, loss: 0.00736919604241848
2023-01-24 08:49:14.064221: step: 1496/531, loss: 0.00026503155822865665
2023-01-24 08:49:15.128460: step: 1500/531, loss: 0.0032672889064997435
2023-01-24 08:49:16.164374: step: 1504/531, loss: 0.00042652423144318163
2023-01-24 08:49:17.229856: step: 1508/531, loss: 0.00013084665988571942
2023-01-24 08:49:18.287834: step: 1512/531, loss: 0.0016687301686033607
2023-01-24 08:49:19.341712: step: 1516/531, loss: 0.0005247325170785189
2023-01-24 08:49:20.408041: step: 1520/531, loss: 0.0005717718740925193
2023-01-24 08:49:21.448703: step: 1524/531, loss: 0.0003974206920247525
2023-01-24 08:49:22.529039: step: 1528/531, loss: 0.010677206330001354
2023-01-24 08:49:23.594987: step: 1532/531, loss: 0.0005944393342360854
2023-01-24 08:49:24.640629: step: 1536/531, loss: 0.00022962574439588934
2023-01-24 08:49:25.684065: step: 1540/531, loss: 4.392466144054197e-05
2023-01-24 08:49:26.753393: step: 1544/531, loss: 0.012663129717111588
2023-01-24 08:49:27.795952: step: 1548/531, loss: 0.0001365838834317401
2023-01-24 08:49:28.863011: step: 1552/531, loss: 0.000226149961235933
2023-01-24 08:49:29.928033: step: 1556/531, loss: 0.004185952711850405
2023-01-24 08:49:30.979776: step: 1560/531, loss: 0.0013196436921134591
2023-01-24 08:49:32.045289: step: 1564/531, loss: 0.018030652776360512
2023-01-24 08:49:33.116982: step: 1568/531, loss: 0.0003566597297322005
2023-01-24 08:49:34.175675: step: 1572/531, loss: 0.0013386617647483945
2023-01-24 08:49:35.236309: step: 1576/531, loss: 9.93379217106849e-05
2023-01-24 08:49:36.306851: step: 1580/531, loss: 0.009382509626448154
2023-01-24 08:49:37.372062: step: 1584/531, loss: 0.0003657048800960183
2023-01-24 08:49:38.429707: step: 1588/531, loss: 0.03480656072497368
2023-01-24 08:49:39.487345: step: 1592/531, loss: 0.0008531854837201536
2023-01-24 08:49:40.554076: step: 1596/531, loss: 0.00010890130943153054
2023-01-24 08:49:41.606138: step: 1600/531, loss: 0.004324667621403933
2023-01-24 08:49:42.675298: step: 1604/531, loss: 0.0058302986435592175
2023-01-24 08:49:43.740062: step: 1608/531, loss: 0.0008046038565225899
2023-01-24 08:49:44.808056: step: 1612/531, loss: 4.122814971196931e-06
2023-01-24 08:49:45.877942: step: 1616/531, loss: 0.0021914870012551546
2023-01-24 08:49:46.941690: step: 1620/531, loss: 0.005860176868736744
2023-01-24 08:49:47.997127: step: 1624/531, loss: 7.749860742478631e-06
2023-01-24 08:49:49.053491: step: 1628/531, loss: 0.00022379022266250104
2023-01-24 08:49:50.098292: step: 1632/531, loss: 0.00016036475426517427
2023-01-24 08:49:51.162576: step: 1636/531, loss: 0.002189396182075143
2023-01-24 08:49:52.219967: step: 1640/531, loss: 0.0010613832855597138
2023-01-24 08:49:53.307787: step: 1644/531, loss: 0.0018733479082584381
2023-01-24 08:49:54.368123: step: 1648/531, loss: 0.002693586517125368
2023-01-24 08:49:55.432964: step: 1652/531, loss: 0.024549435824155807
2023-01-24 08:49:56.498064: step: 1656/531, loss: 0.00792443286627531
2023-01-24 08:49:57.554928: step: 1660/531, loss: 0.0005029304884374142
2023-01-24 08:49:58.617104: step: 1664/531, loss: 6.837258297309745e-06
2023-01-24 08:49:59.686485: step: 1668/531, loss: 0.007883038371801376
2023-01-24 08:50:00.739319: step: 1672/531, loss: 6.306728027993813e-05
2023-01-24 08:50:01.795880: step: 1676/531, loss: 0.0035531676840037107
2023-01-24 08:50:02.866249: step: 1680/531, loss: 0.004806555807590485
2023-01-24 08:50:03.922135: step: 1684/531, loss: 0.0003428776399232447
2023-01-24 08:50:04.976360: step: 1688/531, loss: 0.0005172319361008704
2023-01-24 08:50:06.040988: step: 1692/531, loss: 0.010027148760855198
2023-01-24 08:50:07.097058: step: 1696/531, loss: 0.002648507244884968
2023-01-24 08:50:08.159179: step: 1700/531, loss: 0.0002148015919374302
2023-01-24 08:50:09.210265: step: 1704/531, loss: 0.0025486743543297052
2023-01-24 08:50:10.275227: step: 1708/531, loss: 0.0046396031975746155
2023-01-24 08:50:11.325450: step: 1712/531, loss: 0.012598443776369095
2023-01-24 08:50:12.374008: step: 1716/531, loss: 4.2714276560218423e-07
2023-01-24 08:50:13.431237: step: 1720/531, loss: 0.0010781065793707967
2023-01-24 08:50:14.504962: step: 1724/531, loss: 0.0017423108220100403
2023-01-24 08:50:15.556545: step: 1728/531, loss: 0.004140028264373541
2023-01-24 08:50:16.608978: step: 1732/531, loss: 0.0035397133324295282
2023-01-24 08:50:17.663399: step: 1736/531, loss: 0.00980967003852129
2023-01-24 08:50:18.733592: step: 1740/531, loss: 0.0005589200300164521
2023-01-24 08:50:19.806177: step: 1744/531, loss: 0.002013190882280469
2023-01-24 08:50:20.859112: step: 1748/531, loss: 0.010056786239147186
2023-01-24 08:50:21.914497: step: 1752/531, loss: 0.006478422787040472
2023-01-24 08:50:22.958290: step: 1756/531, loss: 0.002787259640172124
2023-01-24 08:50:24.020233: step: 1760/531, loss: 0.00417192792519927
2023-01-24 08:50:25.075298: step: 1764/531, loss: 0.00402164738625288
2023-01-24 08:50:26.135134: step: 1768/531, loss: 0.0067492881789803505
2023-01-24 08:50:27.204804: step: 1772/531, loss: 0.0014811003347858787
2023-01-24 08:50:28.265985: step: 1776/531, loss: 0.004483489785343409
2023-01-24 08:50:29.340211: step: 1780/531, loss: 0.0004699307319242507
2023-01-24 08:50:30.406104: step: 1784/531, loss: 0.0035550526808947325
2023-01-24 08:50:31.468780: step: 1788/531, loss: 0.007740124128758907
2023-01-24 08:50:32.535464: step: 1792/531, loss: 0.0007996691856533289
2023-01-24 08:50:33.596571: step: 1796/531, loss: 0.001542242942377925
2023-01-24 08:50:34.653503: step: 1800/531, loss: 0.0018089384539052844
2023-01-24 08:50:35.712996: step: 1804/531, loss: 0.005222752224653959
2023-01-24 08:50:36.763002: step: 1808/531, loss: 0.0006715737981721759
2023-01-24 08:50:37.829384: step: 1812/531, loss: 0.00043306872248649597
2023-01-24 08:50:38.881722: step: 1816/531, loss: 0.015228058211505413
2023-01-24 08:50:39.965172: step: 1820/531, loss: 0.05320816859602928
2023-01-24 08:50:41.017333: step: 1824/531, loss: 0.0073781306855380535
2023-01-24 08:50:42.119049: step: 1828/531, loss: 0.001989522948861122
2023-01-24 08:50:43.181090: step: 1832/531, loss: 0.004696752410382032
2023-01-24 08:50:44.266594: step: 1836/531, loss: 0.007823620922863483
2023-01-24 08:50:45.327266: step: 1840/531, loss: 0.015773268416523933
2023-01-24 08:50:46.390486: step: 1844/531, loss: 0.007586033083498478
2023-01-24 08:50:47.453639: step: 1848/531, loss: 1.4352395737660117e-05
2023-01-24 08:50:48.502342: step: 1852/531, loss: 0.0043116421438753605
2023-01-24 08:50:49.568975: step: 1856/531, loss: 0.00011105309386039153
2023-01-24 08:50:50.630757: step: 1860/531, loss: 0.0035492845345288515
2023-01-24 08:50:51.702039: step: 1864/531, loss: 0.0015730762388557196
2023-01-24 08:50:52.754293: step: 1868/531, loss: 0.0020741065964102745
2023-01-24 08:50:53.812276: step: 1872/531, loss: 0.0028160004876554012
2023-01-24 08:50:54.879063: step: 1876/531, loss: 0.0015461607836186886
2023-01-24 08:50:55.941912: step: 1880/531, loss: 0.0020947048906236887
2023-01-24 08:50:57.016357: step: 1884/531, loss: 0.0017362883081659675
2023-01-24 08:50:58.081122: step: 1888/531, loss: 0.004290349315851927
2023-01-24 08:50:59.133766: step: 1892/531, loss: 0.0025052495766431093
2023-01-24 08:51:00.193499: step: 1896/531, loss: 0.000587494345381856
2023-01-24 08:51:01.247709: step: 1900/531, loss: 0.0010572696337476373
2023-01-24 08:51:02.301138: step: 1904/531, loss: 0.0003671610029414296
2023-01-24 08:51:03.364738: step: 1908/531, loss: 0.0027554002590477467
2023-01-24 08:51:04.417378: step: 1912/531, loss: 1.1026335414499044e-05
2023-01-24 08:51:05.477681: step: 1916/531, loss: 0.0021668020635843277
2023-01-24 08:51:06.573343: step: 1920/531, loss: 0.008678543381392956
2023-01-24 08:51:07.646496: step: 1924/531, loss: 0.021237801760435104
2023-01-24 08:51:08.728737: step: 1928/531, loss: 0.024778995662927628
2023-01-24 08:51:09.780699: step: 1932/531, loss: 0.008778535760939121
2023-01-24 08:51:10.858765: step: 1936/531, loss: 0.011332480236887932
2023-01-24 08:51:11.944667: step: 1940/531, loss: 0.010019216686487198
2023-01-24 08:51:13.003460: step: 1944/531, loss: 0.0024461084976792336
2023-01-24 08:51:14.060568: step: 1948/531, loss: 0.001441691885702312
2023-01-24 08:51:15.125952: step: 1952/531, loss: 0.008496014401316643
2023-01-24 08:51:16.187579: step: 1956/531, loss: 0.05084388330578804
2023-01-24 08:51:17.252836: step: 1960/531, loss: 0.00012086767674190924
2023-01-24 08:51:18.298821: step: 1964/531, loss: 2.970803325297311e-05
2023-01-24 08:51:19.365232: step: 1968/531, loss: 0.0028667813166975975
2023-01-24 08:51:20.429949: step: 1972/531, loss: 0.0031741890124976635
2023-01-24 08:51:21.497173: step: 1976/531, loss: 0.0019283414585515857
2023-01-24 08:51:22.552071: step: 1980/531, loss: 0.003965300507843494
2023-01-24 08:51:23.610901: step: 1984/531, loss: 0.012069007381796837
2023-01-24 08:51:24.666552: step: 1988/531, loss: 0.0005573823000304401
2023-01-24 08:51:25.722109: step: 1992/531, loss: 0.005476301070302725
2023-01-24 08:51:26.791327: step: 1996/531, loss: 0.0022730515338480473
2023-01-24 08:51:27.845903: step: 2000/531, loss: 0.0007104698452167213
2023-01-24 08:51:28.910921: step: 2004/531, loss: 0.0003665283729787916
2023-01-24 08:51:29.975660: step: 2008/531, loss: 0.0004408737877383828
2023-01-24 08:51:31.030491: step: 2012/531, loss: 0.0044172462075948715
2023-01-24 08:51:32.098243: step: 2016/531, loss: 0.002731681102886796
2023-01-24 08:51:33.158141: step: 2020/531, loss: 0.0013712862273678184
2023-01-24 08:51:34.209351: step: 2024/531, loss: 0.0017018537037074566
2023-01-24 08:51:35.264350: step: 2028/531, loss: 0.017987927421927452
2023-01-24 08:51:36.335352: step: 2032/531, loss: 0.0010171117028221488
2023-01-24 08:51:37.403342: step: 2036/531, loss: 2.4533940177207114e-06
2023-01-24 08:51:38.465526: step: 2040/531, loss: 0.0029998093377798796
2023-01-24 08:51:39.546555: step: 2044/531, loss: 0.0025358027778565884
2023-01-24 08:51:40.597924: step: 2048/531, loss: 0.0006947174551896751
2023-01-24 08:51:41.656614: step: 2052/531, loss: 0.0024698807392269373
2023-01-24 08:51:42.717364: step: 2056/531, loss: 0.0033368999138474464
2023-01-24 08:51:43.786820: step: 2060/531, loss: 0.005847891326993704
2023-01-24 08:51:44.856139: step: 2064/531, loss: 0.002655237214639783
2023-01-24 08:51:45.932210: step: 2068/531, loss: 1.0428493624203838e-05
2023-01-24 08:51:47.023176: step: 2072/531, loss: 0.0006189014529809356
2023-01-24 08:51:48.093917: step: 2076/531, loss: 0.008097605779767036
2023-01-24 08:51:49.158698: step: 2080/531, loss: 0.0005701733171008527
2023-01-24 08:51:50.222951: step: 2084/531, loss: 0.0013097748160362244
2023-01-24 08:51:51.276308: step: 2088/531, loss: 0.003954808693379164
2023-01-24 08:51:52.347448: step: 2092/531, loss: 0.0138529809191823
2023-01-24 08:51:53.409372: step: 2096/531, loss: 7.44784192647785e-05
2023-01-24 08:51:54.460170: step: 2100/531, loss: 0.008731680922210217
2023-01-24 08:51:55.542001: step: 2104/531, loss: 0.004643022548407316
2023-01-24 08:51:56.596525: step: 2108/531, loss: 0.0021834643557667732
2023-01-24 08:51:57.653414: step: 2112/531, loss: 0.0004960486548952758
2023-01-24 08:51:58.733145: step: 2116/531, loss: 0.0011990171624347568
2023-01-24 08:51:59.789941: step: 2120/531, loss: 0.0029714652337133884
2023-01-24 08:52:00.839629: step: 2124/531, loss: 0.004600778222084045
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3887538713308985, 'r': 0.32088792035852154, 'f1': 0.35157574642191447}, 'combined': 0.2590558131529896, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3857148857300496, 'r': 0.2737219252205131, 'f1': 0.3202084547147142}, 'combined': 0.20050435949426032, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37328407732434926, 'r': 0.3385764496414401, 'f1': 0.3550841571363959}, 'combined': 0.26164095788997593, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3867666353988432, 'r': 0.2845821230707449, 'f1': 0.3278977397251492}, 'combined': 0.2032042330691065, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.35941196033581924, 'r': 0.32463015772267545, 'f1': 0.341136775911964}, 'combined': 0.25136394014565766, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4103736568160889, 'r': 0.28604042986369405, 'f1': 0.3371082218053525}, 'combined': 0.22362624614810514, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 17}
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, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.37589167834240444, 'r': 0.34379466596022573, 'f1': 0.3591274310426936}, 'combined': 0.2646202123472479, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3892832819554885, 'r': 0.2881889760914843, 'f1': 0.3311933414357058}, 'combined': 0.20524657779114158, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 18
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 08:54:28.481451: step: 4/531, loss: 0.016485828906297684
2023-01-24 08:54:29.544669: step: 8/531, loss: 0.0001644348376430571
2023-01-24 08:54:30.594903: step: 12/531, loss: 0.0032943799160420895
2023-01-24 08:54:31.672162: step: 16/531, loss: 0.0008822003728710115
2023-01-24 08:54:32.711982: step: 20/531, loss: 0.0029280143789947033
2023-01-24 08:54:33.761267: step: 24/531, loss: 0.00039174058474600315
2023-01-24 08:54:34.825708: step: 28/531, loss: 0.0027231110725551844
2023-01-24 08:54:35.880853: step: 32/531, loss: 0.0023588051553815603
2023-01-24 08:54:36.942598: step: 36/531, loss: 0.006672924850136042
2023-01-24 08:54:38.028166: step: 40/531, loss: 0.0027809622697532177
2023-01-24 08:54:39.109889: step: 44/531, loss: 0.0018094608094543219
2023-01-24 08:54:40.157425: step: 48/531, loss: 0.001995962345972657
2023-01-24 08:54:41.214554: step: 52/531, loss: 0.005635008215904236
2023-01-24 08:54:42.279769: step: 56/531, loss: 0.00018772840849123895
2023-01-24 08:54:43.345187: step: 60/531, loss: 0.008437195792794228
2023-01-24 08:54:44.407796: step: 64/531, loss: 0.001004083314910531
2023-01-24 08:54:45.474321: step: 68/531, loss: 0.003171943360939622
2023-01-24 08:54:46.536359: step: 72/531, loss: 0.0030991339590400457
2023-01-24 08:54:47.580888: step: 76/531, loss: 0.0003899155417457223
2023-01-24 08:54:48.638708: step: 80/531, loss: 0.002102409955114126
2023-01-24 08:54:49.713906: step: 84/531, loss: 0.0008900128304958344
2023-01-24 08:54:50.768126: step: 88/531, loss: 0.002701554913073778
2023-01-24 08:54:51.831110: step: 92/531, loss: 0.0028115096502006054
2023-01-24 08:54:52.877045: step: 96/531, loss: 0.0022069918923079967
2023-01-24 08:54:53.944549: step: 100/531, loss: 0.00035266514169052243
2023-01-24 08:54:54.988411: step: 104/531, loss: 0.0002775506000034511
2023-01-24 08:54:56.041674: step: 108/531, loss: 0.014359908178448677
2023-01-24 08:54:57.100971: step: 112/531, loss: 0.000952446716837585
2023-01-24 08:54:58.159770: step: 116/531, loss: 0.0006368002505041659
2023-01-24 08:54:59.217179: step: 120/531, loss: 0.002198499860242009
2023-01-24 08:55:00.263007: step: 124/531, loss: 0.002797940978780389
2023-01-24 08:55:01.316201: step: 128/531, loss: 0.0030710017308592796
2023-01-24 08:55:02.379111: step: 132/531, loss: 4.771336080011679e-06
2023-01-24 08:55:03.437021: step: 136/531, loss: 0.00029019967769272625
2023-01-24 08:55:04.509818: step: 140/531, loss: 0.0019449201645329595
2023-01-24 08:55:05.570220: step: 144/531, loss: 0.006696322467178106
2023-01-24 08:55:06.646140: step: 148/531, loss: 0.003324989229440689
2023-01-24 08:55:07.722502: step: 152/531, loss: 0.0005718033644370735
2023-01-24 08:55:08.800359: step: 156/531, loss: 0.0011478849919512868
2023-01-24 08:55:09.885584: step: 160/531, loss: 0.002606028225272894
2023-01-24 08:55:10.939385: step: 164/531, loss: 4.181836629868485e-05
2023-01-24 08:55:11.994989: step: 168/531, loss: 1.4137232938082889e-05
2023-01-24 08:55:13.048771: step: 172/531, loss: 1.2221642009535572e-06
2023-01-24 08:55:14.114894: step: 176/531, loss: 0.0018177279271185398
2023-01-24 08:55:15.174654: step: 180/531, loss: 2.3236299966811202e-05
2023-01-24 08:55:16.231933: step: 184/531, loss: 0.0013298456324264407
2023-01-24 08:55:17.298296: step: 188/531, loss: 0.000456444249721244
2023-01-24 08:55:18.358773: step: 192/531, loss: 0.00041851933929137886
2023-01-24 08:55:19.443099: step: 196/531, loss: 0.0007842280901968479
2023-01-24 08:55:20.500091: step: 200/531, loss: 0.0040849014185369015
2023-01-24 08:55:21.570765: step: 204/531, loss: 0.0035691324155777693
2023-01-24 08:55:22.637172: step: 208/531, loss: 0.004006324801594019
2023-01-24 08:55:23.684684: step: 212/531, loss: 0.00240842392668128
2023-01-24 08:55:24.740648: step: 216/531, loss: 0.0002463726559653878
2023-01-24 08:55:25.795007: step: 220/531, loss: 0.041387658566236496
2023-01-24 08:55:26.841625: step: 224/531, loss: 0.0015840086853131652
2023-01-24 08:55:27.904703: step: 228/531, loss: 0.0018198407487943769
2023-01-24 08:55:28.943151: step: 232/531, loss: 6.201847281772643e-05
2023-01-24 08:55:29.997944: step: 236/531, loss: 0.004232801962643862
2023-01-24 08:55:31.047142: step: 240/531, loss: 0.00021786605066154152
2023-01-24 08:55:32.087665: step: 244/531, loss: 0.00037951269769109786
2023-01-24 08:55:33.152006: step: 248/531, loss: 0.0005722696660086513
2023-01-24 08:55:34.221927: step: 252/531, loss: 0.0009998573223128915
2023-01-24 08:55:35.292430: step: 256/531, loss: 0.0014447090215981007
2023-01-24 08:55:36.363175: step: 260/531, loss: 0.0121343694627285
2023-01-24 08:55:37.436498: step: 264/531, loss: 0.0067059798166155815
2023-01-24 08:55:38.497670: step: 268/531, loss: 0.003779573366045952
2023-01-24 08:55:39.559816: step: 272/531, loss: 0.0005448832525871694
2023-01-24 08:55:40.611516: step: 276/531, loss: 0.0028100148774683475
2023-01-24 08:55:41.671581: step: 280/531, loss: 0.0024854757357388735
2023-01-24 08:55:42.719638: step: 284/531, loss: 0.0022600931115448475
2023-01-24 08:55:43.780574: step: 288/531, loss: 6.12479925621301e-05
2023-01-24 08:55:44.836233: step: 292/531, loss: 5.4878051741980016e-05
2023-01-24 08:55:45.894790: step: 296/531, loss: 8.964359949459322e-06
2023-01-24 08:55:46.959296: step: 300/531, loss: 5.137475091032684e-05
2023-01-24 08:55:48.013097: step: 304/531, loss: 0.0005710149416700006
2023-01-24 08:55:49.074213: step: 308/531, loss: 0.0034550626296550035
2023-01-24 08:55:50.122238: step: 312/531, loss: 0.004638838581740856
2023-01-24 08:55:51.180667: step: 316/531, loss: 0.00041261533624492586
2023-01-24 08:55:52.235424: step: 320/531, loss: 0.0012044655159115791
2023-01-24 08:55:53.288388: step: 324/531, loss: 0.00028150342404842377
2023-01-24 08:55:54.360203: step: 328/531, loss: 0.003794601419940591
2023-01-24 08:55:55.416241: step: 332/531, loss: 6.865726027172059e-05
2023-01-24 08:55:56.471892: step: 336/531, loss: 0.0026643630117177963
2023-01-24 08:55:57.522185: step: 340/531, loss: 0.00249934708699584
2023-01-24 08:55:58.574335: step: 344/531, loss: 0.0005734206060878932
2023-01-24 08:55:59.607203: step: 348/531, loss: 0.0014442644314840436
2023-01-24 08:56:00.664033: step: 352/531, loss: 0.015320328064262867
2023-01-24 08:56:01.718619: step: 356/531, loss: 0.006696663331240416
2023-01-24 08:56:02.792613: step: 360/531, loss: 0.00047120271483436227
2023-01-24 08:56:03.869219: step: 364/531, loss: 0.033359427005052567
2023-01-24 08:56:04.945877: step: 368/531, loss: 0.0034414585679769516
2023-01-24 08:56:06.016376: step: 372/531, loss: 0.0010318740969523787
2023-01-24 08:56:07.090257: step: 376/531, loss: 0.0027982026804238558
2023-01-24 08:56:08.151967: step: 380/531, loss: 0.0008664476918056607
2023-01-24 08:56:09.221240: step: 384/531, loss: 1.4043931741980487e-06
2023-01-24 08:56:10.289410: step: 388/531, loss: 0.0019351415103301406
2023-01-24 08:56:11.347757: step: 392/531, loss: 0.0014457189245149493
2023-01-24 08:56:12.440074: step: 396/531, loss: 0.002615431323647499
2023-01-24 08:56:13.511536: step: 400/531, loss: 0.0014914002967998385
2023-01-24 08:56:14.575016: step: 404/531, loss: 0.0005335441092029214
2023-01-24 08:56:15.631297: step: 408/531, loss: 0.00021663724328391254
2023-01-24 08:56:16.682821: step: 412/531, loss: 0.0002839644730556756
2023-01-24 08:56:17.753506: step: 416/531, loss: 0.0017663523321971297
2023-01-24 08:56:18.805409: step: 420/531, loss: 2.42879286815878e-05
2023-01-24 08:56:19.857314: step: 424/531, loss: 0.00043031765380874276
2023-01-24 08:56:20.914679: step: 428/531, loss: 0.005618552211672068
2023-01-24 08:56:21.975147: step: 432/531, loss: 0.0016697110841050744
2023-01-24 08:56:23.045333: step: 436/531, loss: 0.0019035993609577417
2023-01-24 08:56:24.087807: step: 440/531, loss: 0.0006512982654385269
2023-01-24 08:56:25.140681: step: 444/531, loss: 0.0023728464730083942
2023-01-24 08:56:26.186352: step: 448/531, loss: 1.1175869119028903e-08
2023-01-24 08:56:27.249277: step: 452/531, loss: 0.009548933245241642
2023-01-24 08:56:28.301756: step: 456/531, loss: 0.015602135099470615
2023-01-24 08:56:29.354384: step: 460/531, loss: 0.0004088141140528023
2023-01-24 08:56:30.410897: step: 464/531, loss: 0.000493998930323869
2023-01-24 08:56:31.506956: step: 468/531, loss: 0.0002824018301907927
2023-01-24 08:56:32.577454: step: 472/531, loss: 0.0005933383945375681
2023-01-24 08:56:33.632456: step: 476/531, loss: 0.00015543719928245991
2023-01-24 08:56:34.688826: step: 480/531, loss: 0.002169729443266988
2023-01-24 08:56:35.767714: step: 484/531, loss: 0.0018769189482554793
2023-01-24 08:56:36.813809: step: 488/531, loss: 2.4835267176115394e-09
2023-01-24 08:56:37.867582: step: 492/531, loss: 0.0009975541615858674
2023-01-24 08:56:38.926811: step: 496/531, loss: 0.0008550878264941275
2023-01-24 08:56:39.975202: step: 500/531, loss: 3.923714757547714e-05
2023-01-24 08:56:41.030486: step: 504/531, loss: 7.415201707772212e-06
2023-01-24 08:56:42.096358: step: 508/531, loss: 0.0014785407111048698
2023-01-24 08:56:43.149862: step: 512/531, loss: 0.0010507397819310427
2023-01-24 08:56:44.224477: step: 516/531, loss: 0.005640383344143629
2023-01-24 08:56:45.290535: step: 520/531, loss: 0.004614170640707016
2023-01-24 08:56:46.360242: step: 524/531, loss: 0.0008273420971818268
2023-01-24 08:56:47.431923: step: 528/531, loss: 0.0031886552460491657
2023-01-24 08:56:48.498239: step: 532/531, loss: 0.0012883199378848076
2023-01-24 08:56:49.552597: step: 536/531, loss: 0.0026274370029568672
2023-01-24 08:56:50.599905: step: 540/531, loss: 0.00024105983902700245
2023-01-24 08:56:51.676968: step: 544/531, loss: 0.0007367110229097307
2023-01-24 08:56:52.728354: step: 548/531, loss: 0.00029140946571715176
2023-01-24 08:56:53.781897: step: 552/531, loss: 0.001001829863525927
2023-01-24 08:56:54.841910: step: 556/531, loss: 0.00143907917663455
2023-01-24 08:56:55.902363: step: 560/531, loss: 2.2807764253229834e-05
2023-01-24 08:56:56.972789: step: 564/531, loss: 0.005439003463834524
2023-01-24 08:56:58.027794: step: 568/531, loss: 0.002165445825085044
2023-01-24 08:56:59.083194: step: 572/531, loss: 0.00012455484829843044
2023-01-24 08:57:00.141296: step: 576/531, loss: 2.535478870413499e-06
2023-01-24 08:57:01.209475: step: 580/531, loss: 0.006315668113529682
2023-01-24 08:57:02.278805: step: 584/531, loss: 6.806410056015011e-06
2023-01-24 08:57:03.348495: step: 588/531, loss: 0.0012539697345346212
2023-01-24 08:57:04.411364: step: 592/531, loss: 0.0012168773682788014
2023-01-24 08:57:05.468388: step: 596/531, loss: 0.00023015595797915012
2023-01-24 08:57:06.511640: step: 600/531, loss: 3.5704444599105045e-05
2023-01-24 08:57:07.592405: step: 604/531, loss: 0.00023498994414694607
2023-01-24 08:57:08.639293: step: 608/531, loss: 0.0012686975533142686
2023-01-24 08:57:09.699469: step: 612/531, loss: 0.0016248218016698956
2023-01-24 08:57:10.757649: step: 616/531, loss: 0.00021879211999475956
2023-01-24 08:57:11.822680: step: 620/531, loss: 0.0003992653510067612
2023-01-24 08:57:12.872707: step: 624/531, loss: 0.0003639210481196642
2023-01-24 08:57:13.915648: step: 628/531, loss: 0.0015600253827869892
2023-01-24 08:57:14.975669: step: 632/531, loss: 1.0926994036708493e-05
2023-01-24 08:57:16.045916: step: 636/531, loss: 0.01515612006187439
2023-01-24 08:57:17.127289: step: 640/531, loss: 0.005097487010061741
2023-01-24 08:57:18.200414: step: 644/531, loss: 0.007839183323085308
2023-01-24 08:57:19.270773: step: 648/531, loss: 0.004948712885379791
2023-01-24 08:57:20.332602: step: 652/531, loss: 0.0019577748607844114
2023-01-24 08:57:21.400064: step: 656/531, loss: 0.013227894902229309
2023-01-24 08:57:22.469519: step: 660/531, loss: 1.710490687401034e-05
2023-01-24 08:57:23.539299: step: 664/531, loss: 0.00035234802635386586
2023-01-24 08:57:24.599011: step: 668/531, loss: 0.0025198820512741804
2023-01-24 08:57:25.680866: step: 672/531, loss: 0.0035180984996259212
2023-01-24 08:57:26.768999: step: 676/531, loss: 0.0017515599029138684
2023-01-24 08:57:27.823531: step: 680/531, loss: 0.00039060713606886566
2023-01-24 08:57:28.879066: step: 684/531, loss: 0.0002828391152434051
2023-01-24 08:57:29.943756: step: 688/531, loss: 0.0008307491079904139
2023-01-24 08:57:31.013802: step: 692/531, loss: 0.006182726472616196
2023-01-24 08:57:32.085608: step: 696/531, loss: 0.00020765890076290816
2023-01-24 08:57:33.140214: step: 700/531, loss: 0.004026591777801514
2023-01-24 08:57:34.195435: step: 704/531, loss: 0.004802176728844643
2023-01-24 08:57:35.264094: step: 708/531, loss: 0.004436550661921501
2023-01-24 08:57:36.324045: step: 712/531, loss: 0.007426182273775339
2023-01-24 08:57:37.381680: step: 716/531, loss: 0.002403817605227232
2023-01-24 08:57:38.460197: step: 720/531, loss: 0.004813516512513161
2023-01-24 08:57:39.526144: step: 724/531, loss: 0.001845165272243321
2023-01-24 08:57:40.584632: step: 728/531, loss: 0.003007540013641119
2023-01-24 08:57:41.630453: step: 732/531, loss: 0.0023156744427978992
2023-01-24 08:57:42.687987: step: 736/531, loss: 3.6970041037420742e-06
2023-01-24 08:57:43.745437: step: 740/531, loss: 0.00021665760141331702
2023-01-24 08:57:44.806180: step: 744/531, loss: 0.0005345075041987002
2023-01-24 08:57:45.870078: step: 748/531, loss: 0.0135061489418149
2023-01-24 08:57:46.937100: step: 752/531, loss: 0.00031829887302592397
2023-01-24 08:57:47.990376: step: 756/531, loss: 0.00023274790146388113
2023-01-24 08:57:49.039233: step: 760/531, loss: 0.0020559036638587713
2023-01-24 08:57:50.106296: step: 764/531, loss: 0.004413450602442026
2023-01-24 08:57:51.180437: step: 768/531, loss: 0.0019967348780483007
2023-01-24 08:57:52.244100: step: 772/531, loss: 0.006783493794500828
2023-01-24 08:57:53.322891: step: 776/531, loss: 7.250224734889343e-05
2023-01-24 08:57:54.369260: step: 780/531, loss: 1.827925007091835e-05
2023-01-24 08:57:55.424256: step: 784/531, loss: 2.1787996956845745e-05
2023-01-24 08:57:56.492513: step: 788/531, loss: 0.006557614076882601
2023-01-24 08:57:57.563902: step: 792/531, loss: 0.00016529702406842262
2023-01-24 08:57:58.615074: step: 796/531, loss: 0.0001591194304637611
2023-01-24 08:57:59.675294: step: 800/531, loss: 0.00013501947978511453
2023-01-24 08:58:00.719717: step: 804/531, loss: 0.0037079069297760725
2023-01-24 08:58:01.768236: step: 808/531, loss: 0.0014649454969912767
2023-01-24 08:58:02.832034: step: 812/531, loss: 0.0010747892083600163
2023-01-24 08:58:03.900358: step: 816/531, loss: 0.0015955495182424784
2023-01-24 08:58:04.950600: step: 820/531, loss: 0.0004603270790539682
2023-01-24 08:58:06.015821: step: 824/531, loss: 0.0008048953604884446
2023-01-24 08:58:07.067973: step: 828/531, loss: 0.004007001873105764
2023-01-24 08:58:08.124453: step: 832/531, loss: 0.00034805593895725906
2023-01-24 08:58:09.183418: step: 836/531, loss: 6.917065911693498e-05
2023-01-24 08:58:10.231986: step: 840/531, loss: 0.0018708569696173072
2023-01-24 08:58:11.300530: step: 844/531, loss: 0.0006993492715992033
2023-01-24 08:58:12.347616: step: 848/531, loss: 0.000982363591901958
2023-01-24 08:58:13.436255: step: 852/531, loss: 9.765825780050363e-06
2023-01-24 08:58:14.495869: step: 856/531, loss: 0.0003236057236790657
2023-01-24 08:58:15.554899: step: 860/531, loss: 0.0009666095720604062
2023-01-24 08:58:16.612056: step: 864/531, loss: 0.00017323960491921753
2023-01-24 08:58:17.663044: step: 868/531, loss: 0.00047029071720317006
2023-01-24 08:58:18.722922: step: 872/531, loss: 0.00013420723553281277
2023-01-24 08:58:19.795716: step: 876/531, loss: 0.0011368688428774476
2023-01-24 08:58:20.839816: step: 880/531, loss: 0.003005849663168192
2023-01-24 08:58:21.900971: step: 884/531, loss: 0.004738184157758951
2023-01-24 08:58:22.980902: step: 888/531, loss: 0.0026863841339945793
2023-01-24 08:58:24.037853: step: 892/531, loss: 0.0027179387398064137
2023-01-24 08:58:25.106330: step: 896/531, loss: 0.0030021655838936567
2023-01-24 08:58:26.176463: step: 900/531, loss: 0.0075303916819393635
2023-01-24 08:58:27.249712: step: 904/531, loss: 0.005289142020046711
2023-01-24 08:58:28.302292: step: 908/531, loss: 0.002549083437770605
2023-01-24 08:58:29.360988: step: 912/531, loss: 0.000973164162132889
2023-01-24 08:58:30.417660: step: 916/531, loss: 0.00010077129991259426
2023-01-24 08:58:31.503060: step: 920/531, loss: 0.009604857303202152
2023-01-24 08:58:32.566916: step: 924/531, loss: 0.004010828677564859
2023-01-24 08:58:33.624783: step: 928/531, loss: 0.0017199756111949682
2023-01-24 08:58:34.698704: step: 932/531, loss: 0.008867351338267326
2023-01-24 08:58:35.746466: step: 936/531, loss: 0.00048212322872132063
2023-01-24 08:58:36.805920: step: 940/531, loss: 0.0010061763459816575
2023-01-24 08:58:37.860013: step: 944/531, loss: 0.00029186729807406664
2023-01-24 08:58:38.925506: step: 948/531, loss: 0.0033926840405911207
2023-01-24 08:58:39.986168: step: 952/531, loss: 0.002526672091335058
2023-01-24 08:58:41.042353: step: 956/531, loss: 3.5623535950435326e-05
2023-01-24 08:58:42.105494: step: 960/531, loss: 9.588974353391677e-05
2023-01-24 08:58:43.164826: step: 964/531, loss: 0.001444108784198761
2023-01-24 08:58:44.224373: step: 968/531, loss: 0.00039235668373294175
2023-01-24 08:58:45.282152: step: 972/531, loss: 0.002232030965387821
2023-01-24 08:58:46.367535: step: 976/531, loss: 0.0013621806865558028
2023-01-24 08:58:47.452380: step: 980/531, loss: 0.0010406405199319124
2023-01-24 08:58:48.516323: step: 984/531, loss: 5.313460496836342e-05
2023-01-24 08:58:49.572100: step: 988/531, loss: 0.0002594345423858613
2023-01-24 08:58:50.648830: step: 992/531, loss: 0.002299090614542365
2023-01-24 08:58:51.696197: step: 996/531, loss: 0.00027974246768280864
2023-01-24 08:58:52.756297: step: 1000/531, loss: 0.0873853862285614
2023-01-24 08:58:53.810022: step: 1004/531, loss: 0.0024309372529387474
2023-01-24 08:58:54.860297: step: 1008/531, loss: 0.008802449330687523
2023-01-24 08:58:55.910458: step: 1012/531, loss: 0.0009594323928467929
2023-01-24 08:58:56.980178: step: 1016/531, loss: 0.0005408779834397137
2023-01-24 08:58:58.036700: step: 1020/531, loss: 0.00037356792017817497
2023-01-24 08:58:59.096629: step: 1024/531, loss: 0.011383525095880032
2023-01-24 08:59:00.137963: step: 1028/531, loss: 8.98589423741214e-05
2023-01-24 08:59:01.198099: step: 1032/531, loss: 0.0006295870989561081
2023-01-24 08:59:02.249237: step: 1036/531, loss: 0.002829010831192136
2023-01-24 08:59:03.313539: step: 1040/531, loss: 0.0002396887430222705
2023-01-24 08:59:04.380873: step: 1044/531, loss: 5.0104642923543e-07
2023-01-24 08:59:05.438196: step: 1048/531, loss: 0.0002615940466057509
2023-01-24 08:59:06.497981: step: 1052/531, loss: 0.0038523327093571424
2023-01-24 08:59:07.547820: step: 1056/531, loss: 0.000883518485352397
2023-01-24 08:59:08.609351: step: 1060/531, loss: 0.0021896460093557835
2023-01-24 08:59:09.650750: step: 1064/531, loss: 0.0002651022805366665
2023-01-24 08:59:10.721737: step: 1068/531, loss: 0.004354636184871197
2023-01-24 08:59:11.777444: step: 1072/531, loss: 0.003977876156568527
2023-01-24 08:59:12.839404: step: 1076/531, loss: 0.008849016390740871
2023-01-24 08:59:13.905408: step: 1080/531, loss: 3.6134490073891357e-05
2023-01-24 08:59:14.975231: step: 1084/531, loss: 0.013320890255272388
2023-01-24 08:59:16.047286: step: 1088/531, loss: 7.336511043831706e-05
2023-01-24 08:59:17.111566: step: 1092/531, loss: 0.011483129113912582
2023-01-24 08:59:18.166436: step: 1096/531, loss: 0.00011668517254292965
2023-01-24 08:59:19.232260: step: 1100/531, loss: 0.00870268139988184
2023-01-24 08:59:20.292829: step: 1104/531, loss: 0.0010282648727297783
2023-01-24 08:59:21.351047: step: 1108/531, loss: 0.003967622295022011
2023-01-24 08:59:22.408339: step: 1112/531, loss: 0.002501889830455184
2023-01-24 08:59:23.482382: step: 1116/531, loss: 0.0002148712082998827
2023-01-24 08:59:24.537368: step: 1120/531, loss: 0.0019938137847930193
2023-01-24 08:59:25.594108: step: 1124/531, loss: 0.0022507677786052227
2023-01-24 08:59:26.644259: step: 1128/531, loss: 0.00032830797135829926
2023-01-24 08:59:27.711333: step: 1132/531, loss: 0.002065314445644617
2023-01-24 08:59:28.769113: step: 1136/531, loss: 3.743823981494643e-05
2023-01-24 08:59:29.824406: step: 1140/531, loss: 0.00012083940237062052
2023-01-24 08:59:30.877492: step: 1144/531, loss: 0.00525860209017992
2023-01-24 08:59:31.949514: step: 1148/531, loss: 0.0003096633590757847
2023-01-24 08:59:33.006219: step: 1152/531, loss: 0.008722452446818352
2023-01-24 08:59:34.074347: step: 1156/531, loss: 0.01146688312292099
2023-01-24 08:59:35.134834: step: 1160/531, loss: 0.0019660552497953176
2023-01-24 08:59:36.175430: step: 1164/531, loss: 0.0015725501580163836
2023-01-24 08:59:37.237854: step: 1168/531, loss: 0.0017212495440617204
2023-01-24 08:59:38.303802: step: 1172/531, loss: 0.00023194462119136006
2023-01-24 08:59:39.358267: step: 1176/531, loss: 0.0006005600444041193
2023-01-24 08:59:40.423160: step: 1180/531, loss: 0.0063990936614573
2023-01-24 08:59:41.498003: step: 1184/531, loss: 0.0007296130643226206
2023-01-24 08:59:42.594016: step: 1188/531, loss: 0.0036682954523712397
2023-01-24 08:59:43.649477: step: 1192/531, loss: 0.0004935808246955276
2023-01-24 08:59:44.702632: step: 1196/531, loss: 0.0010374593548476696
2023-01-24 08:59:45.754569: step: 1200/531, loss: 0.008196872659027576
2023-01-24 08:59:46.803680: step: 1204/531, loss: 6.592134013772011e-05
2023-01-24 08:59:47.857025: step: 1208/531, loss: 5.240000518824672e-06
2023-01-24 08:59:48.913934: step: 1212/531, loss: 0.0015342289116233587
2023-01-24 08:59:49.965950: step: 1216/531, loss: 0.0013343931641429663
2023-01-24 08:59:51.027756: step: 1220/531, loss: 5.063352728029713e-05
2023-01-24 08:59:52.088112: step: 1224/531, loss: 0.0011145316530019045
2023-01-24 08:59:53.165786: step: 1228/531, loss: 0.002456244546920061
2023-01-24 08:59:54.212323: step: 1232/531, loss: 0.002808689372614026
2023-01-24 08:59:55.289923: step: 1236/531, loss: 0.0017257626168429852
2023-01-24 08:59:56.331539: step: 1240/531, loss: 0.0009658159106038511
2023-01-24 08:59:57.392077: step: 1244/531, loss: 0.0006192835862748325
2023-01-24 08:59:58.461641: step: 1248/531, loss: 0.002016267506405711
2023-01-24 08:59:59.519721: step: 1252/531, loss: 7.521335646742955e-05
2023-01-24 09:00:00.578160: step: 1256/531, loss: 0.002600456355139613
2023-01-24 09:00:01.636768: step: 1260/531, loss: 8.527469617547467e-06
2023-01-24 09:00:02.696521: step: 1264/531, loss: 0.0032685298938304186
2023-01-24 09:00:03.762011: step: 1268/531, loss: 0.001603559241630137
2023-01-24 09:00:04.823898: step: 1272/531, loss: 0.0025893133133649826
2023-01-24 09:00:05.889254: step: 1276/531, loss: 0.00023609522031620145
2023-01-24 09:00:06.952603: step: 1280/531, loss: 4.347735739429481e-05
2023-01-24 09:00:08.002423: step: 1284/531, loss: 0.00042860786197707057
2023-01-24 09:00:09.062314: step: 1288/531, loss: 0.003873482346534729
2023-01-24 09:00:10.134963: step: 1292/531, loss: 0.00044308914220891893
2023-01-24 09:00:11.192765: step: 1296/531, loss: 2.2038011593394913e-05
2023-01-24 09:00:12.246101: step: 1300/531, loss: 0.038779083639383316
2023-01-24 09:00:13.313697: step: 1304/531, loss: 0.0006104726926423609
2023-01-24 09:00:14.369664: step: 1308/531, loss: 0.00022003143385518342
2023-01-24 09:00:15.424079: step: 1312/531, loss: 0.0012571928091347218
2023-01-24 09:00:16.481291: step: 1316/531, loss: 0.0028441783506423235
2023-01-24 09:00:17.568280: step: 1320/531, loss: 0.004914427176117897
2023-01-24 09:00:18.636828: step: 1324/531, loss: 0.00031373955425806344
2023-01-24 09:00:19.699853: step: 1328/531, loss: 1.7868629583972506e-05
2023-01-24 09:00:20.763700: step: 1332/531, loss: 0.0057790507562458515
2023-01-24 09:00:21.823869: step: 1336/531, loss: 0.0037652403116226196
2023-01-24 09:00:22.913598: step: 1340/531, loss: 0.0009412994841113687
2023-01-24 09:00:23.974819: step: 1344/531, loss: 0.0018789108144119382
2023-01-24 09:00:25.032403: step: 1348/531, loss: 0.00906267762184143
2023-01-24 09:00:26.085687: step: 1352/531, loss: 0.0016206526197493076
2023-01-24 09:00:27.145573: step: 1356/531, loss: 0.001545802573673427
2023-01-24 09:00:28.231417: step: 1360/531, loss: 0.0008290863479487598
2023-01-24 09:00:29.286111: step: 1364/531, loss: 0.0019554882310330868
2023-01-24 09:00:30.353033: step: 1368/531, loss: 0.0003496269346214831
2023-01-24 09:00:31.411269: step: 1372/531, loss: 0.0005644718185067177
2023-01-24 09:00:32.474553: step: 1376/531, loss: 0.004910139366984367
2023-01-24 09:00:33.539786: step: 1380/531, loss: 0.0023308389354497194
2023-01-24 09:00:34.606445: step: 1384/531, loss: 0.0035187278408557177
2023-01-24 09:00:35.676563: step: 1388/531, loss: 0.00235362839885056
2023-01-24 09:00:36.730779: step: 1392/531, loss: 0.004601230379194021
2023-01-24 09:00:37.806018: step: 1396/531, loss: 0.00044968537986278534
2023-01-24 09:00:38.853867: step: 1400/531, loss: 0.17044170200824738
2023-01-24 09:00:39.907698: step: 1404/531, loss: 1.6982727174763568e-05
2023-01-24 09:00:40.964836: step: 1408/531, loss: 0.006890931632369757
2023-01-24 09:00:42.030978: step: 1412/531, loss: 4.8774720198707655e-05
2023-01-24 09:00:43.086750: step: 1416/531, loss: 0.0038381507620215416
2023-01-24 09:00:44.145904: step: 1420/531, loss: 0.00964371208101511
2023-01-24 09:00:45.216340: step: 1424/531, loss: 0.003110338933765888
2023-01-24 09:00:46.276856: step: 1428/531, loss: 0.0013871254632249475
2023-01-24 09:00:47.351852: step: 1432/531, loss: 0.014119843952357769
2023-01-24 09:00:48.421597: step: 1436/531, loss: 0.03157404065132141
2023-01-24 09:00:49.476127: step: 1440/531, loss: 0.0006457576528191566
2023-01-24 09:00:50.558418: step: 1444/531, loss: 0.0011518874671310186
2023-01-24 09:00:51.615711: step: 1448/531, loss: 0.0004716934054158628
2023-01-24 09:00:52.675354: step: 1452/531, loss: 0.005320834927260876
2023-01-24 09:00:53.745417: step: 1456/531, loss: 0.03181644156575203
2023-01-24 09:00:54.795714: step: 1460/531, loss: 0.022640204057097435
2023-01-24 09:00:55.846932: step: 1464/531, loss: 0.00043951653060503304
2023-01-24 09:00:56.910662: step: 1468/531, loss: 0.0020284373313188553
2023-01-24 09:00:57.975260: step: 1472/531, loss: 0.00926901400089264
2023-01-24 09:00:59.034375: step: 1476/531, loss: 0.003973019775003195
2023-01-24 09:01:00.102576: step: 1480/531, loss: 0.006028393749147654
2023-01-24 09:01:01.164889: step: 1484/531, loss: 0.00011165729665663093
2023-01-24 09:01:02.211284: step: 1488/531, loss: 0.00041287802741862833
2023-01-24 09:01:03.254868: step: 1492/531, loss: 0.005346434656530619
2023-01-24 09:01:04.335199: step: 1496/531, loss: 0.006351563148200512
2023-01-24 09:01:05.385252: step: 1500/531, loss: 1.475368389947107e-05
2023-01-24 09:01:06.438632: step: 1504/531, loss: 0.00901619903743267
2023-01-24 09:01:07.502131: step: 1508/531, loss: 3.715350976563059e-05
2023-01-24 09:01:08.558759: step: 1512/531, loss: 0.00014359848864842206
2023-01-24 09:01:09.617169: step: 1516/531, loss: 9.431096259504557e-07
2023-01-24 09:01:10.680271: step: 1520/531, loss: 9.744471753947437e-07
2023-01-24 09:01:11.755367: step: 1524/531, loss: 1.4067901247472037e-05
2023-01-24 09:01:12.851450: step: 1528/531, loss: 0.004908103961497545
2023-01-24 09:01:13.914453: step: 1532/531, loss: 0.009209039621055126
2023-01-24 09:01:14.970481: step: 1536/531, loss: 0.001192554016597569
2023-01-24 09:01:16.029055: step: 1540/531, loss: 0.004860010463744402
2023-01-24 09:01:17.087458: step: 1544/531, loss: 0.011957105249166489
2023-01-24 09:01:18.162099: step: 1548/531, loss: 0.0024243956431746483
2023-01-24 09:01:19.213780: step: 1552/531, loss: 0.015127007849514484
2023-01-24 09:01:20.279502: step: 1556/531, loss: 0.0013533026212826371
2023-01-24 09:01:21.337260: step: 1560/531, loss: 0.006612077355384827
2023-01-24 09:01:22.386204: step: 1564/531, loss: 0.0011698710732161999
2023-01-24 09:01:23.457907: step: 1568/531, loss: 0.00013252052303869277
2023-01-24 09:01:24.515166: step: 1572/531, loss: 0.00015672024164814502
2023-01-24 09:01:25.568839: step: 1576/531, loss: 0.0015872985823079944
2023-01-24 09:01:26.616990: step: 1580/531, loss: 0.00015963762416504323
2023-01-24 09:01:27.667101: step: 1584/531, loss: 2.595854675746523e-05
2023-01-24 09:01:28.720328: step: 1588/531, loss: 0.0
2023-01-24 09:01:29.774739: step: 1592/531, loss: 0.0006789904437027872
2023-01-24 09:01:30.842377: step: 1596/531, loss: 0.0053655230440199375
2023-01-24 09:01:31.890212: step: 1600/531, loss: 0.0007486220565624535
2023-01-24 09:01:32.943895: step: 1604/531, loss: 0.0024495527613908052
2023-01-24 09:01:33.986539: step: 1608/531, loss: 0.0003433394304011017
2023-01-24 09:01:35.042824: step: 1612/531, loss: 0.0029550609178841114
2023-01-24 09:01:36.117265: step: 1616/531, loss: 0.007177832070738077
2023-01-24 09:01:37.171643: step: 1620/531, loss: 0.0010881096823140979
2023-01-24 09:01:38.255116: step: 1624/531, loss: 0.00016112506273202598
2023-01-24 09:01:39.328708: step: 1628/531, loss: 0.0012078933650627732
2023-01-24 09:01:40.395745: step: 1632/531, loss: 0.024158179759979248
2023-01-24 09:01:41.448082: step: 1636/531, loss: 0.000262209156062454
2023-01-24 09:01:42.534945: step: 1640/531, loss: 0.007524306420236826
2023-01-24 09:01:43.609624: step: 1644/531, loss: 0.06044727563858032
2023-01-24 09:01:44.680747: step: 1648/531, loss: 0.0034228444565087557
2023-01-24 09:01:45.734885: step: 1652/531, loss: 0.0034735058434307575
2023-01-24 09:01:46.794785: step: 1656/531, loss: 0.0004593534686136991
2023-01-24 09:01:47.845775: step: 1660/531, loss: 3.261943857069127e-05
2023-01-24 09:01:48.896749: step: 1664/531, loss: 0.0009421770228073001
2023-01-24 09:01:49.985121: step: 1668/531, loss: 0.0011454899795353413
2023-01-24 09:01:51.060125: step: 1672/531, loss: 0.006851317826658487
2023-01-24 09:01:52.117397: step: 1676/531, loss: 0.0009444098686799407
2023-01-24 09:01:53.202400: step: 1680/531, loss: 0.022287234663963318
2023-01-24 09:01:54.256575: step: 1684/531, loss: 0.0001457652688259259
2023-01-24 09:01:55.327417: step: 1688/531, loss: 0.00026868312852457166
2023-01-24 09:01:56.393659: step: 1692/531, loss: 0.0021390998736023903
2023-01-24 09:01:57.458458: step: 1696/531, loss: 0.0011894813505932689
2023-01-24 09:01:58.498945: step: 1700/531, loss: 1.503433031757595e-05
2023-01-24 09:01:59.567773: step: 1704/531, loss: 0.0037068442907184362
2023-01-24 09:02:00.618361: step: 1708/531, loss: 0.00041447763214819133
2023-01-24 09:02:01.694597: step: 1712/531, loss: 0.0014347850810736418
2023-01-24 09:02:02.770347: step: 1716/531, loss: 0.0007021583151072264
2023-01-24 09:02:03.847331: step: 1720/531, loss: 0.0033520509023219347
2023-01-24 09:02:04.911150: step: 1724/531, loss: 0.00010703740554163232
2023-01-24 09:02:05.985891: step: 1728/531, loss: 0.00018746900605037808
2023-01-24 09:02:07.052106: step: 1732/531, loss: 0.002802737755700946
2023-01-24 09:02:08.128962: step: 1736/531, loss: 0.0030879105906933546
2023-01-24 09:02:09.197111: step: 1740/531, loss: 0.0016189685557037592
2023-01-24 09:02:10.251495: step: 1744/531, loss: 0.0009682712843641639
2023-01-24 09:02:11.320534: step: 1748/531, loss: 0.0008436330244876444
2023-01-24 09:02:12.380305: step: 1752/531, loss: 0.020546063780784607
2023-01-24 09:02:13.439949: step: 1756/531, loss: 0.0002602914464659989
2023-01-24 09:02:14.502224: step: 1760/531, loss: 0.0007306385668925941
2023-01-24 09:02:15.569262: step: 1764/531, loss: 0.0066851102747023106
2023-01-24 09:02:16.613817: step: 1768/531, loss: 0.00256662187166512
2023-01-24 09:02:17.676835: step: 1772/531, loss: 0.003725983202457428
2023-01-24 09:02:18.737828: step: 1776/531, loss: 0.004710950888693333
2023-01-24 09:02:19.792141: step: 1780/531, loss: 0.0037541964557021856
2023-01-24 09:02:20.850998: step: 1784/531, loss: 0.0006544382777065039
2023-01-24 09:02:21.906526: step: 1788/531, loss: 0.0043398612178862095
2023-01-24 09:02:22.971927: step: 1792/531, loss: 1.502430336586258e-06
2023-01-24 09:02:24.041622: step: 1796/531, loss: 0.0007283294689841568
2023-01-24 09:02:25.099568: step: 1800/531, loss: 1.8998946416104445e-08
2023-01-24 09:02:26.161491: step: 1804/531, loss: 0.0033150820527225733
2023-01-24 09:02:27.218056: step: 1808/531, loss: 1.0320477485947777e-06
2023-01-24 09:02:28.266390: step: 1812/531, loss: 0.0021151944529265165
2023-01-24 09:02:29.320090: step: 1816/531, loss: 0.005310488399118185
2023-01-24 09:02:30.383766: step: 1820/531, loss: 0.0023086806759238243
2023-01-24 09:02:31.435588: step: 1824/531, loss: 3.3071394227590645e-06
2023-01-24 09:02:32.509983: step: 1828/531, loss: 0.0031708471942692995
2023-01-24 09:02:33.576519: step: 1832/531, loss: 0.0005807864363305271
2023-01-24 09:02:34.636260: step: 1836/531, loss: 1.5153469576034695e-05
2023-01-24 09:02:35.697982: step: 1840/531, loss: 0.003144286572933197
2023-01-24 09:02:36.757462: step: 1844/531, loss: 0.0006509244558401406
2023-01-24 09:02:37.815071: step: 1848/531, loss: 0.0
2023-01-24 09:02:38.862492: step: 1852/531, loss: 0.0006537417066283524
2023-01-24 09:02:39.911476: step: 1856/531, loss: 0.003799894591793418
2023-01-24 09:02:40.975087: step: 1860/531, loss: 0.00012065597547916695
2023-01-24 09:02:42.022084: step: 1864/531, loss: 0.000554021040443331
2023-01-24 09:02:43.081206: step: 1868/531, loss: 0.004134547431021929
2023-01-24 09:02:44.143552: step: 1872/531, loss: 0.0014604346361011267
2023-01-24 09:02:45.214720: step: 1876/531, loss: 0.0024224831722676754
2023-01-24 09:02:46.294826: step: 1880/531, loss: 0.0009388086036778986
2023-01-24 09:02:47.365410: step: 1884/531, loss: 0.004616179969161749
2023-01-24 09:02:48.420735: step: 1888/531, loss: 0.00034893781412392855
2023-01-24 09:02:49.475041: step: 1892/531, loss: 0.011060983873903751
2023-01-24 09:02:50.537310: step: 1896/531, loss: 0.0013159917434677482
2023-01-24 09:02:51.584434: step: 1900/531, loss: 2.4216780730057508e-05
2023-01-24 09:02:52.645546: step: 1904/531, loss: 3.7480374885490164e-05
2023-01-24 09:02:53.738535: step: 1908/531, loss: 0.00861275102943182
2023-01-24 09:02:54.803739: step: 1912/531, loss: 0.0002775720495264977
2023-01-24 09:02:55.884265: step: 1916/531, loss: 0.026195937767624855
2023-01-24 09:02:56.958748: step: 1920/531, loss: 0.0028177814092487097
2023-01-24 09:02:58.009772: step: 1924/531, loss: 0.004467234015464783
2023-01-24 09:02:59.083914: step: 1928/531, loss: 0.00026399921625852585
2023-01-24 09:03:00.145973: step: 1932/531, loss: 0.0006418237462639809
2023-01-24 09:03:01.219953: step: 1936/531, loss: 0.00297364080324769
2023-01-24 09:03:02.275020: step: 1940/531, loss: 0.0022940761409699917
2023-01-24 09:03:03.332359: step: 1944/531, loss: 0.0006617771578021348
2023-01-24 09:03:04.401185: step: 1948/531, loss: 0.0051666004583239555
2023-01-24 09:03:05.465346: step: 1952/531, loss: 0.0004947419511154294
2023-01-24 09:03:06.517575: step: 1956/531, loss: 0.0025995911564677954
2023-01-24 09:03:07.578917: step: 1960/531, loss: 0.011489641852676868
2023-01-24 09:03:08.642125: step: 1964/531, loss: 0.0007339761359617114
2023-01-24 09:03:09.700228: step: 1968/531, loss: 0.0013429466634988785
2023-01-24 09:03:10.764793: step: 1972/531, loss: 0.004915457218885422
2023-01-24 09:03:11.830708: step: 1976/531, loss: 0.0003365647862665355
2023-01-24 09:03:12.911789: step: 1980/531, loss: 1.1311198250041343e-05
2023-01-24 09:03:13.974283: step: 1984/531, loss: 0.004728915635496378
2023-01-24 09:03:15.039405: step: 1988/531, loss: 0.0021634509321302176
2023-01-24 09:03:16.083145: step: 1992/531, loss: 0.005010695196688175
2023-01-24 09:03:17.144165: step: 1996/531, loss: 0.005788684822618961
2023-01-24 09:03:18.203824: step: 2000/531, loss: 0.0042273816652596
2023-01-24 09:03:19.262930: step: 2004/531, loss: 0.0013140605296939611
2023-01-24 09:03:20.337837: step: 2008/531, loss: 0.0004994259215891361
2023-01-24 09:03:21.401866: step: 2012/531, loss: 6.0525995650095865e-05
2023-01-24 09:03:22.469347: step: 2016/531, loss: 0.0117364302277565
2023-01-24 09:03:23.529996: step: 2020/531, loss: 0.0005778932245448232
2023-01-24 09:03:24.593944: step: 2024/531, loss: 0.0004402291961014271
2023-01-24 09:03:25.651771: step: 2028/531, loss: 0.00029284090851433575
2023-01-24 09:03:26.712320: step: 2032/531, loss: 1.7201027731061913e-05
2023-01-24 09:03:27.791741: step: 2036/531, loss: 0.0019599662628024817
2023-01-24 09:03:28.865937: step: 2040/531, loss: 0.0002874326892197132
2023-01-24 09:03:29.927500: step: 2044/531, loss: 0.006079535000026226
2023-01-24 09:03:30.990887: step: 2048/531, loss: 0.006589184049516916
2023-01-24 09:03:32.050283: step: 2052/531, loss: 0.004900340922176838
2023-01-24 09:03:33.106619: step: 2056/531, loss: 0.00044026729301549494
2023-01-24 09:03:34.155015: step: 2060/531, loss: 0.0005237417062744498
2023-01-24 09:03:35.203437: step: 2064/531, loss: 5.508607500814833e-05
2023-01-24 09:03:36.280459: step: 2068/531, loss: 0.0041692522354424
2023-01-24 09:03:37.350345: step: 2072/531, loss: 0.0020148782059550285
2023-01-24 09:03:38.416273: step: 2076/531, loss: 3.255229239584878e-05
2023-01-24 09:03:39.463599: step: 2080/531, loss: 0.003427467541769147
2023-01-24 09:03:40.543810: step: 2084/531, loss: 0.006046326365321875
2023-01-24 09:03:41.603909: step: 2088/531, loss: 0.015670448541641235
2023-01-24 09:03:42.682262: step: 2092/531, loss: 0.0004098574281670153
2023-01-24 09:03:43.741895: step: 2096/531, loss: 0.0025626695714890957
2023-01-24 09:03:44.814923: step: 2100/531, loss: 0.005880072712898254
2023-01-24 09:03:45.932610: step: 2104/531, loss: 0.0007337437709793448
2023-01-24 09:03:46.981995: step: 2108/531, loss: 0.003602172713726759
2023-01-24 09:03:48.038898: step: 2112/531, loss: 0.000552355544641614
2023-01-24 09:03:49.093174: step: 2116/531, loss: 0.0052804420702159405
2023-01-24 09:03:50.157886: step: 2120/531, loss: 0.0012563823256641626
2023-01-24 09:03:51.205533: step: 2124/531, loss: 0.0076697091571986675
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3931957675803099, 'r': 0.3230621771580155, 'f1': 0.3546953486714045}, 'combined': 0.2613544674420875, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38931343679689745, 'r': 0.27732877824125246, 'f1': 0.3239153397256967}, 'combined': 0.20282549309926803, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3801261370486054, 'r': 0.3418971327533946, 'f1': 0.3599995783437342}, 'combined': 0.26526284720064625, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3931559590286749, 'r': 0.289992402601854, 'f1': 0.33378471664292275}, 'combined': 0.20685250045476902, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36422124867336836, 'r': 0.32828290914582536, 'f1': 0.3453195471454091}, 'combined': 0.25444598210714353, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4126531401015937, 'r': 0.28874556962924863, 'f1': 0.3397547339191902}, 'combined': 0.22538185319391826, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 18}
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, 'stategy': 1, 'epoch': 18}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3801261370486054, 'r': 0.3418971327533946, 'f1': 0.3599995783437342}, 'combined': 0.26526284720064625, 'stategy': 1, 'epoch': 18}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3931559590286749, 'r': 0.289992402601854, 'f1': 0.33378471664292275}, 'combined': 0.20685250045476902, 'stategy': 1, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-24 09:06:22.784321: step: 4/531, loss: 0.006720223464071751
2023-01-24 09:06:23.854396: step: 8/531, loss: 0.0059721143916249275
2023-01-24 09:06:24.911873: step: 12/531, loss: 0.0017975919181481004
2023-01-24 09:06:25.964331: step: 16/531, loss: 0.014228818006813526
2023-01-24 09:06:27.014655: step: 20/531, loss: 0.004030162934213877
2023-01-24 09:06:28.058091: step: 24/531, loss: 2.4266817490570247e-05
2023-01-24 09:06:29.109806: step: 28/531, loss: 0.0005736157763749361
2023-01-24 09:06:30.161855: step: 32/531, loss: 3.7223713889034116e-07
2023-01-24 09:06:31.214442: step: 36/531, loss: 5.96017598581966e-05
2023-01-24 09:06:32.260612: step: 40/531, loss: 0.0005894675850868225
2023-01-24 09:06:33.328146: step: 44/531, loss: 6.176848273753421e-06
2023-01-24 09:06:34.366116: step: 48/531, loss: 0.0005704265204258263
2023-01-24 09:06:35.429346: step: 52/531, loss: 0.0005432062316685915
2023-01-24 09:06:36.495441: step: 56/531, loss: 0.0004931489238515496
2023-01-24 09:06:37.550286: step: 60/531, loss: 0.0002893197815865278
2023-01-24 09:06:38.596541: step: 64/531, loss: 4.104947493033251e-06
2023-01-24 09:06:39.662605: step: 68/531, loss: 0.0009174162405543029
2023-01-24 09:06:40.709506: step: 72/531, loss: 6.550588295795023e-05
2023-01-24 09:06:41.757738: step: 76/531, loss: 0.0011277872836217284
2023-01-24 09:06:42.861247: step: 80/531, loss: 0.000191867962712422
2023-01-24 09:06:43.936024: step: 84/531, loss: 0.0001913226442411542
2023-01-24 09:06:44.985700: step: 88/531, loss: 0.002417304553091526
2023-01-24 09:06:46.032102: step: 92/531, loss: 6.102600764279487e-06
2023-01-24 09:06:47.093473: step: 96/531, loss: 0.0005290848203003407
2023-01-24 09:06:48.151889: step: 100/531, loss: 0.003285954473540187
2023-01-24 09:06:49.205983: step: 104/531, loss: 0.001333567313849926
2023-01-24 09:06:50.264293: step: 108/531, loss: 0.0017132742796093225
2023-01-24 09:06:51.325711: step: 112/531, loss: 0.0012153297429904342
2023-01-24 09:06:52.386680: step: 116/531, loss: 5.01338081448921e-06
2023-01-24 09:06:53.455635: step: 120/531, loss: 4.283738962840289e-05
2023-01-24 09:06:54.514640: step: 124/531, loss: 0.015718642622232437
2023-01-24 09:06:55.562750: step: 128/531, loss: 0.003705643117427826
2023-01-24 09:06:56.617026: step: 132/531, loss: 0.006282275076955557
2023-01-24 09:06:57.686080: step: 136/531, loss: 0.003376021981239319
2023-01-24 09:06:58.746757: step: 140/531, loss: 0.019055599346756935
2023-01-24 09:06:59.808189: step: 144/531, loss: 0.00339406356215477
2023-01-24 09:07:00.852462: step: 148/531, loss: 0.0013628635788336396
2023-01-24 09:07:01.912458: step: 152/531, loss: 0.00034405544283799827
2023-01-24 09:07:02.986872: step: 156/531, loss: 0.05066709220409393
2023-01-24 09:07:04.032942: step: 160/531, loss: 3.862890309846989e-07
2023-01-24 09:07:05.093435: step: 164/531, loss: 0.00048249500105157495
2023-01-24 09:07:06.152931: step: 168/531, loss: 0.0006777556263841689
2023-01-24 09:07:07.216623: step: 172/531, loss: 0.005137070547789335
2023-01-24 09:07:08.272192: step: 176/531, loss: 0.002855887869372964
2023-01-24 09:07:09.321419: step: 180/531, loss: 0.003073526080697775
2023-01-24 09:07:10.383903: step: 184/531, loss: 0.005185392219573259
2023-01-24 09:07:11.428321: step: 188/531, loss: 0.015075264498591423
2023-01-24 09:07:12.496668: step: 192/531, loss: 0.028791431337594986
2023-01-24 09:07:13.559339: step: 196/531, loss: 0.0004028986149933189
2023-01-24 09:07:14.617322: step: 200/531, loss: 0.0001295555121032521
2023-01-24 09:07:15.702730: step: 204/531, loss: 2.0119448890909553e-05
2023-01-24 09:07:16.758760: step: 208/531, loss: 0.008962638676166534
2023-01-24 09:07:17.809014: step: 212/531, loss: 0.00038685271283611655
2023-01-24 09:07:18.872707: step: 216/531, loss: 0.0024822228588163853
2023-01-24 09:07:19.937921: step: 220/531, loss: 0.00011196519335499033
2023-01-24 09:07:20.996783: step: 224/531, loss: 0.003326332662254572
2023-01-24 09:07:22.047156: step: 228/531, loss: 0.00796507578343153
2023-01-24 09:07:23.109568: step: 232/531, loss: 0.0005102449795231223
2023-01-24 09:07:24.173951: step: 236/531, loss: 0.00311223603785038
2023-01-24 09:07:25.230811: step: 240/531, loss: 2.756703487705181e-08
2023-01-24 09:07:26.309622: step: 244/531, loss: 0.02590913325548172
2023-01-24 09:07:27.362379: step: 248/531, loss: 2.674696588655934e-07
2023-01-24 09:07:28.415942: step: 252/531, loss: 0.0026235536206513643
2023-01-24 09:07:29.477955: step: 256/531, loss: 0.0032511844765394926
2023-01-24 09:07:30.534192: step: 260/531, loss: 0.003585663391277194
2023-01-24 09:07:31.601943: step: 264/531, loss: 0.0010120905935764313
2023-01-24 09:07:32.656895: step: 268/531, loss: 0.009389442391693592
2023-01-24 09:07:33.709600: step: 272/531, loss: 0.005816968157887459
2023-01-24 09:07:34.780182: step: 276/531, loss: 5.3155639761826023e-05
2023-01-24 09:07:35.849990: step: 280/531, loss: 0.06498151272535324
2023-01-24 09:07:36.916114: step: 284/531, loss: 0.0005738885374739766
2023-01-24 09:07:37.985620: step: 288/531, loss: 0.001633531996048987
2023-01-24 09:07:39.037287: step: 292/531, loss: 0.0004886495298705995
2023-01-24 09:07:40.108048: step: 296/531, loss: 0.0012550371466204524
2023-01-24 09:07:41.171418: step: 300/531, loss: 0.0018726540729403496
2023-01-24 09:07:42.233779: step: 304/531, loss: 0.02041521854698658
2023-01-24 09:07:43.302529: step: 308/531, loss: 0.0008746792445890605
2023-01-24 09:07:44.347770: step: 312/531, loss: 9.644900273997337e-05
2023-01-24 09:07:45.399562: step: 316/531, loss: 2.1154372007003985e-05
2023-01-24 09:07:46.460970: step: 320/531, loss: 0.0011407661950215697
2023-01-24 09:07:47.548905: step: 324/531, loss: 3.353166175656952e-05
2023-01-24 09:07:48.613332: step: 328/531, loss: 0.0018475366523489356
2023-01-24 09:07:49.682466: step: 332/531, loss: 0.0031339076813310385
2023-01-24 09:07:50.744693: step: 336/531, loss: 0.0033028284087777138
2023-01-24 09:07:51.781745: step: 340/531, loss: 0.0006987291853874922
2023-01-24 09:07:52.853263: step: 344/531, loss: 0.0011328631080687046
2023-01-24 09:07:53.900835: step: 348/531, loss: 0.002451628213748336
2023-01-24 09:07:54.983844: step: 352/531, loss: 0.0006278029759414494
2023-01-24 09:07:56.045181: step: 356/531, loss: 0.0001840236218413338
2023-01-24 09:07:57.106646: step: 360/531, loss: 0.0023397752083837986
2023-01-24 09:07:58.179063: step: 364/531, loss: 6.0871720052091405e-05
2023-01-24 09:07:59.228233: step: 368/531, loss: 0.003471350995823741
2023-01-24 09:08:00.282029: step: 372/531, loss: 1.0894418664975092e-05
2023-01-24 09:08:01.343520: step: 376/531, loss: 0.004536926280707121
2023-01-24 09:08:02.394436: step: 380/531, loss: 0.02280188724398613
2023-01-24 09:08:03.466675: step: 384/531, loss: 0.008394991047680378
2023-01-24 09:08:04.518688: step: 388/531, loss: 0.0010285151656717062
2023-01-24 09:08:05.573438: step: 392/531, loss: 0.0001164698987849988
2023-01-24 09:08:06.619457: step: 396/531, loss: 0.0024222531355917454
2023-01-24 09:08:07.685633: step: 400/531, loss: 0.007004153914749622
2023-01-24 09:08:08.743288: step: 404/531, loss: 0.005112409126013517
2023-01-24 09:08:09.824835: step: 408/531, loss: 0.002449022140353918
2023-01-24 09:08:10.880826: step: 412/531, loss: 0.0012433696538209915
2023-01-24 09:08:11.971402: step: 416/531, loss: 0.0034635982010513544
2023-01-24 09:08:13.030898: step: 420/531, loss: 8.951136987889186e-05
2023-01-24 09:08:14.084445: step: 424/531, loss: 6.893683166708797e-05
2023-01-24 09:08:15.135873: step: 428/531, loss: 0.0013753804378211498
2023-01-24 09:08:16.194909: step: 432/531, loss: 0.0008506132289767265
2023-01-24 09:08:17.248781: step: 436/531, loss: 0.006601061671972275
2023-01-24 09:08:18.311265: step: 440/531, loss: 0.0018112276447936893
2023-01-24 09:08:19.373874: step: 444/531, loss: 0.0013045002706348896
2023-01-24 09:08:20.429447: step: 448/531, loss: 0.02691497839987278
2023-01-24 09:08:21.491296: step: 452/531, loss: 0.0008497920935042202
2023-01-24 09:08:22.558185: step: 456/531, loss: 0.02311461977660656
2023-01-24 09:08:23.612882: step: 460/531, loss: 0.005335524678230286
2023-01-24 09:08:24.679596: step: 464/531, loss: 0.007260491140186787
2023-01-24 09:08:25.737681: step: 468/531, loss: 1.8389975593890995e-05
2023-01-24 09:08:26.796338: step: 472/531, loss: 0.0013945504324510694
2023-01-24 09:08:27.868407: step: 476/531, loss: 0.0002992226800415665
2023-01-24 09:08:28.941468: step: 480/531, loss: 0.0002105611638398841
2023-01-24 09:08:30.024065: step: 484/531, loss: 0.0013609671732410789
2023-01-24 09:08:31.083669: step: 488/531, loss: 0.0008427142747677863
2023-01-24 09:08:32.143237: step: 492/531, loss: 0.0007751102675683796
2023-01-24 09:08:33.205438: step: 496/531, loss: 0.0017394828610122204
2023-01-24 09:08:34.250422: step: 500/531, loss: 0.00013782230962533504
2023-01-24 09:08:35.321683: step: 504/531, loss: 0.002614665310829878
2023-01-24 09:08:36.382407: step: 508/531, loss: 8.849025471135974e-05
2023-01-24 09:08:37.441990: step: 512/531, loss: 0.0023913762997835875
2023-01-24 09:08:38.506990: step: 516/531, loss: 0.010207696817815304
2023-01-24 09:08:39.555471: step: 520/531, loss: 5.8562844060361385e-05
2023-01-24 09:08:40.614550: step: 524/531, loss: 0.002058700891211629
2023-01-24 09:08:41.680778: step: 528/531, loss: 0.009050062857568264
2023-01-24 09:08:42.745609: step: 532/531, loss: 0.0024040727876126766
2023-01-24 09:08:43.804487: step: 536/531, loss: 0.001865816069766879
2023-01-24 09:08:44.868131: step: 540/531, loss: 0.0001078991626854986
2023-01-24 09:08:45.925268: step: 544/531, loss: 0.010045819915831089
2023-01-24 09:08:46.989288: step: 548/531, loss: 0.009184224531054497
2023-01-24 09:08:48.063771: step: 552/531, loss: 0.0005415479536168277
2023-01-24 09:08:49.113328: step: 556/531, loss: 0.002615584060549736
2023-01-24 09:08:50.192036: step: 560/531, loss: 0.0029433947056531906
2023-01-24 09:08:51.237112: step: 564/531, loss: 0.0005840560188516974
2023-01-24 09:08:52.297684: step: 568/531, loss: 0.00246348581276834
2023-01-24 09:08:53.341037: step: 572/531, loss: 0.009433802217245102
2023-01-24 09:08:54.430065: step: 576/531, loss: 0.00531425466760993
2023-01-24 09:08:55.482804: step: 580/531, loss: 0.0005168463685549796
2023-01-24 09:08:56.574625: step: 584/531, loss: 3.3897554203576874e-06
2023-01-24 09:08:57.644109: step: 588/531, loss: 0.002574296435341239
2023-01-24 09:08:58.704978: step: 592/531, loss: 0.00025103468215093017
2023-01-24 09:08:59.765566: step: 596/531, loss: 0.001993694109842181
2023-01-24 09:09:00.809367: step: 600/531, loss: 0.002243879484012723
2023-01-24 09:09:01.857326: step: 604/531, loss: 0.0013005051296204329
2023-01-24 09:09:02.909789: step: 608/531, loss: 0.010430709458887577
2023-01-24 09:09:03.968971: step: 612/531, loss: 0.0028112977743148804
2023-01-24 09:09:05.012990: step: 616/531, loss: 0.004245677497237921
2023-01-24 09:09:06.096977: step: 620/531, loss: 5.233210322330706e-05
2023-01-24 09:09:07.165351: step: 624/531, loss: 0.006031180266290903
2023-01-24 09:09:08.235813: step: 628/531, loss: 0.00013853635755367577
2023-01-24 09:09:09.302703: step: 632/531, loss: 0.0033995884004980326
2023-01-24 09:09:10.364345: step: 636/531, loss: 0.001307119382545352
2023-01-24 09:09:11.421771: step: 640/531, loss: 0.008930394425988197
2023-01-24 09:09:12.474585: step: 644/531, loss: 0.0031377198174595833
2023-01-24 09:09:13.545919: step: 648/531, loss: 0.0035512649919837713
2023-01-24 09:09:14.590638: step: 652/531, loss: 0.00042117098928429186
2023-01-24 09:09:15.641114: step: 656/531, loss: 4.277531843399629e-05
2023-01-24 09:09:16.689097: step: 660/531, loss: 0.001540513476356864
2023-01-24 09:09:17.753521: step: 664/531, loss: 2.4710610887268558e-05
2023-01-24 09:09:18.825467: step: 668/531, loss: 0.00015206642274279147
2023-01-24 09:09:19.888710: step: 672/531, loss: 4.5043583668302745e-05
2023-01-24 09:09:20.952198: step: 676/531, loss: 0.00015633433940820396
2023-01-24 09:09:22.034267: step: 680/531, loss: 0.0017591443611308932
2023-01-24 09:09:23.086469: step: 684/531, loss: 0.0011856822529807687
2023-01-24 09:09:24.148244: step: 688/531, loss: 0.0006078141741454601
2023-01-24 09:09:25.220942: step: 692/531, loss: 0.0031036208383738995
2023-01-24 09:09:26.264896: step: 696/531, loss: 0.0007459915359504521
2023-01-24 09:09:27.325327: step: 700/531, loss: 0.0021458277478814125
2023-01-24 09:09:28.380360: step: 704/531, loss: 0.0023647055495530367
2023-01-24 09:09:29.439249: step: 708/531, loss: 0.000632931652944535
2023-01-24 09:09:30.501833: step: 712/531, loss: 0.0003922057512681931
2023-01-24 09:09:31.567437: step: 716/531, loss: 0.00011879483645316213
2023-01-24 09:09:32.629403: step: 720/531, loss: 0.0027899756096303463
2023-01-24 09:09:33.703544: step: 724/531, loss: 0.004695042502135038
2023-01-24 09:09:34.772633: step: 728/531, loss: 0.005567705258727074
2023-01-24 09:09:35.807334: step: 732/531, loss: 1.5464847820112482e-05
2023-01-24 09:09:36.886755: step: 736/531, loss: 0.006585231516510248
2023-01-24 09:09:37.946377: step: 740/531, loss: 0.0009290744201280177
2023-01-24 09:09:39.008489: step: 744/531, loss: 0.00033880904084071517
2023-01-24 09:09:40.056294: step: 748/531, loss: 0.009083887562155724
2023-01-24 09:09:41.120711: step: 752/531, loss: 0.000487333454657346
2023-01-24 09:09:42.185095: step: 756/531, loss: 0.001678626169450581
2023-01-24 09:09:43.241987: step: 760/531, loss: 0.0068448614329099655
2023-01-24 09:09:44.301933: step: 764/531, loss: 9.049963409779593e-05
2023-01-24 09:09:45.364198: step: 768/531, loss: 0.001556702540256083
2023-01-24 09:09:46.414678: step: 772/531, loss: 8.323080692207441e-05
2023-01-24 09:09:47.468385: step: 776/531, loss: 0.003015171969309449
2023-01-24 09:09:48.546612: step: 780/531, loss: 5.8750854805111885e-05
2023-01-24 09:09:49.611487: step: 784/531, loss: 0.004141016397625208
2023-01-24 09:09:50.656809: step: 788/531, loss: 0.0003056746209040284
2023-01-24 09:09:51.740664: step: 792/531, loss: 0.002190647181123495
2023-01-24 09:09:52.804155: step: 796/531, loss: 0.008782587945461273
2023-01-24 09:09:53.844624: step: 800/531, loss: 9.042941383086145e-05
2023-01-24 09:09:54.896151: step: 804/531, loss: 2.3222064555739053e-05
2023-01-24 09:09:55.962533: step: 808/531, loss: 0.002266150899231434
2023-01-24 09:09:57.039261: step: 812/531, loss: 0.0021656586322933435
2023-01-24 09:09:58.091762: step: 816/531, loss: 0.0013136636698618531
2023-01-24 09:09:59.159784: step: 820/531, loss: 0.011663348414003849
2023-01-24 09:10:00.230905: step: 824/531, loss: 0.0018752312753349543
2023-01-24 09:10:01.295890: step: 828/531, loss: 0.00010874243162106723
2023-01-24 09:10:02.362939: step: 832/531, loss: 0.005236182827502489
2023-01-24 09:10:03.421602: step: 836/531, loss: 0.0011878821533173323
2023-01-24 09:10:04.483418: step: 840/531, loss: 0.00010246843885397539
2023-01-24 09:10:05.533732: step: 844/531, loss: 0.0002533915394451469
2023-01-24 09:10:06.598350: step: 848/531, loss: 0.0018395517254248261
2023-01-24 09:10:07.660681: step: 852/531, loss: 0.0007976075867190957
2023-01-24 09:10:08.724348: step: 856/531, loss: 0.0007676354143768549
2023-01-24 09:10:09.760796: step: 860/531, loss: 5.7634802942629904e-05
2023-01-24 09:10:10.817525: step: 864/531, loss: 0.00012060361768817529
2023-01-24 09:10:11.892207: step: 868/531, loss: 2.1103191102156416e-05
2023-01-24 09:10:12.960082: step: 872/531, loss: 0.002773697255179286
2023-01-24 09:10:14.028154: step: 876/531, loss: 0.012475637719035149
2023-01-24 09:10:15.086856: step: 880/531, loss: 0.0020901283714920282
2023-01-24 09:10:16.141901: step: 884/531, loss: 0.01291695050895214
2023-01-24 09:10:17.191455: step: 888/531, loss: 0.0031730765476822853
2023-01-24 09:10:18.266009: step: 892/531, loss: 0.0004845313960686326
2023-01-24 09:10:19.317181: step: 896/531, loss: 0.008706407621502876
2023-01-24 09:10:20.371236: step: 900/531, loss: 0.003484827233478427
2023-01-24 09:10:21.409157: step: 904/531, loss: 3.822789039986674e-06
2023-01-24 09:10:22.468511: step: 908/531, loss: 3.733766789082438e-05
2023-01-24 09:10:23.543679: step: 912/531, loss: 0.0067475964315235615
2023-01-24 09:10:24.612826: step: 916/531, loss: 0.00026243983302265406
2023-01-24 09:10:25.671784: step: 920/531, loss: 0.0004947097040712833
2023-01-24 09:10:26.735572: step: 924/531, loss: 0.005439384374767542
2023-01-24 09:10:27.811994: step: 928/531, loss: 0.0027062678709626198
2023-01-24 09:10:28.883663: step: 932/531, loss: 0.002772000851109624
2023-01-24 09:10:29.946843: step: 936/531, loss: 0.007011901121586561
2023-01-24 09:10:31.019450: step: 940/531, loss: 4.114015246159397e-05
2023-01-24 09:10:32.077388: step: 944/531, loss: 0.0011345319217070937
2023-01-24 09:10:33.150913: step: 948/531, loss: 0.0015942688332870603
2023-01-24 09:10:34.207002: step: 952/531, loss: 0.0003534366551321
2023-01-24 09:10:35.264183: step: 956/531, loss: 0.0025519435293972492
2023-01-24 09:10:36.320289: step: 960/531, loss: 0.00010970090079354122
2023-01-24 09:10:37.394343: step: 964/531, loss: 0.01113598607480526
2023-01-24 09:10:38.446928: step: 968/531, loss: 0.00017252523684874177
2023-01-24 09:10:39.510954: step: 972/531, loss: 1.4288384591054637e-06
2023-01-24 09:10:40.574072: step: 976/531, loss: 0.00038461951771751046
2023-01-24 09:10:41.613800: step: 980/531, loss: 0.00841082725673914
2023-01-24 09:10:42.694074: step: 984/531, loss: 0.007877668365836143
2023-01-24 09:10:43.765233: step: 988/531, loss: 0.0018787410808727145
2023-01-24 09:10:44.831739: step: 992/531, loss: 0.0022774848621338606
2023-01-24 09:10:45.900529: step: 996/531, loss: 0.0013377065770328045
2023-01-24 09:10:46.967445: step: 1000/531, loss: 0.009514780715107918
2023-01-24 09:10:48.022564: step: 1004/531, loss: 0.0007354762055911124
2023-01-24 09:10:49.081546: step: 1008/531, loss: 0.004189879167824984
2023-01-24 09:10:50.143183: step: 1012/531, loss: 0.0005681710899807513
2023-01-24 09:10:51.201634: step: 1016/531, loss: 0.0024610937107354403
2023-01-24 09:10:52.271388: step: 1020/531, loss: 3.1502804631600156e-05
2023-01-24 09:10:53.335027: step: 1024/531, loss: 0.008294281549751759
2023-01-24 09:10:54.398494: step: 1028/531, loss: 0.0022488790564239025
2023-01-24 09:10:55.472610: step: 1032/531, loss: 0.0004743848112411797
2023-01-24 09:10:56.523056: step: 1036/531, loss: 0.0001802453916752711
2023-01-24 09:10:57.587365: step: 1040/531, loss: 0.005130332428961992
2023-01-24 09:10:58.661118: step: 1044/531, loss: 0.003923649899661541
2023-01-24 09:10:59.727362: step: 1048/531, loss: 0.005003295838832855
2023-01-24 09:11:00.804429: step: 1052/531, loss: 0.0006852123187854886
2023-01-24 09:11:01.864634: step: 1056/531, loss: 0.0021669233683496714
2023-01-24 09:11:02.917581: step: 1060/531, loss: 0.00403800792992115
2023-01-24 09:11:03.973917: step: 1064/531, loss: 0.0019535867031663656
2023-01-24 09:11:05.024144: step: 1068/531, loss: 0.0006539862952195108
2023-01-24 09:11:06.085394: step: 1072/531, loss: 0.0026660149451345205
2023-01-24 09:11:07.155888: step: 1076/531, loss: 0.000419384625274688
2023-01-24 09:11:08.212963: step: 1080/531, loss: 0.0021252762526273727
2023-01-24 09:11:09.274285: step: 1084/531, loss: 0.0013478387845680118
2023-01-24 09:11:10.334714: step: 1088/531, loss: 0.0012972408439964056
2023-01-24 09:11:11.394351: step: 1092/531, loss: 0.0012924638576805592
2023-01-24 09:11:12.462920: step: 1096/531, loss: 0.008009380660951138
2023-01-24 09:11:13.516331: step: 1100/531, loss: 0.006106253247708082
2023-01-24 09:11:14.584873: step: 1104/531, loss: 0.00010837097943294793
2023-01-24 09:11:15.640255: step: 1108/531, loss: 0.0015323911793529987
2023-01-24 09:11:16.708154: step: 1112/531, loss: 0.0028600089717656374
2023-01-24 09:11:17.767566: step: 1116/531, loss: 0.0012562470510601997
2023-01-24 09:11:18.844096: step: 1120/531, loss: 0.002116288524121046
2023-01-24 09:11:19.907292: step: 1124/531, loss: 0.00265909219160676
2023-01-24 09:11:20.970333: step: 1128/531, loss: 0.0002130574284819886
2023-01-24 09:11:22.045923: step: 1132/531, loss: 0.012329761870205402
2023-01-24 09:11:23.106381: step: 1136/531, loss: 1.3047178072156385e-05
2023-01-24 09:11:24.189420: step: 1140/531, loss: 0.002820062916725874
2023-01-24 09:11:25.264781: step: 1144/531, loss: 0.008172815665602684
2023-01-24 09:11:26.321013: step: 1148/531, loss: 0.0018082704627886415
2023-01-24 09:11:27.366938: step: 1152/531, loss: 0.001671980251558125
2023-01-24 09:11:28.419469: step: 1156/531, loss: 0.0006852815859019756
2023-01-24 09:11:29.483061: step: 1160/531, loss: 0.0011829659342765808
2023-01-24 09:11:30.535458: step: 1164/531, loss: 0.0006814971566200256
2023-01-24 09:11:31.599824: step: 1168/531, loss: 0.00020453993056435138
2023-01-24 09:11:32.654825: step: 1172/531, loss: 0.0004027107497677207
2023-01-24 09:11:33.714878: step: 1176/531, loss: 0.0015277061611413956
2023-01-24 09:11:34.772281: step: 1180/531, loss: 0.0008155119721777737
2023-01-24 09:11:35.856194: step: 1184/531, loss: 0.0005716923042200506
2023-01-24 09:11:36.928901: step: 1188/531, loss: 0.0046284436248242855
2023-01-24 09:11:38.001020: step: 1192/531, loss: 2.9455501135089435e-05
2023-01-24 09:11:39.082273: step: 1196/531, loss: 0.00408748397603631
2023-01-24 09:11:40.164231: step: 1200/531, loss: 0.008765937760472298
2023-01-24 09:11:41.205216: step: 1204/531, loss: 0.0019150781445205212
2023-01-24 09:11:42.309592: step: 1208/531, loss: 0.0024314725305885077
2023-01-24 09:11:43.373658: step: 1212/531, loss: 0.0006124668288975954
2023-01-24 09:11:44.439753: step: 1216/531, loss: 0.0008364720270037651
2023-01-24 09:11:45.499307: step: 1220/531, loss: 0.0021727036219090223
2023-01-24 09:11:46.571909: step: 1224/531, loss: 0.006255180574953556
2023-01-24 09:11:47.638182: step: 1228/531, loss: 0.003896774258464575
2023-01-24 09:11:48.707620: step: 1232/531, loss: 0.0027974562253803015
2023-01-24 09:11:49.775660: step: 1236/531, loss: 0.00645783357322216
2023-01-24 09:11:50.839392: step: 1240/531, loss: 0.010734925977885723
2023-01-24 09:11:51.898871: step: 1244/531, loss: 0.012926846742630005
2023-01-24 09:11:52.958992: step: 1248/531, loss: 0.00047558307414874434
2023-01-24 09:11:54.023655: step: 1252/531, loss: 2.039467290160246e-06
2023-01-24 09:11:55.071107: step: 1256/531, loss: 7.810291208443232e-06
2023-01-24 09:11:56.140787: step: 1260/531, loss: 0.0014118080725893378
2023-01-24 09:11:57.208703: step: 1264/531, loss: 0.0031001614406704903
2023-01-24 09:11:58.263626: step: 1268/531, loss: 8.220275776693597e-05
2023-01-24 09:11:59.344573: step: 1272/531, loss: 0.010749181732535362
2023-01-24 09:12:00.410861: step: 1276/531, loss: 0.011678296141326427
2023-01-24 09:12:01.482420: step: 1280/531, loss: 0.0004900435451418161
2023-01-24 09:12:02.536387: step: 1284/531, loss: 0.0007815133430995047
2023-01-24 09:12:03.595072: step: 1288/531, loss: 0.0022290016058832407
2023-01-24 09:12:04.666608: step: 1292/531, loss: 0.0035079398658126593
2023-01-24 09:12:05.723028: step: 1296/531, loss: 0.0026895743794739246
2023-01-24 09:12:06.782435: step: 1300/531, loss: 6.101379403844476e-05
2023-01-24 09:12:07.842583: step: 1304/531, loss: 0.00020624278113245964
2023-01-24 09:12:08.925995: step: 1308/531, loss: 0.008379470556974411
2023-01-24 09:12:09.981526: step: 1312/531, loss: 0.0021498200949281454
2023-01-24 09:12:11.048746: step: 1316/531, loss: 0.0001793982955859974
2023-01-24 09:12:12.104008: step: 1320/531, loss: 0.0012288064463064075
2023-01-24 09:12:13.158560: step: 1324/531, loss: 0.00017002425738610327
2023-01-24 09:12:14.214220: step: 1328/531, loss: 0.0027397775556892157
2023-01-24 09:12:15.293365: step: 1332/531, loss: 0.005439895670861006
2023-01-24 09:12:16.357415: step: 1336/531, loss: 0.00027735059848055243
2023-01-24 09:12:17.416063: step: 1340/531, loss: 0.010006377473473549
2023-01-24 09:12:18.497162: step: 1344/531, loss: 0.002805290976539254
2023-01-24 09:12:19.563190: step: 1348/531, loss: 0.007355965208262205
2023-01-24 09:12:20.609896: step: 1352/531, loss: 0.007107268553227186
2023-01-24 09:12:21.665082: step: 1356/531, loss: 0.00012731105380225927
2023-01-24 09:12:22.743938: step: 1360/531, loss: 0.0011664126068353653
2023-01-24 09:12:23.826071: step: 1364/531, loss: 0.0142782311886549
2023-01-24 09:12:24.886980: step: 1368/531, loss: 6.176657620926562e-07
2023-01-24 09:12:25.963225: step: 1372/531, loss: 0.0015357902739197016
2023-01-24 09:12:27.031032: step: 1376/531, loss: 0.0008353438461199403
2023-01-24 09:12:28.099555: step: 1380/531, loss: 1.4515704606310464e-05
2023-01-24 09:12:29.155375: step: 1384/531, loss: 0.00016583810793235898
2023-01-24 09:12:30.214312: step: 1388/531, loss: 0.0017000462394207716
2023-01-24 09:12:31.276193: step: 1392/531, loss: 7.207140151876956e-05
2023-01-24 09:12:32.332046: step: 1396/531, loss: 0.00355811626650393
2023-01-24 09:12:33.393833: step: 1400/531, loss: 0.008616171777248383
2023-01-24 09:12:34.476702: step: 1404/531, loss: 0.00039798705256544054
2023-01-24 09:12:35.552170: step: 1408/531, loss: 0.003896415699273348
2023-01-24 09:12:36.626891: step: 1412/531, loss: 0.0013024717336520553
2023-01-24 09:12:37.688225: step: 1416/531, loss: 0.0007592260953970253
2023-01-24 09:12:38.751912: step: 1420/531, loss: 0.002464998047798872
2023-01-24 09:12:39.808096: step: 1424/531, loss: 0.00017223262693732977
2023-01-24 09:12:40.878351: step: 1428/531, loss: 0.004593865945935249
2023-01-24 09:12:41.939028: step: 1432/531, loss: 0.0008349682902917266
2023-01-24 09:12:43.002655: step: 1436/531, loss: 0.0006441331934183836
2023-01-24 09:12:44.071635: step: 1440/531, loss: 0.0006603756919503212
2023-01-24 09:12:45.136860: step: 1444/531, loss: 0.002461852738633752
2023-01-24 09:12:46.210835: step: 1448/531, loss: 0.0050451443530619144
2023-01-24 09:12:47.279931: step: 1452/531, loss: 0.0010527916019782424
2023-01-24 09:12:48.337877: step: 1456/531, loss: 0.0010714300442487001
2023-01-24 09:12:49.396302: step: 1460/531, loss: 0.00045495573431253433
2023-01-24 09:12:50.459067: step: 1464/531, loss: 0.00023459554358851165
2023-01-24 09:12:51.530441: step: 1468/531, loss: 0.002179292496293783
2023-01-24 09:12:52.593301: step: 1472/531, loss: 7.718374399701133e-05
2023-01-24 09:12:53.657802: step: 1476/531, loss: 0.004777817986905575
2023-01-24 09:12:54.712713: step: 1480/531, loss: 0.0001367541990475729
2023-01-24 09:12:55.778837: step: 1484/531, loss: 0.0012707796413451433
2023-01-24 09:12:56.842036: step: 1488/531, loss: 0.0007572412141598761
2023-01-24 09:12:57.891653: step: 1492/531, loss: 0.0033923774026334286
2023-01-24 09:12:58.945229: step: 1496/531, loss: 0.00013735836546402425
2023-01-24 09:13:00.012591: step: 1500/531, loss: 0.006993074435740709
2023-01-24 09:13:01.073231: step: 1504/531, loss: 0.010927842929959297
2023-01-24 09:13:02.130989: step: 1508/531, loss: 3.1120273433771217e-06
2023-01-24 09:13:03.185383: step: 1512/531, loss: 0.0022322058212012053
2023-01-24 09:13:04.235005: step: 1516/531, loss: 0.00124601018615067
2023-01-24 09:13:05.298625: step: 1520/531, loss: 0.0005221243482083082
2023-01-24 09:13:06.375554: step: 1524/531, loss: 0.0013709780760109425
2023-01-24 09:13:07.445020: step: 1528/531, loss: 0.00789638515561819
2023-01-24 09:13:08.516621: step: 1532/531, loss: 0.0008394402102567255
2023-01-24 09:13:09.573170: step: 1536/531, loss: 0.004712972324341536
2023-01-24 09:13:10.637553: step: 1540/531, loss: 0.005781758576631546
2023-01-24 09:13:11.707649: step: 1544/531, loss: 0.00011162083683302626
2023-01-24 09:13:12.769277: step: 1548/531, loss: 0.0014038147637620568
2023-01-24 09:13:13.829713: step: 1552/531, loss: 0.0007645799778401852
2023-01-24 09:13:14.886964: step: 1556/531, loss: 0.0005982242291793227
2023-01-24 09:13:15.927968: step: 1560/531, loss: 0.00030596094438806176
2023-01-24 09:13:16.979455: step: 1564/531, loss: 0.002186855534091592
2023-01-24 09:13:18.039364: step: 1568/531, loss: 0.0036535398103296757
2023-01-24 09:13:19.101747: step: 1572/531, loss: 0.014048433862626553
2023-01-24 09:13:20.155836: step: 1576/531, loss: 0.00051969412015751
2023-01-24 09:13:21.236213: step: 1580/531, loss: 0.007731867954134941
2023-01-24 09:13:22.306658: step: 1584/531, loss: 0.0045402473770082
2023-01-24 09:13:23.363835: step: 1588/531, loss: 1.7715603462420404e-05
2023-01-24 09:13:24.431193: step: 1592/531, loss: 0.006822424009442329
2023-01-24 09:13:25.486540: step: 1596/531, loss: 0.00033602677285671234
2023-01-24 09:13:26.563687: step: 1600/531, loss: 0.002748908242210746
2023-01-24 09:13:27.668440: step: 1604/531, loss: 0.00048170171794481575
2023-01-24 09:13:28.719132: step: 1608/531, loss: 0.0011635019909590483
2023-01-24 09:13:29.771378: step: 1612/531, loss: 0.000495315354783088
2023-01-24 09:13:30.852281: step: 1616/531, loss: 0.0033146708738058805
2023-01-24 09:13:31.942971: step: 1620/531, loss: 0.0024260953068733215
2023-01-24 09:13:33.014055: step: 1624/531, loss: 0.008035477250814438
2023-01-24 09:13:34.081410: step: 1628/531, loss: 6.469494837801903e-05
2023-01-24 09:13:35.139177: step: 1632/531, loss: 0.0003750807954929769
2023-01-24 09:13:36.197336: step: 1636/531, loss: 0.003918210975825787
2023-01-24 09:13:37.256885: step: 1640/531, loss: 0.0013503653462976217
2023-01-24 09:13:38.308984: step: 1644/531, loss: 0.006134611554443836
2023-01-24 09:13:39.377042: step: 1648/531, loss: 0.0006110779359005392
2023-01-24 09:13:40.450045: step: 1652/531, loss: 2.8610174922505394e-05
2023-01-24 09:13:41.518319: step: 1656/531, loss: 0.00261300103738904
2023-01-24 09:13:42.598463: step: 1660/531, loss: 0.0012822758872061968
2023-01-24 09:13:43.651434: step: 1664/531, loss: 0.006871582940220833
2023-01-24 09:13:44.714816: step: 1668/531, loss: 0.008112279698252678
2023-01-24 09:13:45.765736: step: 1672/531, loss: 0.0027954818215221167
2023-01-24 09:13:46.838803: step: 1676/531, loss: 0.0009296463103964925
2023-01-24 09:13:47.908030: step: 1680/531, loss: 0.007145033683627844
2023-01-24 09:13:48.988219: step: 1684/531, loss: 0.010795000940561295
2023-01-24 09:13:50.037895: step: 1688/531, loss: 0.0046673426404595375
2023-01-24 09:13:51.096330: step: 1692/531, loss: 8.890879854561717e-08
2023-01-24 09:13:52.162101: step: 1696/531, loss: 6.748306986992247e-06
2023-01-24 09:13:53.220274: step: 1700/531, loss: 0.003095329040661454
2023-01-24 09:13:54.286249: step: 1704/531, loss: 0.0003643136296886951
2023-01-24 09:13:55.354449: step: 1708/531, loss: 0.009540271945297718
2023-01-24 09:13:56.408329: step: 1712/531, loss: 0.026444517076015472
2023-01-24 09:13:57.486956: step: 1716/531, loss: 0.005372142884880304
2023-01-24 09:13:58.550618: step: 1720/531, loss: 0.007801800966262817
2023-01-24 09:13:59.603463: step: 1724/531, loss: 0.001963839866220951
2023-01-24 09:14:00.658211: step: 1728/531, loss: 0.00029295426793396473
2023-01-24 09:14:01.733970: step: 1732/531, loss: 0.013960192911326885
2023-01-24 09:14:02.820267: step: 1736/531, loss: 0.006792435888200998
2023-01-24 09:14:03.873182: step: 1740/531, loss: 5.365608103602426e-06
2023-01-24 09:14:04.932970: step: 1744/531, loss: 0.0011303460923954844
2023-01-24 09:14:05.992016: step: 1748/531, loss: 0.0009954527486115694
2023-01-24 09:14:07.037456: step: 1752/531, loss: 0.002465495839715004
2023-01-24 09:14:08.105601: step: 1756/531, loss: 0.008292421698570251
2023-01-24 09:14:09.175941: step: 1760/531, loss: 0.008431659080088139
2023-01-24 09:14:10.244407: step: 1764/531, loss: 0.002968426328152418
2023-01-24 09:14:11.320797: step: 1768/531, loss: 0.005722769536077976
2023-01-24 09:14:12.384984: step: 1772/531, loss: 0.0002745292440522462
2023-01-24 09:14:13.448136: step: 1776/531, loss: 0.00303266872651875
2023-01-24 09:14:14.499546: step: 1780/531, loss: 0.0003002272278536111
2023-01-24 09:14:15.550851: step: 1784/531, loss: 0.04699743539094925
2023-01-24 09:14:16.612274: step: 1788/531, loss: 0.0046489122323691845
2023-01-24 09:14:17.690947: step: 1792/531, loss: 0.0056006391532719135
2023-01-24 09:14:18.742622: step: 1796/531, loss: 0.0013820345047861338
2023-01-24 09:14:19.802928: step: 1800/531, loss: 0.00031669222516939044
2023-01-24 09:14:20.861382: step: 1804/531, loss: 0.008193948306143284
2023-01-24 09:14:21.919635: step: 1808/531, loss: 8.414102194365114e-05
2023-01-24 09:14:22.978320: step: 1812/531, loss: 0.0031748320907354355
2023-01-24 09:14:24.029604: step: 1816/531, loss: 0.002375259529799223
2023-01-24 09:14:25.091281: step: 1820/531, loss: 0.0014962980058044195
2023-01-24 09:14:26.148559: step: 1824/531, loss: 5.357582267606631e-05
2023-01-24 09:14:27.201883: step: 1828/531, loss: 0.0003404039307497442
2023-01-24 09:14:28.283431: step: 1832/531, loss: 0.0028575779870152473
2023-01-24 09:14:29.345512: step: 1836/531, loss: 7.783420733176172e-05
2023-01-24 09:14:30.413155: step: 1840/531, loss: 0.000720977084711194
2023-01-24 09:14:31.472515: step: 1844/531, loss: 0.00033143951441161335
2023-01-24 09:14:32.549463: step: 1848/531, loss: 0.004121869802474976
2023-01-24 09:14:33.623757: step: 1852/531, loss: 0.002924948697909713
2023-01-24 09:14:34.707452: step: 1856/531, loss: 0.009038897231221199
2023-01-24 09:14:35.751542: step: 1860/531, loss: 0.006168980151414871
2023-01-24 09:14:36.816840: step: 1864/531, loss: 0.0015159776667132974
2023-01-24 09:14:37.872588: step: 1868/531, loss: 1.2370785952953156e-05
2023-01-24 09:14:38.937806: step: 1872/531, loss: 0.010927345603704453
2023-01-24 09:14:39.991667: step: 1876/531, loss: 0.00023917449289001524
2023-01-24 09:14:41.058113: step: 1880/531, loss: 0.0007985814590938389
2023-01-24 09:14:42.112323: step: 1884/531, loss: 0.027138935402035713
2023-01-24 09:14:43.176948: step: 1888/531, loss: 0.006283156108111143
2023-01-24 09:14:44.238997: step: 1892/531, loss: 0.00152781349606812
2023-01-24 09:14:45.302108: step: 1896/531, loss: 0.008456099778413773
2023-01-24 09:14:46.346438: step: 1900/531, loss: 0.0011861893581226468
2023-01-24 09:14:47.423977: step: 1904/531, loss: 0.014940268360078335
2023-01-24 09:14:48.521473: step: 1908/531, loss: 3.7218098441371694e-05
2023-01-24 09:14:49.588733: step: 1912/531, loss: 0.003133331658318639
2023-01-24 09:14:50.666906: step: 1916/531, loss: 0.0023243161849677563
2023-01-24 09:14:51.719786: step: 1920/531, loss: 0.004547064192593098
2023-01-24 09:14:52.788047: step: 1924/531, loss: 3.5978862342744833e-06
2023-01-24 09:14:53.847433: step: 1928/531, loss: 1.7694386770017445e-05
2023-01-24 09:14:54.906229: step: 1932/531, loss: 0.0010641299886628985
2023-01-24 09:14:55.956069: step: 1936/531, loss: 0.0022202807012945414
2023-01-24 09:14:57.008619: step: 1940/531, loss: 6.821251736255363e-05
2023-01-24 09:14:58.068870: step: 1944/531, loss: 0.004387903492897749
2023-01-24 09:14:59.119447: step: 1948/531, loss: 0.002930429996922612
2023-01-24 09:15:00.187787: step: 1952/531, loss: 0.01775323413312435
2023-01-24 09:15:01.248368: step: 1956/531, loss: 0.008541782386600971
2023-01-24 09:15:02.308815: step: 1960/531, loss: 0.00044180723489262164
2023-01-24 09:15:03.370441: step: 1964/531, loss: 0.0003124934737570584
2023-01-24 09:15:04.450029: step: 1968/531, loss: 0.0374315045773983
2023-01-24 09:15:05.532723: step: 1972/531, loss: 0.0010741597507148981
2023-01-24 09:15:06.582783: step: 1976/531, loss: 3.249061410315335e-05
2023-01-24 09:15:07.664571: step: 1980/531, loss: 0.017730847001075745
2023-01-24 09:15:08.730794: step: 1984/531, loss: 0.00331980362534523
2023-01-24 09:15:09.797390: step: 1988/531, loss: 6.857659172965214e-05
2023-01-24 09:15:10.898718: step: 1992/531, loss: 0.005316200200468302
2023-01-24 09:15:11.969438: step: 1996/531, loss: 0.003829688997939229
2023-01-24 09:15:13.043524: step: 2000/531, loss: 0.004486995283514261
2023-01-24 09:15:14.096308: step: 2004/531, loss: 0.00022211871691979468
2023-01-24 09:15:15.172942: step: 2008/531, loss: 0.0024807052686810493
2023-01-24 09:15:16.232421: step: 2012/531, loss: 0.00013469728583004326
2023-01-24 09:15:17.307277: step: 2016/531, loss: 0.0018274181056767702
2023-01-24 09:15:18.366228: step: 2020/531, loss: 0.0056982324458658695
2023-01-24 09:15:19.431477: step: 2024/531, loss: 7.212285709101707e-05
2023-01-24 09:15:20.487847: step: 2028/531, loss: 0.0008153259404934943
2023-01-24 09:15:21.542856: step: 2032/531, loss: 0.002765039447695017
2023-01-24 09:15:22.602884: step: 2036/531, loss: 0.011484814807772636
2023-01-24 09:15:23.664662: step: 2040/531, loss: 0.00012637648615054786
2023-01-24 09:15:24.717101: step: 2044/531, loss: 0.010979079641401768
2023-01-24 09:15:25.800541: step: 2048/531, loss: 0.009268800728023052
2023-01-24 09:15:26.869652: step: 2052/531, loss: 0.0038686192128807306
2023-01-24 09:15:27.963856: step: 2056/531, loss: 0.0002875272184610367
2023-01-24 09:15:29.043804: step: 2060/531, loss: 0.0007710916106589139
2023-01-24 09:15:30.107692: step: 2064/531, loss: 2.3162293416589819e-07
2023-01-24 09:15:31.152776: step: 2068/531, loss: 1.2665693247981835e-05
2023-01-24 09:15:32.222425: step: 2072/531, loss: 0.00014252541586756706
2023-01-24 09:15:33.278050: step: 2076/531, loss: 0.0003996905288659036
2023-01-24 09:15:34.340792: step: 2080/531, loss: 0.0008978333789855242
2023-01-24 09:15:35.432789: step: 2084/531, loss: 0.0007441990892402828
2023-01-24 09:15:36.499398: step: 2088/531, loss: 0.00553080765530467
2023-01-24 09:15:37.563750: step: 2092/531, loss: 0.004521744791418314
2023-01-24 09:15:38.622793: step: 2096/531, loss: 0.0038140560500323772
2023-01-24 09:15:39.680974: step: 2100/531, loss: 0.00023906734713818878
2023-01-24 09:15:40.745815: step: 2104/531, loss: 0.006527534686028957
2023-01-24 09:15:41.813009: step: 2108/531, loss: 2.842466074071126e-06
2023-01-24 09:15:42.875673: step: 2112/531, loss: 6.46032058284618e-05
2023-01-24 09:15:43.932738: step: 2116/531, loss: 0.0012776412768289447
2023-01-24 09:15:44.991304: step: 2120/531, loss: 7.714742969255894e-05
2023-01-24 09:15:46.071296: step: 2124/531, loss: 0.0001456171303289011
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3912124244497087, 'r': 0.3206902606494766, 'f1': 0.3524583260944195}, 'combined': 0.2597061350169407, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.38678179122727724, 'r': 0.2755253517308828, 'f1': 0.3218089679510785}, 'combined': 0.20150655002544168, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.378528968405544, 'r': 0.3418971327533946, 'f1': 0.3592817327239062}, 'combined': 0.26473390832287824, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3891138375735475, 'r': 0.2884144044052805, 'f1': 0.331280760730664}, 'combined': 0.20530075312886217, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.36053703814705257, 'r': 0.32496222603387087, 'f1': 0.3418265331733532}, 'combined': 0.25187218233826025, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.4109275312501119, 'r': 0.28716757143267513, 'f1': 0.3380773213575761}, 'combined': 0.22426911416789705, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 19}
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, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.40013567688276547, 'r': 0.32420860347047603, 'f1': 0.3581927338132932}, 'combined': 0.26393148807295286, 'stategy': 1, 'epoch': 6}
Test for Chinese: {'template': {'p': 0.8375, 'r': 0.5, 'f1': 0.6261682242990655}, 'slot': {'p': 0.3876853321450179, 'r': 0.2737219252205131, 'f1': 0.32088542819191224}, 'combined': 0.20092825877437498, 'stategy': 1, 'epoch': 6}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.45108695652173914, 'r': 0.29642857142857143, 'f1': 0.35775862068965514}, 'combined': 0.23850574712643674, 'stategy': 1, 'epoch': 6}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3801261370486054, 'r': 0.3418971327533946, 'f1': 0.3599995783437342}, 'combined': 0.26526284720064625, 'stategy': 1, 'epoch': 18}
Test for Korean: {'template': {'p': 0.8354430379746836, 'r': 0.4925373134328358, 'f1': 0.6197183098591549}, 'slot': {'p': 0.3931559590286749, 'r': 0.289992402601854, 'f1': 0.33378471664292275}, 'combined': 0.20685250045476902, 'stategy': 1, 'epoch': 18}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.4270833333333333, 'r': 0.44565217391304346, 'f1': 0.43617021276595747}, 'combined': 0.21808510638297873, 'stategy': 1, 'epoch': 18}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3727720535604476, 'r': 0.3317459072482921, 'f1': 0.3510644440157629}, 'combined': 0.2586790640116148, 'stategy': 1, 'epoch': 8}
Test for Russian: {'template': {'p': 0.9852941176470589, 'r': 0.5, 'f1': 0.6633663366336634}, 'slot': {'p': 0.41586235172622604, 'r': 0.28649128649128647, 'f1': 0.33926197193682506}, 'combined': 0.22505497148284437, 'stategy': 1, 'epoch': 8}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5454545454545454, 'r': 0.20689655172413793, 'f1': 0.3}, 'combined': 0.19999999999999998, 'stategy': 1, 'epoch': 8}